diff options
Diffstat (limited to 'grep.c')
| -rw-r--r-- | grep.c | 135 |
1 files changed, 104 insertions, 31 deletions
@@ -4,6 +4,8 @@ #include "xdiff-interface.h" #include "diff.h" #include "diffcore.h" +#include "commit.h" +#include "quote.h" static int grep_source_load(struct grep_source *gs); static int grep_source_is_binary(struct grep_source *gs); @@ -31,14 +33,14 @@ void init_grep_defaults(void) opt->max_depth = -1; opt->pattern_type_option = GREP_PATTERN_TYPE_UNSPECIFIED; opt->extended_regexp_option = 0; - strcpy(opt->color_context, ""); - strcpy(opt->color_filename, ""); - strcpy(opt->color_function, ""); - strcpy(opt->color_lineno, ""); - strcpy(opt->color_match_context, GIT_COLOR_BOLD_RED); - strcpy(opt->color_match_selected, GIT_COLOR_BOLD_RED); - strcpy(opt->color_selected, ""); - strcpy(opt->color_sep, GIT_COLOR_CYAN); + color_set(opt->color_context, ""); + color_set(opt->color_filename, ""); + color_set(opt->color_function, ""); + color_set(opt->color_lineno, ""); + color_set(opt->color_match_context, GIT_COLOR_BOLD_RED); + color_set(opt->color_match_selected, GIT_COLOR_BOLD_RED); + color_set(opt->color_selected, ""); + color_set(opt->color_sep, GIT_COLOR_CYAN); opt->color = -1; } @@ -151,14 +153,14 @@ void grep_init(struct grep_opt *opt, const char *prefix) opt->regflags = def->regflags; opt->relative = def->relative; - strcpy(opt->color_context, def->color_context); - strcpy(opt->color_filename, def->color_filename); - strcpy(opt->color_function, def->color_function); - strcpy(opt->color_lineno, def->color_lineno); - strcpy(opt->color_match_context, def->color_match_context); - strcpy(opt->color_match_selected, def->color_match_selected); - strcpy(opt->color_selected, def->color_selected); - strcpy(opt->color_sep, def->color_sep); + color_set(opt->color_context, def->color_context); + color_set(opt->color_filename, def->color_filename); + color_set(opt->color_function, def->color_function); + color_set(opt->color_lineno, def->color_lineno); + color_set(opt->color_match_context, def->color_match_context); + color_set(opt->color_match_selected, def->color_match_selected); + color_set(opt->color_selected, def->color_selected); + color_set(opt->color_sep, def->color_sep); } void grep_commit_pattern_type(enum grep_pattern_type pattern_type, struct grep_opt *opt) @@ -306,9 +308,9 @@ static NORETURN void compile_regexp_failed(const struct grep_pat *p, char where[1024]; if (p->no) - sprintf(where, "In '%s' at %d, ", p->origin, p->no); + xsnprintf(where, sizeof(where), "In '%s' at %d, ", p->origin, p->no); else if (p->origin) - sprintf(where, "%s, ", p->origin); + xsnprintf(where, sizeof(where), "%s, ", p->origin); else where[0] = 0; @@ -322,11 +324,16 @@ static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt) int erroffset; int options = PCRE_MULTILINE; - if (opt->ignore_case) + if (opt->ignore_case) { + if (has_non_ascii(p->pattern)) + p->pcre_tables = pcre_maketables(); options |= PCRE_CASELESS; + } + if (is_utf8_locale() && has_non_ascii(p->pattern)) + options |= PCRE_UTF8; p->pcre_regexp = pcre_compile(p->pattern, options, &error, &erroffset, - NULL); + p->pcre_tables); if (!p->pcre_regexp) compile_regexp_failed(p, error); @@ -360,6 +367,7 @@ static void free_pcre_regexp(struct grep_pat *p) { pcre_free(p->pcre_regexp); pcre_free(p->pcre_extra_info); + pcre_free((void *)p->pcre_tables); } #else /* !USE_LIBPCRE */ static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt) @@ -396,26 +404,68 @@ static int is_fixed(const char *s, size_t len) return 1; } +static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt) +{ + struct strbuf sb = STRBUF_INIT; + int err; + int