Merge branch 'master' into js/fmt-patch

* master: (119 commits)
  diff family: add --check option
  Document that "git add" only adds non-ignored files.
  Add a conversion tool to migrate remote information into the config
  fetch, pull: ask config for remote information
  Fix build procedure for builtin-init-db
  read-tree -m -u: do not overwrite or remove untracked working tree files.
  apply --cached: do not check newly added file in the working tree
  Implement a --dry-run option to git-quiltimport
  Implement git-quiltimport
  Revert "builtin-grep: workaround for non GNU grep."
  builtin-grep: workaround for non GNU grep.
  builtin-grep: workaround for non GNU grep.
  git-am: use apply --cached
  apply --cached: apply a patch without using working tree.
  apply --numstat: show new name, not old name.
  Documentation/Makefile: create tarballs for the man pages and html files
  Allow pickaxe and diff-filter options to be used by git log.
  Libify the index refresh logic
  Builtin git-init-db
  Remove unnecessary local in get_ref_sha1.
  ...

Documentation/SubmittingPatches

@@ -266,8 +266,8 @@ This recipe appears to work with the current [*1*] Thunderbird from Suse.
 The following Thunderbird extensions are needed:
 	AboutConfig 0.5
 		http://aboutconfig.mozdev.org/
-	External Editor 0.5.4
-		http://extensionroom.mozdev.org/more-info/exteditor
+	External Editor 0.7.2
+		http://globs.org/articles.php?lng=en&pg=8
 
 1) Prepare the patch as a text file using your method of choice.
 

Documentation/core-tutorial.txt

@@ -971,7 +971,7 @@ $ git show-branch --topo-order master mybranch
 The first two lines indicate that it is showing the two branches
 and the first line of the commit log message from their
 top-of-the-tree commits, you are currently on `master` branch
-(notice the asterisk `*` character), and the first column for
+(notice the asterisk `\*` character), and the first column for
 the later output lines is used to show commits contained in the
 `master` branch, and the second column for the `mybranch`
 branch. Three commits are shown along with their log messages.

Documentation/diff-options.txt

@@ -10,6 +10,10 @@
 --stat::
 	Generate a diffstat instead of a patch.
 
+--summary::
+	Output a condensed summary of extended header information
+	such as creations, renames and mode changes.
+
 --patch-with-stat::
 	Generate patch and prepend its diffstat.
 

Documentation/git-add.txt

@@ -14,11 +14,13 @@ DESCRIPTION
 A simple wrapper for git-update-index to add files to the index,
 for people used to do "cvs add".
 
+It only adds non-ignored files, to add ignored files use
+"git update-index --add".
 
 OPTIONS
 -------
 <file>...::
-	Files to add to the index.
+	Files to add to the index (see gitlink:git-ls-files[1]).
 
 -n::
         Don't actually add the file(s), just show if they exist.
@@ -68,6 +70,7 @@ git-add git-*.sh::
 See Also
 --------
 gitlink:git-rm[1]
+gitlink:git-ls-files[1]
 
 Author
 ------

Documentation/git-clean.txt

@@ -8,7 +8,7 @@ git-clean - Remove untracked files from the working tree
 SYNOPSIS
 --------
 [verse]
-'git-clean' [-d] [-n] [-q] [-x | -X]
+'git-clean' [-d] [-n] [-q] [-x | -X] [--] <paths>...
 
 DESCRIPTION
 -----------
@@ -16,6 +16,9 @@ Removes files unknown to git.  This allows to clean the working tree
 from files that are not under version control.  If the '-x' option is
 specified, ignored files are also removed, allowing to remove all
 build products.
+When optional `<paths>...` arguments are given, the paths
+affected are further limited to those that match them.
+
 
 OPTIONS
 -------

Documentation/git-cvsexportcommit.txt

@@ -8,7 +8,7 @@ git-cvsexportcommit - Export a commit to a CVS checkout
 
 SYNOPSIS
 --------
-'git-cvsexportcommmit' [-h] [-v] [-c] [-p] [PARENTCOMMIT] COMMITID
+'git-cvsexportcommmit' [-h] [-v] [-c] [-p] [-f] [-m msgprefix] [PARENTCOMMIT] COMMITID
 
 
 DESCRIPTION
@@ -39,6 +39,13 @@ OPTIONS
 	Be pedantic (paranoid) when applying patches. Invokes patch with 
 	--fuzz=0
 
+-f::
+	Force the merge even if the files are not up to date.
+
+-m::
+	Prepend the commit message with the provided prefix. 
+	Useful for patch series and the like.
+
 -v::
 	Verbose.
 

Documentation/git-grep.txt

@@ -8,43 +8,82 @@ git-grep - Print lines matching a pattern
 
 SYNOPSIS
 --------
-'git-grep' [<option>...] [-e] <pattern> [--] [<path>...]
+[verse]
+'git-grep' [--cached]
+	   [-a | --text] [-I] [-i | --ignore-case] [-w | --word-regexp]
+	   [-v | --invert-match]
+	   [-E | --extended-regexp] [-G | --basic-regexp] [-F | --fixed-strings]
+	   [-n] [-l | --files-with-matches] [-L | --files-without-match]
+	   [-c | --count]
+	   [-A <post-context>] [-B <pre-context>] [-C <context>]
+	   [-f <file>] [-e <pattern>]
+	   [<tree>...]
+	   [--] [<path>...]
 
 DESCRIPTION
 -----------
-Searches list of files `git-ls-files` produces for lines
-containing a match to the given pattern.
+Look for specified patterns in the working tree files, blobs
+registered in the index file, or given tree objects.
 
 
 OPTIONS
 -------
+--cached::
+	Instead of searching in the working tree files, check
+	the blobs registerd in the index file.
+
+-a | --text::
+	Process binary files as if they were text.
+
+-i | --ignore-case::
+	Ignore case differences between the patterns and the
+	files.
+
+-w | --word-regexp::
+	Match the pattern only at word boundary (either begin at the
+	beginning of a line, or preceded by a non-word character; end at
+	the end of a line or followed by a non-word character).
+
+-v | --invert-match::
+	Select non-matching lines.
+
+-E | --extended-regexp | -G | --basic-regexp::
+	Use POSIX extended/basic regexp for patterns.  Default
+	is to use basic regexp.
+
+-n::
+	Prefix the line number to matching lines.
+
+-l | --files-with-matches | -L | --files-without-match::
+	Instead of showing every matched line, show only the
+	names of files that contain (or do not contain) matches.
+
+-c | --count::
+	Instead of showing every matched line, show the number of
+	lines that match.
+
+-[ABC] <context>::
+	Show `context` trailing (`A` -- after), or leading (`B`
+	-- before), or both (`C` -- context) lines, and place a
+	line containing `--` between continguous groups of
+	matches.
+
+-f <file>::
+	Read patterns from <file>, one per line.
+
+`<tree>...`::
+	Search blobs in the trees for specified patterns.
+
 `--`::
 	Signals the end of options; the rest of the parameters
 	are <path> limiters.
 
-<option>...::
-	Either an option to pass to `grep` or `git-ls-files`.
-+
-The following are the specific `git-ls-files` options
-that may be given: `-o`, `--cached`, `--deleted`, `--others`,
-`--killed`, `--ignored`, `--modified`, `--exclude=\*`,
-`--exclude-from=\*`, and `--exclude-per-directory=\*`.
-+
-All other options will be passed to `grep`.
-
-<pattern>::
-	The pattern to look for.  The first non option is taken
-	as the pattern; if your pattern begins with a dash, use
-	`-e <pattern>`.
-
-<path>...::
-	Optional paths to limit the set of files to be searched;
-	passed to `git-ls-files`.
-
 
 Author
 ------
-Written by Linus Torvalds <torvalds@osdl.org>
+Originally written by Linus Torvalds <torvalds@osdl.org>, later
+revamped by Junio C Hamano.
+
 
 Documentation
 --------------

Documentation/git-merge-base.txt

@@ -8,16 +8,26 @@ git-merge-base - Finds as good a common ancestor as possible for a merge
 
 SYNOPSIS
 --------
-'git-merge-base' <commit> <commit>
+'git-merge-base' [--all] <commit> <commit>
 
 DESCRIPTION
 -----------
-"git-merge-base" finds as good a common ancestor as possible. Given a
-selection of equally good common ancestors it should not be relied on
-to decide in any particular way.
+
+"git-merge-base" finds as good a common ancestor as possible between
+the two commits. That is, given two commits A and B 'git-merge-base A
+B' will output a commit which is reachable from both A and B through
+the parent relationship.
+
+Given a selection of equally good common ancestors it should not be
+relied on to decide in any particular way.
 
 The "git-merge-base" algorithm is still in flux - use the source...
 
+OPTIONS
+-------
+--all::
+	Output all common ancestors for the two commits instead of
+	just one.
 
 Author
 ------

Documentation/git-quiltimport.txt

@@ -0,0 +1,61 @@
+git-quiltimport(1)
+================
+
+NAME
+----
+git-quiltimport - Applies a quilt patchset onto the current branch
+
+
+SYNOPSIS
+--------
+[verse]
+'git-quiltimport' [--dry-run] [--author <author>] [--patches <dir>]
+
+
+DESCRIPTION
+-----------
+Applies a quilt patchset onto the current git branch, preserving
+the patch boundaries, patch order, and patch descriptions present
+in the quilt patchset.
+
+For each patch the code attempts to extract the author from the
+patch description.  If that fails it falls back to the author
+specified with --author.  If the --author flag was not given
+the patch description is displayed and the user is asked to
+interactively enter the author of the patch.
+
+If a subject is not found in the patch description the patch name is
+preserved as the 1 line subject in the git description.
+
+OPTIONS
+-------
+--dry-run::
+	Walk through the patches in the series and warn
+	if we cannot find all of the necessary information to commit
+	a patch.  At the time of this writing only missing author
+	information is warned about.
+
+--author Author Name <Author Email>::
+	The author name and email address to use when no author
+	information can be found in the patch description.
+
+--patches <dir>::
+	The directory to find the quilt patches and the
+	quilt series file.
+
+        The default for the patch directory is patches
+	or the value of the $QUILT_PATCHES environment
+	variable.
+
+Author
+------
+Written by Eric Biederman <ebiederm@lnxi.com>
+
+Documentation
+--------------
+Documentation by Eric Biederman <ebiederm@lnxi.com>
+
+GIT
+---
+Part of the gitlink:git[7] suite
+

Documentation/git-rebase.txt

@@ -9,9 +9,7 @@ SYNOPSIS
 --------
 'git-rebase' [--onto <newbase>] <upstream> [<branch>]
 
-'git-rebase' --continue
-
-'git-rebase' --abort
+'git-rebase' --continue | --skip | --abort
 
 DESCRIPTION
 -----------
@@ -23,9 +21,10 @@ not exist in the <upstream> branch.
 
 It is possible that a merge failure will prevent this process from being
 completely automatic.  You will have to resolve any such merge failure
-and run `git rebase --continue`.  If you can not resolve the merge
-failure, running `git rebase --abort` will restore the original <branch>
-and remove the working files found in the .dotest directory.
+and run `git rebase --continue`.  Another option is to bypass the commit
+that caused the merge failure with `git rebase --skip`.  To restore the
+original <branch> and remove the .dotest working files, use the command
+`git rebase --abort` instead.
 
 Note that if <branch> is not specified on the command line, the currently
 checked out branch is used.

Documentation/git-repo-config.txt

@@ -23,10 +23,11 @@ You can query/set/replace/unset options with this command. The name is
 actually the section and the key separated by a dot, and the value will be
 escaped.
 
-If you want to set/unset an option which can occur on multiple lines, you
-should provide a POSIX regex for the value. If you want to handle the lines
-*not* matching the regex, just prepend a single exclamation mark in front
-(see EXAMPLES).
+If you want to set/unset an option which can occur on multiple
+lines, a POSIX regexp `value_regex` needs to be given.  Only the
+existing values that match the regexp are updated or unset.  If
+you want to handle the lines that do *not* match the regex, just
+prepend a single exclamation mark in front (see EXAMPLES).
 
 The type specifier can be either '--int' or '--bool', which will make
 'git-repo-config' ensure that the variable(s) are of the given type and

Documentation/git-rev-list.txt

@@ -68,9 +68,10 @@ OPTIONS
 --bisect::
 	Limit output to the one commit object which is roughly halfway
 	between the included and excluded commits. Thus, if 'git-rev-list
-	--bisect foo ^bar ^baz' outputs 'midpoint', the output
-	of 'git-rev-list foo ^midpoint' and 'git-rev-list midpoint
-	^bar ^baz' would be of roughly the same length. Finding the change
+	--bisect foo {caret}bar {caret}baz' outputs 'midpoint', the output
+	of 'git-rev-list foo {caret}midpoint' and 'git-rev-list midpoint
+	{caret}bar {caret}baz' would be of roughly the same length.
+	Finding the change
 	which introduces a regression is thus reduced to a binary search:
 	repeatedly generate and test new 'midpoint's until the commit chain
 	is of length one.

Documentation/git-rev-parse.txt

@@ -67,6 +67,15 @@ OPTIONS
 --all::
 	Show all refs found in `$GIT_DIR/refs`.
 
+--branches::
+	Show branch refs found in `$GIT_DIR/refs/heads`.
+
+--tags::
+	Show tag refs found in `$GIT_DIR/refs/tags`.
+
+--remotes::
+	Show tag refs found in `$GIT_DIR/refs/remotes`.
+
 --show-prefix::
 	When the command is invoked from a subdirectory, show the
 	path of the current directory relative to the top-level

Documentation/git-update-index.txt

@@ -15,7 +15,7 @@ SYNOPSIS
 	     [--cacheinfo <mode> <object> <file>]\*
 	     [--chmod=(+|-)x]
 	     [--assume-unchanged | --no-assume-unchanged]
-	     [--really-refresh] [--unresolve]
+	     [--really-refresh] [--unresolve] [--again]
 	     [--info-only] [--index-info]
 	     [-z] [--stdin]
 	     [--verbose]
@@ -80,6 +80,10 @@ OPTIONS
 	filesystem that has very slow lstat(2) system call
 	(e.g. cifs).
 
+--again::
+	Runs `git-update-index` itself on the paths whose index
+	entries are different from those from the `HEAD` commit.
+
 --unresolve::
 	Restores the 'unmerged' or 'needs updating' state of a
 	file during a merge if it was cleared by accident.

Documentation/install-webdoc.sh

@@ -4,12 +4,16 @@ T="$1"
 
 for h in *.html *.txt howto/*.txt howto/*.html
 do
-	diff -u -I'Last updated [0-9][0-9]-[A-Z][a-z][a-z]-' "$T/$h" "$h" || {
+	if test -f "$T/$h" &&
+	   diff -u -I'Last updated [0-9][0-9]-[A-Z][a-z][a-z]-' "$T/$h" "$h"
+	then
+		:; # up to date
+	else
 		echo >&2 "# install $h $T/$h"
 		rm -f "$T/$h"
 		mkdir -p `dirname "$T/$h"`
 		cp "$h" "$T/$h"
-	}
+	fi
 done
 strip_leading=`echo "$T/" | sed -e 's|.|.|g'`
 for th in "$T"/*.html "$T"/*.txt "$T"/howto/*.txt "$T"/howto/*.html

Makefile

@@ -124,14 +124,15 @@ SCRIPT_SH = \
 	git-tag.sh git-verify-tag.sh \
 	git-applymbox.sh git-applypatch.sh git-am.sh \
 	git-merge.sh git-merge-stupid.sh git-merge-octopus.sh \
-	git-merge-resolve.sh git-merge-ours.sh git-grep.sh \
-	git-lost-found.sh
+	git-merge-resolve.sh git-merge-ours.sh \
+	git-lost-found.sh git-quiltimport.sh
 
 SCRIPT_PERL = \
 	git-archimport.perl git-cvsimport.perl git-relink.perl \
 	git-shortlog.perl git-fmt-merge-msg.perl git-rerere.perl \
 	git-annotate.perl git-cvsserver.perl \
-	git-svnimport.perl git-mv.perl git-cvsexportcommit.perl
+	git-svnimport.perl git-mv.perl git-cvsexportcommit.perl \
+	git-send-email.perl
 
 SCRIPT_PYTHON = \
 	git-merge-recursive.py
@@ -153,22 +154,24 @@ PROGRAMS = \
 	git-convert-objects$X git-diff-files$X \
 	git-diff-index$X git-diff-stages$X \
 	git-diff-tree$X git-fetch-pack$X git-fsck-objects$X \
-	git-hash-object$X git-index-pack$X git-init-db$X git-local-fetch$X \
+	git-hash-object$X git-index-pack$X git-local-fetch$X \
 	git-ls-files$X git-ls-tree$X git-mailinfo$X git-merge-base$X \
 	git-merge-index$X git-mktag$X git-mktree$X git-pack-objects$X git-patch-id$X \
 	git-peek-remote$X git-prune-packed$X git-read-tree$X \
-	git-receive-pack$X git-rev-list$X git-rev-parse$X \
+	git-receive-pack$X git-rev-parse$X \
 	git-send-pack$X git-show-branch$X git-shell$X \
 	git-show-index$X git-ssh-fetch$X \
 	git-ssh-upload$X git-tar-tree$X git-unpack-file$X \
 	git-unpack-objects$X git-update-index$X git-update-server-info$X \
 	git-upload-pack$X git-verify-pack$X git-write-tree$X \
-	git-update-ref$X git-symbolic-ref$X git-check-ref-format$X \
+	git-update-ref$X git-symbolic-ref$X \
 	git-name-rev$X git-pack-redundant$X git-repo-config$X git-var$X \
 	git-describe$X git-merge-tree$X git-blame$X git-imap-send$X
 
 BUILT_INS = git-log$X git-whatchanged$X git-show$X \
-	git-count-objects$X git-diff$X git-push$X
+	git-count-objects$X git-diff$X git-push$X \
+	git-grep$X git-rev-list$X git-check-ref-format$X \
+	git-init-db$X
 
 # what 'all' will build and 'install' will install, in gitexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS)
@@ -205,7 +208,7 @@ DIFF_OBJS = \
 	diffcore-delta.o log-tree.o
 
 LIB_OBJS = \
-	blob.o commit.o connect.o csum-file.o \
+	blob.o commit.o connect.o csum-file.o base85.o \
 	date.o diff-delta.o entry.o exec_cmd.o ident.o index.o \
 	object.o pack-check.o patch-delta.o path.o pkt-line.o \
 	quote.o read-cache.o refs.o run-command.o \
@@ -215,7 +218,9 @@ LIB_OBJS = \
 	$(DIFF_OBJS)
 
 BUILTIN_OBJS = \
-	builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o
+	builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \
+	builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \
+	builtin-init-db.o
 
 GITLIBS = $(LIB_FILE) $(XDIFF_LIB)
 LIBS = $(GITLIBS) -lz
@@ -285,7 +290,9 @@ ifeq ($(uname_S),OpenBSD)
 	ALL_LDFLAGS += -L/usr/local/lib
 endif
 ifeq ($(uname_S),NetBSD)
-	NEEDS_LIBICONV = YesPlease
+	ifeq ($(shell expr "$(uname_R)" : '[01]\.'),2)
+		NEEDS_LIBICONV = YesPlease
+	endif
 	ALL_CFLAGS += -I/usr/pkg/include
 	ALL_LDFLAGS += -L/usr/pkg/lib -Wl,-rpath,/usr/pkg/lib
 endif
@@ -319,10 +326,6 @@ else
 	endif
 endif
 
-ifdef WITH_SEND_EMAIL
-	SCRIPT_PERL += git-send-email.perl
-endif
-
 ifndef NO_CURL
 	ifdef CURLDIR
 		# This is still problematic -- gcc does not always want -R.
@@ -458,6 +461,7 @@ PYTHON_PATH_SQ = $(subst ','\'',$(PYTHON_PATH))
 GIT_PYTHON_DIR_SQ = $(subst ','\'',$(GIT_PYTHON_DIR))
 
 ALL_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' $(COMPAT_CFLAGS)
+ALL_CFLAGS += -DDEFAULT_GIT_TEMPLATE_DIR='"$(template_dir_SQ)"'
 LIB_OBJS += $(COMPAT_OBJS)
 export prefix TAR INSTALL DESTDIR SHELL_PATH template_dir
 ### Build rules
@@ -564,10 +568,6 @@ git-http-push$X: revision.o http.o http-push.o $(LIB_FILE)
 	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \
 		$(LIBS) $(CURL_LIBCURL) $(EXPAT_LIBEXPAT)
 
-init-db.o: init-db.c
-	$(CC) -c $(ALL_CFLAGS) \
-		-DDEFAULT_GIT_TEMPLATE_DIR='"$(template_dir_SQ)"' $*.c
-
 $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
 $(patsubst git-%$X,%.o,$(PROGRAMS)): $(GITLIBS)
 $(DIFF_OBJS): diffcore.h
@@ -607,7 +607,7 @@ test-date$X: test-date.c date.o ctype.o
 	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) test-date.c date.o ctype.o
 
 test-delta$X: test-delta.c diff-delta.o patch-delta.o
-	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^ -lz
+	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^
 
 check:
 	for i in *.c; do sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; done
@@ -651,6 +651,25 @@ dist: git.spec git-tar-tree
 rpm: dist
 	$(RPMBUILD) -ta $(GIT_TARNAME).tar.gz
 
+htmldocs = git-htmldocs-$(GIT_VERSION)
+manpages = git-manpages-$(GIT_VERSION)
+dist-doc:
+	rm -fr .doc-tmp-dir
+	mkdir .doc-tmp-dir
+	$(MAKE) -C Documentation WEBDOC_DEST=../.doc-tmp-dir install-webdoc
+	cd .doc-tmp-dir && $(TAR) cf ../$(htmldocs).tar .
+	gzip -n -9 -f $(htmldocs).tar
+	:
+	rm -fr .doc-tmp-dir
+	mkdir .doc-tmp-dir .doc-tmp-dir/man1 .doc-tmp-dir/man7
+	$(MAKE) -C Documentation DESTDIR=. \
+		man1=../.doc-tmp-dir/man1 \
+		man7=../.doc-tmp-dir/man7 \
+		install
+	cd .doc-tmp-dir && $(TAR) cf ../$(manpages).tar .
+	gzip -n -9 -f $(manpages).tar
+	rm -fr .doc-tmp-dir
+
 ### Cleaning rules
 
 clean:
@@ -658,8 +677,9 @@ clean:
 		$(LIB_FILE) $(XDIFF_LIB)
 	rm -f $(ALL_PROGRAMS) $(BUILT_INS) git$X
 	rm -f *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags
-	rm -rf $(GIT_TARNAME)
+	rm -rf $(GIT_TARNAME) .doc-tmp-dir
 	rm -f $(GIT_TARNAME).tar.gz git-core_$(GIT_VERSION)-*.tar.gz
+	rm -f $(htmldocs).tar $(manpages).tar
 	$(MAKE) -C Documentation/ clean
 	$(MAKE) -C templates clean
 	$(MAKE) -C t/ clean

apply.c

@@ -10,20 +10,25 @@
 #include "cache.h"
 #include "quote.h"
 #include "blob.h"
+#include "delta.h"
 
 //  --check turns on checking that the working tree matches the
 //    files that are being modified, but doesn't apply the patch
 //  --stat does just a diffstat, and doesn't actually apply
 //  --numstat does numeric diffstat, and doesn't actually apply
 //  --index-info shows the old and new index info for paths if available.
+//  --index updates the cache as well.
+//  --cached updates only the cache without ever touching the working tree.
 //
 static const char *prefix;
 static int prefix_length = -1;
+static int newfd = -1;
 
 static int p_value = 1;
 static int allow_binary_replacement = 0;
 static int check_index = 0;
 static int write_index = 0;
+static int cached = 0;
 static int diffstat = 0;
 static int numstat = 0;
 static int summary = 0;
@@ -34,7 +39,7 @@ static int show_index_info = 0;
 static int line_termination = '\n';
 static unsigned long p_context = -1;
 static const char apply_usage[] =
-"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] [-CNUM] [--whitespace=<nowarn|warn|error|error-all|strip>] <patch>...";
+"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--cached] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] [-CNUM] [--whitespace=<nowarn|warn|error|error-all|strip>] <patch>...";
 
 static enum whitespace_eol {
 	nowarn_whitespace,
@@ -113,6 +118,9 @@ struct patch {
 	char *new_name, *old_name, *def_name;
 	unsigned int old_mode, new_mode;
 	int is_rename, is_copy, is_new, is_delete, is_binary;
+#define BINARY_DELTA_DEFLATED 1
+#define BINARY_LITERAL_DEFLATED 2
+	unsigned long deflate_origlen;
 	int lines_added, lines_deleted;
 	int score;
 	struct fragment *fragments;
@@ -966,6 +974,88 @@ static inline int metadata_changes(struct patch *patch)
 		 patch->old_mode != patch->new_mode);
 }
 
+static int parse_binary(char *buffer, unsigned long size, struct patch *patch)
+{
+	/* We have read "GIT binary patch\n"; what follows is a line
+	 * that says the patch method (currently, either "deflated
+	 * literal" or "deflated delta") and the length of data before
+	 * deflating; a sequence of 'length-byte' followed by base-85
+	 * encoded data follows.
+	 *
+	 * Each 5-byte sequence of base-85 encodes up to 4 bytes,
+	 * and we would limit the patch line to 66 characters,
+	 * so one line can fit up to 13 groups that would decode
+	 * to 52 bytes max.  The length byte 'A'-'Z' corresponds
+	 * to 1-26 bytes, and 'a'-'z' corresponds to 27-52 bytes.
+	 * The end of binary is signalled with an empty line.
+	 */
+	int llen, used;
+	struct fragment *fragment;
+	char *data = NULL;
+
+	patch->fragments = fragment = xcalloc(1, sizeof(*fragment));
+
+	/* Grab the type of patch */
+	llen = linelen(buffer, size);
+	used = llen;
+	linenr++;
+
+	if (!strncmp(buffer, "delta ", 6)) {
+		patch->is_binary = BINARY_DELTA_DEFLATED;
+		patch->deflate_origlen = strtoul(buffer + 6, NULL, 10);
+	}
+	else if (!strncmp(buffer, "literal ", 8)) {
+		patch->is_binary = BINARY_LITERAL_DEFLATED;
+		patch->deflate_origlen = strtoul(buffer + 8, NULL, 10);
+	}
+	else
+		return error("unrecognized binary patch at line %d: %.*s",
+			     linenr-1, llen-1, buffer);
+	buffer += llen;
+	while (1) {
+		int byte_length, max_byte_length, newsize;
+		llen = linelen(buffer, size);
+		used += llen;
+		linenr++;
+		if (llen == 1)
+			break;
+		/* Minimum line is "A00000\n" which is 7-byte long,
+		 * and the line length must be multiple of 5 plus 2.
+		 */
+		if ((llen < 7) || (llen-2) % 5)
+			goto corrupt;
+		max_byte_length = (llen - 2) / 5 * 4;
+		byte_length = *buffer;
+		if ('A' <= byte_length && byte_length <= 'Z')
+			byte_length = byte_length - 'A' + 1;
+		else if ('a' <= byte_length && byte_length <= 'z')
+			byte_length = byte_length - 'a' + 27;
+		else
+			goto corrupt;
+		/* if the input length was not multiple of 4, we would
+		 * have filler at the end but the filler should never
+		 * exceed 3 bytes
+		 */
+		if (max_byte_length < byte_length ||
+		    byte_length <= max_byte_length - 4)
+			goto corrupt;
+		newsize = fragment->size + byte_length;
+		data = xrealloc(data, newsize);
+		if (decode_85(data + fragment->size,
+			      buffer + 1,
+			      byte_length))
+			goto corrupt;
+		fragment->size = newsize;
+		buffer += llen;
+		size -= llen;
+	}
+	fragment->patch = data;
+	return used;
+ corrupt:
+	return error("corrupt binary patch at line %d: %.*s",
+		     linenr-1, llen-1, buffer);
+}
+
 static int parse_chunk(char *buffer, unsigned long size, struct patch *patch)
 {
 	int hdrsize, patchsize;
@@ -982,19 +1072,34 @@ static int parse_chunk(char *buffer, unsigned long size, struct patch *patch)
 			"Files ",
 			NULL,
 		};
+		static const char git_binary[] = "GIT binary patch\n";
 		int i;
 		int hd = hdrsize + offset;
 		unsigned long llen = linelen(buffer + hd, size - hd);
 
-		if (!memcmp(" differ\n", buffer + hd + llen - 8, 8))
+		if (llen == sizeof(git_binary) - 1 &&
+		    !memcmp(git_binary, buffer + hd, llen)) {
+			int used;
+			linenr++;
+			used = parse_binary(buffer + hd + llen,
+					    size - hd - llen, patch);
+			if (used)
+				patchsize = used + llen;
+			else
+				patchsize = 0;
+		}
+		else if (!memcmp(" differ\n", buffer + hd + llen - 8, 8)) {
 			for (i = 0; binhdr[i]; i++) {
 				int len = strlen(binhdr[i]);
 				if (len < size - hd &&
 				    !memcmp(binhdr[i], buffer + hd, len)) {
+					linenr++;
 					patch->is_binary = 1;
+					patchsize = llen;
 					break;
 				}
 			}
+		}
 
 		/* Empty patch cannot be applied if:
 		 * - it is a binary patch and we do not do binary_replace, or
@@ -1345,75 +1450,149 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag)
 	return offset;
 }
 
+static char *inflate_it(const void *data, unsigned long size,
+			unsigned long inflated_size)
+{
+	z_stream stream;
+	void *out;
+	int st;
+
+	memset(&stream, 0, sizeof(stream));
+
+	stream.next_in = (unsigned char *)data;
+	stream.avail_in = size;
+	stream.next_out = out = xmalloc(inflated_size);
+	stream.avail_out = inflated_size;
+	inflateInit(&stream);
+	st = inflate(&stream, Z_FINISH);
+	if ((st != Z_STREAM_END) || stream.total_out != inflated_size) {
+		free(out);
+		return NULL;
+	}
+	return out;
+}
+
+static int apply_binary_fragment(struct buffer_desc *desc, struct patch *patch)
+{
+	unsigned long dst_size;
+	struct fragment *fragment = patch->fragments;
+	void *data;
+	void *result;
+
+	data = inflate_it(fragment->patch, fragment->size,
+			  patch->deflate_origlen);
+	if (!data)
+		return error("corrupt patch data");
+	switch (patch->is_binary) {
+	case BINARY_DELTA_DEFLATED:
+		result = patch_delta(desc->buffer, desc->size,
+				     data,
+				     patch->deflate_origlen,
+				     &dst_size);
+		free(desc->buffer);
+		desc->buffer = result;
+		free(data);
+		break;
+	case BINARY_LITERAL_DEFLATED:
+		free(desc->buffer);
+		desc->buffer = data;
+		dst_size = patch->deflate_origlen;
+		break;
+	}
+	if (!desc->buffer)
+		return -1;
+	desc->size = desc->alloc = dst_size;
+	return 0;
+}
+
+static int apply_binary(struct buffer_desc *desc, struct patch *patch)
+{
+	const char *name = patch->old_name ? patch->old_name : patch->new_name;
+	unsigned char sha1[20];
+	unsigned char hdr[50];
+	int hdrlen;
+
+	if (!allow_binary_replacement)
+		return error("cannot apply binary patch to '%s' "
+			     "without --allow-binary-replacement",
+			     name);
+
+	/* For safety, we require patch index line to contain
+	 * full 40-byte textual SHA1 for old and new, at least for now.
+	 */
+	if (strlen(patch->old_sha1_prefix) != 40 ||
+	    strlen(patch->new_sha1_prefix) != 40 ||
+	    get_sha1_hex(patch->old_sha1_prefix, sha1) ||
+	    get_sha1_hex(patch->new_sha1_prefix, sha1))
+		return error("cannot apply binary patch to '%s' "
+			     "without full index line", name);
+
+	if (patch->old_name) {
+		/* See if the old one matches what the patch
+		 * applies to.
+		 */
+		write_sha1_file_prepare(desc->buffer, desc->size,
+					blob_type, sha1, hdr, &hdrlen);
+		if (strcmp(sha1_to_hex(sha1), patch->old_sha1_prefix))
+			return error("the patch applies to '%s' (%s), "
+				     "which does not match the "
+				     "current contents.",
+				     name, sha1_to_hex(sha1));
+	}
+	else {
+		/* Otherwise, the old one must be empty. */
+		if (desc->size)
+			return error("the patch applies to an empty "
+				     "'%s' but it is not empty", name);
+	}
+
+	get_sha1_hex(patch->new_sha1_prefix, sha1);
+	if (!memcmp(sha1, null_sha1, 20)) {
+		free(desc->buffer);
+		desc->alloc = desc->size = 0;
+		desc->buffer = NULL;
+		return 0; /* deletion patch */
+	}
+
+	if (has_sha1_file(sha1)) {
+		/* We already have the postimage */
+		char type[10];
+		unsigned long size;
+
+		free(desc->buffer);
+		desc->buffer = read_sha1_file(sha1, type, &size);
+		if (!desc->buffer)
+			return error("the necessary postimage %s for "
+				     "'%s' cannot be read",
+				     patch->new_sha1_prefix, name);
+		desc->alloc = desc->size = size;
+	}
+	else {
+		/* We have verified desc matches the preimage;
+		 * apply the patch data to it, which is stored
+		 * in the patch->fragments->{patch,size}.
+		 */
+		if (apply_binary_fragment(desc, patch))
+			return error("binary patch does not apply to '%s'",
+				     name);
+
+		/* verify that the result matches */
+		write_sha1_file_prepare(desc->buffer, desc->size, blob_type,
+					sha1, hdr, &hdrlen);
+		if (strcmp(sha1_to_hex(sha1), patch->new_sha1_prefix))
+			return error("binary patch to '%s' creates incorrect result", name);
+	}
+
+	return 0;
+}
+
 static int apply_fragments(struct buffer_desc *desc, struct patch *patch)
 {
 	struct fragment *frag = patch->fragments;
 	const char *name = patch->old_name ? patch->old_name : patch->new_name;
 
