Merge branch 'lt/dirwalk' into jc/dirwalk-n-cache-tree

This commit is what this branch is all about.  It records the
evil merge needed to adjust built-in git-add and git-rm for
the cache-tree extension.

* lt/dirwalk:
  Add builtin "git rm" command
  Move pathspec matching from builtin-add.c into dir.c
  Prevent bogus paths from being added to the index.
  builtin-add: fix unmatched pathspec warnings.
  Remove old "git-add.sh" remnants
  builtin-add: warn on unmatched pathspecs
  Do "git add" as a builtin
  Clean up git-ls-file directory walking library interface
  libify git-ls-files directory traversal

Conflicts:

	Makefile
	builtin.h
	git.c
	update-index.c

Makefile

@@ -113,14 +113,14 @@ SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 ### --- END CONFIGURATION SECTION ---
 
 SCRIPT_SH = \
-	git-add.sh git-bisect.sh git-branch.sh git-checkout.sh \
+	git-bisect.sh git-branch.sh git-checkout.sh \
 	git-cherry.sh git-clean.sh git-clone.sh git-commit.sh \
 	git-fetch.sh \
 	git-format-patch.sh git-ls-remote.sh \
 	git-merge-one-file.sh git-parse-remote.sh \
 	git-prune.sh git-pull.sh git-rebase.sh \
 	git-repack.sh git-request-pull.sh git-reset.sh \
-	git-resolve.sh git-revert.sh git-rm.sh git-sh-setup.sh \
+	git-resolve.sh git-revert.sh git-sh-setup.sh \
 	git-tag.sh git-verify-tag.sh \
 	git-applymbox.sh git-applypatch.sh git-am.sh \
 	git-merge.sh git-merge-stupid.sh git-merge-octopus.sh \
@@ -170,7 +170,8 @@ PROGRAMS = \
 
 BUILT_INS = git-log$X git-whatchanged$X git-show$X \
 	git-count-objects$X git-diff$X git-push$X \
-	git-grep$X git-rev-list$X git-check-ref-format$X \
+	git-grep$X git-add$X git-rm$X git-rev-list$X \
+	git-check-ref-format$X \
 	git-init-db$X
 
 # what 'all' will build and 'install' will install, in gitexecdir
@@ -200,7 +201,7 @@ LIB_H = \
 	blob.h cache.h commit.h csum-file.h delta.h \
 	diff.h object.h pack.h pkt-line.h quote.h refs.h \
 	run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \
-	tree-walk.h log-tree.h
+	tree-walk.h log-tree.h dir.h
 
 DIFF_OBJS = \
 	diff.o diff-lib.o diffcore-break.o diffcore-order.o \
@@ -211,16 +212,16 @@ LIB_OBJS = \
 	blob.o commit.o connect.o csum-file.o cache-tree.o base85.o \
 	date.o diff-delta.o entry.o exec_cmd.o ident.o index.o \
 	object.o pack-check.o patch-delta.o path.o pkt-line.o \
-	quote.o read-cache.o refs.o run-command.o \
+	quote.o read-cache.o refs.o run-command.o dir.o \
 	server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \
 	tag.o tree.o usage.o config.o environment.o ctype.o copy.o \
 	fetch-clone.o revision.o pager.o tree-walk.o xdiff-interface.o \
 	$(DIFF_OBJS)
 
 BUILTIN_OBJS = \
 	builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \
-	builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \
-	builtin-init-db.o
+	builtin-grep.o builtin-add.o builtin-rev-list.o builtin-check-ref-format.o \
+	builtin-rm.o builtin-init-db.o
 
