diff options
author | Michael Hanson <hansonorders@verizon.net> | 2010-11-30 23:52:49 (GMT) |
---|---|---|
committer | Michael Hanson <hansonorders@verizon.net> | 2010-11-30 23:52:49 (GMT) |
commit | ef974fb08972483d6852c9d5b2f23e1d33343b76 (patch) | |
tree | fa5aad1563681bf14a0fed3cdf8f599f7e8e853c /abs/core/grep | |
parent | ba6da4b6e7eab74dd3dcac947a11361b1b9f1eed (diff) | |
download | linhes_pkgbuild-ef974fb08972483d6852c9d5b2f23e1d33343b76.zip linhes_pkgbuild-ef974fb08972483d6852c9d5b2f23e1d33343b76.tar.gz linhes_pkgbuild-ef974fb08972483d6852c9d5b2f23e1d33343b76.tar.bz2 |
Housekeeping
Diffstat (limited to 'abs/core/grep')
-rw-r--r-- | abs/core/grep/01-fgrep.patch | 145 | ||||
-rw-r--r-- | abs/core/grep/02-bracket.patch | 11 | ||||
-rw-r--r-- | abs/core/grep/03-i18n.patch | 303 | ||||
-rw-r--r-- | abs/core/grep/04-oi.patch | 48 | ||||
-rw-r--r-- | abs/core/grep/05-manpage.patch | 19 | ||||
-rw-r--r-- | abs/core/grep/06-color.patch | 10 | ||||
-rw-r--r-- | abs/core/grep/07-icolor.patch | 36 | ||||
-rw-r--r-- | abs/core/grep/08-skip.patch | 42 | ||||
-rw-r--r-- | abs/core/grep/09-egf-speedup.patch | 823 | ||||
-rw-r--r-- | abs/core/grep/10-dfa-optional.patch | 67 | ||||
-rw-r--r-- | abs/core/grep/11-tests.patch | 138 | ||||
-rw-r--r-- | abs/core/grep/12-w.patch | 121 | ||||
-rw-r--r-- | abs/core/grep/13-P.patch | 14 | ||||
-rw-r--r-- | abs/core/grep/14-mem-exhausted.patch | 15 | ||||
-rw-r--r-- | abs/core/grep/15-empty-pattern.patch | 36 | ||||
-rw-r--r-- | abs/core/grep/64-egf-speedup.patch | 791 |
16 files changed, 0 insertions, 2619 deletions
diff --git a/abs/core/grep/01-fgrep.patch b/abs/core/grep/01-fgrep.patch deleted file mode 100644 index c7f8f96..0000000 --- a/abs/core/grep/01-fgrep.patch +++ /dev/null @@ -1,145 +0,0 @@ ---- grep-2.5.1/src/search.c.fgrep 2001-04-19 04:42:14.000000000 +0100 -+++ grep-2.5.1/src/search.c 2004-02-26 13:09:32.000000000 +0000 -@@ -360,13 +360,7 @@ - /* Find a possible match using the KWset matcher. */ - 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; -- } -+ goto failure; - beg += offset; - /* Narrow down to the line containing the candidate, and - run it through DFA. */ -@@ -379,7 +373,7 @@ - while (beg > buf && beg[-1] != eol) - --beg; - if (kwsm.index < kwset_exact_matches) -- goto success; -+ goto success_in_beg_and_end; - if (dfaexec (&dfa, beg, end - beg, &backref) == (size_t) -1) - continue; - } -@@ -398,7 +392,7 @@ - } - /* Successful, no backreferences encountered! */ - if (!backref) -- goto success; -+ goto success_in_beg_and_end; - } - else - end = beg + size; -@@ -413,14 +407,11 @@ - end - beg - 1, &(patterns[i].regs)))) - { - len = patterns[i].regs.end[0] - start; -- if (exact) -- { -- *match_size = len; -- return start; -- } -+ if (exact && !match_words) -+ goto success_in_start_and_len; - if ((!match_lines && !match_words) - || (match_lines && len == end - beg - 1)) -- goto success; -+ goto success_in_beg_and_end; - /* If -w, check if the match aligns with word boundaries. - We do this iteratively because: - (a) the line may contain more than one occurence of the -@@ -434,7 +425,7 @@ - if ((start == 0 || !WCHAR ((unsigned char) beg[start - 1])) - && (len == end - beg - 1 - || !WCHAR ((unsigned char) beg[start + len]))) -- goto success; -+ goto success_in_beg_and_end; - if (len > 0) - { - /* Try a shorter length anchored at the same place. */ -@@ -461,19 +452,26 @@ - } - } /* for Regex patterns. */ - } /* for (beg = end ..) */ -+ -+ failure: - #ifdef MBS_SUPPORT - if (MB_CUR_MAX > 1 && mb_properties) - free (mb_properties); - #endif /* MBS_SUPPORT */ - return (size_t) -1; - -- success: -+ success_in_beg_and_end: -+ len = end - beg; -+ start = beg - buf; -+ /* FALLTHROUGH */ -+ -+ success_in_start_and_len: - #ifdef MBS_SUPPORT - if (MB_CUR_MAX > 1 && mb_properties) - free (mb_properties); - #endif /* MBS_SUPPORT */ -- *match_size = end - beg; -- return beg - buf; -+ *match_size = len; -+ return start; - } - - static void -@@ -516,28 +514,15 @@ - { - 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; -- } -+ goto failure; - #ifdef MBS_SUPPORT - if (MB_CUR_MAX > 1 && mb_properties[offset+beg-buf] == 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 (exact && !match_words) -+ goto success_in_beg_and_len; - if (match_lines) - { - if (beg > buf && beg[-1] != eol) -@@ -551,6 +536,7 @@ - goto success; - } - -+ failure: - #ifdef MBS_SUPPORT - if (MB_CUR_MAX > 1) - free (mb_properties); -@@ -583,7 +569,11 @@ - end++; - while (buf < beg && beg[-1] != eol) - --beg; -- *match_size = end - beg; -+ len = end - beg; -+ /* FALLTHROUGH */ -+ -+ success_in_beg_and_len: -+ *match_size = len; - #ifdef MBS_SUPPORT - if (MB_CUR_MAX > 1) - free (mb_properties); diff --git a/abs/core/grep/02-bracket.patch b/abs/core/grep/02-bracket.patch deleted file mode 100644 index f99571c..0000000 --- a/abs/core/grep/02-bracket.patch +++ /dev/null @@ -1,11 +0,0 @@ ---- grep-2.5.1/src/dfa.c.bracket 2003-10-30 16:21:14.000000000 +0000 -+++ grep-2.5.1/src/dfa.c 2003-10-30 16:22:38.000000000 +0000 -@@ -586,7 +586,7 @@ - work_mbc->coll_elems[work_mbc->ncoll_elems++] = elem; - } - } -- wc = -1; -+ wc1 = wc = -1; - } - else - /* We treat '[' as a normal character here. */ diff --git a/abs/core/grep/03-i18n.patch b/abs/core/grep/03-i18n.patch deleted file mode 100644 index 8dc3dfe..0000000 --- a/abs/core/grep/03-i18n.patch +++ /dev/null @@ -1,303 +0,0 @@ ---- grep-2.5.1/src/dfa.c 2004-02-26 13:09:54.000000000 +0000 -+++ grep-2.5.1/src/dfa.c 2004-05-18 16:43:31.189200479 +0100 -@@ -414,7 +414,7 @@ - - /* This function fetch a wide character, and update cur_mb_len, - used only if the current locale is a multibyte environment. */ --static wchar_t -+static wint_t - fetch_wc (char const *eoferr) - { - wchar_t wc; -@@ -423,7 +423,7 @@ - if (eoferr != 0) - dfaerror (eoferr); - else -- return -1; -+ return WEOF; - } - - cur_mb_len = mbrtowc(&wc, lexptr, lexleft, &mbs); -@@ -459,7 +459,7 @@ - static void - parse_bracket_exp_mb () - { -- wchar_t wc, wc1, wc2; -+ wint_t wc, wc1, wc2; - - /* Work area to build a mb_char_classes. */ - struct mb_char_classes *work_mbc; -@@ -496,7 +496,7 @@ - work_mbc->invert = 0; - do - { -- wc1 = -1; /* mark wc1 is not initialized". */ -+ wc1 = WEOF; /* mark wc1 is not initialized". */ - - /* Note that if we're looking at some other [:...:] construct, - we just treat it as a bunch of ordinary characters. We can do -@@ -586,7 +586,7 @@ - work_mbc->coll_elems[work_mbc->ncoll_elems++] = elem; - } - } -- wc1 = wc = -1; -+ wc1 = wc = WEOF; - } - else - /* We treat '[' as a normal character here. */ -@@ -600,7 +600,7 @@ - wc = fetch_wc(("Unbalanced [")); - } - -- if (wc1 == -1) -+ if (wc1 == WEOF) - wc1 = fetch_wc(_("Unbalanced [")); - - if (wc1 == L'-') -@@ -630,17 +630,17 @@ - } - REALLOC_IF_NECESSARY(work_mbc->range_sts, wchar_t, - range_sts_al, work_mbc->nranges + 1); -- work_mbc->range_sts[work_mbc->nranges] = wc; -+ work_mbc->range_sts[work_mbc->nranges] = (wchar_t)wc; - REALLOC_IF_NECESSARY(work_mbc->range_ends, wchar_t, - range_ends_al, work_mbc->nranges + 1); -- work_mbc->range_ends[work_mbc->nranges++] = wc2; -+ work_mbc->range_ends[work_mbc->nranges++] = (wchar_t)wc2; - } -- else if (wc != -1) -+ else if (wc != WEOF) - /* build normal characters. */ - { - REALLOC_IF_NECESSARY(work_mbc->chars, wchar_t, chars_al, - work_mbc->nchars + 1); -- work_mbc->chars[work_mbc->nchars++] = wc; -+ work_mbc->chars[work_mbc->nchars++] = (wchar_t)wc; - } - } - while ((wc = wc1) != L']'); -@@ -2552,6 +2552,8 @@ - } - - /* match with a character? */ -+ if (case_fold) -+ wc = towlower (wc); - for (i = 0; i<work_mbc->nchars; i++) - { - if (wc == work_mbc->chars[i]) ---- grep-2.5.1/src/grep.c.i18n 2002-03-26 15:54:12.000000000 +0000 -+++ grep-2.5.1/src/grep.c 2004-02-26 13:09:54.000000000 +0000 -@@ -30,6 +30,12 @@ - # include <sys/time.h> - # include <sys/resource.h> - #endif -+#if defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H && defined HAVE_MBRTOWC -+/* We