Merge branch 'nd/submodule-pathspec-ending-with-slash'

Allow "git cmd path/", when the 'path' is where a submodule is
bound to the top-level working tree, to match 'path', despite the
extra and unnecessary trailing slash.

* nd/submodule-pathspec-ending-with-slash:
  clean: use cache_name_is_other()
  clean: replace match_pathspec() with dir_path_match()
  pathspec: pass directory indicator to match_pathspec_item()
  match_pathspec: match pathspec "foo/" against directory "foo"
  dir.c: prepare match_pathspec_item for taking more flags
  pathspec: rename match_pathspec_depth() to match_pathspec()
  pathspec: convert some match_pathspec_depth() to dir_path_match()
  pathspec: convert some match_pathspec_depth() to ce_path_match()

builtin/add.c

@@ -208,8 +208,7 @@ static char *prune_directory(struct dir_struct *dir, struct pathspec *pathspec,
 	i = dir->nr;
 	while (--i >= 0) {
 		struct dir_entry *entry = *src++;
-		if (match_pathspec_depth(pathspec, entry->name, entry->len,
-					 prefix, seen))
+		if (dir_path_match(entry, pathspec, prefix, seen))
 			*dst++ = entry;
 		else if (flag & WARN_IMPLICIT_DOT)
 			/*

builtin/checkout.c

@@ -297,8 +297,7 @@ static int checkout_paths(const struct checkout_opts *opts,
 		 * match_pathspec() for _all_ entries when
 		 * opts->source_tree != NULL.
 		 */
-		if (match_pathspec_depth(&opts->pathspec, ce->name, ce_namelen(ce),
-				   0, ps_matched))
+		if (ce_path_match(ce, &opts->pathspec, ps_matched))
 			ce->ce_flags |= CE_MATCHED;
 	}
 

builtin/clean.c

@@ -933,36 +933,18 @@ int cmd_clean(int argc, const char **argv, const char *prefix)
 
 	for (i = 0; i < dir.nr; i++) {
 		struct dir_entry *ent = dir.entries[i];
-		int len, pos;
 		int matches = 0;
-		const struct cache_entry *ce;
 		struct stat st;
 		const char *rel;
 
-		/*
-		 * Remove the '/' at the end that directory
-		 * walking adds for directory entries.
-		 */
-		len = ent->len;
-		if (len && ent->name[len-1] == '/')
-			len--;
-		pos = cache_name_pos(ent->name, len);
-		if (0 <= pos)
-			continue;	/* exact match */
-		pos = -pos - 1;
-		if (pos < active_nr) {
-			ce = active_cache[pos];
-			if (ce_namelen(ce) == len &&
-			    !memcmp(ce->name, ent->name, len))
-				continue; /* Yup, this one exists unmerged */
-		}
+		if (!cache_name_is_other(ent->name, ent->len))
+			continue;
 
 		if (lstat(ent->name, &st))
 			die_errno("Cannot lstat '%s'", ent->name);
 
 		if (pathspec.nr)
-			matches = match_pathspec_depth(&pathspec, ent->name,
-						       len, 0, NULL);
+			matches = dir_path_match(ent, &pathspec, 0, NULL);
 
 		if (S_ISDIR(st.st_mode)) {
 			if (remove_directories || (matches == MATCHED_EXACTLY)) {

builtin/commit.c

@@ -234,7 +234,7 @@ static int list_paths(struct string_list *list, const char *with_tree,
 
 		if (ce->ce_flags & CE_UPDATE)
 			continue;
-		if (!match_pathspec_depth(pattern, ce->name, ce_namelen(ce), 0, m))
+		if (!ce_path_match(ce, pattern, m))
 			continue;
 		item = string_list_insert(list, ce->name);
 		if (ce_skip_worktree(ce))

builtin/grep.c

@@ -379,7 +379,7 @@ static int grep_cache(struct grep_opt *opt, const struct pathspec *pathspec, int
 		const struct cache_entry *ce = active_cache[nr];
 		if (!S_ISREG(ce->ce_mode))
 			continue;
-		if (!match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL))
+		if (!ce_path_match(ce, pathspec, NULL))
 			continue;
 		/*
 		 * If CE_VALID is on, we assume worktree file and its cache entry
@@ -524,9 +524,7 @@ static int grep_directory(struct grep_opt *opt, const struct pathspec *pathspec,
 
 	fill_directory(&dir, pathspec);
 	for (i = 0; i < dir.nr; i++) {
-		const char *name = dir.entries[i]->name;
-		int namelen = strlen(name);
-		if (!match_pathspec_depth(pathspec, name, namelen, 0, NULL))
+		if (!dir_path_match(dir.entries[i], pathspec, 0, NULL))
 			continue;
 		hit |= grep_file(opt, dir.entries[i]->name);
 		if (hit && opt->status_only)

builtin/ls-files.c

@@ -64,7 +64,7 @@ static void show_dir_entry(const char *tag, struct dir_entry *ent)
 	if (len >= ent->len)
 		die("git ls-files: internal error - directory entry not superset of prefix");
 
