[PATCH] Fix handling of collating symbols in regexps

[Andreas Schwab <schwab at redhat dot com>]

2010-09-01  Andreas Schwab  <schwab@redhat.com>

	[BZ #11561]
	* posix/regcomp.c (parse_bracket_exp): When looking up a
	collating element compare against the associated byte sequence,
	not its name.
---
 posix/regcomp.c |   72 ++++++++++++++++++++----------------------------------
 1 files changed, 27 insertions(+), 45 deletions(-)

diff --git a/posix/regcomp.c b/posix/regcomp.c
index 03ab123..31bd155 100644
--- a/posix/regcomp.c
+++ b/posix/regcomp.c
@@ -2736,40 +2736,29 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
 
   /* Local function for parse_bracket_exp used in _LIBC environement.
      Seek the collating symbol entry correspondings to NAME.
-     Return the index of the symbol in the SYMB_TABLE.  */
+     Return the index of the symbol in the SYMB_TABLE,
+     or -1 if not found.  */
 
   auto inline int32_t
   __attribute ((always_inline))
-  seek_collating_symbol_entry (name, name_len)
-	 const unsigned char *name;
-	 size_t name_len;
+  seek_collating_symbol_entry (const unsigned char *name, size_t name_len)
     {
-      int32_t hash = elem_hash ((const char *) name, name_len);
-      int32_t elem = hash % table_size;
-      if (symb_table[2 * elem] != 0)
-	{
-	  int32_t second = hash % (table_size - 2) + 1;
-
-	  do
-	    {
-	      /* First compare the hashing value.  */
-	      if (symb_table[2 * elem] == hash
-		  /* Compare the length of the name.  */
-		  && name_len == extra[symb_table[2 * elem + 1]]
-		  /* Compare the name.  */
-		  && memcmp (name, &extra[symb_table[2 * elem + 1] + 1],
-			     name_len) == 0)
-		{
-		  /* Yep, this is the entry.  */
-		  break;
-		}
+      int32_t elem;
 
-	      /* Next entry.  */
-	      elem += second;
-	    }
-	  while (symb_table[2 * elem] != 0);
-	}
-      return elem;
+      for (elem = 0; elem < table_size; elem++)
+	if (symb_table[2 * elem] != 0)
+	  {
+	    int32_t idx = symb_table[2 * elem + 1];
+	    /* Skip the name of collating element name.  */
+	    idx += 1 + extra[idx];
+	    if (/* Compare the length of the name.  */
+		name_len == extra[idx]
+		/* Compare the name.  */
+		&& memcmp (name, &extra[idx + 1], name_len) == 0)
+	      /* Yep, this is the entry.  */
+	      return elem;
+	  }
+      return -1;
     }
 
   /* Local function for parse_bracket_exp used in _LIBC environment.
@@ -2778,8 +2767,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
 
   auto inline unsigned int
   __attribute ((always_inline))
-  lookup_collation_sequence_value (br_elem)
-	 bracket_elem_t *br_elem;
+  lookup_collation_sequence_value (bracket_elem_t *br_elem)
     {
       if (br_elem->type == SB_CHAR)
 	{
@@ -2807,7 +2795,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
 	      int32_t elem, idx;
 	      elem = seek_collating_symbol_entry (br_elem->opr.name,
 						  sym_name_len);
-	      if (symb_table[2 * elem] != 0)
+	      if (elem != -1)
 		{
 		  /* We found the entry.  */
 		  idx = symb_table[2 * elem + 1];
@@ -2825,7 +2813,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
 		  /* Return the collation sequence value.  */
 		  return *(unsigned int *) (extra + idx);
 		}
-	      else if (symb_table[2 * elem] == 0 && sym_name_len == 1)
+	      else if (sym_name_len == 1)
 		{
 		  /* No valid character.  Match it as a single byte
 		     character.  */
@@ -2847,11 +2835,8 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
 
   auto inline reg_errcode_t
   __attribute ((always_inline))
-  build_range_exp (sbcset, mbcset, range_alloc, start_elem, end_elem)
-	 re_charset_t *mbcset;
-	 int *range_alloc;
-	 bitset_t sbcset;
-	 bracket_elem_t *start_elem, *end_elem;
+  build_range_exp (bitset_t sbcset, re_charset_t *mbcset, int *range_alloc,
+		   bracket_elem_t *start_elem, bracket_elem_t *end_elem)
     {
       unsigned int ch;
       uint32_t start_collseq;
@@ -2930,25 +2915,22 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
 
   auto inline reg_errcode_t
   __attribute ((always_inline))
-  build_collating_symbol (sbcset, mbcset, coll_sym_alloc, name)
-	 re_charset_t *mbcset;
-	 int *coll_sym_alloc;
-	 bitset_t sbcset;
-	 const unsigned char *name;
+  build_collating_symbol (bitset_t sbcset, re_charset_t *mbcset,
+			  int *coll_sym_alloc, const unsigned char *name)
     {
       int32_t elem, idx;
       size_t name_len = strlen ((const char *) name);
       if (nrules != 0)
 	{
 	  elem = seek_collating_symbol_entry (name, name_len);
-	  if (symb_table[2 * elem] != 0)
+	  if (elem != -1)
 	    {
 	      /* We found the entry.  */
 	      idx = symb_table[2 * elem + 1];
 	      /* Skip the name of collating element name.  */
 	      idx += 1 + extra[idx];
 	    }
-	  else if (symb_table[2 * elem] == 0 && name_len == 1)
+	  else if (name_len == 1)
 	    {
 	      /* No valid character, treat it as a normal
 		 character.  */
-- 
1.7.2.2


-- 
Andreas Schwab, schwab@redhat.com
GPG Key fingerprint = D4E8 DBE3 3813 BB5D FA84  5EC7 45C6 250E 6F00 984E
"And now for something completely different."