Merge branch 'gawk-4.1-stable'

8 files changed, 104 insertions, 44 deletions

diff --git a/ChangeLog b/ChangeLog
index 7f3063f9..bdfca3a0 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,16 @@
+2015-06-14         Arnold D. Robbins     <arnold@skeeve.com>
+
+	* regcomp.c, regex_internal.h, regexec.c: Sync with GLIBC.
+
+	Unrelated:
+
+	* regex_internal.c, regexec.c: __attribute --> __attribute__.
+
+	Related:
+
+	* regex_internal.h: Clean up defines for non-GCC for attribute;
+	essentially sync it with GLIBC.
+
 2015-05-31         Arnold D. Robbins     <arnold@skeeve.com>
 
 	* field.c (posix_def_parse_field): Removed. It's no longer
diff --git a/configure b/configure
index 829b0e76..38df7851 100755
--- a/configure
+++ b/configure
@@ -10798,7 +10798,46 @@ $as_echo "$_found_readline" >&6; }
 
         if test $_found_readline = yes ; then
 	   case $host_os in
-	   *bsd* )	_combo="$_combo -ltermcap"
+	   *bsd* )	{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for tgetent in -ltermcap" >&5
+$as_echo_n "checking for tgetent in -ltermcap... " >&6; }
+if ${ac_cv_lib_termcap_tgetent+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  ac_check_lib_save_LIBS=$LIBS
+LIBS="-ltermcap  $LIBS"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+/* Override any GCC internal prototype to avoid an error.
+   Use char because int might match the return type of a GCC
+   builtin and then its argument prototype would still apply.  */
+#ifdef __cplusplus
+extern "C"
+#endif
+char tgetent ();
+int
+main ()
+{
+return tgetent ();
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  ac_cv_lib_termcap_tgetent=yes
+else
+  ac_cv_lib_termcap_tgetent=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+LIBS=$ac_check_lib_save_LIBS
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_termcap_tgetent" >&5
+$as_echo "$ac_cv_lib_termcap_tgetent" >&6; }
+if test "x$ac_cv_lib_termcap_tgetent" = xyes; then :
+  _combo="$_combo -ltermcap"
+fi
+
 	  	 ;;
 	   esac
 
diff --git a/m4/ChangeLog b/m4/ChangeLog
index 82e0dabe..f271d0ef 100644
--- a/m4/ChangeLog
+++ b/m4/ChangeLog
@@ -1,3 +1,7 @@
+2015-06-15         Yuta SATOH            <nigoro@gentoo.gr.jp>
+
+	* readline.m4: Add check for libtermcap on Gentoo/FreeBSD.
+
 2015-05-19         Arnold D. Robbins     <arnold@skeeve.com>
 
 	* 4.1.3: Release tar ball made.
diff --git a/m4/readline.m4 b/m4/readline.m4
index 740b9c7b..5c0bb1ea 100644
--- a/m4/readline.m4
+++ b/m4/readline.m4
@@ -92,7 +92,7 @@ dnl action if not found:
 
         if test $_found_readline = yes ; then
 	   case $host_os in
-	   *bsd* )	_combo="$_combo -ltermcap"
+	   *bsd* )	AC_CHECK_LIB(termcap, tgetent, _combo="$_combo -ltermcap")
 	  	 ;;
 	   esac
            AC_DEFINE(HAVE_LIBREADLINE,1,
diff --git a/regcomp.c b/regcomp.c
index cdac1924..773af291 100644
--- a/regcomp.c
+++ b/regcomp.c
@@ -235,7 +235,7 @@ btowc (int c)
    compiles PATTERN (of length LENGTH) and puts the result in BUFP.
    Returns 0 if the pattern was valid, otherwise an error string.
 
