From: Junio C Hamano <junkio@cox.net>
Date: Sat, 4 Mar 2006 21:21:17 +0000 (-0800)
Subject: Merge branch 'lt/rev-list'
X-Git-Tag: v1.3.0-rc1~53^2~1
X-Git-Url: https://www.git.lorimer.id.au/gitweb.git/diff_plain/21dbe12c76e43735dc623067c1b09ef43519d9fc?hp=64bc6e3db54ef9e2accfdb8e6c8168f789946fcb

Merge branch 'lt/rev-list'

* lt/rev-list:
setup_revisions(): handle -n<n> and -<n> internally.
git-log (internal): more options.
git-log (internal): add approxidate.
Rip out merge-order and make "git log <paths>..." work again.
Tie it all together: "git log"
Introduce trivial new pager.c helper infrastructure
git-rev-list libification: rev-list walking
Splitting rev-list into revisions lib, end of beginning.
rev-list split: minimum fixup.
First cut at libifying revlist generation
---

diff --git a/Documentation/git-am.txt b/Documentation/git-am.txt
index 02cabc935e..910457d3b3 100644
--- a/Documentation/git-am.txt
+++ b/Documentation/git-am.txt
@@ -9,7 +9,8 @@ git-am - Apply a series of patches in a mailbox
 SYNOPSIS
 --------
 [verse]
-'git-am' [--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way] <mbox>...
+'git-am' [--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way]
+         [--interactive] [--whitespace=<option>] <mbox>...
 'git-am' [--skip | --resolved]
 
 DESCRIPTION
@@ -46,6 +47,10 @@ OPTIONS
 	Skip the current patch.  This is only meaningful when
 	restarting an aborted patch.
 
+--whitespace=<option>::
+	This flag is passed to the `git-apply` program that applies
+	the patch.
+
 --interactive::
 	Run interactively, just like git-applymbox.
 
@@ -80,7 +85,7 @@ names.
 
 SEE ALSO
 --------
-gitlink:git-applymbox[1], gitlink:git-applypatch[1].
+gitlink:git-applymbox[1], gitlink:git-applypatch[1], gitlink:git-apply[1].
 
 
 Author
diff --git a/Documentation/git-apply.txt b/Documentation/git-apply.txt
index 75076b6121..1c64a1aa82 100644
--- a/Documentation/git-apply.txt
+++ b/Documentation/git-apply.txt
@@ -11,6 +11,7 @@ SYNOPSIS
 [verse]
 'git-apply' [--stat] [--numstat] [--summary] [--check] [--index] [--apply]
 	  [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM]
+	  [--whitespace=<nowarn|warn|error|error-all|strip>]
 	  [<patch>...]
 
 DESCRIPTION
@@ -97,6 +98,35 @@ OPTIONS
 	result.  This allows binary files to be patched in a
 	very limited way.
 
+--whitespace=<option>::
+	When applying a patch, detect a new or modified line
+	that ends with trailing whitespaces (this includes a
+	line that solely consists of whitespaces).  By default,
+	the command outputs warning messages and applies the
+	patch.
+	When `git-apply` is used for statistics and not applying a
+	patch, it defaults to `nowarn`.
+	You can use different `<option>` to control this
+	behaviour:
++
+* `nowarn` turns off the trailing whitespace warning.
+* `warn` outputs warnings for a few such errors, but applies the
+  patch (default).
+* `error` outputs warnings for a few such errors, and refuses
+  to apply the patch.
+* `error-all` is similar to `error` but shows all errors.
+* `strip` outputs warnings for a few such errors, strips out the
+  trailing whitespaces and applies the patch.
+
+
+Configuration
+-------------
+
+apply.whitespace::
+	When no `--whitespace` flag is given from the command
+	line, this configuration item is used as the default.
+
+
 Author
 ------
 Written by Linus Torvalds <torvalds@osdl.org>
diff --git a/Documentation/git-cvsserver.txt b/Documentation/git-cvsserver.txt
index 88f07ff15d..19c9c51cff 100644
--- a/Documentation/git-cvsserver.txt
+++ b/Documentation/git-cvsserver.txt
@@ -54,6 +54,30 @@ INSTALLATION
    of branches in git).
      $ cvs co -d mylocaldir master
 
+Eclipse CVS Client Notes
+------------------------
+
+To get a checkout with the Eclipse CVS client:
+
+1. Create a new project from CVS checkout, giving it repository and module
+2. Context Menu->Team->Share Project...
+3. Enter the repository and module information again and click Finish
+4. The Synchronize view appears. Untick  "launch commit wizard" to avoid
+committing the .project file, and select HEAD as the tag to synchronize to.
+Update all incoming changes.
+
+Note that most versions of Eclipse ignore CVS_SERVER (which you can set in
+the Preferences->Team->CVS->ExtConnection pane), so you may have to
+rename, alias or symlink git-cvsserver to 'cvs' on the server.
+
+Clients known to work
+---------------------
+
+CVS 1.12.9 on Debian
+CVS 1.11.17 on MacOSX (from Fink package)
+Eclipse 3.0, 3.1.2 on MacOSX (see Eclipse CVS Client Notes)
+TortoiseCVS
+
 Operations supported
 --------------------
 
diff --git a/Documentation/git-read-tree.txt b/Documentation/git-read-tree.txt
index 6fbd6d9368..844cfda8d2 100644
--- a/Documentation/git-read-tree.txt
+++ b/Documentation/git-read-tree.txt
@@ -8,7 +8,7 @@ git-read-tree - Reads tree information into the index
 
 SYNOPSIS
 --------
-'git-read-tree' (<tree-ish> | [[-m | --reset] [-u | -i]] <tree-ish1> [<tree-ish2> [<tree-ish3>]])
+'git-read-tree' (<tree-ish> | [[-m [--aggressive]| --reset] [-u | -i]] <tree-ish1> [<tree-ish2> [<tree-ish3>]])
 
 
 DESCRIPTION
@@ -50,6 +50,19 @@ OPTIONS
 	trees that are not directly related to the current
 	working tree status into a temporary index file.
 
+--aggressive::
+	Usually a three-way merge by `git-read-tree` resolves
+	the merge for really trivial cases and leaves other
+	cases unresolved in the index, so that Porcelains can
+	implement different merge policies.  This flag makes the
+	command to resolve a few more cases internally:
++
+* when one side removes a path and the other side leaves the path
+  unmodified.  The resolution is to remove that path.
+* when both sides remove a path.  The resolution is to remove that path.
+* when both sides adds a path identically.  The resolution
+  is to add that path.
+
 <tree-ish#>::
 	The id of the tree object(s) to be read/merged.
 
diff --git a/Documentation/git-repo-config.txt b/Documentation/git-repo-config.txt
index 33fcde452a..00efde5f0f 100644
--- a/Documentation/git-repo-config.txt
+++ b/Documentation/git-repo-config.txt
@@ -8,6 +8,7 @@ git-repo-config - Get and set options in .git/config.
 
 SYNOPSIS
 --------
+[verse]
 'git-repo-config' [type] name [value [value_regex]]
 'git-repo-config' [type] --replace-all name [value [value_regex]]
 'git-repo-config' [type] --get name [value_regex]
diff --git a/Documentation/git-rev-list.txt b/Documentation/git-rev-list.txt
index 5b306d6593..8255ae1bce 100644
--- a/Documentation/git-rev-list.txt
+++ b/Documentation/git-rev-list.txt
@@ -18,7 +18,7 @@ SYNOPSIS
 	     [ \--all ]
 	     [ \--topo-order ]
 	     [ \--parents ]
-	     [ \--objects [ \--unpacked ] ]
+	     [ [\--objects | \--objects-edge] [ \--unpacked ] ]
 	     [ \--pretty | \--header ]
 	     [ \--bisect ]
 	     <commit>... [ \-- <paths>... ]
@@ -53,6 +53,14 @@ OPTIONS
 	which I need to download if I have the commit object 'bar', but
 	not 'foo'".
 
+--objects-edge::
+	Similar to `--objects`, but also print the IDs of
+	excluded commits refixed with a `-` character.  This is
+	used by `git-pack-objects` to build 'thin' pack, which
+	records objects in deltified form based on objects
+	contained in these excluded commits to reduce network
+	traffic.
+
 --unpacked::
 	Only useful with `--objects`; print the object IDs that
 	are not in packs.
diff --git a/Documentation/git-svnimport.txt b/Documentation/git-svnimport.txt
index 5c543d5d1b..9d3865719c 100644
--- a/Documentation/git-svnimport.txt
+++ b/Documentation/git-svnimport.txt
@@ -9,11 +9,13 @@ git-svnimport - Import a SVN repository into git
 
 SYNOPSIS
 --------
+[verse]
 'git-svnimport' [ -o <branch-for-HEAD> ] [ -h ] [ -v ] [ -d | -D ]
-			[ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev]
-			[ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ]
-			[ -s start_chg ] [ -m ] [ -M regex ]
-			<SVN_repository_URL> [ <path> ]
+		[ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev]
+		[ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ]
+		[ -s start_chg ] [ -m ] [ -r ] [ -M regex ]
+		[ -I <ignorefile_name> ] [ -A <author_file> ]
+		<SVN_repository_URL> [ <path> ]
 
 
 DESCRIPTION
@@ -65,6 +67,27 @@ When importing incrementally, you might need to edit the .git/svn2git file.
 	Prepend 'rX: ' to commit messages, where X is the imported
 	subversion revision.
 
+-I <ignorefile_name>::
+	Import the svn:ignore directory property to files with this
+	name in each directory. (The Subversion and GIT ignore
+	syntaxes are similar enough that using the Subversion patterns
+	directly with "-I .gitignore" will almost always just work.)
+
+-A <author_file>::
+	Read a file with lines on the form
+
+	  username = User's Full Name <email@addr.es>
+
+	and use "User's Full Name <email@addr.es>" as the GIT
+	author and committer for Subversion commits made by
+	"username". If encountering a commit made by a user not in the
+	list, abort.
+
+	For convenience, this data is saved to $GIT_DIR/svn-authors
+	each time the -A option is provided, and read from that same
+	file each time git-svnimport is run with an existing GIT
+	repository without -A.
+
 -m::
 	Attempt to detect merges based on the commit message. This option
 	will enable default regexes that try to capture the name source
diff --git a/Documentation/git-tools.txt b/Documentation/git-tools.txt
new file mode 100644
index 0000000000..00e57a69ae
--- /dev/null
+++ b/Documentation/git-tools.txt
@@ -0,0 +1,97 @@
+A short git tools survey
+========================
+
+
+Introduction
+------------
+
+Apart from git contrib/ area there are some others third-party tools
+you may want to look.
+
+This document presents a brief summary of each tool and the corresponding
+link.
+
+
+Alternative/Augmentative Procelains
+-----------------------------------
+
+   - *Cogito* (http://www.kernel.org/pub/software/scm/cogito/)
+
+   Cogito is a version control system layered on top of the git tree history
+   storage system. It aims at seamless user interface and ease of use,
+   providing generally smoother user experience than the "raw" Core GIT
+   itself and indeed many other version control systems.
+
+
+   - *pg* (http://www.spearce.org/category/projects/scm/pg/)
+
+   pg is a shell script wrapper around GIT to help the user manage a set of
+   patches to files. pg is somewhat like quilt or StGIT, but it does have a
+   slightly different feature set.
+
+
+   - *StGit* (http://www.procode.org/stgit/)
+
+   Stacked GIT provides a quilt-like patch management functionality in the
+    GIT environment. You can easily manage your patches in the scope of GIT
+   until they get merged upstream.
+
+
+History Viewers
+---------------
+
+   - *gitk* (shipped with git-core)
+
+   gitk is a simple TK GUI for browsing history of GIT repositories easily.
+
+
+   - *gitview*  (contrib/)
+
+   gitview is a GTK based repository browser for git
+
+
+   - *gitweb* (ftp://ftp.kernel.org/pub/software/scm/gitweb/)
+
+   GITweb provides full-fledged web interface for GIT repositories.
+
+
+   - *qgit* (http://digilander.libero.it/mcostalba/)
+
+   QGit is a git/StGIT GUI viewer built on Qt/C++. QGit could be used
+   to browse history and directory tree, view annotated files, commit
+   changes cherry picking single files or applying patches.
+   Currently it is the fastest and most feature rich among the git
+   viewers and commit tools.
+
+
+
+Foreign SCM interface
+---------------------
+
+   - *git-svn* (contrib/)
+
+   git-svn is a simple conduit for changesets between a single Subversion
+   branch and git.
+
+
+   - *quilt2git / git2quilt* (http://home-tj.org/wiki/index.php/Misc)
+
+   These utilities convert patch series in a quilt repository and commit
+   series in git back and forth.
+
+
+Others
+------
+
+   - *(h)gct* (http://www.cyd.liu.se/users/~freku045/gct/)
+
+   Commit Tool or (h)gct is a GUI enabled commit tool for git and
+   Mercurial (hg). It allows the user to view diffs, select which files
+   to committed (or ignored / reverted) write commit messages and
+   perform the commit itself.
+
+   - *git.el* (contrib/)
+
+   This is an Emacs interface for git. The user interface is modeled on
+   pcl-cvs. It has been developed on Emacs 21 and will probably need some
+   tweaking to work on XEmacs.
diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN
index 1056b7c817..d6d1ae0338 100755
--- a/GIT-VERSION-GEN
+++ b/GIT-VERSION-GEN
@@ -7,8 +7,11 @@ DEF_VER=v1.2.GIT
 # (included in release tarballs), then default
 if VN=$(git-describe --abbrev=4 HEAD 2>/dev/null); then
 	VN=$(echo "$VN" | sed -e 's/-/./g');
-else
+elif test -f version
+then
 	VN=$(cat version) || VN="$DEF_VER"
+else
+	VN="$DEF_VER"
 fi
 
 VN=$(expr "$VN" : v*'\(.*\)')
diff --git a/Makefile b/Makefile
index bd156d24fd..a1ec04e3a0 100644
--- a/Makefile
+++ b/Makefile
@@ -196,7 +196,8 @@ LIB_H = \
 
 DIFF_OBJS = \
 	diff.o diffcore-break.o diffcore-order.o diffcore-pathspec.o \
-	diffcore-pickaxe.o diffcore-rename.o tree-diff.o combine-diff.o
+	diffcore-pickaxe.o diffcore-rename.o tree-diff.o combine-diff.o \
+	diffcore-delta.o
 
 LIB_OBJS = \
 	blob.o commit.o connect.o count-delta.o csum-file.o \
@@ -223,11 +224,15 @@ ifeq ($(uname_S),Darwin)
 	NEEDS_SSL_WITH_CRYPTO = YesPlease
 	NEEDS_LIBICONV = YesPlease
 	## fink
-	ALL_CFLAGS += -I/sw/include
-	ALL_LDFLAGS += -L/sw/lib
+	ifeq ($(shell test -d /sw/lib && echo y),y)
+		ALL_CFLAGS += -I/sw/include
+		ALL_LDFLAGS += -L/sw/lib
+	endif
 	## darwinports
-	ALL_CFLAGS += -I/opt/local/include
-	ALL_LDFLAGS += -L/opt/local/lib
+	ifeq ($(shell test -d /opt/local/lib && echo y),y)
+		ALL_CFLAGS += -I/opt/local/include
+		ALL_LDFLAGS += -L/opt/local/lib
+	endif
 endif
 ifeq ($(uname_S),SunOS)
 	NEEDS_SOCKET = YesPlease
diff --git a/apply.c b/apply.c
index 244718ca13..c369966867 100644
--- a/apply.c
+++ b/apply.c
@@ -32,7 +32,57 @@ static int no_add = 0;
 static int show_index_info = 0;
 static int line_termination = '\n';
 static const char apply_usage[] =
-"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] <patch>...";
+"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] [--whitespace=<nowarn|warn|error|error-all|strip>] <patch>...";
+
+static enum whitespace_eol {
+	nowarn_whitespace,
+	warn_on_whitespace,
+	error_on_whitespace,
+	strip_whitespace,
+} new_whitespace = warn_on_whitespace;
+static int whitespace_error = 0;
+static int squelch_whitespace_errors = 5;
+static int applied_after_stripping = 0;
+static const char *patch_input_file = NULL;
+
+static void parse_whitespace_option(const char *option)
+{
+	if (!option) {
+		new_whitespace = warn_on_whitespace;
+		return;
+	}
+	if (!strcmp(option, "warn")) {
+		new_whitespace = warn_on_whitespace;
+		return;
+	}
+	if (!strcmp(option, "nowarn")) {
+		new_whitespace = nowarn_whitespace;
+		return;
+	}
+	if (!strcmp(option, "error")) {
+		new_whitespace = error_on_whitespace;
+		return;
+	}
+	if (!strcmp(option, "error-all")) {
+		new_whitespace = error_on_whitespace;
+		squelch_whitespace_errors = 0;
+		return;
+	}
+	if (!strcmp(option, "strip")) {
+		new_whitespace = strip_whitespace;
+		return;
+	}
+	die("unrecognized whitespace option '%s'", option);
+}
+
+static void set_default_whitespace_mode(const char *whitespace_option)
+{
+	if (!whitespace_option && !apply_default_whitespace) {
+		new_whitespace = (apply
+				  ? warn_on_whitespace
+				  : nowarn_whitespace);
+	}
+}
 
