* posix/regex_internal.c (re_string_reconstruct): Avoid calling

	mbrtowc for very simple UTF-8 case.

2005-09-01  Paul Eggert  <eggert@cs.ucla.edu>

	* posix/regex_internal.c (build_wcs_upper_buffer): Fix portability
	bugs in int versus size_t comparisons.

2005-09-06  Ulrich Drepper  <drepper@redhat.com>

	* posix/regex_internal.c (re_acquire_state): Make DFA pointer arg
	a pointer-to-const.
	(re_acquire_state_context): Likewise.
	* posix/regex_internal.h: Adjust prototypes.

2005-08-31  Jim Meyering  <jim@meyering.net>

	* posix/regcomp.c (search_duplicated_node): Make first pointer arg
	a pointer-to-const.
	* posix/regex_internal.c (create_ci_newstate, create_cd_newstate,
	register_state): Likewise.
	* posix/regexec.c (search_cur_bkref_entry, check_dst_limits):
	(check_dst_limits_calc_pos_1, check_dst_limits_calc_pos):
	(group_nodes_into_DFAstates): Likewise.

	* posix/regexec.c (re_search_internal): Simplify update of
	rm_so and rm_eo by replacing "if (A == B) A += C - B;"
	with the equivalent of "if (A == B) A = C;".

2005-09-06  Ulrich Drepper  <drepper@redhat.com>

	* posix/regcomp.c (re_compile_internal): Change third parameter type
	to size_t.
	(init_dfa): Likewise.  Make sure that arithmetic on pat_len doesn't
	overflow.
	* posix/regex_internal.h (struct re_dfa_t): Change type of nodes_alloc
	and nodes_len to size_t.
	* posix/regex_internal.c (re_dfa_add_node): Use size_t as type for
	new_nodes_alloc.  Check for overflow.

2005-08-31  Paul Eggert  <eggert@cs.ucla.edu>

	* posix/regcomp.c (re_compile_fastmap_iter, init_dfa, init_word_char):
	(optimize_subexps, lower_subexp):
	Don't assume 1<<31 has defined behavior on hosts with 32-bit int,
	since the signed shift might overflow.  Use 1u<<31 instead.
	* posix/regex_internal.h (bitset_set, bitset_clear, bitset_contain):
	Likewise.
	* posix/regexec.c (check_dst_limits_calc_pos_1): Likewise.
	(check_subexp_matching_top): Likewise.
	* posix/regcomp.c (optimize_subexps, lower_subexp):
	Use CHAR_BIT rather than 8, for clarity.
	* posix/regexec.c (check_dst_limits_calc_pos_1):
	(check_subexp_matching_top): Likewise.
	* posix/regcomp.c (init_dfa): Make table_size unsigned, so that we
	don't have to worry about portability issues when shifting it left.
	Remove no-longer-needed test for table_size > 0.
	* posix/regcomp.c (parse_sub_exp): Do not shift more bits than there
	are in a word, as the resulting behavior is undefined.
	* posix/regexec.c (check_dst_limits_calc_pos_1): Likewise;
	in one case, a <= should have been an <, and in another case the
	whole test was missing.
	* posix/regex_internal.h (BYTE_BITS): Remove.  All uses changed to
	the standard name CHAR_BIT.

1 files changed, 23 insertions, 16 deletions

diff --git a/posix/regcomp.c b/posix/regcomp.c
index d8205331d7..c93f79ea24 100644
--- a/posix/regcomp.c
+++ b/posix/regcomp.c
@@ -19,11 +19,11 @@
    02111-1307 USA.  */
 
