svn commit: r322586 - stable/11/usr.bin/grep/regex

[Kyle Evans]

Author: kevans
Date: Wed Aug 16 17:54:29 2017
New Revision: 322586
URL: https://svnweb.freebsd.org/changeset/base/322586

Log:
  bsdgrep: fix escape map building when using TRE (BSD_GREP_FASTMATCH)
  
  MFC r317700: bsdgrep: use calloc where appropriate in grep's tre-fastmatch
  
  Also apply style(9) to a related NULL check.
  
  MFC r317701: bsdgrep: correct test sense from r317700
  
  Kyle's change in review D10098 was correct. I introduced the error when
  extracting a portion of that change.
  
  MFC r317704: bsdgrep: fix escape map building for multibyte strings
  
  In BSD grep, fix escape map building in the regex parser. It was
  previously using memory not explicitly initialized, and the MBS escape
  map was being built based on a version of the pattern with escapes
  already parsed out.
  
  This is Kyle's change, but I restored the broken style that already
  exists in this file.
  
  Approved by:	emaste (mentor, blanket MFC)

Modified:
  stable/11/usr.bin/grep/regex/tre-fastmatch.c
Directory Properties:
  stable/11/   (props changed)

Modified: stable/11/usr.bin/grep/regex/tre-fastmatch.c
==============================================================================
--- stable/11/usr.bin/grep/regex/tre-fastmatch.c	Wed Aug 16 17:54:24 2017	(r322585)
+++ stable/11/usr.bin/grep/regex/tre-fastmatch.c	Wed Aug 16 17:54:29 2017	(r322586)
@@ -98,6 +98,18 @@ static int	fastcmp(const fastmatch_t *fg, const void *
     fg->pattern[siz] = '\0';						\
   }									\
 
+#define CONV_MBS_PAT(src, dest, destsz)					\
+  {									\
+    destsz = wcstombs(NULL, src, 0);					\
+    if (destsz == (size_t)-1)						\
+      return REG_BADPAT;						\
+    dest = malloc(destsz + 1);						\
+    if (dest == NULL)							\
+      return REG_ESPACE;						\
+    wcstombs(dest, src, destsz);					\
+    dest[destsz] = '\0';						\
+  }									\
+
 #define IS_OUT_OF_BOUNDS						\
   ((!fg->reversed							\
     ? ((type == STR_WIDE) ? ((j + fg->wlen) > len)			\
@@ -630,7 +642,7 @@ tre_compile_fast(fastmatch_t *fg, const tre_char_t *pa
 	    if (escaped)
 	      {
 		if (!_escmap)
-		  _escmap = malloc(n * sizeof(bool));
+		  _escmap = calloc(n, sizeof(bool));
 		if (!_escmap)
 		  {
 		    free(tmp);
@@ -714,8 +726,8 @@ badpat:
     {
       if (fg->wescmap != NULL)
 	{
-	  fg->escmap = malloc(fg->len * sizeof(bool));
-	  if (!fg->escmap)
+	  fg->escmap = calloc(fg->len, sizeof(bool));
+	  if (fg->escmap == NULL)
 	    {
 	      tre_free_fast(fg);
 	      return REG_ESPACE;
@@ -723,15 +735,29 @@ badpat:
 	}
 
       escaped = false;
-      for (unsigned int i = 0; i < fg->len; i++)
-	if (fg->pattern[i] == '\\')
-	  escaped = !escaped;
-	else if (fg->pattern[i] == '.' && fg->escmap && escaped)
+      char *_checkpat = NULL;
+      size_t _checklen = 0;
+      unsigned int escofs = 0;
+      /*
+       * Make a copy here of the original pattern, because fg->pattern has
+       * already been stripped of all escape sequences in the above processing.
+       * This is necessary if we wish to later treat fg->escmap as an actual,
+       * functional replacement of fg->wescmap.
+       */
+      CONV_MBS_PAT(pat, _checkpat, _checklen);
+      for (unsigned int i = 0; i < n; i++)
+	if (_checkpat[i] == '\\')
 	  {
-	    fg->escmap[i] = true;
+	    escaped = !escaped;
+	    if (escaped)
+	      ++escofs;
+	  }
+	else if (_checkpat[i] == '.' && fg->escmap != NULL && escaped)
+	  {
+	    fg->escmap[i - escofs] = true;
 	    escaped = false;
 	  }
-	else if (fg->pattern[i] == '.' && !escaped)
+	else if (_checkpat[i] == '.' && !escaped)
 	  {
 	    hasdot = i;
 	    if (firstdot == -1)
@@ -739,6 +765,7 @@ badpat:
 	  }
 	else
 	  escaped = false;
+      free(_checkpat);
     }
 #else
   SAVE_PATTERN(tmp, pos, fg->pattern, fg->len);