 /*
  * For "diff-stat" like behaviour, we keep track of the biggest change
@@ -815,6 +865,25 @@ static int parse_fragment(char *line, unsigned long size, struct patch *patch, s
 			oldlines--;
 			break;
 		case '+':
+			/*
+			 * We know len is at least two, since we have a '+' and
+			 * we checked that the last character was a '\n' above.
+			 * That is, an addition of an empty line would check
+			 * the '+' here.  Sneaky...
+			 */
+			if ((new_whitespace != nowarn_whitespace) &&
+			    isspace(line[len-2])) {
+				whitespace_error++;
+				if (squelch_whitespace_errors &&
+				    squelch_whitespace_errors <
+				    whitespace_error)
+					;
+				else {
+					fprintf(stderr, "Adds trailing whitespace.\n%s:%d:%.*s\n",
+						patch_input_file,
+						linenr, len-2, line+1);
+				}
+			}
 			added++;
 			newlines--;
 			break;
@@ -1092,6 +1161,28 @@ struct buffer_desc {
 	unsigned long alloc;
 };
 
+static int apply_line(char *output, const char *patch, int plen)
+{
+	/* plen is number of bytes to be copied from patch,
+	 * starting at patch+1 (patch[0] is '+').  Typically
+	 * patch[plen] is '\n'.
+	 */
+	int add_nl_to_tail = 0;
+	if ((new_whitespace == strip_whitespace) &&
+	    1 < plen && isspace(patch[plen-1])) {
+		if (patch[plen] == '\n')
+			add_nl_to_tail = 1;
+		plen--;
+		while (0 < plen && isspace(patch[plen]))
+			plen--;
+		applied_after_stripping++;
+	}
+	memcpy(output, patch + 1, plen);
+	if (add_nl_to_tail)
+		output[plen++] = '\n';
+	return plen;
+}
+
 static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag)
 {
 	char *buf = desc->buffer;
@@ -1127,10 +1218,9 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag)
 				break;
 		/* Fall-through for ' ' */
 		case '+':
-			if (*patch != '+' || !no_add) {
-				memcpy(new + newsize, patch + 1, plen);
-				newsize += plen;
-			}
+			if (*patch != '+' || !no_add)
+				newsize += apply_line(new + newsize, patch,
+						      plen);
 			break;
 		case '@': case '\\':
 			/* Ignore it, we already handled it */
@@ -1699,7 +1789,7 @@ static int use_patch(struct patch *p)
 	return 1;
 }
 
-static int apply_patch(int fd)
+static int apply_patch(int fd, const char *filename)
 {
 	int newfd;
 	unsigned long offset, size;
@@ -1707,6 +1797,7 @@ static int apply_patch(int fd)
 	struct patch *list = NULL, **listp = &list;
 	int skipped_patch = 0;
 
+	patch_input_file = filename;
 	if (!buffer)
 		return -1;
 	offset = 0;
@@ -1733,6 +1824,9 @@ static int apply_patch(int fd)
 	}
 
 	newfd = -1;
+	if (whitespace_error && (new_whitespace == error_on_whitespace))
+		apply = 0;
+
 	write_index = check_index && apply;
 	if (write_index)
 		newfd = hold_index_file_for_update(&cache_file, get_index_file());
@@ -1769,17 +1863,28 @@ static int apply_patch(int fd)
 	return 0;
 }
 
+static int git_apply_config(const char *var, const char *value)
+{
+	if (!strcmp(var, "apply.whitespace")) {
+		apply_default_whitespace = strdup(value);
+		return 0;
+	}
+	return git_default_config(var, value);
+}
+
+
 int main(int argc, char **argv)
 {
 	int i;
 	int read_stdin = 1;
+	const char *whitespace_option = NULL;
 
 	for (i = 1; i < argc; i++) {
 		const char *arg = argv[i];
 		int fd;
 
 		if (!strcmp(arg, "-")) {
-			apply_patch(0);
+			apply_patch(0, "<stdin>");
 			read_stdin = 0;
 			continue;
 		}
@@ -1839,11 +1944,18 @@ int main(int argc, char **argv)
 			line_termination = 0;
 			continue;
 		}
+		if (!strncmp(arg, "--whitespace=", 13)) {
+			whitespace_option = arg + 13;
+			parse_whitespace_option(arg + 13);
+			continue;
+		}
 
 		if (check_index && prefix_length < 0) {
 			prefix = setup_git_directory();
 			prefix_length = prefix ? strlen(prefix) : 0;
-			git_config(git_default_config);
+			git_config(git_apply_config);
+			if (!whitespace_option && apply_default_whitespace)
+				parse_whitespace_option(apply_default_whitespace);
 		}
 		if (0 < prefix_length)
 			arg = prefix_filename(prefix, prefix_length, arg);
@@ -1852,10 +1964,38 @@ int main(int argc, char **argv)
 		if (fd < 0)
 			usage(apply_usage);
 		read_stdin = 0;
-		apply_patch(fd);
+		set_default_whitespace_mode(whitespace_option);
+		apply_patch(fd, arg);
 		close(fd);
 	}
+	set_default_whitespace_mode(whitespace_option);
 	if (read_stdin)
-		apply_patch(0);
+		apply_patch(0, "<stdin>");
+	if (whitespace_error) {
+		if (squelch_whitespace_errors &&
+		    squelch_whitespace_errors < whitespace_error) {
+			int squelched =
+				whitespace_error - squelch_whitespace_errors;
+			fprintf(stderr, "warning: squelched %d whitespace error%s\n",
+				squelched,
+				squelched == 1 ? "" : "s");
+		}
+		if (new_whitespace == error_on_whitespace)
+			die("%d line%s add%s trailing whitespaces.",
+			    whitespace_error,
+			    whitespace_error == 1 ? "" : "s",
+			    whitespace_error == 1 ? "s" : "");
+		if (applied_after_stripping)
+			fprintf(stderr, "warning: %d line%s applied after"
+				" stripping trailing whitespaces.\n",
+				applied_after_stripping,
+				applied_after_stripping == 1 ? "" : "s");
+		else if (whitespace_error)
+			fprintf(stderr, "warning: %d line%s add%s trailing"
+				" whitespaces.\n",
+				whitespace_error,
+				whitespace_error == 1 ? "" : "s",
+				whitespace_error == 1 ? "s" : "");
+	}
 	return 0;
 }
diff --git a/cache.h b/cache.h
index 3af6b868e8..8dc1de16e4 100644
--- a/cache.h
+++ b/cache.h
@@ -161,11 +161,13 @@ extern int hold_index_file_for_update(struct cache_file *, const char *path);
 extern int commit_index_file(struct cache_file *);
 extern void rollback_index_file(struct cache_file *);
 
+/* Environment bits from configuration mechanism */
 extern int trust_executable_bit;
 extern int assume_unchanged;
 extern int only_use_symrefs;
 extern int diff_rename_limit_default;
 extern int shared_repository;
+extern const char *apply_default_whitespace;
 
 #define GIT_REPO_VERSION 0
 extern int repository_format_version;
diff --git a/cat-file.c b/cat-file.c
index 96d66b4304..1a613f3ee5 100644
--- a/cat-file.c
+++ b/cat-file.c
@@ -4,6 +4,92 @@
  * Copyright (C) Linus Torvalds, 2005
  */
 #include "cache.h"
+#include "exec_cmd.h"
+
+static void flush_buffer(const char *buf, unsigned long size)
+{
+	while (size > 0) {
+		long ret = xwrite(1, buf, size);
+		if (ret < 0) {
+			/* Ignore epipe */
+			if (errno == EPIPE)
+				break;
+			die("git-cat-file: %s", strerror(errno));
+		} else if (!ret) {
+			die("git-cat-file: disk full?");
+		}
+		size -= ret;
+		buf += ret;
+	}
+}
+
+static int pprint_tag(const unsigned char *sha1, const char *buf, unsigned long size)
+{
+	/* the parser in tag.c is useless here. */
+	const char *endp = buf + size;
+	const char *cp = buf;
+
+	while (cp < endp) {
+		char c = *cp++;
+		if (c != '\n')
+			continue;
+		if (7 <= endp - cp && !memcmp("tagger ", cp, 7)) {
+			const char *tagger = cp;
+
+			/* Found the tagger line.  Copy out the contents
+			 * of the buffer so far.
+			 */
+			flush_buffer(buf, cp - buf);
+
+			/*
+			 * Do something intelligent, like pretty-printing
+			 * the date.
+			 */
+			while (cp < endp) {
+				if (*cp++ == '\n') {
+					/* tagger to cp is a line
+					 * that has ident and time.
+					 */
+					const char *sp = tagger;
+					char *ep;
+					unsigned long date;
+					long tz;
+					while (sp < cp && *sp != '>')
+						sp++;
+					if (sp == cp) {
+						/* give up */
+						flush_buffer(tagger,
+							     cp - tagger);
+						break;
+					}
+					while (sp < cp &&
+					       !('0' <= *sp && *sp <= '9'))
+						sp++;
+					flush_buffer(tagger, sp - tagger);
+					date = strtoul(sp, &ep, 10);
+					tz = strtol(ep, NULL, 10);
+					sp = show_date(date, tz);
+					flush_buffer(sp, strlen(sp));
+					xwrite(1, "\n", 1);
+					break;
+				}
+			}
+			break;
+		}
+		if (cp < endp && *cp == '\n')
+			/* end of header */
+			break;
+	}
+	/* At this point, we have copied out the header up to the end of
+	 * the tagger line and cp points at one past \n.  It could be the
+	 * next header line after the tagger line, or it could be another
+	 * \n that marks the end of the headers.  We need to copy out the
+	 * remainder as is.
+	 */
+	if (cp < endp)
+		flush_buffer(cp, endp - cp);
+	return 0;
+}
 
 int main(int argc, char **argv)
 {
@@ -15,7 +101,7 @@ int main(int argc, char **argv)
 
 	setup_git_directory();
 	if (argc != 3 || get_sha1(argv[2], sha1))
-		usage("git-cat-file [-t|-s|-e|<type>] <sha1>");
+		usage("git-cat-file [-t|-s|-e|-p|<type>] <sha1>");
 
 	opt = 0;
 	if ( argv[1][0] == '-' ) {
@@ -43,6 +129,23 @@ int main(int argc, char **argv)
 	case 'e':
 		return !has_sha1_file(sha1);
 
+	case 'p':
+		if (get_sha1(argv[2], sha1) ||
+		    sha1_object_info(sha1, type, NULL))
+			die("Not a valid object name %s", argv[2]);
+
+		/* custom pretty-print here */
+		if (!strcmp(type, "tree"))
+			return execl_git_cmd("ls-tree", argv[2], NULL);
+
+		buf = read_sha1_file(sha1, type, &size);
+		if (!buf)
+			die("Cannot read object %s", argv[2]);
+		if (!strcmp(type, "tag"))
+			return pprint_tag(sha1, buf, size);
+
+		/* otherwise just spit out the data */
+		break;
 	case 0:
 		buf = read_object_with_reference(sha1, argv[1], &size, NULL);
 		break;
@@ -54,18 +157,6 @@ int main(int argc, char **argv)
 	if (!buf)
 		die("git-cat-file %s: bad file", argv[2]);
 
-	while (size > 0) {
-		long ret = xwrite(1, buf, size);
-		if (ret < 0) {
-			/* Ignore epipe */
-			if (errno == EPIPE)
-				break;
-			die("git-cat-file: %s", strerror(errno));
-		} else if (!ret) {
-			die("git-cat-file: disk full?");
-		}
-		size -= ret;
-		buf += ret;
-	}
+	flush_buffer(buf, size);
 	return 0;
 }
diff --git a/combine-diff.c b/combine-diff.c
index d812600d11..a23894d869 100644
--- a/combine-diff.c
+++ b/combine-diff.c
@@ -621,7 +621,8 @@ static void reuse_combine_diff(struct sline *sline, unsigned long cnt,
 }
 
 static int show_patch_diff(struct combine_diff_path *elem, int num_parent,
-			   int dense, const char *header)
+			   int dense, const char *header,
+			   struct diff_options *opt)
 {
 	unsigned long size, cnt, lno;
 	char *result, *cp, *ep;
@@ -631,6 +632,7 @@ static int show_patch_diff(struct combine_diff_path *elem, int num_parent,
 	char ourtmp_buf[TMPPATHLEN];
 	char *ourtmp = ourtmp_buf;
 	int working_tree_file = !memcmp(elem->sha1, null_sha1, 20);
+	int abbrev = opt->full_index ? 40 : DEFAULT_ABBREV;
 
 	/* Read the result of merge first */
 	if (!working_tree_file) {
@@ -724,7 +726,7 @@ static int show_patch_diff(struct combine_diff_path *elem, int num_parent,
 
 		if (header) {
 			shown_header++;
-			puts(header);
+			printf("%s%c", header, opt->line_termination);
 		}
 		printf("diff --%s ", dense ? "cc" : "combined");
 		if (quote_c_style(elem->path, NULL, NULL, 0))
@@ -735,10 +737,10 @@ static int show_patch_diff(struct combine_diff_path *elem, int num_parent,
 		printf("index ");
 		for (i = 0; i < num_parent; i++) {
 			abb = find_unique_abbrev(elem->parent[i].sha1,
-						 DEFAULT_ABBREV);
+						 abbrev);
 			printf("%s%s", i ? "," : "", abb);
 		}
-		abb = find_unique_abbrev(elem->sha1, DEFAULT_ABBREV);
+		abb = find_unique_abbrev(elem->sha1, abbrev);
 		printf("..%s\n", abb);
 
 		if (mode_differs) {
@@ -797,7 +799,7 @@ static void show_raw_diff(struct combine_diff_path *p, int num_parent, const cha
 		inter_name_termination = 0;
 
 	if (header)
-		puts(header);
+		printf("%s%c", header, line_termination);
 
 	for (i = 0; i < num_parent; i++) {
 		if (p->parent[i].mode)
@@ -862,7 +864,7 @@ int show_combined_diff(struct combine_diff_path *p,
 
 	default:
 	case DIFF_FORMAT_PATCH:
-		return show_patch_diff(p, num_parent, dense, header);
+		return show_patch_diff(p, num_parent, dense, header, opt);
 	}
 }
 
diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl
index 0b7416526d..3c860e458c 100755
--- a/contrib/git-svn/git-svn.perl
+++ b/contrib/git-svn/git-svn.perl
@@ -4,19 +4,12 @@
 use warnings;
 use strict;
 use vars qw/	$AUTHOR $VERSION
-		$SVN_URL $SVN_INFO $SVN_WC
+		$SVN_URL $SVN_INFO $SVN_WC $SVN_UUID
 		$GIT_SVN_INDEX $GIT_SVN
 		$GIT_DIR $REV_DIR/;
 $AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
 $VERSION = '0.10.0';
 $GIT_DIR = $ENV{GIT_DIR} || "$ENV{PWD}/.git";
-$GIT_SVN = $ENV{GIT_SVN_ID} || 'git-svn';
-$GIT_SVN_INDEX = "$GIT_DIR/$GIT_SVN/index";
-$ENV{GIT_DIR} ||= $GIT_DIR;
-$SVN_URL = undef;
-$REV_DIR = "$GIT_DIR/$GIT_SVN/revs";
-$SVN_WC = "$GIT_DIR/$GIT_SVN/tree";
-
 # make sure the svn binary gives consistent output between locales and TZs:
 $ENV{TZ} = 'UTC';
 $ENV{LC_ALL} = 'C';
@@ -24,6 +17,7 @@
 # If SVN:: library support is added, please make the dependencies
 # optional and preserve the capability to use the command-line client.
 # use eval { require SVN::... } to make it lazy load
+# We don't use any modules not in the standard Perl distribution:
 use Carp qw/croak/;
 use IO::File qw//;
 use File::Basename qw/dirname basename/;
@@ -32,27 +26,30 @@
 use File::Spec qw//;
 use POSIX qw/strftime/;
 my $sha1 = qr/[a-f\d]{40}/;
-my $sha1_short = qr/[a-f\d]{6,40}/;
+my $sha1_short = qr/[a-f\d]{4,40}/;
 my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit,
-	$_find_copies_harder, $_l, $_version);
-
-GetOptions(	'revision|r=s' => \$_revision,
-		'no-ignore-externals' => \$_no_ignore_ext,
-		'stdin|' => \$_stdin,
-		'edit|e' => \$_edit,
-		'rmdir' => \$_rmdir,
-		'help|H|h' => \$_help,
-		'find-copies-harder' => \$_find_copies_harder,
-		'l=i' => \$_l,
-		'version|V' => \$_version,
-		'no-stop-on-copy' => \$_no_stop_copy );
+	$_find_copies_harder, $_l, $_version, $_upgrade, $_authors);
+my (@_branch_from, %tree_map, %users);
+
+my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext,
+		'branch|b=s' => \@_branch_from,
+		'authors-file|A=s' => \$_authors );
 my %cmd = (
-	fetch => [ \&fetch, "Download new revisions from SVN" ],
-	init => [ \&init, "Initialize and fetch (import)"],
-	commit => [ \&commit, "Commit git revisions to SVN" ],
-	'show-ignore' => [ \&show_ignore, "Show svn:ignore listings" ],
-	rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)" ],
-	help => [ \&usage, "Show help" ],
+	fetch => [ \&fetch, "Download new revisions from SVN",
+			{ 'revision|r=s' => \$_revision, %fc_opts } ],
+	init => [ \&init, "Initialize and fetch (import)", { } ],
+	commit => [ \&commit, "Commit git revisions to SVN",
+			{	'stdin|' => \$_stdin,
+				'edit|e' => \$_edit,
+				'rmdir' => \$_rmdir,
+				'find-copies-harder' => \$_find_copies_harder,
+				'l=i' => \$_l,
+				%fc_opts,
+			} ],
+	'show-ignore' => [ \&show_ignore, "Show svn:ignore listings", { } ],
+	rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)",
+			{ 'no-ignore-externals' => \$_no_ignore_ext,
+			  'upgrade' => \$_upgrade } ],
 );
 my $cmd;
 for (my $i = 0; $i < @ARGV; $i++) {
@@ -63,16 +60,23 @@
 	}
 };
 
