*
* Copyright (c) 2006 Junio C Hamano
*/
+#define USE_THE_INDEX_COMPATIBILITY_MACROS
#include "cache.h"
+#include "repository.h"
+#include "config.h"
#include "blob.h"
#include "tree.h"
#include "commit.h"
#include "grep.h"
#include "quote.h"
#include "dir.h"
+#include "pathspec.h"
+#include "submodule.h"
+#include "submodule-config.h"
+#include "object-store.h"
static char const * const grep_usage[] = {
- N_("git grep [options] [-e] <pattern> [<rev>...] [[--] <path>...]"),
+ N_("git grep [<options>] [-e] <pattern> [<rev>...] [[--] <path>...]"),
NULL
};
-static int use_threads = 1;
+static int recurse_submodules;
-#ifndef NO_PTHREADS
-#define THREADS 8
-static pthread_t threads[THREADS];
+#define GREP_NUM_THREADS_DEFAULT 8
+static int num_threads;
+
+static pthread_t *threads;
/* We use one producer thread and THREADS consumer
* threads. The producer adds struct work_items to 'todo' and the
static inline void grep_lock(void)
{
- if (use_threads)
- pthread_mutex_lock(&grep_mutex);
+ pthread_mutex_lock(&grep_mutex);
}
static inline void grep_unlock(void)
{
- if (use_threads)
- pthread_mutex_unlock(&grep_mutex);
+ pthread_mutex_unlock(&grep_mutex);
}
/* Signalled when a new work_item is added to todo. */
static int skip_first_line;
-static void add_work(struct grep_opt *opt, enum grep_source_type type,
- const char *name, const void *id)
+static void add_work(struct grep_opt *opt, const struct grep_source *gs)
{
grep_lock();
pthread_cond_wait(&cond_write, &grep_mutex);
}
- grep_source_init(&todo[todo_end].source, type, name, id);
+ todo[todo_end].source = *gs;
if (opt->binary != GREP_BINARY_TEXT)
- grep_source_load_driver(&todo[todo_end].source);
+ grep_source_load_driver(&todo[todo_end].source,
+ opt->repo->index);
todo[todo_end].done = 0;
strbuf_reset(&todo[todo_end].out);
todo_end = (todo_end + 1) % ARRAY_SIZE(todo);
strbuf_init(&todo[i].out, 0);
}
- for (i = 0; i < ARRAY_SIZE(threads); i++) {
+ threads = xcalloc(num_threads, sizeof(*threads));
+ for (i = 0; i < num_threads; i++) {
int err;
struct grep_opt *o = grep_opt_dup(opt);
o->output = strbuf_out;
- o->debug = 0;
+ if (i)
+ o->debug = 0;
compile_grep_patterns(o);
err = pthread_create(&threads[i], NULL, run, o);
int hit = 0;
int i;
+ if (!HAVE_THREADS)
+ BUG("Never call this function unless you have started threads");
+
grep_lock();
all_work_added = 1;
pthread_cond_broadcast(&cond_add);
grep_unlock();
- for (i = 0; i < ARRAY_SIZE(threads); i++) {
+ for (i = 0; i < num_threads; i++) {
void *h;
pthread_join(threads[i], &h);
hit |= (int) (intptr_t) h;
}
+ free(threads);
+
pthread_mutex_destroy(&grep_mutex);
pthread_mutex_destroy(&grep_read_mutex);
pthread_mutex_destroy(&grep_attr_mutex);
return hit;
}
-#else /* !NO_PTHREADS */
-
-static int wait_all(void)
-{
- return 0;
-}
-#endif
-
-static int parse_pattern_type_arg(const char *opt, const char *arg)
-{
- if (!strcmp(arg, "default"))
- return GREP_PATTERN_TYPE_UNSPECIFIED;
- else if (!strcmp(arg, "basic"))
- return GREP_PATTERN_TYPE_BRE;
- else if (!strcmp(arg, "extended"))
- return GREP_PATTERN_TYPE_ERE;
- else if (!strcmp(arg, "fixed"))
- return GREP_PATTERN_TYPE_FIXED;
- else if (!strcmp(arg, "perl"))
- return GREP_PATTERN_TYPE_PCRE;
- die("bad %s argument: %s", opt, arg);
-}
-static void grep_pattern_type_options(const int pattern_type, struct grep_opt *opt)
+static int grep_cmd_config(const char *var, const char *value, void *cb)
{
- switch (pattern_type) {
- case GREP_PATTERN_TYPE_UNSPECIFIED:
- /* fall through */
-
- case GREP_PATTERN_TYPE_BRE:
- opt->fixed = 0;
- opt->pcre = 0;
- opt->regflags &= ~REG_EXTENDED;
- break;
-
- case GREP_PATTERN_TYPE_ERE:
- opt->fixed = 0;
- opt->pcre = 0;
- opt->regflags |= REG_EXTENDED;
- break;
-
- case GREP_PATTERN_TYPE_FIXED:
- opt->fixed = 1;
- opt->pcre = 0;
- opt->regflags &= ~REG_EXTENDED;
- break;
-
- case GREP_PATTERN_TYPE_PCRE:
- opt->fixed = 0;
- opt->pcre = 1;
- opt->regflags &= ~REG_EXTENDED;
- break;
- }
-}
-
-static int grep_config(const char *var, const char *value, void *cb)
-{
- struct grep_opt *opt = cb;
- char *color = NULL;
-
- if (userdiff_config(var, value) < 0)
- return -1;
-
- if (!strcmp(var, "grep.extendedregexp")) {
- if (git_config_bool(var, value))
- opt->extended_regexp_option = 1;
- else
