Update the compat/regex engine from upstream

index d8bde06f1a..a1fb2e400e 100644
@@ -1,5 +1,12 @@
+/*
+ * This is git.git's copy of gawk.git's regex engine. Please see that
+ * project for the latest version & to submit patches to this code,
+ * and git.git's compat/regex/README for information on how git's copy
+ * of this code is maintained.
+ */
+
 /* Extended regular expression matching and search library.
-   Copyright (C) 2002-2007,2009,2010 Free Software Foundation, Inc.
+   Copyright (C) 2002-2016 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
    Contributed by Isamu Hasegawa <[email protected]>.
 

@@ -14,9 +21,20 @@
    Lesser General Public License for more details.
 
    You should have received a copy of the GNU Lesser General Public
-   License along with the GNU C Library; if not, write to the Free
-   Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
-   02110-1301 USA.  */
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#ifdef HAVE_STDINT_H
+#include <stdint.h>
+#endif
+
+#ifdef HAVE_STRINGS_H
+#include <strings.h>
+#endif
+
+#ifdef _LIBC
+# include <locale/weight.h>
+#endif
 
 static reg_errcode_t re_compile_internal (regex_t *preg, const char * pattern,
 					  size_t length, reg_syntax_t syntax);

@@ -126,7 +144,7 @@ static reg_errcode_t mark_opt_subexp (void *extra, bin_tree_t *node);
    POSIX doesn't require that we do anything for REG_NOERROR,
    but why not be nice?  */
 
-const char __re_error_msgid[] attribute_hidden =
+static const char __re_error_msgid[] =
   {
 #define REG_NOERROR_IDX	0
     gettext_noop ("Success")	/* REG_NOERROR */

@@ -150,9 +168,9 @@ const char __re_error_msgid[] attribute_hidden =
     gettext_noop ("Invalid back reference") /* REG_ESUBREG */
     "\0"
 #define REG_EBRACK_IDX	(REG_ESUBREG_IDX + sizeof "Invalid back reference")
-    gettext_noop ("Unmatched [ or [^")	/* REG_EBRACK */
+    gettext_noop ("Unmatched [, [^, [:, [., or [=")	/* REG_EBRACK */
     "\0"
-#define REG_EPAREN_IDX	(REG_EBRACK_IDX + sizeof "Unmatched [ or [^")
+#define REG_EPAREN_IDX	(REG_EBRACK_IDX + sizeof "Unmatched [, [^, [:, [., or [=")
     gettext_noop ("Unmatched ( or \\(") /* REG_EPAREN */
     "\0"
 #define REG_EBRACE_IDX	(REG_EPAREN_IDX + sizeof "Unmatched ( or \\(")

@@ -180,7 +198,7 @@ const char __re_error_msgid[] attribute_hidden =
     gettext_noop ("Unmatched ) or \\)") /* REG_ERPAREN */
   };
 
-const size_t __re_error_msgid_idx[] attribute_hidden =
+static const size_t __re_error_msgid_idx[] =
   {
     REG_NOERROR_IDX,
     REG_NOMATCH_IDX,

@@ -204,20 +222,19 @@ const size_t __re_error_msgid_idx[] attribute_hidden =
 /* Entry points for GNU code.  */
 
 
-#ifdef ZOS_USS
-
-/* For ZOS USS we must define btowc */
-
-wchar_t 
+#ifndef HAVE_BTOWC
+wchar_t
 btowc (int c)
 {
    wchar_t wtmp[2];
    char tmp[2];
+   mbstate_t mbs;
 
+   memset(& mbs, 0, sizeof(mbs));
    tmp[0] = c;
    tmp[1] = 0;
 
-   mbtowc (wtmp, tmp, 1);
+   mbrtowc (wtmp, tmp, 1, & mbs);
    return wtmp[0];
 }
 #endif

@@ -226,12 +243,11 @@ 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 *
-re_compile_pattern (const char *pattern,
-		    size_t length,
+re_compile_pattern (const char *pattern, size_t length,
 		    struct re_pattern_buffer *bufp)
 {
   reg_errcode_t ret;

@@ -254,7 +270,7 @@ re_compile_pattern (const char *pattern,
 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

@@ -303,8 +319,8 @@ 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)

@@ -318,7 +334,7 @@ static void
 re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state,
 			 char *fastmap)
 {
-  volatile re_dfa_t *dfa = (re_dfa_t *) bufp->buffer;
+  re_dfa_t *dfa = (re_dfa_t *) bufp->buffer;
   int node_cnt;
   int icase = (dfa->mb_cur_max == 1 && (bufp->syntax & RE_ICASE));
   for (node_cnt = 0; node_cnt < init_state->nodes.nelem; ++node_cnt)

@@ -332,14 +348,15 @@ re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state,
 #ifdef RE_ENABLE_I18N
 	  if ((bufp->syntax & RE_ICASE) && dfa->mb_cur_max > 1)
 	    {
-	      unsigned char *buf = re_malloc (unsigned char, dfa->mb_cur_max), *p;
+	      unsigned char buf[MB_LEN_MAX];
+	      unsigned char *p;
 	      wchar_t wc;
 	      mbstate_t state;
 
 	      p = buf;
 	      *p++ = dfa->nodes[node].opr.c;
 	      while (++node < dfa->nodes_len
-		     && dfa->nodes[node].type == CHARACTER
+		     &&	dfa->nodes[node].type == CHARACTER
 		     && dfa->nodes[node].mb_partial)
 		*p++ = dfa->nodes[node].opr.c;
 	      memset (&state, '\0', sizeof (state));

@@ -348,7 +365,6 @@ re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state,
 		  && (__wcrtomb ((char *) buf, towlower (wc), &state)
 		      != (size_t) -1))
 		re_set_fastmap (fastmap, 0, buf[0]);
-	      re_free (buf);
 	    }
 #endif
 	}

@@ -450,15 +466,15 @@ 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.
 

@@ -481,9 +497,7 @@ re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state,
    the return codes and their meanings.)  */
 
 int
-regcomp (regex_t *__restrict preg,
-	 const char *__restrict pattern,
-	 int cflags)
+regcomp (regex_t *__restrict preg, const char *__restrict pattern, int cflags)
 {
   reg_errcode_t ret;
   reg_syntax_t syntax = ((cflags & REG_EXTENDED) ? RE_SYNTAX_POSIX_EXTENDED

@@ -542,8 +556,8 @@ weak_alias (__regcomp, regcomp)
    from either regcomp or regexec.   We don't use PREG here.  */
 
 size_t
-regerror(int errcode, const regex_t *__restrict preg,
-	 char *__restrict errbuf, size_t errbuf_size)
+regerror (int errcode, const regex_t *__restrict preg, char *__restrict errbuf,
+	  size_t errbuf_size)
 {
   const char *msg;
   size_t msg_size;

@@ -565,8 +579,12 @@ regerror(int errcode, const regex_t *__restrict preg,
     {
       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);

@@ -679,8 +697,7 @@ char *
    regcomp/regexec above without link errors.  */
 weak_function
 # endif
-re_comp (s)
-     const char *s;
+re_comp (const char *s)
 {
   reg_errcode_t ret;
   char *fastmap;

@@ -709,7 +726,7 @@ 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.  */

@@ -787,7 +804,7 @@ re_compile_internal (regex_t *preg, const char * pattern, size_t length,
   __libc_lock_init (dfa->lock);
 
   err = re_string_construct (&regexp, pattern, length, preg->translate,
-			     syntax & RE_ICASE, dfa);
+			     (syntax & RE_ICASE) != 0, dfa);
   if (BE (err != REG_NOERROR, 0))
     {
     re_compile_internal_free_return:

@@ -886,20 +903,9 @@ init_dfa (re_dfa_t *dfa, size_t pat_len)
     codeset_name = strchr (codeset_name, '.') + 1;
 # endif
 
-  /* strcasecmp isn't a standard interface. brute force check */
-#if 0
   if (strcasecmp (codeset_name, "UTF-8") == 0
       || strcasecmp (codeset_name, "UTF8") == 0)
     dfa->is_utf8 = 1;
-#else
-  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')
-      && (codeset_name[3] == '-'
-          ? codeset_name[4] == '8' && codeset_name[5] == '\0'
-          : codeset_name[3] == '8' && codeset_name[4] == '\0'))
-    dfa->is_utf8 = 1;
-#endif
 
   /* We check exhaustively in the loop below if this charset is a
      superset of ASCII.  */

@@ -964,6 +970,39 @@ init_word_char (re_dfa_t *dfa)
 {
   int i, j, ch;
   dfa->word_ops_used = 1;
+#ifndef GAWK
+  if (BE (dfa->map_notascii == 0, 1))
+    {
+      if (sizeof (dfa->word_char[0]) == 8)
+	{
+          /* 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)
+	{
+	  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);
+	  i = 4;
+	}
+      else
+	abort ();
+      ch = 128;
+
+      if (BE (dfa->is_utf8, 1))
+	{
+	  memset (&dfa->word_char[i], '\0', (SBC_MAX - ch) / 8);
+	  return;
+	}
+    }
+#endif
+
   for (i = 0, ch = 0; i < BITSET_WORDS; ++i)
     for (j = 0; j < BITSET_WORD_BITS; ++j, ++ch)
       if (isalnum (ch) || ch == '_')

@@ -1162,7 +1201,12 @@ analyze (regex_t *preg)
 	  || dfa->eclosures == NULL, 0))
     return REG_ESPACE;
 
-  dfa->subexp_map = re_malloc (int, preg->re_nsub);
+  /* some malloc()-checkers don't like zero allocations */
+  if (preg->re_nsub > 0)
+    dfa->subexp_map = re_malloc (int, preg->re_nsub);
+  else
+    dfa->subexp_map = NULL;
+
   if (dfa->subexp_map != NULL)
     {
       int i;

@@ -1510,7 +1554,7 @@ 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)
 	    {