-# we may be called as git-svn-(command), or git-svn(command).
-foreach (keys %cmd) {
-	if (/git\-svn\-?($_)(?:\.\w+)?$/) {
-		$cmd = $1;
-		last;
-	}
-}
+my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd);
+
+GetOptions(%opts, 'help|H|h' => \$_help,
+		'version|V' => \$_version,
+		'id|i=s' => \$GIT_SVN) or exit 1;
+
+$GIT_SVN ||= $ENV{GIT_SVN_ID} || 'git-svn';
+$GIT_SVN_INDEX = "$GIT_DIR/$GIT_SVN/index";
+$ENV{GIT_DIR} ||= $GIT_DIR;
+$SVN_URL = undef;
+$REV_DIR = "$GIT_DIR/$GIT_SVN/revs";
+$SVN_WC = "$GIT_DIR/$GIT_SVN/tree";
+
 usage(0) if $_help;
 version() if $_version;
-usage(1) unless (defined $cmd);
+usage(1) unless defined $cmd;
+load_authors() if $_authors;
 svn_check_ignore_externals();
 $cmd{$cmd}->[0]->(@ARGV);
 exit 0;
@@ -84,15 +88,25 @@ sub usage {
 	print $fd <<"";
 git-svn - bidirectional operations between a single Subversion tree and git
 Usage: $0 <command> [options] [arguments]\n
-Available commands:
+
+	print $fd "Available commands:\n" unless $cmd;
 
 	foreach (sort keys %cmd) {
-		print $fd '  ',pack('A10',$_),$cmd{$_}->[1],"\n";
+		next if $cmd && $cmd ne $_;
+		print $fd '  ',pack('A13',$_),$cmd{$_}->[1],"\n";
+		foreach (keys %{$cmd{$_}->[2]}) {
+			# prints out arguments as they should be passed:
+			my $x = s#=s$## ? '<arg>' : s#=i$## ? '<num>' : '';
+			print $fd ' ' x 17, join(', ', map { length $_ > 1 ?
+							"--$_" : "-$_" }
+						split /\|/,$_)," $x\n";
+		}
 	}
 	print $fd <<"";
-\nGIT_SVN_ID may be set in the environment to an arbitrary identifier if
-you're tracking multiple SVN branches/repositories in one git repository
-and want to keep them separate.
+\nGIT_SVN_ID may be set in the environment or via the --id/-i switch to an
+arbitrary identifier if you're tracking multiple SVN branches/repositories in
+one git repository and want to keep them separate.  See git-svn(1) for more
+information.
 
 	exit $exit;
 }
@@ -104,15 +118,19 @@ sub version {
 
 sub rebuild {
 	$SVN_URL = shift or undef;
-	my $repo_uuid;
 	my $newest_rev = 0;
+	if ($_upgrade) {
+		sys('git-update-ref',"refs/remotes/$GIT_SVN","$GIT_SVN-HEAD");
+	} else {
+		check_upgrade_needed();
+	}
 
 	my $pid = open(my $rev_list,'-|');
 	defined $pid or croak $!;
 	if ($pid == 0) {
-		exec("git-rev-list","$GIT_SVN-HEAD") or croak $!;
+		exec("git-rev-list","refs/remotes/$GIT_SVN") or croak $!;
 	}
-	my $first;
+	my $latest;
 	while (<$rev_list>) {
 		chomp;
 		my $c = $_;
@@ -132,18 +150,20 @@ sub rebuild {
 					"$c, $id\n";
 			}
 		}
+
+		# if we merged or otherwise started elsewhere, this is
+		# how we break out of it
+		next if (defined $SVN_UUID && ($uuid ne $SVN_UUID));
+		next if (defined $SVN_URL && ($url ne $SVN_URL));
+
 		print "r$rev = $c\n";
-		unless (defined $first) {
+		unless (defined $latest) {
 			if (!$SVN_URL && !$url) {
 				croak "SVN repository location required: $url\n";
 			}
 			$SVN_URL ||= $url;
-			$repo_uuid = setup_git_svn();
-			$first = $rev;
-		}
-		if ($uuid ne $repo_uuid) {
-			croak "Repository UUIDs do not match!\ngot: $uuid\n",
-						"expected: $repo_uuid\n";
+			$SVN_UUID ||= setup_git_svn();
+			$latest = $rev;
 		}
 		assert_revision_eq_or_unknown($rev, $c);
 		sys('git-update-ref',"$GIT_SVN/revs/$rev",$c);
@@ -151,7 +171,7 @@ sub rebuild {
 	}
 	close $rev_list or croak $?;
 	if (!chdir $SVN_WC) {
-		my @svn_co = ('svn','co',"-r$first");
+		my @svn_co = ('svn','co',"-r$latest");
 		push @svn_co, '--ignore-externals' unless $_no_ignore_ext;
 		sys(@svn_co, $SVN_URL, $SVN_WC);
 		chdir $SVN_WC or croak $!;
@@ -168,6 +188,13 @@ sub rebuild {
 		exec('git-write-tree');
 	}
 	waitpid $pid, 0;
+
+	if ($_upgrade) {
+		print STDERR <<"";
+Keeping deprecated refs/head/$GIT_SVN-HEAD for now.  Please remove it
+when you have upgraded your tools and habits to use refs/remotes/$GIT_SVN
+
+	}
 }
 
 sub init {
@@ -180,6 +207,7 @@ sub init {
 
 sub fetch {
 	my (@parents) = @_;
+	check_upgrade_needed();
 	$SVN_URL ||= file_to_s("$GIT_DIR/$GIT_SVN/info/url");
 	my @log_args = -d $SVN_WC ? ($SVN_WC) : ($SVN_URL);
 	unless ($_revision) {
@@ -199,9 +227,6 @@ sub fetch {
 		sys(@svn_co, $SVN_URL, $SVN_WC);
 		chdir $SVN_WC or croak $!;
 		$last_commit = git_commit($base, @parents);
-		unless (-f "$GIT_DIR/refs/heads/master") {
-			sys(qw(git-update-ref refs/heads/master),$last_commit);
-		}
 		assert_svn_wc_clean($base->{revision}, $last_commit);
 	} else {
 		chdir $SVN_WC or croak $!;
@@ -217,16 +242,20 @@ sub fetch {
 		$last_commit = git_commit($log_msg, $last_commit, @parents);
 	}
 	assert_svn_wc_clean($last_rev, $last_commit);
+	unless (-e "$GIT_DIR/refs/heads/master") {
+		sys(qw(git-update-ref refs/heads/master),$last_commit);
+	}
 	return pop @$svn_log;
 }
 
 sub commit {
 	my (@commits) = @_;
+	check_upgrade_needed();
 	if ($_stdin || !@commits) {
 		print "Reading from stdin...\n";
 		@commits = ();
 		while (<STDIN>) {
-			if (/\b([a-f\d]{6,40})\b/) {
+			if (/\b($sha1_short)\b/o) {
 				unshift @commits, $1;
 			}
 		}
@@ -248,7 +277,6 @@ sub commit {
 	chdir $SVN_WC or croak $!;
 	my $svn_current_rev =  svn_info('.')->{'Last Changed Rev'};
 	foreach my $c (@revs) {
-		print "Committing $c\n";
 		my $mods = svn_checkout_tree($svn_current_rev, $c);
 		if (scalar @$mods == 0) {
 			print "Skipping, no changes detected\n";
@@ -295,24 +323,31 @@ sub setup_git_svn {
 	mkpath(["$GIT_DIR/$GIT_SVN/info"]);
 	mkpath([$REV_DIR]);
 	s_to_file($SVN_URL,"$GIT_DIR/$GIT_SVN/info/url");
-	my $uuid = svn_info($SVN_URL)->{'Repository UUID'} or
+	$SVN_UUID = svn_info($SVN_URL)->{'Repository UUID'} or
 					croak "Repository UUID unreadable\n";
-	s_to_file($uuid,"$GIT_DIR/$GIT_SVN/info/uuid");
+	s_to_file($SVN_UUID,"$GIT_DIR/$GIT_SVN/info/uuid");
 
 	open my $fd, '>>', "$GIT_DIR/$GIT_SVN/info/exclude" or croak $!;
 	print $fd '.svn',"\n";
 	close $fd or croak $!;
-	return $uuid;
+	return $SVN_UUID;
 }
 
 sub assert_svn_wc_clean {
 	my ($svn_rev, $treeish) = @_;
 	croak "$svn_rev is not an integer!\n" unless ($svn_rev =~ /^\d+$/);
 	croak "$treeish is not a sha1!\n" unless ($treeish =~ /^$sha1$/o);
-	my $svn_info = svn_info('.');
-	if ($svn_rev != $svn_info->{'Last Changed Rev'}) {
-		croak "Expected r$svn_rev, got r",
-				$svn_info->{'Last Changed Rev'},"\n";
+	my $lcr = svn_info('.')->{'Last Changed Rev'};
+	if ($svn_rev != $lcr) {
+		print STDERR "Checking for copy-tree ... ";
+		# use
+		my @diff = grep(/^Index: /,(safe_qx(qw(svn diff),
+						"-r$lcr:$svn_rev")));
+		if (@diff) {
+			croak "Nope!  Expected r$svn_rev, got r$lcr\n";
+		} else {
+			print STDERR "OK!\n";
+		}
 	}
 	my @status = grep(!/^Performing status on external/,(`svn status`));
 	@status = grep(!/^\s*$/,@status);
@@ -495,7 +530,7 @@ sub svn_checkout_tree {
 	my ($svn_rev, $treeish) = @_;
 	my $from = file_to_s("$REV_DIR/$svn_rev");
 	assert_svn_wc_clean($svn_rev,$from);
-	print "diff-tree '$from' '$treeish'\n";
+	print "diff-tree $from $treeish\n";
 	my $pid = open my $diff_fh, '-|';
 	defined $pid or croak $!;
 	if ($pid == 0) {
@@ -506,7 +541,7 @@ sub svn_checkout_tree {
 	}
 	my $mods = parse_diff_tree($diff_fh);
 	unless (@$mods) {
-		# git can do empty commits, SVN doesn't allow it...
+		# git can do empty commits, but SVN doesn't allow it...
 		return $mods;
 	}
 	my ($rm, $add) = precommit_check($mods);
@@ -593,7 +628,7 @@ sub svn_commit_tree {
 	my ($svn_rev, $commit) = @_;
 	my $commit_msg = "$GIT_DIR/$GIT_SVN/.svn-commit.tmp.$$";
 	my %log_msg = ( msg => '' );
-	open my $msg, '>', $commit_msg  or croak $!;
+	open my $msg, '>', $commit_msg or croak $!;
 
 	chomp(my $type = `git-cat-file -t $commit`);
 	if ($type eq 'commit') {
@@ -607,8 +642,10 @@ sub svn_commit_tree {
 		while (<$msg_fh>) {
 			if (!$in_msg) {
 				$in_msg = 1 if (/^\s*$/);
+			} elsif (/^git-svn-id: /) {
+				# skip this, we regenerate the correct one
+				# on re-fetch anyways
 			} else {
-				$log_msg{msg} .= $_;
 				print $msg $_ or croak $!;
 			}
 		}
@@ -620,6 +657,15 @@ sub svn_commit_tree {
 		my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi';
 		system($editor, $commit_msg);
 	}
+
+	# file_to_s removes all trailing newlines, so just use chomp() here:
+	open $msg, '<', $commit_msg or croak $!;
+	{ local $/; chomp($log_msg{msg} = <$msg>); }
+	close $msg or croak $!;
+
+	my ($oneline) = ($log_msg{msg} =~ /([^\n\r]+)/);
+	print "Committing $commit: $oneline\n";
+
 	my @ci_output = safe_qx(qw(svn commit -F),$commit_msg);
 	my ($committed) = grep(/^Committed revision \d+\./,@ci_output);
 	unlink $commit_msg;
@@ -711,6 +757,10 @@ sub svn_log_raw {
 					author => $author,
 					lines => $lines,
 					msg => '' );
+			if (defined $_authors && ! defined $users{$author}) {
+				die "Author: $author not defined in ",
+						"$_authors file\n";
+			}
 			push @svn_log, \%log_msg;
 			$state = 'msg_start';
 			next;
@@ -810,9 +860,9 @@ sub git_commit {
 	my ($log_msg, @parents) = @_;
 	assert_revision_unknown($log_msg->{revision});
 	my $out_fh = IO::File->new_tmpfile or croak $!;
-	my $info = svn_info('.');
-	my $uuid = $info->{'Repository UUID'};
-	defined $uuid or croak "Unable to get Repository UUID\n";
+	$SVN_UUID ||= svn_info('.')->{'Repository UUID'};
+
+	map_tree_joins() if (@_branch_from && !%tree_map);
 
 	# commit parents can be conditionally bound to a particular
 	# svn revision via: "svn_revno=commit_sha1", filter them out here:
@@ -835,19 +885,26 @@ sub git_commit {
 		git_addremove();
 		chomp(my $tree = `git-write-tree`);
 		croak if $?;
+		if (exists $tree_map{$tree}) {
+			my %seen_parent = map { $_ => 1 } @exec_parents;
+			foreach (@{$tree_map{$tree}}) {
+				# MAXPARENT is defined to 16 in commit-tree.c:
+				if ($seen_parent{$_} || @exec_parents > 16) {
+					next;
+				}
+				push @exec_parents, $_;
+				$seen_parent{$_} = 1;
+			}
+		}
 		my $msg_fh = IO::File->new_tmpfile or croak $!;
 		print $msg_fh $log_msg->{msg}, "\ngit-svn-id: ",
 					"$SVN_URL\@$log_msg->{revision}",
-					" $uuid\n" or croak $!;
+					" $SVN_UUID\n" or croak $!;
 		$msg_fh->flush == 0 or croak $!;
 		seek $msg_fh, 0, 0 or croak $!;
 
-		$ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} =
-						$log_msg->{author};
-		$ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} =
-						$log_msg->{author}."\@$uuid";
-		$ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} =
-						$log_msg->{date};
+		set_commit_env($log_msg);
+
 		my @exec = ('git-commit-tree',$tree);
 		push @exec, '-p', $_  foreach @exec_parents;
 		open STDIN, '<&', $msg_fh or croak $!;
@@ -863,7 +920,7 @@ sub git_commit {
 	if ($commit !~ /^$sha1$/o) {
 		croak "Failed to commit, invalid sha1: $commit\n";
 	}
-	my @update_ref = ('git-update-ref',"refs/heads/$GIT_SVN-HEAD",$commit);
+	my @update_ref = ('git-update-ref',"refs/remotes/$GIT_SVN",$commit);
 	if (my $primary_parent = shift @exec_parents) {
 		push @update_ref, $primary_parent;
 	}
@@ -873,6 +930,16 @@ sub git_commit {
 	return $commit;
 }
 
+sub set_commit_env {
+	my ($log_msg) = @_;
+	my $author = $log_msg->{author};
+	my ($name,$email) = defined $users{$author} ?  @{$users{$author}}
+				: ($author,"$author\@$SVN_UUID");
+	$ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $name;
+	$ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} = $email;
+	$ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_msg->{date};
+}
+
 sub apply_mod_line_blob {
 	my $m = shift;
 	if ($m->{mode_b} =~ /^120/) {
@@ -936,6 +1003,63 @@ sub svn_check_ignore_externals {
 		$_no_ignore_ext = 1;
 	}
 }
+
+sub check_upgrade_needed {
+	my $old = eval {
+		my $pid = open my $child, '-|';
+		defined $pid or croak $!;
+		if ($pid == 0) {
+			close STDERR;
+			exec('git-rev-parse',"$GIT_SVN-HEAD") or croak $?;
+		}
+		my @ret = (<$child>);
+		close $child or croak $?;
+		die $? if $?; # just in case close didn't error out
+		return wantarray ? @ret : join('',@ret);
+	};
+	return unless $old;
+	my $head = eval { safe_qx('git-rev-parse',"refs/remotes/$GIT_SVN") };
+	if ($@ || !$head) {
+		print STDERR "Please run: $0 rebuild --upgrade\n";
+		exit 1;
+	}
+}
+
+# fills %tree_map with a reverse mapping of trees to commits.  Useful
+# for finding parents to commit on.
+sub map_tree_joins {
+	foreach my $br (@_branch_from) {
+		my $pid = open my $pipe, '-|';
+		defined $pid or croak $!;
+		if ($pid == 0) {
+			exec(qw(git-rev-list --pretty=raw), $br) or croak $?;
+		}
+		while (<$pipe>) {
+			if (/^commit ($sha1)$/o) {
+				my $commit = $1;
+				my ($tree) = (<$pipe> =~ /^tree ($sha1)$/o);
+				unless (defined $tree) {
+					die "Failed to parse commit $commit\n";
+				}
+				push @{$tree_map{$tree}}, $commit;
+			}
+		}
+		close $pipe or croak $?;
+	}
+}
+
+# '<svn username> = real-name <email address>' mapping based on git-svnimport:
+sub load_authors {
+	open my $authors, '<', $_authors or die "Can't open $_authors $!\n";
+	while (<$authors>) {
+		chomp;
+		next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/;
+		my ($user, $name, $email) = ($1, $2, $3);
+		$users{$user} = [$name, $email];
+	}
+	close $authors or croak $!;
+}
+
 __END__
 
 Data structures:
@@ -960,7 +1084,7 @@ sub svn_check_ignore_externals {
 	mode_a => first column of diff-index output, no leading ':',
 	mode_b => second column of diff-index output,
 	sha1_b => sha1sum of the final blob,
-	chg => change type [MCRAD],
+	chg => change type [MCRADT],
 	file_a => original file name of a file (iff chg is 'C' or 'R')
 	file_b => new/current file name of a file (any chg)
 }
diff --git a/contrib/git-svn/git-svn.txt b/contrib/git-svn/git-svn.txt
index b4b7789dee..8e9a971a85 100644
--- a/contrib/git-svn/git-svn.txt
+++ b/contrib/git-svn/git-svn.txt
@@ -27,7 +27,7 @@ For importing svn, git-svnimport is potentially more powerful when
 operating on repositories organized under the recommended
 trunk/branch/tags structure, and should be faster, too.
 
