From c884dd12ec062569335702848fc5f29f436c28fa Mon Sep 17 00:00:00 2001 From: Li xin Date: Mon, 25 May 2015 10:15:57 +0900 Subject: [PATCH] grep egrep fgrep: Fix LSB NG cases. The LSB core test requires grep egrep and fgrep can perform pattern matching in searches without regard to case if -i option is specified. Upstream-Status: backport. Signed-off-by: Li Xin --- lib/posix/regex.h | 4 + src/dfa.c | 22 +- src/grep.c | 96 ++++--- src/search.c | 833 +++++++++++++++++++++++++++++++++++++++++++++--------- 4 files changed, 768 insertions(+), 187 deletions(-) diff --git a/lib/posix/regex.h b/lib/posix/regex.h index 63c2fef..7bb2b0e 100644 --- a/lib/posix/regex.h +++ b/lib/posix/regex.h @@ -109,6 +109,10 @@ typedef unsigned long int reg_syntax_t; 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) diff --git a/src/dfa.c b/src/dfa.c index 590bfa7..27c876a 100644 --- a/src/dfa.c +++ b/src/dfa.c @@ -414,7 +414,7 @@ update_mb_len_index (unsigned char const *p, int len) /* 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 @@ fetch_wc (char const *eoferr) if (eoferr != 0) dfaerror (eoferr); else - return -1; + return WEOF; } cur_mb_len = mbrtowc(&wc, lexptr, lexleft, &mbs); @@ -459,7 +459,7 @@ fetch_wc (char const *eoferr) 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 @@ parse_bracket_exp_mb () 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 @@ parse_bracket_exp_mb () work_mbc->coll_elems[work_mbc->ncoll_elems++] = elem; } } - wc = -1; + wc1 = wc = WEOF; } else /* We treat '[' as a normal character here. */ @@ -600,7 +600,7 @@ parse_bracket_exp_mb () wc = fetch_wc(("Unbalanced [")); } - if (wc1 == -1) + if (wc1 == WEOF) wc1 = fetch_wc(_("Unbalanced [")); if (wc1 == L'-') @@ -630,17 +630,17 @@ parse_bracket_exp_mb () } 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_mb_charset (struct dfa *d, int s, position pos, int index) } /* match with a character? */ + if (case_fold) + wc = towlower (wc); for (i = 0; inchars; i++) { if (wc == work_mbc->chars[i]) diff --git a/src/grep.c b/src/grep.c index 2fb2fac..3fd4b47 100644 --- a/src/grep.c +++ b/src/grep.c @@ -30,6 +30,12 @@ # include # include #endif +#if defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H && defined HAVE_MBRTOWC +/* We can handle multibyte string. */ +# define MBS_SUPPORT +# include +# include +#endif #include #include "system.h" #include "getopt.h" @@ -255,19 +261,6 @@ reset (int fd, char const *file, struct stats *stats) 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) @@ -558,33 +551,6 @@ prline (char const *beg, char const *lim, int sep) { 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) { @@ -601,6 +567,7 @@ prline (char const *beg, char const *lim, int sep) fputs ("\33[00m", stdout); beg = b + match_size; } + fputs ("\33[K", stdout); } fwrite (beg, 1, lim - beg, stdout); if (ferror (stdout)) @@ -623,7 +590,7 @@ prpending (char const *lim) size_t match_size; --pending; if (outleft - || (((*execute) (lastout, nl - lastout, &match_size, 0) == (size_t) -1) + || (((*execute) (lastout, nl + 1 - lastout, &match_size, 0) == (size_t) -1) == !out_invert)) prline (lastout, nl + 1, '-'); else @@ -895,6 +862,19 @@ grepfile (char const *file, struct stats *stats) } 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; @@ -1681,9 +1661,6 @@ warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.\n")) out_invert ^= 1; match_lines = match_words = 0; } - else - /* Strip trailing newline. */ - --keycc; } else if (optind < argc) @@ -1697,6 +1674,37 @@ warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.\n")) 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) diff --git a/src/search.c b/src/search.c index 7bd233f..3c6a485 100644 --- a/src/search.c +++ b/src/search.c @@ -18,9 +18,13 @@ /* Written August 1992 by Mike Haertel. */ +#ifndef _GNU_SOURCE +# define _GNU_SOURCE 1 +#endif #ifdef HAVE_CONFIG_H # include #endif +#include #include #if defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H && defined HAVE_MBRTOWC /* We can handle multibyte string. */ @@ -31,7 +35,7 @@ #include "system.h" #include "grep.h" -#include "regex.h" +#include #include "dfa.h" #include "kwset.h" #include "error.h" @@ -39,6 +43,9 @@ #ifdef HAVE_LIBPCRE # include #endif +#ifdef HAVE_LANGINFO_CODESET +# include +#endif #define NCHAR (UCHAR_MAX + 1) @@ -70,9 +77,10 @@ static kwset_t kwset; 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 void Pcompile PARAMS ((char const *, size_t )); 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); @@ -141,38 +158,6 @@ kwsmusts (void) } } -#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) { @@ -181,7 +166,8 @@ Gcompile (char const *pattern, size_t size) size_t total = size; char const *motif = pattern; - re_set_syntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE); + 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); /* For GNU regex compiler we have to pass the patterns separately to detect @@ -218,6 +204,10 @@ Gcompile (char const *pattern, size_t size) 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 @@ -233,7 +223,7 @@ Gcompile (char const *pattern, size_t size) 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); @@ -257,14 +247,15 @@ Ecompile (char const *pattern, size_t size) size_t total = size; char const *motif = pattern; + check_utf8 (); 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); } @@ -301,6 +292,10 @@ Ecompile (char const *pattern, size_t size) 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 @@ -316,7 +311,7 @@ Ecompile (char const *pattern, size_t size) 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); @@ -339,15 +334,34 @@ EGexecute (char const *buf, size_t size, size_t *match_size, int exact) char eol = eolbyte; int backref, start, len; struct kwsmatch kwsm; - size_t i; + size_t i, ret_val; + static int use_dfa; + static int use_dfa_checked = 0; #ifdef MBS_SUPPORT - char *mb_properties = NULL; + 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 - if (MB_CUR_MAX > 1 && kwset) - mb_properties = check_multibyte_string(buf, size); + /* 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; @@ -358,47 +372,120 @@ EGexecute (char const *buf, size_t size, size_t *match_size, int exact) 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) - free(mb_properties); -#endif - return (size_t)-1; + 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) - goto success; - if (dfaexec (&dfa, beg, end - beg, &backref) == (size_t) -1) + 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 (use_dfa && + dfaexec (&dfa, beg, end - beg, &backref) == (size_t) -1) continue; } else { /* No good fixed strings; start with DFA. */ - size_t offset = dfaexec (&dfa, beg, buflim - beg, &backref); +#ifdef MBS_SUPPORT + size_t bytes_left = 0; +#endif /* MBS_SUPPORT */ + 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. */ +#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; } /* Successful, no backreferences encountered! */ - if (!backref) - goto success; + if (use_dfa && !backref) + goto success_in_beg_and_end; } else end = beg + size; @@ -413,14 +500,11 @@ EGexecute (char const *buf, size_t size, size_t *match_size, int exact) 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 @@ -431,10 +515,114 @@ EGexecute (char const *buf, size_t size, size_t *match_size, int exact) 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; + 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. */ @@ -461,26 +649,154 @@ EGexecute (char const *buf, size_t size, size_t *match_size, int exact) } } /* for Regex patterns. */ } /* for (beg = end ..) */ -#ifdef MBS_SUPPORT - if (MB_CUR_MAX > 1 && mb_properties) - free (mb_properties); -#endif /* MBS_SUPPORT */ + + failure: 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; + success_in_beg_and_end: + len = end - beg; + start = beg - buf; + /* FALLTHROUGH */ + + success_in_start_and_len: + *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 @@ -499,6 +815,76 @@ Fcompile (char const *pattern, size_t size) 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) { @@ -506,88 +892,268 @@ Fexecute (char const *buf, size_t size, size_t *match_size, int exact) register size_t len; char eol = eolbyte; struct kwsmatch kwsmatch; + size_t ret_val; #ifdef MBS_SUPPORT - char *mb_properties; - if (MB_CUR_MAX > 1) - 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) + 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) - free(mb_properties); -#endif /* MBS_SUPPORT */ - return offset; + 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; } -#ifdef MBS_SUPPORT - if (MB_CUR_MAX > 1 && mb_properties[offset+beg-buf] == 0) - continue; /* It is a part of multibyte character. */ + else #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); + /* 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 */ - return beg - buf; - } + 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 - if (MB_CUR_MAX > 1) - free (mb_properties); + /* 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 && !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) --beg; - *match_size = end - beg; -#ifdef MBS_SUPPORT - if (MB_CUR_MAX > 1) - free (mb_properties); -#endif /* MBS_SUPPORT */ + len = end - beg; + /* FALLTHROUGH */ + + success_in_beg_and_len: + *match_size = len; return beg - buf; } @@ -701,8 +1267,9 @@ Pexecute (char const *buf, size_t size, size_t *match_size, int exact) 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; } -- 1.8.4.2