[PATCH] regex: merge patches from libc

[Paul Eggert]

2013-02-26  Siddhesh Poyarekar  <address@hidden>
* lib/regex_internal.h (__attribute__): Rename from __attribute.
All uses changed.
(bitset_not, bitset_merge, bitset_mask, re_string_char_size_at)
(re_string_wchar_at, re_string_elem_size_at):
Mark function as possibly unused.

2013-02-12  Andreas Schwab  <address@hidden>  [BZ #11561]
* lib/regcomp.c (parse_bracket_exp) [_LIBC]: When looking up collating
elements compare against the byte sequence of it, not its name.
---
 ChangeLog            | 17 ++++++++++++-
 lib/regcomp.c        | 72 ++++++++++++++++++++--------------------------------
 lib/regex_internal.h | 20 +++++++--------
 3 files changed, 52 insertions(+), 57 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index b3c2bd4..4c9cf75 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,18 @@
+2013-02-25  Paul Eggert  <address@hidden>
+
+       regex: merge patches from libc
+
+       2013-02-26  Siddhesh Poyarekar  <address@hidden>
+       * lib/regex_internal.h (__attribute__): Rename from __attribute.
+       All uses changed.
+       (bitset_not, bitset_merge, bitset_mask, re_string_char_size_at)
+       (re_string_wchar_at, re_string_elem_size_at):
+       Mark function as possibly unused.
+
+       2013-02-12  Andreas Schwab  <address@hidden>  [BZ #11561]
+       * lib/regcomp.c (parse_bracket_exp) [_LIBC]: When looking up collating
+       elements compare against the byte sequence of it, not its name.
+
 2013-02-21  Paul Eggert  <address@hidden>
 
        putenv: port better to native Windows
@@ -249,7 +264,7 @@
 
 2013-01-29  Andreas Schwab  <address@hidden>
 
-       regex: fix buffer overrun in regexp matcher
+       regex: fix buffer overrun in regexp matcher [BZ #15078]
        * lib/regexec.c (extend_buffers): Add parameter min_len.
        (check_matching): Pass minimum needed length.
        (clean_state_log_if_needed): Likewise.
diff --git a/lib/regcomp.c b/lib/regcomp.c
index b236f36..a0db266 100644
--- a/lib/regcomp.c
+++ b/lib/regcomp.c
@@ -2835,40 +2835,29 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, 
re_token_t *token,
 
   /* Local function for parse_bracket_exp used in _LIBC environment.
      Seek the collating symbol entry corresponding 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.
@@ -2877,8 +2866,7 @@ 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)
        {
@@ -2906,7 +2894,7 @@ 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];
@@ -2924,7 +2912,7 @@ 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.  */
@@ -2946,11 +2934,8 @@ 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;
-        Idx *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;
@@ -3030,25 +3015,22 @@ 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;
-        Idx *coll_sym_alloc;
-        bitset_t sbcset;
-        const unsigned char *name;
+  build_collating_symbol (bitset_t sbcset, re_charset_t *mbcset,
+                         Idx *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.  */
diff --git a/lib/regex_internal.h b/lib/regex_internal.h
index fa93382..439444c 100644
--- a/lib/regex_internal.h
+++ b/lib/regex_internal.h
@@ -107,10 +107,8 @@
 # define attribute_hidden
 #endif /* not _LIBC */
 
-#if __GNUC__ >= 4 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 1)
-# define __attribute(arg) __attribute__ (arg)
-#else
-# define __attribute(arg)
+#if __GNUC__ < 3 + (__GNUC_MINOR__ < 1)
+# define __attribute__(arg)
 #endif
 
 typedef __re_idx_t Idx;
@@ -426,7 +424,7 @@ static void build_upper_buffer (re_string_t *pstr) 
internal_function;
 static void re_string_translate_buffer (re_string_t *pstr) internal_function;
 static unsigned int re_string_context_at (const re_string_t *input, Idx idx,
                                          int eflags)
-     internal_function __attribute ((pure));
+     internal_function __attribute__ ((pure));
 #endif
 #define re_string_peek_byte(pstr, offset) \
   ((pstr)->mbs[(pstr)->cur_idx + offset])
@@ -774,7 +772,7 @@ bitset_copy (bitset_t dest, const bitset_t src)
   memcpy (dest, src, sizeof (bitset_t));
 }
 
-static void
+static void __attribute__ ((unused))
 bitset_not (bitset_t set)
 {
   int bitset_i;
@@ -786,7 +784,7 @@ bitset_not (bitset_t set)
        & ~set[BITSET_WORDS - 1]);
 }
 
-static void
+static void __attribute__ ((unused))
 bitset_merge (bitset_t dest, const bitset_t src)
 {
   int bitset_i;
@@ -794,7 +792,7 @@ bitset_merge (bitset_t dest, const bitset_t src)
     dest[bitset_i] |= src[bitset_i];
 }
 
-static void
+static void __attribute__ ((unused))
 bitset_mask (bitset_t dest, const bitset_t src)
 {
   int bitset_i;
@@ -805,7 +803,7 @@ bitset_mask (bitset_t dest, const bitset_t src)
 #ifdef RE_ENABLE_I18N
 /* Functions for re_string.  */
 static int
-internal_function __attribute ((pure))
+internal_function __attribute__ ((pure, unused))
 re_string_char_size_at (const re_string_t *pstr, Idx idx)
 {
   int byte_idx;
@@ -818,7 +816,7 @@ re_string_char_size_at (const re_string_t *pstr, Idx idx)
 }
 
 static wint_t
-internal_function __attribute ((pure))
+internal_function __attribute__ ((pure, unused))
 re_string_wchar_at (const re_string_t *pstr, Idx idx)
 {
   if (pstr->mb_cur_max == 1)
@@ -828,7 +826,7 @@ re_string_wchar_at (const re_string_t *pstr, Idx idx)
 
 # ifndef NOT_IN_libc
 static int
-internal_function __attribute ((pure))
+internal_function __attribute__ ((pure, unused))
 re_string_elem_size_at (const re_string_t *pstr, Idx idx)
 {
 #  ifdef _LIBC
-- 
1.7.11.7