Merge branch 'js/mv'

* js/mv:
  builtin git-mv: support moving directories
  Make git-mv a builtin
  Extract helper bits from c-merge-recursive work

11 files changed, 522 insertions, 340 deletions

diff --git a/Makefile b/Makefile
index 814c5642e7..e9dce268f8 100644
--- a/Makefile
+++ b/Makefile
@@ -151,7 +151,7 @@ SCRIPT_PERL = \
 	git-archimport.perl git-cvsimport.perl git-relink.perl \
 	git-shortlog.perl git-rerere.perl \
 	git-annotate.perl git-cvsserver.perl \
-	git-svnimport.perl git-mv.perl git-cvsexportcommit.perl \
+	git-svnimport.perl git-cvsexportcommit.perl \
 	git-send-email.perl git-svn.perl
 
 SCRIPT_PYTHON = \
@@ -192,7 +192,7 @@ BUILT_INS = git-log$X git-whatchanged$X git-show$X git-update-ref$X \
 	git-read-tree$X git-commit-tree$X git-write-tree$X \
 	git-apply$X git-show-branch$X git-diff-files$X git-update-index$X \
 	git-diff-index$X git-diff-stages$X git-diff-tree$X git-cat-file$X \
-	git-fmt-merge-msg$X git-prune$X
+	git-fmt-merge-msg$X git-prune$X git-mv$X
 
 # what 'all' will build and 'install' will install, in gitexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS)
@@ -221,7 +221,7 @@ 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 dir.h
+	tree-walk.h log-tree.h dir.h path-list.h
 
 DIFF_OBJS = \
 	diff.o diff-lib.o diffcore-break.o diffcore-order.o \
@@ -236,7 +236,7 @@ LIB_OBJS = \
 	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 \
-	alloc.o merge-file.o $(DIFF_OBJS)
+	alloc.o merge-file.o path-list.o $(DIFF_OBJS)
 
 BUILTIN_OBJS = \
 	builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \
@@ -248,7 +248,8 @@ BUILTIN_OBJS = \
 	builtin-apply.o builtin-show-branch.o builtin-diff-files.o \
 	builtin-diff-index.o builtin-diff-stages.o builtin-diff-tree.o \
 	builtin-cat-file.o builtin-mailsplit.o builtin-stripspace.o \
-	builtin-update-ref.o builtin-fmt-merge-msg.o builtin-prune.o
+	builtin-update-ref.o builtin-fmt-merge-msg.o builtin-prune.o \
+	builtin-mv.o
 
 GITLIBS = $(LIB_FILE) $(XDIFF_LIB)
 LIBS = $(GITLIBS) -lz
diff --git a/builtin-add.c b/builtin-add.c
index 3a73a173f7..72d2853176 100644
--- a/builtin-add.c
+++ b/builtin-add.c
@@ -82,45 +82,6 @@ static void fill_directory(struct dir_struct *dir, const char **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 lock_file lock_file;
 
 int cmd_add(int argc, const char **argv, char **envp)
@@ -159,7 +120,6 @@ int cmd_add(int argc, const char **argv, char **envp)
 		}
 		die(builtin_add_usage);
 	}
-	git_config(git_default_config);
 	pathspec = get_pathspec(prefix, argv + i);
 
