diff options
Diffstat (limited to 'grep.c')
| -rw-r--r-- | grep.c | 236 |
1 files changed, 21 insertions, 215 deletions
@@ -166,11 +166,6 @@ void grep_init(struct grep_opt *opt, struct repository *repo, const char *prefix pcre2_malloc, pcre2_free, NULL); #endif -#ifdef USE_LIBPCRE1 - pcre_malloc = malloc; - pcre_free = free; -#endif - *opt = grep_defaults; opt->repo = repo; @@ -223,17 +218,7 @@ static void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, st break; case GREP_PATTERN_TYPE_PCRE: -#ifdef USE_LIBPCRE2 opt->pcre2 = 1; -#else - /* - * It's important that pcre1 always be assigned to - * even when there's no USE_LIBPCRE* defined. We still - * call the PCRE stub function, it just dies with - * "cannot use Perl-compatible regexes[...]". - */ - opt->pcre1 = 1; -#endif break; } } @@ -377,92 +362,6 @@ static int is_fixed(const char *s, size_t len) return 1; } -#ifdef USE_LIBPCRE1 -static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt) -{ - const char *error; - int erroffset; - int options = PCRE_MULTILINE; - int study_options = 0; - - if (opt->ignore_case) { - if (!opt->ignore_locale && has_non_ascii(p->pattern)) - p->pcre1_tables = pcre_maketables(); - options |= PCRE_CASELESS; - } - if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern)) - options |= PCRE_UTF8; - - p->pcre1_regexp = pcre_compile(p->pattern, options, &error, &erroffset, - p->pcre1_tables); - if (!p->pcre1_regexp) - compile_regexp_failed(p, error); - -#if defined(PCRE_CONFIG_JIT) && !defined(NO_LIBPCRE1_JIT) - pcre_config(PCRE_CONFIG_JIT, &p->pcre1_jit_on); - if (opt->debug) - fprintf(stderr, "pcre1_jit_on=%d\n", p->pcre1_jit_on); - - if (p->pcre1_jit_on) - study_options = PCRE_STUDY_JIT_COMPILE; -#endif - - p->pcre1_extra_info = pcre_study(p->pcre1_regexp, study_options, &error); - if (!p->pcre1_extra_info && error) - die("%s", error); -} - -static int pcre1match(struct grep_pat *p, const char *line, const char *eol, - regmatch_t *match, int eflags) -{ - int ovector[30], ret, flags = PCRE_NO_UTF8_CHECK; - - if (eflags & REG_NOTBOL) - flags |= PCRE_NOTBOL; - - ret = pcre_exec(p->pcre1_regexp, p->pcre1_extra_info, line, - eol - line, 0, flags, ovector, - ARRAY_SIZE(ovector)); - - if (ret < 0 && ret != PCRE_ERROR_NOMATCH) - die("pcre_exec failed with error code %d", ret); - if (ret > 0) { - ret = 0; - match->rm_so = ovector[0]; - match->rm_eo = ovector[1]; - } - - return ret; -} - -static void free_pcre1_regexp(struct grep_pat *p) -{ - pcre_free(p->pcre1_regexp); -#ifdef PCRE_CONFIG_JIT - if (p->pcre1_jit_on) - pcre_free_study(p->pcre1_extra_info); - else -#endif - pcre_free(p->pcre1_extra_info); - pcre_free((void *)p->pcre1_tables); -} -#else /* !USE_LIBPCRE1 */ -static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt) -{ - die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE"); -} - -static int pcre1match(struct grep_pat *p, const char *line, const char *eol, - regmatch_t *match, int eflags) -{ - return 1; -} - -static void free_pcre1_regexp(struct grep_pat *p) -{ -} -#endif /* !USE_LIBPCRE1 */ - #ifdef USE_LIBPCRE2 static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt) { @@ -492,7 +391,23 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt } if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern) && !(!opt->ignore_case && (p->fixed || p->is_fixed))) - options |= PCRE2_UTF; + options |= (PCRE2_UTF | PCRE2_MATCH_INVALID_UTF); + + /* Work around https://bugs.exim.org/show_bug.cgi?id=2642 fixed in 10.36 */ + if (PCRE2_MATCH_INVALID_UTF && options & (PCRE2_UTF | PCRE2_CASELESS)) { + struct strbuf buf; + int len; + int err; + + if ((len = pcre2_config(PCRE2_CONFIG_VERSION, NULL)) < 0) + BUG("pcre2_config(..., NULL) failed: %d", len); + strbuf_init(&buf, len + 1); + if ((err = pcre2_config(PCRE2_CONFIG_VERSION, buf.buf)) < 0) + BUG("pcre2_config(..., buf.buf) failed: %d", err); + if (versioncmp(buf.buf, "10.36") < 0) + options |= PCRE2_NO_START_OPTIMIZE; + strbuf_release(&buf); + } p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern, p->patternlen, options, &error, &erroffset, @@ -508,8 +423,6 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt } pcre2_config(PCRE2_CONFIG_JIT, &p->pcre2_jit_on); - if (opt->debug) - fprintf(stderr, "pcre2_jit_on=%d\n", p->pcre2_jit_on); if (p->pcre2_jit_on) { jitret = pcre2_jit_compile(p->pcre2_pattern, PCRE2_JIT_COMPLETE); if (jitret) @@ -535,9 +448,6 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt BUG("pcre2_pattern_info() failed: %d", patinforet); if (jitsizearg == 0) { p->pcre2_jit_on = 0; - if (opt->debug) - fprintf(stderr, "pcre2_jit_on=%d: (*NO_JIT) in