@@ -1519,7 +1563,7 @@ 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))

@@ -1662,7 +1706,7 @@ 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;

@@ -1729,11 +1773,11 @@ 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)
 	  {

@@ -2095,7 +2139,7 @@ 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 has occurred, 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
 	   / \

@@ -2137,7 +2181,7 @@ 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,

@@ -2145,6 +2189,7 @@ parse_reg_exp (re_string_t *regexp, regex_t *preg, re_token_t *token,
 {
   re_dfa_t *dfa = (re_dfa_t *) preg->buffer;
   bin_tree_t *tree, *branch = NULL;
+  bitset_word_t initial_bkref_map = dfa->completed_bkref_map;
   tree = parse_branch (regexp, preg, token, syntax, nest, err);
   if (BE (*err != REG_NOERROR && tree == NULL, 0))
     return NULL;

@@ -2155,9 +2200,16 @@ parse_reg_exp (re_string_t *regexp, regex_t *preg, re_token_t *token,
       if (token->type != OP_ALT && token->type != END_OF_RE
 	  && (nest == 0 || token->type != OP_CLOSE_SUBEXP))
 	{
+	  bitset_word_t accumulated_bkref_map = dfa->completed_bkref_map;
+	  dfa->completed_bkref_map = initial_bkref_map;
 	  branch = parse_branch (regexp, preg, token, syntax, nest, err);
 	  if (BE (*err != REG_NOERROR && branch == NULL, 0))
-	    return NULL;
+	    {
+	      if (tree != NULL)
+		postorder (tree, free_tree, NULL);
+	      return NULL;
+	    }
+	  dfa->completed_bkref_map |= accumulated_bkref_map;
 	}
       else
 	branch = NULL;

@@ -2196,16 +2248,21 @@ parse_branch (re_string_t *regexp, regex_t *preg, re_token_t *token,
       exp = parse_expression (regexp, preg, token, syntax, nest, err);
       if (BE (*err != REG_NOERROR && exp == NULL, 0))
 	{
+	  if (tree != NULL)
+	    postorder (tree, free_tree, NULL);
 	  return NULL;
 	}
       if (tree != NULL && exp != NULL)
 	{
-	  tree = create_tree (dfa, tree, exp, CONCAT);
-	  if (tree == NULL)
+	  bin_tree_t *newtree = create_tree (dfa, tree, exp, CONCAT);
+	  if (newtree == NULL)
 	    {
+	      postorder (exp, free_tree, NULL);
+	      postorder (tree, free_tree, NULL);
 	      *err = REG_ESPACE;
 	      return NULL;
 	    }
+	  tree = newtree;
 	}
       else if (tree == NULL)
 	tree = exp;

@@ -2413,14 +2470,21 @@ parse_expression (re_string_t *regexp, regex_t *preg, re_token_t *token,
   while (token->type == OP_DUP_ASTERISK || token->type == OP_DUP_PLUS
 	 || token->type == OP_DUP_QUESTION || token->type == OP_OPEN_DUP_NUM)
     {
-      tree = parse_dup_op (tree, regexp, dfa, token, syntax, err);
-      if (BE (*err != REG_NOERROR && tree == NULL, 0))
-	return NULL;
+      bin_tree_t *dup_tree = parse_dup_op (tree, regexp, dfa, token, syntax, err);
+      if (BE (*err != REG_NOERROR && dup_tree == NULL, 0))
+	{
+	  if (tree != NULL)
+	    postorder (tree, free_tree, NULL);
+	  return NULL;
+	}
+      tree = dup_tree;
       /* In BRE consecutive duplications are not allowed.  */
       if ((syntax & RE_CONTEXT_INVALID_DUP)
 	  && (token->type == OP_DUP_ASTERISK
 	      || token->type == OP_OPEN_DUP_NUM))
 	{
+	  if (tree != NULL)
+	    postorder (tree, free_tree, NULL);
 	  *err = REG_BADRPT;
 	  return NULL;
 	}

@@ -2454,7 +2518,11 @@ parse_sub_exp (re_string_t *regexp, regex_t *preg, re_token_t *token,
     {
       tree = parse_reg_exp (regexp, preg, token, syntax, nest, err);
       if (BE (*err == REG_NOERROR && token->type != OP_CLOSE_SUBEXP, 0))
-	*err = REG_EPAREN;
+	{
+	  if (tree != NULL)
+	    postorder (tree, free_tree, NULL);
+	  *err = REG_EPAREN;
+	}
       if (BE (*err != REG_NOERROR, 0))
 	return NULL;
     }

@@ -2480,13 +2548,7 @@ parse_dup_op (bin_tree_t *elem, re_string_t *regexp, re_dfa_t *dfa,
 {
   bin_tree_t *tree = NULL, *old_tree = NULL;
   int i, start, end, start_idx = re_string_cur_idx (regexp);
-#ifndef RE_TOKEN_INIT_BUG
   re_token_t start_token = *token;
-#else
-  re_token_t start_token;
-
-  memcpy ((void *) &start_token, (void *) token, sizeof start_token);
-#endif
 
   if (token->type == OP_OPEN_DUP_NUM)
     {

@@ -2571,13 +2633,15 @@ parse_dup_op (bin_tree_t *elem, re_string_t *regexp, re_dfa_t *dfa,
 
       /* Duplicate ELEM before it is marked optional.  */
       elem = duplicate_tree (elem, dfa);
+      if (BE (elem == NULL, 0))
+        goto parse_dup_op_espace;
       old_tree = tree;
     }
   else
     old_tree = NULL;
 
   if (elem->token.type == SUBEXP)
-    postorder (elem, mark_opt_subexp, (void *) (intptr_t) elem->token.opr.idx);
+    postorder (elem, mark_opt_subexp, (void *) (long) elem->token.opr.idx);
 
   tree = create_tree (dfa, elem, NULL, (end == -1 ? OP_DUP_ASTERISK : OP_ALT));
   if (BE (tree == NULL, 0))

@@ -2623,11 +2687,12 @@ parse_dup_op (bin_tree_t *elem, re_string_t *regexp, re_dfa_t *dfa,
 static reg_errcode_t
 internal_function
 # ifdef RE_ENABLE_I18N
-build_range_exp (bitset_t sbcset, re_charset_t *mbcset, int *range_alloc,
-		 bracket_elem_t *start_elem, bracket_elem_t *end_elem)
+build_range_exp (reg_syntax_t syntax, bitset_t sbcset, re_charset_t *mbcset,
+		int *range_alloc, bracket_elem_t *start_elem,
+		bracket_elem_t *end_elem)
 # else /* not RE_ENABLE_I18N */
-build_range_exp (bitset_t sbcset, bracket_elem_t *start_elem,
-		 bracket_elem_t *end_elem)
+build_range_exp (reg_syntax_t syntax, bitset_t sbcset,
+		bracket_elem_t *start_elem, bracket_elem_t *end_elem)
 # endif /* not RE_ENABLE_I18N */
 {
   unsigned int start_ch, end_ch;

@@ -2650,7 +2715,6 @@ build_range_exp (bitset_t sbcset, bracket_elem_t *start_elem,
     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]

@@ -2676,9 +2740,7 @@ build_range_exp (bitset_t sbcset, bracket_elem_t *start_elem,
 #endif
     if (start_wc == WEOF || end_wc == WEOF)
       return REG_ECOLLATE;
-    cmp_buf[0] = start_wc;
-    cmp_buf[4] = end_wc;
-    if (wcscoll (cmp_buf, cmp_buf + 4) > 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.

@@ -2705,7 +2767,14 @@ build_range_exp (bitset_t sbcset, bracket_elem_t *start_elem,
 					new_nranges);
 
 	    if (BE (new_array_start == NULL || new_array_end == NULL, 0))
-	      return REG_ESPACE;
+              {
+                 /* if one is not NULL, free it to avoid leaks */
+                 if (new_array_start != NULL)
+                     re_free(new_array_start);
+                 if (new_array_end != NULL)
+                     re_free(new_array_end);
+	         return REG_ESPACE;
+	      }
 
 	    mbcset->range_starts = new_array_start;
 	    mbcset->range_ends = new_array_end;

@@ -2719,10 +2788,8 @@ build_range_exp (bitset_t sbcset, bracket_elem_t *start_elem,
     /* 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)
-	  bitset_set (sbcset, wc);
+         if (start_wc <= wc && wc <= end_wc)
+           bitset_set (sbcset, wc);
       }
   }
 # else /* not RE_ENABLE_I18N */

@@ -2789,41 +2856,30 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
   const unsigned char *extra;
 
   /* Local function for parse_bracket_exp used in _LIBC environment.
-     Seek the collating symbol entry correspondings to NAME.
-     Return the index of the symbol in the SYMB_TABLE.  */
+     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))
-  seek_collating_symbol_entry (name, name_len)
-	 const unsigned char *name;
-	 size_t name_len;
+  __attribute__ ((always_inline))
+  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.

