1 files changed, 438 insertions, 249 deletions

diff --git a/builtin/ls-files.c b/builtin/ls-files.c
index b5434af0c8..29a26ad8ae 100644
--- a/builtin/ls-files.c
+++ b/builtin/ls-files.c
@@ -6,13 +6,20 @@
  * Copyright (C) Linus Torvalds, 2005
  */
 #include "cache.h"
+#include "repository.h"
+#include "config.h"
 #include "quote.h"
 #include "dir.h"
 #include "builtin.h"
 #include "tree.h"
+#include "cache-tree.h"
 #include "parse-options.h"
 #include "resolve-undo.h"
 #include "string-list.h"
+#include "pathspec.h"
+#include "run-command.h"
+#include "submodule.h"
+#include "submodule-config.h"
 
 static int abbrev;
 static int show_deleted;
@@ -24,17 +31,22 @@ static int show_resolve_undo;
 static int show_modified;
 static int show_killed;
 static int show_valid_bit;
+static int show_fsmonitor_bit;
 static int line_terminator = '\n';
 static int debug_mode;
+static int show_eol;
+static int recurse_submodules;
+static int skipping_duplicates;
 
 static const char *prefix;
 static int max_prefix_len;
 static int prefix_len;
-static const char **pathspec;
+static struct pathspec pathspec;
 static int error_unmatch;
 static char *ps_matched;
 static const char *with_tree;
 static int exc_given;
+static int exclude_args;
 
 static const char *tag_cached = "";
 static const char *tag_unmerged = "";
@@ -45,39 +57,103 @@ static const char *tag_modified = "";
 static const char *tag_skip_worktree = "";
 static const char *tag_resolve_undo = "";
 
-static void write_name(const char* name, size_t len)
+static void write_eolinfo(struct index_state *istate,
+			  const struct cache_entry *ce, const char *path)
 {
-	write_name_quoted_relative(name, len, prefix, prefix_len, stdout,
-			line_terminator);
+	if (show_eol) {
+		struct stat st;
+		const char *i_txt = "";
+		const char *w_txt = "";
+		const char *a_txt = get_convert_attr_ascii(istate, path);
+		if (ce && S_ISREG(ce->ce_mode))
+			i_txt = get_cached_convert_stats_ascii(istate,
+							       ce->name);
+		if (!lstat(path, &st) && S_ISREG(st.st_mode))
+			w_txt = get_wt_convert_stats_ascii(path);
+		printf("i/%-5s w/%-5s attr/%-17s\t", i_txt, w_txt, a_txt);
+	}
+}
+
+static void write_name(const char *name)
+{
+	/*
+	 * With "--full-name", prefix_len=0; this caller needs to pass
+	 * an empty string in that case (a NULL is good for "").
+	 */
+	write_name_quoted_relative(name, prefix_len ? prefix : NULL,
+				   stdout, line_terminator);
+}
+
+static const char *get_tag(const struct cache_entry *ce, const char *tag)
+{
+	static char alttag[4];
+
+	if (tag && *tag && ((show_valid_bit && (ce->ce_flags & CE_VALID)) ||
+		(show_fsmonitor_bit && (ce->ce_flags & CE_FSMONITOR_VALID)))) {
+		memcpy(alttag, tag, 3);
+
+		if (isalpha(tag[0])) {
+			alttag[0] = tolower(tag[0]);
+		} else if (tag[0] == '?') {
+			alttag[0] = '!';
+		} else {
+			alttag[0] = 'v';
+			alttag[1] = tag[0];
+			alttag[2] = ' ';
+			alttag[3] = 0;
+		}
+
+		tag = alttag;
+	}
+
+	return tag;
 }
 
-static void show_dir_entry(const char *tag, struct dir_entry *ent)
+static void print_debug(const struct cache_entry *ce)
+{
+	if (debug_mode) {
+		const struct stat_data *sd = &ce->ce_stat_data;
+
+		printf("  ctime: %u:%u\n", sd->sd_ctime.sec, sd->sd_ctime.nsec);
+		printf("  mtime: %u:%u\n", sd->sd_mtime.sec, sd->sd_mtime.nsec);
+		printf("  dev: %u\tino: %u\n", sd->sd_dev, sd->sd_ino);
+		printf("  uid: %u\tgid: %u\n", sd->sd_uid, sd->sd_gid);
+		printf("  size: %u\tflags: %x\n", sd->sd_size, ce->ce_flags);
+	}
+}
+
+static void show_dir_entry(struct index_state *istate,
+			   const char *tag, struct dir_entry *ent)
 {
 	int len = max_prefix_len;
 
-	if (len >= ent->len)
+	if (len > ent->len)
 		die("git ls-files: internal error - directory entry not superset of prefix");
 