 	fill_directory(&dir, pathspec);
diff --git a/builtin-mv.c b/builtin-mv.c
new file mode 100644
index 0000000000..42c2e39b21
--- /dev/null
+++ b/builtin-mv.c
@@ -0,0 +1,298 @@
+/*
+ * "git mv" builtin command
+ *
+ * Copyright (C) 2006 Johannes Schindelin
+ */
+#include <fnmatch.h>
+
+#include "cache.h"
+#include "builtin.h"
+#include "dir.h"
+#include "cache-tree.h"
+#include "path-list.h"
+
+static const char builtin_mv_usage[] =
+"git-mv [-n] [-f] (<source> <destination> | [-k] <source>... <destination>)";
+
+static const char **copy_pathspec(const char *prefix, const char **pathspec,
+				  int count, int base_name)
+{
+	const char **result = xmalloc((count + 1) * sizeof(const char *));
+	memcpy(result, pathspec, count * sizeof(const char *));
+	result[count] = NULL;
+	if (base_name) {
+		int i;
+		for (i = 0; i < count; i++) {
+			const char *last_slash = strrchr(result[i], '/');
+			if (last_slash)
+				result[i] = last_slash + 1;
+		}
+	}
+	return get_pathspec(prefix, result);
+}
+
+static void show_list(const char *label, struct path_list *list)
+{
+	if (list->nr > 0) {
+		int i;
+		printf("%s", label);
+		for (i = 0; i < list->nr; i++)
+			printf("%s%s", i > 0 ? ", " : "", list->items[i].path);
+		putchar('\n');
+	}
+}
+
+static const char *add_slash(const char *path)
+{
+	int len = strlen(path);
+	if (path[len - 1] != '/') {
+		char *with_slash = xmalloc(len + 2);
+		memcpy(with_slash, path, len);
+		strcat(with_slash + len, "/");
+		return with_slash;
+	}
+	return path;
+}
+
+static struct lock_file lock_file;
+
+int cmd_mv(int argc, const char **argv, char **envp)
+{
+	int i, newfd, count;
+	int verbose = 0, show_only = 0, force = 0, ignore_errors = 0;
+	const char *prefix = setup_git_directory();
+	const char **source, **destination, **dest_path;
+	enum update_mode { BOTH = 0, WORKING_DIRECTORY, INDEX } *modes;
+	struct stat st;
+	struct path_list overwritten = {NULL, 0, 0, 0};
+	struct path_list src_for_dst = {NULL, 0, 0, 0};
+	struct path_list added = {NULL, 0, 0, 0};
+	struct path_list deleted = {NULL, 0, 0, 0};
+	struct path_list changed = {NULL, 0, 0, 0};
+
+	git_config(git_default_config);
+
+	newfd = hold_lock_file_for_update(&lock_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[0] != '-')
+			break;
+		if (!strcmp(arg, "--")) {
+			i++;
+			break;
+		}
+		if (!strcmp(arg, "-n")) {
+			show_only = 1;
+			continue;
+		}
+		if (!strcmp(arg, "-f")) {
+			force = 1;
+			continue;
+		}
+		if (!strcmp(arg, "-k")) {
+			ignore_errors = 1;
+			continue;
+		}
+		die(builtin_mv_usage);
+	}
+	count = argc - i - 1;
+	if (count < 1)
+		usage(builtin_mv_usage);
+
+	source = copy_pathspec(prefix, argv + i, count, 0);
+	modes = xcalloc(count, sizeof(enum update_mode));
+	dest_path = copy_pathspec(prefix, argv + argc - 1, 1, 0);
+
+	if (!lstat(dest_path[0], &st) &&
+			S_ISDIR(st.st_mode)) {
+		dest_path[0] = add_slash(dest_path[0]);
+		destination = copy_pathspec(dest_path[0], argv + i, count, 1);
+	} else {
+		if (count != 1)
+			usage(builtin_mv_usage);
+		destination = dest_path;
+	}
+
+	/* Checking */
+	for (i = 0; i < count; i++) {
+		const char *bad = NULL;
+
+		if (show_only)
+			printf("Checking rename of '%s' to '%s'\n",
+				source[i], destination[i]);
+
+		if (lstat(source[i], &st) < 0)
+			bad = "bad source";
+
+		if (S_ISDIR(st.st_mode)) {
+			const char *dir = source[i], *dest_dir = destination[i];
+			int first, last, len = strlen(dir);
+
+			if (lstat(dest_dir, &st) == 0) {
+				bad = "cannot move directory over file";
+				goto next;
+			}
+
+			modes[i] = WORKING_DIRECTORY;
+
+			first = cache_name_pos(source[i], len);
+			if (first >= 0)
+				die ("Huh? %s/ is in index?", dir);
+
+			first = -1 - first;
+			for (last = first; last < active_nr; last++) {
+				const char *path = active_cache[last]->name;
+				if (strncmp(path, dir, len) || path[len] != '/')
+					break;
+			}
+
+			if (last - first < 1)
+				bad = "source directory is empty";
+			else if (!bad) {
+				int j, dst_len = strlen(dest_dir);
+
+				if (last - first > 0) {