@@ -2831,9 +2887,8 @@ 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))
-  lookup_collation_sequence_value (br_elem)
-	 bracket_elem_t *br_elem;
+  __attribute__ ((always_inline))
+  lookup_collation_sequence_value (bracket_elem_t *br_elem)
     {
       if (br_elem->type == SB_CHAR)
 	{

@@ -2861,7 +2916,7 @@ 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];

@@ -2879,7 +2934,7 @@ 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.  */

@@ -2900,12 +2955,9 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
      update it.  */
 
   auto inline reg_errcode_t
-  __attribute ((always_inline))
-  build_range_exp (sbcset, mbcset, range_alloc, start_elem, end_elem)
-	 re_charset_t *mbcset;
-	 int *range_alloc;
-	 bitset_t sbcset;
-	 bracket_elem_t *start_elem, *end_elem;
+  __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)
     {
       unsigned int ch;
       uint32_t start_collseq;

@@ -2983,26 +3035,23 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
      pointer argument since we may update it.  */
 
   auto inline reg_errcode_t
-  __attribute ((always_inline))
-  build_collating_symbol (sbcset, mbcset, coll_sym_alloc, name)
-	 re_charset_t *mbcset;
-	 int *coll_sym_alloc;
-	 bitset_t sbcset;
-	 const unsigned char *name;
+  __attribute__ ((always_inline))
+  build_collating_symbol (bitset_t sbcset, re_charset_t *mbcset,
+			  int *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.  */

@@ -3082,6 +3131,10 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
   if (BE (sbcset == NULL, 0))
 #endif /* RE_ENABLE_I18N */
     {
+      re_free (sbcset);
+#ifdef RE_ENABLE_I18N
+      re_free (mbcset);
+#endif
       *err = REG_ESPACE;
       return NULL;
     }

@@ -3123,6 +3176,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
       re_token_t token2;
 
       start_elem.opr.name = start_name_buf;
+      start_elem.type = COLL_SYM;
       ret = parse_bracket_element (&start_elem, regexp, token, token_len, dfa,
 				   syntax, first_round);
       if (BE (ret != REG_NOERROR, 0))

@@ -3166,6 +3220,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
       if (is_range_exp == 1)
 	{
 	  end_elem.opr.name = end_name_buf;
+	  end_elem.type = COLL_SYM;
 	  ret = parse_bracket_element (&end_elem, regexp, &token2, token_len2,
 				       dfa, syntax, 1);
 	  if (BE (ret != REG_NOERROR, 0))

@@ -3177,15 +3232,15 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
 	  token_len = peek_token_bracket (token, regexp, syntax);
 
 #ifdef _LIBC
-	  *err = build_range_exp (sbcset, mbcset, &range_alloc,
+	  *err = build_range_exp (syntax, sbcset, mbcset, &range_alloc,
 				  &start_elem, &end_elem);
 #else
 # ifdef RE_ENABLE_I18N
-	  *err = build_range_exp (sbcset,
+	  *err = build_range_exp (syntax, sbcset,
 				  dfa->mb_cur_max > 1 ? mbcset : NULL,
 				  &range_alloc, &start_elem, &end_elem);
 # else
-	  *err = build_range_exp (sbcset, &start_elem, &end_elem);
+	  *err = build_range_exp (syntax, sbcset, &start_elem, &end_elem);
 # endif
 #endif /* RE_ENABLE_I18N */
 	  if (BE (*err != REG_NOERROR, 0))

@@ -3439,8 +3494,6 @@ build_equiv_class (bitset_t sbcset, const unsigned char *name)
       int32_t idx1, idx2;
       unsigned int ch;
       size_t len;
-      /* This #include defines a local function!  */
-# include <locale/weight.h>
       /* Calculate the index for equivalence class.  */
       cp = name;
       table = (const int32_t *) _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB);

@@ -3450,19 +3503,19 @@ build_equiv_class (bitset_t sbcset, const unsigned char *name)
 						   _NL_COLLATE_EXTRAMB);
       indirect = (const int32_t *) _NL_CURRENT (LC_COLLATE,
 						_NL_COLLATE_INDIRECTMB);
-      idx1 = findidx (&cp);
-      if (BE (idx1 == 0 || cp < name + strlen ((const char *) name), 0))
+      idx1 = findidx (table, indirect, extra, &cp, -1);
+      if (BE (idx1 == 0 || *cp != '\0', 0))
 	/* This isn't a valid character.  */
 	return REG_ECOLLATE;
 
-      /* Build single byte matcing table for this equivalence class.  */
+      /* Build single byte matching table for this equivalence class.  */
       char_buf[1] = (unsigned char) '\0';
       len = weights[idx1 & 0xffffff];
       for (ch = 0; ch < SBC_MAX; ++ch)
 	{
 	  char_buf[0] = ch;
 	  cp = char_buf;
-	  idx2 = findidx (&cp);
+	  idx2 = findidx (table, indirect, extra, &cp, 1);
 /*
 	  idx2 = table[ch];
 */

@@ -3630,6 +3683,13 @@ build_charclass_op (re_dfa_t *dfa, RE_TRANSLATE_TYPE trans,
   if (BE (sbcset == NULL, 0))
 #endif /* not RE_ENABLE_I18N */
     {
+      /* if one is not NULL, free it to avoid leaks */
+      if (sbcset != NULL)
+         free(sbcset);
+#ifdef RE_ENABLE_I18N
+      if (mbcset != NULL)
+         free(mbcset);
+#endif
       *err = REG_ESPACE;
       return NULL;
     }

@@ -3672,6 +3732,7 @@ build_charclass_op (re_dfa_t *dfa, RE_TRANSLATE_TYPE trans,
 #endif
 
   /* Build a tree for simple bracket.  */
+  memset(& br_token, 0, sizeof(br_token));	/* silence "not initialized" errors froms static checkers */
   br_token.type = SIMPLE_BRACKET;
   br_token.opr.sbcset = sbcset;
   tree = create_token_tree (dfa, NULL, NULL, &br_token);

@@ -3715,7 +3776,7 @@ build_charclass_op (re_dfa_t *dfa, RE_TRANSLATE_TYPE trans,
 /* This is intended for the expressions like "a{1,3}".
    Fetch a number from `input', and return the number.
    Return -1, if the number field is empty like "{,1}".
-   Return -2, if an error has occurred.  */
+   Return -2, If an error is occured.  */
 
 static int
 fetch_number (re_string_t *input, re_token_t *token, reg_syntax_t syntax)

@@ -3762,6 +3823,7 @@ create_tree (re_dfa_t *dfa, bin_tree_t *left, bin_tree_t *right,
 	     re_token_type_t type)
 {
   re_token_t t;
+  memset(& t, 0, sizeof(t));	/* silence "not initialized" errors froms static checkers */
   t.type = type;
   return create_token_tree (dfa, left, right, &t);
 }

@@ -3806,7 +3868,7 @@ 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)
 {
-  int idx = (int) (intptr_t) extra;
+  int idx = (int) (long) extra;
   if (node->token.type == SUBEXP && node->token.opr.idx == idx)
     node->token.opt_subexp = 1;
 

286 lines not on this page · raw message

index 5cb23e5d59..d6e525e567 100644
@@ -1,5 +1,12 @@
+/*
+ * This is git.git's copy of gawk.git's regex engine. Please see that
+ * project for the latest version & to submit patches to this code,
+ * and git.git's compat/regex/README for information on how git's copy
+ * of this code is maintained.
+ */
+
 /* Extended regular expression matching and search library.
-   Copyright (C) 2002, 2003, 2005 Free Software Foundation, Inc.
+   Copyright (C) 2002-2016 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
    Contributed by Isamu Hasegawa <[email protected]>.
 

@@ -14,15 +21,14 @@
    Lesser General Public License for more details.
 
    You should have received a copy of the GNU Lesser General Public
-   License along with the GNU C Library; if not, write to the Free
-   Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
-   02110-1301 USA.  */
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
 
 #ifdef HAVE_CONFIG_H
 #include "config.h"
 #endif
 
-/* Make sure no one compiles this code with a C++ compiler.  */
+/* Make sure noone compiles this code with a C++ compiler.  */
 #ifdef __cplusplus
 # error "This is C code, use a C compiler"
 #endif

@@ -52,15 +58,15 @@
 # include "../locale/localeinfo.h"
 #endif
 
-#if defined (_MSC_VER)
-#include <stdio.h> /* for size_t */
-#endif
-
 /* On some systems, limits.h sets RE_DUP_MAX to a lower value than
    GNU regex allows.  Include it before <regex.h>, which correctly
    #undefs RE_DUP_MAX and sets it to the right value.  */
 #include <limits.h>
-#include <stdint.h>
+
+/* This header defines the MIN and MAX macros.  */
+#ifdef HAVE_SYS_PARAM_H
+#include <sys/param.h>
+#endif /* HAVE_SYS_PARAM_H */
 
 #ifdef GAWK
 #undef alloca

@@ -70,10 +76,8 @@
 #include "regex_internal.h"
 
 #include "regex_internal.c"
-#ifdef GAWK
-#define bool int
-#define true (1)
-#define false (0)
+#ifndef HAVE_STDBOOL_H
+#include "missing_d/gawkbool.h"
 #endif
 #include "regcomp.c"
 #include "regexec.c"

index d4121f2f4f..6d766114a1 100644
@@ -1,5 +1,12 @@
+/*
+ * This is git.git's copy of gawk.git's regex engine. Please see that
+ * project for the latest version & to submit patches to this code,
+ * and git.git's compat/regex/README for information on how git's copy
+ * of this code is maintained.
+ */
+
 /* Extended regular expression matching and search library.
-   Copyright (C) 2002-2006, 2010 Free Software Foundation, Inc.
+   Copyright (C) 2002-2016 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
    Contributed by Isamu Hasegawa <[email protected]>.
 

@@ -14,9 +21,8 @@
    Lesser General Public License for more details.
 