- opt->extended_regexp_option = 0;
- return 0;
+ int st = grep_config(var, value, cb);
+ if (git_color_default_config(var, value, cb) < 0)
+ st = -1;
+
+ if (!strcmp(var, "grep.threads")) {
+ num_threads = git_config_int(var, value);
+ if (num_threads < 0)
+ die(_("invalid number of threads specified (%d) for %s"),
+ num_threads, var);
+ else if (!HAVE_THREADS && num_threads > 1) {
+ /*
+ * TRANSLATORS: %s is the configuration
+ * variable for tweaking threads, currently
+ * grep.threads
+ */
+ warning(_("no threads support, ignoring %s"), var);
+ num_threads = 1;
+ }
}
- if (!strcmp(var, "grep.patterntype")) {
- opt->pattern_type_option = parse_pattern_type_arg(var, value);
- return 0;
- }
+ if (!strcmp(var, "submodule.recurse"))
+ recurse_submodules = git_config_bool(var, value);
- 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);
- else if (!strcmp(var, "color.grep.context"))
- color = opt->color_context;
- else if (!strcmp(var, "color.grep.filename"))
- color = opt->color_filename;
- else if (!strcmp(var, "color.grep.function"))
- color = opt->color_function;
- else if (!strcmp(var, "color.grep.linenumber"))
- color = opt->color_lineno;
- else if (!strcmp(var, "color.grep.match"))
- color = opt->color_match;
- else if (!strcmp(var, "color.grep.selected"))
- color = opt->color_selected;
- else if (!strcmp(var, "color.grep.separator"))
- color = opt->color_sep;
- else
- return git_color_default_config(var, value, cb);
- if (color) {
- if (!value)
- return config_error_nonbool(var);
- color_parse(value, var, color);
- }
- return 0;
+ return st;
}
-static void *lock_and_read_sha1_file(const unsigned char *sha1, enum object_type *type, unsigned long *size)
+static void *lock_and_read_oid_file(const struct object_id *oid, enum object_type *type, unsigned long *size)
{
void *data;
grep_read_lock();
- data = read_sha1_file(sha1, type, size);
+ data = read_object_file(oid, type, size);
grep_read_unlock();
return data;
}
-static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1,
- const char *filename, int tree_name_len)
+static int grep_oid(struct grep_opt *opt, const struct object_id *oid,
+ const char *filename, int tree_name_len,
+ const char *path)
{
struct strbuf pathbuf = STRBUF_INIT;
+ struct grep_source gs;
if (opt->relative && opt->prefix_length) {
- quote_path_relative(filename + tree_name_len, -1, &pathbuf,
- opt->prefix);
+ quote_path_relative(filename + tree_name_len, opt->prefix, &pathbuf);
strbuf_insert(&pathbuf, 0, filename, tree_name_len);
} else {
strbuf_addstr(&pathbuf, filename);
}
-#ifndef NO_PTHREADS
- if (use_threads) {
- add_work(opt, GREP_SOURCE_SHA1, pathbuf.buf, sha1);
- strbuf_release(&pathbuf);
+ grep_source_init(&gs, GREP_SOURCE_OID, pathbuf.buf, path, oid);
+ strbuf_release(&pathbuf);
+
+ if (num_threads > 1) {
+ /*
+ * add_work() copies gs and thus assumes ownership of
+ * its fields, so do not call grep_source_clear()
+ */
+ add_work(opt, &gs);
return 0;
- } else
-#endif
- {
- struct grep_source gs;
+ } else {
int hit;
- grep_source_init(&gs, GREP_SOURCE_SHA1, pathbuf.buf, sha1);
- strbuf_release(&pathbuf);
hit = grep_source(opt, &gs);
grep_source_clear(&gs);
static int grep_file(struct grep_opt *opt, const char *filename)
{
struct strbuf buf = STRBUF_INIT;
+ struct grep_source gs;
if (opt->relative && opt->prefix_length)
- quote_path_relative(filename, -1, &buf, opt->prefix);
+ quote_path_relative(filename, opt->prefix, &buf);
else
strbuf_addstr(&buf, filename);
-#ifndef NO_PTHREADS
- if (use_threads) {
- add_work(opt, GREP_SOURCE_FILE, buf.buf, filename);
- strbuf_release(&buf);
+ grep_source_init(&gs, GREP_SOURCE_FILE, buf.buf, filename, filename);
+ strbuf_release(&buf);
+
+ if (num_threads > 1) {
+ /*
+ * add_work() copies gs and thus assumes ownership of
+ * its fields, so do not call grep_source_clear()
+ */
+ add_work(opt, &gs);
return 0;
- } else
-#endif
- {
- struct grep_source gs;
+ } else {
int hit;
- grep_source_init(&gs, GREP_SOURCE_FILE, buf.buf, filename);
- strbuf_release(&buf);
hit = grep_source(opt, &gs);
grep_source_clear(&gs);
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));
+ struct child_process child = CHILD_PROCESS_INIT;
int i, status;
for (i = 0; i < path_list->nr; i++)
- argv[i] = path_list->items[i].string;