-git-svn completely ignores the very limited view of branching that
+git-svn mostly ignores the very limited view of branching that
 Subversion has.  This allows git-svn to be much easier to use,
 especially on repositories that are not organized in a manner that
 git-svnimport is designed for.
@@ -41,7 +41,12 @@ init::
 
 fetch::
 	Fetch unfetched revisions from the SVN_URL we are tracking.
-	refs/heads/git-svn-HEAD will be updated to the latest revision.
+	refs/heads/remotes/git-svn will be updated to the latest revision.
+
+	Note: You should never attempt to modify the remotes/git-svn branch
+	outside of git-svn.  Instead, create a branch from remotes/git-svn
+	and work on that branch.  Use the 'commit' command (see below)
+	to write git commits back to remotes/git-svn.
 
 commit::
 	Commit specified commit or tree objects to SVN.  This relies on
@@ -111,8 +116,38 @@ OPTIONS
 	They are both passed directly to git-diff-tree see
 	git-diff-tree(1) for more information.
 
+ADVANCED OPTIONS
+----------------
+-b<refname>::
+--branch <refname>::
+	Used with 'fetch' or 'commit'.
+
+	This can be used to join arbitrary git branches to remotes/git-svn
+	on new commits where the tree object is equivalent.
+
+	When used with different GIT_SVN_ID values, tags and branches in
+	SVN can be tracked this way, as can some merges where the heads
+	end up having completely equivalent content.  This can even be
+	used to track branches across multiple SVN _repositories_.
+
+	This option may be specified multiple times, once for each
+	branch.
+
+-i<GIT_SVN_ID>::
+--id <GIT_SVN_ID>::
+	This sets GIT_SVN_ID (instead of using the environment).  See
+	the section on "Tracking Multiple Repositories or Branches" for
+	more information on using GIT_SVN_ID.
+
 COMPATIBILITY OPTIONS
 ---------------------
+--upgrade::
+	Only used with the 'rebuild' command.
+
+	Run this if you used an old version of git-svn that used
+	'git-svn-HEAD' instead of 'remotes/git-svn' as the branch
+	for tracking the remote.
+
 --no-ignore-externals::
 	Only used with the 'fetch' and 'rebuild' command.
 
@@ -150,14 +185,14 @@ Tracking and contributing to an Subversion managed-project:
 # Fetch remote revisions::
 	git-svn fetch
 # Create your own branch to hack on::
-	git checkout -b my-branch git-svn-HEAD
+	git checkout -b my-branch remotes/git-svn
 # Commit only the git commits you want to SVN::
 	git-svn commit <tree-ish> [<tree-ish_2> ...]
 # Commit all the git commits from my-branch that don't exist in SVN::
-	git commit git-svn-HEAD..my-branch
+	git-svn commit remotes/git-svn..my-branch
 # Something is committed to SVN, pull the latest into your branch::
-	git-svn fetch && git pull . git-svn-HEAD
-# Append svn:ignore settings to the default git exclude file:
+	git-svn fetch && git pull . remotes/git-svn
+# Append svn:ignore settings to the default git exclude file::
 	git-svn show-ignore >> .git/info/exclude
 
 DESIGN PHILOSOPHY
@@ -179,7 +214,9 @@ SVN repositories via one git repository.  Simply set the GIT_SVN_ID
 environment variable to a name other other than "git-svn" (the default)
 and git-svn will ignore the contents of the $GIT_DIR/git-svn directory
 and instead do all of its work in $GIT_DIR/$GIT_SVN_ID for that
-invocation.
+invocation.  The interface branch will be remotes/$GIT_SVN_ID, instead of
+remotes/git-svn.  Any remotes/$GIT_SVN_ID branch should never be modified
+by the user outside of git-svn commands.
 
 ADDITIONAL FETCH ARGUMENTS
 --------------------------
diff --git a/contrib/git-svn/t/t0000-contrib-git-svn.sh b/contrib/git-svn/t/t0000-contrib-git-svn.sh
index 181dfe008b..80ad3573db 100644
--- a/contrib/git-svn/t/t0000-contrib-git-svn.sh
+++ b/contrib/git-svn/t/t0000-contrib-git-svn.sh
@@ -71,14 +71,14 @@ test_expect_success \
 
 
 name='try a deep --rmdir with a commit'
-git checkout -b mybranch git-svn-HEAD
+git checkout -b mybranch remotes/git-svn
 mv dir/a/b/c/d/e/file dir/file
 cp dir/file file
 git update-index --add --remove dir/a/b/c/d/e/file dir/file file
 git commit -m "$name"
 
 test_expect_success "$name" \
-    "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch &&
+    "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch &&
      test -d $SVN_TREE/dir && test ! -d $SVN_TREE/dir/a"
 
 
@@ -91,13 +91,13 @@ git update-index --add dir/file/file
 git commit -m "$name"
 
 test_expect_code 1 "$name" \
-    'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch' \
+    'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch' \
     || true
 
 
 name='detect node change from directory to file #1'
 rm -rf dir $GIT_DIR/index
-git checkout -b mybranch2 git-svn-HEAD
+git checkout -b mybranch2 remotes/git-svn
 mv bar/zzz zzz
 rm -rf bar
 mv zzz bar
@@ -106,13 +106,13 @@ git update-index --add -- bar
 git commit -m "$name"
 
 test_expect_code 1 "$name" \
-    'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch2' \
+    'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch2' \
     || true
 
 
 name='detect node change from file to directory #2'
 rm -f $GIT_DIR/index
-git checkout -b mybranch3 git-svn-HEAD
+git checkout -b mybranch3 remotes/git-svn
 rm bar/zzz
 git-update-index --remove bar/zzz
 mkdir bar/zzz
@@ -121,13 +121,13 @@ git-update-index --add bar/zzz/yyy
 git commit -m "$name"
 
 test_expect_code 1 "$name" \
-    'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch3' \
+    'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch3' \
     || true
 
 
 name='detect node change from directory to file #2'
 rm -f $GIT_DIR/index
-git checkout -b mybranch4 git-svn-HEAD
+git checkout -b mybranch4 remotes/git-svn
 rm -rf dir
 git update-index --remove -- dir/file
 touch dir
@@ -136,19 +136,19 @@ git update-index --add -- dir
 git commit -m "$name"
 
 test_expect_code 1 "$name" \
-    'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch4' \
+    'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch4' \
     || true
 
 
 name='remove executable bit from a file'
 rm -f $GIT_DIR/index
-git checkout -b mybranch5 git-svn-HEAD
+git checkout -b mybranch5 remotes/git-svn
 chmod -x exec.sh
 git update-index exec.sh
 git commit -m "$name"
 
 test_expect_success "$name" \
-    "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 &&
+    "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 &&
      test ! -x $SVN_TREE/exec.sh"
 
 
@@ -158,7 +158,7 @@ git update-index exec.sh
 git commit -m "$name"
 
 test_expect_success "$name" \
-    "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 &&
+    "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 &&
      test -x $SVN_TREE/exec.sh"
 
 
@@ -170,7 +170,7 @@ git update-index exec.sh
 git commit -m "$name"
 
 test_expect_success "$name" \
-    "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 &&
+    "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 &&
      test -L $SVN_TREE/exec.sh"
 
 
@@ -182,7 +182,7 @@ git update-index --add bar/zzz exec-2.sh
 git commit -m "$name"
 
 test_expect_success "$name" \
-    "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 &&
+    "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 &&
      test -x $SVN_TREE/bar/zzz &&
      test -L $SVN_TREE/exec-2.sh"
 
@@ -196,7 +196,7 @@ git update-index exec-2.sh
 git commit -m "$name"
 
 test_expect_success "$name" \
-    "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 &&
+    "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 &&
      test -f $SVN_TREE/exec-2.sh &&
      test ! -L $SVN_TREE/exec-2.sh &&
      diff -u help $SVN_TREE/exec-2.sh"
@@ -207,9 +207,9 @@ name='test fetch functionality (svn => git) with alternate GIT_SVN_ID'
 GIT_SVN_ID=alt
 export GIT_SVN_ID
 test_expect_success "$name" \
-    "git-svn init $svnrepo && git-svn fetch -v &&
-     git-rev-list --pretty=raw git-svn-HEAD | grep ^tree | uniq > a &&
-     git-rev-list --pretty=raw alt-HEAD | grep ^tree | uniq > b &&
+    "git-svn init $svnrepo && git-svn fetch &&
+     git-rev-list --pretty=raw remotes/git-svn | grep ^tree | uniq > a &&
+     git-rev-list --pretty=raw remotes/alt | grep ^tree | uniq > b &&
      diff -u a b"
 
 test_done
diff --git a/contrib/gitview/gitview b/contrib/gitview/gitview
index 4e3847d8bf..781badbc5b 100755
--- a/contrib/gitview/gitview
+++ b/contrib/gitview/gitview
@@ -162,7 +162,7 @@ class CellRendererGraph(gtk.GenericCellRenderer):
 			for item in names:
 				names_len += len(item)
 
-		width = box_size * (cols + 1 ) + names_len 
+		width = box_size * (cols + 1 ) + names_len
 		height = box_size
 
 		# FIXME I have no idea how to use cell_area properly
@@ -239,20 +239,23 @@ class CellRendererGraph(gtk.GenericCellRenderer):
 				box_size / 4, 0, 2 * math.pi)
 
 
+		self.set_colour(ctx, colour, 0.0, 0.5)
+		ctx.stroke_preserve()
+
+		self.set_colour(ctx, colour, 0.5, 1.0)
+		ctx.fill_preserve()
+
 		if (len(names) != 0):
 			name = " "
 			for item in names:
 				name = name + item + " "
 
-			ctx.select_font_face("Monospace")
 			ctx.set_font_size(13)
-			ctx.text_path(name)
-
-		self.set_colour(ctx, colour, 0.0, 0.5)
-		ctx.stroke_preserve()
-
-		self.set_colour(ctx, colour, 0.5, 1.0)
-		ctx.fill()
+			if (flags & 1):
+				self.set_colour(ctx, colour, 0.5, 1.0)
+			else:
+				self.set_colour(ctx, colour, 0.0, 0.5)
+			ctx.show_text(name)
 
 class Commit:
 	""" This represent a commit object obtained after parsing the git-rev-list
@@ -261,11 +264,11 @@ class Commit:
 	children_sha1 = {}
 
 	def __init__(self, commit_lines):
-		self.message 		= ""
+		self.message		= ""
 		self.author		= ""
-		self.date 		= ""
-		self.committer 		= ""
-		self.commit_date 	= ""
+		self.date		= ""
+		self.committer		= ""
+		self.commit_date	= ""
 		self.commit_sha1	= ""
 		self.parent_sha1	= [ ]
 		self.parse_commit(commit_lines)
@@ -365,7 +368,7 @@ class DiffWindow:
 		save_menu.connect("activate", self.save_menu_response, "save")
 		save_menu.show()
 		menu_bar.append(save_menu)
-		vbox.pack_start(menu_bar, False, False, 2)
+		vbox.pack_start(menu_bar, expand=False, fill=True)
 		menu_bar.show()
 
 		scrollwin = gtk.ScrolledWindow()
@@ -391,7 +394,7 @@ class DiffWindow:
 		sourceview.show()
 
 
-	def set_diff(self, commit_sha1, parent_sha1):
+	def set_diff(self, commit_sha1, parent_sha1, encoding):
 		"""Set the differences showed by this window.
 		Compares the two trees and populates the window with the
 		differences.
@@ -401,7 +404,7 @@ class DiffWindow:
 			return
 
 		fp = os.popen("git diff-tree -p " + parent_sha1 + " " + commit_sha1)
-		self.buffer.set_text(fp.read())
+		self.buffer.set_text(unicode(fp.read(), encoding).encode('utf-8'))
 		fp.close()
 		self.window.show()
 
@@ -426,10 +429,11 @@ class GitView:
 
 	def __init__(self, with_diff=0):
 		self.with_diff = with_diff
-		self.window =  	gtk.Window(gtk.WINDOW_TOPLEVEL)
+		self.window =	gtk.Window(gtk.WINDOW_TOPLEVEL)
 		self.window.set_border_width(0)
 		self.window.set_title("Git repository browser")
 
+		self.get_encoding()
 		self.get_bt_sha1()
 
 		# Use three-quarters of the screen by default
@@ -468,22 +472,20 @@ class GitView:
 			self.bt_sha1[sha1].append(name)
 		fp.close()
 
+	def get_encoding(self):
+		fp = os.popen("git repo-config --get i18n.commitencoding")
+		self.encoding=string.strip(fp.readline())
+		fp.close()
+		if (self.encoding == ""):
+			self.encoding = "utf-8"
+
 
 	def construct(self):
 		"""Construct the window contents."""
+		vbox = gtk.VBox()
 		paned = gtk.VPaned()
 		paned.pack1(self.construct_top(), resize=False, shrink=True)
 		paned.pack2(self.construct_bottom(), resize=False, shrink=True)
-		self.window.add(paned)
-		paned.show()
-
-
-	def construct_top(self):
-		"""Construct the top-half of the window."""
-		vbox = gtk.VBox(spacing=6)
-		vbox.set_border_width(12)
-		vbox.show()
-
 		menu_bar = gtk.MenuBar()
 		menu_bar.set_pack_direction(gtk.PACK_DIRECTION_RTL)
 		help_menu = gtk.MenuItem("Help")
@@ -495,11 +497,23 @@ class GitView:
 		help_menu.set_submenu(menu)
 		help_menu.show()
 		menu_bar.append(help_menu)
-		vbox.pack_start(menu_bar, False, False, 2)
 		menu_bar.show()
+		vbox.pack_start(menu_bar, expand=False, fill=True)
+		vbox.pack_start(paned, expand=True, fill=True)
+		self.window.add(vbox)
+		paned.show()
+		vbox.show()
+
+
+	def construct_top(self):
+		"""Construct the top-half of the window."""
+		vbox = gtk.VBox(spacing=6)
+		vbox.set_border_width(12)
+		vbox.show()
+
 
 		scrollwin = gtk.ScrolledWindow()
-		scrollwin.set_policy(gtk.POLICY_NEVER, gtk.POLICY_AUTOMATIC)
+		scrollwin.set_policy(gtk.POLICY_AUTOMATIC, gtk.POLICY_AUTOMATIC)
 		scrollwin.set_shadow_type(gtk.SHADOW_IN)
 		vbox.pack_start(scrollwin, expand=True, fill=True)
 		scrollwin.show()
@@ -683,7 +697,7 @@ class GitView:
 		self.revid_label.set_text(revid_label)
 		self.committer_label.set_text(committer)
 		self.timestamp_label.set_text(timestamp)
-		self.message_buffer.set_text(message)
+		self.message_buffer.set_text(unicode(message, self.encoding).encode('utf-8'))
 
 		for widget in self.parents_widgets:
 			self.table.remove(widget)
@@ -728,7 +742,7 @@ class GitView:
 			button.set_relief(gtk.RELIEF_NONE)
 			button.set_sensitive(True)
 			button.connect("clicked", self._show_clicked_cb,
-					commit.commit_sha1, parent_id)
+					commit.commit_sha1, parent_id, self.encoding)
 			hbox.pack_start(button, expand=False, fill=True)
 			button.show()
 
@@ -784,7 +798,7 @@ class GitView:
 			button.set_relief(gtk.RELIEF_NONE)
 			button.set_sensitive(True)
 			button.connect("clicked", self._show_clicked_cb,
-					child_id, commit.commit_sha1)
+					child_id, commit.commit_sha1, self.encoding)
 			hbox.pack_start(button, expand=False, fill=True)
 			button.show()
 
@@ -870,15 +884,15 @@ class GitView:
 
 		# Reset nodepostion
 		if (last_nodepos > 5):
-			last_nodepos = -1 
+			last_nodepos = -1
 
 		# Add the incomplete lines of the last cell in this
 		try:
 			colour = self.colours[commit.commit_sha1]
 		except KeyError:
 			self.colours[commit.commit_sha1] = last_colour+1
-			last_colour = self.colours[commit.commit_sha1] 
-			colour =   self.colours[commit.commit_sha1] 
+			last_colour = self.colours[commit.commit_sha1]
+			colour =   self.colours[commit.commit_sha1]
 
 		try:
 			node_pos = self.nodepos[commit.commit_sha1]
@@ -910,7 +924,7 @@ class GitView:
 				self.colours[parent_id] = last_colour+1
 				last_colour = self.colours[parent_id]
 				self.nodepos[parent_id] = last_nodepos+1
-				last_nodepos = self.nodepos[parent_id] 
+				last_nodepos = self.nodepos[parent_id]
 
 			in_line.append((node_pos, self.nodepos[parent_id],
 						self.colours[parent_id]))
@@ -946,7 +960,7 @@ class GitView:
 			try:
 				next_commit = self.commits[index+1]
 				if (next_commit.commit_sha1 == sha1 and pos != int(pos)):
-				# join the line back to the node point 
+				# join the line back to the node point
 				# This need to be done only if we modified it
 					in_line.append((pos, pos-0.5, self.colours[sha1]))
 					continue;
@@ -967,10 +981,10 @@ class GitView:
 
 		self.treeview.grab_focus()
 
