Merge branch 'as/check-ignore'

Add a new command "git check-ignore" for debugging .gitignore
files.

The variable names may want to get cleaned up but that can be done
in-tree.

* as/check-ignore:
  clean.c, ls-files.c: respect encapsulation of exclude_list_groups
  t0008: avoid brace expansion
  add git-check-ignore sub-command
  setup.c: document get_pathspec()
  add.c: extract new die_if_path_beyond_symlink() for reuse
  add.c: extract check_path_for_gitlink() from treat_gitlinks() for reuse
  pathspec.c: rename newly public functions for clarity
  add.c: move pathspec matchers into new pathspec.c for reuse
  add.c: remove unused argument from validate_pathspec()
  dir.c: improve docs for match_pathspec() and match_pathspec_depth()
  dir.c: provide clear_directory() for reclaiming dir_struct memory
  dir.c: keep track of where patterns came from
  dir.c: use a single struct exclude_list per source of excludes

Conflicts:
	builtin/ls-files.c
	dir.c

4 files changed, 205 insertions, 66 deletions

diff --git a/builtin/add.c b/builtin/add.c
index 075312afc..7cb6cca56 100644
--- a/builtin/add.c
+++ b/builtin/add.c
@@ -6,6 +6,7 @@
 #include "cache.h"
 #include "builtin.h"
 #include "dir.h"
+#include "pathspec.h"
 #include "exec_cmd.h"
 #include "cache-tree.h"
 #include "run-command.h"
@@ -97,39 +98,6 @@ int add_files_to_cache(const char *prefix, const char **pathspec, int flags)
 	return !!data.add_errors;
 }
 
-static void fill_pathspec_matches(const char **pathspec, char *seen, int specs)
-{
-	int num_unmatched = 0, i;
-
-	/*
-	 * Since we are walking the index as if we were walking the directory,
-	 * we have to mark the matched pathspec as seen; otherwise we will
-	 * mistakenly think that the user gave a pathspec that did not match
-	 * anything.
-	 */
-	for (i = 0; i < specs; i++)
-		if (!seen[i])
-			num_unmatched++;
-	if (!num_unmatched)
-		return;
-	for (i = 0; i < active_nr; i++) {
-		struct cache_entry *ce = active_cache[i];
-		match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, seen);
-	}
-}
-
-static char *find_used_pathspec(const char **pathspec)
-{
-	char *seen;
-	int i;
-
-	for (i = 0; pathspec[i];  i++)
-		; /* just counting */
-	seen = xcalloc(i, 1);
-	fill_pathspec_matches(pathspec, seen, i);
-	return seen;
-}
-
 static char *prune_directory(struct dir_struct *dir, const char **pathspec, int prefix)
 {
 	char *seen;
@@ -149,10 +117,14 @@ static char *prune_directory(struct dir_struct *dir, const char **pathspec, int
 			*dst++ = entry;
 	}
 	dir->nr = dst - dir->entries;
-	fill_pathspec_matches(pathspec, seen, specs);
+	add_pathspec_matches_against_index(pathspec, seen, specs);
 	return seen;
 }
 
+/*
+ * Checks the index to see whether any path in pathspec refers to
+ * something inside a submodule.  If so, dies with an error message.
+ */
 static void treat_gitlinks(const char **pathspec)
 {
 	int i;
@@ -160,24 +132,8 @@ static void treat_gitlinks(const char **pathspec)
 	if (!pathspec || !*pathspec)
 		return;
 
