aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorGeoff Rehmet <csgr@FreeBSD.org>1994-08-24 13:10:34 +0000
committerGeoff Rehmet <csgr@FreeBSD.org>1994-08-24 13:10:34 +0000
commit8387c24d794dc69c6d3d27b2326e6019518bdfc4 (patch)
treec1ef3d28221496e6e87f29d5b1970f4b29776afa
downloadsrc-8387c24d794dc69c6d3d27b2326e6019518bdfc4.tar.gz
src-8387c24d794dc69c6d3d27b2326e6019518bdfc4.zip
Flex version 2.4.7 from LBLvendor/flex/2.4.7
Reviewed by: Geoff.
Notes
Notes: svn path=/vendor/flex/dist/; revision=2258 svn path=/vendor/flex/2.4.7/; revision=2260; tag=vendor/flex/2.4.7
-rw-r--r--usr.bin/lex/COPYING38
-rw-r--r--usr.bin/lex/FlexLexer.h175
-rw-r--r--usr.bin/lex/Makefile57
-rw-r--r--usr.bin/lex/NEWS703
-rw-r--r--usr.bin/lex/README67
-rw-r--r--usr.bin/lex/ccl.c149
-rw-r--r--usr.bin/lex/dfa.c1085
-rw-r--r--usr.bin/lex/ecs.c225
-rw-r--r--usr.bin/lex/flex.skl1225
-rw-r--r--usr.bin/lex/flexdef.h902
-rw-r--r--usr.bin/lex/flexdoc.13045
-rw-r--r--usr.bin/lex/gen.c1461
-rw-r--r--usr.bin/lex/initscan.c2723
-rw-r--r--usr.bin/lex/lex.11001
-rw-r--r--usr.bin/lex/lib/Makefile20
-rw-r--r--usr.bin/lex/lib/libmain.c12
-rw-r--r--usr.bin/lex/lib/libyywrap.c8
-rw-r--r--usr.bin/lex/main.c989
-rw-r--r--usr.bin/lex/misc.c773
-rwxr-xr-xusr.bin/lex/mkskel.sh16
-rw-r--r--usr.bin/lex/nfa.c709
-rw-r--r--usr.bin/lex/parse.y817
-rw-r--r--usr.bin/lex/scan.l572
-rw-r--r--usr.bin/lex/skel.c1232
-rw-r--r--usr.bin/lex/sym.c262
-rw-r--r--usr.bin/lex/tblcmp.c888
-rw-r--r--usr.bin/lex/version.h1
-rw-r--r--usr.bin/lex/yylex.c199
28 files changed, 19354 insertions, 0 deletions
diff --git a/usr.bin/lex/COPYING b/usr.bin/lex/COPYING
new file mode 100644
index 000000000000..dcb775e7c606
--- /dev/null
+++ b/usr.bin/lex/COPYING
@@ -0,0 +1,38 @@
+Flex carries the copyright used for BSD software, slightly modified
+because it originated at the Lawrence Berkeley (not Livermore!) Laboratory,
+which operates under a contract with the Department of Energy:
+
+ Copyright (c) 1990 The Regents of the University of California.
+ All rights reserved.
+
+ This code is derived from software contributed to Berkeley by
+ Vern Paxson.
+
+ The United States Government has rights in this work pursuant
+ to contract no. DE-AC03-76SF00098 between the United States
+ Department of Energy and the University of California.
+
+ Redistribution and use in source and binary forms are permitted
+ provided that: (1) source distributions retain this entire
+ copyright notice and comment, and (2) distributions including
+ binaries display the following acknowledgement: ``This product
+ includes software developed by the University of California,
+ Berkeley and its contributors'' in the documentation or other
+ materials provided with the distribution and in all advertising
+ materials mentioning features or use of this software. Neither the
+ name of the University nor the names of its contributors may be
+ used to endorse or promote products derived from this software
+ without specific prior written permission.
+
+ THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR
+ IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED
+ WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ PURPOSE.
+
+This basically says "do whatever you please with this software except
+remove this notice or take advantage of the University's (or the flex
+authors') name".
+
+Note that the "flex.skl" scanner skeleton carries no copyright notice.
+You are free to do whatever you please with scanners generated using flex;
+for them, you are not even bound by the above copyright.
diff --git a/usr.bin/lex/FlexLexer.h b/usr.bin/lex/FlexLexer.h
new file mode 100644
index 000000000000..feb40b66265d
--- /dev/null
+++ b/usr.bin/lex/FlexLexer.h
@@ -0,0 +1,175 @@
+// $Header: FlexLexer.h,v 1.2 94/01/04 14:57:26 vern Exp $
+
+// FlexLexer.h -- define classes for lexical analyzers generated by flex
+
+// Copyright (c) 1993 The Regents of the University of California.
+// All rights reserved.
+//
+// This code is derived from software contributed to Berkeley by
+// Kent Williams and Tom Epperly.
+//
+// Redistribution and use in source and binary forms are permitted provided
+// that: (1) source distributions retain this entire copyright notice and
+// comment, and (2) distributions including binaries display the following
+// acknowledgement: ``This product includes software developed by the
+// University of California, Berkeley and its contributors'' in the
+// documentation or other materials provided with the distribution and in
+// all advertising materials mentioning features or use of this software.
+// Neither the name of the University nor the names of its contributors may
+// be used to endorse or promote products derived from this software without
+// specific prior written permission.
+// THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+// WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+
+#ifndef __FLEX_LEXER_H
+#define __FLEX_LEXER_H
+
+
+// This file defines two classes. The first, FlexLexer, is an abstract
+// class which specifies the external interface provided to flex C++
+// lexer objects. The second, yyFlexLexer, fills out most of the meat
+// of the lexer class; its internals may vary from lexer to lexer
+// depending on things like whether REJECT is used.
+//
+// If you want to create multiple lexer classes, you use the -P flag
+// to rename each yyFlexLexer to some other xxFlexLexer.
+
+#include <iostream.h>
+
+extern "C++" {
+
+struct yy_buffer_state;
+typedef int yy_state_type;
+
+class FlexLexer {
+public:
+ virtual ~FlexLexer() { }
+
+ const char* YYText() { return yytext; }
+ int YYLeng() { return yyleng; }
+
+ virtual void
+ yy_switch_to_buffer( struct yy_buffer_state* new_buffer ) = 0;
+ virtual struct yy_buffer_state*
+ yy_create_buffer( istream* s, int size ) = 0;
+ virtual void yy_delete_buffer( struct yy_buffer_state* b ) = 0;
+ virtual void yyrestart( istream* s ) = 0;
+
+ virtual int yylex() = 0;
+
+protected:
+ char* yytext;
+ int yyleng;
+};
+
+
+class yyFlexLexer : public FlexLexer {
+public:
+ // arg_yyin and arg_yyout default to the cin and cout, but we
+ // only make that assignment when initializing in yylex().
+ yyFlexLexer( istream* arg_yyin = 0, ostream* arg_yyout = 0 )
+ {
+ yyin = arg_yyin;
+ yyout = arg_yyout;
+ yy_c_buf_p = 0;
+ yy_init = 1;
+ yy_start = 0;
+
+ yy_did_buffer_switch_on_eof = 0;
+
+ yy_looking_for_trail_begin = 0;
+ yy_more_flag = 0;
+ yy_more_len = 0;
+
+ yy_start_stack_ptr = yy_start_stack_depth = 0;
+ yy_start_stack = 0;
+
+ yy_current_buffer = 0;
+
+#ifdef YY_USES_REJECT
+ yy_state_buf = new yy_state_type[YY_BUF_SIZE + 2];
+#else
+ yy_state_buf = 0;
+#endif
+ }
+
+ virtual ~yyFlexLexer()
+ {
+ delete yy_state_buf;
+ }
+
+ void yy_switch_to_buffer( struct yy_buffer_state* new_buffer );
+ struct yy_buffer_state* yy_create_buffer( istream* s, int size );
+ void yy_delete_buffer( struct yy_buffer_state* b );
+ void yyrestart( istream* s );
+
+ virtual int yylex();
+
+protected:
+ virtual int LexerInput( char* buf, int max_size );
+ virtual void LexerOutput( const char* buf, int size );
+ virtual void LexerError( const char* msg );
+
+ void yyunput( int c, char* buf_ptr );
+ int yyinput();
+
+ void yy_load_buffer_state();
+ void yy_init_buffer( struct yy_buffer_state* b, istream* s );
+
+ int yy_start_stack_ptr;
+ int yy_start_stack_depth;
+ int* yy_start_stack;
+
+ void yy_push_state( int new_state );
+ void yy_pop_state();
+ int yy_top_state();
+
+ yy_state_type yy_get_previous_state();
+ yy_state_type yy_try_NUL_trans( yy_state_type current_state );
+ int yy_get_next_buffer();
+
+ istream* yyin; // input source for default LexerInput
+ ostream* yyout; // output sink for default LexerOutput
+
+ struct yy_buffer_state* yy_current_buffer;
+
+ // yy_hold_char holds the character lost when yytext is formed.
+ char yy_hold_char;
+
+ // Number of characters read into yy_ch_buf.
+ int yy_n_chars;
+
+ // Points to current character in buffer.
+ char* yy_c_buf_p;
+
+ int yy_init; // whether we need to initialize
+ int yy_start; // start state number
+
+ // Flag which is used to allow yywrap()'s to do buffer switches
+ // instead of setting up a fresh yyin. A bit of a hack ...
+ int yy_did_buffer_switch_on_eof;
+
+ // The following are not always needed, but may be depending
+ // on use of certain flex features (like REJECT or yymore()).
+
+ yy_state_type yy_last_accepting_state;
+ char* yy_last_accepting_cpos;
+
+ yy_state_type* yy_state_buf;
+ yy_state_type* yy_state_ptr;
+
+ char* yy_full_match;
+ int* yy_full_state;
+ int yy_full_lp;
+
+ int yy_lp;
+ int yy_looking_for_trail_begin;
+
+ int yy_more_flag;
+ int yy_more_len;
+};
+
+}
+
+#endif
diff --git a/usr.bin/lex/Makefile b/usr.bin/lex/Makefile
new file mode 100644
index 000000000000..7f88e6eea4de
--- /dev/null
+++ b/usr.bin/lex/Makefile
@@ -0,0 +1,57 @@
+# $Id$
+#
+# By default, flex will be configured to generate 8-bit scanners only if the
+# -8 flag is given. If you want it to always generate 8-bit scanners, add
+# "-DDEFAULT_CSIZE=256" to CFLAGS. Note that doing so will double the size
+# of all uncompressed scanners.
+#
+# Bootstrapping of lex is handled automatically.
+# ALso note that flex.skel no longer gets installed.
+#
+# XXX Todo:
+# Install as lex++, and install FlexLexer.h
+
+PROG= lex
+LINKS= ${BINDIR}/lex ${BINDIR}/flex
+#LINKS+= ${BINDIR}/lex ${BINDIR}/lex++ ${BINDIR}/flex ${BINDIR}/flex++
+
+SRCS= ccl.c dfa.c ecs.c gen.c main.c misc.c nfa.c parse.y \
+ skel.c sym.c tblcmp.c yylex.c
+OBJS+= scan.o
+LFLAGS+= -is
+CFLAGS+= -I. -I${.CURDIR}
+MAN1= flex.1 flexdoc.1
+MLINKS= flex.1 lex.1 flexdoc.1 lexdoc.1
+
+CLEANFILES+= parse.c parse.h scan.c y.tab.h
+
+
+SUBDIR= lib
+
+.depend: parse.h
+
+parse.c parse.h: parse.y
+ $(YACC) -d $(.CURDIR)/parse.y
+ mv y.tab.c parse.c
+ mv y.tab.h parse.h
+
+.if exists(/usr/bin/lex)
+scan.o: parse.c
+.else
+# We must bootstrap
+scan.o: scan.c parse.h
+
+scan.c:
+ @echo "Bootstrapping flex"
+ @rm -f scan.c
+ @cp -pf ${.CURDIR}/initscan.c scan.c
+.endif
+
+test: check
+check: $(PROG)
+ ./$(PROG) $(LFLAGS) -t $(COMPRESSION) $(.CURDIR)/scan.l \
+ | sed s,\"$(.CURDIR)/scan.l",\"scan.l", \
+ | diff $(.CURDIR)/initscan.c -
+ @echo "Check successful"
+
+.include <bsd.prog.mk>
diff --git a/usr.bin/lex/NEWS b/usr.bin/lex/NEWS
new file mode 100644
index 000000000000..aff90a392a55
--- /dev/null
+++ b/usr.bin/lex/NEWS
@@ -0,0 +1,703 @@
+Changes between release 2.4.7 (03Aug94) and release 2.4.6:
+
+ - Fixed serious bug in reading multiple files.
+
+ - Fixed bug in scanning NUL's.
+
+ - Fixed bug in input() returning 8-bit characters.
+
+ - Fixed bug in matching text with embedded NUL's when
+ using %array or lex compatibility.
+
+ - Fixed multiple invocations of YY_USER_ACTION when using '|'
+ continuation action.
+
+ - Minor prototyping fixes.
+
+Changes between release 2.4.6 (04Jan94) and release 2.4.5:
+
+ - Linking with -lfl no longer required if your program includes
+ its own yywrap() and main() functions. (This change will cause
+ problems if you have a non-ANSI compiler on a system for which
+ sizeof(int) != sizeof(void*) or sizeof(int) != sizeof(size_t).)
+
+ - The use of 'extern "C++"' in FlexLexer.h has been modified to
+ get around an incompatibility with g++'s header files.
+
+
+Changes between release 2.4.5 (11Dec93) and release 2.4.4:
+
+ - Fixed bug breaking C++ scanners that use REJECT or variable
+ trailing context.
+
+ - Fixed serious input problem for interactive scanners on
+ systems for which char is unsigned.
+
+ - Fixed bug in incorrectly treating '$' operator as variable
+ trailing context.
+
+ - Fixed bug in -CF table representation that could lead to
+ corrupt tables.
+
+ - Fixed fairly benign memory leak.
+
+ - Added `extern "C++"' wrapper to FlexLexer.h header. This
+ should overcome the g++ 2.5.X problems mentioned in the
+ NEWS for release 2.4.3.
+
+ - Changed #include of FlexLexer.h to use <> instead of "".
+
+ - Added feature to control whether the scanner attempts to
+ refill the input buffer once it's exhausted. This feature
+ will be documented in the 2.5 release.
+
+
+Changes between release 2.4.4 (07Dec93) and release 2.4.3:
+
+ - Fixed two serious bugs in scanning 8-bit characters.
+
+ - Fixed bug in YY_USER_ACTION that caused it to be executed
+ inappropriately (on the scanner's own internal actions, and
+ with incorrect yytext/yyleng values).
+
+ - Fixed bug in pointing yyin at a new file and resuming scanning.
+
+ - Portability fix regarding min/max/abs macros conflicting with
+ function definitions in standard header files.
+
+ - Added a virtual LexerError() method to the C++ yyFlexLexer class
+ for reporting error messages instead of always using cerr.
+
+ - Added warning in flexdoc that the C++ scanning class is presently
+ experimental and subject to considerable change between major
+ releases.
+
+
+Changes between release 2.4.3 (03Dec93) and release 2.4.2:
+
+ - Fixed bug causing fatal scanner messages to fail to print.
+
+ - Fixed things so FlexLexer.h can be included in other C++
+ sources. One side-effect of this change is that -+ and -CF
+ are now incompatible.
+
+ - libfl.a now supplies private versions of the the <string.h>/
+ <strings.h> string routines needed by flex and the scanners
+ it generates, to enhance portability to some BSD systems.
+
+ - More robust solution to 2.4.2's flexfatal() bug fix.
+
+ - Added ranlib of installed libfl.a.
+
+ - Some lint tweaks.
+
+ - NOTE: problems have been encountered attempting to build flex
+ C++ scanners using g++ version 2.5.X. The problem is due to an
+ unfortunate heuristic in g++ 2.5.X that attempts to discern between
+ C and C++ headers. Because FlexLexer.h is installed (by default)
+ in /usr/local/include and not /usr/local/lib/g++-include, g++ 2.5.X
+ decides that it's a C header :-(. So if you have problems, install
+ the header in /usr/local/lib/g++-include instead.
+
+
+Changes between release 2.4.2 (01Dec93) and release 2.4.1:
+
+ - Fixed bug in libfl.a referring to non-existent "flexfatal" function.
+
+ - Modified to produce both compress'd and gzip'd tar files for
+ distributions (you probably don't care about this change!).
+
+
+Changes between release 2.4.1 (30Nov93) and release 2.3.8:
+
+ - The new '-+' flag instructs flex to generate a C++ scanner class
+ (thanks to Kent Williams). flex writes an implementation of the
+ class defined in FlexLexer.h to lex.yy.cc. You may include
+ multiple scanner classes in your program using the -P flag. Note
+ that the scanner class also provides a mechanism for creating
+ reentrant scanners. The scanner class uses C++ streams for I/O
+ instead of FILE*'s (thanks to Tom Epperly). If the flex executable's
+ name ends in '+' then the '-+' flag is automatically on, so creating
+ a symlink or copy of "flex" to "flex++" results in a version of
+ flex that can be used exclusively for C++ scanners.
+
+ Note that without the '-+' flag, flex-generated scanners can still
+ be compiled using C++ compilers, though they use FILE*'s for I/O
+ instead of streams.
+
+ See the "GENERATING C++ SCANNERS" section of flexdoc for details.
+
+ - The new '-l' flag turns on maximum AT&T lex compatibility. In
+ particular, -l includes support for "yylineno" and makes yytext
+ be an array instead of a pointer. It does not, however, do away
+ with all incompatibilities. See the "INCOMPATIBILITIES WITH LEX
+ AND POSIX" section of flexdoc for details.
+
+ - The new '-P' option specifies a prefix to use other than "yy"
+ for the scanner's globally-visible variables, and for the
+ "lex.yy.c" filename. Using -P you can link together multiple
+ flex scanners in the same executable.
+
+ - The distribution includes a "texinfo" version of flexdoc.1,
+ contributed by Roland Pesch (thanks also to Marq Kole, who
+ contributed another version). It has not been brought up to
+ date, but reflects version 2.3. See MISC/flex.texinfo.
+
+ The flex distribution will soon include G.T. Nicol's flex
+ manual; he is presently bringing it up-to-date for version 2.4.
+
+ - yywrap() is now a function, and you now *must* link flex scanners
+ with libfl.a.
+
+ - Site-configuration is now done via an autoconf-generated
+ "configure" script contributed by Francois Pinard.
+
+ - Scanners now use fread() (or getc(), if interactive) and not
+ read() for input. A new "table compression" option, -Cr,
+ overrides this change and causes the scanner to use read()
+ (because read() is a bit faster than fread()). -f and -F
+ are now equivalent to -Cfr and -CFr; i.e., they imply the
+ -Cr option.
+
+ - In the blessed name of POSIX compliance, flex supports "%array"
+ and "%pointer" directives in the definitions (first) section of
+ the scanner specification. The former specifies that yytext
+ should be an array (of size YYLMAX), the latter, that it should
+ be a pointer. The array version of yytext is universally slower
+ than the pointer version, but has the advantage that its contents
+ remain unmodified across calls to input() and unput() (the pointer
+ version of yytext is, still, trashed by such calls).
+
+ "%array" cannot be used with the '-+' C++ scanner class option.
+
+ - The new '-Ca' option directs flex to trade off memory for
+ natural alignment when generating a scanner's tables. In
+ particular, table entries that would otherwise be "short"
+ become "long".
+
+ - The new '-h' option produces a summary of the flex flags.
+
+ - The new '-V' option reports the flex version number and exits.
+
+ - The new scanner macro YY_START returns an integer value
+ corresponding to the current start condition. You can return
+ to that start condition by passing the value to a subsequent
+ "BEGIN" action. You also can implement "start condition stacks"
+ by storing the values in an integer stack.
+
+ - You can now redefine macros such as YY_INPUT by just #define'ing
+ them to some other value in the first section of the flex input;
+ no need to first #undef them.
+
+ - flex now generates warnings for rules that can't be matched.
+ These warnings can be turned off using the new '-w' flag. If
+ your scanner uses REJECT then you will not get these warnings.
+
+ - If you specify the '-s' flag but the default rule can be matched,
+ flex now generates a warning.
+
+ - "yyleng" is now a global, and may be modified by the user (though
+ doing so and then using yymore() will yield weird results).
+
+ - Name definitions in the first section of a scanner specification
+ can now include a leading '^' or trailing '$' operator. In this
+ case, the definition is *not* pushed back inside of parentheses.
+
+ - Scanners with compressed tables are now "interactive" (-I option)
+ by default. You can suppress this attribute (which makes them
+ run slightly slower) using the new '-B' flag.
+
+ - Flex now generates 8-bit scanners by default, unless you use the
+ -Cf or -CF compression options (-Cfe and -CFe result in 8-bit
+ scanners). You can force it to generate a 7-bit scanner using
+ the new '-7' flag. You can build flex to generate 8-bit scanners
+ for -Cf and -CF, too, by adding -DDEFAULT_CSIZE=256 to CFLAGS
+ in the Makefile.
+
+ - You no longer need to call the scanner routine yyrestart() to
+ inform the scanner that you have switched to a new file after
+ having seen an EOF on the current input file. Instead, just
+ point yyin at the new file and continue scanning.
+
+ - You no longer need to invoke YY_NEW_FILE in an <<EOF>> action
+ to indicate you wish to continue scanning. Simply point yyin
+ at a new file.
+
+ - A leading '#' no longer introduces a comment in a flex input.
+
+ - flex no longer considers formfeed ('\f') a whitespace character.
+
+ - %t, I'm happy to report, has been nuked.
+
+ - The '-p' option may be given twice ('-pp') to instruct flex to
+ report minor performance problems as well as major ones.
+
+ - The '-v' verbose output no longer includes start/finish time
+ information.
+
+ - Newlines in flex inputs can optionally include leading or
+ trailing carriage-returns ('\r'), in support of several PC/Mac
+ run-time libraries that automatically include these.
+
+ - A start condition of the form "<*>" makes the following rule
+ active in every start condition, whether exclusive or inclusive.
+
+ - The following items have been corrected in the flex documentation:
+
+ - '-C' table compression options *are* cumulative.
+
+ - You may modify yytext but not lengthen it by appending
+ characters to the end. Modifying its final character
+ will affect '^' anchoring for the next rule matched
+ if the character is changed to or from a newline.
+
+ - The term "backtracking" has been renamed "backing up",
+ since it is a one-time repositioning and not a repeated
+ search. What used to be the "lex.backtrack" file is now
+ "lex.backup".
+
+ - Unindented "/* ... */" comments are allowed in the first
+ flex input section, but not in the second.
+
+ - yyless() can only be used in the flex input source, not
+ externally.
+
+ - You can use "yyrestart(yyin)" to throw away the
+ current contents of the input buffer.
+
+ - To write high-speed scanners, attempt to match as much
+ text as possible with each rule. See MISC/fastwc/README
+ for more information.
+
+ - Using the beginning-of-line operator ('^') is fairly
+ cheap. Using unput() is expensive. Using yyless() is
+ cheap.
+
+ - An example of scanning strings with embedded escape
+ sequences has been added.
+
+ - The example of backing-up in flexdoc was erroneous; it
+ has been corrected.
+
+ - A flex scanner's internal buffer now dynamically grows if needed
+ to match large tokens. Note that growing the buffer presently
+ requires rescanning the (large) token, so consuming a lot of
+ text this way is a slow process. Also note that presently the
+ buffer does *not* grow if you unput() more text than can fit
+ into the buffer.
+
+ - The MISC/ directory has been reorganized; see MISC/README for
+ details.
+
+ - yyless() can now be used in the third (user action) section
+ of a scanner specification, thanks to Ceriel Jacobs. yyless()
+ remains a macro and cannot be used outside of the scanner source.
+
+ - The skeleton file is no longer opened at run-time, but instead
+ compiled into a large string array (thanks to John Gilmore and
+ friends at Cygnus). You can still use the -S flag to point flex
+ at a different skeleton file, though if you use this option let
+ me know, as I plan to otherwise do away with -S in the near
+ future.
+
+ - flex no longer uses a temporary file to store the scanner's
+ actions.
+
+ - A number of changes have been made to decrease porting headaches.
+ In particular, flex no longer uses memset() or ctime(), and
+ provides a single simple mechanism for dealing with C compilers
+ that still define malloc() as returning char* instead of void*.
+
+ - Flex now detects if the scanner specification requires the -8 flag
+ but the flag was not given or on by default.
+
+ - A number of table-expansion fencepost bugs have been fixed,
+ making flex more robust for generating large scanners.
+
+ - flex more consistently identifies the location of errors in
+ its input.
+
+ - YY_USER_ACTION is now invoked only for "real" actions, not for
+ internal actions used by the scanner for things like filling
+ the buffer or handling EOF.
+
+ - The rule "[^]]" now matches any character other than a ']';
+ formerly it matched any character at all followed by a ']'.
+ This change was made for compatibility with AT&T lex.
+
+ - A large number of miscellaneous bugs have been found and fixed
+ thanks to Gerhard Wilhelms.
+
+ - The source code has been heavily reformatted, making patches
+ relative to previous flex releases no longer accurate.
+
+
+Changes between 2.3 Patch #8 (21Feb93) and 2.3 Patch #7:
+
+ - Fixed bugs in dynamic memory allocation leading to grievous
+ fencepost problems when generating large scanners.
+ - Fixed bug causing infinite loops on character classes with 8-bit
+ characters in them.
+ - Fixed bug in matching repetitions with a lower bound of 0.
+ - Fixed bug in scanning NUL characters using an "interactive" scanner.
+ - Fixed bug in using yymore() at the end of a file.
+ - Fixed bug in misrecognizing rules with variable trailing context.
+ - Fixed bug compiling flex on Suns using gcc 2.
+ - Fixed bug in not recognizing that input files with the character
+ ASCII 128 in them require the -8 flag.
+ - Fixed bug that could cause an infinite loop writing out
+ error messages.
+ - Fixed bug in not recognizing old-style lex % declarations if
+ followed by a tab instead of a space.
+ - Fixed potential crash when flex terminated early (usually due
+ to a bad flag) and the -v flag had been given.
+ - Added some missing declarations of void functions.
+ - Changed to only use '\a' for __STDC__ compilers.
+ - Updated mailing addresses.
+
+
+Changes between 2.3 Patch #7 (28Mar91) and 2.3 Patch #6:
+
+ - Fixed out-of-bounds array access that caused bad tables
+ to be produced on machines where the bad reference happened
+ to yield a 1. This caused problems installing or running
+ flex on some Suns, in particular.
+
+
+Changes between 2.3 Patch #6 (29Aug90) and 2.3 Patch #5:
+
+ - Fixed a serious bug in yymore() which basically made it
+ completely broken. Thanks goes to Jean Christophe of
+ the Nethack development team for finding the problem
+ and passing along the fix.
+
+
+Changes between 2.3 Patch #5 (16Aug90) and 2.3 Patch #4:
+
+ - An up-to-date version of initscan.c so "make test" will
+ work after applying the previous patches
+
+
+Changes between 2.3 Patch #4 (14Aug90) and 2.3 Patch #3:
+
+ - Fixed bug in hexadecimal escapes which allowed only digits,
+ not letters, in escapes
+ - Fixed bug in previous "Changes" file!
+
+
+Changes between 2.3 Patch #3 (03Aug90) and 2.3 Patch #2:
+
+ - Correction to patch #2 for gcc compilation; thanks goes to
+ Paul Eggert for catching this.
+
+
+Changes between 2.3 Patch #2 (02Aug90) and original 2.3 release:
+
+ - Fixed (hopefully) headaches involving declaring malloc()
+ and free() for gcc, which defines __STDC__ but (often) doesn't
+ come with the standard include files such as <stdlib.h>.
+ Reordered #ifdef maze in the scanner skeleton in the hope of
+ getting the declarations right for cfront and g++, too.
+
+ - Note that this patch supercedes patch #1 for release 2.3,
+ which was never announced but was available briefly for
+ anonymous ftp.
+
+
+Changes between 2.3 (full) release of 28Jun90 and 2.2 (alpha) release:
+
+ User-visible:
+
+ - A lone <<EOF>> rule (that is, one which is not qualified with
+ a list of start conditions) now specifies the EOF action for
+ *all* start conditions which haven't already had <<EOF>> actions
+ given. To specify an end-of-file action for just the initial
+ state, use <INITIAL><<EOF>>.
+
+ - -d debug output is now contigent on the global yy_flex_debug
+ being set to a non-zero value, which it is by default.
+
+ - A new macro, YY_USER_INIT, is provided for the user to specify
+ initialization action to be taken on the first call to the
+ scanner. This action is done before the scanner does its
+ own initialization.
+
+ - yy_new_buffer() has been added as an alias for yy_create_buffer()
+
+ - Comments beginning with '#' and extending to the end of the line
+ now work, but have been deprecated (in anticipation of making
+ flex recognize #line directives).
+
+ - The funky restrictions on when semi-colons could follow the
+ YY_NEW_FILE and yyless macros have been removed. They now
+ behave identically to functions.
+
+ - A bug in the sample redefinition of YY_INPUT in the documentation
+ has been corrected.
+
+ - A bug in the sample simple tokener in the documentation has
+ been corrected.
+
+ - The documentation on the incompatibilities between flex and
+ lex has been reordered so that the discussion of yylineno
+ and input() come first, as it's anticipated that these will
+ be the most common source of headaches.
+
+
+ Things which didn't used to be documented but now are:
+
+ - flex interprets "^foo|bar" differently from lex. flex interprets
+ it as "match either a 'foo' or a 'bar', providing it comes at the
+ beginning of a line", whereas lex interprets it as "match either
+ a 'foo' at the beginning of a line, or a 'bar' anywhere".
+
+ - flex initializes the global "yyin" on the first call to the
+ scanner, while lex initializes it at compile-time.
+
+ - yy_switch_to_buffer() can be used in the yywrap() macro/routine.
+
+ - flex scanners do not use stdio for their input, and hence when
+ writing an interactive scanner one must explictly call fflush()
+ after writing out a prompt.
+
+ - flex scanner can be made reentrant (after a fashion) by using
+ "yyrestart( yyin );". This is useful for interactive scanners
+ which have interrupt handlers that long-jump out of the scanner.
+
+ - a defense of why yylineno is not supported is included, along
+ with a suggestion on how to convert scanners which rely on it.
+
+
+ Other changes:
+
+ - Prototypes and proper declarations of void routines have
+ been added to the flex source code, courtesy of Kevin B. Kenny.
+
+ - Routines dealing with memory allocation now use void* pointers
+ instead of char* - see Makefile for porting implications.
+
+ - Error-checking is now done when flex closes a file.
+
+ - Various lint tweaks were added to reduce the number of gripes.
+
+ - Makefile has been further parameterized to aid in porting.
+
+ - Support for SCO Unix added.
+
+ - Flex now sports the latest & greatest UC copyright notice
+ (which is only slightly different from the previous one).
+
+ - A note has been added to flexdoc.1 mentioning work in progress
+ on modifying flex to generate straight C code rather than a
+ table-driven automaton, with an email address of whom to contact
+ if you are working along similar lines.
+
+
+Changes between 2.2 Patch #3 (30Mar90) and 2.2 Patch #2:
+
+ - fixed bug which caused -I scanners to bomb
+
+
+Changes between 2.2 Patch #2 (27Mar90) and 2.2 Patch #1:
+
+ - fixed bug writing past end of input buffer in yyunput()
+ - fixed bug detecting NUL's at the end of a buffer
+
+
+Changes between 2.2 Patch #1 (23Mar90) and 2.2 (alpha) release:
+
+ - Makefile fixes: definition of MAKE variable for systems
+ which don't have it; installation of flexdoc.1 along with
+ flex.1; fixed two bugs which could cause "bigtest" to fail.
+
+ - flex.skel fix for compiling with g++.
+
+ - README and flexdoc.1 no longer list an out-of-date BITNET address
+ for contacting me.
+
+ - minor typos and formatting changes to flex.1 and flexdoc.1.
+
+
+Changes between 2.2 (alpha) release of March '90 and previous release:
+
+ User-visible:
+
+ - Full user documentation now available.
+
+ - Support for 8-bit scanners.
+
+ - Scanners now accept NUL's.
+
+ - A facility has been added for dealing with multiple
+ input buffers.
+
+ - Two manual entries now. One which fully describes flex
+ (rather than just its differences from lex), and the
+ other for quick(er) reference.
+
+ - A number of changes to bring flex closer into compliance
+ with the latest POSIX lex draft:
+
+ %t support
+ flex now accepts multiple input files and concatenates
+ them together to form its input
+ previous -c (compress) flag renamed -C
+ do-nothing -c and -n flags added
+ Any indented code or code within %{}'s in section 2 is
+ now copied to the output
+
+ - yyleng is now a bona fide global integer.
+
+ - -d debug information now gives the line number of the
+ matched rule instead of which number rule it was from
+ the beginning of the file.
+
+ - -v output now includes a summary of the flags used to generate
+ the scanner.
+
+ - unput() and yyrestart() are now globally callable.
+
+ - yyrestart() no longer closes the previous value of yyin.
+
+ - C++ support; generated scanners can be compiled with C++ compiler.
+
+ - Primitive -lfl library added, containing default main()
+ which calls yylex(). A number of routines currently living
+ in the scanner skeleton will probably migrate to here
+ in the future (in particular, yywrap() will probably cease
+ to be a macro and instead be a function in the -lfl library).
+
+ - Hexadecimal (\x) escape sequences added.
+
+ - Support for MS-DOS, VMS, and Turbo-C integrated.
+
+ - The %used/%unused operators have been deprecated. They
+ may go away soon.
+
+
+ Other changes:
+
+ - Makefile enhanced for easier testing and installation.
+ - The parser has been tweaked to detect some erroneous
+ constructions which previously were missed.
+ - Scanner input buffer overflow is now detected.
+ - Bugs with missing "const" declarations fixed.
+ - Out-of-date Minix/Atari patches provided.
+ - Scanners no longer require printf() unless FLEX_DEBUG is being used.
+ - A subtle input() bug has been fixed.
+ - Line numbers for "continued action" rules (those following
+ the special '|' action) are now correct.
+ - unput() bug fixed; had been causing problems porting flex to VMS.
+ - yymore() handling rewritten to fix bug with interaction
+ between yymore() and trailing context.
+ - EOF in actions now generates an error message.
+ - Bug involving -CFe and generating equivalence classes fixed.
+ - Bug which made -CF be treated as -Cf fixed.
+ - Support for SysV tmpnam() added.
+ - Unused #define's for scanner no longer generated.
+ - Error messages which are associated with a particular input
+ line are now all identified with their input line in standard
+ format.
+ - % directives which are valid to lex but not to flex are
+ now ignored instead of generating warnings.
+ - -DSYS_V flag can now also be specified -DUSG for System V
+ compilation.
+
+
+Changes between 2.1 beta-test release of June '89 and previous release:
+
+ User-visible:
+
+ - -p flag generates a performance report to stderr. The report
+ consists of comments regarding features of the scanner rules
+ which result in slower scanners.
+
+ - -b flag generates backtracking information to lex.backtrack.
+ This is a list of scanner states which require backtracking
+ and the characters on which they do so. By adding rules
+ one can remove backtracking states. If all backtracking states
+ are eliminated, the generated scanner will run faster.
+ Backtracking is not yet documented in the manual entry.
+
+ - Variable trailing context now works, i.e., one can have
+ rules like "(foo)*/[ \t]*bletch". Some trailing context
+ patterns still cannot be properly matched and generate
+ error messages. These are patterns where the ending of the
+ first part of the rule matches the beginning of the second
+ part, such as "zx*/xy*", where the 'x*' matches the 'x' at
+ the beginning of the trailing context. Lex won't get these
+ patterns right either.
+
+ - Faster scanners.
+
+ - End-of-file rules. The special rule "<<EOF>>" indicates
+ actions which are to be taken when an end-of-file is
+ encountered and yywrap() returns non-zero (i.e., indicates
+ no further files to process). See manual entry for example.
+
+ - The -r (reject used) flag is gone. flex now scans the input
+ for occurrences of the string "REJECT" to determine if the
+ action is needed. It tries to be intelligent about this but
+ can be fooled. One can force the presence or absence of
+ REJECT by adding a line in the first section of the form
+ "%used REJECT" or "%unused REJECT".
+
+ - yymore() has been implemented. Similarly to REJECT, flex
+ detects the use of yymore(), which can be overridden using
+ "%used" or "%unused".
+
+ - Patterns like "x{0,3}" now work (i.e., with lower-limit == 0).
+
+ - Removed '\^x' for ctrl-x misfeature.
+
+ - Added '\a' and '\v' escape sequences.
+
+ - \<digits> now works for octal escape sequences; previously
+ \0<digits> was required.
+
+ - Better error reporting; line numbers are associated with rules.
+
+ - yyleng is a macro; it cannot be accessed outside of the
+ scanner source file.
+
+ - yytext and yyleng should not be modified within a flex action.
+
+ - Generated scanners #define the name FLEX_SCANNER.
+
+ - Rules are internally separated by YY_BREAK in lex.yy.c rather
+ than break, to allow redefinition.
+
+ - The macro YY_USER_ACTION can be redefined to provide an action
+ which is always executed prior to the matched rule's action.
+
+ - yyrestart() is a new action which can be used to restart
+ the scanner after it has seen an end-of-file (a "real" one,
+ that is, one for which yywrap() returned non-zero). It takes
+ a FILE* argument indicating a new file to scan and sets
+ things up so that a subsequent call to yylex() will start
+ scanning that file.
+
+ - Internal scanner names all preceded by "yy_"
+
+ - lex.yy.c is deleted if errors are encountered during processing.
+
+ - Comments may be put in the first section of the input by preceding
+ them with '#'.
+
+
+
+ Other changes:
+
+ - Some portability-related bugs fixed, in particular for machines
+ with unsigned characters or sizeof( int* ) != sizeof( int ).
+ Also, tweaks for VMS and Microsoft C (MS-DOS), and identifiers all
+ trimmed to be 31 or fewer characters. Shortened file names
+ for dinosaur OS's. Checks for allocating > 64K memory
+ on 16 bit'ers. Amiga tweaks. Compiles using gcc on a Sun-3.
+ - Compressed and fast scanner skeletons merged.
+ - Skeleton header files done away with.
+ - Generated scanner uses prototypes and "const" for __STDC__.
+ - -DSV flag is now -DSYS_V for System V compilation.
+ - Removed all references to FTL language.
+ - Software now covered by BSD Copyright.
+ - flex will replace lex in subsequent BSD releases.
diff --git a/usr.bin/lex/README b/usr.bin/lex/README
new file mode 100644
index 000000000000..339e9bbbd51e
--- /dev/null
+++ b/usr.bin/lex/README
@@ -0,0 +1,67 @@
+This is release 2.4 of flex. See "version.h" for the exact patch-level.
+
+See the file "NEWS" to find out what is new in this Flex release.
+
+Read the file "INSTALL" for general installation directives. Peek near
+the beginning of the file "Makefile.in" for special DEFS values. On most
+systems, you can just run the "configure" script and type "make" to build
+flex; then "make check" to test whether it built correctly; and if it did,
+then "make install" to install it.
+
+If you're feeling adventurous, you can also issue "make bigcheck" (be
+prepared to wait a while).
+
+Note that flex is distributed under a copyright very similar to that of
+BSD Unix, and not under the GNU General Public License (GPL), except for
+the "configure" script, which is covered by the GPL.
+
+Many thanks to the 2.4 pre-testers for finding a bunch of bugs and helping
+increase/test portability: Francois Pinard, Nathan Zelle, Gavin Nicol,
+Chris Thewalt, and Matthew Jacob.
+
+Please send bug reports and feedback to:
+
+ Vern Paxson
+ ICSD, 46A/1123
+ Lawrence Berkeley Laboratory
+ 1 Cyclotron Rd.
+ Berkeley, CA 94720
+
+ vern@ee.lbl.gov
+
+
+The flex distribution consists of the following files:
+
+ README This message
+
+ NEWS Differences between the various releases
+
+ INSTALL General installation information
+
+ COPYING flex's copyright
+
+ configure.in, configure, Makefile.in, install.sh, mkinstalldirs
+ elements of the "autoconf" auto-configuration process
+
+ flexdef.h, parse.y, scan.l, ccl.c, dfa.c, ecs.c, gen.c, main.c,
+ misc.c, nfa.c, sym.c, tblcmp.c, yylex.c
+ source files
+
+ version.h version of this flex release
+
+ flex.skl flex scanner skeleton
+ mkskel.sh script for converting flex.skl to C source file skel.c
+
+ liballoc.c
+ libmain.c flex library (-lfl) sources
+ libyywrap.c
+
+ initscan.c pre-flex'd version of scan.l
+
+ FlexLexer.h header file for C++ lexer class
+
+ flexdoc.1 full user documentation
+ flex.1 reference documentation
+
+ MISC/ a directory containing miscellaneous contributions.
+ See MISC/README for details.
diff --git a/usr.bin/lex/ccl.c b/usr.bin/lex/ccl.c
new file mode 100644
index 000000000000..fe28463923e0
--- /dev/null
+++ b/usr.bin/lex/ccl.c
@@ -0,0 +1,149 @@
+/* ccl - routines for character classes */
+
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: /home/daffy/u0/vern/flex/RCS/ccl.c,v 2.9 93/09/16 20:32:14 vern Exp $ */
+
+#include "flexdef.h"
+
+/* ccladd - add a single character to a ccl */
+
+void ccladd( cclp, ch )
+int cclp;
+int ch;
+ {
+ int ind, len, newpos, i;
+
+ check_char( ch );
+
+ len = ccllen[cclp];
+ ind = cclmap[cclp];
+
+ /* check to see if the character is already in the ccl */
+
+ for ( i = 0; i < len; ++i )
+ if ( ccltbl[ind + i] == ch )
+ return;
+
+ newpos = ind + len;
+
+ if ( newpos >= current_max_ccl_tbl_size )
+ {
+ current_max_ccl_tbl_size += MAX_CCL_TBL_SIZE_INCREMENT;
+
+ ++num_reallocs;
+
+ ccltbl = reallocate_Character_array( ccltbl,
+ current_max_ccl_tbl_size );
+ }
+
+ ccllen[cclp] = len + 1;
+ ccltbl[newpos] = ch;
+ }
+
+
+/* cclinit - return an empty ccl */
+
+int cclinit()
+ {
+ if ( ++lastccl >= current_maxccls )
+ {
+ current_maxccls += MAX_CCLS_INCREMENT;
+
+ ++num_reallocs;
+
+ cclmap = reallocate_integer_array( cclmap, current_maxccls );
+ ccllen = reallocate_integer_array( ccllen, current_maxccls );
+ cclng = reallocate_integer_array( cclng, current_maxccls );
+ }
+
+ if ( lastccl == 1 )
+ /* we're making the first ccl */
+ cclmap[lastccl] = 0;
+
+ else
+ /* The new pointer is just past the end of the last ccl.
+ * Since the cclmap points to the \first/ character of a
+ * ccl, adding the length of the ccl to the cclmap pointer
+ * will produce a cursor to the first free space.
+ */
+ cclmap[lastccl] = cclmap[lastccl - 1] + ccllen[lastccl - 1];
+
+ ccllen[lastccl] = 0;
+ cclng[lastccl] = 0; /* ccl's start out life un-negated */
+
+ return lastccl;
+ }
+
+
+/* cclnegate - negate the given ccl */
+
+void cclnegate( cclp )
+int cclp;
+ {
+ cclng[cclp] = 1;
+ }
+
+
+/* list_character_set - list the members of a set of characters in CCL form
+ *
+ * Writes to the given file a character-class representation of those
+ * characters present in the given CCL. A character is present if it
+ * has a non-zero value in the cset array.
+ */
+
+void list_character_set( file, cset )
+FILE *file;
+int cset[];
+ {
+ register int i;
+
+ putc( '[', file );
+
+ for ( i = 0; i < csize; ++i )
+ {
+ if ( cset[i] )
+ {
+ register int start_char = i;
+
+ putc( ' ', file );
+
+ fputs( readable_form( i ), file );
+
+ while ( ++i < csize && cset[i] )
+ ;
+
+ if ( i - 1 > start_char )
+ /* this was a run */
+ fprintf( file, "-%s", readable_form( i - 1 ) );
+
+ putc( ' ', file );
+ }
+ }
+
+ putc( ']', file );
+ }
diff --git a/usr.bin/lex/dfa.c b/usr.bin/lex/dfa.c
new file mode 100644
index 000000000000..f8fceb975acd
--- /dev/null
+++ b/usr.bin/lex/dfa.c
@@ -0,0 +1,1085 @@
+/* dfa - DFA construction routines */
+
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: dfa.c,v 1.2 94/01/04 14:33:16 vern Exp $ */
+
+#include "flexdef.h"
+
+
+/* declare functions that have forward references */
+
+void dump_associated_rules PROTO((FILE*, int));
+void dump_transitions PROTO((FILE*, int[]));
+void sympartition PROTO((int[], int, int[], int[]));
+int symfollowset PROTO((int[], int, int, int[]));
+
+
+/* check_for_backing_up - check a DFA state for backing up
+ *
+ * synopsis
+ * void check_for_backing_up( int ds, int state[numecs] );
+ *
+ * ds is the number of the state to check and state[] is its out-transitions,
+ * indexed by equivalence class.
+ */
+
+void check_for_backing_up( ds, state )
+int ds;
+int state[];
+ {
+ if ( (reject && ! dfaacc[ds].dfaacc_set) ||
+ (! reject && ! dfaacc[ds].dfaacc_state) )
+ { /* state is non-accepting */
+ ++num_backing_up;
+
+ if ( backing_up_report )
+ {
+ fprintf( backing_up_file,
+ "State #%d is non-accepting -\n", ds );
+
+ /* identify the state */
+ dump_associated_rules( backing_up_file, ds );
+
+ /* Now identify it further using the out- and
+ * jam-transitions.
+ */
+ dump_transitions( backing_up_file, state );
+
+ putc( '\n', backing_up_file );
+ }
+ }
+ }
+
+
+/* check_trailing_context - check to see if NFA state set constitutes
+ * "dangerous" trailing context
+ *
+ * synopsis
+ * void check_trailing_context( int nfa_states[num_states+1], int num_states,
+ * int accset[nacc+1], int nacc );
+ *
+ * NOTES
+ * Trailing context is "dangerous" if both the head and the trailing
+ * part are of variable size \and/ there's a DFA state which contains
+ * both an accepting state for the head part of the rule and NFA states
+ * which occur after the beginning of the trailing context.
+ *
+ * When such a rule is matched, it's impossible to tell if having been
+ * in the DFA state indicates the beginning of the trailing context or
+ * further-along scanning of the pattern. In these cases, a warning
+ * message is issued.
+ *
+ * nfa_states[1 .. num_states] is the list of NFA states in the DFA.
+ * accset[1 .. nacc] is the list of accepting numbers for the DFA state.
+ */
+
+void check_trailing_context( nfa_states, num_states, accset, nacc )
+int *nfa_states, num_states;
+int *accset;
+register int nacc;
+ {
+ register int i, j;
+
+ for ( i = 1; i <= num_states; ++i )
+ {
+ int ns = nfa_states[i];
+ register int type = state_type[ns];
+ register int ar = assoc_rule[ns];
+
+ if ( type == STATE_NORMAL || rule_type[ar] != RULE_VARIABLE )
+ { /* do nothing */
+ }
+
+ else if ( type == STATE_TRAILING_CONTEXT )
+ {
+ /* Potential trouble. Scan set of accepting numbers
+ * for the one marking the end of the "head". We
+ * assume that this looping will be fairly cheap
+ * since it's rare that an accepting number set
+ * is large.
+ */
+ for ( j = 1; j <= nacc; ++j )
+ if ( accset[j] & YY_TRAILING_HEAD_MASK )
+ {
+ line_warning(
+ "dangerous trailing context",
+ rule_linenum[ar] );
+ return;
+ }
+ }
+ }
+ }
+
+
+/* dump_associated_rules - list the rules associated with a DFA state
+ *
+ * Goes through the set of NFA states associated with the DFA and
+ * extracts the first MAX_ASSOC_RULES unique rules, sorts them,
+ * and writes a report to the given file.
+ */
+
+void dump_associated_rules( file, ds )
+FILE *file;
+int ds;
+ {
+ register int i, j;
+ register int num_associated_rules = 0;
+ int rule_set[MAX_ASSOC_RULES + 1];
+ int *dset = dss[ds];
+ int size = dfasiz[ds];
+
+ for ( i = 1; i <= size; ++i )
+ {
+ register int rule_num = rule_linenum[assoc_rule[dset[i]]];
+
+ for ( j = 1; j <= num_associated_rules; ++j )
+ if ( rule_num == rule_set[j] )
+ break;
+
+ if ( j > num_associated_rules )
+ { /* new rule */
+ if ( num_associated_rules < MAX_ASSOC_RULES )
+ rule_set[++num_associated_rules] = rule_num;
+ }
+ }
+
+ bubble( rule_set, num_associated_rules );
+
+ fprintf( file, " associated rule line numbers:" );
+
+ for ( i = 1; i <= num_associated_rules; ++i )
+ {
+ if ( i % 8 == 1 )
+ putc( '\n', file );
+
+ fprintf( file, "\t%d", rule_set[i] );
+ }
+
+ putc( '\n', file );
+ }
+
+
+/* dump_transitions - list the transitions associated with a DFA state
+ *
+ * synopsis
+ * dump_transitions( FILE *file, int state[numecs] );
+ *
+ * Goes through the set of out-transitions and lists them in human-readable
+ * form (i.e., not as equivalence classes); also lists jam transitions
+ * (i.e., all those which are not out-transitions, plus EOF). The dump
+ * is done to the given file.
+ */
+
+void dump_transitions( file, state )
+FILE *file;
+int state[];
+ {
+ register int i, ec;
+ int out_char_set[CSIZE];
+
+ for ( i = 0; i < csize; ++i )
+ {
+ ec = ABS( ecgroup[i] );
+ out_char_set[i] = state[ec];
+ }
+
+ fprintf( file, " out-transitions: " );
+
+ list_character_set( file, out_char_set );
+
+ /* now invert the members of the set to get the jam transitions */
+ for ( i = 0; i < csize; ++i )
+ out_char_set[i] = ! out_char_set[i];
+
+ fprintf( file, "\n jam-transitions: EOF " );
+
+ list_character_set( file, out_char_set );
+
+ putc( '\n', file );
+ }
+
+
+/* epsclosure - construct the epsilon closure of a set of ndfa states
+ *
+ * synopsis
+ * int *epsclosure( int t[num_states], int *numstates_addr,
+ * int accset[num_rules+1], int *nacc_addr,
+ * int *hashval_addr );
+ *
+ * NOTES
+ * The epsilon closure is the set of all states reachable by an arbitrary
+ * number of epsilon transitions, which themselves do not have epsilon
+ * transitions going out, unioned with the set of states which have non-null
+ * accepting numbers. t is an array of size numstates of nfa state numbers.
+ * Upon return, t holds the epsilon closure and *numstates_addr is updated.
+ * accset holds a list of the accepting numbers, and the size of accset is
+ * given by *nacc_addr. t may be subjected to reallocation if it is not
+ * large enough to hold the epsilon closure.
+ *
+ * hashval is the hash value for the dfa corresponding to the state set.
+ */
+
+int *epsclosure( t, ns_addr, accset, nacc_addr, hv_addr )
+int *t, *ns_addr, accset[], *nacc_addr, *hv_addr;
+ {
+ register int stkpos, ns, tsp;
+ int numstates = *ns_addr, nacc, hashval, transsym, nfaccnum;
+ int stkend, nstate;
+ static int did_stk_init = false, *stk;
+
+#define MARK_STATE(state) \
+trans1[state] = trans1[state] - MARKER_DIFFERENCE;
+
+#define IS_MARKED(state) (trans1[state] < 0)
+
+#define UNMARK_STATE(state) \
+trans1[state] = trans1[state] + MARKER_DIFFERENCE;
+
+#define CHECK_ACCEPT(state) \
+{ \
+nfaccnum = accptnum[state]; \
+if ( nfaccnum != NIL ) \
+accset[++nacc] = nfaccnum; \
+}
+
+#define DO_REALLOCATION \
+{ \
+current_max_dfa_size += MAX_DFA_SIZE_INCREMENT; \
+++num_reallocs; \
+t = reallocate_integer_array( t, current_max_dfa_size ); \
+stk = reallocate_integer_array( stk, current_max_dfa_size ); \
+} \
+
+#define PUT_ON_STACK(state) \
+{ \
+if ( ++stkend >= current_max_dfa_size ) \
+DO_REALLOCATION \
+stk[stkend] = state; \
+MARK_STATE(state) \
+}
+
+#define ADD_STATE(state) \
+{ \
+if ( ++numstates >= current_max_dfa_size ) \
+DO_REALLOCATION \
+t[numstates] = state; \
+hashval += state; \
+}
+
+#define STACK_STATE(state) \
+{ \
+PUT_ON_STACK(state) \
+CHECK_ACCEPT(state) \
+if ( nfaccnum != NIL || transchar[state] != SYM_EPSILON ) \
+ADD_STATE(state) \
+}
+
+
+ if ( ! did_stk_init )
+ {
+ stk = allocate_integer_array( current_max_dfa_size );
+ did_stk_init = true;
+ }
+
+ nacc = stkend = hashval = 0;
+
+ for ( nstate = 1; nstate <= numstates; ++nstate )
+ {
+ ns = t[nstate];
+
+ /* The state could be marked if we've already pushed it onto
+ * the stack.
+ */
+ if ( ! IS_MARKED(ns) )
+ {
+ PUT_ON_STACK(ns)
+ CHECK_ACCEPT(ns)
+ hashval += ns;
+ }
+ }
+
+ for ( stkpos = 1; stkpos <= stkend; ++stkpos )
+ {
+ ns = stk[stkpos];
+ transsym = transchar[ns];
+
+ if ( transsym == SYM_EPSILON )
+ {
+ tsp = trans1[ns] + MARKER_DIFFERENCE;
+
+ if ( tsp != NO_TRANSITION )
+ {
+ if ( ! IS_MARKED(tsp) )
+ STACK_STATE(tsp)
+
+ tsp = trans2[ns];
+
+ if ( tsp != NO_TRANSITION && ! IS_MARKED(tsp) )
+ STACK_STATE(tsp)
+ }
+ }
+ }
+
+ /* Clear out "visit" markers. */
+
+ for ( stkpos = 1; stkpos <= stkend; ++stkpos )
+ {
+ if ( IS_MARKED(stk[stkpos]) )
+ UNMARK_STATE(stk[stkpos])
+ else
+ flexfatal( "consistency check failed in epsclosure()" );
+ }
+
+ *ns_addr = numstates;
+ *hv_addr = hashval;
+ *nacc_addr = nacc;
+
+ return t;
+ }
+
+
+/* increase_max_dfas - increase the maximum number of DFAs */
+
+void increase_max_dfas()
+ {
+ current_max_dfas += MAX_DFAS_INCREMENT;
+
+ ++num_reallocs;
+
+ base = reallocate_integer_array( base, current_max_dfas );
+ def = reallocate_integer_array( def, current_max_dfas );
+ dfasiz = reallocate_integer_array( dfasiz, current_max_dfas );
+ accsiz = reallocate_integer_array( accsiz, current_max_dfas );
+ dhash = reallocate_integer_array( dhash, current_max_dfas );
+ dss = reallocate_int_ptr_array( dss, current_max_dfas );
+ dfaacc = reallocate_dfaacc_union( dfaacc, current_max_dfas );
+
+ if ( nultrans )
+ nultrans =
+ reallocate_integer_array( nultrans, current_max_dfas );
+ }
+
+
+/* ntod - convert an ndfa to a dfa
+ *
+ * Creates the dfa corresponding to the ndfa we've constructed. The
+ * dfa starts out in state #1.
+ */
+
+void ntod()
+ {
+ int *accset, ds, nacc, newds;
+ int sym, hashval, numstates, dsize;
+ int num_full_table_rows; /* used only for -f */
+ int *nset, *dset;
+ int targptr, totaltrans, i, comstate, comfreq, targ;
+ int *epsclosure(), snstods(), symlist[CSIZE + 1];
+ int num_start_states;
+ int todo_head, todo_next;
+
+ /* Note that the following are indexed by *equivalence classes*
+ * and not by characters. Since equivalence classes are indexed
+ * beginning with 1, even if the scanner accepts NUL's, this
+ * means that (since every character is potentially in its own
+ * equivalence class) these arrays must have room for indices
+ * from 1 to CSIZE, so their size must be CSIZE + 1.
+ */
+ int duplist[CSIZE + 1], state[CSIZE + 1];
+ int targfreq[CSIZE + 1], targstate[CSIZE + 1];
+
+ accset = allocate_integer_array( num_rules + 1 );
+ nset = allocate_integer_array( current_max_dfa_size );
+
+ /* The "todo" queue is represented by the head, which is the DFA
+ * state currently being processed, and the "next", which is the
+ * next DFA state number available (not in use). We depend on the
+ * fact that snstods() returns DFA's \in increasing order/, and thus
+ * need only know the bounds of the dfas to be processed.
+ */
+ todo_head = todo_next = 0;
+
+ for ( i = 0; i <= csize; ++i )
+ {
+ duplist[i] = NIL;
+ symlist[i] = false;
+ }
+
+ for ( i = 0; i <= num_rules; ++i )
+ accset[i] = NIL;
+
+ if ( trace )
+ {
+ dumpnfa( scset[1] );
+ fputs( "\n\nDFA Dump:\n\n", stderr );
+ }
+
+ inittbl();
+
+ /* Check to see whether we should build a separate table for
+ * transitions on NUL characters. We don't do this for full-speed
+ * (-F) scanners, since for them we don't have a simple state
+ * number lying around with which to index the table. We also
+ * don't bother doing it for scanners unless (1) NUL is in its own
+ * equivalence class (indicated by a positive value of
+ * ecgroup[NUL]), (2) NUL's equivalence class is the last
+ * equivalence class, and (3) the number of equivalence classes is
+ * the same as the number of characters. This latter case comes
+ * about when useecs is false or when it's true but every character
+ * still manages to land in its own class (unlikely, but it's
+ * cheap to check for). If all these things are true then the
+ * character code needed to represent NUL's equivalence class for
+ * indexing the tables is going to take one more bit than the
+ * number of characters, and therefore we won't be assured of
+ * being able to fit it into a YY_CHAR variable. This rules out
+ * storing the transitions in a compressed table, since the code
+ * for interpreting them uses a YY_CHAR variable (perhaps it
+ * should just use an integer, though; this is worth pondering ...
+ * ###).
+ *
+ * Finally, for full tables, we want the number of entries in the
+ * table to be a power of two so the array references go fast (it
+ * will just take a shift to compute the major index). If
+ * encoding NUL's transitions in the table will spoil this, we
+ * give it its own table (note that this will be the case if we're
+ * not using equivalence classes).
+ */
+
+ /* Note that the test for ecgroup[0] == numecs below accomplishes
+ * both (1) and (2) above
+ */
+ if ( ! fullspd && ecgroup[0] == numecs )
+ {
+ /* NUL is alone in its equivalence class, which is the
+ * last one.
+ */
+ int use_NUL_table = (numecs == csize);
+
+ if ( fulltbl && ! use_NUL_table )
+ {
+ /* We still may want to use the table if numecs
+ * is a power of 2.
+ */
+ int power_of_two;
+
+ for ( power_of_two = 1; power_of_two <= csize;
+ power_of_two *= 2 )
+ if ( numecs == power_of_two )
+ {
+ use_NUL_table = true;
+ break;
+ }
+ }
+
+ if ( use_NUL_table )
+ nultrans = allocate_integer_array( current_max_dfas );
+
+ /* From now on, nultrans != nil indicates that we're
+ * saving null transitions for later, separate encoding.
+ */
+ }
+
+
+ if ( fullspd )
+ {
+ for ( i = 0; i <= numecs; ++i )
+ state[i] = 0;
+
+ place_state( state, 0, 0 );
+ dfaacc[i].dfaacc_state = 0;
+ }
+
+ else if ( fulltbl )
+ {
+ if ( nultrans )
+ /* We won't be including NUL's transitions in the
+ * table, so build it for entries from 0 .. numecs - 1.
+ */
+ num_full_table_rows = numecs;
+
+ else
+ /* Take into account the fact that we'll be including
+ * the NUL entries in the transition table. Build it
+ * from 0 .. numecs.
+ */
+ num_full_table_rows = numecs + 1;
+
+ /* Unless -Ca, declare it "short" because it's a real
+ * long-shot that that won't be large enough.
+ */
+ printf( "static const %s yy_nxt[][%d] =\n {\n",
+ /* '}' so vi doesn't get too confused */
+ long_align ? "long" : "short", num_full_table_rows );
+
+ /* Generate 0 entries for state #0. */
+ for ( i = 0; i < num_full_table_rows; ++i )
+ mk2data( 0 );
+
+ /* Force ',' and dataflush() next call to mk2data().*/
+ datapos = NUMDATAITEMS;
+
+ /* Force extra blank line next dataflush(). */
+ dataline = NUMDATALINES;
+ }
+
+ /* Create the first states. */
+
+ num_start_states = lastsc * 2;
+
+ for ( i = 1; i <= num_start_states; ++i )
+ {
+ numstates = 1;
+
+ /* For each start condition, make one state for the case when
+ * we're at the beginning of the line (the '^' operator) and
+ * one for the case when we're not.
+ */
+ if ( i % 2 == 1 )
+ nset[numstates] = scset[(i / 2) + 1];
+ else
+ nset[numstates] =
+ mkbranch( scbol[i / 2], scset[i / 2] );
+
+ nset = epsclosure( nset, &numstates, accset, &nacc, &hashval );
+
+ if ( snstods( nset, numstates, accset, nacc, hashval, &ds ) )
+ {
+ numas += nacc;
+ totnst += numstates;
+ ++todo_next;
+
+ if ( variable_trailing_context_rules && nacc > 0 )
+ check_trailing_context( nset, numstates,
+ accset, nacc );
+ }
+ }
+
+ if ( ! fullspd )
+ {
+ if ( ! snstods( nset, 0, accset, 0, 0, &end_of_buffer_state ) )
+ flexfatal(
+ "could not create unique end-of-buffer state" );
+
+ ++numas;
+ ++num_start_states;
+ ++todo_next;
+ }
+
+ while ( todo_head < todo_next )
+ {
+ targptr = 0;
+ totaltrans = 0;
+
+ for ( i = 1; i <= numecs; ++i )
+ state[i] = 0;
+
+ ds = ++todo_head;
+
+ dset = dss[ds];
+ dsize = dfasiz[ds];
+
+ if ( trace )
+ fprintf( stderr, "state # %d:\n", ds );
+
+ sympartition( dset, dsize, symlist, duplist );
+
+ for ( sym = 1; sym <= numecs; ++sym )
+ {
+ if ( symlist[sym] )
+ {
+ symlist[sym] = 0;
+
+ if ( duplist[sym] == NIL )
+ {
+ /* Symbol has unique out-transitions. */
+ numstates = symfollowset( dset, dsize,
+ sym, nset );
+ nset = epsclosure( nset, &numstates,
+ accset, &nacc, &hashval );
+
+ if ( snstods( nset, numstates, accset,
+ nacc, hashval, &newds ) )
+ {
+ totnst = totnst + numstates;
+ ++todo_next;
+ numas += nacc;
+
+ if (
+ variable_trailing_context_rules &&
+ nacc > 0 )
+ check_trailing_context(
+ nset, numstates,
+ accset, nacc );
+ }
+
+ state[sym] = newds;
+
+ if ( trace )
+ fprintf( stderr, "\t%d\t%d\n",
+ sym, newds );
+
+ targfreq[++targptr] = 1;
+ targstate[targptr] = newds;
+ ++numuniq;
+ }
+
+ else
+ {
+ /* sym's equivalence class has the same
+ * transitions as duplist(sym)'s
+ * equivalence class.
+ */
+ targ = state[duplist[sym]];
+ state[sym] = targ;
+
+ if ( trace )
+ fprintf( stderr, "\t%d\t%d\n",
+ sym, targ );
+
+ /* Update frequency count for
+ * destination state.
+ */
+
+ i = 0;
+ while ( targstate[++i] != targ )
+ ;
+
+ ++targfreq[i];
+ ++numdup;
+ }
+
+ ++totaltrans;
+ duplist[sym] = NIL;
+ }
+ }
+
+ numsnpairs = numsnpairs + totaltrans;
+
+ if ( caseins && ! useecs )
+ {
+ register int j;
+
+ for ( i = 'A', j = 'a'; i <= 'Z'; ++i, ++j )
+ state[i] = state[j];
+ }
+
+ if ( ds > num_start_states )
+ check_for_backing_up( ds, state );
+
+ if ( nultrans )
+ {
+ nultrans[ds] = state[NUL_ec];
+ state[NUL_ec] = 0; /* remove transition */
+ }
+
+ if ( fulltbl )
+ {
+ /* Supply array's 0-element. */
+ if ( ds == end_of_buffer_state )
+ mk2data( -end_of_buffer_state );
+ else
+ mk2data( end_of_buffer_state );
+
+ for ( i = 1; i < num_full_table_rows; ++i )
+ /* Jams are marked by negative of state
+ * number.
+ */
+ mk2data( state[i] ? state[i] : -ds );
+
+ /* Force ',' and dataflush() next call to mk2data().*/
+ datapos = NUMDATAITEMS;
+
+ /* Force extra blank line next dataflush(). */
+ dataline = NUMDATALINES;
+ }
+
+ else if ( fullspd )
+ place_state( state, ds, totaltrans );
+
+ else if ( ds == end_of_buffer_state )
+ /* Special case this state to make sure it does what
+ * it's supposed to, i.e., jam on end-of-buffer.
+ */
+ stack1( ds, 0, 0, JAMSTATE );
+
+ else /* normal, compressed state */
+ {
+ /* Determine which destination state is the most
+ * common, and how many transitions to it there are.
+ */
+
+ comfreq = 0;
+ comstate = 0;
+
+ for ( i = 1; i <= targptr; ++i )
+ if ( targfreq[i] > comfreq )
+ {
+ comfreq = targfreq[i];
+ comstate = targstate[i];
+ }
+
+ bldtbl( state, ds, totaltrans, comstate, comfreq );
+ }
+ }
+
+ if ( fulltbl )
+ dataend();
+
+ else if ( ! fullspd )
+ {
+ cmptmps(); /* create compressed template entries */
+
+ /* Create tables for all the states with only one
+ * out-transition.
+ */
+ while ( onesp > 0 )
+ {
+ mk1tbl( onestate[onesp], onesym[onesp], onenext[onesp],
+ onedef[onesp] );
+ --onesp;
+ }
+
+ mkdeftbl();
+ }
+
+ flex_free( (void *) accset );
+ flex_free( (void *) nset );
+ }
+
+
+/* snstods - converts a set of ndfa states into a dfa state
+ *
+ * synopsis
+ * is_new_state = snstods( int sns[numstates], int numstates,
+ * int accset[num_rules+1], int nacc,
+ * int hashval, int *newds_addr );
+ *
+ * On return, the dfa state number is in newds.
+ */
+
+int snstods( sns, numstates, accset, nacc, hashval, newds_addr )
+int sns[], numstates, accset[], nacc, hashval, *newds_addr;
+ {
+ int didsort = 0;
+ register int i, j;
+ int newds, *oldsns;
+
+ for ( i = 1; i <= lastdfa; ++i )
+ if ( hashval == dhash[i] )
+ {
+ if ( numstates == dfasiz[i] )
+ {
+ oldsns = dss[i];
+
+ if ( ! didsort )
+ {
+ /* We sort the states in sns so we
+ * can compare it to oldsns quickly.
+ * We use bubble because there probably
+ * aren't very many states.
+ */
+ bubble( sns, numstates );
+ didsort = 1;
+ }
+
+ for ( j = 1; j <= numstates; ++j )
+ if ( sns[j] != oldsns[j] )
+ break;
+
+ if ( j > numstates )
+ {
+ ++dfaeql;
+ *newds_addr = i;
+ return 0;
+ }
+
+ ++hshcol;
+ }
+
+ else
+ ++hshsave;
+ }
+
+ /* Make a new dfa. */
+
+ if ( ++lastdfa >= current_max_dfas )
+ increase_max_dfas();
+
+ newds = lastdfa;
+
+ dss[newds] = allocate_integer_array( numstates + 1 );
+
+ /* If we haven't already sorted the states in sns, we do so now,
+ * so that future comparisons with it can be made quickly.
+ */
+
+ if ( ! didsort )
+ bubble( sns, numstates );
+
+ for ( i = 1; i <= numstates; ++i )
+ dss[newds][i] = sns[i];
+
+ dfasiz[newds] = numstates;
+ dhash[newds] = hashval;
+
+ if ( nacc == 0 )
+ {
+ if ( reject )
+ dfaacc[newds].dfaacc_set = (int *) 0;
+ else
+ dfaacc[newds].dfaacc_state = 0;
+
+ accsiz[newds] = 0;
+ }
+
+ else if ( reject )
+ {
+ /* We sort the accepting set in increasing order so the
+ * disambiguating rule that the first rule listed is considered
+ * match in the event of ties will work. We use a bubble
+ * sort since the list is probably quite small.
+ */
+
+ bubble( accset, nacc );
+
+ dfaacc[newds].dfaacc_set = allocate_integer_array( nacc + 1 );
+
+ /* Save the accepting set for later */
+ for ( i = 1; i <= nacc; ++i )
+ {
+ dfaacc[newds].dfaacc_set[i] = accset[i];
+
+ if ( accset[i] <= num_rules )
+ /* Who knows, perhaps a REJECT can yield
+ * this rule.
+ */
+ rule_useful[accset[i]] = true;
+ }
+
+ accsiz[newds] = nacc;
+ }
+
+ else
+ {
+ /* Find lowest numbered rule so the disambiguating rule
+ * will work.
+ */
+ j = num_rules + 1;
+
+ for ( i = 1; i <= nacc; ++i )
+ if ( accset[i] < j )
+ j = accset[i];
+
+ dfaacc[newds].dfaacc_state = j;
+
+ if ( j <= num_rules )
+ rule_useful[j] = true;
+ }
+
+ *newds_addr = newds;
+
+ return 1;
+ }
+
+
+/* symfollowset - follow the symbol transitions one step
+ *
+ * synopsis
+ * numstates = symfollowset( int ds[current_max_dfa_size], int dsize,
+ * int transsym, int nset[current_max_dfa_size] );
+ */
+
+int symfollowset( ds, dsize, transsym, nset )
+int ds[], dsize, transsym, nset[];
+ {
+ int ns, tsp, sym, i, j, lenccl, ch, numstates, ccllist;
+
+ numstates = 0;
+
+ for ( i = 1; i <= dsize; ++i )
+ { /* for each nfa state ns in the state set of ds */
+ ns = ds[i];
+ sym = transchar[ns];
+ tsp = trans1[ns];
+
+ if ( sym < 0 )
+ { /* it's a character class */
+ sym = -sym;
+ ccllist = cclmap[sym];
+ lenccl = ccllen[sym];
+
+ if ( cclng[sym] )
+ {
+ for ( j = 0; j < lenccl; ++j )
+ {
+ /* Loop through negated character
+ * class.
+ */
+ ch = ccltbl[ccllist + j];
+
+ if ( ch == 0 )
+ ch = NUL_ec;
+
+ if ( ch > transsym )
+ /* Transsym isn't in negated
+ * ccl.
+ */
+ break;
+
+ else if ( ch == transsym )
+ /* next 2 */ goto bottom;
+ }
+
+ /* Didn't find transsym in ccl. */
+ nset[++numstates] = tsp;
+ }
+
+ else
+ for ( j = 0; j < lenccl; ++j )
+ {
+ ch = ccltbl[ccllist + j];
+
+ if ( ch == 0 )
+ ch = NUL_ec;
+
+ if ( ch > transsym )
+ break;
+ else if ( ch == transsym )
+ {
+ nset[++numstates] = tsp;
+ break;
+ }
+ }
+ }
+
+ else if ( sym >= 'A' && sym <= 'Z' && caseins )
+ flexfatal( "consistency check failed in symfollowset" );
+
+ else if ( sym == SYM_EPSILON )
+ { /* do nothing */
+ }
+
+ else if ( ABS( ecgroup[sym] ) == transsym )
+ nset[++numstates] = tsp;
+
+ bottom: ;
+ }
+
+ return numstates;
+ }
+
+
+/* sympartition - partition characters with same out-transitions
+ *
+ * synopsis
+ * sympartition( int ds[current_max_dfa_size], int numstates,
+ * int symlist[numecs], int duplist[numecs] );
+ */
+
+void sympartition( ds, numstates, symlist, duplist )
+int ds[], numstates;
+int symlist[], duplist[];
+ {
+ int tch, i, j, k, ns, dupfwd[CSIZE + 1], lenccl, cclp, ich;
+
+ /* Partitioning is done by creating equivalence classes for those
+ * characters which have out-transitions from the given state. Thus
+ * we are really creating equivalence classes of equivalence classes.
