Make git-clean a builtin

This replaces git-clean.sh with builtin-clean.c, and moves
git-clean.sh to the examples.

This also introduces a change in behavior when removing directories
explicitly specified as a path.  For example currently:

1. When dir has only untracked files, these two behave differently:

    $ git clean -n dir
    $ git clean -n dir/

the former says "Would not remove dir/", while the latter would say
"Would remove dir/untracked" for all paths under it, but not the
directory itself.

With -d, the former would stop refusing, however since the user
explicitly asked to remove the directory the -d is no longer required.

2. When there are more parameters:

    $ git clean -n dir foo
    $ git clean -n dir/ foo

both cases refuse to remove dir/ unless -d is specified.  Once again
since both cases requested to remove dir the -d is no longer required.

Thanks to Johannes Schindelin for the conversion to using the
parse-options API.

Signed-off-by: Shawn Bohrer <shawn.bohrer@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

5 files changed, 158 insertions, 1 deletions

diff --git a/Makefile b/Makefile
index cabde8177e..87da99f432 100644
--- a/Makefile
+++ b/Makefile
@@ -213,7 +213,7 @@ BASIC_LDFLAGS =
 
 SCRIPT_SH = \
 	git-bisect.sh git-checkout.sh \
-	git-clean.sh git-clone.sh git-commit.sh \
+	git-clone.sh git-commit.sh \
 	git-ls-remote.sh \
 	git-merge-one-file.sh git-mergetool.sh git-parse-remote.sh \
 	git-pull.sh git-rebase.sh git-rebase--interactive.sh \
@@ -330,6 +330,7 @@ BUILTIN_OBJS = \
 	builtin-check-attr.o \
 	builtin-checkout-index.o \
 	builtin-check-ref-format.o \
+	builtin-clean.o \
 	builtin-commit-tree.o \
 	builtin-count-objects.o \
 	builtin-describe.o \
diff --git a/builtin-clean.c b/builtin-clean.c
new file mode 100644
index 0000000000..55658e742f
--- /dev/null
+++ b/builtin-clean.c
@@ -0,0 +1,154 @@
+/*
+ * "git clean" builtin command
+ *
+ * Copyright (C) 2007 Shawn Bohrer
+ *
+ * Based on git-clean.sh by Pavel Roskin
+ */
+
+#include "builtin.h"
+#include "cache.h"
+#include "dir.h"
+#include "parse-options.h"
+
+static int force;
+
+static const char *const builtin_clean_usage[] = {
+	"git-clean [-d] [-f] [-n] [-q] [-x | -X] [--] <paths>...",
+	NULL
+};
+
+static int git_clean_config(const char *var, const char *value)
+{
+	if (!strcmp(var, "clean.requireforce"))
+		force = !git_config_bool(var, value);
+	return 0;
+}
+
+int cmd_clean(int argc, const char **argv, const char *prefix)
+{
+	int j;
+	int show_only = 0, remove_directories = 0, quiet = 0, ignored = 0;
+	int ignored_only = 0, baselen = 0;
+	struct strbuf directory;
+	struct dir_struct dir;
+	const char *path, *base;
+	static const char **pathspec;
+	struct option options[] = {
+		OPT__QUIET(&quiet),
+		OPT__DRY_RUN(&show_only),
+		OPT_BOOLEAN('f', NULL, &force, "force"),
+		OPT_BOOLEAN('d', NULL, &remove_directories,
+				"remove whole directories"),
+		OPT_BOOLEAN('x', NULL, &ignored, "remove ignored files, too"),
+		OPT_BOOLEAN('X', NULL, &ignored_only,
+				"remove only ignored files"),
+		OPT_END()
+	};
+
+	git_config(git_clean_config);
+	argc = parse_options(argc, argv, options, builtin_clean_usage, 0);
+
+	memset(&dir, 0, sizeof(dir));
+	if (ignored_only) {
+		dir.show_ignored =1;
+		dir.exclude_per_dir = ".gitignore";
+	}
+
+	if (ignored && ignored_only)
+		die("-x and -X cannot be used together");
+