+					source = realloc(source,
+							(count + last - first)
+							* sizeof(char *));
+					destination = realloc(destination,
+							(count + last - first)
+							* sizeof(char *));
+					modes = realloc(modes,
+							(count + last - first)
+							* sizeof(enum update_mode));
+				}
+
+				dest_dir = add_slash(dest_dir);
+
+				for (j = 0; j < last - first; j++) {
+					const char *path =
+						active_cache[first + j]->name;
+					source[count + j] = path;
+					destination[count + j] =
+						prefix_path(dest_dir, dst_len,
+							path + len);
+					modes[count + j] = INDEX;
+				}
+				count += last - first;
+			}
+
+			goto next;
+		}
+
+		if (!bad && lstat(destination[i], &st) == 0) {
+			bad = "destination exists";
+			if (force) {
+				/*
+				 * only files can overwrite each other:
+				 * check both source and destination
+				 */
+				if (S_ISREG(st.st_mode)) {
+					fprintf(stderr, "Warning: %s;"
+							" will overwrite!\n",
+							bad);
+					bad = NULL;
+					path_list_insert(destination[i],
+							&overwritten);
+				} else
+					bad = "Cannot overwrite";
+			}
+		}
+
+		if (!bad &&
+		    !strncmp(destination[i], source[i], strlen(source[i])))
+			bad = "can not move directory into itself";
+
+		if (!bad && cache_name_pos(source[i], strlen(source[i])) < 0)
+			bad = "not under version control";
+
+		if (!bad) {
+			if (path_list_has_path(&src_for_dst, destination[i]))
+				bad = "multiple sources for the same target";
+			else
+				path_list_insert(destination[i], &src_for_dst);
+		}
+
+next:
+		if (bad) {
+			if (ignore_errors) {
+				if (--count > 0) {
+					memmove(source + i, source + i + 1,
+						(count - i) * sizeof(char *));
+					memmove(destination + i,
+						destination + i + 1,
+						(count - i) * sizeof(char *));
+				}
+			} else
+				die ("%s, source=%s, destination=%s",
+				     bad, source[i], destination[i]);
+		}
+	}
+
+	for (i = 0; i < count; i++) {
+		if (show_only || verbose)
+			printf("Renaming %s to %s\n",
+			       source[i], destination[i]);
+		if (!show_only && modes[i] != INDEX &&
+		    rename(source[i], destination[i]) < 0 &&
+		    !ignore_errors)
+			die ("renaming %s failed: %s",
+			     source[i], strerror(errno));
+
+		if (modes[i] == WORKING_DIRECTORY)
+			continue;
+
+		if (cache_name_pos(source[i], strlen(source[i])) >= 0) {
+			path_list_insert(source[i], &deleted);
+
+			/* destination can be a directory with 1 file inside */
+			if (path_list_has_path(&overwritten, destination[i]))
+				path_list_insert(destination[i], &changed);
+			else
+				path_list_insert(destination[i], &added);
+		} else
+			path_list_insert(destination[i], &added);
+	}
+
+        if (show_only) {
+		show_list("Changed  : ", &changed);
+		show_list("Adding   : ", &added);
+		show_list("Deleting : ", &deleted);
+	} else {
+		for (i = 0; i < changed.nr; i++) {
+			const char *path = changed.items[i].path;
+			int i = cache_name_pos(path, strlen(path));
+			struct cache_entry *ce = active_cache[i];
+
+			if (i < 0)
+				die ("Huh? Cache entry for %s unknown?", path);
+			refresh_cache_entry(ce, 0);
+		}
+
+		for (i = 0; i < added.nr; i++) {
+			const char *path = added.items[i].path;
+			add_file_to_index(path, verbose);
+		}
+
+		for (i = 0; i < deleted.nr; i++) {
+			const char *path = deleted.items[i].path;
+			remove_file_from_cache(path);
+		}
+
+		if (active_cache_changed) {
+			if (write_cache(newfd, active_cache, active_nr) ||
+			    close(newfd) ||
+			    commit_lock_file(&lock_file))
+				die("Unable to write new index file");
+		}
+	}
+
+	return 0;
+}
diff --git a/builtin.h b/builtin.h
index 5339d8627f..6f3a43957c 100644
--- a/builtin.h
+++ b/builtin.h
@@ -52,6 +52,7 @@ extern int cmd_rev_parse(int argc, const char **argv, char **envp);
 extern int cmd_update_index(int argc, const char **argv, char **envp);
 extern int cmd_update_ref(int argc, const char **argv, char **envp);
 extern int cmd_fmt_merge_msg(int argc, const char **argv, char **envp);
+extern int cmd_mv(int argc, const char **argv, char **envp);
 