+ */
+
+ for ( i = 1; i <= numecs; ++i )
+ { /* initialize equivalence class list */
+ duplist[i] = i - 1;
+ dupfwd[i] = i + 1;
+ }
+
+ duplist[1] = NIL;
+ dupfwd[numecs] = NIL;
+
+ for ( i = 1; i <= numstates; ++i )
+ {
+ ns = ds[i];
+ tch = transchar[ns];
+
+ if ( tch != SYM_EPSILON )
+ {
+ if ( tch < -lastccl || tch >= csize )
+ {
+ flexfatal(
+ "bad transition character detected in sympartition()" );
+ }
+
+ if ( tch >= 0 )
+ { /* character transition */
+ int ec = ecgroup[tch];
+
+ mkechar( ec, dupfwd, duplist );
+ symlist[ec] = 1;
+ }
+
+ else
+ { /* character class */
+ tch = -tch;
+
+ lenccl = ccllen[tch];
+ cclp = cclmap[tch];
+ mkeccl( ccltbl + cclp, lenccl, dupfwd,
+ duplist, numecs, NUL_ec );
+
+ if ( cclng[tch] )
+ {
+ j = 0;
+
+ for ( k = 0; k < lenccl; ++k )
+ {
+ ich = ccltbl[cclp + k];
+
+ if ( ich == 0 )
+ ich = NUL_ec;
+
+ for ( ++j; j < ich; ++j )
+ symlist[j] = 1;
+ }
+
+ for ( ++j; j <= numecs; ++j )
+ symlist[j] = 1;
+ }
+
+ else
+ for ( k = 0; k < lenccl; ++k )
+ {
+ ich = ccltbl[cclp + k];
+
+ if ( ich == 0 )
+ ich = NUL_ec;
+
+ symlist[ich] = 1;
+ }
+ }
+ }
+ }
+ }
diff --git a/usr.bin/lex/ecs.c b/usr.bin/lex/ecs.c
new file mode 100644
index 000000000000..10b167c5898c
--- /dev/null
+++ b/usr.bin/lex/ecs.c
@@ -0,0 +1,225 @@
+/* ecs - equivalence class routines */
+
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: /home/daffy/u0/vern/flex/RCS/ecs.c,v 2.9 93/12/07 10:18:20 vern Exp $ */
+
+#include "flexdef.h"
+
+/* ccl2ecl - convert character classes to set of equivalence classes */
+
+void ccl2ecl()
+ {
+ int i, ich, newlen, cclp, ccls, cclmec;
+
+ for ( i = 1; i <= lastccl; ++i )
+ {
+ /* We loop through each character class, and for each character
+ * in the class, add the character's equivalence class to the
+ * new "character" class we are creating. Thus when we are all
+ * done, character classes will really consist of collections
+ * of equivalence classes
+ */
+
+ newlen = 0;
+ cclp = cclmap[i];
+
+ for ( ccls = 0; ccls < ccllen[i]; ++ccls )
+ {
+ ich = ccltbl[cclp + ccls];
+ cclmec = ecgroup[ich];
+
+ if ( cclmec > 0 )
+ {
+ ccltbl[cclp + newlen] = cclmec;
+ ++newlen;
+ }
+ }
+
+ ccllen[i] = newlen;
+ }
+ }
+
+
+/* cre8ecs - associate equivalence class numbers with class members
+ *
+ * fwd is the forward linked-list of equivalence class members. bck
+ * is the backward linked-list, and num is the number of class members.
+ *
+ * Returned is the number of classes.
+ */
+
+int cre8ecs( fwd, bck, num )
+int fwd[], bck[], num;
+ {
+ int i, j, numcl;
+
+ numcl = 0;
+
+ /* Create equivalence class numbers. From now on, ABS( bck(x) )
+ * is the equivalence class number for object x. If bck(x)
+ * is positive, then x is the representative of its equivalence
+ * class.
+ */
+ for ( i = 1; i <= num; ++i )
+ if ( bck[i] == NIL )
+ {
+ bck[i] = ++numcl;
+ for ( j = fwd[i]; j != NIL; j = fwd[j] )
+ bck[j] = -numcl;
+ }
+
+ return numcl;
+ }
+
+
+/* mkeccl - update equivalence classes based on character class xtions
+ *
+ * synopsis
+ * Char ccls[];
+ * int lenccl, fwd[llsiz], bck[llsiz], llsiz, NUL_mapping;
+ * void mkeccl( Char ccls[], int lenccl, int fwd[llsiz], int bck[llsiz],
+ * int llsiz, int NUL_mapping );
+ *
+ * ccls contains the elements of the character class, lenccl is the
+ * number of elements in the ccl, fwd is the forward link-list of equivalent
+ * characters, bck is the backward link-list, and llsiz size of the link-list.
+ *
+ * NUL_mapping is the value which NUL (0) should be mapped to.
+ */
+
+void mkeccl( ccls, lenccl, fwd, bck, llsiz, NUL_mapping )
+Char ccls[];
+int lenccl, fwd[], bck[], llsiz, NUL_mapping;
+ {
+ int cclp, oldec, newec;
+ int cclm, i, j;
+ static unsigned char cclflags[CSIZE]; /* initialized to all '\0' */
+
+ /* Note that it doesn't matter whether or not the character class is
+ * negated. The same results will be obtained in either case.
+ */
+
+ cclp = 0;
+
+ while ( cclp < lenccl )
+ {
+ cclm = ccls[cclp];
+
+ if ( NUL_mapping && cclm == 0 )
+ cclm = NUL_mapping;
+
+ oldec = bck[cclm];
+ newec = cclm;
+
+ j = cclp + 1;
+
+ for ( i = fwd[cclm]; i != NIL && i <= llsiz; i = fwd[i] )
+ { /* look for the symbol in the character class */
+ for ( ; j < lenccl; ++j )
+ {
+ register int ccl_char;
+
+ if ( NUL_mapping && ccls[j] == 0 )
+ ccl_char = NUL_mapping;
+ else
+ ccl_char = ccls[j];
+
+ if ( ccl_char > i )
+ break;
+
+ if ( ccl_char == i && ! cclflags[j] )
+ {
+ /* We found an old companion of cclm
+ * in the ccl. Link it into the new
+ * equivalence class and flag it as
+ * having been processed.
+ */
+
+ bck[i] = newec;
+ fwd[newec] = i;
+ newec = i;
+ /* Set flag so we don't reprocess. */
+ cclflags[j] = 1;
+
+ /* Get next equivalence class member. */
+ /* continue 2 */
+ goto next_pt;
+ }
+ }
+
+ /* Symbol isn't in character class. Put it in the old
+ * equivalence class.
+ */
+
+ bck[i] = oldec;
+
+ if ( oldec != NIL )
+ fwd[oldec] = i;
+
+ oldec = i;
+
+ next_pt: ;
+ }
+
+ if ( bck[cclm] != NIL || oldec != bck[cclm] )
+ {
+ bck[cclm] = NIL;
+ fwd[oldec] = NIL;
+ }
+
+ fwd[newec] = NIL;
+
+ /* Find next ccl member to process. */
+
+ for ( ++cclp; cclflags[cclp] && cclp < lenccl; ++cclp )
+ {
+ /* Reset "doesn't need processing" flag. */
+ cclflags[cclp] = 0;
+ }
+ }
+ }
+
+
+/* mkechar - create equivalence class for single character */
+
+void mkechar( tch, fwd, bck )
+int tch, fwd[], bck[];
+ {
+ /* If until now the character has been a proper subset of
+ * an equivalence class, break it away to create a new ec
+ */
+
+ if ( fwd[tch] != NIL )
+ bck[fwd[tch]] = bck[tch];
+
+ if ( bck[tch] != NIL )
+ fwd[bck[tch]] = fwd[tch];
+
+ fwd[tch] = NIL;
+ bck[tch] = NIL;
+ }
diff --git a/usr.bin/lex/flex.skl b/usr.bin/lex/flex.skl
new file mode 100644
index 000000000000..01ff7a1262b4
--- /dev/null
+++ b/usr.bin/lex/flex.skl
@@ -0,0 +1,1225 @@
+/* A lexical scanner generated by flex */
+
+/* Scanner skeleton version:
+ * $Header: /home/daffy/u0/vern/flex/flex-2.4.7/RCS/flex.skl,v 1.2 94/08/03 11:13:24 vern Exp $
+ */
+
+#define FLEX_SCANNER
+
+%-
+#include <stdio.h>
+%*
+
+
+/* cfront 1.2 defines "c_plusplus" instead of "__cplusplus" */
+#ifdef c_plusplus
+#ifndef __cplusplus
+#define __cplusplus
+#endif
+#endif
+
+
+#ifdef __cplusplus
+
+#include <stdlib.h>
+%+
+class istream;
+%*
+#include <unistd.h>
+
+/* Use prototypes in function declarations. */
+#define YY_USE_PROTOS
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else /* ! __cplusplus */
+
+#ifdef __STDC__
+
+#define YY_USE_PROTOS
+#define YY_USE_CONST
+
+#endif /* __STDC__ */
+#endif /* ! __cplusplus */
+
+
+#ifdef __TURBOC__
+#define YY_USE_CONST
+#endif
+
+
+#ifndef YY_USE_CONST
+#ifndef const
+#define const
+#endif
+#endif
+
+
+#ifdef YY_USE_PROTOS
+#define YY_PROTO(proto) proto
+#else
+#define YY_PROTO(proto) ()
+#endif
+
+/* Returned upon end-of-file. */
+#define YY_NULL 0
+
+/* Promotes a possibly negative, possibly signed char to an unsigned
+ * integer for use as an array index. If the signed char is negative,
+ * we want to instead treat it as an 8-bit unsigned char, hence the
+ * double cast.
+ */
+#define YY_SC_TO_UI(c) ((unsigned int) (unsigned char) c)
+
+/* Enter a start condition. This macro really ought to take a parameter,
+ * but we do it the disgusting crufty way forced on us by the ()-less
+ * definition of BEGIN.
+ */
+#define BEGIN yy_start = 1 + 2 *
+
+/* Translate the current start state into a value that can be later handed
+ * to BEGIN to return to the state.
+ */
+#define YY_START ((yy_start - 1) / 2)
+
+/* Action number for EOF rule of a given start state. */
+#define YY_STATE_EOF(state) (YY_END_OF_BUFFER + state + 1)
+
+/* Special action meaning "start processing a new file". Now included
+ * only for backward compatibility with previous versions of flex.
+ */
+#define YY_NEW_FILE yyrestart( yyin )
+
+#define YY_END_OF_BUFFER_CHAR 0
+
+/* Size of default input buffer. */
+#define YY_BUF_SIZE 16384
+
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+
+extern int yyleng;
+%-
+extern FILE *yyin, *yyout;
+%*
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+ extern int yywrap YY_PROTO(( void ));
+#ifdef __cplusplus
+ }
+#endif
+
+#define EOB_ACT_CONTINUE_SCAN 0
+#define EOB_ACT_END_OF_FILE 1
+#define EOB_ACT_LAST_MATCH 2
+
+/* The funky do-while in the following #define is used to turn the definition
+ * int a single C statement (which needs a semi-colon terminator). This
+ * avoids problems with code like:
+ *
+ * if ( condition_holds )
+ * yyless( 5 );
+ * else
+ * do_something_else();
+ *
+ * Prior to using the do-while the compiler would get upset at the
+ * "else" because it interpreted the "if" statement as being all
+ * done when it reached the ';' after the yyless() call.
+ */
+
+/* Return all but the first 'n' matched characters back to the input stream. */
+
+#define yyless(n) \
+ do \
+ { \
+ /* Undo effects of setting up yytext. */ \
+ *yy_cp = yy_hold_char; \
+ yy_c_buf_p = yy_cp = yy_bp + n - YY_MORE_ADJ; \
+ YY_DO_BEFORE_ACTION; /* set up yytext again */ \
+ } \
+ while ( 0 )
+
+#define unput(c) yyunput( c, yytext_ptr )
+
+
+struct yy_buffer_state
+ {
+%-
+ FILE *yy_input_file;
+%+
+ istream* yy_input_file;
+%*
+
+ char *yy_ch_buf; /* input buffer */
+ char *yy_buf_pos; /* current position in input buffer */
+
+ /* Size of input buffer in bytes, not including room for EOB
+ * characters.
+ */
+ int yy_buf_size;
+
+ /* Number of characters read into yy_ch_buf, not including EOB
+ * characters.
+ */
+ int yy_n_chars;
+
+ /* Whether this is an "interactive" input source; if so, and
+ * if we're using stdio for input, then we want to use getc()
+ * instead of fread(), to make sure we stop fetching input after
+ * each newline.
+ */
+ int yy_is_interactive;
+
+ /* Whether to try to fill the input buffer when we reach the
+ * end of it.
+ */
+ int yy_fill_buffer;
+
+ int yy_buffer_status;
+#define YY_BUFFER_NEW 0
+#define YY_BUFFER_NORMAL 1
+ /* When an EOF's been seen but there's still some text to process
+ * then we mark the buffer as YY_EOF_PENDING, to indicate that we
+ * shouldn't try reading from the input source any more. We might
+ * still have a bunch of tokens to match, though, because of
+ * possible backing-up.
+ *
+ * When we actually see the EOF, we change the status to "new"
+ * (via yyrestart()), so that the user can continue scanning by
+ * just pointing yyin at a new input file.
+ */
+#define YY_BUFFER_EOF_PENDING 2
+ };
+
+%- Standard (non-C++) definition
+static YY_BUFFER_STATE yy_current_buffer = 0;
+%*
+
+/* We provide macros for accessing buffer states in case in the
+ * future we want to put the buffer states in a more general
+ * "scanner state".
+ */
+#define YY_CURRENT_BUFFER yy_current_buffer
+
+
+%- Standard (non-C++) definition
+/* yy_hold_char holds the character lost when yytext is formed. */
+static char yy_hold_char;
+
+static int yy_n_chars; /* number of characters read into yy_ch_buf */
+
+
+int yyleng;
+
+/* Points to current character in buffer. */
+static char *yy_c_buf_p = (char *) 0;
+static int yy_init = 1; /* whether we need to initialize */
+static int yy_start = 0; /* start state number */
+
+/* Flag which is used to allow yywrap()'s to do buffer switches
+ * instead of setting up a fresh yyin. A bit of a hack ...
+ */
+static int yy_did_buffer_switch_on_eof;
+
+static void yyunput YY_PROTO(( int c, char *buf_ptr ));
+void yyrestart YY_PROTO(( FILE *input_file ));
+void yy_switch_to_buffer YY_PROTO(( YY_BUFFER_STATE new_buffer ));
+void yy_load_buffer_state YY_PROTO(( void ));
+YY_BUFFER_STATE yy_create_buffer YY_PROTO(( FILE *file, int size ));
+void yy_delete_buffer YY_PROTO(( YY_BUFFER_STATE b ));
+void yy_init_buffer YY_PROTO(( YY_BUFFER_STATE b, FILE *file ));
+
+static int yy_start_stack_ptr = 0;
+static int yy_start_stack_depth = 0;
+static int *yy_start_stack = 0;
+static void yy_push_state YY_PROTO(( int new_state ));
+static void yy_pop_state YY_PROTO(( void ));
+static int yy_top_state YY_PROTO(( void ));
+%*
+
+static void *yy_flex_alloc YY_PROTO(( unsigned int ));
+static void *yy_flex_realloc YY_PROTO(( void *, unsigned int ));
+static void yy_flex_free YY_PROTO(( void * ));
+
+#define yy_new_buffer yy_create_buffer
+
+%% yytext/yyin/yyout/yy_state_type/yylineno etc. def's & init go here
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy YY_PROTO(( char *, const char *, int ));
+#endif
+
+%- Standard (non-C++) definition
+#ifdef __cplusplus
+static int yyinput YY_PROTO(( void ));
+#else
+static int input YY_PROTO(( void ));
+#endif
+%*
+
+%- Standard (non-C++) definition
+static yy_state_type yy_get_previous_state YY_PROTO(( void ));
+static yy_state_type yy_try_NUL_trans YY_PROTO(( yy_state_type current_state ));
+static int yy_get_next_buffer YY_PROTO(( void ));
+static void yy_fatal_error YY_PROTO(( const char msg[] ));
+%*
+
+/* Done after the current pattern has been matched and before the
+ * corresponding action - sets up yytext.
+ */
+#define YY_DO_BEFORE_ACTION \
+ yytext_ptr = yy_bp; \
+%% code to fiddle yytext and yyleng for yymore() goes here
+ yy_hold_char = *yy_cp; \
+ *yy_cp = '\0'; \
+%% code to copy yytext_ptr to yytext[] goes here, if %array
+ yy_c_buf_p = yy_cp;
+
+%% data tables for the DFA and the user's section 1 definitions go here
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifdef YY_MALLOC_DECL
+YY_MALLOC_DECL
+#else
+#if __STDC__
+#ifndef __cplusplus
+#include <stdlib.h>
+#endif
+#else
+/* Just try to get by without declaring the routines. This will fail
+ * miserably on non-ANSI systems for which sizeof(size_t) != sizeof(int)
+ * or sizeof(void*) != sizeof(int).
+ */
+#endif
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#define YY_READ_BUF_SIZE 8192
+#endif
+
+/* Copy whatever the last rule matched to the standard output. */
+
+#ifndef ECHO
+%- Standard (non-C++) definition
+/* This used to be an fputs(), but since the string might contain NUL's,
+ * we now use fwrite().
+ */
+#define ECHO (void) fwrite( yytext, yyleng, 1, yyout )
+%+ C++ definition
+#define ECHO LexerOutput( yytext, yyleng )
+%*
+#endif
+
+/* Gets input and stuffs it into "buf". number of characters read, or YY_NULL,
+ * is returned in "result".
+ */
+#ifndef YY_INPUT
+#define YY_INPUT(buf,result,max_size) \
+%% fread()/read() definition of YY_INPUT goes here unless we're doing C++
+%+ C++ definition
+ if ( (result = LexerInput( (char *) buf, max_size )) < 0 ) \
+ YY_FATAL_ERROR( "input in flex scanner failed" );
+%*
+#endif
+
+/* No semi-colon after return; correct usage is to write "yyterminate();" -
+ * we don't want an extra ';' after the "return" because that will cause
+ * some compilers to complain about unreachable statements.
+ */
+#ifndef yyterminate
+#define yyterminate() return YY_NULL
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Report a fatal error. */
+#ifndef YY_FATAL_ERROR
+%-
+#define YY_FATAL_ERROR(msg) yy_fatal_error( msg )
+%+
+#define YY_FATAL_ERROR(msg) LexerError( msg )
+%*
+#endif
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+%- Standard (non-C++) definition
+#define YY_DECL int yylex YY_PROTO(( void ))
+%+ C++ definition
+#define YY_DECL int yyFlexLexer::yylex()
+%*
+#endif
+
+/* Code executed at the beginning of each rule, after yytext and yyleng
+ * have been set up.
+ */
+#ifndef YY_USER_ACTION
+#define YY_USER_ACTION
+#endif
+
+/* Code executed at the end of each rule. */
+#ifndef YY_BREAK
+#define YY_BREAK break;
+#endif
+
+YY_DECL
+ {
+ register yy_state_type yy_current_state;
+ register char *yy_cp, *yy_bp;
+ register int yy_act;
+
+%% user's declarations go here
+
+ if ( yy_init )
+ {
+#ifdef YY_USER_INIT
+ YY_USER_INIT;
+#endif
+
+ if ( ! yy_start )
+ yy_start = 1; /* first start state */
+
+ if ( ! yyin )
+%-
+ yyin = stdin;
+%+
+ yyin = &cin;
+%*
+
+ if ( ! yyout )
+%-
+ yyout = stdout;
+%+
+ yyout = &cout;
+%*
+
+ if ( yy_current_buffer )
+ yy_init_buffer( yy_current_buffer, yyin );
+ else
+ yy_current_buffer =
+ yy_create_buffer( yyin, YY_BUF_SIZE );
+
+ yy_load_buffer_state();
+
+ yy_init = 0;
+ }
+
+ while ( 1 ) /* loops until end-of-file is reached */
+ {
+%% yymore()-related code goes here
+ yy_cp = yy_c_buf_p;
+
+ /* Support of yytext. */
+ *yy_cp = yy_hold_char;
+
+ /* yy_bp points to the position in yy_ch_buf of the start of
+ * the current run.
+ */
+ yy_bp = yy_cp;
+
+%% code to set up and find next match goes here
+
+yy_find_action:
+%% code to find the action number goes here
+
+ YY_DO_BEFORE_ACTION;
+
+%% code for yylineno update goes here, if -l option
+
+do_action: /* This label is used only to access EOF actions. */
+
+%% debug code goes here
+
+ switch ( yy_act )
+ { /* beginning of action switch */
+%% actions go here
+
+ case YY_END_OF_BUFFER:
+ {
+ /* Amount of text matched not including the EOB char. */
+ int yy_amount_of_matched_text = yy_cp - yytext_ptr - 1;
+
+ /* Undo the effects of YY_DO_BEFORE_ACTION. */
+ *yy_cp = yy_hold_char;
+
+ if ( yy_current_buffer->yy_buffer_status == YY_BUFFER_NEW )
+ {
+ /* We're scanning a new file or input source. It's
+ * possible that this happened because the user
+ * just pointed yyin at a new source and called
+ * yylex(). If so, then we have to assure
+ * consistency between yy_current_buffer and our
+ * globals. Here is the right place to do so, because
+ * this is the first action (other than possibly a
+ * back-up) that will match for the new input source.
+ */
+ yy_n_chars = yy_current_buffer->yy_n_chars;
+ yy_current_buffer->yy_input_file = yyin;
+ yy_current_buffer->yy_buffer_status = YY_BUFFER_NORMAL;
+ }
+
+ /* Note that here we test for yy_c_buf_p "<=" to the position
+ * of the first EOB in the buffer, since yy_c_buf_p will
+ * already have been incremented past the NUL character
+ * (since all states make transitions on EOB to the
+ * end-of-buffer state). Contrast this with the test
+ * in input().
+ */
+ if ( yy_c_buf_p <= &yy_current_buffer->yy_ch_buf[yy_n_chars] )
+ { /* This was really a NUL. */
+ yy_state_type yy_next_state;
+
+ yy_c_buf_p = yytext_ptr + yy_amount_of_matched_text;
+
+ yy_current_state = yy_get_previous_state();
+
+ /* Okay, we're now positioned to make the NUL
+ * transition. We couldn't have
+ * yy_get_previous_state() go ahead and do it
+ * for us because it doesn't know how to deal
+ * with the possibility of jamming (and we don't
+ * want to build jamming into it because then it
+ * will run more slowly).
+ */
+
+ yy_next_state = yy_try_NUL_trans( yy_current_state );
+
+ yy_bp = yytext_ptr + YY_MORE_ADJ;
+
+ if ( yy_next_state )
+ {
+ /* Consume the NUL. */
+ yy_cp = ++yy_c_buf_p;
+ yy_current_state = yy_next_state;
+ goto yy_match;
+ }
+
+ else
+ {
+%% code to do back-up for compressed tables and set up yy_cp goes here
+ goto yy_find_action;
+ }
+ }
+
+ else switch ( yy_get_next_buffer() )
+ {
+ case EOB_ACT_END_OF_FILE:
+ {
+ yy_did_buffer_switch_on_eof = 0;
+
+ if ( yywrap() )
+ {
+ /* Note: because we've taken care in
+ * yy_get_next_buffer() to have set up
+ * yytext, we can now set up
+ * yy_c_buf_p so that if some total
+ * hoser (like flex itself) wants to
+ * call the scanner after we return the
+ * YY_NULL, it'll still work - another
+ * YY_NULL will get returned.
+ */
+ yy_c_buf_p = yytext_ptr + YY_MORE_ADJ;
+
+ yy_act = YY_STATE_EOF(YY_START);
+ goto do_action;
+ }
+
+ else
+ {
+ if ( ! yy_did_buffer_switch_on_eof )
+ YY_NEW_FILE;
+ }
+ break;
+ }
+
+ case EOB_ACT_CONTINUE_SCAN:
+ yy_c_buf_p =
+ yytext_ptr + yy_amount_of_matched_text;
+
+ yy_current_state = yy_get_previous_state();
+
+ yy_cp = yy_c_buf_p;
+ yy_bp = yytext_ptr + YY_MORE_ADJ;
+ goto yy_match;
+
+ case EOB_ACT_LAST_MATCH:
+ yy_c_buf_p =
+ &yy_current_buffer->yy_ch_buf[yy_n_chars];
+
+ yy_current_state = yy_get_previous_state();
+
+ yy_cp = yy_c_buf_p;
+ yy_bp = yytext_ptr + YY_MORE_ADJ;
+ goto yy_find_action;
+ }
+ break;
+ }
+
+ default:
+ YY_FATAL_ERROR(
+ "fatal flex scanner internal error--no action found" );
+ } /* end of action switch */
+ } /* end of scanning one token */
+ } /* end of yylex */
+
+%+
+#ifdef YY_INTERACTIVE
+int yyFlexLexer::LexerInput( char* buf, int /* max_size */ )
+#else
+int yyFlexLexer::LexerInput( char* buf, int max_size )
+#endif
+ {
+ if ( yyin->eof() || yyin->fail() )
+ return 0;
+
+#ifdef YY_INTERACTIVE
+ yyin->get( buf[0] );
+
+ if ( yyin->eof() )
+ return 0;
+
+ if ( yyin->bad() )
+ return -1;
+
+ return 1;
+
+#else
+ (void) yyin->read( buf, max_size );
+
+ if ( yyin->bad() )
+ return -1;
+ else
+ return yyin->gcount();
+#endif
+ }
+
+void yyFlexLexer::LexerOutput( const char* buf, int size )
+ {
+ (void) yyout->write( buf, size );
+ }
+%*
+
+/* yy_get_next_buffer - try to read in a new buffer
+ *
+ * Returns a code representing an action:
+ * EOB_ACT_LAST_MATCH -
+ * EOB_ACT_CONTINUE_SCAN - continue scanning from current position
+ * EOB_ACT_END_OF_FILE - end of file
+ */
+
+%-
+static int yy_get_next_buffer()
+%+
+int yyFlexLexer::yy_get_next_buffer()
+%*
+ {
+ register char *dest = yy_current_buffer->yy_ch_buf;
+ register char *source = yytext_ptr - 1; /* copy prev. char, too */
+ register int number_to_move, i;
+ int ret_val;
+
+ if ( yy_c_buf_p > &yy_current_buffer->yy_ch_buf[yy_n_chars + 1] )
+ YY_FATAL_ERROR(
+ "fatal flex scanner internal error--end of buffer missed" );
+
+ if ( yy_current_buffer->yy_fill_buffer == 0 )
+ { /* Don't try to fill the buffer, so this is an EOF. */
+ if ( yy_c_buf_p - yytext_ptr - YY_MORE_ADJ == 1 )
+ {
+ /* We matched a singled characater, the EOB, so
+ * treat this as a final EOF.
+ */
+ return EOB_ACT_END_OF_FILE;
+ }
+
+ else
+ {
+ /* We matched some text prior to the EOB, first
+ * process it.
+ */
+ return EOB_ACT_LAST_MATCH;
+ }
+ }
+
+ /* Try to read more data. */
+
+ /* First move last chars to start of buffer. */
+ number_to_move = yy_c_buf_p - yytext_ptr;
+
+ for ( i = 0; i < number_to_move; ++i )
+ *(dest++) = *(source++);
+
+ if ( yy_current_buffer->yy_buffer_status == YY_BUFFER_EOF_PENDING )
+ /* don't do the read, it's not guaranteed to return an EOF,
+ * just force an EOF
+ */
+ yy_n_chars = 0;
+
+ else
+ {
+ int num_to_read =
+ yy_current_buffer->yy_buf_size - number_to_move - 1;
+
+ while ( num_to_read <= 0 )
+ { /* Not enough room in the buffer - grow it. */
+#ifdef YY_USES_REJECT
+ YY_FATAL_ERROR(
+"input buffer overflow, can't enlarge buffer because scanner uses REJECT" );
+#else
+
+ /* just a shorter name for the current buffer */
+ YY_BUFFER_STATE b = yy_current_buffer;
+
+ int yy_c_buf_p_offset = yy_c_buf_p - b->yy_ch_buf;
+
+ b->yy_buf_size *= 2;
+ b->yy_ch_buf = (char *)
+ yy_flex_realloc( (void *) b->yy_ch_buf,
+ b->yy_buf_size );
+
+ if ( ! b->yy_ch_buf )
+ YY_FATAL_ERROR(
+ "fatal error - scanner input buffer overflow" );
+
+ yy_c_buf_p = &b->yy_ch_buf[yy_c_buf_p_offset];
+
+ num_to_read = yy_current_buffer->yy_buf_size -
+ number_to_move - 1;
+#endif
+ }
+
+ if ( num_to_read > YY_READ_BUF_SIZE )
+ num_to_read = YY_READ_BUF_SIZE;
+
+ /* Read in more data. */
+ YY_INPUT( (&yy_current_buffer->yy_ch_buf[number_to_move]),
+ yy_n_chars, num_to_read );
+ }
+
+ if ( yy_n_chars == 0 )
+ {
+ if ( number_to_move - YY_MORE_ADJ == 1 )
+ {
+ ret_val = EOB_ACT_END_OF_FILE;
+ yyrestart( yyin );
+ }
+
+ else
+ {
+ ret_val = EOB_ACT_LAST_MATCH;
+ yy_current_buffer->yy_buffer_status =
+ YY_BUFFER_EOF_PENDING;
+ }
+ }
+
+ else
+ ret_val = EOB_ACT_CONTINUE_SCAN;
+
+ yy_n_chars += number_to_move;
+ yy_current_buffer->yy_ch_buf[yy_n_chars] = YY_END_OF_BUFFER_CHAR;
+ yy_current_buffer->yy_ch_buf[yy_n_chars + 1] = YY_END_OF_BUFFER_CHAR;
+
+ /* yytext begins at the second character in yy_ch_buf; the first
+ * character is the one which preceded it before reading in the latest
+ * buffer; it needs to be kept around in case it's a newline, so
+ * yy_get_previous_state() will have with '^' rules active.
+ */
+
+ yytext_ptr = &yy_current_buffer->yy_ch_buf[1];
+
+ return ret_val;
+ }
+
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+%-
+static yy_state_type yy_get_previous_state()
+%+
+yy_state_type yyFlexLexer::yy_get_previous_state()
+%*
+ {
+ register yy_state_type yy_current_state;
+ register char *yy_cp;
+
+%% code to get the start state into yy_current_state goes here
+
+ for ( yy_cp = yytext_ptr + YY_MORE_ADJ; yy_cp < yy_c_buf_p; ++yy_cp )
+ {
+%% code to find the next state goes here
+ }
+
+ return yy_current_state;
+ }
+
+
+/* yy_try_NUL_trans - try to make a transition on the NUL character
+ *
+ * synopsis
+ * next_state = yy_try_NUL_trans( current_state );
+ */
+
+%-
+#ifdef YY_USE_PROTOS
+static yy_state_type yy_try_NUL_trans( yy_state_type yy_current_state )
+#else
+static yy_state_type yy_try_NUL_trans( yy_current_state )
+yy_state_type yy_current_state;
+#endif
+%+
+yy_state_type yyFlexLexer::yy_try_NUL_trans( yy_state_type yy_current_state )
+%*
+ {
+ register int yy_is_jam;
+%% code to find the next state, and perhaps do backing up, goes here
+
+ return yy_is_jam ? 0 : yy_current_state;
+ }
+
+
+%-
+#ifdef YY_USE_PROTOS
+static void yyunput( int c, register char *yy_bp )
+#else
+static void yyunput( c, yy_bp )
+int c;
+register char *yy_bp;
+#endif
+%+
+void yyFlexLexer::yyunput( int c, register char* yy_bp )
+%*
+ {
+ register char *yy_cp = yy_c_buf_p;
+
+ /* undo effects of setting up yytext */
+ *yy_cp = yy_hold_char;
+
+ if ( yy_cp < yy_current_buffer->yy_ch_buf + 2 )
+ { /* need to shift things up to make room */
+ /* +2 for EOB chars. */
+ register int number_to_move = yy_n_chars + 2;
+ register char *dest = &yy_current_buffer->yy_ch_buf[
+ yy_current_buffer->yy_buf_size + 2];
+ register char *source =
+ &yy_current_buffer->yy_ch_buf[number_to_move];
+
+ while ( source > yy_current_buffer->yy_ch_buf )
+ *--dest = *--source;
+
+ yy_cp += dest - source;
+ yy_bp += dest - source;
+ yy_n_chars = yy_current_buffer->yy_buf_size;
+
+ if ( yy_cp < yy_current_buffer->yy_ch_buf + 2 )
+ YY_FATAL_ERROR( "flex scanner push-back overflow" );
+ }
+
+ if ( yy_cp > yy_bp && yy_cp[-1] == '\n' )
+ yy_cp[-2] = '\n';
+
+ *--yy_cp = (char) c;
+
+%% update yylineno here, if doing -l
+
+ /* Note: the formal parameter *must* be called "yy_bp" for this
+ * macro to now work correctly.
+ */
+ YY_DO_BEFORE_ACTION; /* set up yytext again */
+ }
+
+
+%-
+#ifdef __cplusplus
+static int yyinput()
+#else
+static int input()
+#endif
+%+
+int yyFlexLexer::yyinput()
+%*
+ {
+ int c;
+
+ *yy_c_buf_p = yy_hold_char;
+
+ if ( *yy_c_buf_p == YY_END_OF_BUFFER_CHAR )
+ {
+ /* yy_c_buf_p now points to the character we want to return.
+ * If this occurs *before* the EOB characters, then it's a
+ * valid NUL; if not, then we've hit the end of the buffer.
+ */
+ if ( yy_c_buf_p < &yy_current_buffer->yy_ch_buf[yy_n_chars] )
+ /* This was really a NUL. */
+ *yy_c_buf_p = '\0';
+
+ else
+ { /* need more input */
+ yytext_ptr = yy_c_buf_p;
+ ++yy_c_buf_p;
+
+ switch ( yy_get_next_buffer() )
+ {
+ case EOB_ACT_END_OF_FILE:
+ {
+ if ( yywrap() )
+ {
+ yy_c_buf_p =
+ yytext_ptr + YY_MORE_ADJ;
+ return EOF;
+ }
+
+ YY_NEW_FILE;
+#ifdef __cplusplus
+ return yyinput();
+#else
+ return input();
+#endif
+ }
+
+ case EOB_ACT_CONTINUE_SCAN:
+ yy_c_buf_p = yytext_ptr + YY_MORE_ADJ;
+ break;
+
+ case EOB_ACT_LAST_MATCH:
+#ifdef __cplusplus
+ YY_FATAL_ERROR(
+ "unexpected last match in yyinput()" );
+#else
+ YY_FATAL_ERROR(
+ "unexpected last match in input()" );
+#endif
+ }
+ }
+ }
+
+ c = *(unsigned char *) yy_c_buf_p; /* cast for 8-bit char's */
+ *yy_c_buf_p = '\0'; /* preserve yytext */
+ yy_hold_char = *++yy_c_buf_p;
+
+ return c;
+ }
+
+
+%-
+#ifdef YY_USE_PROTOS
+void yyrestart( FILE *input_file )
+#else
+void yyrestart( input_file )
+FILE *input_file;
+#endif
+%+
+void yyFlexLexer::yyrestart( istream* input_file )
+%*
+ {
+ if ( ! yy_current_buffer )
+ yy_current_buffer = yy_create_buffer( yyin, YY_BUF_SIZE );
+
+ yy_init_buffer( yy_current_buffer, input_file );
+ yy_load_buffer_state();
+ }
+
+
+%-
+#ifdef YY_USE_PROTOS
+void yy_switch_to_buffer( YY_BUFFER_STATE new_buffer )
+#else
+void yy_switch_to_buffer( new_buffer )
+YY_BUFFER_STATE new_buffer;
+#endif
+%+
+void yyFlexLexer::yy_switch_to_buffer( YY_BUFFER_STATE new_buffer )
+%*
+ {
+ if ( yy_current_buffer == new_buffer )
+ return;
+
+ if ( yy_current_buffer )
+ {
+ /* Flush out information for old buffer. */
+ *yy_c_buf_p = yy_hold_char;
+ yy_current_buffer->yy_buf_pos = yy_c_buf_p;
+ yy_current_buffer->yy_n_chars = yy_n_chars;
+ }
+
+ yy_current_buffer = new_buffer;
+ yy_load_buffer_state();
+
+ /* We don't actually know whether we did this switch during
+ * EOF (yywrap()) processing, but the only time this flag
+ * is looked at is after yywrap() is called, so it's safe
+ * to go ahead and always set it.
+ */
+ yy_did_buffer_switch_on_eof = 1;
+ }
+
+
+%-
+#ifdef YY_USE_PROTOS
+void yy_load_buffer_state( void )
+#else
+void yy_load_buffer_state()
+#endif
+%+
+void yyFlexLexer::yy_load_buffer_state()
+%*
+ {
+ yy_n_chars = yy_current_buffer->yy_n_chars;
+ yytext_ptr = yy_c_buf_p = yy_current_buffer->yy_buf_pos;
+ yyin = yy_current_buffer->yy_input_file;
+ yy_hold_char = *yy_c_buf_p;
+ }
+
+
+%-
+#ifdef YY_USE_PROTOS
+YY_BUFFER_STATE yy_create_buffer( FILE *file, int size )
+#else
+YY_BUFFER_STATE yy_create_buffer( file, size )
+FILE *file;
+int size;
+#endif
+%+
+YY_BUFFER_STATE yyFlexLexer::yy_create_buffer( istream* file, int size )
+%*
+ {
+ YY_BUFFER_STATE b;
+
+ b = (YY_BUFFER_STATE) yy_flex_alloc( sizeof( struct yy_buffer_state ) );
+
+ if ( ! b )
+ YY_FATAL_ERROR( "out of dynamic memory in yy_create_buffer()" );
+
+ b->yy_buf_size = size;
+
+ /* yy_ch_buf has to be 2 characters longer than the size given because
+ * we need to put in 2 end-of-buffer characters.
+ */
+ b->yy_ch_buf = (char *) yy_flex_alloc( b->yy_buf_size + 2 );
+
+ if ( ! b->yy_ch_buf )
+ YY_FATAL_ERROR( "out of dynamic memory in yy_create_buffer()" );
+
+ yy_init_buffer( b, file );
+
+ return b;
+ }
+
+
+%-
+#ifdef YY_USE_PROTOS
+void yy_delete_buffer( YY_BUFFER_STATE b )
+#else
+void yy_delete_buffer( b )
+YY_BUFFER_STATE b;
+#endif
+%+
+void yyFlexLexer::yy_delete_buffer( YY_BUFFER_STATE b )
+%*
+ {
+ if ( b == yy_current_buffer )
+ yy_current_buffer = (YY_BUFFER_STATE) 0;
+
+ yy_flex_free( (void *) b->yy_ch_buf );
+ yy_flex_free( (void *) b );
+ }
+
+
+%-
+#ifdef YY_USE_PROTOS
+void yy_init_buffer( YY_BUFFER_STATE b, FILE *file )
+#else
+void yy_init_buffer( b, file )
+YY_BUFFER_STATE b;
+FILE *file;
+#endif
+%+
+void yyFlexLexer::yy_init_buffer( YY_BUFFER_STATE b, istream* file )
+%*
+ {
+ b->yy_input_file = file;
+
+ /* We put in the '\n' and start reading from [1] so that an
+ * initial match-at-newline will be true.
+ */
+
+ b->yy_ch_buf[0] = '\n';
+ b->yy_n_chars = 1;
+
+ /* We always need two end-of-buffer characters. The first causes
+ * a transition to the end-of-buffer state. The second causes
+ * a jam in that state.
+ */
+ b->yy_ch_buf[1] = YY_END_OF_BUFFER_CHAR;
+ b->yy_ch_buf[2] = YY_END_OF_BUFFER_CHAR;
+
+ b->yy_buf_pos = &b->yy_ch_buf[1];
+
+%-
+ b->yy_is_interactive = file ? isatty( fileno(file) ) : 0;
+%+
+ b->yy_is_interactive = 0;
+%*
+
+ b->yy_fill_buffer = 1;
+
+ b->yy_buffer_status = YY_BUFFER_NEW;
+ }
+
+
+%-
+#ifdef YY_USE_PROTOS
+static void yy_push_state( int new_state )
+#else
+static void yy_push_state( new_state )
+int new_state;
+#endif
+%+
+void yyFlexLexer::yy_push_state( int new_state )
+%*
+ {
+ if ( yy_start_stack_ptr >= yy_start_stack_depth )
+ {
+ int new_size;
+
+ yy_start_stack_depth += YY_START_STACK_INCR;
+ new_size = yy_start_stack_depth * sizeof( int );
+
+ if ( ! yy_start_stack )
+ yy_start_stack = (int *) yy_flex_alloc( new_size );
+
+ else
+ yy_start_stack = (int *) yy_flex_realloc(
+ (void *) yy_start_stack, new_size );
+
+ if ( ! yy_start_stack )
+ YY_FATAL_ERROR(
+ "out of memory expanding start-condition stack" );
+ }
+
+ yy_start_stack[yy_start_stack_ptr++] = YY_START;
+
+ BEGIN(new_state);
+ }
+
+
+%-
+static void yy_pop_state()
+%+
+void yyFlexLexer::yy_pop_state()
+%*
+ {
+ if ( --yy_start_stack_ptr < 0 )
+ YY_FATAL_ERROR( "start-condition stack underflow" );
+
+ BEGIN(yy_start_stack[yy_start_stack_ptr]);
+ }
+
+
+%-
+static int yy_top_state()
+%+
+int yyFlexLexer::yy_top_state()
+%*
+ {
+ return yy_start_stack[yy_start_stack_ptr - 1];
+ }
+
+
+%-
+#ifdef YY_USE_PROTOS
+static void yy_fatal_error( const char msg[] )
+#else
+static void yy_fatal_error( msg )
+char msg[];
+#endif
+ {
+ (void) fprintf( stderr, "%s\n", msg );
+ exit( 1 );
+ }
+
+%+
+
+void yyFlexLexer::LexerError( const char msg[] )
+ {
+ cerr << msg << '\n';
+ exit( 1 );
+ }
+%*
+
+
+/* Redefine yyless() so it works in section 3 code. */
+
+#undef yyless
+#define yyless(n) \
+ do \
+ { \
+ /* Undo effects of setting up yytext. */ \
+ yytext[yyleng] = yy_hold_char; \
+ yy_c_buf_p = yytext + n - YY_MORE_ADJ; \
+ yy_hold_char = *yy_c_buf_p; \
+ *yy_c_buf_p = '\0'; \
+ yyleng = n; \
+ } \
+ while ( 0 )
+
+
+/* Internal utility routines. */
+
+#ifndef yytext_ptr
+#ifdef YY_USE_PROTOS
+static void yy_flex_strncpy( char *s1, const char *s2, int n )
+#else
+static void yy_flex_strncpy( s1, s2, n )
+char *s1;
+const char *s2;
+int n;
+#endif
+ {
+ register int i;
+ for ( i = 0; i < n; ++i )
+ s1[i] = s2[i];
+ }
+#endif
+
+
+#ifdef YY_USE_PROTOS
+static void *yy_flex_alloc( unsigned int size )
+#else
+static void *yy_flex_alloc( size )
+unsigned int size;
+#endif
+ {
+ return (void *) malloc( size );
+ }
+
+#ifdef YY_USE_PROTOS
+static void *yy_flex_realloc( void *ptr, unsigned int size )
+#else
+static void *yy_flex_realloc( ptr, size )
+void *ptr;
+unsigned int size;
+#endif
+ {
+ return (void *) realloc( ptr, size );
+ }
+
+#ifdef YY_USE_PROTOS
+static void yy_flex_free( void *ptr )
+#else
+static void yy_flex_free( ptr )
+void *ptr;
+#endif
+ {
+ free( ptr );
+ }
diff --git a/usr.bin/lex/flexdef.h b/usr.bin/lex/flexdef.h
new file mode 100644
index 000000000000..c8d4825a0e44
--- /dev/null
+++ b/usr.bin/lex/flexdef.h
@@ -0,0 +1,902 @@
+/* flexdef - definitions file for flex */
+
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* @(#) $Header: flexdef.h,v 1.2 94/01/04 14:33:14 vern Exp $ (LBL) */
+
+#include <stdio.h>
+#include <ctype.h>
+
+#if HAVE_STRING_H
+#include <string.h>
+#else
+#include <strings.h>
+#endif
+
+#if __STDC__
+#include <stdlib.h>
+#endif
+
+/* Always be prepared to generate an 8-bit scanner. */
+#define CSIZE 256
+#define Char unsigned char
+
+/* Size of input alphabet - should be size of ASCII set. */
+#ifndef DEFAULT_CSIZE
+#define DEFAULT_CSIZE 128
+#endif
+
+#ifndef PROTO
+#ifdef __STDC__
+#define PROTO(proto) proto
+#else
+#define PROTO(proto) ()
+#endif
+#endif
+
+#ifdef VMS
+#define unlink delete
+#define SHORT_FILE_NAMES
+#endif
+
+#ifdef MS_DOS
+#define SHORT_FILE_NAMES
+#endif
+
+
+/* Maximum line length we'll have to deal with. */
+#define MAXLINE 2048
+
+#ifndef MIN
+#define MIN(x,y) ((x) < (y) ? (x) : (y))
+#endif
+#ifndef MAX
+#define MAX(x,y) ((x) > (y) ? (x) : (y))
+#endif
+#ifndef ABS
+#define ABS(x) ((x) < 0 ? -(x) : (x))
+#endif
+
+
+/* ANSI C does not guarantee that isascii() is defined */
+#ifndef isascii
+#define isascii(c) ((c) <= 0177)
+#endif
+
+
+#define true 1
+#define false 0
+
+
+/* Special chk[] values marking the slots taking by end-of-buffer and action
+ * numbers.
+ */
+#define EOB_POSITION -1
+#define ACTION_POSITION -2
+
+/* Number of data items per line for -f output. */
+#define NUMDATAITEMS 10
+
+/* Number of lines of data in -f output before inserting a blank line for
+ * readability.
+ */
+#define NUMDATALINES 10
+
+/* Transition_struct_out() definitions. */
+#define TRANS_STRUCT_PRINT_LENGTH 15
+
+/* Returns true if an nfa state has an epsilon out-transition slot
+ * that can be used. This definition is currently not used.
+ */
+#define FREE_EPSILON(state) \
+ (transchar[state] == SYM_EPSILON && \
+ trans2[state] == NO_TRANSITION && \
+ finalst[state] != state)
+
+/* Returns true if an nfa state has an epsilon out-transition character
+ * and both slots are free
+ */
+#define SUPER_FREE_EPSILON(state) \
+ (transchar[state] == SYM_EPSILON && \
+ trans1[state] == NO_TRANSITION) \
+
+/* Maximum number of NFA states that can comprise a DFA state. It's real
+ * big because if there's a lot of rules, the initial state will have a
+ * huge epsilon closure.
+ */
+#define INITIAL_MAX_DFA_SIZE 750
+#define MAX_DFA_SIZE_INCREMENT 750
+
+
+/* A note on the following masks. They are used to mark accepting numbers
+ * as being special. As such, they implicitly limit the number of accepting
+ * numbers (i.e., rules) because if there are too many rules the rule numbers
+ * will overload the mask bits. Fortunately, this limit is \large/ (0x2000 ==
+ * 8192) so unlikely to actually cause any problems. A check is made in
+ * new_rule() to ensure that this limit is not reached.
+ */
+
+/* Mask to mark a trailing context accepting number. */
+#define YY_TRAILING_MASK 0x2000
+
+/* Mask to mark the accepting number of the "head" of a trailing context
+ * rule.
+ */
+#define YY_TRAILING_HEAD_MASK 0x4000
+
+/* Maximum number of rules, as outlined in the above note. */
+#define MAX_RULE (YY_TRAILING_MASK - 1)
+
+
+/* NIL must be 0. If not, its special meaning when making equivalence classes
+ * (it marks the representative of a given e.c.) will be unidentifiable.
+ */
+#define NIL 0
+
+#define JAM -1 /* to mark a missing DFA transition */
+#define NO_TRANSITION NIL
+#define UNIQUE -1 /* marks a symbol as an e.c. representative */
+#define INFINITY -1 /* for x{5,} constructions */
+
+#define INITIAL_MAX_CCLS 100 /* max number of unique character classes */
+#define MAX_CCLS_INCREMENT 100
+
+/* Size of table holding members of character classes. */
+#define INITIAL_MAX_CCL_TBL_SIZE 500
+#define MAX_CCL_TBL_SIZE_INCREMENT 250
+
+#define INITIAL_MAX_RULES 100 /* default maximum number of rules */
+#define MAX_RULES_INCREMENT 100
+
+#define INITIAL_MNS 2000 /* default maximum number of nfa states */
+#define MNS_INCREMENT 1000 /* amount to bump above by if it's not enough */
+
+#define INITIAL_MAX_DFAS 1000 /* default maximum number of dfa states */
+#define MAX_DFAS_INCREMENT 1000
+
+#define JAMSTATE -32766 /* marks a reference to the state that always jams */
+
+/* Enough so that if it's subtracted from an NFA state number, the result
+ * is guaranteed to be negative.
+ */
+#define MARKER_DIFFERENCE 32000
+#define MAXIMUM_MNS 31999
+
+/* Maximum number of nxt/chk pairs for non-templates. */
+#define INITIAL_MAX_XPAIRS 2000
+#define MAX_XPAIRS_INCREMENT 2000
+
+/* Maximum number of nxt/chk pairs needed for templates. */
+#define INITIAL_MAX_TEMPLATE_XPAIRS 2500
+#define MAX_TEMPLATE_XPAIRS_INCREMENT 2500
+
+#define SYM_EPSILON (CSIZE + 1) /* to mark transitions on the symbol epsilon */
+
+#define INITIAL_MAX_SCS 40 /* maximum number of start conditions */
+#define MAX_SCS_INCREMENT 40 /* amount to bump by if it's not enough */
+
+#define ONE_STACK_SIZE 500 /* stack of states with only one out-transition */
+#define SAME_TRANS -1 /* transition is the same as "default" entry for state */
+
+/* The following percentages are used to tune table compression:
+
+ * The percentage the number of out-transitions a state must be of the
+ * number of equivalence classes in order to be considered for table
+ * compaction by using protos.
+ */
+#define PROTO_SIZE_PERCENTAGE 15
+
+/* The percentage the number of homogeneous out-transitions of a state
+ * must be of the number of total out-transitions of the state in order
+ * that the state's transition table is first compared with a potential
+ * template of the most common out-transition instead of with the first
+ * proto in the proto queue.
+ */
+#define CHECK_COM_PERCENTAGE 50
+
+/* The percentage the number of differences between a state's transition
+ * table and the proto it was first compared with must be of the total
+ * number of out-transitions of the state in order to keep the first
+ * proto as a good match and not search any further.
+ */
+#define FIRST_MATCH_DIFF_PERCENTAGE 10
+
+/* The percentage the number of differences between a state's transition
+ * table and the most similar proto must be of the state's total number
+ * of out-transitions to use the proto as an acceptable close match.
+ */
+#define ACCEPTABLE_DIFF_PERCENTAGE 50
+
+/* The percentage the number of homogeneous out-transitions of a state
+ * must be of the number of total out-transitions of the state in order
+ * to consider making a template from the state.
+ */
+#define TEMPLATE_SAME_PERCENTAGE 60
+
+/* The percentage the number of differences between a state's transition
+ * table and the most similar proto must be of the state's total number
+ * of out-transitions to create a new proto from the state.
+ */
+#define NEW_PROTO_DIFF_PERCENTAGE 20
+
+/* The percentage the total number of out-transitions of a state must be
+ * of the number of equivalence classes in order to consider trying to
+ * fit the transition table into "holes" inside the nxt/chk table.
+ */
+#define INTERIOR_FIT_PERCENTAGE 15
+
+/* Size of region set aside to cache the complete transition table of
+ * protos on the proto queue to enable quick comparisons.
+ */
+#define PROT_SAVE_SIZE 2000
+
+#define MSP 50 /* maximum number of saved protos (protos on the proto queue) */
+
+/* Maximum number of out-transitions a state can have that we'll rummage
+ * around through the interior of the internal fast table looking for a
+ * spot for it.
+ */
+#define MAX_XTIONS_FULL_INTERIOR_FIT 4
+
+/* Maximum number of rules which will be reported as being associated
+ * with a DFA state.
+ */
+#define MAX_ASSOC_RULES 100
+
+/* Number that, if used to subscript an array, has a good chance of producing
+ * an error; should be small enough to fit into a short.
+ */
+#define BAD_SUBSCRIPT -32767
+
+/* Absolute value of largest number that can be stored in a short, with a
+ * bit of slop thrown in for general paranoia.
+ */
+#define MAX_SHORT 32700
+
+
+/* Declarations for global variables. */
+
+/* Variables for symbol tables:
+ * sctbl - start-condition symbol table
+ * ndtbl - name-definition symbol table
+ * ccltab - character class text symbol table
+ */
+
+struct hash_entry
+ {
+ struct hash_entry *prev, *next;
+ char *name;
+ char *str_val;
+ int int_val;
+ } ;
+
+typedef struct hash_entry **hash_table;
+
+#define NAME_TABLE_HASH_SIZE 101
+#define START_COND_HASH_SIZE 101
+#define CCL_HASH_SIZE 101
+
+extern struct hash_entry *ndtbl[NAME_TABLE_HASH_SIZE];
+extern struct hash_entry *sctbl[START_COND_HASH_SIZE];
+extern struct hash_entry *ccltab[CCL_HASH_SIZE];
+
+
+/* Variables for flags:
+ * printstats - if true (-v), dump statistics
+ * syntaxerror - true if a syntax error has been found
+ * eofseen - true if we've seen an eof in the input file
+ * ddebug - if true (-d), make a "debug" scanner
+ * trace - if true (-T), trace processing
+ * nowarn - if true (-w), do not generate warnings
+ * spprdflt - if true (-s), suppress the default rule
+ * interactive - if true (-I), generate an interactive scanner
+ * caseins - if true (-i), generate a case-insensitive scanner
+ * lex_compat - if true (-l), maximize compatibility with AT&T lex
+ * useecs - if true (-Ce flag), use equivalence classes
+ * fulltbl - if true (-Cf flag), don't compress the DFA state table
+ * usemecs - if true (-Cm flag), use meta-equivalence classes
+ * fullspd - if true (-F flag), use Jacobson method of table representation
+ * gen_line_dirs - if true (i.e., no -L flag), generate #line directives
+ * performance_report - if > 0 (i.e., -p flag), generate a report relating
+ * to scanner performance; if > 1 (-p -p), report on minor performance
+ * problems, too
+ * backing_up_report - if true (i.e., -b flag), generate "lex.backup" file
+ * listing backing-up states
+ * C_plus_plus - if true (i.e., -+ flag), generate a C++ scanner class;
+ * otherwise, a standard C scanner
+ * long_align - if true (-Ca flag), favor long-word alignment.
+ * use_read - if true (-f, -F, or -Cr) then use read() for scanner input;
+ * otherwise, use fread().
+ * yytext_is_array - if true (i.e., %array directive), then declare
+ * yytext as a array instead of a character pointer. Nice and inefficient.
+ * csize - size of character set for the scanner we're generating;
+ * 128 for 7-bit chars and 256 for 8-bit
+ * yymore_used - if true, yymore() is used in input rules
+ * reject - if true, generate back-up tables for REJECT macro
+ * real_reject - if true, scanner really uses REJECT (as opposed to just
+ * having "reject" set for variable trailing context)
+ * continued_action - true if this rule's action is to "fall through" to
+ * the next rule's action (i.e., the '|' action)
+ * yymore_really_used - has a REALLY_xxx value indicating whether a
+ * %used or %notused was used with yymore()
+ * reject_really_used - same for REJECT
+ */
+
+extern int printstats, syntaxerror, eofseen, ddebug, trace, nowarn, spprdflt;
+extern int interactive, caseins, lex_compat, useecs, fulltbl, usemecs;
+extern int fullspd, gen_line_dirs, performance_report, backing_up_report;
+extern int C_plus_plus, long_align, use_read, yytext_is_array, csize;
+extern int yymore_used, reject, real_reject, continued_action;
+
+#define REALLY_NOT_DETERMINED 0
+#define REALLY_USED 1
+#define REALLY_NOT_USED 2
+extern int yymore_really_used, reject_really_used;
+
+
+/* Variables used in the flex input routines:
+ * datapos - characters on current output line
+ * dataline - number of contiguous lines of data in current data
+ * statement. Used to generate readable -f output
+ * linenum - current input line number
+ * skelfile - the skeleton file
+ * skel - compiled-in skeleton array
+ * skel_ind - index into "skel" array, if skelfile is nil
+ * yyin - input file
+ * backing_up_file - file to summarize backing-up states to
+ * infilename - name of input file
+ * input_files - array holding names of input files
+ * num_input_files - size of input_files array
+ * program_name - name with which program was invoked
+ *
+ * action_array - array to hold the rule actions
+ * action_size - size of action_array
+ * defs1_offset - index where the user's section 1 definitions start
+ * in action_array
+ * prolog_offset - index where the prolog starts in action_array
+ * action_offset - index where the non-prolog starts in action_array
+ * action_index - index where the next action should go, with respect
+ * to "action_array"
+ */
+
+extern int datapos, dataline, linenum;
+extern FILE *skelfile, *yyin, *backing_up_file;
+extern char *skel[];
+extern int skel_ind;
+extern char *infilename;
+extern char **input_files;
+extern int num_input_files;
+extern char *program_name;
+
+extern char *action_array;
+extern int action_size;
+extern int defs1_offset, prolog_offset, action_offset, action_index;
+
+
+/* Variables for stack of states having only one out-transition:
+ * onestate - state number
+ * onesym - transition symbol
+ * onenext - target state
+ * onedef - default base entry
+ * onesp - stack pointer
+ */
+
+extern int onestate[ONE_STACK_SIZE], onesym[ONE_STACK_SIZE];
+extern int onenext[ONE_STACK_SIZE], onedef[ONE_STACK_SIZE], onesp;
+
+
+/* Variables for nfa machine data:
+ * current_mns - current maximum on number of NFA states
+ * num_rules - number of the last accepting state; also is number of
+ * rules created so far
+ * num_eof_rules - number of <<EOF>> rules
+ * default_rule - number of the default rule
+ * current_max_rules - current maximum number of rules
+ * lastnfa - last nfa state number created
+ * firstst - physically the first state of a fragment
+ * lastst - last physical state of fragment
+ * finalst - last logical state of fragment
+ * transchar - transition character
+ * trans1 - transition state
+ * trans2 - 2nd transition state for epsilons
+ * accptnum - accepting number
+ * assoc_rule - rule associated with this NFA state (or 0 if none)
+ * state_type - a STATE_xxx type identifying whether the state is part
+ * of a normal rule, the leading state in a trailing context
+ * rule (i.e., the state which marks the transition from
+ * recognizing the text-to-be-matched to the beginning of
+ * the trailing context), or a subsequent state in a trailing
+ * context rule
+ * rule_type - a RULE_xxx type identifying whether this a ho-hum
+ * normal rule or one which has variable head & trailing
+ * context
+ * rule_linenum - line number associated with rule
+ * rule_useful - true if we've determined that the rule can be matched
+ */
+
+extern int current_mns, num_rules, num_eof_rules, default_rule;
+extern int current_max_rules, lastnfa;
+extern int *firstst, *lastst, *finalst, *transchar, *trans1, *trans2;
+extern int *accptnum, *assoc_rule, *state_type;
+extern int *rule_type, *rule_linenum, *rule_useful;
+
+/* Different types of states; values are useful as masks, as well, for
+ * routines like check_trailing_context().
+ */
+#define STATE_NORMAL 0x1
+#define STATE_TRAILING_CONTEXT 0x2
+
+/* Global holding current type of state we're making. */
+
+extern int current_state_type;
+
+/* Different types of rules. */
+#define RULE_NORMAL 0
+#define RULE_VARIABLE 1
+
+/* True if the input rules include a rule with both variable-length head
+ * and trailing context, false otherwise.
+ */
+extern int variable_trailing_context_rules;
+
+
+/* Variables for protos:
+ * numtemps - number of templates created
+ * numprots - number of protos created
+ * protprev - backlink to a more-recently used proto
+ * protnext - forward link to a less-recently used proto
+ * prottbl - base/def table entry for proto
+ * protcomst - common state of proto
+ * firstprot - number of the most recently used proto
+ * lastprot - number of the least recently used proto
+ * protsave contains the entire state array for protos
+ */
+
+extern int numtemps, numprots, protprev[MSP], protnext[MSP], prottbl[MSP];
+extern int protcomst[MSP], firstprot, lastprot, protsave[PROT_SAVE_SIZE];
+
+
+/* Variables for managing equivalence classes:
+ * numecs - number of equivalence classes
+ * nextecm - forward link of Equivalence Class members
+ * ecgroup - class number or backward link of EC members
+ * nummecs - number of meta-equivalence classes (used to compress
+ * templates)
+ * tecfwd - forward link of meta-equivalence classes members
+ * tecbck - backward link of MEC's
+ */
+
+/* Reserve enough room in the equivalence class arrays so that we
+ * can use the CSIZE'th element to hold equivalence class information
+ * for the NUL character. Later we'll move this information into
+ * the 0th element.
+ */
+extern int numecs, nextecm[CSIZE + 1], ecgroup[CSIZE + 1], nummecs;
+
+/* Meta-equivalence classes are indexed starting at 1, so it's possible
+ * that they will require positions from 1 .. CSIZE, i.e., CSIZE + 1
+ * slots total (since the arrays are 0-based). nextecm[] and ecgroup[]
+ * don't require the extra position since they're indexed from 1 .. CSIZE - 1.
+ */
+extern int tecfwd[CSIZE + 1], tecbck[CSIZE + 1];
+
+
+/* Variables for start conditions:
+ * lastsc - last start condition created
+ * current_max_scs - current limit on number of start conditions
+ * scset - set of rules active in start condition
+ * scbol - set of rules active only at the beginning of line in a s.c.
+ * scxclu - true if start condition is exclusive
+ * sceof - true if start condition has EOF rule
+ * scname - start condition name
+ * actvsc - stack of active start conditions for the current rule;
+ * a negative entry means that the start condition is *not*
+ * active for the current rule. Start conditions may appear
+ * multiple times on the stack; the entry for it closest
+ * to the top of the stack (i.e., actvsc[actvp]) is the
+ * one to use. Others are present from "<sc>{" scoping
+ * constructs.
+ */
+
+extern int lastsc, current_max_scs, *scset, *scbol, *scxclu, *sceof, *actvsc;
+extern char **scname;
+
+
+/* Variables for dfa machine data:
+ * current_max_dfa_size - current maximum number of NFA states in DFA
+ * current_max_xpairs - current maximum number of non-template xtion pairs
+ * current_max_template_xpairs - current maximum number of template pairs
+ * current_max_dfas - current maximum number DFA states
+ * lastdfa - last dfa state number created
+ * nxt - state to enter upon reading character
+ * chk - check value to see if "nxt" applies
+ * tnxt - internal nxt table for templates
+ * base - offset into "nxt" for given state
+ * def - where to go if "chk" disallows "nxt" entry
+ * nultrans - NUL transition for each state
+ * NUL_ec - equivalence class of the NUL character
+ * tblend - last "nxt/chk" table entry being used
+ * firstfree - first empty entry in "nxt/chk" table
+ * dss - nfa state set for each dfa
+ * dfasiz - size of nfa state set for each dfa
+ * dfaacc - accepting set for each dfa state (if using REJECT), or accepting
+ * number, if not
+ * accsiz - size of accepting set for each dfa state
+ * dhash - dfa state hash value
+ * numas - number of DFA accepting states created; note that this
+ * is not necessarily the same value as num_rules, which is the analogous
+ * value for the NFA
+ * numsnpairs - number of state/nextstate transition pairs
+ * jambase - position in base/def where the default jam table starts
+ * jamstate - state number corresponding to "jam" state
+ * end_of_buffer_state - end-of-buffer dfa state number
+ */
+
+extern int current_max_dfa_size, current_max_xpairs;
+extern int current_max_template_xpairs, current_max_dfas;
+extern int lastdfa, *nxt, *chk, *tnxt;
+extern int *base, *def, *nultrans, NUL_ec, tblend, firstfree, **dss, *dfasiz;
+extern union dfaacc_union
+ {
+ int *dfaacc_set;
+ int dfaacc_state;
+ } *dfaacc;
+extern int *accsiz, *dhash, numas;
+extern int numsnpairs, jambase, jamstate;
+extern int end_of_buffer_state;
+
+/* Variables for ccl information:
+ * lastccl - ccl index of the last created ccl
+ * current_maxccls - current limit on the maximum number of unique ccl's
+ * cclmap - maps a ccl index to its set pointer
+ * ccllen - gives the length of a ccl
+ * cclng - true for a given ccl if the ccl is negated
+ * cclreuse - counts how many times a ccl is re-used
+ * current_max_ccl_tbl_size - current limit on number of characters needed
+ * to represent the unique ccl's
+ * ccltbl - holds the characters in each ccl - indexed by cclmap
+ */
+
+extern int lastccl, current_maxccls, *cclmap, *ccllen, *cclng, cclreuse;
+extern int current_max_ccl_tbl_size;
+extern Char *ccltbl;
+
+
+/* Variables for miscellaneous information:
+ * nmstr - last NAME scanned by the scanner
+ * sectnum - section number currently being parsed
+ * nummt - number of empty nxt/chk table entries
+ * hshcol - number of hash collisions detected by snstods
+ * dfaeql - number of times a newly created dfa was equal to an old one
+ * numeps - number of epsilon NFA states created
+ * eps2 - number of epsilon states which have 2 out-transitions
+ * num_reallocs - number of times it was necessary to realloc() a group
+ * of arrays
+ * tmpuses - number of DFA states that chain to templates
+ * totnst - total number of NFA states used to make DFA states
+ * peakpairs - peak number of transition pairs we had to store internally
+ * numuniq - number of unique transitions
+ * numdup - number of duplicate transitions
+ * hshsave - number of hash collisions saved by checking number of states
+ * num_backing_up - number of DFA states requiring backing up
+ * bol_needed - whether scanner needs beginning-of-line recognition
+ */
+
+extern char nmstr[MAXLINE];
+extern int sectnum, nummt, hshcol, dfaeql, numeps, eps2, num_reallocs;
+extern int tmpuses, totnst, peakpairs, numuniq, numdup, hshsave;
+extern int num_backing_up, bol_needed;
+
+void *allocate_array PROTO((int, int));
+void *reallocate_array PROTO((void*, int, int));
+
+void *flex_alloc PROTO((unsigned int));
+void *flex_realloc PROTO((void*, unsigned int));
+void flex_free PROTO((void*));
+
+#define allocate_integer_array(size) \
+ (int *) allocate_array( size, sizeof( int ) )
+
+#define reallocate_integer_array(array,size) \
+ (int *) reallocate_array( (void *) array, size, sizeof( int ) )
+
+#define allocate_int_ptr_array(size) \
+ (int **) allocate_array( size, sizeof( int * ) )
+
+#define allocate_char_ptr_array(size) \
+ (char **) allocate_array( size, sizeof( char * ) )
+
+#define allocate_dfaacc_union(size) \
+ (union dfaacc_union *) \
+ allocate_array( size, sizeof( union dfaacc_union ) )
+
+#define reallocate_int_ptr_array(array,size) \
+ (int **) reallocate_array( (void *) array, size, sizeof( int * ) )
+
+#define reallocate_char_ptr_array(array,size) \
+ (char **) reallocate_array( (void *) array, size, sizeof( char * ) )
+
+#define reallocate_dfaacc_union(array, size) \
+ (union dfaacc_union *) \
+ reallocate_array( (void *) array, size, sizeof( union dfaacc_union ) )
+
+#define allocate_character_array(size) \
+ (char *) allocate_array( size, sizeof( char ) )
+
+#define reallocate_character_array(array,size) \
+ (char *) reallocate_array( (void *) array, size, sizeof( char ) )
+
+#define allocate_Character_array(size) \
+ (Char *) allocate_array( size, sizeof( Char ) )
+
+#define reallocate_Character_array(array,size) \
+ (Char *) reallocate_array( (void *) array, size, sizeof( Char ) )
+
+
+/* Used to communicate between scanner and parser. The type should really
+ * be YYSTYPE, but we can't easily get our hands on it.
+ */
+extern int yylval;
+
+
+/* External functions that are cross-referenced among the flex source files. */
+
+
+/* from file ccl.c */
+
+extern void ccladd PROTO((int, int)); /* add a single character to a ccl */
+extern int cclinit PROTO((void)); /* make an empty ccl */
+extern void cclnegate PROTO((int)); /* negate a ccl */
+
+/* List the members of a set of characters in CCL form. */
+extern void list_character_set PROTO((FILE*, int[]));
+
+
+/* from file dfa.c */
+
+/* Increase the maximum number of dfas. */
+extern void increase_max_dfas PROTO((void));
+
+extern void ntod PROTO((void)); /* convert a ndfa to a dfa */
+
+
+/* from file ecs.c */
+
+/* Convert character classes to set of equivalence classes. */
+extern void ccl2ecl PROTO((void));
+
+/* Associate equivalence class numbers with class members. */
+extern int cre8ecs PROTO((int[], int[], int));
+
+/* Update equivalence classes based on character class transitions. */
+extern void mkeccl PROTO((Char[], int, int[], int[], int, int));
+
+/* Create equivalence class for single character. */
+extern void mkechar PROTO((int, int[], int[]));
+
+
+/* from file gen.c */
+
+extern void make_tables PROTO((void)); /* generate transition tables */
+
+
+/* from file main.c */
+
+extern void flexend PROTO((int));
+extern void usage PROTO((void));
+
+
+/* from file misc.c */
+
+/* Add the given text to the stored actions. */
+extern void add_action PROTO(( char *new_text ));
+
+/* True if a string is all lower case. */
+extern int all_lower PROTO((register char *));
+
+/* True if a string is all upper case. */
+extern int all_upper PROTO((register char *));
+
+/* Bubble sort an integer array. */
+extern void bubble PROTO((int [], int));
+
+/* Check a character to make sure it's in the expected range. */
+extern void check_char PROTO((int c));
+
+/* Shell sort a character array. */
+extern void cshell PROTO((Char [], int, int));
+
+/* Finish up a block of data declarations. */
+extern void dataend PROTO((void));
+
+/* Report an error message and terminate. */
+extern void flexerror PROTO((char[]));
+
+/* Report a fatal error message and terminate. */
+extern void flexfatal PROTO((char[]));
+
+/* Report an error message formatted with one integer argument. */
+extern void lerrif PROTO((char[], int));
+
+/* Report an error message formatted with one string argument. */
+extern void lerrsf PROTO((char[], char[]));
+
+/* Spit out a "# line" statement. */
+extern void line_directive_out PROTO((FILE*));
+
+/* Mark the current position in the action array as the end of the section 1
+ * user defs.
+ */
+extern void mark_defs1 PROTO((void));
+
+/* Mark the current position in the action array as the end of the prolog. */
+extern void mark_prolog PROTO((void));
+
+/* Generate a data statment for a two-dimensional array. */
+extern void mk2data PROTO((int));
+
+extern void mkdata PROTO((int)); /* generate a data statement */
+
+/* Return the integer represented by a string of digits. */
+extern int myctoi PROTO((char []));
+
+/* Return a printable version of the given character, which might be
+ * 8-bit.
+ */
+extern char *readable_form PROTO((int));
+
+/* Write out one section of the skeleton file. */
+extern void skelout PROTO((void));
+
+/* Output a yy_trans_info structure. */
+extern void transition_struct_out PROTO((int, int));
+
+/* Only needed when using certain broken versions of bison to build parse.c. */
+extern void *yy_flex_xmalloc PROTO(( int ));
+
+/* Set a region of memory to 0. */
+extern void zero_out PROTO((char *, int));
+
+
+/* from file nfa.c */
+
+/* Add an accepting state to a machine. */
+extern void add_accept PROTO((int, int));
+
+/* Make a given number of copies of a singleton machine. */
+extern int copysingl PROTO((int, int));
+
+/* Debugging routine to write out an nfa. */
+extern void dumpnfa PROTO((int));
+
+/* Finish up the processing for a rule. */
+extern void finish_rule PROTO((int, int, int, int));
+
+/* Connect two machines together. */
+extern int link_machines PROTO((int, int));
+
+/* Mark each "beginning" state in a machine as being a "normal" (i.e.,
+ * not trailing context associated) state.