- argv[path_list->nr] = NULL;
+ argv_array_push(&child.args, path_list->items[i].string);
+ child.dir = prefix;
+ child.use_shell = 1;
- if (prefix && chdir(prefix))
- die(_("Failed to chdir: %s"), prefix);
- status = run_command_v_opt(argv, RUN_USING_SHELL);
+ status = run_command(&child);
if (status)
exit(status);
- free(argv);
}
-static int grep_cache(struct grep_opt *opt, const struct pathspec *pathspec, int cached)
+static int grep_cache(struct grep_opt *opt,
+ const struct pathspec *pathspec, int cached);
+static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
+ struct tree_desc *tree, struct strbuf *base, int tn_len,
+ int check_attr);
+
+static int grep_submodule(struct grep_opt *opt,
+ const struct pathspec *pathspec,
+ const struct object_id *oid,
+ const char *filename, const char *path, int cached)
+{
+ struct repository subrepo;
+ struct repository *superproject = opt->repo;
+ const struct submodule *sub = submodule_from_path(superproject,
+ &null_oid, path);
+ struct grep_opt subopt;
+ int hit;
+
+ /*
+ * NEEDSWORK: submodules functions need to be protected because they
+ * access the object store via config_from_gitmodules(): the latter
+ * uses get_oid() which, for now, relies on the global the_repository
+ * object.
+ */
+ grep_read_lock();
+
+ if (!is_submodule_active(superproject, path)) {
+ grep_read_unlock();
+ return 0;
+ }
+
+ if (repo_submodule_init(&subrepo, superproject, sub)) {
+ grep_read_unlock();
+ return 0;
+ }
+
+ repo_read_gitmodules(&subrepo);
+
+ /*
+ * NEEDSWORK: This adds the submodule's object directory to the list of
+ * alternates for the single in-memory object store. This has some bad
+ * consequences for memory (processed objects will never be freed) and
+ * performance (this increases the number of pack files git has to pay
+ * attention to, to the sum of the number of pack files in all the
+ * repositories processed so far). This can be removed once the object
+ * store is no longer global and instead is a member of the repository
+ * object.
+ */
+ add_to_alternates_memory(subrepo.objects->odb->path);
+ grep_read_unlock();
+
+ memcpy(&subopt, opt, sizeof(subopt));
+ subopt.repo = &subrepo;
+
+ if (oid) {
+ struct object *object;
+ struct tree_desc tree;
+ void *data;
+ unsigned long size;
+ struct strbuf base = STRBUF_INIT;
+
+ object = parse_object_or_die(oid, oid_to_hex(oid));
+
+ grep_read_lock();
+ data = read_object_with_reference(&subrepo,
+ &object->oid, tree_type,
+ &size, NULL);
+ grep_read_unlock();
+
+ if (!data)
+ die(_("unable to read tree (%s)"), oid_to_hex(&object->oid));
+
+ strbuf_addstr(&base, filename);
+ strbuf_addch(&base, '/');
+
+ init_tree_desc(&tree, data, size);
+ hit = grep_tree(&subopt, pathspec, &tree, &base, base.len,
+ object->type == OBJ_COMMIT);
+ strbuf_release(&base);
+ free(data);
+ } else {
+ hit = grep_cache(&subopt, pathspec, cached);
+ }
+
+ repo_clear(&subrepo);
+ return hit;
+}
+
+static int grep_cache(struct grep_opt *opt,
+ const struct pathspec *pathspec, int cached)
{
+ struct repository *repo = opt->repo;
int hit = 0;
int nr;
- read_cache();
+ struct strbuf name = STRBUF_INIT;
+ int name_base_len = 0;
+ if (repo->submodule_prefix) {
+ name_base_len = strlen(repo->submodule_prefix);
+ strbuf_addstr(&name, repo->submodule_prefix);
+ }
- for (nr = 0; nr < active_nr; nr++) {
- struct cache_entry *ce = active_cache[nr];
- if (!S_ISREG(ce->ce_mode))
- continue;
- if (!match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL))
+ if (repo_read_index(repo) < 0)
+ die(_("index file corrupt"));
+
+ for (nr = 0; nr < repo->index->cache_nr; nr++) {
+ const struct cache_entry *ce = repo->index->cache[nr];
+ strbuf_setlen(&name, name_base_len);
+ strbuf_addstr(&name, ce->name);
+
+ if (S_ISREG(ce->ce_mode) &&
+ match_pathspec(repo->index, pathspec, name.buf, name.len, 0, NULL,
+ S_ISDIR(ce->ce_mode) ||
+ S_ISGITLINK(ce->ce_mode))) {
+ /*
+ * If CE_VALID is on, we assume worktree file and its
+ * cache entry are identical, even if worktree file has
+ * been modified, so use cache version instead
+ */
+ if (cached || (ce->ce_flags & CE_VALID) ||
+ ce_skip_worktree(ce)) {
+ if (ce_stage(ce) || ce_intent_to_add(ce))
+ continue;
+ hit |= grep_oid(opt, &ce->oid, name.buf,