    You should have received a copy of the GNU Lesser General Public
-   License along with the GNU C Library; if not, write to the Free
-   Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
-   02110-1301 USA.  */
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
 
 static void re_string_construct_common (const char *str, int len,
 					re_string_t *pstr,

@@ -45,7 +51,7 @@ MAX(size_t a, size_t b)
    re_string_reconstruct before using the object.  */
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 re_string_allocate (re_string_t *pstr, const char *str, int len, int init_len,
 		    RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa)
 {

@@ -73,7 +79,7 @@ re_string_allocate (re_string_t *pstr, const char *str, int len, int init_len,
 /* This function allocate the buffers, and initialize them.  */
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 re_string_construct (re_string_t *pstr, const char *str, int len,
 		     RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa)
 {

@@ -136,7 +142,7 @@ re_string_construct (re_string_t *pstr, const char *str, int len,
 /* Helper functions for re_string_allocate, and re_string_construct.  */
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 re_string_realloc_buffers (re_string_t *pstr, int new_buf_len)
 {
 #ifdef RE_ENABLE_I18N

@@ -246,13 +252,8 @@ build_wcs_buffer (re_string_t *pstr)
       else
 	p = (const char *) pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx;
       mbclen = __mbrtowc (&wc, p, remain_len, &pstr->cur_state);
-      if (BE (mbclen == (size_t) -2, 0))
-	{
-	  /* The buffer doesn't have enough space, finish to build.  */
-	  pstr->cur_state = prev_st;
-	  break;
-	}
-      else if (BE (mbclen == (size_t) -1 || mbclen == 0, 0))
+      if (BE (mbclen == (size_t) -1 || mbclen == 0
+	      || (mbclen == (size_t) -2 && pstr->bufs_len >= pstr->len), 0))
 	{
 	  /* We treat these cases as a singlebyte character.  */
 	  mbclen = 1;

@@ -261,6 +262,12 @@ build_wcs_buffer (re_string_t *pstr)
 	    wc = pstr->trans[wc];
 	  pstr->cur_state = prev_st;
 	}
+      else if (BE (mbclen == (size_t) -2, 0))
+	{
+	  /* The buffer doesn't have enough space, finish to build.  */
+	  pstr->cur_state = prev_st;
+	  break;
+	}
 
       /* Write wide character and padding.  */
       pstr->wcs[byte_idx++] = wc;

@@ -276,7 +283,7 @@ build_wcs_buffer (re_string_t *pstr)
    but for REG_ICASE.  */
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 build_wcs_upper_buffer (re_string_t *pstr)
 {
   mbstate_t prev_st;

@@ -326,7 +333,7 @@ build_wcs_upper_buffer (re_string_t *pstr)
 		  size_t mbcdlen;
 
 		  wcu = towupper (wc);
-		  mbcdlen = wcrtomb (buf, wcu, &prev_st);
+		  mbcdlen = __wcrtomb (buf, wcu, &prev_st);
 		  if (BE (mbclen == mbcdlen, 1))
 		    memcpy (pstr->mbs + byte_idx, buf, mbclen);
 		  else

@@ -343,9 +350,11 @@ build_wcs_upper_buffer (re_string_t *pstr)
 	      for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;)
 		pstr->wcs[byte_idx++] = WEOF;
 	    }
-	  else if (mbclen == (size_t) -1 || mbclen == 0)
+	  else if (mbclen == (size_t) -1 || mbclen == 0
+		   || (mbclen == (size_t) -2 && pstr->bufs_len >= pstr->len))
 	    {
-	      /* It is an invalid character or '\0'.  Just use the byte.  */
+	      /* It is an invalid character, an incomplete character
+		 at the end of the string, or '\0'.  Just use the byte.  */
 	      int ch = pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx];
 	      pstr->mbs[byte_idx] = ch;
 	      /* And also cast it to wide char.  */

@@ -458,7 +467,8 @@ build_wcs_upper_buffer (re_string_t *pstr)
 	    for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;)
 	      pstr->wcs[byte_idx++] = WEOF;
 	  }
-	else if (mbclen == (size_t) -1 || mbclen == 0)
+	else if (mbclen == (size_t) -1 || mbclen == 0
+		 || (mbclen == (size_t) -2 && pstr->bufs_len >= pstr->len))
 	  {
 	    /* It is an invalid character or '\0'.  Just use the byte.  */
 	    int ch = pstr->raw_mbs[pstr->raw_mbs_idx + src_idx];

@@ -505,11 +515,11 @@ re_string_skip_chars (re_string_t *pstr, int new_raw_idx, wint_t *last_wc)
        rawbuf_idx < new_raw_idx;)
     {
       wchar_t wc2;
-      int remain_len = pstr->len - rawbuf_idx;
+      int remain_len = pstr->raw_len - rawbuf_idx;
       prev_st = pstr->cur_state;
       mbclen = __mbrtowc (&wc2, (const char *) pstr->raw_mbs + rawbuf_idx,
 			  remain_len, &pstr->cur_state);
-      if (BE (mbclen == (size_t) -2 || mbclen == (size_t) -1 || mbclen == 0, 0))
+      if (BE ((ssize_t) mbclen <= 0, 0))
 	{
 	  /* We treat these cases as a single byte character.  */
 	  if (mbclen == 0 || remain_len == 0)

@@ -577,7 +587,7 @@ re_string_translate_buffer (re_string_t *pstr)
    convert to upper case in case of REG_ICASE, apply translation.  */
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 re_string_reconstruct (re_string_t *pstr, int idx, int eflags)
 {
   int offset = idx - pstr->raw_mbs_idx;

@@ -685,7 +695,7 @@ re_string_reconstruct (re_string_t *pstr, int idx, int eflags)
 			 pstr->valid_len - offset);
 	      pstr->valid_len -= offset;
 	      pstr->valid_raw_len -= offset;
-#if DEBUG
+#if defined DEBUG && DEBUG
 	      assert (pstr->valid_len > 0);
 #endif
 	    }

@@ -741,16 +751,18 @@ re_string_reconstruct (re_string_t *pstr, int idx, int eflags)
 			  unsigned char buf[6];
 			  size_t mbclen;
 
+			  const unsigned char *pp = p;
 			  if (BE (pstr->trans != NULL, 0))
 			    {
 			      int i = mlen < 6 ? mlen : 6;
 			      while (--i >= 0)
 				buf[i] = pstr->trans[p[i]];
+			      pp = buf;
 			    }
 			  /* XXX Don't use mbrtowc, we know which conversion
 			     to use (UTF-8 -> UCS4).  */
 			  memset (&cur_state, 0, sizeof (cur_state));
-			  mbclen = __mbrtowc (&wc2, (const char *) p, mlen,
+			  mbclen = __mbrtowc (&wc2, (const char *) pp, mlen,
 					      &cur_state);
 			  if (raw + offset - p <= mbclen
 			      && mbclen < (size_t) -2)

@@ -835,7 +847,7 @@ 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;

@@ -871,7 +883,7 @@ re_string_peek_byte_case (const re_string_t *pstr, int idx)
 }
 
 static unsigned char
-internal_function __attribute ((pure))
+internal_function
 re_string_fetch_byte_case (re_string_t *pstr)
 {
   if (BE (!pstr->mbs_allocated, 1))

@@ -940,7 +952,7 @@ re_string_context_at (const re_string_t *input, int idx, int eflags)
       int wc_idx = idx;
       while(input->wcs[wc_idx] == WEOF)
 	{
-#ifdef DEBUG
+#if defined DEBUG && DEBUG
 	  /* It must not happen.  */
 	  assert (wc_idx >= 0);
 #endif

@@ -967,7 +979,7 @@ re_string_context_at (const re_string_t *input, int idx, int eflags)
 /* Functions for set operation.  */
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 re_node_set_alloc (re_node_set *set, int size)
 {
   /*

@@ -989,7 +1001,7 @@ re_node_set_alloc (re_node_set *set, int size)
 }
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 re_node_set_init_1 (re_node_set *set, int elem)
 {
   set->alloc = 1;

@@ -1005,7 +1017,7 @@ re_node_set_init_1 (re_node_set *set, int elem)
 }
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 re_node_set_init_2 (re_node_set *set, int elem1, int elem2)
 {
   set->alloc = 2;

@@ -1035,7 +1047,7 @@ re_node_set_init_2 (re_node_set *set, int elem1, int elem2)
 }
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 re_node_set_init_copy (re_node_set *dest, const re_node_set *src)
 {
   dest->nelem = src->nelem;

@@ -1060,7 +1072,7 @@ re_node_set_init_copy (re_node_set *dest, const re_node_set *src)
    Note: We assume dest->elems is NULL, when dest->alloc is 0.  */
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 re_node_set_add_intersect (re_node_set *dest, const re_node_set *src1,
 			   const re_node_set *src2)
 {

@@ -1151,7 +1163,7 @@ re_node_set_add_intersect (re_node_set *dest, const re_node_set *src1,
    DEST. Return value indicate the error code or REG_NOERROR if succeeded.  */
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 re_node_set_init_union (re_node_set *dest, const re_node_set *src1,
 			const re_node_set *src2)
 {

@@ -1204,7 +1216,7 @@ re_node_set_init_union (re_node_set *dest, const re_node_set *src1,
    DEST. Return value indicate the error code or REG_NOERROR if succeeded.  */
 
 static reg_errcode_t
-internal_function
+internal_function __attribute_warn_unused_result__
 re_node_set_merge (re_node_set *dest, const re_node_set *src)
 {
   int is, id, sbase, delta;

@@ -1284,10 +1296,10 @@ re_node_set_merge (re_node_set *dest, const re_node_set *src)
 
 /* Insert the new element ELEM to the re_node_set* SET.
    SET should not already have ELEM.
-   return -1 if an error has occurred, return 1 otherwise.  */
+   return -1 if an error is occured, return 1 otherwise.  */
 
 static int
-internal_function
+internal_function __attribute_warn_unused_result__
 re_node_set_insert (re_node_set *set, int elem)
 {
   int idx;

@@ -1341,10 +1353,10 @@ re_node_set_insert (re_node_set *set, int elem)
 
 /* Insert the new element ELEM to the re_node_set* SET.
    SET should not already have any element greater than or equal to ELEM.
-   Return -1 if an error has occurred, return 1 otherwise.  */
+   Return -1 if an error is occured, return 1 otherwise.  */
 
 static int
-internal_function
+internal_function __attribute_warn_unused_result__
 re_node_set_insert_last (re_node_set *set, int elem)
 {
   /* Realloc if we need.  */

@@ -1367,7 +1379,7 @@ 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;

@@ -1382,7 +1394,7 @@ 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;

@@ -1416,7 +1428,7 @@ re_node_set_remove_at (re_node_set *set, int idx)
 
