*
* Copyright (c) 2006 Junio C Hamano
*/
-#define USE_THE_INDEX_COMPATIBILITY_MACROS
#include "cache.h"
+#include "alloc.h"
+#include "gettext.h"
+#include "hex.h"
#include "repository.h"
#include "config.h"
#include "blob.h"
#include "quote.h"
#include "dir.h"
#include "pathspec.h"
+#include "setup.h"
#include "submodule.h"
#include "submodule-config.h"
+#include "object-name.h"
#include "object-store.h"
#include "packfile.h"
+#include "write-or-die.h"
+
+static const char *grep_prefix;
static char const * const grep_usage[] = {
N_("git grep [<options>] [-e] <pattern> [<rev>...] [[--] <path>...]"),
/* Has all work items been added? */
static int all_work_added;
+static struct repository **repos_to_free;
+static size_t repos_to_free_nr, repos_to_free_alloc;
+
/* This lock protects all the variables above. */
static pthread_mutex_t grep_mutex;
grep_unlock();
}
+static void free_repos(void)
+{
+ int i;
+
+ for (i = 0; i < repos_to_free_nr; i++) {
+ repo_clear(repos_to_free[i]);
+ free(repos_to_free[i]);
+ }
+ FREE_AND_NULL(repos_to_free);
+ repos_to_free_nr = 0;
+ repos_to_free_alloc = 0;
+}
+
static void *run(void *arg)
{
int hit = 0;
grep_source_clear_data(&w->source);
work_done(w);
}
- free_grep_patterns(arg);
- free(arg);
+ free_grep_patterns(opt);
+ free(opt);
return (void*) (intptr_t) hit;
}
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_color_default_config(var, value, NULL) < 0)
st = -1;
if (!strcmp(var, "grep.threads")) {
strbuf_reset(out);
if (opt->null_following_name) {
- if (opt->relative && opt->prefix_length) {
+ if (opt->relative && grep_prefix) {
struct strbuf rel_buf = STRBUF_INIT;
const char *rel_name =
relative_path(filename + tree_name_len,
- opt->prefix, &rel_buf);
+ grep_prefix, &rel_buf);
if (tree_name_len)
strbuf_add(out, filename, tree_name_len);
return;
}
- if (opt->relative && opt->prefix_length)
- quote_path(filename + tree_name_len, opt->prefix, out, 0);
+ if (opt->relative && grep_prefix)
+ quote_path(filename + tree_name_len, grep_prefix, out, 0);
else
quote_c_style(filename + tree_name_len, out, NULL, 0);
struct grep_source gs;
grep_source_name(opt, filename, tree_name_len, &pathbuf);
- grep_source_init(&gs, GREP_SOURCE_OID, pathbuf.buf, path, oid);
+ grep_source_init_oid(&gs, pathbuf.buf, path, oid, opt->repo);
strbuf_release(&pathbuf);
if (num_threads > 1) {
struct grep_source gs;
grep_source_name(opt, filename, 0, &buf);
- grep_source_init(&gs, GREP_SOURCE_FILE, buf.buf, filename, filename);
+ grep_source_init_file(&gs, buf.buf, filename);
strbuf_release(&buf);
if (num_threads > 1) {
if (len == 1 && *(const char *)data == '\0')
return;
- string_list_append(path_list, xstrndup(data, len));
+ string_list_append_nodup(path_list, xstrndup(data, len));
}
static void run_pager(struct grep_opt *opt, const char *prefix)
const struct object_id *oid,
const char *filename, const char *path, int cached)
{
- struct repository subrepo;
+ struct repository *subrepo;
struct repository *superproject = opt->repo;
- const struct submodule *sub;
struct grep_opt subopt;
- int hit;
-
- sub = submodule_from_path(superproject, null_oid(), path);
+ int hit = 0;
if (!is_submodule_active(superproject, path))
return 0;
- if (repo_submodule_init(&subrepo, superproject, sub))
+ subrepo = xmalloc(sizeof(*subrepo));
+ if (repo_submodule_init(subrepo, superproject, path, null_oid())) {
+ free(subrepo);
return 0;
+ }
+ ALLOC_GROW(repos_to_free, repos_to_free_nr + 1, repos_to_free_alloc);
+ repos_to_free[repos_to_free_nr++] = subrepo;
/*
* NEEDSWORK: repo_read_gitmodules() might call
* subrepo's odbs to the in-memory alternates list.