-	if (patch->is_binary) {
-		unsigned char sha1[20];
-
-		if (!allow_binary_replacement)
-			return error("cannot apply binary patch to '%s' "
-				     "without --allow-binary-replacement",
-				     name);
-
-		/* For safety, we require patch index line to contain
-		 * full 40-byte textual SHA1 for old and new, at least for now.
-		 */
-		if (strlen(patch->old_sha1_prefix) != 40 ||
-		    strlen(patch->new_sha1_prefix) != 40 ||
-		    get_sha1_hex(patch->old_sha1_prefix, sha1) ||
-		    get_sha1_hex(patch->new_sha1_prefix, sha1))
-			return error("cannot apply binary patch to '%s' "
-				     "without full index line", name);
-
-		if (patch->old_name) {
-			unsigned char hdr[50];
-			int hdrlen;
-
-			/* See if the old one matches what the patch
-			 * applies to.
-			 */
-			write_sha1_file_prepare(desc->buffer, desc->size,
-						blob_type, sha1, hdr, &hdrlen);
-			if (strcmp(sha1_to_hex(sha1), patch->old_sha1_prefix))
-				return error("the patch applies to '%s' (%s), "
-					     "which does not match the "
-					     "current contents.",
-					     name, sha1_to_hex(sha1));
-		}
-		else {
-			/* Otherwise, the old one must be empty. */
-			if (desc->size)
-				return error("the patch applies to an empty "
-					     "'%s' but it is not empty", name);
-		}
-
-		/* For now, we do not record post-image data in the patch,
-		 * and require the object already present in the recipient's
-		 * object database.
-		 */
-		if (desc->buffer) {
-			free(desc->buffer);
-			desc->alloc = desc->size = 0;
-		}
-		get_sha1_hex(patch->new_sha1_prefix, sha1);
-
-		if (memcmp(sha1, null_sha1, 20)) {
-			char type[10];
-			unsigned long size;
-
-			desc->buffer = read_sha1_file(sha1, type, &size);
-			if (!desc->buffer)
-				return error("the necessary postimage %s for "
-					     "'%s' does not exist",
-					     patch->new_sha1_prefix, name);
-			desc->alloc = desc->size = size;
-		}
-
-		return 0;
-	}
+	if (patch->is_binary)
+		return apply_binary(desc, patch);
 
 	while (frag) {
 		if (apply_one_fragment(desc, frag) < 0)
@@ -1424,7 +1603,7 @@ static int apply_fragments(struct buffer_desc *desc, struct patch *patch)
 	return 0;
 }
 
-static int apply_data(struct patch *patch, struct stat *st)
+static int apply_data(struct patch *patch, struct stat *st, struct cache_entry *ce)
 {
 	char *buf;
 	unsigned long size, alloc;
@@ -1433,7 +1612,17 @@ static int apply_data(struct patch *patch, struct stat *st)
 	size = 0;
 	alloc = 0;
 	buf = NULL;
-	if (patch->old_name) {
+	if (cached) {
+		if (ce) {
+			char type[20];
+			buf = read_sha1_file(ce->sha1, type, &size);
+			if (!buf)
+				return error("read of %s failed",
+					     patch->old_name);
+			alloc = size;
+		}
+	}
+	else if (patch->old_name) {
 		size = st->st_size;
 		alloc = size + 8192;
 		buf = xmalloc(alloc);
@@ -1461,16 +1650,21 @@ static int check_patch(struct patch *patch)
 	const char *old_name = patch->old_name;
 	const char *new_name = patch->new_name;
 	const char *name = old_name ? old_name : new_name;
+	struct cache_entry *ce = NULL;
 
 	if (old_name) {
-		int changed;
-		int stat_ret = lstat(old_name, &st);
+		int changed = 0;
+		int stat_ret = 0;
+		unsigned st_mode = 0;
 
+		if (!cached)
+			stat_ret = lstat(old_name, &st);
 		if (check_index) {
 			int pos = cache_name_pos(old_name, strlen(old_name));
 			if (pos < 0)
 				return error("%s: does not exist in index",
 					     old_name);
+			ce = active_cache[pos];
 			if (stat_ret < 0) {
 				struct checkout costate;
 				if (errno != ENOENT)
@@ -1483,40 +1677,46 @@ static int check_patch(struct patch *patch)
 				costate.quiet = 0;
 				costate.not_new = 0;
 				costate.refresh_cache = 1;
-				if (checkout_entry(active_cache[pos],
+				if (checkout_entry(ce,
 						   &costate,
 						   NULL) ||
 				    lstat(old_name, &st))
 					return -1;
 			}
-
-			changed = ce_match_stat(active_cache[pos], &st, 1);
+			if (!cached)
+				changed = ce_match_stat(ce, &st, 1);
 			if (changed)
 				return error("%s: does not match index",
 					     old_name);
+			if (cached)
+				st_mode = ntohl(ce->ce_mode);
 		}
 		else if (stat_ret < 0)
 			return error("%s: %s", old_name, strerror(errno));
 
+		if (!cached)
+			st_mode = ntohl(create_ce_mode(st.st_mode));
+
 		if (patch->is_new < 0)
 			patch->is_new = 0;
-		st.st_mode = ntohl(create_ce_mode(st.st_mode));
 		if (!patch->old_mode)
-			patch->old_mode = st.st_mode;
-		if ((st.st_mode ^ patch->old_mode) & S_IFMT)
+			patch->old_mode = st_mode;
+		if ((st_mode ^ patch->old_mode) & S_IFMT)
 			return error("%s: wrong type", old_name);
-		if (st.st_mode != patch->old_mode)
+		if (st_mode != patch->old_mode)
 			fprintf(stderr, "warning: %s has type %o, expected %o\n",
-				old_name, st.st_mode, patch->old_mode);
+				old_name, st_mode, patch->old_mode);
 	}
 
 	if (new_name && (patch->is_new | patch->is_rename | patch->is_copy)) {
 		if (check_index && cache_name_pos(new_name, strlen(new_name)) >= 0)
 			return error("%s: already exists in index", new_name);
-		if (!lstat(new_name, &st))
-			return error("%s: already exists in working directory", new_name);
-		if (errno != ENOENT)
-			return error("%s: %s", new_name, strerror(errno));
+		if (!cached) {
+			if (!lstat(new_name, &st))
+				return error("%s: already exists in working directory", new_name);
+			if (errno != ENOENT)
+				return error("%s: %s", new_name, strerror(errno));
+		}
 		if (!patch->new_mode) {
 			if (patch->is_new)
 				patch->new_mode = S_IFREG | 0644;
@@ -1533,9 +1733,9 @@ static int check_patch(struct patch *patch)
 			return error("new mode (%o) of %s does not match old mode (%o)%s%s",
 				patch->new_mode, new_name, patch->old_mode,
 				same ? "" : " of ", same ? "" : old_name);
-	}	
+	}
 
-	if (apply_data(patch, &st) < 0)
+	if (apply_data(patch, &st, ce) < 0)
 		return error("%s: patch does not apply", name);
 	return 0;
 }
@@ -1602,7 +1802,7 @@ static void numstat_patch_list(struct patch *patch)
 {
 	for ( ; patch; patch = patch->next) {
 		const char *name;
-		name = patch->old_name ? patch->old_name : patch->new_name;
+		name = patch->new_name ? patch->new_name : patch->old_name;
 		printf("%d\t%d\t", patch->lines_added, patch->lines_deleted);
 		if (line_termination && quote_c_style(name, NULL, NULL, 0))
 			quote_c_style(name, NULL, stdout, 0);
@@ -1718,7 +1918,8 @@ static void remove_file(struct patch *patch)
 		if (remove_file_from_cache(patch->old_name) < 0)
 			die("unable to remove %s from index", patch->old_name);
 	}
-	unlink(patch->old_name);
+	if (!cached)
+		unlink(patch->old_name);
 }
 
 static void add_index_file(const char *path, unsigned mode, void *buf, unsigned long size)
@@ -1735,9 +1936,11 @@ static void add_index_file(const char *path, unsigned mode, void *buf, unsigned
 	memcpy(ce->name, path, namelen);
 	ce->ce_mode = create_ce_mode(mode);
 	ce->ce_flags = htons(namelen);
-	if (lstat(path, &st) < 0)
-		die("unable to stat newly created file %s", path);
-	fill_stat_cache_info(ce, &st);
+	if (!cached) {
+		if (lstat(path, &st) < 0)
+			die("unable to stat newly created file %s", path);
+		fill_stat_cache_info(ce, &st);
+	}
 	if (write_sha1_file(buf, size, blob_type, ce->sha1) < 0)
 		die("unable to create backing store for newly created file %s", path);
 	if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD) < 0)
@@ -1774,6 +1977,8 @@ static int try_create_file(const char *path, unsigned int mode, const char *buf,
  */
 static void create_one_file(char *path, unsigned mode, const char *buf, unsigned long size)
 {
+	if (cached)
+		return;
 	if (!try_create_file(path, mode, buf, size))
 		return;
 
@@ -1873,7 +2078,6 @@ static int use_patch(struct patch *p)
 
 static int apply_patch(int fd, const char *filename)
 {
-	int newfd;
 	unsigned long offset, size;
 	char *buffer = read_patch_file(fd, &size);
 	struct patch *list = NULL, **listp = &list;
@@ -1904,12 +2108,11 @@ static int apply_patch(int fd, const char *filename)
 		size -= nr;
 	}
 
-	newfd = -1;
 	if (whitespace_error && (new_whitespace == error_on_whitespace))
 		apply = 0;
 
 	write_index = check_index && apply;
-	if (write_index)
+	if (write_index && newfd < 0)
 		newfd = hold_index_file_for_update(&cache_file, get_index_file());
 	if (check_index) {
 		if (read_cache() < 0)
@@ -1922,12 +2125,6 @@ static int apply_patch(int fd, const char *filename)
 	if (apply)
 		write_out_results(list, skipped_patch);
 
-	if (write_index) {
-		if (write_cache(newfd, active_cache, active_nr) ||
-		    commit_index_file(&cache_file))
-			die("Unable to write new cachefile");
-	}
-
 	if (show_index_info)
 		show_index_list(list);
 
@@ -1990,7 +2187,8 @@ int main(int argc, char **argv)
 			diffstat = 1;
 			continue;
 		}
-		if (!strcmp(arg, "--allow-binary-replacement")) {
+		if (!strcmp(arg, "--allow-binary-replacement") ||
+		    !strcmp(arg, "--binary")) {
 			allow_binary_replacement = 1;
 			continue;
 		}
@@ -2013,6 +2211,11 @@ int main(int argc, char **argv)
 			check_index = 1;
 			continue;
 		}
+		if (!strcmp(arg, "--cached")) {
+			check_index = 1;
+			cached = 1;
+			continue;
+		}
 		if (!strcmp(arg, "--apply")) {
 			apply = 1;
 			continue;
@@ -2085,5 +2288,12 @@ int main(int argc, char **argv)
 				whitespace_error == 1 ? "" : "s",
 				whitespace_error == 1 ? "s" : "");
 	}
+
+	if (write_index) {
+		if (write_cache(newfd, active_cache, active_nr) ||
+		    commit_index_file(&cache_file))
+			die("Unable to write new cachefile");
+	}
+
 	return 0;
 }

base85.c

@@ -0,0 +1,140 @@
+#include "cache.h"
+
+#undef DEBUG_85
+
+#ifdef DEBUG_85
+#define say(a) fprintf(stderr, a)
+#define say1(a,b) fprintf(stderr, a, b)
+#define say2(a,b,c) fprintf(stderr, a, b, c)
+#else
+#define say(a) do {} while(0)
+#define say1(a,b) do {} while(0)
+#define say2(a,b,c) do {} while(0)
+#endif
+
+static const char en85[] = {
+	'0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
+	'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J',
+	'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T',
+	'U', 'V', 'W', 'X', 'Y', 'Z',
+	'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j',
+	'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't',
+	'u', 'v', 'w', 'x', 'y', 'z',
+	'!', '#', '$', '%', '&', '(', ')', '*', '+', '-',
+	';', '<', '=', '>', '?', '@', '^', '_',	'`', '{',
+	'|', '}', '~'
+};
+
+static char de85[256];
+static void prep_base85(void)
+{
+	int i;
+	if (de85['Z'])
+		return;
+	for (i = 0; i < ARRAY_SIZE(en85); i++) {
+		int ch = en85[i];
+		de85[ch] = i + 1;
+	}
+}
+
+int decode_85(char *dst, char *buffer, int len)
+{
+	prep_base85();
+
+	say2("decode 85 <%.*s>", len/4*5, buffer);
+	while (len) {
+		unsigned acc = 0;
+		int de, cnt = 4;
+		unsigned char ch;
+		do {
+			ch = *buffer++;
+			de = de85[ch];
+			if (--de < 0)
+				return error("invalid base85 alphabet %c", ch);
+			acc = acc * 85 + de;
+		} while (--cnt);
+		ch = *buffer++;
+		de = de85[ch];
+		if (--de < 0)
+			return error("invalid base85 alphabet %c", ch);
+		/*
+		 * Detect overflow.  The largest
+		 * 5-letter possible is "|NsC0" to
+		 * encode 0xffffffff, and "|NsC" gives
+		 * 0x03030303 at this point (i.e.
+		 * 0xffffffff = 0x03030303 * 85).
+		 */
+		if (0x03030303 < acc ||
+		    0xffffffff - de < (acc *= 85))
+			error("invalid base85 sequence %.5s", buffer-5);
+		acc += de;
+		say1(" %08x", acc);
+
+		cnt = (len < 4) ? len : 4;
+		len -= cnt;
+		do {
+			acc = (acc << 8) | (acc >> 24);
+			*dst++ = acc;
+		} while (--cnt);
+	}
+	say("\n");
+
+	return 0;
+}
+
+void encode_85(char *buf, unsigned char *data, int bytes)
+{
+	prep_base85();
+
+	say("encode 85");
+	while (bytes) {
+		unsigned acc = 0;
+		int cnt;
+		for (cnt = 24; cnt >= 0; cnt -= 8) {
+			int ch = *data++;
+			acc |= ch << cnt;
+			if (--bytes == 0)
+				break;
+		}
+		say1(" %08x", acc);
+		for (cnt = 4; cnt >= 0; cnt--) {
+			int val = acc % 85;
+			acc /= 85;
+			buf[cnt] = en85[val];
+		}
+		buf += 5;
+	}
+	say("\n");
+
+	*buf = 0;
+}
+
+#ifdef DEBUG_85
+int main(int ac, char **av)
+{
+	char buf[1024];
+
+	if (!strcmp(av[1], "-e")) {
+		int len = strlen(av[2]);
+		encode_85(buf, av[2], len);
+		if (len <= 26) len = len + 'A' - 1;
+		else len = len + 'a' - 26 + 1;
+		printf("encoded: %c%s\n", len, buf);
+		return 0;
+	}
+	if (!strcmp(av[1], "-d")) {
+		int len = *av[2];
+		if ('A' <= len && len <= 'Z') len = len - 'A' + 1;
+		else len = len - 'a' + 26 + 1;
+		decode_85(buf, av[2]+1, len);
+		printf("decoded: %.*s\n", len, buf);
+		return 0;
+	}
+	if (!strcmp(av[1], "-t")) {
+		char t[4] = { -1,-1,-1,-1 };
+		encode_85(buf, t, 4);
+		printf("encoded: D%s\n", buf);
+		return 0;
+	}
+}
+#endif

builtin-check-ref-format.c

@@ -0,0 +1,14 @@
+/*
+ * GIT - The information manager from hell
+ */
+
+#include "cache.h"
+#include "refs.h"
+#include "builtin.h"
+
+int cmd_check_ref_format(int argc, const char **argv, char **envp)
+{
+	if (argc != 2)
+		usage("git check-ref-format refname");
+	return !!check_ref_format(argv[1]);
+}

builtin-diff.c

@@ -84,8 +84,7 @@ static void stuff_change(struct diff_options *opt,
 
 	if (opt->reverse_diff) {
 		unsigned tmp;
-		const
-			const unsigned char *tmp_u;
+		const unsigned char *tmp_u;
 		const char *tmp_c;
 		tmp = old_mode; old_mode = new_mode; new_mode = tmp;
 		tmp_u = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_u;
@@ -123,7 +122,7 @@ static int builtin_diff_b_f(struct rev_info *revs,
 	stuff_change(&revs->diffopt,
 		     canon_mode(st.st_mode), canon_mode(st.st_mode),
 		     blob[0].sha1, null_sha1,
-		     blob[0].name, path);
+		     path, path);
 	diffcore_std(&revs->diffopt);
 	diff_flush(&revs->diffopt);
 	return 0;
@@ -133,7 +132,9 @@ static int builtin_diff_blobs(struct rev_info *revs,
 			      int argc, const char **argv,
 			      struct blobinfo *blob)
 {
-	/* Blobs */
+	/* Blobs: the arguments are reversed when setup_revisions()
+	 * picked them up.
+	 */
 	unsigned mode = canon_mode(S_IFREG | 0644);
 
 	while (1 < argc) {
@@ -146,8 +147,8 @@ static int builtin_diff_blobs(struct rev_info *revs,
 	}
 	stuff_change(&revs->diffopt,
 		     mode, mode,
-		     blob[0].sha1, blob[1].sha1,
-		     blob[1].name, blob[1].name);
+		     blob[1].sha1, blob[0].sha1,
+		     blob[0].name, blob[0].name);
 	diffcore_std(&revs->diffopt);
 	diff_flush(&revs->diffopt);
 	return 0;