-   Assumes the `allocated' (and perhaps `buffer') and `translate' fields
+   Assumes the 'allocated' (and perhaps 'buffer') and 'translate' fields
    are set in BUFP on entry.  */
 
 const char *
@@ -264,7 +264,7 @@ re_compile_pattern (pattern, length, bufp)
 weak_alias (__re_compile_pattern, re_compile_pattern)
 #endif
 
-/* Set by `re_set_syntax' to the current regexp syntax to recognize.  Can
+/* Set by 're_set_syntax' to the current regexp syntax to recognize.  Can
    also be assigned to arbitrarily: each pattern buffer stores its own
    syntax, so it can be changed between regex compilations.  */
 /* This has no initializer because initialized variables in Emacs
@@ -315,8 +315,8 @@ weak_alias (__re_compile_fastmap, re_compile_fastmap)
 #endif
 
 static inline void
-__attribute ((always_inline))
-re_set_fastmap (char *fastmap, int icase, int ch)
+__attribute__ ((always_inline))
+re_set_fastmap (char *fastmap, bool icase, int ch)
 {
   fastmap[ch] = 1;
   if (icase)
@@ -462,15 +462,15 @@ re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state,
    PREG is a regex_t *.  We do not expect any fields to be initialized,
    since POSIX says we shouldn't.  Thus, we set
 
-     `buffer' to the compiled pattern;
-     `used' to the length of the compiled pattern;
-     `syntax' to RE_SYNTAX_POSIX_EXTENDED if the
+     'buffer' to the compiled pattern;
+     'used' to the length of the compiled pattern;
+     'syntax' to RE_SYNTAX_POSIX_EXTENDED if the
        REG_EXTENDED bit in CFLAGS is set; otherwise, to
        RE_SYNTAX_POSIX_BASIC;
-     `newline_anchor' to REG_NEWLINE being set in CFLAGS;
-     `fastmap' to an allocated space for the fastmap;
-     `fastmap_accurate' to zero;
-     `re_nsub' to the number of subexpressions in PATTERN.
+     'newline_anchor' to REG_NEWLINE being set in CFLAGS;
+     'fastmap' to an allocated space for the fastmap;
+     'fastmap_accurate' to zero;
+     're_nsub' to the number of subexpressions in PATTERN.
 
    PATTERN is the address of the pattern string.
 
@@ -730,7 +730,7 @@ re_comp (s)
 				 + __re_error_msgid_idx[(int) REG_ESPACE]);
     }
 
-  /* Since `re_exec' always passes NULL for the `regs' argument, we
+  /* Since 're_exec' always passes NULL for the 'regs' argument, we
      don't need to initialize the pattern buffer fields which affect it.  */
 
   /* Match anchors at newlines.  */
@@ -1558,7 +1558,7 @@ duplicate_node_closure (re_dfa_t *dfa, int top_org_node, int top_clone_node,
 	     destination.  */
 	  org_dest = dfa->edests[org_node].elems[0];
 	  re_node_set_empty (dfa->edests + clone_node);
-	  /* If the node is root_node itself, it means the epsilon clsoure
+	  /* If the node is root_node itself, it means the epsilon closure
 	     has a loop.   Then tie it to the destination of the root_node.  */
 	  if (org_node == root_node && clone_node != org_node)
 	    {
@@ -1567,7 +1567,7 @@ duplicate_node_closure (re_dfa_t *dfa, int top_org_node, int top_clone_node,
 		return REG_ESPACE;
 	      break;
 	    }
-	  /* In case of the node has another constraint, add it.  */
+	  /* In case the node has another constraint, append it.  */
 	  constraint |= dfa->nodes[org_node].constraint;
 	  clone_dest = duplicate_node (dfa, org_dest, constraint);
 	  if (BE (clone_dest == -1, 0))
@@ -1710,7 +1710,7 @@ calc_eclosure (re_dfa_t *dfa)
       /* If we have already calculated, skip it.  */
       if (dfa->eclosures[node_idx].nelem != 0)
 	continue;
-      /* Calculate epsilon closure of `node_idx'.  */
+      /* Calculate epsilon closure of 'node_idx'.  */
       err = calc_eclosure_iter (&eclosure_elem, dfa, node_idx, 1);
       if (BE (err != REG_NOERROR, 0))
 	return err;
@@ -1777,11 +1777,11 @@ calc_eclosure_iter (re_node_set *new_set, re_dfa_t *dfa, int node, int root)
 	  }
 	else
 	  eclosure_elem = dfa->eclosures[edest];
-	/* Merge the epsilon closure of `edest'.  */
+	/* Merge the epsilon closure of 'edest'.  */
 	err = re_node_set_merge (&eclosure, &eclosure_elem);
 	if (BE (err != REG_NOERROR, 0))
 	  return err;
-	/* If the epsilon closure of `edest' is incomplete,
+	/* If the epsilon closure of 'edest' is incomplete,
 	   the epsilon closure of this node is also incomplete.  */
 	if (dfa->eclosures[edest].nelem == 0)
 	  {
@@ -2143,7 +2143,7 @@ peek_token_bracket (re_token_t *token, re_string_t *input, reg_syntax_t syntax)
 
