1 files changed, 318 insertions, 505 deletions

diff --git a/builtin/grep.c b/builtin/grep.c
index 3d5f6ace97..111b6f6cf1 100644
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -17,43 +17,25 @@
 #include "grep.h"
 #include "quote.h"
 #include "dir.h"
-
-#ifndef NO_PTHREADS
-#include <pthread.h>
-#include "thread-utils.h"
-#endif
+#include "pathspec.h"
 
 static char const * const grep_usage[] = {
-	"git grep [options] [-e] <pattern> [<rev>...] [[--] <path>...]",
+	N_("git grep [<options>] [-e] <pattern> [<rev>...] [[--] <path>...]"),
 	NULL
 };
 
-static int use_threads = 1;
+#define GREP_NUM_THREADS_DEFAULT 8
+static int num_threads;
 
 #ifndef NO_PTHREADS
-#define THREADS 8
-static pthread_t threads[THREADS];
-
-static void *load_sha1(const unsigned char *sha1, unsigned long *size,
-		       const char *name);
-static void *load_file(const char *filename, size_t *sz);
-
-enum work_type {WORK_SHA1, WORK_FILE};
+static pthread_t *threads;
 
 /* We use one producer thread and THREADS consumer
  * threads. The producer adds struct work_items to 'todo' and the
  * consumers pick work items from the same array.
  */
-struct work_item
-{
-	enum work_type type;
-	char *name;
-
-	/* if type == WORK_SHA1, then 'identifier' is a SHA1,
-	 * otherwise type == WORK_FILE, and 'identifier' is a NUL
-	 * terminated filename.
-	 */
-	void *identifier;
+struct work_item {
+	struct grep_source source;
 	char done;
 	struct strbuf out;
 };
@@ -79,13 +61,17 @@ static int all_work_added;
 /* This lock protects all the variables above. */
 static pthread_mutex_t grep_mutex;
 
-/* Used to serialize calls to read_sha1_file. */
-static pthread_mutex_t read_sha1_mutex;
+static inline void grep_lock(void)
+{
+	if (num_threads)
+		pthread_mutex_lock(&grep_mutex);
+}
 
-#define grep_lock() pthread_mutex_lock(&grep_mutex)
-#define grep_unlock() pthread_mutex_unlock(&grep_mutex)
-#define read_sha1_lock() pthread_mutex_lock(&read_sha1_mutex)
-#define read_sha1_unlock() pthread_mutex_unlock(&read_sha1_mutex)
+static inline void grep_unlock(void)
+{
+	if (num_threads)
+		pthread_mutex_unlock(&grep_mutex);
+}
 
 /* Signalled when a new work_item is added to todo. */
 static pthread_cond_t cond_add;
@@ -98,10 +84,10 @@ static pthread_cond_t cond_write;
 /* Signalled when we are finished with everything. */
 static pthread_cond_t cond_result;
 
-static int print_hunk_marks_between_files;
-static int printed_something;
+static int skip_first_line;
 
-static void add_work(enum work_type type, char *name, void *id)
+static void add_work(struct grep_opt *opt, enum grep_source_type type,
+		     const char *name, const char *path, const void *id)
 {
 	grep_lock();
 
@@ -109,9 +95,9 @@ static void add_work(enum work_type type, char *name, void *id)
 		pthread_cond_wait(&cond_write, &grep_mutex);
 	}
 
-	todo[todo_end].type = type;
-	todo[todo_end].name = name;
-	todo[todo_end].identifier = id;
+	grep_source_init(&todo[todo_end].source, type, name, path, id);
+	if (opt->binary != GREP_BINARY_TEXT)
+		grep_source_load_driver(&todo[todo_end].source);
 	todo[todo_end].done = 0;
 	strbuf_reset(&todo[todo_end].out);
 	todo_end = (todo_end + 1) % ARRAY_SIZE(todo);
@@ -139,21 +125,6 @@ static struct work_item *get_work(void)
 	return ret;
 }
 
