File mbcache.diff of Package grep
--- src/dfa.c
+++ src/dfa.c
@@ -2755,7 +2755,8 @@
match needs to be verified by a backtracking matcher. Otherwise
we store a 0 in *backref. */
size_t
-dfaexec (struct dfa *d, char const *begin, size_t size, int *backref)
+dfaexec (struct dfa *d, char const *begin, size_t size, int *backref,
+ struct mb_cache *mb_cache)
{
register int s; /* Current state. */
register unsigned char const *p; /* Current input character. */
@@ -2787,43 +2788,77 @@
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1)
{
- int remain_bytes, i;
buf_begin = begin;
buf_end = end;
-
- /* initialize mblen_buf, and inputwcs. */
- MALLOC(mblen_buf, unsigned char, end - (unsigned char const *)begin + 2);
- MALLOC(inputwcs, wchar_t, end - (unsigned char const *)begin + 2);
- memset(&mbs, 0, sizeof(mbstate_t));
- remain_bytes = 0;
- for (i = 0; i < end - (unsigned char const *)begin + 1; i++)
+ if (mb_cache && mb_cache->mblen_buf && mb_cache->wcs_buf
+ && begin > mb_cache->orig_buf
+ && begin + size <= mb_cache->orig_buf + mb_cache->len)
+ {
+ /* The cache can help us. */
+ MALLOC (mblen_buf, unsigned char, size + 2);
+ MALLOC (inputwcs, wchar_t, size + 2);
+ memcpy (mblen_buf,
+ mb_cache->mblen_buf + (begin - mb_cache->orig_buf),
+ (size + 2) * sizeof (unsigned char));
+ memcpy (inputwcs,
+ mb_cache->wcs_buf + (begin - mb_cache->orig_buf),
+ (size + 2) * sizeof (wchar_t));
+ mblen_buf[size + 1] = 0;
+ inputwcs[size + 1] = 0;
+ }
+ else
{
- if (remain_bytes == 0)
+ int remain_bytes, i;
+
+ /* initialize mblen_buf, and inputwcs. */
+ MALLOC(mblen_buf, unsigned char, end - (unsigned char const *)begin + 2);
+ MALLOC(inputwcs, wchar_t, end - (unsigned char const *)begin + 2);
+ memset(&mbs, 0, sizeof(mbstate_t));
+ remain_bytes = 0;
+ for (i = 0; i < end - (unsigned char const *)begin + 1; i++)
{
- remain_bytes
- = mbrtowc(inputwcs + i, begin + i,
- end - (unsigned char const *)begin - i + 1, &mbs);
- if (remain_bytes <= 1)
+ if (remain_bytes == 0)
{
- remain_bytes = 0;
- inputwcs[i] = (wchar_t)begin[i];
- mblen_buf[i] = 0;
+ remain_bytes
+ = mbrtowc(inputwcs + i, begin + i,
+ end - (unsigned char const *)begin - i + 1, &mbs);
+ if (remain_bytes <= 1)
+ {
+ remain_bytes = 0;
+ inputwcs[i] = (wchar_t)begin[i];
+ mblen_buf[i] = 0;
+ }
+ else
+ {
+ mblen_buf[i] = remain_bytes;
+ remain_bytes--;
+ }
}
else
{
mblen_buf[i] = remain_bytes;
+ inputwcs[i] = 0;
remain_bytes--;
}
}
- else
+ mblen_buf[i] = 0;
+ inputwcs[i] = 0; /* sentinel */
+
+ if (mb_cache)
{
- mblen_buf[i] = remain_bytes;
- inputwcs[i] = 0;
- remain_bytes--;
+ /* Populate the cache. */
+ mb_cache->len = size;
+ mb_cache->orig_buf = begin;
+ free (mb_cache->mblen_buf);
+ free (mb_cache->wcs_buf);
+ MALLOC (mb_cache->mblen_buf, unsigned char, size + 2);
+ MALLOC (mb_cache->wcs_buf, wchar_t, size + 2);
+ memcpy (mb_cache->mblen_buf, mblen_buf,
+ (size + 2) * sizeof (unsigned char));
+ memcpy (mb_cache->wcs_buf, inputwcs,
+ (size + 2) * sizeof (wchar_t));
}
}
- mblen_buf[i] = 0;
- inputwcs[i] = 0; /* sentinel */
}
#endif /* MBS_SUPPORT */
--- src/dfa.h
+++ src/dfa.h
@@ -22,6 +22,8 @@
In addition to clobbering modularity, we eat up valuable
name space. */
+#include "mbcache.h"
+
#ifdef __STDC__
# ifndef _PTR_T
# define _PTR_T
@@ -403,7 +405,8 @@
order to verify backreferencing; otherwise the flag will be cleared.
