From c1b97d6d896b1f22fdf5d28471ef7859ec840a57 Mon Sep 17 00:00:00 2001

From: Andreas Schwab <schwab@redhat.com>

Date: Wed, 1 Sep 2010 17:26:15 +0200

Subject: [PATCH] Fix handling of collating symbols in regexps

[BZ #11561]

* posix/regcomp.c (parse_bracket_exp): When looking up collating

elements compare against the byte sequence of it, not its name.

---

 ChangeLog       |    4 +++

 posix/regcomp.c |   72 ++++++++++++++++++++----------------------------------

 2 files changed, 31 insertions(+), 45 deletions(-)

--- glibc-2.17-c758a686/posix/regcomp.c

+++ glibc-2.17-c758a686/posix/regcomp.c

@@ -2772,40 +2772,29 @@ 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.

@@ -2814,8 +2803,7 @@ 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)

 	{

@@ -2843,7 +2831,7 @@ 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];

@@ -2861,7 +2849,7 @@ 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.  */

@@ -2883,11 +2871,8 @@ 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;

@@ -2966,25 +2951,22 @@ 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.  */