-	def _show_clicked_cb(self, widget,  commit_sha1, parent_sha1):
+	def _show_clicked_cb(self, widget,  commit_sha1, parent_sha1, encoding):
 		"""Callback for when the show button for a parent is clicked."""
 		window = DiffWindow()
-		window.set_diff(commit_sha1, parent_sha1)
+		window.set_diff(commit_sha1, parent_sha1, encoding)
 		self.treeview.grab_focus()
 
 if __name__ == "__main__":
diff --git a/diff-delta.c b/diff-delta.c
index c2f656ae39..2ed5984b1c 100644
--- a/diff-delta.c
+++ b/diff-delta.c
@@ -19,8 +19,9 @@
  */
 
 #include <stdlib.h>
+#include <string.h>
+#include <zlib.h>
 #include "delta.h"
-#include "zlib.h"
 
 
 /* block size: min = 16, max = 64k, power of 2 */
@@ -29,149 +30,87 @@
 #define MIN(a, b) ((a) < (b) ? (a) : (b))
 
 #define GR_PRIME 0x9e370001
-#define HASH(v, b) (((unsigned int)(v) * GR_PRIME) >> (32 - (b)))
-	
-static unsigned int hashbits(unsigned int size)
-{
-	unsigned int val = 1, bits = 0;
-	while (val < size && bits < 32) {
-		val <<= 1;
-	       	bits++;
-	}
-	return bits ? bits: 1;
-}
-
-typedef struct s_chanode {
-	struct s_chanode *next;
-	int icurr;
-} chanode_t;
-
-typedef struct s_chastore {
-	int isize, nsize;
-	chanode_t *ancur;
-} chastore_t;
-
-static void cha_init(chastore_t *cha, int isize, int icount)
-{
-	cha->isize = isize;
-	cha->nsize = icount * isize;
-	cha->ancur = NULL;
-}
-
-static void *cha_alloc(chastore_t *cha)
-{
-	chanode_t *ancur;
-	void *data;
+#define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift))
 
-	ancur = cha->ancur;
-	if (!ancur || ancur->icurr == cha->nsize) {
-		ancur = malloc(sizeof(chanode_t) + cha->nsize);
-		if (!ancur)
-			return NULL;
-		ancur->icurr = 0;
-		ancur->next = cha->ancur;
-		cha->ancur = ancur;
-	}
-
-	data = (void *)ancur + sizeof(chanode_t) + ancur->icurr;
-	ancur->icurr += cha->isize;
-	return data;
-}
-
-static void cha_free(chastore_t *cha)
-{
-	chanode_t *cur = cha->ancur;
-	while (cur) {
-		chanode_t *tmp = cur;
-		cur = cur->next;
-		free(tmp);
-	}
-}
-
-typedef struct s_bdrecord {
-	struct s_bdrecord *next;
-	unsigned int fp;
+struct index {
 	const unsigned char *ptr;
-} bdrecord_t;
-
-typedef struct s_bdfile {
-	chastore_t cha;
-	unsigned int fphbits;
-	bdrecord_t **fphash;
-} bdfile_t;
+	unsigned int val;
+	struct index *next;
+};
 
-static int delta_prepare(const unsigned char *buf, int bufsize, bdfile_t *bdf)
+static struct index ** delta_index(const unsigned char *buf,
+				   unsigned long bufsize,
+				   unsigned int *hash_shift)
 {
-	unsigned int fphbits;
-	int i, hsize;
-	const unsigned char *data, *top;
-	bdrecord_t *brec;
-	bdrecord_t **fphash;
-
-	fphbits = hashbits(bufsize / BLK_SIZE + 1);
-	hsize = 1 << fphbits;
-	fphash = malloc(hsize * sizeof(bdrecord_t *));
-	if (!fphash)
-		return -1;
-	for (i = 0; i < hsize; i++)
-		fphash[i] = NULL;
-	cha_init(&bdf->cha, sizeof(bdrecord_t), hsize / 4 + 1);
-
-	top = buf + bufsize;
-	data = buf + (bufsize / BLK_SIZE) * BLK_SIZE;
-	if (data == top)
+	unsigned int hsize, hshift, entries, blksize, i;
+	const unsigned char *data;
+	struct index *entry, **hash;
+	void *mem;
+
+	/* determine index hash size */
+	entries = (bufsize + BLK_SIZE - 1) / BLK_SIZE;
+	hsize = entries / 4;
+	for (i = 4; (1 << i) < hsize && i < 16; i++);
+	hsize = 1 << i;
+	hshift = 32 - i;
+	*hash_shift = hshift;
+
+	/* allocate lookup index */
+	mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry));
+	if (!mem)
+		return NULL;
+	hash = mem;
+	entry = mem + hsize * sizeof(*hash);
+	memset(hash, 0, hsize * sizeof(*hash));
+
+	/* then populate it */
+	data = buf + entries * BLK_SIZE - BLK_SIZE;
+	blksize = bufsize - (data - buf);
+	while (data >= buf) {
+		unsigned int val = adler32(0, data, blksize);
+		i = HASH(val, hshift);
+		entry->ptr = data;
+		entry->val = val;
+		entry->next = hash[i];
+		hash[i] = entry++;
+		blksize = BLK_SIZE;
 		data -= BLK_SIZE;
+ 	}
 
-	for ( ; data >= buf; data -= BLK_SIZE) {
-		brec = cha_alloc(&bdf->cha);
-		if (!brec) {
-			cha_free(&bdf->cha);
-			free(fphash);
-			return -1;
-		}
-		brec->fp = adler32(0, data, MIN(BLK_SIZE, top - data));
-		brec->ptr = data;
-		i = HASH(brec->fp, fphbits);
-		brec->next = fphash[i];
-		fphash[i] = brec;
-	}
-
-	bdf->fphbits = fphbits;
-	bdf->fphash = fphash;
-
-	return 0;
-}
-
-static void delta_cleanup(bdfile_t *bdf)
-{
-	free(bdf->fphash);
-	cha_free(&bdf->cha);
+	return hash;
 }
 
+/* provide the size of the copy opcode given the block offset and size */
 #define COPYOP_SIZE(o, s) \
     (!!(o & 0xff) + !!(o & 0xff00) + !!(o & 0xff0000) + !!(o & 0xff000000) + \
      !!(s & 0xff) + !!(s & 0xff00) + 1)
 
+/* the maximum size for any opcode */
+#define MAX_OP_SIZE COPYOP_SIZE(0xffffffff, 0xffffffff)
+
 void *diff_delta(void *from_buf, unsigned long from_size,
 		 void *to_buf, unsigned long to_size,
 		 unsigned long *delta_size,
 		 unsigned long max_size)
 {
-	int i, outpos, outsize, inscnt, csize, msize, moff;
-	unsigned int fp;
-	const unsigned char *ref_data, *ref_top, *data, *top, *ptr1, *ptr2;
-	unsigned char *out, *orig;
-	bdrecord_t *brec;
-	bdfile_t bdf;
+	unsigned int i, outpos, outsize, inscnt, hash_shift;
+	const unsigned char *ref_data, *ref_top, *data, *top;
+	unsigned char *out;
+	struct index *entry, **hash;
 
-	if (!from_size || !to_size || delta_prepare(from_buf, from_size, &bdf))
+	if (!from_size || !to_size)
+		return NULL;
+	hash = delta_index(from_buf, from_size, &hash_shift);
+	if (!hash)
 		return NULL;
-	
+
 	outpos = 0;
 	outsize = 8192;
+	if (max_size && outsize >= max_size)
+		outsize = max_size + MAX_OP_SIZE + 1;
 	out = malloc(outsize);
 	if (!out) {
-		delta_cleanup(&bdf);
+		free(hash);
 		return NULL;
 	}
 
@@ -199,28 +138,32 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 	}
 
 	inscnt = 0;
-	moff = 0;
-	while (data < top) {
-		msize = 0;
-		fp = adler32(0, data, MIN(top - data, BLK_SIZE));
-		i = HASH(fp, bdf.fphbits);
-		for (brec = bdf.fphash[i]; brec; brec = brec->next) {
-			if (brec->fp == fp) {
-				csize = ref_top - brec->ptr;
-				if (csize > top - data)
-					csize = top - data;
-				for (ptr1 = brec->ptr, ptr2 = data; 
-				     csize && *ptr1 == *ptr2;
-				     csize--, ptr1++, ptr2++);
 
-				csize = ptr1 - brec->ptr;
-				if (csize > msize) {
-					moff = brec->ptr - ref_data;
-					msize = csize;
-					if (msize >= 0x10000) {
-						msize = 0x10000;
-						break;
-					}
+	while (data < top) {
+		unsigned int moff = 0, msize = 0;
+		unsigned int blksize = MIN(top - data, BLK_SIZE);
+		unsigned int val = adler32(0, data, blksize);
+		i = HASH(val, hash_shift);
+		for (entry = hash[i]; entry; entry = entry->next) {
+			const unsigned char *ref = entry->ptr;
+			const unsigned char *src = data;
+			unsigned int ref_size = ref_top - ref;
+			if (entry->val != val)
+				continue;
+			if (ref_size > top - src)
+				ref_size = top - src;
+			while (ref_size && *src++ == *ref) {
+				ref++;
+				ref_size--;
+			}
+			ref_size = ref - entry->ptr;
+			if (ref_size > msize) {
+				/* this is our best match so far */
+				moff = entry->ptr - ref_data;
+				msize = ref_size;
+				if (msize >= 0x10000) {
+					msize = 0x10000;
+					break;
 				}
 			}
 		}
@@ -235,13 +178,15 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 				inscnt = 0;
 			}
 		} else {
+			unsigned char *op;
+
 			if (inscnt) {
 				out[outpos - inscnt - 1] = inscnt;
 				inscnt = 0;
 			}
 
 			data += msize;
-			orig = out + outpos++;
+			op = out + outpos++;
 			i = 0x80;
 
 			if (moff & 0xff) { out[outpos++] = moff; i |= 0x01; }
@@ -256,23 +201,21 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 			msize >>= 8;
 			if (msize & 0xff) { out[outpos++] = msize; i |= 0x20; }
 
-			*orig = i;
-		}
-
-		if (max_size && outpos > max_size) {
-			free(out);
-			delta_cleanup(&bdf);
-			return NULL;
+			*op = i;
 		}
 
-		/* next time around the largest possible output is 1 + 4 + 3 */
-		if (outpos > outsize - 8) {
+		if (outpos >= outsize - MAX_OP_SIZE) {
 			void *tmp = out;
 			outsize = outsize * 3 / 2;
-			out = realloc(out, outsize);
+			if (max_size && outsize >= max_size)
+				outsize = max_size + MAX_OP_SIZE + 1;
+			if (max_size && outpos > max_size)
+				out = NULL;
+			else
+				out = realloc(out, outsize);
 			if (!out) {
 				free(tmp);
-				delta_cleanup(&bdf);
+				free(hash);
 				return NULL;
 			}
 		}
@@ -281,7 +224,7 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 	if (inscnt)
 		out[outpos - inscnt - 1] = inscnt;
 
-	delta_cleanup(&bdf);
+	free(hash);
 	*delta_size = outpos;
 	return out;
 }
diff --git a/diff.c b/diff.c
index 804c08c2cf..c0548eed98 100644
--- a/diff.c
+++ b/diff.c
@@ -178,11 +178,12 @@ static void emit_rewrite_diff(const char *name_a,
 		copy_file('+', temp[1].name);
 }
 
-static void builtin_diff(const char *name_a,
+static const char *builtin_diff(const char *name_a,
 			 const char *name_b,
 			 struct diff_tempfile *temp,
 			 const char *xfrm_msg,
-			 int complete_rewrite)
+			 int complete_rewrite,
+			 const char **args)
 {
 	int i, next_at, cmd_size;
 	const char *const diff_cmd = "diff -L%s -L%s";
@@ -242,19 +243,24 @@ static void builtin_diff(const char *name_a,
 		}
 		if (xfrm_msg && xfrm_msg[0])
 			puts(xfrm_msg);
+		/*
+		 * we do not run diff between different kind
+		 * of objects.
+		 */
 		if (strncmp(temp[0].mode, temp[1].mode, 3))
-			/* we do not run diff between different kind
-			 * of objects.
-			 */
-			exit(0);
+			return NULL;
 		if (complete_rewrite) {
-			fflush(NULL);
 			emit_rewrite_diff(name_a, name_b, temp);
-			exit(0);
+			return NULL;
 		}
 	}
-	fflush(NULL);
-	execlp("/bin/sh","sh", "-c", cmd, NULL);
+
+	/* This is disgusting */
+	*args++ = "sh";
+	*args++ = "-c";
+	*args++ = cmd;
+	*args = NULL;
+	return "/bin/sh";
 }
 
 struct diff_filespec *alloc_filespec(const char *path)
@@ -559,6 +565,40 @@ static void remove_tempfile_on_signal(int signo)
 	raise(signo);
 }
 
+static int spawn_prog(const char *pgm, const char **arg)
+{
+	pid_t pid;
+	int status;
+
+	fflush(NULL);
+	pid = fork();
+	if (pid < 0)
+		die("unable to fork");
+	if (!pid) {
+		execvp(pgm, (char *const*) arg);
+		exit(255);
+	}
+
+	while (waitpid(pid, &status, 0) < 0) {
+		if (errno == EINTR)
+			continue;
+		return -1;
+	}
+
+	/* Earlier we did not check the exit status because
+	 * diff exits non-zero if files are different, and
+	 * we are not interested in knowing that.  It was a
+	 * mistake which made it harder to quit a diff-*
+	 * session that uses the git-apply-patch-script as
+	 * the GIT_EXTERNAL_DIFF.  A custom GIT_EXTERNAL_DIFF
+	 * should also exit non-zero only when it wants to
+	 * abort the entire diff-* session.
+	 */
+	if (WIFEXITED(status) && !WEXITSTATUS(status))
+		return 0;
+	return -1;
+}
+
 /* An external diff command takes:
  *
  * diff-cmd name infile1 infile1-sha1 infile1-mode \
@@ -573,9 +613,9 @@ static void run_external_diff(const char *pgm,
 			      const char *xfrm_msg,
 			      int complete_rewrite)
 {
+	const char *spawn_arg[10];
 	struct diff_tempfile *temp = diff_temp;
-	pid_t pid;
-	int status;
+	int retval;
 	static int atexit_asked = 0;
 	const char *othername;
 
@@ -592,59 +632,41 @@ static void run_external_diff(const char *pgm,
 		signal(SIGINT, remove_tempfile_on_signal);
 	}
 
-	fflush(NULL);
-	pid = fork();
-	if (pid < 0)
-		die("unable to fork");
-	if (!pid) {
-		if (pgm) {
-			if (one && two) {
-				const char *exec_arg[10];
-				const char **arg = &exec_arg[0];
-				*arg++ = pgm;
-				*arg++ = name;
-				*arg++ = temp[0].name;
-				*arg++ = temp[0].hex;
-				*arg++ = temp[0].mode;
-				*arg++ = temp[1].name;
-				*arg++ = temp[1].hex;
-				*arg++ = temp[1].mode;
-				if (other) {
-					*arg++ = other;
-					*arg++ = xfrm_msg;
-				}
-				*arg = NULL;
-				execvp(pgm, (char *const*) exec_arg);
+	if (pgm) {
+		const char **arg = &spawn_arg[0];
+		if (one && two) {
+			*arg++ = pgm;
+			*arg++ = name;
+			*arg++ = temp[0].name;
+			*arg++ = temp[0].hex;
+			*arg++ = temp[0].mode;
+			*arg++ = temp[1].name;
+			*arg++ = temp[1].hex;
+			*arg++ = temp[1].mode;
+			if (other) {
+				*arg++ = other;
+				*arg++ = xfrm_msg;
 			}
-			else
-				execlp(pgm, pgm, name, NULL);
+		} else {
+			*arg++ = pgm;
+			*arg++ = name;
 		}
-		/*
-		 * otherwise we use the built-in one.
-		 */
-		if (one && two)
-			builtin_diff(name, othername, temp, xfrm_msg,
-				     complete_rewrite);
-		else
+		*arg = NULL;
+	} else {
+		if (one && two) {
+			pgm = builtin_diff(name, othername, temp, xfrm_msg, complete_rewrite, spawn_arg);
+		} else
 			printf("* Unmerged path %s\n", name);
-		exit(0);
 	}
-	if (waitpid(pid, &status, 0) < 0 ||
-	    !WIFEXITED(status) || WEXITSTATUS(status)) {
-		/* Earlier we did not check the exit status because
-		 * diff exits non-zero if files are different, and
-		 * we are not interested in knowing that.  It was a
-		 * mistake which made it harder to quit a diff-*
-		 * session that uses the git-apply-patch-script as
-		 * the GIT_EXTERNAL_DIFF.  A custom GIT_EXTERNAL_DIFF
-		 * should also exit non-zero only when it wants to
-		 * abort the entire diff-* session.
-		 */
-		remove_tempfile();
+
+	retval = 0;
+	if (pgm)
+		retval = spawn_prog(pgm, spawn_arg);
+	remove_tempfile();
+	if (retval) {
 		fprintf(stderr, "external diff died, stopping at %s.\n", name);
 		exit(1);
 	}
-	remove_tempfile();
 }
 
 static void diff_fill_sha1_info(struct diff_filespec *one)
diff --git a/diffcore-break.c b/diffcore-break.c
index c57513a4fa..0fc2b860be 100644
--- a/diffcore-break.c
+++ b/diffcore-break.c
@@ -4,8 +4,6 @@
 #include "cache.h"
 #include "diff.h"
 #include "diffcore.h"
-#include "delta.h"
-#include "count-delta.h"
 
 static int should_break(struct diff_filespec *src,
 			struct diff_filespec *dst,
@@ -47,7 +45,6 @@ static int should_break(struct diff_filespec *src,
 	 * The value we return is 1 if we want the pair to be broken,
 	 * or 0 if we do not.
 	 */
-	void *delta;
 	unsigned long delta_size, base_size, src_copied, literal_added;
 	int to_break = 0;
 