Returns (size_t) -1 if no match is found, or the offset of the first
character after the first & shortest matching string in the buffer. */
-extern size_t dfaexec PARAMS ((struct dfa *, char const *, size_t, int *));
+extern size_t dfaexec PARAMS ((struct dfa *, char const *, size_t, int *,
+ struct mb_cache *));
/* Free the storage held by the components of a struct dfa. */
extern void dfafree PARAMS ((struct dfa *));
--- src/grep.c
+++ src/grep.c
@@ -189,7 +189,8 @@
/* Functions we'll use to search. */
static void (*compile) PARAMS ((char const *, size_t));
-static size_t (*execute) PARAMS ((char const *, size_t, size_t *, int));
+static size_t (*execute) PARAMS ((char const *, size_t, struct mb_cache *,
+ size_t *, int));
/* Like error, but suppress the diagnostic if requested. */
static void
@@ -506,7 +507,7 @@
}
static void
-prline (char const *beg, char const *lim, int sep)
+prline (char const *beg, char const *lim, int sep, struct mb_cache *mb_cache)
{
if (out_file)
printf ("%s%c", filename, sep & filename_mask);
@@ -529,7 +530,8 @@
{
size_t match_size;
size_t match_offset;
- while ((match_offset = (*execute) (beg, lim - beg, &match_size, 1))
+ while ((match_offset = (*execute) (beg, lim - beg, mb_cache,
+ &match_size, 1))
!= (size_t) -1)
{
char const *b = beg + match_offset;
@@ -563,7 +565,8 @@
int i;
for (i = 0; i < lim - beg; i++)
ibeg[i] = tolower (beg[i]);
- while ((match_offset = (*execute) (ibeg, ilim-ibeg, &match_size, 1))
+ while ((match_offset = (*execute) (ibeg, ilim-ibeg, mb_cache,
+ &match_size, 1))
!= (size_t) -1)
{
char const *b = beg + match_offset;
@@ -581,7 +584,8 @@
lastout = lim;
return;
}
- while (lim-beg && (match_offset = (*execute) (beg, lim - beg, &match_size, 1))
+ while (lim-beg && (match_offset = (*execute) (beg, lim - beg, mb_cache,
+ &match_size, 1))
!= (size_t) -1)
{
char const *b = beg + match_offset;
@@ -609,7 +613,7 @@
/* Print pending lines of trailing context prior to LIM. Trailing context ends
at the next matching line when OUTLEFT is 0. */
static void
-prpending (char const *lim)
+prpending (char const *lim, struct mb_cache *mb_cache)
{
if (!lastout)
lastout = bufbeg;
@@ -619,9 +623,10 @@
size_t match_size;
--pending;
if (outleft
- || (((*execute) (lastout, nl - lastout, &match_size, 0) == (size_t) -1)
+ || (((*execute) (lastout, nl - lastout, mb_cache,
+ &match_size, 0) == (size_t) -1)
== !out_invert))
- prline (lastout, nl + 1, '-');
+ prline (lastout, nl + 1, '-', mb_cache);
else
pending = 0;
}
@@ -630,7 +635,8 @@
/* Print the lines between BEG and LIM. Deal with context crap.
