Merge branch 'master' into sp/reflog

* master: (90 commits)
  fetch.c: remove an unused variable and dead code.
  Clean up sha1 file writing
  Builtin git-cat-file
  builtin format-patch: squelch content-type for 7-bit ASCII
  CMIT_FMT_EMAIL: Q-encode Subject: and display-name part of From: fields.
  add more informative error messages to git-mktag
  remove the artificial restriction tagsize < 8kb
  git-rebase: use canonical A..B syntax to format-patch
  git-format-patch: now built-in.
  fmt-patch: Support --attach
  fmt-patch: understand old <his> notation
  Teach fmt-patch about --keep-subject
  Teach fmt-patch about --numbered
  fmt-patch: implement -o <dir>
  fmt-patch: output file names to stdout
  Teach fmt-patch to write individual files.
  built-in tar-tree and remote tar-tree
  Builtin git-diff-files, git-diff-index, git-diff-stages, and git-diff-tree.
  Builtin git-show-branch.
  Builtin git-apply.
  ...

.gitignore

@@ -77,6 +77,7 @@ git-prune
 git-prune-packed
 git-pull
 git-push
+git-quiltimport
 git-read-tree
 git-rebase
 git-receive-pack

Documentation/Makefile

@@ -7,6 +7,7 @@ MAN7_TXT=git.txt
 DOC_HTML=$(patsubst %.txt,%.html,$(MAN1_TXT) $(MAN7_TXT))
 
 ARTICLES = tutorial
+ARTICLES += tutorial-2
 ARTICLES += core-tutorial
 ARTICLES += cvs-migration
 ARTICLES += diffcore

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/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-branch.txt

@@ -49,6 +49,9 @@ OPTIONS
 
 <branchname>::
 	The name of the branch to create or delete.
+	The new branch name must pass all checks defined by
+	gitlink:git-check-ref-format[1].  Some of these checks
+	may restrict the characters allowed in a branch name.
 
 <start-point>::
 	The new branch will be created with a HEAD equal to this.  It may

Documentation/git-check-ref-format.txt

@@ -45,6 +45,8 @@ refname expressions (see gitlink:git-rev-parse[1]).  Namely:
 
 . colon `:` is used as in `srcref:dstref` to mean "use srcref\'s
   value and store it in dstref" in fetch and push operations.
+  It may also be used to select a specific object such as with
+  gitlink:git-cat-file[1] "git-cat-file blob v1.3.3:refs.c".
 
 
 GIT

Documentation/git-checkout.txt

@@ -35,7 +35,10 @@ OPTIONS
 	Force a re-read of everything.
 
 -b::
-	Create a new branch and start it at <branch>.
+	Create a new branch named <new_branch> and start it at
+	<branch>.  The new branch name must pass all checks defined
+	by gitlink:git-check-ref-format[1].  Some of these checks
+	may restrict the characters allowed in a branch name.
 
 -l::
 	Create the new branch's ref log.  This activates recording of

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/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

Documentation/tutorial-2.txt

@@ -0,0 +1,391 @@
+A tutorial introduction to git: part two
+========================================
+
+You should work through link:tutorial.html[A tutorial introduction to
+git] before reading this tutorial.
+
+The goal of this tutorial is to introduce two fundamental pieces of
+git's architecture--the object database and the index file--and to
+provide the reader with everything necessary to understand the rest
+of the git documentation.
+
+The git object database
+-----------------------
+
+Let's start a new project and create a small amount of history:
+
+------------------------------------------------
+$ mkdir test-project
+$ cd test-project
+$ git init-db
+defaulting to local storage area
+$ echo 'hello world' > file.txt
+$ git add .
+$ git commit -a -m "initial commit"
+Committing initial tree 92b8b694ffb1675e5975148e1121810081dbdffe
+$ echo 'hello world!' >file.txt
+$ git commit -a -m "add emphasis"
+------------------------------------------------
+
+What are the 40 digits of hex that git responded to the first commit
+with?
+
+We saw in part one of the tutorial that commits have names like this.
+It turns out that every object in the git history is stored under
+such a 40-digit hex name.  That name is the SHA1 hash of the object's
+contents; among other things, this ensures that git will never store
+the same data twice (since identical data is given an identical SHA1
+name), and that the contents of a git object will never change (since
+that would change the object's name as well).
+
+We can ask git about this particular object with the cat-file
+command--just cut-and-paste from the reply to the initial commit, to
+save yourself typing all 40 hex digits:
+
+------------------------------------------------
+$ git cat-file -t 92b8b694ffb1675e5975148e1121810081dbdffe
+tree
+------------------------------------------------
+
+A tree can refer to one or more "blob" objects, each corresponding to
+a file.  In addition, a tree can also refer to other tree objects,
+thus creating a directory heirarchy.  You can examine the contents of
+any tree using ls-tree (remember that a long enough initial portion
+of the SHA1 will also work):
+
+------------------------------------------------
+$ git ls-tree 92b8b694
+100644 blob 3b18e512dba79e4c8300dd08aeb37f8e728b8dad    file.txt
+------------------------------------------------
+
+Thus we see that this tree has one file in it.  The SHA1 hash is a
+reference to that file's data:
+
+------------------------------------------------
+$ git cat-file -t 3b18e512
+blob
+------------------------------------------------
+
+A "blob" is just file data, which we can also examine with cat-file:
+
+------------------------------------------------
+$ git cat-file blob 3b18e512
+hello world
+------------------------------------------------
+
+Note that this is the old file data; so the object that git named in
+its response to the initial tree was a tree with a snapshot of the
+directory state that was recorded by the first commit.
+
+All of these objects are stored under their SHA1 names inside the git
+directory:
+
+------------------------------------------------
+$ find .git/objects/
+.git/objects/
+.git/objects/pack
+.git/objects/info
+.git/objects/3b
+.git/objects/3b/18e512dba79e4c8300dd08aeb37f8e728b8dad
+.git/objects/92
+.git/objects/92/b8b694ffb1675e5975148e1121810081dbdffe
+.git/objects/54
+.git/objects/54/196cc2703dc165cbd373a65a4dcf22d50ae7f7
+.git/objects/a0
+.git/objects/a0/423896973644771497bdc03eb99d5281615b51
+.git/objects/d0
+.git/objects/d0/492b368b66bdabf2ac1fd8c92b39d3db916e59
+.git/objects/c4
+.git/objects/c4/d59f390b9cfd4318117afde11d601c1085f241
+------------------------------------------------
+
+and the contents of these files is just the compressed data plus a
+header identifying their length and their type.  The type is either a
+blob, a tree, a commit, or a tag.  We've seen a blob and a tree now,
+so next we should look at a commit.
+
+The simplest commit to find is the HEAD commit, which we can find
+from .git/HEAD:
+
+------------------------------------------------
+$ cat .git/HEAD
+ref: refs/heads/master
+------------------------------------------------
+
+As you can see, this tells us which branch we're currently on, and it
+tells us this by naming a file under the .git directory, which itself
+contains a SHA1 name referring to a commit object, which we can
+examine with cat-file:
+
+------------------------------------------------
+$ cat .git/refs/heads/master
+c4d59f390b9cfd4318117afde11d601c1085f241
+$ git cat-file -t c4d59f39
+commit
+$ git cat-file commit c4d59f39
+tree d0492b368b66bdabf2ac1fd8c92b39d3db916e59
+parent 54196cc2703dc165cbd373a65a4dcf22d50ae7f7
+author J. Bruce Fields <bfields@puzzle.fieldses.org> 1143418702 -0500
+committer J. Bruce Fields <bfields@puzzle.fieldses.org> 1143418702 -0500
+
+add emphasis
+------------------------------------------------
+
+The "tree" object here refers to the new state of the tree:
+
+------------------------------------------------
+$ git ls-tree d0492b36
+100644 blob a0423896973644771497bdc03eb99d5281615b51    file.txt
+$ git cat-file commit a0423896
+hello world!
+------------------------------------------------
+
+and the "parent" object refers to the previous commit:
+
+------------------------------------------------
+$ git-cat-file commit 54196cc2
+tree 92b8b694ffb1675e5975148e1121810081dbdffe
+author J. Bruce Fields <bfields@puzzle.fieldses.org> 1143414668 -0500
+committer J. Bruce Fields <bfields@puzzle.fieldses.org> 1143414668 -0500
+
+initial commit
+------------------------------------------------
+
+The tree object is the tree we examined first, and this commit is
+unusual in that it lacks any parent.
+
+Most commits have only one parent, but it is also common for a commit
+to have multiple parents.   In that case the commit represents a
+merge, with the parent references pointing to the heads of the merged
+branches.
+
+Besides blobs, trees, and commits, the only remaining type of object
+is a "tag", which we won't discuss here; refer to gitlink:git-tag[1]
+for details.
+
+So now we know how git uses the object database to represent a
+project's history:
+
+  * "commit" objects refer to "tree" objects representing the
+    snapshot of a directory tree at a particular point in the
+    history, and refer to "parent" commits to show how they're
+    connected into the project history.
+  * "tree" objects represent the state of a single directory,
+    associating directory names to "blob" objects containing file
+    data and "tree" objects containing subdirectory information.
+  * "blob" objects contain file data without any other structure.
+  * References to commit objects at the head of each branch are
+    stored in files under .git/refs/heads/.
+  * The name of the current branch is stored in .git/HEAD.
+
+Note, by the way, that lots of commands take a tree as an argument.
+But as we can see above, a tree can be referred to in many different
+ways--by the SHA1 name for that tree, by the name of a commit that
+refers to the tree, by the name of a branch whose head refers to that
+tree, etc.--and most such commands can accept any of these names.
+
+In command synopses, the word "tree-ish" is sometimes used to
+designate such an argument.
+
+The index file
+--------------
+
+The primary tool we've been using to create commits is "git commit
+-a", which creates a commit including every change you've made to
+your working tree.  But what if you want to commit changes only to
+certain files?  Or only certain changes to certain files?
+
+If we look at the way commits are created under the cover, we'll see
+that there are more flexible ways creating commits.
+
+Continuing with our test-project, let's modify file.txt again:
+
+------------------------------------------------
+$ echo "hello world, again" >>file.txt
+------------------------------------------------
+
+but this time instead of immediately making the commit, let's take an
+intermediate step, and ask for diffs along the way to keep track of
+what's happening:
+
+------------------------------------------------
+$ git diff
+--- a/file.txt
++++ b/file.txt
+@@ -1 +1,2 @@
+ hello world!
++hello world, again
+$ git update-index file.txt
+$ git diff
+------------------------------------------------
+
+The last diff is empty, but no new commits have been made, and the
+head still doesn't contain the new line:
+
+------------------------------------------------
+$ git-diff HEAD
+diff --git a/file.txt b/file.txt
+index a042389..513feba 100644
+--- a/file.txt
++++ b/file.txt
+@@ -1 +1,2 @@
+ hello world!
++hello world, again
+------------------------------------------------
+
+So "git diff" is comparing against something other than the head.
+The thing that it's comparing against is actually the index file,
+which is stored in .git/index in a binary format, but whose contents
+we can examine with ls-files:
+
+------------------------------------------------
+$ git ls-files --stage
+100644 513feba2e53ebbd2532419ded848ba19de88ba00 0       file.txt
+$ git cat-file -t 513feba2
+blob
+$ git cat-file blob 513feba2
+hello world, again
+------------------------------------------------
+
+So what our "git update-index" did was store a new blob and then put
+a reference to it in the index file.  If we modify the file again,
+we'll see that the new modifications are reflected in the "git-diff"
+output:
+
+------------------------------------------------
+$ echo 'again?' >>file.txt
+$ git diff
+index 513feba..ba3da7b 100644
+--- a/file.txt
++++ b/file.txt
+@@ -1,2 +1,3 @@
+ hello world!
+ hello world, again
++again?
+------------------------------------------------
+
+With the right arguments, git diff can also show us the difference
+between the working directory and the last commit, or between the
+index and the last commit:
+
+------------------------------------------------
+$ git diff HEAD
+diff --git a/file.txt b/file.txt
+index a042389..ba3da7b 100644
+--- a/file.txt
++++ b/file.txt
+@@ -1 +1,3 @@
+ hello world!
++hello world, again
++again?
+$ git diff --cached
+diff --git a/file.txt b/file.txt
+index a042389..513feba 100644
+--- a/file.txt
++++ b/file.txt
+@@ -1 +1,2 @@
+ hello world!
++hello world, again
+------------------------------------------------
+
+At any time, we can create a new commit using "git commit" (without
+the -a option), and verify that the state committed only includes the
+changes stored in the index file, not the additional change that is
+still only in our working tree:
+
+------------------------------------------------
+$ git commit -m "repeat"
+$ git diff HEAD
+diff --git a/file.txt b/file.txt
+index 513feba..ba3da7b 100644
+--- a/file.txt
++++ b/file.txt
+@@ -1,2 +1,3 @@
+ hello world!
+ hello world, again
++again?
+------------------------------------------------
+
+So by default "git commit" uses the index to create the commit, not
+the working tree; the -a option to commit tells it to first update
+the index with all changes in the working tree.
+
+Finally, it's worth looking at the effect of "git add" on the index
+file:
+
+------------------------------------------------
+$ echo "goodbye, world" >closing.txt
+$ git add closing.txt
+------------------------------------------------
+
+The effect of the "git add" was to add one entry to the index file:
+
+------------------------------------------------
+$ git ls-files --stage
+100644 8b9743b20d4b15be3955fc8d5cd2b09cd2336138 0       closing.txt
+100644 513feba2e53ebbd2532419ded848ba19de88ba00 0       file.txt
+------------------------------------------------
+
+And, as you can see with cat-file, this new entry refers to the
+current contents of the file:
+
+------------------------------------------------
+$ git cat-file blob a6b11f7a
+goodbye, word
+------------------------------------------------
+
+The "status" command is a useful way to get a quick summary of the
+situation:
+
+------------------------------------------------
+$ git status
+#
+# Updated but not checked in:
+#   (will commit)
+#
+#       new file: closing.txt
+#
+#
+# Changed but not updated:
+#   (use git-update-index to mark for commit)
+#
+#       modified: file.txt
+#
+------------------------------------------------
+
+Since the current state of closing.txt is cached in the index file,
+it is listed as "updated but not checked in".  Since file.txt has
+changes in the working directory that aren't reflected in the index,
+it is marked "changed but not updated".  At this point, running "git
+commit" would create a commit that added closing.txt (with its new
+contents), but that didn't modify file.txt.
+
+Also, note that a bare "git diff" shows the changes to file.txt, but
+not the addition of closing.txt, because the version of closing.txt
+in the index file is identical to the one in the working directory.
+
+In addition to being the staging area for new commits, the index file
+is also populated from the object database when checking out a
+branch, and is used to hold the trees involved in a merge operation.
+See the link:core-tutorial.txt[core tutorial] and the relevant man
+pages for details.
+
+What next?
+----------
+
+At this point you should know everything necessary to read the man
+pages for any of the git commands; one good place to start would be
+with the commands mentioned in link:everyday.html[Everyday git].  You
+should be able to find any unknown jargon in the
+link:glossary.html[Glosssay].
+
+The link:cvs-migration.html[CVS migration] document explains how to
+import a CVS repository into git, and shows how to use git in a
+CVS-like way.
+
+For some interesting examples of git use, see the
+link:howto-index.html[howtos].
+
+For git developers, the link:core-tutorial.html[Core tutorial] goes
+into detail on the lower-level git mechanisms involved in, for
+example, creating a new commit.

Documentation/tutorial.txt

@@ -80,13 +80,13 @@ file; just remove it, then commit.
 At any point you can view the history of your changes using
 
 ------------------------------------------------
-$ git whatchanged
+$ git log
 ------------------------------------------------
 
 If you also want to see complete diffs at each step, use
 
 ------------------------------------------------
-$ git whatchanged -p
+$ git log -p
 ------------------------------------------------
 
 Managing branches
@@ -216,7 +216,7 @@ This actually pulls changes from the branch in Bob's repository named
 "master".  Alice could request a different branch by adding the name
 of the branch to the end of the git pull command line.
 