@@ -58,6 +55,10 @@ static int should_break(struct diff_filespec *src,
 	if (!S_ISREG(src->mode) || !S_ISREG(dst->mode))
 		return 0; /* leave symlink rename alone */
 
+	if (src->sha1_valid && dst->sha1_valid &&
+	    !memcmp(src->sha1, dst->sha1, 20))
+		return 0; /* they are the same */
+
 	if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
 		return 0; /* error but caught downstream */
 
@@ -65,19 +66,11 @@ static int should_break(struct diff_filespec *src,
 	if (base_size < MINIMUM_BREAK_SIZE)
 		return 0; /* we do not break too small filepair */
 
-	delta = diff_delta(src->data, src->size,
-			   dst->data, dst->size,
-			   &delta_size, 0);
-	if (!delta)
-		return 0; /* error but caught downstream */
-
-	/* Estimate the edit size by interpreting delta. */
-	if (count_delta(delta, delta_size,
-			&src_copied, &literal_added)) {
-		free(delta);
-		return 0; /* we cannot tell */
-	}
-	free(delta);
+	if (diffcore_count_changes(src->data, src->size,
+				   dst->data, dst->size,
+				   0,
+				   &src_copied, &literal_added))
+		return 0;
 
 	/* Compute merge-score, which is "how much is removed
 	 * from the source material".  The clean-up stage will
diff --git a/diffcore-delta.c b/diffcore-delta.c
new file mode 100644
index 0000000000..1e6a6911ec
--- /dev/null
+++ b/diffcore-delta.c
@@ -0,0 +1,43 @@
+#include "cache.h"
+#include "diff.h"
+#include "diffcore.h"
+#include "delta.h"
+#include "count-delta.h"
+
+static int diffcore_count_changes_1(void *src, unsigned long src_size,
+				    void *dst, unsigned long dst_size,
+				    unsigned long delta_limit,
+				    unsigned long *src_copied,
+				    unsigned long *literal_added)
+{
+	void *delta;
+	unsigned long delta_size;
+
+	delta = diff_delta(src, src_size,
+			   dst, dst_size,
+			   &delta_size, delta_limit);
+	if (!delta)
+		/* If delta_limit is exceeded, we have too much differences */
+		return -1;
+
+	/* Estimate the edit size by interpreting delta. */
+	if (count_delta(delta, delta_size, src_copied, literal_added)) {
+		free(delta);
+		return -1;
+	}
+	free(delta);
+	return 0;
+}
+
+int diffcore_count_changes(void *src, unsigned long src_size,
+			   void *dst, unsigned long dst_size,
+			   unsigned long delta_limit,
+			   unsigned long *src_copied,
+			   unsigned long *literal_added)
+{
+	return diffcore_count_changes_1(src, src_size,
+					dst, dst_size,
+					delta_limit,
+					src_copied,
+					literal_added);
+}
diff --git a/diffcore-rename.c b/diffcore-rename.c
index ffd126af0d..55cf1c37f3 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -4,8 +4,6 @@
 #include "cache.h"
 #include "diff.h"
 #include "diffcore.h"
-#include "delta.h"
-#include "count-delta.h"
 
 /* Table of rename/copy destinations */
 
@@ -135,7 +133,6 @@ static int estimate_similarity(struct diff_filespec *src,
 	 * match than anything else; the destination does not even
 	 * call into this function in that case.
 	 */
-	void *delta;
 	unsigned long delta_size, base_size, src_copied, literal_added;
 	unsigned long delta_limit;
 	int score;
@@ -165,28 +162,13 @@ static int estimate_similarity(struct diff_filespec *src,
 	if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
 		return 0; /* error but caught downstream */
 
-	delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE;
-	delta = diff_delta(src->data, src->size,
-			   dst->data, dst->size,
-			   &delta_size, delta_limit);
-	if (!delta)
-		/* If delta_limit is exceeded, we have too much differences */
-		return 0;
-
-	/* A delta that has a lot of literal additions would have
-	 * big delta_size no matter what else it does.
-	 */
-	if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE) {
-		free(delta);
-		return 0;
-	}
 
-	/* Estimate the edit size by interpreting delta. */
-	if (count_delta(delta, delta_size, &src_copied, &literal_added)) {
-		free(delta);
+	delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE;
+	if (diffcore_count_changes(src->data, src->size,
+				   dst->data, dst->size,
+				   delta_limit,
+				   &src_copied, &literal_added))
 		return 0;
-	}
-	free(delta);
 
 	/* Extent of damage */
 	if (src->size + literal_added < src_copied)
diff --git a/diffcore.h b/diffcore.h
index 12cd816591..dba4f17658 100644
--- a/diffcore.h
+++ b/diffcore.h
@@ -101,4 +101,10 @@ void diff_debug_queue(const char *, struct diff_queue_struct *);
 #define diff_debug_queue(a,b) do {} while(0)
 #endif
 
+extern int diffcore_count_changes(void *src, unsigned long src_size,
+				  void *dst, unsigned long dst_size,
+				  unsigned long delta_limit,
+				  unsigned long *src_copied,
+				  unsigned long *literal_added);
+
 #endif
diff --git a/environment.c b/environment.c
index 251e53ca09..16c08f0697 100644
--- a/environment.c
+++ b/environment.c
@@ -17,6 +17,7 @@ int only_use_symrefs = 0;
 int repository_format_version = 0;
 char git_commit_encoding[MAX_ENCODING_LENGTH] = "utf-8";
 int shared_repository = 0;
+const char *apply_default_whitespace = NULL;
 
 static char *git_dir, *git_object_dir, *git_index_file, *git_refs_dir,
 	*git_graft_file;
diff --git a/git-am.sh b/git-am.sh
index 7cc4ae5a30..eab4aa891e 100755
--- a/git-am.sh
+++ b/git-am.sh
@@ -2,7 +2,8 @@
 #
 # Copyright (c) 2005, 2006 Junio C Hamano
 
-USAGE='[--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way] <mbox>
+USAGE='[--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way]
+  [--interactive] [--whitespace=<option>] <mbox>...
   or, when resuming [--skip | --resolved]'
 . git-sh-setup
 
@@ -100,7 +101,7 @@ fall_back_3way () {
 }
 
 prec=4
-dotest=.dotest sign= utf8= keep= skip= interactive= resolved= binary=
+dotest=.dotest sign= utf8= keep= skip= interactive= resolved= binary= ws=
 
 while case "$#" in 0) break;; esac
 do
@@ -133,6 +134,9 @@ do
 	--sk|--ski|--skip)
 	skip=t; shift ;;
 
+	--whitespace=*)
+	ws=$1; shift ;;
+
 	--)
 	shift; break ;;
 	-*)
@@ -171,10 +175,11 @@ else
 		exit 1
 	}
 
-	# -b, -s, -u and -k flags are kept for the resuming session after
-	# a patch failure.
+	# -b, -s, -u, -k and --whitespace flags are kept for the
+	# resuming session after a patch failure.
 	# -3 and -i can and must be given when resuming.
 	echo "$binary" >"$dotest/binary"
+	echo " $ws" >"$dotest/whitespace"
 	echo "$sign" >"$dotest/sign"
 	echo "$utf8" >"$dotest/utf8"
 	echo "$keep" >"$dotest/keep"
@@ -202,6 +207,7 @@ if test "$(cat "$dotest/keep")" = t
 then
 	keep=-k
 fi
+ws=`cat "$dotest/whitespace"`
 if test "$(cat "$dotest/sign")" = t
 then
 	SIGNOFF=`git-var GIT_COMMITTER_IDENT | sed -e '
@@ -355,7 +361,7 @@ do
 
 	case "$resolved" in
 	'')
-		git-apply $binary --index "$dotest/patch"
+		git-apply $binary --index $ws "$dotest/patch"
 		apply_status=$?
 		;;
 	t)
diff --git a/git-annotate.perl b/git-annotate.perl
index f9c2c6caf5..d93ee19c7e 100755
--- a/git-annotate.perl
+++ b/git-annotate.perl
@@ -15,6 +15,8 @@ ()
 	print STDERR 'Usage: ${\basename $0} [-s] [-S revs-file] file [ revision ]
 	-l, --long
 			Show long rev (Defaults off)
+	-t, --time
+			Show raw timestamp (Defaults off)
 	-r, --rename
 			Follow renames (Defaults on).
 	-S, --rev-file revs-file
@@ -26,12 +28,13 @@ ()
 	exit(1);
 }
 
-our ($help, $longrev, $rename, $starting_rev, $rev_file) = (0, 0, 1);
+our ($help, $longrev, $rename, $rawtime, $starting_rev, $rev_file) = (0, 0, 1);
 
 my $rc = GetOptions(	"long|l" => \$longrev,
+			"time|t" => \$rawtime,
 			"help|h" => \$help,
 			"rename|r" => \$rename,
-			"rev-file|S" => \$rev_file);
+			"rev-file|S=s" => \$rev_file);
 if (!$rc or $help) {
 	usage();
 }
@@ -125,7 +128,7 @@ ()
 	}
 
 	printf("%s\t(%10s\t%10s\t%d)%s\n", $rev, $committer,
-		format_date($date), $i++, $output);
+		format_date($date), ++$i, $output);
 }
 
 sub init_claim {
@@ -174,7 +177,8 @@ sub git_rev_list {
 
 	my $revlist;
 	if ($rev_file) {
-		open($revlist, '<' . $rev_file);
+		open($revlist, '<' . $rev_file)
+		    or die "Failed to open $rev_file : $!";
 	} else {
 		$revlist = open_pipe("git-rev-list","--parents","--remove-empty",$rev,"--",$file)
 			or die "Failed to exec git-rev-list: $!";
@@ -304,6 +308,12 @@ sub _git_diff_parse {
 			}
 			$ri++;
 
+		} elsif (m/^\\/) {
+			;
+			# Skip \No newline at end of file.
+			# But this can be internationalized, so only look
+			# for an initial \
+
 		} else {
 			if (substr($_,1) ne get_line($slines,$ri) ) {
 				die sprintf("Line %d (%d) does not match:\n|%s\n|%s\n%s => %s\n",
@@ -404,8 +414,10 @@ sub git_commit_info {
 }
 
 sub format_date {
+	if ($rawtime) {
+		return $_[0];
+	}
 	my ($timestamp, $timezone) = split(' ', $_[0]);
-
 	return strftime("%Y-%m-%d %H:%M:%S " . $timezone, gmtime($timestamp));
 }
 
diff --git a/git-branch.sh b/git-branch.sh
index 6ac961e6d1..663a3a370c 100755
--- a/git-branch.sh
+++ b/git-branch.sh
@@ -48,6 +48,12 @@ If you are sure you want to delete it, run 'git branch -D $branch_name'."
     exit 0
 }
 
+ls_remote_branches () {
+    git-rev-parse --symbolic --all |
+    sed -ne 's|^refs/\(remotes/\)|\1|p' |
+    sort
+}
+
 force=
 while case "$#,$1" in 0,*) break ;; *,-*) ;; *) break ;; esac
 do
@@ -56,6 +62,10 @@ do
 		delete_branch "$@"
 		exit
 		;;
+	-r)
+		ls_remote_branches
+		exit
+		;;
 	-f)
 		force="$1"
 		;;
diff --git a/git-commit.sh b/git-commit.sh
index f7ee1aadee..d9ec1f14d9 100755
--- a/git-commit.sh
+++ b/git-commit.sh
@@ -3,7 +3,7 @@
 # Copyright (c) 2005 Linus Torvalds
 # Copyright (c) 2006 Junio C Hamano
 
-USAGE='[-a] [-s] [-v] [--no-verify] [-m <message> | -F <logfile> | (-C|-c) <commit>] [-e] [--author <author>] [[-i | -o] <path>...]'
+USAGE='[-a] [-s] [-v] [--no-verify] [-m <message> | -F <logfile> | (-C|-c) <commit>) [--amend] [-e] [--author <author>] [[-i | -o] <path>...]'
 SUBDIRECTORY_OK=Yes
 . git-sh-setup
 
@@ -64,6 +64,22 @@ run_status () {
 	# We always show status for the whole tree.
 	cd "$TOP"
 
+	IS_INITIAL="$initial_commit"
+	REFERENCE=HEAD
+	case "$amend" in
+	t)
+		# If we are amending the initial commit, there
+		# is no HEAD^1.
+		if git-rev-parse --verify "HEAD^1" >/dev/null 2>&1
+		then
+			REFERENCE="HEAD^1"
+			IS_INITIAL=
+		else
+			IS_INITIAL=t
+		fi
+		;;
+	esac
+
 	# If TMP_INDEX is defined, that means we are doing
 	# "--only" partial commit, and that index file is used
 	# to build the tree for the commit.  Otherwise, if
@@ -85,10 +101,10 @@ run_status () {
 	*)  echo "# On branch $branch" ;;
 	esac
 
-	if test -z "$initial_commit"
+	if test -z "$IS_INITIAL"
 	then
 	    git-diff-index -M --cached --name-status \
-		--diff-filter=MDTCRA HEAD |
+		--diff-filter=MDTCRA $REFERENCE |
 	    sed -e '
 		    s/\\/\\\\/g
 		    s/ /\\ /g
@@ -147,7 +163,7 @@ run_status () {
 
 	if test -n "$verbose"
 	then
-	    git-diff-index --cached -M -p --diff-filter=MDTCRA HEAD
+	    git-diff-index --cached -M -p --diff-filter=MDTCRA $REFERENCE
 	fi
 	case "$committable" in
 	0)
@@ -173,6 +189,7 @@ also=
 only=
 logfile=
 use_commit=
+amend=
 no_edit=
 log_given=
 log_message=
@@ -254,6 +271,12 @@ do
       verify=
       shift
       ;;
+  --a|--am|--ame|--amen|--amend)
+      amend=t
+      log_given=t$log_given
+      use_commit=HEAD
+      shift
+      ;;
   -c)
       case "$#" in 1) usage ;; esac
       shift
@@ -328,6 +351,15 @@ done
 ################################################################
 # Sanity check options
 
+case "$amend,$initial_commit" in
+t,t)
+  die "You do not have anything to amend." ;;
+t,)
+  if [ -f "$GIT_DIR/MERGE_HEAD" ]; then
+    die "You are in the middle of a merge -- cannot amend."
+  fi ;;
+esac
+
 case "$log_given" in
 tt*)
   die "Only one of -c/-C/-F/-m can be used." ;;
@@ -559,13 +591,18 @@ if test -z "$initial_commit"
 then
 	if [ -f "$GIT_DIR/MERGE_HEAD" ]; then
 		PARENTS="-p HEAD "`sed -e 's/^/-p /' "$GIT_DIR/MERGE_HEAD"`
+	elif test -n "$amend"; then
+		PARENTS=$(git-cat-file commit HEAD |
+			sed -n -e '/^$/q' -e 's/^parent /-p /p')
 	fi
+	current=$(git-rev-parse --verify HEAD)
 else
 	if [ -z "$(git-ls-files)" ]; then
 		echo >&2 Nothing to commit
 		exit 1
 	fi
 	PARENTS=""
+	current=
 fi
 
 {
diff --git a/git-cvsserver.perl b/git-cvsserver.perl
index d20d1a8c4b..7d3f78e375 100755
--- a/git-cvsserver.perl
+++ b/git-cvsserver.perl
@@ -53,6 +53,7 @@
     'Entry'           => \&req_Entry,
     'Modified'        => \&req_Modified,
     'Unchanged'       => \&req_Unchanged,
+    'Questionable'    => \&req_Questionable,
     'Argument'        => \&req_Argument,
     'Argumentx'       => \&req_Argument,
     'expand-modules'  => \&req_expandmodules,
@@ -63,6 +64,7 @@
     'ci'              => \&req_ci,
     'diff'            => \&req_diff,
     'log'             => \&req_log,
+    'rlog'            => \&req_log,
     'tag'             => \&req_CATCHALL,
     'status'          => \&req_status,
     'admin'           => \&req_CATCHALL,
@@ -85,6 +87,31 @@
 my $TEMP_DIR = tempdir( CLEANUP => 1 );
 $log->debug("Temporary directory is '$TEMP_DIR'");
 