-	if (!match_pathspec(pathspec, ent->name, ent->len, len, ps_matched))
-		return;
+	/* If ps_matches is non-NULL, figure out which pathspec(s) match. */
+	if (ps_matched)
+		dir_path_match(istate, ent, &pathspec, len, ps_matched);
 
 	fputs(tag, stdout);
-	write_name(ent->name, ent->len);
+	write_eolinfo(istate, NULL, ent->name);
+	write_name(ent->name);
 }
 
-static void show_other_files(struct dir_struct *dir)
+static void show_other_files(struct index_state *istate,
+			     const struct dir_struct *dir)
 {
 	int i;
 
 	for (i = 0; i < dir->nr; i++) {
 		struct dir_entry *ent = dir->entries[i];
-		if (!cache_name_is_other(ent->name, ent->len))
+		if (!index_name_is_other(istate, ent->name, ent->len))
 			continue;
-		show_dir_entry(tag_other, ent);
+		show_dir_entry(istate, tag_other, ent);
 	}
 }
 
-static void show_killed_files(struct dir_struct *dir)
+static void show_killed_files(struct index_state *istate,
+			      const struct dir_struct *dir)
 {
 	int i;
 	for (i = 0; i < dir->nr; i++) {
@@ -91,28 +167,29 @@ static void show_killed_files(struct dir_struct *dir)
 				/* If ent->name is prefix of an entry in the
 				 * cache, it will be killed.
 				 */
-				pos = cache_name_pos(ent->name, ent->len);
+				pos = index_name_pos(istate, ent->name, ent->len);
 				if (0 <= pos)
-					die("bug in show-killed-files");
+					BUG("killed-file %.*s not found",
+						ent->len, ent->name);
 				pos = -pos - 1;
-				while (pos < active_nr &&
-				       ce_stage(active_cache[pos]))
+				while (pos < istate->cache_nr &&
+				       ce_stage(istate->cache[pos]))
 					pos++; /* skip unmerged */
-				if (active_nr <= pos)
+				if (istate->cache_nr <= pos)
 					break;
 				/* pos points at a name immediately after
 				 * ent->name in the cache.  Does it expect
 				 * ent->name to be a directory?
 				 */
-				len = ce_namelen(active_cache[pos]);
+				len = ce_namelen(istate->cache[pos]);
 				if ((ent->len < len) &&
-				    !strncmp(active_cache[pos]->name,
+				    !strncmp(istate->cache[pos]->name,
 					     ent->name, ent->len) &&
-				    active_cache[pos]->name[ent->len] == '/')
+				    istate->cache[pos]->name[ent->len] == '/')
 					killed = 1;
 				break;
 			}
-			if (0 <= cache_name_pos(ent->name, sp - ent->name)) {
+			if (0 <= index_name_pos(istate, ent->name, sp - ent->name)) {
 				/* If any of the leading directories in
 				 * ent->name is registered in the cache,
 				 * ent->name will be killed.
@@ -122,64 +199,69 @@ static void show_killed_files(struct dir_struct *dir)
 			}
 		}
 		if (killed)
-			show_dir_entry(tag_killed, dir->entries[i]);
+			show_dir_entry(istate, tag_killed, dir->entries[i]);
 	}
 }
 
-static void show_ce_entry(const char *tag, struct cache_entry *ce)
-{
-	int len = max_prefix_len;
+static void show_files(struct repository *repo, struct dir_struct *dir);
 
-	if (len >= ce_namelen(ce))
-		die("git ls-files: internal error - cache entry not superset of prefix");
+static void show_submodule(struct repository *superproject,
+			   struct dir_struct *dir, const char *path)
+{
+	struct repository subrepo;
+	const struct submodule *sub = submodule_from_path(superproject,
+							  null_oid(), path);
 
-	if (!match_pathspec(pathspec, ce->name, ce_namelen(ce), len, ps_matched))
+	if (repo_submodule_init(&subrepo, superproject, sub))
 		return;
 
-	if (tag && *tag && show_valid_bit &&
-	    (ce->ce_flags & CE_VALID)) {
-		static char alttag[4];
-		memcpy(alttag, tag, 3);
-		if (isalpha(tag[0]))
-			alttag[0] = tolower(tag[0]);
-		else if (tag[0] == '?')
-			alttag[0] = '!';
-		else {
-			alttag[0] = 'v';
-			alttag[1] = tag[0];
-			alttag[2] = ' ';
-			alttag[3] = 0;
-		}
-		tag = alttag;
-	}
+	if (repo_read_index(&subrepo) < 0)
+		die("index file corrupt");
 