-This merges Bob's changes into her repository; "git whatchanged" will
+This merges Bob's changes into her repository; "git log" will
 now show the new commits.  If Alice has made her own changes in the
 meantime, then Bob's changes will be merged in, and she will need to
 manually fix any conflicts.
@@ -234,7 +234,7 @@ named bob-incoming.  (Unlike git pull, git fetch just fetches a copy
 of Bob's line of development without doing any merging).  Then
 
 -------------------------------------
-$ git whatchanged -p master..bob-incoming
+$ git log -p master..bob-incoming
 -------------------------------------
 
 shows a list of all the changes that Bob made since he branched from
@@ -288,102 +288,179 @@ Git can also be used in a CVS-like mode, with a central repository
 that various users push changes to; see gitlink:git-push[1] and
 link:cvs-migration.html[git for CVS users].
 
-Keeping track of history
-------------------------
+Exploring history
+-----------------
 
-Git history is represented as a series of interrelated commits.  The
-most recent commit in the currently checked-out branch can always be
-referred to as HEAD, and the "parent" of any commit can always be
-referred to by appending a caret, "^", to the end of the name of the
-commit.  So, for example,
+Git history is represented as a series of interrelated commits.  We
+have already seen that the git log command can list those commits.
+Note that first line of each git log entry also gives a name for the
+commit:
 
 -------------------------------------
-git diff HEAD^ HEAD
+$ git log
+commit c82a22c39cbc32576f64f5c6b3f24b99ea8149c7
+Author: Junio C Hamano <junkio@cox.net>
+Date:   Tue May 16 17:18:22 2006 -0700
+
+    merge-base: Clarify the comments on post processing.
 -------------------------------------
 
-shows the difference between the most-recently checked-in state of
-the tree and the previous state, and
+We can give this name to git show to see the details about this
+commit.
 
 -------------------------------------
-git diff HEAD^^ HEAD^
+$ git show c82a22c39cbc32576f64f5c6b3f24b99ea8149c7
 -------------------------------------
 
-shows the difference between that previous state and the state two
-commits ago.  Also, HEAD~5 can be used as a shorthand for HEAD{caret}{caret}{caret}{caret}{caret},
-and more generally HEAD~n can refer to the nth previous commit.
-Commits representing merges have more than one parent, and you can
-specify which parent to follow in that case; see
-gitlink:git-rev-parse[1].
-
-The name of a branch can also be used to refer to the most recent
-commit on that branch; so you can also say things like
+But there other ways to refer to commits.  You can use any initial
+part of the name that is long enough to uniquely identify the commit:
 
 -------------------------------------
-git diff HEAD experimental
+$ git show c82a22c39c	# the first few characters of the name are
+			# usually enough
+$ git show HEAD		# the tip of the current branch
+$ git show experimental	# the tip of the "experimental" branch
 -------------------------------------
 
-to see the difference between the most-recently committed tree in
-the current branch and the most-recently committed tree in the
-experimental branch.
-
-But you may find it more useful to see the list of commits made in
-the experimental branch but not in the current branch, and
+Every commit has at least one "parent" commit, which points to the
+previous state of the project:
 
 -------------------------------------
-git whatchanged HEAD..experimental
+$ git show HEAD^  # to see the parent of HEAD
+$ git show HEAD^^ # to see the grandparent of HEAD
+$ git show HEAD~4 # to see the great-great grandparent of HEAD
 -------------------------------------
 
-will do that, just as
+Note that merge commits may have more than one parent:
 
 -------------------------------------
-git whatchanged experimental..HEAD
+$ git show HEAD^1 # show the first parent of HEAD (same as HEAD^)
+$ git show HEAD^2 # show the second parent of HEAD
 -------------------------------------
 
-will show the list of commits made on the HEAD but not included in
-experimental.
-
-You can also give commits convenient names of your own: after running
+You can also give commits names of your own; after running
 
 -------------------------------------
-$ git-tag v2.5 HEAD^^
+$ git-tag v2.5 1b2e1d63ff
 -------------------------------------
 
-you can refer to HEAD^^ by the name "v2.5".  If you intend to share
-this name with other people (for example, to identify a release
+you can refer to 1b2e1d63ff by the name "v2.5".  If you intend to
+share this name with other people (for example, to identify a release
 version), you should create a "tag" object, and perhaps sign it; see
 gitlink:git-tag[1] for details.
 
-You can revisit the old state of a tree, and make further
-modifications if you wish, using git branch: the command
+Any git command that needs to know a commit can take any of these
+names.  For example:
 
 -------------------------------------
-$ git branch stable-release v2.5
+$ git diff v2.5 HEAD	 # compare the current HEAD to v2.5
+$ git branch stable v2.5 # start a new branch named "stable" based
+			 # at v2.5
+$ git reset --hard HEAD^ # reset your current branch and working
+			 # directory its state at HEAD^
 -------------------------------------
 
-will create a new branch named "stable-release" starting from the
-commit which you tagged with the name v2.5.
-
-You can reset the state of any branch to an earlier commit at any
-time with
-
--------------------------------------
-$ git reset --hard v2.5
--------------------------------------
-
-This will remove all later commits from this branch and reset the
-working tree to the state it had when the given commit was made.  If
-this branch is the only branch containing the later commits, those
-later changes will be lost.  Don't use "git reset" on a
+Be careful with that last command: in addition to losing any changes
+in the working directory, it will also remove all later commits from
+this branch.  If this branch is the only branch containing those
+commits, they will be lost.  (Also, don't use "git reset" on a
 publicly-visible branch that other developers pull from, as git will
-be confused by history that disappears in this way.
+be confused by history that disappears in this way.)
+
+The git grep command can search for strings in any version of your
+project, so
+
+-------------------------------------
+$ git grep "hello" v2.5
+-------------------------------------
+
+searches for all occurences of "hello" in v2.5.
+
+If you leave out the commit name, git grep will search any of the
+files it manages in your current directory.  So
+
+-------------------------------------
+$ git grep "hello"
+-------------------------------------
+
+is a quick way to search just the files that are tracked by git.
+
+Many git commands also take sets of commits, which can be specified
+in a number of ways.  Here are some examples with git log:
+
+-------------------------------------
+$ git log v2.5..v2.6            # commits between v2.5 and v2.6
+$ git log v2.5..                # commits since v2.5
+$ git log --since="2 weeks ago" # commits from the last 2 weeks
+$ git log v2.5.. Makefile       # commits since v2.5 which modify
+				# Makefile
+-------------------------------------
+
+You can also give git log a "range" of commits where the first is not
+necessarily an ancestor of the second; for example, if the tips of
+the branches "stable-release" and "master" diverged from a common
+commit some time ago, then
+
+-------------------------------------
+$ git log stable..experimental
+-------------------------------------
+
+will list commits made in the experimental branch but not in the
+stable branch, while
+
+-------------------------------------
+$ git log experimental..stable
+-------------------------------------
+
+will show the list of commits made on the stable branch but not
+the experimental branch.
+
+The "git log" command has a weakness: it must present commits in a
+list.  When the history has lines of development that diverged and
+then merged back together, the order in which "git log" presents
+those commits is meaningless.
+
+Most projects with multiple contributors (such as the linux kernel,
+or git itself) have frequent merges, and gitk does a better job of
+visualizing their history.  For example,
+
+-------------------------------------
+$ gitk --since="2 weeks ago" drivers/
+-------------------------------------
+
+allows you to browse any commits from the last 2 weeks of commits
+that modified files under the "drivers" directory.
+
+Finally, most commands that take filenames will optionally allow you
+to precede any filename by a commit, to specify a particular version
+fo the file:
+
+-------------------------------------
+$ git diff v2.5:Makefile HEAD:Makefile.in
+-------------------------------------
 
 Next Steps
 ----------
 
-Some good commands to explore next:
+This tutorial should be enough to perform basic distributed revision
+control for your projects.  However, to fully understand the depth
+and power of git you need to understand two simple ideas on which it
+is based:
 
-  * gitlink:git-diff[1]: This flexible command does much more than
-    we've seen in the few examples above.
+  * The object database is the rather elegant system used to
+    store the history of your project--files, directories, and
+    commits.
+
+  * The index file is a cache of the state of a directory tree,
+    used to create commits, check out working directories, and
+    hold the various trees involved in a merge.
+
+link:tutorial-2.html[Part two of this tutorial] explains the object
+database, the index file, and a few other odds and ends that you'll
+need to make the most of git.
+
+If you don't want to consider with that right away, a few other
+digressions that may be interesting at this point are:
 
   * gitlink:git-format-patch[1], gitlink:git-am[1]: These convert
     series of git commits into emailed patches, and vice versa,
@@ -397,8 +474,6 @@ Some good commands to explore next:
     smart enough to perform a close-to-optimal search even in the
     case of complex non-linear history with lots of merged branches.
 
-Other good starting points include link:everyday.html[Everday GIT
-with 20 Commands Or So] and link:cvs-migration.html[git for CVS
-users].  Also, link:core-tutorial.html[A short git tutorial] gives an
-introduction to lower-level git commands for advanced users and
-developers.
+  * link:everyday.html[Everday GIT with 20 Commands Or So]
+
+  * link:cvs-migration.html[git for CVS users].

GIT-VERSION-GEN

@@ -5,7 +5,7 @@ DEF_VER=v1.3.GIT
 
 # First try git-describe, then see if there is a version file
 # (included in release tarballs), then default
-if VN=$(git-describe --abbrev=4 HEAD 2>/dev/null); then
+if VN=$(git describe --abbrev=4 HEAD 2>/dev/null); then
 	VN=$(echo "$VN" | sed -e 's/-/./g');
 elif test -f version
 then
@@ -16,7 +16,7 @@ fi
 
 VN=$(expr "$VN" : v*'\(.*\)')
 
-dirty=$(sh -c 'git-diff-index --name-only HEAD' 2>/dev/null) || dirty=
+dirty=$(sh -c 'git diff-index --name-only HEAD' 2>/dev/null) || dirty=
 case "$dirty" in
 '')
 	;;

Makefile

@@ -113,19 +113,19 @@ SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 ### --- END CONFIGURATION SECTION ---
 
 SCRIPT_SH = \
-	git-add.sh git-bisect.sh git-branch.sh git-checkout.sh \
+	git-bisect.sh git-branch.sh git-checkout.sh \
 	git-cherry.sh git-clean.sh git-clone.sh git-commit.sh \
 	git-fetch.sh \
-	git-format-patch.sh git-ls-remote.sh \
+	git-ls-remote.sh \
 	git-merge-one-file.sh git-parse-remote.sh \
 	git-prune.sh git-pull.sh git-rebase.sh \
 	git-repack.sh git-request-pull.sh git-reset.sh \
-	git-resolve.sh git-revert.sh git-rm.sh git-sh-setup.sh \
+	git-resolve.sh git-revert.sh git-sh-setup.sh \
 	git-tag.sh git-verify-tag.sh \
 	git-applymbox.sh git-applypatch.sh git-am.sh \
 	git-merge.sh git-merge-stupid.sh git-merge-octopus.sh \
 	git-merge-resolve.sh git-merge-ours.sh \
-	git-lost-found.sh
+	git-lost-found.sh git-quiltimport.sh
 
 SCRIPT_PERL = \
 	git-archimport.perl git-cvsimport.perl git-relink.perl \
@@ -149,28 +149,31 @@ SIMPLE_PROGRAMS = \
 
 # ... and all the rest that could be moved out of bindir to gitexecdir
 PROGRAMS = \
-	git-apply$X git-cat-file$X \
-	git-checkout-index$X git-clone-pack$X git-commit-tree$X \
-	git-convert-objects$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-ls-files$X git-ls-tree$X git-mailinfo$X git-merge-base$X \
+	git-checkout-index$X git-clone-pack$X \
+	git-convert-objects$X git-fetch-pack$X git-fsck-objects$X \
+	git-hash-object$X git-index-pack$X git-local-fetch$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$X \
-	git-send-pack$X git-show-branch$X git-shell$X \
+	git-peek-remote$X git-prune-packed$X \
+	git-receive-pack$X git-rev-parse$X \
+	git-send-pack$X git-shell$X \
 	git-show-index$X git-ssh-fetch$X \
-	git-ssh-upload$X git-tar-tree$X git-unpack-file$X \
+	git-ssh-upload$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-grep$X
+	git-grep$X git-add$X git-rm$X git-rev-list$X \
+	git-check-ref-format$X \
+	git-init-db$X git-tar-tree$X git-upload-tar$X git-format-patch$X \
+	git-ls-files$X git-ls-tree$X \
+	git-read-tree$X git-commit-tree$X \
+	git-apply$X git-show-branch$X git-diff-files$X \
+	git-diff-index$X git-diff-stages$X git-diff-tree$X git-cat-file$X
 
 # what 'all' will build and 'install' will install, in gitexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS)
@@ -199,7 +202,7 @@ LIB_H = \
 	blob.h cache.h commit.h csum-file.h delta.h \
 	diff.h object.h pack.h pkt-line.h quote.h refs.h \
 	run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \
-	tree-walk.h log-tree.h
+	tree-walk.h log-tree.h dir.h
 
 DIFF_OBJS = \
 	diff.o diff-lib.o diffcore-break.o diffcore-order.o \
@@ -210,7 +213,7 @@ LIB_OBJS = \
 	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 \
+	quote.o read-cache.o refs.o run-command.o dir.o \
 	server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \
 	tag.o tree.o usage.o config.o environment.o ctype.o copy.o \
 	fetch-clone.o revision.o pager.o tree-walk.o xdiff-interface.o \
@@ -218,7 +221,14 @@ LIB_OBJS = \
 
 BUILTIN_OBJS = \
 	builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \
-	builtin-grep.o
+	builtin-grep.o builtin-add.o builtin-rev-list.o builtin-check-ref-format.o \
+	builtin-rm.o builtin-init-db.o \
+	builtin-tar-tree.o builtin-upload-tar.o \
+	builtin-ls-files.o builtin-ls-tree.o \
+	builtin-read-tree.o builtin-commit-tree.o \
+	builtin-apply.o builtin-show-branch.o builtin-diff-files.o \
+	builtin-diff-index.o builtin-diff-stages.o builtin-diff-tree.o \
+	builtin-cat-file.o
 