-static void grep_sha1_async(struct grep_opt *opt, char *name,
-			    const unsigned char *sha1)
-{
-	unsigned char *s;
-	s = xmalloc(20);
-	memcpy(s, sha1, 20);
-	add_work(WORK_SHA1, name, s);
-}
-
-static void grep_file_async(struct grep_opt *opt, char *name,
-			    const char *filename)
-{
-	add_work(WORK_FILE, name, xstrdup(filename));
-}
-
 static void work_done(struct work_item *w)
 {
 	int old_done;
@@ -165,13 +136,22 @@ static void work_done(struct work_item *w)
 	    todo_done = (todo_done+1) % ARRAY_SIZE(todo)) {
 		w = &todo[todo_done];
 		if (w->out.len) {
-			if (print_hunk_marks_between_files && printed_something)
-				write_or_die(1, "--\n", 3);
-			write_or_die(1, w->out.buf, w->out.len);
-			printed_something = 1;
+			const char *p = w->out.buf;
+			size_t len = w->out.len;
+
+			/* Skip the leading hunk mark of the first file. */
+			if (skip_first_line) {
+				while (len) {
+					len--;
+					if (*p++ == '\n')
+						break;
+				}
+				skip_first_line = 0;
+			}
+
+			write_or_die(1, p, len);
 		}
-		free(w->name);
-		free(w->identifier);
+		grep_source_clear(&w->source);
 	}
 
 	if (old_done != todo_done)
@@ -194,25 +174,8 @@ static void *run(void *arg)
 			break;
 
 		opt->output_priv = w;
-		if (w->type == WORK_SHA1) {
-			unsigned long sz;
-			void* data = load_sha1(w->identifier, &sz, w->name);
-
-			if (data) {
-				hit |= grep_buffer(opt, w->name, data, sz);
-				free(data);
-			}
-		} else if (w->type == WORK_FILE) {
-			size_t sz;
-			void* data = load_file(w->identifier, &sz);
-			if (data) {
-				hit |= grep_buffer(opt, w->name, data, sz);
-				free(data);
-			}
-		} else {
-			assert(0);
-		}
-
+		hit |= grep_source(opt, &w->source);
+		grep_source_clear_data(&w->source);
 		work_done(w);
 	}
 	free_grep_patterns(arg);
@@ -232,24 +195,28 @@ static void start_threads(struct grep_opt *opt)
 	int i;
 
 	pthread_mutex_init(&grep_mutex, NULL);
-	pthread_mutex_init(&read_sha1_mutex, NULL);
+	pthread_mutex_init(&grep_read_mutex, NULL);
+	pthread_mutex_init(&grep_attr_mutex, NULL);
 	pthread_cond_init(&cond_add, NULL);
 	pthread_cond_init(&cond_write, NULL);
 	pthread_cond_init(&cond_result, NULL);
+	grep_use_locks = 1;
 
 	for (i = 0; i < ARRAY_SIZE(todo); i++) {
 		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;
 		compile_grep_patterns(o);
 		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));
 	}
 }
@@ -272,23 +239,25 @@ static int wait_all(void)
 	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(&read_sha1_mutex);
+	pthread_mutex_destroy(&grep_read_mutex);
+	pthread_mutex_destroy(&grep_attr_mutex);
 	pthread_cond_destroy(&cond_add);
 	pthread_cond_destroy(&cond_write);
 	pthread_cond_destroy(&cond_result);
+	grep_use_locks = 0;
 
 	return hit;
 }
 #else /* !NO_PTHREADS */
-#define read_sha1_lock()
-#define read_sha1_unlock()
 
 static int wait_all(void)
 {
@@ -296,264 +265,90 @@ static int wait_all(void)
 }
 #endif
 
-static int grep_config(const char *var, const char *value, void *cb)
+static int grep_cmd_config(const char *var, const char *value, void *cb)
 {
-	struct grep_opt *opt = cb;
-	char *color = NULL;
+	int st = grep_config(var, value, cb);
+	if (git_color_default_config(var, value, cb) < 0)
+		st = -1;
 