 
 /* Add the token TOKEN to dfa->nodes, and return the index of the token.
-   Or return -1, if an error has occurred.  */
+   Or return -1, if an error will be occured.  */
 
 static int
 internal_function

@@ -1446,7 +1458,18 @@ re_dfa_add_node (re_dfa_t *dfa, re_token_t token)
       new_eclosures = re_realloc (dfa->eclosures, re_node_set, new_nodes_alloc);
       if (BE (new_nexts == NULL || new_indices == NULL
 	      || new_edests == NULL || new_eclosures == NULL, 0))
-	return -1;
+        {
+	   /* if any are not NULL, free them, avoid leaks */
+	   if (new_nexts != NULL)
+              re_free(new_nexts);
+	   if (new_indices != NULL)
+              re_free(new_indices);
+	   if (new_edests != NULL)
+              re_free(new_edests);
+	   if (new_eclosures != NULL)
+              re_free(new_eclosures);
+	   return -1;
+	}
       dfa->nexts = new_nexts;
       dfa->org_indices = new_indices;
       dfa->edests = new_edests;

@@ -1486,7 +1509,7 @@ calc_state_hash (const re_node_set *nodes, unsigned int context)
 	   optimization.  */
 
 static re_dfastate_t *
-internal_function
+internal_function __attribute_warn_unused_result__
 re_acquire_state (reg_errcode_t *err, const re_dfa_t *dfa,
 		  const re_node_set *nodes)
 {

@@ -1530,7 +1553,7 @@ re_acquire_state (reg_errcode_t *err, const re_dfa_t *dfa,
 	   optimization.  */
 
 static re_dfastate_t *
-internal_function
+internal_function __attribute_warn_unused_result__
 re_acquire_state_context (reg_errcode_t *err, const re_dfa_t *dfa,
 			  const re_node_set *nodes, unsigned int context)
 {

@@ -1567,6 +1590,7 @@ re_acquire_state_context (reg_errcode_t *err, const re_dfa_t *dfa,
    indicates the error code if failed.  */
 
 static reg_errcode_t
+__attribute_warn_unused_result__
 register_state (const re_dfa_t *dfa, re_dfastate_t *newstate,
 		unsigned int hash)
 {

@@ -1617,11 +1641,11 @@ free_state (re_dfastate_t *state)
   re_free (state);
 }
 
-/* Create the new state which is independ of contexts.
+/* Create the new state which is independent of contexts.
    Return the new state if succeeded, otherwise return NULL.  */
 
 static re_dfastate_t *
-internal_function
+internal_function __attribute_warn_unused_result__
 create_ci_newstate (const re_dfa_t *dfa, const re_node_set *nodes,
 		    unsigned int hash)
 {

@@ -1671,7 +1695,7 @@ create_ci_newstate (const re_dfa_t *dfa, const re_node_set *nodes,
    Return the new state if succeeded, otherwise return NULL.  */
 
 static re_dfastate_t *
-internal_function
+internal_function __attribute_warn_unused_result__
 create_cd_newstate (const re_dfa_t *dfa, const re_node_set *nodes,
 		    unsigned int context, unsigned int hash)
 {

244 lines not on this page · raw message

index 61c9683872..b602b5567f 100644
@@ -1,10 +1,13 @@
-#include <stdio.h>
-#include <stddef.h>
+/*
+ * This is git.git's copy of gawk.git's regex engine. Please see that
+ * project for the latest version & to submit patches to this code,
+ * and git.git's compat/regex/README for information on how git's copy
+ * of this code is maintained.
+ */
 
 /* Definitions for data structures and routines for the regular
    expression library.
-   Copyright (C) 1985,1989-93,1995-98,2000,2001,2002,2003,2005,2006,2008
-   Free Software Foundation, Inc.
+   Copyright (C) 1985, 1989-2016 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
 
    The GNU C Library is free software; you can redistribute it and/or

@@ -18,9 +21,8 @@
    Lesser General Public License for more details.
 
    You should have received a copy of the GNU Lesser General Public
-   License along with the GNU C Library; if not, write to the Free
-   Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
-   02110-1301 USA.  */
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
 
 #ifndef _REGEX_H
 #define _REGEX_H 1

@@ -75,10 +77,10 @@ typedef unsigned long int reg_syntax_t;
 /* If this bit is set, then ^ and $ are always anchors (outside bracket
      expressions, of course).
    If this bit is not set, then it depends:
-        ^  is an anchor if it is at the beginning of a regular
-           expression or after an open-group or an alternation operator;
-        $  is an anchor if it is at the end of a regular expression, or
-           before a close-group or an alternation operator.
+	^  is an anchor if it is at the beginning of a regular
+	   expression or after an open-group or an alternation operator;
+	$  is an anchor if it is at the end of a regular expression, or
+	   before a close-group or an alternation operator.
 
    This bit could be (re)combined with RE_CONTEXT_INDEP_OPS, because
    POSIX draft 11.2 says that * etc. in leading positions is undefined.

@@ -158,10 +160,18 @@ typedef unsigned long int reg_syntax_t;
    If not set, then the GNU regex operators are recognized. */
 # define RE_NO_GNU_OPS (RE_NO_POSIX_BACKTRACKING << 1)
 
+/* If this bit is set, turn on internal regex debugging.
+   If not set, and debugging was on, turn it off.
+   This only works if regex.c is compiled -DDEBUG.
+   We define this bit always, so that all that's needed to turn on
+   debugging is to recompile regex.c; the calling code can always have
+   this bit set, and it won't affect anything in the normal case. */
+# define RE_DEBUG (RE_NO_GNU_OPS << 1)
+
 /* If this bit is set, a syntactically invalid interval is treated as
    a string of ordinary characters.  For example, the ERE 'a{1' is
    treated as 'a\{1'.  */
-# define RE_INVALID_INTERVAL_ORD (RE_NO_GNU_OPS << 1)
+# define RE_INVALID_INTERVAL_ORD (RE_DEBUG << 1)
 
 /* If this bit is set, then ignore case when matching.
    If not set, then case is significant.  */

@@ -178,7 +188,7 @@ typedef unsigned long int reg_syntax_t;
 
 /* If this bit is set, then no_sub will be set to 1 during
    re_compile_pattern.  */
-#define RE_NO_SUB (RE_CONTEXT_INVALID_DUP << 1)
+# define RE_NO_SUB (RE_CONTEXT_INVALID_DUP << 1)
 #endif
 
 /* This global variable defines the particular regexp syntax to use (for

@@ -199,13 +209,14 @@ extern reg_syntax_t re_syntax_options;
    | RE_NO_BK_PARENS              | RE_NO_BK_REFS			\
    | RE_NO_BK_VBAR                | RE_NO_EMPTY_RANGES			\
    | RE_DOT_NEWLINE		  | RE_CONTEXT_INDEP_ANCHORS		\
+   | RE_CHAR_CLASSES							\
    | RE_UNMATCHED_RIGHT_PAREN_ORD | RE_NO_GNU_OPS)
 
 #define RE_SYNTAX_GNU_AWK						\
   ((RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS		\
-   | RE_INVALID_INTERVAL_ORD)						\
+    | RE_INVALID_INTERVAL_ORD)						\
    & ~(RE_DOT_NOT_NULL | RE_CONTEXT_INDEP_OPS				\
-       | RE_CONTEXT_INVALID_OPS ))
+      | RE_CONTEXT_INVALID_OPS ))
 
 #define RE_SYNTAX_POSIX_AWK						\
   (RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS		\

@@ -323,7 +334,7 @@ typedef enum
   /* POSIX regcomp return error codes.  (In the order listed in the
      standard.)  */
   REG_BADPAT,		/* Invalid pattern.  */
-  REG_ECOLLATE,		/* Inalid collating element.  */
+  REG_ECOLLATE,		/* Invalid collating element.  */
   REG_ECTYPE,		/* Invalid character class name.  */
   REG_EESCAPE,		/* Trailing backslash.  */
   REG_ESUBREG,		/* Invalid back reference.  */

@@ -343,9 +354,9 @@ typedef enum
 
 /* This data structure represents a compiled pattern.  Before calling
    the pattern compiler, the fields `buffer', `allocated', `fastmap',
-   `translate', and `no_sub' can be set.  After the pattern has been
-   compiled, the `re_nsub' field is available.  All other fields are
-   private to the regex routines.  */
+   and `translate' can be set.  After the pattern has been compiled,
+   the fields `re_nsub', `not_bol' and `not_eol' are available.  All
+   other fields are private to the regex routines.  */
 
 #ifndef RE_TRANSLATE_TYPE
 # define __RE_TRANSLATE_TYPE unsigned char *

@@ -466,19 +477,24 @@ typedef struct
 #ifdef __USE_GNU
 /* Sets the current default syntax to SYNTAX, and return the old syntax.
    You can also simply assign to the `re_syntax_options' variable.  */
-extern reg_syntax_t re_set_syntax (reg_syntax_t __syntax);
+extern reg_syntax_t re_set_syntax (reg_syntax_t syntax);
 
 /* Compile the regular expression PATTERN, with length LENGTH
    and syntax given by the global `re_syntax_options', into the buffer
-   BUFFER.  Return NULL if successful, and an error string if not.  */
-extern const char *re_compile_pattern (const char *__pattern, size_t __length,
-				       struct re_pattern_buffer *__buffer);
+   BUFFER.  Return NULL if successful, and an error string if not.
+
+   To free the allocated storage, you must call `regfree' on BUFFER.
+   Note that the translate table must either have been initialised by
+   `regcomp', with a malloc'ed value, or set to NULL before calling
+   `regfree'.  */
+extern const char *re_compile_pattern (const char *pattern, size_t length,
+				       struct re_pattern_buffer *buffer);
 
 
 /* Compile a fastmap for the compiled pattern in BUFFER; used to
    accelerate searches.  Return 0 if successful and -2 if was an
    internal error.  */
-extern int re_compile_fastmap (struct re_pattern_buffer *__buffer);
+extern int re_compile_fastmap (struct re_pattern_buffer *buffer);
 