builtin-grep.c

@@ -0,0 +1,902 @@
+/*
+ * Builtin "git grep"
+ *
+ * Copyright (c) 2006 Junio C Hamano
+ */
+#include "cache.h"
+#include "blob.h"
+#include "tree.h"
+#include "commit.h"
+#include "tag.h"
+#include "tree-walk.h"
+#include "builtin.h"
+#include <regex.h>
+#include <fnmatch.h>
+#include <sys/wait.h>
+
+/*
+ * git grep pathspecs are somewhat different from diff-tree pathspecs;
+ * pathname wildcards are allowed.
+ */
+static int pathspec_matches(const char **paths, const char *name)
+{
+	int namelen, i;
+	if (!paths || !*paths)
+		return 1;
+	namelen = strlen(name);
+	for (i = 0; paths[i]; i++) {
+		const char *match = paths[i];
+		int matchlen = strlen(match);
+		const char *cp, *meta;
+
+		if ((matchlen <= namelen) &&
+		    !strncmp(name, match, matchlen) &&
+		    (match[matchlen-1] == '/' ||
+		     name[matchlen] == '\0' || name[matchlen] == '/'))
+			return 1;
+		if (!fnmatch(match, name, 0))
+			return 1;
+		if (name[namelen-1] != '/')
+			continue;
+
+		/* We are being asked if the directory ("name") is worth
+		 * descending into.
+		 *
+		 * Find the longest leading directory name that does
+		 * not have metacharacter in the pathspec; the name
+		 * we are looking at must overlap with that directory.
+		 */
+		for (cp = match, meta = NULL; cp - match < matchlen; cp++) {
+			char ch = *cp;
+			if (ch == '*' || ch == '[' || ch == '?') {
+				meta = cp;
+				break;
+			}
+		}
+		if (!meta)
+			meta = cp; /* fully literal */
+
+		if (namelen <= meta - match) {
+			/* Looking at "Documentation/" and
+			 * the pattern says "Documentation/howto/", or
+			 * "Documentation/diff*.txt".  The name we
+			 * have should match prefix.
+			 */
+			if (!memcmp(match, name, namelen))
+				return 1;
+			continue;
+		}
+
+		if (meta - match < namelen) {
+			/* Looking at "Documentation/howto/" and
+			 * the pattern says "Documentation/h*";
+			 * match up to "Do.../h"; this avoids descending
+			 * into "Documentation/technical/".
+			 */
+			if (!memcmp(match, name, meta - match))
+				return 1;
+			continue;
+		}
+	}
+	return 0;
+}
+
+struct grep_pat {
+	struct grep_pat *next;
+	const char *origin;
+	int no;
+	const char *pattern;
+	regex_t regexp;
+};
+
+struct grep_opt {
+	struct grep_pat *pattern_list;
+	struct grep_pat **pattern_tail;
+	regex_t regexp;
+	unsigned linenum:1;
+	unsigned invert:1;
+	unsigned name_only:1;
+	unsigned unmatch_name_only:1;
+	unsigned count:1;
+	unsigned word_regexp:1;
+	unsigned fixed:1;
+#define GREP_BINARY_DEFAULT	0
+#define GREP_BINARY_NOMATCH	1
+#define GREP_BINARY_TEXT	2
+	unsigned binary:2;
+	int regflags;
+	unsigned pre_context;
+	unsigned post_context;
+};
+
+static void add_pattern(struct grep_opt *opt, const char *pat,
+			const char *origin, int no)
+{
+	struct grep_pat *p = xcalloc(1, sizeof(*p));
+	p->pattern = pat;
+	p->origin = origin;
+	p->no = no;
+	*opt->pattern_tail = p;
+	opt->pattern_tail = &p->next;
+	p->next = NULL;
+}
+
+static void compile_patterns(struct grep_opt *opt)
+{
+	struct grep_pat *p;
+	for (p = opt->pattern_list; p; p = p->next) {
+		int err = regcomp(&p->regexp, p->pattern, opt->regflags);
+		if (err) {
+			char errbuf[1024];
+			char where[1024];
+			if (p->no)
+				sprintf(where, "In '%s' at %d, ",
+					p->origin, p->no);
+			else if (p->origin)
+				sprintf(where, "%s, ", p->origin);
+			else
+				where[0] = 0;
+			regerror(err, &p->regexp, errbuf, 1024);
+			regfree(&p->regexp);
+			die("%s'%s': %s", where, p->pattern, errbuf);
+		}
+	}
+}
+
+static char *end_of_line(char *cp, unsigned long *left)
+{
+	unsigned long l = *left;
+	while (l && *cp != '\n') {
+		l--;
+		cp++;
+	}
+	*left = l;
+	return cp;
+}
+
+static int word_char(char ch)
+{
+	return isalnum(ch) || ch == '_';
+}
+
+static void show_line(struct grep_opt *opt, const char *bol, const char *eol,
+		      const char *name, unsigned lno, char sign)
+{
+	printf("%s%c", name, sign);
+	if (opt->linenum)
+		printf("%d%c", lno, sign);
+	printf("%.*s\n", (int)(eol-bol), bol);
+}
+
+/*
+ * NEEDSWORK: share code with diff.c
+ */
+#define FIRST_FEW_BYTES 8000
+static int buffer_is_binary(const char *ptr, unsigned long size)
+{
+	if (FIRST_FEW_BYTES < size)
+		size = FIRST_FEW_BYTES;
+	if (memchr(ptr, 0, size))
+		return 1;
+	return 0;
+}
+
+static int fixmatch(const char *pattern, char *line, regmatch_t *match)
+{
+	char *hit = strstr(line, pattern);
+	if (!hit) {
+		match->rm_so = match->rm_eo = -1;
+		return REG_NOMATCH;
+	}
+	else {
+		match->rm_so = hit - line;
+		match->rm_eo = match->rm_so + strlen(pattern);
+		return 0;
+	}
+}
+
+static int grep_buffer(struct grep_opt *opt, const char *name,
+		       char *buf, unsigned long size)
+{
+	char *bol = buf;
+	unsigned long left = size;
+	unsigned lno = 1;
+	struct pre_context_line {
+		char *bol;
+		char *eol;
+	} *prev = NULL, *pcl;
+	unsigned last_hit = 0;
+	unsigned last_shown = 0;
+	int binary_match_only = 0;
+	const char *hunk_mark = "";
+	unsigned count = 0;
+
+	if (buffer_is_binary(buf, size)) {
+		switch (opt->binary) {
+		case GREP_BINARY_DEFAULT:
+			binary_match_only = 1;
+			break;
+		case GREP_BINARY_NOMATCH:
+			return 0; /* Assume unmatch */
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (opt->pre_context)
+		prev = xcalloc(opt->pre_context, sizeof(*prev));
+	if (opt->pre_context || opt->post_context)
+		hunk_mark = "--\n";
+
+	while (left) {
+		regmatch_t pmatch[10];
+		char *eol, ch;
+		int hit = 0;
+		struct grep_pat *p;
+
+		eol = end_of_line(bol, &left);
+		ch = *eol;
+		*eol = 0;
+
+		for (p = opt->pattern_list; p; p = p->next) {
+			if (!opt->fixed) {
+				regex_t *exp = &p->regexp;
+				hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
+					       pmatch, 0);
+			}
+			else {
+				hit = !fixmatch(p->pattern, bol, pmatch);
+			}
+
+			if (hit && opt->word_regexp) {
+				/* Match beginning must be either
+				 * beginning of the line, or at word
+				 * boundary (i.e. the last char must
+				 * not be alnum or underscore).
+				 */
+				if ((pmatch[0].rm_so < 0) ||
+				    (eol - bol) <= pmatch[0].rm_so ||
+				    (pmatch[0].rm_eo < 0) ||
+				    (eol - bol) < pmatch[0].rm_eo)
+					die("regexp returned nonsense");
+				if (pmatch[0].rm_so != 0 &&
+				    word_char(bol[pmatch[0].rm_so-1]))
+					hit = 0;
+				if (pmatch[0].rm_eo != (eol-bol) &&
+				    word_char(bol[pmatch[0].rm_eo]))
+					hit = 0;
+			}
+			if (hit)
+				break;
+		}
+		/* "grep -v -e foo -e bla" should list lines
+		 * that do not have either, so inversion should
+		 * be done outside.
+		 */
+		if (opt->invert)
+			hit = !hit;
+		if (opt->unmatch_name_only) {
+			if (hit)
+				return 0;
+			goto next_line;
+		}
+		if (hit) {
+			count++;
+			if (binary_match_only) {
+				printf("Binary file %s matches\n", name);
+				return 1;
+			}
+			if (opt->name_only) {
+				printf("%s\n", name);
+				return 1;
+			}
+			/* Hit at this line.  If we haven't shown the
+			 * pre-context lines, we would need to show them.
+			 * When asked to do "count", this still show
+			 * the context which is nonsense, but the user
+			 * deserves to get that ;-).
+			 */
+			if (opt->pre_context) {
+				unsigned from;
+				if (opt->pre_context < lno)
+					from = lno - opt->pre_context;
+				else
+					from = 1;
+				if (from <= last_shown)
+					from = last_shown + 1;
+				if (last_shown && from != last_shown + 1)
+					printf(hunk_mark);
+				while (from < lno) {
+					pcl = &prev[lno-from-1];
+					show_line(opt, pcl->bol, pcl->eol,
+						  name, from, '-');
+					from++;
+				}
+				last_shown = lno-1;
+			}
+			if (last_shown && lno != last_shown + 1)
+				printf(hunk_mark);
+			if (!opt->count)
+				show_line(opt, bol, eol, name, lno, ':');
+			last_shown = last_hit = lno;
+		}
+		else if (last_hit &&
+			 lno <= last_hit + opt->post_context) {
+			/* If the last hit is within the post context,
+			 * we need to show this line.
+			 */
+			if (last_shown && lno != last_shown + 1)
+				printf(hunk_mark);
+			show_line(opt, bol, eol, name, lno, '-');
+			last_shown = lno;
+		}
+		if (opt->pre_context) {
+			memmove(prev+1, prev,
+				(opt->pre_context-1) * sizeof(*prev));
+			prev->bol = bol;
+			prev->eol = eol;
+		}
+
+	next_line:
+		*eol = ch;
+		bol = eol + 1;
+		if (!left)
+			break;
+		left--;
+		lno++;
+	}
+
+	if (opt->unmatch_name_only) {
+		/* We did not see any hit, so we want to show this */
+		printf("%s\n", name);
+		return 1;
+	}
+
+	/* NEEDSWORK:
+	 * The real "grep -c foo *.c" gives many "bar.c:0" lines,
+	 * which feels mostly useless but sometimes useful.  Maybe
+	 * make it another option?  For now suppress them.
+	 */
+	if (opt->count && count)
+		printf("%s:%u\n", name, count);
+	return !!last_hit;
+}
+
+static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, const char *name)
+{
+	unsigned long size;
+	char *data;
+	char type[20];
+	int hit;
+	data = read_sha1_file(sha1, type, &size);
+	if (!data) {
+		error("'%s': unable to read %s", name, sha1_to_hex(sha1));
+		return 0;
+	}
+	hit = grep_buffer(opt, name, data, size);
+	free(data);
+	return hit;
+}
+
+static int grep_file(struct grep_opt *opt, const char *filename)
+{
+	struct stat st;
+	int i;
+	char *data;
+	if (lstat(filename, &st) < 0) {
+	err_ret:
+		if (errno != ENOENT)
+			error("'%s': %s", filename, strerror(errno));
+		return 0;
+	}
+	if (!st.st_size)
+		return 0; /* empty file -- no grep hit */
+	if (!S_ISREG(st.st_mode))
+		return 0;
+	i = open(filename, O_RDONLY);
+	if (i < 0)
+		goto err_ret;
+	data = xmalloc(st.st_size + 1);
+	if (st.st_size != xread(i, data, st.st_size)) {
+		error("'%s': short read %s", filename, strerror(errno));
+		close(i);
+		free(data);
+		return 0;
+	}
+	close(i);
+	i = grep_buffer(opt, filename, data, st.st_size);
+	free(data);
+	return i;
+}
+
+static int exec_grep(int argc, const char **argv)
+{
+	pid_t pid;
+	int status;
+
+	argv[argc] = NULL;
+	pid = fork();
+	if (pid < 0)
+		return pid;
+	if (!pid) {
+		execvp("grep", (char **) argv);
+		exit(255);
+	}
+	while (waitpid(pid, &status, 0) < 0) {
+		if (errno == EINTR)
+			continue;
+		return -1;
+	}
+	if (WIFEXITED(status)) {
+		if (!WEXITSTATUS(status))
+			return 1;
+		return 0;
+	}
+	return -1;
+}
+
+#define MAXARGS 1000
+#define ARGBUF 4096
+#define push_arg(a) do { \
+	if (nr < MAXARGS) argv[nr++] = (a); \
+	else die("maximum number of args exceeded"); \
+	} while (0)
+
+static int external_grep(struct grep_opt *opt, const char **paths, int cached)
+{
+	int i, nr, argc, hit, len;
+	const char *argv[MAXARGS+1];
+	char randarg[ARGBUF];
+	char *argptr = randarg;
+	struct grep_pat *p;
+
+	len = nr = 0;
+	push_arg("grep");
+	if (opt->fixed)
+		push_arg("-F");
+	if (opt->linenum)
+		push_arg("-n");
+	if (opt->regflags & REG_EXTENDED)
+		push_arg("-E");
+	if (opt->word_regexp)
+		push_arg("-w");
+	if (opt->name_only)
+		push_arg("-l");
+	if (opt->unmatch_name_only)
+		push_arg("-L");
+	if (opt->count)
+		push_arg("-c");
+	if (opt->post_context || opt->pre_context) {
+		if (opt->post_context != opt->pre_context) {
+			if (opt->pre_context) {
+				push_arg("-B");
+				len += snprintf(argptr, sizeof(randarg)-len,
+						"%u", opt->pre_context);
+				if (sizeof(randarg) <= len)
+					die("maximum length of args exceeded");
+				push_arg(argptr);
+				argptr += len;
+			}
+			if (opt->post_context) {
+				push_arg("-A");
+				len += snprintf(argptr, sizeof(randarg)-len,
+						"%u", opt->post_context);
+				if (sizeof(randarg) <= len)
+					die("maximum length of args exceeded");
+				push_arg(argptr);
+				argptr += len;
+			}
+		}
+		else {
+			push_arg("-C");
+			len += snprintf(argptr, sizeof(randarg)-len,
+					"%u", opt->post_context);
+			if (sizeof(randarg) <= len)
+				die("maximum length of args exceeded");
+			push_arg(argptr);
+			argptr += len;
+		}
+	}
+	for (p = opt->pattern_list; p; p = p->next) {
+		push_arg("-e");
+		push_arg(p->pattern);
+	}
+
+	/*
+	 * To make sure we get the header printed out when we want it,
+	 * add /dev/null to the paths to grep.  This is unnecessary
+	 * (and wrong) with "-l" or "-L", which always print out the
+	 * name anyway.
+	 *
+	 * GNU grep has "-H", but this is portable.
+	 */
+	if (!opt->name_only && !opt->unmatch_name_only)
+		push_arg("/dev/null");
+
+	hit = 0;
+	argc = nr;
+	for (i = 0; i < active_nr; i++) {
+		struct cache_entry *ce = active_cache[i];
+		const char *name;
+		if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode)))
+			continue;
+		if (!pathspec_matches(paths, ce->name))
+			continue;
+		name = ce->name;
+		if (name[0] == '-') {
+			int len = ce_namelen(ce);
+			name = xmalloc(len + 3);
+			memcpy(name, "./", 2);
+			memcpy(name + 2, ce->name, len + 1);
+		}
+		argv[argc++] = name;
+		if (argc < MAXARGS)
+			continue;
+		hit += exec_grep(argc, argv);
+		argc = nr;
+	}
+	if (argc > nr)
+		hit += exec_grep(argc, argv);
+	return 0;
+}
+
+static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
+{
+	int hit = 0;
+	int nr;
+	read_cache();
+
+#ifdef __unix__
+	/*
+	 * Use the external "grep" command for the case where
+	 * we grep through the checked-out files. It tends to
+	 * be a lot more optimized
+	 */
+	if (!cached) {
+		hit = external_grep(opt, paths, cached);
+		if (hit >= 0)
+			return hit;
+	}
+#endif
+
+	for (nr = 0; nr < active_nr; nr++) {
+		struct cache_entry *ce = active_cache[nr];
+		if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode)))
+			continue;
+		if (!pathspec_matches(paths, ce->name))
+			continue;
+		if (cached)
+			hit |= grep_sha1(opt, ce->sha1, ce->name);
+		else
+			hit |= grep_file(opt, ce->name);
+	}
+	return hit;
+}
+
+static int grep_tree(struct grep_opt *opt, const char **paths,
+		     struct tree_desc *tree,
+		     const char *tree_name, const char *base)
+{
+	unsigned mode;
+	int len;
+	int hit = 0;
+	const char *path;
+	const unsigned char *sha1;
+	char *down;
+	char *path_buf = xmalloc(PATH_MAX + strlen(tree_name) + 100);
+
+	if (tree_name[0]) {
+		int offset = sprintf(path_buf, "%s:", tree_name);
+		down = path_buf + offset;
+		strcat(down, base);
+	}
+	else {
+		down = path_buf;
+		strcpy(down, base);
+	}
+	len = strlen(path_buf);
+
+	while (tree->size) {
+		int pathlen;
+		sha1 = tree_entry_extract(tree, &path, &mode);
+		pathlen = strlen(path);
+		strcpy(path_buf + len, path);
+
+		if (S_ISDIR(mode))
+			/* Match "abc/" against pathspec to
+			 * decide if we want to descend into "abc"
+			 * directory.
+			 */
+			strcpy(path_buf + len + pathlen, "/");
+
+		if (!pathspec_matches(paths, down))
+			;
+		else if (S_ISREG(mode))
+			hit |= grep_sha1(opt, sha1, path_buf);
+		else if (S_ISDIR(mode)) {
+			char type[20];
+			struct tree_desc sub;
+			void *data;
+			data = read_sha1_file(sha1, type, &sub.size);
+			if (!data)
+				die("unable to read tree (%s)",
+				    sha1_to_hex(sha1));
+			sub.buf = data;
+			hit |= grep_tree(opt, paths, &sub, tree_name, down);
+			free(data);
+		}
+		update_tree_entry(tree);
+	}
+	return hit;
+}
+
+static int grep_object(struct grep_opt *opt, const char **paths,
+		       struct object *obj, const char *name)
+{
+	if (!strcmp(obj->type, blob_type))
+		return grep_sha1(opt, obj->sha1, name);
+	if (!strcmp(obj->type, commit_type) ||
+	    !strcmp(obj->type, tree_type)) {
+		struct tree_desc tree;
+		void *data;
+		int hit;
+		data = read_object_with_reference(obj->sha1, tree_type,
+						  &tree.size, NULL);
+		if (!data)
+			die("unable to read tree (%s)", sha1_to_hex(obj->sha1));
+		tree.buf = data;
+		hit = grep_tree(opt, paths, &tree, name, "");
+		free(data);
+		return hit;
+	}
+	die("unable to grep from object of type %s", obj->type);
+}
+
+static const char builtin_grep_usage[] =
+"git-grep <option>* <rev>* [-e] <pattern> [<path>...]";
+
+int cmd_grep(int argc, const char **argv, char **envp)
+{
+	int hit = 0;
+	int cached = 0;
+	int seen_dashdash = 0;
+	struct grep_opt opt;
+	struct object_list *list, **tail, *object_list = NULL;
+	const char *prefix = setup_git_directory();
+	const char **paths = NULL;
+	int i;
+
+	memset(&opt, 0, sizeof(opt));
+	opt.pattern_tail = &opt.pattern_list;
+	opt.regflags = REG_NEWLINE;
+
+	/*
+	 * If there is no -- then the paths must exist in the working
+	 * tree.  If there is no explicit pattern specified with -e or
+	 * -f, we take the first unrecognized non option to be the
+	 * pattern, but then what follows it must be zero or more
+	 * valid refs up to the -- (if exists), and then existing
+	 * paths.  If there is an explicit pattern, then the first
+	 * unrecocnized non option is the beginning of the refs list
+	 * that continues up to the -- (if exists), and then paths.
+	 */
+
+	tail = &object_list;
+	while (1 < argc) {
+		const char *arg = argv[1];
+		argc--; argv++;
+		if (!strcmp("--cached", arg)) {
+			cached = 1;
+			continue;
+		}
+		if (!strcmp("-a", arg) ||
+		    !strcmp("--text", arg)) {
+			opt.binary = GREP_BINARY_TEXT;
+			continue;
+		}
+		if (!strcmp("-i", arg) ||
+		    !strcmp("--ignore-case", arg)) {
+			opt.regflags |= REG_ICASE;
+			continue;
+		}
+		if (!strcmp("-I", arg)) {
+			opt.binary = GREP_BINARY_NOMATCH;
+			continue;
+		}
+		if (!strcmp("-v", arg) ||
+		    !strcmp("--invert-match", arg)) {
+			opt.invert = 1;
+			continue;
+		}
+		if (!strcmp("-E", arg) ||
+		    !strcmp("--extended-regexp", arg)) {
+			opt.regflags |= REG_EXTENDED;
+			continue;
+		}
+		if (!strcmp("-F", arg) ||
+		    !strcmp("--fixed-strings", arg)) {
+			opt.fixed = 1;
+			continue;
+		}
+		if (!strcmp("-G", arg) ||
+		    !strcmp("--basic-regexp", arg)) {
+			opt.regflags &= ~REG_EXTENDED;
+			continue;
+		}
+		if (!strcmp("-n", arg)) {
+			opt.linenum = 1;
+			continue;
+		}
+		if (!strcmp("-H", arg)) {
+			/* We always show the pathname, so this
+			 * is a noop.
+			 */
+			continue;
+		}
+		if (!strcmp("-l", arg) ||
+		    !strcmp("--files-with-matches", arg)) {
+			opt.name_only = 1;
+			continue;
+		}
+		if (!strcmp("-L", arg) ||
+		    !strcmp("--files-without-match", arg)) {
+			opt.unmatch_name_only = 1;
+			continue;
+		}
+		if (!strcmp("-c", arg) ||
+		    !strcmp("--count", arg)) {
+			opt.count = 1;
+			continue;
+		}
+		if (!strcmp("-w", arg) ||
+		    !strcmp("--word-regexp", arg)) {
+			opt.word_regexp = 1;
+			continue;
+		}
+		if (!strncmp("-A", arg, 2) ||
+		    !strncmp("-B", arg, 2) ||
+		    !strncmp("-C", arg, 2) ||
+		    (arg[0] == '-' && '1' <= arg[1] && arg[1] <= '9')) {
+			unsigned num;
+			const char *scan;
+			switch (arg[1]) {
+			case 'A': case 'B': case 'C':
+				if (!arg[2]) {
+					if (argc <= 1)
+						usage(builtin_grep_usage);
+					scan = *++argv;
+					argc--;
+				}
+				else
+					scan = arg + 2;
+				break;
+			default:
+				scan = arg + 1;
+				break;
+			}
+			if (sscanf(scan, "%u", &num) != 1)
+				usage(builtin_grep_usage);
+			switch (arg[1]) {
+			case 'A':
+				opt.post_context = num;
+				break;
+			default:
+			case 'C':
+				opt.post_context = num;
+			case 'B':
+				opt.pre_context = num;
+				break;
+			}
+			continue;
+		}
+		if (!strcmp("-f", arg)) {
+			FILE *patterns;
+			int lno = 0;
+			char buf[1024];
+			if (argc <= 1)
+				usage(builtin_grep_usage);
+			patterns = fopen(argv[1], "r");
+			if (!patterns)
+				die("'%s': %s", argv[1], strerror(errno));
+			while (fgets(buf, sizeof(buf), patterns)) {
+				int len = strlen(buf);
+				if (buf[len-1] == '\n')
+					buf[len-1] = 0;
+				/* ignore empty line like grep does */
+				if (!buf[0])
+					continue;
+				add_pattern(&opt, strdup(buf), argv[1], ++lno);
+			}
+			fclose(patterns);
+			argv++;
+			argc--;
+			continue;
+		}
+		if (!strcmp("-e", arg)) {
+			if (1 < argc) {
+				add_pattern(&opt, argv[1], "-e option", 0);
+				argv++;
+				argc--;
+				continue;
+			}
+			usage(builtin_grep_usage);
+		}
+		if (!strcmp("--", arg))
+			break;
+		if (*arg == '-')
+			usage(builtin_grep_usage);
+
+		/* First unrecognized non-option token */
+		if (!opt.pattern_list) {
+			add_pattern(&opt, arg, "command line", 0);
+			break;
+		}
+		else {
+			/* We are looking at the first path or rev;
+			 * it is found at argv[1] after leaving the
+			 * loop.
+			 */
+			argc++; argv--;
+			break;
+		}
+	}
+
+	if (!opt.pattern_list)
+		die("no pattern given.");
+	if ((opt.regflags != REG_NEWLINE) && opt.fixed)
+		die("cannot mix --fixed-strings and regexp");
+	if (!opt.fixed)
+		compile_patterns(&opt);
+
+	/* Check revs and then paths */
+	for (i = 1; i < argc; i++) {
+		const char *arg = argv[i];
+		unsigned char sha1[20];
+		/* Is it a rev? */
+		if (!get_sha1(arg, sha1)) {
+			struct object *object = parse_object(sha1);
+			struct object_list *elem;
+			if (!object)
+				die("bad object %s", arg);
+			elem = object_list_insert(object, tail);
+			elem->name = arg;
+			tail = &elem->next;
+			continue;
+		}
+		if (!strcmp(arg, "--")) {
+			i++;
+			seen_dashdash = 1;
+		}
+		break;
+	}
+
+	/* The rest are paths */
+	if (!seen_dashdash) {
+		int j;
+		for (j = i; j < argc; j++)
+			verify_filename(prefix, argv[j]);
+	}
+
+	if (i < argc)
+		paths = get_pathspec(prefix, argv + i);
+	else if (prefix) {
+		paths = xcalloc(2, sizeof(const char *));
+		paths[0] = prefix;
+		paths[1] = NULL;
+	}
+
+	if (!object_list)
+		return !grep_cache(&opt, paths, cached);
+
+	if (cached)
+		die("both --cached and trees are given.");
+
+	for (list = object_list; list; list = list->next) {
+		struct object *real_obj;
+		real_obj = deref_tag(list->item, NULL, 0);
+		if (grep_object(&opt, paths, real_obj, list->name))
+			hit = 1;
+	}
+	return !hit;
+}

builtin-init-db.c

@@ -4,6 +4,7 @@
  * Copyright (C) Linus Torvalds, 2005
  */
 #include "cache.h"
+#include "builtin.h"
 
 #ifndef DEFAULT_GIT_TEMPLATE_DIR
 #define DEFAULT_GIT_TEMPLATE_DIR "/usr/share/git-core/templates/"
@@ -116,7 +117,7 @@ static void copy_templates_1(char *path, int baselen,
 	}
 }
 
-static void copy_templates(const char *git_dir, int len, char *template_dir)
+static void copy_templates(const char *git_dir, int len, const char *template_dir)
 {
 	char path[PATH_MAX];
 	char template_path[PATH_MAX];
@@ -163,7 +164,7 @@ static void copy_templates(const char *git_dir, int len, char *template_dir)
 	closedir(dir);
 }
 
-static void create_default_files(const char *git_dir, char *template_path)
+static void create_default_files(const char *git_dir, const char *template_path)
 {
 	unsigned len = strlen(git_dir);
 	static char path[PATH_MAX];
@@ -234,15 +235,16 @@ static const char init_db_usage[] =
  * On the other hand, it might just make lookup slower and messier. You
  * be the judge.  The default case is to have one DB per managed directory.
  */
-int main(int argc, char **argv)
+int cmd_init_db(int argc, const char **argv, char **envp)
 {
 	const char *git_dir;
 	const char *sha1_dir;
-	char *path, *template_dir = NULL;
+	const char *template_dir = NULL;
+	char *path;
 	int len, i;
 
 	for (i = 1; i < argc; i++, argv++) {
-		char *arg = argv[1];
+		const char *arg = argv[1];
 		if (!strncmp(arg, "--template=", 11))
 			template_dir = arg+11;
 		else if (!strcmp(arg, "--shared"))

builtin-log.c

@@ -23,6 +23,13 @@ static int cmd_log_wc(int argc, const char **argv, char **envp,
 	rev->commit_format = CMIT_FMT_DEFAULT;
 	rev->verbose_header = 1;
 	argc = setup_revisions(argc, argv, rev, "HEAD");
+	if (rev->always_show_header) {
+		if (rev->diffopt.pickaxe || rev->diffopt.filter) {
+			rev->always_show_header = 0;
+			if (rev->diffopt.output_format == DIFF_FORMAT_RAW)
+				rev->diffopt.output_format = DIFF_FORMAT_NO_OUTPUT;
+		}
+	}
 
 	if (argc > 1)
 		die("unrecognized argument: %s", argv[1]);

builtin-rev-list.c

@@ -7,6 +7,7 @@
 #include "tree-walk.h"
 #include "diff.h"
 #include "revision.h"
+#include "builtin.h"
 
 /* bits #0-15 in revision.h */
 
@@ -36,7 +37,7 @@ static const char rev_list_usage[] =
 "    --bisect"
 ;
 
-struct rev_info revs;
+static struct rev_info revs;
 
 static int bisect_list = 0;
 static int show_timestamp = 0;
@@ -291,7 +292,7 @@ static void mark_edges_uninteresting(struct commit_list *list)
 	}
 }
 
-int main(int argc, const char **argv)
+int cmd_rev_list(int argc, const char **argv, char **envp)
 {
 	struct commit_list *list;
 	int i;

builtin.h

@@ -24,5 +24,9 @@ extern int cmd_format_patch(int argc, const char **argv, char **envp);
 extern int cmd_count_objects(int argc, const char **argv, char **envp);
 
 extern int cmd_push(int argc, const char **argv, char **envp);
+extern int cmd_grep(int argc, const char **argv, char **envp);
+extern int cmd_rev_list(int argc, const char **argv, char **envp);
+extern int cmd_check_ref_format(int argc, const char **argv, char **envp);
+extern int cmd_init_db(int argc, const char **argv, char **envp);
 
 #endif

cache.h

@@ -158,6 +158,12 @@ extern int index_pipe(unsigned char *sha1, int fd, const char *type, int write_o
 extern int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object);
 extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st);
 
+#define REFRESH_REALLY		0x0001	/* ignore_valid */
+#define REFRESH_UNMERGED	0x0002	/* allow unmerged */
+#define REFRESH_QUIET		0x0004	/* be quiet about it */
+#define REFRESH_IGNORE_MISSING	0x0008	/* ignore non-existent */
+extern int refresh_cache(unsigned int flags);
+
 struct cache_file {
 	struct cache_file *next;
 	char lockfile[PATH_MAX];
@@ -364,4 +370,8 @@ extern int receive_keep_pack(int fd[2], const char *me, int quiet);
 /* pager.c */
 extern void setup_pager(void);
 
+/* base85 */
+int decode_85(char *dst, char *line, int linelen);
+void encode_85(char *buf, unsigned char *data, int bytes);
+
 #endif /* CACHE_H */

cat-file.c

@@ -103,8 +103,10 @@ int main(int argc, char **argv)
 
 	setup_git_directory();
 	git_config(git_default_config);
-	if (argc != 3 || get_sha1(argv[2], sha1))
+	if (argc != 3)
 		usage("git-cat-file [-t|-s|-e|-p|<type>] <sha1>");
+	if (get_sha1(argv[2], sha1))
+		die("Not a valid object name %s", argv[2]);
 
 	opt = 0;
 	if ( argv[1][0] == '-' ) {
@@ -133,8 +135,7 @@ int main(int argc, char **argv)
 		return !has_sha1_file(sha1);
 
 	case 'p':
-		if (get_sha1(argv[2], sha1) ||
-		    sha1_object_info(sha1, type, NULL))
+		if (sha1_object_info(sha1, type, NULL))
 			die("Not a valid object name %s", argv[2]);
 
 		/* custom pretty-print here */

check-ref-format.c

@@ -1,17 +0,0 @@
-/*
- * GIT - The information manager from hell
- */
-
-#include "cache.h"
-#include "refs.h"
-
-#include <stdio.h>
-
-int main(int ac, char **av)
-{
-	if (ac != 2)
-		usage("git-check-ref-format refname");
-	if (check_ref_format(av[1]))
-		exit(1);
-	return 0;
-}

checkout-index.c

@@ -277,7 +277,7 @@ int main(int argc, char **argv)
 			die("git-checkout-index: don't mix '--stdin' and explicit filenames");
 		p = prefix_path(prefix, prefix_length, arg);
 		checkout_file(p);
-		if (p != arg)
+		if (p < arg || p > arg + strlen(arg))
 			free((char*)p);
 	}
 
@@ -299,7 +299,7 @@ int main(int argc, char **argv)
 				path_name = buf.buf;
 			p = prefix_path(prefix, prefix_length, path_name);
 			checkout_file(p);
-			if (p != path_name)
+			if (p < path_name || p > path_name + strlen(path_name))
 				free((char *)p);
 			if (path_name != buf.buf)
 				free(path_name);

combine-diff.c

@@ -608,6 +608,7 @@ static int show_patch_diff(struct combine_diff_path *elem, int num_parent,
 	int abbrev = opt->full_index ? 40 : DEFAULT_ABBREV;
 	mmfile_t result_file;
 
+	context = opt->context;
 	/* Read the result of merge first */
 	if (!working_tree_file)
 		result = grab_blob(elem->sha1, &result_size);

commit-tree.c

@@ -91,15 +91,19 @@ int main(int argc, char **argv)
 
 	git_config(git_default_config);
 
-	if (argc < 2 || get_sha1(argv[1], tree_sha1) < 0)
+	if (argc < 2)
 		usage(commit_tree_usage);
+	if (get_sha1(argv[1], tree_sha1))
+		die("Not a valid object name %s", argv[1]);
 
 	check_valid(tree_sha1, tree_type);
 	for (i = 2; i < argc; i += 2) {
 		char *a, *b;
 		a = argv[i]; b = argv[i+1];
-		if (!b || strcmp(a, "-p") || get_sha1(b, parent_sha1[parents]))
+		if (!b || strcmp(a, "-p"))
 			usage(commit_tree_usage);
+		if (get_sha1(b, parent_sha1[parents]))
+			die("Not a valid object name %s", b);
 		check_valid(parent_sha1[parents], commit_type);
 		if (new_parent(parents))
 			parents++;

commit.c

@@ -22,25 +22,34 @@ struct sort_node
 
 const char *commit_type = "commit";
 
+struct cmt_fmt_map {
+	const char *n;
+	size_t cmp_len;
+	enum cmit_fmt v;
+} cmt_fmts[] = {
+	{ "raw",	1,	CMIT_FMT_RAW },
+	{ "medium",	1,	CMIT_FMT_MEDIUM },
+	{ "short",	1,	CMIT_FMT_SHORT },
+	{ "email",	1,	CMIT_FMT_EMAIL },
+	{ "full",	5,	CMIT_FMT_FULL },
+	{ "fuller",	5,	CMIT_FMT_FULLER },
+	{ "oneline",	1,	CMIT_FMT_ONELINE },
+};
+
 enum cmit_fmt get_commit_format(const char *arg)
 {
-	if (!*arg)
+	int i;
+
+	if (!arg || !*arg)
 		return CMIT_FMT_DEFAULT;
-	if (!strcmp(arg, "=raw"))
-		return CMIT_FMT_RAW;
-	if (!strcmp(arg, "=medium"))
-		return CMIT_FMT_MEDIUM;
-	if (!strcmp(arg, "=short"))
-		return CMIT_FMT_SHORT;
-	if (!strcmp(arg, "=full"))
-		return CMIT_FMT_FULL;
-	if (!strcmp(arg, "=fuller"))
-		return CMIT_FMT_FULLER;
-	if (!strcmp(arg, "=email"))
-		return CMIT_FMT_EMAIL;
-	if (!strcmp(arg, "=oneline"))
-		return CMIT_FMT_ONELINE;
-	die("invalid --pretty format");
+	if (*arg == '=')
+		arg++;
+	for (i = 0; i < ARRAY_SIZE(cmt_fmts); i++) {
+		if (!strncmp(arg, cmt_fmts[i].n, cmt_fmts[i].cmp_len))
+			return cmt_fmts[i].v;
+	}
+
+	die("invalid --pretty format: %s", arg);
 }
 
 static struct commit *check_commit(struct object *obj,

config.c

@@ -134,6 +134,41 @@ static int get_value(config_fn_t fn, char *name, unsigned int len)
 	return fn(name, value);
 }
 
+static int get_extended_base_var(char *name, int baselen, int c)
+{
+	do {
+		if (c == '\n')
+			return -1;
+		c = get_next_char();
+	} while (isspace(c));
+
+	/* We require the format to be '[base "extension"]' */
+	if (c != '"')
+		return -1;
+	name[baselen++] = '.';
+
+	for (;;) {
+		int c = get_next_char();
+		if (c == '\n')
+			return -1;
+		if (c == '"')
+			break;
+		if (c == '\\') {
+			c = get_next_char();
+			if (c == '\n')
+				return -1;
+		}
+		name[baselen++] = c;
+		if (baselen > MAXNAME / 2)
+			return -1;
+	}
+
+	/* Final ']' */
+	if (get_next_char() != ']')
+		return -1;
+	return baselen;
+}
+
 static int get_base_var(char *name)
 {
 	int baselen = 0;
@@ -144,6 +179,8 @@ static int get_base_var(char *name)
 			return -1;
 		if (c == ']')
 			return baselen;
+		if (isspace(c))
+			return get_extended_base_var(name, baselen, c);
 		if (!isalnum(c) && c != '.')
 			return -1;
 		if (baselen > MAXNAME / 2)
@@ -335,10 +372,12 @@ static int store_aux(const char* key, const char* value)
 			store.offset[store.seen] = ftell(config_file);
 			store.state = KEY_SEEN;
 			store.seen++;
-		} else if (strrchr(key, '.') - key == store.baselen &&
+		} else {
+			if (strrchr(key, '.') - key == store.baselen &&
 			      !strncmp(key, store.key, store.baselen)) {
 					store.state = SECTION_SEEN;
 					store.offset[store.seen] = ftell(config_file);
+			}
 		}
 	}
 	return 0;
@@ -346,8 +385,30 @@ static int store_aux(const char* key, const char* value)
 
 static void store_write_section(int fd, const char* key)
 {
+	const char *dot = strchr(key, '.');
+	int len1 = store.baselen, len2 = -1;
+
+	dot = strchr(key, '.');
+	if (dot) {
+		int dotlen = dot - key;
+		if (dotlen < len1) {
+			len2 = len1 - dotlen - 1;
+			len1 = dotlen;
+		}
+	}
+
 	write(fd, "[", 1);
-	write(fd, key, store.baselen);
+	write(fd, key, len1);
+	if (len2 >= 0) {
+		write(fd, " \"", 2);
+		while (--len2 >= 0) {
+			unsigned char c = *++dot;
+			if (c == '"')
+				write(fd, "\\", 1);
+			write(fd, &c, 1);
+		}
+		write(fd, "\"", 1);
+	}
 	write(fd, "]\n", 2);
 }
 
@@ -421,8 +482,8 @@ int git_config_set(const char* key, const char* value)
 int git_config_set_multivar(const char* key, const char* value,
 	const char* value_regex, int multi_replace)
 {
-	int i;
-	int fd, in_fd;
+	int i, dot;
+	int fd = -1, in_fd;
 	int ret;
 	char* config_filename = strdup(git_path("config"));
 	char* lock_file = strdup(git_path("config.lock"));
@@ -446,16 +507,23 @@ int git_config_set_multivar(const char* key, const char* value,
 	 * Validate the key and while at it, lower case it for matching.
 	 */
 	store.key = (char*)malloc(strlen(key)+1);
-	for (i = 0; key[i]; i++)
-		if (i != store.baselen &&
-				((!isalnum(key[i]) && key[i] != '.') ||
-				 (i == store.baselen+1 && !isalpha(key[i])))) {
-			fprintf(stderr, "invalid key: %s\n", key);
-			free(store.key);
-			ret = 1;
-			goto out_free;
-		} else
-			store.key[i] = tolower(key[i]);
+	dot = 0;
+	for (i = 0; key[i]; i++) {
+		unsigned char c = key[i];
+		if (c == '.')
+			dot = 1;
+		/* Leave the extended basename untouched.. */
+		if (!dot || i > store.baselen) {
+			if (!isalnum(c) || (i == store.baselen+1 && !isalpha(c))) {
+				fprintf(stderr, "invalid key: %s\n", key);
+				free(store.key);
+				ret = 1;
+				goto out_free;
+			}
+			c = tolower(c);
+		}
+		store.key[i] = c;
+	}
 	store.key[i] = 0;
 
 	/*
@@ -480,15 +548,11 @@ int git_config_set_multivar(const char* key, const char* value,
 		if ( ENOENT != errno ) {
 			error("opening %s: %s", config_filename,
 			      strerror(errno));
-			close(fd);
-			unlink(lock_file);
 			ret = 3; /* same as "invalid config file" */
 			goto out_free;
 		}
 		/* if nothing to unset, error out */
 		if (value == NULL) {
-			close(fd);
-			unlink(lock_file);
 			ret = 5;
 			goto out_free;
 		}
@@ -551,8 +615,6 @@ int git_config_set_multivar(const char* key, const char* value,
 		/* if nothing to unset, or too many matches, error out */
 		if ((store.seen == 0 && value == NULL) ||
 				(store.seen > 1 && multi_replace == 0)) {
-			close(fd);
-			unlink(lock_file);
 			ret = 5;
 			goto out_free;
 		}
@@ -601,8 +663,6 @@ int git_config_set_multivar(const char* key, const char* value,
 		unlink(config_filename);
 	}
 
-	close(fd);
-
 	if (rename(lock_file, config_filename) < 0) {
 		fprintf(stderr, "Could not rename the lock file?\n");
 		ret = 4;
@@ -612,10 +672,14 @@ int git_config_set_multivar(const char* key, const char* value,
 	ret = 0;
 
 out_free:
+	if (0 <= fd)
+		close(fd);
 	if (config_filename)
 		free(config_filename);
-	if (lock_file)
+	if (lock_file) {
+		unlink(lock_file);
 		free(lock_file);
+	}
 	return ret;
 }
 

contrib/remotes2config.sh

@@ -0,0 +1,35 @@
+#!/bin/sh
+
+# Use this tool to rewrite your .git/remotes/ files into the config.
+
+. git-sh-setup
+
+if [ -d "$GIT_DIR"/remotes ]; then
+	echo "Rewriting $GIT_DIR/remotes" >&2
+	error=0
+	# rewrite into config
+	{
+		cd "$GIT_DIR"/remotes
+		ls | while read f; do
+			name=$(echo -n "$f" | tr -c "A-Za-z0-9" ".")
+			sed -n \
+			-e "s/^URL: \(.*\)$/remote.$name.url \1 ./p" \
+			-e "s/^Pull: \(.*\)$/remote.$name.fetch \1 ^$ /p" \
+			-e "s/^Push: \(.*\)$/remote.$name.push \1 ^$ /p" \
+			< "$f"
+		done
+		echo done
+	} | while read key value regex; do
+		case $key in
+		done)
+			if [ $error = 0 ]; then
+				mv "$GIT_DIR"/remotes "$GIT_DIR"/remotes.old
+			fi ;;
+		*)
+			echo "git-repo-config $key "$value" $regex"
+			git-repo-config $key "$value" $regex || error=1 ;;
+		esac
+	done
+fi
+
+

convert-objects.c

@@ -321,8 +321,10 @@ int main(int argc, char **argv)
 
 	setup_git_directory();
 