-	switch (userdiff_config(var, value)) {
-	case 0: break;
-	case -1: return -1;
-	default: return 0;
+	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);
 	}
 
-	if (!strcmp(var, "color.grep"))
-		opt->color = git_config_colorbool(var, value, -1);
-	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 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;
+	return st;
 }
 
 static void *lock_and_read_sha1_file(const unsigned char *sha1, enum object_type *type, unsigned long *size)
 {
 	void *data;
 
-	if (use_threads) {
-		read_sha1_lock();
-		data = read_sha1_file(sha1, type, size);
-		read_sha1_unlock();
-	} else {
-		data = read_sha1_file(sha1, type, size);
-	}
-	return data;
-}
-
-static void *load_sha1(const unsigned char *sha1, unsigned long *size,
-		       const char *name)
-{
-	enum object_type type;
-	void *data = lock_and_read_sha1_file(sha1, &type, size);
-
-	if (!data)
-		error("'%s': unable to read %s", name, sha1_to_hex(sha1));
-
+	grep_read_lock();
+	data = read_sha1_file(sha1, 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)
+		     const char *filename, int tree_name_len,
+		     const char *path)
 {
 	struct strbuf pathbuf = STRBUF_INIT;
-	char *name;
 
 	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);
 	}
 
-	name = strbuf_detach(&pathbuf, NULL);
-
 #ifndef NO_PTHREADS
-	if (use_threads) {
-		grep_sha1_async(opt, name, sha1);
+	if (num_threads) {
+		add_work(opt, GREP_SOURCE_SHA1, pathbuf.buf, path, sha1);
+		strbuf_release(&pathbuf);
 		return 0;
 	} else
 #endif
 	{
+		struct grep_source gs;
 		int hit;
-		unsigned long sz;
-		void *data = load_sha1(sha1, &sz, name);
-		if (!data)
-			hit = 0;
-		else
-			hit = grep_buffer(opt, name, data, sz);
 
-		free(data);
-		free(name);
-		return hit;
-	}
-}
+		grep_source_init(&gs, GREP_SOURCE_SHA1, pathbuf.buf, path, sha1);
+		strbuf_release(&pathbuf);
+		hit = grep_source(opt, &gs);
 
-static void *load_file(const char *filename, size_t *sz)
-{
-	struct stat st;
-	char *data;
-	int i;
-
-	if (lstat(filename, &st) < 0) {
-	err_ret:
-		if (errno != ENOENT)
-			error("'%s': %s", filename, strerror(errno));
-		return 0;
-	}
-	if (!S_ISREG(st.st_mode))
-		return 0;
-	*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));
-		close(i);
-		free(data);
-		return 0;
+		grep_source_clear(&gs);
+		return hit;
 	}
-	close(i);
-	data[*sz] = 0;
-	return data;
 }
 
 static int grep_file(struct grep_opt *opt, const char *filename)
 {
 	struct strbuf buf = STRBUF_INIT;
-	char *name;
 
 	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);
-	name = strbuf_detach(&buf, NULL);
 
 #ifndef NO_PTHREADS
-	if (use_threads) {
-		grep_file_async(opt, name, filename);
+	if (num_threads) {
+		add_work(opt, GREP_SOURCE_FILE, buf.buf, filename, filename);
+		strbuf_release(&buf);
 		return 0;
 	} else
 #endif
 	{
+		struct grep_source gs;
 		int hit;
-		size_t sz;
-		void *data = load_file(filename, &sz);
-		if (!data)
-			hit = 0;
-		else
-			hit = grep_buffer(opt, name, data, sz);
 
