rpcgen: Perform shell-style word expansion on RPCGEN_CPP

Up until recently, CPP has been a list of space-separated words, with no
quotes, backslashes or other characters with special meaning to a shell.
However, as of 8fad2cda93c7, (escaped) quotes appear in CPP, and the
rudimentary parser in rpcgen is insufficient, since it will leave the
escaped quotes as escaped rather than performing one level of expansion
as would be done by a shell (whether in a script or a Makefile).

Rather than hack around this in all the places RPCGEN_CPP gets set,
implement proper expansion inside rpcgen. Note that this only deals with
a subset of shell syntax, since we don't handle any of:

  | & ; < > ( ) $ ` * ? [ # ˜ = %

having special meaning (with the exception of how a backslash behaves
inside double quotes, where \$ means a literal $ inside double quotes
but \a means a literal \a), instead using their literal value, but those
are all reasonable restrictions, and can be worked around by avoiding
their use; what's important is that we get the quoting and splitting
right.

This fixes -Winvalid-pp-token spew during build${libcompat}.

Reviewed by:	brooks
Fixes:		8fad2cda93c7 ("bsd.compat.mk: Provide new CPP and sub-make variables")
Differential Revision:	https://reviews.freebsd.org/D41013

1 files changed, 103 insertions, 8 deletions

diff --git a/usr.bin/rpcgen/rpc_main.c b/usr.bin/rpcgen/rpc_main.c
index ba9eda676b39..6576d6cfb919 100644
--- a/usr.bin/rpcgen/rpc_main.c
+++ b/usr.bin/rpcgen/rpc_main.c
@@ -45,6 +45,7 @@ __FBSDID("$FreeBSD$");
 
 #include <err.h>
 #include <ctype.h>
+#include <stdbool.h>
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
@@ -270,20 +271,114 @@ add_warning(void)
 static void
 prepend_cpp(void)
 {
-	int idx = 0;
-	const char *var;
-	char *dupvar, *s, *t;
+	int idx = 0, quoted;
+	const char *var, *s;
+	char *dupvar, *t, *word;
 
 	if (CPP != NULL)
 		insarg(idx++, CPP);
 	else if ((var = getenv("RPCGEN_CPP")) == NULL)
 		insarg(idx++, "/usr/bin/cpp");
 	else {
-		/* Parse command line in a rudimentary way */
-		dupvar = xstrdup(var);
-		for (s = dupvar; (t = strsep(&s, " \t")) != NULL; ) {
-			if (t[0])
-				insarg(idx++, t);
+		/*
+		 * Parse command line like a shell (but only handle whitespace,
+		 * quotes and backslash).
+		 */
+		dupvar = malloc(strlen(var) + 1);
+		quoted = 0;
+		word = NULL;
+		for (s = var, t = dupvar; *s; ++s) {
+			switch (quoted) {
+			/* Unquoted */
+			case 0:
+				switch (*s) {
+				case ' ':
+				case '\t':
+				case '\n':
+					if (word != NULL) {
+						*t++ = '\0';
+						insarg(idx++, word);
+						word = NULL;
+					}
+					break;
+				case '\'':
+					if (word == NULL)
+						word = t;
+					quoted = 1;
+					break;
+				case '"':
+					if (word == NULL)
+						word = t;
+					quoted = 2;
+					break;
+				case '\\':
+					switch (*(s + 1)) {
+					case '\0':
+						break;
+					case '\n':
+						++s;
+						continue;
+					default:
+						++s;
+						break;
+					}
+					/* FALLTHROUGH */
+				default:
+					if (word == NULL)
+						word = t;
+					*t++ = *s;
+					break;
+				}
+				break;
+
+			/* Single-quoted */
+			case 1:
+				switch (*s) {
+				case '\'':
+					quoted = 0;
+					break;
+				default:
+					*t++ = *s;
+					break;
+				}
+				break;
+
+			/* Double-quoted */
+			case 2:
+				switch (*s) {
+				case '"':
+					quoted = 0;
+					break;
+				case '\\':
+					switch (*(s + 1)) {
+					case '\0':
+						break;
+					case '$':
+					case '`':
+					case '"':
+					case '\\':
+						++s;
+						break;
+					case '\n':
+						++s;
+						continue;
+					default:
+						break;
+					}
+					/* FALLTHROUGH */
+				default:
+					*t++ = *s;
+					break;
+				}
+				break;
+			}
+		}
+		if (quoted)
+			errx(1, "RPCGEN_CPP: unterminated %c",
+			    quoted == 1 ? '\'' : '"');
+		if (word != NULL) {
+			*t++ = '\0';
+			insarg(idx++, word);
 		}
 		free(dupvar);
 	}