diff options
Diffstat (limited to 'builtin/grep.c')
-rw-r--r-- | builtin/grep.c | 448 |
1 files changed, 230 insertions, 218 deletions
diff --git a/builtin/grep.c b/builtin/grep.c index d0a73da07a..871afaa3c7 100644 --- a/builtin/grep.c +++ b/builtin/grep.c @@ -11,18 +11,16 @@ #include "tree-walk.h" #include "builtin.h" #include "parse-options.h" +#include "string-list.h" +#include "run-command.h" #include "userdiff.h" #include "grep.h" #include "quote.h" #include "dir.h" - -#ifndef NO_PTHREADS -#include <pthread.h> #include "thread-utils.h" -#endif static char const * const grep_usage[] = { - "git grep [options] [-e] <pattern> [<rev>...] [[--] path...]", + "git grep [options] [-e] <pattern> [<rev>...] [[--] <path>...]", NULL }; @@ -42,8 +40,7 @@ enum work_type {WORK_SHA1, WORK_FILE}; * threads. The producer adds struct work_items to 'todo' and the * consumers pick work items from the same array. */ -struct work_item -{ +struct work_item { enum work_type type; char *name; @@ -247,7 +244,7 @@ static void start_threads(struct grep_opt *opt) err = pthread_create(&threads[i], NULL, run, o); if (err) - die("grep: failed to create thread: %s", + die(_("grep: failed to create thread: %s"), strerror(err)); } } @@ -305,6 +302,19 @@ static int grep_config(const char *var, const char *value, void *cb) default: return 0; } + if (!strcmp(var, "grep.extendedregexp")) { + if (git_config_bool(var, value)) + opt->regflags |= REG_EXTENDED; + else + opt->regflags &= ~REG_EXTENDED; + return 0; + } + + if (!strcmp(var, "grep.linenumber")) { + opt->linenum = git_config_bool(var, value); + return 0; + } + if (!strcmp(var, "color.grep")) opt->color = git_config_colorbool(var, value, -1); else if (!strcmp(var, "color.grep.context")) @@ -331,106 +341,6 @@ static int grep_config(const char *var, const char *value, void *cb) return 0; } -/* - * Return non-zero if max_depth is negative or path has no more then max_depth - * slashes. - */ -static int accept_subdir(const char *path, int max_depth) -{ - if (max_depth < 0) - return 1; - - while ((path = strchr(path, '/')) != NULL) { - max_depth--; - if (max_depth < 0) - return 0; - path++; - } - return 1; -} - -/* - * Return non-zero if name is a subdirectory of match and is not too deep. - */ -static int is_subdir(const char *name, int namelen, - const char *match, int matchlen, int max_depth) -{ - if (matchlen > namelen || strncmp(name, match, matchlen)) - return 0; - - if (name[matchlen] == '\0') /* exact match */ - return 1; - - if (!matchlen || match[matchlen-1] == '/' || name[matchlen] == '/') - return accept_subdir(name + matchlen + 1, max_depth); - - return 0; -} - -/* - * git grep pathspecs are somewhat different from diff-tree pathspecs; - * pathname wildcards are allowed. - */ -static int pathspec_matches(const char **paths, const char *name, int max_depth) -{ - int namelen, i; - if (!paths || !*paths) - return accept_subdir(name, max_depth); - namelen = strlen(name); - for (i = 0; paths[i]; i++) { - const char *match = paths[i]; - int matchlen = strlen(match); - const char *cp, *meta; - - if (is_subdir(name, namelen, match, matchlen, max_depth)) - return 1; - if (!fnmatch(match, name, 0)) - return 1; - if (name[namelen-1] != '/') - continue; - - /* We are being asked if the directory ("name") is worth - * descending into. - * - * Find the longest leading directory name that does - * not have metacharacter in the pathspec; the name - * we are looking at must overlap with that directory. - */ - for (cp = match, meta = NULL; cp - match < matchlen; cp++) { - char ch = *cp; - if (ch == '*' || ch == '[' || ch == '?') { - meta = cp; - break; - } - } - if (!meta) - meta = cp; /* fully literal */ - - if (namelen <= meta - match) { - /* Looking at "Documentation/" and - * the pattern says "Documentation/howto/", or - * "Documentation/diff*.txt". The name we - * have should match prefix. - */ - if (!memcmp(match, name, namelen)) - return 1; - continue; - } - - if (meta - match < namelen) { - /* Looking at "Documentation/howto/" and - * the pattern says "Documentation/h*"; - * match up to "Do.../h"; this avoids descending - * into "Documentation/technical/". - */ - if (!memcmp(match, name, meta - match)) - return 1; - continue; - } - } - return 0; -} - static void *lock_and_read_sha1_file(const unsigned char *sha1, enum object_type *type, unsigned long *size) { void *data; @@ -452,7 +362,7 @@ static void *load_sha1(const unsigned char *sha1, unsigned long *size, void *data = lock_and_read_sha1_file(sha1, &type, size); if (!data) - error("'%s': unable to read %s", name, sha1_to_hex(sha1)); + error(_("'%s': unable to read %s"), name, sha1_to_hex(sha1)); return data; } @@ -503,21 +413,21 @@ static void *load_file(const char *filename, size_t *sz) if (lstat(filename, &st) < 0) { err_ret: if (errno != ENOENT) - error("'%s': %s", filename, strerror(errno)); - return 0; + error(_("'%s': %s"), filename, strerror(errno)); + return NULL; } if (!S_ISREG(st.st_mode)) - return 0; + return NULL; *sz = xsize_t(st.st_size); i = open(filename, O_RDONLY); if (i < 0) goto err_ret; data = xmalloc(*sz + 1); if (st.st_size != read_in_full(i, data, *sz)) { - error("'%s': short read %s", filename, strerror(errno)); + error(_("'%s': short read %s"), filename, strerror(errno)); close(i); free(data); - return 0; + return NULL; } close(i); data[*sz] = 0; @@ -556,7 +466,34 @@ static int grep_file(struct grep_opt *opt, const char *filename) } } -static int grep_cache(struct grep_opt *opt, const char **paths, int cached) +static void append_path(struct grep_opt *opt, const void *data, size_t len) +{ + struct string_list *path_list = opt->output_priv; + + if (len == 1 && *(const char *)data == '\0') + return; + string_list_append(path_list, xstrndup(data, len)); +} + +static void run_pager(struct grep_opt *opt, const char *prefix) +{ + struct string_list *path_list = opt->output_priv; + const char **argv = xmalloc(sizeof(const char *) * (path_list->nr + 1)); + int i, status; + + for (i = 0; i < path_list->nr; i++) + argv[i] = path_list->items[i].string; + argv[path_list->nr] = NULL; + + if (prefix && chdir(prefix)) + die(_("Failed to chdir: %s"), prefix); + status = run_command_v_opt(argv, RUN_USING_SHELL); + if (status) + exit(status); + free(argv); +} + +static int grep_cache(struct grep_opt *opt, const struct pathspec *pathspec, int cached) { int hit = 0; int nr; @@ -566,7 +503,7 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached) struct cache_entry *ce = active_cache[nr]; if (!S_ISREG(ce->ce_mode)) continue; - if (!pathspec_matches(paths, ce->name, opt->max_depth)) + if (!match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL)) continue; /* * If CE_VALID is on, we assume worktree file and its cache entry @@ -590,48 +527,32 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached) if (hit && opt->status_only) break; } - free_grep_patterns(opt); return hit; } -static int grep_tree(struct grep_opt *opt, const char **paths, - struct tree_desc *tree, - const char *tree_name, const char *base) +static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec, + struct tree_desc *tree, struct strbuf *base, int tn_len) { - int len; - int hit = 0; + int hit = 0, match = 0; struct name_entry entry; - char *down; - int tn_len = strlen(tree_name); - struct strbuf pathbuf; - - strbuf_init(&pathbuf, PATH_MAX + tn_len); - - if (tn_len) { - strbuf_add(&pathbuf, tree_name, tn_len); - strbuf_addch(&pathbuf, ':'); - tn_len = pathbuf.len; - } - strbuf_addstr(&pathbuf, base); - len = pathbuf.len; + int old_baselen = base->len; while (tree_entry(tree, &entry)) { int te_len = tree_entry_len(entry.path, entry.sha1); - pathbuf.len = len; - strbuf_add(&pathbuf, entry.path, te_len); - - if (S_ISDIR(entry.mode)) - /* Match "abc/" against pathspec to - * decide