-		free(data);
-		free(name);
+		grep_source_init(&gs, GREP_SOURCE_FILE, buf.buf, filename, filename);
+		strbuf_release(&buf);
+		hit = grep_source(opt, &gs);
+
+		grep_source_clear(&gs);
 		return hit;
 	}
 }
@@ -570,32 +365,30 @@ static void append_path(struct grep_opt *opt, const void *data, size_t 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));
+	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 char **paths, int cached)
+static int grep_cache(struct grep_opt *opt, const struct pathspec *pathspec, int cached)
 {
 	int hit = 0;
 	int nr;
 	read_cache();
 
 	for (nr = 0; nr < active_nr; nr++) {
-		struct cache_entry *ce = active_cache[nr];
-		if (!S_ISREG(ce->ce_mode))
+		const struct cache_entry *ce = active_cache[nr];
+		if (!S_ISREG(ce->ce_mode) || ce_intent_to_add(ce))
 			continue;
-		if (!pathspec_matches(paths, ce->name, opt->max_depth))
+		if (!ce_path_match(ce, pathspec, NULL))
 			continue;
 		/*
 		 * If CE_VALID is on, we assume worktree file and its cache entry
@@ -605,7 +398,7 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
 		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);
+			hit |= grep_sha1(opt, ce->sha1, ce->name, 0, ce->name);
 		}
 		else
 			hit |= grep_file(opt, ce->name);
@@ -622,44 +415,32 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
 	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 check_attr)
 {
-	int len;
 	int hit = 0;
+	enum interesting match = entry_not_interesting;
 	struct name_entry entry;
-	char *down;
-	int tn_len = strlen(tree_name);
-	struct strbuf pathbuf;
+	int old_baselen = base->len;
 
-	strbuf_init(&pathbuf, PATH_MAX + tn_len);
+	while (tree_entry(tree, &entry)) {
+		int te_len = tree_entry_len(&entry);
 
-	if (tn_len) {
-		strbuf_add(&pathbuf, tree_name, tn_len);
-		strbuf_addch(&pathbuf, ':');
-		tn_len = pathbuf.len;
-	}
-	strbuf_addstr(&pathbuf, base);
-	len = pathbuf.len;
+		if (match != all_entries_interesting) {
+			match = tree_entry_interesting(&entry, base, tn_len, pathspec);
+			if (match == all_entries_not_interesting)
+				break;
+			if (match == entry_not_interesting)
+				continue;
+		}
 
-	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);
+		strbuf_add(base, entry.path, te_len);
+
+		if (S_ISREG(entry.mode)) {
+			hit |= grep_sha1(opt, entry.sha1, 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;
@@ -668,42 +449,60 @@ 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,
+					 check_attr);
 			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,
-		       struct object *obj, const char *name)
+static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec,
+		       struct object *obj, const char *name, const char *path)
 {
 	if (obj->type == OBJ_BLOB)
-		return grep_sha1(opt, obj->sha1, name, 0);
+		return grep_sha1(opt, obj->oid.hash, name, 0, path);
 	if (obj->type == OBJ_COMMIT || obj->type == OBJ_TREE) {
 		struct tree_desc tree;
 		void *data;
 		unsigned long size;
-		int hit;
-		data = read_object_with_reference(obj->sha1, tree_type,
+		struct strbuf base;
+		int hit, len;
+
+		grep_read_lock();
+		data = read_object_with_reference(obj->oid.hash, 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);
+		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,
+				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"), typename(obj->type));
 }
 
-static int grep_objects(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;
@@ -713,7 +512,7 @@ static int grep_objects(struct grep_opt *opt, const char **paths,
 	for (i = 0; i < 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)) {
+		if (grep_object(opt, pathspec, real_obj, list->objects[i].name, list->objects[i].path)) {
 			hit = 1;
 			if (opt->status_only)
 				break;
@@ -722,16 +521,22 @@ static int grep_objects(struct grep_opt *opt, const char **paths,
 	return hit;
 }
 