-	if (argc != 2 || get_sha1(argv[1], sha1))
+	if (argc != 2)
 		usage("git-convert-objects <sha1>");
+	if (get_sha1(argv[1], sha1))
+		die("Not a valid object name %s", argv[1]);
 
 	entry = convert_entry(sha1);
 	printf("new sha1: %s\n", sha1_to_hex(entry->new_sha1));

delta.h

@@ -1,11 +1,74 @@
 #ifndef DELTA_H
 #define DELTA_H
 
-/* handling of delta buffers */
-extern void *diff_delta(const void *from_buf, unsigned long from_size,
-			const void *to_buf, unsigned long to_size,
-		        unsigned long *delta_size, unsigned long max_size);
-extern void *patch_delta(void *src_buf, unsigned long src_size,
+/* opaque object for delta index */
+struct delta_index;
+
+/*
+ * create_delta_index: compute index data from given buffer
+ *
+ * This returns a pointer to a struct delta_index that should be passed to
+ * subsequent create_delta() calls, or to free_delta_index().  A NULL pointer
+ * is returned on failure.  The given buffer must not be freed nor altered
+ * before free_delta_index() is called.  The returned pointer must be freed
+ * using free_delta_index().
+ */
+extern struct delta_index *
+create_delta_index(const void *buf, unsigned long bufsize);
+
+/*
+ * free_delta_index: free the index created by create_delta_index()
+ *
+ * Given pointer must be what create_delta_index() returned, or NULL.
+ */
+extern void free_delta_index(struct delta_index *index);
+
+/*
+ * create_delta: create a delta from given index for the given buffer
+ *
+ * This function may be called multiple times with different buffers using
+ * the same delta_index pointer.  If max_delta_size is non-zero and the
+ * resulting delta is to be larger than max_delta_size then NULL is returned.
+ * On success, a non-NULL pointer to the buffer with the delta data is
+ * returned and *delta_size is updated with its size.  The returned buffer
+ * must be freed by the caller.
+ */
+extern void *
+create_delta(const struct delta_index *index,
+	     const void *buf, unsigned long bufsize,
+	     unsigned long *delta_size, unsigned long max_delta_size);
+
+/*
+ * diff_delta: create a delta from source buffer to target buffer
+ *
+ * If max_delta_size is non-zero and the resulting delta is to be larger
+ * than max_delta_size then NULL is returned.  On success, a non-NULL
+ * pointer to the buffer with the delta data is returned and *delta_size is
+ * updated with its size.  The returned buffer must be freed by the caller.
+ */
+static inline void *
+diff_delta(const void *src_buf, unsigned long src_bufsize,
+	   const void *trg_buf, unsigned long trg_bufsize,
+	   unsigned long *delta_size, unsigned long max_delta_size)
+{
+	struct delta_index *index = create_delta_index(src_buf, src_bufsize);
+	if (index) {
+		void *delta = create_delta(index, trg_buf, trg_bufsize,
+					   delta_size, max_delta_size);
+		free_delta_index(index);
+		return delta;
+	}
+	return NULL;
+}
+
+/*
+ * patch_delta: recreate target buffer given source buffer and delta data
+ *
+ * On success, a non-NULL pointer to the target buffer is returned and
+ * *trg_bufsize is updated with its size.  On failure a NULL pointer is
+ * returned.  The returned buffer must be freed by the caller.
+ */
+extern void *patch_delta(const void *src_buf, unsigned long src_size,
 			 const void *delta_buf, unsigned long delta_size,
 			 unsigned long *dst_size);
 
@@ -14,7 +77,7 @@ extern void *patch_delta(void *src_buf, unsigned long src_size,
 
 /*
  * This must be called twice on the delta data buffer, first to get the
- * expected reference buffer size, and again to get the result buffer size.
+ * expected source buffer size, and again to get the target buffer size.
  */
 static inline unsigned long get_delta_hdr_size(const unsigned char **datap,
 					       const unsigned char *top)

describe.c

@@ -105,11 +105,11 @@ static void describe(char *arg, int last_one)
 	static int initialized = 0;
 	struct commit_name *n;
 
-	if (get_sha1(arg, sha1) < 0)
-		usage(describe_usage);
+	if (get_sha1(arg, sha1))
+		die("Not a valid object name %s", arg);
 	cmit = lookup_commit_reference(sha1);
 	if (!cmit)
-		usage(describe_usage);
+		die("%s is not a valid '%s' object", arg, commit_type);
 
 	if (!initialized) {
 		initialized = 1;

diff-delta.c

@@ -20,69 +20,187 @@
 
 #include <stdlib.h>
 #include <string.h>
-#include <zlib.h>
 #include "delta.h"
 
 
-/* block size: min = 16, max = 64k, power of 2 */
-#define BLK_SIZE 16
+/* maximum hash entry list for the same hash bucket */
+#define HASH_LIMIT 64
 
-#define MIN(a, b) ((a) < (b) ? (a) : (b))
+#define RABIN_SHIFT 23
+#define RABIN_WINDOW 16
 
-#define GR_PRIME 0x9e370001
-#define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift))
-
-struct index {
-	const unsigned char *ptr;
-	unsigned int val;
-	struct index *next;
+static const unsigned int T[256] = {
+	0x00000000, 0xab59b4d1, 0x56b369a2, 0xfdeadd73, 0x063f6795, 0xad66d344,
+	0x508c0e37, 0xfbd5bae6, 0x0c7ecf2a, 0xa7277bfb, 0x5acda688, 0xf1941259,
+	0x0a41a8bf, 0xa1181c6e, 0x5cf2c11d, 0xf7ab75cc, 0x18fd9e54, 0xb3a42a85,
+	0x4e4ef7f6, 0xe5174327, 0x1ec2f9c1, 0xb59b4d10, 0x48719063, 0xe32824b2,
+	0x1483517e, 0xbfdae5af, 0x423038dc, 0xe9698c0d, 0x12bc36eb, 0xb9e5823a,
+	0x440f5f49, 0xef56eb98, 0x31fb3ca8, 0x9aa28879, 0x6748550a, 0xcc11e1db,
+	0x37c45b3d, 0x9c9defec, 0x6177329f, 0xca2e864e, 0x3d85f382, 0x96dc4753,
+	0x6b369a20, 0xc06f2ef1, 0x3bba9417, 0x90e320c6, 0x6d09fdb5, 0xc6504964,
+	0x2906a2fc, 0x825f162d, 0x7fb5cb5e, 0xd4ec7f8f, 0x2f39c569, 0x846071b8,
+	0x798aaccb, 0xd2d3181a, 0x25786dd6, 0x8e21d907, 0x73cb0474, 0xd892b0a5,
+	0x23470a43, 0x881ebe92, 0x75f463e1, 0xdeadd730, 0x63f67950, 0xc8afcd81,
+	0x354510f2, 0x9e1ca423, 0x65c91ec5, 0xce90aa14, 0x337a7767, 0x9823c3b6,
+	0x6f88b67a, 0xc4d102ab, 0x393bdfd8, 0x92626b09, 0x69b7d1ef, 0xc2ee653e,
+	0x3f04b84d, 0x945d0c9c, 0x7b0be704, 0xd05253d5, 0x2db88ea6, 0x86e13a77,
+	0x7d348091, 0xd66d3440, 0x2b87e933, 0x80de5de2, 0x7775282e, 0xdc2c9cff,
+	0x21c6418c, 0x8a9ff55d, 0x714a4fbb, 0xda13fb6a, 0x27f92619, 0x8ca092c8,
+	0x520d45f8, 0xf954f129, 0x04be2c5a, 0xafe7988b, 0x5432226d, 0xff6b96bc,
+	0x02814bcf, 0xa9d8ff1e, 0x5e738ad2, 0xf52a3e03, 0x08c0e370, 0xa39957a1,
+	0x584ced47, 0xf3155996, 0x0eff84e5, 0xa5a63034, 0x4af0dbac, 0xe1a96f7d,
+	0x1c43b20e, 0xb71a06df, 0x4ccfbc39, 0xe79608e8, 0x1a7cd59b, 0xb125614a,
+	0x468e1486, 0xedd7a057, 0x103d7d24, 0xbb64c9f5, 0x40b17313, 0xebe8c7c2,
+	0x16021ab1, 0xbd5bae60, 0x6cb54671, 0xc7ecf2a0, 0x3a062fd3, 0x915f9b02,
+	0x6a8a21e4, 0xc1d39535, 0x3c394846, 0x9760fc97, 0x60cb895b, 0xcb923d8a,
+	0x3678e0f9, 0x9d215428, 0x66f4eece, 0xcdad5a1f, 0x3047876c, 0x9b1e33bd,
+	0x7448d825, 0xdf116cf4, 0x22fbb187, 0x89a20556, 0x7277bfb0, 0xd92e0b61,
+	0x24c4d612, 0x8f9d62c3, 0x7836170f, 0xd36fa3de, 0x2e857ead, 0x85dcca7c,
+	0x7e09709a, 0xd550c44b, 0x28ba1938, 0x83e3ade9, 0x5d4e7ad9, 0xf617ce08,
+	0x0bfd137b, 0xa0a4a7aa, 0x5b711d4c, 0xf028a99d, 0x0dc274ee, 0xa69bc03f,
+	0x5130b5f3, 0xfa690122, 0x0783dc51, 0xacda6880, 0x570fd266, 0xfc5666b7,
+	0x01bcbbc4, 0xaae50f15, 0x45b3e48d, 0xeeea505c, 0x13008d2f, 0xb85939fe,
+	0x438c8318, 0xe8d537c9, 0x153feaba, 0xbe665e6b, 0x49cd2ba7, 0xe2949f76,
+	0x1f7e4205, 0xb427f6d4, 0x4ff24c32, 0xe4abf8e3, 0x19412590, 0xb2189141,
+	0x0f433f21, 0xa41a8bf0, 0x59f05683, 0xf2a9e252, 0x097c58b4, 0xa225ec65,
+	0x5fcf3116, 0xf49685c7, 0x033df00b, 0xa86444da, 0x558e99a9, 0xfed72d78,
+	0x0502979e, 0xae5b234f, 0x53b1fe3c, 0xf8e84aed, 0x17bea175, 0xbce715a4,
+	0x410dc8d7, 0xea547c06, 0x1181c6e0, 0xbad87231, 0x4732af42, 0xec6b1b93,
+	0x1bc06e5f, 0xb099da8e, 0x4d7307fd, 0xe62ab32c, 0x1dff09ca, 0xb6a6bd1b,
+	0x4b4c6068, 0xe015d4b9, 0x3eb80389, 0x95e1b758, 0x680b6a2b, 0xc352defa,
+	0x3887641c, 0x93ded0cd, 0x6e340dbe, 0xc56db96f, 0x32c6cca3, 0x999f7872,
+	0x6475a501, 0xcf2c11d0, 0x34f9ab36, 0x9fa01fe7, 0x624ac294, 0xc9137645,
+	0x26459ddd, 0x8d1c290c, 0x70f6f47f, 0xdbaf40ae, 0x207afa48, 0x8b234e99,
+	0x76c993ea, 0xdd90273b, 0x2a3b52f7, 0x8162e626, 0x7c883b55, 0xd7d18f84,
+	0x2c043562, 0x875d81b3, 0x7ab75cc0, 0xd1eee811
 };
 
-static struct index ** delta_index(const unsigned char *buf,
-				   unsigned long bufsize,
-				   unsigned long trg_bufsize,
-				   unsigned int *hash_shift)
-{
-	unsigned int i, hsize, hshift, hlimit, entries, *hash_count;
-	const unsigned char *data;
-	struct index *entry, **hash;
-	void *mem;
+static const unsigned int U[256] = {
+	0x00000000, 0x7eb5200d, 0x5633f4cb, 0x2886d4c6, 0x073e5d47, 0x798b7d4a,
+	0x510da98c, 0x2fb88981, 0x0e7cba8e, 0x70c99a83, 0x584f4e45, 0x26fa6e48,
+	0x0942e7c9, 0x77f7c7c4, 0x5f711302, 0x21c4330f, 0x1cf9751c, 0x624c5511,
+	0x4aca81d7, 0x347fa1da, 0x1bc7285b, 0x65720856, 0x4df4dc90, 0x3341fc9d,
+	0x1285cf92, 0x6c30ef9f, 0x44b63b59, 0x3a031b54, 0x15bb92d5, 0x6b0eb2d8,
+	0x4388661e, 0x3d3d4613, 0x39f2ea38, 0x4747ca35, 0x6fc11ef3, 0x11743efe,
+	0x3eccb77f, 0x40799772, 0x68ff43b4, 0x164a63b9, 0x378e50b6, 0x493b70bb,
+	0x61bda47d, 0x1f088470, 0x30b00df1, 0x4e052dfc, 0x6683f93a, 0x1836d937,
+	0x250b9f24, 0x5bbebf29, 0x73386bef, 0x0d8d4be2, 0x2235c263, 0x5c80e26e,
+	0x740636a8, 0x0ab316a5, 0x2b7725aa, 0x55c205a7, 0x7d44d161, 0x03f1f16c,
+	0x2c4978ed, 0x52fc58e0, 0x7a7a8c26, 0x04cfac2b, 0x73e5d470, 0x0d50f47d,
+	0x25d620bb, 0x5b6300b6, 0x74db8937, 0x0a6ea93a, 0x22e87dfc, 0x5c5d5df1,
+	0x7d996efe, 0x032c4ef3, 0x2baa9a35, 0x551fba38, 0x7aa733b9, 0x041213b4,
+	0x2c94c772, 0x5221e77f, 0x6f1ca16c, 0x11a98161, 0x392f55a7, 0x479a75aa,
+	0x6822fc2b, 0x1697dc26, 0x3e1108e0, 0x40a428ed, 0x61601be2, 0x1fd53bef,
+	0x3753ef29, 0x49e6cf24, 0x665e46a5, 0x18eb66a8, 0x306db26e, 0x4ed89263,
+	0x4a173e48, 0x34a21e45, 0x1c24ca83, 0x6291ea8e, 0x4d29630f, 0x339c4302,
+	0x1b1a97c4, 0x65afb7c9, 0x446b84c6, 0x3adea4cb, 0x1258700d, 0x6ced5000,
+	0x4355d981, 0x3de0f98c, 0x15662d4a, 0x6bd30d47, 0x56ee4b54, 0x285b6b59,
+	0x00ddbf9f, 0x7e689f92, 0x51d01613, 0x2f65361e, 0x07e3e2d8, 0x7956c2d5,
+	0x5892f1da, 0x2627d1d7, 0x0ea10511, 0x7014251c, 0x5facac9d, 0x21198c90,
+	0x099f5856, 0x772a785b, 0x4c921c31, 0x32273c3c, 0x1aa1e8fa, 0x6414c8f7,
+	0x4bac4176, 0x3519617b, 0x1d9fb5bd, 0x632a95b0, 0x42eea6bf, 0x3c5b86b2,
+	0x14dd5274, 0x6a687279, 0x45d0fbf8, 0x3b65dbf5, 0x13e30f33, 0x6d562f3e,
+	0x506b692d, 0x2ede4920, 0x06589de6, 0x78edbdeb, 0x5755346a, 0x29e01467,
+	0x0166c0a1, 0x7fd3e0ac, 0x5e17d3a3, 0x20a2f3ae, 0x08242768, 0x76910765,
+	0x59298ee4, 0x279caee9, 0x0f1a7a2f, 0x71af5a22, 0x7560f609, 0x0bd5d604,
+	0x235302c2, 0x5de622cf, 0x725eab4e, 0x0ceb8b43, 0x246d5f85, 0x5ad87f88,
+	0x7b1c4c87, 0x05a96c8a, 0x2d2fb84c, 0x539a9841, 0x7c2211c0, 0x029731cd,
+	0x2a11e50b, 0x54a4c506, 0x69998315, 0x172ca318, 0x3faa77de, 0x411f57d3,
+	0x6ea7de52, 0x1012fe5f, 0x38942a99, 0x46210a94, 0x67e5399b, 0x19501996,
+	0x31d6cd50, 0x4f63ed5d, 0x60db64dc, 0x1e6e44d1, 0x36e89017, 0x485db01a,
+	0x3f77c841, 0x41c2e84c, 0x69443c8a, 0x17f11c87, 0x38499506, 0x46fcb50b,
+	0x6e7a61cd, 0x10cf41c0, 0x310b72cf, 0x4fbe52c2, 0x67388604, 0x198da609,
+	0x36352f88, 0x48800f85, 0x6006db43, 0x1eb3fb4e, 0x238ebd5d, 0x5d3b9d50,
+	0x75bd4996, 0x0b08699b, 0x24b0e01a, 0x5a05c017, 0x728314d1, 0x0c3634dc,
+	0x2df207d3, 0x534727de, 0x7bc1f318, 0x0574d315, 0x2acc5a94, 0x54797a99,
+	0x7cffae5f, 0x024a8e52, 0x06852279, 0x78300274, 0x50b6d6b2, 0x2e03f6bf,
+	0x01bb7f3e, 0x7f0e5f33, 0x57888bf5, 0x293dabf8, 0x08f998f7, 0x764cb8fa,
+	0x5eca6c3c, 0x207f4c31, 0x0fc7c5b0, 0x7172e5bd, 0x59f4317b, 0x27411176,
+	0x1a7c5765, 0x64c97768, 0x4c4fa3ae, 0x32fa83a3, 0x1d420a22, 0x63f72a2f,
+	0x4b71fee9, 0x35c4dee4, 0x1400edeb, 0x6ab5cde6, 0x42331920, 0x3c86392d,
+	0x133eb0ac, 0x6d8b90a1, 0x450d4467, 0x3bb8646a
+};
 
-	/* determine index hash size */
-	entries = bufsize  / BLK_SIZE;
+struct index_entry {
+	const unsigned char *ptr;
+	unsigned int val;
+	struct index_entry *next;
+};
+
+struct delta_index {
+	const void *src_buf;
+	unsigned long src_size;
+	unsigned int hash_mask;
+	struct index_entry *hash[0];
+};
+
+struct delta_index * create_delta_index(const void *buf, unsigned long bufsize)
+{
+	unsigned int i, hsize, hmask, entries, prev_val, *hash_count;
+	const unsigned char *data, *buffer = buf;
+	struct delta_index *index;
+	struct index_entry *entry, **hash;
+	void *mem;
+	unsigned long memsize;
+
+	if (!buf || !bufsize)
+		return NULL;
+
+	/* Determine index hash size.  Note that indexing skips the
+	   first byte to allow for optimizing the rabin polynomial
+	   initialization in create_delta(). */
+	entries = (bufsize - 1)  / RABIN_WINDOW;
 	hsize = entries / 4;
 	for (i = 4; (1 << i) < hsize && i < 31; i++);
 	hsize = 1 << i;
-	hshift = 32 - i;
-	*hash_shift = hshift;
+	hmask = hsize - 1;
 
 	/* allocate lookup index */
-	mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry));
+	memsize = sizeof(*index) +
+		  sizeof(*hash) * hsize +
+		  sizeof(*entry) * entries;
+	mem = malloc(memsize);
 	if (!mem)
 		return NULL;
+	index = mem;
+	mem = index + 1;
 	hash = mem;
-	entry = mem + hsize * sizeof(*hash);
+	mem = hash + hsize;
+	entry = mem;
+
+	index->src_buf = buf;
+	index->src_size = bufsize;
+	index->hash_mask = hmask;
 	memset(hash, 0, hsize * sizeof(*hash));
 
 	/* allocate an array to count hash entries */
 	hash_count = calloc(hsize, sizeof(*hash_count));
 	if (!hash_count) {
-		free(hash);
+		free(index);
 		return NULL;
 	}
 
 	/* then populate the index */
-	data = buf + entries * BLK_SIZE - BLK_SIZE;
-	while (data >= buf) {
-		unsigned int val = adler32(0, data, BLK_SIZE);
-		i = HASH(val, hshift);
-		entry->ptr = data;
-		entry->val = val;
-		entry->next = hash[i];
-		hash[i] = entry++;
-		hash_count[i]++;
-		data -= BLK_SIZE;
- 	}
+	prev_val = ~0;
+	for (data = buffer + entries * RABIN_WINDOW - RABIN_WINDOW;
+	     data >= buffer;
+	     data -= RABIN_WINDOW) {
+		unsigned int val = 0;
+		for (i = 1; i <= RABIN_WINDOW; i++)
+			val = ((val << 8) | data[i]) ^ T[val >> RABIN_SHIFT];
+		if (val == prev_val) {
+			/* keep the lowest of consecutive identical blocks */
+			entry[-1].ptr = data + RABIN_WINDOW;
+		} else {
+			prev_val = val;
+			i = val & hmask;
+			entry->ptr = data + RABIN_WINDOW;
+			entry->val = val;
+			entry->next = hash[i];
+			hash[i] = entry++;
+			hash_count[i]++;
+		}
+	}
 
 	/*
 	 * Determine a limit on the number of entries in the same hash
@@ -91,27 +209,18 @@ static struct index ** delta_index(const unsigned char *buf,
 	 * bucket that would bring us to O(m*n) computing costs (m and n
 	 * corresponding to reference and target buffer sizes).
 	 *
-	 * The more the target buffer is large, the more it is important to
-	 * have small entry lists for each hash buckets.  With such a limit
-	 * the cost is bounded to something more like O(m+n).
-	 */
-	hlimit = (1 << 26) / trg_bufsize;
-	if (hlimit < 4*BLK_SIZE)
-		hlimit = 4*BLK_SIZE;
-
-	/*
-	 * Now make sure none of the hash buckets has more entries than
+	 * Make sure none of the hash buckets has more entries than
 	 * we're willing to test.  Otherwise we cull the entry list
 	 * uniformly to still preserve a good repartition across
 	 * the reference buffer.
 	 */
 	for (i = 0; i < hsize; i++) {
-		if (hash_count[i] < hlimit)
+		if (hash_count[i] < HASH_LIMIT)
 			continue;
 		entry = hash[i];
 		do {
-			struct index *keep = entry;
-			int skip = hash_count[i] / hlimit / 2;
+			struct index_entry *keep = entry;
+			int skip = hash_count[i] / HASH_LIMIT / 2;
 			do {
 				entry = entry->next;
 			} while(--skip && entry);
@@ -120,32 +229,31 @@ static struct index ** delta_index(const unsigned char *buf,
 	}
 	free(hash_count);
 
-	return hash;
+	return index;
 }
 
-/* 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(const void *from_buf, unsigned long from_size,
-		 const void *to_buf, unsigned long to_size,
-		 unsigned long *delta_size,
-		 unsigned long max_size)
+void free_delta_index(struct delta_index *index)
 {
-	unsigned int i, outpos, outsize, hash_shift;
+	free(index);
+}
+
+/*
+ * The maximum size for any opcode sequence, including the initial header
+ * plus rabin window plus biggest copy.
+ */
+#define MAX_OP_SIZE	(5 + 5 + 1 + RABIN_WINDOW + 7)
+
+void *
+create_delta(const struct delta_index *index,
+	     const void *trg_buf, unsigned long trg_size,
+	     unsigned long *delta_size, unsigned long max_size)
+{
+	unsigned int i, outpos, outsize, val;
 	int inscnt;
 	const unsigned char *ref_data, *ref_top, *data, *top;
 	unsigned char *out;
-	struct index *entry, **hash;
 
-	if (!from_size || !to_size)
-		return NULL;
-	hash = delta_index(from_buf, from_size, to_size, &hash_shift);
-	if (!hash)
+	if (!trg_buf || !trg_size)
 		return NULL;
 
 	outpos = 0;
@@ -153,64 +261,66 @@ void *diff_delta(const void *from_buf, unsigned long from_size,
 	if (max_size && outsize >= max_size)
 		outsize = max_size + MAX_OP_SIZE + 1;
 	out = malloc(outsize);
-	if (!out) {
-		free(hash);
+	if (!out)
 		return NULL;
-	}
-
-	ref_data = from_buf;
-	ref_top = from_buf + from_size;
-	data = to_buf;
-	top = to_buf + to_size;
 
 	/* store reference buffer size */
-	out[outpos++] = from_size;
-	from_size >>= 7;
-	while (from_size) {
-		out[outpos - 1] |= 0x80;
-		out[outpos++] = from_size;
-		from_size >>= 7;
+	i = index->src_size;
+	while (i >= 0x80) {
+		out[outpos++] = i | 0x80;
+		i >>= 7;
 	}
+	out[outpos++] = i;
 
 	/* store target buffer size */
-	out[outpos++] = to_size;
-	to_size >>= 7;
-	while (to_size) {
-		out[outpos - 1] |= 0x80;
-		out[outpos++] = to_size;
-		to_size >>= 7;
+	i = trg_size;
+	while (i >= 0x80) {
+		out[outpos++] = i | 0x80;
+		i >>= 7;
 	}
+	out[outpos++] = i;
 
-	inscnt = 0;
+	ref_data = index->src_buf;
+	ref_top = ref_data + index->src_size;
+	data = trg_buf;
+	top = trg_buf + trg_size;
+
+	outpos++;
+	val = 0;
+	for (i = 0; i < RABIN_WINDOW && data < top; i++, data++) {
+		out[outpos++] = *data;
+		val = ((val << 8) | *data) ^ T[val >> RABIN_SHIFT];
+	}
+	inscnt = i;
 
 	while (data < top) {
 		unsigned int moff = 0, msize = 0;
-		if (data + BLK_SIZE <= top) {
-			unsigned int val = adler32(0, data, BLK_SIZE);
-			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;
-				if (ref_size > 0x10000)
-					ref_size = 0x10000;
-				if (ref_size <= msize)
-					break;
-				while (ref_size-- && *src++ == *ref)
-					ref++;
-				if (msize < ref - entry->ptr) {
-					/* this is our best match so far */
-					msize = ref - entry->ptr;
-					moff = entry->ptr - ref_data;
-				}
+		struct index_entry *entry;
+		val ^= U[data[-RABIN_WINDOW]];
+		val = ((val << 8) | *data) ^ T[val >> RABIN_SHIFT];
+		i = val & index->hash_mask;
+		for (entry = index->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;
+			if (ref_size > 0x10000)
+				ref_size = 0x10000;
+			if (ref_size <= msize)
+				break;
+			while (ref_size-- && *src++ == *ref)
+				ref++;
+			if (msize < ref - entry->ptr) {
+				/* this is our best match so far */
+				msize = ref - entry->ptr;
+				moff = entry->ptr - ref_data;
 			}
 		}
 
-		if (!msize || msize < COPYOP_SIZE(moff, msize)) {
+		if (msize < 4) {
 			if (!inscnt)
 				outpos++;
 			out[outpos++] = *data++;
@@ -222,6 +332,20 @@ void *diff_delta(const void *from_buf, unsigned long from_size,
 		} else {
 			unsigned char *op;
 
+			if (msize >= RABIN_WINDOW) {
+				const unsigned char *sk;
+				sk = data + msize - RABIN_WINDOW;
+				val = 0;
+				for (i = 0; i < RABIN_WINDOW; i++)
+					val = ((val << 8) | *sk++) ^ T[val >> RABIN_SHIFT];
+			} else {
+				const unsigned char *sk = data + 1;
+				for (i = 1; i < msize; i++) {
+					val ^= U[sk[-RABIN_WINDOW]];
+					val = ((val << 8) | *sk++) ^ T[val >> RABIN_SHIFT];
+				}
+			}
+
 			if (inscnt) {
 				while (moff && ref_data[moff-1] == data[-1]) {
 					if (msize == 0x10000)
@@ -266,12 +390,10 @@ void *diff_delta(const void *from_buf, unsigned long from_size,
 			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);
+				break;
+			out = realloc(out, outsize);
 			if (!out) {
 				free(tmp);
-				free(hash);
 				return NULL;
 			}
 		}
@@ -280,7 +402,11 @@ void *diff_delta(const void *from_buf, unsigned long from_size,
 	if (inscnt)
 		out[outpos - inscnt - 1] = inscnt;
 
-	free(hash);
+	if (max_size && outpos > max_size) {
+		free(out);
+		return NULL;
+	}
+
 	*delta_size = outpos;
 	return out;
 }

diff-tree.c

@@ -138,7 +138,10 @@ int main(int argc, const char **argv)
 		opt->diffopt.setup |= (DIFF_SETUP_USE_SIZE_CACHE |
 				       DIFF_SETUP_USE_CACHE);
 	while (fgets(line, sizeof(line), stdin))
-		diff_tree_stdin(line);
+		if (line[0] == '\n')
+			fflush(stdout);
+		else
+			diff_tree_stdin(line);
 
 	return 0;
 }

diff.c

@@ -8,6 +8,7 @@
 #include "quote.h"
 #include "diff.h"
 #include "diffcore.h"
+#include "delta.h"
 #include "xdiff-interface.h"
 
 static int use_size_cache;
@@ -231,11 +232,16 @@ static char *pprint_rename(const char *a, const char *b)
 	 * name-a => name-b
 	 */
 	if (pfx_length + sfx_length) {
+		int a_midlen = len_a - pfx_length - sfx_length;
+		int b_midlen = len_b - pfx_length - sfx_length;
+		if (a_midlen < 0) a_midlen = 0;
+		if (b_midlen < 0) b_midlen = 0;
+
 		name = xmalloc(len_a + len_b - pfx_length - sfx_length + 7);
 		sprintf(name, "%.*s{%.*s => %.*s}%s",
 			pfx_length, a,
-			len_a - pfx_length - sfx_length, a + pfx_length,
-			len_b - pfx_length - sfx_length, b + pfx_length,
+			a_midlen, a + pfx_length,
+			b_midlen, b + pfx_length,
 			a + len_a - sfx_length);
 	}
 	else {
@@ -296,7 +302,6 @@ static const char minuses[]= "--------------------------------------------------
 
 static void show_stats(struct diffstat_t* data)
 {
-	char *prefix = "";
 	int i, len, add, del, total, adds = 0, dels = 0;
 	int max, max_change = 0, max_len = 0;
 	int total_files = data->nr;
@@ -318,6 +323,7 @@ static void show_stats(struct diffstat_t* data)
 	}
 
 	for (i = 0; i < data->nr; i++) {
+		char *prefix = "";
 		char *name = data->files[i]->name;
 		int added = data->files[i]->added;
 		int deleted = data->files[i]->deleted;
@@ -391,6 +397,130 @@ static void show_stats(struct diffstat_t* data)
 			total_files, adds, dels);
 }
 
+struct checkdiff_t {
+	struct xdiff_emit_state xm;
+	const char *filename;
+	int lineno;
+};
+
+static void checkdiff_consume(void *priv, char *line, unsigned long len)
+{
+	struct checkdiff_t *data = priv;
+
+	if (line[0] == '+') {
+		int i, spaces = 0;
+
+		data->lineno++;
+
+		/* check space before tab */
+		for (i = 1; i < len && (line[i] == ' ' || line[i] == '\t'); i++)
+			if (line[i] == ' ')
+				spaces++;
+		if (line[i - 1] == '\t' && spaces)
+			printf("%s:%d: space before tab:%.*s\n",
+				data->filename, data->lineno, (int)len, line);
+
+		/* check white space at line end */
+		if (line[len - 1] == '\n')
+			len--;
+		if (isspace(line[len - 1]))
+			printf("%s:%d: white space at end: %.*s\n",
+				data->filename, data->lineno, (int)len, line);
+	} else if (line[0] == ' ')
+		data->lineno++;
+	else if (line[0] == '@') {
+		char *plus = strchr(line, '+');
+		if (plus)
+			data->lineno = strtol(plus, line + len, 10);
+		else
+			die("invalid diff");
+	}
+}
+
+static unsigned char *deflate_it(char *data,
+				 unsigned long size,
+				 unsigned long *result_size)
+{
+	int bound;
+	unsigned char *deflated;
+	z_stream stream;
+
+	memset(&stream, 0, sizeof(stream));
+	deflateInit(&stream, Z_BEST_COMPRESSION);
+	bound = deflateBound(&stream, size);
+	deflated = xmalloc(bound);
+	stream.next_out = deflated;
+	stream.avail_out = bound;
+
+	stream.next_in = (unsigned char *)data;
+	stream.avail_in = size;
+	while (deflate(&stream, Z_FINISH) == Z_OK)
+		; /* nothing */
+	deflateEnd(&stream);
+	*result_size = stream.total_out;
+	return deflated;
+}
+
+static void emit_binary_diff(mmfile_t *one, mmfile_t *two)
+{
+	void *cp;
+	void *delta;
+	void *deflated;
+	void *data;
+	unsigned long orig_size;
+	unsigned long delta_size;
+	unsigned long deflate_size;
+	unsigned long data_size;
+
+	printf("GIT binary patch\n");
+	/* We could do deflated delta, or we could do just deflated two,
+	 * whichever is smaller.
+	 */
+	delta = NULL;
+	deflated = deflate_it(two->ptr, two->size, &deflate_size);
+	if (one->size && two->size) {
+		delta = diff_delta(one->ptr, one->size,
+				   two->ptr, two->size,
+				   &delta_size, deflate_size);
+		if (delta) {
+			void *to_free = delta;
+			orig_size = delta_size;
+			delta = deflate_it(delta, delta_size, &delta_size);
+			free(to_free);
+		}
+	}
+
+	if (delta && delta_size < deflate_size) {
+		printf("delta %lu\n", orig_size);
+		free(deflated);
+		data = delta;
+		data_size = delta_size;
+	}
+	else {
+		printf("literal %lu\n", two->size);
+		free(delta);
+		data = deflated;
+		data_size = deflate_size;
+	}
+
+	/* emit data encoded in base85 */
+	cp = data;
+	while (data_size) {
+		int bytes = (52 < data_size) ? 52 : data_size;
+		char line[70];
+		data_size -= bytes;
+		if (bytes <= 26)
+			line[0] = bytes + 'A' - 1;
+		else
+			line[0] = bytes - 26 + 'a' - 1;
+		encode_85(line + 1, cp, bytes);
+		cp += bytes;
+		puts(line);
+	}
+	printf("\n");
+	free(data);
+}
+
 #define FIRST_FEW_BYTES 8000
 static int mmfile_is_binary(mmfile_t *mf)
 {
@@ -407,6 +537,7 @@ static void builtin_diff(const char *name_a,
 			 struct diff_filespec *one,
 			 struct diff_filespec *two,
 			 const char *xfrm_msg,
+			 struct diff_options *o,
 			 int complete_rewrite)
 {
 	mmfile_t mf1, mf2;
@@ -451,8 +582,17 @@ static void builtin_diff(const char *name_a,
 	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
 		die("unable to read files to diff");
 