+ */
+extern void mark_beginning_as_normal PROTO((register int));
+
+/* Make a machine that branches to two machines. */
+extern int mkbranch PROTO((int, int));
+
+extern int mkclos PROTO((int)); /* convert a machine into a closure */
+extern int mkopt PROTO((int)); /* make a machine optional */
+
+/* Make a machine that matches either one of two machines. */
+extern int mkor PROTO((int, int));
+
+/* Convert a machine into a positive closure. */
+extern int mkposcl PROTO((int));
+
+extern int mkrep PROTO((int, int, int)); /* make a replicated machine */
+
+/* Create a state with a transition on a given symbol. */
+extern int mkstate PROTO((int));
+
+extern void new_rule PROTO((void)); /* initialize for a new rule */
+
+
+/* from file parse.y */
+
+/* Write out a message formatted with one string, pinpointing its location. */
+extern void format_pinpoint_message PROTO((char[], char[]));
+
+/* Write out a message, pinpointing its location. */
+extern void pinpoint_message PROTO((char[]));
+
+/* Write out a warning, pinpointing it at the given line. */
+void line_warning PROTO(( char[], int ));
+
+/* Write out a message, pinpointing it at the given line. */
+void line_pinpoint PROTO(( char[], int ));
+
+/* Report a formatted syntax error. */
+extern void format_synerr PROTO((char [], char[]));
+extern void synerr PROTO((char [])); /* report a syntax error */
+extern void warn PROTO((char [])); /* report a warning */
+extern int yyparse PROTO((void)); /* the YACC parser */
+
+
+/* from file scan.l */
+
+/* The Flex-generated scanner for flex. */
+extern int flexscan PROTO((void));
+
+/* Open the given file (if NULL, stdin) for scanning. */
+extern void set_input_file PROTO((char*));
+
+/* Wrapup a file in the lexical analyzer. */
+extern int yywrap PROTO((void));
+
+
+/* from file sym.c */
+
+/* Save the text of a character class. */
+extern void cclinstal PROTO ((Char [], int));
+
+/* Lookup the number associated with character class. */
+extern int ccllookup PROTO((Char []));
+
+extern void ndinstal PROTO((char[], Char[])); /* install a name definition */
+/* Increase maximum number of SC's. */
+extern void scextend PROTO((void));
+extern void scinstal PROTO((char[], int)); /* make a start condition */
+
+/* Lookup the number associated with a start condition. */
+extern int sclookup PROTO((char[]));
+
+
+/* from file tblcmp.c */
+
+/* Build table entries for dfa state. */
+extern void bldtbl PROTO((int[], int, int, int, int));
+
+extern void cmptmps PROTO((void)); /* compress template table entries */
+extern void expand_nxt_chk PROTO((void)); /* increase nxt/chk arrays */
+extern void inittbl PROTO((void)); /* initialize transition tables */
+/* Make the default, "jam" table entries. */
+extern void mkdeftbl PROTO((void));
+
+/* Create table entries for a state (or state fragment) which has
+ * only one out-transition.
+ */
+extern void mk1tbl PROTO((int, int, int, int));
+
+/* Place a state into full speed transition table. */
+extern void place_state PROTO((int*, int, int));
+
+/* Save states with only one out-transition to be processed later. */
+extern void stack1 PROTO((int, int, int, int));
+
+
+/* from file yylex.c */
+
+extern int yylex PROTO((void));
diff --git a/usr.bin/lex/flexdoc.1 b/usr.bin/lex/flexdoc.1
new file mode 100644
index 000000000000..b80d5699abca
--- /dev/null
+++ b/usr.bin/lex/flexdoc.1
@@ -0,0 +1,3045 @@
+.TH FLEXDOC 1 "November 1993" "Version 2.4"
+.SH NAME
+flexdoc \- documentation for flex, fast lexical analyzer generator
+.SH SYNOPSIS
+.B flex
+.B [\-bcdfhilnpstvwBFILTV78+ \-C[aefFmr] \-Pprefix \-Sskeleton]
+.I [filename ...]
+.SH DESCRIPTION
+.I flex
+is a tool for generating
+.I scanners:
+programs which recognized lexical patterns in text.
+.I flex
+reads
+the given input files, or its standard input if no file names are given,
+for a description of a scanner to generate. The description is in
+the form of pairs
+of regular expressions and C code, called
+.I rules. flex
+generates as output a C source file,
+.B lex.yy.c,
+which defines a routine
+.B yylex().
+This file is compiled and linked with the
+.B \-lfl
+library to produce an executable. When the executable is run,
+it analyzes its input for occurrences
+of the regular expressions. Whenever it finds one, it executes
+the corresponding C code.
+.SH SOME SIMPLE EXAMPLES
+.PP
+First some simple examples to get the flavor of how one uses
+.I flex.
+The following
+.I flex
+input specifies a scanner which whenever it encounters the string
+"username" will replace it with the user's login name:
+.nf
+
+ %%
+ username printf( "%s", getlogin() );
+
+.fi
+By default, any text not matched by a
+.I flex
+scanner
+is copied to the output, so the net effect of this scanner is
+to copy its input file to its output with each occurrence
+of "username" expanded.
+In this input, there is just one rule. "username" is the
+.I pattern
+and the "printf" is the
+.I action.
+The "%%" marks the beginning of the rules.
+.PP
+Here's another simple example:
+.nf
+
+ int num_lines = 0, num_chars = 0;
+
+ %%
+ \\n ++num_lines; ++num_chars;
+ . ++num_chars;
+
+ %%
+ main()
+ {
+ yylex();
+ printf( "# of lines = %d, # of chars = %d\\n",
+ num_lines, num_chars );
+ }
+
+.fi
+This scanner counts the number of characters and the number
+of lines in its input (it produces no output other than the
+final report on the counts). The first line
+declares two globals, "num_lines" and "num_chars", which are accessible
+both inside
+.B yylex()
+and in the
+.B main()
+routine declared after the second "%%". There are two rules, one
+which matches a newline ("\\n") and increments both the line count and
+the character count, and one which matches any character other than
+a newline (indicated by the "." regular expression).
+.PP
+A somewhat more complicated example:
+.nf
+
+ /* scanner for a toy Pascal-like language */
+
+ %{
+ /* need this for the call to atof() below */
+ #include <math.h>
+ %}
+
+ DIGIT [0-9]
+ ID [a-z][a-z0-9]*
+
+ %%
+
+ {DIGIT}+ {
+ printf( "An integer: %s (%d)\\n", yytext,
+ atoi( yytext ) );
+ }
+
+ {DIGIT}+"."{DIGIT}* {
+ printf( "A float: %s (%g)\\n", yytext,
+ atof( yytext ) );
+ }
+
+ if|then|begin|end|procedure|function {
+ printf( "A keyword: %s\\n", yytext );
+ }
+
+ {ID} printf( "An identifier: %s\\n", yytext );
+
+ "+"|"-"|"*"|"/" printf( "An operator: %s\\n", yytext );
+
+ "{"[^}\\n]*"}" /* eat up one-line comments */
+
+ [ \\t\\n]+ /* eat up whitespace */
+
+ . printf( "Unrecognized character: %s\\n", yytext );
+
+ %%
+
+ main( argc, argv )
+ int argc;
+ char **argv;
+ {
+ ++argv, --argc; /* skip over program name */
+ if ( argc > 0 )
+ yyin = fopen( argv[0], "r" );
+ else
+ yyin = stdin;
+
+ yylex();
+ }
+
+.fi
+This is the beginnings of a simple scanner for a language like
+Pascal. It identifies different types of
+.I tokens
+and reports on what it has seen.
+.PP
+The details of this example will be explained in the following
+sections.
+.SH FORMAT OF THE INPUT FILE
+The
+.I flex
+input file consists of three sections, separated by a line with just
+.B %%
+in it:
+.nf
+
+ definitions
+ %%
+ rules
+ %%
+ user code
+
+.fi
+The
+.I definitions
+section contains declarations of simple
+.I name
+definitions to simplify the scanner specification, and declarations of
+.I start conditions,
+which are explained in a later section.
+.PP
+Name definitions have the form:
+.nf
+
+ name definition
+
+.fi
+The "name" is a word beginning with a letter or an underscore ('_')
+followed by zero or more letters, digits, '_', or '-' (dash).
+The definition is taken to begin at the first non-white-space character
+following the name and continuing to the end of the line.
+The definition can subsequently be referred to using "{name}", which
+will expand to "(definition)". For example,
+.nf
+
+ DIGIT [0-9]
+ ID [a-z][a-z0-9]*
+
+.fi
+defines "DIGIT" to be a regular expression which matches a
+single digit, and
+"ID" to be a regular expression which matches a letter
+followed by zero-or-more letters-or-digits.
+A subsequent reference to
+.nf
+
+ {DIGIT}+"."{DIGIT}*
+
+.fi
+is identical to
+.nf
+
+ ([0-9])+"."([0-9])*
+
+.fi
+and matches one-or-more digits followed by a '.' followed
+by zero-or-more digits.
+.PP
+The
+.I rules
+section of the
+.I flex
+input contains a series of rules of the form:
+.nf
+
+ pattern action
+
+.fi
+where the pattern must be unindented and the action must begin
+on the same line.
+.PP
+See below for a further description of patterns and actions.
+.PP
+Finally, the user code section is simply copied to
+.B lex.yy.c
+verbatim.
+It is used for companion routines which call or are called
+by the scanner. The presence of this section is optional;
+if it is missing, the second
+.B %%
+in the input file may be skipped, too.
+.PP
+In the definitions and rules sections, any
+.I indented
+text or text enclosed in
+.B %{
+and
+.B %}
+is copied verbatim to the output (with the %{}'s removed).
+The %{}'s must appear unindented on lines by themselves.
+.PP
+In the rules section,
+any indented or %{} text appearing before the
+first rule may be used to declare variables
+which are local to the scanning routine and (after the declarations)
+code which is to be executed whenever the scanning routine is entered.
+Other indented or %{} text in the rule section is still copied to the output,
+but its meaning is not well-defined and it may well cause compile-time
+errors (this feature is present for
+.I POSIX
+compliance; see below for other such features).
+.PP
+In the definitions section (but not in the rules section),
+an unindented comment (i.e., a line
+beginning with "/*") is also copied verbatim to the output up
+to the next "*/".
+.SH PATTERNS
+The patterns in the input are written using an extended set of regular
+expressions. These are:
+.nf
+
+ x match the character 'x'
+ . any character except newline
+ [xyz] a "character class"; in this case, the pattern
+ matches either an 'x', a 'y', or a 'z'
+ [abj-oZ] a "character class" with a range in it; matches
+ an 'a', a 'b', any letter from 'j' through 'o',
+ or a 'Z'
+ [^A-Z] a "negated character class", i.e., any character
+ but those in the class. In this case, any
+ character EXCEPT an uppercase letter.
+ [^A-Z\\n] any character EXCEPT an uppercase letter or
+ a newline
+ r* zero or more r's, where r is any regular expression
+ r+ one or more r's
+ r? zero or one r's (that is, "an optional r")
+ r{2,5} anywhere from two to five r's
+ r{2,} two or more r's
+ r{4} exactly 4 r's
+ {name} the expansion of the "name" definition
+ (see above)
+ "[xyz]\\"foo"
+ the literal string: [xyz]"foo
+ \\X if X is an 'a', 'b', 'f', 'n', 'r', 't', or 'v',
+ then the ANSI-C interpretation of \\x.
+ Otherwise, a literal 'X' (used to escape
+ operators such as '*')
+ \\123 the character with octal value 123
+ \\x2a the character with hexadecimal value 2a
+ (r) match an r; parentheses are used to override
+ precedence (see below)
+
+
+ rs the regular expression r followed by the
+ regular expression s; called "concatenation"
+
+
+ r|s either an r or an s
+
+
+ r/s an r but only if it is followed by an s. The
+ s is not part of the matched text. This type
+ of pattern is called as "trailing context".
+ ^r an r, but only at the beginning of a line
+ r$ an r, but only at the end of a line. Equivalent
+ to "r/\\n".
+
+
+ <s>r an r, but only in start condition s (see
+ below for discussion of start conditions)
+ <s1,s2,s3>r
+ same, but in any of start conditions s1,
+ s2, or s3
+ <*>r an r in any start condition, even an exclusive one.
+
+
+ <<EOF>> an end-of-file
+ <s1,s2><<EOF>>
+ an end-of-file when in start condition s1 or s2
+
+.fi
+Note that inside of a character class, all regular expression operators
+lose their special meaning except escape ('\\') and the character class
+operators, '-', ']', and, at the beginning of the class, '^'.
+.PP
+The regular expressions listed above are grouped according to
+precedence, from highest precedence at the top to lowest at the bottom.
+Those grouped together have equal precedence. For example,
+.nf
+
+ foo|bar*
+
+.fi
+is the same as
+.nf
+
+ (foo)|(ba(r*))
+
+.fi
+since the '*' operator has higher precedence than concatenation,
+and concatenation higher than alternation ('|'). This pattern
+therefore matches
+.I either
+the string "foo"
+.I or
+the string "ba" followed by zero-or-more r's.
+To match "foo" or zero-or-more "bar"'s, use:
+.nf
+
+ foo|(bar)*
+
+.fi
+and to match zero-or-more "foo"'s-or-"bar"'s:
+.nf
+
+ (foo|bar)*
+
+.fi
+.PP
+Some notes on patterns:
+.IP -
+A negated character class such as the example "[^A-Z]"
+above
+.I will match a newline
+unless "\\n" (or an equivalent escape sequence) is one of the
+characters explicitly present in the negated character class
+(e.g., "[^A-Z\\n]"). This is unlike how many other regular
+expression tools treat negated character classes, but unfortunately
+the inconsistency is historically entrenched.
+Matching newlines means that a pattern like [^"]* can match the entire
+input unless there's another quote in the input.
+.IP -
+A rule can have at most one instance of trailing context (the '/' operator
+or the '$' operator). The start condition, '^', and "<<EOF>>" patterns
+can only occur at the beginning of a pattern, and, as well as with '/' and '$',
+cannot be grouped inside parentheses. A '^' which does not occur at
+the beginning of a rule or a '$' which does not occur at the end of
+a rule loses its special properties and is treated as a normal character.
+.IP
+The following are illegal:
+.nf
+
+ foo/bar$
+ <sc1>foo<sc2>bar
+
+.fi
+Note that the first of these, can be written "foo/bar\\n".
+.IP
+The following will result in '$' or '^' being treated as a normal character:
+.nf
+
+ foo|(bar$)
+ foo|^bar
+
+.fi
+If what's wanted is a "foo" or a bar-followed-by-a-newline, the following
+could be used (the special '|' action is explained below):
+.nf
+
+ foo |
+ bar$ /* action goes here */
+
+.fi
+A similar trick will work for matching a foo or a
+bar-at-the-beginning-of-a-line.
+.SH HOW THE INPUT IS MATCHED
+When the generated scanner is run, it analyzes its input looking
+for strings which match any of its patterns. If it finds more than
+one match, it takes the one matching the most text (for trailing
+context rules, this includes the length of the trailing part, even
+though it will then be returned to the input). If it finds two
+or more matches of the same length, the
+rule listed first in the
+.I flex
+input file is chosen.
+.PP
+Once the match is determined, the text corresponding to the match
+(called the
+.I token)
+is made available in the global character pointer
+.B yytext,
+and its length in the global integer
+.B yyleng.
+The
+.I action
+corresponding to the matched pattern is then executed (a more
+detailed description of actions follows), and then the remaining
+input is scanned for another match.
+.PP
+If no match is found, then the
+.I default rule
+is executed: the next character in the input is considered matched and
+copied to the standard output. Thus, the simplest legal
+.I flex
+input is:
+.nf
+
+ %%
+
+.fi
+which generates a scanner that simply copies its input (one character
+at a time) to its output.
+.PP
+Note that
+.B yytext
+can be defined in two different ways: either as a character
+.I pointer
+or as a character
+.I array.
+You can control which definition
+.I flex
+uses by including one of the special directives
+.B %pointer
+or
+.B %array
+in the first (definitions) section of your flex input. The default is
+.B %pointer,
+unless you use the
+.B -l
+lex compatibility option, in which case
+.B yytext
+will be an array.
+The advantage of using
+.B %pointer
+is substantially faster scanning and no buffer overflow when matching
+very large tokens (unless you run out of dynamic memory). The disadvantage
+is that you are restricted in how your actions can modify
+.B yytext
+(see the next section), and calls to the
+.B input()
+and
+.B unput()
+functions destroy the present contents of
+.B yytext,
+which can be a considerable porting headache when moving between different
+.I lex
+versions.
+.PP
+The advantage of
+.B %array
+is that you can then modify
+.B yytext
+to your heart's content, and calls to
+.B input()
+and
+.B unput()
+do not destroy
+.B yytext
+(see below). Furthermore, existing
+.I lex
+programs sometimes access
+.B yytext
+externally using declarations of the form:
+.nf
+ extern char yytext[];
+.fi
+This definition is erroneous when used with
+.B %pointer,
+but correct for
+.B %array.
+.PP
+.B %array
+defines
+.B yytext
+to be an array of
+.B YYLMAX
+characters, which defaults to a fairly large value. You can change
+the size by simply #define'ing
+.B YYLMAX
+to a different value in the first section of your
+.I flex
+input. As mentioned above, with
+.B %pointer
+yytext grows dynamically to accomodate large tokens. While this means your
+.B %pointer
+scanner can accomodate very large tokens (such as matching entire blocks
+of comments), bear in mind that each time the scanner must resize
+.B yytext
+it also must rescan the entire token from the beginning, so matching such
+tokens can prove slow.
+.B yytext
+presently does
+.I not
+dynamically grow if a call to
+.B unput()
+results in too much text being pushed back; instead, a run-time error results.
+.PP
+Also note that you cannot use
+.B %array
+with C++ scanner classes
+(the
+.B \-+
+option; see below).
+.SH ACTIONS
+Each pattern in a rule has a corresponding action, which can be any
+arbitrary C statement. The pattern ends at the first non-escaped
+whitespace character; the remainder of the line is its action. If the
+action is empty, then when the pattern is matched the input token
+is simply discarded. For example, here is the specification for a program
+which deletes all occurrences of "zap me" from its input:
+.nf
+
+ %%
+ "zap me"
+
+.fi
+(It will copy all other characters in the input to the output since
+they will be matched by the default rule.)
+.PP
+Here is a program which compresses multiple blanks and tabs down to
+a single blank, and throws away whitespace found at the end of a line:
+.nf
+
+ %%
+ [ \\t]+ putchar( ' ' );
+ [ \\t]+$ /* ignore this token */
+
+.fi
+.PP
+If the action contains a '{', then the action spans till the balancing '}'
+is found, and the action may cross multiple lines.
+.I flex
+knows about C strings and comments and won't be fooled by braces found
+within them, but also allows actions to begin with
+.B %{
+and will consider the action to be all the text up to the next
+.B %}
+(regardless of ordinary braces inside the action).
+.PP
+An action consisting solely of a vertical bar ('|') means "same as
+the action for the next rule." See below for an illustration.
+.PP
+Actions can include arbitrary C code, including
+.B return
+statements to return a value to whatever routine called
+.B yylex().
+Each time
+.B yylex()
+is called it continues processing tokens from where it last left
+off until it either reaches
+the end of the file or executes a return.
+.PP
+Actions are free to modify
+.B yytext
+except for lengthening it (adding
+characters to its end--these will overwrite later characters in the
+input stream). Modifying the final character of yytext may alter
+whether when scanning resumes rules anchored with '^' are active.
+Specifically, changing the final character of yytext to a newline will
+activate such rules on the next scan, and changing it to anything else
+will deactivate the rules. Users should not rely on this behavior being
+present in future releases. Finally, note that none of this paragraph
+applies when using
+.B %array
+(see above).
+.PP
+Actions are free to modify
+.B yyleng
+except they should not do so if the action also includes use of
+.B yymore()
+(see below).
+.PP
+There are a number of special directives which can be included within
+an action:
+.IP -
+.B ECHO
+copies yytext to the scanner's output.
+.IP -
+.B BEGIN
+followed by the name of a start condition places the scanner in the
+corresponding start condition (see below).
+.IP -
+.B REJECT
+directs the scanner to proceed on to the "second best" rule which matched the
+input (or a prefix of the input). The rule is chosen as described
+above in "How the Input is Matched", and
+.B yytext
+and
+.B yyleng
+set up appropriately.
+It may either be one which matched as much text
+as the originally chosen rule but came later in the
+.I flex
+input file, or one which matched less text.
+For example, the following will both count the
+words in the input and call the routine special() whenever "frob" is seen:
+.nf
+
+ int word_count = 0;
+ %%
+
+ frob special(); REJECT;
+ [^ \\t\\n]+ ++word_count;
+
+.fi
+Without the
+.B REJECT,
+any "frob"'s in the input would not be counted as words, since the
+scanner normally executes only one action per token.
+Multiple
+.B REJECT's
+are allowed, each one finding the next best choice to the currently
+active rule. For example, when the following scanner scans the token
+"abcd", it will write "abcdabcaba" to the output:
+.nf
+
+ %%
+ a |
+ ab |
+ abc |
+ abcd ECHO; REJECT;
+ .|\\n /* eat up any unmatched character */
+
+.fi
+(The first three rules share the fourth's action since they use
+the special '|' action.)
+.B REJECT
+is a particularly expensive feature in terms scanner performance;
+if it is used in
+.I any
+of the scanner's actions it will slow down
+.I all
+of the scanner's matching. Furthermore,
+.B REJECT
+cannot be used with the
+.I -Cf
+or
+.I -CF
+options (see below).
+.IP
+Note also that unlike the other special actions,
+.B REJECT
+is a
+.I branch;
+code immediately following it in the action will
+.I not
+be executed.
+.IP -
+.B yymore()
+tells the scanner that the next time it matches a rule, the corresponding
+token should be
+.I appended
+onto the current value of
+.B yytext
+rather than replacing it. For example, given the input "mega-kludge"
+the following will write "mega-mega-kludge" to the output:
+.nf
+
+ %%
+ mega- ECHO; yymore();
+ kludge ECHO;
+
+.fi
+First "mega-" is matched and echoed to the output. Then "kludge"
+is matched, but the previous "mega-" is still hanging around at the
+beginning of
+.B yytext
+so the
+.B ECHO
+for the "kludge" rule will actually write "mega-kludge".
+The presence of
+.B yymore()
+in the scanner's action entails a minor performance penalty in the
+scanner's matching speed.
+.IP -
+.B yyless(n)
+returns all but the first
+.I n
+characters of the current token back to the input stream, where they
+will be rescanned when the scanner looks for the next match.
+.B yytext
+and
+.B yyleng
+are adjusted appropriately (e.g.,
+.B yyleng
+will now be equal to
+.I n
+). For example, on the input "foobar" the following will write out
+"foobarbar":
+.nf
+
+ %%
+ foobar ECHO; yyless(3);
+ [a-z]+ ECHO;
+
+.fi
+An argument of 0 to
+.B yyless
+will cause the entire current input string to be scanned again. Unless you've
+changed how the scanner will subsequently process its input (using
+.B BEGIN,
+for example), this will result in an endless loop.
+.PP
+Note that
+.B yyless
+is a macro and can only be used in the flex input file, not from
+other source files.
+.IP -
+.B unput(c)
+puts the character
+.I c
+back onto the input stream. It will be the next character scanned.
+The following action will take the current token and cause it
+to be rescanned enclosed in parentheses.
+.nf
+
+ {
+ int i;
+ unput( ')' );
+ for ( i = yyleng - 1; i >= 0; --i )
+ unput( yytext[i] );
+ unput( '(' );
+ }
+
+.fi
+Note that since each
+.B unput()
+puts the given character back at the
+.I beginning
+of the input stream, pushing back strings must be done back-to-front.
+Also note that you cannot put back
+.B EOF
+to attempt to mark the input stream with an end-of-file.
+.IP -
+.B input()
+reads the next character from the input stream. For example,
+the following is one way to eat up C comments:
+.nf
+
+ %%
+ "/*" {
+ register int c;
+
+ for ( ; ; )
+ {
+ while ( (c = input()) != '*' &&
+ c != EOF )
+ ; /* eat up text of comment */
+
+ if ( c == '*' )
+ {
+ while ( (c = input()) == '*' )
+ ;
+ if ( c == '/' )
+ break; /* found the end */
+ }
+
+ if ( c == EOF )
+ {
+ error( "EOF in comment" );
+ break;
+ }
+ }
+ }
+
+.fi
+(Note that if the scanner is compiled using
+.B C++,
+then
+.B input()
+is instead referred to as
+.B yyinput(),
+in order to avoid a name clash with the
+.B C++
+stream by the name of
+.I input.)
+.IP -
+.B yyterminate()
+can be used in lieu of a return statement in an action. It terminates
+the scanner and returns a 0 to the scanner's caller, indicating "all done".
+By default,
+.B yyterminate()
+is also called when an end-of-file is encountered. It is a macro and
+may be redefined.
+.SH THE GENERATED SCANNER
+The output of
+.I flex
+is the file
+.B lex.yy.c,
+which contains the scanning routine
+.B yylex(),
+a number of tables used by it for matching tokens, and a number
+of auxiliary routines and macros. By default,
+.B yylex()
+is declared as follows:
+.nf
+
+ int yylex()
+ {
+ ... various definitions and the actions in here ...
+ }
+
+.fi
+(If your environment supports function prototypes, then it will
+be "int yylex( void )".) This definition may be changed by defining
+the "YY_DECL" macro. For example, you could use:
+.nf
+
+ #define YY_DECL float lexscan( a, b ) float a, b;
+
+.fi
+to give the scanning routine the name
+.I lexscan,
+returning a float, and taking two floats as arguments. Note that
+if you give arguments to the scanning routine using a
+K&R-style/non-prototyped function declaration, you must terminate
+the definition with a semi-colon (;).
+.PP
+Whenever
+.B yylex()
+is called, it scans tokens from the global input file
+.I yyin
+(which defaults to stdin). It continues until it either reaches
+an end-of-file (at which point it returns the value 0) or
+one of its actions executes a
+.I return
+statement.
+.PP
+If the scanner reaches an end-of-file, subsequent calls are undefined
+unless either
+.I yyin
+is pointed at a new input file (in which case scanning continues from
+that file), or
+.B yyrestart()
+is called.
+.B yyrestart()
+takes one argument, a
+.B FILE *
+pointer, and initializes
+.I yyin
+for scanning from that file. Essentially there is no difference between
+just assigning
+.I yyin
+to a new input file or using
+.B yyrestart()
+to do so; the latter is available for compatibility with previous versions
+of
+.I flex,
+and because it can be used to switch input files in the middle of scanning.
+It can also be used to throw away the current input buffer, by calling
+it with an argument of
+.I yyin.
+.PP
+If
+.B yylex()
+stops scanning due to executing a
+.I return
+statement in one of the actions, the scanner may then be called again and it
+will resume scanning where it left off.
+.PP
+By default (and for purposes of efficiency), the scanner uses
+block-reads rather than simple
+.I getc()
+calls to read characters from
+.I yyin.
+The nature of how it gets its input can be controlled by defining the
+.B YY_INPUT
+macro.
+YY_INPUT's calling sequence is "YY_INPUT(buf,result,max_size)". Its
+action is to place up to
+.I max_size
+characters in the character array
+.I buf
+and return in the integer variable
+.I result
+either the
+number of characters read or the constant YY_NULL (0 on Unix systems)
+to indicate EOF. The default YY_INPUT reads from the
+global file-pointer "yyin".
+.PP
+A sample definition of YY_INPUT (in the definitions
+section of the input file):
+.nf
+
+ %{
+ #define YY_INPUT(buf,result,max_size) \\
+ { \\
+ int c = getchar(); \\
+ result = (c == EOF) ? YY_NULL : (buf[0] = c, 1); \\
+ }
+ %}
+
+.fi
+This definition will change the input processing to occur
+one character at a time.
+.PP
+You also can add in things like keeping track of the
+input line number this way; but don't expect your scanner to
+go very fast.
+.PP
+When the scanner receives an end-of-file indication from YY_INPUT,
+it then checks the
+.B yywrap()
+function. If
+.B yywrap()
+returns false (zero), then it is assumed that the
+function has gone ahead and set up
+.I yyin
+to point to another input file, and scanning continues. If it returns
+true (non-zero), then the scanner terminates, returning 0 to its
+caller.
+.PP
+The default
+.B yywrap()
+always returns 1.
+.PP
+The scanner writes its
+.B ECHO
+output to the
+.I yyout
+global (default, stdout), which may be redefined by the user simply
+by assigning it to some other
+.B FILE
+pointer.
+.SH START CONDITIONS
+.I flex
+provides a mechanism for conditionally activating rules. Any rule
+whose pattern is prefixed with "<sc>" will only be active when
+the scanner is in the start condition named "sc". For example,
+.nf
+
+ <STRING>[^"]* { /* eat up the string body ... */
+ ...
+ }
+
+.fi
+will be active only when the scanner is in the "STRING" start
+condition, and
+.nf
+
+ <INITIAL,STRING,QUOTE>\\. { /* handle an escape ... */
+ ...
+ }
+
+.fi
+will be active only when the current start condition is
+either "INITIAL", "STRING", or "QUOTE".
+.PP
+Start conditions
+are declared in the definitions (first) section of the input
+using unindented lines beginning with either
+.B %s
+or
+.B %x
+followed by a list of names.
+The former declares
+.I inclusive
+start conditions, the latter
+.I exclusive
+start conditions. A start condition is activated using the
+.B BEGIN
+action. Until the next
+.B BEGIN
+action is executed, rules with the given start
+condition will be active and
+rules with other start conditions will be inactive.
+If the start condition is
+.I inclusive,
+then rules with no start conditions at all will also be active.
+If it is
+.I exclusive,
+then
+.I only
+rules qualified with the start condition will be active.
+A set of rules contingent on the same exclusive start condition
+describe a scanner which is independent of any of the other rules in the
+.I flex
+input. Because of this,
+exclusive start conditions make it easy to specify "mini-scanners"
+which scan portions of the input that are syntactically different
+from the rest (e.g., comments).
+.PP
+If the distinction between inclusive and exclusive start conditions
+is still a little vague, here's a simple example illustrating the
+connection between the two. The set of rules:
+.nf
+
+ %s example
+ %%
+ <example>foo /* do something */
+
+.fi
+is equivalent to
+.nf
+
+ %x example
+ %%
+ <INITIAL,example>foo /* do something */
+
+.fi
+.PP
+Also note that the special start-condition specifier
+.B <*>
+matches every start condition. Thus, the above example could also
+have been written;
+.nf
+
+ %x example
+ %%
+ <*>foo /* do something */
+
+.fi
+.PP
+The default rule (to
+.B ECHO
+any unmatched character) remains active in start conditions.
+.PP
+.B BEGIN(0)
+returns to the original state where only the rules with
+no start conditions are active. This state can also be
+referred to as the start-condition "INITIAL", so
+.B BEGIN(INITIAL)
+is equivalent to
+.B BEGIN(0).
+(The parentheses around the start condition name are not required but
+are considered good style.)
+.PP
+.B BEGIN
+actions can also be given as indented code at the beginning
+of the rules section. For example, the following will cause
+the scanner to enter the "SPECIAL" start condition whenever
+.I yylex()
+is called and the global variable
+.I enter_special
+is true:
+.nf
+
+ int enter_special;
+
+ %x SPECIAL
+ %%
+ if ( enter_special )
+ BEGIN(SPECIAL);
+
+ <SPECIAL>blahblahblah
+ ...more rules follow...
+
+.fi
+.PP
+To illustrate the uses of start conditions,
+here is a scanner which provides two different interpretations
+of a string like "123.456". By default it will treat it as
+as three tokens, the integer "123", a dot ('.'), and the integer "456".
+But if the string is preceded earlier in the line by the string
+"expect-floats"
+it will treat it as a single token, the floating-point number
+123.456:
+.nf
+
+ %{
+ #include <math.h>
+ %}
+ %s expect
+
+ %%
+ expect-floats BEGIN(expect);
+
+ <expect>[0-9]+"."[0-9]+ {
+ printf( "found a float, = %f\\n",
+ atof( yytext ) );
+ }
+ <expect>\\n {
+ /* that's the end of the line, so
+ * we need another "expect-number"
+ * before we'll recognize any more
+ * numbers
+ */
+ BEGIN(INITIAL);
+ }
+
+ [0-9]+ {
+ printf( "found an integer, = %d\\n",
+ atoi( yytext ) );
+ }
+
+ "." printf( "found a dot\\n" );
+
+.fi
+Here is a scanner which recognizes (and discards) C comments while
+maintaining a count of the current input line.
+.nf
+
+ %x comment
+ %%
+ int line_num = 1;
+
+ "/*" BEGIN(comment);
+
+ <comment>[^*\\n]* /* eat anything that's not a '*' */
+ <comment>"*"+[^*/\\n]* /* eat up '*'s not followed by '/'s */
+ <comment>\\n ++line_num;
+ <comment>"*"+"/" BEGIN(INITIAL);
+
+.fi
+This scanner goes to a bit of trouble to match as much
+text as possible with each rule. In general, when attempting to write
+a high-speed scanner try to match as much possible in each rule, as
+it's a big win.
+.PP
+Note that start-conditions names are really integer values and
+can be stored as such. Thus, the above could be extended in the
+following fashion:
+.nf
+
+ %x comment foo
+ %%
+ int line_num = 1;
+ int comment_caller;
+
+ "/*" {
+ comment_caller = INITIAL;
+ BEGIN(comment);
+ }
+
+ ...
+
+ <foo>"/*" {
+ comment_caller = foo;
+ BEGIN(comment);
+ }
+
+ <comment>[^*\\n]* /* eat anything that's not a '*' */
+ <comment>"*"+[^*/\\n]* /* eat up '*'s not followed by '/'s */
+ <comment>\\n ++line_num;
+ <comment>"*"+"/" BEGIN(comment_caller);
+
+.fi
+Furthermore, you can access the current start condition using
+the integer-valued
+.B YY_START
+macro. For example, the above assignments to
+.I comment_caller
+could instead be written
+.nf
+
+ comment_caller = YY_START;
+.fi
+.PP
+Note that start conditions do not have their own name-space; %s's and %x's
+declare names in the same fashion as #define's.
+.PP
+Finally, here's an example of how to match C-style quoted strings using
+exclusive start conditions, including expanded escape sequences (but
+not including checking for a string that's too long):
+.nf
+
+ %x str
+
+ %%
+ char string_buf[MAX_STR_CONST];
+ char *string_buf_ptr;
+
+
+ \\" string_buf_ptr = string_buf; BEGIN(str);
+
+ <str>\\" { /* saw closing quote - all done */
+ BEGIN(INITIAL);
+ *string_buf_ptr = '\\0';
+ /* return string constant token type and
+ * value to parser
+ */
+ }
+
+ <str>\\n {
+ /* error - unterminated string constant */
+ /* generate error message */
+ }
+
+ <str>\\\\[0-7]{1,3} {
+ /* octal escape sequence */
+ int result;
+
+ (void) sscanf( yytext + 1, "%o", &result );
+
+ if ( result > 0xff )
+ /* error, constant is out-of-bounds */
+
+ *string_buf_ptr++ = result;
+ }
+
+ <str>\\\\[0-9]+ {
+ /* generate error - bad escape sequence; something
+ * like '\\48' or '\\0777777'
+ */
+ }
+
+ <str>\\\\n *string_buf_ptr++ = '\\n';
+ <str>\\\\t *string_buf_ptr++ = '\\t';
+ <str>\\\\r *string_buf_ptr++ = '\\r';
+ <str>\\\\b *string_buf_ptr++ = '\\b';
+ <str>\\\\f *string_buf_ptr++ = '\\f';
+
+ <str>\\\\(.|\\n) *string_buf_ptr++ = yytext[1];
+
+ <str>[^\\\\\\n\\"]+ {
+ char *yytext_ptr = yytext;
+
+ while ( *yytext_ptr )
+ *string_buf_ptr++ = *yytext_ptr++;
+ }
+
+.fi
+.SH MULTIPLE INPUT BUFFERS
+Some scanners (such as those which support "include" files)
+require reading from several input streams. As
+.I flex
+scanners do a large amount of buffering, one cannot control
+where the next input will be read from by simply writing a
+.B YY_INPUT
+which is sensitive to the scanning context.
+.B YY_INPUT
+is only called when the scanner reaches the end of its buffer, which
+may be a long time after scanning a statement such as an "include"
+which requires switching the input source.
+.PP
+To negotiate these sorts of problems,
+.I flex
+provides a mechanism for creating and switching between multiple
+input buffers. An input buffer is created by using:
+.nf
+
+ YY_BUFFER_STATE yy_create_buffer( FILE *file, int size )
+
+.fi
+which takes a
+.I FILE
+pointer and a size and creates a buffer associated with the given
+file and large enough to hold
+.I size
+characters (when in doubt, use
+.B YY_BUF_SIZE
+for the size). It returns a
+.B YY_BUFFER_STATE
+handle, which may then be passed to other routines:
+.nf
+
+ void yy_switch_to_buffer( YY_BUFFER_STATE new_buffer )
+
+.fi
+switches the scanner's input buffer so subsequent tokens will
+come from
+.I new_buffer.
+Note that
+.B yy_switch_to_buffer()
+may be used by yywrap() to set things up for continued scanning, instead
+of opening a new file and pointing
+.I yyin
+at it.
+.nf
+
+ void yy_delete_buffer( YY_BUFFER_STATE buffer )
+
+.fi
+is used to reclaim the storage associated with a buffer.
+.PP
+.B yy_new_buffer()
+is an alias for
+.B yy_create_buffer(),
+provided for compatibility with the C++ use of
+.I new
+and
+.I delete
+for creating and destroying dynamic objects.
+.PP
+Finally, the
+.B YY_CURRENT_BUFFER
+macro returns a
+.B YY_BUFFER_STATE
+handle to the current buffer.
+.PP
+Here is an example of using these features for writing a scanner
+which expands include files (the
+.B <<EOF>>
+feature is discussed below):
+.nf
+
+ /* the "incl" state is used for picking up the name
+ * of an include file
+ */
+ %x incl
+
+ %{
+ #define MAX_INCLUDE_DEPTH 10
+ YY_BUFFER_STATE include_stack[MAX_INCLUDE_DEPTH];
+ int include_stack_ptr = 0;
+ %}
+
+ %%
+ include BEGIN(incl);
+
+ [a-z]+ ECHO;
+ [^a-z\\n]*\\n? ECHO;
+
+ <incl>[ \\t]* /* eat the whitespace */
+ <incl>[^ \\t\\n]+ { /* got the include file name */
+ if ( include_stack_ptr >= MAX_INCLUDE_DEPTH )
+ {
+ fprintf( stderr, "Includes nested too deeply" );
+ exit( 1 );
+ }
+
+ include_stack[include_stack_ptr++] =
+ YY_CURRENT_BUFFER;
+
+ yyin = fopen( yytext, "r" );
+
+ if ( ! yyin )
+ error( ... );
+
+ yy_switch_to_buffer(
+ yy_create_buffer( yyin, YY_BUF_SIZE ) );
+
+ BEGIN(INITIAL);
+ }
+
+ <<EOF>> {
+ if ( --include_stack_ptr < 0 )
+ {
+ yyterminate();
+ }
+
+ else
+ {
+ yy_delete_buffer( YY_CURRENT_BUFFER );
+ yy_switch_to_buffer(
+ include_stack[include_stack_ptr] );
+ }
+ }
+
+.fi
+.SH END-OF-FILE RULES
+The special rule "<<EOF>>" indicates
+actions which are to be taken when an end-of-file is
+encountered and yywrap() returns non-zero (i.e., indicates
+no further files to process). The action must finish
+by doing one of four things:
+.IP -
+assigning
+.I yyin
+to a new input file (in previous versions of flex, after doing the
+assignment you had to call the special action
+.B YY_NEW_FILE;
+this is no longer necessary);
+.IP -
+executing a
+.I return
+statement;
+.IP -
+executing the special
+.B yyterminate()
+action;
+.IP -
+or, switching to a new buffer using
+.B yy_switch_to_buffer()
+as shown in the example above.
+.PP
+<<EOF>> rules may not be used with other
+patterns; they may only be qualified with a list of start
+conditions. If an unqualified <<EOF>> rule is given, it
+applies to
+.I all
+start conditions which do not already have <<EOF>> actions. To
+specify an <<EOF>> rule for only the initial start condition, use
+.nf
+
+ <INITIAL><<EOF>>
+
+.fi
+.PP
+These rules are useful for catching things like unclosed comments.
+An example:
+.nf
+
+ %x quote
+ %%
+
+ ...other rules for dealing with quotes...
+
+ <quote><<EOF>> {
+ error( "unterminated quote" );
+ yyterminate();
+ }
+ <<EOF>> {
+ if ( *++filelist )
+ yyin = fopen( *filelist, "r" );
+ else
+ yyterminate();
+ }
+
+.fi
+.SH MISCELLANEOUS MACROS
+The macro
+.bd
+YY_USER_ACTION
+can be defined to provide an action
+which is always executed prior to the matched rule's action. For example,
+it could be #define'd to call a routine to convert yytext to lower-case.
+.PP
+The macro
+.B YY_USER_INIT
+may be defined to provide an action which is always executed before
+the first scan (and before the scanner's internal initializations are done).
+For example, it could be used to call a routine to read
+in a data table or open a logging file.
+.PP
+In the generated scanner, the actions are all gathered in one large
+switch statement and separated using
+.B YY_BREAK,
+which may be redefined. By default, it is simply a "break", to separate
+each rule's action from the following rule's.
+Redefining
+.B YY_BREAK
+allows, for example, C++ users to
+#define YY_BREAK to do nothing (while being very careful that every
+rule ends with a "break" or a "return"!) to avoid suffering from
+unreachable statement warnings where because a rule's action ends with
+"return", the
+.B YY_BREAK
+is inaccessible.
+.SH INTERFACING WITH YACC
+One of the main uses of
+.I flex
+is as a companion to the
+.I yacc
+parser-generator.
+.I yacc
+parsers expect to call a routine named
+.B yylex()
+to find the next input token. The routine is supposed to
+return the type of the next token as well as putting any associated
+value in the global
+.B yylval.
+To use
+.I flex
+with
+.I yacc,
+one specifies the
+.B \-d
+option to
+.I yacc
+to instruct it to generate the file
+.B y.tab.h
+containing definitions of all the
+.B %tokens
+appearing in the
+.I yacc
+input. This file is then included in the
+.I flex
+scanner. For example, if one of the tokens is "TOK_NUMBER",
+part of the scanner might look like:
+.nf
+
+ %{
+ #include "y.tab.h"
+ %}
+
+ %%
+
+ [0-9]+ yylval = atoi( yytext ); return TOK_NUMBER;
+
+.fi
+.SH OPTIONS
+.I flex
+has the following options:
+.TP
+.B \-b
+Generate backing-up information to
+.I lex.backup.
+This is a list of scanner states which require backing up
+and the input characters on which they do so. By adding rules one
+can remove backing-up states. If all backing-up states
+are eliminated and
+.B \-Cf
+or
+.B \-CF
+is used, the generated scanner will run faster (see the
+.B \-p
+flag). Only users who wish to squeeze every last cycle out of their
+scanners need worry about this option. (See the section on Performance
+Considerations below.)
+.TP
+.B \-c
+is a do-nothing, deprecated option included for POSIX compliance.
+.IP
+.B NOTE:
+in previous releases of
+.I flex
+.B \-c
+specified table-compression options. This functionality is
+now given by the
+.B \-C
+flag. To ease the the impact of this change, when
+.I flex
+encounters
+.B \-c,
+it currently issues a warning message and assumes that
+.B \-C
+was desired instead. In the future this "promotion" of
+.B \-c
+to
+.B \-C
+will go away in the name of full POSIX compliance (unless
+the POSIX meaning is removed first).
+.TP
+.B \-d
+makes the generated scanner run in
+.I debug
+mode. Whenever a pattern is recognized and the global
+.B yy_flex_debug
+is non-zero (which is the default),
+the scanner will write to
+.I stderr
+a line of the form:
+.nf
+
+ --accepting rule at line 53 ("the matched text")
+
+.fi
+The line number refers to the location of the rule in the file
+defining the scanner (i.e., the file that was fed to flex). Messages
+are also generated when the scanner backs up, accepts the
+default rule, reaches the end of its input buffer (or encounters
+a NUL; at this point, the two look the same as far as the scanner's concerned),
+or reaches an end-of-file.
+.TP
+.B \-f
+specifies
+.I fast scanner.
+No table compression is done and stdio is bypassed.
+The result is large but fast. This option is equivalent to
+.B \-Cfr
+(see below).
+.TP
+.B \-h
+generates a "help" summary of
+.I flex's
+options to
+.I stderr
+and then exits.
+.TP
+.B \-i
+instructs
+.I flex
+to generate a
+.I case-insensitive
+scanner. The case of letters given in the
+.I flex
+input patterns will
+be ignored, and tokens in the input will be matched regardless of case. The
+matched text given in
+.I yytext
+will have the preserved case (i.e., it will not be folded).
+.TP
+.B \-l
+turns on maximum compatibility with the original AT&T
+.I lex
+implementation. Note that this does not mean
+.I full
+compatibility. Use of this option costs a considerable amount of
+performance, and it cannot be used with the
+.B \-+, -f, -F, -Cf,
+or
+.B -CF
+options. For details on the compatibilities it provides, see the section
+"Incompatibilities With Lex And POSIX" below.
+.TP
+.B \-n
+is another do-nothing, deprecated option included only for
+POSIX compliance.
+.TP
+.B \-p
+generates a performance report to stderr. The report
+consists of comments regarding features of the
+.I flex
+input file which will cause a serious loss of performance in the resulting
+scanner. If you give the flag twice, you will also get comments regarding
+features that lead to minor performance losses.
+.IP
+Note that the use of
+.B REJECT
+and variable trailing context (see the Bugs section in flex(1))
+entails a substantial performance penalty; use of
+.I yymore(),
+the
+.B ^
+operator,
+and the
+.B \-I
+flag entail minor performance penalties.
+.TP
+.B \-s
+causes the
+.I default rule
+(that unmatched scanner input is echoed to
+.I stdout)
+to be suppressed. If the scanner encounters input that does not
+match any of its rules, it aborts with an error. This option is
+useful for finding holes in a scanner's rule set.
+.TP
+.B \-t
+instructs
+.I flex
+to write the scanner it generates to standard output instead
+of
+.B lex.yy.c.
+.TP
+.B \-v
+specifies that
+.I flex
+should write to
+.I stderr
+a summary of statistics regarding the scanner it generates.
+Most of the statistics are meaningless to the casual
+.I flex
+user, but the first line identifies the version of
+.I flex
+(same as reported by
+.B \-V),
+and the next line the flags used when generating the scanner, including
+those that are on by default.
+.TP
+.B \-w
+suppresses warning messages.
+.TP
+.B \-B
+instructs
+.I flex
+to generate a
+.I batch
+scanner, the opposite of
+.I interactive
+scanners generated by
+.B \-I
+(see below). In general, you use
+.B \-B
+when you are
+.I certain
+that your scanner will never be used interactively, and you want to
+squeeze a
+.I little
+more performance out of it. If your goal is instead to squeeze out a
+.I lot
+more performance, you should be using the
+.B \-Cf
+or
+.B \-CF
+options (discussed below), which turn on
+.B \-B
+automatically anyway.
+.TP
+.B \-F
+specifies that the
+.ul
+fast
+scanner table representation should be used (and stdio
+bypassed). This representation is
+about as fast as the full table representation
+.B (-f),
+and for some sets of patterns will be considerably smaller (and for
+others, larger). In general, if the pattern set contains both "keywords"
+and a catch-all, "identifier" rule, such as in the set:
+.nf
+
+ "case" return TOK_CASE;
+ "switch" return TOK_SWITCH;
+ ...
+ "default" return TOK_DEFAULT;
+ [a-z]+ return TOK_ID;
+
+.fi
+then you're better off using the full table representation. If only
+the "identifier" rule is present and you then use a hash table or some such
+to detect the keywords, you're better off using
+.B -F.
+.IP
+This option is equivalent to
+.B \-CFr
+(see below). It cannot be used with
+.B \-+.
+.TP
+.B \-I
+instructs
+.I flex
+to generate an
+.I interactive
+scanner. An interactive scanner is one that only looks ahead to decide
+what token has been matched if it absolutely must. It turns out that
+always looking one extra character ahead, even if the scanner has already
+seen enough text to disambiguate the current token, is a bit faster than
+only looking ahead when necessary. But scanners that always look ahead
+give dreadful interactive performance; for example, when a user types
+a newline, it is not recognized as a newline token until they enter
+.I another
+token, which often means typing in another whole line.
+.IP
+.I Flex
+scanners default to
+.I interactive
+unless you use the
+.B \-Cf
+or
+.B \-CF
+table-compression options (see below). That's because if you're looking
+for high-performance you should be using one of these options, so if you
+didn't,
+.I flex
+assumes you'd rather trade off a bit of run-time performance for intuitive
+interactive behavior. Note also that you
+.I cannot
+use
+.B \-I
+in conjunction with
+.B \-Cf
+or
+.B \-CF.
+Thus, this option is not really needed; it is on by default for all those
+cases in which it is allowed.
+.IP
+You can force a scanner to
+.I not
+be interactive by using
+.B \-B
+(see above).
+.TP
+.B \-L
+instructs
+.I flex
+not to generate
+.B #line
+directives. Without this option,
+.I flex
+peppers the generated scanner
+with #line directives so error messages in the actions will be correctly
+located with respect to the original
+.I flex
+input file, and not to
+the fairly meaningless line numbers of
+.B lex.yy.c.
+(Unfortunately
+.I flex
+does not presently generate the necessary directives
+to "retarget" the line numbers for those parts of
+.B lex.yy.c
+which it generated. So if there is an error in the generated code,
+a meaningless line number is reported.)
+.TP
+.B \-T
+makes
+.I flex
+run in
+.I trace
+mode. It will generate a lot of messages to
+.I stderr
+concerning
+the form of the input and the resultant non-deterministic and deterministic
+finite automata. This option is mostly for use in maintaining
+.I flex.
+.TP
+.B \-V
+prints the version number to
+.I stderr
+and exits.
+.TP
+.B \-7
+instructs
+.I flex
+to generate a 7-bit scanner, i.e., one which can only recognized 7-bit
+characters in its input. The advantage of using
+.B \-7
+is that the scanner's tables can be up to half the size of those generated
+using the
+.B \-8
+option (see below). The disadvantage is that such scanners often hang
+or crash if their input contains an 8-bit character.
+.IP
+Note, however, that unless you generate your scanner using the
+.B \-Cf
+or
+.B \-CF
+table compression options, use of
+.B \-7
+will save only a small amount of table space, and make your scanner
+considerably less portable.
+.I Flex's
+default behavior is to generate an 8-bit scanner unless you use the
+.B \-Cf
+or
+.B \-CF,
+in which case
+.I flex
+defaults to generating 7-bit scanners unless your site was always
+configured to generate 8-bit scanners (as will often be the case
+with non-USA sites). You can tell whether flex generated a 7-bit
+or an 8-bit scanner by inspecting the flag summary in the
+.B \-v
+output as described above.
+.IP
+Note that if you use
+.B \-Cfe
+or
+.B \-CFe
+(those table compression options, but also using equivalence classes as
+discussed see below), flex still defaults to generating an 8-bit
+scanner, since usually with these compression options full 8-bit tables
+are not much more expensive than 7-bit tables.
+.TP
+.B \-8
+instructs
+.I flex
+to generate an 8-bit scanner, i.e., one which can recognize 8-bit
+characters. This flag is only needed for scanners generated using
+.B \-Cf
+or
+.B \-CF,
+as otherwise flex defaults to generating an 8-bit scanner anyway.
+.IP
+See the discussion of
+.B \-7
+above for flex's default behavior and the tradeoffs between 7-bit
+and 8-bit scanners.
+.TP
+.B \-+
+specifies that you want flex to generate a C++
+scanner class. See the section on Generating C++ Scanners below for
+details.
+.TP
+.B \-C[aefFmr]
+controls the degree of table compression and, more generally, trade-offs
+between small scanners and fast scanners.
+.IP
+.B \-Ca
+("align") instructs flex to trade off larger tables in the
+generated scanner for faster performance because the elements of
+the tables are better aligned for memory access and computation. On some
+RISC architectures, fetching and manipulating longwords is more efficient
+than with smaller-sized datums such as shortwords. This option can
+double the size of the tables used by your scanner.
+.IP
+.B \-Ce
+directs
+.I flex
+to construct
+.I equivalence classes,
+i.e., sets of characters
+which have identical lexical properties (for example, if the only
+appearance of digits in the
+.I flex
+input is in the character class
+"[0-9]" then the digits '0', '1', ..., '9' will all be put
+in the same equivalence class). Equivalence classes usually give
+dramatic reductions in the final table/object file sizes (typically
+a factor of 2-5) and are pretty cheap performance-wise (one array
+look-up per character scanned).
+.IP
+.B \-Cf
+specifies that the
+.I full
+scanner tables should be generated -
+.I flex
+should not compress the
+tables by taking advantages of similar transition functions for
+different states.
+.IP
+.B \-CF
+specifies that the alternate fast scanner representation (described
+above under the
+.B \-F
+flag)
+should be used. This option cannot be used with
+.B \-+.
+.IP
+.B \-Cm
+directs
+.I flex
+to construct
+.I meta-equivalence classes,
+which are sets of equivalence classes (or characters, if equivalence
+classes are not being used) that are commonly used together. Meta-equivalence
+classes are often a big win when using compressed tables, but they
+have a moderate performance impact (one or two "if" tests and one
+array look-up per character scanned).
+.IP
+.B \-Cr
+causes the generated scanner to
+.I bypass
+use of the standard I/O library (stdio) for input. Instead of calling
+.B fread()
+or
+.B getc(),
+the scanner will use the
+.B read()
+system call, resulting in a performance gain which varies from system
+to system, but in general is probably negligible unless you are also using
+.B \-Cf
+or
+.B \-CF.
+Using
+.B \-Cr
+can cause strange behavior if, for example, you read from
+.I yyin
+using stdio prior to calling the scanner (because the scanner will miss
+whatever text your previous reads left in the stdio input buffer).
+.IP
+.B \-Cr
+has no effect if you define
+.B YY_INPUT
+(see The Generated Scanner above).
+.IP
+A lone
+.B \-C
+specifies that the scanner tables should be compressed but neither
+equivalence classes nor meta-equivalence classes should be used.
+.IP
+The options
+.B \-Cf
+or
+.B \-CF
+and
+.B \-Cm
+do not make sense together - there is no opportunity for meta-equivalence
+classes if the table is not being compressed. Otherwise the options
+may be freely mixed, and are cumulative.
+.IP
+The default setting is
+.B \-Cem,
+which specifies that
+.I flex
+should generate equivalence classes
+and meta-equivalence classes. This setting provides the highest
+degree of table compression. You can trade off
+faster-executing scanners at the cost of larger tables with
+the following generally being true:
+.nf
+
+ slowest & smallest
+ -Cem
+ -Cm
+ -Ce
+ -C
+ -C{f,F}e
+ -C{f,F}
+ -C{f,F}a
+ fastest & largest
+
+.fi
+Note that scanners with the smallest tables are usually generated and
+compiled the quickest, so
+during development you will usually want to use the default, maximal
+compression.
+.IP
+.B \-Cfe
+is often a good compromise between speed and size for production
+scanners.
+.TP
+.B \-Pprefix
+changes the default
+.I "yy"
+prefix used by
+.I flex
+for all globally-visible variable and function names to instead be
+.I prefix.
+For example,
+.B \-Pfoo
+changes the name of
+.B yytext
+to
+.B footext.
+It also changes the name of the default output file from
+.B lex.yy.c
+to
+.B lex.foo.c.
+Here are all of the names affected:
+.nf
+
+ yyFlexLexer
+ yy_create_buffer
+ yy_delete_buffer
+ yy_flex_debug
+ yy_init_buffer
+ yy_load_buffer_state
+ yy_switch_to_buffer
+ yyin
+ yyleng
+ yylex
+ yyout
+ yyrestart
+ yytext
+ yywrap
+
+.fi
+Within your scanner itself, you can still refer to the global variables
+and functions using either version of their name; but eternally, they
+have the modified name.
+.IP
+This option lets you easily link together multiple
+.I flex
+programs into the same executable. Note, though, that using this
+option also renames
+.B yywrap(),
+so you now
+.I must
+provide your own (appropriately-named) version of the routine for your
+scanner, as linking with
+.B \-lfl
+no longer provides one for you by default.
+.TP
+.B \-Sskeleton_file
+overrides the default skeleton file from which
+.I flex
+constructs its scanners. You'll never need this option unless you are doing
+.I flex
+maintenance or development.
+.SH PERFORMANCE CONSIDERATIONS
+The main design goal of
+.I flex
+is that it generate high-performance scanners. It has been optimized
+for dealing well with large sets of rules. Aside from the effects on
+scanner speed of the table compression
+.B \-C
+options outlined above,
+there are a number of options/actions which degrade performance. These
+are, from most expensive to least:
+.nf
+
+ REJECT
+
+ pattern sets that require backing up
+ arbitrary trailing context
+
+ yymore()
+ '^' beginning-of-line operator
+
+.fi
+with the first three all being quite expensive and the last two
+being quite cheap. Note also that
+.B unput()
+is implemented as a routine call that potentially does quite a bit of
+work, while
+.B yyless()
+is a quite-cheap macro; so if just putting back some excess text you
+scanned, use
+.B yyless().
+.PP
+.B REJECT
+should be avoided at all costs when performance is important.
+It is a particularly expensive option.
+.PP
+Getting rid of backing up is messy and often may be an enormous
+amount of work for a complicated scanner. In principal, one begins
+by using the
+.B \-b
+flag to generate a
+.I lex.backup
+file. For example, on the input
+.nf
+
+ %%
+ foo return TOK_KEYWORD;
+ foobar return TOK_KEYWORD;
+
+.fi
+the file looks like:
+.nf
+
+ State #6 is non-accepting -
+ associated rule line numbers:
+ 2 3
+ out-transitions: [ o ]
+ jam-transitions: EOF [ \\001-n p-\\177 ]
+
+ State #8 is non-accepting -
+ associated rule line numbers:
+ 3
+ out-transitions: [ a ]
+ jam-transitions: EOF [ \\001-` b-\\177 ]
+
+ State #9 is non-accepting -
+ associated rule line numbers:
+ 3
+ out-transitions: [ r ]
+ jam-transitions: EOF [ \\001-q s-\\177 ]
+
+ Compressed tables always back up.
+
+.fi
+The first few lines tell us that there's a scanner state in
+which it can make a transition on an 'o' but not on any other
+character, and that in that state the currently scanned text does not match
+any rule. The state occurs when trying to match the rules found
+at lines 2 and 3 in the input file.
+If the scanner is in that state and then reads
+something other than an 'o', it will have to back up to find
+a rule which is matched. With
+a bit of headscratching one can see that this must be the
+state it's in when it has seen "fo". When this has happened,
+if anything other than another 'o' is seen, the scanner will
+have to back up to simply match the 'f' (by the default rule).
+.PP
+The comment regarding State #8 indicates there's a problem
+when "foob" has been scanned. Indeed, on any character other
+than an 'a', the scanner will have to back up to accept "foo".
+Similarly, the comment for State #9 concerns when "fooba" has
+been scanned and an 'r' does not follow.
+.PP
+The final comment reminds us that there's no point going to
+all the trouble of removing backing up from the rules unless
+we're using
+.B \-Cf
+or
+.B \-CF,
+since there's no performance gain doing so with compressed scanners.
+.PP
+The way to remove the backing up is to add "error" rules:
+.nf
+
+ %%
+ foo return TOK_KEYWORD;
+ foobar return TOK_KEYWORD;
+
+ fooba |
+ foob |
+ fo {
+ /* false alarm, not really a keyword */
+ return TOK_ID;
+ }
+
+.fi
+.PP
+Eliminating backing up among a list of keywords can also be
+done using a "catch-all" rule:
+.nf
+
+ %%
+ foo return TOK_KEYWORD;
+ foobar return TOK_KEYWORD;
+
+ [a-z]+ return TOK_ID;
+
+.fi
+This is usually the best solution when appropriate.
+.PP
+Backing up messages tend to cascade.
+With a complicated set of rules it's not uncommon to get hundreds
+of messages. If one can decipher them, though, it often
+only takes a dozen or so rules to eliminate the backing up (though
+it's easy to make a mistake and have an error rule accidentally match
+a valid token. A possible future
+.I flex
+feature will be to automatically add rules to eliminate backing up).
+.PP
+.I Variable
+trailing context (where both the leading and trailing parts do not have
+a fixed length) entails almost the same performance loss as
+.B REJECT
+(i.e., substantial). So when possible a rule like:
+.nf
+
+ %%
+ mouse|rat/(cat|dog) run();
+
+.fi
+is better written:
+.nf
+
+ %%
+ mouse/cat|dog run();
+ rat/cat|dog run();
+
+.fi
+or as
+.nf
+
+ %%
+ mouse|rat/cat run();
+ mouse|rat/dog run();
+
+.fi
+Note that here the special '|' action does
+.I not
+provide any savings, and can even make things worse (see
+.PP
+A final note regarding performance: as mentioned above in the section
+How the Input is Matched, dynamically resizing
+.B yytext
+to accomodate huge tokens is a slow process because it presently requires that
+the (huge) token be rescanned from the beginning. Thus if performance is
+vital, you should attempt to match "large" quantities of text but not
+"huge" quantities, where the cutoff between the two is at about 8K
+characters/token.
+.PP
+Another area where the user can increase a scanner's performance
+(and one that's easier to implement) arises from the fact that
+the longer the tokens matched, the faster the scanner will run.
+This is because with long tokens the processing of most input
+characters takes place in the (short) inner scanning loop, and
+does not often have to go through the additional work of setting up
+the scanning environment (e.g.,
+.B yytext)
+for the action. Recall the scanner for C comments:
+.nf
+
+ %x comment
+ %%
+ int line_num = 1;
+
+ "/*" BEGIN(comment);
+
+ <comment>[^*\\n]*
+ <comment>"*"+[^*/\\n]*
+ <comment>\\n ++line_num;
+ <comment>"*"+"/" BEGIN(INITIAL);
+
+.fi
+This could be sped up by writing it as:
+.nf
+
+ %x comment
+ %%
+ int line_num = 1;
+
+ "/*" BEGIN(comment);
+
+ <comment>[^*\\n]*
+ <comment>[^*\\n]*\\n ++line_num;
+ <comment>"*"+[^*/\\n]*
+ <comment>"*"+[^*/\\n]*\\n ++line_num;
+ <comment>"*"+"/" BEGIN(INITIAL);
+
+.fi
+Now instead of each newline requiring the processing of another
+action, recognizing the newlines is "distributed" over the other rules
+to keep the matched text as long as possible. Note that
+.I adding
+rules does
+.I not
+slow down the scanner! The speed of the scanner is independent
+of the number of rules or (modulo the considerations given at the
+beginning of this section) how complicated the rules are with
+regard to operators such as '*' and '|'.
+.PP
+A final example in speeding up a scanner: suppose you want to scan
+through a file containing identifiers and keywords, one per line
+and with no other extraneous characters, and recognize all the
+keywords. A natural first approach is:
+.nf
+
+ %%
+ asm |
+ auto |
+ break |
+ ... etc ...
+ volatile |
+ while /* it's a keyword */
+
+ .|\\n /* it's not a keyword */
+
+.fi
+To eliminate the back-tracking, introduce a catch-all rule:
+.nf
+
+ %%
+ asm |
+ auto |
+ break |
+ ... etc ...
+ volatile |
+ while /* it's a keyword */
+
+ [a-z]+ |
+ .|\\n /* it's not a keyword */
+
+.fi
+Now, if it's guaranteed that there's exactly one word per line,
+then we can reduce the total number of matches by a half by
+merging in the recognition of newlines with that of the other
+tokens:
+.nf
+
+ %%
+ asm\\n |
+ auto\\n |
+ break\\n |
+ ... etc ...
+ volatile\\n |
+ while\\n /* it's a keyword */
+
+ [a-z]+\\n |
+ .|\\n /* it's not a keyword */
+
+.fi
+One has to be careful here, as we have now reintroduced backing up
+into the scanner. In particular, while
+.I we
+know that there will never be any characters in the input stream
+other than letters or newlines,
+.I flex
+can't figure this out, and it will plan for possibly needing to back up
+when it has scanned a token like "auto" and then the next character
+is something other than a newline or a letter. Previously it would
+then just match the "auto" rule and be done, but now it has no "auto"
+rule, only a "auto\\n" rule. To eliminate the possibility of backing up,
+we could either duplicate all rules but without final newlines, or,
+since we never expect to encounter such an input and therefore don't
+how it's classified, we can introduce one more catch-all rule, this
+one which doesn't include a newline:
+.nf
+
+ %%
+ asm\\n |
+ auto\\n |
+ break\\n |
+ ... etc ...
+ volatile\\n |
+ while\\n /* it's a keyword */
+
+ [a-z]+\\n |
+ [a-z]+ |
+ .|\\n /* it's not a keyword */
+
+.fi
+Compiled with
+.B \-Cf,
+this is about as fast as one can get a
+.I flex
+scanner to go for this particular problem.
+.PP
+A final note:
+.I flex
+is slow when matching NUL's, particularly when a token contains
+multiple NUL's.
+It's best to write rules which match
+.I short
+amounts of text if it's anticipated that the text will often include NUL's.
+.SH GENERATING C++ SCANNERS
+.I flex
+provides two different ways to generate scanners for use with C++. The
+first way is to simply compile a scanner generated by
+.I flex
+using a C++ compiler instead of a C compiler. You should not encounter
+any compilations errors (please report any you find to the email address
+given in the Author section below). You can then use C++ code in your
+rule actions instead of C code. Note that the default input source for
+your scanner remains
+.I yyin,
+and default echoing is still done to
+.I yyout.
+Both of these remain
+.I FILE *
+variables and not C++
+.I streams.
+.PP
+You can also use
+.I flex
+to generate a C++ scanner class, using the
+.B \-+
+option, which is automatically specified if the name of the flex
+executable ends in a '+', such as
+.I flex++.
+When using this option, flex defaults to generating the scanner to the file
+.B lex.yy.cc
+instead of
+.B lex.yy.c.
+The generated scanner includes the header file
+.I FlexLexer.h,
+which defines the interface to two C++ classes.
+.PP
+The first class,
+.B FlexLexer,
+provides an abstract base class defining the general scanner class
+interface. It provides the following member functions:
+.TP
+.B const char* YYText()
+returns the text of the most recently matched token, the equivalent of
+.B yytext.
+.TP
+.B int YYLeng()
+returns the length of the most recently matched token, the equivalent of
+.B yyleng.
+.PP
+Also provided are member functions equivalent to
+.B yy_switch_to_buffer(),
+.B yy_create_buffer()
+(though the first argument is an
+.B istream*
+object pointer and not a
+.B FILE*),
+.B yy_delete_buffer(),
+and
+.B yyrestart()
+(again, the first argument is a
+.B istream*
+object pointer).
+.PP
+The second class defined in
+.I FlexLexer.h
+is
+.B yyFlexLexer,
+which is derived from
+.B FlexLexer.
+It defines the following additional member functions:
+.TP
+.B
+yyFlexLexer( istream* arg_yyin = 0, ostream* arg_yyout = 0 )
+constructs a
+.B yyFlexLexer
+object using the given streams for input and output. If not specified,
+the streams default to
+.B cin
+and
+.B cout,
+respectively.
+.TP
+.B virtual int yylex()
+performs the same role is
+.B yylex()
+does for ordinary flex scanners: it scans the input stream, consuming
+tokens, until a rule's action returns a value.
+.PP
+In addition,
+.B yyFlexLexer
+defines the following protected virtual functions which you can redefine
+in derived classes to tailor the scanner:
+.TP
+.B
+virtual int LexerInput( char* buf, int max_size )
+reads up to
+.B max_size
+characters into
+.B buf
+and returns the number of characters read. To indicate end-of-input,
+return 0 characters. Note that "interactive" scanners (see the
+.B \-B
+and
+.B \-I
+flags) define the macro
+.B YY_INTERACTIVE.
+If you redefine
+.B LexerInput()
+and need to take different actions depending on whether or not
+the scanner might be scanning an interactive input source, you can
+test for the presence of this name via
+.B #ifdef.
+.TP
+.B
+virtual void LexerOutput( const char* buf, int size )
+writes out
+.B size
+characters from the buffer
+.B buf,
+which, while NUL-terminated, may also contain "internal" NUL's if
+the scanner's rules can match text with NUL's in them.
+.TP
+.B
+virtual void LexerError( const char* msg )
+reports a fatal error message. The default version of this function
+writes the message to the stream
+.B cerr
+and exits.
+.PP
+Note that a
+.B yyFlexLexer
+object contains its
+.I entire
+scanning state. Thus you can use such objects to create reentrant
+scanners. You can instantiate multiple instances of the same
+.B yyFlexLexer
+class, and you can also combine multiple C++ scanner classes together
+in the same program using the
+.B \-P
+option discussed above.
+.PP
+Finally, note that the
+.B %array
+feature is not available to C++ scanner classes; you must use
+.B %pointer
+(the default).
+.PP
+Here is an example of a simple C++ scanner:
+.nf
+
+ // An example of using the flex C++ scanner class.
+
+ %{
+ int mylineno = 0;
+ %}
+
+ string \\"[^\\n"]+\\"
+
+ ws [ \\t]+
+
+ alpha [A-Za-z]
+ dig [0-9]
+ name ({alpha}|{dig}|\\$)({alpha}|{dig}|[_.\\-/$])*
+ num1 [-+]?{dig}+\\.?([eE][-+]?{dig}+)?
+ num2 [-+]?{dig}*\\.{dig}+([eE][-+]?{dig}+)?
+ number {num1}|{num2}
+
+ %%
+
+ {ws} /* skip blanks and tabs */
+
+ "/*" {
+ int c;
+
+ while((c = yyinput()) != 0)
+ {
+ if(c == '\\n')
+ ++mylineno;
+
+ else if(c == '*')
+ {
+ if((c = yyinput()) == '/')
+ break;
+ else
+ unput(c);
+ }
+ }
+ }
+
+ {number} cout << "number " << YYText() << '\\n';
+
+ \\n mylineno++;
+
+ {name} cout << "name " << YYText() << '\\n';
+
+ {string} cout << "string " << YYText() << '\\n';
+
+ %%
+
+ int main( int /* argc */, char** /* argv */ )
+ {
+ FlexLexer* lexer = new yyFlexLexer;
+ while(lexer->yylex() != 0)
+ ;
+ return 0;
+ }
+.fi
+IMPORTANT: the present form of the scanning class is
+.I experimental
+and may change considerably between major releases.
+.SH INCOMPATIBILITIES WITH LEX AND POSIX
+.I flex
+is a rewrite of the AT&T Unix
+.I lex
+tool (the two implementations do not share any code, though),
+with some extensions and incompatibilities, both of which
+are of concern to those who wish to write scanners acceptable
+to either implementation. The POSIX
+.I lex
+specification is closer to
+.I flex's
+behavior than that of the original
+.I lex
+implementation, but there also remain some incompatibilities between
+.I flex
+and POSIX. The intent is that ultimately
+.I flex
+will be fully POSIX-conformant. In this section we discuss all of
+the known areas of incompatibility.
+.PP
+.I flex's
+.B \-l
+option turns on maximum compatibility with the original AT&T
+.I lex
+implementation, at the cost of a major loss in the generated scanner's
+performance. We note below which incompatibilities can be overcome
+using the
+.B \-l
+option.
+.PP
+.I flex
+is fully compatible with
+.I lex
+with the following exceptions:
+.IP -
+The undocumented
+.I lex
+scanner internal variable
+.B yylineno
+is not supported unless
+.B \-l
+is used.
+.IP
+yylineno is not part of the POSIX specification.
+.IP -
+The
+.B input()
+routine is not redefinable, though it may be called to read characters
+following whatever has been matched by a rule. If
+.B input()
+encounters an end-of-file the normal
+.B yywrap()
+processing is done. A ``real'' end-of-file is returned by
+.B input()
+as
+.I EOF.
+.IP
+Input is instead controlled by defining the
+.B YY_INPUT
+macro.
+.IP
+The
+.I flex
+restriction that
+.B input()
+cannot be redefined is in accordance with the POSIX specification,
+which simply does not specify any way of controlling the
+scanner's input other than by making an initial assignment to
+.I yyin.
+.IP -
+.I flex
+scanners are not as reentrant as
+.I lex
+scanners. In particular, if you have an interactive scanner and
+an interrupt handler which long-jumps out of the scanner, and
+the scanner is subsequently called again, you may get the following
+message:
+.nf
+
+ fatal flex scanner internal error--end of buffer missed
+
+.fi
+To reenter the scanner, first use
+.nf
+
+ yyrestart( yyin );
+
+.fi
+Note that this call will throw away any buffered input; usually this
+isn't a problem with an interactive scanner.
+.IP
+Also note that flex C++ scanner classes
+.I are
+reentrant, so if using C++ is an option for you, you should use
+them instead. See "Generating C++ Scanners" above for details.
+.IP -
+.B output()
+is not supported.
+Output from the
+.B ECHO
+macro is done to the file-pointer
+.I yyout
+(default
+.I stdout).
+.IP
+.B output()
+is not part of the POSIX specification.
+.IP -
+.I lex
+does not support exclusive start conditions (%x), though they
+are in the POSIX specification.
+.IP -
+When definitions are expanded,
+.I flex
+encloses them in parentheses.