 
 /* Search in the string STRING (with length LENGTH) for the pattern

@@ -486,30 +502,30 @@ extern int re_compile_fastmap (struct re_pattern_buffer *__buffer);
    characters.  Return the starting position of the match, -1 for no
    match, or -2 for an internal error.  Also return register
    information in REGS (if REGS and BUFFER->no_sub are nonzero).  */
-extern int re_search (struct re_pattern_buffer *__buffer, const char *__cstring,
-		      int __length, int __start, int __range,
-		      struct re_registers *__regs);
+extern int re_search (struct re_pattern_buffer *buffer, const char *c_string,
+		      int length, int start, int range,
+		      struct re_registers *regs);
 
 
 /* Like `re_search', but search in the concatenation of STRING1 and
    STRING2.  Also, stop searching at index START + STOP.  */
-extern int re_search_2 (struct re_pattern_buffer *__buffer,
-			const char *__string1, int __length1,
-			const char *__string2, int __length2, int __start,
-			int __range, struct re_registers *__regs, int __stop);
+extern int re_search_2 (struct re_pattern_buffer *buffer,
+			const char *string1, int length1,
+			const char *string2, int length2, int start,
+			int range, struct re_registers *regs, int stop);
 
 
 /* Like `re_search', but return how many characters in STRING the regexp
    in BUFFER matched, starting at position START.  */
-extern int re_match (struct re_pattern_buffer *__buffer, const char *__cstring,
-		     int __length, int __start, struct re_registers *__regs);
+extern int re_match (struct re_pattern_buffer *buffer, const char *c_string,
+		     int length, int start, struct re_registers *regs);
 
 
 /* Relates to `re_match' as `re_search_2' relates to `re_search'.  */
-extern int re_match_2 (struct re_pattern_buffer *__buffer,
-		       const char *__string1, int __length1,
-		       const char *__string2, int __length2, int __start,
-		       struct re_registers *__regs, int __stop);
+extern int re_match_2 (struct re_pattern_buffer *buffer,
+		       const char *string1, int length1,
+		       const char *string2, int length2, int start,
+		       struct re_registers *regs, int stop);
 
 
 /* Set REGS to hold NUM_REGS registers, storing them in STARTS and

@@ -524,13 +540,13 @@ extern int re_match_2 (struct re_pattern_buffer *__buffer,
    Unless this function is called, the first search or match using
    PATTERN_BUFFER will allocate its own register data, without
    freeing the old data.  */
-extern void re_set_registers (struct re_pattern_buffer *__buffer,
-			      struct re_registers *__regs,
-			      unsigned int __num_regs,
-			      regoff_t *__starts, regoff_t *__ends);
+extern void re_set_registers (struct re_pattern_buffer *buffer,
+			      struct re_registers *regs,
+			      unsigned int num_regs,
+			      regoff_t *starts, regoff_t *ends);
 #endif	/* Use GNU */
 
-#if defined _REGEX_RE_COMP || (defined _LIBC && defined __USE_BSD)
+#if defined _REGEX_RE_COMP || (defined _LIBC && defined __USE_MISC)
 # ifndef _CRAY
 /* 4.2 bsd compatibility.  */
 extern char *re_comp (const char *);

@@ -560,19 +576,19 @@ extern int re_exec (const char *);
 #endif
 
 /* POSIX compatibility.  */
-extern int regcomp (regex_t *__restrict __preg,
-		    const char *__restrict __pattern,
-		    int __cflags);
+extern int regcomp (regex_t *__restrict preg,
+		    const char *__restrict pattern,
+		    int cflags);
 
-extern int regexec (const regex_t *__restrict __preg,
-		    const char *__restrict __cstring, size_t __nmatch,
-		    regmatch_t __pmatch[__restrict_arr],
-		    int __eflags);
+extern int regexec (const regex_t *__restrict preg,
+		    const char *__restrict c_string, size_t nmatch,
+		    regmatch_t pmatch[__restrict_arr],
+		    int eflags);
 
-extern size_t regerror (int __errcode, const regex_t *__restrict __preg,
-			char *__restrict __errbuf, size_t __errbuf_size);
+extern size_t regerror (int errcode, const regex_t *__restrict preg,
+			char *__restrict errbuf, size_t errbuf_size);
 
-extern void regfree (regex_t *__preg);
+extern void regfree (regex_t *preg);
 