can handle multibyte string. */ -+# define MBS_SUPPORT -+# include <wchar.h> -+# include <wctype.h> -+#endif - #include <stdio.h> - #include "system.h" - #include "getopt.h" -@@ -1697,6 +1703,37 @@ - if (!install_matcher (matcher) && !install_matcher ("default")) - abort (); - -+#ifdef MBS_SUPPORT -+ if (MB_CUR_MAX != 1 && match_icase) -+ { -+ wchar_t wc; -+ mbstate_t cur_state, prev_state; -+ int i, len = strlen(keys); -+ -+ memset(&cur_state, 0, sizeof(mbstate_t)); -+ for (i = 0; i <= len ;) -+ { -+ size_t mbclen; -+ mbclen = mbrtowc(&wc, keys + i, len - 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 (iswupper((wint_t)wc)) -+ { -+ wc = towlower((wint_t)wc); -+ wcrtomb(keys + i, wc, &cur_state); -+ } -+ } -+ i += mbclen; -+ } -+ } -+#endif /* MBS_SUPPORT */ -+ - (*compile)(keys, keycc); - - if ((argc - optind > 1 && !no_filenames) || with_filenames) ---- grep-2.5.1/src/search.c.i18n 2004-02-26 13:09:54.000000000 +0000 -+++ grep-2.5.1/src/search.c 2004-02-26 13:17:12.000000000 +0000 -@@ -149,15 +149,16 @@ - static char* - check_multibyte_string(char const *buf, size_t size) - { -- char *mb_properties = malloc(size); -+ 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 = mbrlen(buf + i, size - i, &cur_state); -+ mbclen = mbrtowc(&wc, buf + i, size - i, &cur_state); - - if (mbclen == (size_t) -1 || mbclen == (size_t) -2 || mbclen == 0) - { -@@ -165,6 +166,14 @@ - 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; - } -@@ -233,7 +242,7 @@ - static char const line_end[] = "\\)$"; - static char const word_beg[] = "\\(^\\|[^[:alnum:]_]\\)\\("; - static char const word_end[] = "\\)\\([^[:alnum:]_]\\|$\\)"; -- char *n = malloc (sizeof word_beg - 1 + size + sizeof word_end); -+ char *n = xmalloc (sizeof word_beg - 1 + size + sizeof word_end); - size_t i; - strcpy (n, match_lines ? line_beg : word_beg); - i = strlen (n); -@@ -316,7 +325,7 @@ - static char const line_end[] = ")$"; - static char const word_beg[] = "(^|[^[:alnum:]_])("; - static char const word_end[] = ")([^[:alnum:]_]|$)"; -- char *n = malloc (sizeof word_beg - 1 + size + sizeof word_end); -+ char *n = xmalloc (sizeof word_beg - 1 + size + sizeof word_end); - size_t i; - strcpy (n, match_lines ? line_beg : word_beg); - i = strlen(n); -@@ -339,14 +348,20 @@ - char eol = eolbyte; - int backref, start, len; - struct kwsmatch kwsm; -- size_t i; -+ size_t i, ret_val; - #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); -+ if (MB_CUR_MAX > 1) -+ { -+ if (match_icase) -+ { -+ char *case_buf = xmalloc(size); -+ memcpy(case_buf, buf, size); -+ buf = case_buf; -+ } -+ if (kwset) -+ mb_properties = check_multibyte_string(buf, size); -+ } - #endif /* MBS_SUPPORT */ - - buflim = buf + size; -@@ -455,8 +470,13 @@ - - failure: - #ifdef MBS_SUPPORT -- if (MB_CUR_MAX > 1 && mb_properties) -- free (mb_properties); -+ if (MB_CUR_MAX > 1) -+ { -+ if (mb_properties) -+ free (mb_properties); -+ if (match_icase) -+ free ((char *) buf); -+ } - #endif /* MBS_SUPPORT */ - return (size_t) -1; - -@@ -467,8 +487,13 @@ - - success_in_start_and_len: - #ifdef MBS_SUPPORT -- if (MB_CUR_MAX > 1 && mb_properties) -- free (mb_properties); -+ if (MB_CUR_MAX > 1) -+ { -+ if (mb_properties) -+ free (mb_properties); -+ if (match_icase) -+ free ((char *) buf); -+ } - #endif /* MBS_SUPPORT */ - *match_size = len; - return start; -@@ -504,10 +529,19 @@ - register size_t len; - char eol = eolbyte; - struct kwsmatch kwsmatch; -+ size_t ret_val; - #ifdef MBS_SUPPORT -- char *mb_properties; -+ char *mb_properties = NULL; - if (MB_CUR_MAX > 1) -- mb_properties = check_multibyte_string (buf, size); -+ { -+ if (match_icase) -+ { -+ char *case_buf = xmalloc(size); -+ memcpy(case_buf, buf, size); -+ buf = case_buf; -+ } -+ mb_properties = check_multibyte_string(buf, size); -+ } - #endif /* MBS_SUPPORT */ - - for (beg = buf; beg <= buf + size; ++beg) -@@ -565,7 +599,12 @@ - failure: - #ifdef MBS_SUPPORT - if (MB_CUR_MAX > 1) -- free (mb_properties); -+ { -+ if (match_icase) -+ free((char *) buf); -+ if (mb_properties) -+ free(mb_properties); -+ } - #endif /* MBS_SUPPORT */ - return -1; - -@@ -581,7 +620,12 @@ - *match_size = len; - #ifdef MBS_SUPPORT - if (MB_CUR_MAX > 1) -- free (mb_properties); -+ { -+ if (mb_properties) -+ free (mb_properties); -+ if (match_icase) -+ free ((char *) buf); -+ } - #endif /* MBS_SUPPORT */ - return beg - buf; - } diff --git a/abs/core/grep/04-oi.patch b/abs/core/grep/04-oi.patch deleted file mode 100644 index eb997ad..0000000 --- a/abs/core/grep/04-oi.patch +++ /dev/null @@ -1,48 +0,0 @@ ---- grep-2.5.1/lib/posix/regex.h.oi 2004-01-05 12:09:12.984391131 +0000 -+++ grep-2.5.1/lib/posix/regex.h 2004-01-05 12:09:24.717990622 +0000 -@@ -109,6 +109,10 @@ - If not set, \{, \}, {, and } are literals. */ - #define RE_INTERVALS (RE_HAT_LISTS_NOT_NEWLINE << 1) - -+/* If this bit is set, then ignore case when matching. -+ If not set, then case is significant. */ -+#define RE_ICASE (RE_INVALID_INTERVAL_ORD << 1) -+ - /* If this bit is set, +, ? and | aren't recognized as operators. - If not set, they are. */ - #define RE_LIMITED_OPS (RE_INTERVALS << 1) ---- grep-2.5.1/src/search.c.oi 2004-01-05 12:07:00.550199415 +0000 -+++ grep-2.5.1/src/search.c 2004-01-05 12:07:00.566197505 +0000 -@@ -31,7 +31,7 @@ - - #include "system.h" - #include "grep.h" --#include "regex.h" -+#include <regex.h> - #include "dfa.h" - #include "kwset.h" - #include "error.h" -@@ -190,7 +190,7 @@ - size_t total = size; - char const *motif = pattern; - -- re_set_syntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE); -+ re_set_syntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE | (match_icase ? RE_ICASE : 0)); - dfasyntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE, match_icase, eolbyte); - - /* For GNU regex compiler we have to pass the patterns separately to detect -@@ -268,12 +268,12 @@ - - if (strcmp (matcher, "awk") == 0) - { -- re_set_syntax (RE_SYNTAX_AWK); -+ re_set_syntax (RE_SYNTAX_AWK | (match_icase ? RE_ICASE : 0)); - dfasyntax (RE_SYNTAX_AWK, match_icase, eolbyte); - } - else - { -- re_set_syntax (RE_SYNTAX_POSIX_EGREP); -+ re_set_syntax (RE_SYNTAX_POSIX_EGREP | (match_icase ? RE_ICASE : 0)); - dfasyntax (RE_SYNTAX_POSIX_EGREP, match_icase, eolbyte); - } - diff --git a/abs/core/grep/05-manpage.patch b/abs/core/grep/05-manpage.patch deleted file mode 100644 index 284f0c4..0000000 --- a/abs/core/grep/05-manpage.patch +++ /dev/null @@ -1,19 +0,0 @@ ---- grep-2.5.1/doc/grep.1.manpage 2002-01-22 13:20:04.000000000 +0000 -+++ grep-2.5.1/doc/grep.1 2003-10-08 09:37:32.000000000 +0100 -@@ -191,6 +191,7 @@ - .I PATTERN - as a list of fixed strings, separated by newlines, - any of which is to be matched. -+.TP - .BR \-P ", " \-\^\-perl-regexp - Interpret - .I PATTERN -@@ -302,7 +303,7 @@ - This is especially useful for tools like zgrep, e.g. - .B "gzip -cd foo.gz |grep --label=foo something" - .TP --.BR \-\^\-line-buffering -+.BR \-\^\-line-buffered - Use line buffering, it can be a performance penality. - .TP - .BR \-q ", " \-\^\-quiet ", " \-\^\-silent diff --git a/abs/core/grep/06-color.patch b/abs/core/grep/06-color.patch deleted file mode 100644 index f54c258..0000000 --- a/abs/core/grep/06-color.patch +++ /dev/null @@ -1,10 +0,0 @@ ---- grep-2.5.1/src/grep.c.color 2004-11-16 16:46:22.845505847 +0000 -+++ grep-2.5.1/src/grep.c 2004-11-16 16:46:27.961530537 +0000 -@@ -607,6 +607,7 @@ - fputs ("\33[00m", stdout); - beg = b + match_size; - } -+ fputs ("\33[K", stdout); - } - fwrite (beg, 1, lim - beg, stdout); - if (ferror (stdout)) diff --git a/abs/core/grep/07-icolor.patch b/abs/core/grep/07-icolor.patch deleted file mode 100644 index 14b2617..0000000 --- a/abs/core/grep/07-icolor.patch +++ /dev/null @@ -1,36 +0,0 @@ ---- grep-2.5.1a/src/grep.c.icolor 2005-01-07 12:05:20.877785250 +0000 -+++ grep-2.5.1a/src/grep.c 2005-01-07 12:05:44.690194388 +0000 -@@ -564,33 +564,6 @@ - { - size_t match_size; - size_t match_offset; -- if(match_icase) -- { -- /* Yuck, this