+With lex, the following:
+.nf
+
+ NAME [A-Z][A-Z0-9]*
+ %%
+ foo{NAME}? printf( "Found it\\n" );
+ %%
+
+.fi
+will not match the string "foo" because when the macro
+is expanded the rule is equivalent to "foo[A-Z][A-Z0-9]*?"
+and the precedence is such that the '?' is associated with
+"[A-Z0-9]*". With
+.I flex,
+the rule will be expanded to
+"foo([A-Z][A-Z0-9]*)?" and so the string "foo" will match.
+.IP
+Note that if the definition begins with
+.B ^
+or ends with
+.B $
+then it is
+.I not
+expanded with parentheses, to allow these operators to appear in
+definitions without losing their special meanings. But the
+.B <s>, /,
+and
+.B <<EOF>>
+operators cannot be used in a
+.I flex
+definition.
+.IP
+Using
+.B \-l
+results in the
+.I lex
+behavior of no parentheses around the definition.
+.IP
+The POSIX specification is that the definition be enclosed in parentheses.
+.IP -
+The
+.I lex
+.B %r
+(generate a Ratfor scanner) option is not supported. It is not part
+of the POSIX specification.
+.IP -
+After a call to
+.B unput(),
+.I yytext
+and
+.I yyleng
+are undefined until the next token is matched, unless the scanner
+was built using
+.B %array.
+This is not the case with
+.I lex
+or the POSIX specification. The
+.B \-l
+option does away with this incompatibility.
+.IP -
+The precedence of the
+.B {}
+(numeric range) operator is different.
+.I lex
+interprets "abc{1,3}" as "match one, two, or
+three occurrences of 'abc'", whereas
+.I flex
+interprets it as "match 'ab'
+followed by one, two, or three occurrences of 'c'". The latter is
+in agreement with the POSIX specification.
+.IP -
+The precedence of the
+.B ^
+operator is different.
+.I lex
+interprets "^foo|bar" as "match either 'foo' at the beginning of a line,
+or 'bar' anywhere", whereas
+.I flex
+interprets it as "match either 'foo' or 'bar' if they come at the beginning
+of a line". The latter is in agreement with the POSIX specification.
+.IP -
+.I yyin
+is
+.I initialized
+by
+.I lex
+to be
+.I stdin;
+.I flex,
+on the other hand,
+initializes
+.I yyin
+to NULL
+and then
+.I assigns
+it to
+.I stdin
+the first time the scanner is called, providing
+.I yyin
+has not already been assigned to a non-NULL value. The difference is
+subtle, but the net effect is that with
+.I flex
+scanners,
+.I yyin
+does not have a valid value until the scanner has been called.
+.IP
+The
+.B \-l
+option does away with this incompatibility.
+.IP -
+The special table-size declarations such as
+.B %a
+supported by
+.I lex
+are not required by
+.I flex
+scanners;
+.I flex
+ignores them.
+.IP -
+The name
+.bd
+FLEX_SCANNER
+is #define'd so scanners may be written for use with either
+.I flex
+or
+.I lex.
+.PP
+The following
+.I flex
+features are not included in
+.I lex
+or the POSIX specification:
+.nf
+
+ yyterminate()
+ <<EOF>>
+ <*>
+ YY_DECL
+ YY_START
+ YY_USER_ACTION
+ #line directives
+ %{}'s around actions
+ multiple actions on a line
+
+.fi
+plus almost all of the flex flags.
+The last feature in the list refers to the fact that with
+.I flex
+you can put multiple actions on the same line, separated with
+semi-colons, while with
+.I lex,
+the following
+.nf
+
+ foo handle_foo(); ++num_foos_seen;
+
+.fi
+is (rather surprisingly) truncated to
+.nf
+
+ foo handle_foo();
+
+.fi
+.I flex
+does not truncate the action. Actions that are not enclosed in
+braces are simply terminated at the end of the line.
+.SH DIAGNOSTICS
+.PP
+.I warning, rule cannot be matched
+indicates that the given rule
+cannot be matched because it follows other rules that will
+always match the same text as it. For
+example, in the following "foo" cannot be matched because it comes after
+an identifier "catch-all" rule:
+.nf
+
+ [a-z]+ got_identifier();
+ foo got_foo();
+
+.fi
+Using
+.B REJECT
+in a scanner suppresses this warning.
+.PP
+.I warning,
+.B \-s
+.I
+option given but default rule can be matched
+means that it is possible (perhaps only in a particular start condition)
+that the default rule (match any single character) is the only one
+that will match a particular input. Since
+.B \-s
+was given, presumably this is not intended.
+.PP
+.I reject_used_but_not_detected undefined
+or
+.I yymore_used_but_not_detected undefined -
+These errors can occur at compile time. They indicate that the
+scanner uses
+.B REJECT
+or
+.B yymore()
+but that
+.I flex
+failed to notice the fact, meaning that
+.I flex
+scanned the first two sections looking for occurrences of these actions
+and failed to find any, but somehow you snuck some in (via a #include
+file, for example). Make an explicit reference to the action in your
+.I flex
+input file. (Note that previously
+.I flex
+supported a
+.B %used/%unused
+mechanism for dealing with this problem; this feature is still supported
+but now deprecated, and will go away soon unless the author hears from
+people who can argue compellingly that they need it.)
+.PP
+.I flex scanner jammed -
+a scanner compiled with
+.B \-s
+has encountered an input string which wasn't matched by
+any of its rules. This error can also occur due to internal problems.
+.PP
+.I token too large, exceeds YYLMAX -
+your scanner uses
+.B %array
+and one of its rules matched a string longer than the
+.B YYLMAX
+constant (8K bytes by default). You can increase the value by
+#define'ing
+.B YYLMAX
+in the definitions section of your
+.I flex
+input.
+.PP
+.I scanner requires \-8 flag to
+.I use the character 'x' -
+Your scanner specification includes recognizing the 8-bit character
+.I 'x'
+and you did not specify the \-8 flag, and your scanner defaulted to 7-bit
+because you used the
+.B \-Cf
+or
+.B \-CF
+table compression options. See the discussion of the
+.B \-7
+flag for details.
+.PP
+.I flex scanner push-back overflow -
+you used
+.B unput()
+to push back so much text that the scanner's buffer could not hold
+both the pushed-back text and the current token in
+.B yytext.
+Ideally the scanner should dynamically resize the buffer in this case, but at
+present it does not.
+.PP
+.I
+input buffer overflow, can't enlarge buffer because scanner uses REJECT -
+the scanner was working on matching an extremely large token and needed
+to expand the input buffer. This doesn't work with scanners that use
+.B
+REJECT.
+.PP
+.I
+fatal flex scanner internal error--end of buffer missed -
+This can occur in an scanner which is reentered after a long-jump
+has jumped out (or over) the scanner's activation frame. Before
+reentering the scanner, use:
+.nf
+
+ yyrestart( yyin );
+
+.fi
+or, as noted above, switch to using the C++ scanner class.
+.PP
+.I too many start conditions in <> construct! -
+you listed more start conditions in a <> construct than exist (so
+you must have listed at least one of them twice).
+.SH FILES
+See flex(1).
+.SH DEFICIENCIES / BUGS
+Again, see flex(1).
+.SH "SEE ALSO"
+.PP
+flex(1), lex(1), yacc(1), sed(1), awk(1).
+.PP
+M. E. Lesk and E. Schmidt,
+.I LEX \- Lexical Analyzer Generator
+.SH AUTHOR
+Vern Paxson, with the help of many ideas and much inspiration from
+Van Jacobson. Original version by Jef Poskanzer. The fast table
+representation is a partial implementation of a design done by Van
+Jacobson. The implementation was done by Kevin Gong and Vern Paxson.
+.PP
+Thanks to the many
+.I flex
+beta-testers, feedbackers, and contributors, especially Francois Pinard,
+Casey Leedom,
+Nelson H.F. Beebe, benson@odi.com, Peter A. Bigot, Keith Bostic, Frederic
+Brehm, Nick Christopher, Jason Coughlin, Bill Cox, Dave Curtis, Scott David
+Daniels, Chris G. Demetriou, Mike Donahue, Chuck Doucette, Tom Epperly, Leo
+Eskin, Chris Faylor, Jon Forrest, Kaveh R. Ghazi,
+Eric Goldman, Ulrich Grepel, Jan Hajic,
+Jarkko Hietaniemi, Eric Hughes, John Interrante,
+Ceriel Jacobs, Jeffrey R. Jones, Henry
+Juengst, Amir Katz, ken@ken.hilco.com, Kevin B. Kenny, Marq Kole, Ronald
+Lamprecht, Greg Lee, Craig Leres, John Levine, Steve Liddle,
+Mohamed el Lozy, Brian Madsen, Chris
+Metcalf, Luke Mewburn, Jim Meyering, G.T. Nicol, Landon Noll, Marc Nozell,
+Richard Ohnemus, Sven Panne, Roland Pesch, Walter Pelissero, Gaumond
+Pierre, Esmond Pitt, Jef Poskanzer, Joe Rahmeh, Frederic Raimbault,
+Rick Richardson,
+Kevin Rodgers, Jim Roskind,
+Doug Schmidt, Philippe Schnoebelen, Andreas Schwab,
+Alex Siegel, Mike Stump, Paul Stuart, Dave Tallman, Chris Thewalt,
+Paul Tuinenga, Gary Weik, Frank Whaley, Gerhard Wilhelms, Kent Williams, Ken
+Yap, Nathan Zelle, David Zuhn, and those whose names have slipped my marginal
+mail-archiving skills but whose contributions are appreciated all the
+same.
+.PP
+Thanks to Keith Bostic, Jon Forrest, Noah Friedman,
+John Gilmore, Craig Leres, John Levine, Bob Mulcahy, G.T.
+Nicol, Francois Pinard, Rich Salz, and Richard Stallman for help with various
+distribution headaches.
+.PP
+Thanks to Esmond Pitt and Earle Horton for 8-bit character support; to
+Benson Margulies and Fred Burke for C++ support; to Kent Williams and Tom
+Epperly for C++ class support; to Ove Ewerlid for support of NUL's; and to
+Eric Hughes for support of multiple buffers.
+.PP
+This work was primarily done when I was with the Real Time Systems Group
+at the Lawrence Berkeley Laboratory in Berkeley, CA. Many thanks to all there
+for the support I received.
+.PP
+Send comments to:
+.nf
+
+ Vern Paxson
+ Systems Engineering
+ Bldg. 46A, Room 1123
+ Lawrence Berkeley Laboratory
+ University of California
+ Berkeley, CA 94720
+
+ vern@ee.lbl.gov
+
+.fi
diff --git a/usr.bin/lex/gen.c b/usr.bin/lex/gen.c
new file mode 100644
index 000000000000..e2096f2548a8
--- /dev/null
+++ b/usr.bin/lex/gen.c
@@ -0,0 +1,1461 @@
+/* gen - actual generation (writing) of flex scanners */
+
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: /home/daffy/u0/vern/flex/flex-2.4.7/RCS/gen.c,v 1.3 94/08/03 11:37:45 vern Exp $ */
+
+#include "flexdef.h"
+
+
+/* declare functions that have forward references */
+
+void gen_next_state PROTO((int));
+void genecs PROTO((void));
+void indent_put2s PROTO((char [], char []));
+void indent_puts PROTO((char []));
+
+
+static int indent_level = 0; /* each level is 8 spaces */
+
+#define indent_up() (++indent_level)
+#define indent_down() (--indent_level)
+#define set_indent(indent_val) indent_level = indent_val
+
+/* Almost everything is done in terms of arrays starting at 1, so provide
+ * a null entry for the zero element of all C arrays. (The exception
+ * to this is that the fast table representation generally uses the
+ * 0 elements of its arrays, too.)
+ */
+static char C_int_decl[] = "static const int %s[%d] =\n { 0,\n";
+static char C_short_decl[] = "static const short int %s[%d] =\n { 0,\n";
+static char C_long_decl[] = "static const long int %s[%d] =\n { 0,\n";
+static char C_state_decl[] =
+ "static const yy_state_type %s[%d] =\n { 0,\n";
+
+
+/* Indent to the current level. */
+
+void do_indent()
+ {
+ register int i = indent_level * 8;
+
+ while ( i >= 8 )
+ {
+ putchar( '\t' );
+ i -= 8;
+ }
+
+ while ( i > 0 )
+ {
+ putchar( ' ' );
+ --i;
+ }
+ }
+
+
+/* Generate the code to keep backing-up information. */
+
+void gen_backing_up()
+ {
+ if ( reject || num_backing_up == 0 )
+ return;
+
+ if ( fullspd )
+ indent_puts( "if ( yy_current_state[-1].yy_nxt )" );
+ else
+ indent_puts( "if ( yy_accept[yy_current_state] )" );
+
+ indent_up();
+ indent_puts( "{" );
+ indent_puts( "yy_last_accepting_state = yy_current_state;" );
+ indent_puts( "yy_last_accepting_cpos = yy_cp;" );
+ indent_puts( "}" );
+ indent_down();
+ }
+
+
+/* Generate the code to perform the backing up. */
+
+void gen_bu_action()
+ {
+ if ( reject || num_backing_up == 0 )
+ return;
+
+ set_indent( 3 );
+
+ indent_puts( "case 0: /* must back up */" );
+ indent_puts( "/* undo the effects of YY_DO_BEFORE_ACTION */" );
+ indent_puts( "*yy_cp = yy_hold_char;" );
+
+ if ( fullspd || fulltbl )
+ indent_puts( "yy_cp = yy_last_accepting_cpos + 1;" );
+ else
+ /* Backing-up info for compressed tables is taken \after/
+ * yy_cp has been incremented for the next state.
+ */
+ indent_puts( "yy_cp = yy_last_accepting_cpos;" );
+
+ indent_puts( "yy_current_state = yy_last_accepting_state;" );
+ indent_puts( "goto yy_find_action;" );
+ putchar( '\n' );
+
+ set_indent( 0 );
+ }
+
+
+/* genctbl - generates full speed compressed transition table */
+
+void genctbl()
+ {
+ register int i;
+ int end_of_buffer_action = num_rules + 1;
+
+ /* Table of verify for transition and offset to next state. */
+ printf( "static const struct yy_trans_info yy_transition[%d] =\n",
+ tblend + numecs + 1 );
+ printf( " {\n" );
+
+ /* We want the transition to be represented as the offset to the
+ * next state, not the actual state number, which is what it currently
+ * is. The offset is base[nxt[i]] - (base of current state)]. That's
+ * just the difference between the starting points of the two involved
+ * states (to - from).
+ *
+ * First, though, we need to find some way to put in our end-of-buffer
+ * flags and states. We do this by making a state with absolutely no
+ * transitions. We put it at the end of the table.
+ */
+
+ /* We need to have room in nxt/chk for two more slots: One for the
+ * action and one for the end-of-buffer transition. We now *assume*
+ * that we're guaranteed the only character we'll try to index this
+ * nxt/chk pair with is EOB, i.e., 0, so we don't have to make sure
+ * there's room for jam entries for other characters.
+ */
+
+ while ( tblend + 2 >= current_max_xpairs )
+ expand_nxt_chk();
+
+ while ( lastdfa + 1 >= current_max_dfas )
+ increase_max_dfas();
+
+ base[lastdfa + 1] = tblend + 2;
+ nxt[tblend + 1] = end_of_buffer_action;
+ chk[tblend + 1] = numecs + 1;
+ chk[tblend + 2] = 1; /* anything but EOB */
+
+ /* So that "make test" won't show arb. differences. */
+ nxt[tblend + 2] = 0;
+
+ /* Make sure every state has an end-of-buffer transition and an
+ * action #.
+ */
+ for ( i = 0; i <= lastdfa; ++i )
+ {
+ int anum = dfaacc[i].dfaacc_state;
+ int offset = base[i];
+
+ chk[offset] = EOB_POSITION;
+ chk[offset - 1] = ACTION_POSITION;
+ nxt[offset - 1] = anum; /* action number */
+ }
+
+ for ( i = 0; i <= tblend; ++i )
+ {
+ if ( chk[i] == EOB_POSITION )
+ transition_struct_out( 0, base[lastdfa + 1] - i );
+
+ else if ( chk[i] == ACTION_POSITION )
+ transition_struct_out( 0, nxt[i] );
+
+ else if ( chk[i] > numecs || chk[i] == 0 )
+ transition_struct_out( 0, 0 ); /* unused slot */
+
+ else /* verify, transition */
+ transition_struct_out( chk[i],
+ base[nxt[i]] - (i - chk[i]) );
+ }
+
+
+ /* Here's the final, end-of-buffer state. */
+ transition_struct_out( chk[tblend + 1], nxt[tblend + 1] );
+ transition_struct_out( chk[tblend + 2], nxt[tblend + 2] );
+
+ printf( " };\n" );
+ printf( "\n" );
+
+ /* Table of pointers to start states. */
+ printf(
+ "static const struct yy_trans_info *yy_start_state_list[%d] =\n",
+ lastsc * 2 + 1 );
+ printf( " {\n" ); /* } so vi doesn't get confused */
+
+ for ( i = 0; i <= lastsc * 2; ++i )
+ printf( " &yy_transition[%d],\n", base[i] );
+
+ dataend();
+
+ if ( useecs )
+ genecs();
+ }
+
+
+/* Generate equivalence-class tables. */
+
+void genecs()
+ {
+ Char clower();
+ register int i, j;
+ int numrows;
+
+ printf( C_int_decl, "yy_ec", csize );
+
+ for ( i = 1; i < csize; ++i )
+ {
+ if ( caseins && (i >= 'A') && (i <= 'Z') )
+ ecgroup[i] = ecgroup[clower( i )];
+
+ ecgroup[i] = ABS( ecgroup[i] );
+ mkdata( ecgroup[i] );
+ }
+
+ dataend();
+
+ if ( trace )
+ {
+ fputs( "\n\nEquivalence Classes:\n\n", stderr );
+
+ numrows = csize / 8;
+
+ for ( j = 0; j < numrows; ++j )
+ {
+ for ( i = j; i < csize; i = i + numrows )
+ {
+ fprintf( stderr, "%4s = %-2d",
+ readable_form( i ), ecgroup[i] );
+
+ putc( ' ', stderr );
+ }
+
+ putc( '\n', stderr );
+ }
+ }
+ }
+
+
+/* Generate the code to find the action number. */
+
+void gen_find_action()
+ {
+ if ( fullspd )
+ indent_puts( "yy_act = yy_current_state[-1].yy_nxt;" );
+
+ else if ( fulltbl )
+ indent_puts( "yy_act = yy_accept[yy_current_state];" );
+
+ else if ( reject )
+ {
+ indent_puts( "yy_current_state = *--yy_state_ptr;" );
+ indent_puts( "yy_lp = yy_accept[yy_current_state];" );
+
+ puts(
+ "find_rule: /* we branch to this label when backing up */" );
+
+ indent_puts(
+ "for ( ; ; ) /* until we find what rule we matched */" );
+
+ indent_up();
+
+ indent_puts( "{" );
+
+ indent_puts(
+ "if ( yy_lp && yy_lp < yy_accept[yy_current_state + 1] )" );
+ indent_up();
+ indent_puts( "{" );
+ indent_puts( "yy_act = yy_acclist[yy_lp];" );
+
+ if ( variable_trailing_context_rules )
+ {
+ indent_puts( "if ( yy_act & YY_TRAILING_HEAD_MASK ||" );
+ indent_puts( " yy_looking_for_trail_begin )" );
+ indent_up();
+ indent_puts( "{" );
+
+ indent_puts(
+ "if ( yy_act == yy_looking_for_trail_begin )" );
+ indent_up();
+ indent_puts( "{" );
+ indent_puts( "yy_looking_for_trail_begin = 0;" );
+ indent_puts( "yy_act &= ~YY_TRAILING_HEAD_MASK;" );
+ indent_puts( "break;" );
+ indent_puts( "}" );
+ indent_down();
+
+ indent_puts( "}" );
+ indent_down();
+
+ indent_puts( "else if ( yy_act & YY_TRAILING_MASK )" );
+ indent_up();
+ indent_puts( "{" );
+ indent_puts(
+ "yy_looking_for_trail_begin = yy_act & ~YY_TRAILING_MASK;" );
+ indent_puts(
+ "yy_looking_for_trail_begin |= YY_TRAILING_HEAD_MASK;" );
+
+ if ( real_reject )
+ {
+ /* Remember matched text in case we back up
+ * due to REJECT.
+ */
+ indent_puts( "yy_full_match = yy_cp;" );
+ indent_puts( "yy_full_state = yy_state_ptr;" );
+ indent_puts( "yy_full_lp = yy_lp;" );
+ }
+
+ indent_puts( "}" );
+ indent_down();
+
+ indent_puts( "else" );
+ indent_up();
+ indent_puts( "{" );
+ indent_puts( "yy_full_match = yy_cp;" );
+ indent_puts( "yy_full_state = yy_state_ptr;" );
+ indent_puts( "yy_full_lp = yy_lp;" );
+ indent_puts( "break;" );
+ indent_puts( "}" );
+ indent_down();
+
+ indent_puts( "++yy_lp;" );
+ indent_puts( "goto find_rule;" );
+ }
+
+ else
+ {
+ /* Remember matched text in case we back up due to trailing
+ * context plus REJECT.
+ */
+ indent_up();
+ indent_puts( "{" );
+ indent_puts( "yy_full_match = yy_cp;" );
+ indent_puts( "break;" );
+ indent_puts( "}" );
+ indent_down();
+ }
+
+ indent_puts( "}" );
+ indent_down();
+
+ indent_puts( "--yy_cp;" );
+
+ /* We could consolidate the following two lines with those at
+ * the beginning, but at the cost of complaints that we're
+ * branching inside a loop.
+ */
+ indent_puts( "yy_current_state = *--yy_state_ptr;" );
+ indent_puts( "yy_lp = yy_accept[yy_current_state];" );
+
+ indent_puts( "}" );
+
+ indent_down();
+ }
+
+ else
+ /* compressed */
+ indent_puts( "yy_act = yy_accept[yy_current_state];" );
+ }
+
+
+/* genftbl - generates full transition table */
+
+void genftbl()
+ {
+ register int i;
+ int end_of_buffer_action = num_rules + 1;
+
+ printf( long_align ? C_long_decl : C_short_decl,
+ "yy_accept", lastdfa + 1 );
+
+ dfaacc[end_of_buffer_state].dfaacc_state = end_of_buffer_action;
+
+ for ( i = 1; i <= lastdfa; ++i )
+ {
+ register int anum = dfaacc[i].dfaacc_state;
+
+ mkdata( anum );
+
+ if ( trace && anum )
+ fprintf( stderr, "state # %d accepts: [%d]\n",
+ i, anum );
+ }
+
+ dataend();
+
+ if ( useecs )
+ genecs();
+
+ /* Don't have to dump the actual full table entries - they were
+ * created on-the-fly.
+ */
+ }
+
+
+/* Generate the code to find the next compressed-table state. */
+
+void gen_next_compressed_state( char_map )
+char *char_map;
+ {
+ indent_put2s( "register YY_CHAR yy_c = %s;", char_map );
+
+ /* Save the backing-up info \before/ computing the next state
+ * because we always compute one more state than needed - we
+ * always proceed until we reach a jam state
+ */
+ gen_backing_up();
+
+ indent_puts(
+"while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )" );
+ indent_up();
+ indent_puts( "{" );
+ indent_puts( "yy_current_state = (int) yy_def[yy_current_state];" );
+
+ if ( usemecs )
+ {
+ /* We've arrange it so that templates are never chained
+ * to one another. This means we can afford to make a
+ * very simple test to see if we need to convert to
+ * yy_c's meta-equivalence class without worrying
+ * about erroneously looking up the meta-equivalence
+ * class twice
+ */
+ do_indent();
+
+ /* lastdfa + 2 is the beginning of the templates */
+ printf( "if ( yy_current_state >= %d )\n", lastdfa + 2 );
+
+ indent_up();
+ indent_puts( "yy_c = yy_meta[(unsigned int) yy_c];" );
+ indent_down();
+ }
+
+ indent_puts( "}" );
+ indent_down();
+
+ indent_puts(
+"yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];" );
+ }
+
+
+/* Generate the code to find the next match. */
+
+void gen_next_match()
+ {
+ /* NOTE - changes in here should be reflected in gen_next_state() and
+ * gen_NUL_trans().
+ */
+ char *char_map = useecs ?
+ "yy_ec[YY_SC_TO_UI(*yy_cp)]" :
+ "YY_SC_TO_UI(*yy_cp)";
+
+ char *char_map_2 = useecs ?
+ "yy_ec[YY_SC_TO_UI(*++yy_cp)]" :
+ "YY_SC_TO_UI(*++yy_cp)";
+
+ if ( fulltbl )
+ {
+ indent_put2s(
+ "while ( (yy_current_state = yy_nxt[yy_current_state][%s]) > 0 )",
+ char_map );
+
+ indent_up();
+
+ if ( num_backing_up > 0 )
+ {
+ indent_puts( "{" ); /* } for vi */
+ gen_backing_up();
+ putchar( '\n' );
+ }
+
+ indent_puts( "++yy_cp;" );
+
+ if ( num_backing_up > 0 )
+ /* { for vi */
+ indent_puts( "}" );
+
+ indent_down();
+
+ putchar( '\n' );
+ indent_puts( "yy_current_state = -yy_current_state;" );
+ }
+
+ else if ( fullspd )
+ {
+ indent_puts( "{" ); /* } for vi */
+ indent_puts(
+ "register const struct yy_trans_info *yy_trans_info;\n" );
+ indent_puts( "register YY_CHAR yy_c;\n" );
+ indent_put2s( "for ( yy_c = %s;", char_map );
+ indent_puts(
+ " (yy_trans_info = &yy_current_state[(unsigned int) yy_c])->" );
+ indent_puts( "yy_verify == yy_c;" );
+ indent_put2s( " yy_c = %s )", char_map_2 );
+
+ indent_up();
+
+ if ( num_backing_up > 0 )
+ indent_puts( "{" ); /* } for vi */
+
+ indent_puts( "yy_current_state += yy_trans_info->yy_nxt;" );
+
+ if ( num_backing_up > 0 )
+ {
+ putchar( '\n' );
+ gen_backing_up(); /* { for vi */
+ indent_puts( "}" );
+ }
+
+ indent_down(); /* { for vi */
+ indent_puts( "}" );
+ }
+
+ else
+ { /* compressed */
+ indent_puts( "do" );
+
+ indent_up();
+ indent_puts( "{" ); /* } for vi */
+
+ gen_next_state( false );
+
+ indent_puts( "++yy_cp;" );
+
+ /* { for vi */
+ indent_puts( "}" );
+ indent_down();
+
+ do_indent();
+
+ if ( interactive )
+ printf( "while ( yy_base[yy_current_state] != %d );\n",
+ jambase );
+ else
+ printf( "while ( yy_current_state != %d );\n",
+ jamstate );
+
+ if ( ! reject && ! interactive )
+ {
+ /* Do the guaranteed-needed backing up to figure out
+ * the match.
+ */
+ indent_puts( "yy_cp = yy_last_accepting_cpos;" );
+ indent_puts(
+ "yy_current_state = yy_last_accepting_state;" );
+ }
+ }
+ }
+
+
+/* Generate the code to find the next state. */
+
+void gen_next_state( worry_about_NULs )
+int worry_about_NULs;
+ { /* NOTE - changes in here should be reflected in get_next_match() */
+ char char_map[256];
+
+ if ( worry_about_NULs && ! nultrans )
+ {
+ if ( useecs )
+ (void) sprintf( char_map,
+ "(*yy_cp ? yy_ec[YY_SC_TO_UI(*yy_cp)] : %d)",
+ NUL_ec );
+ else
+ (void) sprintf( char_map,
+ "(*yy_cp ? YY_SC_TO_UI(*yy_cp) : %d)", NUL_ec );
+ }
+
+ else
+ strcpy( char_map, useecs ? "yy_ec[YY_SC_TO_UI(*yy_cp)]" :
+ "YY_SC_TO_UI(*yy_cp)" );
+
+ if ( worry_about_NULs && nultrans )
+ {
+ if ( ! fulltbl && ! fullspd )
+ /* Compressed tables back up *before* they match. */
+ gen_backing_up();
+
+ indent_puts( "if ( *yy_cp )" );
+ indent_up();
+ indent_puts( "{" ); /* } for vi */
+ }
+
+ if ( fulltbl )
+ indent_put2s(
+ "yy_current_state = yy_nxt[yy_current_state][%s];",
+ char_map );
+
+ else if ( fullspd )
+ indent_put2s(
+ "yy_current_state += yy_current_state[%s].yy_nxt;",
+ char_map );
+
+ else
+ gen_next_compressed_state( char_map );
+
+ if ( worry_about_NULs && nultrans )
+ {
+ /* { for vi */
+ indent_puts( "}" );
+ indent_down();
+ indent_puts( "else" );
+ indent_up();
+ indent_puts(
+ "yy_current_state = yy_NUL_trans[yy_current_state];" );
+ indent_down();
+ }
+
+ if ( fullspd || fulltbl )
+ gen_backing_up();
+
+ if ( reject )
+ indent_puts( "*yy_state_ptr++ = yy_current_state;" );
+ }
+
+
+/* Generate the code to make a NUL transition. */
+
+void gen_NUL_trans()
+ { /* NOTE - changes in here should be reflected in get_next_match() */
+ int need_backing_up = (num_backing_up > 0 && ! reject);
+
+ if ( need_backing_up )
+ /* We'll need yy_cp lying around for the gen_backing_up(). */
+ indent_puts( "register char *yy_cp = yy_c_buf_p;" );
+
+ putchar( '\n' );
+
+ if ( nultrans )
+ {
+ indent_puts(
+ "yy_current_state = yy_NUL_trans[yy_current_state];" );
+ indent_puts( "yy_is_jam = (yy_current_state == 0);" );
+ }
+
+ else if ( fulltbl )
+ {
+ do_indent();
+ printf( "yy_current_state = yy_nxt[yy_current_state][%d];\n",
+ NUL_ec );
+ indent_puts( "yy_is_jam = (yy_current_state <= 0);" );
+ }
+
+ else if ( fullspd )
+ {
+ do_indent();
+ printf( "register int yy_c = %d;\n", NUL_ec );
+
+ indent_puts(
+ "register const struct yy_trans_info *yy_trans_info;\n" );
+ indent_puts(
+ "yy_trans_info = &yy_current_state[(unsigned int) yy_c];" );
+ indent_puts( "yy_current_state += yy_trans_info->yy_nxt;" );
+
+ indent_puts(
+ "yy_is_jam = (yy_trans_info->yy_verify != yy_c);" );
+ }
+
+ else
+ {
+ char NUL_ec_str[20];
+
+ (void) sprintf( NUL_ec_str, "%d", NUL_ec );
+ gen_next_compressed_state( NUL_ec_str );
+
+ if ( reject )
+ indent_puts( "*yy_state_ptr++ = yy_current_state;" );
+
+ do_indent();
+
+ printf( "yy_is_jam = (yy_current_state == %d);\n", jamstate );
+ }
+
+ /* If we've entered an accepting state, back up; note that
+ * compressed tables have *already* done such backing up, so
+ * we needn't bother with it again.
+ */
+ if ( need_backing_up && (fullspd || fulltbl) )
+ {
+ putchar( '\n' );
+ indent_puts( "if ( ! yy_is_jam )" );
+ indent_up();
+ indent_puts( "{" );
+ gen_backing_up();
+ indent_puts( "}" );
+ indent_down();
+ }
+ }
+
+
+/* Generate the code to find the start state. */
+
+void gen_start_state()
+ {
+ if ( fullspd )
+ indent_put2s(
+ "yy_current_state = yy_start_state_list[yy_start%s];",
+ bol_needed ? " + (yy_bp[-1] == '\\n' ? 1 : 0)" : "" );
+
+ else
+ {
+ indent_puts( "yy_current_state = yy_start;" );
+
+ if ( bol_needed )
+ {
+ indent_puts( "if ( yy_bp[-1] == '\\n' )" );
+ indent_up();
+ indent_puts( "++yy_current_state;" );
+ indent_down();
+ }
+
+ if ( reject )
+ {
+ /* Set up for storing up states. */
+ indent_puts( "yy_state_ptr = yy_state_buf;" );
+ indent_puts( "*yy_state_ptr++ = yy_current_state;" );
+ }
+ }
+ }
+
+
+/* gentabs - generate data statements for the transition tables */
+
+void gentabs()
+ {
+ int i, j, k, *accset, nacc, *acc_array, total_states;
+ int end_of_buffer_action = num_rules + 1;
+
+ /* *Everything* is done in terms of arrays starting at 1, so provide
+ * a null entry for the zero element of all C arrays.
+ */
+ static char C_char_decl[] =
+ "static const YY_CHAR %s[%d] =\n { 0,\n"; /* } for vi */
+
+ acc_array = allocate_integer_array( current_max_dfas );
+ nummt = 0;
+
+ /* The compressed table format jams by entering the "jam state",
+ * losing information about the previous state in the process.
+ * In order to recover the previous state, we effectively need
+ * to keep backing-up information.
+ */
+ ++num_backing_up;
+
+ if ( reject )
+ {
+ /* Write out accepting list and pointer list.
+ *
+ * First we generate the "yy_acclist" array. In the process,
+ * we compute the indices that will go into the "yy_accept"
+ * array, and save the indices in the dfaacc array.
+ */
+ int EOB_accepting_list[2];
+
+ /* Set up accepting structures for the End Of Buffer state. */
+ EOB_accepting_list[0] = 0;
+ EOB_accepting_list[1] = end_of_buffer_action;
+ accsiz[end_of_buffer_state] = 1;
+ dfaacc[end_of_buffer_state].dfaacc_set = EOB_accepting_list;
+
+ printf( long_align ? C_long_decl : C_short_decl,
+ "yy_acclist", MAX( numas, 1 ) + 1 );
+
+ j = 1; /* index into "yy_acclist" array */
+
+ for ( i = 1; i <= lastdfa; ++i )
+ {
+ acc_array[i] = j;
+
+ if ( accsiz[i] != 0 )
+ {
+ accset = dfaacc[i].dfaacc_set;
+ nacc = accsiz[i];
+
+ if ( trace )
+ fprintf( stderr,
+ "state # %d accepts: ", i );
+
+ for ( k = 1; k <= nacc; ++k )
+ {
+ int accnum = accset[k];
+
+ ++j;
+
+ if ( variable_trailing_context_rules &&
+ ! (accnum & YY_TRAILING_HEAD_MASK) &&
+ accnum > 0 && accnum <= num_rules &&
+ rule_type[accnum] == RULE_VARIABLE )
+ {
+ /* Special hack to flag
+ * accepting number as part
+ * of trailing context rule.
+ */
+ accnum |= YY_TRAILING_MASK;
+ }
+
+ mkdata( accnum );
+
+ if ( trace )
+ {
+ fprintf( stderr, "[%d]",
+ accset[k] );
+
+ if ( k < nacc )
+ fputs( ", ", stderr );
+ else
+ putc( '\n', stderr );
+ }
+ }
+ }
+ }
+
+ /* add accepting number for the "jam" state */
+ acc_array[i] = j;
+
+ dataend();
+ }
+
+ else
+ {
+ dfaacc[end_of_buffer_state].dfaacc_state = end_of_buffer_action;
+
+ for ( i = 1; i <= lastdfa; ++i )
+ acc_array[i] = dfaacc[i].dfaacc_state;
+
+ /* add accepting number for jam state */
+ acc_array[i] = 0;
+ }
+
+ /* Spit out "yy_accept" array. If we're doing "reject", it'll be
+ * pointers into the "yy_acclist" array. Otherwise it's actual
+ * accepting numbers. In either case, we just dump the numbers.
+ */
+
+ /* "lastdfa + 2" is the size of "yy_accept"; includes room for C arrays
+ * beginning at 0 and for "jam" state.
+ */
+ k = lastdfa + 2;
+
+ if ( reject )
+ /* We put a "cap" on the table associating lists of accepting
+ * numbers with state numbers. This is needed because we tell
+ * where the end of an accepting list is by looking at where
+ * the list for the next state starts.
+ */
+ ++k;
+
+ printf( long_align ? C_long_decl : C_short_decl, "yy_accept", k );
+
+ for ( i = 1; i <= lastdfa; ++i )
+ {
+ mkdata( acc_array[i] );
+
+ if ( ! reject && trace && acc_array[i] )
+ fprintf( stderr, "state # %d accepts: [%d]\n",
+ i, acc_array[i] );
+ }
+
+ /* Add entry for "jam" state. */
+ mkdata( acc_array[i] );
+
+ if ( reject )
+ /* Add "cap" for the list. */
+ mkdata( acc_array[i] );
+
+ dataend();
+
+ if ( useecs )
+ genecs();
+
+ if ( usemecs )
+ {
+ /* Write out meta-equivalence classes (used to index
+ * templates with).
+ */
+
+ if ( trace )
+ fputs( "\n\nMeta-Equivalence Classes:\n", stderr );
+
+ printf( C_int_decl, "yy_meta", numecs + 1 );
+
+ for ( i = 1; i <= numecs; ++i )
+ {
+ if ( trace )
+ fprintf( stderr, "%d = %d\n",
+ i, ABS( tecbck[i] ) );
+
+ mkdata( ABS( tecbck[i] ) );
+ }
+
+ dataend();
+ }
+
+ total_states = lastdfa + numtemps;
+
+ printf( (tblend >= MAX_SHORT || long_align) ?
+ C_long_decl : C_short_decl,
+ "yy_base", total_states + 1 );
+
+ for ( i = 1; i <= lastdfa; ++i )
+ {
+ register int d = def[i];
+
+ if ( base[i] == JAMSTATE )
+ base[i] = jambase;
+
+ if ( d == JAMSTATE )
+ def[i] = jamstate;
+
+ else if ( d < 0 )
+ {
+ /* Template reference. */
+ ++tmpuses;
+ def[i] = lastdfa - d + 1;
+ }
+
+ mkdata( base[i] );
+ }
+
+ /* Generate jam state's base index. */
+ mkdata( base[i] );
+
+ for ( ++i /* skip jam state */; i <= total_states; ++i )
+ {
+ mkdata( base[i] );
+ def[i] = jamstate;
+ }
+
+ dataend();
+
+ printf( (total_states >= MAX_SHORT || long_align) ?
+ C_long_decl : C_short_decl,
+ "yy_def", total_states + 1 );
+
+ for ( i = 1; i <= total_states; ++i )
+ mkdata( def[i] );
+
+ dataend();
+
+ printf( (total_states >= MAX_SHORT || long_align) ?
+ C_long_decl : C_short_decl,
+ "yy_nxt", tblend + 1 );
+
+ for ( i = 1; i <= tblend; ++i )
+ {
+ if ( nxt[i] == 0 || chk[i] == 0 )
+ nxt[i] = jamstate; /* new state is the JAM state */
+
+ mkdata( nxt[i] );
+ }
+
+ dataend();
+
+ printf( (total_states >= MAX_SHORT || long_align) ?
+ C_long_decl : C_short_decl,
+ "yy_chk", tblend + 1 );
+
+ for ( i = 1; i <= tblend; ++i )
+ {
+ if ( chk[i] == 0 )
+ ++nummt;
+
+ mkdata( chk[i] );
+ }
+
+ dataend();
+ }
+
+
+/* Write out a formatted string (with a secondary string argument) at the
+ * current indentation level, adding a final newline.
+ */
+
+void indent_put2s( fmt, arg )
+char fmt[], arg[];
+ {
+ do_indent();
+ printf( fmt, arg );
+ putchar( '\n' );
+ }
+
+
+/* Write out a string at the current indentation level, adding a final
+ * newline.
+ */
+
+void indent_puts( str )
+char str[];
+ {
+ do_indent();
+ puts( str );
+ }
+
+
+/* make_tables - generate transition tables and finishes generating output file
+ */
+
+void make_tables()
+ {
+ register int i;
+ int did_eof_rule = false;
+
+ skelout();
+
+ /* First, take care of YY_DO_BEFORE_ACTION depending on yymore
+ * being used.
+ */
+ set_indent( 1 );
+
+ if ( yymore_used )
+ {
+ indent_puts( "yytext_ptr -= yy_more_len; \\" );
+ indent_puts( "yyleng = yy_cp - yytext_ptr; \\" );
+ }
+
+ else
+ indent_puts( "yyleng = yy_cp - yy_bp; \\" );
+
+ /* Now also deal with copying yytext_ptr to yytext if needed. */
+ skelout();
+ if ( yytext_is_array )
+ {
+ indent_puts( "if ( yyleng >= YYLMAX ) \\" );
+ indent_up();
+ indent_puts(
+ "YY_FATAL_ERROR( \"token too large, exceeds YYLMAX\" ); \\" );
+ indent_down();
+ indent_puts(
+ "yy_flex_strncpy( yytext, yytext_ptr, yyleng + 1 ); \\" );
+ }
+
+ set_indent( 0 );
+
+ skelout();
+
+
+ printf( "#define YY_END_OF_BUFFER %d\n", num_rules + 1 );
+
+ if ( fullspd )
+ {
+ /* Need to define the transet type as a size large
+ * enough to hold the biggest offset.
+ */
+ int total_table_size = tblend + numecs + 1;
+ char *trans_offset_type =
+ (total_table_size >= MAX_SHORT || long_align) ?
+ "long" : "short";
+
+ set_indent( 0 );
+ indent_puts( "struct yy_trans_info" );
+ indent_up();
+ indent_puts( "{" ); /* } for vi */
+
+ if ( long_align )
+ indent_puts( "long yy_verify;" );
+ else
+ indent_puts( "short yy_verify;" );
+
+ /* In cases where its sister yy_verify *is* a "yes, there is
+ * a transition", yy_nxt is the offset (in records) to the
+ * next state. In most cases where there is no transition,
+ * the value of yy_nxt is irrelevant. If yy_nxt is the -1th
+ * record of a state, though, then yy_nxt is the action number
+ * for that state.
+ */
+
+ indent_put2s( "%s yy_nxt;", trans_offset_type );
+ indent_puts( "};" );
+ indent_down();
+ }
+
+ if ( fullspd )
+ genctbl();
+ else if ( fulltbl )
+ genftbl();
+ else
+ gentabs();
+
+ /* Definitions for backing up. We don't need them if REJECT
+ * is being used because then we use an alternative backin-up
+ * technique instead.
+ */
+ if ( num_backing_up > 0 && ! reject )
+ {
+ if ( ! C_plus_plus )
+ {
+ indent_puts(
+ "static yy_state_type yy_last_accepting_state;" );
+ indent_puts(
+ "static char *yy_last_accepting_cpos;\n" );
+ }
+ }
+
+ if ( nultrans )
+ {
+ printf( C_state_decl, "yy_NUL_trans", lastdfa + 1 );
+
+ for ( i = 1; i <= lastdfa; ++i )
+ {
+ if ( fullspd )
+ printf( " &yy_transition[%d],\n", base[i] );
+ else
+ mkdata( nultrans[i] );
+ }
+
+ dataend();
+ }
+
+ if ( ddebug )
+ { /* Spit out table mapping rules to line numbers. */
+ indent_puts( "extern int yy_flex_debug;" );
+ indent_puts( "int yy_flex_debug = 1;\n" );
+
+ printf( long_align ? C_long_decl : C_short_decl,
+ "yy_rule_linenum", num_rules );
+ for ( i = 1; i < num_rules; ++i )
+ mkdata( rule_linenum[i] );
+ dataend();
+ }
+
+ if ( reject )
+ {
+ /* Declare state buffer variables. */
+ if ( ! C_plus_plus )
+ {
+ puts(
+ "static yy_state_type yy_state_buf[YY_BUF_SIZE + 2], *yy_state_ptr;" );
+ puts( "static char *yy_full_match;" );
+ puts( "static int yy_lp;" );
+ }
+
+ if ( variable_trailing_context_rules )
+ {
+ if ( ! C_plus_plus )
+ {
+ puts(
+ "static int yy_looking_for_trail_begin = 0;" );
+ puts( "static int yy_full_lp;" );
+ puts( "static int *yy_full_state;" );
+ }
+
+ printf( "#define YY_TRAILING_MASK 0x%x\n",
+ (unsigned int) YY_TRAILING_MASK );
+ printf( "#define YY_TRAILING_HEAD_MASK 0x%x\n",
+ (unsigned int) YY_TRAILING_HEAD_MASK );
+ }
+
+ puts( "#define REJECT \\" );
+ puts( "{ \\" ); /* } for vi */
+ puts(
+ "*yy_cp = yy_hold_char; /* undo effects of setting up yytext */ \\" );
+ puts(
+ "yy_cp = yy_full_match; /* restore poss. backed-over text */ \\" );
+
+ if ( variable_trailing_context_rules )
+ {
+ puts(
+ "yy_lp = yy_full_lp; /* restore orig. accepting pos. */ \\" );
+ puts(
+ "yy_state_ptr = yy_full_state; /* restore orig. state */ \\" );
+ puts(
+ "yy_current_state = *yy_state_ptr; /* restore curr. state */ \\" );
+ }
+
+ puts( "++yy_lp; \\" );
+ puts( "goto find_rule; \\" );
+ /* { for vi */
+ puts( "}" );
+ }
+
+ else
+ {
+ puts(
+ "/* The intent behind this definition is that it'll catch" );
+ puts( " * any uses of REJECT which flex missed." );
+ puts( " */" );
+ puts( "#define REJECT reject_used_but_not_detected" );
+ }
+
+ if ( yymore_used )
+ {
+ if ( ! C_plus_plus )
+ {
+ indent_puts( "static int yy_more_flag = 0;" );
+ indent_puts( "static int yy_more_len = 0;" );
+ }
+
+ indent_puts( "#define yymore() (yy_more_flag = 1)" );
+ indent_puts( "#define YY_MORE_ADJ yy_more_len" );
+ }
+
+ else
+ {
+ indent_puts( "#define yymore() yymore_used_but_not_detected" );
+ indent_puts( "#define YY_MORE_ADJ 0" );
+ }
+
+ if ( ! C_plus_plus )
+ {
+ if ( yytext_is_array )
+ {
+ puts( "#ifndef YYLMAX" );
+ puts( "#define YYLMAX 8192" );
+ puts( "#endif\n" );
+ puts( "char yytext[YYLMAX];" );
+ puts( "char *yytext_ptr;" );
+ }
+
+ else
+ puts( "char *yytext;" );
+ }
+
+ fputs( &action_array[defs1_offset], stdout );
+
+ skelout();
+
+ if ( ! C_plus_plus )
+ {
+ if ( use_read )
+ {
+ printf(
+"\tif ( (result = read( fileno(yyin), (char *) buf, max_size )) < 0 ) \\\n" );
+ printf(
+ "\t\tYY_FATAL_ERROR( \"input in flex scanner failed\" );\n" );
+ }
+
+ else
+ {
+ printf(
+ "\tif ( yy_current_buffer->yy_is_interactive ) \\\n" );
+ printf( "\t\t{ \\\n" );
+ printf( "\t\tint c = getc( yyin ); \\\n" );
+ printf( "\t\tresult = c == EOF ? 0 : 1; \\\n" );
+ printf( "\t\tbuf[0] = (char) c; \\\n" );
+ printf( "\t\t} \\\n" );
+ printf(
+ "\telse if ( ((result = fread( buf, 1, max_size, yyin )) == 0) \\\n" );
+ printf( "\t\t && ferror( yyin ) ) \\\n" );
+ printf(
+ "\t\tYY_FATAL_ERROR( \"input in flex scanner failed\" );\n" );
+ }
+ }
+
+ skelout();
+
+ /* Copy prolog to output file. */
+ fputs( &action_array[prolog_offset], stdout );
+
+ skelout();
+
+ set_indent( 2 );
+
+ if ( yymore_used )
+ {
+ indent_puts( "yy_more_len = 0;" );
+ indent_puts( "if ( yy_more_flag )" );
+ indent_up();
+ indent_puts( "{" );
+ indent_puts( "yy_more_len = yyleng;" );
+ indent_puts( "yy_more_flag = 0;" );
+ indent_puts( "}" );
+ indent_down();
+ }
+
+ skelout();
+
+ gen_start_state();
+
+ /* Note, don't use any indentation. */
+ puts( "yy_match:" );
+ gen_next_match();
+
+ skelout();
+ set_indent( 2 );
+ gen_find_action();
+
+ skelout();
+ if ( lex_compat )
+ {
+ indent_puts( "if ( yy_act != YY_END_OF_BUFFER )" );
+ indent_up();
+ indent_puts( "{" );
+ indent_puts( "int yyl;" );
+ indent_puts( "for ( yyl = 0; yyl < yyleng; ++yyl )" );
+ indent_up();
+ indent_puts( "if ( yytext[yyl] == '\\n' )" );
+ indent_up();
+ indent_puts( "++yylineno;" );
+ indent_down();
+ indent_down();
+ indent_puts( "}" );
+ indent_down();
+ }
+
+ skelout();
+ if ( ddebug )
+ {
+ indent_puts( "if ( yy_flex_debug )" );
+ indent_up();
+
+ indent_puts( "{" );
+ indent_puts( "if ( yy_act == 0 )" );
+ indent_up();
+ indent_puts(
+ "fprintf( stderr, \"--scanner backing up\\n\" );" );
+ indent_down();
+
+ do_indent();
+ printf( "else if ( yy_act < %d )\n", num_rules );
+ indent_up();
+ indent_puts(
+ "fprintf( stderr, \"--accepting rule at line %d (\\\"%s\\\")\\n\"," );
+ indent_puts( " yy_rule_linenum[yy_act], yytext );" );
+ indent_down();
+
+ do_indent();
+ printf( "else if ( yy_act == %d )\n", num_rules );
+ indent_up();
+ indent_puts(
+ "fprintf( stderr, \"--accepting default rule (\\\"%s\\\")\\n\"," );
+ indent_puts( " yytext );" );
+ indent_down();
+
+ do_indent();
+ printf( "else if ( yy_act == %d )\n", num_rules + 1 );
+ indent_up();
+ indent_puts(
+ "fprintf( stderr, \"--(end of buffer or a NUL)\\n\" );" );
+ indent_down();
+
+ do_indent();
+ printf( "else\n" );
+ indent_up();
+ indent_puts(
+ "fprintf( stderr, \"--EOF (start condition %d)\\n\", YY_START );" );
+ indent_down();
+
+ indent_puts( "}" );
+ indent_down();
+ }
+
+ /* Copy actions to output file. */
+ skelout();
+ indent_up();
+ gen_bu_action();
+ fputs( &action_array[action_offset], stdout );
+
+ /* generate cases for any missing EOF rules */
+ for ( i = 1; i <= lastsc; ++i )
+ if ( ! sceof[i] )
+ {
+ do_indent();
+ printf( "case YY_STATE_EOF(%s):\n", scname[i] );
+ did_eof_rule = true;
+ }
+
+ if ( did_eof_rule )
+ {
+ indent_up();
+ indent_puts( "yyterminate();" );
+ indent_down();
+ }
+
+
+ /* Generate code for handling NUL's, if needed. */
+
+ /* First, deal with backing up and setting up yy_cp if the scanner
+ * finds that it should JAM on the NUL.
+ */
+ skelout();
+ set_indent( 7 );
+
+ if ( fullspd || fulltbl )
+ indent_puts( "yy_cp = yy_c_buf_p;" );
+
+ else
+ { /* compressed table */
+ if ( ! reject && ! interactive )
+ {
+ /* Do the guaranteed-needed backing up to figure
+ * out the match.
+ */
+ indent_puts( "yy_cp = yy_last_accepting_cpos;" );
+ indent_puts(
+ "yy_current_state = yy_last_accepting_state;" );
+ }
+
+ else
+ /* Still need to initialize yy_cp, though
+ * yy_current_state was set up by
+ * yy_get_previous_state().
+ */
+ indent_puts( "yy_cp = yy_c_buf_p;" );
+ }
+
+
+ /* Generate code for yy_get_previous_state(). */
+ set_indent( 1 );
+ skelout();
+
+ if ( bol_needed )
+ indent_puts( "register char *yy_bp = yytext_ptr;\n" );
+
+ gen_start_state();
+
+ set_indent( 2 );
+ skelout();
+ gen_next_state( true );
+
+ set_indent( 1 );
+ skelout();
+ gen_NUL_trans();
+
+ skelout();
+ if ( lex_compat )
+ { /* update yylineno inside of unput() */
+ indent_puts( "if ( c == '\\n' )" );
+ indent_up();
+ indent_puts( "--yylineno;" );
+ indent_down();
+ }
+
+ skelout();
+
+ /* Copy remainder of input to output. */
+
+ line_directive_out( stdout );
+
+ if ( sectnum == 3 )
+ (void) flexscan(); /* copy remainder of input to output */
+ }
diff --git a/usr.bin/lex/initscan.c b/usr.bin/lex/initscan.c
new file mode 100644
index 000000000000..7daaef23826a
--- /dev/null
+++ b/usr.bin/lex/initscan.c
@@ -0,0 +1,2723 @@
+/* A lexical scanner generated by flex */
+
+/* Scanner skeleton version:
+ * $Header: /home/daffy/u0/vern/flex/flex-2.4.7/RCS/flex.skl,v 1.2 94/08/03 11:13:24 vern Exp $
+ */
+
+#define FLEX_SCANNER
+
+#include <stdio.h>
+
+
+/* cfront 1.2 defines "c_plusplus" instead of "__cplusplus" */
+#ifdef c_plusplus
+#ifndef __cplusplus
+#define __cplusplus
+#endif
+#endif
+
+
+#ifdef __cplusplus
+
+#include <stdlib.h>
+#include <unistd.h>
+
+/* Use prototypes in function declarations. */
+#define YY_USE_PROTOS
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else /* ! __cplusplus */
+
+#ifdef __STDC__
+
+#define YY_USE_PROTOS
+#define YY_USE_CONST
+
+#endif /* __STDC__ */
+#endif /* ! __cplusplus */
+
+
+#ifdef __TURBOC__
+#define YY_USE_CONST
+#endif
+
+
+#ifndef YY_USE_CONST
+#ifndef const
+#define const
+#endif
+#endif
+
+
+#ifdef YY_USE_PROTOS
+#define YY_PROTO(proto) proto
+#else
+#define YY_PROTO(proto) ()
+#endif
+
+/* Returned upon end-of-file. */
+#define YY_NULL 0
+
+/* Promotes a possibly negative, possibly signed char to an unsigned
+ * integer for use as an array index. If the signed char is negative,
+ * we want to instead treat it as an 8-bit unsigned char, hence the
+ * double cast.
+ */
+#define YY_SC_TO_UI(c) ((unsigned int) (unsigned char) c)
+
+/* Enter a start condition. This macro really ought to take a parameter,
+ * but we do it the disgusting crufty way forced on us by the ()-less
+ * definition of BEGIN.
+ */
+#define BEGIN yy_start = 1 + 2 *
+
+/* Translate the current start state into a value that can be later handed
+ * to BEGIN to return to the state.
+ */
+#define YY_START ((yy_start - 1) / 2)
+
+/* Action number for EOF rule of a given start state. */
+#define YY_STATE_EOF(state) (YY_END_OF_BUFFER + state + 1)
+
+/* Special action meaning "start processing a new file". Now included
+ * only for backward compatibility with previous versions of flex.
+ */
+#define YY_NEW_FILE yyrestart( yyin )
+
+#define YY_END_OF_BUFFER_CHAR 0
+
+/* Size of default input buffer. */
+#define YY_BUF_SIZE 16384
+
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+
+extern int yyleng;
+extern FILE *yyin, *yyout;
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+ extern int yywrap YY_PROTO(( void ));
+#ifdef __cplusplus
+ }
+#endif
+
+#define EOB_ACT_CONTINUE_SCAN 0
+#define EOB_ACT_END_OF_FILE 1
+#define EOB_ACT_LAST_MATCH 2
+
+/* The funky do-while in the following #define is used to turn the definition
+ * int a single C statement (which needs a semi-colon terminator). This
+ * avoids problems with code like:
+ *
+ * if ( condition_holds )
+ * yyless( 5 );
+ * else
+ * do_something_else();
+ *
+ * Prior to using the do-while the compiler would get upset at the
+ * "else" because it interpreted the "if" statement as being all
+ * done when it reached the ';' after the yyless() call.
+ */
+
+/* Return all but the first 'n' matched characters back to the input stream. */
+
+#define yyless(n) \
+ do \
+ { \
+ /* Undo effects of setting up yytext. */ \
+ *yy_cp = yy_hold_char; \
+ yy_c_buf_p = yy_cp = yy_bp + n - YY_MORE_ADJ; \
+ YY_DO_BEFORE_ACTION; /* set up yytext again */ \
+ } \
+ while ( 0 )
+
+#define unput(c) yyunput( c, yytext_ptr )
+
+
+struct yy_buffer_state
+ {
+ FILE *yy_input_file;
+
+ char *yy_ch_buf; /* input buffer */
+ char *yy_buf_pos; /* current position in input buffer */
+
+ /* Size of input buffer in bytes, not including room for EOB
+ * characters.
+ */
+ int yy_buf_size;
+
+ /* Number of characters read into yy_ch_buf, not including EOB
+ * characters.
+ */
+ int yy_n_chars;
+
+ /* Whether this is an "interactive" input source; if so, and
+ * if we're using stdio for input, then we want to use getc()
+ * instead of fread(), to make sure we stop fetching input after
+ * each newline.
+ */
+ int yy_is_interactive;
+
+ /* Whether to try to fill the input buffer when we reach the
+ * end of it.
+ */
+ int yy_fill_buffer;
+
+ int yy_buffer_status;
+#define YY_BUFFER_NEW 0
+#define YY_BUFFER_NORMAL 1
+ /* When an EOF's been seen but there's still some text to process
+ * then we mark the buffer as YY_EOF_PENDING, to indicate that we
+ * shouldn't try reading from the input source any more. We might
+ * still have a bunch of tokens to match, though, because of
+ * possible backing-up.
+ *
+ * When we actually see the EOF, we change the status to "new"
+ * (via yyrestart()), so that the user can continue scanning by
+ * just pointing yyin at a new input file.
+ */
+#define YY_BUFFER_EOF_PENDING 2
+ };
+
+static YY_BUFFER_STATE yy_current_buffer = 0;
+
+/* We provide macros for accessing buffer states in case in the
+ * future we want to put the buffer states in a more general
+ * "scanner state".
+ */
+#define YY_CURRENT_BUFFER yy_current_buffer
+
+
+/* yy_hold_char holds the character lost when yytext is formed. */
+static char yy_hold_char;
+
+static int yy_n_chars; /* number of characters read into yy_ch_buf */
+
+
+int yyleng;
+
+/* Points to current character in buffer. */
+static char *yy_c_buf_p = (char *) 0;
+static int yy_init = 1; /* whether we need to initialize */
+static int yy_start = 0; /* start state number */
+
+/* Flag which is used to allow yywrap()'s to do buffer switches
+ * instead of setting up a fresh yyin. A bit of a hack ...
+ */
+static int yy_did_buffer_switch_on_eof;
+
+static void yyunput YY_PROTO(( int c, char *buf_ptr ));
+void yyrestart YY_PROTO(( FILE *input_file ));
+void yy_switch_to_buffer YY_PROTO(( YY_BUFFER_STATE new_buffer ));
+void yy_load_buffer_state YY_PROTO(( void ));
+YY_BUFFER_STATE yy_create_buffer YY_PROTO(( FILE *file, int size ));
+void yy_delete_buffer YY_PROTO(( YY_BUFFER_STATE b ));
+void yy_init_buffer YY_PROTO(( YY_BUFFER_STATE b, FILE *file ));
+
+static int yy_start_stack_ptr = 0;
+static int yy_start_stack_depth = 0;
+static int *yy_start_stack = 0;
+static void yy_push_state YY_PROTO(( int new_state ));
+static void yy_pop_state YY_PROTO(( void ));
+static int yy_top_state YY_PROTO(( void ));
+
+static void *yy_flex_alloc YY_PROTO(( unsigned int ));
+static void *yy_flex_realloc YY_PROTO(( void *, unsigned int ));
+static void yy_flex_free YY_PROTO(( void * ));
+
+#define yy_new_buffer yy_create_buffer
+
+#define INITIAL 0
+#define SECT2 1
+#define SECT2PROLOG 2
+#define SECT3 3
+#define CODEBLOCK 4
+#define PICKUPDEF 5
+#define SC 6
+#define CARETISBOL 7
+#define NUM 8
+#define QUOTE 9
+#define FIRSTCCL 10
+#define CCL 11
+#define ACTION 12
+#define RECOVER 13
+#define BRACEERROR 14
+#define C_COMMENT 15
+#define ACTION_COMMENT 16
+#define ACTION_STRING 17
+#define PERCENT_BRACE_ACTION 18
+#define USED_LIST 19
+#define CODEBLOCK_2 20
+typedef unsigned char YY_CHAR;
+typedef int yy_state_type;
+FILE *yyin = (FILE *) 0, *yyout = (FILE *) 0;
+extern char *yytext;
+#define yytext_ptr yytext
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy YY_PROTO(( char *, const char *, int ));
+#endif
+
+#ifdef __cplusplus
+static int yyinput YY_PROTO(( void ));
+#else
+static int input YY_PROTO(( void ));
+#endif
+
+static yy_state_type yy_get_previous_state YY_PROTO(( void ));
+static yy_state_type yy_try_NUL_trans YY_PROTO(( yy_state_type current_state ));
+static int yy_get_next_buffer YY_PROTO(( void ));
+static void yy_fatal_error YY_PROTO(( const char msg[] ));
+
+/* Done after the current pattern has been matched and before the
+ * corresponding action - sets up yytext.