 extern int cmd_write_tree(int argc, const char **argv, char **envp);
 extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix);
diff --git a/cache.h b/cache.h
index eee5fc9f8d..c575b8a996 100644
--- a/cache.h
+++ b/cache.h
@@ -115,6 +115,7 @@ static inline unsigned int create_ce_mode(unsigned int mode)
 extern struct cache_entry **active_cache;
 extern unsigned int active_nr, active_alloc, active_cache_changed;
 extern struct cache_tree *active_cache_tree;
+extern int cache_errno;
 
 #define GIT_DIR_ENVIRONMENT "GIT_DIR"
 #define DEFAULT_GIT_DIR_ENVIRONMENT ".git"
@@ -142,6 +143,7 @@ extern void verify_non_filename(const char *prefix, const char *name);
 
 /* Initialize and use the cache information */
 extern int read_cache(void);
+extern int read_cache_from(const char *path);
 extern int write_cache(int newfd, struct cache_entry **cache, int entries);
 extern int verify_path(const char *path);
 extern int cache_name_pos(const char *name, int namelen);
@@ -149,8 +151,10 @@ extern int cache_name_pos(const char *name, int namelen);
 #define ADD_CACHE_OK_TO_REPLACE 2	/* Ok to replace file/directory */
 #define ADD_CACHE_SKIP_DFCHECK 4	/* Ok to skip DF conflict checks */
 extern int add_cache_entry(struct cache_entry *ce, int option);
+extern struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really);
 extern int remove_cache_entry_at(int pos);
 extern int remove_file_from_cache(const char *path);
+extern int add_file_to_index(const char *path, int verbose);
 extern int ce_same_name(struct cache_entry *a, struct cache_entry *b);
 extern int ce_match_stat(struct cache_entry *ce, struct stat *st, int);
 extern int ce_modified(struct cache_entry *ce, struct stat *st, int);
diff --git a/git-mv.perl b/git-mv.perl
deleted file mode 100755
index 75aa8feeb6..0000000000
--- a/git-mv.perl
+++ /dev/null
@@ -1,250 +0,0 @@
-#!/usr/bin/perl
-#
-# Copyright 2005, Ryan Anderson <ryan@michonline.com>
-#                 Josef Weidendorfer <Josef.Weidendorfer@gmx.de>
-#
-# This file is licensed under the GPL v2, or a later version
-# at the discretion of Linus Torvalds.
-
-
-use warnings;
-use strict;
-use Getopt::Std;
-
-sub usage() {
-	print <<EOT;
-$0 [-f] [-n] <source> <destination>
-$0 [-f] [-n] [-k] <source> ... <destination directory>
-EOT
-	exit(1);
-}
-
-our ($opt_n, $opt_f, $opt_h, $opt_k, $opt_v);
-getopts("hnfkv") || usage;
-usage() if $opt_h;
-@ARGV >= 1 or usage;
-
-my $GIT_DIR = `git rev-parse --git-dir`;
-exit 1 if $?; # rev-parse would have given "not a git dir" message.
-chomp($GIT_DIR);
-
-my (@srcArgs, @dstArgs, @srcs, @dsts);
-my ($src, $dst, $base, $dstDir);
-
-# remove any trailing slash in arguments
-for (@ARGV) { s/\/*$//; }
-
-my $argCount = scalar @ARGV;
-if (-d $ARGV[$argCount-1]) {
-	$dstDir = $ARGV[$argCount-1];
-	@srcArgs = @ARGV[0..$argCount-2];
-
-	foreach $src (@srcArgs) {
-		$base = $src;
-		$base =~ s/^.*\///;
-		$dst = "$dstDir/". $base;
-		push @dstArgs, $dst;
-	}
-}
-else {
-    if ($argCount < 2) {
-	print "Error: need at least two arguments\n";
-	exit(1);
-    }
-    if ($argCount > 2) {
-	print "Error: moving to directory '"
-	    . $ARGV[$argCount-1]
-	    . "' not possible; not existing\n";
-	exit(1);
-    }
-    @srcArgs = ($ARGV[0]);
-    @dstArgs = ($ARGV[1]);
-    $dstDir = "";
-}
-
-my $subdir_prefix = `git rev-parse --show-prefix`;
-chomp($subdir_prefix);
-
-# run in git base directory, so that git-ls-files lists all revisioned files
-chdir "$GIT_DIR/..";
-
-# normalize paths, needed to compare against versioned files and update-index
-# also, this is nicer to end-users by doing ".//a/./b/.//./c" ==> "a/b/c"
-for (@srcArgs, @dstArgs) {
-    # prepend git prefix as we run from base directory
-    $_ = $subdir_prefix.$_;
-    s|^\./||;
-    s|/\./|/| while (m|/\./|);
-    s|//+|/|g;
-    # Also "a/b/../c" ==> "a/c"
-    1 while (s,(^|/)[^/]+/\.\./,$1,);
-}
-
-my (@allfiles,@srcfiles,@dstfiles);
-my $safesrc;
-my (%overwritten, %srcForDst);
-
-$/ = "\0";
-open(F, 'git-ls-files -z |')
-        or die "Failed to open pipe from git-ls-files: " . $!;