 
 #ifdef __cplusplus

634 lines not on this page · raw message

new file mode 100644
index 0000000000..29f7f40837
@@ -0,0 +1,448 @@
+/*
+ * This is git.git's copy of gawk.git's regex engine. Please see that
+ * project for the latest version & to submit patches to this code,
+ * and git.git's compat/regex/README for information on how git's copy
+ * of this code is maintained.
+ */
+
+/* intprops.h -- properties of integer types
+
+   Copyright (C) 2001-2016 Free Software Foundation, Inc.
+
+   This program 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,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   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 Lesser General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+/* Written by Paul Eggert.  */
+
+#ifndef _GL_INTPROPS_H
+#define _GL_INTPROPS_H
+
+#include <limits.h>
+
+#ifndef __has_builtin
+# define __has_builtin(x) 0
+#endif
+
+/* Return a value with the common real type of E and V and the value of V.  */
+#define _GL_INT_CONVERT(e, v) (0 * (e) + (v))
+
+/* Act like _GL_INT_CONVERT (E, -V) but work around a bug in IRIX 6.5 cc; see
+   <http://lists.gnu.org/archive/html/bug-gnulib/2011-05/msg00406.html>.  */
+#define _GL_INT_NEGATE_CONVERT(e, v) (0 * (e) - (v))
+
+/* The extra casts in the following macros work around compiler bugs,
+   e.g., in Cray C 5.0.3.0.  */
+
+/* True if the arithmetic type T is an integer type.  bool counts as
+   an integer.  */
+#define TYPE_IS_INTEGER(t) ((t) 1.5 == 1)
+
+/* True if the real type T is signed.  */
+#define TYPE_SIGNED(t) (! ((t) 0 < (t) -1))
+
+/* Return 1 if the real expression E, after promotion, has a
+   signed or floating type.  */
+#define EXPR_SIGNED(e) (_GL_INT_NEGATE_CONVERT (e, 1) < 0)
+
+
+/* Minimum and maximum values for integer types and expressions.  */
+
+/* The width in bits of the integer type or expression T.
+   Padding bits are not supported; this is checked at compile-time below.  */
+#define TYPE_WIDTH(t) (sizeof (t) * CHAR_BIT)
+
+/* The maximum and minimum values for the integer type T.  */
+#define TYPE_MINIMUM(t) ((t) ~ TYPE_MAXIMUM (t))
+#define TYPE_MAXIMUM(t)                                                 \
+  ((t) (! TYPE_SIGNED (t)                                               \
+        ? (t) -1                                                        \
+        : ((((t) 1 << (TYPE_WIDTH (t) - 2)) - 1) * 2 + 1)))
+
+/* The maximum and minimum values for the type of the expression E,
+   after integer promotion.  E should not have side effects.  */
+#define _GL_INT_MINIMUM(e)                                              \
+  (EXPR_SIGNED (e)                                                      \
+   ? ~ _GL_SIGNED_INT_MAXIMUM (e)                                       \
+   : _GL_INT_CONVERT (e, 0))
+#define _GL_INT_MAXIMUM(e)                                              \
+  (EXPR_SIGNED (e)                                                      \
+   ? _GL_SIGNED_INT_MAXIMUM (e)                                         \
+   : _GL_INT_NEGATE_CONVERT (e, 1))
+#define _GL_SIGNED_INT_MAXIMUM(e)                                       \
+  (((_GL_INT_CONVERT (e, 1) << (TYPE_WIDTH ((e) + 0) - 2)) - 1) * 2 + 1)
+
+/* Work around OpenVMS incompatibility with C99.  */
+#if !defined LLONG_MAX && defined __INT64_MAX
+# define LLONG_MAX __INT64_MAX
+# define LLONG_MIN __INT64_MIN
+#endif
+
+/* Does the __typeof__ keyword work?  This could be done by
+   'configure', but for now it's easier to do it by hand.  */
+#if (2 <= __GNUC__ \
+     || (1210 <= __IBMC__ && defined __IBM__TYPEOF__) \
+     || (0x5110 <= __SUNPRO_C && !__STDC__))
+# define _GL_HAVE___TYPEOF__ 1
+#else
+# define _GL_HAVE___TYPEOF__ 0
+#endif
+
+/* Return 1 if the integer type or expression T might be signed.  Return 0
+   if it is definitely unsigned.  This macro does not evaluate its argument,
+   and expands to an integer constant expression.  */
+#if _GL_HAVE___TYPEOF__
+# define _GL_SIGNED_TYPE_OR_EXPR(t) TYPE_SIGNED (__typeof__ (t))
+#else
+# define _GL_SIGNED_TYPE_OR_EXPR(t) 1
+#endif
+
+/* Bound on length of the string representing an unsigned integer
+   value representable in B bits.  log10 (2.0) < 146/485.  The
+   smallest value of B where this bound is not tight is 2621.  */
+#define INT_BITS_STRLEN_BOUND(b) (((b) * 146 + 484) / 485)
+
+/* Bound on length of the string representing an integer type or expression T.
+   Subtract 1 for the sign bit if T is signed, and then add 1 more for
+   a minus sign if needed.
+
+   Because _GL_SIGNED_TYPE_OR_EXPR sometimes returns 0 when its argument is
+   signed, this macro may overestimate the true bound by one byte when
+   applied to unsigned types of size 2, 4, 16, ... bytes.  */
+#define INT_STRLEN_BOUND(t)                                     \
+  (INT_BITS_STRLEN_BOUND (TYPE_WIDTH (t) - _GL_SIGNED_TYPE_OR_EXPR (t)) \
+   + _GL_SIGNED_TYPE_OR_EXPR (t))
+
+/* Bound on buffer size needed to represent an integer type or expression T,
+   including the terminating null.  */
+#define INT_BUFSIZE_BOUND(t) (INT_STRLEN_BOUND (t) + 1)
+
+
+/* Range overflow checks.
+
+   The INT_<op>_RANGE_OVERFLOW macros return 1 if the corresponding C
+   operators might not yield numerically correct answers due to
+   arithmetic overflow.  They do not rely on undefined or
+   implementation-defined behavior.  Their implementations are simple
+   and straightforward, but they are a bit harder to use than the
+   INT_<op>_OVERFLOW macros described below.
+
+   Example usage:
+
+     long int i = ...;
+     long int j = ...;
+     if (INT_MULTIPLY_RANGE_OVERFLOW (i, j, LONG_MIN, LONG_MAX))
+       printf ("multiply would overflow");
+     else
+       printf ("product is %ld", i * j);
+
+   Restrictions on *_RANGE_OVERFLOW macros:
+
+   These macros do not check for all possible numerical problems or
+   undefined or unspecified behavior: they do not check for division
+   by zero, for bad shift counts, or for shifting negative numbers.
+
+   These macros may evaluate their arguments zero or multiple times,
+   so the arguments should not have side effects.  The arithmetic
+   arguments (including the MIN and MAX arguments) must be of the same
+   integer type after the usual arithmetic conversions, and the type
+   must have minimum value MIN and maximum MAX.  Unsigned types should
+   use a zero MIN of the proper type.
+
+   These macros are tuned for constant MIN and MAX.  For commutative
+   operations such as A + B, they are also tuned for constant B.  */
+
+/* Return 1 if A + B would overflow in [MIN,MAX] arithmetic.
+   See above for restrictions.  */
+#define INT_ADD_RANGE_OVERFLOW(a, b, min, max)          \
+  ((b) < 0                                              \
+   ? (a) < (min) - (b)                                  \
+   : (max) - (b) < (a))
+
+/* Return 1 if A - B would overflow in [MIN,MAX] arithmetic.
+   See above for restrictions.  */
+#define INT_SUBTRACT_RANGE_OVERFLOW(a, b, min, max)     \
+  ((b) < 0                                              \
+   ? (max) + (b) < (a)                                  \
+   : (a) < (min) + (b))
+
+/* Return 1 if - A would overflow in [MIN,MAX] arithmetic.
+   See above for restrictions.  */
+#define INT_NEGATE_RANGE_OVERFLOW(a, min, max)          \
+  ((min) < 0                                            \
+   ? (a) < - (max)                                      \
+   : 0 < (a))
+
+/* Return 1 if A * B would overflow in [MIN,MAX] arithmetic.
+   See above for restrictions.  Avoid && and || as they tickle
+   bugs in Sun C 5.11 2010/08/13 and other compilers; see
+   <http://lists.gnu.org/archive/html/bug-gnulib/2011-05/msg00401.html>.  */
+#define INT_MULTIPLY_RANGE_OVERFLOW(a, b, min, max)     \
+  ((b) < 0                                              \
+   ? ((a) < 0                                           \
+      ? (a) < (max) / (b)                               \
+      : (b) == -1                                       \
+      ? 0                                               \
+      : (min) / (b) < (a))                              \
+   : (b) == 0                                           \
+   ? 0                                                  \
+   : ((a) < 0                                           \
+      ? (a) < (min) / (b)                               \
+      : (max) / (b) < (a)))
+
+/* Return 1 if A / B would overflow in [MIN,MAX] arithmetic.
+   See above for restrictions.  Do not check for division by zero.  */
+#define INT_DIVIDE_RANGE_OVERFLOW(a, b, min, max)       \
+  ((min) < 0 && (b) == -1 && (a) < - (max))
+
+/* Return 1 if A % B would overflow in [MIN,MAX] arithmetic.
+   See above for restrictions.  Do not check for division by zero.
+   Mathematically, % should never overflow, but on x86-like hosts
+   INT_MIN % -1 traps, and the C standard permits this, so treat this
+   as an overflow too.  */
+#define INT_REMAINDER_RANGE_OVERFLOW(a, b, min, max)    \
+  INT_DIVIDE_RANGE_OVERFLOW (a, b, min, max)
+
+/* Return 1 if A << B would overflow in [MIN,MAX] arithmetic.
+   See above for restrictions.  Here, MIN and MAX are for A only, and B need
+   not be of the same type as the other arguments.  The C standard says that
+   behavior is undefined for shifts unless 0 <= B < wordwidth, and that when
+   A is negative then A << B has undefined behavior and A >> B has
+   implementation-defined behavior, but do not check these other
+   restrictions.  */
+#define INT_LEFT_SHIFT_RANGE_OVERFLOW(a, b, min, max)   \
+  ((a) < 0                                              \
+   ? (a) < (min) >> (b)                                 \
+   : (max) >> (b) < (a))
+
+/* True if __builtin_add_overflow (A, B, P) works when P is non-null.  */
+#define _GL_HAS_BUILTIN_OVERFLOW \
+  (5 <= __GNUC__ || __has_builtin (__builtin_add_overflow))
+
+/* True if __builtin_add_overflow_p (A, B, C) works.  */
+#define _GL_HAS_BUILTIN_OVERFLOW_P \
+  (7 <= __GNUC__ || __has_builtin (__builtin_add_overflow_p))
+
+/* The _GL*_OVERFLOW macros have the same restrictions as the
+   *_RANGE_OVERFLOW macros, except that they do not assume that operands
+   (e.g., A and B) have the same type as MIN and MAX.  Instead, they assume
+   that the result (e.g., A + B) has that type.  */
+#if _GL_HAS_BUILTIN_OVERFLOW_P
+# define _GL_ADD_OVERFLOW(a, b, min, max)                               \
+   __builtin_add_overflow_p (a, b, (__typeof__ ((a) + (b))) 0)
+# define _GL_SUBTRACT_OVERFLOW(a, b, min, max)                          \
+   __builtin_sub_overflow_p (a, b, (__typeof__ ((a) - (b))) 0)
+# define _GL_MULTIPLY_OVERFLOW(a, b, min, max)                          \
+   __builtin_mul_overflow_p (a, b, (__typeof__ ((a) * (b))) 0)