+# if we are called with a pserver argument,
+# deal with the authentication cat before entereing the
+# main loop
+if (@ARGV && $ARGV[0] eq 'pserver') {
+    my $line = <STDIN>; chomp $line;
+    unless( $line eq 'BEGIN AUTH REQUEST') {
+       die "E Do not understand $line - expecting BEGIN AUTH REQUEST\n";
+    }
+    $line = <STDIN>; chomp $line;
+    req_Root('root', $line) # reuse Root
+       or die "E Invalid root $line \n";
+    $line = <STDIN>; chomp $line;
+    unless ($line eq 'anonymous') {
+       print "E Only anonymous user allowed via pserver\n";
+       print "I HATE YOU\n";
+    }
+    $line = <STDIN>; chomp $line;    # validate the password?
+    $line = <STDIN>; chomp $line;
+    unless ($line eq 'END AUTH REQUEST') {
+       die "E Do not understand $line -- expecting END AUTH REQUEST\n";
+    }
+    print "I LOVE YOU\n";
+    # and now back to our regular programme...
+}
+
 # Keep going until the client closes the connection
 while (<STDIN>)
 {
@@ -137,8 +164,21 @@ sub req_Root
     $state->{CVSROOT} = $data;
 
     $ENV{GIT_DIR} = $state->{CVSROOT} . "/";
+    unless (-d $ENV{GIT_DIR} && -e $ENV{GIT_DIR}.'HEAD') {
+       print "E $ENV{GIT_DIR} does not seem to be a valid GIT repository\n";
+        print "E \n";
+        print "error 1 $ENV{GIT_DIR} is not a valid repository\n";
+       return 0;
+    }
 
-    foreach my $line ( `git-var -l` )
+    my @gitvars = `git-var -l`;
+    if ($?) {
+       print "E problems executing git-var on the server -- this is not a git repository or the PATH is not set correcly.\n";
+        print "E \n";
+        print "error 1 - problem executing git-var\n";
+       return 0;
+    }
+    foreach my $line ( @gitvars )
     {
         next unless ( $line =~ /^(.*?)\.(.*?)=(.*)$/ );
         $cfg->{$1}{$2} = $3;
@@ -150,6 +190,7 @@ sub req_Root
         print "E the repo config file needs a [gitcvs] section added, and the parameter 'enabled' set to 1\n";
         print "E \n";
         print "error 1 GITCVS emulation disabled\n";
+        return 0;
     }
 
     if ( defined ( $cfg->{gitcvs}{logfile} ) )
@@ -158,6 +199,8 @@ sub req_Root
     } else {
         $log->nofile();
     }
+
+    return 1;
 }
 
 # Global_option option \n
@@ -459,6 +502,22 @@ sub req_Unchanged
     #$log->debug("req_Unchanged : $data");
 }
 
+# Questionable filename \n
+#     Response expected: no. Additional data: no.
+#     Tell the server to check whether filename should be ignored,
+#     and if not, next time the server sends responses, send (in
+#     a M response) `?' followed by the directory and filename.
+#     filename must not contain `/'; it needs to be a file in the
+#     directory named by the most recent Directory request.
+sub req_Questionable
+{
+    my ( $cmd, $data ) = @_;
+
+    $state->{entries}{$state->{directory}.$data}{questionable} = 1;
+
+    #$log->debug("req_Questionable : $data");
+}
+
 # Argument text \n
 #     Response expected: no. Save argument for use in a subsequent command.
 #     Arguments accumulate until an argument-using command is given, at which
@@ -553,8 +612,62 @@ sub req_co
     my $updater = GITCVS::updater->new($state->{CVSROOT}, $module, $log);
     $updater->update();
 
+    $checkout_path =~ s|/$||; # get rid of trailing slashes
+
+    # Eclipse seems to need the Clear-sticky command
+    # to prepare the 'Entries' file for the new directory.
+    print "Clear-sticky $checkout_path/\n";
+    print $state->{CVSROOT} . "/$module/\n";
+    print "Clear-static-directory $checkout_path/\n";
+    print $state->{CVSROOT} . "/$module/\n";
+    print "Clear-sticky $checkout_path/\n"; # yes, twice
+    print $state->{CVSROOT} . "/$module/\n";
+    print "Template $checkout_path/\n";
+    print $state->{CVSROOT} . "/$module/\n";
+    print "0\n";
+
     # instruct the client that we're checking out to $checkout_path
-    print "E cvs server: updating $checkout_path\n";
+    print "E cvs checkout: Updating $checkout_path\n";
+
+    my %seendirs = ();
+    my $lastdir ='';
+
+    # recursive
+    sub prepdir {
+       my ($dir, $repodir, $remotedir, $seendirs) = @_;
+       my $parent = dirname($dir);
+       $dir       =~ s|/+$||;
+       $repodir   =~ s|/+$||;
+       $remotedir =~ s|/+$||;
+       $parent    =~ s|/+$||;
+       $log->debug("announcedir $dir, $repodir, $remotedir" );
+
+       if ($parent eq '.' || $parent eq './') {
+           $parent = '';
+       }
+       # recurse to announce unseen parents first
+       if (length($parent) && !exists($seendirs->{$parent})) {
+           prepdir($parent, $repodir, $remotedir, $seendirs);
+       }
+       # Announce that we are going to modify at the parent level
+       if ($parent) {
+           print "E cvs checkout: Updating $remotedir/$parent\n";
+       } else {
+           print "E cvs checkout: Updating $remotedir\n";
+       }
+       print "Clear-sticky $remotedir/$parent/\n";
+       print "$repodir/$parent/\n";
+
+       print "Clear-static-directory $remotedir/$dir/\n";
+       print "$repodir/$dir/\n";
+       print "Clear-sticky $remotedir/$parent/\n"; # yes, twice
+       print "$repodir/$parent/\n";
+       print "Template $remotedir/$dir/\n";
+       print "$repodir/$dir/\n";
+       print "0\n";
+
+       $seendirs->{$dir} = 1;
+    }
 
     foreach my $git ( @{$updater->gethead} )
     {
@@ -563,25 +676,32 @@ sub req_co
 
         ( $git->{name}, $git->{dir} ) = filenamesplit($git->{name});
 
+       if (length($git->{dir}) && $git->{dir} ne './'
+           && $git->{dir} ne $lastdir ) {
+           unless (exists($seendirs{$git->{dir}})) {
+               prepdir($git->{dir}, $state->{CVSROOT} . "/$module/",
+                       $checkout_path, \%seendirs);
+               $lastdir = $git->{dir};
+               $seendirs{$git->{dir}} = 1;
+           }
+           print "E cvs checkout: Updating /$checkout_path/$git->{dir}\n";
+       }
+
         # modification time of this file
         print "Mod-time $git->{modified}\n";
 
         # print some information to the client
-        print "MT +updated\n";
-        print "MT text U\n";
         if ( defined ( $git->{dir} ) and $git->{dir} ne "./" )
         {
-            print "MT fname $checkout_path/$git->{dir}$git->{name}\n";
+            print "M U $checkout_path/$git->{dir}$git->{name}\n";
         } else {
-            print "MT fname $checkout_path/$git->{name}\n";
+            print "M U $checkout_path/$git->{name}\n";
         }
-        print "MT newline\n";
-        print "MT -updated\n";
 
-        # instruct client we're sending a file to put in this path
-        print "Created $checkout_path/" . ( defined ( $git->{dir} ) ? $git->{dir} . "/" : "" ) . "\n";
+       # instruct client we're sending a file to put in this path
+       print "Created $checkout_path/" . ( defined ( $git->{dir} ) and $git->{dir} ne "./" ? $git->{dir} . "/" : "" ) . "\n";
 
-        print $state->{CVSROOT} . "/$module/" . ( defined ( $git->{dir} ) ? $git->{dir} . "/" : "" ) . "$git->{name}\n";
+       print $state->{CVSROOT} . "/$module/" . ( defined ( $git->{dir} ) and $git->{dir} ne "./" ? $git->{dir} . "/" : "" ) . "$git->{name}\n";
 
         # this is an "entries" line
         print "/$git->{name}/1.$git->{revision}///\n";
@@ -612,6 +732,26 @@ sub req_update
 
     argsplit("update");
 
+    #
+    # It may just be a client exploring the available heads/modukles
+    # in that case, list them as top level directories and leave it
+    # at that. Eclipse uses this technique to offer you a list of
+    # projects (heads in this case) to checkout.
+    #
+    if ($state->{module} eq '') {
+        print "E cvs update: Updating .\n";
+	opendir HEADS, $state->{CVSROOT} . '/refs/heads';
+	while (my $head = readdir(HEADS)) {
+	    if (-f $state->{CVSROOT} . '/refs/heads/' . $head) {
+	        print "E cvs update: New directory `$head'\n";
+	    }
+	}
+	closedir HEADS;
+	print "ok\n";
+	return 1;
+    }
+
+
     # Grab a handle to the SQLite db and do any necessary updates
     my $updater = GITCVS::updater->new($state->{CVSROOT}, $state->{module}, $log);
 
@@ -657,8 +797,27 @@ sub req_update
 
         #$log->debug("Target revision is $meta->{revision}, current working revision is $wrev");
 
-        # Files are up to date if the working copy and repo copy have the same revision, and the working copy is unmodified _and_ the user hasn't specified -C
-        next if ( defined ( $wrev ) and defined($meta->{revision}) and $wrev == $meta->{revision} and $state->{entries}{$filename}{unchanged} and not exists ( $state->{opt}{C} ) );
+        # Files are up to date if the working copy and repo copy have the same revision,
+        # and the working copy is unmodified _and_ the user hasn't specified -C
+        next if ( defined ( $wrev )
+                  and defined($meta->{revision})
+                  and $wrev == $meta->{revision}
+                  and $state->{entries}{$filename}{unchanged}
+                  and not exists ( $state->{opt}{C} ) );
+
+        # If the working copy and repo copy have the same revision,
+        # but the working copy is modified, tell the client it's modified
+        if ( defined ( $wrev )
+             and defined($meta->{revision})
+             and $wrev == $meta->{revision}
+             and not exists ( $state->{opt}{C} ) )
+        {
+            $log->info("Tell the client the file is modified");
+            print "MT text U\n";
+            print "MT fname $filename\n";
+            print "MT newline\n";
+            next;
+        }
 
         if ( $meta->{filehash} eq "deleted" )
         {
@@ -670,7 +829,8 @@ sub req_update
             print "Removed $dirpart\n";
             print "$filepart\n";
         }
-        elsif ( not defined ( $state->{entries}{$filename}{modified_hash} ) or $state->{entries}{$filename}{modified_hash} eq $oldmeta->{filehash} )
+        elsif ( not defined ( $state->{entries}{$filename}{modified_hash} )
+		or $state->{entries}{$filename}{modified_hash} eq $oldmeta->{filehash} )
         {
             $log->info("Updating '$filename'");
             # normal update, just send the new revision (either U=Update, or A=Add, or R=Remove)
@@ -706,6 +866,7 @@ sub req_update
             # transmit file
             transmitfile($meta->{filehash});
         } else {
+            $log->info("Updating '$filename'");
             my ( $filepart, $dirpart ) = filenamesplit($meta->{name});
 
             my $dir = tempdir( DIR => $TEMP_DIR, CLEANUP => 1 ) . "/";
@@ -781,6 +942,12 @@ sub req_ci
 
     $log->info("req_ci : " . ( defined($data) ? $data : "[NULL]" ));
 
+    if ( @ARGV && $ARGV[0] eq 'pserver')
+    {
+        print "error 1 pserver access cannot commit\n";
+        exit;
+    }
+
     if ( -e $state->{CVSROOT} . "/index" )
     {
         print "error 1 Index already exists in git repo\n";
@@ -2271,7 +2438,7 @@ sub gethead
 
     return $self->{gethead_cache} if ( defined ( $self->{gethead_cache} ) );
 
-    my $db_query = $self->{dbh}->prepare_cached("SELECT name, filehash, mode, revision, modified, commithash, author FROM head",{},1);
+    my $db_query = $self->{dbh}->prepare_cached("SELECT name, filehash, mode, revision, modified, commithash, author FROM head ORDER BY name ASC",{},1);
     $db_query->execute();
 
     my $tree = [];
diff --git a/git-format-patch.sh b/git-format-patch.sh
index eb75de4601..2bd26395ec 100755
--- a/git-format-patch.sh
+++ b/git-format-patch.sh
@@ -174,7 +174,7 @@ titleScript='
 process_one () {
 	perl -w -e '
 my ($keep_subject, $num, $signoff, $commsg) = @ARGV;
-my ($signoff_pattern, $done_header, $done_subject, $signoff_seen,
+my ($signoff_pattern, $done_header, $done_subject, $done_separator, $signoff_seen,
     $last_was_signoff);
 
 if ($signoff) {
@@ -228,6 +228,11 @@ while (<FH>) {
 	$done_subject = 1;
 	next;
     }
+    unless ($done_separator) {
+        print "\n";
+        $done_separator = 1;
+        next if (/^$/);
+    }
 
     $last_was_signoff = 0;
     if (/Signed-off-by:/i) {
diff --git a/git-mv.perl b/git-mv.perl
index 2ea852c918..75aa8feeb6 100755
--- a/git-mv.perl
+++ b/git-mv.perl
@@ -19,25 +19,26 @@ ()
 	exit(1);
 }
 
-my $GIT_DIR = `git rev-parse --git-dir`;
-exit 1 if $?; # rev-parse would have given "not a git dir" message.
-chomp($GIT_DIR);
-
 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];
-	# remove any trailing slash
-	$dstDir =~ s/\/$//;
 	@srcArgs = @ARGV[0..$argCount-2];
-	
+
 	foreach $src (@srcArgs) {
 		$base = $src;
 		$base =~ s/^.*\///;
@@ -46,10 +47,14 @@ ()
 	}
 }
 else {
-    if ($argCount != 2) {
+    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 exisiting\n";
+	    . "' not possible; not existing\n";
 	exit(1);
     }
     @srcArgs = ($ARGV[0]);
@@ -57,6 +62,24 @@ ()
     $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);
diff --git a/git-send-email.perl b/git-send-email.perl
index b0d095b4e9..7c8d51223f 100755
--- a/git-send-email.perl
+++ b/git-send-email.perl
@@ -54,7 +54,7 @@
 		    "compose" => \$compose,
 		    "quiet" => \$quiet,
 		    "suppress-from" => \$suppress_from,
-		    "no-signed-off-cc" => \$no_signed_off_cc,
+		    "no-signed-off-cc|no-signed-off-by-cc" => \$no_signed_off_cc,
 	 );
 
 # Now, let's fill any that aren't set in with defaults:
diff --git a/git-svnimport.perl b/git-svnimport.perl
index ee2940f480..639aa41861 100755
--- a/git-svnimport.perl
+++ b/git-svnimport.perl
@@ -13,6 +13,7 @@
 use strict;
 use warnings;
 use Getopt::Std;
+use File::Copy;
 use File::Spec;
 use File::Temp qw(tempfile);
 use File::Path qw(mkpath);
@@ -29,19 +30,21 @@
 $SIG{'PIPE'}="IGNORE";
 $ENV{'TZ'}="UTC";
 
-our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T,$opt_b,$opt_r,$opt_s,$opt_l,$opt_d,$opt_D);
+our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T,
+    $opt_b,$opt_r,$opt_I,$opt_A,$opt_s,$opt_l,$opt_d,$opt_D);
 
 sub usage() {
 	print STDERR <<END;
 Usage: ${\basename $0}     # fetch/update GIT from SVN
        [-o branch-for-HEAD] [-h] [-v] [-l max_rev]
        [-C GIT_repository] [-t tagname] [-T trunkname] [-b branchname]
-       [-d|-D] [-i] [-u] [-r] [-s start_chg] [-m] [-M regex] [SVN_URL]
+       [-d|-D] [-i] [-u] [-r] [-I ignorefilename] [-s start_chg]
+       [-m] [-M regex] [-A author_file] [SVN_URL]
 END
 	exit(1);
 }
 
-getopts("b:C:dDhil:mM:o:rs:t:T:uv") or usage();
+getopts("A:b:C:dDhiI:l:mM:o:rs:t:T:uv") or usage();
 usage if $opt_h;
 
 my $tag_name = $opt_t || "tags";
@@ -66,6 +69,25 @@ END
 	push (@mergerx, qr/$opt_M/);
 }
 
+# Absolutize filename now, since we will have chdir'ed by the time we
+# get around to opening it.
+$opt_A = File::Spec->rel2abs($opt_A) if $opt_A;
+
+our %users = ();
+our $users_file = undef;
+sub read_users($) {
+	$users_file = File::Spec->rel2abs(@_);
+	die "Cannot open $users_file\n" unless -f $users_file;
+	open(my $authors,$users_file);
+	while(<$authors>) {
+		chomp;
+		next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/;
+		(my $user,my $name,my $email) = ($1,$2,$3);
+		$users{$user} = [$name,$email];
+	}
+	close($authors);
+}
+
 select(STDERR); $|=1; select(STDOUT);
 
 
@@ -112,16 +134,40 @@ sub file {
 		    DIR => File::Spec->tmpdir(), UNLINK => 1);
 
 	print "... $rev $path ...\n" if $opt_v;
-	my $pool = SVN::Pool->new();
-	eval { $self->{'svn'}->get_file($path,$rev,$fh,$pool); };
-	$pool->clear;
+	my (undef, $properties);
+	eval { (undef, $properties)
+		   = $self->{'svn'}->get_file($path,$rev,$fh); };
 	if($@) {
 		return undef if $@ =~ /Attempted to get checksum/;
 		die $@;
 	}
+	my $mode;
+	if (exists $properties->{'svn:executable'}) {
+		$mode = '0755';
+	} else {
+		$mode = '0644';
+	}
 	close ($fh);
 
