search.c
来自「linux平台中」· C语言 代码 · 共 725 行 · 第 1/2 页
C
725 行
/* search.c - searching subroutines using dfa, kwset and regex for grep. Copyright 1992, 1998, 2000 Free Software Foundation, Inc. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. *//* Written August 1992 by Mike Haertel. */#ifdef HAVE_CONFIG_H# include <config.h>#endif#include <sys/types.h>#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 "system.h"#include "grep.h"#include "regex.h"#include "dfa.h"#include "kwset.h"#include "error.h"#include "xalloc.h"#ifdef HAVE_LIBPCRE# include <pcre.h>#endif#define NCHAR (UCHAR_MAX + 1)/* For -w, we also consider _ to be word constituent. */#define WCHAR(C) (ISALNUM(C) || (C) == '_')/* DFA compiled regexp. */static struct dfa dfa;/* The Regex compiled patterns. */static struct patterns{ /* Regex compiled regexp. */ struct re_pattern_buffer regexbuf; struct re_registers regs; /* This is here on account of a BRAIN-DEAD Q@#%!# library interface in regex.c. */} patterns0;struct patterns *patterns;size_t pcount;/* KWset compiled pattern. For Ecompile and Gcompile, we compile a list of strings, at least one of which is known to occur in any string matching the regexp. */static kwset_t kwset;/* Number of compiled fixed strings known to exactly match the regexp. If kwsexec returns < kwset_exact_matches, then we don't need to 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));#endifstatic void kwsinit PARAMS ((void));static void kwsmusts PARAMS ((void));static void Gcompile PARAMS ((char const *, size_t));static void Ecompile PARAMS ((char const *, size_t));static size_t EGexecute PARAMS ((char const *, size_t, size_t *, int ));static void Fcompile PARAMS ((char const *, size_t));static size_t Fexecute PARAMS ((char const *, size_t, size_t *, int));static void Pcompile PARAMS ((char const *, size_t ));static size_t Pexecute PARAMS ((char const *, size_t, size_t *, int));voiddfaerror (char const *mesg){ error (2, 0, mesg);}static voidkwsinit (void){ static char trans[NCHAR]; int i; if (match_icase) for (i = 0; i < NCHAR; ++i) trans[i] = TOLOWER (i); if (!(kwset = kwsalloc (match_icase ? trans : (char *) 0))) error (2, 0, _("memory exhausted"));}/* If the DFA turns out to have some set of fixed strings one of which must occur in the match, then we build a kwset matcher to find those strings, and thus quickly filter out impossible matches. */static voidkwsmusts (void){ struct dfamust const *dm; char const *err; if (dfa.musts) { kwsinit (); /* First, we compile in the substrings known to be exact matches. The kwset matcher will return the index of the matching string that it chooses. */ for (dm = dfa.musts; dm; dm = dm->next) { if (!dm->exact) continue; ++kwset_exact_matches; if ((err = kwsincr (kwset, dm->must, strlen (dm->must))) != 0) error (2, 0, err); } /* Now, we compile the substrings that will require the use of the regexp matcher. */ for (dm = dfa.musts; dm; dm = dm->next) { if (dm->exact) continue; if ((err = kwsincr (kwset, dm->must, strlen (dm->must))) != 0) error (2, 0, err); } if ((err = kwsprep (kwset)) != 0) error (2, 0, err); }}#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;}#endifstatic voidGcompile (char const *pattern, size_t size){ const char *err; char const *sep; size_t total = size; char const *motif = pattern; re_set_syntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE); 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 errors like "[\nallo\n]\n". The patterns here are "[", "allo" and "]" GNU regex should have raise a syntax error. The same for backref, where the backref should have been local to each pattern. */ do { size_t len; sep = memchr (motif, '\n', total); if (sep) { len = sep - motif; sep++; total -= (len + 1); } else { len = total; total = 0; } patterns = realloc (patterns, (pcount + 1) * sizeof (*patterns)); if (patterns == NULL) error (2, errno, _("memory exhausted")); patterns[pcount] = patterns0; if ((err = re_compile_pattern (motif, len, &(patterns[pcount].regexbuf))) != 0) error (2, 0, err); pcount++; motif = sep; } while (sep && total != 0); /* 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 to decide whether the match should really count. */ if (match_words || match_lines) { /* In the whole-word case, we use the pattern: \(^\|[^[:alnum:]_]\)\(userpattern\)\([^[:alnum:]_]|$\). In the whole-line case, we use the pattern: ^\(userpattern\)$. */ static char const line_beg[] = "^\\("; static char const line_end[] = "\\)$"; static char const word_beg[] = "\\(^\\|[^[:alnum:]_]\\)\\("; static char const word_end[] = "\\)\\([^[:alnum:]_]\\|$\\)"; char *n = malloc (sizeof word_beg - 1 + size + sizeof word_end); size_t i; strcpy (n, match_lines ? line_beg : word_beg); i = strlen (n); memcpy (n + i, pattern, size); i += size; strcpy (n + i, match_lines ? line_end : word_end); i += strlen (n + i); pattern = n; size = i; } dfacomp (pattern, size, &dfa, 1); kwsmusts ();}static voidEcompile (char const *pattern, size_t size){ const char *err; const char *sep; size_t total = size; char const *motif = pattern; if (strcmp (matcher, "awk") == 0) { re_set_syntax (RE_SYNTAX_AWK); dfasyntax (RE_SYNTAX_AWK, match_icase, eolbyte); } else { re_set_syntax (RE_SYNTAX_POSIX_EGREP); dfasyntax (RE_SYNTAX_POSIX_EGREP, match_icase, eolbyte); } /* For GNU regex compiler we have to pass the patterns separately to detect errors like "[\nallo\n]\n". The patterns here are "[", "allo" and "]" GNU regex should have raise a syntax error. The same for backref, where the backref should have been local to each pattern. */ do { size_t len; sep = memchr (motif, '\n', total); if (sep) { len = sep - motif; sep++; total -= (len + 1); } else { len = total; total = 0; } patterns = realloc (patterns, (pcount + 1) * sizeof (*patterns)); if (patterns == NULL) error (2, errno, _("memory exhausted")); patterns[pcount] = patterns0; if ((err = re_compile_pattern (motif, len, &(patterns[pcount].regexbuf))) != 0) error (2, 0, err); pcount++; motif = sep; } while (sep && total != 0); /* In the match_words and match_lines cases, we use a different pattern for the DFA matcher that will quickly throw out cases that won't work. Then if DFA succeeds we do some hairy stuff using the regex matcher to decide whether the match should really count. */ if (match_words || match_lines) { /* In the whole-word case, we use the pattern: (^|[^[:alnum:]_])(userpattern)([^[:alnum:]_]|$). In the whole-line case, we use the pattern: ^(userpattern)$. */ static char const line_beg[] = "^("; static char const line_end[] = ")$"; static char const word_beg[] = "(^|[^[:alnum:]_])("; static char const word_end[] = ")([^[:alnum:]_]|$)"; char *n = malloc (sizeof word_beg - 1 + size + sizeof word_end); size_t i; strcpy (n, match_lines ? line_beg : word_beg); i = strlen(n); memcpy (n + i, pattern, size); i += size; strcpy (n + i, match_lines ? line_end : word_end); i += strlen (n + i); pattern = n; size = i; } dfacomp (pattern, size, &dfa, 1); kwsmusts ();}static size_tEGexecute (char const *buf, size_t size, size_t *match_size, int exact){ register char const *buflim, *beg, *end; char eol = eolbyte; int backref, start, len; struct kwsmatch kwsm; size_t i;#ifdef MBS_SUPPORT char *mb_properties = NULL;#endif /* MBS_SUPPORT */#ifdef MBS_SUPPORT if (MB_CUR_MAX > 1 && kwset) mb_properties = check_multibyte_string(buf, size);#endif /* MBS_SUPPORT */ buflim = buf + size; for (beg = end = buf; end < buflim; beg = end) { if (!exact) { if (kwset) { /* Find a possible match using the KWset matcher. */ size_t offset = kwsexec (kwset, beg, buflim - beg, &kwsm); if (offset == (size_t) -1) {
⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?