 GITLIBS = $(LIB_FILE) $(XDIFF_LIB)
 LIBS = $(GITLIBS) -lz
@@ -418,6 +428,9 @@ else
 	ALL_CFLAGS += -Dsockaddr_storage=sockaddr_in6
 endif
 endif
+ifdef NO_INET_NTOP
+	LIB_OBJS += compat/inet_ntop.o
+endif
 
 ifdef NO_ICONV
 	ALL_CFLAGS += -DNO_ICONV
@@ -459,6 +472,7 @@ 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 += $(COMPAT_OBJS)
 export prefix TAR INSTALL DESTDIR SHELL_PATH template_dir
 ### Build rules
@@ -565,10 +579,6 @@ git-http-push$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
@@ -625,7 +635,14 @@ install: all
 	$(MAKE) -C templates install
 	$(INSTALL) -d -m755 '$(DESTDIR_SQ)$(GIT_PYTHON_DIR_SQ)'
 	$(INSTALL) $(PYMODULES) '$(DESTDIR_SQ)$(GIT_PYTHON_DIR_SQ)'
-	$(foreach p,$(BUILT_INS), rm -f '$(DESTDIR_SQ)$(bindir_SQ)/$p' && ln '$(DESTDIR_SQ)$(bindir_SQ)/git$X' '$(DESTDIR_SQ)$(bindir_SQ)/$p' ;)
+	if test 'z$(bindir_SQ)' != 'z$(gitexecdir_SQ)'; \
+	then \
+		ln -f '$(DESTDIR_SQ)$(bindir_SQ)/git$X' \
+			'$(DESTDIR_SQ)$(gitexecdir_SQ)/git$X' || \
+		cp '$(DESTDIR_SQ)$(bindir_SQ)/git$X' \
+			'$(DESTDIR_SQ)$(gitexecdir_SQ)/git$X'; \
+	fi
+	$(foreach p,$(BUILT_INS), rm -f '$(DESTDIR_SQ)$(gitexecdir_SQ)/$p' && ln '$(DESTDIR_SQ)$(gitexecdir_SQ)/git$X' '$(DESTDIR_SQ)$(gitexecdir_SQ)/$p' ;)
 
 install-doc:
 	$(MAKE) -C Documentation install
@@ -652,6 +669,25 @@ 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:
@@ -659,8 +695,9 @@ 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

builtin-add.c

@@ -0,0 +1,187 @@
+/*
+ * "git add" builtin command
+ *
+ * Copyright (C) 2006 Linus Torvalds
+ */
+#include <fnmatch.h>
+
+#include "cache.h"
+#include "builtin.h"
+#include "dir.h"
+
+static const char builtin_add_usage[] =
+"git-add [-n] [-v] <filepattern>...";
+
+static void prune_directory(struct dir_struct *dir, const char **pathspec, int prefix)
+{
+	char *seen;
+	int i, specs;
+	struct dir_entry **src, **dst;
+
+	for (specs = 0; pathspec[specs];  specs++)
+		/* nothing */;
+	seen = xmalloc(specs);
+	memset(seen, 0, specs);
+
+	src = dst = dir->entries;
+	i = dir->nr;
+	while (--i >= 0) {
+		struct dir_entry *entry = *src++;
+		if (!match_pathspec(pathspec, entry->name, entry->len, prefix, seen)) {
+			free(entry);
+			continue;
+		}
+		*dst++ = entry;
+	}
+	dir->nr = dst - dir->entries;
+
+	for (i = 0; i < specs; i++) {
+		struct stat st;
+		const char *match;
+		if (seen[i])
+			continue;
+
+		/* Existing file? We must have ignored it */
+		match = pathspec[i];
+		if (!match[0] || !lstat(match, &st))
+			continue;
+		die("pathspec '%s' did not match any files", match);
+	}
+}
+
+static void fill_directory(struct dir_struct *dir, const char **pathspec)
+{
+	const char *path, *base;
+	int baselen;
+
+	/* Set up the default git porcelain excludes */
+	memset(dir, 0, sizeof(*dir));
+	dir->exclude_per_dir = ".gitignore";
+	path = git_path("info/exclude");
+	if (!access(path, R_OK))
+		add_excludes_from_file(dir, path);
+
+	/*
+	 * Calculate common prefix for the pathspec, and
+	 * use that to optimize the directory walk
+	 */
+	baselen = common_prefix(pathspec);
+	path = ".";
+	base = "";
+	if (baselen) {
+		char *common = xmalloc(baselen + 1);
+		common = xmalloc(baselen + 1);
+		memcpy(common, *pathspec, baselen);
+		common[baselen] = 0;
+		path = base = common;
+	}
+
+	/* Read the directory and prune it */
+	read_directory(dir, path, base, baselen);
+	if (pathspec)
+		prune_directory(dir, pathspec, baselen);
+}
+
+static int add_file_to_index(const char *path, int verbose)
+{
+	int size, namelen;
+	struct stat st;
+	struct cache_entry *ce;
+
+	if (lstat(path, &st))
+		die("%s: unable to stat (%s)", path, strerror(errno));
+
+	if (!S_ISREG(st.st_mode) && !S_ISLNK(st.st_mode))
+		die("%s: can only add regular files or symbolic links", path);
+
+	namelen = strlen(path);
+	size = cache_entry_size(namelen);
+	ce = xcalloc(1, size);
+	memcpy(ce->name, path, namelen);
+	ce->ce_flags = htons(namelen);
+	fill_stat_cache_info(ce, &st);
+
+	ce->ce_mode = create_ce_mode(st.st_mode);
+	if (!trust_executable_bit) {
+		/* If there is an existing entry, pick the mode bits
+		 * from it.
+		 */
+		int pos = cache_name_pos(path, namelen);
+		if (pos >= 0)
+			ce->ce_mode = active_cache[pos]->ce_mode;
+	}
+
+	if (index_path(ce->sha1, path, &st, 1))
+		die("unable to index file %s", path);
+	if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD))
+		die("unable to add %s to index",path);
+	if (verbose)
+		printf("add '%s'\n", path);
+	return 0;
+}
+
+static struct cache_file cache_file;
+
+int cmd_add(int argc, const char **argv, char **envp)
+{
+	int i, newfd;
+	int verbose = 0, show_only = 0;
+	const char *prefix = setup_git_directory();
+	const char **pathspec;
+	struct dir_struct dir;
+
+	git_config(git_default_config);
+
+	newfd = hold_index_file_for_update(&cache_file, get_index_file());
+	if (newfd < 0)
+		die("unable to create new cachefile");
+
+	if (read_cache() < 0)
+		die("index file corrupt");
+
+	for (i = 1; i < argc; i++) {
+		const char *arg = argv[i];
+
+		if (arg[0] != '-')
+			break;
+		if (!strcmp(arg, "--")) {
+			i++;
+			break;
+		}
+		if (!strcmp(arg, "-n")) {
+			show_only = 1;
+			continue;
+		}
+		if (!strcmp(arg, "-v")) {
+			verbose = 1;
+			continue;
+		}
+		die(builtin_add_usage);
+	}
+	git_config(git_default_config);
+	pathspec = get_pathspec(prefix, argv + i);
+
+	fill_directory(&dir, pathspec);
+
+	if (show_only) {
+		const char *sep = "", *eof = "";
+		for (i = 0; i < dir.nr; i++) {
+			printf("%s%s", sep, dir.entries[i]->name);
+			sep = " ";
+			eof = "\n";
+		}
+		fputs(eof, stdout);
+		return 0;
+	}
+
+	for (i = 0; i < dir.nr; i++)
+		add_file_to_index(dir.entries[i]->name, verbose);
+
+	if (active_cache_changed) {
+		if (write_cache(newfd, active_cache, active_nr) ||
+		    commit_index_file(&cache_file))
+			die("Unable to write new index file");
+	}
+
+	return 0;
+}

builtin-apply.c

@@ -11,12 +11,15 @@
 #include "quote.h"
 #include "blob.h"
 #include "delta.h"
+#include "builtin.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;
@@ -26,6 +29,7 @@ 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;
@@ -36,7 +40,7 @@ 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,
@@ -1600,7 +1604,7 @@ 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;
@@ -1609,7 +1613,17 @@ 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);
@@ -1637,16 +1651,21 @@ 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)
@@ -1659,40 +1678,46 @@ 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;
@@ -1709,9 +1734,9 @@ 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;
 }
@@ -1778,7 +1803,7 @@ 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);
@@ -1894,7 +1919,8 @@ 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)
@@ -1911,9 +1937,11 @@ 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)
@@ -1950,6 +1978,8 @@ 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;
 
@@ -2122,7 +2152,7 @@ static int git_apply_config(const char *var, const char *value)
 }
 
 
-int main(int argc, char **argv)
+int cmd_apply(int argc, const char **argv, char **envp)
 {
 	int i;
 	int read_stdin = 1;
@@ -2182,6 +2212,11 @@ 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;

builtin-cat-file.c

@@ -7,6 +7,7 @@
 #include "exec_cmd.h"
 #include "tag.h"
 #include "tree.h"
+#include "builtin.h"
 
 static void flush_buffer(const char *buf, unsigned long size)
 {
@@ -93,7 +94,7 @@ static int pprint_tag(const unsigned char *sha1, const char *buf, unsigned long
 	return 0;
 }
 
-int main(int argc, char **argv)
+int cmd_cat_file(int argc, const char **argv, char **envp)
 {
 	unsigned char sha1[20];
 	char type[20];

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-commit-tree.c

@@ -6,6 +6,7 @@
 #include "cache.h"
 #include "commit.h"
 #include "tree.h"
+#include "builtin.h"
 
 #define BLOCKING (1ul << 14)
 
@@ -76,7 +77,7 @@ static int new_parent(int idx)
 	return 1;
 }
 
-int main(int argc, char **argv)
+int cmd_commit_tree(int argc, const char **argv, char **envp)
 {
 	int i;
 	int parents = 0;
@@ -98,7 +99,7 @@ int main(int argc, char **argv)
 
 	check_valid(tree_sha1, tree_type);
 	for (i = 2; i < argc; i += 2) {
-		char *a, *b;
+		const char *a, *b;
 		a = argv[i]; b = argv[i+1];
 		if (!b || strcmp(a, "-p"))
 			usage(commit_tree_usage);

builtin-diff-files.c

@@ -7,12 +7,13 @@
 #include "diff.h"
 #include "commit.h"
 #include "revision.h"
+#include "builtin.h"
 
 static const char diff_files_usage[] =
 "git-diff-files [-q] [-0/-1/2/3 |-c|--cc] [<common diff options>] [<path>...]"
 COMMON_DIFF_OPTIONS_HELP;
 
-int main(int argc, const char **argv)
+int cmd_diff_files(int argc, const char **argv, char **envp)
 {
 	struct rev_info rev;
 	int silent = 0;

builtin-diff-index.c

@@ -2,13 +2,14 @@
 #include "diff.h"
 #include "commit.h"
 #include "revision.h"
+#include "builtin.h"
 
 static const char diff_cache_usage[] =
 "git-diff-index [-m] [--cached] "
 "[<common diff options>] <tree-ish> [<path>...]"
 COMMON_DIFF_OPTIONS_HELP;
 
-int main(int argc, const char **argv)
+int cmd_diff_index(int argc, const char **argv, char **envp)
 {
 	struct rev_info rev;
 	int cached = 0;

builtin-diff-stages.c

@@ -4,6 +4,7 @@
 
 #include "cache.h"
 #include "diff.h"
+#include "builtin.h"
 
 static struct diff_options diff_options;
 
@@ -54,7 +55,7 @@ static void diff_stages(int stage1, int stage2, const char **pathspec)
 	}
 }
 
-int main(int ac, const char **av)
+int cmd_diff_stages(int ac, const char **av, char **envp)
 {
 	int stage1, stage2;
 	const char *prefix = setup_git_directory();

builtin-diff-tree.c

@@ -2,6 +2,7 @@
 #include "diff.h"
 #include "commit.h"
 #include "log-tree.h"
+#include "builtin.h"
 
 static struct rev_info log_tree_opt;
 
@@ -58,7 +59,7 @@ static const char diff_tree_usage[] =
 "  --root        include the initial commit as diff against /dev/null\n"
 COMMON_DIFF_OPTIONS_HELP;
 
-int main(int argc, const char **argv)
+int cmd_diff_tree(int argc, const char **argv, char **envp)
 {
 	int nr_sha1;
 	char line[1000];
@@ -138,7 +139,10 @@ 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;
 }

builtin-diff.c

@@ -122,7 +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;
@@ -233,7 +233,7 @@ static int builtin_diff_combined(struct rev_info *revs,
 	return 0;
 }
 
-static void add_head(struct rev_info *revs)
+void add_head(struct rev_info *revs)
 {
 	unsigned char sha1[20];
 	struct object *obj;

builtin-grep.c

@@ -453,7 +453,6 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 
 	len = nr = 0;
 	push_arg("grep");
-	push_arg("-H");
 	if (opt->fixed)
 		push_arg("-F");
 	if (opt->linenum)
@@ -503,17 +502,35 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 		push_arg("-e");
 		push_arg(p->pattern);
 	}
-	push_arg("--");
+
+	/*
+	 * 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];
+		char *name;
 		if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode)))
 			continue;
 		if (!pathspec_matches(paths, ce->name))
 			continue;
-		argv[argc++] = ce->name;
+		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);

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

@@ -11,6 +11,9 @@
 #include "log-tree.h"
 #include "builtin.h"
 
+/* this is in builtin-diff.c */
+void add_head(struct rev_info *revs);
+
 static int cmd_log_wc(int argc, const char **argv, char **envp,
 		      struct rev_info *rev)
 {
@@ -20,6 +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]);
@@ -69,12 +79,76 @@ int cmd_log(int argc, const char **argv, char **envp)
 	return cmd_log_wc(argc, argv, envp, &rev);
 }
 
+static int istitlechar(char c)
+{
+	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') ||
+		(c >= '0' && c <= '9') || c == '.' || c == '_';
+}
+
+static FILE *realstdout = NULL;
+static char *output_directory = NULL;
+
+static void reopen_stdout(struct commit *commit, int nr, int keep_subject)
+{
+	char filename[1024];
+	char *sol;
+	int len = 0;
+
+	if (output_directory) {
+		strncpy(filename, output_directory, 1010);
+		len = strlen(filename);
+		if (filename[len - 1] != '/')
+			filename[len++] = '/';
+	}
+
+	sprintf(filename + len, "%04d", nr);
+	len = strlen(filename);
+
+	sol = strstr(commit->buffer, "\n\n");
+	if (sol) {
+		int j, space = 1;
+
+		sol += 2;
+		/* strip [PATCH] or [PATCH blabla] */
+		if (!keep_subject && !strncmp(sol, "[PATCH", 6)) {
+			char *eos = strchr(sol + 6, ']');
+			if (eos) {
+				while (isspace(*eos))
+					eos++;
+				sol = eos;
+			}
+		}
+
+		for (j = 0; len < 1024 - 6 && sol[j] && sol[j] != '\n'; j++) {
+			if (istitlechar(sol[j])) {
+				if (space) {
+					filename[len++] = '-';
+					space = 0;
+				}
+				filename[len++] = sol[j];
+				if (sol[j] == '.')
+					while (sol[j + 1] == '.')
+						j++;
+			} else
+				space = 1;
+		}
+		while (filename[len - 1] == '.' || filename[len - 1] == '-')
+			len--;
+	}
+	strcpy(filename + len, ".txt");
+	fprintf(realstdout, "%s\n", filename);
+	freopen(filename, "w", stdout);
+}
+
 int cmd_format_patch(int argc, const char **argv, char **envp)
 {
 	struct commit *commit;
 	struct commit **list = NULL;
 	struct rev_info rev;
-	int nr = 0;
+	int nr = 0, total, i, j;
+	int use_stdout = 0;
+	int numbered = 0;
+	int keep_subject = 0;
 
 	init_revisions(&rev);
 	rev.commit_format = CMIT_FMT_EMAIL;
@@ -85,23 +159,89 @@ int cmd_format_patch(int argc, const char **argv, char **envp)
 	rev.combine_merges = 0;
 	rev.ignore_merges = 1;
 	rev.diffopt.output_format = DIFF_FORMAT_PATCH;
+
+	/*
+	 * Parse the arguments before setup_revisions(), or something
+	 * like "git fmt-patch -o a123 HEAD^.." may fail; a123 is
+	 * possibly a valid SHA1.
+	 */
+	for (i = 1, j = 1; i < argc; i++) {
+		if (!strcmp(argv[i], "--stdout"))
+			use_stdout = 1;
+		else if (!strcmp(argv[i], "-n") ||
+				!strcmp(argv[i], "--numbered"))
+			numbered = 1;
+		else if (!strcmp(argv[i], "-k") ||
+				!strcmp(argv[i], "--keep-subject")) {
+			keep_subject = 1;
+			rev.total = -1;
+		} else if (!strcmp(argv[i], "-o")) {
+			if (argc < 3)
+				die ("Which directory?");
+			if (mkdir(argv[i + 1], 0777) < 0 && errno != EEXIST)
+				die("Could not create directory %s",
+						argv[i + 1]);
+			output_directory = strdup(argv[i + 1]);
+			i++;
+		}
+		else if (!strcmp(argv[i], "--attach"))
+			rev.mime_boundary = git_version_string;
+		else if (!strncmp(argv[i], "--attach=", 9))
+			rev.mime_boundary = argv[i] + 9;
+		else
+			argv[j++] = argv[i];
+	}
+	argc = j;
+
+	if (numbered && keep_subject < 0)
+		die ("-n and -k are mutually exclusive.");
+
 	argc = setup_revisions(argc, argv, &rev, "HEAD");
+	if (argc > 1)
+		die ("unrecognized argument: %s", argv[1]);
+
+	if (rev.pending_objects && rev.pending_objects->next == NULL) {
+		rev.pending_objects->item->flags |= UNINTERESTING;
+		add_head(&rev);
+	}
+
+	if (!use_stdout)
+		realstdout = fdopen(dup(1), "w");
 
 	prepare_revision_walk(&rev);
 	while ((commit = get_revision(&rev)) != NULL) {
+		/* ignore merges */
+		if (commit->parents && commit->parents->next)
+			continue;
 		nr++;
 		list = realloc(list, nr * sizeof(list[0]));
 		list[nr - 1] = commit;
 	}
+	total = nr;
+	if (numbered)
+		rev.total = total;
 	while (0 <= --nr) {
 		int shown;
 		commit = list[nr];
+		rev.nr = total - nr;
+		if (!use_stdout)
+			reopen_stdout(commit, rev.nr, keep_subject);
 		shown = log_tree_commit(&rev, commit);
 		free(commit->buffer);
 		commit->buffer = NULL;
-		if (shown)
-			printf("-- \n%s\n\n", git_version_string);
+		if (shown) {
+			if (rev.mime_boundary)
+				printf("\n--%s%s--\n\n\n",
+				       mime_boundary_leader,
+				       rev.mime_boundary);
+			else
+				printf("-- \n%s\n\n", git_version_string);
+		}
+		if (!use_stdout)
+			fclose(stdout);
 	}
+	if (output_directory)
+		free(output_directory);
 	free(list);
 	return 0;
 }

builtin-ls-files.c

@@ -5,23 +5,21 @@
  *
  * Copyright (C) Linus Torvalds, 2005
  */
-#include <dirent.h>
 #include <fnmatch.h>
 
