Merge branch 'gawk-4.0-stable'

1 files changed, 46 insertions, 18 deletions

diff --git a/dfa.c b/dfa.c
index 21cabc3b..f9355f19 100644
--- a/dfa.c
+++ b/dfa.c
@@ -36,6 +36,12 @@
 #if HAVE_SETLOCALE
 #include <locale.h>
 #endif
+#ifdef HAVE_STDBOOL_H
+#include <stdbool.h>
+#else
+#include "missing_d/gawkbool.h"
+#endif /* HAVE_STDBOOL_H */
+
 
 #define STREQ(a, b) (strcmp (a, b) == 0)
 
@@ -53,7 +59,7 @@
 #include "gettext.h"
 #define _(str) gettext (str)
 
-#include "mbsupport.h"  /* defines MBS_SUPPORT to 1 or 0, as appropriate */
+#include "mbsupport.h"          /* defines MBS_SUPPORT to 1 or 0, as appropriate */
 #if MBS_SUPPORT
 /* We can handle multibyte strings. */
 #include <wchar.h>
@@ -61,10 +67,6 @@
 #endif
 
 #ifdef GAWK
-#define bool int
-#define true (1)
-#define false (0)
-
 /* The __pure__ attribute was added in gcc 2.96.  */
 #if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 96)
 # define _GL_ATTRIBUTE_PURE __attribute__ ((__pure__))
@@ -343,7 +345,7 @@ struct mb_char_classes
   wchar_t *range_sts;           /* Range characters (start of the range).  */
   wchar_t *range_ends;          /* Range characters (end of the range).  */
   size_t nranges;
-  char **equivs;                /* Equivalent classes.  */
+  char **equivs;                /* Equivalence classes.  */
   size_t nequivs;
   char **coll_elems;
   size_t ncoll_elems;           /* Collating elements.  */
@@ -1053,12 +1055,10 @@ parse_bracket_exp (void)
 
               else if (MBS_SUPPORT && (c1 == '=' || c1 == '.'))
                 {
-                  char *elem;
-                  MALLOC (elem, len + 1);
-                  strncpy (elem, str, len + 1);
+                  char *elem = xmemdup (str, len + 1);
 
                   if (c1 == '=')
-                    /* build equivalent class.  */
+                    /* build equivalence class.  */
                     {
                       REALLOC_IF_NECESSARY (work_mbc->equivs,
                                             equivs_al, work_mbc->nequivs + 1);
@@ -1136,6 +1136,33 @@ parse_bracket_exp (void)
             }
           else
             {
+#ifndef GAWK
+              /* Defer to the system regex library about the meaning
+                 of range expressions.  */
+              regex_t re;
+              char pattern[6] = { '[', 0, '-', 0, ']', 0 };
+              char subject[2] = { 0, 0 };
+              c1 = c;
+              if (case_fold)
+                {
+                  c1 = tolower (c1);
+                  c2 = tolower (c2);
+                }
+
+              pattern[1] = c1;
+              pattern[3] = c2;
+              regcomp (&re, pattern, REG_NOSUB);
+              for (c = 0; c < NOTCHAR; ++c)
+                {
+                  if ((case_fold && isupper (c))
+                      || (MB_CUR_MAX > 1 && btowc (c) == WEOF))
+                    continue;
+                  subject[0] = c;
+                  if (regexec (&re, subject, 0, NULL, 0) != REG_NOMATCH)
+                    setbit_case_fold_c (c, ccl);
+                }
+              regfree (&re);
+#else
               c1 = c;
               if (case_fold)
                 {
@@ -1144,6 +1171,7 @@ parse_bracket_exp (void)
                 }
               for (c = c1; c <= c2; c++)
                 setbit_case_fold_c (c, ccl);
+#endif
             }
 
           colon_warning_state |= 8;
@@ -3021,7 +3049,7 @@ match_mb_charset (struct dfa *d, state_num s, position pos, size_t idx)
   strncpy (buffer, (char const *) buf_begin + idx, match_len);
   buffer[match_len] = '\0';
 
-  /* match with an equivalent class?  */
+  /* match with an equivalence class?  */
   for (i = 0; i < work_mbc->nequivs; i++)
     {
       op_len = strlen (work_mbc->equivs[i]);
@@ -3051,8 +3079,7 @@ match_mb_charset (struct dfa *d, state_num s, position pos, size_t idx)
   /* match with a range?  */
   for (i = 0; i < work_mbc->nranges; i++)
     {
-      if (work_mbc->range_sts[i] <= wc &&
-          wc <= work_mbc->range_ends[i])
+      if (work_mbc->range_sts[i] <= wc && wc <= work_mbc->range_ends[i])
         goto charset_matched;
     }
 
@@ -3151,6 +3178,8 @@ transit_state_consume_1char (struct dfa *d, state_num s,
 
   if (match_lens == NULL && work_mbls != NULL)
     free (work_mbls);
+
+  /* FIXME: this return value is always ignored.  */
   return rs;
 }
 
@@ -3195,7 +3224,7 @@ transit_state (struct dfa *d, state_num s, unsigned char const **pp)
 
       /* We must update the pointer if state transition succeeded.  */
       if (rs == TRANSIT_STATE_DONE)
-        ++ * pp;
+        ++*pp;
 
       free (match_lens);
       return s1;
@@ -3408,7 +3437,7 @@ dfaexec (struct dfa *d, char const *begin, char *end,
       if ((char *) p <= end && p[-1] == eol)
         {
           if (count)
-            ++ * count;
+            ++*count;
 
           if (d->mb_cur_max > 1)
             prepare_wc_buf ((const char *) p, end);
@@ -3669,7 +3698,7 @@ icatalloc (char *old, char const *new)
   if (newsize == 0)
     return old;
   result = xrealloc (old, oldsize + newsize + 1);
-  strcpy (result + oldsize, new);
+  memcpy (result + oldsize, new, newsize + 1);
   return result;
 }
 
@@ -4062,8 +4091,7 @@ done:
     {
       MALLOC (dm, 1);
       dm->exact = exact;
-      MALLOC (dm->must, strlen (result) + 1);
-      strcpy (dm->must, result);
+      dm->must = xmemdup (result, strlen (result) + 1);
       dm->next = d->musts;
       d->musts = dm;
     }