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, 57 insertions, 16 deletions

diff --git a/lib/libc/locale/collate.c b/lib/libc/locale/collate.c
index c67f7bcd646e..c992d2299ab7 100644
--- a/lib/libc/locale/collate.c
+++ b/lib/libc/locale/collate.c
@@ -140,7 +140,9 @@ __collate_load_tables_l(const char *encoding, struct xlocale_collate *table)
 		(void) _close(fd);
 		return (_LDP_ERROR);
 	}
-	if (sbuf.st_size < (COLLATE_STR_LEN + sizeof (info))) {
+	if (sbuf.st_size < (COLLATE_FMT_VERSION_LEN +
+			    XLOCALE_DEF_VERSION_LEN +
+			    sizeof (info))) {
 		(void) _close(fd);
 		errno = EINVAL;
 		return (_LDP_ERROR);
@@ -151,12 +153,14 @@ __collate_load_tables_l(const char *encoding, struct xlocale_collate *table)
 		return (_LDP_ERROR);
 	}
 
-	if (strncmp(TMP, COLLATE_VERSION, COLLATE_STR_LEN) != 0) {
+	if (strncmp(TMP, COLLATE_FMT_VERSION, COLLATE_FMT_VERSION_LEN) != 0) {
 		(void) munmap(map, sbuf.st_size);
 		errno = EINVAL;
 		return (_LDP_ERROR);
 	}
-	TMP += COLLATE_STR_LEN;
+	TMP += COLLATE_FMT_VERSION_LEN;
+	strlcat(table->header.version, TMP, sizeof (table->header.version));
+	TMP += XLOCALE_DEF_VERSION_LEN;
 
 	info = (void *)TMP;
 	TMP += sizeof (*info);
diff --git a/lib/libc/locale/collate.h b/lib/libc/locale/collate.h
index 4abb1f936ae2..9983cdbd969d 100644
--- a/lib/libc/locale/collate.h
+++ b/lib/libc/locale/collate.h
@@ -53,7 +53,9 @@
 #endif
 
 #define	COLLATE_STR_LEN		24		/* should be 64-bit multiple */
-#define	COLLATE_VERSION		"BSD 1.0\n"
+
+#define	COLLATE_FMT_VERSION_LEN	12
+#define	COLLATE_FMT_VERSION	"BSD 1.0\n"
 
