Sync regex routines with GLIBC.

5 files changed, 25 insertions, 12 deletions

diff --git a/ChangeLog b/ChangeLog
index 352d9da1..00369398 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+2012-11-30         Arnold D. Robbins     <arnold@skeeve.com>
+
+	* regcomp.c, regex.c, regex_internal.h, regexec.c: Sync
+	with GLIBC.  Why not.
+
 2012-01-30         Andrew J. Schorr     <aschorr@telemetry-investments.com>
 
 	Further cleanups of macros in awk.h
diff --git a/regcomp.c b/regcomp.c
index f83e454d..f6a7fdf6 100644
--- a/regcomp.c
+++ b/regcomp.c
@@ -573,8 +573,12 @@ regerror (errcode, preg, errbuf, errbuf_size)
     {
       if (BE (msg_size > errbuf_size, 0))
 	{
+#if defined HAVE_MEMPCPY || defined _LIBC
+	  *((char *) __mempcpy (errbuf, msg, errbuf_size - 1)) = '\0';
+#else
 	  memcpy (errbuf, msg, errbuf_size - 1);
 	  errbuf[errbuf_size - 1] = 0;
+#endif
 	}
       else
 	memcpy (errbuf, msg, msg_size);
@@ -896,7 +900,7 @@ init_dfa (re_dfa_t *dfa, size_t pat_len)
 # endif
 
   /* strcasecmp isn't a standard interface. brute force check */
-#if 0
+#ifndef GAWK
   if (strcasecmp (codeset_name, "UTF-8") == 0
       || strcasecmp (codeset_name, "UTF8") == 0)
     dfa->is_utf8 = 1;
@@ -978,8 +982,12 @@ init_word_char (re_dfa_t *dfa)
     {
       if (sizeof (dfa->word_char[0]) == 8)
 	{
-	  dfa->word_char[0] = UINT64_C (0x03ff000000000000);
-	  dfa->word_char[1] = UINT64_C (0x07fffffe87fffffe);
+          /* The extra temporaries here avoid "implicitly truncated"
+             warnings in the case when this is dead code, i.e. 32-bit.  */
+          const uint64_t wc0 = UINT64_C (0x03ff000000000000);
+          const uint64_t wc1 = UINT64_C (0x07fffffe87fffffe);
+	  dfa->word_char[0] = wc0;
+	  dfa->word_char[1] = wc1;
 	  i = 2;
 	}
       else if (sizeof (dfa->word_char[0]) == 4)
@@ -2679,7 +2687,6 @@ build_range_exp (reg_syntax_t syntax, bitset_t sbcset,
 # endif /* not RE_ENABLE_I18N */
 {
   unsigned int start_ch, end_ch;
-
   /* Equivalence Classes and Character Classes can't be a range start/end.  */
   if (BE (start_elem->type == EQUIV_CLASS || start_elem->type == CHAR_CLASS
 	  || end_elem->type == EQUIV_CLASS || end_elem->type == CHAR_CLASS,
diff --git a/regex.c b/regex.c
index 3abc7585..5ce79e09 100644
--- a/regex.c
+++ b/regex.c
@@ -1,5 +1,5 @@
 /* Extended regular expression matching and search library.
-   Copyright (C) 2002, 2003, 2005 Free Software Foundation, Inc.
+   Copyright (C) 2002-2012 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
    Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>.
 
@@ -56,6 +56,9 @@
    #undefs RE_DUP_MAX and sets it to the right value.  */
 #include <limits.h>
 
+/* This header defines the MIN and MAX macros.  */
+#include <sys/param.h>
+
 #ifdef GAWK
 #undef alloca
 #define alloca alloca_is_bad_you_should_never_use_it
diff --git a/regex_internal.h b/regex_internal.h
index f38a13b0..36f29e47 100644
--- a/regex_internal.h
+++ b/regex_internal.h
@@ -1,5 +1,5 @@
 /* Extended regular expression matching and search library.
-   Copyright (C) 2002-2005, 2007, 2008, 2010, 2011 Free Software Foundation, Inc.
+   Copyright (C) 2002-2012 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
    Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>.
 
@@ -92,7 +92,7 @@ is_blank (int c)
 # ifdef _LIBC
 #  undef gettext
 #  define gettext(msgid) \
-  INTUSE(__dcgettext) (_libc_intl_domainname, msgid, LC_MESSAGES)
+  __dcgettext (_libc_intl_domainname, msgid, LC_MESSAGES)
 # endif
 #else
 # define gettext(msgid) (msgid)
diff --git a/regexec.c b/regexec.c
index ea4a02f7..ff90fe31 100644
--- a/regexec.c
+++ b/regexec.c
@@ -375,7 +375,7 @@ re_search_2_stub (bufp, string1, length1, string2, length2, start, range, regs,
   const char *str;
   int rval;
   int len = length1 + length2;
-  int free_str = 0;
+  char *s = NULL;
 
   if (BE (length1 < 0 || length2 < 0 || stop < 0 || len < length1, 0))
     return -2;
@@ -384,7 +384,7 @@ re_search_2_stub (bufp, string1, length1, string2, length2, start, range, regs,
   if (length2 > 0)
     if (length1 > 0)
       {
-	char *s = re_malloc (char, len);
+	s = re_malloc (char, len);
 
 	if (BE (s == NULL, 0))
 	  return -2;
@@ -395,7 +395,6 @@ re_search_2_stub (bufp, string1, length1, string2, length2, start, range, regs,
 	memcpy (s + length1, string2, length2);
 #endif
 	str = s;
-	free_str = 1;
       }
     else
       str = string2;
@@ -403,8 +402,7 @@ re_search_2_stub (bufp, string1, length1, string2, length2, start, range, regs,
     str = string1;
 
   rval = re_search_stub (bufp, str, len, start, range, stop, regs, ret_len);
-  if (free_str)
-    re_free ((char *) str);
+  re_free (s);
   return rval;
 }