If NLINESP is non-null, store a count of lines between BEG and LIM. */
static void
-prtext (char const *beg, char const *lim, int *nlinesp)
+prtext (char const *beg, char const *lim, int *nlinesp,
+ struct mb_cache *mb_cache)
{
static int used; /* avoid printing "--" before any output */
char const *bp, *p;
@@ -638,7 +644,7 @@
int i, n;
if (!out_quiet && pending > 0)
- prpending (beg);
+ prpending (beg, mb_cache);
p = beg;
@@ -662,7 +668,7 @@
{
char const *nl = memchr (p, eol, beg - p);
nl++;
- prline (p, nl, '-');
+ prline (p, nl, '-', mb_cache);
p = nl;
}
}
@@ -675,7 +681,7 @@
char const *nl = memchr (p, eol, lim - p);
nl++;
if (!out_quiet)
- prline (p, nl, ':');
+ prline (p, nl, ':', mb_cache);
p = nl;
}
*nlinesp = n;
@@ -685,7 +691,7 @@
}
else
if (!out_quiet)
- prline (beg, lim, ':');
+ prline (beg, lim, ':', mb_cache);
pending = out_quiet ? 0 : out_after;
used = 1;
@@ -695,7 +701,7 @@
between matching lines if OUT_INVERT is true). Return a count of
lines printed. */
static int
-grepbuf (char const *beg, char const *lim)
+grepbuf (char const *beg, char const *lim, struct mb_cache *mb_cache)
{
int nlines, n;
register char const *p;
@@ -704,7 +710,8 @@
nlines = 0;
p = beg;
- while ((match_offset = (*execute) (p, lim - p, &match_size, 0)) != (size_t) -1)
+ while ((match_offset = (*execute) (p, lim - p, mb_cache,
+ &match_size, 0)) != (size_t) -1)
{
char const *b = p + match_offset;
char const *endp = b + match_size;
@@ -713,7 +720,7 @@
break;
if (!out_invert)
{
- prtext (b, endp, (int *) 0);
+ prtext (b, endp, (int *) 0, mb_cache);
nlines++;
outleft--;
if (!outleft || done_on_match)
@@ -726,7 +733,7 @@
}
else if (p < b)
{
- prtext (p, b, &n);
+ prtext (p, b, &n, mb_cache);
nlines += n;
outleft -= n;
if (!outleft)
@@ -736,7 +743,7 @@
}
if (out_invert && p < lim)
{
- prtext (p, lim, &n);
+ prtext (p, lim, &n, mb_cache);
nlines += n;
outleft -= n;
}
@@ -756,7 +763,16 @@
char *beg;
char *lim;
char eol = eolbyte;
+ struct mb_cache *mb_cache;
+#ifdef MBS_SUPPORT
+ struct mb_cache mb_cache_inst;
+ mb_cache = &mb_cache_inst;
+ mb_cache->mblen_buf = 0;
+ mb_cache->wcs_buf = 0;
+#else
+ mb_cache = 0;
+#endif
if (!reset (fd, file, stats))
return 0;
@@ -823,9 +839,9 @@
if (beg < lim)
{
if (outleft)
- nlines += grepbuf (beg, lim);
+ nlines += grepbuf (beg, lim, mb_cache);
if (pending)
- prpending (lim);
+ prpending (lim, mb_cache);
if((!outleft && !pending) || (nlines && done_on_match && !out_invert))
goto finish_grep;
}
@@ -853,6 +869,12 @@
totalcc = add_count (totalcc, buflim - bufbeg - save);
if (out_line)
nlscan (beg);
+#ifdef MBS_SUPPORT
+ free (mb_cache->wcs_buf);
+ free (mb_cache->mblen_buf);
+ mb_cache->wcs_buf = 0;
+ mb_cache->mblen_buf = 0;
+#endif
if (! fillbuf (save, stats))
{
if (! is_EISDIR (errno, file))
@@ -864,9 +886,9 @@
{
*buflim++ = eol;
if (outleft)
- nlines += grepbuf (bufbeg + save - residue, buflim);
+ nlines += grepbuf (bufbeg + save - residue, buflim, mb_cache);