-static int grep_directory(struct grep_opt *opt, const char **paths)
+static int grep_directory(struct grep_opt *opt, const struct pathspec *pathspec,
+			  int exc_std, int use_index)
 {
 	struct dir_struct dir;
 	int i, hit = 0;
 
 	memset(&dir, 0, sizeof(dir));
-	setup_standard_excludes(&dir);
+	if (!use_index)
+		dir.flags |= DIR_NO_GITLINKS;
+	if (exc_std)
+		setup_standard_excludes(&dir);
 
-	fill_directory(&dir, paths);
+	fill_directory(&dir, pathspec);
 	for (i = 0; i < dir.nr; i++) {
+		if (!dir_path_match(dir.entries[i], pathspec, 0, NULL))
+			continue;
 		hit |= grep_file(opt, dir.entries[i]->name);
 		if (hit && opt->status_only)
 			break;
@@ -752,7 +557,7 @@ 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;
@@ -762,25 +567,24 @@ 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);
-	while (strbuf_getline(&sb, patterns, '\n') == 0) {
-		char *s;
-		size_t len;
-
+		die_errno(_("cannot open '%s'"), arg);
+	while (strbuf_getline(&sb, patterns) == 0) {
 		/* ignore empty line like grep does */
 		if (sb.len == 0)
 			continue;
 
