Add collation version support to querylocale(3).

Provide a way to ask for an opaque version string for a locale_t, so
that potential changes in sort order can be detected.  Similar to
ICU's ucol_getVersion() and Windows' GetNLSVersionEx(), this API is
intended to allow databases to detect when text order-based indexes
might need to be rebuilt.

The CLDR version is extracted from CLDR source data by the Makefile
under tools/tools/locale, written into the machine-generated Makefile
under shared/colldef, passed to localedef -V, and then written into
LC_COLLATE file headers.  The initial version is 34.0.
tools/tools/locale was recently updated to pull down 35.0, but the
output hasn't been committed under share/colldef yet, so that will
provide the first observable change when it happens.  Other versioning
schemes are possible in future, because the format is unspecified.

Reviewed by:	bapt, 0mp, kib, yuripv (albeit a long time ago)
Differential Revision:	https://reviews.freebsd.org/D17166

5 files changed, 36 insertions, 6 deletions

diff --git a/usr.bin/localedef/bootstrap/bootstrap_xlocale_private.h b/usr.bin/localedef/bootstrap/bootstrap_xlocale_private.h
index 243139ff09b8..48203aaa0f61 100644
--- a/usr.bin/localedef/bootstrap/bootstrap_xlocale_private.h
+++ b/usr.bin/localedef/bootstrap/bootstrap_xlocale_private.h
@@ -51,4 +51,7 @@ struct localedef_bootstrap_xlocale_component {
 	char unused;
 };
 
+/* This must agree with the definition in xlocale_private.h. */
+#define XLOCALE_DEF_VERSION_LEN 12
+
 #endif /* _LOCALDEF_BOOTSTRAP_XLOCALE_PRIVATE_H */
diff --git a/usr.bin/localedef/collate.c b/usr.bin/localedef/collate.c
index 3e3c7539dd8d..0bed283b6aab 100644
--- a/usr.bin/localedef/collate.c
+++ b/usr.bin/localedef/collate.c
@@ -1119,7 +1119,8 @@ dump_collate(void)
 	collelem_t		*ce;
 	collchar_t		*cc;
 	subst_t			*sb;
-	char			vers[COLLATE_STR_LEN];
+	char			fmt_version[COLLATE_FMT_VERSION_LEN];
+	char			def_version[XLOCALE_DEF_VERSION_LEN];
 	collate_char_t		chars[UCHAR_MAX + 1];
 	collate_large_t		*large;
 	collate_subst_t		*subst[COLL_WEIGHTS_MAX];
@@ -1160,8 +1161,11 @@ dump_collate(void)
 	}
 
 	(void) memset(&chars, 0, sizeof (chars));
-	(void) memset(vers, 0, COLLATE_STR_LEN);
-	(void) strlcpy(vers, COLLATE_VERSION, sizeof (vers));
+	(void) memset(fmt_version, 0, COLLATE_FMT_VERSION_LEN);
+	(void) strlcpy(fmt_version, COLLATE_FMT_VERSION, sizeof (fmt_version));
+	(void) memset(def_version, 0, XLOCALE_DEF_VERSION_LEN);
+	if (version)
+		(void) strlcpy(def_version, version, sizeof (def_version));
 
 	/*
 	 * We need to make sure we arrange for the UNDEFINED field
@@ -1301,7 +1305,8 @@ dump_collate(void)
 	collinfo.chain_count = htote(chain_count);
 	collinfo.large_count = htote(large_count);
 