-	if (!show_stage) {
-		fputs(tag, stdout);
-	} else {
-		printf("%s%06o %s %d\t",
-		       tag,
-		       ce->ce_mode,
-		       find_unique_abbrev(ce->sha1,abbrev),
-		       ce_stage(ce));
-	}
-	write_name(ce->name, ce_namelen(ce));
-	if (debug_mode) {
-		printf("  ctime: %d:%d\n", ce->ce_ctime.sec, ce->ce_ctime.nsec);
-		printf("  mtime: %d:%d\n", ce->ce_mtime.sec, ce->ce_mtime.nsec);
-		printf("  dev: %d\tino: %d\n", ce->ce_dev, ce->ce_ino);
-		printf("  uid: %d\tgid: %d\n", ce->ce_uid, ce->ce_gid);
-		printf("  size: %d\tflags: %x\n", ce->ce_size, ce->ce_flags);
+	show_files(&subrepo, dir);
+
+	repo_clear(&subrepo);
+}
+
+static void show_ce(struct repository *repo, struct dir_struct *dir,
+		    const struct cache_entry *ce, const char *fullname,
+		    const char *tag)
+{
+	if (max_prefix_len > strlen(fullname))
+		die("git ls-files: internal error - cache entry not superset of prefix");
+
+	if (recurse_submodules && S_ISGITLINK(ce->ce_mode) &&
+	    is_submodule_active(repo, ce->name)) {
+		show_submodule(repo, dir, ce->name);
+	} else if (match_pathspec(repo->index, &pathspec, fullname, strlen(fullname),
+				  max_prefix_len, ps_matched,
+				  S_ISDIR(ce->ce_mode) ||
+				  S_ISGITLINK(ce->ce_mode))) {
+		tag = get_tag(ce, tag);
+
+		if (!show_stage) {
+			fputs(tag, stdout);
+		} else {
+			printf("%s%06o %s %d\t",
+			       tag,
+			       ce->ce_mode,
+			       find_unique_abbrev(&ce->oid, abbrev),
+			       ce_stage(ce));
+		}
+		write_eolinfo(repo->index, ce, fullname);
+		write_name(fullname);
+		print_debug(ce);
 	}
 }
 
-static void show_ru_info(void)
+static void show_ru_info(struct index_state *istate)
 {
 	struct string_list_item *item;
 
-	if (!the_index.resolve_undo)
+	if (!istate->resolve_undo)
 		return;
 
-	for_each_string_list_item(item, the_index.resolve_undo) {
+	for_each_string_list_item(item, istate->resolve_undo) {
 		const char *path = item->string;
 		struct resolve_undo_info *ui = item->util;
 		int i, len;
@@ -187,119 +269,205 @@ static void show_ru_info(void)
 		len = strlen(path);
 		if (len < max_prefix_len)
 			continue; /* outside of the prefix */
-		if (!match_pathspec(pathspec, path, len, max_prefix_len, ps_matched))
+		if (!match_pathspec(istate, &pathspec, path, len,
+				    max_prefix_len, ps_matched, 0))
 			continue; /* uninterested */
 		for (i = 0; i < 3; i++) {
 			if (!ui->mode[i])
 				continue;
 			printf("%s%06o %s %d\t", tag_resolve_undo, ui->mode[i],
-			       find_unique_abbrev(ui->sha1[i], abbrev),
+			       find_unique_abbrev(&ui->oid[i], abbrev),
 			       i + 1);
-			write_name(path, len);
+			write_name(path);
 		}
 	}
 }
 
-static int ce_excluded(struct path_exclude_check *check, struct cache_entry *ce)
+static int ce_excluded(struct dir_struct *dir, struct index_state *istate,
+		       const char *fullname, const struct cache_entry *ce)
 {
 	int dtype = ce_to_dtype(ce);
-	return path_excluded(check, ce->name, ce_namelen(ce), &dtype);
+	return is_excluded(dir, istate, fullname, &dtype);
 }
 
-static void show_files(struct dir_struct *dir)
+static void construct_fullname(struct strbuf *out, const struct repository *repo,
+			       const struct cache_entry *ce)
 {
-	int i;
-	struct path_exclude_check check;
+	strbuf_reset(out);
+	if (repo->submodule_prefix)
+		strbuf_addstr(out, repo->submodule_prefix);
+	strbuf_addstr(out, ce->name);
+}
 
-	if ((dir->flags & DIR_SHOW_IGNORED))
-		path_exclude_check_init(&check, dir);
+static void show_files(struct repository *repo, struct dir_struct *dir)
+{
+	int i;
+	struct strbuf fullname = STRBUF_INIT;
 