regex\n", - p->pcre2_jit_on); return; } } @@ -588,11 +498,6 @@ static void free_pcre2_pattern(struct grep_pat *p) #else /* !USE_LIBPCRE2 */ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt) { - /* - * Unreachable until USE_LIBPCRE2 becomes synonymous with - * USE_LIBPCRE. See the sibling comment in - * grep_set_pattern_type_option(). - */ die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE"); } @@ -616,8 +521,6 @@ static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt) if (opt->ignore_case) regflags |= REG_ICASE; err = regcomp(&p->regexp, sb.buf, regflags); - if (opt->debug) - fprintf(stderr, "fixed %s\n", sb.buf); strbuf_release(&sb); if (err) { char errbuf[1024]; @@ -693,11 +596,6 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt) return; } - if (opt->pcre1) { - compile_pcre1_regexp(p, opt); - return; - } - if (p->ignore_case) regflags |= REG_ICASE; if (opt->extended_regexp_option) @@ -812,87 +710,6 @@ static struct grep_expr *compile_pattern_expr(struct grep_pat **list) return compile_pattern_or(list); } -static void indent(int in) -{ - while (in-- > 0) - fputc(' ', stderr); -} - -static void dump_grep_pat(struct grep_pat *p) -{ - switch (p->token) { - case GREP_AND: fprintf(stderr, "*and*"); break; - case GREP_OPEN_PAREN: fprintf(stderr, "*(*"); break; - case GREP_CLOSE_PAREN: fprintf(stderr, "*)*"); break; - case GREP_NOT: fprintf(stderr, "*not*"); break; - case GREP_OR: fprintf(stderr, "*or*"); break; - - case GREP_PATTERN: fprintf(stderr, "pattern"); break; - case GREP_PATTERN_HEAD: fprintf(stderr, "pattern_head"); break; - case GREP_PATTERN_BODY: fprintf(stderr, "pattern_body"); break; - } - - switch (p->token) { - default: break; - case GREP_PATTERN_HEAD: - fprintf(stderr, "<head %d>", p->field); break; - case GREP_PATTERN_BODY: - fprintf(stderr, "<body>"); break; - } - switch (p->token) { - default: break; - case GREP_PATTERN_HEAD: - case GREP_PATTERN_BODY: - case GREP_PATTERN: - fprintf(stderr, "%.*s", (int)p->patternlen, p->pattern); - break; - } - fputc('\n', stderr); -} - -static void dump_grep_expression_1(struct grep_expr *x, int in) -{ - indent(in); - switch (x->node) { - case GREP_NODE_TRUE: - fprintf(stderr, "true\n"); - break; - case GREP_NODE_ATOM: - dump_grep_pat(x->u.atom); - break; - case GREP_NODE_NOT: - fprintf(stderr, "(not\n"); - dump_grep_expression_1(x->u.unary, in+1); - indent(in); - fprintf(stderr, ")\n"); - break; - case GREP_NODE_AND: - fprintf(stderr, "(and\n"); - dump_grep_expression_1(x->u.binary.left, in+1); - dump_grep_expression_1(x->u.binary.right, in+1); - indent(in); - fprintf(stderr, ")\n"); - break; - case GREP_NODE_OR: - fprintf(stderr, "(or\n"); - dump_grep_expression_1(x->u.binary.left, in+1); - dump_grep_expression_1(x->u.binary.right, in+1); - indent(in); - fprintf(stderr, ")\n"); - break; - } -} - -static void dump_grep_expression(struct grep_opt *opt) -{ - struct grep_expr *x = opt->pattern_expression; - - if (opt->all_match) - fprintf(stderr, "[all-match]\n"); - dump_grep_expression_1(x, 0); - fflush(NULL); -} - static struct grep_expr *grep_true_expr(void) { struct grep_expr *z = xcalloc(1, sizeof(*z)); @@ -973,7 +790,7 @@ static struct grep_expr *grep_splice_or(struct grep_expr *x, struct grep_expr *y return z; } -static void compile_grep_patterns_real(struct grep_opt *opt) +void compile_grep_patterns(struct grep_opt *opt) { struct grep_pat *p; struct grep_expr *header_expr = prep_header_patterns(opt); @@ -993,7 +810,7 @@ static void compile_grep_patterns_real(struct grep_opt *opt) if (opt->all_match || header_expr) opt->extended = 1; - else if (!opt->extended && !opt->debug) + else if (!opt->extended) return; p = opt->pattern_list; @@ -1016,13 +833,6 @@ static void compile_grep_patterns_real(struct grep_opt *opt) opt->all_match = 1; } -void compile_grep_patterns(struct grep_opt *opt) -{ - compile_grep_patterns_real(opt); - if (opt->debug) - dump_grep_expression(opt); -} - static void free_pattern_expr(struct grep_expr *x) { switch (x->node) { @@ -1051,9 +861,7 @@ void free_grep_patterns(struct grep_opt *opt) case GREP_PATTERN: /* atom */ case GREP_PATTERN_HEAD: case GREP_PATTERN_BODY: - if (p->pcre1_regexp) - free_pcre1_regexp(p); - else if (p->pcre2_pattern) + if (p->pcre2_pattern) free_pcre2_pattern(p); else regfree(&p->regexp); @@ -1116,9 +924,7 @@ static int patmatch(struct grep_pat *p, char *line, char *eol, { int hit; - if (p->pcre1_regexp) - hit = !pcre1match(p, line, eol, match, eflags); - else if (p->pcre2_pattern) + if (p->pcre2_pattern) hit = !pcre2match(p, line, eol, match, eflags); else hit = !regexec_buf(&p->regexp, line, eol - line, 1, match, |