 #define	COLLATE_MAX_PRIORITY	(0x7fffffff)	/* max signed value */
 #define	COLLATE_SUBST_PRIORITY	(0x40000000)	/* bit indicates subst table */
@@ -69,7 +71,8 @@
 /*
  * The collate file format is as follows:
  *
- * char		version[COLLATE_STR_LEN];	// must be COLLATE_VERSION
+ * char	fmt_version[COLLATE_FMT_VERSION_LEN];	// must be COLLATE_FMT_VERSION
+ * char	def_version[XLOCALE_DEF_VERSION_LEN];	// NUL-terminated, may be empty
  * collate_info_t	info;			// see below, includes padding
  * collate_char_pri_t	char_data[256];		// 8 bit char values
  * collate_subst_t	subst[*];		// 0 or more substitutions
diff --git a/lib/libc/locale/querylocale.3 b/lib/libc/locale/querylocale.3
index d1bb688ed907..ecafee49a712 100644
--- a/lib/libc/locale/querylocale.3
+++ b/lib/libc/locale/querylocale.3
@@ -27,12 +27,12 @@
 .\"
 .\" $FreeBSD$
 .\"
-.Dd May 3, 2013
+.Dd November 8, 2020
 .Dt QUERYLOCALE 3
 .Os
 .Sh NAME
 .Nm querylocale
-.Nd Look up the locale name for a specified category
+.Nd Look up the locale name or version for a specified category
 .Sh LIBRARY
 .Lb libc
 .Sh SYNOPSIS
@@ -40,11 +40,22 @@
 .Ft const char *
 .Fn querylocale "int mask" "locale_t locale"
 .Sh DESCRIPTION
-Returns the name of the locale for the category specified by
+Returns the name or version of the locale for the category specified by
 .Fa mask .
-This possible values for the mask are the same as those in
-.Xr newlocale 3 .
-If more than one bit in the mask is set, the returned value is undefined.
+The possible values for the mask are the same as those in
+.Xr newlocale 3 ,
+when requesting the locale name.
+Specify the bitwise OR of
+.Fa LC_VERSION_MASK
+and another mask value to request a version string.
+Version strings can be compared to detect changes to the locale's definition.
+The structure of the version string is unspecified.
+Currently, version information is only available for
+.Fa LC_COLLATE_MASK ,
+and an empty string is returned for other categories.
+If more than one bit in the mask is set, not counting
+.Fa LC_VERSION_MASK ,
+the returned value is undefined.
 .Sh SEE ALSO
 .Xr duplocale 3 ,
 .Xr freelocale 3 ,
@@ -52,3 +63,12 @@ If more than one bit in the mask is set, the returned value is undefined.
 .Xr newlocale 3 ,
 .Xr uselocale 3 ,
 .Xr xlocale 3
+.Sh HISTORY
+The
+.Fn querylocale
+function first appeared in
+.Fx 9.1 ,
+and is based on the function of the same name in Darwin.
+.Fa LC_VERSION_MASK
+first appeared in
+.Fx 13.0 .
diff --git a/lib/libc/locale/xlocale.c b/lib/libc/locale/xlocale.c
index 465172fe24eb..fb674f86bbff 100644
--- a/lib/libc/locale/xlocale.c
+++ b/lib/libc/locale/xlocale.c
@@ -231,6 +231,8 @@ static int dupcomponent(int type, locale_t base, locale_t new)
 		if (new->components[type]) {
 			strncpy(new->components[type]->locale, src->locale,
 			    ENCODING_LEN);
+			strncpy(new->components[type]->version, src->version,
+			    XLOCALE_DEF_VERSION_LEN);
 		}
 	} else if (base->components[type]) {
 		new->components[type] = xlocale_retain(base->components[type]);
@@ -346,17 +348,24 @@ freelocale(locale_t loc)
 }
 
 /*
- * Returns the name of the locale for a particular component of a locale_t.
+ * Returns the name or version of the locale for a particular component of a
+ * locale_t.
  */
 const char *querylocale(int mask, locale_t loc)
 {
-	int type = ffs(mask) - 1;
+	int type = ffs(mask & ~LC_VERSION_MASK) - 1;
 	FIX_LOCALE(loc);
 	if (type >= XLC_LAST)
 		return (NULL);
-	if (loc->components[type])
-		return (loc->components[type]->locale);
-	return ("C");
+	if (mask & LC_VERSION_MASK) {
+		if (loc->components[type])
+			return (loc->components[type]->version);
+		return ("");
+	} else {
+		if (loc->components[type])
+			return (loc->components[type]->locale);
+		return ("C");
+	}
 }
 
 /*
diff --git a/lib/libc/locale/xlocale_private.h b/lib/libc/locale/xlocale_private.h
index fc04c9dd43a3..391e375bc03d 100644
--- a/lib/libc/locale/xlocale_private.h
+++ b/lib/libc/locale/xlocale_private.h
@@ -91,6 +91,9 @@ struct xlocale_refcounted {
 	/** Function used to destroy this component, if one is required*/
 	void(*destructor)(void*);
 };
+
+#define XLOCALE_DEF_VERSION_LEN 12
+
 /**
  * Header for a locale component.  All locale components must begin with this
  * header.
@@ -99,6 +102,8 @@ struct xlocale_component {
 	struct xlocale_refcounted header;
 	/** Name of the locale used for this component. */
 	char locale[ENCODING_LEN+1];
+	/** Version of the definition for this component. */
+	char version[XLOCALE_DEF_VERSION_LEN];
 };
 
 /**