 	/* For cached/deleted files we don't need to even do the readdir */
 	if (show_others || show_killed) {
-		fill_directory(dir, pathspec);
+		if (!show_others)
+			dir->flags |= DIR_COLLECT_KILLED_ONLY;
+		fill_directory(dir, repo->index, &pathspec);
 		if (show_others)
-			show_other_files(dir);
+			show_other_files(repo->index, dir);
 		if (show_killed)
-			show_killed_files(dir);
+			show_killed_files(repo->index, dir);
 	}
-	if (show_cached | show_stage) {
-		for (i = 0; i < active_nr; i++) {
-			struct cache_entry *ce = active_cache[i];
-			if ((dir->flags & DIR_SHOW_IGNORED) &&
-			    !ce_excluded(&check, ce))
-				continue;
-			if (show_unmerged && !ce_stage(ce))
-				continue;
-			if (ce->ce_flags & CE_UPDATE)
-				continue;
-			show_ce_entry(ce_stage(ce) ? tag_unmerged :
-				(ce_skip_worktree(ce) ? tag_skip_worktree : tag_cached), ce);
+
+	if (!(show_cached || show_stage || show_deleted || show_modified))
+		return;
+	/* TODO: audit for interaction with sparse-index. */
+	ensure_full_index(repo->index);
+	for (i = 0; i < repo->index->cache_nr; i++) {
+		const struct cache_entry *ce = repo->index->cache[i];
+		struct stat st;
+		int stat_err;
+
+		construct_fullname(&fullname, repo, ce);
+
+		if ((dir->flags & DIR_SHOW_IGNORED) &&
+			!ce_excluded(dir, repo->index, fullname.buf, ce))
+			continue;
+		if (ce->ce_flags & CE_UPDATE)
+			continue;
+		if ((show_cached || show_stage) &&
+		    (!show_unmerged || ce_stage(ce))) {
+			show_ce(repo, dir, ce, fullname.buf,
+				ce_stage(ce) ? tag_unmerged :
+				(ce_skip_worktree(ce) ? tag_skip_worktree :
+				 tag_cached));
+			if (skipping_duplicates)
+				goto skip_to_next_name;
 		}
-	}
-	if (show_deleted | show_modified) {
-		for (i = 0; i < active_nr; i++) {
-			struct cache_entry *ce = active_cache[i];
-			struct stat st;
-			int err;
-			if ((dir->flags & DIR_SHOW_IGNORED) &&
-			    !ce_excluded(&check, ce))
-				continue;
-			if (ce->ce_flags & CE_UPDATE)
-				continue;
-			if (ce_skip_worktree(ce))
-				continue;
-			err = lstat(ce->name, &st);
-			if (show_deleted && err)
-				show_ce_entry(tag_removed, ce);
-			if (show_modified && ce_modified(ce, &st, 0))
-				show_ce_entry(tag_modified, ce);
+
+		if (!(show_deleted || show_modified))
+			continue;
+		if (ce_skip_worktree(ce))
+			continue;
+		stat_err = lstat(fullname.buf, &st);
+		if (stat_err && (errno != ENOENT && errno != ENOTDIR))
+			error_errno("cannot lstat '%s'", fullname.buf);
+		if (stat_err && show_deleted) {
+			show_ce(repo, dir, ce, fullname.buf, tag_removed);
+			if (skipping_duplicates)
+				goto skip_to_next_name;
+		}
+		if (show_modified &&
+		    (stat_err || ie_modified(repo->index, ce, &st, 0))) {
+			show_ce(repo, dir, ce, fullname.buf, tag_modified);
+			if (skipping_duplicates)
+				goto skip_to_next_name;
+		}
+		continue;
+
+skip_to_next_name:
+		{
+			int j;
+			struct cache_entry **cache = repo->index->cache;
+			for (j = i + 1; j < repo->index->cache_nr; j++)
+				if (strcmp(ce->name, cache[j]->name))
+					break;
+			i = j - 1; /* compensate for the for loop */
 		}
 	}
 
-	if ((dir->flags & DIR_SHOW_IGNORED))
-		path_exclude_check_clear(&check);
+	strbuf_release(&fullname);
 }
 
 /*
  * Prune the index to only contain stuff starting with "prefix"
  */
-static void prune_cache(const char *prefix)
+static void prune_index(struct index_state *istate,
+			const char *prefix, size_t prefixlen)
 {
-	int pos = cache_name_pos(prefix, max_prefix_len);
+	int pos;
 	unsigned int first, last;
 
+	if (!prefix || !istate->cache_nr)
+		return;
+	pos = index_name_pos(istate, prefix, prefixlen);
 	if (pos < 0)
 		pos = -pos-1;
-	memmove(active_cache, active_cache + pos,
-		(active_nr - pos) * sizeof(struct cache_entry *));
-	active_nr -= pos;
-	first = 0;
-	last = active_nr;
+	first = pos;
+	last = istate->cache_nr;
 	while (last > first) {
-		int next = (last + first) >> 1;
-		struct cache_entry *ce = active_cache[next];
-		if (!strncmp(ce->name, prefix, max_prefix_len)) {
+		int next = first + ((last - first) >> 1);
+		const struct cache_entry *ce = istate->cache[next];
+		if (!strncmp(ce->name, prefix, prefixlen)) {
 			first = next+1;
 			continue;
 		}
 		last = next;
 	}
-	active_nr = last;
+	MOVE_ARRAY(istate->cache, istate->cache + pos, last - pos);
+	istate->cache_nr = last - pos;
 }
 
-static void strip_trailing_slash_from_submodules(void)
+static int get_common_prefix_len(const char *common_prefix)
 {
-	const char **p;
+	int common_prefix_len;
 
