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

.gitignore

@@ -22,6 +22,7 @@
 /git-bundle
 /git-cat-file
 /git-check-attr
+/git-check-ignore
 /git-check-ref-format
 /git-checkout
 /git-checkout-index

Documentation/git-check-ignore.txt

@@ -0,0 +1,89 @@
+git-check-ignore(1)
+===================
+
+NAME
+----
+git-check-ignore - Debug gitignore / exclude files
+
+
+SYNOPSIS
+--------
+[verse]
+'git check-ignore' [options] pathname...
+'git check-ignore' [options] --stdin < <list-of-paths>
+
+DESCRIPTION
+-----------
+
+For each pathname given via the command-line or from a file via
+`--stdin`, show the pattern from .gitignore (or other input files to
+the exclude mechanism) that decides if the pathname is excluded or
+included.  Later patterns within a file take precedence over earlier
+ones.
+
+OPTIONS
+-------
+-q, --quiet::
+	Don't output anything, just set exit status.  This is only
+	valid with a single pathname.
+
+-v, --verbose::
+	Also output details about the matching pattern (if any)
+	for each given pathname.
+
+--stdin::
+	Read file names from stdin instead of from the command-line.
+
+-z::
+	The output format is modified to be machine-parseable (see
+	below).  If `--stdin` is also given, input paths are separated
+	with a NUL character instead of a linefeed character.
+
+OUTPUT
+------
+
+By default, any of the given pathnames which match an ignore pattern
+will be output, one per line.  If no pattern matches a given path,
+nothing will be output for that path; this means that path will not be
+ignored.
+
+If `--verbose` is specified, the output is a series of lines of the form:
+
+<source> <COLON> <linenum> <COLON> <pattern> <HT> <pathname>
+
+<pathname> is the path of a file being queried, <pattern> is the
+matching pattern, <source> is the pattern's source file, and <linenum>
+is the line number of the pattern within that source.  If the pattern
+contained a `!` prefix or `/` suffix, it will be preserved in the
+output.  <source> will be an absolute path when referring to the file
+configured by `core.excludesfile`, or relative to the repository root
+when referring to `.git/info/exclude` or a per-directory exclude file.
+
+If `-z` is specified, the pathnames in the output are delimited by the
+null character; if `--verbose` is also specified then null characters
+are also used instead of colons and hard tabs:
+
+<source> <NULL> <linenum> <NULL> <pattern> <NULL> <pathname> <NULL>
+
+
+EXIT STATUS
+-----------
+
+0::
+	One or more of the provided paths is ignored.
+
+1::
+	None of the provided paths are ignored.
+
+128::
+	A fatal error was encountered.
+
+SEE ALSO
+--------
+linkgit:gitignore[5]
+linkgit:gitconfig[5]
+linkgit:git-ls-files[5]
+
+GIT
+---
+Part of the linkgit:git[1] suite

Documentation/gitignore.txt

@@ -184,8 +184,10 @@ The second .gitignore prevents git from ignoring
 
 SEE ALSO
 --------
-linkgit:git-rm[1], linkgit:git-update-index[1],
-linkgit:gitrepository-layout[5]
+linkgit:git-rm[1],
+linkgit:git-update-index[1],
+linkgit:gitrepository-layout[5],
+linkgit:git-check-ignore[1]
 
 GIT
 ---

Documentation/technical/api-directory-listing.txt

@@ -67,16 +67,20 @@ marked. If you to exclude files, make sure you have loaded index first.
 * Prepare `struct dir_struct dir` and clear it with `memset(&dir, 0,
   sizeof(dir))`.
 
-* Call `add_exclude()` to add single exclude pattern,
-  `add_excludes_from_file()` to add patterns from a file
-  (e.g. `.git/info/exclude`), and/or set `dir.exclude_per_dir`.  A
-  short-hand function `setup_standard_excludes()` can be used to set up
-  the standard set of exclude settings.
+* To add single exclude pattern, call `add_exclude_list()` and then
+  `add_exclude()`.
+
+* To add patterns from a file (e.g. `.git/info/exclude`), call
+  `add_excludes_from_file()` , and/or set `dir.exclude_per_dir`.  A
+  short-hand function `setup_standard_excludes()` can be used to set
+  up the standard set of exclude settings.
 
 * Set options described in the Data Structure section above.
 
 * Call `read_directory()`.
 
 * Use `dir.entries[]`.
 
+* Call `clear_directory()` when none of the contained elements are no longer in use.
+
 (JC)

Makefile

@@ -666,6 +666,7 @@ LIB_H += pack-revindex.h
 LIB_H += pack.h
 LIB_H += parse-options.h
 LIB_H += patch-ids.h
+LIB_H += pathspec.h
 LIB_H += pkt-line.h
 LIB_H += progress.h
 LIB_H += prompt.h
@@ -789,6 +790,7 @@ LIB_OBJS += parse-options-cb.o
 LIB_OBJS += patch-delta.o
 LIB_OBJS += patch-ids.o
 LIB_OBJS += path.o
+LIB_OBJS += pathspec.o
 LIB_OBJS += pkt-line.o
 LIB_OBJS += preload-index.o
 LIB_OBJS += pretty.o
@@ -854,6 +856,7 @@ BUILTIN_OBJS += builtin/branch.o
 BUILTIN_OBJS += builtin/bundle.o
 BUILTIN_OBJS += builtin/cat-file.o
 BUILTIN_OBJS += builtin/check-attr.o
+BUILTIN_OBJS += builtin/check-ignore.o
 BUILTIN_OBJS += builtin/check-ref-format.o
 BUILTIN_OBJS += builtin/checkout-index.o
 BUILTIN_OBJS += builtin/checkout.o

builtin.h

@@ -52,6 +52,7 @@ extern int cmd_cat_file(int argc, const char **argv, const char *prefix);
 extern int cmd_checkout(int argc, const char **argv, const char *prefix);
 extern int cmd_checkout_index(int argc, const char **argv, const char *prefix);
 extern int cmd_check_attr(int argc, const char **argv, const char *prefix);
+extern int cmd_check_ignore(int argc, const char **argv, const char *prefix);
 extern int cmd_check_ref_format(int argc, const char **argv, const char *prefix);
 extern int cmd_cherry(int argc, const char **argv, const char *prefix);
 extern int cmd_cherry_pick(int argc, const char **argv, const char *prefix);

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;
@@ -149,35 +117,23 @@ 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;
 
 	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])) {