 #include "cache.h"
 #include "quote.h"
+#include "dir.h"
+#include "builtin.h"
 
 static int abbrev = 0;
 static int show_deleted = 0;
 static int show_cached = 0;
 static int show_others = 0;
-static int show_ignored = 0;
 static int show_stage = 0;
 static int show_unmerged = 0;
 static int show_modified = 0;
 static int show_killed = 0;
-static int show_other_directories = 0;
-static int hide_empty_directories = 0;
 static int show_valid_bit = 0;
 static int line_terminator = '\n';
 
@@ -38,309 +36,6 @@ static const char *tag_other = "";
 static const char *tag_killed = "";
 static const char *tag_modified = "";
 
-static const char *exclude_per_dir = NULL;
-
-/* We maintain three exclude pattern lists:
- * EXC_CMDL lists patterns explicitly given on the command line.
- * EXC_DIRS lists patterns obtained from per-directory ignore files.
- * EXC_FILE lists patterns from fallback ignore files.
- */
-#define EXC_CMDL 0
-#define EXC_DIRS 1
-#define EXC_FILE 2
-static struct exclude_list {
-	int nr;
-	int alloc;
-	struct exclude {
-		const char *pattern;
-		const char *base;
-		int baselen;
-	} **excludes;
-} exclude_list[3];
-
-static void add_exclude(const char *string, const char *base,
-			int baselen, struct exclude_list *which)
-{
-	struct exclude *x = xmalloc(sizeof (*x));
-
-	x->pattern = string;
-	x->base = base;
-	x->baselen = baselen;
-	if (which->nr == which->alloc) {
-		which->alloc = alloc_nr(which->alloc);
-		which->excludes = realloc(which->excludes,
-					  which->alloc * sizeof(x));
-	}
-	which->excludes[which->nr++] = x;
-}
-
-static int add_excludes_from_file_1(const char *fname,
-				    const char *base,
-				    int baselen,
-				    struct exclude_list *which)
-{
-	int fd, i;
-	long size;
-	char *buf, *entry;
-
-	fd = open(fname, O_RDONLY);
-	if (fd < 0)
-		goto err;
-	size = lseek(fd, 0, SEEK_END);
-	if (size < 0)
-		goto err;
-	lseek(fd, 0, SEEK_SET);
-	if (size == 0) {
-		close(fd);
-		return 0;
-	}
-	buf = xmalloc(size+1);
-	if (read(fd, buf, size) != size)
-		goto err;
-	close(fd);
-
-	buf[size++] = '\n';
-	entry = buf;
-	for (i = 0; i < size; i++) {
-		if (buf[i] == '\n') {
-			if (entry != buf + i && entry[0] != '#') {
-				buf[i - (i && buf[i-1] == '\r')] = 0;
-				add_exclude(entry, base, baselen, which);
-			}
-			entry = buf + i + 1;
-		}
-	}
-	return 0;
-
- err:
-	if (0 <= fd)
-		close(fd);
-	return -1;
-}
-
-static void add_excludes_from_file(const char *fname)
-{
-	if (add_excludes_from_file_1(fname, "", 0,
-				     &exclude_list[EXC_FILE]) < 0)
-		die("cannot use %s as an exclude file", fname);
-}
-
-static int push_exclude_per_directory(const char *base, int baselen)
-{
-	char exclude_file[PATH_MAX];
-	struct exclude_list *el = &exclude_list[EXC_DIRS];
-	int current_nr = el->nr;
-
-	if (exclude_per_dir) {
-		memcpy(exclude_file, base, baselen);
-		strcpy(exclude_file + baselen, exclude_per_dir);
-		add_excludes_from_file_1(exclude_file, base, baselen, el);
-	}
-	return current_nr;
-}
-
-static void pop_exclude_per_directory(int stk)
-{
-	struct exclude_list *el = &exclude_list[EXC_DIRS];
-
-	while (stk < el->nr)
-		free(el->excludes[--el->nr]);
-}
-
-/* Scan the list and let the last match determines the fate.
- * Return 1 for exclude, 0 for include and -1 for undecided.
- */
-static int excluded_1(const char *pathname,
-		      int pathlen,
-		      struct exclude_list *el)
-{
-	int i;
-
-	if (el->nr) {
-		for (i = el->nr - 1; 0 <= i; i--) {
-			struct exclude *x = el->excludes[i];
-			const char *exclude = x->pattern;
-			int to_exclude = 1;
-
-			if (*exclude == '!') {
-				to_exclude = 0;
-				exclude++;
-			}
-
-			if (!strchr(exclude, '/')) {
-				/* match basename */
-				const char *basename = strrchr(pathname, '/');
-				basename = (basename) ? basename+1 : pathname;
-				if (fnmatch(exclude, basename, 0) == 0)
-					return to_exclude;
-			}
-			else {
-				/* match with FNM_PATHNAME:
-				 * exclude has base (baselen long) implicitly
-				 * in front of it.
-				 */
-				int baselen = x->baselen;
-				if (*exclude == '/')
-					exclude++;
-
-				if (pathlen < baselen ||
-				    (baselen && pathname[baselen-1] != '/') ||
-				    strncmp(pathname, x->base, baselen))
-				    continue;
-
-				if (fnmatch(exclude, pathname+baselen,
-					    FNM_PATHNAME) == 0)
-					return to_exclude;
-			}
-		}
-	}
-	return -1; /* undecided */
-}
-
-static int excluded(const char *pathname)
-{
-	int pathlen = strlen(pathname);
-	int st;
-
-	for (st = EXC_CMDL; st <= EXC_FILE; st++) {
-		switch (excluded_1(pathname, pathlen, &exclude_list[st])) {
-		case 0:
-			return 0;
-		case 1:
-			return 1;
-		}
-	}
-	return 0;
-}
-
-struct nond_on_fs {
-	int len;
-	char name[FLEX_ARRAY]; /* more */
-};
-
-static struct nond_on_fs **dir;
-static int nr_dir;
-static int dir_alloc;
-
-static void add_name(const char *pathname, int len)
-{
-	struct nond_on_fs *ent;
-
-	if (cache_name_pos(pathname, len) >= 0)
-		return;
-
-	if (nr_dir == dir_alloc) {
-		dir_alloc = alloc_nr(dir_alloc);
-		dir = xrealloc(dir, dir_alloc*sizeof(ent));
-	}
-	ent = xmalloc(sizeof(*ent) + len + 1);
-	ent->len = len;
-	memcpy(ent->name, pathname, len);
-	ent->name[len] = 0;
-	dir[nr_dir++] = ent;
-}
-
-static int dir_exists(const char *dirname, int len)
-{
-	int pos = cache_name_pos(dirname, len);
-	if (pos >= 0)
-		return 1;
-	pos = -pos-1;
-	if (pos >= active_nr) /* can't */
-		return 0;
-	return !strncmp(active_cache[pos]->name, dirname, len);
-}
-
-/*
- * Read a directory tree. We currently ignore anything but
- * directories, regular files and symlinks. That's because git
- * doesn't handle them at all yet. Maybe that will change some
- * day.
- *
- * Also, we ignore the name ".git" (even if it is not a directory).
- * That likely will not change.
- */
-static int read_directory(const char *path, const char *base, int baselen)
-{
-	DIR *fdir = opendir(path);
-	int contents = 0;
-
-	if (fdir) {
-		int exclude_stk;
-		struct dirent *de;
-		char fullname[MAXPATHLEN + 1];
-		memcpy(fullname, base, baselen);
-
-		exclude_stk = push_exclude_per_directory(base, baselen);
-
-		while ((de = readdir(fdir)) != NULL) {
-			int len;
-
-			if ((de->d_name[0] == '.') &&
-			    (de->d_name[1] == 0 ||
-			     !strcmp(de->d_name + 1, ".") ||
-			     !strcmp(de->d_name + 1, "git")))
-				continue;
-			len = strlen(de->d_name);
-			memcpy(fullname + baselen, de->d_name, len+1);
-			if (excluded(fullname) != show_ignored) {
-				if (!show_ignored || DTYPE(de) != DT_DIR) {
-					continue;
-				}
-			}
-
-			switch (DTYPE(de)) {
-			struct stat st;
-			int subdir, rewind_base;
-			default:
-				continue;
-			case DT_UNKNOWN:
-				if (lstat(fullname, &st))
-					continue;
-				if (S_ISREG(st.st_mode) || S_ISLNK(st.st_mode))
-					break;
-				if (!S_ISDIR(st.st_mode))
-					continue;
-				/* fallthrough */
-			case DT_DIR:
-				memcpy(fullname + baselen + len, "/", 2);
-				len++;
-				rewind_base = nr_dir;
-				subdir = read_directory(fullname, fullname,
-				                        baselen + len);
-				if (show_other_directories &&
-				    (subdir || !hide_empty_directories) &&
-				    !dir_exists(fullname, baselen + len)) {
-					// Rewind the read subdirectory
-					while (nr_dir > rewind_base)
-						free(dir[--nr_dir]);
-					break;
-				}
-				contents += subdir;
-				continue;
-			case DT_REG:
-			case DT_LNK:
-				break;
-			}
-			add_name(fullname, baselen + len);
-			contents++;
-		}
-		closedir(fdir);
-
-		pop_exclude_per_directory(exclude_stk);
-	}
-
-	return contents;
-}
-
-static int cmp_name(const void *p1, const void *p2)
-{
-	const struct nond_on_fs *e1 = *(const struct nond_on_fs **)p1;
-	const struct nond_on_fs *e2 = *(const struct nond_on_fs **)p2;
-
-	return cache_name_compare(e1->name, e1->len,
-				  e2->name, e2->len);
-}
 
 /*
  * Match a pathspec against a filename. The first "len" characters
@@ -377,7 +72,7 @@ static int match(const char **spec, char *ps_matched,
 	return 0;
 }
 
-static void show_dir_entry(const char *tag, struct nond_on_fs *ent)
+static void show_dir_entry(const char *tag, struct dir_entry *ent)
 {
 	int len = prefix_len;
 	int offset = prefix_offset;
@@ -393,14 +88,14 @@ static void show_dir_entry(const char *tag, struct nond_on_fs *ent)
 	putchar(line_terminator);
 }
 
-static void show_other_files(void)
+static void show_other_files(struct dir_struct *dir)
 {
 	int i;
-	for (i = 0; i < nr_dir; i++) {
+	for (i = 0; i < dir->nr; i++) {
 		/* We should not have a matching entry, but we
 		 * may have an unmerged entry for this path.
 		 */
-		struct nond_on_fs *ent = dir[i];
+		struct dir_entry *ent = dir->entries[i];
 		int pos = cache_name_pos(ent->name, ent->len);
 		struct cache_entry *ce;
 		if (0 <= pos)
@@ -416,11 +111,11 @@ static void show_other_files(void)
 	}
 }
 
-static void show_killed_files(void)
+static void show_killed_files(struct dir_struct *dir)
 {
 	int i;
-	for (i = 0; i < nr_dir; i++) {
-		struct nond_on_fs *ent = dir[i];
+	for (i = 0; i < dir->nr; i++) {
+		struct dir_entry *ent = dir->entries[i];
 		char *cp, *sp;
 		int pos, len, killed = 0;
 
@@ -461,7 +156,7 @@ static void show_killed_files(void)
 			}
 		}
 		if (killed)
-			show_dir_entry(tag_killed, dir[i]);
+			show_dir_entry(tag_killed, dir->entries[i]);
 	}
 }
 
@@ -512,7 +207,7 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce)
 	}
 }
 
-static void show_files(void)
+static void show_files(struct dir_struct *dir)
 {
 	int i;
 
@@ -521,39 +216,18 @@ static void show_files(void)
 		const char *path = ".", *base = "";
 		int baselen = prefix_len;
 
-		if (baselen) {
+		if (baselen)
 			path = base = prefix;
-			if (exclude_per_dir) {
-				char *p, *pp = xmalloc(baselen+1);
-				memcpy(pp, prefix, baselen+1);
-				p = pp;
-				while (1) {
-					char save = *p;
-					*p = 0;
-					push_exclude_per_directory(pp, p-pp);
-					*p++ = save;
-					if (!save)
-						break;
-					p = strchr(p, '/');
-					if (p)
-						p++;
-					else
-						p = pp + baselen;
-				}
-				free(pp);
-			}
-		}
-		read_directory(path, base, baselen);
-		qsort(dir, nr_dir, sizeof(struct nond_on_fs *), cmp_name);
+		read_directory(dir, path, base, baselen);
 		if (show_others)
-			show_other_files();
+			show_other_files(dir);
 		if (show_killed)
-			show_killed_files();
+			show_killed_files(dir);
 	}
 	if (show_cached | show_stage) {
 		for (i = 0; i < active_nr; i++) {
 			struct cache_entry *ce = active_cache[i];
-			if (excluded(ce->name) != show_ignored)
+			if (excluded(dir, ce->name) != dir->show_ignored)
 				continue;
 			if (show_unmerged && !ce_stage(ce))
 				continue;
@@ -565,7 +239,7 @@ static void show_files(void)
 			struct cache_entry *ce = active_cache[i];
 			struct stat st;
 			int err;
-			if (excluded(ce->name) != show_ignored)
+			if (excluded(dir, ce->name) != dir->show_ignored)
 				continue;
 			err = lstat(ce->name, &st);
 			if (show_deleted && err)
@@ -648,11 +322,13 @@ static const char ls_files_usage[] =
 	"[ --exclude-per-directory=<filename> ] [--full-name] [--abbrev] "
 	"[--] [<file>]*";
 
-int main(int argc, const char **argv)
+int cmd_ls_files(int argc, const char **argv, char** envp)
 {
 	int i;
 	int exc_given = 0;
+	struct dir_struct dir;
 