-	for (i = 0; i < active_nr; i++) {
-		struct cache_entry *ce = active_cache[i];
-		if (S_ISGITLINK(ce->ce_mode)) {
-			int len = ce_namelen(ce), j;
-			for (j = 0; pathspec[j]; j++) {
-				int len2 = strlen(pathspec[j]);
-				if (len2 <= len || pathspec[j][len] != '/' ||
-				    memcmp(ce->name, pathspec[j], len))
-					continue;
-				if (len2 == len + 1)
-					/* strip trailing slash */
-					pathspec[j] = xstrndup(ce->name, len);
-				else
-					die (_("Path '%s' is in submodule '%.*s'"),
-						pathspec[j], len, ce->name);
-			}
-		}
-	}
+	for (i = 0; pathspec[i]; i++)
+		pathspec[i] = check_path_for_gitlink(pathspec[i]);
 }
 
 static void refresh(int verbose, const char **pathspec)
@@ -197,17 +153,19 @@ static void refresh(int verbose, const char **pathspec)
         free(seen);
 }
 
-static const char **validate_pathspec(int argc, const char **argv, const char *prefix)
+/*
+ * Normalizes argv relative to prefix, via get_pathspec(), and then
+ * runs die_if_path_beyond_symlink() on each path in the normalized
+ * list.
+ */
+static const char **validate_pathspec(const char **argv, const char *prefix)
 {
 	const char **pathspec = get_pathspec(prefix, argv);
 
 	if (pathspec) {
 		const char **p;
 		for (p = pathspec; *p; p++) {
-			if (has_symlink_leading_path(*p, strlen(*p))) {
-				int len = prefix ? strlen(prefix) : 0;
-				die(_("'%s' is beyond a symbolic link"), *p + len);
-			}
+			die_if_path_beyond_symlink(*p, prefix);
 		}
 	}
 
@@ -248,7 +206,7 @@ int interactive_add(int argc, const char **argv, const char *prefix, int patch)
 	const char **pathspec = NULL;
 
 	if (argc) {
-		pathspec = validate_pathspec(argc, argv, prefix);
+		pathspec = validate_pathspec(argv, prefix);
 		if (!pathspec)
 			return -1;
 	}
@@ -415,7 +373,7 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 		fprintf(stderr, _("Maybe you wanted to say 'git add .'?\n"));
 		return 0;
 	}
-	pathspec = validate_pathspec(argc, argv, prefix);
+	pathspec = validate_pathspec(argv, prefix);
 