-	if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2))
-		printf("Binary files %s and %s differ\n", lbl[0], lbl[1]);
+	if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2)) {
+		/* Quite common confusing case */
+		if (mf1.size == mf2.size &&
+		    !memcmp(mf1.ptr, mf2.ptr, mf1.size))
+			goto free_ab_and_return;
+		if (o->binary)
+			emit_binary_diff(&mf1, &mf2);
+		else
+			printf("Binary files %s and %s differ\n",
+			       lbl[0], lbl[1]);
+	}
 	else {
 		/* Crazy xdl interfaces.. */
 		const char *diffopts = getenv("GIT_DIFF_OPTS");
@@ -463,7 +603,7 @@ static void builtin_diff(const char *name_a,
 
 		ecbdata.label_path = lbl;
 		xpp.flags = XDF_NEED_MINIMAL;
-		xecfg.ctxlen = 3;
+		xecfg.ctxlen = o->context;
 		xecfg.flags = XDL_EMIT_FUNCNAMES;
 		if (!diffopts)
 			;
@@ -524,6 +664,41 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 	}
 }
 
+static void builtin_checkdiff(const char *name_a, const char *name_b,
+			     struct diff_filespec *one,
+			     struct diff_filespec *two)
+{
+	mmfile_t mf1, mf2;
+	struct checkdiff_t data;
+
+	if (!two)
+		return;
+
+	memset(&data, 0, sizeof(data));
+	data.xm.consume = checkdiff_consume;
+	data.filename = name_b ? name_b : name_a;
+	data.lineno = 0;
+
+	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
+		die("unable to read files to diff");
+
+	if (mmfile_is_binary(&mf2))
+		return;
+	else {
+		/* Crazy xdl interfaces.. */
+		xpparam_t xpp;
+		xdemitconf_t xecfg;
+		xdemitcb_t ecb;
+
+		xpp.flags = XDF_NEED_MINIMAL;
+		xecfg.ctxlen = 0;
+		xecfg.flags = 0;
+		ecb.outf = xdiff_outf;
+		ecb.priv = &data;
+		xdl_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
+	}
+}
+
 struct diff_filespec *alloc_filespec(const char *path)
 {
 	int namelen = strlen(path);
@@ -928,6 +1103,7 @@ static void run_diff_cmd(const char *pgm,
 			 struct diff_filespec *one,
 			 struct diff_filespec *two,
 			 const char *xfrm_msg,
+			 struct diff_options *o,
 			 int complete_rewrite)
 {
 	if (pgm) {
@@ -937,7 +1113,7 @@ static void run_diff_cmd(const char *pgm,
 	}
 	if (one && two)
 		builtin_diff(name, other ? other : name,
-			     one, two, xfrm_msg, complete_rewrite);
+			     one, two, xfrm_msg, o, complete_rewrite);
 	else
 		printf("* Unmerged path %s\n", name);
 }
@@ -971,7 +1147,7 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o)
 
 	if (DIFF_PAIR_UNMERGED(p)) {
 		/* unmerged */
-		run_diff_cmd(pgm, p->one->path, NULL, NULL, NULL, NULL, 0);
+		run_diff_cmd(pgm, p->one->path, NULL, NULL, NULL, NULL, o, 0);
 		return;
 	}
 
@@ -1041,14 +1217,14 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o)
 		 * needs to be split into deletion and creation.
 		 */
 		struct diff_filespec *null = alloc_filespec(two->path);
-		run_diff_cmd(NULL, name, other, one, null, xfrm_msg, 0);
+		run_diff_cmd(NULL, name, other, one, null, xfrm_msg, o, 0);
 		free(null);
 		null = alloc_filespec(one->path);
-		run_diff_cmd(NULL, name, other, null, two, xfrm_msg, 0);
+		run_diff_cmd(NULL, name, other, null, two, xfrm_msg, o, 0);
 		free(null);
 	}
 	else
-		run_diff_cmd(pgm, name, other, one, two, xfrm_msg,
+		run_diff_cmd(pgm, name, other, one, two, xfrm_msg, o,
 			     complete_rewrite);
 
 	free(name_munged);
@@ -1079,6 +1255,25 @@ static void run_diffstat(struct diff_filepair *p, struct diff_options *o,
 	builtin_diffstat(name, other, p->one, p->two, diffstat, complete_rewrite);
 }
 
+static void run_checkdiff(struct diff_filepair *p, struct diff_options *o)
+{
+	const char *name;
+	const char *other;
+
+	if (DIFF_PAIR_UNMERGED(p)) {
+		/* unmerged */
+		return;
+	}
+
+	name = p->one->path;
+	other = (strcmp(name, p->two->path) ? p->two->path : NULL);
+
+	diff_fill_sha1_info(p->one);
+	diff_fill_sha1_info(p->two);
+
+	builtin_checkdiff(name, other, p->one, p->two);
+}
+
 void diff_setup(struct diff_options *options)
 {
 	memset(options, 0, sizeof(*options));
@@ -1086,6 +1281,7 @@ void diff_setup(struct diff_options *options)
 	options->line_termination = '\n';
 	options->break_opt = -1;
 	options->rename_limit = -1;
+	options->context = 3;
 
 	options->change = diff_change;
 	options->add_remove = diff_addremove;
@@ -1103,7 +1299,8 @@ int diff_setup_done(struct diff_options *options)
 	 * recursive bits for other formats here.
 	 */
 	if ((options->output_format == DIFF_FORMAT_PATCH) ||
-	    (options->output_format == DIFF_FORMAT_DIFFSTAT))
+	    (options->output_format == DIFF_FORMAT_DIFFSTAT) ||
+	    (options->output_format == DIFF_FORMAT_CHECKDIFF))
 		options->recursive = 1;
 
 	if (options->detect_rename && options->rename_limit < 0)
@@ -1126,17 +1323,70 @@ int diff_setup_done(struct diff_options *options)
 	return 0;
 }
 
+int opt_arg(const char *arg, int arg_short, const char *arg_long, int *val)
+{
+	char c, *eq;
+	int len;
+
+	if (*arg != '-')
+		return 0;
+	c = *++arg;
+	if (!c)
+		return 0;
+	if (c == arg_short) {
+		c = *++arg;
+		if (!c)
+			return 1;
+		if (val && isdigit(c)) {
+			char *end;
+			int n = strtoul(arg, &end, 10);
+			if (*end)
+				return 0;
+			*val = n;
+			return 1;
+		}
+		return 0;
+	}
+	if (c != '-')
+		return 0;
+	arg++;
+	eq = strchr(arg, '=');
+	if (eq)
+		len = eq - arg;
+	else
+		len = strlen(arg);
+	if (!len || strncmp(arg, arg_long, len))
+		return 0;
+	if (eq) {
+		int n;
+		char *end;
+		if (!isdigit(*++eq))
+			return 0;
+		n = strtoul(eq, &end, 10);
+		if (*end)
+			return 0;
+		*val = n;
+	}
+	return 1;
+}
+
 int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 {
 	const char *arg = av[0];
 	if (!strcmp(arg, "-p") || !strcmp(arg, "-u"))
 		options->output_format = DIFF_FORMAT_PATCH;
+	else if (opt_arg(arg, 'U', "unified", &options->context))
+		options->output_format = DIFF_FORMAT_PATCH;
 	else if (!strcmp(arg, "--patch-with-raw")) {
 		options->output_format = DIFF_FORMAT_PATCH;
 		options->with_raw = 1;
 	}
 	else if (!strcmp(arg, "--stat"))
 		options->output_format = DIFF_FORMAT_DIFFSTAT;
+	else if (!strcmp(arg, "--check"))
+		options->output_format = DIFF_FORMAT_CHECKDIFF;
+	else if (!strcmp(arg, "--summary"))
+		options->summary = 1;
 	else if (!strcmp(arg, "--patch-with-stat")) {
 		options->output_format = DIFF_FORMAT_PATCH;
 		options->with_stat = 1;
@@ -1147,6 +1397,10 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		options->rename_limit = strtoul(arg+2, NULL, 10);
 	else if (!strcmp(arg, "--full-index"))
 		options->full_index = 1;
+	else if (!strcmp(arg, "--binary")) {
+		options->output_format = DIFF_FORMAT_PATCH;
+		options->full_index = options->binary = 1;
+	}
 	else if (!strcmp(arg, "--name-only"))
 		options->output_format = DIFF_FORMAT_NAME;
 	else if (!strcmp(arg, "--name-status"))
@@ -1453,6 +1707,19 @@ static void diff_flush_stat(struct diff_filepair *p, struct diff_options *o,
 	run_diffstat(p, o, diffstat);
 }
 
+static void diff_flush_checkdiff(struct diff_filepair *p,
+		struct diff_options *o)
+{
+	if (diff_unmodified_pair(p))
+		return;
+
+	if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
+	    (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
+		return; /* no tree diffs in patch format */
+
+	run_checkdiff(p, o);
+}
+
 int diff_queue_is_empty(void)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
@@ -1583,6 +1850,9 @@ static void flush_one_pair(struct diff_filepair *p,
 		case DIFF_FORMAT_DIFFSTAT:
 			diff_flush_stat(p, options, diffstat);
 			break;
+		case DIFF_FORMAT_CHECKDIFF:
+			diff_flush_checkdiff(p, options);
+			break;
 		case DIFF_FORMAT_PATCH:
 			diff_flush_patch(p, options);
 			break;
@@ -1603,6 +1873,85 @@ static void flush_one_pair(struct diff_filepair *p,
 	}
 }
 
+static void show_file_mode_name(const char *newdelete, struct diff_filespec *fs)
+{
+	if (fs->mode)
+		printf(" %s mode %06o %s\n", newdelete, fs->mode, fs->path);
+	else
+		printf(" %s %s\n", newdelete, fs->path);
+}
+
+
+static void show_mode_change(struct diff_filepair *p, int show_name)
+{
+	if (p->one->mode && p->two->mode && p->one->mode != p->two->mode) {
+		if (show_name)
+			printf(" mode change %06o => %06o %s\n",
+			       p->one->mode, p->two->mode, p->two->path);
+		else
+			printf(" mode change %06o => %06o\n",
+			       p->one->mode, p->two->mode);
+	}
+}
+
+static void show_rename_copy(const char *renamecopy, struct diff_filepair *p)
+{
+	const char *old, *new;
+
+	/* Find common prefix */
+	old = p->one->path;
+	new = p->two->path;
+	while (1) {
+		const char *slash_old, *slash_new;
+		slash_old = strchr(old, '/');
+		slash_new = strchr(new, '/');
+		if (!slash_old ||
+		    !slash_new ||
+		    slash_old - old != slash_new - new ||
+		    memcmp(old, new, slash_new - new))
+			break;
+		old = slash_old + 1;
+		new = slash_new + 1;
+	}
+	/* p->one->path thru old is the common prefix, and old and new
+	 * through the end of names are renames
+	 */
+	if (old != p->one->path)
+		printf(" %s %.*s{%s => %s} (%d%%)\n", renamecopy,
+		       (int)(old - p->one->path), p->one->path,
+		       old, new, (int)(0.5 + p->score * 100.0/MAX_SCORE));
+	else
+		printf(" %s %s => %s (%d%%)\n", renamecopy,
+		       p->one->path, p->two->path,
+		       (int)(0.5 + p->score * 100.0/MAX_SCORE));
+	show_mode_change(p, 0);
+}
+
+static void diff_summary(struct diff_filepair *p)
+{
+	switch(p->status) {
+	case DIFF_STATUS_DELETED:
+		show_file_mode_name("delete", p->one);
+		break;
+	case DIFF_STATUS_ADDED:
+		show_file_mode_name("create", p->two);
+		break;
+	case DIFF_STATUS_COPIED:
+		show_rename_copy("copy", p);
+		break;
+	case DIFF_STATUS_RENAMED:
+		show_rename_copy("rename", p);
+		break;
+	default:
+		if (p->score) {
+			printf(" rewrite %s (%d%%)\n", p->two->path,
+				(int)(0.5 + p->score * 100.0/MAX_SCORE));
+			show_mode_change(p, 0);
+		} else	show_mode_change(p, 1);
+		break;
+	}
+}
+
 void diff_flush(struct diff_options *options)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
@@ -1636,7 +1985,6 @@ void diff_flush(struct diff_options *options)
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
 		flush_one_pair(p, diff_output_format, options, diffstat);
-		diff_free_filepair(p);
 	}
 
 	if (diffstat) {
@@ -1644,6 +1992,12 @@ void diff_flush(struct diff_options *options)
 		free(diffstat);
 	}
 
+	for (i = 0; i < q->nr; i++) {
+		if (options->summary)
+			diff_summary(q->queue[i]);
+		diff_free_filepair(q->queue[i]);
+	}
+
 	free(q->queue);
 	q->queue = NULL;
 	q->nr = q->alloc = 0;

diff.h

@@ -28,9 +28,12 @@ struct diff_options {
 		 with_raw:1,
 		 with_stat:1,
 		 tree_in_recursive:1,
+		 binary:1,
 		 full_index:1,
 		 silent_on_remove:1,
-		 find_copies_harder:1;
+		 find_copies_harder:1,
+		 summary:1;
+	int context;
 	int break_opt;
 	int detect_rename;
 	int line_termination;
@@ -150,6 +153,7 @@ extern int diff_queue_is_empty(void);
 #define DIFF_FORMAT_NAME	4
 #define DIFF_FORMAT_NAME_STATUS	5
 #define DIFF_FORMAT_DIFFSTAT	6
+#define DIFF_FORMAT_CHECKDIFF	7
 
 extern void diff_flush(struct diff_options*);
 

git-am.sh

@@ -15,6 +15,10 @@ stop_here () {
 }
 
 stop_here_user_resolve () {
+    if [ -n "$resolvemsg" ]; then
+	    echo "$resolvemsg"
+	    stop_here $1
+    fi
     cmdline=$(basename $0)
     if test '' != "$interactive"
     then
@@ -55,46 +59,12 @@ fall_back_3way () {
 	GIT_INDEX_FILE="$dotest/patch-merge-tmp-index" \
 	git-write-tree >"$dotest/patch-merge-base+" &&
 	# index has the base tree now.
-	(
-	    cd "$dotest/patch-merge-tmp-dir" &&
-	    GIT_INDEX_FILE="../patch-merge-tmp-index" \
-	    GIT_OBJECT_DIRECTORY="$O_OBJECT" \
-	    git-apply $binary --index <../patch
-        )
+	GIT_INDEX_FILE="$dotest/patch-merge-tmp-index" \
+	git-apply $binary --cached <"$dotest/patch"
     then
 	echo Using index info to reconstruct a base tree...
 	mv "$dotest/patch-merge-base+" "$dotest/patch-merge-base"
 	mv "$dotest/patch-merge-tmp-index" "$dotest/patch-merge-index"
-    else
-	# Otherwise, try nearby trees that can be used to apply the
-	# patch.
-	(
-	    N=10
-
-	    # Hoping the patch is against our recent commits...
-	    git-rev-list --max-count=$N HEAD
-
-	    # or hoping the patch is against known tags...
-	    git-ls-remote --tags .
-	) |
-	while read base junk
-	do
-	    # See if we have it as a tree...
-	    git-cat-file tree "$base" >/dev/null 2>&1 || continue
-
-	    rm -fr "$dotest"/patch-merge-* &&
-	    mkdir "$dotest/patch-merge-tmp-dir" || break
-	    (
-		cd "$dotest/patch-merge-tmp-dir" &&
-		GIT_INDEX_FILE=../patch-merge-tmp-index &&
-		GIT_OBJECT_DIRECTORY="$O_OBJECT" &&
-		export GIT_INDEX_FILE GIT_OBJECT_DIRECTORY &&
-		git-read-tree "$base" &&
-		git-apply $binary --index &&
-		mv ../patch-merge-tmp-index ../patch-merge-index &&
-		echo "$base" >../patch-merge-base
-	    ) <"$dotest/patch"  2>/dev/null && break
-	done
     fi
 
     test -f "$dotest/patch-merge-index" &&
@@ -121,7 +91,7 @@ fall_back_3way () {
 }
 
 prec=4
-dotest=.dotest sign= utf8= keep= skip= interactive= resolved= binary= ws=
+dotest=.dotest sign= utf8= keep= skip= interactive= resolved= binary= ws= resolvemsg=
 
 while case "$#" in 0) break;; esac
 do
@@ -157,6 +127,9 @@ do
 	--whitespace=*)
 	ws=$1; shift ;;
 
+	--resolvemsg=*)
+	resolvemsg=$(echo "$1" | sed -e "s/^--resolvemsg=//"); shift ;;
+
 	--)
 	shift; break ;;
 	-*)
@@ -185,7 +158,7 @@ then
 else
 	# Make sure we are not given --skip nor --resolved
 	test ",$skip,$resolved," = ,,, ||
-		die "we are not resuming."
+		die "Resolve operation not in progress, we are not resuming."
 
 	# Start afresh.
 	mkdir -p "$dotest" || exit

git-branch.sh

@@ -82,8 +82,7 @@ done
 
 case "$#" in
 0)
-	git-rev-parse --symbolic --all |
-	sed -ne 's|^refs/heads/||p' |
+	git-rev-parse --symbolic --branches |
 	sort |
 	while read ref
 	do

git-checkout.sh

@@ -144,7 +144,7 @@ else
 	work=`git write-tree` &&
 	git read-tree --reset $new &&
 	git checkout-index -f -u -q -a &&
-	git read-tree -m -u $old $new $work || exit
+	git read-tree -m -u --aggressive $old $new $work || exit
 
 	if result=`git write-tree 2>/dev/null`
 	then

git-clean.sh

@@ -3,13 +3,15 @@
 # Copyright (c) 2005-2006 Pavel Roskin
 #
 
-USAGE="[-d] [-n] [-q] [-x | -X]"
+USAGE="[-d] [-n] [-q] [-x | -X] [--] <paths>..."
 LONG_USAGE='Clean untracked files from the working directory
 	-d	remove directories as well
 	-n 	don'\''t remove anything, just show what would be done
 	-q	be quiet, only report errors
 	-x	remove ignored files as well
-	-X	remove only ignored files as well'
+	-X	remove only ignored files
+When optional <paths>... arguments are given, the paths
+affected are further limited to those that match them.'
 SUBDIRECTORY_OK=Yes
 . git-sh-setup
 
@@ -44,8 +46,15 @@ do
 	-X)
 		ignoredonly=1
 		;;
-	*)
+	--)
+		shift
+		break
+		;;
+	-*)
 		usage
+		;;
+	*)
+		break
 	esac
 	shift
 done
@@ -64,7 +73,7 @@ if [ -z "$ignored" ]; then
 	fi
 fi
 
-git-ls-files --others --directory $excl ${excl_info:+"$excl_info"} |
+git-ls-files --others --directory $excl ${excl_info:+"$excl_info"} -- "$@" |
 while read -r file; do
 	if [ -d "$file" -a ! -L "$file" ]; then
 		if [ -z "$cleandir" ]; then

git-clone.sh

@@ -261,11 +261,7 @@ yes,yes)
 	    ;;
 	yes)
 	    mkdir -p "$GIT_DIR/objects/info"
-	    {
-		test -f "$repo/objects/info/alternates" &&
-		cat "$repo/objects/info/alternates";
-		echo "$repo/objects"
-	    } >"$GIT_DIR/objects/info/alternates"
+	    echo "$repo/objects" >> "$GIT_DIR/objects/info/alternates"
 	    ;;
 	esac
 	git-ls-remote "$repo" >"$GIT_DIR/CLONE_HEAD"

git-commit.sh

@@ -640,6 +640,8 @@ case "$no_edit" in
 		exit 1
 		;;
 	esac
+	git-var GIT_AUTHOR_IDENT > /dev/null  || die
+	git-var GIT_COMMITTER_IDENT > /dev/null  || die
 	${VISUAL:-${EDITOR:-vi}} "$GIT_DIR/COMMIT_EDITMSG"
 	;;
 esac

git-cvsexportcommit.perl

@@ -10,9 +10,9 @@ unless ($ENV{GIT_DIR} && -r $ENV{GIT_DIR}){
     die "GIT_DIR is not defined or is unreadable";
 }
 
-our ($opt_h, $opt_p, $opt_v, $opt_c );
+our ($opt_h, $opt_p, $opt_v, $opt_c, $opt_f, $opt_m );
 
-getopts('hpvc');
+getopts('hpvcfm:');
 
 $opt_h && usage();
 
@@ -77,12 +77,16 @@ if ($parent) {
 $opt_v && print "Applying to CVS commit $commit from parent $parent\n";
 
 # grab the commit message
-`git-cat-file commit $commit | sed -e '1,/^\$/d' > .msg`;
+open(MSG, ">.msg") or die "Cannot open .msg for writing";
+print MSG $opt_m;
+close MSG;
+
+`git-cat-file commit $commit | sed -e '1,/^\$/d' >> .msg`;
 $? && die "Error extracting the commit message";
 
 my (@afiles, @dfiles, @mfiles);
 my @files = safe_pipe_capture('git-diff-tree', '-r', $parent, $commit);
-print @files;
+#print @files;
 $? && die "Error in git-diff-tree";
 foreach my $f (@files) {
     chomp $f;
@@ -109,7 +113,7 @@ foreach my $f (@afiles) {
     if (@status > 1) { warn 'Strange! cvs status returned more than one line?'};
     unless ($status[0] =~ m/Status: Unknown$/) {
  	$dirty = 1;
-	warn "File $f is already known in your CVS checkout!\n";
+	warn "File $f is already known in your CVS checkout -- perhaps it has been added by another user. Or this may indicate that it exists on a different branch. If this is the case, use -f to force the merge.\n";
     }
 }
 foreach my $f (@mfiles, @dfiles) {
@@ -122,7 +126,11 @@ foreach my $f (@mfiles, @dfiles) {
     }
 }
 if ($dirty) {
-    die "Exiting: your CVS tree is not clean for this merge.";
+    if ($opt_f) {	warn "The tree is not clean -- forced merge\n";
+	$dirty = 0;
+    } else {
+	die "Exiting: your CVS tree is not clean for this merge.";
+    }
 }
 
 ###
@@ -215,7 +223,7 @@ if ($opt_c) {
 }
 sub usage {
 	print STDERR <<END;
-Usage: GIT_DIR=/path/to/.git ${\basename $0} [-h] [-p] [-v] [-c] [ parent ] commit
+Usage: GIT_DIR=/path/to/.git ${\basename $0} [-h] [-p] [-v] [-c] [-f] [-m msgprefix] [ parent ] commit
 END
 	exit(1);
 }

git-cvsimport.perl

@@ -350,7 +350,7 @@ sub _line {
 				return $res;
 			} elsif($line =~ s/^E //) {
 				# print STDERR "S: $line\n";
-			} elsif($line =~ /^Remove-entry /i) {
+			} elsif($line =~ /^(Remove-entry|Removed) /i) {
 				$line = $self->readline(); # filename
 				$line = $self->readline(); # OK
 				chomp $line;

git-cvsserver.perl

@@ -214,8 +214,7 @@ sub req_Globaloption
 {
     my ( $cmd, $data ) = @_;
     $log->debug("req_Globaloption : $data");
-
-    # TODO : is this data useful ???
+    $state->{globaloptions}{$data} = 1;
 }
 
 # Valid-responses request-list \n
@@ -267,12 +266,32 @@ sub req_Directory
 
     $state->{localdir} = $data;
     $state->{repository} = $repository;
-    $state->{directory} = $repository;
-    $state->{directory} =~ s/^$state->{CVSROOT}\///;
-    $state->{module} = $1 if ($state->{directory} =~ s/^(.*?)(\/|$)//);
+    $state->{path} = $repository;
+    $state->{path} =~ s/^$state->{CVSROOT}\///;
+    $state->{module} = $1 if ($state->{path} =~ s/^(.*?)(\/|$)//);
+    $state->{path} .= "/" if ( $state->{path} =~ /\S/ );
+
+    $state->{directory} = $state->{localdir};
+    $state->{directory} = "" if ( $state->{directory} eq "." );
     $state->{directory} .= "/" if ( $state->{directory} =~ /\S/ );
 
-    $log->debug("req_Directory : localdir=$data repository=$repository directory=$state->{directory} module=$state->{module}");
+    if ( not defined($state->{prependdir}) and $state->{localdir} eq "." and $state->{path} =~ /\S/ )
+    {
+        $log->info("Setting prepend to '$state->{path}'");
+        $state->{prependdir} = $state->{path};
+        foreach my $entry ( keys %{$state->{entries}} )
+        {
+            $state->{entries}{$state->{prependdir} . $entry} = $state->{entries}{$entry};
+            delete $state->{entries}{$entry};
+        }
+    }
+
+    if ( defined ( $state->{prependdir} ) )
+    {
+        $log->debug("Prepending '$state->{prependdir}' to state|directory");
+        $state->{directory} = $state->{prependdir} . $state->{directory}
+    }
+    $log->debug("req_Directory : localdir=$data repository=$repository path=$state->{path} directory=$state->{directory} module=$state->{module}");
 }
 
 # Entry entry-line \n
@@ -290,7 +309,7 @@ sub req_Entry
 {
     my ( $cmd, $data ) = @_;
 
-    $log->debug("req_Entry : $data");
+    #$log->debug("req_Entry : $data");
 
     my @data = split(/\//, $data);
 
@@ -300,6 +319,22 @@ sub req_Entry
         options     => $data[4],
         tag_or_date => $data[5],
     };
+
+    $log->info("Received entry line '$data' => '" . $state->{directory} . $data[1] . "'");
+}
+
+# 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 ) = @_;
+
+    $log->debug("req_Questionable : $data");
+    $state->{entries}{$state->{directory}.$data}{questionable} = 1;
 }
 
 # add \n
@@ -332,8 +367,7 @@ sub req_add
             next;
         }
 
-
-        my ( $filepart, $dirpart ) = filenamesplit($filename);
+        my ( $filepart, $dirpart ) = filenamesplit($filename, 1);
 
         print "E cvs add: scheduling file `$filename' for addition\n";
 
@@ -414,7 +448,7 @@ sub req_remove
         }
 
 
-        my ( $filepart, $dirpart ) = filenamesplit($filename);
+        my ( $filepart, $dirpart ) = filenamesplit($filename, 1);
 
         print "E cvs remove: scheduling `$filename' for removal\n";
 
@@ -502,22 +536,6 @@ 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
@@ -757,8 +775,7 @@ sub req_update
 
     $updater->update();
 
-    # if no files were specified, we need to work out what files we should be providing status on ...
-    argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 );
+    argsfromdir($updater);
 
     #$log->debug("update state : " . Dumper($state));
 
@@ -767,6 +784,8 @@ sub req_update
     {
         $filename = filecleanup($filename);
 
+        $log->debug("Processing file $filename");
+
         # if we have a -C we should pretend we never saw modified stuff
         if ( exists ( $state->{opt}{C} ) )
         {
@@ -821,13 +840,16 @@ sub req_update
 
         if ( $meta->{filehash} eq "deleted" )
         {
-            my ( $filepart, $dirpart ) = filenamesplit($filename);
+            my ( $filepart, $dirpart ) = filenamesplit($filename,1);
 
             $log->info("Removing '$filename' from working copy (no longer in the repo)");
 
             print "E cvs update: `$filename' is no longer in the repository\n";
-            print "Removed $dirpart\n";
-            print "$filepart\n";
+            # Don't want to actually _DO_ the update if -n specified
+            unless ( $state->{globaloptions}{-n} ) {
+		print "Removed $dirpart\n";
+		print "$filepart\n";
+	    }
         }
         elsif ( not defined ( $state->{entries}{$filename}{modified_hash} )
 		or $state->{entries}{$filename}{modified_hash} eq $oldmeta->{filehash} )
@@ -840,34 +862,42 @@ sub req_update
             print "MT newline\n";
             print "MT -updated\n";
 
-            my ( $filepart, $dirpart ) = filenamesplit($filename);
-            $dirpart =~ s/^$state->{directory}//;
+            my ( $filepart, $dirpart ) = filenamesplit($filename,1);
 
-            if ( defined ( $wrev ) )
-            {
-                # instruct client we're sending a file to put in this path as a replacement
-                print "Update-existing $dirpart\n";
-                $log->debug("Updating existing file 'Update-existing $dirpart'");
-            } else {
-                # instruct client we're sending a file to put in this path as a new file
-                print "Created $dirpart\n";
-                $log->debug("Creating new file 'Created $dirpart'");
-            }
-            print $state->{CVSROOT} . "/$state->{module}/$filename\n";
+	    # Don't want to actually _DO_ the update if -n specified
+	    unless ( $state->{globaloptions}{-n} )
+	    {
+		if ( defined ( $wrev ) )
+		{
+		    # instruct client we're sending a file to put in this path as a replacement
+		    print "Update-existing $dirpart\n";
+		    $log->debug("Updating existing file 'Update-existing $dirpart'");
+		} else {
+		    # instruct client we're sending a file to put in this path as a new file
+		    print "Clear-static-directory $dirpart\n";
+		    print $state->{CVSROOT} . "/$state->{module}/$dirpart\n";
+		    print "Clear-sticky $dirpart\n";
+		    print $state->{CVSROOT} . "/$state->{module}/$dirpart\n";
 
-            # this is an "entries" line
-            $log->debug("/$filepart/1.$meta->{revision}///");
-            print "/$filepart/1.$meta->{revision}///\n";
+		    $log->debug("Creating new file 'Created $dirpart'");
+		    print "Created $dirpart\n";
+		}
+		print $state->{CVSROOT} . "/$state->{module}/$filename\n";
 
-            # permissions
-            $log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}");
-            print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n";
+		# this is an "entries" line
+		$log->debug("/$filepart/1.$meta->{revision}///");
+		print "/$filepart/1.$meta->{revision}///\n";
 
-            # transmit file
-            transmitfile($meta->{filehash});
+		# permissions
+		$log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}");
+		print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n";
+
+		# transmit file
+		transmitfile($meta->{filehash});
+	    }
         } else {
             $log->info("Updating '$filename'");
-            my ( $filepart, $dirpart ) = filenamesplit($meta->{name});
+            my ( $filepart, $dirpart ) = filenamesplit($meta->{name},1);
 
             my $dir = tempdir( DIR => $TEMP_DIR, CLEANUP => 1 ) . "/";
 