+	memset(&dir, 0, sizeof(dir));
 	prefix = setup_git_directory();
 	if (prefix)
 		prefix_offset = strlen(prefix);
@@ -697,7 +373,7 @@ int main(int argc, const char **argv)
 			continue;
 		}
 		if (!strcmp(arg, "-i") || !strcmp(arg, "--ignored")) {
-			show_ignored = 1;
+			dir.show_ignored = 1;
 			continue;
 		}
 		if (!strcmp(arg, "-s") || !strcmp(arg, "--stage")) {
@@ -709,11 +385,11 @@ int main(int argc, const char **argv)
 			continue;
 		}
 		if (!strcmp(arg, "--directory")) {
-			show_other_directories = 1;
+			dir.show_other_directories = 1;
 			continue;
 		}
 		if (!strcmp(arg, "--no-empty-directory")) {
-			hide_empty_directories = 1;
+			dir.hide_empty_directories = 1;
 			continue;
 		}
 		if (!strcmp(arg, "-u") || !strcmp(arg, "--unmerged")) {
@@ -726,27 +402,27 @@ int main(int argc, const char **argv)
 		}
 		if (!strcmp(arg, "-x") && i+1 < argc) {
 			exc_given = 1;
-			add_exclude(argv[++i], "", 0, &exclude_list[EXC_CMDL]);
+			add_exclude(argv[++i], "", 0, &dir.exclude_list[EXC_CMDL]);
 			continue;
 		}
 		if (!strncmp(arg, "--exclude=", 10)) {
 			exc_given = 1;
-			add_exclude(arg+10, "", 0, &exclude_list[EXC_CMDL]);
+			add_exclude(arg+10, "", 0, &dir.exclude_list[EXC_CMDL]);
 			continue;
 		}
 		if (!strcmp(arg, "-X") && i+1 < argc) {
 			exc_given = 1;
-			add_excludes_from_file(argv[++i]);
+			add_excludes_from_file(&dir, argv[++i]);
 			continue;
 		}
 		if (!strncmp(arg, "--exclude-from=", 15)) {
 			exc_given = 1;
-			add_excludes_from_file(arg+15);
+			add_excludes_from_file(&dir, arg+15);
 			continue;
 		}
 		if (!strncmp(arg, "--exclude-per-directory=", 24)) {
 			exc_given = 1;
-			exclude_per_dir = arg + 24;
+			dir.exclude_per_dir = arg + 24;
 			continue;
 		}
 		if (!strcmp(arg, "--full-name")) {
@@ -788,7 +464,7 @@ int main(int argc, const char **argv)
 		ps_matched = xcalloc(1, num);
 	}
 
-	if (show_ignored && !exc_given) {
+	if (dir.show_ignored && !exc_given) {
 		fprintf(stderr, "%s: --ignored needs some exclude pattern\n",
 			argv[0]);
 		exit(1);
@@ -802,7 +478,7 @@ int main(int argc, const char **argv)
 	read_cache();
 	if (prefix)
 		prune_cache();
-	show_files();
+	show_files(&dir);
 
 	if (ps_matched) {
 		/* We need to make sure all pathspec matched otherwise

builtin-ls-tree.c

@@ -7,6 +7,7 @@
 #include "blob.h"
 #include "tree.h"
 #include "quote.h"
+#include "builtin.h"
 
 static int line_termination = '\n';
 #define LS_RECURSIVE 1
@@ -15,7 +16,7 @@ static int line_termination = '\n';
 #define LS_NAME_ONLY 8
 static int abbrev = 0;
 static int ls_options = 0;
-const char **pathspec;
+static const char **pathspec;
 static int chomp_prefix = 0;
 static const char *prefix;
 
@@ -84,7 +85,7 @@ static int show_tree(unsigned char *sha1, const char *base, int baselen,
 	return retval;
 }
 
-int main(int argc, const char **argv)
+int cmd_ls_tree(int argc, const char **argv, char **envp)
 {
 	unsigned char sha1[20];
 	struct tree *tree;

builtin-read-tree.c

@@ -11,6 +11,7 @@
 #include "tree.h"
 #include <sys/time.h>
 #include <signal.h>
+#include "builtin.h"
 
 static int reset = 0;
 static int merge = 0;
@@ -408,7 +409,7 @@ static void verify_uptodate(struct cache_entry *ce)
 {
 	struct stat st;
 
-	if (index_only)
+	if (index_only || reset)
 		return;
 
 	if (!lstat(ce->name, &st)) {
@@ -426,6 +427,21 @@ static void verify_uptodate(struct cache_entry *ce)
 	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);
@@ -443,6 +459,9 @@ 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;
@@ -452,6 +471,8 @@ 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;
@@ -487,6 +508,7 @@ 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;
@@ -498,8 +520,11 @@ 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];
@@ -515,8 +540,15 @@ 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++) {
@@ -575,6 +607,8 @@ 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;
 		}
 		/*
@@ -592,6 +626,8 @@ static int threeway_merge(struct cache_entry **stages)
 	if (index) {
 		verify_uptodate(index);
 	}
+	else if (path)
+		verify_absent(path, "overwritten");
 
 	nontrivial_merge = 1;
 
@@ -689,7 +725,7 @@ static int oneway_merge(struct cache_entry **src)
 			     merge_size);
 
 	if (!a)
-		return deleted_entry(old, NULL);
+		return deleted_entry(old, old);
 	if (old && same(old, a)) {
 		if (reset) {
 			struct stat st;
@@ -699,7 +735,7 @@ static int oneway_merge(struct cache_entry **src)
 		}
 		return keep_entry(old);
 	}
-	return merged_entry(a, NULL);
+	return merged_entry(a, old);
 }
 
 static int read_cache_unmerged(void)
@@ -728,7 +764,7 @@ static const char read_tree_usage[] = "git-read-tree (<sha> | -m [--aggressive]
 
 static struct cache_file cache_file;
 
-int main(int argc, char **argv)
+int cmd_read_tree(int argc, const char **argv, char **envp)
 {
 	int i, newfd, stage = 0;
 	unsigned char sha1[20];

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;
@@ -84,7 +85,7 @@ static void show_commit(struct commit *commit)
 		static char pretty_header[16384];
 		pretty_print_commit(revs.commit_format, commit, ~0,
 				    pretty_header, sizeof(pretty_header),
-				    revs.abbrev);
+				    revs.abbrev, NULL, NULL);
 		printf("%s%c", pretty_header, hdr_termination);
 	}
 	fflush(stdout);
@@ -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-rm.c

@@ -0,0 +1,150 @@
+/*
+ * "git rm" builtin command
+ *
+ * Copyright (C) Linus Torvalds 2006
+ */
+#include "cache.h"
+#include "builtin.h"
+#include "dir.h"
+
+static const char builtin_rm_usage[] =
+"git-rm [-n] [-v] [-f] <filepattern>...";
+
+static struct {
+	int nr, alloc;
+	const char **name;
+} list;
+
+static void add_list(const char *name)
+{
+	if (list.nr >= list.alloc) {
+		list.alloc = alloc_nr(list.alloc);
+		list.name = xrealloc(list.name, list.alloc * sizeof(const char *));
+	}
+	list.name[list.nr++] = name;
+}
+
+static int remove_file(const char *name)
+{
+	int ret;
+	char *slash;
+
+	ret = unlink(name);
+	if (!ret && (slash = strrchr(name, '/'))) {
+		char *n = strdup(name);
+		do {
+			n[slash - name] = 0;
+			name = n;
+		} while (!rmdir(name) && (slash = strrchr(name, '/')));
+	}
+	return ret;
+}
+
+static struct cache_file cache_file;
+
+int cmd_rm(int argc, const char **argv, char **envp)
+{
+	int i, newfd;
+	int verbose = 0, show_only = 0, force = 0;
+	const char *prefix = setup_git_directory();
+	const char **pathspec;
+	char *seen;
+
+	git_config(git_default_config);
+
+	newfd = hold_index_file_for_update(&cache_file, get_index_file());
+	if (newfd < 0)
+		die("unable to create new index file");
+
+	if (read_cache() < 0)
+		die("index file corrupt");
+
+	for (i = 1 ; i < argc ; i++) {
+		const char *arg = argv[i];
+
+		if (*arg != '-')
+			break;
+		if (!strcmp(arg, "--")) {
+			i++;
+			break;
+		}
+		if (!strcmp(arg, "-n")) {
+			show_only = 1;
+			continue;
+		}
+		if (!strcmp(arg, "-v")) {
+			verbose = 1;
+			continue;
+		}
+		if (!strcmp(arg, "-f")) {
+			force = 1;
+			continue;
+		}
+		die(builtin_rm_usage);
+	}
+	pathspec = get_pathspec(prefix, argv + i);
+
+	seen = NULL;
+	if (pathspec) {
+		for (i = 0; pathspec[i] ; i++)
+			/* nothing */;
+		seen = xmalloc(i);
+		memset(seen, 0, i);
+	}
+
+	for (i = 0; i < active_nr; i++) {
+		struct cache_entry *ce = active_cache[i];
+		if (!match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, seen))
+			continue;
+		add_list(ce->name);
+	}
+
+	if (pathspec) {
+		const char *match;
+		for (i = 0; (match = pathspec[i]) != NULL ; i++) {
+			if (*match && !seen[i])
+				die("pathspec '%s' did not match any files", match);
+		}
+	}
+
+	/*
+	 * First remove the names from the index: we won't commit
+	 * the index unless all of them succeed
+	 */
+	for (i = 0; i < list.nr; i++) {
+		const char *path = list.name[i];
+		printf("rm '%s'\n", path);
+
+		if (remove_file_from_cache(path))
+			die("git rm: unable to remove %s", path);
+	}
+
+	/*
+	 * Then, if we used "-f", remove the filenames from the
+	 * workspace. If we fail to remove the first one, we
+	 * abort the "git rm" (but once we've successfully removed
+	 * any file at all, we'll go ahead and commit to it all:
+	 * by then we've already committed ourself and can't fail
+	 * in the middle)
+	 */
+	if (force) {
+		int removed = 0;
+		for (i = 0; i < list.nr; i++) {
+			const char *path = list.name[i];
+			if (!remove_file(path)) {
+				removed = 1;
+				continue;
+			}
+			if (!removed)
+				die("git rm: %s: %s", path, strerror(errno));
+		}
+	}
+
+	if (active_cache_changed) {
+		if (write_cache(newfd, active_cache, active_nr) ||
+		    commit_index_file(&cache_file))
+			die("Unable to write new index file");
+	}
+
+	return 0;
+}

builtin-show-branch.c

@@ -3,13 +3,14 @@
 #include "cache.h"
 #include "commit.h"
 #include "refs.h"
+#include "builtin.h"
 
 static const char show_branch_usage[] =
 "git-show-branch [--dense] [--current] [--all] [--heads] [--tags] [--topo-order] [--more=count | --list | --independent | --merge-base ] [--topics] [<refs>...]";
 
 static int default_num = 0;
 static int default_alloc = 0;
-static char **default_arg = NULL;
+static const char **default_arg = NULL;
 
 #define UNINTERESTING	01
 
@@ -259,7 +260,7 @@ static void show_one_commit(struct commit *commit, int no_name)
 	struct commit_name *name = commit->object.util;
 	if (commit->object.parsed)
 		pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0,
-				    pretty, sizeof(pretty), 0);
+				    pretty, sizeof(pretty), 0, NULL, NULL);
 	else
 		strcpy(pretty, "(unavailable)");
 	if (!strncmp(pretty, "[PATCH] ", 8))
@@ -548,7 +549,7 @@ static int omit_in_dense(struct commit *commit, struct commit **rev, int n)
 	return 0;
 }
 
-int main(int ac, char **av)
+int cmd_show_branch(int ac, const char **av, char **envp)
 {
 	struct commit *rev[MAX_REVS], *commit;
 	struct commit_list *list = NULL, *seen = NULL;
@@ -581,7 +582,7 @@ int main(int ac, char **av)
 	}
 
 	while (1 < ac && av[1][0] == '-') {
-		char *arg = av[1];
+		const char *arg = av[1];
 		if (!strcmp(arg, "--")) {
 			ac--; av++;
 			break;

builtin-tar-tree.c

@@ -7,11 +7,14 @@
 #include "commit.h"
 #include "strbuf.h"
 #include "tar.h"
+#include "builtin.h"
+#include "pkt-line.h"
 
 #define RECORDSIZE	(512)
 #define BLOCKSIZE	(RECORDSIZE * 20)
 
-static const char tar_tree_usage[] = "git-tar-tree <key> [basedir]";
+static const char tar_tree_usage[] =
+"git-tar-tree [--remote=<repo>] <ent> [basedir]";
 
 static char block[BLOCKSIZE];
 static unsigned long offset;
@@ -301,7 +304,7 @@ static void traverse_tree(struct tree_desc *tree, struct strbuf *path)
 	}
 }
 
-int main(int argc, char **argv)
+static int generate_tar(int argc, const char **argv, char** envp)
 {
 	unsigned char sha1[20], tree_sha1[20];
 	struct commit *commit;
@@ -348,3 +351,58 @@ int main(int argc, char **argv)
 	free(current_path.buf);
 	return 0;
 }
+
+static const char *exec = "git-upload-tar";
+
+static int remote_tar(int argc, const char **argv)
+{
+	int fd[2], ret, len;
+	pid_t pid;
+	char buf[1024];
+	char *url;
+
+	if (argc < 3 || 4 < argc)
+		usage(tar_tree_usage);
+
+	/* --remote=<repo> */
+	url = strdup(argv[1]+9);
+	pid = git_connect(fd, url, exec);
+	if (pid < 0)
+		return 1;
+
+	packet_write(fd[1], "want %s\n", argv[2]);
+	if (argv[3])
+		packet_write(fd[1], "base %s\n", argv[3]);
+	packet_flush(fd[1]);
+
+	len = packet_read_line(fd[0], buf, sizeof(buf));
+	if (!len)
+		die("git-tar-tree: expected ACK/NAK, got EOF");
+	if (buf[len-1] == '\n')
+		buf[--len] = 0;
+	if (strcmp(buf, "ACK")) {
+		if (5 < len && !strncmp(buf, "NACK ", 5))
+			die("git-tar-tree: NACK %s", buf + 5);
+		die("git-tar-tree: protocol error");
+	}
+	/* expect a flush */
+	len = packet_read_line(fd[0], buf, sizeof(buf));
+	if (len)
+		die("git-tar-tree: expected a flush");
+
+	/* Now, start reading from fd[0] and spit it out to stdout */
+	ret = copy_fd(fd[0], 1);
+	close(fd[0]);
+
+	ret |= finish_connect(pid);
+	return !!ret;
+}
+
+int cmd_tar_tree(int argc, const char **argv, char **envp)
+{
+	if (argc < 2)
+		usage(tar_tree_usage);
+	if (!strncmp("--remote=", argv[1], 9))
+		return remote_tar(argc, argv);
+	return generate_tar(argc, argv, envp);
+}

builtin-upload-tar.c

@@ -0,0 +1,74 @@
+/*
+ * Copyright (c) 2006 Junio C Hamano
+ */
+#include "cache.h"
+#include "pkt-line.h"
+#include "exec_cmd.h"
+#include "builtin.h"
+
+static const char upload_tar_usage[] = "git-upload-tar <repo>";
+
+static int nak(const char *reason)
+{
+	packet_write(1, "NACK %s\n", reason);
+	packet_flush(1);
+	return 1;
+}
+
+int cmd_upload_tar(int argc, const char **argv, char **envp)
+{
+	int len;
+	const char *dir = argv[1];
+	char buf[8192];
+	unsigned char sha1[20];
+	char *base = NULL;
+	char hex[41];
+	int ac;
+	const char *av[4];
+
+	if (argc != 2)
+		usage(upload_tar_usage);
+	if (strlen(dir) < sizeof(buf)-1)
+		strcpy(buf, dir); /* enter-repo smudges its argument */
+	else
+		packet_write(1, "NACK insanely long repository name %s\n", dir);
+	if (!enter_repo(buf, 0)) {
+		packet_write(1, "NACK not a git archive %s\n", dir);
+		packet_flush(1);
+		return 1;
+	}
+
+	len = packet_read_line(0, buf, sizeof(buf));
+	if (len < 5 || strncmp("want ", buf, 5))
+		return nak("expected want");
+	if (buf[len-1] == '\n')
+		buf[--len] = 0;
+	if (get_sha1(buf + 5, sha1))
+		return nak("expected sha1");
+        strcpy(hex, sha1_to_hex(sha1));
+
+	len = packet_read_line(0, buf, sizeof(buf));
+	if (len) {
+		if (len < 5 || strncmp("base ", buf, 5))
+			return nak("expected (optional) base");
+		if (buf[len-1] == '\n')
+			buf[--len] = 0;
+		base = strdup(buf + 5);
+		len = packet_read_line(0, buf, sizeof(buf));
+	}
+	if (len)
+		return nak("expected flush");
+
+	packet_write(1, "ACK\n");
+	packet_flush(1);
+
+	ac = 0;
+	av[ac++] = "tar-tree";
+	av[ac++] = hex;
+	if (base)
+		av[ac++] = base;
+	av[ac++] = NULL;
+	execv_git_cmd(av);
+	/* should it return that is an error */
+	return 1;
+}

builtin.h

@@ -25,5 +25,23 @@ 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_rm(int argc, const char **argv, char **envp);
+extern int cmd_add(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);
+extern int cmd_tar_tree(int argc, const char **argv, char **envp);
+extern int cmd_upload_tar(int argc, const char **argv, char **envp);
+extern int cmd_ls_files(int argc, const char **argv, char **envp);
+extern int cmd_ls_tree(int argc, const char **argv, char **envp);
+extern int cmd_read_tree(int argc, const char **argv, char **envp);
+extern int cmd_commit_tree(int argc, const char **argv, char **envp);
+extern int cmd_apply(int argc, const char **argv, char **envp);
+extern int cmd_show_branch(int argc, const char **argv, char **envp);
+extern int cmd_diff_files(int argc, const char **argv, char **envp);
+extern int cmd_diff_index(int argc, const char **argv, char **envp);
+extern int cmd_diff_stages(int argc, const char **argv, char **envp);
+extern int cmd_diff_tree(int argc, const char **argv, char **envp);
+extern int cmd_cat_file(int argc, const char **argv, char **envp);
 
