Skip site navigation (1)Skip section navigation (2) 
Date:      Fri, 23 Oct 2015 23:24:03 +0000 (UTC)
From:      Baptiste Daroussin <bapt@FreeBSD.org>
To:        src-committers@freebsd.org, svn-src-projects@freebsd.org
Subject:   svn commit: r289860 - in projects/collation/lib/libc: locale string
Message-ID:  <201510232324.t9NNO3uL056494@repo.freebsd.org>
next in thread | raw e-mail | index | archive | help 
Author: bapt
Date: Fri Oct 23 23:24:03 2015
New Revision: 289860
URL: https://svnweb.freebsd.org/changeset/base/289860

Log:
  collate: Fix expansion substitions (broken upstream too)
  
  Through testing, the user noted that some Cyrillic characters were not
  sorting correctly, and this was confirmed.
  
  After extensive testing and review, the localedef tool was eliminated
  as the culprit.  The sustitutions were encoded correctly in LC_COLLATE.
  
  The error was mainly in wcscoll where character expansions were
  mishandled.  The main directive pass routines had to be written to
  go back for a new collation value when the "state" variable was set.
  Before pointers were being advanced, the second lookup was gettting
  applied to the wrong character, etc.
  
  The "eat expansion codes" section on collate.c also had a bug.  Later
  own, the "state" variable logic was changed to only set if next
  code was greater than zero (rather than >= 0).
  
  Some additional cleanups got captured from previous work:
  1) The previous commit moved the binary search comment from the
     correct location to a wrong location because it's wrong upstream
     in Illumos.  The comment has little value so I just removed it.
  2) Don't check if pointers are null before freeing, this is
     redundant as free() handles null pointers.
  3) The two binary search trees were standardized wrt initialization
  4) On the binary search trees, a negative "high" exits rather than
     checking the table count again.
  
  Submitted by:	marino
  Obtained from:	DragonflyBSD

Modified:
  projects/collation/lib/libc/locale/collate.c
  projects/collation/lib/libc/string/wcscoll.c

Modified: projects/collation/lib/libc/locale/collate.c
==============================================================================
--- projects/collation/lib/libc/locale/collate.c	Fri Oct 23 23:07:45 2015	(r289859)
+++ projects/collation/lib/libc/locale/collate.c	Fri Oct 23 23:24:03 2015	(r289860)
@@ -202,7 +202,6 @@ __collate_load_tables_l(const char *enco
 		table->large_pri_table = NULL;
 
 	table->__collate_load_error = 0;
-
 	return (_LDP_LOADED);
 }
 
@@ -226,27 +225,18 @@ substsearch(struct xlocale_collate *tabl
 	return (p->pri);
 }
 
-/*
- * Note: for performance reasons, we have expanded bsearch here.  This avoids
- * function call overhead with each comparison.
- */
-
 static collate_chain_t *
 chainsearch(struct xlocale_collate *table, const wchar_t *key, int *len)
 {
-	int low;
-	int high;
+	int low = 0;
+	int high = table->info->chain_count - 1;;
 	int next, compar, l;
 	collate_chain_t *p;
-	collate_chain_t *tab;
+	collate_chain_t *tab = table->chain_pri_table;
 
-	if (table->info->chain_count == 0)
+	if (high < 0)
 		return (NULL);
 
-	low = 0;
-	high = table->info->chain_count - 1;
-	tab = table->chain_pri_table;
-
 	while (low <= high) {
 		next = (low + high) / 2;
 		p = tab + next;
@@ -276,7 +266,7 @@ largesearch(struct xlocale_collate *tabl
 	collate_large_t *p;
 	collate_large_t *tab = table->large_pri_table;
 
-	if (table->info->large_count == 0)
+	if (high < 0)
 		return (NULL);
 
 	while (low <= high) {
@@ -320,7 +310,10 @@ _collate_lookup(struct xlocale_collate *
 	if ((sptr = *state) != NULL) {
 		*pri = *sptr;
 		sptr++;
-		*state = *sptr ? sptr : NULL;
+		if ((sptr == *state) || (sptr == NULL))
+			*state = NULL;
+		else
+			*state = sptr;
 		*len = 0;
 		return;
 	}
@@ -381,7 +374,7 @@ _collate_lookup(struct xlocale_collate *
 	 * code ensures this for us.
 	 */
 	if ((sptr = substsearch(table, *pri, which)) != NULL) {
-		if ((*pri = *sptr) != 0) {
+		if ((*pri = *sptr) > 0) {
 			sptr++;
 			*state = *sptr ? sptr : NULL;
 		}

