diff options
Diffstat (limited to 'grep.c')
| -rw-r--r-- | grep.c | 339 |
1 files changed, 267 insertions, 72 deletions
@@ -3,18 +3,64 @@ #include "userdiff.h" #include "xdiff-interface.h" -void append_header_grep_pattern(struct grep_opt *opt, enum grep_header_field field, const char *pat) +static struct grep_pat *create_grep_pat(const char *pat, size_t patlen, + const char *origin, int no, + enum grep_pat_token t, + enum grep_header_field field) { struct grep_pat *p = xcalloc(1, sizeof(*p)); - p->pattern = pat; - p->patternlen = strlen(pat); - p->origin = "header"; - p->no = 0; - p->token = GREP_PATTERN_HEAD; + p->pattern = xmemdupz(pat, patlen); + p->patternlen = patlen; + p->origin = origin; + p->no = no; + p->token = t; p->field = field; - *opt->header_tail = p; - opt->header_tail = &p->next; + return p; +} + +static void do_append_grep_pat(struct grep_pat ***tail, struct grep_pat *p) +{ + **tail = p; + *tail = &p->next; p->next = NULL; + + switch (p->token) { + case GREP_PATTERN: /* atom */ + case GREP_PATTERN_HEAD: + case GREP_PATTERN_BODY: + for (;;) { + struct grep_pat *new_pat; + size_t len = 0; + char *cp = p->pattern + p->patternlen, *nl = NULL; + while (++len <= p->patternlen) { + if (*(--cp) == '\n') { + nl = cp; + break; + } + } + if (!nl) + break; + new_pat = create_grep_pat(nl + 1, len - 1, p->origin, + p->no, p->token, p->field); + new_pat->next = p->next; + if (!p->next) + *tail = &new_pat->next; + p->next = new_pat; + *nl = '\0'; + p->patternlen -= len; + } + break; + default: + break; + } +} + +void append_header_grep_pattern(struct grep_opt *opt, + enum grep_header_field field, const char *pat) +{ + struct grep_pat *p = create_grep_pat(pat, strlen(pat), "header", 0, + GREP_PATTERN_HEAD, field); + do_append_grep_pat(&opt->header_tail, p); } void append_grep_pattern(struct grep_opt *opt, const char *pat, @@ -26,15 +72,8 @@ void append_grep_pattern(struct grep_opt *opt, const char *pat, void append_grep_pat(struct grep_opt *opt, const char *pat, size_t patlen, const char *origin, int no, enum grep_pat_token t) { - struct grep_pat *p = xcalloc(1, sizeof(*p)); - p->pattern = pat; - p->patternlen = patlen; - p->origin = origin; - p->no = no; - p->token = t; - *opt->pattern_tail = p; - opt->pattern_tail = &p->next; - p->next = NULL; + struct grep_pat *p = create_grep_pat(pat, patlen, origin, no, t, 0); + do_append_grep_pat(&opt->pattern_tail, p); } struct grep_opt *grep_opt_dup(const struct grep_opt *opt) @@ -79,7 +118,7 @@ static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt) { const char *error; int erroffset; - int options = 0; + int options = PCRE_MULTILINE; if (opt->ignore_case) options |= PCRE_CASELESS; @@ -168,15 +207,10 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt) p->fixed = 0; if (p->fixed) { - if (opt->regflags & REG_ICASE || p->ignore_case) { - static char trans[256]; - int i; - for (i = 0; i < 256; i++) - trans[i] = tolower(i); - p->kws = kwsalloc(trans); - } else { + if (opt->regflags & REG_ICASE || p->ignore_case) + p->kws = kwsalloc(tolower_trans_tbl); + else p->kws = kwsalloc(NULL); - } kwsincr(p->kws, p->pattern, p->patternlen); kwsprep(p->kws); return; @@ -323,7 +357,7 @@ static struct grep_expr *prep_header_patterns(struct grep_opt *opt) if (!opt->header_list) return NULL; - p = opt->header_list; + for (p = opt->header_list; p; p = p->next) { if (p->token != GREP_PATTERN_HEAD) die("bug: a non-header pattern in grep header list."); @@ -435,6 +469,7 @@ void free_grep_patterns(struct grep_opt *opt) free_pcre_regexp(p); else regfree(&p->regexp); + free(p->pattern); break; default: break; @@ -807,38 +842,43 @@ static void show_line(struct grep_opt *opt, char *bol, char *eol, } #ifndef NO_PTHREADS +int grep_use_locks; + /* * This lock protects access to the gitattributes machinery, which is * not thread-safe. */ pthread_mutex_t grep_attr_mutex; -static inline void grep_attr_lock(struct grep_opt *opt) +static inline void grep_attr_lock(void) { - if (opt->use_threads) + if (grep_use_locks) pthread_mutex_lock(&grep_attr_mutex); } -static inline void grep_attr_unlock(struct grep_opt *opt) +static inline void grep_attr_unlock(void) { - if (opt->use_threads) + if (grep_use_locks) pthread_mutex_unlock(&grep_attr_mutex); } + +/* + * Same as git_attr_mutex, but protecting the thread-unsafe object db access. + */ +pthread_mutex_t grep_read_mutex; + #else -#define grep_attr_lock(opt) -#define grep_attr_unlock(opt) +#define grep_attr_lock() +#define grep_attr_unlock() #endif -static int match_funcname(struct grep_opt *opt, const char *name, char *bol, char *eol) +static int match_funcname(struct grep_opt *opt, struct grep_source *gs, char *bol, char *eol) { xdemitconf_t *xecfg = opt->priv; if (xecfg && !xecfg->find_func) { - struct userdiff_driver *drv; - grep_attr_lock(opt); - drv = userdiff_find_by_path(name); - grep_attr_unlock(opt); - if (drv && drv->funcname.pattern) { - const struct userdiff_funcname *pe = &drv->funcname; + grep_source_load_driver(gs); + if (gs->driver->funcname.pattern) { + const struct userdiff_funcname *pe = &gs->driver->funcname; xdiff_set_find_func(xecfg, pe->pattern, pe->cflags); } else { xecfg = opt->priv = NULL; @@ -858,33 +898,33 @@ static int match_funcname(struct grep_opt *opt, const char *name, char *bol, cha return 0; } -static void show_funcname_line(struct grep_opt *opt, const char *name, - char *buf, char *bol, unsigned lno) +static void show_funcname_line(struct grep_opt *opt, struct grep_source *gs, + char *bol, unsigned lno) { - while (bol > buf) { + while (bol > gs->buf) { char *eol = --bol; - while (bol > buf && bol[-1] != '\n') + while (bol > gs->buf && bol[-1] != '\n') bol--; lno--; if (lno <= opt->last_shown) break; - if (match_funcname(opt, name, bol, eol)) { - show_line(opt, bol, eol, name, lno, '='); + if (match_funcname(opt, gs, bol, eol)) { + show_line(opt, bol, eol, gs->name, lno, '='); break; } } } -static void show_pre_context(struct grep_opt *opt, const char *name, char *buf, +static void show_pre_context(struct grep_opt *opt, struct grep_source *gs, char *bol, char *end, unsigned lno) { unsigned cur = lno, from = 1, funcname_lno = 0; int funcname_needed = !!opt->funcname; - if (opt->funcbody && !match_funcname(opt, name, bol, end)) + if (opt->funcbody && !match_funcname(opt, gs, bol, end)) funcname_needed = 2; if (opt->pre_context < lno) @@ -893,14 +933,14 @@ static void show_pre_context(struct grep_opt *opt, const char *name, char *buf, from = opt->last_shown + 1; /* Rewind. */ - while (bol > buf && + while (bol > gs->buf && cur > (funcname_needed == 2 ? opt->last_shown + 1 : from)) { char *eol = --bol; - while (bol > buf && bol[-1] != '\n') + while (bol > gs->buf && bol[-1] != '\n') bol--; cur--; - if (funcname_needed && match_funcname(opt, name, bol, eol)) { + if (funcname_needed && match_funcname(opt, gs, bol, eol)) { funcname_lno = cur; funcname_needed = 0; } @@ -908,7 +948,7 @@ static void show_pre_context(struct grep_opt *opt, const char *name, char *buf, /* We need to look even further back to find a function signature. */ if (opt->funcname && funcname_needed) - show_funcname_line(opt, name, buf, bol, cur); + show_funcname_line(opt, gs, bol, cur); /* Back