-
-@allfiles = map { chomp; $_; } <F>;
-close(F);
-
-
-my ($i, $bad);
-while(scalar @srcArgs > 0) {
-    $src = shift @srcArgs;
-    $dst = shift @dstArgs;
-    $bad = "";
-
-    for ($src, $dst) {
-	# Be nicer to end-users by doing ".//a/./b/.//./c" ==> "a/b/c"
-	s|^\./||;
-	s|/\./|/| while (m|/\./|);
-	s|//+|/|g;
-	# Also "a/b/../c" ==> "a/c"
-	1 while (s,(^|/)[^/]+/\.\./,$1,);
-    }
-
-    if ($opt_v) {
-	print "Checking rename of '$src' to '$dst'\n";
-    }
-
-    unless (-f $src || -l $src || -d $src) {
-	$bad = "bad source '$src'";
-    }
-
-    $safesrc = quotemeta($src);
-    @srcfiles = grep /^$safesrc(\/|$)/, @allfiles;
-
-    $overwritten{$dst} = 0;
-    if (($bad eq "") && -e $dst) {
-	$bad = "destination '$dst' already exists";
-	if ($opt_f) {
-	    # only files can overwrite each other: check both source and destination
-	    if (-f $dst && (scalar @srcfiles == 1)) {
-		print "Warning: $bad; will overwrite!\n";
-		$bad = "";
-		$overwritten{$dst} = 1;
-	    }
-	    else {
-		$bad = "Can not overwrite '$src' with '$dst'";
-	    }
-	}
-    }
-    
-    if (($bad eq "") && ($dst =~ /^$safesrc\//)) {
-	$bad = "can not move directory '$src' into itself";
-    }
-
-    if ($bad eq "") {
-        if (scalar @srcfiles == 0) {
-	    $bad = "'$src' not under version control";
-	}
-    }
-
-    if ($bad eq "") {
-       if (defined $srcForDst{$dst}) {
-           $bad = "can not move '$src' to '$dst'; already target of ";
-           $bad .= "'".$srcForDst{$dst}."'";
-       }
-       else {
-           $srcForDst{$dst} = $src;
-       }
-    }
-
-    if ($bad ne "") {
-	if ($opt_k) {
-	    print "Warning: $bad; skipping\n";
-	    next;
-	}
-	print "Error: $bad\n";
-	exit(1);
-    }
-    push @srcs, $src;
-    push @dsts, $dst;
-}
-
-# Final pass: rename/move
-my (@deletedfiles,@addedfiles,@changedfiles);
-$bad = "";
-while(scalar @srcs > 0) {
-    $src = shift @srcs;
-    $dst = shift @dsts;
-
-    if ($opt_n || $opt_v) { print "Renaming $src to $dst\n"; }
-    if (!$opt_n) {
-	if (!rename($src,$dst)) {
-	    $bad = "renaming '$src' failed: $!";
-	    if ($opt_k) {
-		print "Warning: skipped: $bad\n";
-		$bad = "";
-		next;
-	    }
-	    last;
-	}
-    }
-
-    $safesrc = quotemeta($src);
-    @srcfiles = grep /^$safesrc(\/|$)/, @allfiles;
-    @dstfiles = @srcfiles;
-    s/^$safesrc(\/|$)/$dst$1/ for @dstfiles;
-
-    push @deletedfiles, @srcfiles;
-    if (scalar @srcfiles == 1) {
-	# $dst can be a directory with 1 file inside
-	if ($overwritten{$dst} ==1) {
-	    push @changedfiles, $dstfiles[0];
-
-	} else {
-	    push @addedfiles, $dstfiles[0];
-	}
-    }
-    else {
-	push @addedfiles, @dstfiles;
-    }
-}
-
-if ($opt_n) {
-    if (@changedfiles) {
-	print "Changed  : ". join(", ", @changedfiles) ."\n";
-    }
-    if (@addedfiles) {
-	print "Adding   : ". join(", ", @addedfiles) ."\n";
-    }
-    if (@deletedfiles) {
-	print "Deleting : ". join(", ", @deletedfiles) ."\n";
-    }
-}
-else {
-    if (@changedfiles) {
-	open(H, "| git-update-index -z --stdin")
-		or die "git-update-index failed to update changed files with code $!\n";
-	foreach my $fileName (@changedfiles) {
-		print H "$fileName\0";
-	}
-	close(H);
-    }
-    if (@addedfiles) {
-	open(H, "| git-update-index --add -z --stdin")
-		or die "git-update-index failed to add new names with code $!\n";
-	foreach my $fileName (@addedfiles) {
-		print H "$fileName\0";
-	}
-	close(H);
-    }
-    if (@deletedfiles) {
-	open(H, "| git-update-index --remove -z --stdin")
-		or die "git-update-index failed to remove old names with code $!\n";
-	foreach my $fileName (@deletedfiles) {
-		print H "$fileName\0";
-	}
-	close(H);
-    }
-}
-
-if ($bad ne "") {
-    print "Error: $bad\n";
-    exit(1);
-}
diff --git a/git.c b/git.c
index 885e1ce75b..4ea5efb7a5 100644
--- a/git.c
+++ b/git.c
@@ -259,6 +259,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "update-ref", cmd_update_ref },
 		{ "fmt-merge-msg", cmd_fmt_merge_msg },
 		{ "prune", cmd_prune },
+		{ "mv", cmd_mv },
 	};
 	int i;
 