regflags; + + basic_regex_quote_buf(&sb, p->pattern); + regflags = opt->regflags & ~REG_EXTENDED; + 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]; + regerror(err, &p->regexp, errbuf, sizeof(errbuf)); + regfree(&p->regexp); + compile_regexp_failed(p, errbuf); + } +} + static void compile_regexp(struct grep_pat *p, struct grep_opt *opt) { + int icase, ascii_only; int err; p->word_regexp = opt->word_regexp; p->ignore_case = opt->ignore_case; + icase = opt->regflags & REG_ICASE || p->ignore_case; + ascii_only = !has_non_ascii(p->pattern); + /* + * Even when -F (fixed) asks us to do a non-regexp search, we + * may not be able to correctly case-fold when -i + * (ignore-case) is asked (in which case, we'll synthesize a + * regexp to match the pattern that matches regexp special + * characters literally, while ignoring case differences). On + * the other hand, even without -F, if the pattern does not + * have any regexp special characters and there is no need for + * case-folding search, we can internally turn it into a + * simple string match using kws. p->fixed tells us if we + * want to use kws. + */ if (opt->fixed || is_fixed(p->pattern, p->patternlen)) - p->fixed = 1; + p->fixed = !icase || ascii_only; else p->fixed = 0; if (p->fixed) { - if (opt->regflags & REG_ICASE || p->ignore_case) - p->kws = kwsalloc(tolower_trans_tbl); - else - p->kws = kwsalloc(NULL); + p->kws = kwsalloc(icase ? tolower_trans_tbl : NULL); kwsincr(p->kws, p->pattern, p->patternlen); kwsprep(p->kws); return; + } else if (opt->fixed) { + /* + * We come here when the pattern has the non-ascii + * characters we cannot case-fold, and asked to + * ignore-case. + */ + compile_fixed_regexp(p, opt); + return; } if (opt->pcre) { @@ -1396,9 +1446,17 @@ static int fill_textconv_grep(struct userdiff_driver *driver, return 0; } +static int is_empty_line(const char *bol, const char *eol) +{ + while (bol < eol && isspace(*bol)) + bol++; + return bol == eol; +} + static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int collect_hits) { char *bol; + char *peek_bol = NULL; unsigned long left; unsigned lno = 1; unsigned last_hit = 0; @@ -1543,8 +1601,24 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle show_function = 1; goto next_line; } - if (show_function && match_funcname(opt, gs, bol, eol)) - show_function = 0; + if (show_function && (!peek_bol || peek_bol < bol)) { + unsigned long peek_left = left; + char *peek_eol = eol; + + /* + * Trailing empty lines are not interesting. + * Peek past them to see if they belong to the + * body of the current function. + */ + peek_bol = bol; + while (is_empty_line(peek_bol, peek_eol)) { + peek_bol = peek_eol + 1; + peek_eol = end_of_line(peek_bol, &peek_left); + } + + if (match_funcname(opt, gs, peek_bol, peek_eol)) + show_function = 0; + } if (show_function || (last_hit && lno <= last_hit + opt->post_context)) { /* If the last hit is within the post context, @@ -1732,7 +1806,7 @@ static int grep_source_load_file(struct grep_source *gs) if (lstat(filename, &st) < 0) { err_ret: if (errno != ENOENT) - error(_("'%s': %s"), filename, strerror(errno)); + error_errno(_("failed to stat '%s'"), filename); return -1; } if (!S_ISREG(st.st_mode)) @@ -1741,15 +1815,14 @@ static int grep_source_load_file(struct grep_source *gs) i = open(filename, O_RDONLY); if (i < 0) goto err_ret; - data = xmalloc(size + 1); + data = xmallocz(size); if (st.st_size != read_in_full(i, data, size)) { - error(_("'%s': short read %s"), filename, strerror(errno)); + error_errno(_("'%s': short read"), filename); close(i); free(data); return -1; } close(i); - data[size] = 0; gs->buf = data; gs->size = size; |