-	for (p = pathspec; *p != NULL; p++) {
-		int len = strlen(*p), pos;
+	if (!common_prefix)
+		return 0;
 
-		if (len < 1 || (*p)[len - 1] != '/')
-			continue;
-		pos = cache_name_pos(*p, len - 1);
-		if (pos >= 0 && S_ISGITLINK(active_cache[pos]->ce_mode))
-			*p = xstrndup(*p, len - 1);
-	}
+	common_prefix_len = strlen(common_prefix);
+
+	/*
+	 * If the prefix has a trailing slash, strip it so that submodules wont
+	 * be pruned from the index.
+	 */
+	if (common_prefix[common_prefix_len - 1] == '/')
+		common_prefix_len--;
+
+	return common_prefix_len;
+}
+
+static int read_one_entry_opt(struct index_state *istate,
+			      const struct object_id *oid,
+			      struct strbuf *base,
+			      const char *pathname,
+			      unsigned mode, int opt)
+{
+	int len;
+	struct cache_entry *ce;
+
+	if (S_ISDIR(mode))
+		return READ_TREE_RECURSIVE;
+
+	len = strlen(pathname);
+	ce = make_empty_cache_entry(istate, base->len + len);
+
+	ce->ce_mode = create_ce_mode(mode);
+	ce->ce_flags = create_ce_flags(1);
+	ce->ce_namelen = base->len + len;
+	memcpy(ce->name, base->buf, base->len);
+	memcpy(ce->name + base->len, pathname, len+1);
+	oidcpy(&ce->oid, oid);
+	return add_index_entry(istate, ce, opt);
+}
+
+static int read_one_entry(const struct object_id *oid, struct strbuf *base,
+			  const char *pathname, unsigned mode,
+			  void *context)
+{
+	struct index_state *istate = context;
+	return read_one_entry_opt(istate, oid, base, pathname,
+				  mode,
+				  ADD_CACHE_OK_TO_ADD|ADD_CACHE_SKIP_DFCHECK);
+}
+
+/*
+ * This is used when the caller knows there is no existing entries at
+ * the stage that will conflict with the entry being added.
+ */
+static int read_one_entry_quick(const struct object_id *oid, struct strbuf *base,
+				const char *pathname, unsigned mode,
+				void *context)
+{
+	struct index_state *istate = context;
+	return read_one_entry_opt(istate, oid, base, pathname,
+				  mode, ADD_CACHE_JUST_APPEND);
 }
 
 /*
@@ -310,41 +478,68 @@ static void strip_trailing_slash_from_submodules(void)
  * that were given from the command line.  We are not
  * going to write this index out.
  */
-void overlay_tree_on_cache(const char *tree_name, const char *prefix)
+void overlay_tree_on_index(struct index_state *istate,
+			   const char *tree_name, const char *prefix)
 {
 	struct tree *tree;
-	unsigned char sha1[20];
+	struct object_id oid;
 	struct pathspec pathspec;
 	struct cache_entry *last_stage0 = NULL;
 	int i;
+	read_tree_fn_t fn = NULL;
+	int err;
 
-	if (get_sha1(tree_name, sha1))
+	if (get_oid(tree_name, &oid))
 		die("tree-ish %s not found.", tree_name);
-	tree = parse_tree_indirect(sha1);
+	tree = parse_tree_indirect(&oid);
 	if (!tree)
 		die("bad tree-ish %s", tree_name);
 
 	/* Hoist the unmerged entries up to stage #3 to make room */
-	for (i = 0; i < active_nr; i++) {
-		struct cache_entry *ce = active_cache[i];
+	/* TODO: audit for interaction with sparse-index. */
+	ensure_full_index(istate);
+	for (i = 0; i < istate->cache_nr; i++) {
+		struct cache_entry *ce = istate->cache[i];
 		if (!ce_stage(ce))
 			continue;
 		ce->ce_flags |= CE_STAGEMASK;
 	}
 
 	if (prefix) {
-		static const char *(matchbuf[2]);
-		matchbuf[0] = prefix;
-		matchbuf[1] = NULL;
-		init_pathspec(&pathspec, matchbuf);
-		pathspec.items[0].use_wildcard = 0;
+		static const char *(matchbuf[1]);
+		matchbuf[0] = NULL;
+		parse_pathspec(&pathspec, PATHSPEC_ALL_MAGIC,
+			       PATHSPEC_PREFER_CWD, prefix, matchbuf);
 	} else
-		init_pathspec(&pathspec, NULL);
-	if (read_tree(tree, 1, &pathspec))
+		memset(&pathspec, 0, sizeof(pathspec));
+
+	/*
+	 * See if we have cache entry at the stage.  If so,
+	 * do it the original slow way, otherwise, append and then
+	 * sort at the end.
+	 */
+	for (i = 0; !fn && i < istate->cache_nr; i++) {
+		const struct cache_entry *ce = istate->cache[i];
+		if (ce_stage(ce) == 1)
+			fn = read_one_entry;
+	}
+
+	if (!fn)
+		fn = read_one_entry_quick;
+	err = read_tree(the_repository, tree, &pathspec, fn, istate);
+	if (err)
 		die("unable to read tree entries %s", tree_name);
 