@@ -892,19 +922,29 @@ sub req_update
                 $log->info("Merged successfully");
                 print "M M $filename\n";
                 $log->debug("Update-existing $dirpart");
-                print "Update-existing $dirpart\n";
-                $log->debug($state->{CVSROOT} . "/$state->{module}/$filename");
-                print $state->{CVSROOT} . "/$state->{module}/$filename\n";
-                $log->debug("/$filepart/1.$meta->{revision}///");
-                print "/$filepart/1.$meta->{revision}///\n";
+
+                # Don't want to actually _DO_ the update if -n specified
+                unless ( $state->{globaloptions}{-n} )
+                {
+                    print "Update-existing $dirpart\n";
+                    $log->debug($state->{CVSROOT} . "/$state->{module}/$filename");
+                    print $state->{CVSROOT} . "/$state->{module}/$filename\n";
+                    $log->debug("/$filepart/1.$meta->{revision}///");
+                    print "/$filepart/1.$meta->{revision}///\n";
+                }
             }
             elsif ( $return == 1 )
             {
                 $log->info("Merged with conflicts");
                 print "M C $filename\n";
-                print "Update-existing $dirpart\n";
-                print $state->{CVSROOT} . "/$state->{module}/$filename\n";
-                print "/$filepart/1.$meta->{revision}/+//\n";
+
+                # Don't want to actually _DO_ the update if -n specified
+                unless ( $state->{globaloptions}{-n} )
+                {
+                    print "Update-existing $dirpart\n";
+                    print $state->{CVSROOT} . "/$state->{module}/$filename\n";
+                    print "/$filepart/1.$meta->{revision}/+//\n";
+                }
             }
             else
             {
@@ -912,17 +952,21 @@ sub req_update
                 next;
             }
 
-            # permissions
-            $log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}");
-            print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n";
+            # Don't want to actually _DO_ the update if -n specified
+            unless ( $state->{globaloptions}{-n} )
+            {
+                # permissions
+                $log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}");
+                print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n";
 
-            # transmit file, format is single integer on a line by itself (file
-            # size) followed by the file contents
-            # TODO : we should copy files in blocks
-            my $data = `cat $file_local`;
-            $log->debug("File size : " . length($data));
-            print length($data) . "\n";
-            print $data;
+                # transmit file, format is single integer on a line by itself (file
+                # size) followed by the file contents
+                # TODO : we should copy files in blocks
+                my $data = `cat $file_local`;
+                $log->debug("File size : " . length($data));
+                print length($data) . "\n";
+                print $data;
+            }
 
             chdir "/";
         }
@@ -950,6 +994,7 @@ sub req_ci
 
     if ( -e $state->{CVSROOT} . "/index" )
     {
+        $log->warn("file 'index' already exists in the git repository");
         print "error 1 Index already exists in git repo\n";
         exit;
     }
@@ -957,6 +1002,7 @@ sub req_ci
     my $lockfile = "$state->{CVSROOT}/refs/heads/$state->{module}.lock";
     unless ( sysopen(LOCKFILE,$lockfile,O_EXCL|O_CREAT|O_WRONLY) )
     {
+        $log->warn("lockfile '$lockfile' already exists, please try again");
         print "error 1 Lock file '$lockfile' already exists, please try again\n";
         exit;
     }
@@ -988,6 +1034,7 @@ sub req_ci
     # foreach file specified on the commandline ...
     foreach my $filename ( @{$state->{args}} )
     {
+        my $committedfile = $filename;
         $filename = filecleanup($filename);
 
         next unless ( exists $state->{entries}{$filename}{modified_filename} or not $state->{entries}{$filename}{unchanged} );
@@ -1022,7 +1069,7 @@ sub req_ci
             exit;
         }
 
-        push @committedfiles, $filename;
+        push @committedfiles, $committedfile;
         $log->info("Committing $filename");
 
         system("mkdir","-p",$dirpart) unless ( -d $dirpart );
@@ -1105,7 +1152,7 @@ sub req_ci
 
         my $meta = $updater->getmeta($filename);
 
-        my ( $filepart, $dirpart ) = filenamesplit($filename);
+        my ( $filepart, $dirpart ) = filenamesplit($filename, 1);
 
         $log->debug("Checked-in $dirpart : $filename");
 
@@ -1141,7 +1188,7 @@ sub req_status
     $updater->update();
 
     # if no files were specified, we need to work out what files we should be providing status on ...
-    argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 );
+    argsfromdir($updater);
 
     # foreach file specified on the commandline ...
     foreach my $filename ( @{$state->{args}} )
@@ -1242,7 +1289,7 @@ sub req_diff
     $updater->update();
 
     # if no files were specified, we need to work out what files we should be providing status on ...
-    argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 );
+    argsfromdir($updater);
 
     # foreach file specified on the commandline ...
     foreach my $filename ( @{$state->{args}} )
@@ -1384,7 +1431,7 @@ sub req_log
     $updater->update();
 
     # if no files were specified, we need to work out what files we should be providing status on ...
-    argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 );
+    argsfromdir($updater);
 
     # foreach file specified on the commandline ...
     foreach my $filename ( @{$state->{args}} )
@@ -1460,7 +1507,7 @@ sub req_annotate
     $updater->update();
 
     # if no files were specified, we need to work out what files we should be providing annotate on ...
-    argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 );
+    argsfromdir($updater);
 
     # we'll need a temporary checkout dir
     my $tmpdir = tempdir ( DIR => $TEMP_DIR );
@@ -1655,13 +1702,36 @@ sub argsfromdir
 {
     my $updater = shift;
 
-    $state->{args} = [];
+    $state->{args} = [] if ( scalar(@{$state->{args}}) == 1 and $state->{args}[0] eq "." );
 
-    foreach my $file ( @{$updater->gethead} )
+    return if ( scalar ( @{$state->{args}} ) > 1 );
+
+    if ( scalar(@{$state->{args}}) == 1 )
     {
-        next if ( $file->{filehash} eq "deleted" and not defined ( $state->{entries}{$file->{name}} ) );
-        next unless ( $file->{name} =~ s/^$state->{directory}// );
-        push @{$state->{args}}, $file->{name};
+        my $arg = $state->{args}[0];
+        $arg .= $state->{prependdir} if ( defined ( $state->{prependdir} ) );
+
+        $log->info("Only one arg specified, checking for directory expansion on '$arg'");
+
+        foreach my $file ( @{$updater->gethead} )
+        {
+            next if ( $file->{filehash} eq "deleted" and not defined ( $state->{entries}{$file->{name}} ) );
+            next unless ( $file->{name} =~ /^$arg\// or $file->{name} eq $arg  );
+            push @{$state->{args}}, $file->{name};
+        }
+
+        shift @{$state->{args}} if ( scalar(@{$state->{args}}) > 1 );
+    } else {
+        $log->info("Only one arg specified, populating file list automatically");
+
+        $state->{args} = [];
+
+        foreach my $file ( @{$updater->gethead} )
+        {
+            next if ( $file->{filehash} eq "deleted" and not defined ( $state->{entries}{$file->{name}} ) );
+            next unless ( $file->{name} =~ s/^$state->{prependdir}// );
+            push @{$state->{args}}, $file->{name};
+        }
     }
 }
 
@@ -1736,11 +1806,17 @@ sub transmitfile
 sub filenamesplit
 {
     my $filename = shift;
+    my $fixforlocaldir = shift;
 
     my ( $filepart, $dirpart ) = ( $filename, "." );
     ( $filepart, $dirpart ) = ( $2, $1 ) if ( $filename =~ /(.*)\/(.*)/ );
     $dirpart .= "/";
 
+    if ( $fixforlocaldir )
+    {
+        $dirpart =~ s/^$state->{prependdir}//;
+    }
+
     return ( $filepart, $dirpart );
 }
 
@@ -1756,8 +1832,7 @@ sub filecleanup
     }
 
     $filename =~ s/^\.\///g;
-    $filename = $state->{directory} . $filename;
-
+    $filename = $state->{prependdir} . $filename;
     return $filename;
 }
 

git-format-patch.sh

@@ -274,7 +274,7 @@ print "\n---\n\n";
 close FH or die "close $commsg pipe";
 ' "$keep_subject" "$num" "$signoff" "$headers" "$mimemagic" $commsg
 
-	git-diff-tree -p $diff_opts "$commit" | git-apply --stat --summary
+	git-diff-tree -p --stat --summary $diff_opts "$commit"
 	echo
 	case "$mimemagic" in
 	'');;

git-grep.sh

@@ -1,62 +0,0 @@
-#!/bin/sh
-#
-# Copyright (c) Linus Torvalds, 2005
-#
-
-USAGE='[<option>...] [-e] <pattern> [<path>...]'
-SUBDIRECTORY_OK='Yes'
-. git-sh-setup
-
-got_pattern () {
-	if [ -z "$no_more_patterns" ]
-	then
-		pattern="$1" no_more_patterns=yes
-	else
-		die "git-grep: do not specify more than one pattern"
-	fi
-}
-
-no_more_patterns=
-pattern=
-flags=()
-git_flags=()
-while : ; do
-	case "$1" in
-	-o|--cached|--deleted|--others|--killed|\
-	--ignored|--modified|--exclude=*|\
-	--exclude-from=*|\--exclude-per-directory=*)
-		git_flags=("${git_flags[@]}" "$1")
-		;;
-	-e)
-		got_pattern "$2"
-		shift
-		;;
-	-A|-B|-C|-D|-d|-f|-m)
-		flags=("${flags[@]}" "$1" "$2")
-		shift
-		;;
-	--)
-		# The rest are git-ls-files paths
-		shift
-		break
-		;;
-	-*)
-		flags=("${flags[@]}" "$1")
-		;;
-	*)
-		if [ -z "$no_more_patterns" ]
-		then
-			got_pattern "$1"
-			shift
-		fi
-		[ "$1" = -- ] && shift
-		break
-		;;
-	esac
-	shift
-done
-[ "$pattern" ] || {
-	usage
-}
-git-ls-files -z "${git_flags[@]}" -- "$@" |
-	xargs -0 grep "${flags[@]}" -e "$pattern" --

git-merge.sh

@@ -55,8 +55,7 @@ finish () {
 
 	case "$no_summary" in
 	'')
-		git-diff-tree -p -M "$head" "$1" |
-		git-apply --stat --summary
+		git-diff-tree -p --stat --summary -M "$head" "$1"
 		;;
 	esac
 }

git-parse-remote.sh

@@ -10,7 +10,10 @@ get_data_source () {
 		# Not so fast.	This could be the partial URL shorthand...
 		token=$(expr "z$1" : 'z\([^/]*\)/')
 		remainder=$(expr "z$1" : 'z[^/]*/\(.*\)')
-		if test -f "$GIT_DIR/branches/$token"
+		if test "$(git-repo-config --get "remote.$token.url")"
+		then
+			echo config-partial
+		elif test -f "$GIT_DIR/branches/$token"
 		then
 			echo branches-partial
 		else
@@ -18,7 +21,10 @@ get_data_source () {
 		fi
 		;;
 	*)
-		if test -f "$GIT_DIR/remotes/$1"
+		if test "$(git-repo-config --get "remote.$1.url")"
+		then
+			echo config
+		elif test -f "$GIT_DIR/remotes/$1"
 		then
 			echo remotes
 		elif test -f "$GIT_DIR/branches/$1"
@@ -35,6 +41,15 @@ get_remote_url () {
 	case "$data_source" in
 	'')
 		echo "$1" ;;
+	config-partial)
+		token=$(expr "z$1" : 'z\([^/]*\)/')
+		remainder=$(expr "z$1" : 'z[^/]*/\(.*\)')
+		url=$(git-repo-config --get "remote.$token.url")
+		echo "$url/$remainder"
+		;;
+	config)
+		git-repo-config --get "remote.$1.url"
+		;;
 	remotes)
 		sed -ne '/^URL: */{
 			s///p
@@ -56,8 +71,10 @@ get_remote_url () {
 get_remote_default_refs_for_push () {
 	data_source=$(get_data_source "$1")
 	case "$data_source" in
-	'' | branches | branches-partial)
+	'' | config-partial | branches | branches-partial)
 		;; # no default push mapping, just send matching refs.
+	config)
+		git-repo-config --get-all "remote.$1.push" ;;
 	remotes)
 		sed -ne '/^Push: */{
 			s///p
@@ -111,8 +128,11 @@ canon_refs_list_for_fetch () {
 get_remote_default_refs_for_fetch () {
 	data_source=$(get_data_source "$1")
 	case "$data_source" in
-	'' | branches-partial)
+	'' | config-partial | branches-partial)
 		echo "HEAD:" ;;
+	config)
+		canon_refs_list_for_fetch \
+			$(git-repo-config --get-all "remote.$1.fetch") ;;
 	branches)
 		remote_branch=$(sed -ne '/#/s/.*#//p' "$GIT_DIR/branches/$1")
 		case "$remote_branch" in '') remote_branch=master ;; esac

git-quiltimport.sh

@@ -0,0 +1,118 @@
+#!/bin/sh
+USAGE='--dry-run --author <author> --patches </path/to/quilt/patch/directory>'
+SUBDIRECTORY_ON=Yes
+. git-sh-setup
+
+dry_run=""
+quilt_author=""
+while case "$#" in 0) break;; esac
+do
+	case "$1" in
+	--au=*|--aut=*|--auth=*|--autho=*|--author=*)
+		quilt_author=$(expr "$1" : '-[^=]*\(.*\)')
+		shift
+		;;
+
+	--au|--aut|--auth|--autho|--author)
+		case "$#" in 1) usage ;; esac
+		shift
+		quilt_author="$1"
+		shift
+		;;
+
+	--dry-run)
+		shift
+		dry_run=1
+		;;
+
+	--pa=*|--pat=*|--patc=*|--patch=*|--patche=*|--patches=*)
+		QUILT_PATCHES=$(expr "$1" : '-[^=]*\(.*\)')
+		shift
+		;;
+
+	--pa|--pat|--patc|--patch|--patche|--patches)
+		case "$#" in 1) usage ;; esac
+		shift
+		QUILT_PATCHES="$1"
+		shift
+		;;
+
+	*)
+		break
+		;;
+	esac
+done
+
+# Quilt Author
+if [ -n "$quilt_author" ] ; then
+	quilt_author_name=$(expr "z$quilt_author" : 'z\(.*[^ ]\) *<.*') &&
+	quilt_author_email=$(expr "z$quilt_author" : '.*<\([^>]*\)') &&
+	test '' != "$quilt_author_name" &&
+	test '' != "$quilt_author_email" ||
+	die "malformatted --author parameter"
+fi
+
+# Quilt patch directory
+: ${QUILT_PATCHES:=patches}
+if ! [ -d "$QUILT_PATCHES" ] ; then
+	echo "The \"$QUILT_PATCHES\" directory does not exist."
+	exit 1
+fi
+
+# Temporay directories
+tmp_dir=.dotest
+tmp_msg="$tmp_dir/msg"
+tmp_patch="$tmp_dir/patch"
+tmp_info="$tmp_dir/info"
+
+
+# Find the intial commit
+commit=$(git-rev-parse HEAD)
+
+mkdir $tmp_dir || exit 2
+for patch_name in $(cat "$QUILT_PATCHES/series" | grep -v '^#'); do
+	echo $patch_name
+	(cat $QUILT_PATCHES/$patch_name | git-mailinfo "$tmp_msg" "$tmp_patch" > "$tmp_info") || exit 3
+
+	# Parse the author information
+	export GIT_AUTHOR_NAME=$(sed -ne 's/Author: //p' "$tmp_info")
+	export GIT_AUTHOR_EMAIL=$(sed -ne 's/Email: //p' "$tmp_info")
+	while test -z "$GIT_AUTHOR_EMAIL" && test -z "$GIT_AUTHOR_NAME" ; do
+		if [ -n "$quilt_author" ] ; then
+			GIT_AUTHOR_NAME="$quilt_author_name";
+			GIT_AUTHOR_EMAIL="$quilt_author_email";
+		elif [ -n "$dry_run" ]; then
+			echo "No author found in $patch_name" >&2;
+			GIT_AUTHOR_NAME="dry-run-not-found";
+			GIT_AUTHOR_EMAIL="dry-run-not-found";
+		else
+			echo "No author found in $patch_name" >&2;
+			echo "---"
+			cat $tmp_msg
+			echo -n "Author: ";
+			read patch_author
+
+			echo "$patch_author"
+
+			patch_author_name=$(expr "z$patch_author" : 'z\(.*[^ ]\) *<.*') &&
+			patch_author_email=$(expr "z$patch_author" : '.*<\([^>]*\)') &&
+			test '' != "$patch_author_name" &&
+			test '' != "$patch_author_email" &&
+			GIT_AUTHOR_NAME="$patch_author_name" &&
+			GIT_AUTHOR_EMAIL="$patch_author_email"
+		fi
+	done
+	export GIT_AUTHOR_DATE=$(sed -ne 's/Date: //p' "$tmp_info")
+	export SUBJECT=$(sed -ne 's/Subject: //p' "$tmp_info")
+	if [ -z "$SUBJECT" ] ; then
+		SUBJECT=$(echo $patch_name | sed -e 's/.patch$//')
+	fi
+
+	if [ -z "$dry_run" ] ; then
+		git-apply --index -C1 "$tmp_patch" &&
+		tree=$(git-write-tree) &&
+		commit=$((echo "$SUBJECT"; echo; cat "$tmp_msg") | git-commit-tree $tree -p $commit) &&
+		git-update-ref HEAD $commit || exit 4
+	fi
+done
+rm -rf $tmp_dir || exit 5

git-rebase.sh

@@ -12,9 +12,10 @@ It then attempts to create a new commit for each commit from the original
 
 It is possible that a merge failure will prevent this process from being
 completely automatic.  You will have to resolve any such merge failure
-and run git-rebase --continue.  If you can not resolve the merge failure,
-running git-rebase --abort will restore the original <branch> and remove
-the working files found in the .dotest directory.
+and run git rebase --continue.  Another option is to bypass the commit
+that caused the merge failure with git rebase --skip.  To restore the
+original <branch> and remove the .dotest working files, use the command
+git rebase --abort instead.
 
 Note that if <branch> is not specified on the command line, the
 currently checked out branch is used.  You must be in the top
@@ -28,6 +29,11 @@ Example:       git-rebase master~1 topic
 '
 . git-sh-setup
 
+RESOLVEMSG="
+When you have resolved this problem run \"git rebase --continue\".
+If you would prefer to skip this patch, instead run \"git rebase --skip\".
+To restore the original branch and stop rebasing run \"git rebase --abort\".
+"
 unset newbase
 while case "$#" in 0) break ;; esac
 do
@@ -40,7 +46,11 @@ do
 			exit 1
 			;;
 		esac
-		git am --resolved --3way
+		git am --resolved --3way --resolvemsg="$RESOLVEMSG"
+		exit
+		;;
+	--skip)
+		git am -3 --skip --resolvemsg="$RESOLVEMSG"
 		exit
 		;;
 	--abort)
@@ -143,4 +153,5 @@ then
 fi
 
 git-format-patch -k --stdout --full-index "$upstream" ORIG_HEAD |
-git am --binary -3 -k
+git am --binary -3 -k --resolvemsg="$RESOLVEMSG"
+

git-repack.sh

@@ -48,15 +48,15 @@ name=$(git-rev-list --objects --all $rev_list 2>&1 |
 	exit 1
 if [ -z "$name" ]; then
 	echo Nothing new to pack.
-	exit 0
+else
+	echo "Pack pack-$name created."
+
+	mkdir -p "$PACKDIR" || exit
+
+	mv .tmp-pack-$name.pack "$PACKDIR/pack-$name.pack" &&
+	mv .tmp-pack-$name.idx  "$PACKDIR/pack-$name.idx" ||
+	exit
 fi
-echo "Pack pack-$name created."
-
-mkdir -p "$PACKDIR" || exit
-
-mv .tmp-pack-$name.pack "$PACKDIR/pack-$name.pack" &&
-mv .tmp-pack-$name.idx  "$PACKDIR/pack-$name.idx" ||
-exit
 
 if test "$remove_redundant" = t
 then

git-request-pull.sh

@@ -30,4 +30,4 @@ echo "  $url"
 echo
 
 git log  $baserev..$headrev | git-shortlog ;
-git diff $baserev..$headrev | git-apply --stat --summary
+git diff --stat --summary $baserev..$headrev

git-reset.sh

@@ -6,6 +6,7 @@ USAGE='[--mixed | --soft | --hard]  [<commit-ish>]'
 tmp=${GIT_DIR}/reset.$$
 trap 'rm -f $tmp-*' 0 1 2 3 15
 
+update=
 reset_type=--mixed
 case "$1" in
 --mixed | --soft | --hard)
@@ -23,24 +24,7 @@ rev=$(git-rev-parse --verify $rev^0) || exit
 # behind before a hard reset, so that we can remove them.
 if test "$reset_type" = "--hard"
 then
-	{
-		git-ls-files --stage -z
-		git-rev-parse --verify HEAD 2>/dev/null &&
-		git-ls-tree -r -z HEAD
-	} | perl -e '
-	    use strict;
-	    my %seen;
-	    $/ = "\0";
-	    while (<>) {
-		chomp;
-		my ($info, $path) = split(/\t/, $_);
-		next if ($info =~ / tree /);
-		if (!$seen{$path}) {
-			$seen{$path} = 1;
-			print "$path\0";
-		}
-	    }
-	' >$tmp-exists
+	update=-u
 fi
 
 # Soft reset does not touch the index file nor the working tree
@@ -54,7 +38,7 @@ then
 		die "Cannot do a soft reset in the middle of a merge."
 	fi
 else
-	git-read-tree --reset "$rev" || exit
+	git-read-tree --reset $update "$rev" || exit
 fi
 
 # Any resets update HEAD to the head being switched to.
@@ -68,33 +52,7 @@ git-update-ref HEAD "$rev"
 
 case "$reset_type" in
 --hard )
-	# Hard reset matches the working tree to that of the tree
-	# being switched to.
-	git-checkout-index -f -u -q -a
-	git-ls-files --cached -z |
-	perl -e '
-		use strict;
-		my (%keep, $fh);
-		$/ = "\0";
-		while (<STDIN>) {
-			chomp;
-			$keep{$_} = 1;
-		}
-		open $fh, "<", $ARGV[0]
-			or die "cannot open $ARGV[0]";
-		while (<$fh>) {
-			chomp;
-			if (! exists $keep{$_}) {
-				# it is ok if this fails -- it may already
-				# have been culled by checkout-index.
-				unlink $_;
-				while (s|/[^/]*$||) {
-					rmdir($_) or last;
-				}
-			}
-		}
-	' $tmp-exists
-	;;
+	;; # Nothing else to do
 --soft )
 	;; # Nothing else to do
 --mixed )

git-revert.sh

@@ -137,7 +137,7 @@ esac >.msg
 # $prev and $commit on top of us (when cherry-picking or replaying).
 
 echo >&2 "First trying simple merge strategy to $me."
-git-read-tree -m -u $base $head $next &&
+git-read-tree -m -u --aggressive $base $head $next &&
 result=$(git-write-tree 2>/dev/null) || {
     echo >&2 "Simple $me fails; trying Automatic $me."
     git-merge-index -o git-merge-one-file -a || {

git-send-email.perl

@@ -40,7 +40,8 @@ my $compose_filename = ".msg.$$";
 my (@to,@cc,@initial_cc,$initial_reply_to,$initial_subject,@files,$from,$compose,$time);
 
 # Behavior modification variables
-my ($chain_reply_to, $smtp_server, $quiet, $suppress_from, $no_signed_off_cc) = (1, "localhost", 0, 0, 0);
+my ($chain_reply_to, $quiet, $suppress_from, $no_signed_off_cc) = (1, 0, 0, 0);
+my $smtp_server;
 
 # Example reply to:
 #$initial_reply_to = ''; #<20050203173208.GA23964@foobar.com>';
@@ -89,6 +90,41 @@ sub gitvar_ident {
 my ($author) = gitvar_ident('GIT_AUTHOR_IDENT');
 my ($committer) = gitvar_ident('GIT_COMMITTER_IDENT');
 
+my %aliases;
+chomp(my @alias_files = `git-repo-config --get-all sendemail.aliasesfile`);
+chomp(my $aliasfiletype = `git-repo-config sendemail.aliasfiletype`);
+my %parse_alias = (
+	# multiline formats can be supported in the future
+	mutt => sub { my $fh = shift; while (<$fh>) {
+		if (/^alias\s+(\S+)\s+(.*)$/) {
+			my ($alias, $addr) = ($1, $2);
+			$addr =~ s/#.*$//; # mutt allows # comments
+			 # commas delimit multiple addresses
+			$aliases{$alias} = [ split(/\s*,\s*/, $addr) ];
+		}}},
+	mailrc => sub { my $fh = shift; while (<$fh>) {
+		if (/^alias\s+(\S+)\s+(.*)$/) {
+			# spaces delimit multiple addresses
+			$aliases{$1} = [ split(/\s+/, $2) ];
+		}}},
+	pine => sub { my $fh = shift; while (<$fh>) {
+		if (/^(\S+)\s+(.*)$/) {
+			$aliases{$1} = [ split(/\s*,\s*/, $2) ];
+		}}},
+	gnus => sub { my $fh = shift; while (<$fh>) {
+		if (/\(define-mail-alias\s+"(\S+?)"\s+"(\S+?)"\)/) {
+			$aliases{$1} = [ $2 ];
+		}}}
+);
+
+if (@alias_files && defined $parse_alias{$aliasfiletype}) {
+	foreach my $file (@alias_files) {
+		open my $fh, '<', $file or die "opening $file: $!\n";
+		$parse_alias{$aliasfiletype}->($fh);
+		close $fh;
+	}
+}
+
 my $prompting = 0;
 if (!defined $from) {
 	$from = $author || $committer;
@@ -112,6 +148,19 @@ if (!@to) {
 	$prompting++;
 }
 
+sub expand_aliases {
+	my @cur = @_;
+	my @last;
+	do {
+		@last = @cur;
+		@cur = map { $aliases{$_} ? @{$aliases{$_}} : $_ } @last;
+	} while (join(',',@cur) ne join(',',@last));
+	return @cur;
+}
+
+@to = expand_aliases(@to);
+@initial_cc = expand_aliases(@initial_cc);
+
 if (!defined $initial_subject && $compose) {
 	do {
 		$_ = $term->readline("What subject should the emails start with? ",
@@ -131,8 +180,14 @@ if (!defined $initial_reply_to && $prompting) {
 	$initial_reply_to =~ s/(^\s+|\s+$)//g;
 }
 
-if (!defined $smtp_server) {
-	$smtp_server = "localhost";
+if (!$smtp_server) {
+	foreach (qw( /usr/sbin/sendmail /usr/lib/sendmail )) {
+		if (-x $_) {
+			$smtp_server = $_;
+			last;
+		}
+	}
+	$smtp_server ||= 'localhost'; # could be 127.0.0.1, too... *shrug*
 }
 
 if ($compose) {
@@ -252,6 +307,10 @@ our ($message_id, $cc, %mail, $subject, $reply_to, $message);
 
 sub extract_valid_address {
 	my $address = shift;
+
+	# check for a local address:
+	return $address if ($address =~ /^([\w\-]+)$/);
+
 	if ($have_email_valid) {
 		return Email::Valid->address($address);
 	} else {
@@ -310,26 +369,39 @@ X-Mailer: git-send-email $gitversion
 ";
 	$header .= "In-Reply-To: $reply_to\n" if $reply_to;
 
-	$smtp ||= Net::SMTP->new( $smtp_server );
-	$smtp->mail( $from ) or die $smtp->message;
-	$smtp->to( @recipients ) or die $smtp->message;
-	$smtp->data or die $smtp->message;
-	$smtp->datasend("$header\n$message") or die $smtp->message;
-	$smtp->dataend() or die $smtp->message;
-	$smtp->ok or die "Failed to send $subject\n".$smtp->message;
-
+	if ($smtp_server =~ m#^/#) {
+		my $pid = open my $sm, '|-';
+		defined $pid or die $!;
+		if (!$pid) {
+			exec($smtp_server,'-i',@recipients) or die $!;
+		}
+		print $sm "$header\n$message";
+		close $sm or die $?;
+	} else {
+		$smtp ||= Net::SMTP->new( $smtp_server );
+		$smtp->mail( $from ) or die $smtp->message;
+		$smtp->to( @recipients ) or die $smtp->message;
+		$smtp->data or die $smtp->message;
+		$smtp->datasend("$header\n$message") or die $smtp->message;
+		$smtp->dataend() or die $smtp->message;
+		$smtp->ok or die "Failed to send $subject\n".$smtp->message;
+	}
 	if ($quiet) {
 		printf "Sent %s\n", $subject;
 	} else {
-		print "OK. Log says:
-Date: $date
-Server: $smtp_server Port: 25
-From: $from
-Subject: $subject
-Cc: $cc
-To: $to
-
-Result: ", $smtp->code, ' ', ($smtp->message =~ /\n([^\n]+\n)$/s), "\n";
+		print "OK. Log says:\nDate: $date\n";
+		if ($smtp) {
+			print "Server: $smtp_server\n";
+		} else {
+			print "Sendmail: $smtp_server\n";
+		}
+		print "From: $from\nSubject: $subject\nCc: $cc\nTo: $to\n\n";
+		if ($smtp) {
+			print "Result: ", $smtp->code, ' ',
+				($smtp->message =~ /\n([^\n]+\n)$/s), "\n";
+		} else {
+			print "Result: OK\n";
+		}
 	}
 }
 
@@ -430,9 +502,14 @@ sub unique_email_list(@) {
 	my @emails;
 
 	foreach my $entry (@_) {
-		my $clean = extract_valid_address($entry);
-		next if $seen{$clean}++;
-		push @emails, $entry;
+		if (my $clean = extract_valid_address($entry)) {
+			$seen{$clean} ||= 0;
+			next if $seen{$clean}++;
+			push @emails, $entry;
+		} else {
+			print STDERR "W: unable to extract a valid address",
+					" from: $entry\n";
+		}
 	}
 	return @emails;
 }

git-tag.sh

@@ -25,14 +25,12 @@ do
 	force=1
 	;;
     -l)
-        cd "$GIT_DIR/refs" &&
 	case "$#" in
 	1)
-		find tags -type f -print ;;
-	*)
-		shift
-		find tags -type f -print | grep "$@" ;;
+		set x . ;;
 	esac
+	shift
+	git rev-parse --symbolic --tags | sort | grep "$@"
 	exit $?
 	;;
     -m)

git.c

@@ -50,6 +50,10 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "fmt-patch", cmd_format_patch },
 		{ "count-objects", cmd_count_objects },
 		{ "diff", cmd_diff },
+		{ "grep", cmd_grep },
+		{ "rev-list", cmd_rev_list },
+		{ "init-db", cmd_init_db },
+		{ "check-ref-format", cmd_check_ref_format }
 	};
 	int i;
 

git.spec.in

@@ -74,12 +74,12 @@ Git revision tree visualiser ('gitk')
 %setup -q
 
 %build
-make %{_smp_mflags} CFLAGS="$RPM_OPT_FLAGS" WITH_OWN_SUBPROCESS_PY=YesPlease WITH_SEND_EMAIL=1 \
+make %{_smp_mflags} CFLAGS="$RPM_OPT_FLAGS" WITH_OWN_SUBPROCESS_PY=YesPlease \
      prefix=%{_prefix} all %{!?_without_docs: doc}
 