-		s = strbuf_detach(&sb, &len);
-		append_grep_pat(grep_opt, s, len, arg, ++lno, GREP_PATTERN);
+		append_grep_pat(grep_opt, sb.buf, sb.len, arg, ++lno,
+				GREP_PATTERN);
 	}
-	fclose(patterns);
+	if (!from_stdin)
+		fclose(patterns);
 	strbuf_release(&sb);
 	return 0;
 }
@@ -821,92 +625,108 @@ static int pattern_callback(const struct option *opt, const char *arg,
 	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;
-	int cached = 0;
+	int cached = 0, untracked = 0, opt_exclude = -1;
 	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 = 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;
+
 	struct option options[] = {
-		OPT_BOOLEAN(0, "cached", &cached,
-			"search in index instead of in the work tree"),
-		OPT_BOOLEAN(0, "index", &use_index,
-			"--no-index finds in contents not managed by git"),
+		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_BOOL(0, "untracked", &untracked,
+			N_("search in both tracked and untracked files")),
+		OPT_SET_INT(0, "exclude-standard", &opt_exclude,
+			    N_("ignore files specified via '.gitignore'"), 1),
 		OPT_GROUP(""),
-		OPT_BOOLEAN('v', "invert-match", &opt.invert,
-			"show non-matching lines"),
-		OPT_BOOLEAN('i', "ignore-case", &opt.ignore_case,
-			"case insensitive matching"),
-		OPT_BOOLEAN('w', "word-regexp", &opt.word_regexp,
-			"match patterns only at word boundaries"),
+		OPT_BOOL('v', "invert-match", &opt.invert,
+			N_("show non-matching lines")),
+		OPT_BOOL('i', "ignore-case", &opt.ignore_case,
+			N_("case insensitive matching")),
+		OPT_BOOL('w', "word-regexp", &opt.word_regexp,
+			N_("match patterns only at word boundaries")),
 		OPT_SET_INT('a', "text", &opt.binary,
-			"process binary files as text", GREP_BINARY_TEXT),
+			N_("process binary files as text"), GREP_BINARY_TEXT),
 		OPT_SET_INT('I', NULL, &opt.binary,
-			"don't match patterns in binary files",
+			N_("don't match patterns in binary files"),
 			GREP_BINARY_NOMATCH),
-		{ OPTION_INTEGER, 0, "max-depth", &opt.max_depth, "depth",
-			"descend at most <depth> levels", PARSE_OPT_NONEG,
+		OPT_BOOL(0, "textconv", &opt.allow_textconv,
+			 N_("process binary files with textconv filters")),
+		{ OPTION_INTEGER, 0, "max-depth", &opt.max_depth, N_("depth"),
+			N_("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_arg,
+			    N_("use extended POSIX regular expressions"),
+			    GREP_PATTERN_TYPE_ERE),
+		OPT_SET_INT('G', "basic-regexp", &pattern_type_arg,
+			    N_("use basic POSIX regular expressions (default)"),
+			    GREP_PATTERN_TYPE_BRE),
+		OPT_SET_INT('F', "fixed-strings", &pattern_type_arg,
+			    N_("interpret patterns as fixed strings"),
+			    GREP_PATTERN_TYPE_FIXED),
+		OPT_SET_INT('P', "perl-regexp", &pattern_type_arg,
+			    N_("use Perl-compatible regular expressions"),
+			    GREP_PATTERN_TYPE_PCRE),
 		OPT_GROUP(""),
-		OPT_BOOLEAN('n', NULL, &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_BOOL('n', "line-number", &opt.linenum, N_("show line numbers")),
+		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,
-			"show filenames relative to top directory", 1),
-		OPT_BOOLEAN('l', "files-with-matches", &opt.name_only,
-			"show only filenames instead of matching lines"),
-		OPT_BOOLEAN(0, "name-only", &opt.name_only,
-			"synonym for --files-with-matches"),
-		OPT_BOOLEAN('L', "files-without-match",
+			N_("show filenames relative to top directory"), 1),
+		OPT_BOOL('l', "files-with-matches", &opt.name_only,
+			N_("show only filenames instead of matching lines")),
+		OPT_BOOL(0, "name-only", &opt.name_only,
+			N_("synonym for --files-with-matches")),
+		OPT_BOOL('L', "files-without-match",
 			&opt.unmatch_name_only,
-			"show only the names of files without match"),
-		OPT_BOOLEAN('z', "null", &opt.null_following_name,
-			"print NUL after filenames"),
-		OPT_BOOLEAN('c', "count", &opt.count,
-			"show the number of matches instead of matching lines"),
-		OPT__COLOR(&opt.color, "highlight matches"),
+			N_("show only the names of files without match")),
+		OPT_BOOL('z', "null", &opt.null_following_name,
+			N_("print NUL after filenames")),
+		OPT_BOOL('c', "count", &opt.count,
+			N_("show the number of matches instead of matching lines")),
+		OPT__COLOR(&opt.color, N_("highlight matches")),
+		OPT_BOOL(0, "break", &opt.file_break,
+			N_("print empty line between matches from different files")),
+		OPT_BOOL(0, "heading", &opt.heading,
+			N_("show filename only once above matches from same file")),
 		OPT_GROUP(""),
-		OPT_CALLBACK('C', NULL, &opt, "n",
-			"show <n> context lines before and after matches",
+		OPT_CALLBACK('C', "context", &opt, N_("n"),
+			N_("show <n> context lines before and after matches"),
 			context_callback),
-		OPT_INTEGER('B', NULL, &opt.pre_context,
-			"show <n> context lines before matches"),
-		OPT_INTEGER('A', NULL, &opt.post_context,
-			"show <n> context lines after matches"),
-		OPT_NUMBER_CALLBACK(&opt, "shortcut for -C NUM",
+		OPT_INTEGER('B', "before-context", &opt.pre_context,
+			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,
-			"show a line with the function name before matches"),
+		OPT_BOOL('p', "show-function", &opt.funcname,
+			N_("show a line with the function name before matches")),
+		OPT_BOOL('W', "function-context", &opt.funcbody,
+			N_("show the surrounding function")),
 		OPT_GROUP(""),
-		OPT_CALLBACK('f', NULL, &opt, "file",
-			"read patterns from file", file_callback),
-		{ OPTION_CALLBACK, 'e', NULL, &opt, "pattern",
-			"match <pattern>", PARSE_OPT_NONEG, pattern_callback },
+		OPT_CALLBACK('f', NULL, &opt, N_("file"),
+			N_("read patterns from file"), file_callback),
+		{ OPTION_CALLBACK, 'e', NULL, &opt, N_("pattern"),
+			N_("match <pattern>"), PARSE_OPT_NONEG, pattern_callback },
 		{ OPTION_CALLBACK, 0, "and", &opt, NULL,
-		  "combine patterns specified with -e",
+		  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, "",
@@ -915,49 +735,25 @@ 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_BOOLEAN(0, "all-match", &opt.all_match,
-			"show only matches from files that match all patterns"),
+		OPT__QUIET(&opt.status_only,
+			   N_("indicate hit with exit status without output")),
+		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_GROUP(""),
 		{ OPTION_STRING, 'O', "open-files-in-pager", &show_in_pager,
-			"pager", "show matching files in the 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,
-			    "allow calling of grep(1) (ignored by this build)"),
-		{ OPTION_CALLBACK, 0, "help-all", &options, NULL, "show usage",
-		  PARSE_OPT_HIDDEN | PARSE_OPT_NOARG, help_callback },
+		OPT_BOOL(0, "ext-grep", &external_grep_allowed__ignored,
+			 N_("allow calling of grep(1) (ignored by this build)")),
 		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;
-
-	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);
-	if (opt.color == -1)
-		opt.color = git_use_color_default;
+	init_grep_defaults();
+	git_config(grep_cmd_config, NULL);
+	grep_init(&opt, prefix);
 
