* Copyright (c) 2006 Junio C Hamano
*/
#include "cache.h"
+#include "repository.h"
+#include "config.h"
#include "blob.h"
#include "tree.h"
#include "commit.h"
#include "quote.h"
#include "dir.h"
#include "pathspec.h"
+#include "submodule.h"
+#include "submodule-config.h"
static char const * const grep_usage[] = {
N_("git grep [<options>] [-e] <pattern> [<rev>...] [[--] <path>...]"),
NULL
};
+static int recurse_submodules;
+
#define GREP_NUM_THREADS_DEFAULT 8
static int num_threads;
static inline void grep_lock(void)
{
- if (num_threads)
- pthread_mutex_lock(&grep_mutex);
+ assert(num_threads);
+ pthread_mutex_lock(&grep_mutex);
}
static inline void grep_unlock(void)
{
- if (num_threads)
- pthread_mutex_unlock(&grep_mutex);
+ assert(num_threads);
+ pthread_mutex_unlock(&grep_mutex);
}
/* Signalled when a new work_item is added to todo. */
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);
static int grep_cmd_config(const char *var, const char *value, void *cb)
{
int st = grep_config(var, value, cb);
- if (git_color_default_config(var, value, cb) < 0)
+ if (git_default_config(var, value, cb) < 0)
st = -1;
if (!strcmp(var, "grep.threads")) {
if (num_threads < 0)
die(_("invalid number of threads specified (%d) for %s"),
num_threads, var);
+#ifdef NO_PTHREADS
+ else if (num_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 = 0;
+ }
+#endif
}
+ if (!strcmp(var, "submodule.recurse"))
+ recurse_submodules = git_config_bool(var, value);
+
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_sha1_file(oid->hash, type, size);
grep_read_unlock();
return data;
}
-static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1,
+static int grep_oid(struct grep_opt *opt, const struct object_id *oid,
const char *filename, int tree_name_len,
const char *path)
{
#ifndef NO_PTHREADS
if (num_threads) {
- add_work(opt, GREP_SOURCE_SHA1, pathbuf.buf, path, sha1);
+ add_work(opt, GREP_SOURCE_OID, pathbuf.buf, path, oid);
strbuf_release(&pathbuf);
return 0;
} else
struct grep_source gs;
int hit;
- grep_source_init(&gs, GREP_SOURCE_SHA1, pathbuf.buf, path, sha1);
+ grep_source_init(&gs, GREP_SOURCE_OID, pathbuf.buf, path, oid);
strbuf_release(&pathbuf);
hit = grep_source(opt, &gs);
exit(status);
}
-static int grep_cache(struct grep_opt *opt, const struct pathspec *pathspec, int cached)
+static int grep_cache(struct grep_opt *opt, struct repository *repo,
+ 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, struct repository *repo);
+
+static int grep_submodule(struct grep_opt *opt, struct repository *superproject,
+ const struct pathspec *pathspec,
+ const struct object_id *oid,
+ const char *filename, const char *path)
+{
+ struct repository submodule;
+ int hit;
+
+ if (!is_submodule_active(superproject, path))
+ return 0;
+
+ if (repo_submodule_init(&submodule, superproject, path))
+ return 0;
+
+ repo_read_gitmodules(&submodule);
+
+ /*
+ * 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(submodule.objectdir);
+
+ 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(object->oid.hash, 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(opt, pathspec, &tree, &base, base.len,
+ object->type == OBJ_COMMIT, &submodule);
+ strbuf_release(&base);
+ free(data);
+ } else {
+ hit = grep_cache(opt, &submodule, pathspec, 1);
+ }
+
+ repo_clear(&submodule);
+ return hit;
+}
+
+static int grep_cache(struct grep_opt *opt, struct repository *repo,
+ const struct pathspec *pathspec, int cached)
{
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++) {
- const struct cache_entry *ce = active_cache[nr];
- if (!S_ISREG(ce->ce_mode))
- continue;
- if (!ce_path_match(ce, pathspec, NULL))
+ repo_read_index(repo);
+
+ 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(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(pathspec, name.buf, NULL)) {
+ hit |= grep_submodule(opt, repo, pathspec, NULL, ce->name, ce->name);
+ } 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) || ce_intent_to_add(ce))
- continue;
- hit |= grep_sha1(opt, ce->oid.hash, ce->name, 0,
- ce->name);
}
- 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,
- int check_attr)
+ int check_attr, struct repository *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(&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.oid->hash, base->buf, tn_len,
+ hit |= grep_oid(opt, entry.oid, base->buf, tn_len,
check_attr ? base->buf + tn_len : NULL);
- }
- else if (S_ISDIR(entry.mode)) {
+ } 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.oid->hash, &type, &size);
+ data = lock_and_read_oid_file(entry.oid, &type, &size);
if (!data)
die(_("unable to read tree (%s)"),
oid_to_hex(entry.oid));
strbuf_addch(base, '/');
init_tree_desc(&sub, data, size);
hit |= grep_tree(opt, pathspec, &sub, base, tn_len,
- check_attr);
+ check_attr, repo);
free(data);
+ } else if (recurse_submodules && S_ISGITLINK(entry.mode)) {
+ hit |= grep_submodule(opt, repo, pathspec, entry.oid,
+ base->buf, base->buf + tn_len);
}
+