*/
obj_read_lock();
- repo_read_gitmodules(&subrepo, 0);
/*
- * 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.
+ * NEEDSWORK: when reading a submodule, the sparsity settings in the
+ * superproject are incorrectly forgotten or misused. For example:
+ *
+ * 1. "command_requires_full_index"
+ * When this setting is turned on for `grep`, only the superproject
+ * knows it. All the submodules are read with their own configs
+ * and get prepare_repo_settings()'d. Therefore, these submodules
+ * "forget" the sparse-index feature switch. As a result, the index
+ * of these submodules are expanded unexpectedly.
+ *
+ * 2. "core_apply_sparse_checkout"
+ * When running `grep` in the superproject, this setting is
+ * populated using the superproject's configs. However, once
+ * initialized, this config is globally accessible and is read by
+ * prepare_repo_settings() for the submodules. For instance, if a
+ * submodule is using a sparse-checkout, however, the superproject
+ * is not, the result is that the config from the superproject will
+ * dictate the behavior for the submodule, making it "forget" its
+ * sparse-checkout state.
+ *
+ * 3. "core_sparse_checkout_cone"
+ * ditto.
+ *
+ * Note that this list is not exhaustive.
+ */
+ repo_read_gitmodules(subrepo, 0);
+
+ /*
+ * All code paths tested by test code no longer need submodule ODBs to
+ * be added as alternates, but add it to the list just in case.
+ * Submodule ODBs added through add_submodule_odb_by_path() will be
+ * lazily registered as alternates when needed (and except in an
+ * unexpected code interaction, it won't be needed).
*/
- add_to_alternates_memory(subrepo.objects->odb->path);
+ add_submodule_odb_by_path(subrepo->objects->odb->path);
obj_read_unlock();
memcpy(&subopt, opt, sizeof(subopt));
- subopt.repo = &subrepo;
+ subopt.repo = subrepo;
if (oid) {
- struct object *object;
+ enum object_type object_type;
struct tree_desc tree;
void *data;
unsigned long size;
struct strbuf base = STRBUF_INIT;
obj_read_lock();
- object = parse_object_or_die(oid, NULL);
+ object_type = oid_object_info(subrepo, oid, NULL);
obj_read_unlock();
- data = read_object_with_reference(&subrepo,
- &object->oid, tree_type,
+ data = read_object_with_reference(subrepo,
+ oid, OBJ_TREE,
&size, NULL);
if (!data)
- die(_("unable to read tree (%s)"), oid_to_hex(&object->oid));
+ die(_("unable to read tree (%s)"), oid_to_hex(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);
+ object_type == OBJ_COMMIT);
strbuf_release(&base);
free(data);
} else {
hit = grep_cache(&subopt, pathspec, cached);
}
- repo_clear(&subrepo);
return hit;
}
if (repo_read_index(repo) < 0)
die(_("index file corrupt"));
- /* TODO: audit for interaction with sparse-index. */
- ensure_full_index(repo->index);
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_ISSPARSEDIR(ce->ce_mode)) {
+ enum object_type type;
+ struct tree_desc tree;
+ void *data;
+ unsigned long size;
- if (S_ISREG(ce->ce_mode) &&
+ data = repo_read_object_file(the_repository, &ce->oid,
+ &type, &size);
+ init_tree_desc(&tree, data, size);
+
+ hit |= grep_tree(opt, pathspec, &tree, &name, 0, 0);
+ strbuf_setlen(&name, name_base_len);
+ strbuf_addstr(&name, ce->name);
+ free(data);
+ } else 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))) {
void *data;
unsigned long size;
- data = read_object_file(&entry.oid, &type, &size);
+ data = repo_read_object_file(the_repository,
+ &entry.oid, &type, &size);
if (!data)
die(_("unable to read tree (%s)"),
oid_to_hex(&entry.oid));
int hit, len;
data = read_object_with_reference(opt->repo,