 #endif

cache.h

@@ -142,6 +142,7 @@ extern void verify_non_filename(const char *prefix, const char *name);
 /* Initialize and use the cache information */
 extern int read_cache(void);
 extern int write_cache(int newfd, struct cache_entry **cache, int entries);
+extern int verify_path(const char *path);
 extern int cache_name_pos(const char *name, int namelen);
 #define ADD_CACHE_OK_TO_ADD 1		/* Ok to add */
 #define ADD_CACHE_OK_TO_REPLACE 2	/* Ok to replace file/directory */
@@ -154,10 +155,17 @@ extern int ce_match_stat(struct cache_entry *ce, struct stat *st, int);
 extern int ce_modified(struct cache_entry *ce, struct stat *st, int);
 extern int ce_path_match(const struct cache_entry *ce, const char **pathspec);
 extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, const char *type);
+extern int read_pipe(int fd, char** return_buf, unsigned long* return_size);
 extern int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object);
 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];

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;
-}

commit.c

@@ -422,6 +422,46 @@ static int get_one_line(const char *msg, unsigned long len)
 	return ret;
 }
 
+static int is_rfc2047_special(char ch)
+{
+	return ((ch & 0x80) || (ch == '=') || (ch == '?') || (ch == '_'));
+}
+
+static int add_rfc2047(char *buf, const char *line, int len)
+{
+	char *bp = buf;
+	int i, needquote;
+	static const char q_utf8[] = "=?utf-8?q?";
+
+	for (i = needquote = 0; !needquote && i < len; i++) {
+		unsigned ch = line[i];
+		if (ch & 0x80)
+			needquote++;
+		if ((i + 1 < len) &&
+		    (ch == '=' && line[i+1] == '?'))
+			needquote++;
+	}
+	if (!needquote)
+		return sprintf(buf, "%.*s", len, line);
+
+	memcpy(bp, q_utf8, sizeof(q_utf8)-1);
+	bp += sizeof(q_utf8)-1;
+	for (i = 0; i < len; i++) {
+		unsigned ch = line[i];
+		if (is_rfc2047_special(ch)) {
+			sprintf(bp, "=%02X", ch);
+			bp += 3;
+		}
+		else if (ch == ' ')
+			*bp++ = '_';
+		else
+			*bp++ = ch;
+	}
+	memcpy(bp, "?=", 2);
+	bp += 2;
+	return bp - buf;
+}
+
 static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const char *line)
 {
 	char *date;
@@ -440,12 +480,26 @@ static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const c
 	tz = strtol(date, NULL, 10);
 
 	if (fmt == CMIT_FMT_EMAIL) {
-		what = "From";
+		char *name_tail = strchr(line, '<');
+		int display_name_length;
+		if (!name_tail)
+			return 0;
+		while (line < name_tail && isspace(name_tail[-1]))
+			name_tail--;
+		display_name_length = name_tail - line;
 		filler = "";
+		strcpy(buf, "From: ");
+		ret = strlen(buf);
+		ret += add_rfc2047(buf + ret, line, display_name_length);
+		memcpy(buf + ret, name_tail, namelen - display_name_length);
+		ret += namelen - display_name_length;
+		buf[ret++] = '\n';
+	}
+	else {
+		ret = sprintf(buf, "%s: %.*s%.*s\n", what,
+			      (fmt == CMIT_FMT_FULLER) ? 4 : 0,
+			      filler, namelen, line);
 	}
-	ret = sprintf(buf, "%s: %.*s%.*s\n", what,
-		      (fmt == CMIT_FMT_FULLER) ? 4 : 0,
-		      filler, namelen, line);
 	switch (fmt) {
 	case CMIT_FMT_MEDIUM:
 		ret += sprintf(buf + ret, "Date:   %s\n", show_date(time, tz));
@@ -498,20 +552,31 @@ static int add_merge_info(enum cmit_fmt fmt, char *buf, const struct commit *com
 	return offset;
 }
 
-unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit, unsigned long len, char *buf, unsigned long space, int abbrev)
+unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit, unsigned long len, char *buf, unsigned long space, int abbrev, const char *subject, const char *after_subject)
 {
 	int hdr = 1, body = 0;
 	unsigned long offset = 0;
 	int indent = 4;
 	int parents_shown = 0;
 	const char *msg = commit->buffer;
-	const char *subject = NULL;
+	int plain_non_ascii = 0;
 
-	if (fmt == CMIT_FMT_EMAIL)
-		subject = "Subject: [PATCH] ";
 	if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
 		indent = 0;
 
+	/* After-subject is used to pass in Content-Type: multipart
+	 * MIME header; in that case we do not have to do the
+	 * plaintext content type even if the commit message has
+	 * non 7-bit ASCII character.  Otherwise, check if we need
+	 * to say this is not a 7-bit ASCII.
+	 */
+	if (fmt == CMIT_FMT_EMAIL && !after_subject) {
+		int i;
+		for (i = 0; !plain_non_ascii && msg[i] && i < len; i++)
+			if (msg[i] & 0x80)
+				plain_non_ascii = 1;
+	}
+
 	for (;;) {
 		const char *line = msg;
 		int linelen = get_one_line(msg, len);
@@ -587,13 +652,31 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit
 			int slen = strlen(subject);
 			memcpy(buf + offset, subject, slen);
 			offset += slen;
+			offset += add_rfc2047(buf + offset, line, linelen);
+		}
+		else {
+			memset(buf + offset, ' ', indent);
+			memcpy(buf + offset + indent, line, linelen);
+			offset += linelen + indent;
 		}
-		memset(buf + offset, ' ', indent);
-		memcpy(buf + offset + indent, line, linelen);
-		offset += linelen + indent;
 		buf[offset++] = '\n';
 		if (fmt == CMIT_FMT_ONELINE)
 			break;
+		if (subject && plain_non_ascii) {
+			static const char header[] =
+				"Content-Type: text/plain; charset=UTF-8\n"
+				"Content-Transfer-Encoding: 8bit\n";
+			memcpy(buf + offset, header, sizeof(header)-1);
+			offset += sizeof(header)-1;
+		}
+		if (after_subject) {
+			int slen = strlen(after_subject);
+			if (slen > space - offset - 1)
+				slen = space - offset - 1;
+			memcpy(buf + offset, after_subject, slen);
+			offset += slen;
+			after_subject = NULL;
+		}
 		subject = NULL;
 	}
 	while (offset && isspace(buf[offset-1]))

commit.h

@@ -51,7 +51,7 @@ enum cmit_fmt {
 };
 
 extern enum cmit_fmt get_commit_format(const char *arg);
-extern unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *, unsigned long len, char *buf, unsigned long space, int abbrev);
+extern unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *, unsigned long len, char *buf, unsigned long space, int abbrev, const char *subject, const char *after_subject);
 
 /** Removes the first commit from a list sorted by date, and adds all
  * of its parents.

compat/inet_ntop.c

@@ -0,0 +1,200 @@
+/*
+ * Copyright (c) 1996-1999 by Internet Software Consortium.
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND INTERNET SOFTWARE CONSORTIUM DISCLAIMS
+ * ALL WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES
+ * OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL INTERNET SOFTWARE
+ * CONSORTIUM BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL
+ * DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR
+ * PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
+ * ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS
+ * SOFTWARE.
+ */
+
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <stdio.h>
+#include <string.h>
+
+#ifndef NS_INADDRSZ
+#define NS_INADDRSZ	4
+#endif
+#ifndef NS_IN6ADDRSZ
+#define NS_IN6ADDRSZ	16
+#endif
+#ifndef NS_INT16SZ
+#define NS_INT16SZ	2
+#endif
+
+/*
+ * WARNING: Don't even consider trying to compile this on a system where
+ * sizeof(int) < 4.  sizeof(int) > 4 is fine; all the world's not a VAX.
+ */
+
+/* const char *
+ * inet_ntop4(src, dst, size)
+ *	format an IPv4 address
+ * return:
+ *	`dst' (as a const)
+ * notes:
+ *	(1) uses no statics
+ *	(2) takes a u_char* not an in_addr as input
+ * author:
+ *	Paul Vixie, 1996.
+ */
+static const char *
+inet_ntop4(src, dst, size)
+	const u_char *src;
+	char *dst;
+	size_t size;
+{
+	static const char fmt[] = "%u.%u.%u.%u";
+	char tmp[sizeof "255.255.255.255"];
+	int nprinted;
+
+	nprinted = snprintf(tmp, sizeof(tmp), fmt, src[0], src[1], src[2], src[3]);
+	if (nprinted < 0)
+		return (NULL);	/* we assume "errno" was set by "snprintf()" */
+	if ((size_t)nprinted > size) {
+		errno = ENOSPC;
+		return (NULL);
+	}
+	strcpy(dst, tmp);
+	return (dst);
+}
+
+#ifndef NO_IPV6
+/* const char *
+ * inet_ntop6(src, dst, size)
+ *	convert IPv6 binary address into presentation (printable) format
+ * author:
+ *	Paul Vixie, 1996.
+ */
+static const char *
+inet_ntop6(src, dst, size)
+	const u_char *src;
+	char *dst;
+	size_t size;
+{
+	/*
+	 * Note that int32_t and int16_t need only be "at least" large enough
+	 * to contain a value of the specified size.  On some systems, like
+	 * Crays, there is no such thing as an integer variable with 16 bits.
+	 * Keep this in mind if you think this function should have been coded
+	 * to use pointer overlays.  All the world's not a VAX.
+	 */
+	char tmp[sizeof "ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255"], *tp;
+	struct { int base, len; } best, cur;
+	u_int words[NS_IN6ADDRSZ / NS_INT16SZ];
+	int i;
+
+	/*
+	 * Preprocess:
+	 *	Copy the input (bytewise) array into a wordwise array.
+	 *	Find the longest run of 0x00's in src[] for :: shorthanding.
+	 */
+	memset(words, '\0', sizeof words);
+	for (i = 0; i < NS_IN6ADDRSZ; i++)
+		words[i / 2] |= (src[i] << ((1 - (i % 2)) << 3));
+	best.base = -1;
+	cur.base = -1;
+	for (i = 0; i < (NS_IN6ADDRSZ / NS_INT16SZ); i++) {
+		if (words[i] == 0) {
+			if (cur.base == -1)
+				cur.base = i, cur.len = 1;
+			else
+				cur.len++;
+		} else {
+			if (cur.base != -1) {
+				if (best.base == -1 || cur.len > best.len)
+					best = cur;
+				cur.base = -1;
+			}
+		}
+	}
+	if (cur.base != -1) {
+		if (best.base == -1 || cur.len > best.len)
+			best = cur;
+	}
+	if (best.base != -1 && best.len < 2)
+		best.base = -1;
+
+	/*
+	 * Format the result.
+	 */
+	tp = tmp;
+	for (i = 0; i < (NS_IN6ADDRSZ / NS_INT16SZ); i++) {
+		/* Are we inside the best run of 0x00's? */
+		if (best.base != -1 && i >= best.base &&
+		    i < (best.base + best.len)) {
+			if (i == best.base)
+				*tp++ = ':';
+			continue;
+		}
+		/* Are we following an initial run of 0x00s or any real hex? */
+		if (i != 0)
+			*tp++ = ':';
+		/* Is this address an encapsulated IPv4? */
+		if (i == 6 && best.base == 0 &&
+		    (best.len == 6 || (best.len == 5 && words[5] == 0xffff))) {
+			if (!inet_ntop4(src+12, tp, sizeof tmp - (tp - tmp)))
+				return (NULL);
+			tp += strlen(tp);
+			break;
+		}
+		tp += snprintf(tp, sizeof tmp - (tp - tmp), "%x", words[i]);
+	}
+	/* Was it a trailing run of 0x00's? */
+	if (best.base != -1 && (best.base + best.len) ==
+	    (NS_IN6ADDRSZ / NS_INT16SZ))
+		*tp++ = ':';
+	*tp++ = '\0';
+
+	/*
+	 * Check for overflow, copy, and we're done.
+	 */
+	if ((size_t)(tp - tmp) > size) {
+		errno = ENOSPC;
+		return (NULL);
+	}
+	strcpy(dst, tmp);
+	return (dst);
+}
+#endif
+
+/* char *
+ * inet_ntop(af, src, dst, size)
+ *	convert a network format address to presentation format.
+ * return:
+ *	pointer to presentation format address (`dst'), or NULL (see errno).
+ * author:
+ *	Paul Vixie, 1996.
+ */
+const char *
+inet_ntop(af, src, dst, size)
+	int af;
+	const void *src;
+	char *dst;
+	size_t size;
+{
+	switch (af) {
+	case AF_INET:
+		return (inet_ntop4(src, dst, size));
+#ifndef NO_IPV6
+	case AF_INET6:
+		return (inet_ntop6(src, dst, size));
+#endif
+	default:
+		errno = EAFNOSUPPORT;
+		return (NULL);
+	}
+	/* NOTREACHED */
+}

connect.c

@@ -100,7 +100,7 @@ int path_match(const char *path, int nr, char **match)
 		if (pathlen > len && path[pathlen - len - 1] != '/')
 			continue;
 		*s = 0;
-		return 1;
+		return (i + 1);
 	}
 	return 0;
 }

contrib/git-svn/Makefile

@@ -30,6 +30,7 @@ git-svn.html : git-svn.txt
 		-f ../../Documentation/asciidoc.conf $<
 test: git-svn
 	cd t && $(SHELL) ./t0000-contrib-git-svn.sh
+	cd t && $(SHELL) ./t0001-contrib-git-svn-props.sh
 
 clean:
 	rm -f git-svn *.xml *.html *.1

contrib/git-svn/git-svn.perl

@@ -8,7 +8,7 @@ use vars qw/	$AUTHOR $VERSION
 		$GIT_SVN_INDEX $GIT_SVN
 		$GIT_DIR $REV_DIR/;
 $AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
-$VERSION = '1.0.0';
+$VERSION = '1.1.0-pre';
 