if we want to descend into "abc" - * directory. - */ - strbuf_addch(&pathbuf, '/'); - - down = pathbuf.buf + tn_len; - if (!pathspec_matches(paths, down, opt->max_depth)) - ; - else if (S_ISREG(entry.mode)) - hit |= grep_sha1(opt, entry.sha1, pathbuf.buf, tn_len); + + if (match != 2) { + match = tree_entry_interesting(&entry, base, tn_len, pathspec); + if (match < 0) + break; + if (match == 0) + continue; + } + + strbuf_add(base, entry.path, te_len); + + if (S_ISREG(entry.mode)) { + hit |= grep_sha1(opt, entry.sha1, base->buf, tn_len); + } else if (S_ISDIR(entry.mode)) { enum object_type type; struct tree_desc sub; @@ -640,20 +561,23 @@ static int grep_tree(struct grep_opt *opt, const char **paths, data = lock_and_read_sha1_file(entry.sha1, &type, &size); if (!data) - die("unable to read tree (%s)", + die(_("unable to read tree (%s)"), sha1_to_hex(entry.sha1)); + + strbuf_addch(base, '/'); init_tree_desc(&sub, data, size); - hit |= grep_tree(opt, paths, &sub, tree_name, down); + hit |= grep_tree(opt, pathspec, &sub, base, tn_len); free(data); } + strbuf_setlen(base, old_baselen); + if (hit && opt->status_only) break; } - strbuf_release(&pathbuf); return hit; } -static int grep_object(struct grep_opt *opt, const char **paths, +static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec, struct object *obj, const char *name) { if (obj->type == OBJ_BLOB) @@ -662,20 +586,49 @@ static int grep_object(struct grep_opt *opt, const char **paths, struct tree_desc tree; void *data; unsigned long size; - int hit; + struct strbuf base; + int hit, len; + data = read_object_with_reference(obj->sha1, tree_type, &size, NULL); if (!data) - die("unable to read tree (%s)", sha1_to_hex(obj->sha1)); + die(_("unable to read tree (%s)"), sha1_to_hex(obj->sha1)); + + len = name ? strlen(name) : 0; + strbuf_init(&base, PATH_MAX + len + 1); + if (len) { + strbuf_add(&base, name, len); + strbuf_addch(&base, ':'); + } init_tree_desc(&tree, data, size); - hit = grep_tree(opt, paths, &tree, name, ""); + hit = grep_tree(opt, pathspec, &tree, &base, base.len); + strbuf_release(&base); free(data); return hit; } - die("unable to grep from object of type %s", typename(obj->type)); + die(_("unable to grep from object of type %s"), typename(obj->type)); } -static int grep_directory(struct grep_opt *opt, const char **paths) +static int grep_objects(struct grep_opt *opt, const struct pathspec *pathspec, + const struct object_array *list) +{ + unsigned int i; + int hit = 0; + const unsigned int nr = list->nr; + + for (i = 0; i < nr; i++) { + struct object *real_obj; + real_obj = deref_tag(list->objects[i].item, NULL, 0); + if (grep_object(opt, pathspec, real_obj, list->objects[i].name)) { + hit = 1; + if (opt->status_only) + break; + } + } + return hit; +} + +static int grep_directory(struct grep_opt *opt, const struct pathspec *pathspec) { struct dir_struct dir; int i, hit = 0; @@ -683,13 +636,16 @@ static int grep_directory(struct grep_opt *opt, const char **paths) memset(&dir, 0, sizeof(dir)); setup_standard_excludes(&dir); - fill_directory(&dir, paths); + fill_directory(&dir, pathspec->raw); for (i = 0; i < dir.nr; i++) { + const char *name = dir.entries[i]->name; + int namelen = strlen(name); + if (!match_pathspec_depth(pathspec, name, namelen, 0, NULL)) + continue; hit |= grep_file(opt, dir.entries[i]->name); if (hit && opt->status_only) break; } - free_grep_patterns(opt); return hit; } @@ -706,7 +662,7 @@ static int context_callback(const struct option *opt, const char *arg, } value = strtol(arg, (char **)&endp, 10); if (*endp) { - return error("switch `%c' expects a numerical value", + return error(_("switch `%c' expects a numerical value"), opt->short_name); } grep_opt->pre_context = grep_opt->post_context = value; @@ -716,13 +672,14 @@ static int context_callback(const struct option *opt, const char *arg, static int file_callback(const struct