diff --git a/path-list.c b/path-list.c
new file mode 100644
index 0000000000..f15a10de37
--- /dev/null
+++ b/path-list.c
@@ -0,0 +1,105 @@
+#include <stdio.h>
+#include "cache.h"
+#include "path-list.h"
+
+/* if there is no exact match, point to the index where the entry could be
+ * inserted */
+static int get_entry_index(const struct path_list *list, const char *path,
+		int *exact_match)
+{
+	int left = -1, right = list->nr;
+
+	while (left + 1 < right) {
+		int middle = (left + right) / 2;
+		int compare = strcmp(path, list->items[middle].path);
+		if (compare < 0)
+			right = middle;
+		else if (compare > 0)
+			left = middle;
+		else {
+			*exact_match = 1;
+			return middle;
+		}
+	}
+
+	*exact_match = 0;
+	return right;
+}
+
+/* returns -1-index if already exists */
+static int add_entry(struct path_list *list, const char *path)
+{
+	int exact_match;
+	int index = get_entry_index(list, path, &exact_match);
+
+	if (exact_match)
+		return -1 - index;
+
+	if (list->nr + 1 >= list->alloc) {
+		list->alloc += 32;
+		list->items = xrealloc(list->items, list->alloc
+				* sizeof(struct path_list_item));
+	}
+	if (index < list->nr)
+		memmove(list->items + index + 1, list->items + index,
+				(list->nr - index)
+				* sizeof(struct path_list_item));
+	list->items[index].path = list->strdup_paths ?
+		strdup(path) : (char *)path;
+	list->items[index].util = NULL;
+	list->nr++;
+
+	return index;
+}
+
+struct path_list_item *path_list_insert(const char *path, struct path_list *list)
+{
+	int index = add_entry(list, path);
+
+	if (index < 0)
+		index = 1 - index;
+
+	return list->items + index;
+}
+
+int path_list_has_path(const struct path_list *list, const char *path)
+{
+	int exact_match;
+	get_entry_index(list, path, &exact_match);
+	return exact_match;
+}
+
+struct path_list_item *path_list_lookup(const char *path, struct path_list *list)
+{
+	int exact_match, i = get_entry_index(list, path, &exact_match);
+	if (!exact_match)
+		return NULL;
+	return list->items + i;
+}
+
+void path_list_clear(struct path_list *list, int free_items)
+{
+	if (list->items) {
+		int i;
+		if (free_items)
+			for (i = 0; i < list->nr; i++) {
+				if (list->strdup_paths)
+					free(list->items[i].path);
+				if (list->items[i].util)
+					free(list->items[i].util);
+			}
+		free(list->items);
+	}
+	list->items = NULL;
+	list->nr = list->alloc = 0;
+}
+
+void print_path_list(const char *text, const struct path_list *p)
+{
+	int i;
+	if ( text )
+		printf("%s\n", text);
+	for (i = 0; i < p->nr; i++)
+		printf("%s:%p\n", p->items[i].path, p->items[i].util);
+}
+
diff --git a/path-list.h b/path-list.h
new file mode 100644
index 0000000000..d6401eaa35
--- /dev/null
+++ b/path-list.h
@@ -0,0 +1,22 @@
+#ifndef _PATH_LIST_H_
+#define _PATH_LIST_H_
+
+struct path_list_item {
+	char *path;
+	void *util;
+};
+struct path_list
+{
+	struct path_list_item *items;
+	unsigned int nr, alloc;
+	unsigned int strdup_paths:1;
+};
+
+void print_path_list(const char *text, const struct path_list *p);
+
+int path_list_has_path(const struct path_list *list, const char *path);
+void path_list_clear(struct path_list *list, int free_items);
+struct path_list_item *path_list_insert(const char *path, struct path_list *list);
+struct path_list_item *path_list_lookup(const char *path, struct path_list *list);
+
+#endif /* _PATH_LIST_H_ */
diff --git a/read-cache.c b/read-cache.c
index a50d3612c8..c0b031367b 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -24,6 +24,11 @@ unsigned int active_nr = 0, active_alloc = 0, active_cache_changed = 0;
 