+	if (!show_only && !force)
+		die("clean.requireForce set and -n or -f not given; refusing to clean");
+
+	dir.show_other_directories = 1;
+
+	if (!ignored) {
+		dir.exclude_per_dir = ".gitignore";
+		if (!access(git_path("info/exclude"), F_OK)) {
+			char *exclude_path = git_path("info/exclude");
+			add_excludes_from_file(&dir, exclude_path);
+		}
+	}
+
+	pathspec = get_pathspec(prefix, argv);
+	read_cache();
+
+	/*
+	 * Calculate common prefix for the pathspec, and
+	 * use that to optimize the directory walk
+	 */
+	baselen = common_prefix(pathspec);
+	path = ".";
+	base = "";
+	if (baselen)
+		path = base = xmemdupz(*pathspec, baselen);
+	read_directory(&dir, path, base, baselen, pathspec);
+	strbuf_init(&directory, 0);
+
+	for (j = 0; j < dir.nr; ++j) {
+		struct dir_entry *ent = dir.entries[j];
+		int len, pos, specs;
+		struct cache_entry *ce;
+		struct stat st;
+		char *seen;
+
+		/*
+		 * 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 (!lstat(ent->name, &st) && (S_ISDIR(st.st_mode))) {
+			int matched_path = 0;
+			strbuf_addstr(&directory, ent->name);
+			if (pathspec) {
+				for (specs =0; pathspec[specs]; ++specs)
+					/* nothing */;
+				seen = xcalloc(specs, 1);
+				/* Check if directory was explictly passed as
+				 * pathspec.  If so we want to remove it */
+				if (match_pathspec(pathspec, ent->name, ent->len,
+						   baselen, seen))
+					matched_path = 1;
+				free(seen);
+			}
+			if (show_only && (remove_directories || matched_path)) {
+				printf("Would remove %s\n", directory.buf);
+			} else if (quiet && (remove_directories || matched_path)) {
+				remove_dir_recursively(&directory, 0);
+			} else if (remove_directories || matched_path) {
+				printf("Removing %s\n", directory.buf);
+				remove_dir_recursively(&directory, 0);
+			} else if (show_only) {
+				printf("Would not remove %s\n", directory.buf);
+			} else {
+				printf("Not removing %s\n", directory.buf);
+			}
+			strbuf_reset(&directory);
+		} else {
+			if (show_only) {
+				printf("Would remove %s\n", ent->name);
+				continue;
+			} else if (!quiet) {
+				printf("Removing %s\n", ent->name);
+			}
+			unlink(ent->name);
+		}
+	}
+
+	strbuf_release(&directory);
+	return 0;
+}
diff --git a/builtin.h b/builtin.h
index 9a6213af12..8248f293e6 100644
--- a/builtin.h
+++ b/builtin.h
@@ -24,6 +24,7 @@ extern int cmd_check_attr(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);
+extern int cmd_clean(int argc, const char **argv, const char *prefix);
 extern int cmd_commit_tree(int argc, const char **argv, const char *prefix);
 extern int cmd_count_objects(int argc, const char **argv, const char *prefix);
 extern int cmd_describe(int argc, const char **argv, const char *prefix);
diff --git a/git-clean.sh b/contrib/examples/git-clean.sh
index 01c95e9fe8..01c95e9fe8 100755
--- a/git-clean.sh
+++ b/contrib/examples/git-clean.sh
diff --git a/git.c b/git.c
index 7604319b5a..0c0483f815 100644
--- a/git.c
+++ b/git.c
@@ -293,6 +293,7 @@ static void handle_internal_command(int argc, const char **argv)
 		{ "check-attr", cmd_check_attr, RUN_SETUP | NEED_WORK_TREE },
 		{ "cherry", cmd_cherry, RUN_SETUP },
 		{ "cherry-pick", cmd_cherry_pick, RUN_SETUP | NEED_WORK_TREE },
+		{ "clean", cmd_clean, RUN_SETUP | NEED_WORK_TREE },
 		{ "commit-tree", cmd_commit_tree, RUN_SETUP },
 		{ "config", cmd_config },
 		{ "count-objects", cmd_count_objects, RUN_SETUP },