 %install
 rm -rf $RPM_BUILD_ROOT
-make %{_smp_mflags} DESTDIR=$RPM_BUILD_ROOT WITH_OWN_SUBPROCESS_PY=YesPlease WITH_SEND_EMAIL=1 \
+make %{_smp_mflags} DESTDIR=$RPM_BUILD_ROOT WITH_OWN_SUBPROCESS_PY=YesPlease \
      prefix=%{_prefix} mandir=%{_mandir} \
      install %{!?_without_docs: install-doc}
 

ls-tree.c

@@ -142,8 +142,8 @@ int main(int argc, const char **argv)
 
 	if (argc < 2)
 		usage(ls_tree_usage);
-	if (get_sha1(argv[1], sha1) < 0)
-		usage(ls_tree_usage);
+	if (get_sha1(argv[1], sha1))
+		die("Not a valid object name %s", argv[1]);
 
 	pathspec = get_pathspec(prefix, argv + 2);
 	tree = parse_tree_indirect(sha1);

merge-base.c

@@ -82,8 +82,9 @@ static struct commit *interesting(struct commit_list *list)
  * commit B.
  *
  *
- * Another pathological example how this thing can fail to mark an ancestor
- * of a merge base as UNINTERESTING without the postprocessing phase.
+ * Another pathological example how this thing used to fail to mark an
+ * ancestor of a merge base as UNINTERESTING before we introduced the
+ * postprocessing phase (mark_reachable_commits).
  *
  *		  2
  *		  H
@@ -118,7 +119,9 @@ static struct commit *interesting(struct commit_list *list)
  *	 D7			2 3 7 7 3 2 1 2
  *	 E7			2 3 7 7 7 2 1 2
  *
- * and we end up showing E as an interesting merge base.
+ * and we ended up showing E as an interesting merge base.
+ * The postprocessing phase re-injects C and continues traversal
+ * to contaminate D and E.
  */
 
 static int show_all = 0;
@@ -247,10 +250,12 @@ int main(int argc, char **argv)
 			usage(merge_base_usage);
 		argc--; argv++;
 	}
-	if (argc != 3 ||
-	    get_sha1(argv[1], rev1key) ||
-	    get_sha1(argv[2], rev2key))
+	if (argc != 3)
 		usage(merge_base_usage);
+	if (get_sha1(argv[1], rev1key))
+		die("Not a valid object name %s", argv[1]);
+	if (get_sha1(argv[2], rev2key))
+		die("Not a valid object name %s", argv[2]);
 	rev1 = lookup_commit_reference(rev1key);
 	rev2 = lookup_commit_reference(rev2key);
 	if (!rev1 || !rev2)

merge-tree.c

@@ -149,7 +149,7 @@ static void *get_tree_descriptor(struct tree_desc *desc, const char *rev)
 	unsigned char sha1[20];
 	void *buf;
 
-	if (get_sha1(rev, sha1) < 0)
+	if (get_sha1(rev, sha1))
 		die("unknown rev %s", rev);
 	buf = fill_tree_descriptor(desc, sha1);
 	if (!buf)

pack-objects.c

@@ -156,7 +156,7 @@ static void prepare_pack_revindex(struct pack_revindex *rix)
 
 	rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1));
 	for (i = 0; i < num_ent; i++) {
-		long hl = *((long *)(index + 24 * i));
+		unsigned int hl = *((unsigned int *)(index + 24 * i));
 		rix->revindex[i] = ntohl(hl);
 	}
 	/* This knows the pack format -- the 20-byte trailer
@@ -994,6 +994,7 @@ static int type_size_sort(const struct object_entry *a, const struct object_entr
 struct unpacked {
 	struct object_entry *entry;
 	void *data;
+	struct delta_index *index;
 };
 
 /*
@@ -1004,61 +1005,59 @@ struct unpacked {
  * more importantly, the bigger file is likely the more recent
  * one.
  */
-static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_depth)
+static int try_delta(struct unpacked *trg, struct unpacked *src,
+		     struct delta_index *src_index, unsigned max_depth)
 {
-	struct object_entry *cur_entry = cur->entry;
-	struct object_entry *old_entry = old->entry;
-	unsigned long size, oldsize, delta_size, sizediff;
-	long max_size;
+	struct object_entry *trg_entry = trg->entry;
+	struct object_entry *src_entry = src->entry;
+	unsigned long size, src_size, delta_size, sizediff, max_size;
 	void *delta_buf;
 
 	/* Don't bother doing diffs between different types */
-	if (cur_entry->type != old_entry->type)
+	if (trg_entry->type != src_entry->type)
 		return -1;
 
 	/* We do not compute delta to *create* objects we are not
 	 * going to pack.
 	 */
-	if (cur_entry->preferred_base)
+	if (trg_entry->preferred_base)
 		return -1;
 
-	/* If the current object is at pack edge, take the depth the
+	/*
+	 * If the current object is at pack edge, take the depth the
 	 * objects that depend on the current object into account --
 	 * otherwise they would become too deep.
 	 */
-	if (cur_entry->delta_child) {
-		if (max_depth <= cur_entry->delta_limit)
+	if (trg_entry->delta_child) {
+		if (max_depth <= trg_entry->delta_limit)
 			return 0;
-		max_depth -= cur_entry->delta_limit;
+		max_depth -= trg_entry->delta_limit;
 	}
-
-	if (old_entry->depth >= max_depth)
+	if (src_entry->depth >= max_depth)
 		return 0;
 
-	/*
-	 * NOTE!
-	 *
-	 * We always delta from the bigger to the smaller, since that's
-	 * more space-efficient (deletes don't have to say _what_ they
-	 * delete).
-	 */
-	size = cur_entry->size;
-	max_size = size / 2 - 20;
-	if (cur_entry->delta)
-		max_size = cur_entry->delta_size-1;
-	oldsize = old_entry->size;
-	sizediff = oldsize < size ? size - oldsize : 0;
+	/* Now some size filtering heuristics. */
+	size = trg_entry->size;
+	max_size = size/2 - 20;
+	max_size = max_size * (max_depth - src_entry->depth) / max_depth;
+	if (max_size == 0)
+		return 0;
+	if (trg_entry->delta && trg_entry->delta_size <= max_size)
+		max_size = trg_entry->delta_size-1;
+	src_size = src_entry->size;
+	sizediff = src_size < size ? size - src_size : 0;
 	if (sizediff >= max_size)
 		return 0;
-	delta_buf = diff_delta(old->data, oldsize,
-			       cur->data, size, &delta_size, max_size);
+
+	delta_buf = create_delta(src_index, trg->data, size, &delta_size, max_size);
 	if (!delta_buf)
 		return 0;
-	cur_entry->delta = old_entry;
-	cur_entry->delta_size = delta_size;
-	cur_entry->depth = old_entry->depth + 1;
+
+	trg_entry->delta = src_entry;
+	trg_entry->delta_size = delta_size;
+	trg_entry->depth = src_entry->depth + 1;
 	free(delta_buf);
-	return 0;
+	return 1;
 }
 
 static void progress_interval(int signum)
@@ -1108,12 +1107,14 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 
 		if (entry->size < 50)
 			continue;
-
+		free_delta_index(n->index);
+		n->index = NULL;
 		free(n->data);
 		n->entry = entry;
 		n->data = read_sha1_file(entry->sha1, type, &size);
 		if (size != entry->size)
-			die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size);
+			die("object %s inconsistent object length (%lu vs %lu)",
+			    sha1_to_hex(entry->sha1), size, entry->size);
 
 		j = window;
 		while (--j > 0) {
@@ -1124,18 +1125,20 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 			m = array + other_idx;
 			if (!m->entry)
 				break;
-			if (try_delta(n, m, depth) < 0)
+			if (try_delta(n, m, m->index, depth) < 0)
 				break;
 		}
-#if 0
 		/* if we made n a delta, and if n is already at max
 		 * depth, leaving it in the window is pointless.  we
 		 * should evict it first.
-		 * ... in theory only; somehow this makes things worse.
 		 */
 		if (entry->delta && depth <= entry->depth)
 			continue;
-#endif
+
+		n->index = create_delta_index(n->data, size);
+		if (!n->index)
+			die("out of memory");
+
 		idx++;
 		if (idx >= window)
 			idx = 0;
@@ -1144,8 +1147,10 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 	if (progress)
 		fputc('\n', stderr);
 
-	for (i = 0; i < window; ++i)
+	for (i = 0; i < window; ++i) {
+		free_delta_index(array[i].index);
 		free(array[i].data);
+	}
 	free(array);
 }
 

patch-delta.c

@@ -13,7 +13,7 @@
 #include <string.h>
 #include "delta.h"
 
-void *patch_delta(void *src_buf, unsigned long src_size,
+void *patch_delta(const void *src_buf, unsigned long src_size,
 		  const void *delta_buf, unsigned long delta_size,
 		  unsigned long *dst_size)
 {

read-cache.c

@@ -496,6 +496,123 @@ int add_cache_entry(struct cache_entry *ce, int option)
 	return 0;
 }
 
+/* Three functions to allow overloaded pointer return; see linux/err.h */
+static inline void *ERR_PTR(long error)
+{
+	return (void *) error;
+}
+
+static inline long PTR_ERR(const void *ptr)
+{
+	return (long) ptr;
+}
+
+static inline long IS_ERR(const void *ptr)
+{
+	return (unsigned long)ptr > (unsigned long)-1000L;
+}
+
+/*
+ * "refresh" does not calculate a new sha1 file or bring the
+ * cache up-to-date for mode/content changes. But what it
+ * _does_ do is to "re-match" the stat information of a file
+ * with the cache, so that you can refresh the cache for a
+ * file that hasn't been changed but where the stat entry is
+ * out of date.
+ *
+ * For example, you'd want to do this after doing a "git-read-tree",
+ * to link up the stat cache details with the proper files.
+ */
+static struct cache_entry *refresh_entry(struct cache_entry *ce, int really)
+{
+	struct stat st;
+	struct cache_entry *updated;
+	int changed, size;
+
+	if (lstat(ce->name, &st) < 0)
+		return ERR_PTR(-errno);
+
+	changed = ce_match_stat(ce, &st, really);
+	if (!changed) {
+		if (really && assume_unchanged &&
+		    !(ce->ce_flags & htons(CE_VALID)))
+			; /* mark this one VALID again */
+		else
+			return NULL;
+	}
+
+	if (ce_modified(ce, &st, really))
+		return ERR_PTR(-EINVAL);
+
+	size = ce_size(ce);
+	updated = xmalloc(size);
+	memcpy(updated, ce, size);
+	fill_stat_cache_info(updated, &st);
+
+	/* In this case, if really is not set, we should leave
+	 * CE_VALID bit alone.  Otherwise, paths marked with
+	 * --no-assume-unchanged (i.e. things to be edited) will
+	 * reacquire CE_VALID bit automatically, which is not
+	 * really what we want.
+	 */
+	if (!really && assume_unchanged && !(ce->ce_flags & htons(CE_VALID)))
+		updated->ce_flags &= ~htons(CE_VALID);
+
+	return updated;
+}
+
+int refresh_cache(unsigned int flags)
+{
+	int i;
+	int has_errors = 0;
+	int really = (flags & REFRESH_REALLY) != 0;
+	int allow_unmerged = (flags & REFRESH_UNMERGED) != 0;
+	int quiet = (flags & REFRESH_QUIET) != 0;
+	int not_new = (flags & REFRESH_IGNORE_MISSING) != 0;
+
+	for (i = 0; i < active_nr; i++) {
+		struct cache_entry *ce, *new;
+		ce = active_cache[i];
+		if (ce_stage(ce)) {
+			while ((i < active_nr) &&
+			       ! strcmp(active_cache[i]->name, ce->name))
+				i++;
+			i--;
+			if (allow_unmerged)
+				continue;
+			printf("%s: needs merge\n", ce->name);
+			has_errors = 1;
+			continue;
+		}
+
+		new = refresh_entry(ce, really);
+		if (!new)
+			continue;
+		if (IS_ERR(new)) {
+			if (not_new && PTR_ERR(new) == -ENOENT)
+				continue;
+			if (really && PTR_ERR(new) == -EINVAL) {
+				/* If we are doing --really-refresh that
+				 * means the index is not valid anymore.
+				 */
+				ce->ce_flags &= ~htons(CE_VALID);
+				active_cache_changed = 1;
+			}
+			if (quiet)
+				continue;
+			printf("%s: needs update\n", ce->name);
+			has_errors = 1;
+			continue;
+		}
+		active_cache_changed = 1;
+		/* You can NOT just free active_cache[i] here, since it
+		 * might not be necessarily malloc()ed but can also come
+		 * from mmap(). */
+		active_cache[i] = new;
+	}
+	return has_errors;
+}
+
 static int verify_hdr(struct cache_header *hdr, unsigned long size)
 {
 	SHA_CTX c;
@@ -552,7 +669,7 @@ int read_cache(void)
 
 	active_nr = ntohl(hdr->hdr_entries);
 	active_alloc = alloc_nr(active_nr);
-	active_cache = calloc(active_alloc, sizeof(struct cache_entry *));
+	active_cache = xcalloc(active_alloc, sizeof(struct cache_entry *));
 
 	offset = sizeof(*hdr);
 	for (i = 0; i < active_nr; i++) {

read-tree.c

@@ -12,6 +12,7 @@
 #include <sys/time.h>
 #include <signal.h>
 
+static int reset = 0;
 static int merge = 0;
 static int update = 0;
 static int index_only = 0;
@@ -407,7 +408,7 @@ static void verify_uptodate(struct cache_entry *ce)
 {
 	struct stat st;
 
-	if (index_only)
+	if (index_only || reset)
 		return;
 
 	if (!lstat(ce->name, &st)) {
@@ -416,11 +417,30 @@ static void verify_uptodate(struct cache_entry *ce)
 			return;
 		errno = 0;
 	}
+	if (reset) {
+		ce->ce_flags |= htons(CE_UPDATE);
+		return;
+	}
 	if (errno == ENOENT)
 		return;
 	die("Entry '%s' not uptodate. Cannot merge.", ce->name);
 }
 
+/*
+ * We do not want to remove or overwrite a working tree file that
+ * is not tracked.
+ */
+static void verify_absent(const char *path, const char *action)
+{
+	struct stat st;
+
+	if (index_only || reset || !update)
+		return;
+	if (!lstat(path, &st))
+		die("Untracked working tree file '%s' "
+		    "would be %s by merge.", path, action);
+}
+
 static int merged_entry(struct cache_entry *merge, struct cache_entry *old)
 {
 	merge->ce_flags |= htons(CE_UPDATE);
@@ -438,6 +458,9 @@ static int merged_entry(struct cache_entry *merge, struct cache_entry *old)
 			verify_uptodate(old);
 		}
 	}
+	else
+		verify_absent(merge->name, "overwritten");
+
 	merge->ce_flags &= ~htons(CE_STAGEMASK);
 	add_cache_entry(merge, ADD_CACHE_OK_TO_ADD);
 	return 1;
@@ -447,6 +470,8 @@ static int deleted_entry(struct cache_entry *ce, struct cache_entry *old)
 {
 	if (old)
 		verify_uptodate(old);
+	else
+		verify_absent(ce->name, "removed");
 	ce->ce_mode = 0;
 	add_cache_entry(ce, ADD_CACHE_OK_TO_ADD);
 	return 1;
@@ -482,6 +507,7 @@ static int threeway_merge(struct cache_entry **stages)
 	int count;
 	int head_match = 0;
 	int remote_match = 0;
+	const char *path = NULL;
 
 	int df_conflict_head = 0;
 	int df_conflict_remote = 0;
@@ -493,8 +519,11 @@ static int threeway_merge(struct cache_entry **stages)
 	for (i = 1; i < head_idx; i++) {
 		if (!stages[i])
 			any_anc_missing = 1;
-		else
+		else {
+			if (!path)
+				path = stages[i]->name;
 			no_anc_exists = 0;
+		}
 	}
 
 	index = stages[0];
@@ -510,8 +539,15 @@ static int threeway_merge(struct cache_entry **stages)
 		remote = NULL;
 	}
 
+	if (!path && index)
+		path = index->name;
+	if (!path && head)
+		path = head->name;
+	if (!path && remote)
+		path = remote->name;
+
 	/* First, if there's a #16 situation, note that to prevent #13
-	 * and #14. 
+	 * and #14.
 	 */
 	if (!same(remote, head)) {
 		for (i = 1; i < head_idx; i++) {
@@ -570,6 +606,8 @@ static int threeway_merge(struct cache_entry **stages)
 		    (remote_deleted && head && head_match)) {
 			if (index)
 				return deleted_entry(index, index);
+			else if (path)
+				verify_absent(path, "removed");
 			return 0;
 		}
 		/*
@@ -587,6 +625,8 @@ static int threeway_merge(struct cache_entry **stages)
 	if (index) {
 		verify_uptodate(index);
 	}
+	else if (path)
+		verify_absent(path, "overwritten");
 
 	nontrivial_merge = 1;
 
@@ -684,11 +724,17 @@ static int oneway_merge(struct cache_entry **src)
 			     merge_size);
 
 	if (!a)
-		return 0;
+		return deleted_entry(old, old);
 	if (old && same(old, a)) {
+		if (reset) {
+			struct stat st;
+			if (lstat(old->name, &st) ||
+			    ce_match_stat(old, &st, 1))
+				old->ce_flags |= htons(CE_UPDATE);
+		}
 		return keep_entry(old);
 	}
-	return merged_entry(a, NULL);
+	return merged_entry(a, old);
 }
 
 static int read_cache_unmerged(void)
@@ -719,7 +765,7 @@ static struct cache_file cache_file;
 
 int main(int argc, char **argv)
 {
-	int i, newfd, reset, stage = 0;
+	int i, newfd, stage = 0;
 	unsigned char sha1[20];
 	merge_fn_t fn = NULL;
 
@@ -794,8 +840,8 @@ int main(int argc, char **argv)
 		if (1 < index_only + update)
 			usage(read_tree_usage);
 
-		if (get_sha1(arg, sha1) < 0)
-			usage(read_tree_usage);
+		if (get_sha1(arg, sha1))
+			die("Not a valid object name %s", arg);
 		if (list_tree(sha1) < 0)
 			die("failed to unpack tree object %s", arg);
 		stage++;

refs.c

@@ -114,7 +114,7 @@ int read_ref(const char *filename, unsigned char *sha1)
 	return -1;
 }
 
-static int do_for_each_ref(const char *base, int (*fn)(const char *path, const unsigned char *sha1))
+static int do_for_each_ref(const char *base, int (*fn)(const char *path, const unsigned char *sha1), int trim)
 {
 	int retval = 0;
 	DIR *dir = opendir(git_path("%s", base));
@@ -146,7 +146,7 @@ static int do_for_each_ref(const char *base, int (*fn)(const char *path, const u
 			if (stat(git_path("%s", path), &st) < 0)
 				continue;
 			if (S_ISDIR(st.st_mode)) {
-				retval = do_for_each_ref(path, fn);
+				retval = do_for_each_ref(path, fn, trim);
 				if (retval)
 					break;
 				continue;
@@ -160,7 +160,7 @@ static int do_for_each_ref(const char *base, int (*fn)(const char *path, const u
 				      "commit object!", path);
 				continue;
 			}
-			retval = fn(path, sha1);
+			retval = fn(path + trim, sha1);
 			if (retval)
 				break;
 		}
@@ -180,7 +180,22 @@ int head_ref(int (*fn)(const char *path, const unsigned char *sha1))
 
 int for_each_ref(int (*fn)(const char *path, const unsigned char *sha1))
 {
-	return do_for_each_ref("refs", fn);
+	return do_for_each_ref("refs", fn, 0);
+}
+
+int for_each_tag_ref(int (*fn)(const char *path, const unsigned char *sha1))
+{
+	return do_for_each_ref("refs/tags", fn, 10);
+}
+
+int for_each_branch_ref(int (*fn)(const char *path, const unsigned char *sha1))
+{
+	return do_for_each_ref("refs/heads", fn, 11);
+}
+
+int for_each_remote_ref(int (*fn)(const char *path, const unsigned char *sha1))
+{
+	return do_for_each_ref("refs/remotes", fn, 13);
 }
 
 static char *ref_file_name(const char *ref)
@@ -205,12 +220,9 @@ static char *ref_lock_file_name(const char *ref)
 
 int get_ref_sha1(const char *ref, unsigned char *sha1)
 {
-	const char *filename;
-
 	if (check_ref_format(ref))
 		return -1;
-	filename = git_path("refs/%s", ref);
-	return read_ref(filename, sha1);
+	return read_ref(git_path("refs/%s", ref), sha1);
 }
 
 static int lock_ref_file(const char *filename, const char *lock_filename,

refs.h

@@ -7,6 +7,9 @@
  */
 extern int head_ref(int (*fn)(const char *path, const unsigned char *sha1));
 extern int for_each_ref(int (*fn)(const char *path, const unsigned char *sha1));
+extern int for_each_tag_ref(int (*fn)(const char *path, const unsigned char *sha1));
+extern int for_each_branch_ref(int (*fn)(const char *path, const unsigned char *sha1));
+extern int for_each_remote_ref(int (*fn)(const char *path, const unsigned char *sha1));
 
 /** Reads the refs file specified into sha1 **/
 extern int get_ref_sha1(const char *ref, unsigned char *sha1);

repo-config.c

@@ -64,12 +64,13 @@ static int show_config(const char* key_, const char* value_)
 
 static int get_value(const char* key_, const char* regex_)
 {
-	int i;
+	char *tl;
 
-	key = malloc(strlen(key_)+1);
-	for (i = 0; key_[i]; i++)
-		key[i] = tolower(key_[i]);
-	key[i] = 0;
+	key = strdup(key_);
+	for (tl=key+strlen(key)-1; tl >= key && *tl != '.'; --tl)
+		*tl = tolower(*tl);
+	for (tl=key; *tl && *tl != '.'; ++tl)
+		*tl = tolower(*tl);
 
 	if (use_key_regexp) {
 		key_regexp = (regex_t*)malloc(sizeof(regex_t));

rev-parse.c

@@ -36,6 +36,7 @@ static int is_rev_argument(const char *arg)
 		"--all",
 		"--bisect",
 		"--dense",
+		"--branches",
 		"--header",
 		"--max-age=",
 		"--max-count=",
@@ -45,7 +46,9 @@ static int is_rev_argument(const char *arg)
 		"--objects-edge",
 		"--parents",
 		"--pretty",
+		"--remotes",
 		"--sparse",
+		"--tags",
 		"--topo-order",
 		"--date-order",
 		"--unpacked",
@@ -165,7 +168,7 @@ int main(int argc, char **argv)
 	int i, as_is = 0, verify = 0;
 	unsigned char sha1[20];
 	const char *prefix = setup_git_directory();
-	
+
 	git_config(git_default_config);
 
 	for (i = 1; i < argc; i++) {
@@ -255,6 +258,18 @@ int main(int argc, char **argv)
 				for_each_ref(show_reference);
 				continue;
 			}
+			if (!strcmp(arg, "--branches")) {
+				for_each_branch_ref(show_reference);
+				continue;
+			}
+			if (!strcmp(arg, "--tags")) {
+				for_each_tag_ref(show_reference);
+				continue;
+			}
+			if (!strcmp(arg, "--remotes")) {
+				for_each_remote_ref(show_reference);
+				continue;
+			}
 			if (!strcmp(arg, "--show-prefix")) {
 				if (prefix)
 					puts(prefix);

revision.c

@@ -794,7 +794,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 			local_flags = UNINTERESTING;
 			arg++;
 		}
-		if (get_sha1(arg, sha1) < 0) {
+		if (get_sha1(arg, sha1)) {
 			int j;
 
 			if (seen_dashdash || local_flags)
@@ -820,7 +820,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 	if (def && !revs->pending_objects) {
 		unsigned char sha1[20];
 		struct object *object;
-		if (get_sha1(def, sha1) < 0)
+		if (get_sha1(def, sha1))
 			die("bad default revision '%s'", def);
 		object = get_reference(revs, def, sha1, 0);
 		add_pending_object(revs, object, def);

sha1_file.c

@@ -217,6 +217,8 @@ char *sha1_pack_index_name(const unsigned char *sha1)
 struct alternate_object_database *alt_odb_list;
 static struct alternate_object_database **alt_odb_tail;
 
+static void read_info_alternates(const char * alternates, int depth);
+
 /*
  * Prepare alternate object database registry.
  *
@@ -232,13 +234,84 @@ static struct alternate_object_database **alt_odb_tail;
  * SHA1, an extra slash for the first level indirection, and the
  * terminating NUL.
  */
+static int link_alt_odb_entry(const char * entry, int len, const char * relative_base, int depth)
+{
+	struct stat st;
+	const char *objdir = get_object_directory();
+	struct alternate_object_database *ent;
+	struct alternate_object_database *alt;
+	/* 43 = 40-byte + 2 '/' + terminating NUL */
+	int pfxlen = len;
+	int entlen = pfxlen + 43;
+	int base_len = -1;
+
+	if (*entry != '/' && relative_base) {
+		/* Relative alt-odb */
+		if (base_len < 0)
+			base_len = strlen(relative_base) + 1;
+		entlen += base_len;
+		pfxlen += base_len;
+	}
+	ent = xmalloc(sizeof(*ent) + entlen);
+
+	if (*entry != '/' && relative_base) {
+		memcpy(ent->base, relative_base, base_len - 1);
+		ent->base[base_len - 1] = '/';
+		memcpy(ent->base + base_len, entry, len);
+	}
+	else
+		memcpy(ent->base, entry, pfxlen);
+
+	ent->name = ent->base + pfxlen + 1;
+	ent->base[pfxlen + 3] = '/';
+	ent->base[pfxlen] = ent->base[entlen-1] = 0;
+
+	/* Detect cases where alternate disappeared */
+	if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) {
+		error("object directory %s does not exist; "
+		      "check .git/objects/info/alternates.",
+		      ent->base);
+		free(ent);
+		return -1;
+	}
+
+	/* Prevent the common mistake of listing the same
+	 * thing twice, or object directory itself.
+	 */
+	for (alt = alt_odb_list; alt; alt = alt->next) {
+		if (!memcmp(ent->base, alt->base, pfxlen)) {
+			free(ent);
+			return -1;
+		}
+	}
+	if (!memcmp(ent->base, objdir, pfxlen)) {
+		free(ent);
+		return -1;
+	}
+
+	/* add the alternate entry */
+	*alt_odb_tail = ent;
+	alt_odb_tail = &(ent->next);
+	ent->next = NULL;
+
+	/* recursively add alternates */
+	read_info_alternates(ent->base, depth + 1);
+
+	ent->base[pfxlen] = '/';
+
+	return 0;
+}
+
 static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
-				 const char *relative_base)
+				 const char *relative_base, int depth)
 {
 	const char *cp, *last;
-	struct alternate_object_database *ent;
-	const char *objdir = get_object_directory();
-	int base_len = -1;
+
+	if (depth > 5) {
+		error("%s: ignoring alternate object stores, nesting too deep.",
+				relative_base);
+		return;
+	}
 
 	last = alt;
 	while (last < ep) {
@@ -249,60 +322,15 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
 			last = cp + 1;
 			continue;
 		}
-		for ( ; cp < ep && *cp != sep; cp++)
-			;
+		while (cp < ep && *cp != sep)
+			cp++;
 		if (last != cp) {
-			struct stat st;
-			struct alternate_object_database *alt;
-			/* 43 = 40-byte + 2 '/' + terminating NUL */
-			int pfxlen = cp - last;
-			int entlen = pfxlen + 43;
-
-			if (*last != '/' && relative_base) {
-				/* Relative alt-odb */
-				if (base_len < 0)
-					base_len = strlen(relative_base) + 1;
-				entlen += base_len;
-				pfxlen += base_len;
-			}
-			ent = xmalloc(sizeof(*ent) + entlen);
-
-			if (*last != '/' && relative_base) {
-				memcpy(ent->base, relative_base, base_len - 1);
-				ent->base[base_len - 1] = '/';
-				memcpy(ent->base + base_len,
-				       last, cp - last);
-			}
-			else
-				memcpy(ent->base, last, pfxlen);
-
-			ent->name = ent->base + pfxlen + 1;
-			ent->base[pfxlen + 3] = '/';
-			ent->base[pfxlen] = ent->base[entlen-1] = 0;
-
-			/* Detect cases where alternate disappeared */
-			if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) {
-				error("object directory %s does not exist; "
-				      "check .git/objects/info/alternates.",
-				      ent->base);
-				goto bad;
-			}
-			ent->base[pfxlen] = '/';
-
-			/* Prevent the common mistake of listing the same
-			 * thing twice, or object directory itself.
-			 */
-			for (alt = alt_odb_list; alt; alt = alt->next)
-				if (!memcmp(ent->base, alt->base, pfxlen))
-					goto bad;
-			if (!memcmp(ent->base, objdir, pfxlen)) {
-			bad:
-				free(ent);
-			}
-			else {
-				*alt_odb_tail = ent;
-				alt_odb_tail = &(ent->next);
-				ent->next = NULL;
+			if ((*last != '/') && depth) {
+				error("%s: ignoring relative alternate object store %s",
+						relative_base, last);
+			} else {
+				link_alt_odb_entry(last, cp - last,
+						relative_base, depth);
 			}
 		}
 		while (cp < ep && *cp == sep)
@@ -311,23 +339,14 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
 	}
 }
 
-void prepare_alt_odb(void)
+static void read_info_alternates(const char * relative_base, int depth)
 {
-	char path[PATH_MAX];
 	char *map;
-	int fd;
 	struct stat st;
-	char *alt;
+	char path[PATH_MAX];
+	int fd;
 
-	alt = getenv(ALTERNATE_DB_ENVIRONMENT);
-	if (!alt) alt = "";
-
-	if (alt_odb_tail)
-		return;
-	alt_odb_tail = &alt_odb_list;
-	link_alt_odb_entries(alt, alt + strlen(alt), ':', NULL);
-
-	sprintf(path, "%s/info/alternates", get_object_directory());
+	sprintf(path, "%s/info/alternates", relative_base);
 	fd = open(path, O_RDONLY);
 	if (fd < 0)
 		return;
@@ -340,11 +359,26 @@ void prepare_alt_odb(void)
 	if (map == MAP_FAILED)
 		return;
 
-	link_alt_odb_entries(map, map + st.st_size, '\n',
-			     get_object_directory());
+	link_alt_odb_entries(map, map + st.st_size, '\n', relative_base, depth);
+
 	munmap(map, st.st_size);
 }
 
+void prepare_alt_odb(void)
+{
+	char *alt;
+
+	alt = getenv(ALTERNATE_DB_ENVIRONMENT);
+	if (!alt) alt = "";
+
+	if (alt_odb_tail)
+		return;
+	alt_odb_tail = &alt_odb_list;
+	link_alt_odb_entries(alt, alt + strlen(alt), ':', NULL, 0);
+
+	read_info_alternates(get_object_directory(), 0);
+}
+
 static char *find_sha1_file(const unsigned char *sha1, struct stat *st)
 {
 	char *name = sha1_file_name(sha1);
@@ -1127,7 +1161,7 @@ int find_pack_entry_one(const unsigned char *sha1,
 		int mi = (lo + hi) / 2;
 		int cmp = memcmp(index + 24 * mi + 4, sha1, 20);
 		if (!cmp) {
-			e->offset = ntohl(*((int*)(index + 24 * mi)));
+			e->offset = ntohl(*((unsigned int *)(index + 24 * mi)));
 			memcpy(e->sha1, sha1, 20);
 			e->p = p;
 			return 1;

sha1_name.c

@@ -458,17 +458,56 @@ int get_sha1(const char *name, unsigned char *sha1)
 {
 	int ret;
 	unsigned unused;
+	int namelen = strlen(name);
+	const char *cp;
 
 	prepare_alt_odb();
-	ret = get_sha1_1(name, strlen(name), sha1);
-	if (ret < 0) {
-		const char *cp = strchr(name, ':');
-		if (cp) {
-			unsigned char tree_sha1[20];
-			if (!get_sha1_1(name, cp-name, tree_sha1))
-				return get_tree_entry(tree_sha1, cp+1, sha1,
-						      &unused);
+	ret = get_sha1_1(name, namelen, sha1);
+	if (!ret)
+		return ret;
+	/* sha1:path --> object name of path in ent sha1
+	 * :path -> object name of path in index
+	 * :[0-3]:path -> object name of path in index at stage
+	 */
+	if (name[0] == ':') {
+		int stage = 0;
+		struct cache_entry *ce;
+		int pos;
+		if (namelen < 3 ||
+		    name[2] != ':' ||
+		    name[1] < '0' || '3' < name[1])
+			cp = name + 1;
+		else {
+			stage = name[1] - '0';
+			cp = name + 3;
 		}
+		namelen = namelen - (cp - name);
+		if (!active_cache)
+			read_cache();
+		if (active_nr < 0)
+			return -1;
+		pos = cache_name_pos(cp, namelen);
+		if (pos < 0)
+			pos = -pos - 1;
+		while (pos < active_nr) {
+			ce = active_cache[pos];
+			if (ce_namelen(ce) != namelen ||
+			    memcmp(ce->name, cp, namelen))
+				break;
+			if (ce_stage(ce) == stage) {
+				memcpy(sha1, ce->sha1, 20);
+				return 0;
+			}
+			pos++;
+		}
+		return -1;
+	}
+	cp = strchr(name, ':');
+	if (cp) {
+		unsigned char tree_sha1[20];
+		if (!get_sha1_1(name, cp-name, tree_sha1))
+			return get_tree_entry(tree_sha1, cp+1, sha1,
+					      &unused);
 	}
 	return ret;
 }

ssh-upload.c

@@ -134,7 +134,7 @@ int main(int argc, char **argv)
 	commit_id = argv[arg];
 	url = argv[arg + 1];
 	if (get_sha1(commit_id, sha1))
-		usage(ssh_push_usage);
+		die("Not a valid object name %s", commit_id);
 	memcpy(hex, sha1_to_hex(sha1), sizeof(hex));
 	argv[arg] = hex;
 

t/t1002-read-tree-m-u-2way.sh

@@ -39,7 +39,6 @@ test_expect_success \
      echo nitfol >nitfol &&
      echo bozbar >bozbar &&
      echo rezrov >rezrov &&
-     echo yomin >yomin &&
      git-update-index --add nitfol bozbar rezrov &&
      treeH=`git-write-tree` &&
      echo treeH $treeH &&
@@ -56,7 +55,8 @@ test_expect_success \
 
 test_expect_success \
     '1, 2, 3 - no carry forward' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      git-read-tree -m -u $treeH $treeM &&
      git-ls-files --stage >1-3.out &&
      cmp M.out 1-3.out &&
@@ -66,11 +66,12 @@ test_expect_success \
      check_cache_at frotz clean &&
      check_cache_at nitfol clean'
 