+ 0, name.buf);
+ } else {
+ hit |= grep_file(opt, name.buf);
+ }
+ } else if (recurse_submodules && S_ISGITLINK(ce->ce_mode) &&
+ submodule_path_match(repo->index, pathspec, name.buf, NULL)) {
+ hit |= grep_submodule(opt, pathspec, NULL, ce->name,
+ ce->name, cached);
+ } else {
continue;
- /*
- * If CE_VALID is on, we assume worktree file and its cache entry
- * are identical, even if worktree file has been modified, so use
- * cache version instead
- */
- if (cached || (ce->ce_flags & CE_VALID) || ce_skip_worktree(ce)) {
- if (ce_stage(ce))
- continue;
- hit |= grep_sha1(opt, ce->sha1, ce->name, 0);
}
- else
- hit |= grep_file(opt, ce->name);
+
if (ce_stage(ce)) {
do {
nr++;
- } while (nr < active_nr &&
- !strcmp(ce->name, active_cache[nr]->name));
+ } while (nr < repo->index->cache_nr &&
+ !strcmp(ce->name, repo->index->cache[nr]->name));
nr--; /* compensate for loop control */
}
if (hit && opt->status_only)
break;
}
+
+ strbuf_release(&name);
return hit;
}
static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
- struct tree_desc *tree, struct strbuf *base, int tn_len)
+ struct tree_desc *tree, struct strbuf *base, int tn_len,
+ int check_attr)
{
+ struct repository *repo = opt->repo;
int hit = 0;
enum interesting match = entry_not_interesting;
struct name_entry entry;
int old_baselen = base->len;
+ struct strbuf name = STRBUF_INIT;
+ int name_base_len = 0;
+ if (repo->submodule_prefix) {
+ strbuf_addstr(&name, repo->submodule_prefix);
+ name_base_len = name.len;
+ }
while (tree_entry(tree, &entry)) {
int te_len = tree_entry_len(&entry);
if (match != all_entries_interesting) {
- match = tree_entry_interesting(&entry, base, tn_len, pathspec);
+ strbuf_addstr(&name, base->buf + tn_len);
+ match = tree_entry_interesting(repo->index,
+ &entry, &name,
+ 0, pathspec);
+ strbuf_setlen(&name, name_base_len);
+
if (match == all_entries_not_interesting)
break;
if (match == entry_not_interesting)
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)) {
+ hit |= grep_oid(opt, &entry.oid, base->buf, tn_len,
+ check_attr ? base->buf + tn_len : NULL);
+ } else if (S_ISDIR(entry.mode)) {
enum object_type type;
struct tree_desc sub;
void *data;
unsigned long size;
- data = lock_and_read_sha1_file(entry.sha1, &type, &size);
+ data = lock_and_read_oid_file(&entry.oid, &type, &size);
if (!data)
die(_("unable to read tree (%s)"),
- sha1_to_hex(entry.sha1));
+ oid_to_hex(&entry.oid));
strbuf_addch(base, '/');
init_tree_desc(&sub, data, size);
- hit |= grep_tree(opt, pathspec, &sub, base, tn_len);
+ hit |= grep_tree(opt, pathspec, &sub, base, tn_len,
+ check_attr);
free(data);
+ } else if (recurse_submodules && S_ISGITLINK(entry.mode)) {
+ hit |= grep_submodule(opt, pathspec, &entry.oid,
+ base->buf, base->buf + tn_len,
+ 1); /* ignored */
}
+
strbuf_setlen(base, old_baselen);
if (hit && opt->status_only)
break;
}
+
+ strbuf_release(&name);
return hit;
}
static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec,
- struct object *obj, const char *name)
+ struct object *obj, const char *name, const char *path)
{
if (obj->type == OBJ_BLOB)
- return grep_sha1(opt, obj->sha1, name, 0);
+ return grep_oid(opt, &obj->oid, name, 0, path);
if (obj->type == OBJ_COMMIT || obj->type == OBJ_TREE) {
struct tree_desc tree;
void *data;
int hit, len;
grep_read_lock();
- data = read_object_with_reference(obj->sha1, tree_type,
+ data = read_object_with_reference(opt->repo,
+ &obj->oid, tree_type,
&size, NULL);
grep_read_unlock();
if (!data)
- die(_("unable to read tree (%s)"), sha1_to_hex(obj->sha1));
+ die(_("unable to read tree (%s)"), oid_to_hex(&obj->oid));
len = name ? strlen(name) : 0;
strbuf_init(&base, PATH_MAX + len + 1);
strbuf_addch(&base, ':');
}
init_tree_desc(&tree, data, size);
- hit = grep_tree(opt, pathspec, &tree, &base, base.len);
+ hit = grep_tree(opt, pathspec, &tree, &base, base.len,
+ obj->type == OBJ_COMMIT);
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"), type_name(obj->type));
}
static int grep_objects(struct grep_opt *opt, const struct pathspec *pathspec,
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)) {
+ real_obj = deref_tag(opt->repo, list->objects[i].item,
+ NULL, 0);
+
+ /* load the gitmodules file for this rev */
+ if (recurse_submodules) {