forward. */ while (cur < lno) { @@ -916,7 +956,7 @@ static void show_pre_context(struct grep_opt *opt, const char *name, char *buf, while (*eol != '\n') eol++; - show_line(opt, bol, eol, name, cur, sign); + show_line(opt, bol, eol, gs->name, cur, sign); bol = eol + 1; cur++; } @@ -983,11 +1023,10 @@ static void std_output(struct grep_opt *opt, const void *buf, size_t size) fwrite(buf, size, 1, stdout); } -static int grep_buffer_1(struct grep_opt *opt, const char *name, - char *buf, unsigned long size, int collect_hits) +static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int collect_hits) { - char *bol = buf; - unsigned long left = size; + char *bol; + unsigned long left; unsigned lno = 1; unsigned last_hit = 0; int binary_match_only = 0; @@ -1017,11 +1056,11 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name, switch (opt->binary) { case GREP_BINARY_DEFAULT: - if (buffer_is_binary(buf, size)) + if (grep_source_is_binary(gs)) binary_match_only = 1; break; case GREP_BINARY_NOMATCH: - if (buffer_is_binary(buf, size)) + if (grep_source_is_binary(gs)) return 0; /* Assume unmatch */ break; case GREP_BINARY_TEXT: @@ -1035,6 +1074,11 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name, try_lookahead = should_lookahead(opt); + if (grep_source_load(gs) < 0) + return 0; + + bol = gs->buf; + left = gs->size; while (left) { char *eol, ch; int hit; @@ -1083,14 +1127,14 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name, if (opt->status_only) return 1; if (opt->name_only) { - show_name(opt, name); + show_name(opt, gs->name); return 1; } if (opt->count) goto next_line; if (binary_match_only) { opt->output(opt, "Binary file ", 12); - output_color(opt, name, strlen(name), + output_color(opt, gs->name, strlen(gs->name), opt->color_filename); opt->output(opt, " matches\n", 9); return 1; @@ -1099,23 +1143,23 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name, * pre-context lines, we would need to show them. */ if (opt->pre_context || opt->funcbody) - show_pre_context(opt, name, buf, bol, eol, lno); + show_pre_context(opt, gs, bol, eol, lno); else if (opt->funcname) - show_funcname_line(opt, name, buf, bol, lno); - show_line(opt, bol, eol, name, lno, ':'); + show_funcname_line(opt, gs, bol, lno); + show_line(opt, bol, eol, gs->name, lno, ':'); last_hit = lno; if (opt->funcbody) show_function = 1; goto next_line; } - if (show_function && match_funcname(opt, name, bol, eol)) + if (show_function && match_funcname(opt, gs, bol, eol)) show_function = 0; if (show_function || (last_hit && lno <= last_hit + opt->post_context)) { /* If the last hit is within the post context, * we need to show this line. */ - show_line(opt, bol, eol, name, lno, '-'); + show_line(opt, bol, eol, gs->name, lno, '-'); } next_line: @@ -1133,7 +1177,7 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name, return 0; if (opt->unmatch_name_only) { /* We did not see any hit, so we want to show this */ - show_name(opt, name); + show_name(opt, gs->name); return 1; } @@ -1147,7 +1191,7 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name, */ if (opt->count && count) { char buf[32]; - output_color(opt, name, strlen(name), opt->color_filename); + output_color(opt, gs->name, strlen(gs->name), opt->color_filename); output_sep(opt, ':'); snprintf(buf, sizeof(buf), "%u\n", count); opt->output(opt, buf, strlen(buf)); @@ -1182,23 +1226,174 @@ static int chk_hit_marker(struct grep_expr *x) } } -int grep_buffer(struct grep_opt *opt, const char *name, char *buf, unsigned long size) +int grep_source(struct grep_opt *opt, struct grep_source *gs) { /* * we