-	if ((wr_category(vers, COLLATE_STR_LEN, f) < 0) ||
+	if ((wr_category(fmt_version, COLLATE_FMT_VERSION_LEN, f) < 0) ||
+	    (wr_category(def_version, XLOCALE_DEF_VERSION_LEN, f) < 0) ||
 	    (wr_category(&collinfo, sizeof (collinfo), f) < 0) ||
 	    (wr_category(&chars, sizeof (chars), f) < 0)) {
 		return;
diff --git a/usr.bin/localedef/localedef.1 b/usr.bin/localedef/localedef.1
index 126193caebb3..f67672f9a0c6 100644
--- a/usr.bin/localedef/localedef.1
+++ b/usr.bin/localedef/localedef.1
@@ -33,7 +33,7 @@
 .\"
 .\" $FreeBSD$
 .\"
-.Dd October 18, 2018
+.Dd November 8, 2020
 .Dt LOCALEDEF 1
 .Os
 .Sh NAME
@@ -135,6 +135,14 @@ If not supplied, then default screen widths will be assumed, which will
 generally not account for East Asian encodings requiring more than a single
 character cell to display, nor for combining or accent marks that occupy
 no additional screen width.
+.It Fl V Ar version
+Specifies a version string describing the version of the locale definition.
+This string can be retrieved with
+.Xr querylocale 3 ,
+and is intended to allow applications to detect locale definition changes.
+Currently it is stored only for the
+.Sy LC_COLLATE
+category.
 .El
 .Pp
 The following operands are required:
@@ -198,6 +206,7 @@ If an error is detected, no permanent output will be created.
 .Xr locale 1 ,
 .Xr iconv_open 3 ,
 .Xr nl_langinfo 3 ,
+.Xr querylocale 3 ,
 .Xr strftime 3 ,
 .Xr environ 7
 .Sh WARNINGS
diff --git a/usr.bin/localedef/localedef.c b/usr.bin/localedef/localedef.c
index 40b4ee58367f..390ebf8784ef 100644
--- a/usr.bin/localedef/localedef.c
+++ b/usr.bin/localedef/localedef.c
@@ -48,6 +48,7 @@ __FBSDID("$FreeBSD$");
 #include <limits.h>
 #include <locale.h>
 #include <dirent.h>
+#include "collate.h"
 #include "localedef.h"
 #include "parser.h"
 
@@ -62,6 +63,7 @@ int undefok = 0;
 int warnok = 0;
 static char *locname = NULL;
 static char locpath[PATH_MAX];
+char *version = NULL;
 
 const char *
 category_name(void)
@@ -253,6 +255,7 @@ usage(void)
 	(void) fprintf(stderr, "  -u encoding : assume encoding\n");
 	(void) fprintf(stderr, "  -w widths   : use screen widths file\n");
 	(void) fprintf(stderr, "  -i locsrc   : source file for locale\n");
+	(void) fprintf(stderr, "  -V version  : version string for locale\n");
 	exit(4);
 }
 
@@ -279,7 +282,7 @@ main(int argc, char **argv)
 
 	(void) setlocale(LC_ALL, "");
 
-	while ((c = getopt(argc, argv, "blw:i:cf:u:vUD")) != -1) {
+	while ((c = getopt(argc, argv, "blw:i:cf:u:vUDV:")) != -1) {
 		switch (c) {
 		case 'D':
 			bsd = 1;
@@ -314,6 +317,9 @@ main(int argc, char **argv)
 		case '?':
 			usage();
 			break;
+		case 'V':
+			version = optarg;
+			break;
 		}
 	}
 
@@ -325,6 +331,11 @@ main(int argc, char **argv)
 		(void) printf("Processing locale %s.\n", locname);
 	}
 
+	if (version && strlen(version) >= XLOCALE_DEF_VERSION_LEN) {
+		(void) fprintf(stderr, "Version string too long.\n");
+		exit(1);
+	}
+
 	if (cfname) {
 		if (verbose)
 			(void) printf("Loading charmap %s.\n", cfname);
diff --git a/usr.bin/localedef/localedef.h b/usr.bin/localedef/localedef.h
index b8c831f1d38d..ba95e27701d8 100644
--- a/usr.bin/localedef/localedef.h
+++ b/usr.bin/localedef/localedef.h
@@ -55,6 +55,8 @@ extern int undefok;	/* mostly ignore undefined symbols */
 extern int warnok;
 extern int warnings;
 
+extern char *version;
+
 int yylex(void);
 void yyerror(const char *);
 _Noreturn void errf(const char *, ...) __printflike(1, 2);