 use Cwd qw/abs_path/;
 $GIT_DIR = abs_path($ENV{GIT_DIR} || '.git');
@@ -39,6 +39,10 @@ my $_svn_co_url_revs;
 my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext,
 		'branch|b=s' => \@_branch_from,
 		'authors-file|A=s' => \$_authors );
+
+# yes, 'native' sets "\n".  Patches to fix this for non-*nix systems welcome:
+my %EOL = ( CR => "\015", LF => "\012", CRLF => "\015\012", native => "\012" );
+
 my %cmd = (
 	fetch => [ \&fetch, "Download new revisions from SVN",
 			{ 'revision|r=s' => \$_revision, %fc_opts } ],
@@ -207,7 +211,7 @@ sub rebuild {
 		push @svn_up, '--ignore-externals' unless $_no_ignore_ext;
 		sys(@svn_up,"-r$newest_rev");
 		$ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX;
-		git_addremove();
+		index_changes();
 		exec('git-write-tree');
 	}
 	waitpid $pid, 0;
@@ -249,7 +253,7 @@ sub fetch {
 		chdir $SVN_WC or croak $!;
 		read_uuid();
 		$last_commit = git_commit($base, @parents);
-		assert_svn_wc_clean($base->{revision}, $last_commit);
+		assert_tree($last_commit);
 	} else {
 		chdir $SVN_WC or croak $!;
 		read_uuid();
@@ -259,16 +263,20 @@ sub fetch {
 	push @svn_up, '--ignore-externals' unless $_no_ignore_ext;
 	my $last = $base;
 	while (my $log_msg = next_log_entry($svn_log)) {
-		assert_svn_wc_clean($last->{revision}, $last_commit);
+		assert_tree($last_commit);
 		if ($last->{revision} >= $log_msg->{revision}) {
 			croak "Out of order: last >= current: ",
 				"$last->{revision} >= $log_msg->{revision}\n";
 		}
+		# Revert is needed for cases like:
+		# https://svn.musicpd.org/Jamming/trunk (r166:167), but
+		# I can't seem to reproduce something like that on a test...
+		sys(qw/svn revert -R ./);
+		assert_svn_wc_clean($last->{revision});
 		sys(@svn_up,"-r$log_msg->{revision}");
 		$last_commit = git_commit($log_msg, $last_commit, @parents);
 		$last = $log_msg;
 	}
-	assert_svn_wc_clean($last->{revision}, $last_commit);
 	unless (-e "$GIT_DIR/refs/heads/master") {
 		sys(qw(git-update-ref refs/heads/master),$last_commit);
 	}
@@ -314,7 +322,6 @@ sub commit {
 		$svn_current_rev = svn_commit_tree($svn_current_rev, $c);
 	}
 	print "Done committing ",scalar @revs," revisions to SVN\n";
-
 }
 
 sub show_ignore {
@@ -367,13 +374,11 @@ sub setup_git_svn {
 }
 
 sub assert_svn_wc_clean {
-	my ($svn_rev, $treeish) = @_;
+	my ($svn_rev) = @_;
 	croak "$svn_rev is not an integer!\n" unless ($svn_rev =~ /^\d+$/);
-	croak "$treeish is not a sha1!\n" unless ($treeish =~ /^$sha1$/o);
 	my $lcr = svn_info('.')->{'Last Changed Rev'};
 	if ($svn_rev != $lcr) {
 		print STDERR "Checking for copy-tree ... ";
-		# use
 		my @diff = grep(/^Index: /,(safe_qx(qw(svn diff),
 						"-r$lcr:$svn_rev")));
 		if (@diff) {
@@ -389,7 +394,6 @@ sub assert_svn_wc_clean {
 		print STDERR $_ foreach @status;
 		croak;
 	}
-	assert_tree($treeish);
 }
 
 sub assert_tree {
@@ -416,7 +420,7 @@ sub assert_tree {
 		unlink $tmpindex or croak $!;
 	}
 	$ENV{GIT_INDEX_FILE} = $tmpindex;
-	git_addremove();
+	index_changes(1);
 	chomp(my $tree = `git-write-tree`);
 	if ($old_index) {
 		$ENV{GIT_INDEX_FILE} = $old_index;
@@ -426,6 +430,7 @@ sub assert_tree {
 	if ($tree ne $expected) {
 		croak "Tree mismatch, Got: $tree, Expected: $expected\n";
 	}
+	unlink $tmpindex;
 }
 
 sub parse_diff_tree {
@@ -562,7 +567,8 @@ sub precommit_check {
 sub svn_checkout_tree {
 	my ($svn_rev, $treeish) = @_;
 	my $from = file_to_s("$REV_DIR/$svn_rev");
-	assert_svn_wc_clean($svn_rev,$from);
+	assert_svn_wc_clean($svn_rev);
+	assert_tree($from);
 	print "diff-tree $from $treeish\n";
 	my $pid = open my $diff_fh, '-|';
 	defined $pid or croak $!;
@@ -852,13 +858,75 @@ sub svn_info {
 
 sub sys { system(@_) == 0 or croak $? }
 
-sub git_addremove {
-	system( "git-diff-files --name-only -z ".
-				" | git-update-index --remove -z --stdin && ".
-		"git-ls-files -z --others ".
-			"'--exclude-from=$GIT_DIR/$GIT_SVN/info/exclude'".
-				" | git-update-index --add -z --stdin"
-		) == 0 or croak $?
+sub eol_cp {
+	my ($from, $to) = @_;
+	my $es = safe_qx(qw/svn propget svn:eol-style/, $to);
+	open my $rfd, '<', $from or croak $!;
+	binmode $rfd or croak $!;
+	open my $wfd, '>', $to or croak $!;
+	binmode $wfd or croak $!;
+
+	my $eol = $EOL{$es} or undef;
+	if ($eol) {
+		print  "$eol: $from => $to\n";
+	}
+	my $buf;
+	while (1) {
+		my ($r, $w, $t);
+		defined($r = sysread($rfd, $buf, 4096)) or croak $!;
+		return unless $r;
+		$buf =~ s/(?:\015|\012|\015\012)/$eol/gs if $eol;
+		for ($w = 0; $w < $r; $w += $t) {
+			$t = syswrite($wfd, $buf, $r - $w, $w) or croak $!;
+		}
+	}
+}
+
+sub do_update_index {
+	my ($z_cmd, $cmd, $no_text_base) = @_;
+
+	my $z = open my $p, '-|';
+	defined $z or croak $!;
+	unless ($z) { exec @$z_cmd or croak $! }
+
+	my $pid = open my $ui, '|-';
+	defined $pid or croak $!;
+	unless ($pid) {
+		exec('git-update-index',"--$cmd",'-z','--stdin') or croak $!;
+	}
+	local $/ = "\0";
+	while (my $x = <$p>) {
+		chomp $x;
+		if (!$no_text_base && lstat $x && ! -l _ &&
+				safe_qx(qw/svn propget svn:keywords/,$x)) {
+			my $mode = -x _ ? 0755 : 0644;
+			my ($v,$d,$f) = File::Spec->splitpath($x);
+			my $tb = File::Spec->catfile($d, '.svn', 'tmp',
+						'text-base',"$f.svn-base");
+			$tb =~ s#^/##;
+			unless (-f $tb) {
+				$tb = File::Spec->catfile($d, '.svn',
+						'text-base',"$f.svn-base");
+				$tb =~ s#^/##;
+			}
+			unlink $x or croak $!;
+			eol_cp($tb, $x);
+			chmod(($mode &~ umask), $x) or croak $!;
+		}
+		print $ui $x,"\0";
+	}
+	close $ui or croak $!;
+}
+
+sub index_changes {
+	my $no_text_base = shift;
+	do_update_index([qw/git-diff-files --name-only -z/],
+			'remove',
+			$no_text_base);
+	do_update_index([qw/git-ls-files -z --others/,
+			      "--exclude-from=$GIT_DIR/$GIT_SVN/info/exclude"],
+			'add',
+			$no_text_base);
 }
 
 sub s_to_file {
@@ -936,7 +1004,7 @@ sub git_commit {
 	defined $pid or croak $!;
 	if ($pid == 0) {
 		$ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX;
-		git_addremove();
+		index_changes();
 		chomp(my $tree = `git-write-tree`);
 		croak if $?;
 		if (exists $tree_map{$tree}) {

contrib/git-svn/t/lib-git-svn.sh

@@ -0,0 +1,39 @@
+PATH=$PWD/../:$PATH
+if test -d ../../../t
+then
+    cd ../../../t
+else
+    echo "Must be run in contrib/git-svn/t" >&2
+    exit 1
+fi
+
+. ./test-lib.sh
+
+GIT_DIR=$PWD/.git
+GIT_SVN_DIR=$GIT_DIR/git-svn
+SVN_TREE=$GIT_SVN_DIR/tree
+
+svnadmin >/dev/null 2>&1
+if test $? != 1
+then
+    test_expect_success 'skipping contrib/git-svn test' :
+    test_done
+    exit
+fi
+
+svn >/dev/null 2>&1
+if test $? != 1
+then
+    test_expect_success 'skipping contrib/git-svn test' :
+    test_done
+    exit
+fi
+
+svnrepo=$PWD/svnrepo
+
+set -e
+
+svnadmin create $svnrepo
+svnrepo="file://$svnrepo/test-git-svn"
+
+

contrib/git-svn/t/t0000-contrib-git-svn.sh

@@ -3,48 +3,10 @@
 # Copyright (c) 2006 Eric Wong
 #
 
-
-PATH=$PWD/../:$PATH
 test_description='git-svn tests'
-if test -d ../../../t
-then
-    cd ../../../t
-else
-    echo "Must be run in contrib/git-svn/t" >&2
-    exit 1
-fi
-
-. ./test-lib.sh
-
-GIT_DIR=$PWD/.git
-GIT_SVN_DIR=$GIT_DIR/git-svn
-SVN_TREE=$GIT_SVN_DIR/tree
-
-svnadmin >/dev/null 2>&1
-if test $? != 1
-then
-    test_expect_success 'skipping contrib/git-svn test' :
-    test_done
-    exit
-fi
-
-svn >/dev/null 2>&1
-if test $? != 1
-then
-    test_expect_success 'skipping contrib/git-svn test' :
-    test_done
-    exit
-fi
-
-svnrepo=$PWD/svnrepo
-
-set -e
-
-svnadmin create $svnrepo
-svnrepo="file://$svnrepo/test-git-svn"
+. ./lib-git-svn.sh
 
 mkdir import
-
 cd import
 
 echo foo > foo
@@ -55,10 +17,9 @@ mkdir -p bar
 echo 'zzz' > bar/zzz
 echo '#!/bin/sh' > exec.sh
 chmod +x exec.sh
-svn import -m 'import for git-svn' . $svnrepo >/dev/null
+svn import -m 'import for git-svn' . "$svnrepo" >/dev/null
 
 cd ..
-
 rm -rf import
 
 test_expect_success \

contrib/git-svn/t/t0001-contrib-git-svn-props.sh

@@ -0,0 +1,125 @@
+#!/bin/sh
+#
+# Copyright (c) 2006 Eric Wong
+#
+
+test_description='git-svn property tests'
+. ./lib-git-svn.sh
+
+mkdir import
+
+a_crlf=
+a_lf=
+a_cr=
+a_ne_crlf=
+a_ne_lf=
+a_ne_cr=
+a_empty=
+a_empty_lf=
+a_empty_cr=
+a_empty_crlf=
+
+cd import
+	cat >> kw.c <<''
+/* Make it look like somebody copied a file from CVS into SVN: */
+/* $Id: kw.c,v 1.1.1.1 1994/03/06 00:00:00 eric Exp $ */
+
+	printf "Hello\r\nWorld\r\n" > crlf
+	a_crlf=`git-hash-object -w crlf`
+	printf "Hello\rWorld\r" > cr
+	a_cr=`git-hash-object -w cr`
+	printf "Hello\nWorld\n" > lf
+	a_lf=`git-hash-object -w lf`
+
+	printf "Hello\r\nWorld" > ne_crlf
+	a_ne_crlf=`git-hash-object -w ne_crlf`
+	printf "Hello\nWorld" > ne_lf
+	a_ne_lf=`git-hash-object -w ne_lf`
+	printf "Hello\rWorld" > ne_cr
+	a_ne_cr=`git-hash-object -w ne_cr`
+
+	touch empty
+	a_empty=`git-hash-object -w empty`
+	printf "\n" > empty_lf
+	a_empty_lf=`git-hash-object -w empty_lf`
+	printf "\r" > empty_cr
+	a_empty_cr=`git-hash-object -w empty_cr`
+	printf "\r\n" > empty_crlf
+	a_empty_crlf=`git-hash-object -w empty_crlf`
+
+	svn import -m 'import for git-svn' . "$svnrepo" >/dev/null
+cd ..
+
+rm -rf import
+svn co "$svnrepo" test_wc
+
+cd test_wc
+	echo 'Greetings' >> kw.c
+	svn commit -m 'Not yet an $Id$'
+	svn up
+
+	echo 'Hello world' >> kw.c
+	svn commit -m 'Modified file, but still not yet an $Id$'
+	svn up
+
+	svn propset svn:keywords Id kw.c
+	svn commit -m 'Propset $Id$'
+	svn up
+cd ..
+
+git-svn init "$svnrepo"
+git-svn fetch
+
+git checkout -b mybranch remotes/git-svn
+echo 'Hi again' >> kw.c
+name='test svn:keywords ignoring'
+
+git commit -a -m "$name"
+git-svn commit remotes/git-svn..mybranch
+git pull . remotes/git-svn
+
+expect='/* $Id$ */'
+got="`sed -ne 2p kw.c`"
+test_expect_success 'raw $Id$ found in kw.c' "test '$expect' = '$got'"
+
+cd test_wc
+	svn propset svn:eol-style CR empty
+	svn propset svn:eol-style CR crlf
+	svn propset svn:eol-style CR ne_crlf
+	svn commit -m 'propset CR on crlf files'
+	svn up
+cd ..
+
+git-svn fetch
+git pull . remotes/git-svn
+
+svn co "$svnrepo" new_wc
+for i in crlf ne_crlf lf ne_lf cr ne_cr empty_cr empty_lf empty empty_crlf
+do
+	test_expect_success "Comparing $i" "cmp $i new_wc/$i"
+done
+
+
+cd test_wc
+	printf '$Id$\rHello\rWorld\r' > cr
+	printf '$Id$\rHello\rWorld' > ne_cr
+	a_cr=`printf '$Id$\r\nHello\r\nWorld\r\n' | git-hash-object --stdin`
+	a_ne_cr=`printf '$Id$\r\nHello\r\nWorld' | git-hash-object --stdin`
+	svn propset svn:eol-style CRLF cr
+	svn propset svn:eol-style CRLF ne_cr
+	svn propset svn:keywords Id cr
+	svn propset svn:keywords Id ne_cr
+	svn commit -m 'propset CRLF on cr files'
+	svn up
+cd ..
+
+git-svn fetch
+git pull . remotes/git-svn
+
+b_cr="`git-hash-object cr`"
+b_ne_cr="`git-hash-object ne_cr`"
+
+test_expect_success 'CRLF + $Id$' "test '$a_cr' = '$b_cr'"
+test_expect_success 'CRLF + $Id$ (no newline)' "test '$a_ne_cr' = '$b_ne_cr'"
+
+test_done