+ submodule_free(opt->repo);
+ gitmodules_config_oid(&real_obj->oid);
+ }
+ if (grep_object(opt, pathspec, real_obj, list->objects[i].name,
+ list->objects[i].path)) {
hit = 1;
if (opt->status_only)
break;
}
static int grep_directory(struct grep_opt *opt, const struct pathspec *pathspec,
- int exc_std)
+ int exc_std, int use_index)
{
struct dir_struct dir;
int i, hit = 0;
memset(&dir, 0, sizeof(dir));
+ if (!use_index)
+ dir.flags |= DIR_NO_GITLINKS;
if (exc_std)
setup_standard_excludes(&dir);
- fill_directory(&dir, pathspec->raw);
+ fill_directory(&dir, opt->repo->index, pathspec);
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))
+ if (!dir_path_match(opt->repo->index, dir.entries[i], pathspec, 0, NULL))
continue;
hit |= grep_file(opt, dir.entries[i]->name);
if (hit && opt->status_only)
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, "-");
+ int from_stdin;
FILE *patterns;
int lno = 0;
struct strbuf sb = STRBUF_INIT;
+ BUG_ON_OPT_NEG(unset);
+
+ from_stdin = !strcmp(arg, "-");
patterns = from_stdin ? stdin : fopen(arg, "r");
if (!patterns)
die_errno(_("cannot open '%s'"), arg);
- while (strbuf_getline(&sb, patterns, '\n') == 0) {
+ while (strbuf_getline(&sb, patterns) == 0) {
/* ignore empty line like grep does */
if (sb.len == 0)
continue;
static int not_callback(const struct option *opt, const char *arg, int unset)
{
struct grep_opt *grep_opt = opt->value;
+ BUG_ON_OPT_NEG(unset);
+ BUG_ON_OPT_ARG(arg);
append_grep_pattern(grep_opt, "--not", "command line", 0, GREP_NOT);
return 0;
}
static int and_callback(const struct option *opt, const char *arg, int unset)
{
struct grep_opt *grep_opt = opt->value;
+ BUG_ON_OPT_NEG(unset);
+ BUG_ON_OPT_ARG(arg);
append_grep_pattern(grep_opt, "--and", "command line", 0, GREP_AND);
return 0;
}
static int open_callback(const struct option *opt, const char *arg, int unset)
{
struct grep_opt *grep_opt = opt->value;
+ BUG_ON_OPT_NEG(unset);
+ BUG_ON_OPT_ARG(arg);
append_grep_pattern(grep_opt, "(", "command line", 0, GREP_OPEN_PAREN);
return 0;
}
static int close_callback(const struct option *opt, const char *arg, int unset)
{
struct grep_opt *grep_opt = opt->value;
+ BUG_ON_OPT_NEG(unset);
+ BUG_ON_OPT_ARG(arg);
append_grep_pattern(grep_opt, ")", "command line", 0, GREP_CLOSE_PAREN);
return 0;
}
int unset)
{
struct grep_opt *grep_opt = opt->value;
+ BUG_ON_OPT_NEG(unset);
append_grep_pattern(grep_opt, arg, "-e option", 0, GREP_PATTERN);
return 0;
}
-static int help_callback(const struct option *opt, const char *arg, int unset)
-{
- return -1;
-}
-
int cmd_grep(int argc, const char **argv, const char *prefix)
{
int hit = 0;
const char *show_in_pager = NULL, *default_pager = "dummy";
struct grep_opt opt;
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 use_index = 1;
int pattern_type_arg = GREP_PATTERN_TYPE_UNSPECIFIED;
+ int allow_revs;
struct option options[] = {
- OPT_BOOLEAN(0, "cached", &cached,
+ OPT_BOOL(0, "cached", &cached,
N_("search in index instead of in the work tree")),
OPT_NEGBIT(0, "no-index", &use_index,
N_("find in contents not managed by git"), 1),
- OPT_BOOLEAN(0, "untracked", &untracked,
+ OPT_BOOL(0, "untracked", &untracked,
N_("search in both tracked and untracked files")),
OPT_SET_INT(0, "exclude-standard", &opt_exclude,
- N_("search also in ignored files"), 1),
+ N_("ignore files specified via '.gitignore'"), 1),
+ OPT_BOOL(0, "recurse-submodules", &recurse_submodules,
+ N_("recursively search in each submodule")),
OPT_GROUP(""),
- OPT_BOOLEAN('v', "invert-match", &opt.invert,
+ OPT_BOOL('v', "invert-match", &opt.invert,
N_("show non-matching lines")),
- OPT_BOOLEAN('i', "ignore-case", &opt.ignore_case,
+ OPT_BOOL('i', "ignore-case", &opt.ignore_case,
N_("case insensitive matching")),
- OPT_BOOLEAN('w', "word-regexp", &opt.word_regexp,
+ OPT_BOOL('w', "word-regexp", &opt.word_regexp,
N_("match patterns only at word boundaries")),
OPT_SET_INT('a', "text", &opt.binary,
N_("process binary files as text"), GREP_BINARY_TEXT),
OPT_SET_INT('I', NULL, &opt.binary,
N_("don't match patterns in binary files"),
GREP_BINARY_NOMATCH),
+ OPT_BOOL(0, "textconv", &opt.allow_textconv,
+ N_("process binary files with textconv filters")),
+ OPT_SET_INT('r', "recursive", &opt.max_depth,