if (pending)
- prpending (buflim);
+ prpending (buflim, mb_cache);
}
finish_grep:
@@ -874,6 +896,11 @@
out_quiet -= not_text;
if ((not_text & ~out_quiet) && nlines != 0)
printf (_("Binary file %s matches\n"), filename);
+
+#ifdef MBS_SUPPORT
+ free (mb_cache->wcs_buf);
+ free (mb_cache->mblen_buf);
+#endif
return nlines;
}
--- src/grep.h
+++ src/grep.h
@@ -20,6 +20,8 @@
# define __attribute__(x)
#endif
+#include "mbcache.h"
+
/* Grep.c expects the matchers vector to be terminated
by an entry with a NULL compile, and to contain at least
an entry named "default". */
@@ -28,7 +30,8 @@
{
char name[8];
void (*compile) PARAMS ((char const *, size_t));
- size_t (*execute) PARAMS ((char const *, size_t, size_t *, int));
+ size_t (*execute) PARAMS ((char const *, size_t, struct mb_cache *,
+ size_t *, int));
} const matchers[];
/* Exported from fgrepmat.c, egrepmat.c, grepmat.c. */
--- src/mbcache.h
+++ src/mbcache.h
@@ -0,0 +1,14 @@
+#ifndef MB_CACHE_DEFINED
+#define MB_CACHE_DEFINED
+#ifdef MBS_SUPPORT
+struct mb_cache
+{
+ size_t len;
+ const char *orig_buf; /* not the only reference; do not free */
+ wchar_t *wcs_buf;
+ unsigned char *mblen_buf;
+};
+#else
+struct mb_cache;
+#endif
+#endif
--- src/search.c
+++ src/search.c
@@ -71,18 +71,23 @@
static int kwset_exact_matches;
#if defined(MBS_SUPPORT)
-static char* check_multibyte_string PARAMS ((char const *buf, size_t size));
+static char* check_multibyte_string PARAMS ((char const *buf, size_t size,
+ struct mb_cache *,
+ char const *orig_buf));
extern int convert_mbstr;
#endif
static void kwsinit PARAMS ((void));
static void kwsmusts PARAMS ((void));
static void Gcompile PARAMS ((char const *, size_t));
static void Ecompile PARAMS ((char const *, size_t));
-static size_t EGexecute PARAMS ((char const *, size_t, size_t *, int ));
+static size_t EGexecute PARAMS ((char const *, size_t, struct mb_cache *,
+ size_t *, int ));
static void Fcompile PARAMS ((char const *, size_t));
-static size_t Fexecute PARAMS ((char const *, size_t, size_t *, int));
+static size_t Fexecute PARAMS ((char const *, size_t, struct mb_cache *,
+ size_t *, int));
static void Pcompile PARAMS ((char const *, size_t ));
-static size_t Pexecute PARAMS ((char const *, size_t, size_t *, int));
+static size_t Pexecute PARAMS ((char const *, size_t, struct mb_cache *,
+ size_t *, int));
void
dfaerror (char const *mesg)
@@ -148,35 +153,61 @@
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)
+check_multibyte_string(char const *buf, size_t size, struct mb_cache *mb_cache,
+ char const *orig_buf)
{
char *mb_properties = xmalloc(size);
mbstate_t cur_state;
wchar_t wc;
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 = mbrtowc (&wc, buf + i, size - i, &cur_state);
+ if (mb_cache && mb_cache->mblen_buf
+ && orig_buf > mb_cache->orig_buf
+ && orig_buf + size <= mb_cache->orig_buf + mb_cache->len)
+ {
+ /* The cache can help us. */
+ memcpy (mb_properties,