-	if (!match_pathspec_depth(&pathspec, ent->name, ent->len, len, ps_matched))
+	if (!dir_path_match(ent, &pathspec, len, ps_matched))
 		return;
 
 	fputs(tag, stdout);
@@ -139,7 +139,9 @@ static void show_ce_entry(const char *tag, const struct cache_entry *ce)
 	if (len >= ce_namelen(ce))
 		die("git ls-files: internal error - cache entry not superset of prefix");
 
-	if (!match_pathspec_depth(&pathspec, ce->name, ce_namelen(ce), len, ps_matched))
+	if (!match_pathspec(&pathspec, ce->name, ce_namelen(ce),
+			    len, ps_matched,
+			    S_ISDIR(ce->ce_mode) || S_ISGITLINK(ce->ce_mode)))
 		return;
 
 	if (tag && *tag && show_valid_bit &&
@@ -195,7 +197,8 @@ static void show_ru_info(void)
 		len = strlen(path);
 		if (len < max_prefix_len)
 			continue; /* outside of the prefix */
-		if (!match_pathspec_depth(&pathspec, path, len, max_prefix_len, ps_matched))
+		if (!match_pathspec(&pathspec, path, len,
+				    max_prefix_len, ps_matched, 0))
 			continue; /* uninterested */
 		for (i = 0; i < 3; i++) {
 			if (!ui->mode[i])

builtin/ls-tree.c

@@ -171,7 +171,7 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix)
 	 * show_recursive() rolls its own matching code and is
 	 * generally ignorant of 'struct pathspec'. The magic mask
 	 * cannot be lifted until it is converted to use
-	 * match_pathspec_depth() or tree_entry_interesting()
+	 * match_pathspec() or tree_entry_interesting()
 	 */
 	parse_pathspec(&pathspec, PATHSPEC_GLOB | PATHSPEC_ICASE,
 		       PATHSPEC_PREFER_CWD,

builtin/rm.c

@@ -308,7 +308,7 @@ int cmd_rm(int argc, const char **argv, const char *prefix)
 
 	for (i = 0; i < active_nr; i++) {
 		const struct cache_entry *ce = active_cache[i];
-		if (!match_pathspec_depth(&pathspec, ce->name, ce_namelen(ce), 0, seen))
+		if (!ce_path_match(ce, &pathspec, seen))
 			continue;
 		ALLOC_GROW(list.entry, list.nr + 1, list.alloc);
 		list.entry[list.nr].name = xstrdup(ce->name);

builtin/update-index.c

@@ -12,6 +12,7 @@
 #include "resolve-undo.h"
 #include "parse-options.h"
 #include "pathspec.h"
+#include "dir.h"
 
 /*
  * Default to not allowing changes to the list of files. The
@@ -561,7 +562,7 @@ static int do_reupdate(int ac, const char **av,
 		int save_nr;
 		char *path;
 
-		if (ce_stage(ce) || !ce_path_match(ce, &pathspec))
+		if (ce_stage(ce) || !ce_path_match(ce, &pathspec, NULL))
 			continue;
 		if (has_head)
 			old = read_one_ent(NULL, head_sha1,

cache.h

@@ -503,8 +503,6 @@ extern void *read_blob_data_from_index(struct index_state *, const char *, unsig
 extern int ie_match_stat(const struct index_state *, const struct cache_entry *, struct stat *, unsigned int);
 extern int ie_modified(const struct index_state *, const struct cache_entry *, struct stat *, unsigned int);
 
-extern int ce_path_match(const struct cache_entry *ce, const struct pathspec *pathspec);
-
 #define HASH_WRITE_OBJECT 1
 #define HASH_FORMAT_CHECK 2
 extern int index_fd(unsigned char *sha1, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags);

diff-lib.c

@@ -11,6 +11,7 @@
 #include "unpack-trees.h"
 #include "refs.h"
 #include "submodule.h"
+#include "dir.h"
 