+ N_("search in subdirectories (default)"), -1),
{ OPTION_INTEGER, 0, "max-depth", &opt.max_depth, N_("depth"),
N_("descend at most <depth> levels"), PARSE_OPT_NONEG,
NULL, 1 },
N_("use Perl-compatible regular expressions"),
GREP_PATTERN_TYPE_PCRE),
OPT_GROUP(""),
- OPT_BOOLEAN('n', "line-number", &opt.linenum, N_("show line numbers")),
+ OPT_BOOL('n', "line-number", &opt.linenum, N_("show line numbers")),
+ OPT_BOOL(0, "column", &opt.columnnum, N_("show column number of first match")),
OPT_NEGBIT('h', NULL, &opt.pathname, N_("don't show filenames"), 1),
OPT_BIT('H', NULL, &opt.pathname, N_("show filenames"), 1),
OPT_NEGBIT(0, "full-name", &opt.relative,
N_("show filenames relative to top directory"), 1),
- OPT_BOOLEAN('l', "files-with-matches", &opt.name_only,
+ OPT_BOOL('l', "files-with-matches", &opt.name_only,
N_("show only filenames instead of matching lines")),
- OPT_BOOLEAN(0, "name-only", &opt.name_only,
+ OPT_BOOL(0, "name-only", &opt.name_only,
N_("synonym for --files-with-matches")),
- OPT_BOOLEAN('L', "files-without-match",
+ OPT_BOOL('L', "files-without-match",
&opt.unmatch_name_only,
N_("show only the names of files without match")),
- OPT_BOOLEAN('z', "null", &opt.null_following_name,
- N_("print NUL after filenames")),
- OPT_BOOLEAN('c', "count", &opt.count,
+ OPT_BOOL_F('z', "null", &opt.null_following_name,
+ N_("print NUL after filenames"),
+ PARSE_OPT_NOCOMPLETE),
+ OPT_BOOL('o', "only-matching", &opt.only_matching,
+ N_("show only matching parts of a line")),
+ OPT_BOOL('c', "count", &opt.count,
N_("show the number of matches instead of matching lines")),
OPT__COLOR(&opt.color, N_("highlight matches")),
- OPT_BOOLEAN(0, "break", &opt.file_break,
+ OPT_BOOL(0, "break", &opt.file_break,
N_("print empty line between matches from different files")),
- OPT_BOOLEAN(0, "heading", &opt.heading,
+ OPT_BOOL(0, "heading", &opt.heading,
N_("show filename only once above matches from same file")),
OPT_GROUP(""),
OPT_CALLBACK('C', "context", &opt, N_("n"),
N_("show <n> context lines before matches")),
OPT_INTEGER('A', "after-context", &opt.post_context,
N_("show <n> context lines after matches")),
+ OPT_INTEGER(0, "threads", &num_threads,
+ N_("use <n> worker threads")),
OPT_NUMBER_CALLBACK(&opt, N_("shortcut for -C NUM"),
context_callback),
- OPT_BOOLEAN('p', "show-function", &opt.funcname,
+ OPT_BOOL('p', "show-function", &opt.funcname,
N_("show a line with the function name before matches")),
- OPT_BOOLEAN('W', "function-context", &opt.funcbody,
+ OPT_BOOL('W', "function-context", &opt.funcbody,
N_("show the surrounding function")),
OPT_GROUP(""),
OPT_CALLBACK('f', NULL, &opt, N_("file"),
{ OPTION_CALLBACK, 0, "and", &opt, NULL,
N_("combine patterns specified with -e"),
PARSE_OPT_NOARG | PARSE_OPT_NONEG, and_callback },
- OPT_BOOLEAN(0, "or", &dummy, ""),
+ OPT_BOOL(0, "or", &dummy, ""),
{ OPTION_CALLBACK, 0, "not", &opt, NULL, "",
PARSE_OPT_NOARG | PARSE_OPT_NONEG, not_callback },
{ OPTION_CALLBACK, '(', NULL, &opt, NULL, "",
close_callback },
OPT__QUIET(&opt.status_only,
N_("indicate hit with exit status without output")),
- OPT_BOOLEAN(0, "all-match", &opt.all_match,
+ OPT_BOOL(0, "all-match", &opt.all_match,
N_("show only matches from files that match all patterns")),
- { OPTION_SET_INT, 0, "debug", &opt.debug, NULL,
- N_("show parse tree for grep expression"),
- PARSE_OPT_NOARG | PARSE_OPT_HIDDEN, NULL, 1 },
+ OPT_SET_INT_F(0, "debug", &opt.debug,
+ N_("show parse tree for grep expression"),
+ 1, PARSE_OPT_HIDDEN),
OPT_GROUP(""),
{ OPTION_STRING, 'O', "open-files-in-pager", &show_in_pager,
N_("pager"), N_("show matching files in the pager"),
- PARSE_OPT_OPTARG, NULL, (intptr_t)default_pager },
- OPT_BOOLEAN(0, "ext-grep", &external_grep_allowed__ignored,
- N_("allow calling of grep(1) (ignored by this build)")),
- { OPTION_CALLBACK, 0, "help-all", &options, NULL, N_("show usage"),
- PARSE_OPT_HIDDEN | PARSE_OPT_NOARG, help_callback },
+ PARSE_OPT_OPTARG | PARSE_OPT_NOCOMPLETE,
+ NULL, (intptr_t)default_pager },
+ OPT_BOOL_F(0, "ext-grep", &external_grep_allowed__ignored,
+ N_("allow calling of grep(1) (ignored by this build)"),
+ PARSE_OPT_NOCOMPLETE),
OPT_END()
};
- /*
- * 'git grep -h', unlike 'git grep -h <pattern>', is a request
- * to show usage information and exit.