 GITLIBS = $(LIB_FILE) $(XDIFF_LIB)
 LIBS = $(GITLIBS) -lz

builtin-add.c

@@ -0,0 +1,189 @@
+/*
+ * "git add" builtin command
+ *
+ * Copyright (C) 2006 Linus Torvalds
+ */
+#include <fnmatch.h>
+
+#include "cache.h"
+#include "builtin.h"
+#include "dir.h"
+#include "cache-tree.h"
+
+static const char builtin_add_usage[] =
+"git-add [-n] [-v] <filepattern>...";
+
+static void prune_directory(struct dir_struct *dir, const char **pathspec, int prefix)
+{
+	char *seen;
+	int i, specs;
+	struct dir_entry **src, **dst;
+
+	for (specs = 0; pathspec[specs];  specs++)
+		/* nothing */;
+	seen = xmalloc(specs);
+	memset(seen, 0, specs);
+
+	src = dst = dir->entries;
+	i = dir->nr;
+	while (--i >= 0) {
+		struct dir_entry *entry = *src++;
+		if (!match_pathspec(pathspec, entry->name, entry->len, prefix, seen)) {
+			free(entry);
+			continue;
+		}
+		*dst++ = entry;
+	}
+	dir->nr = dst - dir->entries;
+
+	for (i = 0; i < specs; i++) {
+		struct stat st;
+		const char *match;
+		if (seen[i])
+			continue;
+
+		/* Existing file? We must have ignored it */
+		match = pathspec[i];
+		if (!match[0] || !lstat(match, &st))
+			continue;
+		die("pathspec '%s' did not match any files", match);
+	}
+}
+
+static void fill_directory(struct dir_struct *dir, const char **pathspec)
+{
+	const char *path, *base;
+	int baselen;
+
+	/* Set up the default git porcelain excludes */
+	memset(dir, 0, sizeof(*dir));
+	dir->exclude_per_dir = ".gitignore";
+	path = git_path("info/exclude");
+	if (!access(path, R_OK))
+		add_excludes_from_file(dir, path);
+
+	/*
+	 * Calculate common prefix for the pathspec, and
+	 * use that to optimize the directory walk
+	 */
+	baselen = common_prefix(pathspec);
+	path = ".";
+	base = "";
+	if (baselen) {
+		char *common = xmalloc(baselen + 1);
+		common = xmalloc(baselen + 1);
+		memcpy(common, *pathspec, baselen);
+		common[baselen] = 0;
+		path = base = common;
+	}
+
+	/* Read the directory and prune it */
+	read_directory(dir, path, base, baselen);
+	if (pathspec)
+		prune_directory(dir, pathspec, baselen);
+}
+
+static int add_file_to_index(const char *path, int verbose)
+{
+	int size, namelen;
+	struct stat st;
+	struct cache_entry *ce;
+
+	if (lstat(path, &st))
+		die("%s: unable to stat (%s)", path, strerror(errno));
+
+	if (!S_ISREG(st.st_mode) && !S_ISLNK(st.st_mode))
+		die("%s: can only add regular files or symbolic links", path);
+
+	namelen = strlen(path);
+	size = cache_entry_size(namelen);
+	ce = xcalloc(1, size);
+	memcpy(ce->name, path, namelen);
+	ce->ce_flags = htons(namelen);
+	fill_stat_cache_info(ce, &st);
+
+	ce->ce_mode = create_ce_mode(st.st_mode);
+	if (!trust_executable_bit) {
+		/* If there is an existing entry, pick the mode bits
+		 * from it.
+		 */
+		int pos = cache_name_pos(path, namelen);
+		if (pos >= 0)
+			ce->ce_mode = active_cache[pos]->ce_mode;
+	}
+
+	if (index_path(ce->sha1, path, &st, 1))
+		die("unable to index file %s", path);
+	if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD))
+		die("unable to add %s to index",path);
+	if (verbose)
+		printf("add '%s'\n", path);
+	cache_tree_invalidate_path(active_cache_tree, path);
+	return 0;
+}
+
+static struct cache_file cache_file;
+
+int cmd_add(int argc, const char **argv, char **envp)
+{
+	int i, newfd;
+	int verbose = 0, show_only = 0;
+	const char *prefix = setup_git_directory();
+	const char **pathspec;
+	struct dir_struct dir;
+
+	git_config(git_default_config);
+
+	newfd = hold_index_file_for_update(&cache_file, get_index_file());
+	if (newfd < 0)
+		die("unable to create new cachefile");
+
+	if (read_cache() < 0)
+		die("index file corrupt");
+
+	for (i = 1; i < argc; i++) {
+		const char *arg = argv[i];
+
+		if (arg[0] != '-')
+			break;
+		if (!strcmp(arg, "--")) {
+			i++;
+			break;
+		}
+		if (!strcmp(arg, "-n")) {
+			show_only = 1;
+			continue;
+		}
+		if (!strcmp(arg, "-v")) {
+			verbose = 1;
+			continue;
+		}
+		die(builtin_add_usage);
+	}
+	git_config(git_default_config);
+	pathspec = get_pathspec(prefix, argv + i);
+
+	fill_directory(&dir, pathspec);
+
+	if (show_only) {
+		const char *sep = "", *eof = "";
+		for (i = 0; i < dir.nr; i++) {
+			printf("%s%s", sep, dir.entries[i]->name);
+			sep = " ";
+			eof = "\n";
+		}
+		fputs(eof, stdout);
+		return 0;
+	}
+
+	for (i = 0; i < dir.nr; i++)
+		add_file_to_index(dir.entries[i]->name, verbose);
+
+	if (active_cache_changed) {
+		if (write_cache(newfd, active_cache, active_nr) ||
+		    commit_index_file(&cache_file))
+			die("Unable to write new index file");
+	}
+
+	return 0;
+}