is tricky */ -- char *buf = (char*) xmalloc (lim - beg); -- char *ibeg = buf; -- char *ilim = ibeg + (lim - beg); -- int i; -- for (i = 0; i < lim - beg; i++) -- ibeg[i] = tolower (beg[i]); -- while ((match_offset = (*execute) (ibeg, ilim-ibeg, &match_size, 1)) -- != (size_t) -1) -- { -- char const *b = beg + match_offset; -- if (b == lim) -- break; -- fwrite (beg, sizeof (char), match_offset, stdout); -- printf ("\33[%sm", grep_color); -- fwrite (b, sizeof (char), match_size, stdout); -- fputs ("\33[00m", stdout); -- beg = b + match_size; -- ibeg = ibeg + match_offset + match_size; -- } -- fwrite (beg, 1, lim - beg, stdout); -- free (buf); -- lastout = lim; -- return; -- } - while (lim-beg && (match_offset = (*execute) (beg, lim - beg, &match_size, 1)) - != (size_t) -1) - { diff --git a/abs/core/grep/08-skip.patch b/abs/core/grep/08-skip.patch deleted file mode 100644 index fb6645f..0000000 --- a/abs/core/grep/08-skip.patch +++ /dev/null @@ -1,42 +0,0 @@ ---- grep-2.5.1a/src/grep.c.skip 2006-05-31 09:26:58.000000000 +0100 -+++ grep-2.5.1a/src/grep.c 2006-05-31 09:28:24.000000000 +0100 -@@ -261,19 +261,6 @@ - bufbeg[-1] = eolbyte; - bufdesc = fd; - -- if (fstat (fd, &stats->stat) != 0) -- { -- error (0, errno, "fstat"); -- return 0; -- } -- if (directories == SKIP_DIRECTORIES && S_ISDIR (stats->stat.st_mode)) -- return 0; --#ifndef DJGPP -- if (devices == SKIP_DEVICES && (S_ISCHR(stats->stat.st_mode) || S_ISBLK(stats->stat.st_mode) || S_ISSOCK(stats->stat.st_mode))) --#else -- if (devices == SKIP_DEVICES && (S_ISCHR(stats->stat.st_mode) || S_ISBLK(stats->stat.st_mode))) --#endif -- return 0; - if (S_ISREG (stats->stat.st_mode)) - { - if (file) -@@ -875,6 +862,19 @@ - } - else - { -+ if (stat (file, &stats->stat) != 0) -+ { -+ suppressible_error (file, errno); -+ return 1; -+ } -+ if (directories == SKIP_DIRECTORIES && S_ISDIR (stats->stat.st_mode)) -+ return 1; -+#ifndef DJGPP -+ if (devices == SKIP_DEVICES && (S_ISCHR(stats->stat.st_mode) || S_ISBLK(stats->stat.st_mode) || S_ISSOCK(stats->stat.st_mode) || S_ISFIFO(stats->stat.st_mode))) -+#else -+ if (devices == SKIP_DEVICES && (S_ISCHR(stats->stat.st_mode) || S_ISBLK(stats->stat.st_mode))) -+#endif -+ return 1; - while ((desc = open (file, O_RDONLY)) < 0 && errno == EINTR) - continue; - diff --git a/abs/core/grep/09-egf-speedup.patch b/abs/core/grep/09-egf-speedup.patch deleted file mode 100644 index 08e92c7..0000000 --- a/abs/core/grep/09-egf-speedup.patch +++ /dev/null @@ -1,823 +0,0 @@ ---- grep-2.5.1/src/search.c 2004-12-31 15:28:35.720391036 +0000 -+++ grep-2.5.1a/src/search.c 2005-01-07 14:53:10.308860193 +0000 -@@ -18,9 +18,13 @@ - - /* Written August 1992 by Mike Haertel. */ - -+#ifndef _GNU_SOURCE -+# define _GNU_SOURCE 1 -+#endif - #ifdef HAVE_CONFIG_H - # include <config.h> - #endif -+#include <assert.h> - #include <sys/types.h> - #if defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H && defined HAVE_MBRTOWC - /* We can handle multibyte string. */ -@@ -39,6 +43,9 @@ - #ifdef HAVE_LIBPCRE - # include <pcre.h> - #endif -+#ifdef HAVE_LANGINFO_CODESET -+# include <langinfo.h> -+#endif - - #define NCHAR (UCHAR_MAX + 1) - -@@ -70,9 +77,10 @@ - call the regexp matcher at all. */ - static int kwset_exact_matches; - --#if defined(MBS_SUPPORT) --static char* check_multibyte_string PARAMS ((char const *buf, size_t size)); --#endif -+/* UTF-8 encoding allows some optimizations that we can't otherwise -+ assume in a multibyte encoding. */ -+static int using_utf8; -+ - static void kwsinit PARAMS ((void)); - static void kwsmusts PARAMS ((void)); - static void Gcompile PARAMS ((char const *, size_t)); -@@ -84,6 +92,15 @@ - static size_t Pexecute PARAMS ((char const *, size_t, size_t *, int)); - - void -+check_utf8 (void) -+{ -+#ifdef HAVE_LANGINFO_CODESET -+ if (strcmp (nl_langinfo (CODESET), "UTF-8") == 0) -+ using_utf8 = 1; -+#endif -+} -+ -+void - dfaerror (char const *mesg) - { - error (2, 0, mesg); -@@ -141,47 +158,6 @@ - } - } - --#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 = 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 (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; -- } -- -- return mb_properties; --} --#endif -- - static void - Gcompile (char const *pattern, size_t size) - { -@@ -190,6 +166,7 @@ - size_t total = size; - char const *motif = pattern; - -+ check_utf8 (); - re_set_syntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE | (match_icase ? RE_ICASE : 0)); - dfasyntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE, match_icase, eolbyte); - -@@ -266,6 +243,7 @@ - size_t total = size; - char const *motif = pattern; - -+ check_utf8 (); - if (strcmp (matcher, "awk") == 0) - { - re_set_syntax (RE_SYNTAX_AWK | (match_icase ? RE_ICASE : 0)); -@@ -350,18 +328,9 @@ - struct kwsmatch kwsm; - size_t i, ret_val; - #ifdef MBS_SUPPORT -- char *mb_properties = NULL; -- if (MB_CUR_MAX > 1) -- { -- if (match_icase) -- { -- char *case_buf = xmalloc(size); -- memcpy(case_buf, buf, size); -- buf = case_buf; -- } -- if (kwset) -- mb_properties = check_multibyte_string(buf, size); -- } -+ int mb_cur_max = MB_CUR_MAX; -+ mbstate_t mbs; -+ memset (&mbs, '\0', sizeof (mbstate_t)); - #endif /* MBS_SUPPORT */ - - buflim = buf + size; -@@ -373,21 +342,63 @@ - if (kwset) - { - /* Find a possible match using the KWset matcher. */ -- size_t offset = kwsexec (kwset, beg, buflim - beg, &kwsm); -+#ifdef MBS_SUPPORT -+ size_t bytes_left = 0; -+#endif /* MBS_SUPPORT */ -+ size_t offset; -+#ifdef MBS_SUPPORT -+ /* kwsexec doesn't work with match_icase and multibyte input. */ -+ if (match_icase && mb_cur_max > 1) -+ /* Avoid kwset */ -+ offset = 0; -+ else -+#endif /* MBS_SUPPORT */ -+ offset = kwsexec (kwset, beg, buflim - beg, &kwsm); - if (offset == (size_t) -1) - goto failure; -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1 && !using_utf8) -+ { -+ bytes_left = offset; -+ while (bytes_left) -+ { -+ size_t mlen = mbrlen (beg, bytes_left, &mbs); -+ if (mlen == (size_t) -1 || mlen == 0) -+ { -+ /* Incomplete character: treat as single-byte. */ -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ beg++; -+ bytes_left--; -+ continue; -+ } -+ -+ if (mlen == (size_t) -2) -+ /* Offset points inside multibyte character: -+ * no good. */ -+ break; -+ -+ beg += mlen; -+ bytes_left -= mlen; -+ } -+ } -+ else -+#endif /* MBS_SUPPORT */ - beg += offset; - /* Narrow down to the line containing the candidate, and - run it through DFA. */ - end = memchr(beg, eol, buflim - beg); - end++; - #ifdef MBS_SUPPORT -- if (MB_CUR_MAX > 1 && mb_properties[beg - buf] == 0) -+ if (mb_cur_max > 1 && bytes_left) - continue; --#endif -+#endif /* MBS_SUPPORT */ - while (beg > buf && beg[-1] != eol) - --beg; -- if (kwsm.index < kwset_exact_matches) -+ if ( -+#ifdef MBS_SUPPORT -+ !