- */
- if (argc == 2 && !strcmp(argv[1], "-h"))
- usage_with_options(grep_usage, options);
-
- memset(&opt, 0, sizeof(opt));
- opt.prefix = prefix;
- opt.prefix_length = (prefix && *prefix) ? strlen(prefix) : 0;
- opt.relative = 1;
- opt.pathname = 1;
- opt.pattern_tail = &opt.pattern_list;
- opt.header_tail = &opt.header_list;
- opt.regflags = REG_NEWLINE;
- 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, GIT_COLOR_BOLD_RED);
- strcpy(opt.color_selected, "");
- strcpy(opt.color_sep, GIT_COLOR_CYAN);
- opt.color = -1;
- git_config(grep_config, &opt);
+ init_grep_defaults(the_repository);
+ git_config(grep_cmd_config, NULL);
+ grep_init(&opt, the_repository, prefix);
/*
* If there is no -- then the paths must exist in the working
*/
argc = parse_options(argc, argv, prefix, options, grep_usage,
PARSE_OPT_KEEP_DASHDASH |
- PARSE_OPT_STOP_AT_NON_OPTION |
- PARSE_OPT_NO_INTERNAL_HELP);
-
- if (pattern_type_arg != GREP_PATTERN_TYPE_UNSPECIFIED)
- grep_pattern_type_options(pattern_type_arg, &opt);
- else if (opt.pattern_type_option != GREP_PATTERN_TYPE_UNSPECIFIED)
- grep_pattern_type_options(opt.pattern_type_option, &opt);
- else if (opt.extended_regexp_option)
- grep_pattern_type_options(GREP_PATTERN_TYPE_ERE, &opt);
-
- if (use_index && !startup_info->have_repository)
- /* die the same way as if we did it at the beginning */
- setup_git_directory();
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ grep_commit_pattern_type(pattern_type_arg, &opt);
+
+ if (use_index && !startup_info->have_repository) {
+ int fallback = 0;
+ git_config_get_bool("grep.fallbacktonoindex", &fallback);
+ if (fallback)
+ use_index = 0;
+ else
+ /* die the same way as if we did it at the beginning */
+ setup_git_directory();
+ }
+ /* Ignore --recurse-submodules if --no-index is given or implied */
+ if (!use_index)
+ recurse_submodules = 0;
/*
* skip a -- separator; we know it cannot be
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."));
- if (!opt.fixed && opt.ignore_case)
- opt.regflags |= REG_ICASE;
+ die(_("no pattern given"));
- compile_grep_patterns(&opt);
+ /* --only-matching has no effect with --invert. */
+ if (opt.invert)
+ opt.only_matching = 0;
- /* Check revs and then paths */
+ /*
+ * We have to find "--" in a separate pass, because its presence
+ * influences how we will parse arguments that come before it.
+ */
for (i = 0; i < argc; i++) {
- const char *arg = argv[i];
- unsigned char sha1[20];
- /* Is it a rev? */
- if (!get_sha1(arg, sha1)) {
- struct object *object = parse_object(sha1);
- if (!object)
- die(_("bad object %s"), arg);
- add_object_array(object, arg, &list);
- continue;
+ if (!strcmp(argv[i], "--")) {
+ seen_dashdash = 1;
+ break;
}
+ }
+
+ /*
+ * Resolve any rev arguments. If we have a dashdash, then everything up
+ * to it must resolve as a rev. If not, then we stop at the first
+ * non-rev and assume everything else is a path.