 struct cache_tree *active_cache_tree = NULL;
 
+int cache_errno = 0;
+
+static void *cache_mmap = NULL;
+static size_t cache_mmap_size = 0;
+
 /*
  * This only updates the "non-critical" parts of the directory
  * cache, ie the parts that aren't tracked by GIT, and only used
@@ -314,6 +319,45 @@ int remove_file_from_cache(const char *path)
 	return 0;
 }
 
+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;
+}
+
 int ce_same_name(struct cache_entry *a, struct cache_entry *b)
 {
 	int len = ce_namelen(a);
@@ -577,22 +621,6 @@ int add_cache_entry(struct cache_entry *ce, int option)
 	return 0;
 }
 
-/* Three functions to allow overloaded pointer return; see linux/err.h */
-static inline void *ERR_PTR(long error)
-{
-	return (void *) error;
-}
-
-static inline long PTR_ERR(const void *ptr)
-{
-	return (long) ptr;
-}
-
-static inline long IS_ERR(const void *ptr)
-{
-	return (unsigned long)ptr > (unsigned long)-1000L;
-}
-
 /*
  * "refresh" does not calculate a new sha1 file or bring the
  * cache up-to-date for mode/content changes. But what it
@@ -604,14 +632,16 @@ static inline long IS_ERR(const void *ptr)
  * For example, you'd want to do this after doing a "git-read-tree",
  * to link up the stat cache details with the proper files.
  */
-static struct cache_entry *refresh_entry(struct cache_entry *ce, int really)
+struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really)
 {
 	struct stat st;
 	struct cache_entry *updated;
 	int changed, size;
 
-	if (lstat(ce->name, &st) < 0)
-		return ERR_PTR(-errno);
+	if (lstat(ce->name, &st) < 0) {
+		cache_errno = errno;
+		return NULL;
+	}
 
 	changed = ce_match_stat(ce, &st, really);
 	if (!changed) {
@@ -619,11 +649,13 @@ static struct cache_entry *refresh_entry(struct cache_entry *ce, int really)
 		    !(ce->ce_flags & htons(CE_VALID)))
 			; /* mark this one VALID again */
 		else
-			return NULL;
+			return ce;
 	}
 
-	if (ce_modified(ce, &st, really))
-		return ERR_PTR(-EINVAL);
+	if (ce_modified(ce, &st, really)) {
+		cache_errno = EINVAL;
+		return NULL;
+	}
 
 	size = ce_size(ce);
 	updated = xmalloc(size);
@@ -666,13 +698,13 @@ int refresh_cache(unsigned int flags)
 			continue;
 		}
 