 /* Entry point of the parser.
    Parse the regular expression REGEXP and return the structure tree.
-   If an error is occured, ERR is set by error code, and return NULL.
+   If an error occurs, ERR is set by error code, and return NULL.
    This function build the following tree, from regular expression <reg_exp>:
 	   CAT
 	   / \
@@ -2185,7 +2185,7 @@ parse (re_string_t *regexp, regex_t *preg, reg_syntax_t syntax,
 	  /   \
    <branch1> <branch2>
 
-   ALT means alternative, which represents the operator `|'.  */
+   ALT means alternative, which represents the operator '|'.  */
 
 static bin_tree_t *
 parse_reg_exp (re_string_t *regexp, regex_t *preg, re_token_t *token,
@@ -2681,7 +2681,7 @@ parse_dup_op (bin_tree_t *elem, re_string_t *regexp, re_dfa_t *dfa,
      Build the range expression which starts from START_ELEM, and ends
      at END_ELEM.  The result are written to MBCSET and SBCSET.
      RANGE_ALLOC is the allocated size of mbcset->range_starts, and
-     mbcset->range_ends, is a pointer argument sinse we may
+     mbcset->range_ends, is a pointer argument since we may
      update it.  */
 
 static reg_errcode_t
@@ -2855,13 +2855,13 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
   const int32_t *symb_table;
   const unsigned char *extra;
 
-  /* Local function for parse_bracket_exp used in _LIBC environement.
-     Seek the collating symbol entry correspondings to NAME.
+  /* 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,
      or -1 if not found.  */
 
   auto inline int32_t
-  __attribute ((always_inline))
+  __attribute__ ((always_inline))
   seek_collating_symbol_entry (const unsigned char *name, size_t name_len)
     {
       int32_t elem;
@@ -2887,7 +2887,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
      Return the value if succeeded, UINT_MAX otherwise.  */
 
   auto inline unsigned int
-  __attribute ((always_inline))
+  __attribute__ ((always_inline))
   lookup_collation_sequence_value (bracket_elem_t *br_elem)
     {
       if (br_elem->type == SB_CHAR)
@@ -2947,15 +2947,15 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
       return UINT_MAX;
     }
 
-  /* Local function for parse_bracket_exp used in _LIBC environement.
+  /* Local function for parse_bracket_exp used in _LIBC environment.
      Build the range expression which starts from START_ELEM, and ends
      at END_ELEM.  The result are written to MBCSET and SBCSET.
      RANGE_ALLOC is the allocated size of mbcset->range_starts, and
-     mbcset->range_ends, is a pointer argument sinse we may
+     mbcset->range_ends, is a pointer argument since we may
      update it.  */
 
   auto inline reg_errcode_t
-  __attribute ((always_inline))
+  __attribute__ ((always_inline))
   build_range_exp (bitset_t sbcset, re_charset_t *mbcset, int *range_alloc,
 		   bracket_elem_t *start_elem, bracket_elem_t *end_elem)
     {
@@ -3028,14 +3028,14 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
       return REG_NOERROR;
     }
 
-  /* Local function for parse_bracket_exp used in _LIBC environement.
+  /* Local function for parse_bracket_exp used in _LIBC environment.
      Build the collating element which is represented by NAME.
      The result are written to MBCSET and SBCSET.
      COLL_SYM_ALLOC is the allocated size of mbcset->coll_sym, is a
-     pointer argument sinse we may update it.  */
+     pointer argument since we may update it.  */
 
   auto inline reg_errcode_t
-  __attribute ((always_inline))
+  __attribute__ ((always_inline))
   build_collating_symbol (bitset_t sbcset, re_charset_t *mbcset,
 			  int *coll_sym_alloc, const unsigned char *name)
     {
@@ -3474,7 +3474,7 @@ parse_bracket_symbol (bracket_elem_t *elem, re_string_t *regexp,
      Build the equivalence class which is represented by NAME.
      The result are written to MBCSET and SBCSET.
      EQUIV_CLASS_ALLOC is the allocated size of mbcset->equiv_classes,
-     is a pointer argument sinse we may update it.  */
+     is a pointer argument since we may update it.  */
 