 /*
  * diff-files
@@ -108,7 +109,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 		if (diff_can_quit_early(&revs->diffopt))
 			break;
 
-		if (!ce_path_match(ce, &revs->prune_data))
+		if (!ce_path_match(ce, &revs->prune_data, NULL))
 			continue;
 
 		if (ce_stage(ce)) {
@@ -438,7 +439,7 @@ static int oneway_diff(const struct cache_entry * const *src,
 	if (tree == o->df_conflict_entry)
 		tree = NULL;
 
-	if (ce_path_match(idx ? idx : tree, &revs->prune_data)) {
+	if (ce_path_match(idx ? idx : tree, &revs->prune_data, NULL)) {
 		do_oneway_diff(o, idx, tree);
 		if (diff_can_quit_early(&revs->diffopt)) {
 			o->exiting_early = 1;

dir.c

@@ -195,6 +195,9 @@ int within_depth(const char *name, int namelen,
 	return 1;
 }
 
+#define DO_MATCH_EXCLUDE   1
+#define DO_MATCH_DIRECTORY 2
+
 /*
  * Does 'match' match the given name?
  * A match is found if
@@ -208,7 +211,7 @@ int within_depth(const char *name, int namelen,
  * It returns 0 when there is no match.
  */
 static int match_pathspec_item(const struct pathspec_item *item, int prefix,
-			       const char *name, int namelen)
+			       const char *name, int namelen, unsigned flags)
 {
 	/* name/namelen has prefix cut off by caller */
 	const char *match = item->match + prefix;
@@ -218,7 +221,7 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix,
 	 * The normal call pattern is:
 	 * 1. prefix = common_prefix_len(ps);
 	 * 2. prune something, or fill_directory
-	 * 3. match_pathspec_depth()
+	 * 3. match_pathspec()
 	 *
 	 * 'prefix' at #1 may be shorter than the command's prefix and
 	 * it's ok for #2 to match extra files. Those extras will be
@@ -257,7 +260,11 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix,
 
 		if (match[matchlen-1] == '/' || name[matchlen] == '/')
 			return MATCHED_RECURSIVELY;
-	}
+	} else if ((flags & DO_MATCH_DIRECTORY) &&
+		   match[matchlen - 1] == '/' &&
+		   namelen == matchlen - 1 &&
+		   !ps_strncmp(item, match, name, namelen))
+		return MATCHED_EXACTLY;
 
 	if (item->nowildcard_len < item->len &&
 	    !git_fnmatch(item, match, name,
@@ -282,12 +289,12 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix,
  * pathspec did not match any names, which could indicate that the
  * user mistyped the nth pathspec.
  */
-static int match_pathspec_depth_1(const struct pathspec *ps,
+static int do_match_pathspec(const struct pathspec *ps,
 			     const char *name, int namelen,
 			     int prefix, char *seen,
-				  int exclude)
+			     unsigned flags)
 {
-	int i, retval = 0;
+	int i, retval = 0, exclude = flags & DO_MATCH_EXCLUDE;
 
 	GUARD_PATHSPEC(ps,
 		       PATHSPEC_FROMTOP |
@@ -327,7 +334,8 @@ static int match_pathspec_depth_1(const struct pathspec *ps,
 		 */
 		if (seen && ps->items[i].magic & PATHSPEC_EXCLUDE)
 			seen[i] = MATCHED_FNMATCH;
-		how = match_pathspec_item(ps->items+i, prefix, name, namelen);
+		how = match_pathspec_item(ps->items+i, prefix, name,
+					  namelen, flags);
 		if (ps->recursive &&
 		    (ps->magic & PATHSPEC_MAXDEPTH) &&
 		    ps->max_depth != -1 &&
@@ -350,15 +358,19 @@ static int match_pathspec_depth_1(const struct pathspec *ps,
 	return retval;
 }
 