-	return $name;
+	return ($name, $mode);
+}
+
+sub ignore {
+	my($self,$path,$rev) = @_;
+
+	print "... $rev $path ...\n" if $opt_v;
+	my (undef,undef,$properties)
+	    = $self->{'svn'}->get_dir($path,$rev,undef);
+	if (exists $properties->{'svn:ignore'}) {
+		my ($fh, $name) = tempfile('gitsvn.XXXXXX',
+					   DIR => File::Spec->tmpdir(),
+					   UNLINK => 1);
+		print $fh $properties->{'svn:ignore'};
+		close($fh);
+		return $name;
+	} else {
+		return undef;
+	}
 }
 
 package main;
@@ -263,6 +309,14 @@ ($$)
 -d $git_dir
 	or die "Could not create git subdir ($git_dir).\n";
 
+my $default_authors = "$git_dir/svn-authors";
+if ($opt_A) {
+	read_users($opt_A);
+	copy($opt_A,$default_authors) or die "Copy failed: $!";
+} else {
+	read_users($default_authors) if -f $default_authors;
+}
+
 open BRANCHES,">>", "$git_dir/svn2git";
 
 sub node_kind($$$) {
@@ -296,7 +350,7 @@ ($$$)
 	my $svnpath = revert_split_path($branch,$path);
 
 	# now get it
-	my $name;
+	my ($name,$mode);
 	if($opt_d) {
 		my($req,$res);
 
@@ -316,8 +370,9 @@ ($$$)
 			return undef if $res->code == 301; # directory?
 			die $res->status_line." at $url\n";
 		}
+		$mode = '0644'; # can't obtain mode via direct http request?
 	} else {
-		$name = $svn->file("$svnpath",$rev);
+		($name,$mode) = $svn->file("$svnpath",$rev);
 		return undef unless defined $name;
 	}
 
@@ -331,10 +386,37 @@ ($$$)
 	chomp $sha;
 	close $F;
 	unlink $name;
-	my $mode = "0644"; # SV does not seem to store any file modes
 	return [$mode, $sha, $path];
 }
 
+sub get_ignore($$$$$) {
+	my($new,$old,$rev,$branch,$path) = @_;
+
+	return unless $opt_I;
+	my $svnpath = revert_split_path($branch,$path);
+	my $name = $svn->ignore("$svnpath",$rev);
+	if ($path eq '/') {
+		$path = $opt_I;
+	} else {
+		$path = File::Spec->catfile($path,$opt_I);
+	}
+	if (defined $name) {
+		my $pid = open(my $F, '-|');
+		die $! unless defined $pid;
+		if (!$pid) {
+			exec("git-hash-object", "-w", $name)
+			    or die "Cannot create object: $!\n";
+		}
+		my $sha = <$F>;
+		chomp $sha;
+		close $F;
+		unlink $name;
+		push(@$new,['0644',$sha,$path]);
+	} else {
+		push(@$old,$path);
+	}
+}
+
 sub split_path($$) {
 	my($rev,$path) = @_;
 	my $branch;
@@ -431,6 +513,10 @@ sub commit {
 
 	if (not defined $author) {
 		$author_name = $author_email = "unknown";
+	} elsif (defined $users_file) {
+		die "User $author is not listed in $users_file\n"
+		    unless exists $users{$author};
+		($author_name,$author_email) = @{$users{$author}};
 	} elsif ($author =~ /^(.*?)\s+<(.*)>$/) {
 		($author_name, $author_email) = ($1, $2);
 	} else {
@@ -540,6 +626,9 @@ sub commit {
 						my $opath = $action->[3];
 						print STDERR "$revision: $branch: could not fetch '$opath'\n";
 					}
+				} elsif ($node_kind eq $SVN::Node::dir) {
+					get_ignore(\@new, \@old, $revision,
+						   $branch,$path);
 				}
 			} elsif ($action->[0] eq "D") {
 				push(@old,$path);
@@ -548,6 +637,9 @@ sub commit {
 				if ($node_kind eq $SVN::Node::file) {
 					my $f = get_file($revision,$branch,$path);
 					push(@new,$f) if $f;
+				} elsif ($node_kind eq $SVN::Node::dir) {
+					get_ignore(\@new, \@old, $revision,
+						   $branch,$path);
 				}
 			} else {
 				die "$revision: unknown action '".$action->[0]."' for $path\n";
diff --git a/git-verify-tag.sh b/git-verify-tag.sh
index 726b1e706b..36f171b302 100755
--- a/git-verify-tag.sh
+++ b/git-verify-tag.sh
@@ -4,9 +4,21 @@ USAGE='<tag>'
 SUBDIRECTORY_OK='Yes'
 . git-sh-setup
 
+verbose=
+while case $# in 0) break;; esac
+do
+	case "$1" in
+	-v|--v|--ve|--ver|--verb|--verbo|--verbos|--verbose)
+		verbose=t ;;
+	*)
+		break ;;
+	esac
+	shift
+done
+
 if [ "$#" != "1" ]
 then
-  usage
+	usage
 fi
 
 type="$(git-cat-file -t "$1" 2>/dev/null)" ||
@@ -15,6 +27,13 @@ type="$(git-cat-file -t "$1" 2>/dev/null)" ||
 test "$type" = tag ||
 	die "$1: cannot verify a non-tag object of type $type."
 
+case "$verbose" in
+t)
+	git-cat-file -p "$1" |
+	sed -n -e '/^-----BEGIN PGP SIGNATURE-----/q' -e p
+	;;
+esac
+
 git-cat-file tag "$1" >"$GIT_DIR/.tmp-vtag" || exit 1
 cat "$GIT_DIR/.tmp-vtag" |
 sed '/-----BEGIN PGP/Q' |
diff --git a/pack-objects.c b/pack-objects.c
index 21ee572f48..136a7f5aad 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -99,7 +99,7 @@ static int reused_delta = 0;
 
 static int pack_revindex_ix(struct packed_git *p)
 {
-	unsigned long ui = (unsigned long)(long)p;
+	unsigned long ui = (unsigned long)p;
 	int i;
 
 	ui = ui ^ (ui >> 16); /* defeat structure alignment */
diff --git a/read-tree.c b/read-tree.c
index f39fe5ca65..be29b3fe11 100644
--- a/read-tree.c
+++ b/read-tree.c
@@ -560,9 +560,11 @@ static int threeway_merge(struct cache_entry **stages)
 		 */
 		if ((head_deleted && remote_deleted) ||
 		    (head_deleted && remote && remote_match) ||
-		    (remote_deleted && head && head_match))
+		    (remote_deleted && head && head_match)) {
+			if (index)
+				return deleted_entry(index, index);
 			return 0;
-
+		}
 		/*
 		 * Added in both, identically.
 		 */
@@ -704,7 +706,7 @@ static int read_cache_unmerged(void)
 	return deleted;
 }
 
-static const char read_tree_usage[] = "git-read-tree (<sha> | -m [-u | -i] <sha1> [<sha2> [<sha3>]])";
+static const char read_tree_usage[] = "git-read-tree (<sha> | -m [--aggressive] [-u | -i] <sha1> [<sha2> [<sha3>]])";
 
 static struct cache_file cache_file;
 
diff --git a/refs.c b/refs.c
index 826ae7ade7..982ebf8ae5 100644
--- a/refs.c
+++ b/refs.c
@@ -151,10 +151,15 @@ static int do_for_each_ref(const char *base, int (*fn)(const char *path, const u
 					break;
 				continue;
 			}
-			if (read_ref(git_path("%s", path), sha1) < 0)
+			if (read_ref(git_path("%s", path), sha1) < 0) {
+				fprintf(stderr, "%s points nowhere!", path);
 				continue;
-			if (!has_sha1_file(sha1))
+			}
+			if (!has_sha1_file(sha1)) {
+				fprintf(stderr, "%s does not point to a valid "
+						"commit object!", path);
 				continue;
+			}
 			retval = fn(path, sha1);
 			if (retval)
 				break;
diff --git a/show-branch.c b/show-branch.c
index 5a86ae2f9e..24efb65e62 100644
--- a/show-branch.c
+++ b/show-branch.c
@@ -5,7 +5,7 @@
 #include "refs.h"
 
 static const char show_branch_usage[] =
-"git-show-branch [--current] [--all] [--heads] [--tags] [--topo-order] [--more=count | --list | --independent | --merge-base ] [<refs>...]";
+"git-show-branch [--current] [--all] [--heads] [--tags] [--topo-order] [--more=count | --list | --independent | --merge-base ] [--topics] [<refs>...]";
 
 static int default_num = 0;
 static int default_alloc = 0;
@@ -547,6 +547,7 @@ int main(int ac, char **av)
 	int shown_merge_point = 0;
 	int with_current_branch = 0;
 	int head_at = -1;
+	int topics = 0;
 
 	setup_git_directory();
 	git_config(git_show_branch_config);
@@ -587,6 +588,8 @@ int main(int ac, char **av)
 			independent = 1;
 		else if (!strcmp(arg, "--topo-order"))
 			lifo = 1;
+		else if (!strcmp(arg, "--topics"))
+			topics = 1;
 		else if (!strcmp(arg, "--date-order"))
 			lifo = 0;
 		else
@@ -724,11 +727,17 @@ int main(int ac, char **av)
 	while (seen) {
 		struct commit *commit = pop_one_commit(&seen);
 		int this_flag = commit->object.flags;
+		int is_merge_point = ((this_flag & all_revs) == all_revs);
 
-		shown_merge_point |= ((this_flag & all_revs) == all_revs);
+		shown_merge_point |= is_merge_point;
 
 		if (1 < num_rev) {
 			int is_merge = !!(commit->parents && commit->parents->next);
+			if (topics &&
+			    !is_merge_point &&
+			    (this_flag & (1u << REV_SHIFT)))
+				continue;
+
 			for (i = 0; i < num_rev; i++) {
 				int mark;
 				if (!(this_flag & (1u << (i + REV_SHIFT))))
diff --git a/t/t3600-rm.sh b/t/t3600-rm.sh
index cabfadd56d..d1947e11c1 100755
--- a/t/t3600-rm.sh
+++ b/t/t3600-rm.sh
@@ -8,11 +8,20 @@ test_description='Test of the various options to git-rm.'
 . ./test-lib.sh
 
 # Setup some files to be removed, some with funny characters
-touch -- foo bar baz 'space embedded' 'tab	embedded' 'newline
-embedded' -q
-git-add -- foo bar baz 'space embedded' 'tab	embedded' 'newline
-embedded' -q
-git-commit -m "add files"
+touch -- foo bar baz 'space embedded' -q
+git-add -- foo bar baz 'space embedded' -q
+git-commit -m "add normal files"
+test_tabs=y
+if touch -- 'tab	embedded' 'newline
+embedded'
+then
+git-add -- 'tab	embedded' 'newline
+embedded'
+git-commit -m "add files with tabs and newlines"
+else
+    say 'Your filesystem does not allow tabs in filenames.'
+    test_tabs=n
+fi
 
 test_expect_success \
     'Pre-check that foo exists and is in index before git-rm foo' \
@@ -42,16 +51,18 @@ test_expect_success \
     'Test that "git-rm -- -q" succeeds (remove a file that looks like an option)' \
     'git-rm -- -q'
 
-test_expect_success \
+test "$test_tabs" = y && test_expect_success \
     "Test that \"git-rm -f\" succeeds with embedded space, tab, or newline characters." \
     "git-rm -f 'space embedded' 'tab	embedded' 'newline
 embedded'"
 
+if test "$test_tabs" = y; then
 chmod u-w .
 test_expect_failure \
     'Test that "git-rm -f" fails if its rm fails' \
     'git-rm -f baz'
 chmod u+w .
+fi
 
 test_expect_success \
     'When the rm in "git-rm -f" fails, it should not remove the file from the index' \
diff --git a/t/t7001-mv.sh b/t/t7001-mv.sh
index 43d74c502e..811a4797a5 100755
--- a/t/t7001-mv.sh
+++ b/t/t7001-mv.sh
@@ -11,17 +11,31 @@ test_expect_success \
      git-commit -m add -a'
 
 test_expect_success \
-    'moving the file' \
+    'moving the file out of subdirectory' \
     'cd path0 && git-mv COPYING ../path1/COPYING'
 
 # in path0 currently
 test_expect_success \
     'commiting the change' \
-    'cd .. && git-commit -m move -a'
+    'cd .. && git-commit -m move-out -a'
 
 test_expect_success \
     'checking the commit' \
     'git-diff-tree -r -M --name-status  HEAD^ HEAD | \
     grep -E "^R100.+path0/COPYING.+path1/COPYING"'
 
+test_expect_success \
+    'moving the file back into subdirectory' \
+    'cd path0 && git-mv ../path1/COPYING COPYING'
+
+# in path0 currently
+test_expect_success \
+    'commiting the change' \
+    'cd .. && git-commit -m move-in -a'
+
+test_expect_success \
+    'checking the commit' \
+    'git-diff-tree -r -M --name-status  HEAD^ HEAD | \
+    grep -E "^R100.+path1/COPYING.+path0/COPYING"'
+
 test_done
diff --git a/t/t8001-annotate.sh b/t/t8001-annotate.sh
new file mode 100755
index 0000000000..172908a5b0
--- /dev/null
+++ b/t/t8001-annotate.sh
@@ -0,0 +1,90 @@
+#!/bin/sh
+
+test_description='git-annotate'
+. ./test-lib.sh
+
+test_expect_success \
+    'prepare reference tree' \
+    'echo "1A quick brown fox jumps over the" >file &&
+     echo "lazy dog" >>file &&
+     git add file
+     GIT_AUTHOR_NAME="A" git commit -a -m "Initial."'
+
+test_expect_success \
+    'check all lines blamed on A' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "A") == 2 ]'
+
+test_expect_success \
+    'Setup new lines blamed on B' \
+    'echo "2A quick brown fox jumps over the" >>file &&
+     echo "lazy dog" >> file &&
+     GIT_AUTHOR_NAME="B" git commit -a -m "Second."'
+
+test_expect_success \
+    'Two lines blamed on A' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "A") == 2 ]'
+
+test_expect_success \
+    'Two lines blamed on B' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "B") == 2 ]'
+
+test_expect_success \
+    'merge-setup part 1' \
+    'git checkout -b branch1 master &&
+     echo "3A slow green fox jumps into the" >> file &&
+     echo "well." >> file &&
+     GIT_AUTHOR_NAME="B1" git commit -a -m "Branch1-1"'
+
+test_expect_success \
+    'Two lines blamed on A' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "^A$") == 2 ]'
+
+test_expect_success \
+    'Two lines blamed on B' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "^B$") == 2 ]'
+
+test_expect_success \
+    'Two lines blamed on B1' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "^B1$") == 2 ]'
+
+test_expect_success \
+    'merge-setup part 2' \
+    'git checkout -b branch2 master &&
+     sed -e "s/2A quick brown/4A quick brown lazy dog/" < file > file.new &&
+     mv file.new file &&
+     GIT_AUTHOR_NAME="B2" git commit -a -m "Branch2-1"'
+
+test_expect_success \
+    'Two lines blamed on A' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "^A$") == 2 ]'
+
+test_expect_success \
+    'One line blamed on B' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "^B$") == 1 ]'
+
+test_expect_success \
+    'One line blamed on B2' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "^B2$") == 1 ]'
+
+
+test_expect_success \
+    'merge-setup part 3' \
+    'git pull . branch1'
+
+test_expect_success \
+    'Two lines blamed on A' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "^A$") == 2 ]'
+
+test_expect_success \
+    'One line blamed on B' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "^B$") == 1 ]'
+
+test_expect_success \
+    'Two lines blamed on B1' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "^B1$") == 2 ]'
+
+test_expect_success \
+    'One line blamed on B2' \
+    '[ $(git annotate file | awk "{print \$3}" | grep -c "^B2$") == 1 ]'
+
+test_done
diff --git a/tar-tree.c b/tar-tree.c
index e85a1ed660..e478e13e28 100644
--- a/tar-tree.c
+++ b/tar-tree.c
@@ -304,9 +304,11 @@ static void write_header(const unsigned char *sha1, char typeflag, const char *b
 	}
 
 	if (S_ISDIR(mode))
-		mode |= 0755;	/* GIT doesn't store permissions of dirs */
-	if (S_ISLNK(mode))
-		mode |= 0777;   /* ... nor of symlinks */
+		mode |= 0777;
+	else if (S_ISREG(mode))
+		mode |= (mode & 0100) ? 0777 : 0666;
+	else if (S_ISLNK(mode))
+		mode |= 0777;
 	sprintf(&header[100], "%07o", mode & 07777);
 
 	/* XXX: should we provide more meaningful info here? */
@@ -391,7 +393,7 @@ int main(int argc, char **argv)
 		usage(tar_tree_usage);
 	}
 
-	commit = lookup_commit_reference(sha1);
+	commit = lookup_commit_reference_gently(sha1, 1);
 	if (commit) {
 		write_global_extended_header(commit->object.sha1);
 		archive_time = commit->date;
diff --git a/update-index.c b/update-index.c
index ce1db38d16..797245ab27 100644
--- a/update-index.c
+++ b/update-index.c
@@ -577,9 +577,11 @@ int main(int argc, const char **argv)
 				break;
 			}
 			if (!strcmp(path, "--index-info")) {
+				if (i != argc - 1)
+					die("--index-info must be at the end");
 				allow_add = allow_replace = allow_remove = 1;
 				read_index_info(line_termination);
-				continue;
+				break;
 			}
 			if (!strcmp(path, "--ignore-missing")) {
 				not_new = 1;