grep: -z no longer considers '\200' to be binary data

This avoids a problem when using grep -z in a Windows-1252 locale.
Plus, it lets 'grep -z' run a bit faster.
* NEWS: Document this.
* src/grep.c (buffer_textbin): Don't look for '\200' if -z.
* tests/pcre-z: Test for new behavior.

3 files changed, 9 insertions, 9 deletions

diff --git a/NEWS b/NEWS
index 9377d7d6..51b63fb4 100644
--- a/NEWS
+++ b/NEWS
@@ -26,6 +26,8 @@ GNU grep NEWS                                    -*- outline -*-
   In locales with multibyte character encodings other than UTF-8,
   grep -P now reports an error and exits instead of misbehaving.
 
+  grep -z no longer automatically treats the byte '\200' as binary data.
+
 * Noteworthy changes in release 2.20 (2014-06-03) [stable]
 
 ** Bug fixes
diff --git a/src/grep.c b/src/grep.c
index 1aa64db2..1c6fee87 100644
--- a/src/grep.c
+++ b/src/grep.c
@@ -462,14 +462,10 @@ textbin_is_binary (enum textbin textbin)
 static enum textbin
 buffer_textbin (char const *buf, size_t size)
 {
-  char badbyte = eolbyte ? '\0' : '\200';
+  if (eolbyte && memchr (buf, '\0', size))
+    return TEXTBIN_BINARY;
 
-  if (MB_CUR_MAX <= 1)
-    {
-      if (memchr (buf, badbyte, size))
-        return TEXTBIN_BINARY;
-    }
-  else
+  if (1 < MB_CUR_MAX)
     {
       mbstate_t mbs = { 0 };
       size_t clen;
@@ -477,8 +473,6 @@ buffer_textbin (char const *buf, size_t size)
 
       for (p = buf; p < buf + size; p += clen)
         {
-          if (*p == badbyte)
-            return TEXTBIN_BINARY;
           clen = mb_clen (p, buf + size - p, &mbs);
           if ((size_t) -2 <= clen)
             return clen == (size_t) -2 ? TEXTBIN_UNKNOWN : TEXTBIN_BINARY;
diff --git a/tests/pcre-z b/tests/pcre-z
index 99ebc43c..6bbde947 100755
--- a/tests/pcre-z
+++ b/tests/pcre-z
@@ -20,4 +20,8 @@ grep -Pz "$REGEX" in > out 2>err || fail=1
 compare exp out || fail=1
 compare /dev/null err || fail=1
 
+printf '\200\0' >in0
+LC_ALL=C grep -z . in0 >out || fail=1
+compare in0 out || fail=1
+
 Exit $fail