option *opt, const char *arg, int unset) { struct grep_opt *grep_opt = opt->value; + int from_stdin = !strcmp(arg, "-"); FILE *patterns; int lno = 0; struct strbuf sb = STRBUF_INIT; - patterns = fopen(arg, "r"); + patterns = from_stdin ? stdin : fopen(arg, "r"); if (!patterns) - die_errno("cannot open '%s'", arg); + die_errno(_("cannot open '%s'"), arg); while (strbuf_getline(&sb, patterns, '\n') == 0) { char *s; size_t len; @@ -734,7 +691,8 @@ static int file_callback(const struct option *opt, const char *arg, int unset) s = strbuf_detach(&sb, &len); append_grep_pat(grep_opt, s, len, arg, ++lno, GREP_PATTERN); } - fclose(patterns); + if (!from_stdin) + fclose(patterns); strbuf_release(&sb); return 0; } @@ -786,12 +744,24 @@ int cmd_grep(int argc, const char **argv, const char *prefix) int cached = 0; int seen_dashdash = 0; int external_grep_allowed__ignored; + const char *show_in_pager = NULL, *default_pager = "dummy"; struct grep_opt opt; - struct object_array list = { 0, 0, NULL }; + struct object_array list = OBJECT_ARRAY_INIT; const char **paths = NULL; + struct pathspec pathspec; + struct string_list path_list = STRING_LIST_INIT_NODUP; int i; int dummy; - int nongit = 0, use_index = 1; + int use_index = 1; + enum { + pattern_type_unspecified = 0, + pattern_type_bre, + pattern_type_ere, + pattern_type_fixed, + pattern_type_pcre, + }; + int pattern_type = pattern_type_unspecified; + struct option options[] = { OPT_BOOLEAN(0, "cached", &cached, "search in index instead of in the work tree"), @@ -813,15 +783,20 @@ int cmd_grep(int argc, const char **argv, const char *prefix) "descend at most <depth> levels", PARSE_OPT_NONEG, NULL, 1 }, OPT_GROUP(""), - OPT_BIT('E', "extended-regexp", &opt.regflags, - "use extended POSIX regular expressions", REG_EXTENDED), - OPT_NEGBIT('G', "basic-regexp", &opt.regflags, - "use basic POSIX regular expressions (default)", - REG_EXTENDED), - OPT_BOOLEAN('F', "fixed-strings", &opt.fixed, - "interpret patterns as fixed strings"), + OPT_SET_INT('E', "extended-regexp", &pattern_type, + "use extended POSIX regular expressions", + pattern_type_ere), + OPT_SET_INT('G', "basic-regexp", &pattern_type, + "use basic POSIX regular expressions (default)", + pattern_type_bre), + OPT_SET_INT('F', "fixed-strings", &pattern_type, + "interpret patterns as fixed strings", + pattern_type_fixed), + OPT_SET_INT('P', "perl-regexp", &pattern_type, + "use Perl-compatible regular expressions", + pattern_type_pcre), OPT_GROUP(""), - OPT_BOOLEAN('n', NULL, &opt.linenum, "show line numbers"), + OPT_BOOLEAN('n', "line-number", &opt.linenum, "show line numbers"), OPT_NEGBIT('h', NULL, &opt.pathname, "don't show filenames", 1), OPT_BIT('H', NULL, &opt.pathname, "show filenames", 1), OPT_NEGBIT(0, "full-name", &opt.relative, @@ -867,11 +842,14 @@ int cmd_grep(int argc, const char **argv, const char *prefix) { OPTION_CALLBACK, ')', NULL, &opt, NULL, "", PARSE_OPT_NOARG | PARSE_OPT_NONEG | PARSE_OPT_NODASH, close_callback }, - OPT_BOOLEAN('q', "quiet", &opt.status_only, - "indicate hit with exit status without output"), + OPT__QUIET(&opt.status_only, + "indicate hit with exit status without output"), OPT_BOOLEAN(0, "all-match", &opt.all_match, "show only matches from files that match all patterns"), OPT_GROUP(""), + { OPTION_STRING, 'O', "open-files-in-pager", &show_in_pager, + "pager", "show matching files in the pager", + PARSE_OPT_OPTARG, NULL, (intptr_t)default_pager }, OPT_BOOLEAN(0, "ext-grep", &external_grep_allowed__ignored, "allow calling of grep(1) (ignored by this build)"), { OPTION_CALLBACK, 0, "help-all", &options, NULL, "show usage", @@ -879,8 +857,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix) OPT_END() }; - prefix = setup_git_directory_gently(&nongit); - /* * 'git grep -h', unlike 'git grep -h <pattern>', is a request * to show usage information and exit. @@ -924,8 +900,30 @@ int cmd_grep(int