+ */
+#define YY_DO_BEFORE_ACTION \
+ yytext_ptr = yy_bp; \
+ yyleng = yy_cp - yy_bp; \
+ yy_hold_char = *yy_cp; \
+ *yy_cp = '\0'; \
+ yy_c_buf_p = yy_cp;
+
+#define YY_END_OF_BUFFER 113
+static const short int yy_accept[408] =
+ { 0,
+ 0, 0, 0, 0, 41, 41, 110, 110, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 113, 111, 6, 17, 111, 15, 1, 16,
+ 111, 111, 111, 14, 60, 53, 54, 60, 47, 60,
+ 59, 60, 60, 60, 60, 44, 43, 60, 60, 45,
+ 46, 41, 42, 41, 40, 39, 40, 40, 110, 110,
+ 26, 27, 26, 26, 26, 26, 26, 26, 29, 28,
+ 30, 29, 65, 61, 62, 64, 66, 80, 81, 80,
+
+ 78, 77, 79, 67, 69, 67, 68, 67, 72, 72,
+ 72, 74, 76, 74, 74, 74, 75, 92, 97, 92,
+ 96, 98, 98, 93, 93, 93, 90, 91, 111, 31,
+ 111, 83, 111, 82, 20, 22, 20, 21, 101, 102,
+ 101, 100, 103, 105, 103, 106, 107, 88, 88, 89,
+ 88, 88, 88, 88, 88, 88, 36, 33, 32, 36,
+ 36, 36, 88, 6, 17, 0, 17, 15, 1, 16,
+ 0, 16, 13, 7, 0, 0, 0, 3, 0, 4,
+ 0, 2, 14, 53, 54, 0, 0, 0, 54, 50,
+ 50, 0, 0, 57, 0, 108, 108, 108, 49, 48,
+
+ 49, 44, 43, 0, 43, 56, 44, 41, 42, 40,
+ 39, 39, 37, 38, 110, 110, 26, 27, 26, 26,
+ 26, 26, 29, 28, 30, 63, 64, 81, 77, 69,
+ 109, 109, 109, 70, 71, 76, 73, 92, 97, 0,
+ 95, 0, 94, 93, 93, 93, 0, 31, 0, 31,
+ 31, 83, 20, 22, 18, 101, 102, 101, 102, 102,
+ 99, 103, 105, 104, 88, 88, 88, 89, 85, 88,
+ 88, 88, 36, 33, 32, 36, 36, 84, 13, 7,
+ 0, 12, 0, 0, 0, 0, 3, 0, 0, 4,
+ 0, 5, 0, 51, 0, 52, 0, 0, 57, 0,
+
+ 57, 57, 108, 108, 49, 49, 58, 56, 37, 38,
+ 26, 26, 26, 23, 26, 0, 109, 109, 93, 93,
+ 0, 19, 0, 85, 85, 88, 88, 36, 36, 12,
+ 0, 0, 0, 3, 0, 0, 4, 5, 5, 52,
+ 52, 0, 57, 57, 57, 57, 108, 26, 26, 23,
+ 23, 0, 109, 93, 93, 19, 19, 88, 88, 36,
+ 36, 0, 0, 0, 10, 0, 57, 57, 57, 57,
+ 26, 26, 93, 93, 88, 88, 36, 36, 0, 0,
+ 0, 0, 57, 57, 24, 25, 86, 87, 86, 87,
+ 34, 35, 0, 9, 0, 0, 11, 55, 9, 9,
+
+ 0, 0, 8, 0, 8, 8, 0
+ } ;
+
+static const int yy_ec[256] =
+ { 0,
+ 1, 1, 1, 1, 1, 1, 1, 1, 2, 3,
+ 1, 1, 4, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 2, 1, 5, 1, 6, 7, 1, 8, 9,
+ 9, 10, 9, 11, 12, 9, 13, 14, 14, 14,
+ 14, 14, 14, 14, 14, 14, 14, 1, 1, 15,
+ 1, 16, 9, 1, 22, 23, 24, 25, 26, 27,
+ 21, 21, 28, 29, 30, 21, 31, 32, 33, 34,
+ 21, 35, 36, 37, 38, 21, 21, 39, 40, 21,
+ 17, 18, 19, 20, 21, 1, 22, 23, 24, 25,
+
+ 26, 27, 21, 21, 28, 29, 30, 21, 31, 32,
+ 33, 34, 21, 35, 36, 37, 38, 21, 21, 39,
+ 40, 21, 41, 42, 43, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1
+ } ;
+
+static const int yy_meta[44] =
+ { 0,
+ 1, 2, 3, 1, 4, 1, 1, 5, 1, 6,
+ 1, 7, 5, 8, 1, 1, 1, 9, 10, 1,
+ 11, 12, 12, 12, 12, 12, 12, 11, 11, 11,
+ 11, 11, 11, 11, 11, 11, 13, 11, 11, 11,
+ 5, 1, 14
+ } ;
+
+static const short int yy_base[470] =
+ { 0,
+ 0, 43, 85, 126, 89, 102, 1611, 1610, 168, 1605,
+ 108, 111, 211, 0, 1591, 1590, 252, 254, 116, 119,
+ 98, 122, 144, 146, 297, 0, 93, 104, 338, 340,
+ 149, 151, 257, 266, 268, 274, 383, 0, 425, 428,
+ 1596, 1595, 1607, 1615, 278, 1602, 1602, 0, 281, 1600,
+ 1600, 462, 1592, 0, 1615, 431, 1597, 1597, 1615, 285,
+ 1615, 1584, 1580, 331, 503, 437, 1593, 1593, 110, 1580,
+ 1615, 0, 1590, 1590, 0, 1590, 1588, 221, 1587, 1615,
+ 0, 1585, 1585, 1615, 0, 1561, 1546, 1511, 0, 1551,
+ 1543, 1543, 1615, 1615, 1498, 0, 1615, 1615, 1500, 1487,
+
+ 1615, 1463, 1615, 1615, 1466, 1460, 1615, 332, 1615, 333,
+ 126, 1615, 1411, 1398, 0, 334, 1615, 0, 1383, 1383,
+ 1615, 341, 1371, 0, 1354, 1336, 1615, 1615, 271, 1371,
+ 287, 1370, 1366, 1615, 0, 1362, 1349, 1331, 290, 1335,
+ 347, 1325, 0, 1323, 1310, 1615, 0, 0, 350, 1306,
+ 1287, 1246, 1615, 0, 1249, 1227, 0, 1264, 1261, 1255,
+ 1225, 1197, 1213, 351, 1213, 1213, 1615, 0, 358, 1198,
+ 1193, 1615, 0, 0, 443, 361, 447, 0, 342, 0,
+ 363, 1615, 0, 451, 1191, 1188, 1149, 365, 1615, 1615,
+ 1185, 1181, 1155, 1135, 423, 1615, 1125, 0, 0, 1615,
+
+ 546, 588, 1121, 1108, 1615, 0, 1615, 0, 1615, 0,
+ 0, 1095, 0, 0, 1088, 1615, 0, 1615, 0, 1061,
+ 1041, 630, 0, 1069, 1615, 1615, 0, 1615, 838, 1615,
+ 1615, 837, 0, 1615, 1615, 1615, 1615, 0, 1615, 434,
+ 1615, 0, 1615, 0, 821, 817, 373, 843, 376, 1615,
+ 842, 1615, 0, 1615, 463, 467, 834, 471, 1615, 833,
+ 1615, 0, 1615, 1615, 0, 441, 793, 1615, 673, 0,
+ 805, 802, 0, 830, 1615, 795, 792, 1615, 0, 0,
+ 594, 818, 817, 597, 784, 790, 0, 775, 786, 0,
+ 473, 807, 478, 1615, 486, 806, 590, 776, 790, 588,
+
+ 469, 703, 793, 0, 0, 0, 1615, 0, 0, 0,
+ 780, 772, 0, 800, 800, 730, 788, 0, 775, 767,
+ 600, 795, 602, 0, 773, 772, 764, 770, 762, 1615,
+ 610, 772, 751, 0, 740, 745, 0, 1615, 765, 1615,
+ 764, 740, 488, 803, 601, 817, 1615, 742, 730, 1615,
+ 760, 760, 1615, 738, 726, 1615, 756, 735, 723, 733,
+ 721, 714, 716, 726, 1615, 724, 602, 831, 715, 658,
+ 512, 473, 454, 459, 435, 438, 422, 430, 606, 410,
+ 357, 342, 338, 278, 0, 0, 0, 0, 0, 0,
+ 0, 0, 614, 255, 618, 131, 1615, 1615, 1615, 156,
+
+ 620, 622, 153, 625, 1615, 95, 1615, 858, 872, 886,
+ 900, 914, 928, 942, 956, 970, 984, 998, 1012, 1026,
+ 1040, 1054, 1062, 1075, 1081, 1094, 1108, 1122, 1136, 1150,
+ 1164, 1178, 1186, 1199, 1207, 1220, 1234, 1248, 1262, 1272,
+ 1280, 1293, 1307, 1321, 1335, 1349, 1363, 1371, 1384, 1398,
+ 1412, 1416, 1419, 1432, 1446, 1460, 710, 1474, 1487, 1501,
+ 1515, 711, 1529, 1537, 1544, 712, 743, 1557, 1571
+ } ;
+
+static const short int yy_def[470] =
+ { 0,
+ 407, 407, 408, 408, 409, 410, 411, 411, 407, 9,
+ 412, 412, 407, 13, 413, 413, 414, 414, 415, 415,
+ 416, 416, 417, 417, 407, 25, 418, 418, 413, 413,
+ 419, 419, 420, 420, 421, 421, 407, 37, 422, 422,
+ 37, 37, 407, 407, 407, 407, 407, 423, 407, 407,
+ 407, 424, 407, 425, 407, 407, 407, 407, 407, 407,
+ 407, 407, 426, 427, 407, 407, 407, 407, 407, 407,
+ 407, 428, 407, 428, 429, 430, 429, 429, 431, 407,
+ 432, 407, 432, 407, 433, 433, 433, 432, 434, 407,
+ 407, 434, 407, 407, 407, 435, 407, 407, 407, 407,
+
+ 407, 407, 407, 407, 407, 407, 407, 427, 407, 436,
+ 437, 407, 407, 407, 438, 427, 407, 439, 407, 439,
+ 407, 440, 407, 441, 441, 441, 407, 407, 442, 407,
+ 442, 407, 407, 407, 443, 407, 443, 407, 444, 407,
+ 444, 407, 445, 407, 445, 407, 446, 447, 447, 407,
+ 447, 447, 407, 448, 448, 448, 449, 407, 407, 449,
+ 449, 449, 447, 407, 407, 407, 407, 423, 407, 407,
+ 407, 407, 450, 451, 407, 407, 407, 452, 407, 453,
+ 454, 407, 425, 407, 407, 407, 407, 455, 407, 407,
+ 407, 407, 407, 456, 426, 407, 407, 457, 458, 407,
+
+ 407, 407, 407, 407, 407, 459, 407, 428, 407, 429,
+ 430, 430, 460, 461, 431, 407, 432, 407, 433, 433,
+ 433, 407, 434, 407, 407, 407, 435, 407, 407, 407,
+ 407, 407, 462, 407, 407, 407, 407, 439, 407, 440,
+ 407, 440, 407, 441, 441, 441, 442, 407, 442, 407,
+ 407, 407, 443, 407, 463, 444, 407, 444, 407, 407,
+ 407, 445, 407, 407, 447, 447, 447, 407, 407, 448,
+ 448, 448, 449, 407, 407, 449, 449, 407, 450, 451,
+ 407, 407, 407, 407, 407, 407, 464, 407, 407, 465,
+ 454, 407, 454, 407, 455, 407, 455, 407, 456, 456,
+
+ 456, 456, 407, 466, 458, 201, 407, 459, 460, 461,
+ 433, 433, 222, 407, 222, 222, 407, 467, 441, 441,
+ 463, 407, 463, 269, 269, 448, 448, 449, 449, 407,
+ 407, 407, 407, 464, 407, 407, 465, 407, 407, 407,
+ 407, 407, 456, 456, 456, 456, 407, 433, 433, 407,
+ 407, 316, 407, 441, 441, 407, 407, 448, 448, 449,
+ 449, 407, 407, 407, 407, 407, 456, 456, 456, 456,
+ 433, 433, 441, 441, 448, 448, 449, 449, 468, 407,
+ 407, 407, 456, 456, 433, 433, 441, 441, 448, 448,
+ 449, 449, 468, 407, 468, 407, 407, 407, 407, 407,
+
+ 469, 469, 407, 469, 407, 407, 0, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407
+ } ;
+
+static const short int yy_nxt[1659] =
+ { 0,
+ 44, 45, 46, 47, 44, 44, 44, 44, 44, 44,
+ 44, 44, 44, 44, 44, 44, 44, 44, 44, 44,
+ 48, 48, 48, 48, 48, 48, 48, 48, 48, 48,
+ 48, 48, 48, 48, 48, 48, 48, 48, 48, 48,
+ 44, 44, 44, 44, 49, 50, 51, 44, 44, 52,
+ 44, 44, 44, 44, 44, 53, 44, 44, 44, 44,
+ 44, 44, 44, 54, 54, 54, 54, 54, 54, 54,
+ 54, 54, 54, 54, 54, 54, 54, 54, 54, 54,
+ 54, 54, 54, 44, 44, 44, 56, 57, 58, 59,
+ 60, 73, 74, 61, 61, 130, 131, 61, 405, 62,
+
+ 44, 63, 64, 76, 73, 77, 130, 131, 78, 90,
+ 91, 92, 90, 91, 92, 110, 206, 111, 105, 106,
+ 107, 105, 106, 107, 44, 65, 61, 66, 67, 68,
+ 59, 60, 69, 108, 61, 61, 108, 235, 61, 110,
+ 70, 111, 63, 64, 235, 71, 113, 114, 113, 114,
+ 207, 136, 137, 136, 137, 115, 405, 115, 138, 399,
+ 138, 116, 117, 116, 117, 401, 65, 61, 81, 81,
+ 82, 83, 81, 81, 81, 81, 81, 84, 81, 81,
+ 81, 81, 81, 81, 81, 81, 81, 81, 85, 85,
+ 85, 85, 85, 85, 85, 85, 85, 85, 85, 85,
+
+ 85, 85, 86, 85, 85, 85, 85, 87, 81, 81,
+ 81, 93, 93, 44, 93, 93, 93, 93, 93, 93,
+ 94, 94, 93, 93, 93, 93, 95, 93, 93, 93,
+ 93, 96, 96, 96, 96, 96, 96, 96, 96, 96,
+ 96, 96, 96, 96, 96, 96, 96, 96, 96, 96,
+ 96, 93, 93, 93, 99, 100, 99, 100, 399, 140,
+ 141, 213, 101, 214, 101, 102, 142, 102, 140, 141,
+ 144, 145, 146, 248, 249, 142, 144, 145, 146, 164,
+ 165, 166, 169, 170, 171, 147, 190, 191, 192, 251,
+ 249, 147, 257, 258, 103, 300, 103, 118, 118, 119,
+
+ 120, 121, 118, 118, 122, 118, 118, 118, 118, 123,
+ 118, 118, 118, 118, 118, 118, 118, 124, 124, 124,
+ 124, 124, 124, 124, 124, 124, 124, 124, 124, 124,
+ 124, 125, 124, 124, 124, 124, 126, 127, 118, 128,
+ 132, 133, 132, 133, 197, 197, 232, 197, 241, 260,
+ 258, 266, 164, 165, 166, 300, 267, 398, 242, 169,
+ 170, 171, 281, 282, 283, 292, 293, 296, 297, 198,
+ 198, 233, 198, 288, 284, 248, 249, 289, 251, 249,
+ 134, 397, 134, 148, 149, 150, 151, 148, 148, 152,
+ 148, 148, 153, 148, 148, 148, 148, 148, 148, 148,
+
+ 148, 148, 148, 154, 154, 154, 154, 154, 154, 154,
+ 154, 154, 154, 154, 154, 154, 154, 155, 154, 154,
+ 154, 154, 156, 148, 148, 148, 158, 159, 160, 158,
+ 159, 160, 184, 185, 186, 396, 301, 187, 202, 203,
+ 204, 241, 266, 187, 281, 282, 283, 267, 281, 282,
+ 283, 242, 184, 185, 186, 392, 284, 187, 391, 161,
+ 284, 302, 161, 390, 162, 322, 323, 162, 174, 257,
+ 258, 389, 188, 260, 258, 292, 293, 285, 188, 286,
+ 339, 293, 345, 175, 388, 176, 300, 176, 296, 297,
+ 387, 176, 188, 176, 176, 177, 176, 178, 386, 179,
+
+ 180, 367, 181, 199, 199, 300, 199, 199, 199, 199,
+ 199, 199, 199, 199, 199, 199, 200, 199, 199, 199,
+ 199, 199, 199, 201, 201, 201, 201, 201, 201, 201,
+ 201, 201, 201, 201, 201, 201, 201, 201, 201, 201,
+ 201, 201, 201, 199, 199, 199, 305, 305, 385, 305,
+ 305, 305, 305, 305, 305, 305, 305, 306, 305, 306,
+ 305, 305, 305, 305, 305, 305, 306, 306, 306, 306,
+ 306, 306, 306, 306, 306, 306, 306, 306, 306, 306,
+ 306, 306, 306, 306, 306, 306, 305, 305, 307, 202,
+ 203, 204, 341, 297, 187, 281, 282, 283, 331, 282,
+
+ 283, 343, 322, 323, 357, 323, 299, 284, 394, 395,
+ 284, 331, 282, 283, 369, 383, 394, 395, 300, 300,
+ 400, 395, 403, 404, 403, 404, 344, 406, 404, 188,
+ 313, 313, 314, 315, 313, 313, 313, 313, 313, 316,
+ 313, 313, 313, 313, 313, 313, 313, 313, 313, 313,
+ 316, 316, 316, 316, 316, 316, 316, 316, 316, 316,
+ 316, 316, 316, 316, 316, 316, 316, 316, 316, 316,
+ 313, 313, 313, 324, 324, 300, 324, 324, 324, 324,
+ 324, 324, 325, 324, 324, 324, 324, 324, 324, 324,
+ 324, 324, 324, 325, 325, 325, 325, 325, 325, 325,
+
+ 325, 325, 325, 325, 325, 325, 325, 325, 325, 325,
+ 325, 325, 325, 324, 324, 324, 346, 304, 318, 347,
+ 300, 304, 318, 347, 346, 346, 346, 346, 346, 346,
+ 316, 316, 300, 352, 316, 316, 316, 316, 316, 382,
+ 316, 316, 316, 316, 316, 316, 316, 316, 316, 316,
+ 353, 381, 380, 379, 353, 378, 377, 376, 375, 356,
+ 374, 373, 351, 350, 372, 371, 366, 340, 338, 365,
+ 316, 316, 316, 325, 325, 364, 325, 325, 325, 325,
+ 325, 325, 363, 325, 325, 325, 325, 325, 325, 325,
+ 325, 325, 325, 362, 361, 360, 359, 358, 356, 355,
+
+ 354, 231, 351, 350, 349, 348, 196, 300, 342, 340,
+ 338, 336, 335, 325, 325, 325, 368, 333, 332, 330,
+ 300, 330, 329, 328, 368, 368, 368, 368, 368, 368,
+ 370, 274, 327, 326, 300, 269, 259, 259, 370, 370,
+ 370, 370, 370, 370, 384, 250, 250, 320, 300, 319,
+ 317, 229, 384, 384, 384, 384, 384, 384, 55, 55,
+ 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,
+ 55, 55, 72, 72, 72, 72, 72, 72, 72, 72,
+ 72, 72, 72, 72, 72, 72, 75, 75, 75, 75,
+ 75, 75, 75, 75, 75, 75, 75, 75, 75, 75,
+
+ 79, 79, 79, 79, 79, 79, 79, 79, 79, 79,
+ 79, 79, 79, 79, 89, 89, 89, 89, 89, 89,
+ 89, 89, 89, 89, 89, 89, 89, 89, 44, 44,
+ 44, 44, 44, 44, 44, 44, 44, 44, 44, 44,
+ 44, 44, 98, 98, 98, 98, 98, 98, 98, 98,
+ 98, 98, 98, 98, 98, 98, 104, 104, 104, 104,
+ 104, 104, 104, 104, 104, 104, 104, 104, 104, 104,
+ 109, 109, 109, 109, 109, 109, 109, 109, 109, 109,
+ 109, 109, 109, 109, 112, 112, 112, 112, 112, 112,
+ 112, 112, 112, 112, 112, 112, 112, 112, 129, 129,
+
+ 129, 129, 129, 129, 129, 129, 129, 129, 129, 129,
+ 129, 129, 135, 135, 135, 135, 135, 135, 135, 135,
+ 135, 135, 135, 135, 135, 135, 139, 139, 139, 139,
+ 139, 139, 139, 139, 139, 139, 139, 139, 139, 139,
+ 143, 143, 143, 143, 143, 143, 143, 143, 143, 143,
+ 143, 143, 143, 143, 157, 157, 157, 157, 157, 157,
+ 157, 157, 157, 157, 157, 157, 157, 157, 168, 168,
+ 224, 312, 168, 168, 168, 173, 173, 173, 173, 173,
+ 173, 173, 173, 173, 173, 173, 173, 183, 183, 311,
+ 216, 183, 183, 183, 194, 194, 212, 194, 194, 194,
+
+ 194, 194, 194, 194, 194, 194, 194, 194, 196, 196,
+ 205, 196, 196, 196, 196, 196, 196, 196, 196, 196,
+ 196, 196, 208, 208, 205, 208, 208, 208, 208, 208,
+ 208, 208, 208, 208, 208, 208, 210, 210, 303, 210,
+ 210, 210, 210, 210, 210, 210, 210, 210, 210, 210,
+ 211, 211, 300, 211, 211, 211, 211, 211, 211, 211,
+ 211, 211, 211, 211, 215, 215, 215, 215, 215, 215,
+ 215, 215, 215, 215, 215, 215, 215, 215, 217, 217,
+ 298, 217, 217, 190, 217, 217, 217, 217, 190, 294,
+ 189, 217, 219, 219, 189, 172, 219, 219, 219, 223,
+
+ 223, 172, 223, 223, 223, 223, 223, 223, 223, 223,
+ 223, 223, 223, 227, 227, 167, 167, 227, 227, 227,
+ 231, 231, 278, 231, 231, 231, 231, 231, 231, 231,
+ 231, 231, 231, 231, 234, 234, 277, 234, 234, 234,
+ 234, 234, 234, 234, 234, 234, 234, 234, 237, 237,
+ 276, 237, 237, 237, 237, 237, 237, 275, 237, 237,
+ 237, 237, 238, 238, 275, 274, 272, 238, 238, 238,
+ 238, 238, 240, 240, 271, 240, 240, 240, 240, 240,
+ 240, 240, 240, 240, 240, 240, 244, 244, 269, 268,
+ 244, 244, 244, 247, 247, 247, 247, 247, 247, 247,
+
+ 247, 247, 247, 247, 247, 247, 247, 253, 253, 268,
+ 253, 253, 263, 253, 253, 253, 253, 253, 253, 253,
+ 253, 256, 256, 256, 256, 256, 263, 256, 256, 256,
+ 256, 256, 256, 256, 256, 262, 262, 261, 259, 262,
+ 262, 262, 262, 255, 262, 262, 262, 262, 262, 264,
+ 264, 254, 264, 264, 264, 264, 264, 264, 264, 264,
+ 264, 264, 264, 265, 265, 254, 265, 265, 252, 265,
+ 265, 265, 265, 252, 250, 246, 265, 270, 270, 245,
+ 243, 270, 270, 270, 273, 239, 239, 273, 273, 273,
+ 273, 273, 273, 273, 273, 273, 273, 273, 279, 279,
+
+ 236, 279, 279, 279, 279, 279, 279, 279, 279, 279,
+ 279, 279, 280, 280, 236, 280, 280, 280, 280, 280,
+ 280, 280, 280, 280, 280, 280, 287, 287, 287, 290,
+ 290, 290, 291, 291, 291, 291, 291, 291, 291, 291,
+ 291, 291, 291, 291, 291, 291, 295, 295, 295, 295,
+ 295, 295, 295, 295, 295, 295, 295, 295, 295, 295,
+ 299, 299, 230, 299, 299, 299, 299, 299, 299, 230,
+ 299, 299, 299, 299, 305, 305, 229, 305, 305, 305,
+ 305, 305, 305, 305, 305, 305, 305, 308, 308, 228,
+ 308, 308, 308, 308, 308, 308, 308, 308, 308, 308,
+
+ 308, 309, 309, 228, 309, 309, 309, 309, 309, 309,
+ 309, 309, 309, 309, 309, 310, 310, 226, 310, 310,
+ 310, 310, 310, 310, 310, 310, 310, 310, 310, 321,
+ 321, 321, 321, 321, 321, 321, 321, 321, 321, 321,
+ 321, 321, 321, 334, 334, 225, 225, 334, 334, 334,
+ 337, 337, 224, 222, 337, 337, 337, 393, 393, 393,
+ 393, 393, 393, 393, 393, 393, 393, 393, 393, 393,
+ 393, 402, 402, 402, 402, 402, 402, 402, 402, 402,
+ 402, 402, 402, 402, 402, 221, 220, 218, 218, 216,
+ 209, 212, 209, 209, 193, 205, 205, 195, 193, 189,
+
+ 189, 182, 172, 172, 167, 167, 407, 163, 163, 97,
+ 97, 88, 80, 80, 43, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407
+ } ;
+
+static const short int yy_chk[1659] =
+ { 0,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 3, 3, 3, 3,
+ 3, 5, 5, 3, 3, 27, 27, 3, 406, 3,
+
+ 21, 3, 3, 6, 6, 6, 28, 28, 6, 11,
+ 11, 11, 12, 12, 12, 21, 69, 21, 19, 19,
+ 19, 20, 20, 20, 22, 3, 3, 4, 4, 4,
+ 4, 4, 4, 19, 4, 4, 20, 111, 4, 22,
+ 4, 22, 4, 4, 111, 4, 23, 23, 24, 24,
+ 69, 31, 31, 32, 32, 23, 403, 24, 31, 400,
+ 32, 23, 23, 24, 24, 396, 4, 4, 9, 9,
+ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9,
+ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9,
+ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9,
+
+ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9,
+ 9, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 17, 17, 18, 18, 394, 33,
+ 33, 78, 17, 78, 18, 17, 33, 18, 34, 34,
+ 35, 35, 35, 129, 129, 34, 36, 36, 36, 45,
+ 45, 45, 49, 49, 49, 35, 60, 60, 60, 131,
+ 131, 36, 139, 139, 17, 384, 18, 25, 25, 25,
+
+ 25, 25, 25, 25, 25, 25, 25, 25, 25, 25,
+ 25, 25, 25, 25, 25, 25, 25, 25, 25, 25,
+ 25, 25, 25, 25, 25, 25, 25, 25, 25, 25,
+ 25, 25, 25, 25, 25, 25, 25, 25, 25, 25,
+ 29, 29, 30, 30, 64, 108, 110, 116, 122, 141,
+ 141, 149, 164, 164, 164, 383, 149, 382, 122, 169,
+ 169, 169, 176, 176, 176, 181, 181, 188, 188, 64,
+ 108, 110, 116, 179, 176, 247, 247, 179, 249, 249,
+ 29, 381, 30, 37, 37, 37, 37, 37, 37, 37,
+ 37, 37, 37, 37, 37, 37, 37, 37, 37, 37,
+
+ 37, 37, 37, 37, 37, 37, 37, 37, 37, 37,
+ 37, 37, 37, 37, 37, 37, 37, 37, 37, 37,
+ 37, 37, 37, 37, 37, 37, 39, 39, 39, 40,
+ 40, 40, 56, 56, 56, 380, 195, 56, 66, 66,
+ 66, 240, 266, 66, 175, 175, 175, 266, 177, 177,
+ 177, 240, 184, 184, 184, 378, 175, 184, 377, 39,
+ 177, 195, 40, 376, 39, 255, 255, 40, 52, 256,
+ 256, 375, 56, 258, 258, 291, 291, 175, 66, 177,
+ 293, 293, 301, 52, 374, 52, 301, 52, 295, 295,
+ 373, 52, 184, 52, 52, 52, 52, 52, 372, 52,
+
+ 52, 343, 52, 65, 65, 343, 65, 65, 65, 65,
+ 65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+ 65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+ 65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+ 65, 65, 65, 65, 65, 65, 201, 201, 371, 201,
+ 201, 201, 201, 201, 201, 201, 201, 201, 201, 201,
+ 201, 201, 201, 201, 201, 201, 201, 201, 201, 201,
+ 201, 201, 201, 201, 201, 201, 201, 201, 201, 201,
+ 201, 201, 201, 201, 201, 201, 201, 201, 201, 202,
+ 202, 202, 297, 297, 202, 281, 281, 281, 284, 284,
+
+ 284, 300, 321, 321, 323, 323, 300, 281, 379, 379,
+ 284, 331, 331, 331, 345, 367, 393, 393, 345, 367,
+ 395, 395, 401, 401, 402, 402, 300, 404, 404, 202,
+ 222, 222, 222, 222, 222, 222, 222, 222, 222, 222,
+ 222, 222, 222, 222, 222, 222, 222, 222, 222, 222,
+ 222, 222, 222, 222, 222, 222, 222, 222, 222, 222,
+ 222, 222, 222, 222, 222, 222, 222, 222, 222, 222,
+ 222, 222, 222, 269, 269, 370, 269, 269, 269, 269,
+ 269, 269, 269, 269, 269, 269, 269, 269, 269, 269,
+ 269, 269, 269, 269, 269, 269, 269, 269, 269, 269,
+
+ 269, 269, 269, 269, 269, 269, 269, 269, 269, 269,
+ 269, 269, 269, 269, 269, 269, 302, 457, 462, 466,
+ 302, 457, 462, 466, 302, 302, 302, 302, 302, 302,
+ 316, 316, 369, 316, 316, 316, 316, 316, 316, 366,
+ 316, 316, 316, 316, 316, 316, 316, 316, 316, 316,
+ 467, 364, 363, 362, 467, 361, 360, 359, 358, 357,
+ 355, 354, 352, 351, 349, 348, 342, 341, 339, 336,
+ 316, 316, 316, 325, 325, 335, 325, 325, 325, 325,
+ 325, 325, 333, 325, 325, 325, 325, 325, 325, 325,
+ 325, 325, 325, 332, 329, 328, 327, 326, 322, 320,
+
+ 319, 317, 315, 314, 312, 311, 303, 299, 298, 296,
+ 292, 289, 288, 325, 325, 325, 344, 286, 285, 283,
+ 344, 282, 277, 276, 344, 344, 344, 344, 344, 344,
+ 346, 274, 272, 271, 346, 267, 260, 257, 346, 346,
+ 346, 346, 346, 346, 368, 251, 248, 246, 368, 245,
+ 232, 229, 368, 368, 368, 368, 368, 368, 408, 408,
+ 408, 408, 408, 408, 408, 408, 408, 408, 408, 408,
+ 408, 408, 409, 409, 409, 409, 409, 409, 409, 409,
+ 409, 409, 409, 409, 409, 409, 410, 410, 410, 410,
+ 410, 410, 410, 410, 410, 410, 410, 410, 410, 410,
+
+ 411, 411, 411, 411, 411, 411, 411, 411, 411, 411,
+ 411, 411, 411, 411, 412, 412, 412, 412, 412, 412,
+ 412, 412, 412, 412, 412, 412, 412, 412, 413, 413,
+ 413, 413, 413, 413, 413, 413, 413, 413, 413, 413,
+ 413, 413, 414, 414, 414, 414, 414, 414, 414, 414,
+ 414, 414, 414, 414, 414, 414, 415, 415, 415, 415,
+ 415, 415, 415, 415, 415, 415, 415, 415, 415, 415,
+ 416, 416, 416, 416, 416, 416, 416, 416, 416, 416,
+ 416, 416, 416, 416, 417, 417, 417, 417, 417, 417,
+ 417, 417, 417, 417, 417, 417, 417, 417, 418, 418,
+
+ 418, 418, 418, 418, 418, 418, 418, 418, 418, 418,
+ 418, 418, 419, 419, 419, 419, 419, 419, 419, 419,
+ 419, 419, 419, 419, 419, 419, 420, 420, 420, 420,
+ 420, 420, 420, 420, 420, 420, 420, 420, 420, 420,
+ 421, 421, 421, 421, 421, 421, 421, 421, 421, 421,
+ 421, 421, 421, 421, 422, 422, 422, 422, 422, 422,
+ 422, 422, 422, 422, 422, 422, 422, 422, 423, 423,
+ 224, 221, 423, 423, 423, 424, 424, 424, 424, 424,
+ 424, 424, 424, 424, 424, 424, 424, 425, 425, 220,
+ 215, 425, 425, 425, 426, 426, 212, 426, 426, 426,
+
+ 426, 426, 426, 426, 426, 426, 426, 426, 427, 427,
+ 204, 427, 427, 427, 427, 427, 427, 427, 427, 427,
+ 427, 427, 428, 428, 203, 428, 428, 428, 428, 428,
+ 428, 428, 428, 428, 428, 428, 429, 429, 197, 429,
+ 429, 429, 429, 429, 429, 429, 429, 429, 429, 429,
+ 430, 430, 194, 430, 430, 430, 430, 430, 430, 430,
+ 430, 430, 430, 430, 431, 431, 431, 431, 431, 431,
+ 431, 431, 431, 431, 431, 431, 431, 431, 432, 432,
+ 193, 432, 432, 192, 432, 432, 432, 432, 191, 187,
+ 186, 432, 433, 433, 185, 171, 433, 433, 433, 434,
+
+ 434, 170, 434, 434, 434, 434, 434, 434, 434, 434,
+ 434, 434, 434, 435, 435, 166, 165, 435, 435, 435,
+ 436, 436, 163, 436, 436, 436, 436, 436, 436, 436,
+ 436, 436, 436, 436, 437, 437, 162, 437, 437, 437,
+ 437, 437, 437, 437, 437, 437, 437, 437, 438, 438,
+ 161, 438, 438, 438, 438, 438, 438, 160, 438, 438,
+ 438, 438, 439, 439, 159, 158, 156, 439, 439, 439,
+ 439, 439, 440, 440, 155, 440, 440, 440, 440, 440,
+ 440, 440, 440, 440, 440, 440, 441, 441, 152, 151,
+ 441, 441, 441, 442, 442, 442, 442, 442, 442, 442,
+
+ 442, 442, 442, 442, 442, 442, 442, 443, 443, 150,
+ 443, 443, 145, 443, 443, 443, 443, 443, 443, 443,
+ 443, 444, 444, 444, 444, 444, 144, 444, 444, 444,
+ 444, 444, 444, 444, 444, 445, 445, 142, 140, 445,
+ 445, 445, 445, 138, 445, 445, 445, 445, 445, 446,
+ 446, 137, 446, 446, 446, 446, 446, 446, 446, 446,
+ 446, 446, 446, 447, 447, 136, 447, 447, 133, 447,
+ 447, 447, 447, 132, 130, 126, 447, 448, 448, 125,
+ 123, 448, 448, 448, 449, 120, 119, 449, 449, 449,
+ 449, 449, 449, 449, 449, 449, 449, 449, 450, 450,
+
+ 114, 450, 450, 450, 450, 450, 450, 450, 450, 450,
+ 450, 450, 451, 451, 113, 451, 451, 451, 451, 451,
+ 451, 451, 451, 451, 451, 451, 452, 452, 452, 453,
+ 453, 453, 454, 454, 454, 454, 454, 454, 454, 454,
+ 454, 454, 454, 454, 454, 454, 455, 455, 455, 455,
+ 455, 455, 455, 455, 455, 455, 455, 455, 455, 455,
+ 456, 456, 106, 456, 456, 456, 456, 456, 456, 105,
+ 456, 456, 456, 456, 458, 458, 102, 458, 458, 458,
+ 458, 458, 458, 458, 458, 458, 458, 459, 459, 100,
+ 459, 459, 459, 459, 459, 459, 459, 459, 459, 459,
+
+ 459, 460, 460, 99, 460, 460, 460, 460, 460, 460,
+ 460, 460, 460, 460, 460, 461, 461, 95, 461, 461,
+ 461, 461, 461, 461, 461, 461, 461, 461, 461, 463,
+ 463, 463, 463, 463, 463, 463, 463, 463, 463, 463,
+ 463, 463, 463, 464, 464, 92, 91, 464, 464, 464,
+ 465, 465, 90, 88, 465, 465, 465, 468, 468, 468,
+ 468, 468, 468, 468, 468, 468, 468, 468, 468, 468,
+ 468, 469, 469, 469, 469, 469, 469, 469, 469, 469,
+ 469, 469, 469, 469, 469, 87, 86, 83, 82, 79,
+ 77, 76, 74, 73, 70, 68, 67, 63, 62, 58,
+
+ 57, 53, 51, 50, 47, 46, 43, 42, 41, 16,
+ 15, 10, 8, 7, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407, 407, 407,
+ 407, 407, 407, 407, 407, 407, 407, 407
+ } ;
+
+static yy_state_type yy_last_accepting_state;
+static char *yy_last_accepting_cpos;
+
+/* The intent behind this definition is that it'll catch
+ * any uses of REJECT which flex missed.
+ */
+#define REJECT reject_used_but_not_detected
+#define yymore() yymore_used_but_not_detected
+#define YY_MORE_ADJ 0
+char *yytext;
+# line 1 "scan.l"
+/* scan.l - scanner for flex input */
+# line 4 "scan.l"
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: scan.l,v 1.2 94/01/04 14:33:09 vern Exp $ */
+
+#include "flexdef.h"
+#include "parse.h"
+
+#define ACTION_ECHO add_action( yytext )
+#define MARK_END_OF_PROLOG mark_prolog();
+
+#define YY_DECL \
+ int flexscan()
+
+#define RETURNCHAR \
+ yylval = (unsigned char) yytext[0]; \
+ return CHAR;
+
+#define RETURNNAME \
+ strcpy( nmstr, yytext ); \
+ return NAME;
+
+#define PUT_BACK_STRING(str, start) \
+ for ( i = strlen( str ) - 1; i >= start; --i ) \
+ unput((str)[i])
+
+#define CHECK_REJECT(str) \
+ if ( all_upper( str ) ) \
+ reject = true;
+
+#define CHECK_YYMORE(str) \
+ if ( all_lower( str ) ) \
+ yymore_used = true;
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifdef YY_MALLOC_DECL
+YY_MALLOC_DECL
+#else
+#if __STDC__
+#ifndef __cplusplus
+#include <stdlib.h>
+#endif
+#else
+/* Just try to get by without declaring the routines. This will fail
+ * miserably on non-ANSI systems for which sizeof(size_t) != sizeof(int)
+ * or sizeof(void*) != sizeof(int).
+ */
+#endif
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#define YY_READ_BUF_SIZE 8192
+#endif
+
+/* Copy whatever the last rule matched to the standard output. */
+
+#ifndef ECHO
+/* This used to be an fputs(), but since the string might contain NUL's,
+ * we now use fwrite().
+ */
+#define ECHO (void) fwrite( yytext, yyleng, 1, yyout )
+#endif
+
+/* Gets input and stuffs it into "buf". number of characters read, or YY_NULL,
+ * is returned in "result".
+ */
+#ifndef YY_INPUT
+#define YY_INPUT(buf,result,max_size) \
+ if ( yy_current_buffer->yy_is_interactive ) \
+ { \
+ int c = getc( yyin ); \
+ result = c == EOF ? 0 : 1; \
+ buf[0] = (char) c; \
+ } \
+ else if ( ((result = fread( buf, 1, max_size, yyin )) == 0) \
+ && ferror( yyin ) ) \
+ YY_FATAL_ERROR( "input in flex scanner failed" );
+#endif
+
+/* No semi-colon after return; correct usage is to write "yyterminate();" -
+ * we don't want an extra ';' after the "return" because that will cause
+ * some compilers to complain about unreachable statements.
+ */
+#ifndef yyterminate
+#define yyterminate() return YY_NULL
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Report a fatal error. */
+#ifndef YY_FATAL_ERROR
+#define YY_FATAL_ERROR(msg) yy_fatal_error( msg )
+#endif
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+#define YY_DECL int yylex YY_PROTO(( void ))
+#endif
+
+/* Code executed at the beginning of each rule, after yytext and yyleng
+ * have been set up.
+ */
+#ifndef YY_USER_ACTION
+#define YY_USER_ACTION
+#endif
+
+/* Code executed at the end of each rule. */
+#ifndef YY_BREAK
+#define YY_BREAK break;
+#endif
+
+YY_DECL
+ {
+ register yy_state_type yy_current_state;
+ register char *yy_cp, *yy_bp;
+ register int yy_act;
+
+# line 82 "scan.l"
+
+ static int bracelevel, didadef, indented_code, checking_used;
+
+ int doing_codeblock = false;
+ int i;
+ Char nmdef[MAXLINE], myesc();
+
+
+
+ if ( yy_init )
+ {
+#ifdef YY_USER_INIT
+ YY_USER_INIT;
+#endif
+
+ if ( ! yy_start )
+ yy_start = 1; /* first start state */
+
+ if ( ! yyin )
+ yyin = stdin;
+
+ if ( ! yyout )
+ yyout = stdout;
+
+ if ( yy_current_buffer )
+ yy_init_buffer( yy_current_buffer, yyin );
+ else
+ yy_current_buffer =
+ yy_create_buffer( yyin, YY_BUF_SIZE );
+
+ yy_load_buffer_state();
+
+ yy_init = 0;
+ }
+
+ while ( 1 ) /* loops until end-of-file is reached */
+ {
+ yy_cp = yy_c_buf_p;
+
+ /* Support of yytext. */
+ *yy_cp = yy_hold_char;
+
+ /* yy_bp points to the position in yy_ch_buf of the start of
+ * the current run.
+ */
+ yy_bp = yy_cp;
+
+ yy_current_state = yy_start;
+ if ( yy_bp[-1] == '\n' )
+ ++yy_current_state;
+yy_match:
+ do
+ {
+ register YY_CHAR yy_c = yy_ec[YY_SC_TO_UI(*yy_cp)];
+ if ( yy_accept[yy_current_state] )
+ {
+ yy_last_accepting_state = yy_current_state;
+ yy_last_accepting_cpos = yy_cp;
+ }
+ while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+ {
+ yy_current_state = (int) yy_def[yy_current_state];
+ if ( yy_current_state >= 408 )
+ yy_c = yy_meta[(unsigned int) yy_c];
+ }
+ yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+ ++yy_cp;
+ }
+ while ( yy_base[yy_current_state] != 1615 );
+
+yy_find_action:
+ yy_act = yy_accept[yy_current_state];
+
+ YY_DO_BEFORE_ACTION;
+
+
+do_action: /* This label is used only to access EOF actions. */
+
+
+ switch ( yy_act )
+ { /* beginning of action switch */
+ case 0: /* must back up */
+ /* undo the effects of YY_DO_BEFORE_ACTION */
+ *yy_cp = yy_hold_char;
+ yy_cp = yy_last_accepting_cpos;
+ yy_current_state = yy_last_accepting_state;
+ goto yy_find_action;
+
+case 1:
+YY_USER_ACTION
+# line 90 "scan.l"
+indented_code = true; BEGIN(CODEBLOCK);
+ YY_BREAK
+case 2:
+YY_USER_ACTION
+# line 91 "scan.l"
+ACTION_ECHO; BEGIN(C_COMMENT);
+ YY_BREAK
+case 3:
+YY_USER_ACTION
+# line 92 "scan.l"
+return SCDECL;
+ YY_BREAK
+case 4:
+YY_USER_ACTION
+# line 93 "scan.l"
+return XSCDECL;
+ YY_BREAK
+case 5:
+YY_USER_ACTION
+# line 94 "scan.l"
+{
+ ++linenum;
+ line_directive_out( (FILE *) 0 );
+ indented_code = false;
+ BEGIN(CODEBLOCK);
+ }
+ YY_BREAK
+case 6:
+YY_USER_ACTION
+# line 101 "scan.l"
+return WHITESPACE;
+ YY_BREAK
+case 7:
+YY_USER_ACTION
+# line 103 "scan.l"
+{
+ sectnum = 2;
+ bracelevel = 0;
+ mark_defs1();
+ line_directive_out( (FILE *) 0 );
+ BEGIN(SECT2PROLOG);
+ return SECTEND;
+ }
+ YY_BREAK
+case 8:
+YY_USER_ACTION
+# line 112 "scan.l"
+{
+ if ( lex_compat )
+ warn( "%pointer incompatible with -l option" );
+ else
+ yytext_is_array = false;
+ ++linenum;
+ }
+ YY_BREAK
+case 9:
+YY_USER_ACTION
+# line 119 "scan.l"
+{
+ if ( C_plus_plus )
+ warn( "%array incompatible with -+ option" );
+ else
+ yytext_is_array = true;
+ ++linenum;
+ }
+ YY_BREAK
+case 10:
+YY_USER_ACTION
+# line 127 "scan.l"
+{
+ warn( "%used/%unused have been deprecated" );
+ checking_used = REALLY_USED; BEGIN(USED_LIST);
+ }
+ YY_BREAK
+case 11:
+YY_USER_ACTION
+# line 131 "scan.l"
+{
+ warn( "%used/%unused have been deprecated" );
+ checking_used = REALLY_NOT_USED; BEGIN(USED_LIST);
+ }
+ YY_BREAK
+case 12:
+YY_USER_ACTION
+# line 137 "scan.l"
+++linenum; /* ignore */
+ YY_BREAK
+case 13:
+YY_USER_ACTION
+# line 139 "scan.l"
+synerr( "unrecognized '%' directive" );
+ YY_BREAK
+case 14:
+YY_USER_ACTION
+# line 141 "scan.l"
+{
+ strcpy( nmstr, yytext );
+ didadef = false;
+ BEGIN(PICKUPDEF);
+ }
+ YY_BREAK
+case 15:
+YY_USER_ACTION
+# line 147 "scan.l"
+RETURNNAME;
+ YY_BREAK
+case 16:
+YY_USER_ACTION
+# line 148 "scan.l"
+++linenum; /* allows blank lines in section 1 */
+ YY_BREAK
+case 17:
+YY_USER_ACTION
+# line 149 "scan.l"
+++linenum; return '\n';
+ YY_BREAK
+case 18:
+YY_USER_ACTION
+# line 152 "scan.l"
+ACTION_ECHO; BEGIN(INITIAL);
+ YY_BREAK
+case 19:
+YY_USER_ACTION
+# line 153 "scan.l"
+++linenum; ACTION_ECHO; BEGIN(INITIAL);
+ YY_BREAK
+case 20:
+YY_USER_ACTION
+# line 154 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 21:
+YY_USER_ACTION
+# line 155 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 22:
+YY_USER_ACTION
+# line 156 "scan.l"
+++linenum; ACTION_ECHO;
+ YY_BREAK
+case 23:
+YY_USER_ACTION
+# line 159 "scan.l"
+++linenum; BEGIN(INITIAL);
+ YY_BREAK
+case 24:
+YY_USER_ACTION
+# line 160 "scan.l"
+ACTION_ECHO; CHECK_REJECT(yytext);
+ YY_BREAK
+case 25:
+YY_USER_ACTION
+# line 161 "scan.l"
+ACTION_ECHO; CHECK_YYMORE(yytext);
+ YY_BREAK
+case 26:
+YY_USER_ACTION
+# line 162 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 27:
+YY_USER_ACTION
+# line 163 "scan.l"
+{
+ ++linenum;
+ ACTION_ECHO;
+ if ( indented_code )
+ BEGIN(INITIAL);
+ }
+ YY_BREAK
+case 28:
+YY_USER_ACTION
+# line 171 "scan.l"
+/* separates name and definition */
+ YY_BREAK
+case 29:
+YY_USER_ACTION
+# line 173 "scan.l"
+{
+ strcpy( (char *) nmdef, yytext );
+
+ /* Skip trailing whitespace. */
+ for ( i = strlen( (char *) nmdef ) - 1;
+ i >= 0 && (nmdef[i] == ' ' || nmdef[i] == '\t');
+ --i )
+ ;
+
+ nmdef[i + 1] = '\0';
+
+ ndinstal( nmstr, nmdef );
+ didadef = true;
+ }
+ YY_BREAK
+case 30:
+YY_USER_ACTION
+# line 188 "scan.l"
+{
+ if ( ! didadef )
+ synerr( "incomplete name definition" );
+ BEGIN(INITIAL);
+ ++linenum;
+ }
+ YY_BREAK
+case 31:
+YY_USER_ACTION
+# line 195 "scan.l"
+++linenum; BEGIN(INITIAL); RETURNNAME;
+ YY_BREAK
+case 32:
+YY_USER_ACTION
+# line 198 "scan.l"
+++linenum; BEGIN(INITIAL);
+ YY_BREAK
+case 33:
+YY_USER_ACTION
+# line 199 "scan.l"
+
+ YY_BREAK
+case 34:
+YY_USER_ACTION
+# line 200 "scan.l"
+{
+ if ( all_upper( yytext ) )
+ reject_really_used = checking_used;
+ else
+ synerr(
+ "unrecognized %used/%unused construct" );
+ }
+ YY_BREAK
+case 35:
+YY_USER_ACTION
+# line 207 "scan.l"
+{
+ if ( all_lower( yytext ) )
+ yymore_really_used = checking_used;
+ else
+ synerr(
+ "unrecognized %used/%unused construct" );
+ }
+ YY_BREAK
+case 36:
+YY_USER_ACTION
+# line 214 "scan.l"
+synerr( "unrecognized %used/%unused construct" );
+ YY_BREAK
+case 37:
+YY_USER_ACTION
+# line 217 "scan.l"
+++bracelevel; yyless( 2 ); /* eat only %{ */
+ YY_BREAK
+case 38:
+YY_USER_ACTION
+# line 218 "scan.l"
+--bracelevel; yyless( 2 ); /* eat only %} */
+ YY_BREAK
+case 39:
+YY_USER_ACTION
+# line 220 "scan.l"
+ACTION_ECHO; /* indented code in prolog */
+ YY_BREAK
+case 40:
+YY_USER_ACTION
+# line 222 "scan.l"
+{ /* non-indented code */
+ if ( bracelevel <= 0 )
+ { /* not in %{ ... %} */
+ yyless( 0 ); /* put it all back */
+ mark_prolog();
+ BEGIN(SECT2);
+ }
+ else
+ ACTION_ECHO;
+ }
+ YY_BREAK
+case 41:
+YY_USER_ACTION
+# line 233 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 42:
+YY_USER_ACTION
+# line 234 "scan.l"
+++linenum; ACTION_ECHO;
+ YY_BREAK
+case YY_STATE_EOF(SECT2PROLOG):
+# line 236 "scan.l"
+{
+ mark_prolog();
+ sectnum = 0;
+ yyterminate(); /* to stop the parser */
+ }
+ YY_BREAK
+case 43:
+YY_USER_ACTION
+# line 242 "scan.l"
+++linenum; /* allow blank lines in section 2 */
+ YY_BREAK
+case 44:
+YY_USER_ACTION
+# line 244 "scan.l"
+{
+ indented_code = (yytext[0] != '%');
+ doing_codeblock = true;
+ bracelevel = 1;
+
+ if ( indented_code )
+ ACTION_ECHO;
+
+ BEGIN(CODEBLOCK_2);
+ }
+ YY_BREAK
+case 45:
+YY_USER_ACTION
+# line 255 "scan.l"
+BEGIN(SC); return '<';
+ YY_BREAK
+case 46:
+YY_USER_ACTION
+# line 256 "scan.l"
+return '^';
+ YY_BREAK
+case 47:
+YY_USER_ACTION
+# line 257 "scan.l"
+BEGIN(QUOTE); return '"';
+ YY_BREAK
+case 48:
+*yy_cp = yy_hold_char; /* undo effects of setting up yytext */
+yy_c_buf_p = yy_cp = yy_bp + 1;
+YY_DO_BEFORE_ACTION; /* set up yytext again */
+YY_USER_ACTION
+# line 258 "scan.l"
+BEGIN(NUM); return '{';
+ YY_BREAK
+case 49:
+YY_USER_ACTION
+# line 259 "scan.l"
+BEGIN(BRACEERROR);
+ YY_BREAK
+case 50:
+*yy_cp = yy_hold_char; /* undo effects of setting up yytext */
+yy_c_buf_p = yy_cp = yy_bp + 1;
+YY_DO_BEFORE_ACTION; /* set up yytext again */
+YY_USER_ACTION
+# line 260 "scan.l"
+return '$';
+ YY_BREAK
+case 51:
+YY_USER_ACTION
+# line 262 "scan.l"
+{
+ bracelevel = 1;
+ BEGIN(PERCENT_BRACE_ACTION);
+ return '\n';
+ }
+ YY_BREAK
+case 52:
+YY_USER_ACTION
+# line 267 "scan.l"
+continued_action = true; ++linenum; return '\n';
+ YY_BREAK
+case 53:
+YY_USER_ACTION
+# line 269 "scan.l"
+{
+ /* This rule is separate from the one below because
+ * otherwise we get variable trailing context, so
+ * we can't build the scanner using -{f,F}.
+ */
+ bracelevel = 0;
+ continued_action = false;
+ BEGIN(ACTION);
+ return '\n';
+ }
+ YY_BREAK
+case 54:
+YY_USER_ACTION
+# line 280 "scan.l"
+{
+ bracelevel = 0;
+ continued_action = false;
+ BEGIN(ACTION);
+ unput( '\n' ); /* so <ACTION> sees it */
+ return '\n';
+ }
+ YY_BREAK
+case 55:
+YY_USER_ACTION
+# line 288 "scan.l"
+return EOF_OP;
+ YY_BREAK
+case 56:
+YY_USER_ACTION
+# line 290 "scan.l"
+{
+ sectnum = 3;
+ BEGIN(SECT3);
+ yyterminate(); /* to stop the parser */
+ }
+ YY_BREAK
+case 57:
+YY_USER_ACTION
+# line 296 "scan.l"
+{
+ int cclval;
+
+ strcpy( nmstr, yytext );
+
+ /* Check to see if we've already encountered this
+ * ccl.
+ */
+ if ( (cclval = ccllookup( (Char *) nmstr )) )
+ {
+ if ( input() != ']' )
+ synerr( "bad character class" );
+
+ yylval = cclval;
+ ++cclreuse;
+ return PREVCCL;
+ }
+ else
+ {
+ /* We fudge a bit. We know that this ccl will
+ * soon be numbered as lastccl + 1 by cclinit.
+ */
+ cclinstal( (Char *) nmstr, lastccl + 1 );
+
+ /* Push back everything but the leading bracket
+ * so the ccl can be rescanned.
+ */
+ yyless( 1 );
+
+ BEGIN(FIRSTCCL);
+ return '[';
+ }
+ }
+ YY_BREAK
+case 58:
+YY_USER_ACTION
+# line 330 "scan.l"
+{
+ register Char *nmdefptr;
+ Char *ndlookup();
+
+ strcpy( nmstr, yytext + 1 );
+ nmstr[yyleng - 2] = '\0'; /* chop trailing brace */
+
+ if ( ! (nmdefptr = ndlookup( nmstr )) )
+ format_synerr( "undefined definition {%s}",
+ nmstr );
+
+ else
+ { /* push back name surrounded by ()'s */
+ int len = strlen( (char *) nmdefptr );
+
+ if ( lex_compat || nmdefptr[0] == '^' ||
+ (len > 0 && nmdefptr[len - 1] == '$') )
+ { /* don't use ()'s after all */
+ PUT_BACK_STRING((char *) nmdefptr, 0);
+
+ if ( nmdefptr[0] == '^' )
+ BEGIN(CARETISBOL);
+ }
+
+ else
+ {
+ unput(')');
+ PUT_BACK_STRING((char *) nmdefptr, 0);
+ unput('(');
+ }
+ }
+ }
+ YY_BREAK
+case 59:
+YY_USER_ACTION
+# line 363 "scan.l"
+return (unsigned char) yytext[0];
+ YY_BREAK
+case 60:
+YY_USER_ACTION
+# line 364 "scan.l"
+RETURNCHAR;
+ YY_BREAK
+case 61:
+YY_USER_ACTION
+# line 367 "scan.l"
+return (unsigned char) yytext[0];
+ YY_BREAK
+case 62:
+YY_USER_ACTION
+# line 368 "scan.l"
+BEGIN(SECT2); return '>';
+ YY_BREAK
+case 63:
+*yy_cp = yy_hold_char; /* undo effects of setting up yytext */
+yy_c_buf_p = yy_cp = yy_bp + 1;
+YY_DO_BEFORE_ACTION; /* set up yytext again */
+YY_USER_ACTION
+# line 369 "scan.l"
+BEGIN(CARETISBOL); return '>';
+ YY_BREAK
+case 64:
+YY_USER_ACTION
+# line 370 "scan.l"
+RETURNNAME;
+ YY_BREAK
+case 65:
+YY_USER_ACTION
+# line 371 "scan.l"
+{
+ format_synerr( "bad <start condition>: %s", yytext );
+ }
+ YY_BREAK
+case 66:
+YY_USER_ACTION
+# line 375 "scan.l"
+BEGIN(SECT2); return '^';
+ YY_BREAK
+case 67:
+YY_USER_ACTION
+# line 378 "scan.l"
+RETURNCHAR;
+ YY_BREAK
+case 68:
+YY_USER_ACTION
+# line 379 "scan.l"
+BEGIN(SECT2); return '"';
+ YY_BREAK
+case 69:
+YY_USER_ACTION
+# line 381 "scan.l"
+{
+ synerr( "missing quote" );
+ BEGIN(SECT2);
+ ++linenum;
+ return '"';
+ }
+ YY_BREAK
+case 70:
+*yy_cp = yy_hold_char; /* undo effects of setting up yytext */
+yy_c_buf_p = yy_cp = yy_bp + 1;
+YY_DO_BEFORE_ACTION; /* set up yytext again */
+YY_USER_ACTION
+# line 389 "scan.l"
+BEGIN(CCL); return '^';
+ YY_BREAK
+case 71:
+*yy_cp = yy_hold_char; /* undo effects of setting up yytext */
+yy_c_buf_p = yy_cp = yy_bp + 1;
+YY_DO_BEFORE_ACTION; /* set up yytext again */
+YY_USER_ACTION
+# line 390 "scan.l"
+return '^';
+ YY_BREAK
+case 72:
+YY_USER_ACTION
+# line 391 "scan.l"
+BEGIN(CCL); RETURNCHAR;
+ YY_BREAK
+case 73:
+*yy_cp = yy_hold_char; /* undo effects of setting up yytext */
+yy_c_buf_p = yy_cp = yy_bp + 1;
+YY_DO_BEFORE_ACTION; /* set up yytext again */
+YY_USER_ACTION
+# line 393 "scan.l"
+return '-';
+ YY_BREAK
+case 74:
+YY_USER_ACTION
+# line 394 "scan.l"
+RETURNCHAR;
+ YY_BREAK
+case 75:
+YY_USER_ACTION
+# line 395 "scan.l"
+BEGIN(SECT2); return ']';
+ YY_BREAK
+case 76:
+YY_USER_ACTION
+# line 396 "scan.l"
+{
+ synerr( "bad character class" );
+ BEGIN(SECT2);
+ return ']';
+ }
+ YY_BREAK
+case 77:
+YY_USER_ACTION
+# line 403 "scan.l"
+{
+ yylval = myctoi( yytext );
+ return NUMBER;
+ }
+ YY_BREAK
+case 78:
+YY_USER_ACTION
+# line 408 "scan.l"
+return ',';
+ YY_BREAK
+case 79:
+YY_USER_ACTION
+# line 409 "scan.l"
+BEGIN(SECT2); return '}';
+ YY_BREAK
+case 80:
+YY_USER_ACTION
+# line 411 "scan.l"
+{
+ synerr( "bad character inside {}'s" );
+ BEGIN(SECT2);
+ return '}';
+ }
+ YY_BREAK
+case 81:
+YY_USER_ACTION
+# line 417 "scan.l"
+{
+ synerr( "missing }" );
+ BEGIN(SECT2);
+ ++linenum;
+ return '}';
+ }
+ YY_BREAK
+case 82:
+YY_USER_ACTION
+# line 425 "scan.l"
+synerr( "bad name in {}'s" ); BEGIN(SECT2);
+ YY_BREAK
+case 83:
+YY_USER_ACTION
+# line 426 "scan.l"
+synerr( "missing }" ); ++linenum; BEGIN(SECT2);
+ YY_BREAK
+case 84:
+YY_USER_ACTION
+# line 429 "scan.l"
+ACTION_ECHO; BEGIN(ACTION_COMMENT);
+ YY_BREAK
+case 85:
+YY_USER_ACTION
+# line 430 "scan.l"
+bracelevel = 0;
+ YY_BREAK
+case 86:
+YY_USER_ACTION
+# line 431 "scan.l"
+{
+ ACTION_ECHO;
+ CHECK_REJECT(yytext);
+ }
+ YY_BREAK
+case 87:
+YY_USER_ACTION
+# line 435 "scan.l"
+{
+ ACTION_ECHO;
+ CHECK_YYMORE(yytext);
+ }
+ YY_BREAK
+case 88:
+YY_USER_ACTION
+# line 439 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 89:
+YY_USER_ACTION
+# line 440 "scan.l"
+{
+ ++linenum;
+ ACTION_ECHO;
+ if ( bracelevel == 0 ||
+ (doing_codeblock && indented_code) )
+ {
+ if ( ! doing_codeblock )
+ add_action( "\tYY_BREAK\n" );
+
+ doing_codeblock = false;
+ BEGIN(SECT2);
+ }
+ }
+ YY_BREAK
+ /* Reject and YYmore() are checked for above, in PERCENT_BRACE_ACTION */
+case 90:
+YY_USER_ACTION
+# line 456 "scan.l"
+ACTION_ECHO; ++bracelevel;
+ YY_BREAK
+case 91:
+YY_USER_ACTION
+# line 457 "scan.l"
+ACTION_ECHO; --bracelevel;
+ YY_BREAK
+case 92:
+YY_USER_ACTION
+# line 458 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 93:
+YY_USER_ACTION
+# line 459 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 94:
+YY_USER_ACTION
+# line 460 "scan.l"
+ACTION_ECHO; BEGIN(ACTION_COMMENT);
+ YY_BREAK
+case 95:
+YY_USER_ACTION
+# line 461 "scan.l"
+ACTION_ECHO; /* character constant */
+ YY_BREAK
+case 96:
+YY_USER_ACTION
+# line 462 "scan.l"
+ACTION_ECHO; BEGIN(ACTION_STRING);
+ YY_BREAK
+case 97:
+YY_USER_ACTION
+# line 463 "scan.l"
+{
+ ++linenum;
+ ACTION_ECHO;
+ if ( bracelevel == 0 )
+ {
+ add_action( "\tYY_BREAK\n" );
+ BEGIN(SECT2);
+ }
+ }
+ YY_BREAK
+case 98:
+YY_USER_ACTION
+# line 472 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 99:
+YY_USER_ACTION
+# line 474 "scan.l"
+{
+ ACTION_ECHO;
+ if ( doing_codeblock )
+ BEGIN(CODEBLOCK_2);
+ else
+ BEGIN(ACTION);
+ }
+ YY_BREAK
+case 100:
+YY_USER_ACTION
+# line 482 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 101:
+YY_USER_ACTION
+# line 483 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 102:
+YY_USER_ACTION
+# line 484 "scan.l"
+++linenum; ACTION_ECHO;
+ YY_BREAK
+case 103:
+YY_USER_ACTION
+# line 486 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 104:
+YY_USER_ACTION
+# line 487 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case 105:
+YY_USER_ACTION
+# line 488 "scan.l"
+++linenum; ACTION_ECHO;
+ YY_BREAK
+case 106:
+YY_USER_ACTION
+# line 489 "scan.l"
+ACTION_ECHO; BEGIN(ACTION);
+ YY_BREAK
+case 107:
+YY_USER_ACTION
+# line 490 "scan.l"
+ACTION_ECHO;
+ YY_BREAK
+case YY_STATE_EOF(ACTION):
+case YY_STATE_EOF(ACTION_COMMENT):
+case YY_STATE_EOF(ACTION_STRING):
+# line 492 "scan.l"
+{
+ synerr( "EOF encountered inside an action" );
+ yyterminate();
+ }
+ YY_BREAK
+case 108:
+YY_USER_ACTION
+# line 498 "scan.l"
+{
+ yylval = myesc( (Char *) yytext );
+ return CHAR;
+ }
+ YY_BREAK
+case 109:
+YY_USER_ACTION
+# line 503 "scan.l"
+{
+ yylval = myesc( (Char *) yytext );
+ BEGIN(CCL);
+ return CHAR;
+ }
+ YY_BREAK
+case 110:
+YY_USER_ACTION
+# line 510 "scan.l"
+ECHO;
+ YY_BREAK
+case YY_STATE_EOF(SECT3):
+# line 511 "scan.l"
+sectnum = 0; yyterminate();
+ YY_BREAK
+case 111:
+YY_USER_ACTION
+# line 513 "scan.l"
+format_synerr( "bad character: %s", yytext );
+ YY_BREAK
+case 112:
+YY_USER_ACTION
+# line 515 "scan.l"
+YY_FATAL_ERROR( "flex scanner jammed" );
+ YY_BREAK
+case YY_STATE_EOF(INITIAL):
+case YY_STATE_EOF(SECT2):
+case YY_STATE_EOF(CODEBLOCK):
+case YY_STATE_EOF(PICKUPDEF):
+case YY_STATE_EOF(SC):
+case YY_STATE_EOF(CARETISBOL):
+case YY_STATE_EOF(NUM):
+case YY_STATE_EOF(QUOTE):
+case YY_STATE_EOF(FIRSTCCL):
+case YY_STATE_EOF(CCL):
+case YY_STATE_EOF(RECOVER):
+case YY_STATE_EOF(BRACEERROR):
+case YY_STATE_EOF(C_COMMENT):
+case YY_STATE_EOF(PERCENT_BRACE_ACTION):
+case YY_STATE_EOF(USED_LIST):
+case YY_STATE_EOF(CODEBLOCK_2):
+ yyterminate();
+
+ case YY_END_OF_BUFFER:
+ {
+ /* Amount of text matched not including the EOB char. */
+ int yy_amount_of_matched_text = yy_cp - yytext_ptr - 1;
+
+ /* Undo the effects of YY_DO_BEFORE_ACTION. */
+ *yy_cp = yy_hold_char;
+
+ if ( yy_current_buffer->yy_buffer_status == YY_BUFFER_NEW )
+ {
+ /* We're scanning a new file or input source. It's
+ * possible that this happened because the user
+ * just pointed yyin at a new source and called
+ * yylex(). If so, then we have to assure
+ * consistency between yy_current_buffer and our
+ * globals. Here is the right place to do so, because
+ * this is the first action (other than possibly a
+ * back-up) that will match for the new input source.
+ */
+ yy_n_chars = yy_current_buffer->yy_n_chars;
+ yy_current_buffer->yy_input_file = yyin;
+ yy_current_buffer->yy_buffer_status = YY_BUFFER_NORMAL;
+ }
+
+ /* Note that here we test for yy_c_buf_p "<=" to the position
+ * of the first EOB in the buffer, since yy_c_buf_p will
+ * already have been incremented past the NUL character
+ * (since all states make transitions on EOB to the
+ * end-of-buffer state). Contrast this with the test
+ * in input().
+ */
+ if ( yy_c_buf_p <= &yy_current_buffer->yy_ch_buf[yy_n_chars] )
+ { /* This was really a NUL. */
+ yy_state_type yy_next_state;
+
+ yy_c_buf_p = yytext_ptr + yy_amount_of_matched_text;
+
+ yy_current_state = yy_get_previous_state();
+
+ /* Okay, we're now positioned to make the NUL
+ * transition. We couldn't have
+ * yy_get_previous_state() go ahead and do it
+ * for us because it doesn't know how to deal
+ * with the possibility of jamming (and we don't
+ * want to build jamming into it because then it
+ * will run more slowly).
+ */
+
+ yy_next_state = yy_try_NUL_trans( yy_current_state );
+
+ yy_bp = yytext_ptr + YY_MORE_ADJ;
+
+ if ( yy_next_state )
+ {
+ /* Consume the NUL. */
+ yy_cp = ++yy_c_buf_p;
+ yy_current_state = yy_next_state;
+ goto yy_match;
+ }
+
+ else
+ {
+ yy_cp = yy_c_buf_p;
+ goto yy_find_action;
+ }
+ }
+
+ else switch ( yy_get_next_buffer() )
+ {
+ case EOB_ACT_END_OF_FILE:
+ {
+ yy_did_buffer_switch_on_eof = 0;
+
+ if ( yywrap() )
+ {
+ /* Note: because we've taken care in
+ * yy_get_next_buffer() to have set up
+ * yytext, we can now set up
+ * yy_c_buf_p so that if some total
+ * hoser (like flex itself) wants to
+ * call the scanner after we return the
+ * YY_NULL, it'll still work - another
+ * YY_NULL will get returned.
+ */
+ yy_c_buf_p = yytext_ptr + YY_MORE_ADJ;
+
+ yy_act = YY_STATE_EOF(YY_START);
+ goto do_action;
+ }
+
+ else
+ {
+ if ( ! yy_did_buffer_switch_on_eof )
+ YY_NEW_FILE;
+ }
+ break;
+ }
+
+ case EOB_ACT_CONTINUE_SCAN:
+ yy_c_buf_p =
+ yytext_ptr + yy_amount_of_matched_text;
+
+ yy_current_state = yy_get_previous_state();
+
+ yy_cp = yy_c_buf_p;
+ yy_bp = yytext_ptr + YY_MORE_ADJ;
+ goto yy_match;
+
+ case EOB_ACT_LAST_MATCH:
+ yy_c_buf_p =
+ &yy_current_buffer->yy_ch_buf[yy_n_chars];
+
+ yy_current_state = yy_get_previous_state();
+
+ yy_cp = yy_c_buf_p;
+ yy_bp = yytext_ptr + YY_MORE_ADJ;
+ goto yy_find_action;
+ }
+ break;
+ }
+
+ default:
+ YY_FATAL_ERROR(
+ "fatal flex scanner internal error--no action found" );
+ } /* end of action switch */
+ } /* end of scanning one token */
+ } /* end of yylex */
+
+
+/* yy_get_next_buffer - try to read in a new buffer
+ *
+ * Returns a code representing an action:
+ * EOB_ACT_LAST_MATCH -
+ * EOB_ACT_CONTINUE_SCAN - continue scanning from current position
+ * EOB_ACT_END_OF_FILE - end of file
+ */
+
+static int yy_get_next_buffer()
+ {
+ register char *dest = yy_current_buffer->yy_ch_buf;
+ register char *source = yytext_ptr - 1; /* copy prev. char, too */
+ register int number_to_move, i;
+ int ret_val;
+
+ if ( yy_c_buf_p > &yy_current_buffer->yy_ch_buf[yy_n_chars + 1] )
+ YY_FATAL_ERROR(
+ "fatal flex scanner internal error--end of buffer missed" );
+
+ if ( yy_current_buffer->yy_fill_buffer == 0 )
+ { /* Don't try to fill the buffer, so this is an EOF. */
+ if ( yy_c_buf_p - yytext_ptr - YY_MORE_ADJ == 1 )
+ {
+ /* We matched a singled characater, the EOB, so
+ * treat this as a final EOF.
+ */
+ return EOB_ACT_END_OF_FILE;
+ }
+
+ else
+ {
+ /* We matched some text prior to the EOB, first
+ * process it.
+ */
+ return EOB_ACT_LAST_MATCH;
+ }
+ }
+
+ /* Try to read more data. */
+
+ /* First move last chars to start of buffer. */
+ number_to_move = yy_c_buf_p - yytext_ptr;
+
+ for ( i = 0; i < number_to_move; ++i )
+ *(dest++) = *(source++);
+
+ if ( yy_current_buffer->yy_buffer_status == YY_BUFFER_EOF_PENDING )
+ /* don't do the read, it's not guaranteed to return an EOF,
+ * just force an EOF
+ */
+ yy_n_chars = 0;
+
+ else
+ {
+ int num_to_read =
+ yy_current_buffer->yy_buf_size - number_to_move - 1;
+
+ while ( num_to_read <= 0 )
+ { /* Not enough room in the buffer - grow it. */
+#ifdef YY_USES_REJECT
+ YY_FATAL_ERROR(
+"input buffer overflow, can't enlarge buffer because scanner uses REJECT" );
+#else
+
+ /* just a shorter name for the current buffer */
+ YY_BUFFER_STATE b = yy_current_buffer;
+
+ int yy_c_buf_p_offset = yy_c_buf_p - b->yy_ch_buf;
+
+ b->yy_buf_size *= 2;
+ b->yy_ch_buf = (char *)
+ yy_flex_realloc( (void *) b->yy_ch_buf,
+ b->yy_buf_size );
+
+ if ( ! b->yy_ch_buf )
+ YY_FATAL_ERROR(
+ "fatal error - scanner input buffer overflow" );
+
+ yy_c_buf_p = &b->yy_ch_buf[yy_c_buf_p_offset];
+
+ num_to_read = yy_current_buffer->yy_buf_size -
+ number_to_move - 1;
+#endif
+ }
+
+ if ( num_to_read > YY_READ_BUF_SIZE )
+ num_to_read = YY_READ_BUF_SIZE;
+
+ /* Read in more data. */
+ YY_INPUT( (&yy_current_buffer->yy_ch_buf[number_to_move]),
+ yy_n_chars, num_to_read );
+ }
+
+ if ( yy_n_chars == 0 )
+ {
+ if ( number_to_move - YY_MORE_ADJ == 1 )
+ {
+ ret_val = EOB_ACT_END_OF_FILE;
+ yyrestart( yyin );
+ }
+
+ else
+ {
+ ret_val = EOB_ACT_LAST_MATCH;
+ yy_current_buffer->yy_buffer_status =
+ YY_BUFFER_EOF_PENDING;
+ }
+ }
+
+ else
+ ret_val = EOB_ACT_CONTINUE_SCAN;
+
+ yy_n_chars += number_to_move;
+ yy_current_buffer->yy_ch_buf[yy_n_chars] = YY_END_OF_BUFFER_CHAR;
+ yy_current_buffer->yy_ch_buf[yy_n_chars + 1] = YY_END_OF_BUFFER_CHAR;
+
+ /* yytext begins at the second character in yy_ch_buf; the first
+ * character is the one which preceded it before reading in the latest
+ * buffer; it needs to be kept around in case it's a newline, so
+ * yy_get_previous_state() will have with '^' rules active.
+ */
+
+ yytext_ptr = &yy_current_buffer->yy_ch_buf[1];
+
+ return ret_val;
+ }
+
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+static yy_state_type yy_get_previous_state()
+ {
+ register yy_state_type yy_current_state;
+ register char *yy_cp;
+
+ register char *yy_bp = yytext_ptr;
+
+ yy_current_state = yy_start;
+ if ( yy_bp[-1] == '\n' )
+ ++yy_current_state;
+
+ for ( yy_cp = yytext_ptr + YY_MORE_ADJ; yy_cp < yy_c_buf_p; ++yy_cp )
+ {
+ register YY_CHAR yy_c = (*yy_cp ? yy_ec[YY_SC_TO_UI(*yy_cp)] : 1);
+ if ( yy_accept[yy_current_state] )
+ {
+ yy_last_accepting_state = yy_current_state;
+ yy_last_accepting_cpos = yy_cp;
+ }
+ while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+ {
+ yy_current_state = (int) yy_def[yy_current_state];
+ if ( yy_current_state >= 408 )
+ yy_c = yy_meta[(unsigned int) yy_c];
+ }
+ yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+ }
+
+ return yy_current_state;
+ }
+
+
+/* yy_try_NUL_trans - try to make a transition on the NUL character
+ *
+ * synopsis
+ * next_state = yy_try_NUL_trans( current_state );
+ */
+
+#ifdef YY_USE_PROTOS
+static yy_state_type yy_try_NUL_trans( yy_state_type yy_current_state )
+#else
+static yy_state_type yy_try_NUL_trans( yy_current_state )
+yy_state_type yy_current_state;
+#endif
+ {
+ register int yy_is_jam;
+ register char *yy_cp = yy_c_buf_p;
+
+ register YY_CHAR yy_c = 1;
+ if ( yy_accept[yy_current_state] )
+ {
+ yy_last_accepting_state = yy_current_state;
+ yy_last_accepting_cpos = yy_cp;
+ }
+ while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+ {
+ yy_current_state = (int) yy_def[yy_current_state];
+ if ( yy_current_state >= 408 )
+ yy_c = yy_meta[(unsigned int) yy_c];
+ }
+ yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+ yy_is_jam = (yy_current_state == 407);
+
+ return yy_is_jam ? 0 : yy_current_state;
+ }
+
+
+#ifdef YY_USE_PROTOS
+static void yyunput( int c, register char *yy_bp )
+#else
+static void yyunput( c, yy_bp )
+int c;
+register char *yy_bp;
+#endif
+ {
+ register char *yy_cp = yy_c_buf_p;
+
+ /* undo effects of setting up yytext */
+ *yy_cp = yy_hold_char;
+
+ if ( yy_cp < yy_current_buffer->yy_ch_buf + 2 )
+ { /* need to shift things up to make room */
+ /* +2 for EOB chars. */
+ register int number_to_move = yy_n_chars + 2;
+ register char *dest = &yy_current_buffer->yy_ch_buf[
+ yy_current_buffer->yy_buf_size + 2];
+ register char *source =
+ &yy_current_buffer->yy_ch_buf[number_to_move];
+
+ while ( source > yy_current_buffer->yy_ch_buf )
+ *--dest = *--source;
+
+ yy_cp += dest - source;
+ yy_bp += dest - source;
+ yy_n_chars = yy_current_buffer->yy_buf_size;
+
+ if ( yy_cp < yy_current_buffer->yy_ch_buf + 2 )
+ YY_FATAL_ERROR( "flex scanner push-back overflow" );
+ }
+
+ if ( yy_cp > yy_bp && yy_cp[-1] == '\n' )
+ yy_cp[-2] = '\n';
+
+ *--yy_cp = (char) c;
+
+
+ /* Note: the formal parameter *must* be called "yy_bp" for this
+ * macro to now work correctly.
+ */
+ YY_DO_BEFORE_ACTION; /* set up yytext again */
+ }
+
+
+#ifdef __cplusplus
+static int yyinput()
+#else
+static int input()
+#endif
+ {
+ int c;
+
+ *yy_c_buf_p = yy_hold_char;
+
+ if ( *yy_c_buf_p == YY_END_OF_BUFFER_CHAR )
+ {
+ /* yy_c_buf_p now points to the character we want to return.
+ * If this occurs *before* the EOB characters, then it's a
+ * valid NUL; if not, then we've hit the end of the buffer.
+ */
+ if ( yy_c_buf_p < &yy_current_buffer->yy_ch_buf[yy_n_chars] )
+ /* This was really a NUL. */
+ *yy_c_buf_p = '\0';
+
+ else
+ { /* need more input */
+ yytext_ptr = yy_c_buf_p;
+ ++yy_c_buf_p;
+
+ switch ( yy_get_next_buffer() )
+ {
+ case EOB_ACT_END_OF_FILE:
+ {
+ if ( yywrap() )
+ {
+ yy_c_buf_p =
+ yytext_ptr + YY_MORE_ADJ;
+ return EOF;
+ }
+
+ YY_NEW_FILE;
+#ifdef __cplusplus
+ return yyinput();
+#else
+ return input();
+#endif
+ }
+
+ case EOB_ACT_CONTINUE_SCAN:
+ yy_c_buf_p = yytext_ptr + YY_MORE_ADJ;
+ break;
+
+ case EOB_ACT_LAST_MATCH:
+#ifdef __cplusplus
+ YY_FATAL_ERROR(
+ "unexpected last match in yyinput()" );
+#else
+ YY_FATAL_ERROR(
+ "unexpected last match in input()" );
+#endif
+ }
+ }
+ }
+
+ c = *(unsigned char *) yy_c_buf_p; /* cast for 8-bit char's */
+ *yy_c_buf_p = '\0'; /* preserve yytext */
+ yy_hold_char = *++yy_c_buf_p;
+
+ return c;
+ }
+
+
+#ifdef YY_USE_PROTOS
+void yyrestart( FILE *input_file )
+#else
+void yyrestart( input_file )
+FILE *input_file;
+#endif
+ {
+ if ( ! yy_current_buffer )
+ yy_current_buffer = yy_create_buffer( yyin, YY_BUF_SIZE );
+
+ yy_init_buffer( yy_current_buffer, input_file );
+ yy_load_buffer_state();
+ }
+
+
+#ifdef YY_USE_PROTOS
+void yy_switch_to_buffer( YY_BUFFER_STATE new_buffer )
+#else
+void yy_switch_to_buffer( new_buffer )
+YY_BUFFER_STATE new_buffer;
+#endif
+ {
+ if ( yy_current_buffer == new_buffer )
+ return;
+
+ if ( yy_current_buffer )
+ {
+ /* Flush out information for old buffer. */
+ *yy_c_buf_p = yy_hold_char;
+ yy_current_buffer->yy_buf_pos = yy_c_buf_p;
+ yy_current_buffer->yy_n_chars = yy_n_chars;
+ }
+
+ yy_current_buffer = new_buffer;
+ yy_load_buffer_state();
+
+ /* We don't actually know whether we did this switch during
+ * EOF (yywrap()) processing, but the only time this flag
+ * is looked at is after yywrap() is called, so it's safe
+ * to go ahead and always set it.
+ */
+ yy_did_buffer_switch_on_eof = 1;
+ }
+
+
+#ifdef YY_USE_PROTOS
+void yy_load_buffer_state( void )
+#else
+void yy_load_buffer_state()
+#endif
+ {
+ yy_n_chars = yy_current_buffer->yy_n_chars;
+ yytext_ptr = yy_c_buf_p = yy_current_buffer->yy_buf_pos;
+ yyin = yy_current_buffer->yy_input_file;
+ yy_hold_char = *yy_c_buf_p;
+ }
+
+
+#ifdef YY_USE_PROTOS
+YY_BUFFER_STATE yy_create_buffer( FILE *file, int size )
+#else
+YY_BUFFER_STATE yy_create_buffer( file, size )
+FILE *file;
+int size;
+#endif
+ {
+ YY_BUFFER_STATE b;
+
+ b = (YY_BUFFER_STATE) yy_flex_alloc( sizeof( struct yy_buffer_state ) );
+
+ if ( ! b )
+ YY_FATAL_ERROR( "out of dynamic memory in yy_create_buffer()" );
+
+ b->yy_buf_size = size;
+
+ /* yy_ch_buf has to be 2 characters longer than the size given because
+ * we need to put in 2 end-of-buffer characters.
+ */
+ b->yy_ch_buf = (char *) yy_flex_alloc( b->yy_buf_size + 2 );
+
+ if ( ! b->yy_ch_buf )
+ YY_FATAL_ERROR( "out of dynamic memory in yy_create_buffer()" );
+
+ yy_init_buffer( b, file );
+
+ return b;
+ }
+
+
+#ifdef YY_USE_PROTOS
+void yy_delete_buffer( YY_BUFFER_STATE b )
+#else
+void yy_delete_buffer( b )
+YY_BUFFER_STATE b;
+#endif
+ {
+ if ( b == yy_current_buffer )
+ yy_current_buffer = (YY_BUFFER_STATE) 0;
+
+ yy_flex_free( (void *) b->yy_ch_buf );
+ yy_flex_free( (void *) b );
+ }
+
+
+#ifdef YY_USE_PROTOS
+void yy_init_buffer( YY_BUFFER_STATE b, FILE *file )
+#else
+void yy_init_buffer( b, file )
+YY_BUFFER_STATE b;
+FILE *file;
+#endif
+ {
+ b->yy_input_file = file;
+
+ /* We put in the '\n' and start reading from [1] so that an
+ * initial match-at-newline will be true.
+ */
+
+ b->yy_ch_buf[0] = '\n';
+ b->yy_n_chars = 1;
+
+ /* We always need two end-of-buffer characters. The first causes
+ * a transition to the end-of-buffer state. The second causes
+ * a jam in that state.