 	/*
 	 * If there is no -- then the paths must exist in the working
@@ -971,12 +767,18 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	 */
 	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 (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();
+	}
 
 	/*
 	 * skip a -- separator; we know it cannot be
@@ -1005,28 +807,12 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		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))
-		use_threads = 0;
-
-	if (use_threads) {
-		if (opt.pre_context || opt.post_context)
-			print_hunk_marks_between_files = 1;
-		start_threads(&opt);
-	}
-#else
-	use_threads = 0;
-#endif
 
 	compile_grep_patterns(&opt);
 
@@ -1034,12 +820,13 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	for (i = 0; i < argc; i++) {
 		const char *arg = argv[i];
 		unsigned char sha1[20];
+		struct object_context oc;
 		/* 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);
+		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;
 		}
 		if (!strcmp(arg, "--")) {
@@ -1049,23 +836,43 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		break;
 	}
 
+#ifndef NO_PTHREADS
+	if (list.nr || cached || show_in_pager)
+		num_threads = 0;
+	else if (num_threads == 0)
+		num_threads = GREP_NUM_THREADS_DEFAULT;
+	else if (num_threads < 0)
+		die(_("invalid number of threads specified (%d)"), num_threads);
+#else
+	num_threads = 0;
+#endif
+
+#ifndef NO_PTHREADS
+	if (num_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);
+	}
+#endif
+
 	/* The rest are paths */
 	if (!seen_dashdash) {
 		int j;
 		for (j = i; j < argc; j++)
-			verify_filename(prefix, argv[j]);
+			verify_filename(prefix, argv[j], j == i);
 	}
 
-	if (i < argc)
-		paths = get_pathspec(prefix, argv + i);
-	else if (prefix) {
-		paths = xcalloc(2, sizeof(const char *));
-		paths[0] = prefix;
-		paths[1] = NULL;
-	}
+	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");
+		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;
@@ -1074,6 +881,9 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		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",
@@ -1084,28 +894,31 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-	if (!show_in_pager)
+	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 (!use_index) {
-		if (cached)
-			die("--cached 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 cannot be used with revs.");
-		hit = grep_directory(&opt, paths);
+			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."));
 	} else if (!list.nr) {
 		if (!cached)
 			setup_work_tree();
 
-		hit = grep_cache(&opt, paths, cached);
+		hit = grep_cache(&opt, &pathspec, cached);
 	} else {
 		if (cached)
-			die("both --cached and trees are given.");
-		hit = grep_objects(&opt, paths, &list);
+			die(_("both --cached and trees are given."));
+		hit = grep_objects(&opt, &pathspec, &list);
 	}
 
-	if (use_threads)
+	if (num_threads)
 		hit |= wait_all();
 	if (hit && show_in_pager)
 		run_pager(&opt, prefix);