argc, const char **argv, const char *prefix) PARSE_OPT_KEEP_DASHDASH | PARSE_OPT_STOP_AT_NON_OPTION | PARSE_OPT_NO_INTERNAL_HELP); + switch (pattern_type) { + case pattern_type_fixed: + opt.fixed = 1; + opt.pcre = 0; + break; + case pattern_type_bre: + opt.fixed = 0; + opt.pcre = 0; + opt.regflags &= ~REG_EXTENDED; + break; + case pattern_type_ere: + opt.fixed = 0; + opt.pcre = 0; + opt.regflags |= REG_EXTENDED; + break; + case pattern_type_pcre: + opt.fixed = 0; + opt.pcre = 1; + break; + default: + break; /* nothing */ + } - if (use_index && nongit) + if (use_index && !startup_info->have_repository) /* die the same way as if we did it at the beginning */ setup_git_directory(); @@ -947,12 +945,22 @@ int cmd_grep(int argc, const char **argv, const char *prefix) argc--; } + if (show_in_pager == default_pager) + show_in_pager = git_pager(1); + if (show_in_pager) { + opt.color = 0; + opt.name_only = 1; + opt.null_following_name = 1; + opt.output_priv = &path_list; + opt.output = append_path; + string_list_append(&path_list, show_in_pager); + use_threads = 0; + } + if (!opt.pattern_list) - die("no pattern given."); + die(_("no pattern given.")); if (!opt.fixed && opt.ignore_case) opt.regflags |= REG_ICASE; - if ((opt.regflags != REG_NEWLINE) && opt.fixed) - die("cannot mix --fixed-strings and regexp"); #ifndef NO_PTHREADS if (online_cpus() == 1 || !grep_threads_ok(&opt)) @@ -977,7 +985,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix) if (!get_sha1(arg, sha1)) { struct object *object = parse_object(sha1); if (!object) - die("bad object %s", arg); + die(_("bad object %s"), arg); add_object_array(object, arg, &list); continue; } @@ -995,52 +1003,56 @@ int cmd_grep(int argc, const char **argv, const char *prefix) verify_filename(prefix, argv[j]); } - if (i < argc) - paths = get_pathspec(prefix, argv + i); - else if (prefix) { - paths = xcalloc(2, sizeof(const char *)); - paths[0] = prefix; - paths[1] = NULL; + paths = get_pathspec(prefix, argv + i); + init_pathspec(&pathspec, paths); + pathspec.max_depth = opt.max_depth; + pathspec.recursive = 1; + + if (show_in_pager && (cached || list.nr)) + die(_("--open-files-in-pager only works on the worktree")); + + if (show_in_pager && opt.pattern_list && !opt.pattern_list->next) { + const char *pager = path_list.items[0].string; + int len = strlen(pager); + + if (len > 4 && is_dir_sep(pager[len - 5])) + pager += len - 4; + + if (!strcmp("less", pager) || !strcmp("vi", pager)) { + struct strbuf buf = STRBUF_INIT; + strbuf_addf(&buf, "+/%s%s", + strcmp("less", pager) ? "" : "*", + opt.pattern_list->pattern); + string_list_append(&path_list, buf.buf); + strbuf_detach(&buf, NULL); + } } + if (!show_in_pager) + setup_pager(); + + if (!use_index) { - int hit; if (cached) - die("--cached cannot be used with --no-index."); + die(_("--cached cannot be used with --no-index.")); if (list.nr) - die("--no-index cannot be used with revs."); - hit = grep_directory(&opt, paths); - if (use_threads) - hit |= wait_all(); - return !hit; - } - - if (!list.nr) { - int hit; + die(_("--no-index cannot be used with revs.")); + hit = grep_directory(&opt, &pathspec); + } else if (!list.nr) { if (!cached) setup_work_tree(); - hit = grep_cache(&opt, paths, cached); - if (use_threads) - hit |= wait_all(); - return !hit; - } - - if (cached) - die("both --cached and trees are given."); - - for (i = 0; i < list.nr; i++) { - struct object *real_obj; - real_obj = deref_tag(list.objects[i].item, NULL, 0); - if (grep_object(&opt, paths, real_obj, list.objects[i].name)) { - hit = 1; - if (opt.status_only) - break; - } + hit = grep_cache(&opt, &pathspec, cached); + } else { + if (cached) + die(_("both --cached and trees are given.")); + hit = grep_objects(&opt, &pathspec, &list); } if (use_threads) hit |= wait_all(); + if (hit && show_in_pager) + run_pager(&opt, prefix); free_grep_patterns(&opt); return !hit; } |