+ mb_cache->mblen_buf + (orig_buf - mb_cache->orig_buf),
+ size);
- 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;
- }
- else if (match_icase)
+ }
+ else
+ {
+ memset(mb_properties, 0, sizeof(char)*size);
+ for (i = 0; i < size ;)
{
- if (iswupper ((wint_t) wc))
- {
- wc = towlower ((wint_t) wc);
- wcrtomb (buf + i, wc, &cur_state);
- }
+ size_t mbclen;
+ mbclen = mbrtowc(&wc, 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;
+ }
+ else if (match_icase)
+ {
+ if (iswupper((wint_t)wc))
+ {
+ wc = towlower((wint_t)wc);
+ wcrtomb(buf + i, wc, &cur_state);
+ }
+ }
+ mb_properties[i] = mbclen;
+ i += mbclen;
+ }
+
+ /* Now populate the cache. */
+ if (mb_cache)
+ {
+ free (mb_cache->wcs_buf);
+ mb_cache->wcs_buf = NULL;
+ free (mb_cache->mblen_buf);
+ mb_cache->len = size;
+ mb_cache->orig_buf = orig_buf;
+ mb_cache->mblen_buf = xmalloc (size);
+ memcpy (mb_cache->mblen_buf, mb_properties, size);
}
- mb_properties[i] = mbclen;
- i += mbclen;
}
return mb_properties;
@@ -363,9 +394,11 @@
}
static size_t
-EGexecute (char const *buf, size_t size, size_t *match_size, int exact)
+EGexecute (char const *buf, size_t size, struct mb_cache *mb_cache,
+ size_t *match_size, int exact)
{
register char const *buflim, *beg, *end;
+ char const *orig_buf = buf;
char eol = eolbyte;
int backref, start, len;
struct kwsmatch kwsm;
@@ -380,7 +413,7 @@
memcpy (case_buf, buf, size);
buf = case_buf;
if (kwset && convert_mbstr)
- mb_properties = check_multibyte_string (buf, size);
+ mb_properties = check_multibyte_string (buf, size, mb_cache, orig_buf);
}
}
#endif /* MBS_SUPPORT */
@@ -416,13 +449,13 @@
--beg;
if (kwsm.index < kwset_exact_matches)
goto success;
- if (dfaexec (&dfa, beg, end - beg, &backref) == (size_t) -1)
+ if (dfaexec (&dfa, beg, end - beg, &backref, mb_cache) == (size_t) -1)
continue;
}
else
{
/* No good fixed strings; start with DFA. */
- size_t offset = dfaexec (&dfa, beg, buflim - beg, &backref);
+ size_t offset = dfaexec (&dfa, beg, buflim - beg, &backref, mb_cache);
if (offset == (size_t) -1)
break;
/* Narrow down to the line we've found. */
@@ -547,9 +580,11 @@
}
static size_t
-Fexecute (char const *buf, size_t size, size_t *match_size, int exact)
+Fexecute (char const *buf, size_t size, struct mb_cache *mb_cache,
+ size_t *match_size, int exact)
{
register char const *beg, *try, *end;
+ char const *orig_buf = buf;
register size_t len;
char eol = eolbyte;
struct kwsmatch kwsmatch;
@@ -564,7 +599,7 @@
memcpy (case_buf, buf, size);
buf = case_buf;
if (convert_mbstr)
- mb_properties = check_multibyte_string (buf, size);
+ mb_properties = check_multibyte_string (buf, size, mb_cache, orig_buf);
}
}
#endif /* MBS_SUPPORT */
@@ -755,7 +790,8 @@
}
static size_t
-Pexecute (char const *buf, size_t size, size_t *match_size, int exact)
+Pexecute (char const *buf, size_t size, struct mb_cache *mb_cache,
+ size_t *match_size, int exact)
{
#if !HAVE_LIBPCRE
abort ();