-	for (i = 0; i < active_nr; i++) {
-		struct cache_entry *ce = active_cache[i];
+	/*
+	 * Sort the cache entry -- we need to nuke the cache tree, though.
+	 */
+	if (fn == read_one_entry_quick) {
+		cache_tree_free(&istate->cache_tree);
+		QSORT(istate->cache, istate->cache_nr, cmp_cache_name_compare);
+	}
+
+	for (i = 0; i < istate->cache_nr; i++) {
+		struct cache_entry *ce = istate->cache[i];
 		switch (ce_stage(ce)) {
 		case 0:
 			last_stage0 = ce;
@@ -364,66 +559,20 @@ void overlay_tree_on_cache(const char *tree_name, const char *prefix)
 	}
 }
 
-int report_path_error(const char *ps_matched, const char **pathspec, const char *prefix)
-{
-	/*
-	 * Make sure all pathspec matched; otherwise it is an error.
-	 */
-	struct strbuf sb = STRBUF_INIT;
-	const char *name;
-	int num, errors = 0;
-	for (num = 0; pathspec[num]; num++) {
-		int other, found_dup;
-
-		if (ps_matched[num])
-			continue;
-		/*
-		 * The caller might have fed identical pathspec
-		 * twice.  Do not barf on such a mistake.
-		 */
-		for (found_dup = other = 0;
-		     !found_dup && pathspec[other];
-		     other++) {
-			if (other == num || !ps_matched[other])
-				continue;
-			if (!strcmp(pathspec[other], pathspec[num]))
-				/*
-				 * Ok, we have a match already.
-				 */
-				found_dup = 1;
-		}
-		if (found_dup)
-			continue;
-
-		name = quote_path_relative(pathspec[num], -1, &sb, prefix);
-		error("pathspec '%s' did not match any file(s) known to git.",
-		      name);
-		errors++;
-	}
-	strbuf_release(&sb);
-	return errors;
-}
-
 static const char * const ls_files_usage[] = {
-	N_("git ls-files [options] [<file>...]"),
+	N_("git ls-files [<options>] [<file>...]"),
 	NULL
 };
 
-static int option_parse_z(const struct option *opt,
-			  const char *arg, int unset)
-{
-	line_terminator = unset ? '\n' : '\0';
-
-	return 0;
-}
-
 static int option_parse_exclude(const struct option *opt,
 				const char *arg, int unset)
 {
-	struct exclude_list *list = opt->value;
+	struct string_list *exclude_list = opt->value;
+
+	BUG_ON_OPT_NEG(unset);
 
 	exc_given = 1;
-	add_exclude(arg, "", 0, list);
+	string_list_append(exclude_list, arg);
 
 	return 0;
 }
@@ -433,8 +582,10 @@ static int option_parse_exclude_from(const struct option *opt,
 {
 	struct dir_struct *dir = opt->value;
 
+	BUG_ON_OPT_NEG(unset);
+
 	exc_given = 1;
-	add_excludes_from_file(dir, arg);
+	add_patterns_from_file(dir, arg);
 
 	return 0;
 }
@@ -444,6 +595,9 @@ static int option_parse_exclude_standard(const struct option *opt,
 {
 	struct dir_struct *dir = opt->value;
 
+	BUG_ON_OPT_NEG(unset);
+	BUG_ON_OPT_ARG(arg);
+
 	exc_given = 1;
 	setup_standard_excludes(dir);
 
@@ -452,80 +606,93 @@ static int option_parse_exclude_standard(const struct option *opt,
 