builtin-rm.c

@@ -0,0 +1,151 @@
+/*
+ * "git rm" builtin command
+ *
+ * Copyright (C) Linus Torvalds 2006
+ */
+#include "cache.h"
+#include "builtin.h"
+#include "dir.h"
+
+static const char builtin_rm_usage[] =
+"git-rm [-n] [-v] [-f] <filepattern>...";
+
+static struct {
+	int nr, alloc;
+	const char **name;
+} list;
+
+static void add_list(const char *name)
+{
+	if (list.nr >= list.alloc) {
+		list.alloc = alloc_nr(list.alloc);
+		list.name = xrealloc(list.name, list.alloc * sizeof(const char *));
+	}
+	list.name[list.nr++] = name;
+}
+
+static int remove_file(const char *name)
+{
+	int ret;
+	char *slash;
+
+	ret = unlink(name);
+	if (!ret && (slash = strrchr(name, '/'))) {
+		char *n = strdup(name);
+		do {
+			n[slash - name] = 0;
+			name = n;
+		} while (!rmdir(name) && (slash = strrchr(name, '/')));
+	}
+	return ret;
+}
+
+static struct cache_file cache_file;
+
+int cmd_rm(int argc, const char **argv, char **envp)
+{
+	int i, newfd;
+	int verbose = 0, show_only = 0, force = 0;
+	const char *prefix = setup_git_directory();
+	const char **pathspec;
+	char *seen;
+
+	git_config(git_default_config);
+
+	newfd = hold_index_file_for_update(&cache_file, get_index_file());
+	if (newfd < 0)
+		die("unable to create new index file");
+
+	if (read_cache() < 0)
+		die("index file corrupt");
+
+	for (i = 1 ; i < argc ; i++) {
+		const char *arg = argv[i];
+
+		if (*arg != '-')
+			break;
+		if (!strcmp(arg, "--")) {
+			i++;
+			break;
+		}
+		if (!strcmp(arg, "-n")) {
+			show_only = 1;
+			continue;
+		}
+		if (!strcmp(arg, "-v")) {
+			verbose = 1;
+			continue;
+		}
+		if (!strcmp(arg, "-f")) {
+			force = 1;
+			continue;
+		}
+		die(builtin_rm_usage);
+	}
+	pathspec = get_pathspec(prefix, argv + i);
+
+	seen = NULL;
+	if (pathspec) {
+		for (i = 0; pathspec[i] ; i++)
+			/* nothing */;
+		seen = xmalloc(i);
+		memset(seen, 0, i);
+	}
+
+	for (i = 0; i < active_nr; i++) {
+		struct cache_entry *ce = active_cache[i];
+		if (!match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, seen))
+			continue;
+		add_list(ce->name);
+	}
+
+	if (pathspec) {
+		const char *match;
+		for (i = 0; (match = pathspec[i]) != NULL ; i++) {
+			if (*match && !seen[i])
+				die("pathspec '%s' did not match any files", match);
+		}
+	}
+
+	/*
+	 * First remove the names from the index: we won't commit
+	 * the index unless all of them succeed
+	 */
+	for (i = 0; i < list.nr; i++) {
+		const char *path = list.name[i];
+		printf("rm '%s'\n", path);
+
+		if (remove_file_from_cache(path))
+			die("git rm: unable to remove %s", path);
+		cache_tree_invalidate_path(active_cache_tree, path);
+	}
+
+	/*
+	 * Then, if we used "-f", remove the filenames from the
+	 * workspace. If we fail to remove the first one, we
+	 * abort the "git rm" (but once we've successfully removed
+	 * any file at all, we'll go ahead and commit to it all:
+	 * by then we've already committed ourself and can't fail
+	 * in the middle)
+	 */
+	if (force) {
+		int removed = 0;
+		for (i = 0; i < list.nr; i++) {
+			const char *path = list.name[i];
+			if (!remove_file(path)) {
+				removed = 1;
+				continue;
+			}
+			if (!removed)
+				die("git rm: %s: %s", path, strerror(errno));
+		}
+	}
+
+	if (active_cache_changed) {
+		if (write_cache(newfd, active_cache, active_nr) ||
+		    commit_index_file(&cache_file))
+			die("Unable to write new index file");
+	}
+
+	return 0;
+}