(match_icase && mb_cur_max > 1) && -+#endif /* MBS_SUPPORT */ -+ (kwsm.index < kwset_exact_matches)) - goto success_in_beg_and_end; - if (dfaexec (&dfa, beg, end - beg, &backref) == (size_t) -1) - continue; -@@ -395,13 +406,47 @@ - else - { - /* No good fixed strings; start with DFA. */ -+#ifdef MBS_SUPPORT -+ size_t bytes_left = 0; -+#endif /* MBS_SUPPORT */ - size_t offset = dfaexec (&dfa, beg, buflim - beg, &backref); - if (offset == (size_t) -1) - break; - /* Narrow down to the line we've found. */ -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1 && !using_utf8) -+ { -+ bytes_left = offset; -+ while (bytes_left) -+ { -+ size_t mlen = mbrlen (beg, bytes_left, &mbs); -+ if (mlen == (size_t) -1 || mlen == 0) -+ { -+ /* Incomplete character: treat as single-byte. */ -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ beg++; -+ bytes_left--; -+ continue; -+ } -+ -+ if (mlen == (size_t) -2) -+ /* Offset points inside multibyte character: -+ * no good. */ -+ break; -+ -+ beg += mlen; -+ bytes_left -= mlen; -+ } -+ } -+ else -+#endif /* MBS_SUPPORT */ - beg += offset; - end = memchr (beg, eol, buflim - beg); - end++; -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1 && bytes_left) -+ continue; -+#endif /* MBS_SUPPORT */ - while (beg > buf && beg[-1] != eol) - --beg; - } -@@ -469,15 +514,6 @@ - } /* for (beg = end ..) */ - - failure: --#ifdef MBS_SUPPORT -- if (MB_CUR_MAX > 1) -- { -- if (mb_properties) -- free (mb_properties); -- if (match_icase) -- free ((char *) buf); -- } --#endif /* MBS_SUPPORT */ - return (size_t) -1; - - success_in_beg_and_end: -@@ -486,24 +522,144 @@ - /* FALLTHROUGH */ - - success_in_start_and_len: --#ifdef MBS_SUPPORT -- if (MB_CUR_MAX > 1) -- { -- if (mb_properties) -- free (mb_properties); -- if (match_icase) -- free ((char *) buf); -- } --#endif /* MBS_SUPPORT */ - *match_size = len; - return start; - } - -+#ifdef MBS_SUPPORT -+static int f_i_multibyte; /* whether we're using the new -Fi MB method */ -+static struct -+{ -+ wchar_t **patterns; -+ size_t count, maxlen; -+ unsigned char *match; -+} Fimb; -+#endif -+ - static void - Fcompile (char const *pattern, size_t size) - { -+ int mb_cur_max = MB_CUR_MAX; - char const *beg, *lim, *err; - -+ check_utf8 (); -+#ifdef MBS_SUPPORT -+ /* Support -F -i for UTF-8 input. */ -+ if (match_icase && mb_cur_max > 1) -+ { -+ mbstate_t mbs; -+ wchar_t *wcpattern = xmalloc ((size + 1) * sizeof (wchar_t)); -+ const char *patternend = pattern; -+ size_t wcsize; -+ kwset_t fimb_kwset = NULL; -+ char *starts = NULL; -+ wchar_t *wcbeg, *wclim; -+ size_t allocated = 0; -+ -+ memset (&mbs, '\0', sizeof (mbs)); -+# ifdef __GNU_LIBRARY__ -+ wcsize = mbsnrtowcs (wcpattern, &patternend, size, size, &mbs); -+ if (patternend != pattern + size) -+ wcsize = (size_t) -1; -+# else -+ { -+ char *patterncopy = xmalloc (size + 1); -+ -+ memcpy (patterncopy, pattern, size); -+ patterncopy[size] = '\0'; -+ patternend = patterncopy; -+ wcsize = mbsrtowcs (wcpattern, &patternend, size, &mbs); -+ if (patternend != patterncopy + size) -+ wcsize = (size_t) -1; -+ free (patterncopy); -+ } -+# endif -+ if (wcsize + 2 <= 2) -+ { -+fimb_fail: -+ free (wcpattern); -+ free (starts); -+ if (fimb_kwset) -+ kwsfree (fimb_kwset); -+ free (Fimb.patterns); -+ Fimb.patterns = NULL; -+ } -+ else -+ { -+ if (!(fimb_kwset = kwsalloc (NULL))) -+ error (2, 0, _("memory exhausted")); -+ -+ starts = xmalloc (mb_cur_max * 3); -+ wcbeg = wcpattern; -+ do -+ { -+ int i; -+ size_t wclen; -+ -+ if (Fimb.count >= allocated) -+ { -+ if (allocated == 0) -+ allocated = 128; -+ else -+ allocated *= 2; -+ Fimb.patterns = xrealloc (Fimb.patterns, -+ sizeof (wchar_t *) * allocated); -+ } -+ Fimb.patterns[Fimb.count++] = wcbeg; -+ for (wclim = wcbeg; -+ wclim < wcpattern + wcsize && *wclim != L'\n'; ++wclim) -+ *wclim = towlower (*wclim); -+ *wclim = L'\0'; -+ wclen = wclim - wcbeg; -+ if (wclen > Fimb.maxlen) -+ Fimb.maxlen = wclen; -+ if (wclen > 3) -+ wclen = 3; -+ if (wclen == 0) -+ { -+ if ((err = kwsincr (fimb_kwset, "", 0)) != 0) -+ error (2, 0, err); -+ } -+ else -+ for (i = 0; i < (1 << wclen); i++) -+ { -+ char *p = starts; -+ int j, k; -+ -+ for (j = 0; j < wclen; ++j) -+ { -+ wchar_t wc = wcbeg[j]; -+ if (i & (1 << j)) -+ { -+ wc = towupper (wc); -+ if (wc == wcbeg[j]) -+ continue; -+ } -+ k = wctomb (p, wc); -+ if (k <= 0) -+ goto fimb_fail; -+ p += k; -+ } -+ if ((err = kwsincr (fimb_kwset, starts, p - starts)) != 0) -+ error (2, 0, err); -+ } -+ if (wclim < wcpattern + wcsize) -+ ++wclim; -+ wcbeg = wclim; -+ } -+ while (wcbeg < wcpattern + wcsize); -+ f_i_multibyte = 1; -+ kwset = fimb_kwset; -+ free (starts); -+ Fimb.match = xmalloc (Fimb.count); -+ if ((err = kwsprep (kwset)) != 0) -+ error (2, 0, err); -+ return; -+ } -+ } -+#endif /* MBS_SUPPORT */ -+ -+ - kwsinit (); - beg = pattern; - do -@@ -522,6 +678,76 @@ - error (2, 0, err); - } - -+#ifdef MBS_SUPPORT -+static int -+Fimbexec (const char *buf, size_t size, size_t *plen, int exact) -+{ -+ size_t len, letter, i; -+ int ret = -1; -+ mbstate_t mbs; -+ wchar_t wc; -+ int patterns_left; -+ -+ assert (match_icase && f_i_multibyte == 1); -+ assert (MB_CUR_MAX > 1); -+ -+ memset (&mbs, '\0', sizeof (mbs)); -+ memset (Fimb.match, '\1', Fimb.count); -+ letter = len = 0; -+ patterns_left = 1; -+ while (patterns_left && len <= size) -+ { -+ size_t c; -+ -+ patterns_left = 0; -+ if (len < size) -+ { -+ c = mbrtowc (&wc, buf + len, size - len, &mbs); -+ if (c + 2 <= 2) -+ return ret; -+ -+ wc = towlower (wc); -+ } -+ else -+ { -+ c = 1; -+ wc = L'\0'; -+ } -+ -+ for (i = 0; i < Fimb.count; i++) -+ { -+ if (Fimb.match[i]) -+ { -+ if (Fimb.patterns[i][letter] == L'\0') -+ { -+ /* Found a match. */ -+ *plen = len; -+ if (!exact && !match_words) -+ return 0; -+ else -+ { -+ /* For -w or exact look for longest match. */ -+ ret = 0; -+ Fimb.match[i] = '\0'; -+ continue; -+ } -+ } -+ -+ if (Fimb.patterns[i][letter] == wc) -+ patterns_left = 1; -+ else -+ Fimb.match[i] = '\0'; -+ } -+ } -+ -+ len += c; -+ letter++; -+ } -+ -+ return ret; -+} -+#endif /* MBS_SUPPORT */ -+ - static size_t - Fexecute (char const *buf, size_t size, size_t *match_size, int exact) - { -@@ -531,80 +757,258 @@ - struct kwsmatch kwsmatch; - size_t ret_val; - #ifdef MBS_SUPPORT -- char *mb_properties = NULL; -- if (MB_CUR_MAX > 1) -- { -- if (match_icase) -- { -- char *case_buf = xmalloc(size); -- memcpy(case_buf, buf, size); -- buf = case_buf; -- } -- mb_properties = check_multibyte_string(buf, size); -- } -+ int mb_cur_max = MB_CUR_MAX; -+ mbstate_t mbs; -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ const char *last_char = NULL; - #endif /* MBS_SUPPORT */ - - for (beg = buf; beg <= buf + size; ++beg) - { -- size_t offset = kwsexec (kwset, beg, buf + size - beg, &kwsmatch); -+ size_t offset; -+ offset = kwsexec (kwset, beg, buf + size - beg, &kwsmatch); -+ - if (offset == (size_t) -1) - goto failure; - #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 && !using_utf8) -+ { -+ size_t bytes_left = offset; -+ while (bytes_left) -+ { -+ size_t mlen = mbrlen (beg, bytes_left, &mbs); -+ -+ last_char = beg; -+ if (mlen == (size_t) -1 || mlen == 0) -+ { -+ /* Incomplete character: treat as single-byte. */ -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ beg++; -+ bytes_left--; -+ continue; -+ } -+ -+ if (mlen == (size_t) -2) -+ /* Offset points inside multibyte character: no good. */ -+ break; -+ -+ beg += mlen; -+ bytes_left -= mlen; -+ } -+ -+ if (bytes_left) -+ continue; -+ } -+ else - #endif /* MBS_SUPPORT */ - beg += offset; -+#ifdef MBS_SUPPORT -+ /* For f_i_multibyte, the string at beg now matches first 3 chars of -+ one of the search strings (less if there are shorter search strings). -+ See if this is a real match. */ -+ if (f_i_multibyte -+ && Fimbexec (beg, buf + size - beg, &kwsmatch.size[0], exact)) -+ goto next_char; -+#endif /* MBS_SUPPORT */ - len = kwsmatch.size[0]; - if (exact && !match_words) - goto success_in_beg_and_len; - if (match_lines) - { - if (beg > buf && beg[-1] != eol) -- continue; -+ goto next_char; - if (beg + len < buf + size && beg[len] != eol) -- continue; -+ goto next_char; - goto success; - } - else if (match_words) -- for (try = beg; len; ) -- { -- if (try > buf && WCHAR((unsigned char) try[-1])) -- break; -- if (try + len < buf + size && WCHAR((unsigned char) try[len])) -- { -- offset = kwsexec (kwset, beg, --len, &kwsmatch); -- if (offset == (size_t) -1) -- { -+ { -+ while (len) -+ { -+ int word_match = 0; -+ if (beg > buf) -+ { - #ifdef MBS_SUPPORT -- if (MB_CUR_MAX > 1) -- free (mb_properties); -+ if (mb_cur_max > 1) -+ { -+ const char *s; -+ int mr; -+ wchar_t pwc; -+ -+ if (using_utf8) -+ { -+ s = beg - 1; -+ while (s > buf -+ && (unsigned char) *s >= 0x80 -+ && (unsigned char) *s <= 0xbf) -+ --s; -+ } -+ else -+ s = last_char; -+ mr = mbtowc (&pwc, s, beg - s); -+ if (mr <= 0) -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ else if ((iswalnum (pwc) || pwc == L'_') -+ && mr == (int) (beg - s)) -+ goto next_char; -+ } -+ else - #endif /* MBS_SUPPORT */ -- return offset; -- } -- try = beg + offset; -- len = kwsmatch.size[0]; -- } -- else -- goto success; -- } -+ if (WCHAR ((unsigned char) beg[-1])) -+ goto next_char; -+ } -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1) -+ { -+ wchar_t nwc; -+ int mr; -+ -+ mr = mbtowc (&nwc, beg + len, buf + size - beg - len); -+ if (mr <= 0) -+ { -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ word_match = 1; -+ } -+ else if (!iswalnum (nwc) && nwc != L'_') -+ word_match = 1; -+ } -+ else -+#endif /* MBS_SUPPORT */ -+ if (beg + len >= buf + size || !WCHAR ((unsigned char) beg[len])) -+ word_match = 1; -+ if (word_match) -+ { -+ if (!exact) -+ /* Returns the whole line now we know there's a word match. */ -+ goto success; -+ else -+ /* Returns just this word match. */ -+ goto success_in_beg_and_len; -+ } -+ if (len > 0) -+ { -+ /* Try a shorter length anchored at the same place. */ -+ --len; -+ offset = kwsexec (kwset, beg, len, &kwsmatch); -+ -+ if (offset == -1) -+ goto next_char; /* Try a different anchor. */ -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1 && !using_utf8) -+ { -+ size_t bytes_left = offset; -+ while (bytes_left) -+ { -+ size_t mlen = mbrlen (beg, bytes_left, &mbs); -+ -+ last_char = beg; -+ if (mlen == (size_t) -1 || mlen == 0) -+ { -+ /* Incomplete character: treat as single-byte. */ -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ beg++; -+ bytes_left--; -+ continue; -+ } -+ -+ if (mlen == (size_t) -2) -+ { -+ /* Offset points inside multibyte character: -+ * no good. */ -+ break; -+ } -+ -+ beg += mlen; -+ bytes_left -= mlen; -+ } -+ -+ if (bytes_left) -+ { -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ goto next_char; /* Try a different anchor. */ -+ } -+ } -+ else -+#endif /* MBS_SUPPORT */ -+ beg += offset; -+#ifdef MBS_SUPPORT -+ /* The string at beg now matches first 3 chars of one of -+ the search strings (less if there are shorter search -+ strings). See if this is a real match. */ -+ if (f_i_multibyte -+ && Fimbexec (beg, len - offset, &kwsmatch.size[0], -+ exact)) -+ goto next_char; -+#endif /* MBS_SUPPORT */ -+ len = kwsmatch.size[0]; -+ } -+ } -+ } - else - goto success; -+next_char:; -+#ifdef MBS_SUPPORT -+ /* Advance to next character. For MB_CUR_MAX == 1 case this is handled -+ by ++beg above. */ -+ if (mb_cur_max > 1) -+ { -+ if (using_utf8) -+ { -+ unsigned char c = *beg; -+ if (c >= 0xc2) -+ { -+ if (c < 0xe0) -+ ++beg; -+ else if (c < 0xf0) -+ beg += 2; -+ else if (c < 0xf8) -+ beg += 3; -+ else if (c < 0xfc) -+ beg += 4; -+ else if (c < 0xfe) -+ beg += 5; -+ } -+ } -+ else -+ { -+ size_t l = mbrlen (beg, buf + size - beg, &mbs); -+ -+ last_char = beg; -+ if (l + 2 >= 2) -+ beg += l - 1; -+ else -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ } -+ } -+#endif /* MBS_SUPPORT */ - } - - failure: -+ return -1; -+ -+ success: - #ifdef MBS_SUPPORT -- if (MB_CUR_MAX > 1) -+ if (mb_cur_max > 1 && !using_utf8) - { -- if (match_icase) -- free((char *) buf); -- if (mb_properties) -- free(mb_properties); -+ end = beg + len; -+ while (end < buf + size) -+ { -+ size_t mlen = mbrlen (end, buf + size - end, &mbs); -+ if (mlen == (size_t) -1 || mlen == (size_t) -2 || mlen == 0) -+ { -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ mlen = 1; -+ } -+ if (mlen == 1 && *end == eol) -+ break; -+ -+ end += mlen; -+ } - } -+ else - #endif /* MBS_SUPPORT */ -- return -1; -- -- success: - end = memchr (beg + len, eol, (buf + size) - (beg + len)); -+ - end++; - while (buf < beg && beg[-1] != eol) - --beg; -@@ -613,15 +1017,6 @@ - - success_in_beg_and_len: - *match_size = len; --#ifdef MBS_SUPPORT -- if (MB_CUR_MAX > 1) -- { -- if (mb_properties) -- free (mb_properties); -- if (match_icase) -- free ((char *) buf); -- } --#endif /* MBS_SUPPORT */ - return beg - buf; - } - diff --git a/abs/core/grep/10-dfa-optional.patch b/abs/core/grep/10-dfa-optional.patch deleted file mode 100644 index 784eba9..0000000 --- a/abs/core/grep/10-dfa-optional.patch +++ /dev/null @@ -1,67 +0,0 @@ ---- grep-2.5.1a/src/search.c.dfa-optional 2005-01-07 14:58:45.714869815 +0000 -+++ grep-2.5.1a/src/search.c 2005-01-07 14:58:45.725867716 +0000 -@@ -327,12 +327,34 @@ - int backref, start, len; - struct kwsmatch kwsm; - size_t i, ret_val; -+ static int use_dfa; -+ static int use_dfa_checked = 0; - #ifdef MBS_SUPPORT - int mb_cur_max = MB_CUR_MAX; - mbstate_t mbs; - memset (&mbs, '\0', sizeof (mbstate_t)); - #endif /* MBS_SUPPORT */ - -+ if (!use_dfa_checked) -+ { -+ char *grep_use_dfa = getenv ("GREP_USE_DFA"); -+ if (!grep_use_dfa) -+ { -+#ifdef MBS_SUPPORT -+ /* Turn off DFA when processing multibyte input. */ -+ use_dfa = (MB_CUR_MAX == 1); -+#else -+ use_dfa = 1; -+#endif /* MBS_SUPPORT */ -+ } -+ else -+ { -+ use_dfa = atoi (grep_use_dfa); -+ } -+ -+ use_dfa_checked = 1; -+ } -+ - buflim = buf + size; - - for (beg = end = buf; end < buflim; beg = end) -@@ -400,7 +422,8 @@ - #endif /* MBS_SUPPORT */ - (kwsm.index < kwset_exact_matches)) - goto success_in_beg_and_end; -- if (dfaexec (&dfa, beg, end - beg, &backref) == (size_t) -1) -+ if (use_dfa && -+ dfaexec (&dfa, beg, end - beg, &backref) == (size_t) -1) - continue; - } - else -@@ -409,7 +432,9 @@ - #ifdef MBS_SUPPORT - size_t bytes_left = 0; - #endif /* MBS_SUPPORT */ -- size_t offset = dfaexec (&dfa, beg, buflim - beg, &backref); -+ size_t offset = 0; -+ if (use_dfa) -+ offset = dfaexec (&dfa, beg, buflim - beg, &backref); - if (offset == (size_t) -1) - break; - /* Narrow down to the line we've found. */ -@@ -451,7 +476,7 @@ - --beg; - } - /* Successful, no backreferences encountered! */ -- if (!backref) -+ if (use_dfa && !backref) - goto success_in_beg_and_end; - } - else diff --git a/abs/core/grep/11-tests.patch b/abs/core/grep/11-tests.patch deleted file mode 100644 index 2934a21..0000000 --- a/abs/core/grep/11-tests.patch +++ /dev/null @@ -1,138 +0,0 @@ ---- grep-2.5.1/tests/Makefile.am.jj 2001-03-07 05:11:27.000000000 +0100 -+++ grep-2.5.1/tests/Makefile.am 2004-12-31 11:42:41.595492300 +0100 -@@ -3,7 +3,8 @@ - AWK=@AWK@ - - TESTS = warning.sh khadafy.sh spencer1.sh bre.sh ere.sh \ -- status.sh empty.sh options.sh backref.sh file.sh -+ status.sh empty.sh options.sh backref.sh file.sh \ -+ fmbtest.sh - EXTRA_DIST = $(TESTS) \ - khadafy.lines khadafy.regexp \ - spencer1.awk spencer1.tests \ ---- grep-2.5.1/tests/fmbtest.sh 2004-12-31 13:30:23.942871250 +0100 -+++ grep-2.5.1/tests/fmbtest.sh 2004-12-31 14:09:13.219463855 +0100 -@@ -0,0 +1,111 @@ -+#!/bin/sh -+ -+: ${srcdir=.} -+ -+# If cs_CZ.UTF-8 locale doesn't work, skip this test silently -+LC_ALL=cs_CZ.UTF-8 locale -k LC_CTYPE 2>/dev/null | ${GREP} -q charmap.*UTF-8 \ -+ || exit 77 -+ -+failures=0 -+ -+cat > csinput <<EOF -+01 Žluťoučká číše -+ČíŠE 02 -+03 Z číší Čiší cosi -+04 Čí -+Še 05 -+06 ČČČČČČČíšČÍŠčíš -+07 ČČČ ČČČČíšČÍŠčíšEEEE -+čAs 08 -+09Čapka -+10ČaSy se měnÍ -+ČÍšE11 -+Čas12 -+𝇕ČÍšE𝇓13 -+ŽČÍšE𝇓14 -+𝇕ČÍšEŽ15 -+ŽČÍšEŽ16 -+ČÍšE𝇓17 -+ČÍšEŽ18 -+19𝇕ČÍše -+20ŽČÍše -+EOF -+cat > cspatfile <<EOF -+ČÍšE -+Čas -+EOF -+ -+for mode in F G E; do -+ -+test1="$(echo `LC_ALL=cs_CZ.UTF-8 ${GREP} -${mode} -f cspatfile csinput \ -+ | LC_ALL=C sed 's/^.*\([0-9][0-9]\).*$/\1/'`)" -+if test "$test1" != "11 12 13 14 15 16 17 18"; then -+ echo "Test #1 ${mode} failed: $test1" -+ failures=1 -+fi -+ -+test2="$(echo `LC_ALL=cs_CZ.UTF-8 ${GREP} -${mode}i -f cspatfile csinput \ -+ | LC_ALL=C sed 's/^.*\([0-9][0-9]\).*$/\1/'`)" -+if test "$test2" != "01 02 07 08 10 11 12 13 14 15 16 17 18 19 20"; then -+ echo "Test #2 ${mode} failed: $test2" -+ failures=1 -+fi -+ -+test3="$(echo `LC_ALL=cs_CZ.UTF-8 ${GREP} -${mode}i -e 'ČÍšE' -e 'Čas' csinput \ -+ | LC_ALL=C sed 's/^.*\([0-9][0-9]\).*$/\1/'`)" -+if test "$test3" != "01 02 07 08 10 11 12 13 14 15 16 17 18 19 20"; then -+ echo "Test #3 ${mode} failed: $test3" -+ failures=1 -+fi -+ -+test4="$(echo `LC_ALL=cs_CZ.UTF-8 ${GREP} -${mode}iw -f cspatfile csinput \ -+ | LC_ALL=C sed 's/^.*\([0-9][0-9]\).