- &obj->oid, tree_type,
+ &obj->oid, OBJ_TREE,
&size, NULL);
if (!data)
die(_("unable to read tree (%s)"), oid_to_hex(&obj->oid));
static int grep_directory(struct grep_opt *opt, const struct pathspec *pathspec,
int exc_std, int use_index)
{
- struct dir_struct dir;
+ struct dir_struct dir = DIR_INIT;
int i, hit = 0;
- dir_init(&dir);
if (!use_index)
dir.flags |= DIR_NO_GITLINKS;
if (exc_std)
struct grep_opt opt;
struct object_array list = OBJECT_ARRAY_INIT;
struct pathspec pathspec;
- struct string_list path_list = STRING_LIST_INIT_NODUP;
+ struct string_list path_list = STRING_LIST_INIT_DUP;
int i;
int dummy;
int use_index = 1;
- int pattern_type_arg = GREP_PATTERN_TYPE_UNSPECIFIED;
int allow_revs;
struct option options[] = {
N_("descend at most <depth> levels"), PARSE_OPT_NONEG,
NULL, 1 },
OPT_GROUP(""),
- OPT_SET_INT('E', "extended-regexp", &pattern_type_arg,
+ OPT_SET_INT('E', "extended-regexp", &opt.pattern_type_option,
N_("use extended POSIX regular expressions"),
GREP_PATTERN_TYPE_ERE),
- OPT_SET_INT('G', "basic-regexp", &pattern_type_arg,
+ OPT_SET_INT('G', "basic-regexp", &opt.pattern_type_option,
N_("use basic POSIX regular expressions (default)"),
GREP_PATTERN_TYPE_BRE),
- OPT_SET_INT('F', "fixed-strings", &pattern_type_arg,
+ OPT_SET_INT('F', "fixed-strings", &opt.pattern_type_option,
N_("interpret patterns as fixed strings"),
GREP_PATTERN_TYPE_FIXED),
- OPT_SET_INT('P', "perl-regexp", &pattern_type_arg,
+ OPT_SET_INT('P', "perl-regexp", &opt.pattern_type_option,
N_("use Perl-compatible regular expressions"),
GREP_PATTERN_TYPE_PCRE),
OPT_GROUP(""),
OPT_BOOL_F(0, "ext-grep", &external_grep_allowed__ignored,
N_("allow calling of grep(1) (ignored by this build)"),
PARSE_OPT_NOCOMPLETE),
+ OPT_INTEGER('m', "max-count", &opt.max_count,
+ N_("maximum number of results per file")),
OPT_END()
};
+ grep_prefix = prefix;
- git_config(grep_cmd_config, NULL);
- grep_init(&opt, the_repository, prefix);
+ grep_init(&opt, the_repository);
+ git_config(grep_cmd_config, &opt);
/*
* 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);
- grep_commit_pattern_type(pattern_type_arg, &opt);
+
+ if (the_repository->gitdir) {
+ prepare_repo_settings(the_repository);
+ the_repository->settings.command_requires_full_index = 0;
+ }
if (use_index && !startup_info->have_repository) {
int fallback = 0;
if (recurse_submodules && untracked)
die(_("--untracked not supported with --recurse-submodules"));
+ /*
+ * Optimize out the case where the amount of matches is limited to zero.
+ * We do this to keep results consistent with GNU grep(1).
+ */
+ if (opt.max_count == 0)
+ return 1;
+
if (show_in_pager) {
if (num_threads > 1)
warning(_("invalid option combination, ignoring --threads"));
strbuf_addf(&buf, "+/%s%s",
strcmp("less", pager) ? "" : "*",
opt.pattern_list->pattern);
- string_list_append(&path_list,
- strbuf_detach(&buf, NULL));
+ string_list_append_nodup(&path_list,
+ strbuf_detach(&buf, NULL));
}
}
if (!show_in_pager && !opt.status_only)
setup_pager();
- if (!use_index && (untracked || cached))
- die(_("--cached or --untracked cannot be used with --no-index"));
-
- if (untracked && cached)
- die(_("--untracked cannot be used with --cached"));
+ die_for_incompatible_opt3(!use_index, "--no-index",
+ untracked, "--untracked",
+ cached, "--cached");
if (!use_index || untracked) {
int use_exclude = (opt_exclude < 0) ? use_index : !!opt_exclude;
if (hit && show_in_pager)
run_pager(&opt, prefix);
clear_pathspec(&pathspec);
+ string_list_clear(&path_list, 0);
free_grep_patterns(&opt);
+ object_array_clear(&list);
+ free_repos();
return !hit;
}