+ */
+ allow_revs = use_index && !untracked;
+ for (i = 0; i < argc; i++) {
+ const char *arg = argv[i];
+ struct object_id oid;
+ struct object_context oc;
+ struct object *object;
+
if (!strcmp(arg, "--")) {
i++;
- seen_dashdash = 1;
+ break;
}
- break;
- }
-#ifndef NO_PTHREADS
- if (list.nr || cached || online_cpus() == 1)
- use_threads = 0;
-#else
- use_threads = 0;
-#endif
+ if (!allow_revs) {
+ if (seen_dashdash)
+ die(_("--no-index or --untracked cannot be used with revs"));
+ break;
+ }
-#ifndef NO_PTHREADS
- if (use_threads) {
- if (!(opt.name_only || opt.unmatch_name_only || opt.count)
- && (opt.pre_context || opt.post_context ||
- opt.file_break || opt.funcbody))
- skip_first_line = 1;
- start_threads(&opt);
+ if (get_oid_with_context(the_repository, arg,
+ GET_OID_RECORD_PATH,
+ &oid, &oc)) {
+ if (seen_dashdash)
+ die(_("unable to resolve revision: %s"), arg);
+ break;
+ }
+
+ object = parse_object_or_die(&oid, arg);
+ if (!seen_dashdash)
+ verify_non_filename(prefix, arg);
+ add_object_array_with_path(object, arg, &list, oc.mode, oc.path);
+ free(oc.path);
}
-#endif
- /* The rest are paths */
+ /*
+ * Anything left over is presumed to be a path. But in the non-dashdash
+ * "do what I mean" case, we verify and complain when that isn't true.
+ */
if (!seen_dashdash) {
int j;
for (j = i; j < argc; j++)
- verify_filename(prefix, argv[j], j == i);
+ verify_filename(prefix, argv[j], j == i && allow_revs);
}
- paths = get_pathspec(prefix, argv + i);
- init_pathspec(&pathspec, paths);
+ parse_pathspec(&pathspec, 0,
+ PATHSPEC_PREFER_CWD |
+ (opt.max_depth != -1 ? PATHSPEC_MAXDEPTH_VALID : 0),
+ prefix, argv + i);
pathspec.max_depth = opt.max_depth;
pathspec.recursive = 1;
+ pathspec.recurse_submodules = !!recurse_submodules;
+
+ if (list.nr || cached || show_in_pager) {
+ if (num_threads > 1)
+ warning(_("invalid option combination, ignoring --threads"));
+ num_threads = 1;
+ } else if (!HAVE_THREADS && num_threads > 1) {
+ warning(_("no threads support, ignoring --threads"));
+ num_threads = 1;
+ } else if (num_threads < 0)
+ die(_("invalid number of threads specified (%d)"), num_threads);
+ else if (num_threads == 0)
+ num_threads = HAVE_THREADS ? GREP_NUM_THREADS_DEFAULT : 1;
+
+ if (num_threads > 1) {
+ if (!HAVE_THREADS)
+ BUG("Somebody got num_threads calculation wrong!");
+ if (!(opt.name_only || opt.unmatch_name_only || opt.count)
+ && (opt.pre_context || opt.post_context ||
+ opt.file_break || opt.funcbody))
+ skip_first_line = 1;
+ start_threads(&opt);
+ } else {
+ /*
+ * The compiled patterns on the main path are only
+ * used when not using threading. Otherwise
+ * start_threads() above calls compile_grep_patterns()
+ * for each thread.
+ */
+ compile_grep_patterns(&opt);
+ }
if (show_in_pager && (cached || list.nr))
die(_("--open-files-in-pager only works on the worktree"));
if (len > 4 && is_dir_sep(pager[len - 5]))
pager += len - 4;
+ if (opt.ignore_case && !strcmp("less", pager))
+ string_list_append(&path_list, "-I");
+
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);
+ string_list_append(&path_list,
+ strbuf_detach(&buf, NULL));
}
}
- if (!show_in_pager)
+ if (recurse_submodules && untracked)
+ die(_("--untracked not supported with --recurse-submodules"));
+
+ if (!show_in_pager && !opt.status_only)
setup_pager();
if (!use_index && (untracked || cached))
- die(_("--cached or --untracked cannot be used with --no-index."));
+ die(_("--cached or --untracked cannot be used with --no-index"));
if (!use_index || untracked) {
int use_exclude = (opt_exclude < 0) ? use_index : !!opt_exclude;
- if (list.nr)
- die(_("--no-index or --untracked cannot be used with revs."));
- hit = grep_directory(&opt, &pathspec, use_exclude);
+ hit = grep_directory(&opt, &pathspec, use_exclude, use_index);
} else if (0 <= opt_exclude) {
- die(_("--[no-]exclude-standard cannot be used for tracked contents."));
+ die(_("--[no-]exclude-standard cannot be used for tracked contents"));
} else if (!list.nr) {
if (!cached)
setup_work_tree();
hit = grep_cache(&opt, &pathspec, cached);
} else {
if (cached)
- die(_("both --cached and trees are given."));
+ die(_("both --cached and trees are given"));
+
hit = grep_objects(&opt, &pathspec, &list);
}
- if (use_threads)
+ if (num_threads > 1)
hit |= wait_all();
if (hit && show_in_pager)
run_pager(&opt, prefix);
+ clear_pathspec(&pathspec);
free_grep_patterns(&opt);
+ grep_destroy();
return !hit;
}