+ */
+ b->yy_ch_buf[1] = YY_END_OF_BUFFER_CHAR;
+ b->yy_ch_buf[2] = YY_END_OF_BUFFER_CHAR;
+
+ b->yy_buf_pos = &b->yy_ch_buf[1];
+
+ b->yy_is_interactive = file ? isatty( fileno(file) ) : 0;
+
+ b->yy_fill_buffer = 1;
+
+ b->yy_buffer_status = YY_BUFFER_NEW;
+ }
+
+
+#ifdef YY_USE_PROTOS
+static void yy_push_state( int new_state )
+#else
+static void yy_push_state( new_state )
+int new_state;
+#endif
+ {
+ if ( yy_start_stack_ptr >= yy_start_stack_depth )
+ {
+ int new_size;
+
+ yy_start_stack_depth += YY_START_STACK_INCR;
+ new_size = yy_start_stack_depth * sizeof( int );
+
+ if ( ! yy_start_stack )
+ yy_start_stack = (int *) yy_flex_alloc( new_size );
+
+ else
+ yy_start_stack = (int *) yy_flex_realloc(
+ (void *) yy_start_stack, new_size );
+
+ if ( ! yy_start_stack )
+ YY_FATAL_ERROR(
+ "out of memory expanding start-condition stack" );
+ }
+
+ yy_start_stack[yy_start_stack_ptr++] = YY_START;
+
+ BEGIN(new_state);
+ }
+
+
+static void yy_pop_state()
+ {
+ if ( --yy_start_stack_ptr < 0 )
+ YY_FATAL_ERROR( "start-condition stack underflow" );
+
+ BEGIN(yy_start_stack[yy_start_stack_ptr]);
+ }
+
+
+static int yy_top_state()
+ {
+ return yy_start_stack[yy_start_stack_ptr - 1];
+ }
+
+
+#ifdef YY_USE_PROTOS
+static void yy_fatal_error( const char msg[] )
+#else
+static void yy_fatal_error( msg )
+char msg[];
+#endif
+ {
+ (void) fprintf( stderr, "%s\n", msg );
+ exit( 1 );
+ }
+
+
+
+/* Redefine yyless() so it works in section 3 code. */
+
+#undef yyless
+#define yyless(n) \
+ do \
+ { \
+ /* Undo effects of setting up yytext. */ \
+ yytext[yyleng] = yy_hold_char; \
+ yy_c_buf_p = yytext + n - YY_MORE_ADJ; \
+ yy_hold_char = *yy_c_buf_p; \
+ *yy_c_buf_p = '\0'; \
+ yyleng = n; \
+ } \
+ while ( 0 )
+
+
+/* Internal utility routines. */
+
+#ifndef yytext_ptr
+#ifdef YY_USE_PROTOS
+static void yy_flex_strncpy( char *s1, const char *s2, int n )
+#else
+static void yy_flex_strncpy( s1, s2, n )
+char *s1;
+const char *s2;
+int n;
+#endif
+ {
+ register int i;
+ for ( i = 0; i < n; ++i )
+ s1[i] = s2[i];
+ }
+#endif
+
+
+#ifdef YY_USE_PROTOS
+static void *yy_flex_alloc( unsigned int size )
+#else
+static void *yy_flex_alloc( size )
+unsigned int size;
+#endif
+ {
+ return (void *) malloc( size );
+ }
+
+#ifdef YY_USE_PROTOS
+static void *yy_flex_realloc( void *ptr, unsigned int size )
+#else
+static void *yy_flex_realloc( ptr, size )
+void *ptr;
+unsigned int size;
+#endif
+ {
+ return (void *) realloc( ptr, size );
+ }
+
+#ifdef YY_USE_PROTOS
+static void yy_flex_free( void *ptr )
+#else
+static void yy_flex_free( ptr )
+void *ptr;
+#endif
+ {
+ free( ptr );
+ }
+# line 515 "scan.l"
+
+
+
+int yywrap()
+ {
+ if ( --num_input_files > 0 )
+ {
+ set_input_file( *++input_files );
+ return 0;
+ }
+
+ else
+ return 1;
+ }
+
+
+/* set_input_file - open the given file (if NULL, stdin) for scanning */
+
+void set_input_file( file )
+char *file;
+ {
+ if ( file )
+ {
+ infilename = file;
+ yyin = fopen( infilename, "r" );
+
+ if ( yyin == NULL )
+ lerrsf( "can't open %s", file );
+ }
+
+ else
+ {
+ yyin = stdin;
+ infilename = "<stdin>";
+ }
+ }
+
+
+/* Wrapper routines for accessing the scanner's malloc routines. */
+
+void *flex_alloc( size )
+unsigned int size;
+ {
+ return yy_flex_alloc( size );
+ }
+
+void *flex_realloc( ptr, size )
+void *ptr;
+unsigned int size;
+ {
+ return yy_flex_realloc( ptr, size );
+ }
+
+void flex_free( ptr )
+void *ptr;
+ {
+ yy_flex_free( ptr );
+ }
diff --git a/usr.bin/lex/lex.1 b/usr.bin/lex/lex.1
new file mode 100644
index 000000000000..6aba4d6977ac
--- /dev/null
+++ b/usr.bin/lex/lex.1
@@ -0,0 +1,1001 @@
+.TH FLEX 1 "November 1993" "Version 2.4"
+.SH NAME
+flex \- fast lexical analyzer generator
+.SH SYNOPSIS
+.B flex
+.B [\-bcdfhilnpstvwBFILTV78+ \-C[aefFmr] \-Pprefix \-Sskeleton]
+.I [filename ...]
+.SH DESCRIPTION
+.I flex
+is a tool for generating
+.I scanners:
+programs which recognized lexical patterns in text.
+.I flex
+reads
+the given input files, or its standard input if no file names are given,
+for a description of a scanner to generate. The description is in
+the form of pairs
+of regular expressions and C code, called
+.I rules. flex
+generates as output a C source file,
+.B lex.yy.c,
+which defines a routine
+.B yylex().
+This file is compiled and linked with the
+.B \-lfl
+library to produce an executable. When the executable is run,
+it analyzes its input for occurrences
+of the regular expressions. Whenever it finds one, it executes
+the corresponding C code.
+.PP
+For full documentation, see
+.B flexdoc(1).
+This manual entry is intended for use as a quick reference.
+.SH OPTIONS
+.I flex
+has the following options:
+.TP
+.B \-b
+generate backing-up information to
+.I lex.backup.
+This is a list of scanner states which require backing up and the input
+characters on which they do so. By adding rules one can remove
+backing-up states. If all backing-up states are eliminated and
+.B \-Cf
+or
+.B \-CF
+is used, the generated scanner will run faster.
+.TP
+.B \-c
+is a do-nothing, deprecated option included for POSIX compliance.
+.IP
+.B NOTE:
+in previous releases of
+.I flex
+.B \-c
+specified table-compression options. This functionality is
+now given by the
+.B \-C
+flag. To ease the the impact of this change, when
+.I flex
+encounters
+.B \-c,
+it currently issues a warning message and assumes that
+.B \-C
+was desired instead. In the future this "promotion" of
+.B \-c
+to
+.B \-C
+will go away in the name of full POSIX compliance (unless
+the POSIX meaning is removed first).
+.TP
+.B \-d
+makes the generated scanner run in
+.I debug
+mode. Whenever a pattern is recognized and the global
+.B yy_flex_debug
+is non-zero (which is the default), the scanner will
+write to
+.I stderr
+a line of the form:
+.nf
+
+ --accepting rule at line 53 ("the matched text")
+
+.fi
+The line number refers to the location of the rule in the file
+defining the scanner (i.e., the file that was fed to flex). Messages
+are also generated when the scanner backs up, accepts the
+default rule, reaches the end of its input buffer (or encounters
+a NUL; the two look the same as far as the scanner's concerned),
+or reaches an end-of-file.
+.TP
+.B \-f
+specifies
+.I fast scanner.
+No table compression is done and stdio is bypassed.
+The result is large but fast. This option is equivalent to
+.B \-Cfr
+(see below).
+.TP
+.B \-h
+generates a "help" summary of
+.I flex's
+options to
+.I stderr
+and then exits.
+.TP
+.B \-i
+instructs
+.I flex
+to generate a
+.I case-insensitive
+scanner. The case of letters given in the
+.I flex
+input patterns will
+be ignored, and tokens in the input will be matched regardless of case. The
+matched text given in
+.I yytext
+will have the preserved case (i.e., it will not be folded).
+.TP
+.B \-l
+turns on maximum compatibility with the original AT&T lex implementation,
+at a considerable performance cost. This option is incompatible with
+.B \-+, \-f, \-F, \-Cf,
+or
+.B \-CF.
+See
+.I flexdoc(1)
+for details.
+.TP
+.B \-n
+is another do-nothing, deprecated option included only for
+POSIX compliance.
+.TP
+.B \-p
+generates a performance report to stderr. The report
+consists of comments regarding features of the
+.I flex
+input file which will cause a loss of performance in the resulting scanner.
+If you give the flag twice, you will also get comments regarding
+features that lead to minor performance losses.
+.TP
+.B \-s
+causes the
+.I default rule
+(that unmatched scanner input is echoed to
+.I stdout)
+to be suppressed. If the scanner encounters input that does not
+match any of its rules, it aborts with an error.
+.TP
+.B \-t
+instructs
+.I flex
+to write the scanner it generates to standard output instead
+of
+.B lex.yy.c.
+.TP
+.B \-v
+specifies that
+.I flex
+should write to
+.I stderr
+a summary of statistics regarding the scanner it generates.
+.TP
+.B \-w
+suppresses warning messages.
+.TP
+.B \-B
+instructs
+.I flex
+to generate a
+.I batch
+scanner instead of an
+.I interactive
+scanner (see
+.B \-I
+below). See
+.I flexdoc(1)
+for details. Scanners using
+.B \-Cf
+or
+.B \-CF
+compression options automatically specify this option, too.
+.TP
+.B \-F
+specifies that the
+.ul
+fast
+scanner table representation should be used (and stdio bypassed).
+This representation is about as fast as the full table representation
+.B (-f),
+and for some sets of patterns will be considerably smaller (and for
+others, larger). It cannot be used with the
+.B \-+
+option. See
+.B flexdoc(1)
+for more details.
+.IP
+This option is equivalent to
+.B \-CFr
+(see below).
+.TP
+.B \-I
+instructs
+.I flex
+to generate an
+.I interactive
+scanner, that is, a scanner which stops immediately rather than
+looking ahead if it knows
+that the currently scanned text cannot be part of a longer rule's match.
+This is the opposite of
+.I batch
+scanners (see
+.B \-B
+above). See
+.B flexdoc(1)
+for details.
+.IP
+Note,
+.B \-I
+cannot be used in conjunction with
+.I full
+or
+.I fast tables,
+i.e., the
+.B \-f, \-F, \-Cf,
+or
+.B \-CF
+flags. For other table compression options,
+.B \-I
+is the default.
+.TP
+.B \-L
+instructs
+.I flex
+not to generate
+.B #line
+directives in
+.B lex.yy.c.
+The default is to generate such directives so error
+messages in the actions will be correctly
+located with respect to the original
+.I flex
+input file, and not to
+the fairly meaningless line numbers of
+.B lex.yy.c.
+.TP
+.B \-T
+makes
+.I flex
+run in
+.I trace
+mode. It will generate a lot of messages to
+.I stderr
+concerning
+the form of the input and the resultant non-deterministic and deterministic
+finite automata. This option is mostly for use in maintaining
+.I flex.
+.TP
+.B \-V
+prints the version number to
+.I stderr
+and exits.
+.TP
+.B \-7
+instructs
+.I flex
+to generate a 7-bit scanner, which can save considerable table space,
+especially when using
+.B \-Cf
+or
+.B \-CF
+(and, at most sites,
+.B \-7
+is on by default for these options. To see if this is the case, use the
+.B -v
+verbose flag and check the flag summary it reports).
+.TP
+.B \-8
+instructs
+.I flex
+to generate an 8-bit scanner. This is the default except for the
+.B \-Cf
+and
+.B \-CF
+compression options, for which the default is site-dependent, and
+can be checked by inspecting the flag summary generated by the
+.B \-v
+option.
+.TP
+.B \-+
+specifies that you want flex to generate a C++
+scanner class. See the section on Generating C++ Scanners in
+.I flexdoc(1)
+for details.
+.TP
+.B \-C[aefFmr]
+controls the degree of table compression and scanner optimization.
+.IP
+.B \-Ca
+trade off larger tables in the generated scanner for faster performance
+because the elements of the tables are better aligned for memory access
+and computation. This option can double the size of the tables used by
+your scanner.
+.IP
+.B \-Ce
+directs
+.I flex
+to construct
+.I equivalence classes,
+i.e., sets of characters
+which have identical lexical properties.
+Equivalence classes usually give
+dramatic reductions in the final table/object file sizes (typically
+a factor of 2-5) and are pretty cheap performance-wise (one array
+look-up per character scanned).
+.IP
+.B \-Cf
+specifies that the
+.I full
+scanner tables should be generated -
+.I flex
+should not compress the
+tables by taking advantages of similar transition functions for
+different states.
+.IP
+.B \-CF
+specifies that the alternate fast scanner representation (described in
+.B flexdoc(1))
+should be used. This option cannot be used with
+.B \-+.
+.IP
+.B \-Cm
+directs
+.I flex
+to construct
+.I meta-equivalence classes,
+which are sets of equivalence classes (or characters, if equivalence
+classes are not being used) that are commonly used together. Meta-equivalence
+classes are often a big win when using compressed tables, but they
+have a moderate performance impact (one or two "if" tests and one
+array look-up per character scanned).
+.IP
+.B \-Cr
+causes the generated scanner to
+.I bypass
+using stdio for input. In general this option results in a minor
+performance gain only worthwhile if used in conjunction with
+.B \-Cf
+or
+.B \-CF.
+It can cause surprising behavior if you use stdio yourself to
+read from
+.I yyin
+prior to calling the scanner.
+.IP
+A lone
+.B \-C
+specifies that the scanner tables should be compressed but neither
+equivalence classes nor meta-equivalence classes should be used.
+.IP
+The options
+.B \-Cf
+or
+.B \-CF
+and
+.B \-Cm
+do not make sense together - there is no opportunity for meta-equivalence
+classes if the table is not being compressed. Otherwise the options
+may be freely mixed.
+.IP
+The default setting is
+.B \-Cem,
+which specifies that
+.I flex
+should generate equivalence classes
+and meta-equivalence classes. This setting provides the highest
+degree of table compression. You can trade off
+faster-executing scanners at the cost of larger tables with
+the following generally being true:
+.nf
+
+ slowest & smallest
+ -Cem
+ -Cm
+ -Ce
+ -C
+ -C{f,F}e
+ -C{f,F}
+ -C{f,F}a
+ fastest & largest
+
+.fi
+.IP
+.B \-C
+options are cumulative.
+.TP
+.B \-Pprefix
+changes the default
+.I "yy"
+prefix used by
+.I flex
+to be
+.I prefix
+instead. See
+.I flexdoc(1)
+for a description of all the global variables and file names that
+this affects.
+.TP
+.B \-Sskeleton_file
+overrides the default skeleton file from which
+.I flex
+constructs its scanners. You'll never need this option unless you are doing
+.I flex
+maintenance or development.
+.SH SUMMARY OF FLEX REGULAR EXPRESSIONS
+The patterns in the input are written using an extended set of regular
+expressions. These are:
+.nf
+
+ x match the character 'x'
+ . any character except newline
+ [xyz] a "character class"; in this case, the pattern
+ matches either an 'x', a 'y', or a 'z'
+ [abj-oZ] a "character class" with a range in it; matches
+ an 'a', a 'b', any letter from 'j' through 'o',
+ or a 'Z'
+ [^A-Z] a "negated character class", i.e., any character
+ but those in the class. In this case, any
+ character EXCEPT an uppercase letter.
+ [^A-Z\\n] any character EXCEPT an uppercase letter or
+ a newline
+ r* zero or more r's, where r is any regular expression
+ r+ one or more r's
+ r? zero or one r's (that is, "an optional r")
+ r{2,5} anywhere from two to five r's
+ r{2,} two or more r's
+ r{4} exactly 4 r's
+ {name} the expansion of the "name" definition
+ (see above)
+ "[xyz]\\"foo"
+ the literal string: [xyz]"foo
+ \\X if X is an 'a', 'b', 'f', 'n', 'r', 't', or 'v',
+ then the ANSI-C interpretation of \\x.
+ Otherwise, a literal 'X' (used to escape
+ operators such as '*')
+ \\123 the character with octal value 123
+ \\x2a the character with hexadecimal value 2a
+ (r) match an r; parentheses are used to override
+ precedence (see below)
+
+
+ rs the regular expression r followed by the
+ regular expression s; called "concatenation"
+
+
+ r|s either an r or an s
+
+
+ r/s an r but only if it is followed by an s. The
+ s is not part of the matched text. This type
+ of pattern is called as "trailing context".
+ ^r an r, but only at the beginning of a line
+ r$ an r, but only at the end of a line. Equivalent
+ to "r/\\n".
+
+
+ <s>r an r, but only in start condition s (see
+ below for discussion of start conditions)
+ <s1,s2,s3>r
+ same, but in any of start conditions s1,
+ s2, or s3
+ <*>r an r in any start condition, even an exclusive one.
+
+
+ <<EOF>> an end-of-file
+ <s1,s2><<EOF>>
+ an end-of-file when in start condition s1 or s2
+
+.fi
+The regular expressions listed above are grouped according to
+precedence, from highest precedence at the top to lowest at the bottom.
+Those grouped together have equal precedence.
+.PP
+Some notes on patterns:
+.IP -
+Negated character classes
+.I match newlines
+unless "\\n" (or an equivalent escape sequence) is one of the
+characters explicitly present in the negated character class
+(e.g., "[^A-Z\\n]").
+.IP -
+A rule can have at most one instance of trailing context (the '/' operator
+or the '$' operator). The start condition, '^', and "<<EOF>>" patterns
+can only occur at the beginning of a pattern, and, as well as with '/' and '$',
+cannot be grouped inside parentheses. The following are all illegal:
+.nf
+
+ foo/bar$
+ foo|(bar$)
+ foo|^bar
+ <sc1>foo<sc2>bar
+
+.fi
+.SH SUMMARY OF SPECIAL ACTIONS
+In addition to arbitrary C code, the following can appear in actions:
+.IP -
+.B ECHO
+copies yytext to the scanner's output.
+.IP -
+.B BEGIN
+followed by the name of a start condition places the scanner in the
+corresponding start condition.
+.IP -
+.B REJECT
+directs the scanner to proceed on to the "second best" rule which matched the
+input (or a prefix of the input).
+.B yytext
+and
+.B yyleng
+are set up appropriately. Note that
+.B REJECT
+is a particularly expensive feature in terms scanner performance;
+if it is used in
+.I any
+of the scanner's actions it will slow down
+.I all
+of the scanner's matching. Furthermore,
+.B REJECT
+cannot be used with the
+.B \-f
+or
+.B \-F
+options.
+.IP
+Note also that unlike the other special actions,
+.B REJECT
+is a
+.I branch;
+code immediately following it in the action will
+.I not
+be executed.
+.IP -
+.B yymore()
+tells the scanner that the next time it matches a rule, the corresponding
+token should be
+.I appended
+onto the current value of
+.B yytext
+rather than replacing it.
+.IP -
+.B yyless(n)
+returns all but the first
+.I n
+characters of the current token back to the input stream, where they
+will be rescanned when the scanner looks for the next match.
+.B yytext
+and
+.B yyleng
+are adjusted appropriately (e.g.,
+.B yyleng
+will now be equal to
+.I n
+).
+.IP -
+.B unput(c)
+puts the character
+.I c
+back onto the input stream. It will be the next character scanned.
+.IP -
+.B input()
+reads the next character from the input stream (this routine is called
+.B yyinput()
+if the scanner is compiled using
+.B C++).
+.IP -
+.B yyterminate()
+can be used in lieu of a return statement in an action. It terminates
+the scanner and returns a 0 to the scanner's caller, indicating "all done".
+.IP
+By default,
+.B yyterminate()
+is also called when an end-of-file is encountered. It is a macro and
+may be redefined.
+.IP -
+.B YY_NEW_FILE
+is an action available only in <<EOF>> rules. It means "Okay, I've
+set up a new input file, continue scanning". It is no longer required;
+you can just assign
+.I yyin
+to point to a new file in the <<EOF>> action.
+.IP -
+.B yy_create_buffer( file, size )
+takes a
+.I FILE
+pointer and an integer
+.I size.
+It returns a YY_BUFFER_STATE
+handle to a new input buffer large enough to accomodate
+.I size
+characters and associated with the given file. When in doubt, use
+.B YY_BUF_SIZE
+for the size.
+.IP -
+.B yy_switch_to_buffer( new_buffer )
+switches the scanner's processing to scan for tokens from
+the given buffer, which must be a YY_BUFFER_STATE.
+.IP -
+.B yy_delete_buffer( buffer )
+deletes the given buffer.
+.SH VALUES AVAILABLE TO THE USER
+.IP -
+.B char *yytext
+holds the text of the current token. It may be modified but not lengthened
+(you cannot append characters to the end). Modifying the last character
+may affect the activity of rules anchored using '^' during the next scan;
+see
+.B flexdoc(1)
+for details.
+.IP
+If the special directive
+.B %array
+appears in the first section of the scanner description, then
+.B yytext
+is instead declared
+.B char yytext[YYLMAX],
+where
+.B YYLMAX
+is a macro definition that you can redefine in the first section
+if you don't like the default value (generally 8KB). Using
+.B %array
+results in somewhat slower scanners, but the value of
+.B yytext
+becomes immune to calls to
+.I input()
+and
+.I unput(),
+which potentially destroy its value when
+.B yytext
+is a character pointer. The opposite of
+.B %array
+is
+.B %pointer,
+which is the default.
+.IP
+You cannot use
+.B %array
+when generating C++ scanner classes
+(the
+.B \-+
+flag).
+.IP -
+.B int yyleng
+holds the length of the current token.
+.IP -
+.B FILE *yyin
+is the file which by default
+.I flex
+reads from. It may be redefined but doing so only makes sense before
+scanning begins or after an EOF has been encountered. Changing it in
+the midst of scanning will have unexpected results since
+.I flex
+buffers its input; use
+.B yyrestart()
+instead.
+Once scanning terminates because an end-of-file
+has been seen,
+.B
+you can assign
+.I yyin
+at the new input file and then call the scanner again to continue scanning.
+.IP -
+.B void yyrestart( FILE *new_file )
+may be called to point
+.I yyin
+at the new input file. The switch-over to the new file is immediate
+(any previously buffered-up input is lost). Note that calling
+.B yyrestart()
+with
+.I yyin
+as an argument thus throws away the current input buffer and continues
+scanning the same input file.
+.IP -
+.B FILE *yyout
+is the file to which
+.B ECHO
+actions are done. It can be reassigned by the user.
+.IP -
+.B YY_CURRENT_BUFFER
+returns a
+.B YY_BUFFER_STATE
+handle to the current buffer.
+.IP -
+.B YY_START
+returns an integer value corresponding to the current start
+condition. You can subsequently use this value with
+.B BEGIN
+to return to that start condition.
+.SH MACROS AND FUNCTIONS YOU CAN REDEFINE
+.IP -
+.B YY_DECL
+controls how the scanning routine is declared.
+By default, it is "int yylex()", or, if prototypes are being
+used, "int yylex(void)". This definition may be changed by redefining
+the "YY_DECL" macro. Note that
+if you give arguments to the scanning routine using a
+K&R-style/non-prototyped function declaration, you must terminate
+the definition with a semi-colon (;).
+.IP -
+The nature of how the scanner
+gets its input can be controlled by redefining the
+.B YY_INPUT
+macro.
+YY_INPUT's calling sequence is "YY_INPUT(buf,result,max_size)". Its
+action is to place up to
+.I max_size
+characters in the character array
+.I buf
+and return in the integer variable
+.I result
+either the
+number of characters read or the constant YY_NULL (0 on Unix systems)
+to indicate EOF. The default YY_INPUT reads from the
+global file-pointer "yyin".
+A sample redefinition of YY_INPUT (in the definitions
+section of the input file):
+.nf
+
+ %{
+ #undef YY_INPUT
+ #define YY_INPUT(buf,result,max_size) \\
+ { \\
+ int c = getchar(); \\
+ result = (c == EOF) ? YY_NULL : (buf[0] = c, 1); \\
+ }
+ %}
+
+.fi
+.IP -
+When the scanner receives an end-of-file indication from YY_INPUT,
+it then checks the function
+.B yywrap()
+function. If
+.B yywrap()
+returns false (zero), then it is assumed that the
+function has gone ahead and set up
+.I yyin
+to point to another input file, and scanning continues. If it returns
+true (non-zero), then the scanner terminates, returning 0 to its
+caller.
+.IP
+The default
+.B yywrap()
+always returns 1.
+.IP -
+YY_USER_ACTION
+can be redefined to provide an action
+which is always executed prior to the matched rule's action.
+.IP -
+The macro
+.B YY_USER_INIT
+may be redefined to provide an action which is always executed before
+the first scan.
+.IP -
+In the generated scanner, the actions are all gathered in one large
+switch statement and separated using
+.B YY_BREAK,
+which may be redefined. By default, it is simply a "break", to separate
+each rule's action from the following rule's.
+.SH FILES
+.TP
+.B \-lfl
+library with which to link scanners to obtain the default versions
+of
+.I yywrap()
+and/or
+.I main().
+.TP
+.I lex.yy.c
+generated scanner (called
+.I lexyy.c
+on some systems).
+.TP
+.I lex.yy.cc
+generated C++ scanner class, when using
+.B -+.
+.TP
+.I <FlexLexer.h>
+header file defining the C++ scanner base class,
+.B FlexLexer,
+and its derived class,
+.B yyFlexLexer.
+.TP
+.I flex.skl
+skeleton scanner. This file is only used when building flex, not when
+flex executes.
+.TP
+.I lex.backup
+backing-up information for
+.B \-b
+flag (called
+.I lex.bck
+on some systems).
+.SH "SEE ALSO"
+.PP
+flexdoc(1), lex(1), yacc(1), sed(1), awk(1).
+.PP
+M. E. Lesk and E. Schmidt,
+.I LEX \- Lexical Analyzer Generator
+.SH DIAGNOSTICS
+.PP
+.I reject_used_but_not_detected undefined
+or
+.PP
+.I yymore_used_but_not_detected undefined -
+These errors can occur at compile time. They indicate that the
+scanner uses
+.B REJECT
+or
+.B yymore()
+but that
+.I flex
+failed to notice the fact, meaning that
+.I flex
+scanned the first two sections looking for occurrences of these actions
+and failed to find any, but somehow you snuck some in (via a #include
+file, for example). Make an explicit reference to the action in your
+.I flex
+input file. (Note that previously
+.I flex
+supported a
+.B %used/%unused
+mechanism for dealing with this problem; this feature is still supported
+but now deprecated, and will go away soon unless the author hears from
+people who can argue compellingly that they need it.)
+.PP
+.I flex scanner jammed -
+a scanner compiled with
+.B \-s
+has encountered an input string which wasn't matched by
+any of its rules.
+.PP
+.I warning, rule cannot be matched
+indicates that the given rule
+cannot be matched because it follows other rules that will
+always match the same text as it. See
+.I flexdoc(1)
+for an example.
+.PP
+.I warning,
+.B \-s
+.I
+option given but default rule can be matched
+means that it is possible (perhaps only in a particular start condition)
+that the default rule (match any single character) is the only one
+that will match a particular input. Since
+.PP
+.I scanner input buffer overflowed -
+a scanner rule matched more text than the available dynamic memory.
+.PP
+.I token too large, exceeds YYLMAX -
+your scanner uses
+.B %array
+and one of its rules matched a string longer than the
+.B YYLMAX
+constant (8K bytes by default). You can increase the value by
+#define'ing
+.B YYLMAX
+in the definitions section of your
+.I flex
+input.
+.PP
+.I scanner requires \-8 flag to
+.I use the character 'x' -
+Your scanner specification includes recognizing the 8-bit character
+.I 'x'
+and you did not specify the \-8 flag, and your scanner defaulted to 7-bit
+because you used the
+.B \-Cf
+or
+.B \-CF
+table compression options.
+.PP
+.I flex scanner push-back overflow -
+you used
+.B unput()
+to push back so much text that the scanner's buffer could not hold
+both the pushed-back text and the current token in
+.B yytext.
+Ideally the scanner should dynamically resize the buffer in this case, but at
+present it does not.
+.PP
+.I
+input buffer overflow, can't enlarge buffer because scanner uses REJECT -
+the scanner was working on matching an extremely large token and needed
+to expand the input buffer. This doesn't work with scanners that use
+.B
+REJECT.
+.PP
+.I
+fatal flex scanner internal error--end of buffer missed -
+This can occur in an scanner which is reentered after a long-jump
+has jumped out (or over) the scanner's activation frame. Before
+reentering the scanner, use:
+.nf
+
+ yyrestart( yyin );
+
+.fi
+or use C++ scanner classes (the
+.B \-+
+option), which are fully reentrant.
+.SH AUTHOR
+Vern Paxson, with the help of many ideas and much inspiration from
+Van Jacobson. Original version by Jef Poskanzer.
+.PP
+See flexdoc(1) for additional credits and the address to send comments to.
+.SH DEFICIENCIES / BUGS
+.PP
+Some trailing context
+patterns cannot be properly matched and generate
+warning messages ("dangerous trailing context"). These are
+patterns where the ending of the
+first part of the rule matches the beginning of the second
+part, such as "zx*/xy*", where the 'x*' matches the 'x' at
+the beginning of the trailing context. (Note that the POSIX draft
+states that the text matched by such patterns is undefined.)
+.PP
+For some trailing context rules, parts which are actually fixed-length are
+not recognized as such, leading to the abovementioned performance loss.
+In particular, parts using '|' or {n} (such as "foo{3}") are always
+considered variable-length.
+.PP
+Combining trailing context with the special '|' action can result in
+.I fixed
+trailing context being turned into the more expensive
+.I variable
+trailing context. For example, in the following:
+.nf
+
+ %%
+ abc |
+ xyz/def
+
+.fi
+.PP
+Use of
+.B unput()
+or
+.B input()
+invalidates yytext and yyleng, unless the
+.B %array
+directive
+or the
+.B \-l
+option has been used.
+.PP
+Use of unput() to push back more text than was matched can
+result in the pushed-back text matching a beginning-of-line ('^')
+rule even though it didn't come at the beginning of the line
+(though this is rare!).
+.PP
+Pattern-matching of NUL's is substantially slower than matching other
+characters.
+.PP
+Dynamic resizing of the input buffer is slow, as it entails rescanning
+all the text matched so far by the current (generally huge) token.
+.PP
+.I flex
+does not generate correct #line directives for code internal
+to the scanner; thus, bugs in
+.I flex.skl
+yield bogus line numbers.
+.PP
+Due to both buffering of input and read-ahead, you cannot intermix
+calls to <stdio.h> routines, such as, for example,
+.B getchar(),
+with
+.I flex
+rules and expect it to work. Call
+.B input()
+instead.
+.PP
+The total table entries listed by the
+.B \-v
+flag excludes the number of table entries needed to determine
+what rule has been matched. The number of entries is equal
+to the number of DFA states if the scanner does not use
+.B REJECT,
+and somewhat greater than the number of states if it does.
+.PP
+.B REJECT
+cannot be used with the
+.B \-f
+or
+.B \-F
+options.
+.PP
+The
+.I flex
+internal algorithms need documentation.
diff --git a/usr.bin/lex/lib/Makefile b/usr.bin/lex/lib/Makefile
new file mode 100644
index 000000000000..406e542a9149
--- /dev/null
+++ b/usr.bin/lex/lib/Makefile
@@ -0,0 +1,20 @@
+# $Id$
+
+LIB= ln
+SRCS= libmain.c libyywrap.c
+LINKS= ${LIBDIR}/libln.a ${LIBDIR}/libl.a \
+
+.if !defined(NOPROFILE)
+LINKS+= ${LIBDIR}/libln_p.a ${LIBDIR}/libl_p.a
+.endif
+
+.if !defined(NOSHARED)
+LINKS+= ${LIBDIR}/libln.so.$(SHLIB_MAJOR).$(SHLIB_MINOR) \
+ ${LIBDIR}/libl.so.$(SHLIB_MAJOR).$(SHLIB_MINOR)
+.endif
+
+#This is where we get our SHLIB_MAJOR and SHLIB_MINOR
+.include "${.CURDIR}/../../../lib/Makefile.inc"
+
+.include <bsd.lib.mk>
+
diff --git a/usr.bin/lex/lib/libmain.c b/usr.bin/lex/lib/libmain.c
new file mode 100644
index 000000000000..a893c7abd3d2
--- /dev/null
+++ b/usr.bin/lex/lib/libmain.c
@@ -0,0 +1,12 @@
+/* libmain - flex run-time support library "main" function */
+
+/* $Header: /home/daffy/u0/vern/flex/RCS/libmain.c,v 1.3 93/04/14 22:41:55 vern Exp $ */
+
+extern int yylex();
+
+int main( argc, argv )
+int argc;
+char *argv[];
+ {
+ return yylex();
+ }
diff --git a/usr.bin/lex/lib/libyywrap.c b/usr.bin/lex/lib/libyywrap.c
new file mode 100644
index 000000000000..b18f54e6e8f9
--- /dev/null
+++ b/usr.bin/lex/lib/libyywrap.c
@@ -0,0 +1,8 @@
+/* libyywrap - flex run-time support library "yywrap" function */
+
+/* $Header: /home/daffy/u0/vern/flex/RCS/libyywrap.c,v 1.1 93/10/02 15:23:09 vern Exp $ */
+
+int yywrap()
+ {
+ return 1;
+ }
diff --git a/usr.bin/lex/main.c b/usr.bin/lex/main.c
new file mode 100644
index 000000000000..a90027add059
--- /dev/null
+++ b/usr.bin/lex/main.c
@@ -0,0 +1,989 @@
+/* flex - tool to generate fast lexical analyzers */
+
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+#ifndef lint
+char copyright[] =
+"@(#) Copyright (c) 1990 The Regents of the University of California.\n\
+ All rights reserved.\n";
+#endif /* not lint */
+
+/* $Header: main.c,v 1.2 94/01/04 14:33:11 vern Exp $ */
+
+
+#include "flexdef.h"
+#include "version.h"
+
+static char flex_version[] = FLEX_VERSION;
+
+
+/* declare functions that have forward references */
+
+void flexinit PROTO((int, char**));
+void readin PROTO((void));
+void set_up_initial_allocations PROTO((void));
+
+
+/* these globals are all defined and commented in flexdef.h */
+int printstats, syntaxerror, eofseen, ddebug, trace, nowarn, spprdflt;
+int interactive, caseins, lex_compat, useecs, fulltbl, usemecs;
+int fullspd, gen_line_dirs, performance_report, backing_up_report;
+int C_plus_plus, long_align, use_read, yytext_is_array, csize;
+int yymore_used, reject, real_reject, continued_action;
+int yymore_really_used, reject_really_used;
+int datapos, dataline, linenum;
+FILE *skelfile = NULL;
+int skel_ind = 0;
+char *action_array;
+int action_size, defs1_offset, prolog_offset, action_offset, action_index;
+char *infilename = NULL;
+int onestate[ONE_STACK_SIZE], onesym[ONE_STACK_SIZE];
+int onenext[ONE_STACK_SIZE], onedef[ONE_STACK_SIZE], onesp;
+int current_mns, num_rules, num_eof_rules, default_rule;
+int current_max_rules, lastnfa;
+int *firstst, *lastst, *finalst, *transchar, *trans1, *trans2;
+int *accptnum, *assoc_rule, *state_type;
+int *rule_type, *rule_linenum, *rule_useful;
+int current_state_type;
+int variable_trailing_context_rules;
+int numtemps, numprots, protprev[MSP], protnext[MSP], prottbl[MSP];
+int protcomst[MSP], firstprot, lastprot, protsave[PROT_SAVE_SIZE];
+int numecs, nextecm[CSIZE + 1], ecgroup[CSIZE + 1], nummecs, tecfwd[CSIZE + 1];
+int tecbck[CSIZE + 1];
+int lastsc, current_max_scs, *scset, *scbol, *scxclu, *sceof, *actvsc;
+char **scname;
+int current_max_dfa_size, current_max_xpairs;
+int current_max_template_xpairs, current_max_dfas;
+int lastdfa, *nxt, *chk, *tnxt;
+int *base, *def, *nultrans, NUL_ec, tblend, firstfree, **dss, *dfasiz;
+union dfaacc_union *dfaacc;
+int *accsiz, *dhash, numas;
+int numsnpairs, jambase, jamstate;
+int lastccl, current_maxccls, *cclmap, *ccllen, *cclng, cclreuse;
+int current_max_ccl_tbl_size;
+Char *ccltbl;
+char nmstr[MAXLINE];
+int sectnum, nummt, hshcol, dfaeql, numeps, eps2, num_reallocs;
+int tmpuses, totnst, peakpairs, numuniq, numdup, hshsave;
+int num_backing_up, bol_needed;
+FILE *backing_up_file;
+int end_of_buffer_state;
+char **input_files;
+int num_input_files;
+char *program_name;
+
+#ifndef SHORT_FILE_NAMES
+static char *outfile_template = "lex.%s.%s";
+#else
+static char *outfile_template = "lex%s.%s";
+#endif
+static char outfile_path[64];
+
+static int outfile_created = 0;
+static int use_stdout;
+static char *skelname = NULL;
+static char *prefix = "yy";
+
+
+int main( argc, argv )
+int argc;
+char **argv;
+ {
+ int i;
+
+ flexinit( argc, argv );
+
+ readin();
+
+ ntod();
+
+ for ( i = 1; i <= num_rules; ++i )
+ if ( ! rule_useful[i] && i != default_rule )
+ line_warning( "rule cannot be matched",
+ rule_linenum[i] );
+
+ if ( spprdflt && ! reject && rule_useful[default_rule] )
+ line_warning( "-s option given but default rule can be matched",
+ rule_linenum[default_rule] );
+
+ /* Generate the C state transition tables from the DFA. */
+ make_tables();
+
+ /* Note, flexend does not return. It exits with its argument
+ * as status.
+ */
+ flexend( 0 );
+
+ return 0; /* keep compilers/lint happy */
+ }
+
+
+/* flexend - terminate flex
+ *
+ * note
+ * This routine does not return.
+ */
+
+void flexend( exit_status )
+int exit_status;
+
+ {
+ int tblsiz;
+ int unlink();
+
+ if ( skelfile != NULL )
+ {
+ if ( ferror( skelfile ) )
+ flexfatal(
+ "error occurred when reading skeleton file" );
+
+ else if ( fclose( skelfile ) )
+ flexfatal(
+ "error occurred when closing skeleton file" );
+ }
+
+ if ( exit_status != 0 && outfile_created )
+ {
+ if ( ferror( stdout ) )
+ flexfatal( "error occurred when writing output file" );
+
+ else if ( fclose( stdout ) )
+ flexfatal( "error occurred when closing output file" );
+
+ else if ( unlink( outfile_path ) )
+ flexfatal( "error occurred when deleting output file" );
+ }
+
+ if ( backing_up_report && backing_up_file )
+ {
+ if ( num_backing_up == 0 )
+ fprintf( backing_up_file, "No backing up.\n" );
+ else if ( fullspd || fulltbl )
+ fprintf( backing_up_file,
+ "%d backing up (non-accepting) states.\n",
+ num_backing_up );
+ else
+ fprintf( backing_up_file,
+ "Compressed tables always back up.\n" );
+
+ if ( ferror( backing_up_file ) )
+ flexfatal( "error occurred when writing backup file" );
+
+ else if ( fclose( backing_up_file ) )
+ flexfatal( "error occurred when closing backup file" );
+ }
+
+ if ( printstats )
+ {
+ fprintf( stderr, "%s version %s usage statistics:\n",
+ program_name, flex_version );
+
+ fprintf( stderr, " scanner options: -" );
+
+ if ( C_plus_plus )
+ putc( '+', stderr );
+ if ( backing_up_report )
+ putc( 'b', stderr );
+ if ( ddebug )
+ putc( 'd', stderr );
+ if ( caseins )
+ putc( 'i', stderr );
+ if ( lex_compat )
+ putc( 'l', stderr );
+ if ( performance_report > 0 )
+ putc( 'p', stderr );
+ if ( performance_report > 1 )
+ putc( 'p', stderr );
+ if ( spprdflt )
+ putc( 's', stderr );
+ if ( use_stdout )
+ putc( 't', stderr );
+ if ( printstats )
+ putc( 'v', stderr ); /* always true! */
+ if ( nowarn )
+ putc( 'w', stderr );
+ if ( ! interactive )
+ putc( 'B', stderr );
+ if ( interactive )
+ putc( 'I', stderr );
+ if ( ! gen_line_dirs )
+ putc( 'L', stderr );
+ if ( trace )
+ putc( 'T', stderr );
+ if ( csize == 128 )
+ putc( '7', stderr );
+ else
+ putc( '8', stderr );
+
+ fprintf( stderr, " -C" );
+
+ if ( long_align )
+ putc( 'a', stderr );
+ if ( fulltbl )
+ putc( 'f', stderr );
+ if ( fullspd )
+ putc( 'F', stderr );
+ if ( useecs )
+ putc( 'e', stderr );
+ if ( usemecs )
+ putc( 'm', stderr );
+ if ( use_read )
+ putc( 'r', stderr );
+
+ if ( skelname )
+ fprintf( stderr, " -S%s", skelname );
+
+ if ( strcmp( prefix, "yy" ) )
+ fprintf( stderr, " -P%s", prefix );
+
+ putc( '\n', stderr );
+
+ fprintf( stderr, " %d/%d NFA states\n", lastnfa, current_mns );
+ fprintf( stderr, " %d/%d DFA states (%d words)\n", lastdfa,
+ current_max_dfas, totnst );
+ fprintf( stderr, " %d rules\n",
+ num_rules + num_eof_rules - 1 /* - 1 for def. rule */ );
+
+ if ( num_backing_up == 0 )
+ fprintf( stderr, " No backing up\n" );
+ else if ( fullspd || fulltbl )
+ fprintf( stderr,
+ " %d backing-up (non-accepting) states\n",
+ num_backing_up );
+ else
+ fprintf( stderr,
+ " Compressed tables always back-up\n" );
+
+ if ( bol_needed )
+ fprintf( stderr,
+ " Beginning-of-line patterns used\n" );
+
+ fprintf( stderr, " %d/%d start conditions\n", lastsc,
+ current_max_scs );
+ fprintf( stderr,
+ " %d epsilon states, %d double epsilon states\n",
+ numeps, eps2 );
+
+ if ( lastccl == 0 )
+ fprintf( stderr, " no character classes\n" );
+ else
+ fprintf( stderr,
+ " %d/%d character classes needed %d/%d words of storage, %d reused\n",
+ lastccl, current_maxccls,
+ cclmap[lastccl] + ccllen[lastccl],
+ current_max_ccl_tbl_size, cclreuse );
+
+ fprintf( stderr, " %d state/nextstate pairs created\n",
+ numsnpairs );
+ fprintf( stderr, " %d/%d unique/duplicate transitions\n",
+ numuniq, numdup );
+
+ if ( fulltbl )
+ {
+ tblsiz = lastdfa * numecs;
+ fprintf( stderr, " %d table entries\n", tblsiz );
+ }
+
+ else
+ {
+ tblsiz = 2 * (lastdfa + numtemps) + 2 * tblend;
+
+ fprintf( stderr, " %d/%d base-def entries created\n",
+ lastdfa + numtemps, current_max_dfas );
+ fprintf( stderr,
+ " %d/%d (peak %d) nxt-chk entries created\n",
+ tblend, current_max_xpairs, peakpairs );
+ fprintf( stderr,
+ " %d/%d (peak %d) template nxt-chk entries created\n",
+ numtemps * nummecs, current_max_template_xpairs,
+ numtemps * numecs );
+ fprintf( stderr, " %d empty table entries\n", nummt );
+ fprintf( stderr, " %d protos created\n", numprots );
+ fprintf( stderr, " %d templates created, %d uses\n",
+ numtemps, tmpuses );
+ }
+
+ if ( useecs )
+ {
+ tblsiz = tblsiz + csize;
+ fprintf( stderr,
+ " %d/%d equivalence classes created\n",
+ numecs, csize );
+ }
+
+ if ( usemecs )
+ {
+ tblsiz = tblsiz + numecs;
+ fprintf( stderr,
+ " %d/%d meta-equivalence classes created\n",
+ nummecs, csize );
+ }
+
+ fprintf( stderr,
+ " %d (%d saved) hash collisions, %d DFAs equal\n",
+ hshcol, hshsave, dfaeql );
+ fprintf( stderr, " %d sets of reallocations needed\n",
+ num_reallocs );
+ fprintf( stderr, " %d total table entries needed\n", tblsiz );
+ }
+
+#ifndef VMS
+ exit( exit_status );
+#else
+ exit( exit_status + 1 );
+#endif
+ }
+
+
+/* flexinit - initialize flex */
+
+void flexinit( argc, argv )
+int argc;
+char **argv;
+ {
+ int i, sawcmpflag;
+ int csize_given, interactive_given;
+ char *arg, *mktemp();
+
+ printstats = syntaxerror = trace = spprdflt = caseins = false;
+ lex_compat = false;
+ C_plus_plus = backing_up_report = ddebug = fulltbl = fullspd = false;
+ long_align = nowarn = yymore_used = continued_action = reject = false;
+ yytext_is_array = yymore_really_used = reject_really_used = false;
+ gen_line_dirs = usemecs = useecs = true;
+ performance_report = 0;
+
+ sawcmpflag = false;
+ use_read = use_stdout = false;
+ csize_given = false;
+ interactive_given = false;
+
+ /* Initialize dynamic array for holding the rule actions. */
+ action_size = 2048; /* default size of action array in bytes */
+ action_array = allocate_character_array( action_size );
+ defs1_offset = prolog_offset = action_offset = action_index = 0;
+ action_array[0] = '\0';
+
+ program_name = argv[0];
+
+ if ( program_name[0] != '\0' &&
+ program_name[strlen( program_name ) - 1] == '+' )
+ C_plus_plus = true;
+
+ /* read flags */
+ for ( --argc, ++argv; argc ; --argc, ++argv )
+ {
+ if ( argv[0][0] != '-' || argv[0][1] == '\0' )
+ break;
+
+ arg = argv[0];
+
+ for ( i = 1; arg[i] != '\0'; ++i )
+ switch ( arg[i] )
+ {
+ case '+':
+ C_plus_plus = true;
+ break;
+
+ case 'B':
+ interactive = false;
+ interactive_given = true;
+ break;
+
+ case 'b':
+ backing_up_report = true;
+ break;
+
+ case 'c':
+ fprintf( stderr,
+ "%s: Assuming use of deprecated -c flag is really intended to be -C\n",
+ program_name );
+
+ /* fall through */
+
+ case 'C':
+ if ( i != 1 )
+ flexerror(
+ "-C flag must be given separately" );
+
+ if ( ! sawcmpflag )
+ {
+ useecs = false;
+ usemecs = false;
+ fulltbl = false;
+ sawcmpflag = true;
+ }
+
+ for ( ++i; arg[i] != '\0'; ++i )
+ switch ( arg[i] )
+ {
+ case 'a':
+ long_align =
+ true;
+ break;
+
+ case 'e':
+ useecs = true;
+ break;
+
+ case 'F':
+ fullspd = true;
+ break;
+
+ case 'f':
+ fulltbl = true;
+ break;
+
+ case 'm':
+ usemecs = true;
+ break;
+
+ case 'r':
+ use_read = true;
+ break;
+
+ default:
+ lerrif(
+ "unknown -C option '%c'",
+ (int) arg[i] );
+ break;
+ }
+
+ goto get_next_arg;
+
+ case 'd':
+ ddebug = true;
+ break;
+
+ case 'f':
+ useecs = usemecs = false;
+ use_read = fulltbl = true;
+ break;
+
+ case 'F':
+ useecs = usemecs = false;
+ use_read = fullspd = true;
+ break;
+
+ case 'h':
+ usage();
+ exit( 0 );
+
+ case 'I':
+ interactive = true;
+ interactive_given = true;
+ break;
+
+ case 'i':
+ caseins = true;
+ break;
+
+ case 'l':
+ lex_compat = true;
+ break;
+
+ case 'L':
+ gen_line_dirs = false;
+ break;
+
+ case 'n':
+ /* Stupid do-nothing deprecated
+ * option.
+ */
+ break;
+
+ case 'P':
+ if ( i != 1 )
+ flexerror(
+ "-P flag must be given separately" );
+
+ prefix = arg + i + 1;
+ goto get_next_arg;
+
+ case 'p':
+ ++performance_report;
+ break;
+
+ case 'S':
+ if ( i != 1 )
+ flexerror(
+ "-S flag must be given separately" );
+
+ skelname = arg + i + 1;
+ goto get_next_arg;
+
+ case 's':
+ spprdflt = true;
+ break;
+
+ case 't':
+ use_stdout = true;
+ break;
+
+ case 'T':
+ trace = true;
+ break;
+
+ case 'v':
+ printstats = true;
+ break;
+
+ case 'V':
+ fprintf( stderr, "%s version %s\n",
+ program_name, flex_version );
+ exit( 0 );
+
+ case 'w':
+ nowarn = true;
+ break;
+
+ case '7':
+ csize = 128;
+ csize_given = true;
+ break;
+
+ case '8':
+ csize = CSIZE;
+ csize_given = true;
+ break;
+
+ default:
+ fprintf( stderr,
+ "%s: unknown flag '%c'\n",
+ program_name, (int) arg[i] );
+ usage();
+ exit( 1 );
+ }
+
+ /* Used by -C, -S and -P flags in lieu of a "continue 2"
+ * control.
+ */
+ get_next_arg: ;
+ }
+
+ if ( ! csize_given )
+ {
+ if ( (fulltbl || fullspd) && ! useecs )
+ csize = DEFAULT_CSIZE;
+ else
+ csize = CSIZE;
+ }
+
+ if ( ! interactive_given )
+ {
+ if ( fulltbl || fullspd )
+ interactive = false;
+ else
+ interactive = true;
+ }
+
+ if ( lex_compat )
+ {
+ if ( C_plus_plus )
+ flexerror( "Can't use -+ with -l option" );
+
+ if ( fulltbl || fullspd )
+ flexerror( "Can't use -f or -F with -l option" );
+
+ /* Don't rely on detecting use of yymore() and REJECT,
+ * just assume they'll be used.
+ */
+ yymore_really_used = reject_really_used = true;
+
+ yytext_is_array = true;
+ use_read = false;
+ }
+
+ if ( (fulltbl || fullspd) && usemecs )
+ flexerror( "-Cf/-CF and -Cm don't make sense together" );
+
+ if ( (fulltbl || fullspd) && interactive )
+ flexerror( "-Cf/-CF and -I are incompatible" );
+
+ if ( fulltbl && fullspd )
+ flexerror( "-Cf and -CF are mutually exclusive" );
+
+ if ( C_plus_plus && fullspd )
+ flexerror( "Can't use -+ with -CF option" );
+
+ if ( ! use_stdout )
+ {
+ FILE *prev_stdout;
+ char *suffix;
+
+ if ( C_plus_plus )
+ suffix = "cc";
+ else
+ suffix = "c";
+
+ sprintf( outfile_path, outfile_template, prefix, suffix );
+
+ prev_stdout = freopen( outfile_path, "w", stdout );
+
+ if ( prev_stdout == NULL )
+ lerrsf( "could not create %s", outfile_path );
+
+ outfile_created = 1;
+ }
+
+ num_input_files = argc;
+ input_files = argv;
+ set_input_file( num_input_files > 0 ? input_files[0] : NULL );
+
+ if ( backing_up_report )
+ {
+#ifndef SHORT_FILE_NAMES
+ backing_up_file = fopen( "lex.backup", "w" );
+#else
+ backing_up_file = fopen( "lex.bck", "w" );
+#endif
+
+ if ( backing_up_file == NULL )
+ flexerror( "could not create lex.backup" );
+ }
+
+ else
+ backing_up_file = NULL;
+
+
+ lastccl = 0;
+ lastsc = 0;
+
+ if ( skelname && (skelfile = fopen( skelname, "r" )) == NULL )
+ lerrsf( "can't open skeleton file %s", skelname );
+
+ if ( strcmp( prefix, "yy" ) )
+ {
+#define GEN_PREFIX(name) printf( "#define yy%s %s%s\n", name, prefix, name );
+ GEN_PREFIX( "FlexLexer" );
+ GEN_PREFIX( "_create_buffer" );
+ GEN_PREFIX( "_delete_buffer" );
+ GEN_PREFIX( "_flex_debug" );
+ GEN_PREFIX( "_init_buffer" );
+ GEN_PREFIX( "_load_buffer_state" );
+ GEN_PREFIX( "_switch_to_buffer" );
+ GEN_PREFIX( "in" );
+ GEN_PREFIX( "leng" );
+ GEN_PREFIX( "lex" );
+ GEN_PREFIX( "out" );
+ GEN_PREFIX( "restart" );
+ GEN_PREFIX( "text" );
+ GEN_PREFIX( "wrap" );
+ printf( "\n" );
+ }
+
+
+ lastdfa = lastnfa = 0;
+ num_rules = num_eof_rules = default_rule = 0;
+ numas = numsnpairs = tmpuses = 0;
+ numecs = numeps = eps2 = num_reallocs = hshcol = dfaeql = totnst = 0;
+ numuniq = numdup = hshsave = eofseen = datapos = dataline = 0;
+ num_backing_up = onesp = numprots = 0;
+ variable_trailing_context_rules = bol_needed = false;
+
+ linenum = sectnum = 1;
+ firstprot = NIL;
+
+ /* Used in mkprot() so that the first proto goes in slot 1
+ * of the proto queue.
+ */
+ lastprot = 1;
+
+ if ( useecs )
+ {
+ /* Set up doubly-linked equivalence classes. */
+
+ /* We loop all the way up to csize, since ecgroup[csize] is
+ * the position used for NUL characters.
+ */
+ ecgroup[1] = NIL;
+
+ for ( i = 2; i <= csize; ++i )
+ {
+ ecgroup[i] = i - 1;
+ nextecm[i - 1] = i;
+ }
+
+ nextecm[csize] = NIL;
+ }
+
+ else
+ {
+ /* Put everything in its own equivalence class. */
+ for ( i = 1; i <= csize; ++i )
+ {
+ ecgroup[i] = i;
+ nextecm[i] = BAD_SUBSCRIPT; /* to catch errors */
+ }
+ }
+
+ set_up_initial_allocations();
+ }
+
+
+/* readin - read in the rules section of the input file(s) */
+
+void readin()
+ {
+ skelout();
+
+ line_directive_out( (FILE *) 0 );
+
+ if ( yyparse() )
+ {
+ pinpoint_message( "fatal parse error" );
+ flexend( 1 );
+ }
+
+ if ( syntaxerror )
+ flexend( 1 );
+
+ if ( yymore_really_used == REALLY_USED )
+ yymore_used = true;
+ else if ( yymore_really_used == REALLY_NOT_USED )
+ yymore_used = false;
+
+ if ( reject_really_used == REALLY_USED )
+ reject = true;
+ else if ( reject_really_used == REALLY_NOT_USED )
+ reject = false;
+
+ if ( performance_report > 0 )
+ {
+ if ( lex_compat )
+ {
+ fprintf( stderr,
+"-l AT&T lex compatibility option entails a large performance penalty\n" );
+ fprintf( stderr,
+" and may be the actual source of other reported performance penalties\n" );
+ }
+
+ if ( performance_report > 1 )
+ {
+ if ( interactive )
+ fprintf( stderr,
+ "-I (interactive) entails a minor performance penalty\n" );
+
+ if ( yymore_used )
+ fprintf( stderr,
+ "yymore() entails a minor performance penalty\n" );
+ }
+
+ if ( reject )
+ fprintf( stderr,
+ "REJECT entails a large performance penalty\n" );
+
+ if ( variable_trailing_context_rules )
+ fprintf( stderr,
+"Variable trailing context rules entail a large performance penalty\n" );
+ }
+
+ if ( reject )
+ real_reject = true;
+
+ if ( variable_trailing_context_rules )
+ reject = true;
+
+ if ( (fulltbl || fullspd) && reject )
+ {
+ if ( real_reject )
+ flexerror( "REJECT cannot be used with -f or -F" );
+ else
+ flexerror(
+ "variable trailing context rules cannot be used with -f or -F" );
+ }
+
+ if ( csize == 256 )
+ puts( "typedef unsigned char YY_CHAR;" );
+ else
+ puts( "typedef char YY_CHAR;" );
+
+ if ( C_plus_plus )
+ {
+ puts( "#define yytext_ptr yytext" );
+
+ if ( interactive )
+ puts( "#define YY_INTERACTIVE" );
+ }
+
+ if ( fullspd )
+ printf(
+ "typedef const struct yy_trans_info *yy_state_type;\n" );
+ else if ( ! C_plus_plus )
+ printf( "typedef int yy_state_type;\n" );
+
+ if ( reject )
+ printf( "\n#define YY_USES_REJECT\n" );
+
+ if ( ddebug )
+ puts( "\n#define FLEX_DEBUG" );
+
+ if ( lex_compat )
+ {
+ printf( "FILE *yyin = stdin, *yyout = stdout;\n" );
+ printf( "extern int yylineno;\n" );
+ printf( "int yylineno = 1;\n" );
+ }
+ else if ( ! C_plus_plus )
+ printf( "FILE *yyin = (FILE *) 0, *yyout = (FILE *) 0;\n" );
+
+ if ( C_plus_plus )
+ printf( "\n#include <FlexLexer.h>\n" );
+
+ else
+ {
+ if ( yytext_is_array )
+ puts( "extern char yytext[];\n" );
+
+ else
+ {
+ puts( "extern char *yytext;" );
+ puts( "#define yytext_ptr yytext" );
+ }
+ }
+
+ if ( useecs )
+ numecs = cre8ecs( nextecm, ecgroup, csize );
+ else
+ numecs = csize;
+
+ /* Now map the equivalence class for NUL to its expected place. */
+ ecgroup[0] = ecgroup[csize];
+ NUL_ec = ABS( ecgroup[0] );
+
+ if ( useecs )
+ ccl2ecl();
+ }
+
+
+/* set_up_initial_allocations - allocate memory for internal tables */
+
+void set_up_initial_allocations()
+ {
+ current_mns = INITIAL_MNS;
+ firstst = allocate_integer_array( current_mns );
+ lastst = allocate_integer_array( current_mns );
+ finalst = allocate_integer_array( current_mns );
+ transchar = allocate_integer_array( current_mns );
+ trans1 = allocate_integer_array( current_mns );
+ trans2 = allocate_integer_array( current_mns );
+ accptnum = allocate_integer_array( current_mns );
+ assoc_rule = allocate_integer_array( current_mns );
+ state_type = allocate_integer_array( current_mns );
+
+ current_max_rules = INITIAL_MAX_RULES;
+ rule_type = allocate_integer_array( current_max_rules );
+ rule_linenum = allocate_integer_array( current_max_rules );
+ rule_useful = allocate_integer_array( current_max_rules );
+
+ current_max_scs = INITIAL_MAX_SCS;
+ scset = allocate_integer_array( current_max_scs );
+ scbol = allocate_integer_array( current_max_scs );
+ scxclu = allocate_integer_array( current_max_scs );
+ sceof = allocate_integer_array( current_max_scs );
+ scname = allocate_char_ptr_array( current_max_scs );
+ actvsc = allocate_integer_array( current_max_scs );
+
+ current_maxccls = INITIAL_MAX_CCLS;
+ cclmap = allocate_integer_array( current_maxccls );
+ ccllen = allocate_integer_array( current_maxccls );
+ cclng = allocate_integer_array( current_maxccls );
+
+ current_max_ccl_tbl_size = INITIAL_MAX_CCL_TBL_SIZE;
+ ccltbl = allocate_Character_array( current_max_ccl_tbl_size );
+
+ current_max_dfa_size = INITIAL_MAX_DFA_SIZE;
+
+ current_max_xpairs = INITIAL_MAX_XPAIRS;
+ nxt = allocate_integer_array( current_max_xpairs );
+ chk = allocate_integer_array( current_max_xpairs );
+
+ current_max_template_xpairs = INITIAL_MAX_TEMPLATE_XPAIRS;
+ tnxt = allocate_integer_array( current_max_template_xpairs );
+
+ current_max_dfas = INITIAL_MAX_DFAS;
+ base = allocate_integer_array( current_max_dfas );
+ def = allocate_integer_array( current_max_dfas );
+ dfasiz = allocate_integer_array( current_max_dfas );
+ accsiz = allocate_integer_array( current_max_dfas );
+ dhash = allocate_integer_array( current_max_dfas );
+ dss = allocate_int_ptr_array( current_max_dfas );
+ dfaacc = allocate_dfaacc_union( current_max_dfas );
+
+ nultrans = (int *) 0;
+ }
+
+
+void usage()
+ {
+ fprintf( stderr,
+"%s [-bcdfhilnpstvwBFILTV78+ -C[aefFmr] -Pprefix -Sskeleton] [file ...]\n",
+ program_name );
+
+ fprintf( stderr,
+ "\t-b generate backing-up information to lex.backup\n" );
+ fprintf( stderr, "\t-c do-nothing POSIX option\n" );
+ fprintf( stderr, "\t-d turn on debug mode in generated scanner\n" );
+ fprintf( stderr, "\t-f generate fast, large scanner\n" );
+ fprintf( stderr, "\t-h produce this help message\n" );
+ fprintf( stderr, "\t-i generate case-insensitive scanner\n" );
+ fprintf( stderr, "\t-l maximal compatibility with original lex\n" );
+ fprintf( stderr, "\t-n do-nothing POSIX option\n" );
+ fprintf( stderr, "\t-p generate performance report to stderr\n" );
+ fprintf( stderr,
+ "\t-s suppress default rule to ECHO unmatched text\n" );
+ fprintf( stderr,
+ "\t-t write generated scanner on stdout instead of lex.yy.c\n" );
+ fprintf( stderr,
+ "\t-v write summary of scanner statistics to stderr\n" );
+ fprintf( stderr, "\t-w do not generate warnings\n" );
+ fprintf( stderr, "\t-B generate batch scanner (opposite of -I)\n" );
+ fprintf( stderr,
+ "\t-F use alternative fast scanner representation\n" );
+ fprintf( stderr,
+ "\t-I generate interactive scanner (opposite of -B)\n" );
+ fprintf( stderr, "\t-L suppress #line directives in scanner\n" );
+ fprintf( stderr, "\t-T %s should run in trace mode\n", program_name );
+ fprintf( stderr, "\t-V report %s version\n", program_name );
+ fprintf( stderr, "\t-7 generate 7-bit scanner\n" );
+ fprintf( stderr, "\t-8 generate 8-bit scanner\n" );
+ fprintf( stderr, "\t-+ generate C++ scanner class\n" );
+ fprintf( stderr,
+ "\t-C specify degree of table compression (default is -Cem):\n" );
+ fprintf( stderr,
+ "\t\t-Ca trade off larger tables for better memory alignment\n" );
+ fprintf( stderr, "\t\t-Ce construct equivalence classes\n" );
+ fprintf( stderr,
+ "\t\t-Cf do not compress scanner tables; use -f representation\n" );
+ fprintf( stderr,
+ "\t\t-CF do not compress scanner tables; use -F representation\n" );
+ fprintf( stderr, "\t\t-Cm construct meta-equivalence classes\n" );
+ fprintf( stderr,
+ "\t\t-Cr use read() instead of stdio for scanner input\n" );
+ fprintf( stderr, "\t-P specify scanner prefix other than \"yy\"\n" );
+ fprintf( stderr, "\t-S specify skeleton file\n" );
+ }
diff --git a/usr.bin/lex/misc.c b/usr.bin/lex/misc.c
new file mode 100644
index 000000000000..006f5fcde026
--- /dev/null
+++ b/usr.bin/lex/misc.c
@@ -0,0 +1,773 @@
+/* misc - miscellaneous flex routines */
+
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: misc.c,v 1.2 94/01/04 14:33:10 vern Exp $ */
+
+#include "flexdef.h"
+
+
+
+/* declare functions that have forward references */
+
+void dataflush PROTO((void));
+int otoi PROTO((Char []));
+
+
+void add_action( new_text )
+char *new_text;
+ {
+ int len = strlen( new_text );
+
+ while ( len + action_index >= action_size - 10 /* slop */ )
+ {
+ action_size *= 2;
+ action_array =
+ reallocate_character_array( action_array, action_size );
+ }
+
+ strcpy( &action_array[action_index], new_text );
+
+ action_index += len;
+ }
+
+
+/* allocate_array - allocate memory for an integer array of the given size */
+
+void *allocate_array( size, element_size )
+int size, element_size;
+ {
+ register void *mem;
+
+ /* On 16-bit int machines (e.g., 80286) we might be trying to
+ * allocate more than a signed int can hold, and that won't
+ * work. Cheap test:
+ */
+ if ( element_size * size <= 0 )
+ flexfatal( "request for < 1 byte in allocate_array()" );
+
+ mem = flex_alloc( element_size * size );
+
+ if ( mem == NULL )
+ flexfatal( "memory allocation failed in allocate_array()" );
+
+ return mem;
+ }
+
+
+/* all_lower - true if a string is all lower-case */
+
+int all_lower( str )
+register char *str;
+ {
+ while ( *str )
+ {
+ if ( ! isascii( (Char) *str ) || ! islower( *str ) )
+ return 0;
+ ++str;
+ }
+
+ return 1;
+ }
+
+
+/* all_upper - true if a string is all upper-case */
+
+int all_upper( str )
+register char *str;
+ {
+ while ( *str )
+ {
+ if ( ! isascii( (Char) *str ) || ! isupper( *str ) )
+ return 0;
+ ++str;
+ }
+
+ return 1;
+ }
+
+
+/* bubble - bubble sort an integer array in increasing order
+ *
+ * synopsis
+ * int v[n], n;
+ * void bubble( v, n );
+ *
+ * description
+ * sorts the first n elements of array v and replaces them in
+ * increasing order.
+ *
+ * passed
+ * v - the array to be sorted
+ * n - the number of elements of 'v' to be sorted
+ */
+
+void bubble( v, n )
+int v[], n;
+ {
+ register int i, j, k;
+
+ for ( i = n; i > 1; --i )
+ for ( j = 1; j < i; ++j )
+ if ( v[j] > v[j + 1] ) /* compare */
+ {
+ k = v[j]; /* exchange */
+ v[j] = v[j + 1];
+ v[j + 1] = k;
+ }
+ }
+
+
+/* check_char - checks a character to make sure it's within the range
+ * we're expecting. If not, generates fatal error message
+ * and exits.
+ */
+
+void check_char( c )
+int c;
+ {
+ if ( c >= CSIZE )
+ lerrsf( "bad character '%s' detected in check_char()",
+ readable_form( c ) );
+
+ if ( c >= csize )
+ lerrsf( "scanner requires -8 flag to use the character '%s'",
+ readable_form( c ) );
+ }
+
+
+
+/* clower - replace upper-case letter to lower-case */
+
+Char clower( c )
+register int c;
+ {
+ return (Char) ((isascii( c ) && isupper( c )) ? tolower( c ) : c);
+ }
+
+
+/* copy_string - returns a dynamically allocated copy of a string */
+
+char *copy_string( str )
+register char *str;
+ {
+ register char *c;
+ char *copy;
+
+ /* find length */
+ for ( c = str; *c; ++c )
+ ;
+
+ copy = (char *) flex_alloc( (c - str + 1) * sizeof( char ) );
+
+ if ( copy == NULL )
+ flexfatal( "dynamic memory failure in copy_string()" );
+
+ for ( c = copy; (*c++ = *str++); )
+ ;
+
+ return copy;
+ }
+
+
+/* copy_unsigned_string -
+ * returns a dynamically allocated copy of a (potentially) unsigned string
+ */
+
+Char *copy_unsigned_string( str )
+register Char *str;
+ {
+ register Char *c;
+ Char *copy;
+
+ /* find length */
+ for ( c = str; *c; ++c )
+ ;
+
+ copy = allocate_Character_array( c - str + 1 );
+
+ for ( c = copy; (*c++ = *str++); )
+ ;
+
+ return copy;
+ }
+
+
+/* cshell - shell sort a character array in increasing order
+ *
+ * synopsis
+ *
+ * Char v[n];
+ * int n, special_case_0;
+ * cshell( v, n, special_case_0 );
+ *
+ * description
+ * Does a shell sort of the first n elements of array v.
+ * If special_case_0 is true, then any element equal to 0
+ * is instead assumed to have infinite weight.
+ *
+ * passed
+ * v - array to be sorted
+ * n - number of elements of v to be sorted
+ */
+
+void cshell( v, n, special_case_0 )
+Char v[];
+int n, special_case_0;
+ {
+ int gap, i, j, jg;
+ Char k;
+
+ for ( gap = n / 2; gap > 0; gap = gap / 2 )
+ for ( i = gap; i < n; ++i )
+ for ( j = i - gap; j >= 0; j = j - gap )
+ {
+ jg = j + gap;
+
+ if ( special_case_0 )
+ {
+ if ( v[jg] == 0 )
+ break;
+
+ else if ( v[j] != 0 && v[j] <= v[jg] )
+ break;
+ }
+
+ else if ( v[j] <= v[jg] )
+ break;
+
+ k = v[j];
+ v[j] = v[jg];
+ v[jg] = k;
+ }
+ }
+
+
+/* dataend - finish up a block of data declarations */
+
+void dataend()
+ {
+ if ( datapos > 0 )
+ dataflush();
+
+ /* add terminator for initialization; { for vi */
+ puts( " } ;\n" );
+
+ dataline = 0;
+ datapos = 0;
+ }
+
+
+/* dataflush - flush generated data statements */
+
+void dataflush()
+ {
+ putchar( '\n' );
+
+ if ( ++dataline >= NUMDATALINES )
+ {
+ /* Put out a blank line so that the table is grouped into
+ * large blocks that enable the user to find elements easily.
+ */
+ putchar( '\n' );
+ dataline = 0;
+ }
+
+ /* Reset the number of characters written on the current line. */
+ datapos = 0;
+ }
+
+
+/* flexerror - report an error message and terminate */
+
+void flexerror( msg )
+char msg[];
+ {
+ fprintf( stderr, "%s: %s\n", program_name, msg );
+ flexend( 1 );
+ }
+
+
+/* flexfatal - report a fatal error message and terminate */
+
+void flexfatal( msg )
+char msg[];
+ {
+ fprintf( stderr, "%s: fatal internal error, %s\n", program_name, msg );
+ exit( 1 );
+ }
+
+
+/* lerrif - report an error message formatted with one integer argument */
+
+void lerrif( msg, arg )
+char msg[];
+int arg;
+ {
+ char errmsg[MAXLINE];
+ (void) sprintf( errmsg, msg, arg );
+ flexerror( errmsg );
+ }
+
+
+/* lerrsf - report an error message formatted with one string argument */
+
+void lerrsf( msg, arg )
+char msg[], arg[];
+ {
+ char errmsg[MAXLINE];
+
+ (void) sprintf( errmsg, msg, arg );
+ flexerror( errmsg );
+ }
+
+
+/* htoi - convert a hexadecimal digit string to an integer value */
+
+int htoi( str )
+Char str[];
+ {
+ unsigned int result;
+
+ (void) sscanf( (char *) str, "%x", &result );
+
+ return result;
+ }
+
+
+/* is_hex_digit - returns true if a character is a valid hex digit, false
+ * otherwise
+ */
+
+int is_hex_digit( ch )
+int ch;
+ {
+ if ( isdigit( ch ) )
+ return 1;
+
+ switch ( clower( ch ) )
+ {
+ case 'a':
+ case 'b':
+ case 'c':
+ case 'd':
+ case 'e':
+ case 'f':
+ return 1;
+
+ default:
+ return 0;
+ }
+ }
+
+
+/* line_directive_out - spit out a "# line" statement */
+
+void line_directive_out( output_file )
+FILE *output_file;
+ {
+ if ( infilename && gen_line_dirs )
+ {
+ char directive[MAXLINE];
+ sprintf( directive, "# line %d \"%s\"\n", linenum, infilename );
+
+ /* If output_file is nil then we should put the directive in
+ * the accumulated actions.
+ */
+ if ( output_file )
+ fputs( directive, output_file );
+ else
+ add_action( directive );
+ }
+ }
+
+
+/* mark_defs1 - mark the current position in the action array as
+ * representing where the user's section 1 definitions end
+ * and the prolog begins
+ */
+void mark_defs1()
+ {
+ defs1_offset = 0;
+ action_array[action_index++] = '\0';
+ action_offset = prolog_offset = action_index;
+ action_array[action_index] = '\0';
+ }
+
+
+/* mark_prolog - mark the current position in the action array as
+ * representing the end of the action prolog
+ */
+void mark_prolog()
+ {
+ action_array[action_index++] = '\0';
+ action_offset = action_index;
+ action_array[action_index] = '\0';
+ }
+
+
+/* mk2data - generate a data statement for a two-dimensional array
+ *
+ * Generates a data statement initializing the current 2-D array to "value".
+ */
+void mk2data( value )
+int value;
+ {
+ if ( datapos >= NUMDATAITEMS )
+ {
+ putchar( ',' );
+ dataflush();
+ }
+
+ if ( datapos == 0 )
+ /* Indent. */
+ fputs( " ", stdout );
+
+ else
+ putchar( ',' );
+
+ ++datapos;
+
+ printf( "%5d", value );
+ }
+
+
+/* mkdata - generate a data statement
+ *
+ * Generates a data statement initializing the current array element to
+ * "value".