 	if (read_cache() < 0)
 		die(_("index file corrupt"));
@@ -448,7 +406,7 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 
 		path_exclude_check_init(&check, &dir);
 		if (!seen)
-			seen = find_used_pathspec(pathspec);
+			seen = find_pathspecs_matching_against_index(pathspec);
 		for (i = 0; pathspec[i]; i++) {
 			if (!seen[i] && pathspec[i][0]
 			    && !file_exists(pathspec[i])) {
diff --git a/builtin/check-ignore.c b/builtin/check-ignore.c
new file mode 100644
index 000000000..709535ce0
--- /dev/null
+++ b/builtin/check-ignore.c
@@ -0,0 +1,173 @@
+#include "builtin.h"
+#include "cache.h"
+#include "dir.h"
+#include "quote.h"
+#include "pathspec.h"
+#include "parse-options.h"
+
+static int quiet, verbose, stdin_paths;
+static const char * const check_ignore_usage[] = {
+"git check-ignore [options] pathname...",
+"git check-ignore [options] --stdin < <list-of-paths>",
+NULL
+};
+
+static int null_term_line;
+
+static const struct option check_ignore_options[] = {
+	OPT__QUIET(&quiet, N_("suppress progress reporting")),
+	OPT__VERBOSE(&verbose, N_("be verbose")),
+	OPT_GROUP(""),
+	OPT_BOOLEAN(0, "stdin", &stdin_paths,
+		    N_("read file names from stdin")),
+	OPT_BOOLEAN('z', NULL, &null_term_line,
+		    N_("input paths are terminated by a null character")),
+	OPT_END()
+};
+
+static void output_exclude(const char *path, struct exclude *exclude)
+{
+	char *bang  = exclude->flags & EXC_FLAG_NEGATIVE  ? "!" : "";
+	char *slash = exclude->flags & EXC_FLAG_MUSTBEDIR ? "/" : "";
+	if (!null_term_line) {
+		if (!verbose) {
+			write_name_quoted(path, stdout, '\n');
+		} else {
+			quote_c_style(exclude->el->src, NULL, stdout, 0);
+			printf(":%d:%s%s%s\t",
+			       exclude->srcpos,
+			       bang, exclude->pattern, slash);
+			quote_c_style(path, NULL, stdout, 0);
+			fputc('\n', stdout);
+		}
+	} else {
+		if (!verbose) {
+			printf("%s%c", path, '\0');
+		} else {
+			printf("%s%c%d%c%s%s%s%c%s%c",
+			       exclude->el->src, '\0',
+			       exclude->srcpos, '\0',
+			       bang, exclude->pattern, slash, '\0',
+			       path, '\0');
+		}
+	}
+}
+
+static int check_ignore(const char *prefix, const char **pathspec)
+{
+	struct dir_struct dir;
+	const char *path, *full_path;
+	char *seen;
+	int num_ignored = 0, dtype = DT_UNKNOWN, i;
+	struct path_exclude_check check;
+	struct exclude *exclude;
+
+	/* read_cache() is only necessary so we can watch out for submodules. */
+	if (read_cache() < 0)
+		die(_("index file corrupt"));
+
+	memset(&dir, 0, sizeof(dir));
+	dir.flags |= DIR_COLLECT_IGNORED;
+	setup_standard_excludes(&dir);
+
+	if (!pathspec || !*pathspec) {
+		if (!quiet)
+			fprintf(stderr, "no pathspec given.\n");
+		return 0;
+	}
+
+	path_exclude_check_init(&check, &dir);
+	/*
+	 * look for pathspecs matching entries in the index, since these
+	 * should not be ignored, in order to be consistent with
+	 * 'git status', 'git add' etc.
+	 */
+	seen = find_pathspecs_matching_against_index(pathspec);
+	for (i = 0; pathspec[i]; i++) {
+		path = pathspec[i];
+		full_path = prefix_path(prefix, prefix
+					? strlen(prefix) : 0, path);
+		full_path = check_path_for_gitlink(full_path);
+		die_if_path_beyond_symlink(full_path, prefix);
+		if (!seen[i] && path[0]) {
+			exclude = last_exclude_matching_path(&check, full_path,
+							     -1, &dtype);
+			if (exclude) {
+				if (!quiet)
+					output_exclude(path, exclude);
+				num_ignored++;
+			}
+		}
+	}
+	free(seen);
+	clear_directory(&dir);
+	path_exclude_check_clear(&check);
+
+	return num_ignored;
+}
+
+static int check_ignore_stdin_paths(const char *prefix)
+{
+	struct strbuf buf, nbuf;
+	char **pathspec = NULL;
+	size_t nr = 0, alloc = 0;
+	int line_termination = null_term_line ? 0 : '\n';
+	int num_ignored;
+
+	strbuf_init(&buf, 0);
+	strbuf_init(&nbuf, 0);
+	while (strbuf_getline(&buf, stdin, line_termination) != EOF) {
+		if (line_termination && buf.buf[0] == '"') {
+			strbuf_reset(&nbuf);
+			if (unquote_c_style(&nbuf, buf.buf, NULL))
+				die("line is badly quoted");
+			strbuf_swap(&buf, &nbuf);
+		}
+		ALLOC_GROW(pathspec, nr + 1, alloc);
+		pathspec[nr] = xcalloc(strlen(buf.buf) + 1, sizeof(*buf.buf));
+		strcpy(pathspec[nr++], buf.buf);
+	}
+	ALLOC_GROW(pathspec, nr + 1, alloc);
+	pathspec[nr] = NULL;
+	num_ignored = check_ignore(prefix, (const char **)pathspec);
+	maybe_flush_or_die(stdout, "attribute to stdout");
+	strbuf_release(&buf);
+	strbuf_release(&nbuf);
+	free(pathspec);
+	return num_ignored;
+}
+
+int cmd_check_ignore(int argc, const char **argv, const char *prefix)
+{
+	int num_ignored;
+
+	git_config(git_default_config, NULL);
+
+	argc = parse_options(argc, argv, prefix, check_ignore_options,
+			     check_ignore_usage, 0);
+
+	if (stdin_paths) {
+		if (argc > 0)
+			die(_("cannot specify pathnames with --stdin"));
+	} else {
+		if (null_term_line)
+			die(_("-z only makes sense with --stdin"));
+		if (argc == 0)
+			die(_("no path specified"));
+	}
+	if (quiet) {
+		if (argc > 1)
+			die(_("--quiet is only valid with a single pathname"));
+		if (verbose)
+			die(_("cannot have both --quiet and --verbose"));
+	}
+
+	if (stdin_paths) {
+		num_ignored = check_ignore_stdin_paths(prefix);
+	} else {
+		num_ignored = check_ignore(prefix, argv);
+		maybe_flush_or_die(stdout, "ignore to stdout");
+	}
+
+	return !num_ignored;
+}
diff --git a/builtin/clean.c b/builtin/clean.c
index f4b760bf3..04e396b17 100644
--- a/builtin/clean.c
+++ b/builtin/clean.c
@@ -153,6 +153,7 @@ int cmd_clean(int argc, const char **argv, const char *prefix)
 	static const char **pathspec;
 	struct strbuf buf = STRBUF_INIT;
 	struct string_list exclude_list = STRING_LIST_INIT_NODUP;
+	struct exclude_list *el;
 	const char *qname;
 	char *seen = NULL;
 	struct option options[] = {
@@ -205,9 +206,9 @@ int cmd_clean(int argc, const char **argv, const char *prefix)
 	if (!ignored)
 		setup_standard_excludes(&dir);
 
