Mika Fischer <[EMAIL PROTECTED]> tried to post the attached grep patch for
mitigating the 100x slowdown in UTF-8 locales to this list, but his mail
never got through.
Please let him know what you think about it.
Markus
P.S.: Who should one contact if there is a malfunction of the linux-utf8
list server? Others have complained before that they can't post here.
--
Markus Kuhn, Computer Laboratory, University of Cambridge
http://www.cl.cam.ac.uk/~mgk25/ || CB3 0FD, Great Britain
--- search.c.orig 2003-11-10 12:18:23.000000000 +0100
+++ search.c 2003-11-10 13:10:46.000000000 +0100
@@ -17,6 +17,8 @@
02111-1307, USA. */
/* Written August 1992 by Mike Haertel. */
+/* 2003-11-10 Mika Fischer <[EMAIL PROTECTED]>:
+ * Do not compute character lengths in advance, do it when needed. */
#ifdef HAVE_CONFIG_H
# include <config.h>
@@ -141,38 +143,6 @@
}
}
-#ifdef MBS_SUPPORT
-/* This function allocate the array which correspond to "buf".
- Then this check multibyte string and mark on the positions which
- are not singlebyte character nor the first byte of a multibyte
- character. Caller must free the array. */
-static char*
-check_multibyte_string(char const *buf, size_t size)
-{
- char *mb_properties = malloc(size);
- mbstate_t cur_state;
- int i;
- memset(&cur_state, 0, sizeof(mbstate_t));
- memset(mb_properties, 0, sizeof(char)*size);
- for (i = 0; i < size ;)
- {
- size_t mbclen;
- mbclen = mbrlen(buf + i, size - i, &cur_state);
-
- if (mbclen == (size_t) -1 || mbclen == (size_t) -2 || mbclen == 0)
- {
- /* An invalid sequence, or a truncated multibyte character.
- We treat it as a singlebyte character. */
- mbclen = 1;
- }
- mb_properties[i] = mbclen;
- i += mbclen;
- }
-
- return mb_properties;
-}
-#endif
-
static void
Gcompile (char const *pattern, size_t size)
{
@@ -341,12 +311,7 @@
struct kwsmatch kwsm;
size_t i;
#ifdef MBS_SUPPORT
- char *mb_properties = NULL;
-#endif /* MBS_SUPPORT */
-
-#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1 && kwset)
- mb_properties = check_multibyte_string(buf, size);
+ mbstate_t cur_state;
#endif /* MBS_SUPPORT */
buflim = buf + size;
@@ -361,10 +326,6 @@
size_t offset = kwsexec (kwset, beg, buflim - beg, &kwsm);
if (offset == (size_t) -1)
{
-#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1)
- free(mb_properties);
-#endif
return (size_t)-1;
}
beg += offset;
@@ -373,8 +334,12 @@
end = memchr(beg, eol, buflim - beg);
end++;
#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1 && mb_properties[beg - buf] == 0)
- continue;
+ if (MB_CUR_MAX > 1)
+ {
+ memset(&cur_state, 0, sizeof(mbstate_t));
+ if (mbrlen(beg, buflim - beg, &cur_state) < 0)
+ continue;
+ }
#endif
while (beg > buf && beg[-1] != eol)
--beg;
@@ -461,17 +426,9 @@
}
} /* for Regex patterns. */
} /* for (beg = end ..) */
-#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1 && mb_properties)
- free (mb_properties);
-#endif /* MBS_SUPPORT */
return (size_t) -1;
success:
-#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1 && mb_properties)
- free (mb_properties);
-#endif /* MBS_SUPPORT */
*match_size = end - beg;
return beg - buf;
}
@@ -507,9 +464,7 @@
char eol = eolbyte;
struct kwsmatch kwsmatch;
#ifdef MBS_SUPPORT
- char *mb_properties;
- if (MB_CUR_MAX > 1)
- mb_properties = check_multibyte_string (buf, size);
+ mbstate_t cur_state;
#endif /* MBS_SUPPORT */
for (beg = buf; beg <= buf + size; ++beg)
@@ -517,25 +472,21 @@
size_t offset = kwsexec (kwset, beg, buf + size - beg, &kwsmatch);
if (offset == (size_t) -1)
{
-#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1)
- free(mb_properties);
-#endif /* MBS_SUPPORT */
return offset;
}
#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1 && mb_properties[offset+beg-buf] == 0)
- continue; /* It is a part of multibyte character. */
+ if (MB_CUR_MAX > 1)
+ {
+ memset(&cur_state, 0, sizeof(mbstate_t));
+ if (mbrlen(beg + offset, buf + size - beg, &cur_state) < 0)
+ continue; /* It is a part of multibyte character. */
+ }
#endif /* MBS_SUPPORT */
beg += offset;
len = kwsmatch.size[0];
if (exact)
{
*match_size = len;
-#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1)
- free (mb_properties);
-#endif /* MBS_SUPPORT */
return beg - buf;
}
if (match_lines)
@@ -556,10 +507,6 @@
offset = kwsexec (kwset, beg, --len, &kwsmatch);
if (offset == (size_t) -1)
{
-#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1)
- free (mb_properties);
-#endif /* MBS_SUPPORT */
return offset;
}
try = beg + offset;
@@ -572,10 +519,6 @@
goto success;
}
-#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1)
- free (mb_properties);
-#endif /* MBS_SUPPORT */
return -1;
success:
@@ -584,10 +527,6 @@
while (buf < beg && beg[-1] != eol)
--beg;
*match_size = end - beg;
-#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1)
- free (mb_properties);
-#endif /* MBS_SUPPORT */
return beg - buf;
}