 static reg_errcode_t re_compile_internal (regex_t *preg, const char * pattern,
-					  int length, reg_syntax_t syntax);
+					  size_t length, reg_syntax_t syntax);
 static void re_compile_fastmap_iter (regex_t *bufp,
 				     const re_dfastate_t *init_state,
 				     char *fastmap);
-static reg_errcode_t init_dfa (re_dfa_t *dfa, int pat_len);
+static reg_errcode_t init_dfa (re_dfa_t *dfa, size_t pat_len);
 static void init_word_char (re_dfa_t *dfa);
 #ifdef RE_ENABLE_I18N
 static void free_charset (re_charset_t *cset);
@@ -51,7 +51,7 @@ static reg_errcode_t duplicate_node_closure (re_dfa_t *dfa, int top_org_node,
 					     int top_clone_node, int root_node,
 					     unsigned int constraint);
 static int duplicate_node (re_dfa_t *dfa, int org_idx, unsigned int constraint);
-static int search_duplicated_node (re_dfa_t *dfa, int org_node,
+static int search_duplicated_node (const re_dfa_t *dfa, int org_node,
 				   unsigned int constraint);
 static reg_errcode_t calc_eclosure (re_dfa_t *dfa);
 static reg_errcode_t calc_eclosure_iter (re_node_set *new_set, re_dfa_t *dfa,
@@ -368,7 +368,7 @@ re_compile_fastmap_iter (bufp, init_state, fastmap)
 	  int i, j, ch;
 	  for (i = 0, ch = 0; i < BITSET_UINTS; ++i)
 	    for (j = 0; j < UINT_BITS; ++j, ++ch)
-	      if (dfa->nodes[node].opr.sbcset[i] & (1 << j))
+	      if (dfa->nodes[node].opr.sbcset[i] & (1u << j))
 		re_set_fastmap (fastmap, icase, ch);
 	}
 #ifdef RE_ENABLE_I18N
@@ -740,7 +740,7 @@ static reg_errcode_t
 re_compile_internal (preg, pattern, length, syntax)
      regex_t *preg;
      const char * pattern;
-     int length;
+     size_t length;
      reg_syntax_t syntax;
 {
   reg_errcode_t err = REG_NOERROR;
@@ -781,6 +781,7 @@ re_compile_internal (preg, pattern, length, syntax)
       return err;
     }
 #ifdef DEBUG
+  /* Note: length+1 will not overflow since it is checked in init_dfa.  */
   dfa->re_str = re_malloc (char, length + 1);
   strncpy (dfa->re_str, pattern, length + 1);
 #endif
@@ -840,9 +841,9 @@ re_compile_internal (preg, pattern, length, syntax)
 static reg_errcode_t
 init_dfa (dfa, pat_len)
      re_dfa_t *dfa;
-     int pat_len;
+     size_t pat_len;
 {
-  int table_size;
+  unsigned int table_size;
 #ifndef _LIBC
   char *codeset_name;
 #endif
@@ -852,11 +853,15 @@ init_dfa (dfa, pat_len)
   /* Force allocation of str_tree_storage the first time.  */
   dfa->str_tree_storage_idx = BIN_TREE_STORAGE_SIZE;
 
+  /* Avoid overflows.  */
+  if (pat_len == SIZE_MAX)
+    return REG_ESPACE;
+
   dfa->nodes_alloc = pat_len + 1;
   dfa->nodes = re_malloc (re_token_t, dfa->nodes_alloc);
 
   /*  table_size = 2 ^ ceil(log pat_len) */
-  for (table_size = 1; table_size > 0; table_size <<= 1)
+  for (table_size = 1; ; table_size <<= 1)
     if (table_size > pat_len)
       break;
 
@@ -916,7 +921,7 @@ init_dfa (dfa, pat_len)
 	      {
 		wint_t wch = __btowc (ch);
 		if (wch != WEOF)
-		  dfa->sb_char[i] |= 1 << j;
+		  dfa->sb_char[i] |= 1u << j;
 # ifndef _LIBC
 		if (isascii (ch) && wch != ch)
 		  dfa->map_notascii = 1;
@@ -944,7 +949,7 @@ init_word_char (dfa)
   for (i = 0, ch = 0; i < BITSET_UINTS; ++i)
     for (j = 0; j < UINT_BITS; ++j, ++ch)
       if (isalnum (ch) || ch == '_')
-	dfa->word_char[i] |= 1 << j;
+	dfa->word_char[i] |= 1u << j;
 }
 
 /* Free the work area which are only used while compiling.  */
@@ -1277,8 +1282,8 @@ optimize_subexps (extra, node)
         node->left->parent = node;
 
       dfa->subexp_map[other_idx] = dfa->subexp_map[node->token.opr.idx];
-      if (other_idx < 8 * sizeof (dfa->used_bkref_map))
-	dfa->used_bkref_map &= ~(1 << other_idx);
+      if (other_idx < CHAR_BIT * sizeof dfa->used_bkref_map)
+	dfa->used_bkref_map &= ~(1u << other_idx);
     }
 
   return REG_NOERROR;
@@ -1326,8 +1331,8 @@ lower_subexp (err, preg, node)
 	 very common, so we do not lose much.  An example that triggers
 	 this case is the sed "script" /\(\)/x.  */
       && node->left != NULL
-      && (node->token.opr.idx >= 8 * sizeof (dfa->used_bkref_map)
-	  || !(dfa->used_bkref_map & (1 << node->token.opr.idx))))
+      && (node->token.opr.idx >= CHAR_BIT * sizeof dfa->used_bkref_map
+	  || !(dfa->used_bkref_map & (1u << node->token.opr.idx))))
     return node->left;
 
   /* Convert the SUBEXP node to the concatenation of an
@@ -1574,7 +1579,7 @@ duplicate_node_closure (dfa, top_org_node, top_clone_node, root_node,
 
 static int
 search_duplicated_node (dfa, org_node, constraint)
-     re_dfa_t *dfa;
+     const re_dfa_t *dfa;
      int org_node;
      unsigned int constraint;
 {
@@ -2492,7 +2497,9 @@ parse_sub_exp (regexp, preg, token, syntax, nest, err)
       if (BE (*err != REG_NOERROR, 0))
 	return NULL;
     }
-  dfa->completed_bkref_map |= 1 << cur_nsub;
+
+  if (cur_nsub <= '9' - '1')
+    dfa->completed_bkref_map |= 1 << cur_nsub;
 
   tree = create_tree (dfa, tree, NULL, SUBEXP);
   if (BE (tree == NULL, 0))