 int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 {
-	int require_work_tree = 0, show_tag = 0;
-	const char *max_prefix;
-	struct dir_struct dir;
+	int require_work_tree = 0, show_tag = 0, i;
+	char *max_prefix;
+	struct dir_struct dir = DIR_INIT;
+	struct pattern_list *pl;
+	struct string_list exclude_list = STRING_LIST_INIT_NODUP;
 	struct option builtin_ls_files_options[] = {
-		{ OPTION_CALLBACK, 'z', NULL, NULL, NULL,
-			N_("paths are separated with NUL character"),
-			PARSE_OPT_NOARG, option_parse_z },
-		OPT_BOOLEAN('t', NULL, &show_tag,
+		/* Think twice before adding "--nul" synonym to this */
+		OPT_SET_INT('z', NULL, &line_terminator,
+			N_("paths are separated with NUL character"), '\0'),
+		OPT_BOOL('t', NULL, &show_tag,
 			N_("identify the file status with tags")),
-		OPT_BOOLEAN('v', NULL, &show_valid_bit,
+		OPT_BOOL('v', NULL, &show_valid_bit,
 			N_("use lowercase letters for 'assume unchanged' files")),
-		OPT_BOOLEAN('c', "cached", &show_cached,
+		OPT_BOOL('f', NULL, &show_fsmonitor_bit,
+			N_("use lowercase letters for 'fsmonitor clean' files")),
+		OPT_BOOL('c', "cached", &show_cached,
 			N_("show cached files in the output (default)")),
-		OPT_BOOLEAN('d', "deleted", &show_deleted,
+		OPT_BOOL('d', "deleted", &show_deleted,
 			N_("show deleted files in the output")),
-		OPT_BOOLEAN('m', "modified", &show_modified,
+		OPT_BOOL('m', "modified", &show_modified,
 			N_("show modified files in the output")),
-		OPT_BOOLEAN('o', "others", &show_others,
+		OPT_BOOL('o', "others", &show_others,
 			N_("show other files in the output")),
 		OPT_BIT('i', "ignored", &dir.flags,
 			N_("show ignored files in the output"),
 			DIR_SHOW_IGNORED),
-		OPT_BOOLEAN('s', "stage", &show_stage,
+		OPT_BOOL('s', "stage", &show_stage,
 			N_("show staged contents' object name in the output")),
-		OPT_BOOLEAN('k', "killed", &show_killed,
+		OPT_BOOL('k', "killed", &show_killed,
 			N_("show files on the filesystem that need to be removed")),
 		OPT_BIT(0, "directory", &dir.flags,
-			N_("show 'other' directories' name only"),
+			N_("show 'other' directories' names only"),
 			DIR_SHOW_OTHER_DIRECTORIES),
+		OPT_BOOL(0, "eol", &show_eol, N_("show line endings of files")),
 		OPT_NEGBIT(0, "empty-directory", &dir.flags,
 			N_("don't show empty directories"),
 			DIR_HIDE_EMPTY_DIRECTORIES),
-		OPT_BOOLEAN('u', "unmerged", &show_unmerged,
+		OPT_BOOL('u', "unmerged", &show_unmerged,
 			N_("show unmerged files in the output")),
-		OPT_BOOLEAN(0, "resolve-undo", &show_resolve_undo,
+		OPT_BOOL(0, "resolve-undo", &show_resolve_undo,
 			    N_("show resolve-undo information")),
-		{ OPTION_CALLBACK, 'x', "exclude", &dir.exclude_list[EXC_CMDL], N_("pattern"),
+		OPT_CALLBACK_F('x', "exclude", &exclude_list, N_("pattern"),
 			N_("skip files matching pattern"),
-			0, option_parse_exclude },
-		{ OPTION_CALLBACK, 'X', "exclude-from", &dir, N_("file"),
+			PARSE_OPT_NONEG, option_parse_exclude),
+		OPT_CALLBACK_F('X', "exclude-from", &dir, N_("file"),
 			N_("exclude patterns are read from <file>"),
-			0, option_parse_exclude_from },
+			PARSE_OPT_NONEG, option_parse_exclude_from),
 		OPT_STRING(0, "exclude-per-directory", &dir.exclude_per_dir, N_("file"),
 			N_("read additional per-directory exclude patterns in <file>")),
-		{ OPTION_CALLBACK, 0, "exclude-standard", &dir, NULL,
+		OPT_CALLBACK_F(0, "exclude-standard", &dir, NULL,
 			N_("add the standard git exclusions"),
-			PARSE_OPT_NOARG, option_parse_exclude_standard },
-		{ OPTION_SET_INT, 0, "full-name", &prefix_len, NULL,
-			N_("make the output relative to the project top directory"),
-			PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL },
-		OPT_BOOLEAN(0, "error-unmatch", &error_unmatch,
+			PARSE_OPT_NOARG | PARSE_OPT_NONEG,
+			option_parse_exclude_standard),
+		OPT_SET_INT_F(0, "full-name", &prefix_len,
+			      N_("make the output relative to the project top directory"),
+			      0, PARSE_OPT_NONEG),
+		OPT_BOOL(0, "recurse-submodules", &recurse_submodules,
+			N_("recurse through submodules")),
+		OPT_BOOL(0, "error-unmatch", &error_unmatch,
 			N_("if any <file> is not in the index, treat this as an error")),
 		OPT_STRING(0, "with-tree", &with_tree, N_("tree-ish"),
 			N_("pretend that paths removed since <tree-ish> are still present")),
 		OPT__ABBREV(&abbrev),
-		OPT_BOOLEAN(0, "debug", &debug_mode, N_("show debugging data")),
+		OPT_BOOL(0, "debug", &debug_mode, N_("show debugging data")),
+		OPT_BOOL(0, "deduplicate", &skipping_duplicates,
+			 N_("suppress duplicate entries")),
 		OPT_END()
 	};
 
 	if (argc == 2 && !strcmp(argv[1], "-h"))
 		usage_with_options(ls_files_usage, builtin_ls_files_options);
 
