maint: update all copyright year number ranges

[gnulib.git] / lib / regcomp.c

diff --git a/lib/regcomp.c b/lib/regcomp.c
index b51a9a6..6d32726 100644 (file)
--- a/lib/regcomp.c
+++ b/lib/regcomp.c
@@ -1,20 +1,21 @@
 /* Extended regular expression matching and search library.
-   Copyright (C) 2002-2012 Free Software Foundation, Inc.
+   Copyright (C) 2002-2013 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
    Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>.
 
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation; either version 2, or (at your option)
-   any later version.
+   The GNU C Library is free software; you can redistribute it and/or
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
 
-   This program is distributed in the hope that it will be useful,
+   The GNU C Library is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-   GNU General Public License for more details.
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
 
-   You should have received a copy of the GNU General Public License along
-   with this program; if not, see <http://www.gnu.org/licenses/>.  */
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
 
 static reg_errcode_t re_compile_internal (regex_t *preg, const char * pattern,
                                          size_t length, reg_syntax_t syntax);
@@ -899,8 +900,10 @@ init_dfa (re_dfa_t *dfa, size_t pat_len)
                       != 0);
 #else
   codeset_name = nl_langinfo (CODESET);
-  if (strcasecmp (codeset_name, "UTF-8") == 0
-      || strcasecmp (codeset_name, "UTF8") == 0)
+  if ((codeset_name[0] == 'U' || codeset_name[0] == 'u')
+      && (codeset_name[1] == 'T' || codeset_name[1] == 't')
+      && (codeset_name[2] == 'F' || codeset_name[2] == 'f')
+      && strcmp (codeset_name + 3 + (codeset_name[3] == '-'), "8") == 0)
     dfa->is_utf8 = 1;
 
   /* We check exhaustively in the loop below if this charset is a
@@ -950,24 +953,28 @@ static void
 internal_function
 init_word_char (re_dfa_t *dfa)
 {
-  dfa->word_ops_used = 1;
   int i = 0;
   int j;
   int ch = 0;
+  dfa->word_ops_used = 1;
   if (BE (dfa->map_notascii == 0, 1))
     {
+      bitset_word_t bits0 = 0x00000000;
+      bitset_word_t bits1 = 0x03ff0000;
+      bitset_word_t bits2 = 0x87fffffe;
+      bitset_word_t bits3 = 0x07fffffe;
       if (BITSET_WORD_BITS == 64)
        {
-         dfa->word_char[0] = UINT64_C (0x03ff000000000000);
-         dfa->word_char[1] = UINT64_C (0x07fffffe87fffffe);
+         dfa->word_char[0] = bits1 << 31 << 1 | bits0;
+         dfa->word_char[1] = bits3 << 31 << 1 | bits2;
          i = 2;
        }
       else if (BITSET_WORD_BITS == 32)
        {
-         dfa->word_char[0] = UINT32_C (0x00000000);
-         dfa->word_char[1] = UINT32_C (0x03ff0000);
-         dfa->word_char[2] = UINT32_C (0x87fffffe);
-         dfa->word_char[3] = UINT32_C (0x07fffffe);
+         dfa->word_char[0] = bits0;
+         dfa->word_char[1] = bits1;
+         dfa->word_char[2] = bits2;
+         dfa->word_char[3] = bits3;
          i = 4;
        }
       else
@@ -2617,7 +2624,10 @@ parse_dup_op (bin_tree_t *elem, re_string_t *regexp, re_dfa_t *dfa,
     old_tree = NULL;
 
   if (elem->token.type == SUBEXP)
-    postorder (elem, mark_opt_subexp, (void *) (long) elem->token.opr.idx);
+    {
+      uintptr_t subidx = elem->token.opr.idx;
+      postorder (elem, mark_opt_subexp, (void *) subidx);
+    }
 
   tree = create_tree (dfa, elem, NULL,
                      (end == REG_MISSING ? OP_DUP_ASTERISK : OP_ALT));
@@ -2702,7 +2712,6 @@ build_range_exp (const reg_syntax_t syntax,
     wchar_t wc;
     wint_t start_wc;
     wint_t end_wc;
-    wchar_t cmp_buf[6] = {L'\0', L'\0', L'\0', L'\0', L'\0', L'\0'};
 
     start_ch = ((start_elem->type == SB_CHAR) ? start_elem->opr.ch
                : ((start_elem->type == COLL_SYM) ? start_elem->opr.name[0]
@@ -2716,11 +2725,7 @@ build_range_exp (const reg_syntax_t syntax,
              ? __btowc (end_ch) : end_elem->opr.wch);
     if (start_wc == WEOF || end_wc == WEOF)
       return REG_ECOLLATE;
-    cmp_buf[0] = start_wc;
-    cmp_buf[4] = end_wc;
-
-    if (BE ((syntax & RE_NO_EMPTY_RANGES)
-            && wcscoll (cmp_buf, cmp_buf + 4) > 0, 0))
+    else if (BE ((syntax & RE_NO_EMPTY_RANGES) && start_wc > end_wc, 0))
       return REG_ERANGE;
 
     /* Got valid collation sequence values, add them as a new entry.
@@ -2761,9 +2766,7 @@ build_range_exp (const reg_syntax_t syntax,
     /* Build the table for single byte characters.  */
     for (wc = 0; wc < SBC_MAX; ++wc)
       {
-       cmp_buf[2] = wc;
-       if (wcscoll (cmp_buf, cmp_buf + 2) <= 0
-           && wcscoll (cmp_buf + 2, cmp_buf + 4) <= 0)
+       if (start_wc <= wc && wc <= end_wc)
          bitset_set (sbcset, wc);
       }
   }
@@ -2960,6 +2963,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
              0))
        return REG_ERANGE;
 
+      /* FIXME: Implement rational ranges here, too.  */
       start_collseq = lookup_collation_sequence_value (start_elem);
       end_collseq = lookup_collation_sequence_value (end_elem);
       /* Check start/end collation sequence values.  */
@@ -3852,7 +3856,7 @@ create_token_tree (re_dfa_t *dfa, bin_tree_t *left, bin_tree_t *right,
 static reg_errcode_t
 mark_opt_subexp (void *extra, bin_tree_t *node)
 {
-  Idx idx = (Idx) (long) extra;
+  Idx idx = (uintptr_t) extra;
   if (node->token.type == SUBEXP && node->token.opr.idx == idx)
     node->token.opt_subexp = 1;