-int match_pathspec_depth(const struct pathspec *ps,
+int match_pathspec(const struct pathspec *ps,
 		   const char *name, int namelen,
-			 int prefix, char *seen)
+		   int prefix, char *seen, int is_dir)
 {
 	int positive, negative;
-	positive = match_pathspec_depth_1(ps, name, namelen, prefix, seen, 0);
+	unsigned flags = is_dir ? DO_MATCH_DIRECTORY : 0;
+	positive = do_match_pathspec(ps, name, namelen,
+				     prefix, seen, flags);
 	if (!(ps->magic & PATHSPEC_EXCLUDE) || !positive)
 		return positive;
-	negative = match_pathspec_depth_1(ps, name, namelen, prefix, seen, 1);
+	negative = do_match_pathspec(ps, name, namelen,
+				     prefix, seen,
+				     flags | DO_MATCH_EXCLUDE);
 	return negative ? 0 : positive;
 }
 

dir.h

@@ -132,9 +132,9 @@ struct dir_struct {
 extern int simple_length(const char *match);
 extern int no_wildcard(const char *string);
 extern char *common_prefix(const struct pathspec *pathspec);
-extern int match_pathspec_depth(const struct pathspec *pathspec,
+extern int match_pathspec(const struct pathspec *pathspec,
 			  const char *name, int namelen,
-				int prefix, char *seen);
+			  int prefix, char *seen, int is_dir);
 extern int within_depth(const char *name, int namelen, int depth, int max_depth);
 
 extern int fill_directory(struct dir_struct *dir, const struct pathspec *pathspec);
@@ -205,4 +205,22 @@ extern int git_fnmatch(const struct pathspec_item *item,
 		       const char *pattern, const char *string,
 		       int prefix);
 
+static inline int ce_path_match(const struct cache_entry *ce,
+				const struct pathspec *pathspec,
+				char *seen)
+{
+	return match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, seen,
+			      S_ISDIR(ce->ce_mode) || S_ISGITLINK(ce->ce_mode));
+}
+
+static inline int dir_path_match(const struct dir_entry *ent,
+				 const struct pathspec *pathspec,
+				 int prefix, char *seen)
+{
+	int has_trailing_dir = ent->len && ent->name[ent->len - 1] == '/';
+	int len = has_trailing_dir ? ent->len - 1 : ent->len;
+	return match_pathspec(pathspec, ent->name, len, prefix, seen,
+			      has_trailing_dir);
+}
+
 #endif

pathspec.c

@@ -33,7 +33,7 @@ void add_pathspec_matches_against_index(const struct pathspec *pathspec,
 		return;
 	for (i = 0; i < active_nr; i++) {
 		const struct cache_entry *ce = active_cache[i];
-		match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, seen);
+		ce_path_match(ce, pathspec, seen);
 	}
 }
 

preload-index.c

@@ -3,6 +3,7 @@
  */
 #include "cache.h"
 #include "pathspec.h"
+#include "dir.h"
 
 #ifdef NO_PTHREADS
 static void preload_index(struct index_state *index,
@@ -53,7 +54,7 @@ static void *preload_thread(void *_data)
 			continue;
 		if (ce_uptodate(ce))
 			continue;
-		if (!ce_path_match(ce, &p->pathspec))
+		if (!ce_path_match(ce, &p->pathspec, NULL))
 			continue;
 		if (threaded_has_symlink_leading_path(&cache, ce->name, ce_namelen(ce)))
 			continue;

read-cache.c

@@ -730,11 +730,6 @@ int ce_same_name(const struct cache_entry *a, const struct cache_entry *b)
 	return ce_namelen(b) == len && !memcmp(a->name, b->name, len);
 }
 
-int ce_path_match(const struct cache_entry *ce, const struct pathspec *pathspec)
-{
-	return match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL);
-}
-
 /*
  * We fundamentally don't like some paths: we don't want
  * dot or dot-dot anywhere, and for obvious reasons don't
@@ -1157,8 +1152,7 @@ int refresh_index(struct index_state *istate, unsigned int flags,
 		if (ignore_submodules && S_ISGITLINK(ce->ce_mode))
 			continue;
 
-		if (pathspec &&
-		    !match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, seen))
+		if (pathspec && !ce_path_match(ce, pathspec, seen))
 			filtered = 1;
 
 		if (ce_stage(ce)) {

rerere.c

@@ -672,8 +672,8 @@ int rerere_forget(struct pathspec *pathspec)
 	find_conflict(&conflict);
 	for (i = 0; i < conflict.nr; i++) {
 		struct string_list_item *it = &conflict.items[i];
-		if (!match_pathspec_depth(pathspec, it->string, strlen(it->string),
-					  0, NULL))
+		if (!match_pathspec(pathspec, it->string,
+				    strlen(it->string), 0, NULL, 0))
 			continue;
 		rerere_forget_one_path(it->string, &merge_rr);
 	}