do not have to do the two-pass grep when we do not check * buffer-wide "all-match". */ if (!opt->all_match) - return grep_buffer_1(opt, name, buf, size, 0); + return grep_source_1(opt, gs, 0); /* Otherwise the toplevel "or" terms hit a bit differently. * We first clear hit markers from them. */ clr_hit_marker(opt->pattern_expression); - grep_buffer_1(opt, name, buf, size, 1); + grep_source_1(opt, gs, 1); if (!chk_hit_marker(opt->pattern_expression)) return 0; - return grep_buffer_1(opt, name, buf, size, 0); + return grep_source_1(opt, gs, 0); +} + +int grep_buffer(struct grep_opt *opt, char *buf, unsigned long size) +{ + struct grep_source gs; + int r; + + grep_source_init(&gs, GREP_SOURCE_BUF, NULL, NULL); + gs.buf = buf; + gs.size = size; + + r = grep_source(opt, &gs); + + grep_source_clear(&gs); + return r; +} + +void grep_source_init(struct grep_source *gs, enum grep_source_type type, + const char *name, const void *identifier) +{ + gs->type = type; + gs->name = name ? xstrdup(name) : NULL; + gs->buf = NULL; + gs->size = 0; + gs->driver = NULL; + + switch (type) { + case GREP_SOURCE_FILE: + gs->identifier = xstrdup(identifier); + break; + case GREP_SOURCE_SHA1: + gs->identifier = xmalloc(20); + memcpy(gs->identifier, identifier, 20); + break; + case GREP_SOURCE_BUF: + gs->identifier = NULL; + } +} + +void grep_source_clear(struct grep_source *gs) +{ + free(gs->name); + gs->name = NULL; + free(gs->identifier); + gs->identifier = NULL; + grep_source_clear_data(gs); +} + +void grep_source_clear_data(struct grep_source *gs) +{ + switch (gs->type) { + case GREP_SOURCE_FILE: + case GREP_SOURCE_SHA1: + free(gs->buf); + gs->buf = NULL; + gs->size = 0; + break; + case GREP_SOURCE_BUF: + /* leave user-provided buf intact */ + break; + } +} + +static int grep_source_load_sha1(struct grep_source *gs) +{ + enum object_type type; + + grep_read_lock(); + gs->buf = read_sha1_file(gs->identifier, &type, &gs->size); + grep_read_unlock(); + + if (!gs->buf) + return error(_("'%s': unable to read %s"), + gs->name, + sha1_to_hex(gs->identifier)); + return 0; +} + +static int grep_source_load_file(struct grep_source *gs) +{ + const char *filename = gs->identifier; + struct stat st; + char *data; + size_t size; + int i; + + if (lstat(filename, &st) < 0) { + err_ret: + if (errno != ENOENT) + error(_("'%s': %s"), filename, strerror(errno)); + return -1; + } + if (!S_ISREG(st.st_mode)) + return -1; + size = xsize_t(st.st_size); + i = open(filename, O_RDONLY); + if (i < 0) + goto err_ret; + data = xmalloc(size + 1); + if (st.st_size != read_in_full(i, data, size)) { + error(_("'%s': short read %s"), filename, strerror(errno)); + close(i); + free(data); + return -1; + } + close(i); + data[size] = 0; + + gs->buf = data; + gs->size = size; + return 0; +} + +int grep_source_load(struct grep_source *gs) +{ + if (gs->buf) + return 0; + + switch (gs->type) { + case GREP_SOURCE_FILE: + return grep_source_load_file(gs); + case GREP_SOURCE_SHA1: + return grep_source_load_sha1(gs); + case GREP_SOURCE_BUF: + return gs->buf ? 0 : -1; + } + die("BUG: invalid grep_source type"); +} + +void grep_source_load_driver(struct grep_source *gs) +{ + if (gs->driver) + return; + + grep_attr_lock(); + gs->driver = userdiff_find_by_path(gs->name); + if (!gs->driver) + gs->driver = userdiff_find_by_name("default"); + grep_attr_unlock(); +} + +int grep_source_is_binary(struct grep_source *gs) +{ + grep_source_load_driver(gs); + if (gs->driver->binary != -1) + return gs->driver->binary; + + if (!grep_source_load(gs)) + return buffer_is_binary(gs->buf, gs->size); + + return 0; } |