-echo '+100644 X 0	yomin' >expected
-
 test_expect_success \
     '4 - carry forward local addition.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
+     echo "+100644 X 0	yomin" >expected &&
+     echo yomin >yomin &&
      git-update-index --add yomin &&
      git-read-tree -m -u $treeH $treeM &&
      git-ls-files --stage >4.out || return 1
@@ -85,7 +86,9 @@ test_expect_success \
 
 test_expect_success \
     '5 - carry forward local addition.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
+     git-read-tree -m -u $treeH &&
      echo yomin >yomin &&
      git-update-index --add yomin &&
      echo yomin yomin >yomin &&
@@ -103,7 +106,9 @@ test_expect_success \
 
 test_expect_success \
     '6 - local addition already has the same.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
+     echo frotz >frotz &&
      git-update-index --add frotz &&
      git-read-tree -m -u $treeH $treeM &&
      git-ls-files --stage >6.out &&
@@ -117,7 +122,8 @@ test_expect_success \
 
 test_expect_success \
     '7 - local addition already has the same.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo frotz >frotz &&
      git-update-index --add frotz &&
      echo frotz frotz >frotz &&
@@ -134,14 +140,16 @@ test_expect_success \
 
 test_expect_success \
     '8 - conflicting addition.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo frotz frotz >frotz &&
      git-update-index --add frotz &&
      if git-read-tree -m -u $treeH $treeM; then false; else :; fi'
 
 test_expect_success \
     '9 - conflicting addition.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo frotz frotz >frotz &&
      git-update-index --add frotz &&
      echo frotz >frotz &&
@@ -149,7 +157,8 @@ test_expect_success \
 
 test_expect_success \
     '10 - path removed.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo rezrov >rezrov &&
      git-update-index --add rezrov &&
      git-read-tree -m -u $treeH $treeM &&
@@ -160,7 +169,8 @@ test_expect_success \
 
 test_expect_success \
     '11 - dirty path removed.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo rezrov >rezrov &&
      git-update-index --add rezrov &&
      echo rezrov rezrov >rezrov &&
@@ -168,14 +178,16 @@ test_expect_success \
 
 test_expect_success \
     '12 - unmatching local changes being removed.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo rezrov rezrov >rezrov &&
      git-update-index --add rezrov &&
      if git-read-tree -m -u $treeH $treeM; then false; else :; fi'
 
 test_expect_success \
     '13 - unmatching local changes being removed.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo rezrov rezrov >rezrov &&
      git-update-index --add rezrov &&
      echo rezrov >rezrov &&
@@ -188,7 +200,8 @@ EOF
 
 test_expect_success \
     '14 - unchanged in two heads.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo nitfol nitfol >nitfol &&
      git-update-index --add nitfol &&
      git-read-tree -m -u $treeH $treeM &&
@@ -207,7 +220,8 @@ test_expect_success \
 
 test_expect_success \
     '15 - unchanged in two heads.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo nitfol nitfol >nitfol &&
      git-update-index --add nitfol &&
      echo nitfol nitfol nitfol >nitfol &&
@@ -227,14 +241,16 @@ test_expect_success \
 
 test_expect_success \
     '16 - conflicting local change.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo bozbar bozbar >bozbar &&
      git-update-index --add bozbar &&
      if git-read-tree -m -u $treeH $treeM; then false; else :; fi'
 
 test_expect_success \
     '17 - conflicting local change.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo bozbar bozbar >bozbar &&
      git-update-index --add bozbar &&
      echo bozbar bozbar bozbar >bozbar &&
@@ -242,7 +258,8 @@ test_expect_success \
 
 test_expect_success \
     '18 - local change already having a good result.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo gnusto >bozbar &&
      git-update-index --add bozbar &&
      git-read-tree -m -u $treeH $treeM &&
@@ -254,7 +271,8 @@ test_expect_success \
 
 test_expect_success \
     '19 - local change already having a good result, further modified.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo gnusto >bozbar &&
      git-update-index --add bozbar &&
      echo gnusto gnusto >bozbar &&
@@ -273,7 +291,8 @@ test_expect_success \
 
 test_expect_success \
     '20 - no local change, use new tree.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo bozbar >bozbar &&
      git-update-index --add bozbar &&
      git-read-tree -m -u $treeH $treeM &&
@@ -285,7 +304,8 @@ test_expect_success \
 
 test_expect_success \
     '21 - no local change, dirty cache.' \
-    'rm -f .git/index &&
+    'rm -f .git/index nitfol bozbar rezrov frotz &&
+     git-read-tree --reset -u $treeH &&
      echo bozbar >bozbar &&
      git-update-index --add bozbar &&
      echo gnusto gnusto >bozbar &&
@@ -294,7 +314,7 @@ test_expect_success \
 # Also make sure we did not break DF vs DF/DF case.
 test_expect_success \
     'DF vs DF/DF case setup.' \
-    'rm -f .git/index &&
+    'rm -f .git/index
      echo DF >DF &&
      git-update-index --add DF &&
      treeDF=`git-write-tree` &&

t/t1300-repo-config.sh

@@ -229,7 +229,7 @@ test_expect_failure 'invalid key' 'git-repo-config inval.2key blabla'
 test_expect_success 'correct key' 'git-repo-config 123456.a123 987'
 
 test_expect_success 'hierarchical section' \
-	'git-repo-config 1.2.3.alpha beta'
+	'git-repo-config Version.1.2.3eX.Alpha beta'
 
 cat > expect << EOF
 [beta] ; silly comment # another comment
@@ -241,8 +241,8 @@ noIndent= sillyValue ; 'nother silly comment
 	NoNewLine = wow2 for me
 [123456]
 	a123 = 987
-[1.2.3]
-	alpha = beta
+[Version "1.2.3eX"]
+	Alpha = beta
 EOF
 
 test_expect_success 'hierarchical section value' 'cmp .git/config expect'
@@ -251,7 +251,7 @@ cat > expect << EOF
 beta.noindent=sillyValue
 nextsection.nonewline=wow2 for me
 123456.a123=987
-1.2.3.alpha=beta
+version.1.2.3eX.alpha=beta
 EOF
 
 test_expect_success 'working --list' \

t/t2101-update-index-reupdate.sh

@@ -0,0 +1,82 @@
+#!/bin/sh
+#
+# Copyright (c) 2006 Junio C Hamano
+#
+
+test_description='git-update-index --again test.
+'
+
+. ./test-lib.sh
+
+test_expect_success 'update-index --add' \
+	'echo hello world >file1 &&
+	 echo goodbye people >file2 &&
+	 git-update-index --add file1 file2 &&
+	 git-ls-files -s >current &&
+	 cmp current - <<\EOF
+100644 3b18e512dba79e4c8300dd08aeb37f8e728b8dad 0	file1
+100644 9db8893856a8a02eaa73470054b7c1c5a7c82e47 0	file2
+EOF'
+
+test_expect_success 'update-index --again' \
+	'rm -f file1 &&
+	echo hello everybody >file2 &&
+	if git-update-index --again
+	then
+		echo should have refused to remove file1
+		exit 1
+	else
+		echo happy - failed as expected
+	fi &&
+	 git-ls-files -s >current &&
+	 cmp current - <<\EOF
+100644 3b18e512dba79e4c8300dd08aeb37f8e728b8dad 0	file1
+100644 9db8893856a8a02eaa73470054b7c1c5a7c82e47 0	file2
+EOF'
+
+test_expect_success 'update-index --remove --again' \
+	'git-update-index --remove --again &&
+	 git-ls-files -s >current &&
+	 cmp current - <<\EOF
+100644 0f1ae1422c2bf43f117d3dbd715c988a9ed2103f 0	file2
+EOF'
+
+test_expect_success 'first commit' 'git-commit -m initial'
+
+test_expect_success 'update-index again' \
+	'mkdir -p dir1 &&
+	echo hello world >dir1/file3 &&
+	echo goodbye people >file2 &&
+	git-update-index --add file2 dir1/file3 &&
+	echo hello everybody >file2
+	echo happy >dir1/file3 &&
+	git-update-index --again &&
+	git-ls-files -s >current &&
+	cmp current - <<\EOF
+100644 53ab446c3f4e42ce9bb728a0ccb283a101be4979 0	dir1/file3
+100644 0f1ae1422c2bf43f117d3dbd715c988a9ed2103f 0	file2
+EOF'
+
+test_expect_success 'update-index --update from subdir' \
+	'echo not so happy >file2 &&
+	cd dir1 &&
+	cat ../file2 >file3 &&
+	git-update-index --again &&
+	cd .. &&
+	git-ls-files -s >current &&
+	cmp current - <<\EOF
+100644 d7fb3f695f06c759dbf3ab00046e7cc2da22d10f 0	dir1/file3
+100644 0f1ae1422c2bf43f117d3dbd715c988a9ed2103f 0	file2
+EOF'
+
+test_expect_success 'update-index --update with pathspec' \
+	'echo very happy >file2 &&
+	cat file2 >dir1/file3 &&
+	git-update-index --again dir1/ &&
+	git-ls-files -s >current &&
+	cmp current - <<\EOF
+100644 594fb5bb1759d90998e2bf2a38261ae8e243c760 0	dir1/file3
+100644 0f1ae1422c2bf43f117d3dbd715c988a9ed2103f 0	file2
+EOF'
+
+test_done

t/t3500-cherry.sh

@@ -30,6 +30,7 @@ test_expect_success \
      git-commit -m "Add C." &&
 
      git-checkout -f master &&
+     rm -f B C &&
 
      echo Third >> A &&
      git-update-index A &&

t/t4002-diff-basic.sh

@@ -191,7 +191,7 @@ test_expect_success \
     'rm -fr Z [A-Z][A-Z] &&
      git-read-tree $tree_A &&
      git-checkout-index -f -a &&
-     git-read-tree -m $tree_O || return 1
+     git-read-tree --reset $tree_O || return 1
      git-update-index --refresh >/dev/null ;# this can exit non-zero
      git-diff-files >.test-a &&
      cmp_diff_files_output .test-a .test-recursive-OA'
@@ -201,7 +201,7 @@ test_expect_success \
     'rm -fr Z [A-Z][A-Z] &&
      git-read-tree $tree_B &&
      git-checkout-index -f -a &&
-     git-read-tree -m $tree_O || return 1
+     git-read-tree --reset $tree_O || return 1
      git-update-index --refresh >/dev/null ;# this can exit non-zero
      git-diff-files >.test-a &&
      cmp_diff_files_output .test-a .test-recursive-OB'
@@ -211,7 +211,7 @@ test_expect_success \
     'rm -fr Z [A-Z][A-Z] &&
      git-read-tree $tree_B &&
      git-checkout-index -f -a &&
-     git-read-tree -m $tree_A || return 1
+     git-read-tree --reset $tree_A || return 1
      git-update-index --refresh >/dev/null ;# this can exit non-zero
      git-diff-files >.test-a &&
      cmp_diff_files_output .test-a .test-recursive-AB'

t/t4012-diff-binary.sh

@@ -0,0 +1,85 @@
+#!/bin/sh
+#
+# Copyright (c) 2006 Junio C Hamano
+#
+
+test_description='Binary diff and apply
+'
+
+. ./test-lib.sh
+
+test_expect_success 'prepare repository' \
+	'echo AIT >a && echo BIT >b && echo CIT >c && echo DIT >d &&
+	 git-update-index --add a b c d &&
+	 echo git >a &&
+	 cat ../test4012.png >b &&
+	 echo git >c &&
+	 cat b b >d'
+
+test_expect_success 'diff without --binary' \
+	'git-diff | git-apply --stat --summary >current &&
+	 cmp current - <<\EOF
+ a |    2 +-
+ b |  Bin
+ c |    2 +-
+ d |  Bin
+ 4 files changed, 2 insertions(+), 2 deletions(-)
+EOF'
+
+test_expect_success 'diff with --binary' \
+	'git-diff --binary | git-apply --stat --summary >current &&
+	 cmp current - <<\EOF
+ a |    2 +-
+ b |  Bin
+ c |    2 +-
+ d |  Bin
+ 4 files changed, 2 insertions(+), 2 deletions(-)
+EOF'
+
+# apply needs to be able to skip the binary material correctly
+# in order to report the line number of a corrupt patch.
+test_expect_success 'apply detecting corrupt patch correctly' \
+	'git-diff | sed -e 's/-CIT/xCIT/' >broken &&
+	 if git-apply --stat --summary broken 2>detected
+	 then
+		echo unhappy - should have detected an error
+		(exit 1)
+	 else
+		echo happy
+	 fi &&
+	 detected=`cat detected` &&
+	 detected=`expr "$detected" : "fatal.*at line \\([0-9]*\\)\$"` &&
+	 detected=`sed -ne "${detected}p" broken` &&
+	 test "$detected" = xCIT'
+
+test_expect_success 'apply detecting corrupt patch correctly' \
+	'git-diff --binary | sed -e 's/-CIT/xCIT/' >broken &&
+	 if git-apply --stat --summary broken 2>detected
+	 then
+		echo unhappy - should have detected an error
+		(exit 1)
+	 else
+		echo happy
+	 fi &&
+	 detected=`cat detected` &&
+	 detected=`expr "$detected" : "fatal.*at line \\([0-9]*\\)\$"` &&
+	 detected=`sed -ne "${detected}p" broken` &&
+	 test "$detected" = xCIT'
+
+test_expect_success 'initial commit' 'git-commit -a -m initial'
+
+# Try removal (b), modification (d), and creation (e).
+test_expect_success 'diff-index with --binary' \
+	'echo AIT >a && mv b e && echo CIT >c && cat e >d &&
+	 git-update-index --add --remove a b c d e &&
+	 tree0=`git-write-tree` &&
+	 git-diff --cached --binary >current &&
+	 git-apply --stat --summary current'
+
+test_expect_success 'apply binary patch' \
+	'git-reset --hard &&
+	 git-apply --binary --index <current &&
+	 tree1=`git-write-tree` &&
+	 test "$tree1" = "$tree0"'
+
+test_done

t/t5700-clone-reference.sh

@@ -0,0 +1,78 @@
+#!/bin/sh
+#
+# Copyright (C) 2006 Martin Waitz <tali@admingilde.org>
+#
+
+test_description='test clone --reference'
+. ./test-lib.sh
+
+base_dir=`pwd`
+
+test_expect_success 'preparing first repository' \
+'test_create_repo A && cd A &&
+echo first > file1 &&
+git add file1 &&
+git commit -m initial'
+
+cd "$base_dir"
+
+test_expect_success 'preparing second repository' \
+'git clone A B && cd B &&
+echo second > file2 &&
+git add file2 &&
+git commit -m addition &&
+git repack -a -d &&
+git prune'
+
+cd "$base_dir"
+
+test_expect_success 'cloning with reference' \
+'git clone -l -s --reference B A C'
+
+cd "$base_dir"
+
+test_expect_success 'existance of info/alternates' \
+'test `wc -l <C/.git/objects/info/alternates` = 2'
+
+cd "$base_dir"
+
+test_expect_success 'pulling from reference' \
+'cd C &&
+git pull ../B'
+
+cd "$base_dir"
+
+test_expect_success 'that reference gets used' \
+'cd C &&
+echo "0 objects, 0 kilobytes" > expected &&
+git count-objects > current &&
+diff expected current'
+
+cd "$base_dir"
+
+test_expect_success 'updating origin' \
+'cd A &&
+echo third > file3 &&
+git add file3 &&
+git commit -m update &&
+git repack -a -d &&
+git prune'
+
+cd "$base_dir"
+
+test_expect_success 'pulling changes from origin' \
+'cd C &&
+git pull origin'
+
+cd "$base_dir"
+
+# the 2 local objects are commit and tree from the merge
+test_expect_success 'that alternate to origin gets used' \
+'cd C &&
+echo "2 objects" > expected &&
+git count-objects | cut -d, -f1 > current &&
+diff expected current'
+
+cd "$base_dir"
+
+test_done

t/t5710-info-alternate.sh

@@ -0,0 +1,105 @@
+#!/bin/sh
+#
+# Copyright (C) 2006 Martin Waitz <tali@admingilde.org>
+#
+
+test_description='test transitive info/alternate entries'
+. ./test-lib.sh
+
+# test that a file is not reachable in the current repository
+# but that it is after creating a info/alternate entry
+reachable_via() {
+	alternate="$1"
+	file="$2"
+	if git cat-file -e "HEAD:$file"; then return 1; fi
+	echo "$alternate" >> .git/objects/info/alternate
+	git cat-file -e "HEAD:$file"
+}
+
+test_valid_repo() {
+	git fsck-objects --full > fsck.log &&
+	test `wc -l < fsck.log` = 0
+}
+
+base_dir=`pwd`
+
+test_expect_success 'preparing first repository' \
+'test_create_repo A && cd A &&
+echo "Hello World" > file1 &&
+git add file1 &&
+git commit -m "Initial commit" file1 &&
+git repack -a -d &&
+git prune'
+
+cd "$base_dir"
+
+test_expect_success 'preparing second repository' \
+'git clone -l -s A B && cd B &&
+echo "foo bar" > file2 &&
+git add file2 &&
+git commit -m "next commit" file2 &&
+git repack -a -d -l &&
+git prune'
+
+cd "$base_dir"
+
+test_expect_success 'preparing third repository' \
+'git clone -l -s B C && cd C &&
+echo "Goodbye, cruel world" > file3 &&
+git add file3 &&
+git commit -m "one more" file3 &&
+git repack -a -d -l &&
+git prune'
+
+cd "$base_dir"
+
+test_expect_failure 'creating too deep nesting' \
+'git clone -l -s C D &&
+git clone -l -s D E &&
+git clone -l -s E F &&
+git clone -l -s F G &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_expect_success 'validity of third repository' \
+'cd C &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_expect_success 'validity of fourth repository' \
+'cd D &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_expect_success 'breaking of loops' \
+"echo '$base_dir/B/.git/objects' >> '$base_dir'/A/.git/objects/info/alternates&&
+cd C &&
+test_valid_repo"
+
+cd "$base_dir"
+
+test_expect_failure 'that info/alternates is neccessary' \
+'cd C &&
+rm .git/objects/info/alternates &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_expect_success 'that relative alternate is possible for current dir' \
+'cd C &&
+echo "../../../B/.git/objects" > .git/objects/info/alternates &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_expect_failure 'that relative alternate is only possible for current dir' \
+'cd D &&
+test_valid_repo'
+
+cd "$base_dir"
+
+test_done
+

t/t6022-merge-rename.sh

@@ -111,6 +111,7 @@ test_expect_success 'pull renaming branch into unrenaming one' \
 
 test_expect_success 'pull renaming branch into another renaming one' \
 '
+	rm -f B
 	git reset --hard
 	git checkout red
 	git pull . white && {

tar-tree.c

@@ -321,8 +321,8 @@ int main(int argc, char **argv)
 		strbuf_append_string(&current_path, "/");
 		/* FALLTHROUGH */
 	case 2:
-		if (get_sha1(argv[1], sha1) < 0)
-			usage(tar_tree_usage);
+		if (get_sha1(argv[1], sha1))
+			die("Not a valid object name %s", argv[1]);
 		break;
 	default:
 		usage(tar_tree_usage);

unpack-file.c

@@ -27,8 +27,10 @@ int main(int argc, char **argv)
 {
 	unsigned char sha1[20];
 
-	if (argc != 2 || get_sha1(argv[1], sha1))
+	if (argc != 2)
 		usage("git-unpack-file <sha1>");
+	if (get_sha1(argv[1], sha1))
+		die("Not a valid object name %s", argv[1]);
 
 	setup_git_directory();
 	git_config(git_default_config);

update-index.c

@@ -18,9 +18,6 @@
 static int allow_add;
 static int allow_remove;
 static int allow_replace;
-static int allow_unmerged; /* --refresh needing merge is not error */
-static int not_new; /* --refresh not having working tree files is not error */
-static int quiet; /* --refresh needing update is not error */
 static int info_only;
 static int force_remove;
 static int verbose;
@@ -28,23 +25,6 @@ static int mark_valid_only = 0;
 #define MARK_VALID 1
 #define UNMARK_VALID 2
 
-
-/* Three functions to allow overloaded pointer return; see linux/err.h */
-static inline void *ERR_PTR(long error)
-{
-	return (void *) error;
-}
-
-static inline long PTR_ERR(const void *ptr)
-{
-	return (long) ptr;
-}
-
-static inline long IS_ERR(const void *ptr)
-{
-	return (unsigned long)ptr > (unsigned long)-1000L;
-}
-
 static void report(const char *fmt, ...)
 {
 	va_list vp;
@@ -140,103 +120,6 @@ static int add_file_to_cache(const char *path)
 	return 0;
 }
 
-/*
- * "refresh" does not calculate a new sha1 file or bring the
- * cache up-to-date for mode/content changes. But what it
- * _does_ do is to "re-match" the stat information of a file
- * with the cache, so that you can refresh the cache for a
- * file that hasn't been changed but where the stat entry is
- * out of date.
- *
- * For example, you'd want to do this after doing a "git-read-tree",
- * to link up the stat cache details with the proper files.
- */
-static struct cache_entry *refresh_entry(struct cache_entry *ce, int really)
-{
-	struct stat st;
-	struct cache_entry *updated;
-	int changed, size;
-
-	if (lstat(ce->name, &st) < 0)
-		return ERR_PTR(-errno);
-
-	changed = ce_match_stat(ce, &st, really);
-	if (!changed) {
-		if (really && assume_unchanged &&
-		    !(ce->ce_flags & htons(CE_VALID)))
-			; /* mark this one VALID again */
-		else
-			return NULL;
-	}
-
-	if (ce_modified(ce, &st, really))
-		return ERR_PTR(-EINVAL);
-
-	size = ce_size(ce);
-	updated = xmalloc(size);
-	memcpy(updated, ce, size);
-	fill_stat_cache_info(updated, &st);
-
-	/* In this case, if really is not set, we should leave
-	 * CE_VALID bit alone.  Otherwise, paths marked with
-	 * --no-assume-unchanged (i.e. things to be edited) will
-	 * reacquire CE_VALID bit automatically, which is not
-	 * really what we want.
-	 */
-	if (!really && assume_unchanged && !(ce->ce_flags & htons(CE_VALID)))
-		updated->ce_flags &= ~htons(CE_VALID);
-
-	return updated;
-}
-
-static int refresh_cache(int really)
-{
-	int i;
-	int has_errors = 0;
-
-	for (i = 0; i < active_nr; i++) {
-		struct cache_entry *ce, *new;
-		ce = active_cache[i];
-		if (ce_stage(ce)) {
-			while ((i < active_nr) &&
-			       ! strcmp(active_cache[i]->name, ce->name))
-				i++;
-			i--;
-			if (allow_unmerged)
-				continue;
-			printf("%s: needs merge\n", ce->name);
-			has_errors = 1;
-			continue;
-		}
-
-		new = refresh_entry(ce, really);
-		if (!new)
-			continue;
-		if (IS_ERR(new)) {
-			if (not_new && PTR_ERR(new) == -ENOENT)
-				continue;
-			if (really && PTR_ERR(new) == -EINVAL) {
-				/* If we are doing --really-refresh that
-				 * means the index is not valid anymore.
-				 */
-				ce->ce_flags &= ~htons(CE_VALID);
-				active_cache_changed = 1;
-			}
-			if (quiet)
-				continue;
-			printf("%s: needs update\n", ce->name);
-			has_errors = 1;
-			continue;
-		}
-		active_cache_changed = 1;
-		/* You can NOT just free active_cache[i] here, since it
-		 * might not be necessarily malloc()ed but can also come
-		 * from mmap(). */
-		active_cache[i] = new;
-	}
-	return has_errors;
-}
-
 /*
  * We fundamentally don't like some paths: we don't want
  * dot or dot-dot anywhere, and for obvious reasons don't
@@ -382,7 +265,7 @@ static void update_one(const char *path, const char *prefix, int prefix_length)
 		die("Unable to process file %s", path);
 	report("add '%s'", path);
  free_return:
-	if (p != path)
+	if (p < path || p > path + strlen(path))
 		free((char*)p);
 }
 
@@ -476,7 +359,7 @@ static void read_index_info(int line_termination)
 }
 
 static const char update_index_usage[] =
-"git-update-index [-q] [--add] [--replace] [--remove] [--unmerged] [--refresh] [--really-refresh] [--cacheinfo] [--chmod=(+|-)x] [--assume-unchanged] [--info-only] [--force-remove] [--stdin] [--index-info] [--unresolve] [--ignore-missing] [-z] [--verbose] [--] <file>...";
+"git-update-index [-q] [--add] [--replace] [--remove] [--unmerged] [--refresh] [--really-refresh] [--cacheinfo] [--chmod=(+|-)x] [--assume-unchanged] [--info-only] [--force-remove] [--stdin] [--index-info] [--unresolve] [--again] [--ignore-missing] [-z] [--verbose] [--] <file>...";
 
 static unsigned char head_sha1[20];
 static unsigned char merge_head_sha1[20];
@@ -491,11 +374,13 @@ static struct cache_entry *read_one_ent(const char *which,
 	struct cache_entry *ce;
 
 	if (get_tree_entry(ent, path, sha1, &mode)) {
-		error("%s: not in %s branch.", path, which);
+		if (which)
+			error("%s: not in %s branch.", path, which);
 		return NULL;
 	}
 	if (mode == S_IFDIR) {
-		error("%s: not a blob in %s branch.", path, which);
+		if (which)
+			error("%s: not a blob in %s branch.", path, which);
 		return NULL;
 	}
 	size = cache_entry_size(namelen);
@@ -594,12 +479,55 @@ static int do_unresolve(int ac, const char **av,
 		const char *arg = av[i];
 		const char *p = prefix_path(prefix, prefix_length, arg);
 		err |= unresolve_one(p);
-		if (p != arg)
+		if (p < arg || p > arg + strlen(arg))
 			free((char*)p);
 	}
 	return err;
 }
 
+static int do_reupdate(int ac, const char **av,
+		       const char *prefix, int prefix_length)
+{
+	/* Read HEAD and run update-index on paths that are
+	 * merged and already different between index and HEAD.
+	 */
+	int pos;
+	int has_head = 1;
+	const char **pathspec = get_pathspec(prefix, av + 1);
+
+	if (read_ref(git_path("HEAD"), head_sha1))
+		/* If there is no HEAD, that means it is an initial
+		 * commit.  Update everything in the index.
+		 */
+		has_head = 0;
+ redo:
+	for (pos = 0; pos < active_nr; pos++) {
+		struct cache_entry *ce = active_cache[pos];
+		struct cache_entry *old = NULL;
+		int save_nr;
+
+		if (ce_stage(ce) || !ce_path_match(ce, pathspec))
+			continue;
+		if (has_head)
+			old = read_one_ent(NULL, head_sha1,
+					   ce->name, ce_namelen(ce), 0);
+		if (old && ce->ce_mode == old->ce_mode &&
+		    !memcmp(ce->sha1, old->sha1, 20)) {
+			free(old);
+			continue; /* unchanged */
+		}
+		/* Be careful.  The working tree may not have the
+		 * path anymore, in which case, under 'allow_remove',
+		 * or worse yet 'allow_replace', active_nr may decrease.
+		 */
+		save_nr = active_nr;
+		update_one(ce->name + prefix_length, prefix, prefix_length);
+		if (save_nr != active_nr)
+			goto redo;
+	}
+	return 0;
+}
+
 int main(int argc, const char **argv)
 {
 	int i, newfd, entries, has_errors = 0, line_termination = '\n';
@@ -608,6 +536,7 @@ int main(int argc, const char **argv)
 	const char *prefix = setup_git_directory();
 	int prefix_length = prefix ? strlen(prefix) : 0;
 	char set_executable_bit = 0;
+	unsigned int refresh_flags = 0;
 
 	git_config(git_default_config);
 
@@ -628,7 +557,7 @@ int main(int argc, const char **argv)
 				continue;
 			}
 			if (!strcmp(path, "-q")) {
-				quiet = 1;
+				refresh_flags |= REFRESH_QUIET;
 				continue;
 			}
 			if (!strcmp(path, "--add")) {
@@ -644,15 +573,15 @@ int main(int argc, const char **argv)
 				continue;
 			}
 			if (!strcmp(path, "--unmerged")) {
-				allow_unmerged = 1;
+				refresh_flags |= REFRESH_UNMERGED;
 				continue;
 			}
 			if (!strcmp(path, "--refresh")) {
-				has_errors |= refresh_cache(0);
+				has_errors |= refresh_cache(refresh_flags);
 				continue;
 			}
 			if (!strcmp(path, "--really-refresh")) {
-				has_errors |= refresh_cache(1);
+				has_errors |= refresh_cache(REFRESH_REALLY | refresh_flags);
 				continue;
 			}
 			if (!strcmp(path, "--cacheinfo")) {
@@ -717,8 +646,15 @@ int main(int argc, const char **argv)
 					active_cache_changed = 0;
 				goto finish;
 			}
+			if (!strcmp(path, "--again")) {
+				has_errors = do_reupdate(argc - i, argv + i,
+							 prefix, prefix_length);
+				if (has_errors)
+					active_cache_changed = 0;
+				goto finish;
+			}
 			if (!strcmp(path, "--ignore-missing")) {
-				not_new = 1;
+				refresh_flags |= REFRESH_IGNORE_MISSING;
 				continue;
 			}
 			if (!strcmp(path, "--verbose")) {
@@ -750,7 +686,7 @@ int main(int argc, const char **argv)
 			update_one(p, NULL, 0);
 			if (set_executable_bit)
 				chmod_path(set_executable_bit, p);
-			if (p != path_name)
+			if (p < path_name || p > path_name + strlen(path_name))
 				free((char*) p);
 			if (path_name != buf.buf)
 				free(path_name);

update-ref.c

@@ -32,10 +32,10 @@ int main(int argc, char **argv)
 	refname = argv[1];
 	value = argv[2];
 	oldval = argv[3];
-	if (get_sha1(value, sha1) < 0)
+	if (get_sha1(value, sha1))
 		die("%s: not a valid SHA1", value);
 	memset(oldsha1, 0, 20);
-	if (oldval && get_sha1(oldval, oldsha1) < 0)
+	if (oldval && get_sha1(oldval, oldsha1))
 		die("%s: not a valid old SHA1", oldval);
 
 	path = resolve_ref(git_path("%s", refname), currsha1, !!oldval);