Modified: projects/collation/lib/libc/string/wcscoll.c
==============================================================================
--- projects/collation/lib/libc/string/wcscoll.c	Fri Oct 23 23:07:45 2015	(r289859)
+++ projects/collation/lib/libc/string/wcscoll.c	Fri Oct 23 23:24:03 2015	(r289860)
@@ -77,6 +77,7 @@ wcscoll_l(const wchar_t *ws1, const wcha
 		const int32_t *st2 = NULL;
 		const wchar_t	*w1 = ws1;
 		const wchar_t	*w2 = ws2;
+		int check1, check2;
 
 		/* special pass for UNDEFINED */
 		if (pass == table->info->directive_count) {
@@ -110,25 +111,36 @@ wcscoll_l(const wchar_t *ws1, const wcha
 		}
 
 		if (direc & DIRECTIVE_POSITION) {
-			while ((*w1 || st1) && (*w2 || st2)) {
+			while (*w1 && *w2) {
 				pri1 = pri2 = 0;
-				_collate_lookup(table, w1, &len1, &pri1, pass,
-				    &st1);
-				if (pri1 <= 0) {
-					if (pri1 < 0) {
-						errno = EINVAL;
-						goto fail;
+				check1 = check2 = 1;
+				while ((pri1 == pri2) && (check1 || check2)) {
+					if (check1) {
+						_collate_lookup(table, w1, &len1,
+						    &pri1, pass, &st1);
+						if (pri1 < 0) {
+							errno = EINVAL;
+							goto fail;
+						}
+						if (!pri1) {
+							pri1 = COLLATE_MAX_PRIORITY;
+							st1 = NULL;
+						}
+						check1 = (st1 != NULL);
 					}
-					pri1 = COLLATE_MAX_PRIORITY;
-				}
-				_collate_lookup(table, w2, &len2, &pri2, pass,
-				    &st2);
-				if (pri2 <= 0) {
-					if (pri2 < 0) {
-						errno = EINVAL;
-						goto fail;
+					if (check2) {
+						_collate_lookup(table, w2, &len2,
+						    &pri2, pass, &st2);
+						if (pri2 < 0) {
+							errno = EINVAL;
+							goto fail;
+						}
+						if (!pri2) {
+							pri2 = COLLATE_MAX_PRIORITY;
+							st2 = NULL;
+						}
+						check2 = (st2 != NULL);
 					}
-					pri2 = COLLATE_MAX_PRIORITY;
 				}
 				if (pri1 != pri2) {
 					ret = pri1 - pri2;
@@ -138,29 +150,38 @@ wcscoll_l(const wchar_t *ws1, const wcha
 				w2 += len2;
 			}
 		} else {
-			while ((*w1 || st1) && (*w2 || st2)) {
+			while (*w1 && *w2) {
 				pri1 = pri2 = 0;
-				while (*w1) {
-					_collate_lookup(table, w1, &len1,
-					    &pri1, pass, &st1);
-					if (pri1 > 0)
-						break;
-					if (pri1 < 0) {
-						errno = EINVAL;
-						goto fail;
+				check1 = check2 = 1;
+				while ((pri1 == pri2) && (check1 || check2)) {
+					while (check1 && *w1) {
+						_collate_lookup(table, w1,
+						    &len1, &pri1, pass, &st1);
+						if (pri1 > 0)
+							break;
+						if (pri1 < 0) {
+							errno = EINVAL;
+							goto fail;
+						}
+						st1 = NULL;
+						w1 += 1;
 					}
-					w1 += len1;
-				}
-				while (*w2) {
-					_collate_lookup(table, w2, &len2,
-					    &pri2, pass, &st2);
-					if (pri2 > 0)
-						break;
-					if (pri2 < 0) {
-						errno = EINVAL;
-						goto fail;
+					check1 = (st1 != NULL);
+					while (check2 && *w2) {
+						_collate_lookup(table, w2,
+						    &len2, &pri2, pass, &st2);
+						if (pri2 > 0)
+							break;
+						if (pri2 < 0) {
+							errno = EINVAL;
+							goto fail;
+						}
+						st2 = NULL;
+						w2 += 1;
 					}
-					w2 += len2;
+					check2 = (st2 != NULL);
+					if (!pri1 || !pri2)
+						break;
 				}
 				if (!pri1 || !pri2)
 					break;
@@ -185,10 +206,8 @@ wcscoll_l(const wchar_t *ws1, const wcha
 	ret = 0;
 
 end:
-	if (tr1)
-		free(tr1);
-	if (tr2)
-		free(tr2);
+	free(tr1);
+	free(tr2);
 
 	return (ret);

Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201510232324.t9NNO3uL056494>