about summary refs log tree commit diff
path: root/locale/programs/ld-collate.c
diff options
context:
space:
mode:
authorCarlos O'Donell <carlos@systemhalted.org>2015-10-08 16:34:53 -0400
committerCarlos O'Donell <carlos@systemhalted.org>2015-10-08 16:57:11 -0400
commit6c84109cfa26f35c3dfed3acb97d347361bd5849 (patch)
tree0a1c08e31f8b7ee1ca4f75c21347323e18457a66 /locale/programs/ld-collate.c
parent666bb4dc55f5a93538d020024c34abad641f50ae (diff)
downloadglibc-6c84109cfa26f35c3dfed3acb97d347361bd5849.tar.gz
glibc-6c84109cfa26f35c3dfed3acb97d347361bd5849.tar.xz
glibc-6c84109cfa26f35c3dfed3acb97d347361bd5849.zip
strcoll: Remove incorrect STRDIFF-based optimization (Bug 18589).
The optimization introduced in commit
f13c2a8dff2329c6692a80176262ceaaf8a6f74e, causes regressions in
sorting for languages that have digraphs that change sort order, like
cs_CZ which sorts ch between h and i.

My analysis shows the fast-forwarding optimization in STRCOLL advances
through a digraph while possibly stopping in the middle which results
in a subsequent skipping of the digraph and incorrect sorting. The
optimization is incorrect as implemented and because of that I'm
removing it for 2.23, and I will also commit this fix for 2.22 where
it was originally introduced.

This patch reverts the optimization, introduces a new bug-strcoll2.c
regression test that tests both cs_CZ.UTF-8 and da_DK.ISO-8859-1 and
ensures they sort one digraph each correctly. The optimization can't be
applied without regressing this test.

Checked on x86_64, bug-strcoll2.c fails without this patch and passes
after. This will also get a fix on 2.22 which has the same bug.

(cherry picked from commit 87701a58e291bd7ac3b407d10a829dac52c9c16e)
Diffstat (limited to 'locale/programs/ld-collate.c')
-rw-r--r--locale/programs/ld-collate.c9
1 files changed, 0 insertions, 9 deletions
diff --git a/locale/programs/ld-collate.c b/locale/programs/ld-collate.c
index a39a94f2cc..dc0fe30a13 100644
--- a/locale/programs/ld-collate.c
+++ b/locale/programs/ld-collate.c
@@ -32,7 +32,6 @@
 #include "linereader.h"
 #include "locfile.h"
 #include "elem-hash.h"
-#include "../localeinfo.h"
 
 /* Uncomment the following line in the production version.  */
 /* #define NDEBUG 1 */
@@ -2131,8 +2130,6 @@ collate_output (struct localedef_t *locale, const struct charmap_t *charmap,
 	  /* The words have to be handled specially.  */
 	  if (idx == _NL_ITEM_INDEX (_NL_COLLATE_SYMB_HASH_SIZEMB))
 	    add_locale_uint32 (&file, 0);
-	  else if (idx == _NL_ITEM_INDEX (_NL_COLLATE_ENCODING_TYPE))
-	    add_locale_uint32 (&file, __cet_other);
 	  else
 	    add_locale_empty (&file);
 	}
@@ -2496,12 +2493,6 @@ collate_output (struct localedef_t *locale, const struct charmap_t *charmap,
   add_locale_raw_data (&file, collate->mbseqorder, 256);
   add_locale_collseq_table (&file, &collate->wcseqorder);
   add_locale_string (&file, charmap->code_set_name);
-  if (strcmp (charmap->code_set_name, "UTF-8") == 0)
-    add_locale_uint32 (&file, __cet_utf8);
-  else if (charmap->mb_cur_max == 1)
-    add_locale_uint32 (&file, __cet_8bit);
-  else
-    add_locale_uint32 (&file, __cet_other);
   write_locale_data (output_path, LC_COLLATE, "LC_COLLATE", &file);
 
   obstack_free (&weightpool, NULL);