+#else
+# define _GL_ADD_OVERFLOW(a, b, min, max)                                \
+   ((min) < 0 ? INT_ADD_RANGE_OVERFLOW (a, b, min, max)                  \
+    : (a) < 0 ? (b) <= (a) + (b)                                         \
+    : (b) < 0 ? (a) <= (a) + (b)                                         \
+    : (a) + (b) < (b))
+# define _GL_SUBTRACT_OVERFLOW(a, b, min, max)                           \
+   ((min) < 0 ? INT_SUBTRACT_RANGE_OVERFLOW (a, b, min, max)             \
+    : (a) < 0 ? 1                                                        \
+    : (b) < 0 ? (a) - (b) <= (a)                                         \
+    : (a) < (b))
+# define _GL_MULTIPLY_OVERFLOW(a, b, min, max)                           \
+   (((min) == 0 && (((a) < 0 && 0 < (b)) || ((b) < 0 && 0 < (a))))       \
+    || INT_MULTIPLY_RANGE_OVERFLOW (a, b, min, max))
+#endif
+#define _GL_DIVIDE_OVERFLOW(a, b, min, max)                             \
+  ((min) < 0 ? (b) == _GL_INT_NEGATE_CONVERT (min, 1) && (a) < - (max)  \
+   : (a) < 0 ? (b) <= (a) + (b) - 1                                     \
+   : (b) < 0 && (a) + (b) <= (a))
+#define _GL_REMAINDER_OVERFLOW(a, b, min, max)                          \
+  ((min) < 0 ? (b) == _GL_INT_NEGATE_CONVERT (min, 1) && (a) < - (max)  \
+   : (a) < 0 ? (a) % (b) != ((max) - (b) + 1) % (b)                     \
+   : (b) < 0 && ! _GL_UNSIGNED_NEG_MULTIPLE (a, b, max))
+
+/* Return a nonzero value if A is a mathematical multiple of B, where
+   A is unsigned, B is negative, and MAX is the maximum value of A's
+   type.  A's type must be the same as (A % B)'s type.  Normally (A %
+   -B == 0) suffices, but things get tricky if -B would overflow.  */
+#define _GL_UNSIGNED_NEG_MULTIPLE(a, b, max)                            \
+  (((b) < -_GL_SIGNED_INT_MAXIMUM (b)                                   \
+    ? (_GL_SIGNED_INT_MAXIMUM (b) == (max)                              \
+       ? (a)                                                            \
+       : (a) % (_GL_INT_CONVERT (a, _GL_SIGNED_INT_MAXIMUM (b)) + 1))   \
+    : (a) % - (b))                                                      \
+   == 0)
+
+/* Check for integer overflow, and report low order bits of answer.
+
+   The INT_<op>_OVERFLOW macros return 1 if the corresponding C operators
+   might not yield numerically correct answers due to arithmetic overflow.
+   The INT_<op>_WRAPV macros also store the low-order bits of the answer.
+   These macros work correctly on all known practical hosts, and do not rely
+   on undefined behavior due to signed arithmetic overflow.
+
+   Example usage, assuming A and B are long int:
+
+     if (INT_MULTIPLY_OVERFLOW (a, b))
+       printf ("result would overflow\n");
+     else
+       printf ("result is %ld (no overflow)\n", a * b);
+
+   Example usage with WRAPV flavor:
+
+     long int result;
+     bool overflow = INT_MULTIPLY_WRAPV (a, b, &result);
+     printf ("result is %ld (%s)\n", result,
+             overflow ? "after overflow" : "no overflow");
+
+   Restrictions on these macros:
+
+   These macros do not check for all possible numerical problems or
+   undefined or unspecified behavior: they do not check for division
+   by zero, for bad shift counts, or for shifting negative numbers.
+
+   These macros may evaluate their arguments zero or multiple times, so the
+   arguments should not have side effects.
+
+   The WRAPV macros are not constant expressions.  They support only
+   +, binary -, and *.  The result type must be signed.
+
+   These macros are tuned for their last argument being a constant.
+
+   Return 1 if the integer expressions A * B, A - B, -A, A * B, A / B,
+   A % B, and A << B would overflow, respectively.  */
+
+#define INT_ADD_OVERFLOW(a, b) \
+  _GL_BINARY_OP_OVERFLOW (a, b, _GL_ADD_OVERFLOW)
+#define INT_SUBTRACT_OVERFLOW(a, b) \
+  _GL_BINARY_OP_OVERFLOW (a, b, _GL_SUBTRACT_OVERFLOW)
+#if _GL_HAS_BUILTIN_OVERFLOW_P
+# define INT_NEGATE_OVERFLOW(a) INT_SUBTRACT_OVERFLOW (0, a)
+#else
+# define INT_NEGATE_OVERFLOW(a) \
+   INT_NEGATE_RANGE_OVERFLOW (a, _GL_INT_MINIMUM (a), _GL_INT_MAXIMUM (a))
+#endif
+#define INT_MULTIPLY_OVERFLOW(a, b) \
+  _GL_BINARY_OP_OVERFLOW (a, b, _GL_MULTIPLY_OVERFLOW)
+#define INT_DIVIDE_OVERFLOW(a, b) \
+  _GL_BINARY_OP_OVERFLOW (a, b, _GL_DIVIDE_OVERFLOW)
+#define INT_REMAINDER_OVERFLOW(a, b) \
+  _GL_BINARY_OP_OVERFLOW (a, b, _GL_REMAINDER_OVERFLOW)
+#define INT_LEFT_SHIFT_OVERFLOW(a, b) \
+  INT_LEFT_SHIFT_RANGE_OVERFLOW (a, b, \
+                                 _GL_INT_MINIMUM (a), _GL_INT_MAXIMUM (a))
+
+/* Return 1 if the expression A <op> B would overflow,
+   where OP_RESULT_OVERFLOW (A, B, MIN, MAX) does the actual test,
+   assuming MIN and MAX are the minimum and maximum for the result type.
+   Arguments should be free of side effects.  */
+#define _GL_BINARY_OP_OVERFLOW(a, b, op_result_overflow)        \
+  op_result_overflow (a, b,                                     \
+                      _GL_INT_MINIMUM (0 * (b) + (a)),          \
+                      _GL_INT_MAXIMUM (0 * (b) + (a)))
+
+/* Store the low-order bits of A + B, A - B, A * B, respectively, into *R.
+   Return 1 if the result overflows.  See above for restrictions.  */
+#define INT_ADD_WRAPV(a, b, r) \
+  _GL_INT_OP_WRAPV (a, b, r, +, __builtin_add_overflow, INT_ADD_OVERFLOW)
+#define INT_SUBTRACT_WRAPV(a, b, r) \
+  _GL_INT_OP_WRAPV (a, b, r, -, __builtin_sub_overflow, INT_SUBTRACT_OVERFLOW)
+#define INT_MULTIPLY_WRAPV(a, b, r) \
+  _GL_INT_OP_WRAPV (a, b, r, *, __builtin_mul_overflow, INT_MULTIPLY_OVERFLOW)
+
+/* Nonzero if this compiler has GCC bug 68193 or Clang bug 25390.  See:
+   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68193
+   https://llvm.org/bugs/show_bug.cgi?id=25390
+   For now, assume all versions of GCC-like compilers generate bogus
+   warnings for _Generic.  This matters only for older compilers that
+   lack __builtin_add_overflow.  */
+#if __GNUC__
+# define _GL__GENERIC_BOGUS 1
+#else
+# define _GL__GENERIC_BOGUS 0
+#endif
+
+/* Store the low-order bits of A <op> B into *R, where OP specifies
+   the operation.  BUILTIN is the builtin operation, and OVERFLOW the
+   overflow predicate.  Return 1 if the result overflows.  See above
+   for restrictions.  */
+#if _GL_HAS_BUILTIN_OVERFLOW
+# define _GL_INT_OP_WRAPV(a, b, r, op, builtin, overflow) builtin (a, b, r)
+#elif 201112 <= __STDC_VERSION__ && !_GL__GENERIC_BOGUS
+# define _GL_INT_OP_WRAPV(a, b, r, op, builtin, overflow) \
+   (_Generic \
+    (*(r), \
+     signed char: \
+       _GL_INT_OP_CALC (a, b, r, op, overflow, unsigned char, \
+                        signed char, SCHAR_MIN, SCHAR_MAX), \
+     short int: \
+       _GL_INT_OP_CALC (a, b, r, op, overflow, unsigned short int, \
+                        short int, SHRT_MIN, SHRT_MAX), \
+     int: \
+       _GL_INT_OP_CALC (a, b, r, op, overflow, unsigned int, \
+                        int, INT_MIN, INT_MAX), \
+     long int: \
+       _GL_INT_OP_CALC (a, b, r, op, overflow, unsigned long int, \
+                        long int, LONG_MIN, LONG_MAX), \
+     long long int: \
+       _GL_INT_OP_CALC (a, b, r, op, overflow, unsigned long long int, \
+                        long long int, LLONG_MIN, LLONG_MAX)))
+#else
+# define _GL_INT_OP_WRAPV(a, b, r, op, builtin, overflow) \
+   (sizeof *(r) == sizeof (signed char) \
+    ? _GL_INT_OP_CALC (a, b, r, op, overflow, unsigned char, \
+                       signed char, SCHAR_MIN, SCHAR_MAX) \
+    : sizeof *(r) == sizeof (short int) \
+    ? _GL_INT_OP_CALC (a, b, r, op, overflow, unsigned short int, \
+                       short int, SHRT_MIN, SHRT_MAX) \
+    : sizeof *(r) == sizeof (int) \
+    ? _GL_INT_OP_CALC (a, b, r, op, overflow, unsigned int, \
+                       int, INT_MIN, INT_MAX) \
+    : _GL_INT_OP_WRAPV_LONGISH(a, b, r, op, overflow))
+# ifdef LLONG_MAX
+#  define _GL_INT_OP_WRAPV_LONGISH(a, b, r, op, overflow) \
+    (sizeof *(r) == sizeof (long int) \
+     ? _GL_INT_OP_CALC (a, b, r, op, overflow, unsigned long int, \
+                        long int, LONG_MIN, LONG_MAX) \
+     : _GL_INT_OP_CALC (a, b, r, op, overflow, unsigned long long int, \
+                        long long int, LLONG_MIN, LLONG_MAX))
+# else
+#  define _GL_INT_OP_WRAPV_LONGISH(a, b, r, op, overflow) \
+    _GL_INT_OP_CALC (a, b, r, op, overflow, unsigned long int, \
+                     long int, LONG_MIN, LONG_MAX)
+# endif
+#endif
+
+/* Store the low-order bits of A <op> B into *R, where the operation
+   is given by OP.  Use the unsigned type UT for calculation to avoid
+   overflow problems.  *R's type is T, with extremal values TMIN and
+   TMAX.  T must be a signed integer type.  Return 1 if the result
+   overflows.  */
+#define _GL_INT_OP_CALC(a, b, r, op, overflow, ut, t, tmin, tmax) \
+  (sizeof ((a) op (b)) < sizeof (t) \
+   ? _GL_INT_OP_CALC1 ((t) (a), (t) (b), r, op, overflow, ut, t, tmin, tmax) \
+   : _GL_INT_OP_CALC1 (a, b, r, op, overflow, ut, t, tmin, tmax))
+#define _GL_INT_OP_CALC1(a, b, r, op, overflow, ut, t, tmin, tmax) \
+  ((overflow (a, b) \
+    || (EXPR_SIGNED ((a) op (b)) && ((a) op (b)) < (tmin)) \
+    || (tmax) < ((a) op (b))) \
+   ? (*(r) = _GL_INT_OP_WRAPV_VIA_UNSIGNED (a, b, op, ut, t, tmin, tmax), 1) \
+   : (*(r) = _GL_INT_OP_WRAPV_VIA_UNSIGNED (a, b, op, ut, t, tmin, tmax), 0))
+
+/* Return A <op> B, where the operation is given by OP.  Use the
+   unsigned type UT for calculation to avoid overflow problems.
+   Convert the result to type T without overflow by subtracting TMIN
+   from large values before converting, and adding it afterwards.
+   Compilers can optimize all the operations except OP.  */
+#define _GL_INT_OP_WRAPV_VIA_UNSIGNED(a, b, op, ut, t, tmin, tmax) \
+  (((ut) (a) op (ut) (b)) <= (tmax) \
+   ? (t) ((ut) (a) op (ut) (b)) \
+   : ((t) (((ut) (a) op (ut) (b)) - (tmin)) + (tmin)))
+
+#endif /* _GL_INTPROPS_H */

286 lines not on this page · raw message

index 5e9ea26cd4..5688a639bf 100644
@@ -24,9 +24,7 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
-#ifdef HAVE_STDINT_H
 #include <stdint.h>
-#endif
 
 #ifdef HAVE_STRINGS_H
 #include <strings.h>

@@ -2641,7 +2639,7 @@ 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);
+    postorder (elem, mark_opt_subexp, (void *) (intptr_t) elem->token.opr.idx);
 
   tree = create_tree (dfa, elem, NULL, (end == -1 ? OP_DUP_ASTERISK : OP_ALT));
   if (BE (tree == NULL, 0))

@@ -3868,7 +3866,7 @@ 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)
 {
-  int idx = (int) (long) extra;
+  int idx = (int) (intptr_t) extra;
   if (node->token.type == SUBEXP && node->token.opr.idx == idx)
     node->token.opt_subexp = 1;