+ */
+void mkdata( value )
+int value;
+ {
+ if ( datapos >= NUMDATAITEMS )
+ {
+ putchar( ',' );
+ dataflush();
+ }
+
+ if ( datapos == 0 )
+ /* Indent. */
+ fputs( " ", stdout );
+ else
+ putchar( ',' );
+
+ ++datapos;
+
+ printf( "%5d", value );
+ }
+
+
+/* myctoi - return the integer represented by a string of digits */
+
+int myctoi( array )
+char array[];
+ {
+ int val = 0;
+
+ (void) sscanf( array, "%d", &val );
+
+ return val;
+ }
+
+
+/* myesc - return character corresponding to escape sequence */
+
+Char myesc( array )
+Char array[];
+ {
+ Char c, esc_char;
+
+ switch ( array[1] )
+ {
+ case 'b': return '\b';
+ case 'f': return '\f';
+ case 'n': return '\n';
+ case 'r': return '\r';
+ case 't': return '\t';
+
+#ifdef __STDC__
+ case 'a': return '\a';
+ case 'v': return '\v';
+#else
+ case 'a': return '\007';
+ case 'v': return '\013';
+#endif
+
+ case '0':
+ case '1':
+ case '2':
+ case '3':
+ case '4':
+ case '5':
+ case '6':
+ case '7':
+ case '8':
+ case '9':
+ { /* \<octal> */
+ int sptr = 1;
+
+ while ( isascii( array[sptr] ) &&
+ isdigit( array[sptr] ) )
+ /* Don't increment inside loop control
+ * because if isdigit() is a macro it might
+ * expand into multiple increments ...
+ */
+ ++sptr;
+
+ c = array[sptr];
+ array[sptr] = '\0';
+
+ esc_char = otoi( array + 1 );
+
+ array[sptr] = c;
+
+ return esc_char;
+ }
+
+ case 'x':
+ { /* \x<hex> */
+ int sptr = 2;
+
+ while ( isascii( array[sptr] ) &&
+ is_hex_digit( (char) array[sptr] ) )
+ /* Don't increment inside loop control
+ * because if isdigit() is a macro it might
+ * expand into multiple increments ...
+ */
+ ++sptr;
+
+ c = array[sptr];
+ array[sptr] = '\0';
+
+ esc_char = htoi( array + 2 );
+
+ array[sptr] = c;
+
+ return esc_char;
+ }
+
+ default:
+ return array[1];
+ }
+ }
+
+
+/* otoi - convert an octal digit string to an integer value */
+
+int otoi( str )
+Char str[];
+ {
+ unsigned int result;
+
+ (void) sscanf( (char *) str, "%o", &result );
+ return result;
+ }
+
+
+/* readable_form - return the the human-readable form of a character
+ *
+ * The returned string is in static storage.
+ */
+
+char *readable_form( c )
+register int c;
+ {
+ static char rform[10];
+
+ if ( (c >= 0 && c < 32) || c >= 127 )
+ {
+ switch ( c )
+ {
+ case '\b': return "\\b";
+ case '\f': return "\\f";
+ case '\n': return "\\n";
+ case '\r': return "\\r";
+ case '\t': return "\\t";
+
+#ifdef __STDC__
+ case '\a': return "\\a";
+ case '\v': return "\\v";
+#endif
+
+ default:
+ (void) sprintf( rform, "\\%.3o",
+ (unsigned int) c );
+ return rform;
+ }
+ }
+
+ else if ( c == ' ' )
+ return "' '";
+
+ else
+ {
+ rform[0] = c;
+ rform[1] = '\0';
+
+ return rform;
+ }
+ }
+
+
+/* reallocate_array - increase the size of a dynamic array */
+
+void *reallocate_array( array, size, element_size )
+void *array;
+int size, element_size;
+ {
+ register void *new_array;
+
+ /* Same worry as in allocate_array(): */
+ if ( size * element_size <= 0 )
+ flexfatal(
+ "attempt to increase array size by less than 1 byte" );
+
+ new_array = flex_realloc( array, size * element_size );
+
+ if ( new_array == NULL )
+ flexfatal( "attempt to increase array size failed" );
+
+ return new_array;
+ }
+
+
+/* skelout - write out one section of the skeleton file
+ *
+ * Description
+ * Copies skelfile or skel array to stdout until a line beginning with
+ * "%%" or EOF is found.
+ */
+void skelout()
+ {
+ char buf_storage[MAXLINE];
+ char *buf = buf_storage;
+ int do_copy = 1;
+
+ /* Loop pulling lines either from the skelfile, if we're using
+ * one, or from the skel[] array.
+ */
+ while ( skelfile ?
+ (fgets( buf, MAXLINE, skelfile ) != NULL) :
+ ((buf = skel[skel_ind++]) != 0) )
+ { /* copy from skel array */
+ if ( buf[0] == '%' )
+ { /* control line */
+ switch ( buf[1] )
+ {
+ case '%':
+ return;
+
+ case '+':
+ do_copy = C_plus_plus;
+ break;
+
+ case '-':
+ do_copy = ! C_plus_plus;
+ break;
+
+ case '*':
+ do_copy = 1;
+ break;
+
+ default:
+ flexfatal(
+ "bad line in skeleton file" );
+ }
+ }
+
+ else if ( do_copy )
+ {
+ if ( skelfile )
+ /* Skeleton file reads include final
+ * newline, skel[] array does not.
+ */
+ fputs( buf, stdout );
+ else
+ printf( "%s\n", buf );
+ }
+ }
+ }
+
+
+/* transition_struct_out - output a yy_trans_info structure
+ *
+ * outputs the yy_trans_info structure with the two elements, element_v and
+ * element_n. Formats the output with spaces and carriage returns.
+ */
+
+void transition_struct_out( element_v, element_n )
+int element_v, element_n;
+ {
+ printf( "%7d, %5d,", element_v, element_n );
+
+ datapos += TRANS_STRUCT_PRINT_LENGTH;
+
+ if ( datapos >= 75 )
+ {
+ putchar( '\n' );
+
+ if ( ++dataline % 10 == 0 )
+ putchar( '\n' );
+
+ datapos = 0;
+ }
+ }
+
+
+/* The following is only needed when building flex's parser using certain
+ * broken versions of bison.
+ */
+void *yy_flex_xmalloc( size )
+int size;
+ {
+ void *result = flex_alloc( size );
+
+ if ( ! result )
+ flexfatal( "memory allocation failed in yy_flex_xmalloc()" );
+
+ return result;
+ }
+
+
+/* zero_out - set a region of memory to 0
+ *
+ * Sets region_ptr[0] through region_ptr[size_in_bytes - 1] to zero.
+ */
+
+void zero_out( region_ptr, size_in_bytes )
+char *region_ptr;
+int size_in_bytes;
+ {
+ register char *rp, *rp_end;
+
+ rp = region_ptr;
+ rp_end = region_ptr + size_in_bytes;
+
+ while ( rp < rp_end )
+ *rp++ = 0;
+ }
diff --git a/usr.bin/lex/mkskel.sh b/usr.bin/lex/mkskel.sh
new file mode 100755
index 000000000000..ffc7c7fe9aab
--- /dev/null
+++ b/usr.bin/lex/mkskel.sh
@@ -0,0 +1,16 @@
+#! /bin/sh
+
+cat <<!
+/* File created from flex.skel via mkskel.sh */
+
+#include "flexdef.h"
+
+char *skel[] = {
+!
+
+sed 's/\\/&&/g' $* | sed 's/"/\\"/g' | sed 's/.*/ "&",/'
+
+cat <<!
+ 0
+};
+!
diff --git a/usr.bin/lex/nfa.c b/usr.bin/lex/nfa.c
new file mode 100644
index 000000000000..be041fd4032c
--- /dev/null
+++ b/usr.bin/lex/nfa.c
@@ -0,0 +1,709 @@
+/* nfa - NFA construction routines */
+
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: /home/daffy/u0/vern/flex/flex-2.4.7/RCS/nfa.c,v 1.2 94/08/03 11:13:29 vern Exp $ */
+
+#include "flexdef.h"
+
+
+/* declare functions that have forward references */
+
+int dupmachine PROTO((int));
+void mkxtion PROTO((int, int));
+
+
+/* add_accept - add an accepting state to a machine
+ *
+ * accepting_number becomes mach's accepting number.
+ */
+
+void add_accept( mach, accepting_number )
+int mach, accepting_number;
+ {
+ /* Hang the accepting number off an epsilon state. if it is associated
+ * with a state that has a non-epsilon out-transition, then the state
+ * will accept BEFORE it makes that transition, i.e., one character
+ * too soon.
+ */
+
+ if ( transchar[finalst[mach]] == SYM_EPSILON )
+ accptnum[finalst[mach]] = accepting_number;
+
+ else
+ {
+ int astate = mkstate( SYM_EPSILON );
+ accptnum[astate] = accepting_number;
+ (void) link_machines( mach, astate );
+ }
+ }
+
+
+/* copysingl - make a given number of copies of a singleton machine
+ *
+ * synopsis
+ *
+ * newsng = copysingl( singl, num );
+ *
+ * newsng - a new singleton composed of num copies of singl
+ * singl - a singleton machine
+ * num - the number of copies of singl to be present in newsng
+ */
+
+int copysingl( singl, num )
+int singl, num;
+ {
+ int copy, i;
+
+ copy = mkstate( SYM_EPSILON );
+
+ for ( i = 1; i <= num; ++i )
+ copy = link_machines( copy, dupmachine( singl ) );
+
+ return copy;
+ }
+
+
+/* dumpnfa - debugging routine to write out an nfa */
+
+void dumpnfa( state1 )
+int state1;
+
+ {
+ int sym, tsp1, tsp2, anum, ns;
+
+ fprintf( stderr,
+ "\n\n********** beginning dump of nfa with start state %d\n",
+ state1 );
+
+ /* We probably should loop starting at firstst[state1] and going to
+ * lastst[state1], but they're not maintained properly when we "or"
+ * all of the rules together. So we use our knowledge that the machine
+ * starts at state 1 and ends at lastnfa.
+ */
+
+ /* for ( ns = firstst[state1]; ns <= lastst[state1]; ++ns ) */
+ for ( ns = 1; ns <= lastnfa; ++ns )
+ {
+ fprintf( stderr, "state # %4d\t", ns );
+
+ sym = transchar[ns];
+ tsp1 = trans1[ns];
+ tsp2 = trans2[ns];
+ anum = accptnum[ns];
+
+ fprintf( stderr, "%3d: %4d, %4d", sym, tsp1, tsp2 );
+
+ if ( anum != NIL )
+ fprintf( stderr, " [%d]", anum );
+
+ fprintf( stderr, "\n" );
+ }
+
+ fprintf( stderr, "********** end of dump\n" );
+ }
+
+
+/* dupmachine - make a duplicate of a given machine
+ *
+ * synopsis
+ *
+ * copy = dupmachine( mach );
+ *
+ * copy - holds duplicate of mach
+ * mach - machine to be duplicated
+ *
+ * note that the copy of mach is NOT an exact duplicate; rather, all the
+ * transition states values are adjusted so that the copy is self-contained,
+ * as the original should have been.
+ *
+ * also note that the original MUST be contiguous, with its low and high
+ * states accessible by the arrays firstst and lastst
+ */
+
+int dupmachine( mach )
+int mach;
+ {
+ int i, init, state_offset;
+ int state = 0;
+ int last = lastst[mach];
+
+ for ( i = firstst[mach]; i <= last; ++i )
+ {
+ state = mkstate( transchar[i] );
+
+ if ( trans1[i] != NO_TRANSITION )
+ {
+ mkxtion( finalst[state], trans1[i] + state - i );
+
+ if ( transchar[i] == SYM_EPSILON &&
+ trans2[i] != NO_TRANSITION )
+ mkxtion( finalst[state],
+ trans2[i] + state - i );
+ }
+
+ accptnum[state] = accptnum[i];
+ }
+
+ if ( state == 0 )
+ flexfatal( "empty machine in dupmachine()" );
+
+ state_offset = state - i + 1;
+
+ init = mach + state_offset;
+ firstst[init] = firstst[mach] + state_offset;
+ finalst[init] = finalst[mach] + state_offset;
+ lastst[init] = lastst[mach] + state_offset;
+
+ return init;
+ }
+
+
+/* finish_rule - finish up the processing for a rule
+ *
+ * An accepting number is added to the given machine. If variable_trail_rule
+ * is true then the rule has trailing context and both the head and trail
+ * are variable size. Otherwise if headcnt or trailcnt is non-zero then
+ * the machine recognizes a pattern with trailing context and headcnt is
+ * the number of characters in the matched part of the pattern, or zero
+ * if the matched part has variable length. trailcnt is the number of
+ * trailing context characters in the pattern, or zero if the trailing
+ * context has variable length.
+ */
+
+void finish_rule( mach, variable_trail_rule, headcnt, trailcnt )
+int mach, variable_trail_rule, headcnt, trailcnt;
+ {
+ char action_text[MAXLINE];
+
+ add_accept( mach, num_rules );
+
+ /* We did this in new_rule(), but it often gets the wrong
+ * number because we do it before we start parsing the current rule.
+ */
+ rule_linenum[num_rules] = linenum;
+
+ /* If this is a continued action, then the line-number has already
+ * been updated, giving us the wrong number.
+ */
+ if ( continued_action )
+ --rule_linenum[num_rules];
+
+ sprintf( action_text, "case %d:\n", num_rules );
+ add_action( action_text );
+
+ if ( variable_trail_rule )
+ {
+ rule_type[num_rules] = RULE_VARIABLE;
+
+ if ( performance_report > 0 )
+ fprintf( stderr,
+ "Variable trailing context rule at line %d\n",
+ rule_linenum[num_rules] );
+
+ variable_trailing_context_rules = true;
+ }
+
+ else
+ {
+ rule_type[num_rules] = RULE_NORMAL;
+
+ if ( headcnt > 0 || trailcnt > 0 )
+ {
+ /* Do trailing context magic to not match the trailing
+ * characters.
+ */
+ char *scanner_cp = "yy_c_buf_p = yy_cp";
+ char *scanner_bp = "yy_bp";
+
+ add_action(
+ "*yy_cp = yy_hold_char; /* undo effects of setting up yytext */\n" );
+
+ if ( headcnt > 0 )
+ {
+ sprintf( action_text, "%s = %s + %d;\n",
+ scanner_cp, scanner_bp, headcnt );
+ add_action( action_text );
+ }
+
+ else
+ {
+ sprintf( action_text, "%s -= %d;\n",
+ scanner_cp, trailcnt );
+ add_action( action_text );
+ }
+
+ add_action(
+ "YY_DO_BEFORE_ACTION; /* set up yytext again */\n" );
+ }
+ }
+
+ /* Okay, in the action code at this point yytext and yyleng have
+ * their proper final values for this rule, so here's the point
+ * to do any user action. But don't do it for continued actions,
+ * as that'll result in multiple YY_USER_ACTION's.
+ */
+ if ( ! continued_action )
+ add_action( "YY_USER_ACTION\n" );
+
+ line_directive_out( (FILE *) 0 );
+ }
+
+
+/* link_machines - connect two machines together
+ *
+ * synopsis
+ *
+ * new = link_machines( first, last );
+ *
+ * new - a machine constructed by connecting first to last
+ * first - the machine whose successor is to be last
+ * last - the machine whose predecessor is to be first
+ *
+ * note: this routine concatenates the machine first with the machine
+ * last to produce a machine new which will pattern-match first first
+ * and then last, and will fail if either of the sub-patterns fails.
+ * FIRST is set to new by the operation. last is unmolested.
+ */
+
+int link_machines( first, last )
+int first, last;
+ {
+ if ( first == NIL )
+ return last;
+
+ else if ( last == NIL )
+ return first;
+
+ else
+ {
+ mkxtion( finalst[first], last );
+ finalst[first] = finalst[last];
+ lastst[first] = MAX( lastst[first], lastst[last] );
+ firstst[first] = MIN( firstst[first], firstst[last] );
+
+ return first;
+ }
+ }
+
+
+/* mark_beginning_as_normal - mark each "beginning" state in a machine
+ * as being a "normal" (i.e., not trailing context-
+ * associated) states
+ *
+ * The "beginning" states are the epsilon closure of the first state
+ */
+
+void mark_beginning_as_normal( mach )
+register int mach;
+ {
+ switch ( state_type[mach] )
+ {
+ case STATE_NORMAL:
+ /* Oh, we've already visited here. */
+ return;
+
+ case STATE_TRAILING_CONTEXT:
+ state_type[mach] = STATE_NORMAL;
+
+ if ( transchar[mach] == SYM_EPSILON )
+ {
+ if ( trans1[mach] != NO_TRANSITION )
+ mark_beginning_as_normal(
+ trans1[mach] );
+
+ if ( trans2[mach] != NO_TRANSITION )
+ mark_beginning_as_normal(
+ trans2[mach] );
+ }
+ break;
+
+ default:
+ flexerror(
+ "bad state type in mark_beginning_as_normal()" );
+ break;
+ }
+ }
+
+
+/* mkbranch - make a machine that branches to two machines
+ *
+ * synopsis
+ *
+ * branch = mkbranch( first, second );
+ *
+ * branch - a machine which matches either first's pattern or second's
+ * first, second - machines whose patterns are to be or'ed (the | operator)
+ *
+ * Note that first and second are NEITHER destroyed by the operation. Also,
+ * the resulting machine CANNOT be used with any other "mk" operation except
+ * more mkbranch's. Compare with mkor()
+ */
+
+int mkbranch( first, second )
+int first, second;
+ {
+ int eps;
+
+ if ( first == NO_TRANSITION )
+ return second;
+
+ else if ( second == NO_TRANSITION )
+ return first;
+
+ eps = mkstate( SYM_EPSILON );
+
+ mkxtion( eps, first );
+ mkxtion( eps, second );
+
+ return eps;
+ }
+
+
+/* mkclos - convert a machine into a closure
+ *
+ * synopsis
+ * new = mkclos( state );
+ *
+ * new - a new state which matches the closure of "state"
+ */
+
+int mkclos( state )
+int state;
+ {
+ return mkopt( mkposcl( state ) );
+ }
+
+
+/* mkopt - make a machine optional
+ *
+ * synopsis
+ *
+ * new = mkopt( mach );
+ *
+ * new - a machine which optionally matches whatever mach matched
+ * mach - the machine to make optional
+ *
+ * notes:
+ * 1. mach must be the last machine created
+ * 2. mach is destroyed by the call
+ */
+
+int mkopt( mach )
+int mach;
+ {
+ int eps;
+
+ if ( ! SUPER_FREE_EPSILON(finalst[mach]) )
+ {
+ eps = mkstate( SYM_EPSILON );
+ mach = link_machines( mach, eps );
+ }
+
+ /* Can't skimp on the following if FREE_EPSILON(mach) is true because
+ * some state interior to "mach" might point back to the beginning
+ * for a closure.
+ */
+ eps = mkstate( SYM_EPSILON );
+ mach = link_machines( eps, mach );
+
+ mkxtion( mach, finalst[mach] );
+
+ return mach;
+ }
+
+
+/* mkor - make a machine that matches either one of two machines
+ *
+ * synopsis
+ *
+ * new = mkor( first, second );
+ *
+ * new - a machine which matches either first's pattern or second's
+ * first, second - machines whose patterns are to be or'ed (the | operator)
+ *
+ * note that first and second are both destroyed by the operation
+ * the code is rather convoluted because an attempt is made to minimize
+ * the number of epsilon states needed
+ */
+
+int mkor( first, second )
+int first, second;
+ {
+ int eps, orend;
+
+ if ( first == NIL )
+ return second;
+
+ else if ( second == NIL )
+ return first;
+
+ else
+ {
+ /* See comment in mkopt() about why we can't use the first
+ * state of "first" or "second" if they satisfy "FREE_EPSILON".
+ */
+ eps = mkstate( SYM_EPSILON );
+
+ first = link_machines( eps, first );
+
+ mkxtion( first, second );
+
+ if ( SUPER_FREE_EPSILON(finalst[first]) &&
+ accptnum[finalst[first]] == NIL )
+ {
+ orend = finalst[first];
+ mkxtion( finalst[second], orend );
+ }
+
+ else if ( SUPER_FREE_EPSILON(finalst[second]) &&
+ accptnum[finalst[second]] == NIL )
+ {
+ orend = finalst[second];
+ mkxtion( finalst[first], orend );
+ }
+
+ else
+ {
+ eps = mkstate( SYM_EPSILON );
+
+ first = link_machines( first, eps );
+ orend = finalst[first];
+
+ mkxtion( finalst[second], orend );
+ }
+ }
+
+ finalst[first] = orend;
+ return first;
+ }
+
+
+/* mkposcl - convert a machine into a positive closure
+ *
+ * synopsis
+ * new = mkposcl( state );
+ *
+ * new - a machine matching the positive closure of "state"
+ */
+
+int mkposcl( state )
+int state;
+ {
+ int eps;
+
+ if ( SUPER_FREE_EPSILON(finalst[state]) )
+ {
+ mkxtion( finalst[state], state );
+ return state;
+ }
+
+ else
+ {
+ eps = mkstate( SYM_EPSILON );
+ mkxtion( eps, state );
+ return link_machines( state, eps );
+ }
+ }
+
+
+/* mkrep - make a replicated machine
+ *
+ * synopsis
+ * new = mkrep( mach, lb, ub );
+ *
+ * new - a machine that matches whatever "mach" matched from "lb"
+ * number of times to "ub" number of times
+ *
+ * note
+ * if "ub" is INFINITY then "new" matches "lb" or more occurrences of "mach"
+ */
+
+int mkrep( mach, lb, ub )
+int mach, lb, ub;
+ {
+ int base_mach, tail, copy, i;
+
+ base_mach = copysingl( mach, lb - 1 );
+
+ if ( ub == INFINITY )
+ {
+ copy = dupmachine( mach );
+ mach = link_machines( mach,
+ link_machines( base_mach, mkclos( copy ) ) );
+ }
+
+ else
+ {
+ tail = mkstate( SYM_EPSILON );
+
+ for ( i = lb; i < ub; ++i )
+ {
+ copy = dupmachine( mach );
+ tail = mkopt( link_machines( copy, tail ) );
+ }
+
+ mach = link_machines( mach, link_machines( base_mach, tail ) );
+ }
+
+ return mach;
+ }
+
+
+/* mkstate - create a state with a transition on a given symbol
+ *
+ * synopsis
+ *
+ * state = mkstate( sym );
+ *
+ * state - a new state matching sym
+ * sym - the symbol the new state is to have an out-transition on
+ *
+ * note that this routine makes new states in ascending order through the
+ * state array (and increments LASTNFA accordingly). The routine DUPMACHINE
+ * relies on machines being made in ascending order and that they are
+ * CONTIGUOUS. Change it and you will have to rewrite DUPMACHINE (kludge
+ * that it admittedly is)
+ */
+
+int mkstate( sym )
+int sym;
+ {
+ if ( ++lastnfa >= current_mns )
+ {
+ if ( (current_mns += MNS_INCREMENT) >= MAXIMUM_MNS )
+ lerrif(
+ "input rules are too complicated (>= %d NFA states)",
+ current_mns );
+
+ ++num_reallocs;
+
+ firstst = reallocate_integer_array( firstst, current_mns );
+ lastst = reallocate_integer_array( lastst, current_mns );
+ finalst = reallocate_integer_array( finalst, current_mns );
+ transchar = reallocate_integer_array( transchar, current_mns );
+ trans1 = reallocate_integer_array( trans1, current_mns );
+ trans2 = reallocate_integer_array( trans2, current_mns );
+ accptnum = reallocate_integer_array( accptnum, current_mns );
+ assoc_rule =
+ reallocate_integer_array( assoc_rule, current_mns );
+ state_type =
+ reallocate_integer_array( state_type, current_mns );
+ }
+
+ firstst[lastnfa] = lastnfa;
+ finalst[lastnfa] = lastnfa;
+ lastst[lastnfa] = lastnfa;
+ transchar[lastnfa] = sym;
+ trans1[lastnfa] = NO_TRANSITION;
+ trans2[lastnfa] = NO_TRANSITION;
+ accptnum[lastnfa] = NIL;
+ assoc_rule[lastnfa] = num_rules;
+ state_type[lastnfa] = current_state_type;
+
+ /* Fix up equivalence classes base on this transition. Note that any
+ * character which has its own transition gets its own equivalence
+ * class. Thus only characters which are only in character classes
+ * have a chance at being in the same equivalence class. E.g. "a|b"
+ * puts 'a' and 'b' into two different equivalence classes. "[ab]"
+ * puts them in the same equivalence class (barring other differences
+ * elsewhere in the input).
+ */
+
+ if ( sym < 0 )
+ {
+ /* We don't have to update the equivalence classes since
+ * that was already done when the ccl was created for the
+ * first time.
+ */
+ }
+
+ else if ( sym == SYM_EPSILON )
+ ++numeps;
+
+ else
+ {
+ check_char( sym );
+
+ if ( useecs )
+ /* Map NUL's to csize. */
+ mkechar( sym ? sym : csize, nextecm, ecgroup );
+ }
+
+ return lastnfa;
+ }
+
+
+/* mkxtion - make a transition from one state to another
+ *
+ * synopsis
+ *
+ * mkxtion( statefrom, stateto );
+ *
+ * statefrom - the state from which the transition is to be made
+ * stateto - the state to which the transition is to be made
+ */
+
+void mkxtion( statefrom, stateto )
+int statefrom, stateto;
+ {
+ if ( trans1[statefrom] == NO_TRANSITION )
+ trans1[statefrom] = stateto;
+
+ else if ( (transchar[statefrom] != SYM_EPSILON) ||
+ (trans2[statefrom] != NO_TRANSITION) )
+ flexfatal( "found too many transitions in mkxtion()" );
+
+ else
+ { /* second out-transition for an epsilon state */
+ ++eps2;
+ trans2[statefrom] = stateto;
+ }
+ }
+
+/* new_rule - initialize for a new rule */
+
+void new_rule()
+ {
+ if ( ++num_rules >= current_max_rules )
+ {
+ ++num_reallocs;
+ current_max_rules += MAX_RULES_INCREMENT;
+ rule_type = reallocate_integer_array( rule_type,
+ current_max_rules );
+ rule_linenum = reallocate_integer_array( rule_linenum,
+ current_max_rules );
+ rule_useful = reallocate_integer_array( rule_useful,
+ current_max_rules );
+ }
+
+ if ( num_rules > MAX_RULE )
+ lerrif( "too many rules (> %d)!", MAX_RULE );
+
+ rule_linenum[num_rules] = linenum;
+ rule_useful[num_rules] = false;
+ }
diff --git a/usr.bin/lex/parse.y b/usr.bin/lex/parse.y
new file mode 100644
index 000000000000..c14f2452ca4a
--- /dev/null
+++ b/usr.bin/lex/parse.y
@@ -0,0 +1,817 @@
+/* parse.y - parser for flex input */
+
+%token CHAR NUMBER SECTEND SCDECL XSCDECL WHITESPACE NAME PREVCCL EOF_OP
+
+%{
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: /home/daffy/u0/vern/flex/RCS/parse.y,v 2.15 93/12/09 13:57:23 vern Exp $ */
+
+
+/* Some versions of bison are broken in that they use alloca() but don't
+ * declare it properly. The following is the patented (just kidding!)
+ * #ifdef chud to fix the problem, courtesy of Francois Pinard.
+ */
+#ifdef YYBISON
+/* AIX requires this to be the first thing in the file. */
+#ifdef __GNUC__
+#define alloca __builtin_alloca
+#else /* not __GNUC__ */
+#if HAVE_ALLOCA_H
+#include <alloca.h>
+#else /* not HAVE_ALLOCA_H */
+#ifdef _AIX
+ #pragma alloca
+#else /* not _AIX */
+char *alloca ();
+#endif /* not _AIX */
+#endif /* not HAVE_ALLOCA_H */
+#endif /* not __GNUC__ */
+#endif /* YYBISON */
+
+/* Bletch, ^^^^ that was ugly! */
+
+
+#include "flexdef.h"
+
+int pat, scnum, eps, headcnt, trailcnt, anyccl, lastchar, i, actvp, rulelen;
+int trlcontxt, xcluflg, cclsorted, varlength, variable_trail_rule;
+int *active_ss;
+Char clower();
+void build_eof_action();
+void yyerror();
+
+static int madeany = false; /* whether we've made the '.' character class */
+int previous_continued_action; /* whether the previous rule's action was '|' */
+
+/* On some over-ambitious machines, such as DEC Alpha's, the default
+ * token type is "long" instead of "int"; this leads to problems with
+ * declaring yylval in flexdef.h. But so far, all the yacc's I've seen
+ * wrap their definitions of YYSTYPE with "#ifndef YYSTYPE"'s, so the
+ * following should ensure that the default token type is "int".
+ */
+#define YYSTYPE int
+
+%}
+
+%%
+goal : initlex sect1 sect1end sect2 initforrule
+ { /* add default rule */
+ int def_rule;
+
+ pat = cclinit();
+ cclnegate( pat );
+
+ def_rule = mkstate( -pat );
+
+ /* Remember the number of the default rule so we
+ * don't generate "can't match" warnings for it.
+ */
+ default_rule = num_rules;
+
+ finish_rule( def_rule, false, 0, 0 );
+
+ for ( i = 1; i <= lastsc; ++i )
+ scset[i] = mkbranch( scset[i], def_rule );
+
+ if ( spprdflt )
+ add_action(
+ "YY_FATAL_ERROR( \"flex scanner jammed\" )" );
+ else
+ add_action( "ECHO" );
+
+ add_action( ";\n\tYY_BREAK\n" );
+ }
+ ;
+
+initlex :
+ { /* initialize for processing rules */
+
+ /* Create default DFA start condition. */
+ scinstal( "INITIAL", false );
+
+ /* Initially, the start condition scoping is
+ * "no start conditions active".
+ */
+ actvp = 0;
+ }
+ ;
+
+sect1 : sect1 startconddecl WHITESPACE namelist1 '\n'
+ |
+ | error '\n'
+ { synerr( "unknown error processing section 1" ); }
+ ;
+
+sect1end : SECTEND
+ {
+ /* We now know how many start conditions there
+ * are, so create the "activity" map indicating
+ * which conditions are active.
+ */
+ active_ss = allocate_integer_array( lastsc + 1 );
+
+ for ( i = 1; i <= lastsc; ++i )
+ active_ss[i] = 0;
+ }
+ ;
+
+startconddecl : SCDECL
+ { xcluflg = false; }
+
+ | XSCDECL
+ { xcluflg = true; }
+ ;
+
+namelist1 : namelist1 WHITESPACE NAME
+ { scinstal( nmstr, xcluflg ); }
+
+ | NAME
+ { scinstal( nmstr, xcluflg ); }
+
+ | error
+ { synerr( "bad start condition list" ); }
+ ;
+
+sect2 : sect2 initforrule flexrule '\n'
+ |
+ ;
+
+initforrule :
+ {
+ /* Initialize for a parse of one rule. */
+ trlcontxt = variable_trail_rule = varlength = false;
+ trailcnt = headcnt = rulelen = 0;
+ current_state_type = STATE_NORMAL;
+ previous_continued_action = continued_action;
+ new_rule();
+ }
+ ;
+
+flexrule : scon '^' rule
+ {
+ pat = $3;
+ finish_rule( pat, variable_trail_rule,
+ headcnt, trailcnt );
+
+ for ( i = 1; i <= actvp; ++i )
+ scbol[actvsc[i]] =
+ mkbranch( scbol[actvsc[i]], pat );
+
+ if ( ! bol_needed )
+ {
+ bol_needed = true;
+
+ if ( performance_report > 1 )
+ pinpoint_message(
+ "'^' operator results in sub-optimal performance" );
+ }
+ }
+
+ | scon rule
+ {
+ pat = $2;
+ finish_rule( pat, variable_trail_rule,
+ headcnt, trailcnt );
+
+ for ( i = 1; i <= actvp; ++i )
+ scset[actvsc[i]] =
+ mkbranch( scset[actvsc[i]], pat );
+ }
+
+ | '^' rule
+ {
+ pat = $2;
+ finish_rule( pat, variable_trail_rule,
+ headcnt, trailcnt );
+
+ /* Add to all non-exclusive start conditions,
+ * including the default (0) start condition.
+ */
+
+ for ( i = 1; i <= lastsc; ++i )
+ if ( ! scxclu[i] )
+ scbol[i] = mkbranch( scbol[i], pat );
+
+ if ( ! bol_needed )
+ {
+ bol_needed = true;
+
+ if ( performance_report > 1 )
+ pinpoint_message(
+ "'^' operator results in sub-optimal performance" );
+ }
+ }
+
+ | rule
+ {
+ pat = $1;
+ finish_rule( pat, variable_trail_rule,
+ headcnt, trailcnt );
+
+ for ( i = 1; i <= lastsc; ++i )
+ if ( ! scxclu[i] )
+ scset[i] = mkbranch( scset[i], pat );
+ }
+
+ | scon EOF_OP
+ { build_eof_action(); }
+
+ | EOF_OP
+ {
+ /* This EOF applies to all start conditions
+ * which don't already have EOF actions.
+ */
+ actvp = 0;
+
+ for ( i = 1; i <= lastsc; ++i )
+ if ( ! sceof[i] )
+ actvsc[++actvp] = i;
+
+ if ( actvp == 0 )
+ warn(
+ "all start conditions already have <<EOF>> rules" );
+
+ else
+ build_eof_action();
+ }
+
+ | error
+ { synerr( "unrecognized rule" ); }
+ ;
+
+scon : '<' namelist2 '>'
+
+ | '<' '*' '>'
+ {
+ actvp = 0;
+
+ for ( i = 1; i <= lastsc; ++i )
+ actvsc[++actvp] = i;
+ }
+ ;
+
+namelist2 : namelist2 ',' sconname
+
+ | { actvp = 0; } sconname
+
+ | error
+ { synerr( "bad start condition list" ); }
+ ;
+
+sconname : NAME
+ {
+ if ( (scnum = sclookup( nmstr )) == 0 )
+ format_pinpoint_message(
+ "undeclared start condition %s",
+ nmstr );
+ else
+ {
+ if ( ++actvp >= current_max_scs )
+ /* Some bozo has included multiple
+ * instances of start condition names.
+ */
+ pinpoint_message(
+ "too many start conditions in <> construct!" );
+
+ else
+ actvsc[actvp] = scnum;
+ }
+ }
+ ;
+
+rule : re2 re
+ {
+ if ( transchar[lastst[$2]] != SYM_EPSILON )
+ /* Provide final transition \now/ so it
+ * will be marked as a trailing context
+ * state.
+ */
+ $2 = link_machines( $2,
+ mkstate( SYM_EPSILON ) );
+
+ mark_beginning_as_normal( $2 );
+ current_state_type = STATE_NORMAL;
+
+ if ( previous_continued_action )
+ {
+ /* We need to treat this as variable trailing
+ * context so that the backup does not happen
+ * in the action but before the action switch
+ * statement. If the backup happens in the
+ * action, then the rules "falling into" this
+ * one's action will *also* do the backup,
+ * erroneously.
+ */
+ if ( ! varlength || headcnt != 0 )
+ warn(
+ "trailing context made variable due to preceding '|' action" );
+
+ /* Mark as variable. */
+ varlength = true;
+ headcnt = 0;
+ }
+
+ if ( lex_compat || (varlength && headcnt == 0) )
+ { /* variable trailing context rule */
+ /* Mark the first part of the rule as the
+ * accepting "head" part of a trailing
+ * context rule.
+ *
+ * By the way, we didn't do this at the
+ * beginning of this production because back
+ * then current_state_type was set up for a
+ * trail rule, and add_accept() can create
+ * a new state ...
+ */
+ add_accept( $1,
+ num_rules | YY_TRAILING_HEAD_MASK );
+ variable_trail_rule = true;
+ }
+
+ else
+ trailcnt = rulelen;
+
+ $$ = link_machines( $1, $2 );
+ }
+
+ | re2 re '$'
+ { synerr( "trailing context used twice" ); }
+
+ | re '$'
+ {
+ headcnt = 0;
+ trailcnt = 1;
+ rulelen = 1;
+ varlength = false;
+
+ current_state_type = STATE_TRAILING_CONTEXT;
+
+ if ( trlcontxt )
+ {
+ synerr( "trailing context used twice" );
+ $$ = mkstate( SYM_EPSILON );
+ }
+
+ else if ( previous_continued_action )
+ {
+ /* See the comment in the rule for "re2 re"
+ * above.
+ */
+ warn(
+ "trailing context made variable due to preceding '|' action" );
+
+ varlength = true;
+ }
+
+ if ( lex_compat || varlength )
+ {
+ /* Again, see the comment in the rule for
+ * "re2 re" above.
+ */
+ add_accept( $1,
+ num_rules | YY_TRAILING_HEAD_MASK );
+ variable_trail_rule = true;
+ }
+
+ trlcontxt = true;
+
+ eps = mkstate( SYM_EPSILON );
+ $$ = link_machines( $1,
+ link_machines( eps, mkstate( '\n' ) ) );
+ }
+
+ | re
+ {
+ $$ = $1;
+
+ if ( trlcontxt )
+ {
+ if ( lex_compat || (varlength && headcnt == 0) )
+ /* Both head and trail are
+ * variable-length.
+ */
+ variable_trail_rule = true;
+ else
+ trailcnt = rulelen;
+ }
+ }
+ ;
+
+
+re : re '|' series
+ {
+ varlength = true;
+ $$ = mkor( $1, $3 );
+ }
+
+ | series
+ { $$ = $1; }
+ ;
+
+
+re2 : re '/'
+ {
+ /* This rule is written separately so the
+ * reduction will occur before the trailing
+ * series is parsed.
+ */
+
+ if ( trlcontxt )
+ synerr( "trailing context used twice" );
+ else
+ trlcontxt = true;
+
+ if ( varlength )
+ /* We hope the trailing context is
+ * fixed-length.
+ */
+ varlength = false;
+ else
+ headcnt = rulelen;
+
+ rulelen = 0;
+
+ current_state_type = STATE_TRAILING_CONTEXT;
+ $$ = $1;
+ }
+ ;
+
+series : series singleton
+ {
+ /* This is where concatenation of adjacent patterns
+ * gets done.
+ */
+ $$ = link_machines( $1, $2 );
+ }
+
+ | singleton
+ { $$ = $1; }
+ ;
+
+singleton : singleton '*'
+ {
+ varlength = true;
+
+ $$ = mkclos( $1 );
+ }
+
+ | singleton '+'
+ {
+ varlength = true;
+ $$ = mkposcl( $1 );
+ }
+
+ | singleton '?'
+ {
+ varlength = true;
+ $$ = mkopt( $1 );
+ }
+
+ | singleton '{' NUMBER ',' NUMBER '}'
+ {
+ varlength = true;
+
+ if ( $3 > $5 || $3 < 0 )
+ {
+ synerr( "bad iteration values" );
+ $$ = $1;
+ }
+ else
+ {
+ if ( $3 == 0 )
+ {
+ if ( $5 <= 0 )
+ {
+ synerr(
+ "bad iteration values" );
+ $$ = $1;
+ }
+ else
+ $$ = mkopt(
+ mkrep( $1, 1, $5 ) );
+ }
+ else
+ $$ = mkrep( $1, $3, $5 );
+ }
+ }
+
+ | singleton '{' NUMBER ',' '}'
+ {
+ varlength = true;
+
+ if ( $3 <= 0 )
+ {
+ synerr( "iteration value must be positive" );
+ $$ = $1;
+ }
+
+ else
+ $$ = mkrep( $1, $3, INFINITY );
+ }
+
+ | singleton '{' NUMBER '}'
+ {
+ /* The singleton could be something like "(foo)",
+ * in which case we have no idea what its length
+ * is, so we punt here.
+ */
+ varlength = true;
+
+ if ( $3 <= 0 )
+ {
+ synerr( "iteration value must be positive" );
+ $$ = $1;
+ }
+
+ else
+ $$ = link_machines( $1,
+ copysingl( $1, $3 - 1 ) );
+ }
+
+ | '.'
+ {
+ if ( ! madeany )
+ {
+ /* Create the '.' character class. */
+ anyccl = cclinit();
+ ccladd( anyccl, '\n' );
+ cclnegate( anyccl );
+
+ if ( useecs )
+ mkeccl( ccltbl + cclmap[anyccl],
+ ccllen[anyccl], nextecm,
+ ecgroup, csize, csize );
+
+ madeany = true;
+ }
+
+ ++rulelen;
+
+ $$ = mkstate( -anyccl );
+ }
+
+ | fullccl
+ {
+ if ( ! cclsorted )
+ /* Sort characters for fast searching. We
+ * use a shell sort since this list could
+ * be large.
+ */
+ cshell( ccltbl + cclmap[$1], ccllen[$1], true );
+
+ if ( useecs )
+ mkeccl( ccltbl + cclmap[$1], ccllen[$1],
+ nextecm, ecgroup, csize, csize );
+
+ ++rulelen;
+
+ $$ = mkstate( -$1 );
+ }
+
+ | PREVCCL
+ {
+ ++rulelen;
+
+ $$ = mkstate( -$1 );
+ }
+
+ | '"' string '"'
+ { $$ = $2; }
+
+ | '(' re ')'
+ { $$ = $2; }
+
+ | CHAR
+ {
+ ++rulelen;
+
+ if ( caseins && $1 >= 'A' && $1 <= 'Z' )
+ $1 = clower( $1 );
+
+ $$ = mkstate( $1 );
+ }
+ ;
+
+fullccl : '[' ccl ']'
+ { $$ = $2; }
+
+ | '[' '^' ccl ']'
+ {
+ cclnegate( $3 );
+ $$ = $3;
+ }
+ ;
+
+ccl : ccl CHAR '-' CHAR
+ {
+ if ( caseins )
+ {
+ if ( $2 >= 'A' && $2 <= 'Z' )
+ $2 = clower( $2 );
+ if ( $4 >= 'A' && $4 <= 'Z' )
+ $4 = clower( $4 );
+ }
+
+ if ( $2 > $4 )
+ synerr( "negative range in character class" );
+
+ else
+ {
+ for ( i = $2; i <= $4; ++i )
+ ccladd( $1, i );
+
+ /* Keep track if this ccl is staying in
+ * alphabetical order.
+ */
+ cclsorted = cclsorted && ($2 > lastchar);
+ lastchar = $4;
+ }
+
+ $$ = $1;
+ }
+
+ | ccl CHAR
+ {
+ if ( caseins && $2 >= 'A' && $2 <= 'Z' )
+ $2 = clower( $2 );
+
+ ccladd( $1, $2 );
+ cclsorted = cclsorted && ($2 > lastchar);
+ lastchar = $2;
+ $$ = $1;
+ }
+
+ |
+ {
+ cclsorted = true;
+ lastchar = 0;
+ $$ = cclinit();
+ }
+ ;
+
+string : string CHAR
+ {
+ if ( caseins && $2 >= 'A' && $2 <= 'Z' )
+ $2 = clower( $2 );
+
+ ++rulelen;
+
+ $$ = link_machines( $1, mkstate( $2 ) );
+ }
+
+ |
+ { $$ = mkstate( SYM_EPSILON ); }
+ ;
+
+%%
+
+
+/* build_eof_action - build the "<<EOF>>" action for the active start
+ * conditions
+ */
+
+void build_eof_action()
+ {
+ register int i;
+ char action_text[MAXLINE];
+
+ for ( i = 1; i <= actvp; ++i )
+ {
+ if ( sceof[actvsc[i]] )
+ format_pinpoint_message(
+ "multiple <<EOF>> rules for start condition %s",
+ scname[actvsc[i]] );
+
+ else
+ {
+ sceof[actvsc[i]] = true;
+ sprintf( action_text, "case YY_STATE_EOF(%s):\n",
+ scname[actvsc[i]] );
+ add_action( action_text );
+ }
+ }
+
+ line_directive_out( (FILE *) 0 );
+
+ /* This isn't a normal rule after all - don't count it as
+ * such, so we don't have any holes in the rule numbering
+ * (which make generating "rule can never match" warnings
+ * more difficult.
+ */
+ --num_rules;
+ ++num_eof_rules;
+ }
+
+
+/* format_synerr - write out formatted syntax error */
+
+void format_synerr( msg, arg )
+char msg[], arg[];
+ {
+ char errmsg[MAXLINE];
+
+ (void) sprintf( errmsg, msg, arg );
+ synerr( errmsg );
+ }
+
+
+/* synerr - report a syntax error */
+
+void synerr( str )
+char str[];
+ {
+ syntaxerror = true;
+ pinpoint_message( str );
+ }
+
+
+/* warn - report a warning, unless -w was given */
+
+void warn( str )
+char str[];
+ {
+ line_warning( str, linenum );
+ }
+
+/* format_pinpoint_message - write out a message formatted with one string,
+ * pinpointing its location
+ */
+
+void format_pinpoint_message( msg, arg )
+char msg[], arg[];
+ {
+ char errmsg[MAXLINE];
+
+ (void) sprintf( errmsg, msg, arg );
+ pinpoint_message( errmsg );
+ }
+
+
+/* pinpoint_message - write out a message, pinpointing its location */
+
+void pinpoint_message( str )
+char str[];
+ {
+ line_pinpoint( str, linenum );
+ }
+
+
+/* line_warning - report a warning at a given line, unless -w was given */
+
+void line_warning( str, line )
+char str[];
+int line;
+ {
+ char warning[MAXLINE];
+
+ if ( ! nowarn )
+ {
+ sprintf( warning, "warning, %s", str );
+ line_pinpoint( warning, line );
+ }
+ }
+
+
+/* line_pinpoint - write out a message, pinpointing it at the given line */
+
+void line_pinpoint( str, line )
+char str[];
+int line;
+ {
+ fprintf( stderr, "\"%s\", line %d: %s\n", infilename, line, str );
+ }
+
+
+/* yyerror - eat up an error message from the parser;
+ * currently, messages are ignore
+ */
+
+void yyerror( msg )
+char msg[];
+ {
+ }
diff --git a/usr.bin/lex/scan.l b/usr.bin/lex/scan.l
new file mode 100644
index 000000000000..74b589c771ce
--- /dev/null
+++ b/usr.bin/lex/scan.l
@@ -0,0 +1,572 @@
+/* scan.l - scanner for flex input */
+
+%{
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: scan.l,v 1.2 94/01/04 14:33:09 vern Exp $ */
+
+#include "flexdef.h"
+#include "parse.h"
+
+#define ACTION_ECHO add_action( yytext )
+#define MARK_END_OF_PROLOG mark_prolog();
+
+#define YY_DECL \
+ int flexscan()
+
+#define RETURNCHAR \
+ yylval = (unsigned char) yytext[0]; \
+ return CHAR;
+
+#define RETURNNAME \
+ strcpy( nmstr, yytext ); \
+ return NAME;
+
+#define PUT_BACK_STRING(str, start) \
+ for ( i = strlen( str ) - 1; i >= start; --i ) \
+ unput((str)[i])
+
+#define CHECK_REJECT(str) \
+ if ( all_upper( str ) ) \
+ reject = true;
+
+#define CHECK_YYMORE(str) \
+ if ( all_lower( str ) ) \
+ yymore_used = true;
+%}
+
+%x SECT2 SECT2PROLOG SECT3 CODEBLOCK PICKUPDEF SC CARETISBOL NUM QUOTE
+%x FIRSTCCL CCL ACTION RECOVER BRACEERROR C_COMMENT ACTION_COMMENT
+%x ACTION_STRING PERCENT_BRACE_ACTION USED_LIST CODEBLOCK_2
+
+WS [ \t]+
+OPTWS [ \t]*
+NOT_WS [^ \t\n]
+
+NL (\n|\r\n|\n\r)
+
+NAME ([a-z_][a-z_0-9-]*)
+NOT_NAME [^a-z_*\n]+
+
+SCNAME {NAME}
+
+ESCSEQ (\\([^\n]|[0-9]{1,3}|x[0-9a-f]{1,2}))
+
+FIRST_CCL_CHAR ([^\\\n]|{ESCSEQ})
+CCL_CHAR ([^\\\n\]]|{ESCSEQ})
+
+%%
+ static int bracelevel, didadef, indented_code, checking_used;
+
+ int doing_codeblock = false;
+ int i;
+ Char nmdef[MAXLINE], myesc();
+
+
+^{WS} indented_code = true; BEGIN(CODEBLOCK);
+^"/*" ACTION_ECHO; BEGIN(C_COMMENT);
+^"%s"{NAME}? return SCDECL;
+^"%x"{NAME}? return XSCDECL;
+^"%{".*{NL} {
+ ++linenum;
+ line_directive_out( (FILE *) 0 );
+ indented_code = false;
+ BEGIN(CODEBLOCK);
+ }
+
+{WS} return WHITESPACE;
+
+^"%%".* {
+ sectnum = 2;
+ bracelevel = 0;
+ mark_defs1();
+ line_directive_out( (FILE *) 0 );
+ BEGIN(SECT2PROLOG);
+ return SECTEND;
+ }
+
+^"%pointer".*{NL} {
+ if ( lex_compat )
+ warn( "%pointer incompatible with -l option" );
+ else
+ yytext_is_array = false;
+ ++linenum;
+ }
+^"%array".*{NL} {
+ if ( C_plus_plus )
+ warn( "%array incompatible with -+ option" );
+ else
+ yytext_is_array = true;
+ ++linenum;
+ }
+
+^"%used" {
+ warn( "%used/%unused have been deprecated" );
+ checking_used = REALLY_USED; BEGIN(USED_LIST);
+ }
+^"%unused" {
+ warn( "%used/%unused have been deprecated" );
+ checking_used = REALLY_NOT_USED; BEGIN(USED_LIST);
+ }
+
+
+^"%"[aceknopr]{OPTWS}[0-9]*{OPTWS}{NL} ++linenum; /* ignore */
+
+^"%"[^sxanpekotcru{}].* synerr( "unrecognized '%' directive" );
+
+^{NAME} {
+ strcpy( nmstr, yytext );
+ didadef = false;
+ BEGIN(PICKUPDEF);
+ }
+
+{SCNAME} RETURNNAME;
+^{OPTWS}{NL} ++linenum; /* allows blank lines in section 1 */
+{OPTWS}{NL} ++linenum; return '\n';
+
+
+<C_COMMENT>"*/" ACTION_ECHO; BEGIN(INITIAL);
+<C_COMMENT>"*/".*{NL} ++linenum; ACTION_ECHO; BEGIN(INITIAL);
+<C_COMMENT>[^*\n]+ ACTION_ECHO;
+<C_COMMENT>"*" ACTION_ECHO;
+<C_COMMENT>{NL} ++linenum; ACTION_ECHO;
+
+
+<CODEBLOCK>^"%}".*{NL} ++linenum; BEGIN(INITIAL);
+<CODEBLOCK>"reject" ACTION_ECHO; CHECK_REJECT(yytext);
+<CODEBLOCK>"yymore" ACTION_ECHO; CHECK_YYMORE(yytext);
+<CODEBLOCK>{NAME}|{NOT_NAME}|. ACTION_ECHO;
+<CODEBLOCK>{NL} {
+ ++linenum;
+ ACTION_ECHO;
+ if ( indented_code )
+ BEGIN(INITIAL);
+ }
+
+
+<PICKUPDEF>{WS} /* separates name and definition */
+
+<PICKUPDEF>{NOT_WS}.* {
+ strcpy( (char *) nmdef, yytext );
+
+ /* Skip trailing whitespace. */
+ for ( i = strlen( (char *) nmdef ) - 1;
+ i >= 0 && (nmdef[i] == ' ' || nmdef[i] == '\t');
+ --i )
+ ;
+
+ nmdef[i + 1] = '\0';
+
+ ndinstal( nmstr, nmdef );
+ didadef = true;
+ }
+
+<PICKUPDEF>{NL} {
+ if ( ! didadef )
+ synerr( "incomplete name definition" );
+ BEGIN(INITIAL);
+ ++linenum;
+ }
+
+<RECOVER>.*{NL} ++linenum; BEGIN(INITIAL); RETURNNAME;
+
+
+<USED_LIST>{NL} ++linenum; BEGIN(INITIAL);
+<USED_LIST>{WS}
+<USED_LIST>"reject" {
+ if ( all_upper( yytext ) )
+ reject_really_used = checking_used;
+ else
+ synerr(
+ "unrecognized %used/%unused construct" );
+ }
+<USED_LIST>"yymore" {
+ if ( all_lower( yytext ) )
+ yymore_really_used = checking_used;
+ else
+ synerr(
+ "unrecognized %used/%unused construct" );
+ }
+<USED_LIST>{NOT_WS}+ synerr( "unrecognized %used/%unused construct" );
+
+
+<SECT2PROLOG>^"%{".* ++bracelevel; yyless( 2 ); /* eat only %{ */
+<SECT2PROLOG>^"%}".* --bracelevel; yyless( 2 ); /* eat only %} */
+
+<SECT2PROLOG>^{WS}.* ACTION_ECHO; /* indented code in prolog */
+
+<SECT2PROLOG>^{NOT_WS}.* { /* non-indented code */
+ if ( bracelevel <= 0 )
+ { /* not in %{ ... %} */
+ yyless( 0 ); /* put it all back */
+ mark_prolog();
+ BEGIN(SECT2);
+ }
+ else
+ ACTION_ECHO;
+ }
+
+<SECT2PROLOG>.* ACTION_ECHO;
+<SECT2PROLOG>{NL} ++linenum; ACTION_ECHO;
+
+<SECT2PROLOG><<EOF>> {
+ mark_prolog();
+ sectnum = 0;
+ yyterminate(); /* to stop the parser */
+ }
+
+<SECT2>^{OPTWS}{NL} ++linenum; /* allow blank lines in section 2 */
+
+<SECT2>^({WS}|"%{") {
+ indented_code = (yytext[0] != '%');
+ doing_codeblock = true;
+ bracelevel = 1;
+
+ if ( indented_code )
+ ACTION_ECHO;
+
+ BEGIN(CODEBLOCK_2);
+ }
+
+<SECT2>^"<" BEGIN(SC); return '<';
+<SECT2>^"^" return '^';
+<SECT2>\" BEGIN(QUOTE); return '"';
+<SECT2>"{"/[0-9] BEGIN(NUM); return '{';
+<SECT2>"{"[^0-9\n][^}\n]* BEGIN(BRACEERROR);
+<SECT2>"$"/([ \t]|{NL}) return '$';
+
+<SECT2>{WS}"%{" {
+ bracelevel = 1;
+ BEGIN(PERCENT_BRACE_ACTION);
+ return '\n';
+ }
+<SECT2>{WS}"|".*{NL} continued_action = true; ++linenum; return '\n';
+
+<SECT2>{WS} {
+ /* This rule is separate from the one below because
+ * otherwise we get variable trailing context, so
+ * we can't build the scanner using -{f,F}.
+ */
+ bracelevel = 0;
+ continued_action = false;
+ BEGIN(ACTION);
+ return '\n';
+ }
+
+<SECT2>{OPTWS}{NL} {
+ bracelevel = 0;
+ continued_action = false;
+ BEGIN(ACTION);
+ unput( '\n' ); /* so <ACTION> sees it */
+ return '\n';
+ }
+
+<SECT2>"<<EOF>>" return EOF_OP;
+
+<SECT2>^"%%".* {
+ sectnum = 3;
+ BEGIN(SECT3);
+ yyterminate(); /* to stop the parser */
+ }
+
+<SECT2>"["{FIRST_CCL_CHAR}{CCL_CHAR}* {
+ int cclval;
+
+ strcpy( nmstr, yytext );
+
+ /* Check to see if we've already encountered this
+ * ccl.
+ */
+ if ( (cclval = ccllookup( (Char *) nmstr )) )
+ {
+ if ( input() != ']' )
+ synerr( "bad character class" );
+
+ yylval = cclval;
+ ++cclreuse;
+ return PREVCCL;
+ }
+ else
+ {
+ /* We fudge a bit. We know that this ccl will
+ * soon be numbered as lastccl + 1 by cclinit.
+ */
+ cclinstal( (Char *) nmstr, lastccl + 1 );
+
+ /* Push back everything but the leading bracket
+ * so the ccl can be rescanned.