+	el = add_exclude_list(&dir, EXC_CMDL, "--exclude option");
 	for (i = 0; i < exclude_list.nr; i++)
-		add_exclude(exclude_list.items[i].string, "", 0,
-			    &dir.exclude_list[EXC_CMDL]);
+		add_exclude(exclude_list.items[i].string, "", 0, el, -(i+1));
 
 	pathspec = get_pathspec(prefix, argv);
 
diff --git a/builtin/ls-files.c b/builtin/ls-files.c
index 373c57344..175e6e3e7 100644
--- a/builtin/ls-files.c
+++ b/builtin/ls-files.c
@@ -35,6 +35,7 @@ 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 = "";
@@ -420,10 +421,10 @@ static int option_parse_z(const struct option *opt,
 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;
 
 	exc_given = 1;
-	add_exclude(arg, "", 0, list);
+	string_list_append(exclude_list, arg);
 
 	return 0;
 }
@@ -452,9 +453,11 @@ 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;
+	int require_work_tree = 0, show_tag = 0, i;
 	const char *max_prefix;
 	struct dir_struct dir;
+	struct exclude_list *el;
+	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"),
@@ -488,7 +491,7 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 			N_("show unmerged files in the output")),
 		OPT_BOOLEAN(0, "resolve-undo", &show_resolve_undo,
 			    N_("show resolve-undo information")),
-		{ OPTION_CALLBACK, 'x', "exclude", &dir.exclude_list[EXC_CMDL], N_("pattern"),
+		{ OPTION_CALLBACK, 'x', "exclude", &exclude_list, N_("pattern"),
 			N_("skip files matching pattern"),
 			0, option_parse_exclude },
 		{ OPTION_CALLBACK, 'X', "exclude-from", &dir, N_("file"),
@@ -525,6 +528,10 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 
 	argc = parse_options(argc, argv, prefix, builtin_ls_files_options,
 			ls_files_usage, 0);
+	el = add_exclude_list(&dir, EXC_CMDL, "--exclude option");
+	for (i = 0; i < exclude_list.nr; i++) {
+		add_exclude(exclude_list.items[i].string, "", 0, el, --exclude_args);
+	}
 	if (show_tag || show_valid_bit) {
 		tag_cached = "H ";
 		tag_unmerged = "M ";