*$/\1/'`)" -+if test "$test4" != "01 02 08 13 17 19"; then -+ echo "Test #4 ${mode} failed: $test4" -+ failures=1 -+fi -+ -+done -+ -+# Test that -F --color=always prefers longer matches. -+test5="`echo 'Cosi tu ČišÍ...' \ -+ | LC_ALL=cs_CZ.UTF-8 ${GREP} --color=always -Fi -e 'čiš' -e 'čiší'`" -+if echo "$test5" | LC_ALL=C ${GREP} -q 'Cosi tu .*\[.*mČišÍ.*\[.*m\(.\[K\)\?\.\.\.'; then -+ : -+else -+ echo "Test #5 F failed: $test5" -+ failures=1 -+fi -+ -+for mode in G E; do -+ -+# Test that -{G,E} --color=always prefers earlier pattern matches. -+test6="`echo 'Cosi tu ČišÍ...' \ -+ | LC_ALL=cs_CZ.UTF-8 ${GREP} --color=always -${mode}i -e 'čiš' -e 'čiší'`" -+if echo "$test6" | LC_ALL=C ${GREP} -q 'Cosi tu .*\[.*mČiš.*\[.*m\(.\[K\)\?Í\.\.\.'; then -+ : -+else -+ echo "Test #6 ${mode} failed: $test6" -+ failures=1 -+fi -+ -+# Test that -{G,E} --color=always prefers earlier pattern matches. -+test7="`echo 'Cosi tu ČišÍ...' \ -+ | LC_ALL=cs_CZ.UTF-8 ${GREP} --color=always -${mode}i -e 'čiší' -e 'čiš'`" -+if echo "$test7" | LC_ALL=C ${GREP} -q 'Cosi tu .*\[.*mČišÍ.*\[.*m\(.\[K\)\?\.\.\.'; then -+ : -+else -+ echo "Test #7 ${mode} failed: $test7" -+ failures=1 -+fi -+ -+test8="$(echo `LC_ALL=cs_CZ.UTF-8 ${GREP} -${mode}i -e 'Č.šE' -e 'Č[a-f]s' csinput \ -+ | LC_ALL=C sed 's/^.*\([0-9][0-9]\).*$/\1/'`)" -+if test "$test8" != "01 02 07 08 10 11 12 13 14 15 16 17 18 19 20"; then -+ echo "Test #8 ${mode} failed: $test8" -+ failures=1 -+fi -+ -+done -+ -+exit $failures ---- grep-2.5.1/tests/Makefile.in.jj 2004-12-31 11:42:53.000000000 +0100 -+++ grep-2.5.1/tests/Makefile.in 2004-12-31 11:43:36.871514505 +0100 -@@ -97,7 +97,8 @@ install_sh = @install_sh@ - AWK = @AWK@ - - TESTS = warning.sh khadafy.sh spencer1.sh bre.sh ere.sh \ -- status.sh empty.sh options.sh backref.sh file.sh -+ status.sh empty.sh options.sh backref.sh file.sh \ -+ fmbtest.sh - - EXTRA_DIST = $(TESTS) \ - khadafy.lines khadafy.regexp \ diff --git a/abs/core/grep/12-w.patch b/abs/core/grep/12-w.patch deleted file mode 100644 index 79ae2ae..0000000 --- a/abs/core/grep/12-w.patch +++ /dev/null @@ -1,121 +0,0 @@ ---- grep-2.5.1a/src/search.c.w 2006-02-20 14:27:27.000000000 +0000 -+++ grep-2.5.1a/src/search.c 2006-02-20 14:32:07.000000000 +0000 -@@ -507,10 +507,114 @@ - if (match_words) - while (start >= 0) - { -- if ((start == 0 || !WCHAR ((unsigned char) beg[start - 1])) -- && (len == end - beg - 1 -- || !WCHAR ((unsigned char) beg[start + len]))) -- goto success_in_beg_and_end; -+ int lword_match = 0; -+ if (start == 0) -+ lword_match = 1; -+ else -+ { -+ assert (start > 0); -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1) -+ { -+ const char *s; -+ size_t mr; -+ wchar_t pwc; -+ -+ /* Locate the start of the multibyte character -+ before the match position (== beg + start). */ -+ if (using_utf8) -+ { -+ /* UTF-8 is a special case: scan backwards -+ until we find a 7-bit character or a -+ lead byte. */ -+ s = beg + start - 1; -+ while (s > buf -+ && (unsigned char) *s >= 0x80 -+ && (unsigned char) *s <= 0xbf) -+ --s; -+ } -+ else -+ { -+ /* Scan forwards to find the start of the -+ last complete character before the -+ match position. */ -+ size_t bytes_left = start - 1; -+ s = beg; -+ while (bytes_left > 0) -+ { -+ mr = mbrlen (s, bytes_left, &mbs); -+ if (mr == (size_t) -1 || mr == 0) -+ { -+ memset (&mbs, '\0', sizeof (mbs)); -+ s++; -+ bytes_left--; -+ continue; -+ } -+ if (mr == (size_t) -2) -+ { -+ memset (&mbs, '\0', sizeof (mbs)); -+ break; -+ } -+ s += mr; -+ bytes_left -= mr; -+ } -+ } -+ mr = mbrtowc (&pwc, s, beg + start - s, &mbs); -+ if (mr == (size_t) -2 || mr == (size_t) -1 || -+ mr == 0) -+ { -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ lword_match = 1; -+ } -+ else if (!(iswalnum (pwc) || pwc == L'_') -+ && mr == beg + start - s) -+ lword_match = 1; -+ } -+ else -+#endif /* MBS_SUPPORT */ -+ if (!WCHAR ((unsigned char) beg[start - 1])) -+ lword_match = 1; -+ } -+ -+ if (lword_match) -+ { -+ int rword_match = 0; -+ if (start + len == end - beg - 1) -+ rword_match = 1; -+ else -+ { -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1) -+ { -+ wchar_t nwc; -+ int mr; -+ -+ mr = mbtowc (&nwc, beg + start + len, -+ end - beg - start - len - 1); -+ if (mr <= 0) -+ { -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ rword_match = 1; -+ } -+ else if (!iswalnum (nwc) && nwc != L'_') -+ rword_match = 1; -+ } -+ else -+#endif /* MBS_SUPPORT */ -+ if (!WCHAR ((unsigned char) beg[start + len])) -+ rword_match = 1; -+ } -+ -+ if (rword_match) -+ { -+ if (!exact) -+ /* Returns the whole line. */ -+ goto success_in_beg_and_end; -+ else -+ /* Returns just this word match. */ -+ goto success_in_start_and_len; -+ } -+ } - if (len > 0) - { - /* Try a shorter length anchored at the same place. */ diff --git a/abs/core/grep/13-P.patch b/abs/core/grep/13-P.patch deleted file mode 100644 index 9dca4ad..0000000 --- a/abs/core/grep/13-P.patch +++ /dev/null @@ -1,14 +0,0 @@ ---- grep-2.5.1a/src/search.c.P 2006-02-03 14:08:00.000000000 +0000 -+++ grep-2.5.1a/src/search.c 2006-02-03 14:11:20.000000000 +0000 -@@ -1234,8 +1234,9 @@ - char eol = eolbyte; - if (!exact) - { -- end = memchr (end, eol, buflim - end); -- end++; -+ while (end < buflim) -+ if (*end++ == eol) -+ break; - while (buf < beg && beg[-1] != eol) - --beg; - } diff --git a/abs/core/grep/14-mem-exhausted.patch b/abs/core/grep/14-mem-exhausted.patch deleted file mode 100644 index d6a996d..0000000 --- a/abs/core/grep/14-mem-exhausted.patch +++ /dev/null @@ -1,15 +0,0 @@ ---- grep-2.5.1a/src/grep.c.mem-exhausted 2006-11-22 14:49:35.000000000 +0000 -+++ grep-2.5.1a/src/grep.c 2006-11-22 14:53:12.000000000 +0000 -@@ -299,6 +299,12 @@ - int cc = 1; - char *readbuf; - size_t readsize; -+ const size_t max_save = 200 * 1024 * 1024; -+ -+ /* Limit the amount of saved data to 200Mb so we don't fail on -+ * large files. */ -+ if (save > max_save) -+ save = max_save; - - /* Offset from start of buffer to start of old stuff - that we want to save. */ diff --git a/abs/core/grep/15-empty-pattern.patch b/abs/core/grep/15-empty-pattern.patch deleted file mode 100644 index acb702a..0000000 --- a/abs/core/grep/15-empty-pattern.patch +++ /dev/null @@ -1,36 +0,0 @@ ---- grep-2.5.1a/src/grep.c.empty-pattern 2006-11-22 19:05:43.000000000 +0000 -+++ grep-2.5.1a/src/grep.c 2006-11-22 19:22:04.000000000 +0000 -@@ -1667,9 +1667,6 @@ - out_invert ^= 1; - match_lines = match_words = 0; - } -- else -- /* Strip trailing newline. */ -- --keycc; - } - else - if (optind < argc) ---- grep-2.5.1a/src/search.c.empty-pattern 2006-11-22 19:21:11.000000000 +0000 -+++ grep-2.5.1a/src/search.c 2006-11-22 19:35:06.000000000 +0000 -@@ -204,6 +204,10 @@ - motif = sep; - } while (sep && total != 0); - -+ /* Strip trailing newline. */ -+ if (size && pattern[size - 1] == '\n') -+ size--; -+ - /* In the match_words and match_lines cases, we use a different pattern - for the DFA matcher that will quickly throw out cases that won't work. - Then if DFA succeeds we do some hairy stuff using the regex matcher -@@ -288,6 +292,10 @@ - motif = sep; - } while (sep && total != 0); - -+ /* Strip trailing newline. */ -+ if (size && pattern[size - 1] == '\n') -+ size--; -+ - /* In the match_words and match_lines cases, we use a different pattern - for the DFA matcher that will quickly throw out cases that won't work. - Then if DFA succeeds we do some hairy stuff using the regex matcher diff --git a/abs/core/grep/64-egf-speedup.patch b/abs/core/grep/64-egf-speedup.patch deleted file mode 100644 index a1fa024..0000000 --- a/abs/core/grep/64-egf-speedup.patch +++ /dev/null @@ -1,791 +0,0 @@ ---- a/src/search.c.orig -+++ b/src/search.c -@@ -18,10 +18,15 @@ - - /* Written August 1992 by Mike Haertel. */ - -+#ifndef _GNU_SOURCE -+# define _GNU_SOURCE 1 -+#endif - #ifdef HAVE_CONFIG_H - # include <config.h> - #endif - -+#include <assert.h> -+ - #include <sys/types.h> - - #include "mbsupport.h" -@@ -43,6 +48,9 @@ - #ifdef HAVE_LIBPCRE - # include <pcre.h> - #endif -+#ifdef HAVE_LANGINFO_CODESET -+# include <langinfo.h> -+#endif - - #define NCHAR (UCHAR_MAX + 1) - -@@ -68,6 +76,19 @@ - error (2, 0, _("memory exhausted")); - } - -+/* UTF-8 encoding allows some optimizations that we can't otherwise -+ assume in a multibyte encoding. */ -+static int using_utf8; -+ -+void -+check_utf8 (void) -+{ -+#ifdef HAVE_LANGINFO_CODESET -+ if (strcmp (nl_langinfo (CODESET), "UTF-8") == 0) -+ using_utf8 = 1; -+#endif -+} -+ - #ifndef FGREP_PROGRAM - /* DFA compiled regexp. */ - static struct dfa dfa; -@@ -134,49 +155,6 @@ - } - #endif /* !FGREP_PROGRAM */ - --#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 single byte 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 = 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 (mbclen == (size_t) -1 || mbclen == (size_t) -2 || mbclen == 0) -- { -- /* An invalid sequence, or a truncated multibyte character. -- We treat it as a single byte 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; -- } -- -- return mb_properties; --} --#endif /* MBS_SUPPORT */ -- - #if defined(GREP_PROGRAM) || defined(EGREP_PROGRAM) - #ifdef EGREP_PROGRAM - COMPILE_FCT(Ecompile) -@@ -193,6 +171,7 @@ - size_t total = size; - char const *motif = pattern; - -+ check_utf8 (); - #if 0 - if (match_icase) - syntax_bits |= RE_ICASE; -@@ -303,20 +282,9 @@ hunk6 - struct kwsmatch kwsm; - size_t i, ret_val; - #ifdef MBS_SUPPORT -- char *mb_properties = NULL; -- if (MB_CUR_MAX > 1) -- { -- if (match_icase) -- { -- char *case_buf = xmalloc(size); -- memcpy(case_buf, buf, size); -- if (start_ptr) -- start_ptr = case_buf + (start_ptr - buf); -- buf = case_buf; -- } -- if (kwset) -- mb_properties = check_multibyte_string(buf, size); -- } -+ int mb_cur_max = MB_CUR_MAX; -+ mbstate_t mbs; -+ memset (&mbs, '\0', sizeof (mbstate_t)); - #endif /* MBS_SUPPORT */ - - buflim = buf + size; -@@ -329,21 +282,63 @@ hunk6 - if (kwset) - { - /* Find a possible match using the KWset matcher. */ -- size_t offset = kwsexec (kwset, beg, buflim - beg, &kwsm); -+#ifdef MBS_SUPPORT -+ size_t bytes_left = 0; -+#endif /* MBS_SUPPORT */ -+ size_t offset; -+#ifdef MBS_SUPPORT -+ /* kwsexec doesn't work with match_icase and multibyte input. */ -+ if (match_icase && mb_cur_max > 1) -+ /* Avoid kwset */ -+ offset = 0; -+ else -+#endif /* MBS_SUPPORT */ -+ offset = kwsexec (kwset, beg, buflim - beg, &kwsm); - if (offset == (size_t) -1) -- goto failure; -+ return (size_t)-1; -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1 && !using_utf8) -+ { -+ bytes_left = offset; -+ while (bytes_left) -+ { -+ size_t mlen = mbrlen (beg, bytes_left, &mbs); -+ if (mlen == (size_t) -1 || mlen == 0) -+ { -+ /* Incomplete character: treat as single-byte. */ -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ beg++; -+ bytes_left--; -+ continue; -+ } -+ -+ if (mlen == (size_t) -2) -+ /* Offset points inside multibyte character: -+ * no good. */ -+ break; -+ -+ beg += mlen; -+ bytes_left -= mlen; -+ } -+ } -+ else -+#endif /* MBS_SUPPORT */ - beg += offset; - /* Narrow down to the line containing the candidate, and - run it through DFA. */ - end = memchr(beg, eol, buflim - beg); - end++; - #ifdef MBS_SUPPORT -- if (MB_CUR_MAX > 1 && mb_properties[beg - buf] == 0) -+ if (mb_cur_max > 1 && bytes_left) - continue; - #endif - while (beg > buf && beg[-1] != eol) - --beg; -- if (kwsm.index < kwset_exact_matches) -+ if ( -+#ifdef MBS_SUPPORT -+ !(match_icase && mb_cur_max > 1) && -+#endif /* MBS_SUPPORT */ -+ (kwsm.index < kwset_exact_matches)) - goto success; - if (dfaexec (&dfa, beg, end - beg, &backref) == (size_t) -1) - continue; -@@ -351,13 +363,47 @@ - else - { - /* No good fixed strings; start with DFA. */ -+#ifdef MBS_SUPPORT -+ size_t bytes_left = 0; -+#endif /* MBS_SUPPORT */ - size_t offset = dfaexec (&dfa, beg, buflim - beg, &backref); - if (offset == (size_t) -1) - break; - /* Narrow down to the line we've found. */ -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1 && !using_utf8) -+ { -+ bytes_left = offset; -+ while (bytes_left) -+ { -+ size_t mlen = mbrlen (beg, bytes_left, &mbs); -+ if (mlen == (size_t) -1 || mlen == 0) -+ { -+ /* Incomplete character: treat as single-byte. */ -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ beg++; -+ bytes_left--; -+ continue; -+ } -+ -+ if (mlen == (size_t) -2) -+ /* Offset points inside multibyte character: -+ * no good. */ -+ break; -+ -+ beg += mlen; -+ bytes_left -= mlen; -+ } -+ } -+ else -+#endif /* MBS_SUPPORT */ - beg += offset; - end = memchr (beg, eol, buflim - beg); - end++; -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1 && bytes_left) -+ continue; -+#endif /* MBS_SUPPORT */ - while (beg > buf && beg[-1] != eol) - --beg; - } -@@ -475,24 +521,144 @@ - *match_size = len; - ret_val = beg - buf; - out: --#ifdef MBS_SUPPORT -- if (MB_CUR_MAX > 1) -- { -- if (match_icase) -- free((char*)buf); -- if (mb_properties) -- free(mb_properties); -- } --#endif /* MBS_SUPPORT */ - return ret_val; - } - #endif /* defined(GREP_PROGRAM) || defined(EGREP_PROGRAM) */ - -+#ifdef MBS_SUPPORT -+static int f_i_multibyte; /* whether we're using the new -Fi MB method */ -+static struct -+{ -+ wchar_t **patterns; -+ size_t count, maxlen; -+ unsigned char *match; -+} Fimb; -+#endif -+ - #if defined(GREP_PROGRAM) || defined(FGREP_PROGRAM) - COMPILE_FCT(Fcompile) - { -+ int mb_cur_max = MB_CUR_MAX; - char const *beg, *lim, *err; - -+ check_utf8 (); -+#ifdef MBS_SUPPORT -+ /* Support -F -i for UTF-8 input. */ -+ if (match_icase && mb_cur_max > 1) -+ { -+ mbstate_t mbs; -+ wchar_t *wcpattern = xmalloc ((size + 1) * sizeof (wchar_t)); -+ const char *patternend = pattern; -+ size_t wcsize; -+ kwset_t fimb_kwset = NULL; -+ char *starts = NULL; -+ wchar_t *wcbeg, *wclim; -+ size_t allocated = 0; -+ -+ memset (&mbs, '\0', sizeof (mbs)); -+# ifdef __GNU_LIBRARY__ -+ wcsize = mbsnrtowcs (wcpattern, &patternend, size, size, &mbs); -+ if (patternend != pattern + size) -+ wcsize = (size_t) -1; -+# else -+ { -+ char *patterncopy = xmalloc (size + 1); -+ -+ memcpy (patterncopy, pattern, size); -+ patterncopy[size] = '\0'; -+ patternend = patterncopy; -+ wcsize = mbsrtowcs (wcpattern, &patternend, size, &mbs); -+ if (patternend != patterncopy + size) -+ wcsize = (size_t) -1; -+ free (patterncopy); -+ } -+# endif -+ if (wcsize + 2 <= 2) -+ { -+fimb_fail: -+ free (wcpattern); -+ free (starts); -+ if (fimb_kwset) -+ kwsfree (fimb_kwset); -+ free (Fimb.patterns); -+ Fimb.patterns = NULL; -+ } -+ else -+ { -+ if (!(fimb_kwset = kwsalloc (NULL))) -+ error (2, 0, _("memory exhausted")); -+ -+ starts = xmalloc (mb_cur_max * 3); -+ wcbeg = wcpattern; -+ do -+ { -+ int i; -+ size_t wclen; -+ -+ if (Fimb.count >= allocated) -+ { -+ if (allocated == 0) -+ allocated = 128; -+ else -+ allocated *= 2; -+ Fimb.patterns = xrealloc (Fimb.patterns, -+ sizeof (wchar_t *) * allocated); -+ } -+ Fimb.patterns[Fimb.count++] = wcbeg; -+ for (wclim = wcbeg; -+ wclim < wcpattern + wcsize && *wclim != L'\n'; ++wclim) -+ *wclim = towlower (*wclim); -+ *wclim = L'\0'; -+ wclen = wclim - wcbeg; -+ if (wclen > Fimb.maxlen) -+ Fimb.maxlen = wclen; -+ if (wclen > 3) -+ wclen = 3; -+ if (wclen == 0) -+ { -+ if ((err = kwsincr (fimb_kwset, "", 0)) != 0) -+ error (2, 0, err); -+ } -+ else -+ for (i = 0; i < (1 << wclen); i++) -+ { -+ char *p = starts; -+ int j, k; -+ -+ for (j = 0; j < wclen; ++j) -+ { -+ wchar_t wc = wcbeg[j]; -+ if (i & (1 << j)) -+ { -+ wc = towupper (wc); -+ if (wc == wcbeg[j]) -+ continue; -+ } -+ k = wctomb (p, wc); -+ if (k <= 0) -+ goto fimb_fail; -+ p += k; -+ } -+ if ((err = kwsincr (fimb_kwset, starts, p - starts)) != 0) -+ error (2, 0, err); -+ } -+ if (wclim < wcpattern + wcsize) -+ ++wclim; -+ wcbeg = wclim; -+ } -+ while (wcbeg < wcpattern + wcsize); -+ f_i_multibyte = 1; -+ kwset = fimb_kwset; -+ free (starts); -+ Fimb.match = xmalloc (Fimb.count); -+ if ((err = kwsprep (kwset)) != 0) -+ error (2, 0, err); -+ return; -+ } -+ } -+#endif /* MBS_SUPPORT */ -+ -+ - kwsinit (); - beg = pattern; - do -@@ -511,6 +677,76 @@ - error (2, 0, err); - } - -+#ifdef MBS_SUPPORT -+static int -+Fimbexec (const char *buf, size_t size, size_t *plen, int exact) -+{ -+ size_t len, letter, i; -+ int ret = -1; -+ mbstate_t mbs; -+ wchar_t wc; -+ int patterns_left; -+ -+ assert (match_icase && f_i_multibyte == 1); -+ assert (MB_CUR_MAX > 1); -+ -+ memset (&mbs, '\0', sizeof (mbs)); -+ memset (Fimb.match, '\1', Fimb.count); -+ letter = len = 0; -+ patterns_left = 1; -+ while (patterns_left && len <= size) -+ { -+ size_t c; -+ -+ patterns_left = 0; -+ if (len < size) -+ { -+ c = mbrtowc (&wc, buf + len, size - len, &mbs); -+ if (c + 2 <= 2) -+ return ret; -+ -+ wc = towlower (wc); -+ } -+ else -+ { -+ c = 1; -+ wc = L'\0'; -+ } -+ -+ for (i = 0; i < Fimb.count; i++) -+ { -+ if (Fimb.match[i]) -+ { -+ if (Fimb.patterns[i][letter] == L'\0') -+ { -+ /* Found a match. */ -+ *plen = len; -+ if (!exact && !match_words) -+ return 0; -+ else -+ { -+ /* For -w or exact look for longest match. */ -+ ret = 0; -+ Fimb.match[i] = '\0'; -+ continue; -+ } -+ } -+ -+ if (Fimb.patterns[i][letter] == wc) -+ patterns_left = 1; -+ else -+ Fimb.match[i] = '\0'; -+ } -+ } -+ -+ len += c; -+ letter++; -+ } -+ -+ return ret; -+} -+#endif /* MBS_SUPPORT */ -+ - EXECUTE_FCT(Fexecute) - { - register char const *beg, *try, *end; -@@ -519,69 +755,256 @@ - struct kwsmatch kwsmatch; - size_t ret_val; - #ifdef MBS_SUPPORT -- char *mb_properties = NULL; -- if (MB_CUR_MAX > 1) -- { -- if (match_icase) -- { -- char *case_buf = xmalloc(size); -- memcpy(case_buf, buf, size); -- if (start_ptr) -- start_ptr = case_buf + (start_ptr - buf); -- buf = case_buf; -- } -- mb_properties = check_multibyte_string(buf, size); -- } -+ int mb_cur_max = MB_CUR_MAX; -+ mbstate_t mbs; -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ const char *last_char = NULL; - #endif /* MBS_SUPPORT */ - - for (beg = start_ptr ? start_ptr : buf; beg <= buf + size; beg++) - { - size_t offset = kwsexec (kwset, beg, buf + size - beg, &kwsmatch); - if (offset == (size_t) -1) -- goto failure; -+ 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 && !using_utf8) -+ { -+ size_t bytes_left = offset; -+ while (bytes_left) -+ { -+ size_t mlen = mbrlen (beg, bytes_left, &mbs); -+ -+ last_char = beg; -+ if (mlen == (size_t) -1 || mlen == 0) -+ { -+ /* Incomplete character: treat as single-byte. */ -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ beg++; -+ bytes_left--; -+ continue; -+ } -+ -+ if (mlen == (size_t) -2) -+ /* Offset points inside multibyte character: no good. */ -+ break; -+ -+ beg += mlen; -+ bytes_left -= mlen; -+ } -+ -+ if (bytes_left) -+ continue; -+ } -+ else - #endif /* MBS_SUPPORT */ - beg += offset; -+#ifdef MBS_SUPPORT -+ /* For f_i_multibyte, the string at beg now matches first 3 chars of -+ one of the search strings (less if there are shorter search strings). -+ See if this is a real match. */ -+ if (f_i_multibyte -+ && Fimbexec (beg, buf + size - beg, &kwsmatch.size[0], start_ptr == NULL)) -+ goto next_char; -+#endif /* MBS_SUPPORT */ - len = kwsmatch.size[0]; - if (start_ptr && !match_words) - goto success_in_beg_and_len; - if (match_lines) - { - if (beg > buf && beg[-1] != eol) -- continue; -+ goto next_char; - if (beg + len < buf + size && beg[len] != eol) -- continue; -+ goto next_char; - goto success; - } - else if (match_words) -- for (try = beg; len; ) -- { -- if (try > buf && WCHAR((unsigned char) try[-1])) -- break; -- if (try + len < buf + size && WCHAR((unsigned char) try[len])) -- { -- offset = kwsexec (kwset, beg, --len, &kwsmatch); -- if (offset == (size_t) -1) -- break; -- try = beg + offset; -- len = kwsmatch.size[0]; -- } -- else if (!start_ptr) -- goto success; -- else -- goto success_in_beg_and_len; -- } /* for (try) */ -- else -- goto success; -- } /* for (beg in buf) */ -+ { -+ while (len) -+ { -+ int word_match = 0; -+ if (beg > buf) -+ { -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1) -+ { -+ const char *s; -+ int mr; -+ wchar_t pwc; -+ -+ if (using_utf8) -+ { -+ s = beg - 1; -+ while (s > buf -+ && (unsigned char) *s >= 0x80 -+ && (unsigned char) *s <= 0xbf) -+ --s; -+ } -+ else -+ s = last_char; -+ mr = mbtowc (&pwc, s, beg - s); -+ if (mr <= 0) -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ else if ((iswalnum (pwc) || pwc == L'_') -+ && mr == (int) (beg - s)) -+ goto next_char; -+ } -+ else -+#endif /* MBS_SUPPORT */ -+ if (WCHAR ((unsigned char) beg[-1])) -+ goto next_char; -+ } -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1) -+ { -+ wchar_t nwc; -+ int mr; - -- failure: -- ret_val = -1; -- goto out; -+ mr = mbtowc (&nwc, beg + len, buf + size - beg - len); -+ if (mr <= 0) -+ { -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ word_match = 1; -+ } -+ else if (!iswalnum (nwc) && nwc != L'_') -+ word_match = 1; -+ } -+ else -+#endif /* MBS_SUPPORT */ -+ if (beg + len >= buf + size || !WCHAR ((unsigned char) beg[len])) -+ word_match = 1; -+ if (word_match) -+ { -+ if (start_ptr == NULL) -+ /* Returns the whole line now we know there's a word match. */ -+ goto success; -+ else { -+ /* Returns just this word match. */ -+ *match_size = len; -+ return beg - buf; -+ } -+ } -+ if (len > 0) -+ { -+ /* Try a shorter length anchored at the same place. */ -+ --len; -+ offset = kwsexec (kwset, beg, len, &kwsmatch); -+ -+ if (offset == -1) -+ goto next_char; /* Try a different anchor. */ -+#ifdef MBS_SUPPORT -+ -+ if (mb_cur_max > 1 && !using_utf8) -+ { -+ size_t bytes_left = offset; -+ while (bytes_left) -+ { -+ size_t mlen = mbrlen (beg, bytes_left, &mbs); -+ -+ last_char = beg; -+ if (mlen == (size_t) -1 || mlen == 0) -+ { -+ /* Incomplete character: treat as single-byte. */ -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ beg++; -+ bytes_left--; -+ continue; -+ } -+ -+ if (mlen == (size_t) -2) -+ { -+ /* Offset points inside multibyte character: -+ * no good. */ -+ break; -+ } -+ -+ beg += mlen; -+ bytes_left -= mlen; -+ } -+ -+ if (bytes_left) -+ { -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ goto next_char; /* Try a different anchor. */ -+ } -+ } -+ else -+#endif /* MBS_SUPPORT */ -+ beg += offset; -+#ifdef MBS_SUPPORT -+ /* The string at beg now matches first 3 chars of one of -+ the search strings (less if there are shorter search -+ strings). See if this is a real match. */ -+ if (f_i_multibyte -+ && Fimbexec (beg, len - offset, &kwsmatch.size[0], -+ start_ptr == NULL)) -+ goto next_char; -+#endif /* MBS_SUPPORT */ -+ len = kwsmatch.size[0]; -+ } -+ } -+ } -+ else -+ goto success; -+next_char:; -+#ifdef MBS_SUPPORT -+ /* Advance to next character. For MB_CUR_MAX == 1 case this is handled -+ by ++beg above. */ -+ if (mb_cur_max > 1) -+ { -+ if (using_utf8) -+ { -+ unsigned char c = *beg; -+ if (c >= 0xc2) -+ { -+ if (c < 0xe0) -+ ++beg; -+ else if (c < 0xf0) -+ beg += 2; -+ else if (c < 0xf8) -+ beg += 3; -+ else if (c < 0xfc) -+ beg += 4; -+ else if (c < 0xfe) -+ beg += 5; -+ } -+ } -+ else -+ { -+ size_t l = mbrlen (beg, buf + size - beg, &mbs); -+ -+ last_char = beg; -+ if (l + 2 >= 2) -+ beg += l - 1; -+ else -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ } -+ } -+#endif /* MBS_SUPPORT */ -+ } -+ -+ return -1; - - success: -+#ifdef MBS_SUPPORT -+ if (mb_cur_max > 1 && !using_utf8) -+ { -+ end = beg + len; -+ while (end < buf + size) -+ { -+ size_t mlen = mbrlen (end, buf + size - end, &mbs); -+ if (mlen == (size_t) -1 || mlen == (size_t) -2 || mlen == 0) -+ { -+ memset (&mbs, '\0', sizeof (mbstate_t)); -+ mlen = 1; -+ } -+ if (mlen == 1 && *end == eol) -+ break; -+ -+ end += mlen; -+ } -+ } -+ else -+ #endif /* MBS_SUPPORT */ - end = memchr (beg + len, eol, (buf + size) - (beg + len)); - end++; - while (buf < beg && beg[-1] != eol) -@@ -591,15 +1016,6 @@ - *match_size = len; - ret_val = beg - buf; - out: --#ifdef MBS_SUPPORT -- if (MB_CUR_MAX > 1) -- { -- if (match_icase) -- free((char*)buf); -- if (mb_properties) -- free(mb_properties); -- } --#endif /* MBS_SUPPORT */ - return ret_val; - } - #endif /* defined(GREP_PROGRAM) || defined(FGREP_PROGRAM) */ |