resolve-undo.c

@@ -185,7 +185,7 @@ void unmerge_index(struct index_state *istate, const struct pathspec *pathspec)
 
 	for (i = 0; i < istate->cache_nr; i++) {
 		const struct cache_entry *ce = istate->cache[i];
-		if (!match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL))
+		if (!ce_path_match(ce, pathspec, NULL))
 			continue;
 		i = unmerge_index_entry_at(istate, i);
 	}

revision.c

@@ -16,6 +16,7 @@
 #include "line-log.h"
 #include "mailmap.h"
 #include "commit-slab.h"
+#include "dir.h"
 
 volatile show_early_output_fn_t show_early_output;
 
@@ -1400,7 +1401,7 @@ static void prepare_show_merge(struct rev_info *revs)
 		const struct cache_entry *ce = active_cache[i];
 		if (!ce_stage(ce))
 			continue;
-		if (ce_path_match(ce, &revs->prune_data)) {
+		if (ce_path_match(ce, &revs->prune_data, NULL)) {
 			prune_num++;
 			prune = xrealloc(prune, sizeof(*prune) * prune_num);
 			prune[prune_num-2] = ce->name;

t/t4010-diff-pathspec.sh

@@ -140,4 +140,10 @@ test_expect_success 'diff multiple wildcard pathspecs' '
 	test_cmp expect actual
 '
 
+test_expect_success 'diff-cache ignores trailing slash on submodule path' '
+	git diff --name-only HEAD^ submod >expect &&
+	git diff --name-only HEAD^ submod/ >actual &&
+	test_cmp expect actual
+'
+
 test_done

t/t6131-pathspec-icase.sh

@@ -69,7 +69,7 @@ test_expect_success 'tree_entry_interesting matches :(icase)bar with empty prefi
 	test_cmp expect actual
 '
 
-test_expect_success 'match_pathspec_depth matches :(icase)bar' '
+test_expect_success 'match_pathspec matches :(icase)bar' '
 	cat <<-EOF >expect &&
 	BAR
 	bAr
@@ -79,7 +79,7 @@ test_expect_success 'match_pathspec_depth matches :(icase)bar' '
 	test_cmp expect actual
 '
 
-test_expect_success 'match_pathspec_depth matches :(icase)bar with prefix' '
+test_expect_success 'match_pathspec matches :(icase)bar with prefix' '
 	cat <<-EOF >expect &&
 	fOo/BAR
 	fOo/bAr
@@ -89,7 +89,7 @@ test_expect_success 'match_pathspec_depth matches :(icase)bar with prefix' '
 	test_cmp expect actual
 '
 
-test_expect_success 'match_pathspec_depth matches :(icase)bar with empty prefix' '
+test_expect_success 'match_pathspec matches :(icase)bar with empty prefix' '
 	cat <<-EOF >expect &&
 	bar
 	fOo/BAR

wt-status.c

@@ -510,7 +510,7 @@ static void wt_status_collect_changes_initial(struct wt_status *s)
 		struct wt_status_change_data *d;
 		const struct cache_entry *ce = active_cache[i];
 
-		if (!ce_path_match(ce, &s->pathspec))
+		if (!ce_path_match(ce, &s->pathspec, NULL))
 			continue;
 		it = string_list_insert(&s->change, ce->name);
 		d = it->util;
@@ -552,7 +552,7 @@ static void wt_status_collect_untracked(struct wt_status *s)
 	for (i = 0; i < dir.nr; i++) {
 		struct dir_entry *ent = dir.entries[i];
 		if (cache_name_is_other(ent->name, ent->len) &&
-		    match_pathspec_depth(&s->pathspec, ent->name, ent->len, 0, NULL))
+		    dir_path_match(ent, &s->pathspec, 0, NULL))
 			string_list_insert(&s->untracked, ent->name);
 		free(ent);
 	}
@@ -560,7 +560,7 @@ static void wt_status_collect_untracked(struct wt_status *s)
 	for (i = 0; i < dir.ignored_nr; i++) {
 		struct dir_entry *ent = dir.ignored[i];
 		if (cache_name_is_other(ent->name, ent->len) &&
-		    match_pathspec_depth(&s->pathspec, ent->name, ent->len, 0, NULL))
+		    dir_path_match(ent, &s->pathspec, 0, NULL))
 			string_list_insert(&s->ignored, ent->name);
 		free(ent);
 	}