-	memset(&dir, 0, sizeof(dir));
 	prefix = cmd_prefix;
 	if (prefix)
 		prefix_len = strlen(prefix);
 	git_config(git_default_config, NULL);
 
-	if (read_cache() < 0)
+	if (repo_read_index(the_repository) < 0)
 		die("index file corrupt");
 
 	argc = parse_options(argc, argv, prefix, builtin_ls_files_options,
 			ls_files_usage, 0);
-	if (show_tag || show_valid_bit) {
+	pl = add_pattern_list(&dir, EXC_CMDL, "--exclude option");
+	for (i = 0; i < exclude_list.nr; i++) {
+		add_pattern(exclude_list.items[i].string, "", 0, pl, --exclude_args);
+	}
+	if (show_tag || show_valid_bit || show_fsmonitor_bit) {
 		tag_cached = "H ";
 		tag_unmerged = "M ";
 		tag_removed = "R ";
@@ -543,40 +710,58 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 		 * you also show the stage information.
 		 */
 		show_stage = 1;
+	if (show_tag || show_stage)
+		skipping_duplicates = 0;
 	if (dir.exclude_per_dir)
 		exc_given = 1;
 
 	if (require_work_tree && !is_inside_work_tree())
 		setup_work_tree();
 
-	pathspec = get_pathspec(prefix, argv);
+	if (recurse_submodules &&
+	    (show_stage || show_deleted || show_others || show_unmerged ||
+	     show_killed || show_modified || show_resolve_undo || with_tree))
+		die("ls-files --recurse-submodules unsupported mode");
 
-	/* be nice with submodule paths ending in a slash */
-	if (pathspec)
-		strip_trailing_slash_from_submodules();
+	if (recurse_submodules && error_unmatch)
+		die("ls-files --recurse-submodules does not support "
+		    "--error-unmatch");
 
-	/* Find common prefix for all pathspec's */
-	max_prefix = common_prefix(pathspec);
-	max_prefix_len = max_prefix ? strlen(max_prefix) : 0;
+	parse_pathspec(&pathspec, 0,
+		       PATHSPEC_PREFER_CWD,
+		       prefix, argv);
+
+	/*
+	 * Find common prefix for all pathspec's
+	 * This is used as a performance optimization which unfortunately cannot
+	 * be done when recursing into submodules because when a pathspec is
+	 * given which spans repository boundaries you can't simply remove the
+	 * submodule entry because the pathspec may match something inside the
+	 * submodule.
+	 */
+	if (recurse_submodules)
+		max_prefix = NULL;
+	else
+		max_prefix = common_prefix(&pathspec);
+	max_prefix_len = get_common_prefix_len(max_prefix);
+
+	prune_index(the_repository->index, max_prefix, max_prefix_len);
 
 	/* Treat unmatching pathspec elements as errors */
-	if (pathspec && error_unmatch) {
-		int num;
-		for (num = 0; pathspec[num]; num++)
-			;
-		ps_matched = xcalloc(1, num);
-	}
+	if (pathspec.nr && error_unmatch)
+		ps_matched = xcalloc(pathspec.nr, 1);
+
+	if ((dir.flags & DIR_SHOW_IGNORED) && !show_others && !show_cached)
+		die("ls-files -i must be used with either -o or -c");
 
 	if ((dir.flags & DIR_SHOW_IGNORED) && !exc_given)
 		die("ls-files --ignored needs some exclude pattern");
 
 	/* With no flags, we default to showing the cached files */
-	if (!(show_stage | show_deleted | show_others | show_unmerged |
-	      show_killed | show_modified | show_resolve_undo))
+	if (!(show_stage || show_deleted || show_others || show_unmerged ||
+	      show_killed || show_modified || show_resolve_undo))
 		show_cached = 1;
 
-	if (max_prefix)
-		prune_cache(max_prefix);
 	if (with_tree) {
 		/*
 		 * Basic sanity check; show-stages and show-unmerged
@@ -584,20 +769,24 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 		 */
 		if (show_stage || show_unmerged)
 			die("ls-files --with-tree is incompatible with -s or -u");
-		overlay_tree_on_cache(with_tree, max_prefix);
+		overlay_tree_on_index(the_repository->index, with_tree, max_prefix);
 	}
-	show_files(&dir);
+
+	show_files(the_repository, &dir);
+
 	if (show_resolve_undo)
-		show_ru_info();
+		show_ru_info(the_repository->index);
 
 	if (ps_matched) {
 		int bad;
-		bad = report_path_error(ps_matched, pathspec, prefix);
+		bad = report_path_error(ps_matched, &pathspec);
 		if (bad)
 			fprintf(stderr, "Did you forget to 'git add'?\n");
 
 		return bad ? 1 : 0;
 	}
 
+	dir_clear(&dir);
+	free(max_prefix);
 	return 0;
 }