-		new = refresh_entry(ce, really);
-		if (!new)
+		new = refresh_cache_entry(ce, really);
+		if (new == ce)
 			continue;
-		if (IS_ERR(new)) {
-			if (not_new && PTR_ERR(new) == -ENOENT)
+		if (!new) {
+			if (not_new && cache_errno == ENOENT)
 				continue;
-			if (really && PTR_ERR(new) == -EINVAL) {
+			if (really && cache_errno == EINVAL) {
 				/* If we are doing --really-refresh that
 				 * means the index is not valid anymore.
 				 */
@@ -729,39 +761,43 @@ static int read_index_extension(const char *ext, void *data, unsigned long sz)
 
 int read_cache(void)
 {
+	return read_cache_from(get_index_file());
+}
+
+/* remember to discard_cache() before reading a different cache! */
+int read_cache_from(const char *path)
+{
 	int fd, i;
 	struct stat st;
-	unsigned long size, offset;
-	void *map;
+	unsigned long offset;
 	struct cache_header *hdr;
 
 	errno = EBUSY;
-	if (active_cache)
+	if (cache_mmap)
 		return active_nr;
 
 	errno = ENOENT;
 	index_file_timestamp = 0;
-	fd = open(get_index_file(), O_RDONLY);
+	fd = open(path, O_RDONLY);
 	if (fd < 0) {
 		if (errno == ENOENT)
 			return 0;
 		die("index file open failed (%s)", strerror(errno));
 	}
 
-	size = 0; /* avoid gcc warning */
-	map = MAP_FAILED;
+	cache_mmap = MAP_FAILED;
 	if (!fstat(fd, &st)) {
-		size = st.st_size;
+		cache_mmap_size = st.st_size;
 		errno = EINVAL;
-		if (size >= sizeof(struct cache_header) + 20)
-			map = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
+		if (cache_mmap_size >= sizeof(struct cache_header) + 20)
+			cache_mmap = mmap(NULL, cache_mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
 	}
 	close(fd);
-	if (map == MAP_FAILED)
+	if (cache_mmap == MAP_FAILED)
 		die("index file mmap failed (%s)", strerror(errno));
 
-	hdr = map;
-	if (verify_hdr(hdr, size) < 0)
+	hdr = cache_mmap;
+	if (verify_hdr(hdr, cache_mmap_size) < 0)
 		goto unmap;
 
 	active_nr = ntohl(hdr->hdr_entries);
@@ -770,12 +806,12 @@ int read_cache(void)
 
 	offset = sizeof(*hdr);
 	for (i = 0; i < active_nr; i++) {
-		struct cache_entry *ce = (struct cache_entry *) ((char *) map + offset);
+		struct cache_entry *ce = (struct cache_entry *) ((char *) cache_mmap + offset);
 		offset = offset + ce_size(ce);
 		active_cache[i] = ce;
 	}
 	index_file_timestamp = st.st_mtime;
-	while (offset <= size - 20 - 8) {
+	while (offset <= cache_mmap_size - 20 - 8) {
 		/* After an array of active_nr index entries,
 		 * there can be arbitrary number of extended
 		 * sections, each of which is prefixed with
@@ -783,10 +819,10 @@ int read_cache(void)
 		 * in 4-byte network byte order.
 		 */
 		unsigned long extsize;
-		memcpy(&extsize, (char *) map + offset + 4, 4);
+		memcpy(&extsize, (char *) cache_mmap + offset + 4, 4);
 		extsize = ntohl(extsize);
-		if (read_index_extension(((const char *) map) + offset,
-					 (char *) map + offset + 8,
+		if (read_index_extension(((const char *) cache_mmap) + offset,
+					 (char *) cache_mmap + offset + 8,
 					 extsize) < 0)
 			goto unmap;
 		offset += 8;
@@ -795,7 +831,7 @@ int read_cache(void)
 	return active_nr;
 
 unmap:
-	munmap(map, size);
+	munmap(cache_mmap, cache_mmap_size);
 	errno = EINVAL;
 	die("index file corrupt");
 }
diff --git a/t/t7001-mv.sh b/t/t7001-mv.sh
index 322eaadc73..900ca93cde 100755
--- a/t/t7001-mv.sh
+++ b/t/t7001-mv.sh
@@ -74,4 +74,8 @@ test_expect_success \
      git-diff-tree -r -M --name-status  HEAD^ HEAD | \
      grep -E "^R100.+path2/README.+path1/path2/README"'
 
+test_expect_failure \
+    'do not move directory over existing directory' \
+    'mkdir path0 && mkdir path0/path2 && git-mv path2 path0'
+
 test_done