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, const char *path)
+ struct object *obj, const char *name, const char *path,
+ struct repository *repo)
{
if (obj->type == OBJ_BLOB)
- return grep_sha1(opt, obj->oid.hash, name, 0, path);
+ return grep_oid(opt, &obj->oid, name, 0, path);
if (obj->type == OBJ_COMMIT || obj->type == OBJ_TREE) {
struct tree_desc tree;
void *data;
}
init_tree_desc(&tree, data, size);
hit = grep_tree(opt, pathspec, &tree, &base, base.len,
- obj->type == OBJ_COMMIT);
+ obj->type == OBJ_COMMIT, repo);
strbuf_release(&base);
free(data);
return hit;
}
static int grep_objects(struct grep_opt *opt, const struct pathspec *pathspec,
+ struct repository *repo,
const struct object_array *list)
{
unsigned int i;
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, list->objects[i].path)) {
+
+ /* load the gitmodules file for this rev */
+ if (recurse_submodules) {
+ submodule_free();
+ gitmodules_config_oid(&real_obj->oid);
+ }
+ if (grep_object(opt, pathspec, real_obj, list->objects[i].name, list->objects[i].path,
+ repo)) {
hit = 1;
if (opt->status_only)
break;
if (exc_std)
setup_standard_excludes(&dir);
- fill_directory(&dir, pathspec);
+ fill_directory(&dir, &the_index, pathspec);
for (i = 0; i < dir.nr; i++) {
if (!dir_path_match(dir.entries[i], pathspec, 0, NULL))
continue;
int dummy;
int use_index = 1;
int pattern_type_arg = GREP_PATTERN_TYPE_UNSPECIFIED;
+ int allow_revs;
struct option options[] = {
OPT_BOOL(0, "cached", &cached,
N_("search in both tracked and untracked files")),
OPT_SET_INT(0, "exclude-standard", &opt_exclude,
N_("ignore files specified via '.gitignore'"), 1),
+ OPT_BOOL(0, "recurse-submodules", &recurse_submodules,
+ N_("recursively search in each submodule")),
OPT_GROUP(""),
OPT_BOOL('v', "invert-match", &opt.invert,
N_("show non-matching lines")),
if (!opt.pattern_list)
die(_("no pattern given."));
- if (!opt.fixed && opt.ignore_case)
- opt.regflags |= REG_ICASE;
- compile_grep_patterns(&opt);
+ /*
+ * 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++) {
+ if (!strcmp(argv[i], "--")) {
+ seen_dashdash = 1;
+ break;
+ }
+ }
- /* Check revs and then paths */
+ /*
+ * 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];
- unsigned char sha1[20];
+ struct object_id oid;
struct object_context oc;
- /* Is it a rev? */
- if (!get_sha1_with_context(arg, 0, sha1, &oc)) {
- struct object *object = parse_object_or_die(sha1, arg);
- if (!seen_dashdash)
- verify_non_filename(prefix, arg);
- add_object_array_with_path(object, arg, &list, oc.mode, oc.path);
- continue;
- }
+ struct object *object;
+
if (!strcmp(arg, "--")) {
i++;
- seen_dashdash = 1;
+ break;
+ }
+
+ if (!allow_revs) {
+ if (seen_dashdash)
+ die(_("--no-index or --untracked cannot be used with revs"));
+ break;
+ }
+
+ if (get_oid_with_context(arg, GET_OID_RECORD_PATH,
+ &oid, &oc)) {
+ if (seen_dashdash)
+ die(_("unable to resolve revision: %s"), arg);
+ break;
}
- 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);
}
+ /*
+ * 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 && allow_revs);
+ }
+
+ 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;
+
#ifndef NO_PTHREADS
if (list.nr || cached || show_in_pager)
num_threads = 0;
num_threads = GREP_NUM_THREADS_DEFAULT;
else if (num_threads < 0)
die(_("invalid number of threads specified (%d)"), num_threads);
+ if (num_threads == 1)
+ num_threads = 0;
#else
+ if (num_threads)
+ warning(_("no threads support, ignoring --threads"));
num_threads = 0;
#endif
+ if (!num_threads)
+ /*
+ * The compiled patterns on the main path are only
+ * used when not using threading. Otherwise
+ * start_threads() below calls compile_grep_patterns()
+ * for each thread.
+ */
+ compile_grep_patterns(&opt);
+
#ifndef NO_PTHREADS
if (num_threads) {
if (!(opt.name_only || opt.unmatch_name_only || opt.count)
}
#endif
- /* The rest are paths */
- if (!seen_dashdash) {
- int j;
- for (j = i; j < argc; j++)
- verify_filename(prefix, argv[j], j == i);
- }
-
- 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;
-
if (show_in_pager && (cached || list.nr))
die(_("--open-files-in-pager only works on the worktree"));
}
}
+ if (recurse_submodules && (!use_index || untracked))
+ die(_("option not supported with --recurse-submodules."));
+
if (!show_in_pager && !opt.status_only)
setup_pager();
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, use_index);
} else if (0 <= opt_exclude) {
die(_("--[no-]exclude-standard cannot be used for tracked contents."));
if (!cached)
setup_work_tree();
- hit = grep_cache(&opt, &pathspec, cached);
+ hit = grep_cache(&opt, the_repository, &pathspec, cached);
} else {
if (cached)
die(_("both --cached and trees are given."));
- hit = grep_objects(&opt, &pathspec, &list);
+
+ hit = grep_objects(&opt, &pathspec, the_repository, &list);
}
if (num_threads)
hit |= wait_all();
if (hit && show_in_pager)
run_pager(&opt, prefix);
+ clear_pathspec(&pathspec);
free_grep_patterns(&opt);
return !hit;
}