+ */
+ yyless( 1 );
+
+ BEGIN(FIRSTCCL);
+ return '[';
+ }
+ }
+
+<SECT2>"{"{NAME}"}" {
+ register Char *nmdefptr;
+ Char *ndlookup();
+
+ strcpy( nmstr, yytext + 1 );
+ nmstr[yyleng - 2] = '\0'; /* chop trailing brace */
+
+ if ( ! (nmdefptr = ndlookup( nmstr )) )
+ format_synerr( "undefined definition {%s}",
+ nmstr );
+
+ else
+ { /* push back name surrounded by ()'s */
+ int len = strlen( (char *) nmdefptr );
+
+ if ( lex_compat || nmdefptr[0] == '^' ||
+ (len > 0 && nmdefptr[len - 1] == '$') )
+ { /* don't use ()'s after all */
+ PUT_BACK_STRING((char *) nmdefptr, 0);
+
+ if ( nmdefptr[0] == '^' )
+ BEGIN(CARETISBOL);
+ }
+
+ else
+ {
+ unput(')');
+ PUT_BACK_STRING((char *) nmdefptr, 0);
+ unput('(');
+ }
+ }
+ }
+
+<SECT2>[/|*+?.()] return (unsigned char) yytext[0];
+<SECT2>. RETURNCHAR;
+
+
+<SC>[,*] return (unsigned char) yytext[0];
+<SC>">" BEGIN(SECT2); return '>';
+<SC>">"/^ BEGIN(CARETISBOL); return '>';
+<SC>{SCNAME} RETURNNAME;
+<SC>. {
+ format_synerr( "bad <start condition>: %s", yytext );
+ }
+
+<CARETISBOL>"^" BEGIN(SECT2); return '^';
+
+
+<QUOTE>[^"\n] RETURNCHAR;
+<QUOTE>\" BEGIN(SECT2); return '"';
+
+<QUOTE>{NL} {
+ synerr( "missing quote" );
+ BEGIN(SECT2);
+ ++linenum;
+ return '"';
+ }
+
+
+<FIRSTCCL>"^"/[^-\]\n] BEGIN(CCL); return '^';
+<FIRSTCCL>"^"/("-"|"]") return '^';
+<FIRSTCCL>. BEGIN(CCL); RETURNCHAR;
+
+<CCL>-/[^\]\n] return '-';
+<CCL>[^\]\n] RETURNCHAR;
+<CCL>"]" BEGIN(SECT2); return ']';
+<CCL>.|{NL} {
+ synerr( "bad character class" );
+ BEGIN(SECT2);
+ return ']';
+ }
+
+
+<NUM>[0-9]+ {
+ yylval = myctoi( yytext );
+ return NUMBER;
+ }
+
+<NUM>"," return ',';
+<NUM>"}" BEGIN(SECT2); return '}';
+
+<NUM>. {
+ synerr( "bad character inside {}'s" );
+ BEGIN(SECT2);
+ return '}';
+ }
+
+<NUM>{NL} {
+ synerr( "missing }" );
+ BEGIN(SECT2);
+ ++linenum;
+ return '}';
+ }
+
+
+<BRACEERROR>"}" synerr( "bad name in {}'s" ); BEGIN(SECT2);
+<BRACEERROR>{NL} synerr( "missing }" ); ++linenum; BEGIN(SECT2);
+
+
+<CODEBLOCK_2>"/*" ACTION_ECHO; BEGIN(ACTION_COMMENT);
+<PERCENT_BRACE_ACTION,CODEBLOCK_2>{OPTWS}"%}".* bracelevel = 0;
+<PERCENT_BRACE_ACTION,CODEBLOCK_2,ACTION>"reject" {
+ ACTION_ECHO;
+ CHECK_REJECT(yytext);
+ }
+<PERCENT_BRACE_ACTION,CODEBLOCK_2,ACTION>"yymore" {
+ ACTION_ECHO;
+ CHECK_YYMORE(yytext);
+ }
+<PERCENT_BRACE_ACTION,CODEBLOCK_2>{NAME}|{NOT_NAME}|. ACTION_ECHO;
+<PERCENT_BRACE_ACTION,CODEBLOCK_2>{NL} {
+ ++linenum;
+ ACTION_ECHO;
+ if ( bracelevel == 0 ||
+ (doing_codeblock && indented_code) )
+ {
+ if ( ! doing_codeblock )
+ add_action( "\tYY_BREAK\n" );
+
+ doing_codeblock = false;
+ BEGIN(SECT2);
+ }
+ }
+
+
+ /* Reject and YYmore() are checked for above, in PERCENT_BRACE_ACTION */
+<ACTION>"{" ACTION_ECHO; ++bracelevel;
+<ACTION>"}" ACTION_ECHO; --bracelevel;
+<ACTION>[^a-z_{}"'/\n]+ ACTION_ECHO;
+<ACTION>{NAME} ACTION_ECHO;
+<ACTION>"/*" ACTION_ECHO; BEGIN(ACTION_COMMENT);
+<ACTION>"'"([^'\\\n]|\\.)*"'" ACTION_ECHO; /* character constant */
+<ACTION>\" ACTION_ECHO; BEGIN(ACTION_STRING);
+<ACTION>{NL} {
+ ++linenum;
+ ACTION_ECHO;
+ if ( bracelevel == 0 )
+ {
+ add_action( "\tYY_BREAK\n" );
+ BEGIN(SECT2);
+ }
+ }
+<ACTION>. ACTION_ECHO;
+
+<ACTION_COMMENT>"*/" {
+ ACTION_ECHO;
+ if ( doing_codeblock )
+ BEGIN(CODEBLOCK_2);
+ else
+ BEGIN(ACTION);
+ }
+
+<ACTION_COMMENT>"*" ACTION_ECHO;
+<ACTION_COMMENT>[^*\n]+ ACTION_ECHO;
+<ACTION_COMMENT>[^*\n]*{NL} ++linenum; ACTION_ECHO;
+
+<ACTION_STRING>[^"\\\n]+ ACTION_ECHO;
+<ACTION_STRING>\\. ACTION_ECHO;
+<ACTION_STRING>{NL} ++linenum; ACTION_ECHO;
+<ACTION_STRING>\" ACTION_ECHO; BEGIN(ACTION);
+<ACTION_STRING>. ACTION_ECHO;
+
+<ACTION,ACTION_COMMENT,ACTION_STRING><<EOF>> {
+ synerr( "EOF encountered inside an action" );
+ yyterminate();
+ }
+
+
+<SECT2,QUOTE,CCL>{ESCSEQ} {
+ yylval = myesc( (Char *) yytext );
+ return CHAR;
+ }
+
+<FIRSTCCL>{ESCSEQ} {
+ yylval = myesc( (Char *) yytext );
+ BEGIN(CCL);
+ return CHAR;
+ }
+
+
+<SECT3>.*(\n?) ECHO;
+<SECT3><<EOF>> sectnum = 0; yyterminate();
+
+<*>.|\n format_synerr( "bad character: %s", yytext );
+
+%%
+
+
+int yywrap()
+ {
+ if ( --num_input_files > 0 )
+ {
+ set_input_file( *++input_files );
+ return 0;
+ }
+
+ else
+ return 1;
+ }
+
+
+/* set_input_file - open the given file (if NULL, stdin) for scanning */
+
+void set_input_file( file )
+char *file;
+ {
+ if ( file )
+ {
+ infilename = file;
+ yyin = fopen( infilename, "r" );
+
+ if ( yyin == NULL )
+ lerrsf( "can't open %s", file );
+ }
+
+ else
+ {
+ yyin = stdin;
+ infilename = "<stdin>";
+ }
+ }
+
+
+/* Wrapper routines for accessing the scanner's malloc routines. */
+
+void *flex_alloc( size )
+unsigned int size;
+ {
+ return yy_flex_alloc( size );
+ }
+
+void *flex_realloc( ptr, size )
+void *ptr;
+unsigned int size;
+ {
+ return yy_flex_realloc( ptr, size );
+ }
+
+void flex_free( ptr )
+void *ptr;
+ {
+ yy_flex_free( ptr );
+ }
diff --git a/usr.bin/lex/skel.c b/usr.bin/lex/skel.c
new file mode 100644
index 000000000000..4ab49d1085cd
--- /dev/null
+++ b/usr.bin/lex/skel.c
@@ -0,0 +1,1232 @@
+/* File created from flex.skel via mkskel.sh */
+
+#include "flexdef.h"
+
+char *skel[] = {
+ "/* A lexical scanner generated by flex */",
+ "",
+ "/* Scanner skeleton version:",
+ " * $Header: /home/daffy/u0/vern/flex/flex-2.4.7/RCS/flex.skl,v 1.2 94/08/03 11:13:24 vern Exp $",
+ " */",
+ "",
+ "#define FLEX_SCANNER",
+ "",
+ "%-",
+ "#include <stdio.h>",
+ "%*",
+ "",
+ "",
+ "/* cfront 1.2 defines \"c_plusplus\" instead of \"__cplusplus\" */",
+ "#ifdef c_plusplus",
+ "#ifndef __cplusplus",
+ "#define __cplusplus",
+ "#endif",
+ "#endif",
+ "",
+ "",
+ "#ifdef __cplusplus",
+ "",
+ "#include <stdlib.h>",
+ "%+",
+ "class istream;",
+ "%*",
+ "#include <unistd.h>",
+ "",
+ "/* Use prototypes in function declarations. */",
+ "#define YY_USE_PROTOS",
+ "",
+ "/* The \"const\" storage-class-modifier is valid. */",
+ "#define YY_USE_CONST",
+ "",
+ "#else /* ! __cplusplus */",
+ "",
+ "#ifdef __STDC__",
+ "",
+ "#define YY_USE_PROTOS",
+ "#define YY_USE_CONST",
+ "",
+ "#endif /* __STDC__ */",
+ "#endif /* ! __cplusplus */",
+ "",
+ "",
+ "#ifdef __TURBOC__",
+ "#define YY_USE_CONST",
+ "#endif",
+ "",
+ "",
+ "#ifndef YY_USE_CONST",
+ "#ifndef const",
+ "#define const",
+ "#endif",
+ "#endif",
+ "",
+ "",
+ "#ifdef YY_USE_PROTOS",
+ "#define YY_PROTO(proto) proto",
+ "#else",
+ "#define YY_PROTO(proto) ()",
+ "#endif",
+ "",
+ "/* Returned upon end-of-file. */",
+ "#define YY_NULL 0",
+ "",
+ "/* Promotes a possibly negative, possibly signed char to an unsigned",
+ " * integer for use as an array index. If the signed char is negative,",
+ " * we want to instead treat it as an 8-bit unsigned char, hence the",
+ " * double cast.",
+ " */",
+ "#define YY_SC_TO_UI(c) ((unsigned int) (unsigned char) c)",
+ "",
+ "/* Enter a start condition. This macro really ought to take a parameter,",
+ " * but we do it the disgusting crufty way forced on us by the ()-less",
+ " * definition of BEGIN.",
+ " */",
+ "#define BEGIN yy_start = 1 + 2 *",
+ "",
+ "/* Translate the current start state into a value that can be later handed",
+ " * to BEGIN to return to the state.",
+ " */",
+ "#define YY_START ((yy_start - 1) / 2)",
+ "",
+ "/* Action number for EOF rule of a given start state. */",
+ "#define YY_STATE_EOF(state) (YY_END_OF_BUFFER + state + 1)",
+ "",
+ "/* Special action meaning \"start processing a new file\". Now included",
+ " * only for backward compatibility with previous versions of flex.",
+ " */",
+ "#define YY_NEW_FILE yyrestart( yyin )",
+ "",
+ "#define YY_END_OF_BUFFER_CHAR 0",
+ "",
+ "/* Size of default input buffer. */",
+ "#define YY_BUF_SIZE 16384",
+ "",
+ "typedef struct yy_buffer_state *YY_BUFFER_STATE;",
+ "",
+ "extern int yyleng;",
+ "%-",
+ "extern FILE *yyin, *yyout;",
+ "%*",
+ "",
+ "#ifdef __cplusplus",
+ "extern \"C\" {",
+ "#endif",
+ " extern int yywrap YY_PROTO(( void ));",
+ "#ifdef __cplusplus",
+ " }",
+ "#endif",
+ "",
+ "#define EOB_ACT_CONTINUE_SCAN 0",
+ "#define EOB_ACT_END_OF_FILE 1",
+ "#define EOB_ACT_LAST_MATCH 2",
+ "",
+ "/* The funky do-while in the following #define is used to turn the definition",
+ " * int a single C statement (which needs a semi-colon terminator). This",
+ " * avoids problems with code like:",
+ " *",
+ " * if ( condition_holds )",
+ " * yyless( 5 );",
+ " * else",
+ " * do_something_else();",
+ " *",
+ " * Prior to using the do-while the compiler would get upset at the",
+ " * \"else\" because it interpreted the \"if\" statement as being all",
+ " * done when it reached the ';' after the yyless() call.",
+ " */",
+ "",
+ "/* Return all but the first 'n' matched characters back to the input stream. */",
+ "",
+ "#define yyless(n) \\",
+ " do \\",
+ " { \\",
+ " /* Undo effects of setting up yytext. */ \\",
+ " *yy_cp = yy_hold_char; \\",
+ " yy_c_buf_p = yy_cp = yy_bp + n - YY_MORE_ADJ; \\",
+ " YY_DO_BEFORE_ACTION; /* set up yytext again */ \\",
+ " } \\",
+ " while ( 0 )",
+ "",
+ "#define unput(c) yyunput( c, yytext_ptr )",
+ "",
+ "",
+ "struct yy_buffer_state",
+ " {",
+ "%-",
+ " FILE *yy_input_file;",
+ "%+",
+ " istream* yy_input_file;",
+ "%*",
+ "",
+ " char *yy_ch_buf; /* input buffer */",
+ " char *yy_buf_pos; /* current position in input buffer */",
+ "",
+ " /* Size of input buffer in bytes, not including room for EOB",
+ " * characters.",
+ " */",
+ " int yy_buf_size;",
+ "",
+ " /* Number of characters read into yy_ch_buf, not including EOB",
+ " * characters.",
+ " */",
+ " int yy_n_chars;",
+ "",
+ " /* Whether this is an \"interactive\" input source; if so, and",
+ " * if we're using stdio for input, then we want to use getc()",
+ " * instead of fread(), to make sure we stop fetching input after",
+ " * each newline.",
+ " */",
+ " int yy_is_interactive;",
+ "",
+ " /* Whether to try to fill the input buffer when we reach the",
+ " * end of it.",
+ " */",
+ " int yy_fill_buffer;",
+ "",
+ " int yy_buffer_status;",
+ "#define YY_BUFFER_NEW 0",
+ "#define YY_BUFFER_NORMAL 1",
+ " /* When an EOF's been seen but there's still some text to process",
+ " * then we mark the buffer as YY_EOF_PENDING, to indicate that we",
+ " * shouldn't try reading from the input source any more. We might",
+ " * still have a bunch of tokens to match, though, because of",
+ " * possible backing-up.",
+ " *",
+ " * When we actually see the EOF, we change the status to \"new\"",
+ " * (via yyrestart()), so that the user can continue scanning by",
+ " * just pointing yyin at a new input file.",
+ " */",
+ "#define YY_BUFFER_EOF_PENDING 2",
+ " };",
+ "",
+ "%- Standard (non-C++) definition",
+ "static YY_BUFFER_STATE yy_current_buffer = 0;",
+ "%*",
+ "",
+ "/* We provide macros for accessing buffer states in case in the",
+ " * future we want to put the buffer states in a more general",
+ " * \"scanner state\".",
+ " */",
+ "#define YY_CURRENT_BUFFER yy_current_buffer",
+ "",
+ "",
+ "%- Standard (non-C++) definition",
+ "/* yy_hold_char holds the character lost when yytext is formed. */",
+ "static char yy_hold_char;",
+ "",
+ "static int yy_n_chars; /* number of characters read into yy_ch_buf */",
+ "",
+ "",
+ "int yyleng;",
+ "",
+ "/* Points to current character in buffer. */",
+ "static char *yy_c_buf_p = (char *) 0;",
+ "static int yy_init = 1; /* whether we need to initialize */",
+ "static int yy_start = 0; /* start state number */",
+ "",
+ "/* Flag which is used to allow yywrap()'s to do buffer switches",
+ " * instead of setting up a fresh yyin. A bit of a hack ...",
+ " */",
+ "static int yy_did_buffer_switch_on_eof;",
+ "",
+ "static void yyunput YY_PROTO(( int c, char *buf_ptr ));",
+ "void yyrestart YY_PROTO(( FILE *input_file ));",
+ "void yy_switch_to_buffer YY_PROTO(( YY_BUFFER_STATE new_buffer ));",
+ "void yy_load_buffer_state YY_PROTO(( void ));",
+ "YY_BUFFER_STATE yy_create_buffer YY_PROTO(( FILE *file, int size ));",
+ "void yy_delete_buffer YY_PROTO(( YY_BUFFER_STATE b ));",
+ "void yy_init_buffer YY_PROTO(( YY_BUFFER_STATE b, FILE *file ));",
+ "",
+ "static int yy_start_stack_ptr = 0;",
+ "static int yy_start_stack_depth = 0;",
+ "static int *yy_start_stack = 0;",
+ "static void yy_push_state YY_PROTO(( int new_state ));",
+ "static void yy_pop_state YY_PROTO(( void ));",
+ "static int yy_top_state YY_PROTO(( void ));",
+ "%*",
+ "",
+ "static void *yy_flex_alloc YY_PROTO(( unsigned int ));",
+ "static void *yy_flex_realloc YY_PROTO(( void *, unsigned int ));",
+ "static void yy_flex_free YY_PROTO(( void * ));",
+ "",
+ "#define yy_new_buffer yy_create_buffer",
+ "",
+ "%% yytext/yyin/yyout/yy_state_type/yylineno etc. def's & init go here",
+ "",
+ "#ifndef yytext_ptr",
+ "static void yy_flex_strncpy YY_PROTO(( char *, const char *, int ));",
+ "#endif",
+ "",
+ "%- Standard (non-C++) definition",
+ "#ifdef __cplusplus",
+ "static int yyinput YY_PROTO(( void ));",
+ "#else",
+ "static int input YY_PROTO(( void ));",
+ "#endif",
+ "%*",
+ "",
+ "%- Standard (non-C++) definition",
+ "static yy_state_type yy_get_previous_state YY_PROTO(( void ));",
+ "static yy_state_type yy_try_NUL_trans YY_PROTO(( yy_state_type current_state ));",
+ "static int yy_get_next_buffer YY_PROTO(( void ));",
+ "static void yy_fatal_error YY_PROTO(( const char msg[] ));",
+ "%*",
+ "",
+ "/* Done after the current pattern has been matched and before the",
+ " * corresponding action - sets up yytext.",
+ " */",
+ "#define YY_DO_BEFORE_ACTION \\",
+ " yytext_ptr = yy_bp; \\",
+ "%% code to fiddle yytext and yyleng for yymore() goes here",
+ " yy_hold_char = *yy_cp; \\",
+ " *yy_cp = '\\0'; \\",
+ "%% code to copy yytext_ptr to yytext[] goes here, if %array",
+ " yy_c_buf_p = yy_cp;",
+ "",
+ "%% data tables for the DFA and the user's section 1 definitions go here",
+ "",
+ "/* Macros after this point can all be overridden by user definitions in",
+ " * section 1.",
+ " */",
+ "",
+ "#ifdef YY_MALLOC_DECL",
+ "YY_MALLOC_DECL",
+ "#else",
+ "#if __STDC__",
+ "#ifndef __cplusplus",
+ "#include <stdlib.h>",
+ "#endif",
+ "#else",
+ "/* Just try to get by without declaring the routines. This will fail",
+ " * miserably on non-ANSI systems for which sizeof(size_t) != sizeof(int)",
+ " * or sizeof(void*) != sizeof(int).",
+ " */",
+ "#endif",
+ "#endif",
+ "",
+ "/* Amount of stuff to slurp up with each read. */",
+ "#ifndef YY_READ_BUF_SIZE",
+ "#define YY_READ_BUF_SIZE 8192",
+ "#endif",
+ "",
+ "/* Copy whatever the last rule matched to the standard output. */",
+ "",
+ "#ifndef ECHO",
+ "%- Standard (non-C++) definition",
+ "/* This used to be an fputs(), but since the string might contain NUL's,",
+ " * we now use fwrite().",
+ " */",
+ "#define ECHO (void) fwrite( yytext, yyleng, 1, yyout )",
+ "%+ C++ definition",
+ "#define ECHO LexerOutput( yytext, yyleng )",
+ "%*",
+ "#endif",
+ "",
+ "/* Gets input and stuffs it into \"buf\". number of characters read, or YY_NULL,",
+ " * is returned in \"result\".",
+ " */",
+ "#ifndef YY_INPUT",
+ "#define YY_INPUT(buf,result,max_size) \\",
+ "%% fread()/read() definition of YY_INPUT goes here unless we're doing C++",
+ "%+ C++ definition",
+ " if ( (result = LexerInput( (char *) buf, max_size )) < 0 ) \\",
+ " YY_FATAL_ERROR( \"input in flex scanner failed\" );",
+ "%*",
+ "#endif",
+ "",
+ "/* No semi-colon after return; correct usage is to write \"yyterminate();\" -",
+ " * we don't want an extra ';' after the \"return\" because that will cause",
+ " * some compilers to complain about unreachable statements.",
+ " */",
+ "#ifndef yyterminate",
+ "#define yyterminate() return YY_NULL",
+ "#endif",
+ "",
+ "/* Number of entries by which start-condition stack grows. */",
+ "#ifndef YY_START_STACK_INCR",
+ "#define YY_START_STACK_INCR 25",
+ "#endif",
+ "",
+ "/* Report a fatal error. */",
+ "#ifndef YY_FATAL_ERROR",
+ "%-",
+ "#define YY_FATAL_ERROR(msg) yy_fatal_error( msg )",
+ "%+",
+ "#define YY_FATAL_ERROR(msg) LexerError( msg )",
+ "%*",
+ "#endif",
+ "",
+ "/* Default declaration of generated scanner - a define so the user can",
+ " * easily add parameters.",
+ " */",
+ "#ifndef YY_DECL",
+ "%- Standard (non-C++) definition",
+ "#define YY_DECL int yylex YY_PROTO(( void ))",
+ "%+ C++ definition",
+ "#define YY_DECL int yyFlexLexer::yylex()",
+ "%*",
+ "#endif",
+ "",
+ "/* Code executed at the beginning of each rule, after yytext and yyleng",
+ " * have been set up.",
+ " */",
+ "#ifndef YY_USER_ACTION",
+ "#define YY_USER_ACTION",
+ "#endif",
+ "",
+ "/* Code executed at the end of each rule. */",
+ "#ifndef YY_BREAK",
+ "#define YY_BREAK break;",
+ "#endif",
+ "",
+ "YY_DECL",
+ " {",
+ " register yy_state_type yy_current_state;",
+ " register char *yy_cp, *yy_bp;",
+ " register int yy_act;",
+ "",
+ "%% user's declarations go here",
+ "",
+ " if ( yy_init )",
+ " {",
+ "#ifdef YY_USER_INIT",
+ " YY_USER_INIT;",
+ "#endif",
+ "",
+ " if ( ! yy_start )",
+ " yy_start = 1; /* first start state */",
+ "",
+ " if ( ! yyin )",
+ "%-",
+ " yyin = stdin;",
+ "%+",
+ " yyin = &cin;",
+ "%*",
+ "",
+ " if ( ! yyout )",
+ "%-",
+ " yyout = stdout;",
+ "%+",
+ " yyout = &cout;",
+ "%*",
+ "",
+ " if ( yy_current_buffer )",
+ " yy_init_buffer( yy_current_buffer, yyin );",
+ " else",
+ " yy_current_buffer =",
+ " yy_create_buffer( yyin, YY_BUF_SIZE );",
+ "",
+ " yy_load_buffer_state();",
+ "",
+ " yy_init = 0;",
+ " }",
+ "",
+ " while ( 1 ) /* loops until end-of-file is reached */",
+ " {",
+ "%% yymore()-related code goes here",
+ " yy_cp = yy_c_buf_p;",
+ "",
+ " /* Support of yytext. */",
+ " *yy_cp = yy_hold_char;",
+ "",
+ " /* yy_bp points to the position in yy_ch_buf of the start of",
+ " * the current run.",
+ " */",
+ " yy_bp = yy_cp;",
+ "",
+ "%% code to set up and find next match goes here",
+ "",
+ "yy_find_action:",
+ "%% code to find the action number goes here",
+ "",
+ " YY_DO_BEFORE_ACTION;",
+ "",
+ "%% code for yylineno update goes here, if -l option",
+ "",
+ "do_action: /* This label is used only to access EOF actions. */",
+ "",
+ "%% debug code goes here",
+ "",
+ " switch ( yy_act )",
+ " { /* beginning of action switch */",
+ "%% actions go here",
+ "",
+ " case YY_END_OF_BUFFER:",
+ " {",
+ " /* Amount of text matched not including the EOB char. */",
+ " int yy_amount_of_matched_text = yy_cp - yytext_ptr - 1;",
+ "",
+ " /* Undo the effects of YY_DO_BEFORE_ACTION. */",
+ " *yy_cp = yy_hold_char;",
+ "",
+ " if ( yy_current_buffer->yy_buffer_status == YY_BUFFER_NEW )",
+ " {",
+ " /* We're scanning a new file or input source. It's",
+ " * possible that this happened because the user",
+ " * just pointed yyin at a new source and called",
+ " * yylex(). If so, then we have to assure",
+ " * consistency between yy_current_buffer and our",
+ " * globals. Here is the right place to do so, because",
+ " * this is the first action (other than possibly a",
+ " * back-up) that will match for the new input source.",
+ " */",
+ " yy_n_chars = yy_current_buffer->yy_n_chars;",
+ " yy_current_buffer->yy_input_file = yyin;",
+ " yy_current_buffer->yy_buffer_status = YY_BUFFER_NORMAL;",
+ " }",
+ "",
+ " /* Note that here we test for yy_c_buf_p \"<=\" to the position",
+ " * of the first EOB in the buffer, since yy_c_buf_p will",
+ " * already have been incremented past the NUL character",
+ " * (since all states make transitions on EOB to the",
+ " * end-of-buffer state). Contrast this with the test",
+ " * in input().",
+ " */",
+ " if ( yy_c_buf_p <= &yy_current_buffer->yy_ch_buf[yy_n_chars] )",
+ " { /* This was really a NUL. */",
+ " yy_state_type yy_next_state;",
+ "",
+ " yy_c_buf_p = yytext_ptr + yy_amount_of_matched_text;",
+ "",
+ " yy_current_state = yy_get_previous_state();",
+ "",
+ " /* Okay, we're now positioned to make the NUL",
+ " * transition. We couldn't have",
+ " * yy_get_previous_state() go ahead and do it",
+ " * for us because it doesn't know how to deal",
+ " * with the possibility of jamming (and we don't",
+ " * want to build jamming into it because then it",
+ " * will run more slowly).",
+ " */",
+ "",
+ " yy_next_state = yy_try_NUL_trans( yy_current_state );",
+ "",
+ " yy_bp = yytext_ptr + YY_MORE_ADJ;",
+ "",
+ " if ( yy_next_state )",
+ " {",
+ " /* Consume the NUL. */",
+ " yy_cp = ++yy_c_buf_p;",
+ " yy_current_state = yy_next_state;",
+ " goto yy_match;",
+ " }",
+ "",
+ " else",
+ " {",
+ "%% code to do back-up for compressed tables and set up yy_cp goes here",
+ " goto yy_find_action;",
+ " }",
+ " }",
+ "",
+ " else switch ( yy_get_next_buffer() )",
+ " {",
+ " case EOB_ACT_END_OF_FILE:",
+ " {",
+ " yy_did_buffer_switch_on_eof = 0;",
+ "",
+ " if ( yywrap() )",
+ " {",
+ " /* Note: because we've taken care in",
+ " * yy_get_next_buffer() to have set up",
+ " * yytext, we can now set up",
+ " * yy_c_buf_p so that if some total",
+ " * hoser (like flex itself) wants to",
+ " * call the scanner after we return the",
+ " * YY_NULL, it'll still work - another",
+ " * YY_NULL will get returned.",
+ " */",
+ " yy_c_buf_p = yytext_ptr + YY_MORE_ADJ;",
+ "",
+ " yy_act = YY_STATE_EOF(YY_START);",
+ " goto do_action;",
+ " }",
+ "",
+ " else",
+ " {",
+ " if ( ! yy_did_buffer_switch_on_eof )",
+ " YY_NEW_FILE;",
+ " }",
+ " break;",
+ " }",
+ "",
+ " case EOB_ACT_CONTINUE_SCAN:",
+ " yy_c_buf_p =",
+ " yytext_ptr + yy_amount_of_matched_text;",
+ "",
+ " yy_current_state = yy_get_previous_state();",
+ "",
+ " yy_cp = yy_c_buf_p;",
+ " yy_bp = yytext_ptr + YY_MORE_ADJ;",
+ " goto yy_match;",
+ "",
+ " case EOB_ACT_LAST_MATCH:",
+ " yy_c_buf_p =",
+ " &yy_current_buffer->yy_ch_buf[yy_n_chars];",
+ "",
+ " yy_current_state = yy_get_previous_state();",
+ "",
+ " yy_cp = yy_c_buf_p;",
+ " yy_bp = yytext_ptr + YY_MORE_ADJ;",
+ " goto yy_find_action;",
+ " }",
+ " break;",
+ " }",
+ "",
+ " default:",
+ " YY_FATAL_ERROR(",
+ " \"fatal flex scanner internal error--no action found\" );",
+ " } /* end of action switch */",
+ " } /* end of scanning one token */",
+ " } /* end of yylex */",
+ "",
+ "%+",
+ "#ifdef YY_INTERACTIVE",
+ "int yyFlexLexer::LexerInput( char* buf, int /* max_size */ )",
+ "#else",
+ "int yyFlexLexer::LexerInput( char* buf, int max_size )",
+ "#endif",
+ " {",
+ " if ( yyin->eof() || yyin->fail() )",
+ " return 0;",
+ "",
+ "#ifdef YY_INTERACTIVE",
+ " yyin->get( buf[0] );",
+ "",
+ " if ( yyin->eof() )",
+ " return 0;",
+ "",
+ " if ( yyin->bad() )",
+ " return -1;",
+ "",
+ " return 1;",
+ "",
+ "#else",
+ " (void) yyin->read( buf, max_size );",
+ "",
+ " if ( yyin->bad() )",
+ " return -1;",
+ " else",
+ " return yyin->gcount();",
+ "#endif",
+ " }",
+ "",
+ "void yyFlexLexer::LexerOutput( const char* buf, int size )",
+ " {",
+ " (void) yyout->write( buf, size );",
+ " }",
+ "%*",
+ "",
+ "/* yy_get_next_buffer - try to read in a new buffer",
+ " *",
+ " * Returns a code representing an action:",
+ " * EOB_ACT_LAST_MATCH -",
+ " * EOB_ACT_CONTINUE_SCAN - continue scanning from current position",
+ " * EOB_ACT_END_OF_FILE - end of file",
+ " */",
+ "",
+ "%-",
+ "static int yy_get_next_buffer()",
+ "%+",
+ "int yyFlexLexer::yy_get_next_buffer()",
+ "%*",
+ " {",
+ " register char *dest = yy_current_buffer->yy_ch_buf;",
+ " register char *source = yytext_ptr - 1; /* copy prev. char, too */",
+ " register int number_to_move, i;",
+ " int ret_val;",
+ "",
+ " if ( yy_c_buf_p > &yy_current_buffer->yy_ch_buf[yy_n_chars + 1] )",
+ " YY_FATAL_ERROR(",
+ " \"fatal flex scanner internal error--end of buffer missed\" );",
+ "",
+ " if ( yy_current_buffer->yy_fill_buffer == 0 )",
+ " { /* Don't try to fill the buffer, so this is an EOF. */",
+ " if ( yy_c_buf_p - yytext_ptr - YY_MORE_ADJ == 1 )",
+ " {",
+ " /* We matched a singled characater, the EOB, so",
+ " * treat this as a final EOF.",
+ " */",
+ " return EOB_ACT_END_OF_FILE;",
+ " }",
+ "",
+ " else",
+ " {",
+ " /* We matched some text prior to the EOB, first",
+ " * process it.",
+ " */",
+ " return EOB_ACT_LAST_MATCH;",
+ " }",
+ " }",
+ "",
+ " /* Try to read more data. */",
+ "",
+ " /* First move last chars to start of buffer. */",
+ " number_to_move = yy_c_buf_p - yytext_ptr;",
+ "",
+ " for ( i = 0; i < number_to_move; ++i )",
+ " *(dest++) = *(source++);",
+ "",
+ " if ( yy_current_buffer->yy_buffer_status == YY_BUFFER_EOF_PENDING )",
+ " /* don't do the read, it's not guaranteed to return an EOF,",
+ " * just force an EOF",
+ " */",
+ " yy_n_chars = 0;",
+ "",
+ " else",
+ " {",
+ " int num_to_read =",
+ " yy_current_buffer->yy_buf_size - number_to_move - 1;",
+ "",
+ " while ( num_to_read <= 0 )",
+ " { /* Not enough room in the buffer - grow it. */",
+ "#ifdef YY_USES_REJECT",
+ " YY_FATAL_ERROR(",
+ "\"input buffer overflow, can't enlarge buffer because scanner uses REJECT\" );",
+ "#else",
+ "",
+ " /* just a shorter name for the current buffer */",
+ " YY_BUFFER_STATE b = yy_current_buffer;",
+ "",
+ " int yy_c_buf_p_offset = yy_c_buf_p - b->yy_ch_buf;",
+ "",
+ " b->yy_buf_size *= 2;",
+ " b->yy_ch_buf = (char *)",
+ " yy_flex_realloc( (void *) b->yy_ch_buf,",
+ " b->yy_buf_size );",
+ "",
+ " if ( ! b->yy_ch_buf )",
+ " YY_FATAL_ERROR(",
+ " \"fatal error - scanner input buffer overflow\" );",
+ "",
+ " yy_c_buf_p = &b->yy_ch_buf[yy_c_buf_p_offset];",
+ "",
+ " num_to_read = yy_current_buffer->yy_buf_size -",
+ " number_to_move - 1;",
+ "#endif",
+ " }",
+ "",
+ " if ( num_to_read > YY_READ_BUF_SIZE )",
+ " num_to_read = YY_READ_BUF_SIZE;",
+ "",
+ " /* Read in more data. */",
+ " YY_INPUT( (&yy_current_buffer->yy_ch_buf[number_to_move]),",
+ " yy_n_chars, num_to_read );",
+ " }",
+ "",
+ " if ( yy_n_chars == 0 )",
+ " {",
+ " if ( number_to_move - YY_MORE_ADJ == 1 )",
+ " {",
+ " ret_val = EOB_ACT_END_OF_FILE;",
+ " yyrestart( yyin );",
+ " }",
+ "",
+ " else",
+ " {",
+ " ret_val = EOB_ACT_LAST_MATCH;",
+ " yy_current_buffer->yy_buffer_status =",
+ " YY_BUFFER_EOF_PENDING;",
+ " }",
+ " }",
+ "",
+ " else",
+ " ret_val = EOB_ACT_CONTINUE_SCAN;",
+ "",
+ " yy_n_chars += number_to_move;",
+ " yy_current_buffer->yy_ch_buf[yy_n_chars] = YY_END_OF_BUFFER_CHAR;",
+ " yy_current_buffer->yy_ch_buf[yy_n_chars + 1] = YY_END_OF_BUFFER_CHAR;",
+ "",
+ " /* yytext begins at the second character in yy_ch_buf; the first",
+ " * character is the one which preceded it before reading in the latest",
+ " * buffer; it needs to be kept around in case it's a newline, so",
+ " * yy_get_previous_state() will have with '^' rules active.",
+ " */",
+ "",
+ " yytext_ptr = &yy_current_buffer->yy_ch_buf[1];",
+ "",
+ " return ret_val;",
+ " }",
+ "",
+ "",
+ "/* yy_get_previous_state - get the state just before the EOB char was reached */",
+ "",
+ "%-",
+ "static yy_state_type yy_get_previous_state()",
+ "%+",
+ "yy_state_type yyFlexLexer::yy_get_previous_state()",
+ "%*",
+ " {",
+ " register yy_state_type yy_current_state;",
+ " register char *yy_cp;",
+ "",
+ "%% code to get the start state into yy_current_state goes here",
+ "",
+ " for ( yy_cp = yytext_ptr + YY_MORE_ADJ; yy_cp < yy_c_buf_p; ++yy_cp )",
+ " {",
+ "%% code to find the next state goes here",
+ " }",
+ "",
+ " return yy_current_state;",
+ " }",
+ "",
+ "",
+ "/* yy_try_NUL_trans - try to make a transition on the NUL character",
+ " *",
+ " * synopsis",
+ " * next_state = yy_try_NUL_trans( current_state );",
+ " */",
+ "",
+ "%-",
+ "#ifdef YY_USE_PROTOS",
+ "static yy_state_type yy_try_NUL_trans( yy_state_type yy_current_state )",
+ "#else",
+ "static yy_state_type yy_try_NUL_trans( yy_current_state )",
+ "yy_state_type yy_current_state;",
+ "#endif",
+ "%+",
+ "yy_state_type yyFlexLexer::yy_try_NUL_trans( yy_state_type yy_current_state )",
+ "%*",
+ " {",
+ " register int yy_is_jam;",
+ "%% code to find the next state, and perhaps do backing up, goes here",
+ "",
+ " return yy_is_jam ? 0 : yy_current_state;",
+ " }",
+ "",
+ "",
+ "%-",
+ "#ifdef YY_USE_PROTOS",
+ "static void yyunput( int c, register char *yy_bp )",
+ "#else",
+ "static void yyunput( c, yy_bp )",
+ "int c;",
+ "register char *yy_bp;",
+ "#endif",
+ "%+",
+ "void yyFlexLexer::yyunput( int c, register char* yy_bp )",
+ "%*",
+ " {",
+ " register char *yy_cp = yy_c_buf_p;",
+ "",
+ " /* undo effects of setting up yytext */",
+ " *yy_cp = yy_hold_char;",
+ "",
+ " if ( yy_cp < yy_current_buffer->yy_ch_buf + 2 )",
+ " { /* need to shift things up to make room */",
+ " /* +2 for EOB chars. */",
+ " register int number_to_move = yy_n_chars + 2;",
+ " register char *dest = &yy_current_buffer->yy_ch_buf[",
+ " yy_current_buffer->yy_buf_size + 2];",
+ " register char *source =",
+ " &yy_current_buffer->yy_ch_buf[number_to_move];",
+ "",
+ " while ( source > yy_current_buffer->yy_ch_buf )",
+ " *--dest = *--source;",
+ "",
+ " yy_cp += dest - source;",
+ " yy_bp += dest - source;",
+ " yy_n_chars = yy_current_buffer->yy_buf_size;",
+ "",
+ " if ( yy_cp < yy_current_buffer->yy_ch_buf + 2 )",
+ " YY_FATAL_ERROR( \"flex scanner push-back overflow\" );",
+ " }",
+ "",
+ " if ( yy_cp > yy_bp && yy_cp[-1] == '\\n' )",
+ " yy_cp[-2] = '\\n';",
+ "",
+ " *--yy_cp = (char) c;",
+ "",
+ "%% update yylineno here, if doing -l",
+ "",
+ " /* Note: the formal parameter *must* be called \"yy_bp\" for this",
+ " * macro to now work correctly.",
+ " */",
+ " YY_DO_BEFORE_ACTION; /* set up yytext again */",
+ " }",
+ "",
+ "",
+ "%-",
+ "#ifdef __cplusplus",
+ "static int yyinput()",
+ "#else",
+ "static int input()",
+ "#endif",
+ "%+",
+ "int yyFlexLexer::yyinput()",
+ "%*",
+ " {",
+ " int c;",
+ "",
+ " *yy_c_buf_p = yy_hold_char;",
+ "",
+ " if ( *yy_c_buf_p == YY_END_OF_BUFFER_CHAR )",
+ " {",
+ " /* yy_c_buf_p now points to the character we want to return.",
+ " * If this occurs *before* the EOB characters, then it's a",
+ " * valid NUL; if not, then we've hit the end of the buffer.",
+ " */",
+ " if ( yy_c_buf_p < &yy_current_buffer->yy_ch_buf[yy_n_chars] )",
+ " /* This was really a NUL. */",
+ " *yy_c_buf_p = '\\0';",
+ "",
+ " else",
+ " { /* need more input */",
+ " yytext_ptr = yy_c_buf_p;",
+ " ++yy_c_buf_p;",
+ "",
+ " switch ( yy_get_next_buffer() )",
+ " {",
+ " case EOB_ACT_END_OF_FILE:",
+ " {",
+ " if ( yywrap() )",
+ " {",
+ " yy_c_buf_p =",
+ " yytext_ptr + YY_MORE_ADJ;",
+ " return EOF;",
+ " }",
+ "",
+ " YY_NEW_FILE;",
+ "#ifdef __cplusplus",
+ " return yyinput();",
+ "#else",
+ " return input();",
+ "#endif",
+ " }",
+ "",
+ " case EOB_ACT_CONTINUE_SCAN:",
+ " yy_c_buf_p = yytext_ptr + YY_MORE_ADJ;",
+ " break;",
+ "",
+ " case EOB_ACT_LAST_MATCH:",
+ "#ifdef __cplusplus",
+ " YY_FATAL_ERROR(",
+ " \"unexpected last match in yyinput()\" );",
+ "#else",
+ " YY_FATAL_ERROR(",
+ " \"unexpected last match in input()\" );",
+ "#endif",
+ " }",
+ " }",
+ " }",
+ "",
+ " c = *(unsigned char *) yy_c_buf_p; /* cast for 8-bit char's */",
+ " *yy_c_buf_p = '\\0'; /* preserve yytext */",
+ " yy_hold_char = *++yy_c_buf_p;",
+ "",
+ " return c;",
+ " }",
+ "",
+ "",
+ "%-",
+ "#ifdef YY_USE_PROTOS",
+ "void yyrestart( FILE *input_file )",
+ "#else",
+ "void yyrestart( input_file )",
+ "FILE *input_file;",
+ "#endif",
+ "%+",
+ "void yyFlexLexer::yyrestart( istream* input_file )",
+ "%*",
+ " {",
+ " if ( ! yy_current_buffer )",
+ " yy_current_buffer = yy_create_buffer( yyin, YY_BUF_SIZE );",
+ "",
+ " yy_init_buffer( yy_current_buffer, input_file );",
+ " yy_load_buffer_state();",
+ " }",
+ "",
+ "",
+ "%-",
+ "#ifdef YY_USE_PROTOS",
+ "void yy_switch_to_buffer( YY_BUFFER_STATE new_buffer )",
+ "#else",
+ "void yy_switch_to_buffer( new_buffer )",
+ "YY_BUFFER_STATE new_buffer;",
+ "#endif",
+ "%+",
+ "void yyFlexLexer::yy_switch_to_buffer( YY_BUFFER_STATE new_buffer )",
+ "%*",
+ " {",
+ " if ( yy_current_buffer == new_buffer )",
+ " return;",
+ "",
+ " if ( yy_current_buffer )",
+ " {",
+ " /* Flush out information for old buffer. */",
+ " *yy_c_buf_p = yy_hold_char;",
+ " yy_current_buffer->yy_buf_pos = yy_c_buf_p;",
+ " yy_current_buffer->yy_n_chars = yy_n_chars;",
+ " }",
+ "",
+ " yy_current_buffer = new_buffer;",
+ " yy_load_buffer_state();",
+ "",
+ " /* We don't actually know whether we did this switch during",
+ " * EOF (yywrap()) processing, but the only time this flag",
+ " * is looked at is after yywrap() is called, so it's safe",
+ " * to go ahead and always set it.",
+ " */",
+ " yy_did_buffer_switch_on_eof = 1;",
+ " }",
+ "",
+ "",
+ "%-",
+ "#ifdef YY_USE_PROTOS",
+ "void yy_load_buffer_state( void )",
+ "#else",
+ "void yy_load_buffer_state()",
+ "#endif",
+ "%+",
+ "void yyFlexLexer::yy_load_buffer_state()",
+ "%*",
+ " {",
+ " yy_n_chars = yy_current_buffer->yy_n_chars;",
+ " yytext_ptr = yy_c_buf_p = yy_current_buffer->yy_buf_pos;",
+ " yyin = yy_current_buffer->yy_input_file;",
+ " yy_hold_char = *yy_c_buf_p;",
+ " }",
+ "",
+ "",
+ "%-",
+ "#ifdef YY_USE_PROTOS",
+ "YY_BUFFER_STATE yy_create_buffer( FILE *file, int size )",
+ "#else",
+ "YY_BUFFER_STATE yy_create_buffer( file, size )",
+ "FILE *file;",
+ "int size;",
+ "#endif",
+ "%+",
+ "YY_BUFFER_STATE yyFlexLexer::yy_create_buffer( istream* file, int size )",
+ "%*",
+ " {",
+ " YY_BUFFER_STATE b;",
+ "",
+ " b = (YY_BUFFER_STATE) yy_flex_alloc( sizeof( struct yy_buffer_state ) );",
+ "",
+ " if ( ! b )",
+ " YY_FATAL_ERROR( \"out of dynamic memory in yy_create_buffer()\" );",
+ "",
+ " b->yy_buf_size = size;",
+ "",
+ " /* yy_ch_buf has to be 2 characters longer than the size given because",
+ " * we need to put in 2 end-of-buffer characters.",
+ " */",
+ " b->yy_ch_buf = (char *) yy_flex_alloc( b->yy_buf_size + 2 );",
+ "",
+ " if ( ! b->yy_ch_buf )",
+ " YY_FATAL_ERROR( \"out of dynamic memory in yy_create_buffer()\" );",
+ "",
+ " yy_init_buffer( b, file );",
+ "",
+ " return b;",
+ " }",
+ "",
+ "",
+ "%-",
+ "#ifdef YY_USE_PROTOS",
+ "void yy_delete_buffer( YY_BUFFER_STATE b )",
+ "#else",
+ "void yy_delete_buffer( b )",
+ "YY_BUFFER_STATE b;",
+ "#endif",
+ "%+",
+ "void yyFlexLexer::yy_delete_buffer( YY_BUFFER_STATE b )",
+ "%*",
+ " {",
+ " if ( b == yy_current_buffer )",
+ " yy_current_buffer = (YY_BUFFER_STATE) 0;",
+ "",
+ " yy_flex_free( (void *) b->yy_ch_buf );",
+ " yy_flex_free( (void *) b );",
+ " }",
+ "",
+ "",
+ "%-",
+ "#ifdef YY_USE_PROTOS",
+ "void yy_init_buffer( YY_BUFFER_STATE b, FILE *file )",
+ "#else",
+ "void yy_init_buffer( b, file )",
+ "YY_BUFFER_STATE b;",
+ "FILE *file;",
+ "#endif",
+ "%+",
+ "void yyFlexLexer::yy_init_buffer( YY_BUFFER_STATE b, istream* file )",
+ "%*",
+ " {",
+ " b->yy_input_file = file;",
+ "",
+ " /* We put in the '\\n' and start reading from [1] so that an",
+ " * initial match-at-newline will be true.",
+ " */",
+ "",
+ " b->yy_ch_buf[0] = '\\n';",
+ " b->yy_n_chars = 1;",
+ "",
+ " /* We always need two end-of-buffer characters. The first causes",
+ " * a transition to the end-of-buffer state. The second causes",
+ " * a jam in that state.",
+ " */",
+ " b->yy_ch_buf[1] = YY_END_OF_BUFFER_CHAR;",
+ " b->yy_ch_buf[2] = YY_END_OF_BUFFER_CHAR;",
+ "",
+ " b->yy_buf_pos = &b->yy_ch_buf[1];",
+ "",
+ "%-",
+ " b->yy_is_interactive = file ? isatty( fileno(file) ) : 0;",
+ "%+",
+ " b->yy_is_interactive = 0;",
+ "%*",
+ "",
+ " b->yy_fill_buffer = 1;",
+ "",
+ " b->yy_buffer_status = YY_BUFFER_NEW;",
+ " }",
+ "",
+ "",
+ "%-",
+ "#ifdef YY_USE_PROTOS",
+ "static void yy_push_state( int new_state )",
+ "#else",
+ "static void yy_push_state( new_state )",
+ "int new_state;",
+ "#endif",
+ "%+",
+ "void yyFlexLexer::yy_push_state( int new_state )",
+ "%*",
+ " {",
+ " if ( yy_start_stack_ptr >= yy_start_stack_depth )",
+ " {",
+ " int new_size;",
+ "",
+ " yy_start_stack_depth += YY_START_STACK_INCR;",
+ " new_size = yy_start_stack_depth * sizeof( int );",
+ "",
+ " if ( ! yy_start_stack )",
+ " yy_start_stack = (int *) yy_flex_alloc( new_size );",
+ "",
+ " else",
+ " yy_start_stack = (int *) yy_flex_realloc(",
+ " (void *) yy_start_stack, new_size );",
+ "",
+ " if ( ! yy_start_stack )",
+ " YY_FATAL_ERROR(",
+ " \"out of memory expanding start-condition stack\" );",
+ " }",
+ "",
+ " yy_start_stack[yy_start_stack_ptr++] = YY_START;",
+ "",
+ " BEGIN(new_state);",
+ " }",
+ "",
+ "",
+ "%-",
+ "static void yy_pop_state()",
+ "%+",
+ "void yyFlexLexer::yy_pop_state()",
+ "%*",
+ " {",
+ " if ( --yy_start_stack_ptr < 0 )",
+ " YY_FATAL_ERROR( \"start-condition stack underflow\" );",
+ "",
+ " BEGIN(yy_start_stack[yy_start_stack_ptr]);",
+ " }",
+ "",
+ "",
+ "%-",
+ "static int yy_top_state()",
+ "%+",
+ "int yyFlexLexer::yy_top_state()",
+ "%*",
+ " {",
+ " return yy_start_stack[yy_start_stack_ptr - 1];",
+ " }",
+ "",
+ "",
+ "%-",
+ "#ifdef YY_USE_PROTOS",
+ "static void yy_fatal_error( const char msg[] )",
+ "#else",
+ "static void yy_fatal_error( msg )",
+ "char msg[];",
+ "#endif",
+ " {",
+ " (void) fprintf( stderr, \"%s\\n\", msg );",
+ " exit( 1 );",
+ " }",
+ "",
+ "%+",
+ "",
+ "void yyFlexLexer::LexerError( const char msg[] )",
+ " {",
+ " cerr << msg << '\\n';",
+ " exit( 1 );",
+ " }",
+ "%*",
+ "",
+ "",
+ "/* Redefine yyless() so it works in section 3 code. */",
+ "",
+ "#undef yyless",
+ "#define yyless(n) \\",
+ " do \\",
+ " { \\",
+ " /* Undo effects of setting up yytext. */ \\",
+ " yytext[yyleng] = yy_hold_char; \\",
+ " yy_c_buf_p = yytext + n - YY_MORE_ADJ; \\",
+ " yy_hold_char = *yy_c_buf_p; \\",
+ " *yy_c_buf_p = '\\0'; \\",
+ " yyleng = n; \\",
+ " } \\",
+ " while ( 0 )",
+ "",
+ "",
+ "/* Internal utility routines. */",
+ "",
+ "#ifndef yytext_ptr",
+ "#ifdef YY_USE_PROTOS",
+ "static void yy_flex_strncpy( char *s1, const char *s2, int n )",
+ "#else",
+ "static void yy_flex_strncpy( s1, s2, n )",
+ "char *s1;",
+ "const char *s2;",
+ "int n;",
+ "#endif",
+ " {",
+ " register int i;",
+ " for ( i = 0; i < n; ++i )",
+ " s1[i] = s2[i];",
+ " }",
+ "#endif",
+ "",
+ "",
+ "#ifdef YY_USE_PROTOS",
+ "static void *yy_flex_alloc( unsigned int size )",
+ "#else",
+ "static void *yy_flex_alloc( size )",
+ "unsigned int size;",
+ "#endif",
+ " {",
+ " return (void *) malloc( size );",
+ " }",
+ "",
+ "#ifdef YY_USE_PROTOS",
+ "static void *yy_flex_realloc( void *ptr, unsigned int size )",
+ "#else",
+ "static void *yy_flex_realloc( ptr, size )",
+ "void *ptr;",
+ "unsigned int size;",
+ "#endif",
+ " {",
+ " return (void *) realloc( ptr, size );",
+ " }",
+ "",
+ "#ifdef YY_USE_PROTOS",
+ "static void yy_flex_free( void *ptr )",
+ "#else",
+ "static void yy_flex_free( ptr )",
+ "void *ptr;",
+ "#endif",
+ " {",
+ " free( ptr );",
+ " }",
+ 0
+};
diff --git a/usr.bin/lex/sym.c b/usr.bin/lex/sym.c
new file mode 100644
index 000000000000..3c156fe9faf0
--- /dev/null
+++ b/usr.bin/lex/sym.c
@@ -0,0 +1,262 @@
+/* sym - symbol table routines */
+
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: sym.c,v 1.2 94/01/04 14:33:06 vern Exp $ */
+
+#include "flexdef.h"
+
+
+/* declare functions that have forward references */
+
+int hashfunct PROTO((register char[], int));
+
+
+struct hash_entry *ndtbl[NAME_TABLE_HASH_SIZE];
+struct hash_entry *sctbl[START_COND_HASH_SIZE];
+struct hash_entry *ccltab[CCL_HASH_SIZE];
+
+struct hash_entry *findsym();
+
+
+/* addsym - add symbol and definitions to symbol table
+ *
+ * -1 is returned if the symbol already exists, and the change not made.
+ */
+
+int addsym( sym, str_def, int_def, table, table_size )
+register char sym[];
+char *str_def;
+int int_def;
+hash_table table;
+int table_size;
+ {
+ int hash_val = hashfunct( sym, table_size );
+ register struct hash_entry *sym_entry = table[hash_val];
+ register struct hash_entry *new_entry;
+ register struct hash_entry *successor;
+
+ while ( sym_entry )
+ {
+ if ( ! strcmp( sym, sym_entry->name ) )
+ { /* entry already exists */
+ return -1;
+ }
+
+ sym_entry = sym_entry->next;
+ }
+
+ /* create new entry */
+ new_entry = (struct hash_entry *)
+ flex_alloc( sizeof( struct hash_entry ) );
+
+ if ( new_entry == NULL )
+ flexfatal( "symbol table memory allocation failed" );
+
+ if ( (successor = table[hash_val]) )
+ {
+ new_entry->next = successor;
+ successor->prev = new_entry;
+ }
+ else
+ new_entry->next = NULL;
+
+ new_entry->prev = NULL;
+ new_entry->name = sym;
+ new_entry->str_val = str_def;
+ new_entry->int_val = int_def;
+
+ table[hash_val] = new_entry;
+
+ return 0;
+ }
+
+
+/* cclinstal - save the text of a character class */
+
+void cclinstal( ccltxt, cclnum )
+Char ccltxt[];
+int cclnum;
+ {
+ /* We don't bother checking the return status because we are not
+ * called unless the symbol is new.
+ */
+ Char *copy_unsigned_string();
+
+ (void) addsym( (char *) copy_unsigned_string( ccltxt ),
+ (char *) 0, cclnum,
+ ccltab, CCL_HASH_SIZE );
+ }
+
+
+/* ccllookup - lookup the number associated with character class text
+ *
+ * Returns 0 if there's no CCL associated with the text.
+ */
+
+int ccllookup( ccltxt )
+Char ccltxt[];
+ {
+ return findsym( (char *) ccltxt, ccltab, CCL_HASH_SIZE )->int_val;
+ }
+
+
+/* findsym - find symbol in symbol table */
+
+struct hash_entry *findsym( sym, table, table_size )
+register char sym[];
+hash_table table;
+int table_size;
+ {
+ static struct hash_entry empty_entry =
+ {
+ (struct hash_entry *) 0, (struct hash_entry *) 0,
+ (char *) 0, (char *) 0, 0,
+ } ;
+ register struct hash_entry *sym_entry =
+ table[hashfunct( sym, table_size )];
+
+ while ( sym_entry )
+ {
+ if ( ! strcmp( sym, sym_entry->name ) )
+ return sym_entry;
+ sym_entry = sym_entry->next;
+ }
+
+ return &empty_entry;
+ }
+
+
+/* hashfunct - compute the hash value for "str" and hash size "hash_size" */
+
+int hashfunct( str, hash_size )
+register char str[];
+int hash_size;
+ {
+ register int hashval;
+ register int locstr;
+
+ hashval = 0;
+ locstr = 0;
+
+ while ( str[locstr] )
+ {
+ hashval = (hashval << 1) + (unsigned char) str[locstr++];
+ hashval %= hash_size;
+ }
+
+ return hashval;
+ }
+
+
+/* ndinstal - install a name definition */
+
+void ndinstal( name, definition )
+char name[];
+Char definition[];
+ {
+ char *copy_string();
+ Char *copy_unsigned_string();
+
+ if ( addsym( copy_string( name ),
+ (char *) copy_unsigned_string( definition ), 0,
+ ndtbl, NAME_TABLE_HASH_SIZE ) )
+ synerr( "name defined twice" );
+ }
+
+
+/* ndlookup - lookup a name definition
+ *
+ * Returns a nil pointer if the name definition does not exist.
+ */
+
+Char *ndlookup( nd )
+char nd[];
+ {
+ return (Char *) findsym( nd, ndtbl, NAME_TABLE_HASH_SIZE )->str_val;
+ }
+
+
+/* scextend - increase the maximum number of start conditions */
+
+void scextend()
+ {
+ current_max_scs += MAX_SCS_INCREMENT;
+
+ ++num_reallocs;
+
+ scset = reallocate_integer_array( scset, current_max_scs );
+ scbol = reallocate_integer_array( scbol, current_max_scs );
+ scxclu = reallocate_integer_array( scxclu, current_max_scs );
+ sceof = reallocate_integer_array( sceof, current_max_scs );
+ scname = reallocate_char_ptr_array( scname, current_max_scs );
+ actvsc = reallocate_integer_array( actvsc, current_max_scs );
+ }
+
+
+/* scinstal - make a start condition
+ *
+ * NOTE
+ * The start condition is "exclusive" if xcluflg is true.
+ */
+
+void scinstal( str, xcluflg )
+char str[];
+int xcluflg;
+ {
+ char *copy_string();
+
+ /* Generate start condition definition, for use in BEGIN et al. */
+ printf( "#define %s %d\n", str, lastsc );
+
+ if ( ++lastsc >= current_max_scs )
+ scextend();
+
+ scname[lastsc] = copy_string( str );
+
+ if ( addsym( scname[lastsc], (char *) 0, lastsc,
+ sctbl, START_COND_HASH_SIZE ) )
+ format_pinpoint_message( "start condition %s declared twice",
+ str );
+
+ scset[lastsc] = mkstate( SYM_EPSILON );
+ scbol[lastsc] = mkstate( SYM_EPSILON );
+ scxclu[lastsc] = xcluflg;
+ sceof[lastsc] = false;
+ }
+
+
+/* sclookup - lookup the number associated with a start condition
+ *
+ * Returns 0 if no such start condition.
+ */
+
+int sclookup( str )
+char str[];
+ {
+ return findsym( str, sctbl, START_COND_HASH_SIZE )->int_val;
+ }
diff --git a/usr.bin/lex/tblcmp.c b/usr.bin/lex/tblcmp.c
new file mode 100644
index 000000000000..224dd13883b5
--- /dev/null
+++ b/usr.bin/lex/tblcmp.c
@@ -0,0 +1,888 @@
+/* tblcmp - table compression routines */
+
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: /home/daffy/u0/vern/flex/RCS/tblcmp.c,v 2.10 93/12/07 10:18:30 vern Exp $ */
+
+#include "flexdef.h"
+
+
+/* declarations for functions that have forward references */
+
+void mkentry PROTO((register int*, int, int, int, int));
+void mkprot PROTO((int[], int, int));
+void mktemplate PROTO((int[], int, int));
+void mv2front PROTO((int));
+int tbldiff PROTO((int[], int, int[]));
+
+
+/* bldtbl - build table entries for dfa state
+ *
+ * synopsis
+ * int state[numecs], statenum, totaltrans, comstate, comfreq;
+ * bldtbl( state, statenum, totaltrans, comstate, comfreq );
+ *
+ * State is the statenum'th dfa state. It is indexed by equivalence class and
+ * gives the number of the state to enter for a given equivalence class.
+ * totaltrans is the total number of transitions out of the state. Comstate
+ * is that state which is the destination of the most transitions out of State.
+ * Comfreq is how many transitions there are out of State to Comstate.
+ *
+ * A note on terminology:
+ * "protos" are transition tables which have a high probability of
+ * either being redundant (a state processed later will have an identical
+ * transition table) or nearly redundant (a state processed later will have
+ * many of the same out-transitions). A "most recently used" queue of
+ * protos is kept around with the hope that most states will find a proto
+ * which is similar enough to be usable, and therefore compacting the
+ * output tables.
+ * "templates" are a special type of proto. If a transition table is
+ * homogeneous or nearly homogeneous (all transitions go to the same
+ * destination) then the odds are good that future states will also go
+ * to the same destination state on basically the same character set.
+ * These homogeneous states are so common when dealing with large rule
+ * sets that they merit special attention. If the transition table were
+ * simply made into a proto, then (typically) each subsequent, similar
+ * state will differ from the proto for two out-transitions. One of these
+ * out-transitions will be that character on which the proto does not go
+ * to the common destination, and one will be that character on which the
+ * state does not go to the common destination. Templates, on the other
+ * hand, go to the common state on EVERY transition character, and therefore
+ * cost only one difference.
+ */
+
+void bldtbl( state, statenum, totaltrans, comstate, comfreq )
+int state[], statenum, totaltrans, comstate, comfreq;
+ {
+ int extptr, extrct[2][CSIZE + 1];
+ int mindiff, minprot, i, d;
+
+ /* If extptr is 0 then the first array of extrct holds the result
+ * of the "best difference" to date, which is those transitions
+ * which occur in "state" but not in the proto which, to date,
+ * has the fewest differences between itself and "state". If
+ * extptr is 1 then the second array of extrct hold the best
+ * difference. The two arrays are toggled between so that the
+ * best difference to date can be kept around and also a difference
+ * just created by checking against a candidate "best" proto.
+ */
+
+ extptr = 0;
+
+ /* If the state has too few out-transitions, don't bother trying to
+ * compact its tables.
+ */
+
+ if ( (totaltrans * 100) < (numecs * PROTO_SIZE_PERCENTAGE) )
+ mkentry( state, numecs, statenum, JAMSTATE, totaltrans );
+
+ else
+ {
+ /* "checkcom" is true if we should only check "state" against
+ * protos which have the same "comstate" value.
+ */
+ int checkcom =
+ comfreq * 100 > totaltrans * CHECK_COM_PERCENTAGE;
+
+ minprot = firstprot;
+ mindiff = totaltrans;
+
+ if ( checkcom )
+ {
+ /* Find first proto which has the same "comstate". */
+ for ( i = firstprot; i != NIL; i = protnext[i] )
+ if ( protcomst[i] == comstate )
+ {
+ minprot = i;
+ mindiff = tbldiff( state, minprot,
+ extrct[extptr] );
+ break;
+ }
+ }
+
+ else
+ {
+ /* Since we've decided that the most common destination
+ * out of "state" does not occur with a high enough
+ * frequency, we set the "comstate" to zero, assuring
+ * that if this state is entered into the proto list,
+ * it will not be considered a template.
+ */
+ comstate = 0;
+
+ if ( firstprot != NIL )
+ {
+ minprot = firstprot;
+ mindiff = tbldiff( state, minprot,
+ extrct[extptr] );
+ }
+ }
+
+ /* We now have the first interesting proto in "minprot". If
+ * it matches within the tolerances set for the first proto,
+ * we don't want to bother scanning the rest of the proto list
+ * to see if we have any other reasonable matches.
+ */
+
+ if ( mindiff * 100 > totaltrans * FIRST_MATCH_DIFF_PERCENTAGE )
+ {
+ /* Not a good enough match. Scan the rest of the
+ * protos.
+ */
+ for ( i = minprot; i != NIL; i = protnext[i] )
+ {
+ d = tbldiff( state, i, extrct[1 - extptr] );
+ if ( d < mindiff )
+ {
+ extptr = 1 - extptr;
+ mindiff = d;
+ minprot = i;
+ }
+ }
+ }
+
+ /* Check if the proto we've decided on as our best bet is close
+ * enough to the state we want to match to be usable.
+ */
+
+ if ( mindiff * 100 > totaltrans * ACCEPTABLE_DIFF_PERCENTAGE )
+ {
+ /* No good. If the state is homogeneous enough,
+ * we make a template out of it. Otherwise, we
+ * make a proto.
+ */
+
+ if ( comfreq * 100 >=
+ totaltrans * TEMPLATE_SAME_PERCENTAGE )
+ mktemplate( state, statenum, comstate );
+
+ else
+ {
+ mkprot( state, statenum, comstate );
+ mkentry( state, numecs, statenum,
+ JAMSTATE, totaltrans );
+ }
+ }
+
+ else
+ { /* use the proto */
+ mkentry( extrct[extptr], numecs, statenum,
+ prottbl[minprot], mindiff );
+
+ /* If this state was sufficiently different from the
+ * proto we built it from, make it, too, a proto.
+ */
+
+ if ( mindiff * 100 >=
+ totaltrans * NEW_PROTO_DIFF_PERCENTAGE )
+ mkprot( state, statenum, comstate );
+
+ /* Since mkprot added a new proto to the proto queue,
+ * it's possible that "minprot" is no longer on the
+ * proto queue (if it happened to have been the last
+ * entry, it would have been bumped off). If it's
+ * not there, then the new proto took its physical
+ * place (though logically the new proto is at the
+ * beginning of the queue), so in that case the
+ * following call will do nothing.
+ */
+
+ mv2front( minprot );
+ }
+ }
+ }
+
+
+/* cmptmps - compress template table entries
+ *
+ * Template tables are compressed by using the 'template equivalence
+ * classes', which are collections of transition character equivalence
+ * classes which always appear together in templates - really meta-equivalence
+ * classes.
+ */
+
+void cmptmps()
+ {
+ int tmpstorage[CSIZE + 1];
+ register int *tmp = tmpstorage, i, j;
+ int totaltrans, trans;
+
+ peakpairs = numtemps * numecs + tblend;
+
+ if ( usemecs )
+ {
+ /* Create equivalence classes based on data gathered on
+ * template transitions.
+ */
+ nummecs = cre8ecs( tecfwd, tecbck, numecs );
+ }
+
+ else
+ nummecs = numecs;
+
+ while ( lastdfa + numtemps + 1 >= current_max_dfas )
+ increase_max_dfas();
+
+ /* Loop through each template. */
+
+ for ( i = 1; i <= numtemps; ++i )
+ {
+ /* Number of non-jam transitions out of this template. */
+ totaltrans = 0;
+
+ for ( j = 1; j <= numecs; ++j )
+ {
+ trans = tnxt[numecs * i + j];
+
+ if ( usemecs )
+ {
+ /* The absolute value of tecbck is the
+ * meta-equivalence class of a given
+ * equivalence class, as set up by cre8ecs().
+ */
+ if ( tecbck[j] > 0 )
+ {
+ tmp[tecbck[j]] = trans;
+
+ if ( trans > 0 )
+ ++totaltrans;
+ }
+ }
+
+ else
+ {
+ tmp[j] = trans;
+
+ if ( trans > 0 )
+ ++totaltrans;
+ }
+ }
+
+ /* It is assumed (in a rather subtle way) in the skeleton
+ * that if we're using meta-equivalence classes, the def[]
+ * entry for all templates is the jam template, i.e.,
+ * templates never default to other non-jam table entries
+ * (e.g., another template)
+ */
+
+ /* Leave room for the jam-state after the last real state. */
+ mkentry( tmp, nummecs, lastdfa + i + 1, JAMSTATE, totaltrans );
+ }
+ }
+
+
+
+/* expand_nxt_chk - expand the next check arrays */
+
+void expand_nxt_chk()
+ {
+ register int old_max = current_max_xpairs;
+
+ current_max_xpairs += MAX_XPAIRS_INCREMENT;
+
+ ++num_reallocs;
+
+ nxt = reallocate_integer_array( nxt, current_max_xpairs );
+ chk = reallocate_integer_array( chk, current_max_xpairs );
+
+ zero_out( (char *) (chk + old_max),
+ MAX_XPAIRS_INCREMENT * sizeof( int ) / sizeof( char ) );
+ }
+
+
+/* find_table_space - finds a space in the table for a state to be placed
+ *
+ * synopsis
+ * int *state, numtrans, block_start;
+ * int find_table_space();
+ *
+ * block_start = find_table_space( state, numtrans );
+ *
+ * State is the state to be added to the full speed transition table.
+ * Numtrans is the number of out-transitions for the state.
+ *
+ * find_table_space() returns the position of the start of the first block (in
+ * chk) able to accommodate the state
+ *
+ * In determining if a state will or will not fit, find_table_space() must take
+ * into account the fact that an end-of-buffer state will be added at [0],
+ * and an action number will be added in [-1].
+ */
+
+int find_table_space( state, numtrans )
+int *state, numtrans;
+ {
+ /* Firstfree is the position of the first possible occurrence of two
+ * consecutive unused records in the chk and nxt arrays.
+ */
+ register int i;
+ register int *state_ptr, *chk_ptr;
+ register int *ptr_to_last_entry_in_state;
+
+ /* If there are too many out-transitions, put the state at the end of
+ * nxt and chk.
+ */
+ if ( numtrans > MAX_XTIONS_FULL_INTERIOR_FIT )
+ {
+ /* If table is empty, return the first available spot in
+ * chk/nxt, which should be 1.
+ */
+ if ( tblend < 2 )
+ return 1;
+
+ /* Start searching for table space near the end of
+ * chk/nxt arrays.
+ */
+ i = tblend - numecs;
+ }
+
+ else
+ /* Start searching for table space from the beginning
+ * (skipping only the elements which will definitely not
+ * hold the new state).
+ */
+ i = firstfree;
+
+ while ( 1 ) /* loops until a space is found */
+ {
+ while ( i + numecs >= current_max_xpairs )
+ expand_nxt_chk();
+
+ /* Loops until space for end-of-buffer and action number
+ * are found.
+ */
+ while ( 1 )
+ {
+ /* Check for action number space. */
+ if ( chk[i - 1] == 0 )
+ {
+ /* Check for end-of-buffer space. */
+ if ( chk[i] == 0 )
+ break;
+
+ else
+ /* Since i != 0, there is no use
+ * checking to see if (++i) - 1 == 0,
+ * because that's the same as i == 0,
+ * so we skip a space.
+ */
+ i += 2;
+ }
+
+ else
+ ++i;
+
+ while ( i + numecs >= current_max_xpairs )
+ expand_nxt_chk();
+ }
+
+ /* If we started search from the beginning, store the new
+ * firstfree for the next call of find_table_space().
+ */
+ if ( numtrans <= MAX_XTIONS_FULL_INTERIOR_FIT )
+ firstfree = i + 1;
+
+ /* Check to see if all elements in chk (and therefore nxt)
+ * that are needed for the new state have not yet been taken.
+ */
+
+ state_ptr = &state[1];
+ ptr_to_last_entry_in_state = &chk[i + numecs + 1];
+
+ for ( chk_ptr = &chk[i + 1];
+ chk_ptr != ptr_to_last_entry_in_state; ++chk_ptr )
+ if ( *(state_ptr++) != 0 && *chk_ptr != 0 )
+ break;
+
+ if ( chk_ptr == ptr_to_last_entry_in_state )
+ return i;
+
+ else
+ ++i;
+ }
+ }
+
+
+/* inittbl - initialize transition tables
+ *
+ * Initializes "firstfree" to be one beyond the end of the table. Initializes
+ * all "chk" entries to be zero.
+ */
+void inittbl()
+ {
+ register int i;
+
+ zero_out( (char *) chk,
+ current_max_xpairs * sizeof( int ) / sizeof( char ) );
+
+ tblend = 0;
+ firstfree = tblend + 1;
+ numtemps = 0;
+
+ if ( usemecs )
+ {
+ /* Set up doubly-linked meta-equivalence classes; these
+ * are sets of equivalence classes which all have identical
+ * transitions out of TEMPLATES.
+ */
+
+ tecbck[1] = NIL;
+
+ for ( i = 2; i <= numecs; ++i )
+ {
+ tecbck[i] = i - 1;
+ tecfwd[i - 1] = i;
+ }
+
+ tecfwd[numecs] = NIL;
+ }
+ }
+
+
+/* mkdeftbl - make the default, "jam" table entries */
+
+void mkdeftbl()
+ {
+ int i;
+
+ jamstate = lastdfa + 1;
+
+ ++tblend; /* room for transition on end-of-buffer character */
+
+ while ( tblend + numecs >= current_max_xpairs )
+ expand_nxt_chk();
+
+ /* Add in default end-of-buffer transition. */
+ nxt[tblend] = end_of_buffer_state;
+ chk[tblend] = jamstate;
+
+ for ( i = 1; i <= numecs; ++i )
+ {
+ nxt[tblend + i] = 0;
+ chk[tblend + i] = jamstate;
+ }
+
+ jambase = tblend;
+
+ base[jamstate] = jambase;
+ def[jamstate] = 0;
+
+ tblend += numecs;
+ ++numtemps;
+ }
+
+
+/* mkentry - create base/def and nxt/chk entries for transition array
+ *
+ * synopsis
+ * int state[numchars + 1], numchars, statenum, deflink, totaltrans;
+ * mkentry( state, numchars, statenum, deflink, totaltrans );
+ *
+ * "state" is a transition array "numchars" characters in size, "statenum"
+ * is the offset to be used into the base/def tables, and "deflink" is the
+ * entry to put in the "def" table entry. If "deflink" is equal to
+ * "JAMSTATE", then no attempt will be made to fit zero entries of "state"
+ * (i.e., jam entries) into the table. It is assumed that by linking to
+ * "JAMSTATE" they will be taken care of. In any case, entries in "state"
+ * marking transitions to "SAME_TRANS" are treated as though they will be
+ * taken care of by whereever "deflink" points. "totaltrans" is the total
+ * number of transitions out of the state. If it is below a certain threshold,
+ * the tables are searched for an interior spot that will accommodate the
+ * state array.
+ */
+
+void mkentry( state, numchars, statenum, deflink, totaltrans )
+register int *state;
+int numchars, statenum, deflink, totaltrans;
+ {
+ register int minec, maxec, i, baseaddr;
+ int tblbase, tbllast;
+
+ if ( totaltrans == 0 )
+ { /* there are no out-transitions */
+ if ( deflink == JAMSTATE )
+ base[statenum] = JAMSTATE;
+ else
+ base[statenum] = 0;
+
+ def[statenum] = deflink;
+ return;
+ }
+
+ for ( minec = 1; minec <= numchars; ++minec )
+ {
+ if ( state[minec] != SAME_TRANS )
+ if ( state[minec] != 0 || deflink != JAMSTATE )
+ break;
+ }
+
+ if ( totaltrans == 1 )
+ {
+ /* There's only one out-transition. Save it for later to fill
+ * in holes in the tables.
+ */
+ stack1( statenum, minec, state[minec], deflink );
+ return;
+ }
+
+ for ( maxec = numchars; maxec > 0; --maxec )
+ {
+ if ( state[maxec] != SAME_TRANS )
+ if ( state[maxec] != 0 || deflink != JAMSTATE )
+ break;
+ }
+
+ /* Whether we try to fit the state table in the middle of the table
+ * entries we have already generated, or if we just take the state
+ * table at the end of the nxt/chk tables, we must make sure that we
+ * have a valid base address (i.e., non-negative). Note that
+ * negative base addresses dangerous at run-time (because indexing
+ * the nxt array with one and a low-valued character will access
+ * memory before the start of the array.
+ */
+
+ /* Find the first transition of state that we need to worry about. */
+ if ( totaltrans * 100 <= numchars * INTERIOR_FIT_PERCENTAGE )
+ {
+ /* Attempt to squeeze it into the middle of the tables. */
+ baseaddr = firstfree;
+
+ while ( baseaddr < minec )
+ {
+ /* Using baseaddr would result in a negative base
+ * address below; find the next free slot.
+ */
+ for ( ++baseaddr; chk[baseaddr] != 0; ++baseaddr )
+ ;
+ }
+
+ while ( baseaddr + maxec - minec + 1 >= current_max_xpairs )
+ expand_nxt_chk();
+
+ for ( i = minec; i <= maxec; ++i )
+ if ( state[i] != SAME_TRANS &&
+ (state[i] != 0 || deflink != JAMSTATE) &&
+ chk[baseaddr + i - minec] != 0 )
+ { /* baseaddr unsuitable - find another */
+ for ( ++baseaddr;
+ baseaddr < current_max_xpairs &&
+ chk[baseaddr] != 0; ++baseaddr )
+ ;
+
+ while ( baseaddr + maxec - minec + 1 >=
+ current_max_xpairs )
+ expand_nxt_chk();
+
+ /* Reset the loop counter so we'll start all
+ * over again next time it's incremented.
+ */
+
+ i = minec - 1;
+ }
+ }
+
+ else
+ {
+ /* Ensure that the base address we eventually generate is
+ * non-negative.
+ */
+ baseaddr = MAX( tblend + 1, minec );
+ }
+
+ tblbase = baseaddr - minec;
+ tbllast = tblbase + maxec;
+
+ while ( tbllast + 1 >= current_max_xpairs )
+ expand_nxt_chk();
+
+ base[statenum] = tblbase;
+ def[statenum] = deflink;
+
+ for ( i = minec; i <= maxec; ++i )
+ if ( state[i] != SAME_TRANS )
+ if ( state[i] != 0 || deflink != JAMSTATE )
+ {
+ nxt[tblbase + i] = state[i];
+ chk[tblbase + i] = statenum;
+ }
+
+ if ( baseaddr == firstfree )
+ /* Find next free slot in tables. */
+ for ( ++firstfree; chk[firstfree] != 0; ++firstfree )
+ ;
+
+ tblend = MAX( tblend, tbllast );
+ }
+
+
+/* mk1tbl - create table entries for a state (or state fragment) which
+ * has only one out-transition
+ */
+
+void mk1tbl( state, sym, onenxt, onedef )
+int state, sym, onenxt, onedef;
+ {
+ if ( firstfree < sym )
+ firstfree = sym;
+
+ while ( chk[firstfree] != 0 )
+ if ( ++firstfree >= current_max_xpairs )
+ expand_nxt_chk();
+
+ base[state] = firstfree - sym;
+ def[state] = onedef;
+ chk[firstfree] = state;
+ nxt[firstfree] = onenxt;
+
+ if ( firstfree > tblend )
+ {
+ tblend = firstfree++;
+
+ if ( firstfree >= current_max_xpairs )
+ expand_nxt_chk();
+ }
+ }
+
+
+/* mkprot - create new proto entry */
+
+void mkprot( state, statenum, comstate )
+int state[], statenum, comstate;
+ {
+ int i, slot, tblbase;
+
+ if ( ++numprots >= MSP || numecs * numprots >= PROT_SAVE_SIZE )
+ {
+ /* Gotta make room for the new proto by dropping last entry in
+ * the queue.
+ */
+ slot = lastprot;
+ lastprot = protprev[lastprot];
+ protnext[lastprot] = NIL;
+ }
+
+ else
+ slot = numprots;
+
+ protnext[slot] = firstprot;
+
+ if ( firstprot != NIL )
+ protprev[firstprot] = slot;
+
+ firstprot = slot;
+ prottbl[slot] = statenum;
+ protcomst[slot] = comstate;
+
+ /* Copy state into save area so it can be compared with rapidly. */
+ tblbase = numecs * (slot - 1);
+
+ for ( i = 1; i <= numecs; ++i )
+ protsave[tblbase + i] = state[i];
+ }
+
+
+/* mktemplate - create a template entry based on a state, and connect the state
+ * to it
+ */
+
+void mktemplate( state, statenum, comstate )
+int state[], statenum, comstate;
+ {
+ int i, numdiff, tmpbase, tmp[CSIZE + 1];
+ Char transset[CSIZE + 1];
+ int tsptr;
+
+ ++numtemps;
+
+ tsptr = 0;
+
+ /* Calculate where we will temporarily store the transition table
+ * of the template in the tnxt[] array. The final transition table
+ * gets created by cmptmps().
+ */
+
+ tmpbase = numtemps * numecs;
+
+ if ( tmpbase + numecs >= current_max_template_xpairs )
+ {
+ current_max_template_xpairs += MAX_TEMPLATE_XPAIRS_INCREMENT;
+
+ ++num_reallocs;
+
+ tnxt = reallocate_integer_array( tnxt,
+ current_max_template_xpairs );
+ }
+
+ for ( i = 1; i <= numecs; ++i )
+ if ( state[i] == 0 )
+ tnxt[tmpbase + i] = 0;
+ else
+ {
+ transset[tsptr++] = i;
+ tnxt[tmpbase + i] = comstate;
+ }
+
+ if ( usemecs )
+ mkeccl( transset, tsptr, tecfwd, tecbck, numecs, 0 );
+
+ mkprot( tnxt + tmpbase, -numtemps, comstate );
+
+ /* We rely on the fact that mkprot adds things to the beginning
+ * of the proto queue.
+ */
+
+ numdiff = tbldiff( state, firstprot, tmp );
+ mkentry( tmp, numecs, statenum, -numtemps, numdiff );
+ }
+
+
+/* mv2front - move proto queue element to front of queue */
+
+void mv2front( qelm )
+int qelm;
+ {
+ if ( firstprot != qelm )
+ {
+ if ( qelm == lastprot )
+ lastprot = protprev[lastprot];
+
+ protnext[protprev[qelm]] = protnext[qelm];
+
+ if ( protnext[qelm] != NIL )
+ protprev[protnext[qelm]] = protprev[qelm];
+
+ protprev[qelm] = NIL;
+ protnext[qelm] = firstprot;
+ protprev[firstprot] = qelm;
+ firstprot = qelm;
+ }
+ }
+
+
+/* place_state - place a state into full speed transition table
+ *
+ * State is the statenum'th state. It is indexed by equivalence class and
+ * gives the number of the state to enter for a given equivalence class.
+ * Transnum is the number of out-transitions for the state.
+ */
+
+void place_state( state, statenum, transnum )
+int *state, statenum, transnum;
+ {
+ register int i;
+ register int *state_ptr;
+ int position = find_table_space( state, transnum );
+
+ /* "base" is the table of start positions. */
+ base[statenum] = position;
+
+ /* Put in action number marker; this non-zero number makes sure that
+ * find_table_space() knows that this position in chk/nxt is taken
+ * and should not be used for another accepting number in another
+ * state.
+ */
+ chk[position - 1] = 1;
+
+ /* Put in end-of-buffer marker; this is for the same purposes as
+ * above.
+ */
+ chk[position] = 1;
+
+ /* Place the state into chk and nxt. */
+ state_ptr = &state[1];
+
+ for ( i = 1; i <= numecs; ++i, ++state_ptr )
+ if ( *state_ptr != 0 )
+ {
+ chk[position + i] = i;
+ nxt[position + i] = *state_ptr;
+ }
+
+ if ( position + numecs > tblend )
+ tblend = position + numecs;
+ }
+
+
+/* stack1 - save states with only one out-transition to be processed later
+ *
+ * If there's room for another state on the "one-transition" stack, the
+ * state is pushed onto it, to be processed later by mk1tbl. If there's
+ * no room, we process the sucker right now.
+ */
+
+void stack1( statenum, sym, nextstate, deflink )
+int statenum, sym, nextstate, deflink;
+ {
+ if ( onesp >= ONE_STACK_SIZE - 1 )
+ mk1tbl( statenum, sym, nextstate, deflink );
+
+ else
+ {
+ ++onesp;
+ onestate[onesp] = statenum;
+ onesym[onesp] = sym;
+ onenext[onesp] = nextstate;
+ onedef[onesp] = deflink;
+ }
+ }
+
+
+/* tbldiff - compute differences between two state tables
+ *
+ * "state" is the state array which is to be extracted from the pr'th
+ * proto. "pr" is both the number of the proto we are extracting from
+ * and an index into the save area where we can find the proto's complete
+ * state table. Each entry in "state" which differs from the corresponding
+ * entry of "pr" will appear in "ext".
+ *
+ * Entries which are the same in both "state" and "pr" will be marked
+ * as transitions to "SAME_TRANS" in "ext". The total number of differences
+ * between "state" and "pr" is returned as function value. Note that this
+ * number is "numecs" minus the number of "SAME_TRANS" entries in "ext".
+ */
+
+int tbldiff( state, pr, ext )
+int state[], pr, ext[];
+ {
+ register int i, *sp = state, *ep = ext, *protp;
+ register int numdiff = 0;
+
+ protp = &protsave[numecs * (pr - 1)];
+
+ for ( i = numecs; i > 0; --i )
+ {
+ if ( *++protp == *++sp )
+ *++ep = SAME_TRANS;
+ else
+ {
+ *++ep = *sp;
+ ++numdiff;
+ }
+ }
+
+ return numdiff;
+ }
diff --git a/usr.bin/lex/version.h b/usr.bin/lex/version.h
new file mode 100644
index 000000000000..633a31ef947e
--- /dev/null
+++ b/usr.bin/lex/version.h
@@ -0,0 +1 @@
+#define FLEX_VERSION "2.4.7"
diff --git a/usr.bin/lex/yylex.c b/usr.bin/lex/yylex.c
new file mode 100644
index 000000000000..563297a094b2
--- /dev/null
+++ b/usr.bin/lex/yylex.c
@@ -0,0 +1,199 @@
+/* yylex - scanner front-end for flex */
+
+/*-
+ * Copyright (c) 1990 The Regents of the University of California.
+ * All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Vern Paxson.
+ *
+ * The United States Government has rights in this work pursuant
+ * to contract no. DE-AC03-76SF00098 between the United States
+ * Department of Energy and the University of California.
+ *
+ * Redistribution and use in source and binary forms are permitted provided
+ * that: (1) source distributions retain this entire copyright notice and
+ * comment, and (2) distributions including binaries display the following
+ * acknowledgement: ``This product includes software developed by the
+ * University of California, Berkeley and its contributors'' in the
+ * documentation or other materials provided with the distribution and in
+ * all advertising materials mentioning features or use of this software.
+ * Neither the name of the University nor the names of its contributors may
+ * be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+/* $Header: /home/daffy/u0/vern/flex/RCS/yylex.c,v 2.10 93/09/16 20:31:48 vern Exp $ */
+
+#include <ctype.h>
+#include "flexdef.h"
+#include "parse.h"
+
+
+/* yylex - scan for a regular expression token */
+
+int yylex()
+ {
+ int toktype;
+ static int beglin = false;
+
+ if ( eofseen )
+ toktype = EOF;
+ else
+ toktype = flexscan();
+
+ if ( toktype == EOF || toktype == 0 )
+ {
+ eofseen = 1;
+
+ if ( sectnum == 1 )
+ {
+ synerr( "premature EOF" );
+ sectnum = 2;
+ toktype = SECTEND;
+ }
+
+ else
+ toktype = 0;
+ }
+
+ if ( trace )
+ {
+ if ( beglin )
+ {
+ fprintf( stderr, "%d\t", num_rules + 1 );
+ beglin = 0;
+ }
+
+ switch ( toktype )
+ {
+ case '<':
+ case '>':
+ case '^':
+ case '$':
+ case '"':
+ case '[':
+ case ']':
+ case '{':
+ case '}':
+ case '|':
+ case '(':
+ case ')':
+ case '-':
+ case '/':
+ case '\\':
+ case '?':
+ case '.':
+ case '*':
+ case '+':
+ case ',':
+ (void) putc( toktype, stderr );
+ break;
+
+ case '\n':
+ (void) putc( '\n', stderr );
+
+ if ( sectnum == 2 )
+ beglin = 1;
+
+ break;
+
+ case SCDECL:
+ fputs( "%s", stderr );
+ break;
+
+ case XSCDECL:
+ fputs( "%x", stderr );
+ break;
+
+ case WHITESPACE:
+ (void) putc( ' ', stderr );
+ break;
+
+ case SECTEND:
+ fputs( "%%\n", stderr );
+
+ /* We set beglin to be true so we'll start
+ * writing out numbers as we echo rules.
+ * flexscan() has already assigned sectnum.
+ */
+
+ if ( sectnum == 2 )
+ beglin = 1;
+
+ break;
+
+ case NAME:
+ fprintf( stderr, "'%s'", nmstr );
+ break;
+
+ case CHAR:
+ switch ( yylval )
+ {
+ case '<':
+ case '>':
+ case '^':
+ case '$':
+ case '"':
+ case '[':
+ case ']':
+ case '{':
+ case '}':
+ case '|':
+ case '(':
+ case ')':
+ case '-':
+ case '/':
+ case '\\':
+ case '?':
+ case '.':
+ case '*':
+ case '+':
+ case ',':
+ fprintf( stderr, "\\%c",
+ yylval );
+ break;
+
+ default:
+ if ( ! isascii( yylval ) ||
+ ! isprint( yylval ) )
+ fprintf( stderr,
+ "\\%.3o",
+ (unsigned int) yylval );
+ else
+ (void) putc( yylval,
+ stderr );
+ break;
+ }
+
+ break;
+
+ case NUMBER:
+ fprintf( stderr, "%d", yylval );
+ break;
+
+ case PREVCCL:
+ fprintf( stderr, "[%d]", yylval );
+ break;
+
+ case EOF_OP:
+ fprintf( stderr, "<<EOF>>" );
+ break;
+
+ case 0:
+ fprintf( stderr, "End Marker" );
+ break;
+
+ default:
+ fprintf( stderr,
+ "*Something Weird* - tok: %d val: %d\n",
+ toktype, yylval );
+ break;
+ }
+ }
+
+ return toktype;
+ }