 static reg_errcode_t
 #ifdef RE_ENABLE_I18N
@@ -3568,7 +3568,7 @@ build_equiv_class (bitset_t sbcset, const unsigned char *name)
      Build the character class which is represented by NAME.
      The result are written to MBCSET and SBCSET.
      CHAR_CLASS_ALLOC is the allocated size of mbcset->char_classes,
-     is a pointer argument sinse we may update it.  */
+     is a pointer argument since we may update it.  */
 
 static reg_errcode_t
 #ifdef RE_ENABLE_I18N
diff --git a/regex_internal.c b/regex_internal.c
index 5a5b9363..fcfa4ada 100644
--- a/regex_internal.c
+++ b/regex_internal.c
@@ -838,7 +838,7 @@ re_string_reconstruct (re_string_t *pstr, int idx, int eflags)
 }
 
 static unsigned char
-internal_function __attribute ((pure))
+internal_function __attribute__ ((pure))
 re_string_peek_byte_case (const re_string_t *pstr, int idx)
 {
   int ch, off;
@@ -1370,7 +1370,7 @@ re_node_set_insert_last (re_node_set *set, int elem)
    return 1 if SET1 and SET2 are equivalent, return 0 otherwise.  */
 
 static int
-internal_function __attribute ((pure))
+internal_function __attribute__ ((pure))
 re_node_set_compare (const re_node_set *set1, const re_node_set *set2)
 {
   int i;
@@ -1385,7 +1385,7 @@ re_node_set_compare (const re_node_set *set1, const re_node_set *set2)
 /* Return (idx + 1) if SET contains the element ELEM, return 0 otherwise.  */
 
 static int
-internal_function __attribute ((pure))
+internal_function __attribute__ ((pure))
 re_node_set_contains (const re_node_set *set, int elem)
 {
   unsigned int idx, right, mid;
diff --git a/regex_internal.h b/regex_internal.h
index 327bd7e0..4d0028ff 100644
--- a/regex_internal.h
+++ b/regex_internal.h
@@ -148,11 +148,8 @@ is_blank (int c)
 # define attribute_hidden
 #endif /* not _LIBC */
 
-#ifdef __GNUC__
-# define __attribute(arg) __attribute__ (arg)
-#else
-# define __attribute(arg)
-# define __attribute__(arg)	/* GAWK: They left this out. Duh. */
+#if __GNUC__ < 3 + (__GNUC_MINOR__ < 1)
+# define __attribute__(arg)
 #endif
 
 #ifdef GAWK
@@ -803,6 +800,10 @@ re_string_wchar_at (const re_string_t *pstr, int idx)
 }
 
 # ifndef NOT_IN_libc
+#  ifdef _LIBC
+#   include <locale/weight.h>
+#  endif
+
 static int
 internal_function __attribute__ ((pure, unused))
 re_string_elem_size_at (const re_string_t *pstr, int idx)
@@ -810,7 +811,6 @@ re_string_elem_size_at (const re_string_t *pstr, int idx)
 #  ifdef _LIBC
   const unsigned char *p, *extra;
   const int32_t *table, *indirect;
-#   include <locale/weight.h>
   uint_fast32_t nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES);
 
   if (nrules != 0)
diff --git a/regexec.c b/regexec.c
index 46a4d0ae..cff69bfc 100644
--- a/regexec.c
+++ b/regexec.c
@@ -17,6 +17,10 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
+#ifdef HAVE_STDINT_H
+#include <stdint.h>
+#endif /* HAVE_STDINT_H */
+
 static reg_errcode_t match_ctx_init (re_match_context_t *cache, int eflags,
 				     int n) internal_function;
 static void match_ctx_clean (re_match_context_t *mctx) internal_function;
@@ -1055,7 +1059,7 @@ prune_impossible_nodes (mctx)
    since initial states may have constraints like "\<", "^", etc..  */
 
 static inline re_dfastate_t *
-__attribute ((always_inline)) internal_function
+__attribute__ ((always_inline)) internal_function
 acquire_init_state_context (reg_errcode_t *err, const re_match_context_t *mctx,
 			    int idx)
 {