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
+
+

diff.c

@@ -237,7 +237,7 @@ static char *pprint_rename(const char *a, const char *b)
 		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);
+		name = xmalloc(pfx_length + a_midlen + b_midlen + sfx_length + 7);
 		sprintf(name, "%.*s{%.*s => %.*s}%s",
 			pfx_length, a,
 			a_midlen, a + pfx_length,
@@ -299,6 +299,7 @@ static void diffstat_consume(void *priv, char *line, unsigned long len)
 
 static const char pluses[] = "++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++";
 static const char minuses[]= "----------------------------------------------------------------------";
+const char mime_boundary_leader[] = "------------";
 
 static void show_stats(struct diffstat_t* data)
 {
@@ -397,6 +398,46 @@ 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, NULL, 10);
+		else
+			die("invalid diff");
+	}
+}
+
 static unsigned char *deflate_it(char *data,
 				 unsigned long size,
 				 unsigned long *result_size)
@@ -624,6 +665,41 @@ 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);
@@ -1180,6 +1256,25 @@ 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));
@@ -1205,9 +1300,18 @@ 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;
 
+	/*
+	 * These combinations do not make sense.
+	 */
+	if (options->output_format == DIFF_FORMAT_RAW)
+		options->with_raw = 0;
+	if (options->output_format == DIFF_FORMAT_DIFFSTAT)
+		options->with_stat  = 0;
+
 	if (options->detect_rename && options->rename_limit < 0)
 		options->rename_limit = diff_rename_limit_default;
 	if (options->setup & DIFF_SETUP_USE_CACHE) {
@@ -1288,6 +1392,8 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 	}
 	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")) {
@@ -1610,6 +1716,19 @@ 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;
@@ -1740,6 +1859,9 @@ 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;
@@ -1867,7 +1989,13 @@ void diff_flush(struct diff_options *options)
 		show_stats(diffstat);
 		free(diffstat);
 		diffstat = NULL;
-		putchar(options->line_termination);
+		if (options->summary)
+			for (i = 0; i < q->nr; i++)
+				diff_summary(q->queue[i]);
+		if (options->stat_sep)
+			fputs(options->stat_sep, stdout);
+		else
+			putchar(options->line_termination);
 	}
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
@@ -1880,7 +2008,7 @@ void diff_flush(struct diff_options *options)
 	}
 
 	for (i = 0; i < q->nr; i++) {
-		if (options->summary)
+		if (diffstat && options->summary)
 			diff_summary(q->queue[i]);
 		diff_free_filepair(q->queue[i]);
 	}

diff.h

@@ -44,6 +44,7 @@ struct diff_options {
 	int rename_limit;
 	int setup;
 	int abbrev;
+	const char *stat_sep;
 
 	int nr_paths;
 	const char **paths;
@@ -52,6 +53,8 @@ struct diff_options {
 	add_remove_fn_t add_remove;
 };
 
+extern const char mime_boundary_leader[];
+
 extern void diff_tree_setup_paths(const char **paths, struct diff_options *);
 extern void diff_tree_release_paths(struct diff_options *);
 extern int diff_tree(struct tree_desc *t1, struct tree_desc *t2,
@@ -153,6 +156,7 @@ 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*);
 

dir.c

@@ -0,0 +1,401 @@
+/*
+ * This handles recursive filename detection with exclude
+ * files, index knowledge etc..
+ *
+ * Copyright (C) Linus Torvalds, 2005-2006
+ *		 Junio Hamano, 2005-2006
+ */
+#include <dirent.h>
+#include <fnmatch.h>
+
+#include "cache.h"
+#include "dir.h"
+
+int common_prefix(const char **pathspec)
+{
+	const char *path, *slash, *next;
+	int prefix;
+
+	if (!pathspec)
+		return 0;
+
+	path = *pathspec;
+	slash = strrchr(path, '/');
+	if (!slash)
+		return 0;
+
+	prefix = slash - path + 1;
+	while ((next = *++pathspec) != NULL) {
+		int len = strlen(next);
+		if (len >= prefix && !memcmp(path, next, len))
+			continue;
+		for (;;) {
+			if (!len)
+				return 0;
+			if (next[--len] != '/')
+				continue;
+			if (memcmp(path, next, len+1))
+				continue;
+			prefix = len + 1;
+			break;
+		}
+	}
+	return prefix;
+}
+
+static int match_one(const char *match, const char *name, int namelen)
+{
+	int matchlen;
+
+	/* If the match was just the prefix, we matched */
+	matchlen = strlen(match);
+	if (!matchlen)
+		return 1;
+
+	/*
+	 * If we don't match the matchstring exactly,
+	 * we need to match by fnmatch
+	 */
+	if (strncmp(match, name, matchlen))
+		return !fnmatch(match, name, 0);
+
+	/*
+	 * If we did match the string exactly, we still
+	 * need to make sure that it happened on a path
+	 * component boundary (ie either the last character
+	 * of the match was '/', or the next character of
+	 * the name was '/' or the terminating NUL.
+	 */
+	return	match[matchlen-1] == '/' ||
+		name[matchlen] == '/' ||
+		!name[matchlen];
+}
+
+int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen)
+{
+	int retval;
+	const char *match;
+
+	name += prefix;
+	namelen -= prefix;
+
+	for (retval = 0; (match = *pathspec++) != NULL; seen++) {
+		if (retval & *seen)
+			continue;
+		match += prefix;
+		if (match_one(match, name, namelen)) {
+			retval = 1;
+			*seen = 1;
+		}
+	}
+	return retval;
+}
+
+void add_exclude(const char *string, const char *base,
+		 int baselen, struct exclude_list *which)
+{
+	struct exclude *x = xmalloc(sizeof (*x));
+
+	x->pattern = string;
+	x->base = base;
+	x->baselen = baselen;
+	if (which->nr == which->alloc) {
+		which->alloc = alloc_nr(which->alloc);
+		which->excludes = realloc(which->excludes,
+					  which->alloc * sizeof(x));
+	}
+	which->excludes[which->nr++] = x;
+}
+
+static int add_excludes_from_file_1(const char *fname,
+				    const char *base,
+				    int baselen,
+				    struct exclude_list *which)
+{
+	int fd, i;
+	long size;
+	char *buf, *entry;
+
+	fd = open(fname, O_RDONLY);
+	if (fd < 0)
+		goto err;
+	size = lseek(fd, 0, SEEK_END);
+	if (size < 0)
+		goto err;
+	lseek(fd, 0, SEEK_SET);
+	if (size == 0) {
+		close(fd);
+		return 0;
+	}
+	buf = xmalloc(size+1);
+	if (read(fd, buf, size) != size)
+		goto err;
+	close(fd);
+
+	buf[size++] = '\n';
+	entry = buf;
+	for (i = 0; i < size; i++) {
+		if (buf[i] == '\n') {
+			if (entry != buf + i && entry[0] != '#') {
+				buf[i - (i && buf[i-1] == '\r')] = 0;
+				add_exclude(entry, base, baselen, which);
+			}
+			entry = buf + i + 1;
+		}
+	}
+	return 0;
+
+ err:
+	if (0 <= fd)
+		close(fd);
+	return -1;
+}
+
+void add_excludes_from_file(struct dir_struct *dir, const char *fname)
+{
+	if (add_excludes_from_file_1(fname, "", 0,
+				     &dir->exclude_list[EXC_FILE]) < 0)
+		die("cannot use %s as an exclude file", fname);
+}
+
+static int push_exclude_per_directory(struct dir_struct *dir, const char *base, int baselen)
+{
+	char exclude_file[PATH_MAX];
+	struct exclude_list *el = &dir->exclude_list[EXC_DIRS];
+	int current_nr = el->nr;
+
+	if (dir->exclude_per_dir) {
+		memcpy(exclude_file, base, baselen);
+		strcpy(exclude_file + baselen, dir->exclude_per_dir);
+		add_excludes_from_file_1(exclude_file, base, baselen, el);
+	}
+	return current_nr;
+}
+
+static void pop_exclude_per_directory(struct dir_struct *dir, int stk)
+{
+	struct exclude_list *el = &dir->exclude_list[EXC_DIRS];
+
+	while (stk < el->nr)
+		free(el->excludes[--el->nr]);
+}
+
+/* Scan the list and let the last match determines the fate.
+ * Return 1 for exclude, 0 for include and -1 for undecided.
+ */
+static int excluded_1(const char *pathname,
+		      int pathlen,
+		      struct exclude_list *el)
+{
+	int i;
+
+	if (el->nr) {
+		for (i = el->nr - 1; 0 <= i; i--) {
+			struct exclude *x = el->excludes[i];
+			const char *exclude = x->pattern;
+			int to_exclude = 1;
+
+			if (*exclude == '!') {
+				to_exclude = 0;
+				exclude++;
+			}
+
+			if (!strchr(exclude, '/')) {
+				/* match basename */
+				const char *basename = strrchr(pathname, '/');
+				basename = (basename) ? basename+1 : pathname;
+				if (fnmatch(exclude, basename, 0) == 0)
+					return to_exclude;
+			}
+			else {
+				/* match with FNM_PATHNAME:
+				 * exclude has base (baselen long) implicitly
+				 * in front of it.
+				 */
+				int baselen = x->baselen;
+				if (*exclude == '/')
+					exclude++;
+
+				if (pathlen < baselen ||
+				    (baselen && pathname[baselen-1] != '/') ||
+				    strncmp(pathname, x->base, baselen))
+				    continue;
+
+				if (fnmatch(exclude, pathname+baselen,
+					    FNM_PATHNAME) == 0)
+					return to_exclude;
+			}
+		}
+	}
+	return -1; /* undecided */
+}
+
+int excluded(struct dir_struct *dir, const char *pathname)
+{
+	int pathlen = strlen(pathname);
+	int st;
+
+	for (st = EXC_CMDL; st <= EXC_FILE; st++) {
+		switch (excluded_1(pathname, pathlen, &dir->exclude_list[st])) {
+		case 0:
+			return 0;
+		case 1:
+			return 1;
+		}
+	}
+	return 0;
+}
+
+static void add_name(struct dir_struct *dir, const char *pathname, int len)
+{
+	struct dir_entry *ent;
+
+	if (cache_name_pos(pathname, len) >= 0)
+		return;
+
+	if (dir->nr == dir->alloc) {
+		int alloc = alloc_nr(dir->alloc);
+		dir->alloc = alloc;
+		dir->entries = xrealloc(dir->entries, alloc*sizeof(ent));
+	}
+	ent = xmalloc(sizeof(*ent) + len + 1);
+	ent->len = len;
+	memcpy(ent->name, pathname, len);
+	ent->name[len] = 0;
+	dir->entries[dir->nr++] = ent;
+}
+
+static int dir_exists(const char *dirname, int len)
+{
+	int pos = cache_name_pos(dirname, len);
+	if (pos >= 0)
+		return 1;
+	pos = -pos-1;
+	if (pos >= active_nr) /* can't */
+		return 0;
+	return !strncmp(active_cache[pos]->name, dirname, len);
+}
+
+/*
+ * Read a directory tree. We currently ignore anything but
+ * directories, regular files and symlinks. That's because git
+ * doesn't handle them at all yet. Maybe that will change some
+ * day.
+ *
+ * Also, we ignore the name ".git" (even if it is not a directory).
+ * That likely will not change.
+ */
+static int read_directory_recursive(struct dir_struct *dir, const char *path, const char *base, int baselen)
+{
+	DIR *fdir = opendir(path);
+	int contents = 0;
+
+	if (fdir) {
+		int exclude_stk;
+		struct dirent *de;
+		char fullname[MAXPATHLEN + 1];
+		memcpy(fullname, base, baselen);
+
+		exclude_stk = push_exclude_per_directory(dir, base, baselen);
+
+		while ((de = readdir(fdir)) != NULL) {
+			int len;
+
+			if ((de->d_name[0] == '.') &&
+			    (de->d_name[1] == 0 ||
+			     !strcmp(de->d_name + 1, ".") ||
+			     !strcmp(de->d_name + 1, "git")))
+				continue;
+			len = strlen(de->d_name);
+			memcpy(fullname + baselen, de->d_name, len+1);
+			if (excluded(dir, fullname) != dir->show_ignored) {
+				if (!dir->show_ignored || DTYPE(de) != DT_DIR) {
+					continue;
+				}
+			}
+
+			switch (DTYPE(de)) {
+			struct stat st;
+			int subdir, rewind_base;
+			default:
+				continue;
+			case DT_UNKNOWN:
+				if (lstat(fullname, &st))
+					continue;
+				if (S_ISREG(st.st_mode) || S_ISLNK(st.st_mode))
+					break;
+				if (!S_ISDIR(st.st_mode))
+					continue;
+				/* fallthrough */
+			case DT_DIR:
+				memcpy(fullname + baselen + len, "/", 2);
+				len++;
+				rewind_base = dir->nr;
+				subdir = read_directory_recursive(dir, fullname, fullname,
+				                        baselen + len);
+				if (dir->show_other_directories &&
+				    (subdir || !dir->hide_empty_directories) &&
+				    !dir_exists(fullname, baselen + len)) {
+					// Rewind the read subdirectory
+					while (dir->nr > rewind_base)
+						free(dir->entries[--dir->nr]);
+					break;
+				}
+				contents += subdir;
+				continue;
+			case DT_REG:
+			case DT_LNK:
+				break;
+			}
+			add_name(dir, fullname, baselen + len);
+			contents++;
+		}
+		closedir(fdir);
+
+		pop_exclude_per_directory(dir, exclude_stk);
+	}
+
+	return contents;
+}
+
+static int cmp_name(const void *p1, const void *p2)
+{
+	const struct dir_entry *e1 = *(const struct dir_entry **)p1;
+	const struct dir_entry *e2 = *(const struct dir_entry **)p2;
+
+	return cache_name_compare(e1->name, e1->len,
+				  e2->name, e2->len);
+}
+
+int read_directory(struct dir_struct *dir, const char *path, const char *base, int baselen)
+{
+	/*
+	 * Make sure to do the per-directory exclude for all the
+	 * directories leading up to our base.
+	 */
+	if (baselen) {
+		if (dir->exclude_per_dir) {
+			char *p, *pp = xmalloc(baselen+1);
+			memcpy(pp, base, baselen+1);
+			p = pp;
+			while (1) {
+				char save = *p;
+				*p = 0;
+				push_exclude_per_directory(dir, pp, p-pp);
+				*p++ = save;
+				if (!save)
+					break;
+				p = strchr(p, '/');
+				if (p)
+					p++;
+				else
+					p = pp + baselen;
+			}
+			free(pp);
+		}
+	}
+
+	read_directory_recursive(dir, path, base, baselen);
+	qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
+	return dir->nr;
+}

dir.h

@@ -0,0 +1,51 @@
+#ifndef DIR_H
+#define DIR_H
+
+/*
+ * We maintain three exclude pattern lists:
+ * EXC_CMDL lists patterns explicitly given on the command line.
+ * EXC_DIRS lists patterns obtained from per-directory ignore files.
+ * EXC_FILE lists patterns from fallback ignore files.
+ */
+#define EXC_CMDL 0
+#define EXC_DIRS 1
+#define EXC_FILE 2
+
+
+struct dir_entry {
+	int len;
+	char name[FLEX_ARRAY]; /* more */
+};
+
+struct exclude_list {
+	int nr;
+	int alloc;
+	struct exclude {
+		const char *pattern;
+		const char *base;
+		int baselen;
+	} **excludes;
+};
+
+struct dir_struct {
+	int nr, alloc;
+	unsigned int show_ignored:1,
+		     show_other_directories:1,
+		     hide_empty_directories:1;
+	struct dir_entry **entries;
+
+	/* Exclude info */
+	const char *exclude_per_dir;
+	struct exclude_list exclude_list[3];
+};
+
+extern int common_prefix(const char **pathspec);
+extern int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen);
+
+extern int read_directory(struct dir_struct *, const char *path, const char *base, int baselen);
+extern int excluded(struct dir_struct *, const char *);
+extern void add_excludes_from_file(struct dir_struct *, const char *fname);
+extern void add_exclude(const char *string, const char *base,
+			int baselen, struct exclude_list *which);
+
+#endif

fetch-pack.c

@@ -262,22 +262,58 @@ static void mark_recent_complete_commits(unsigned long cutoff)
 
 static void filter_refs(struct ref **refs, int nr_match, char **match)
 {
-	struct ref *prev, *current, *next;
+	struct ref **return_refs;
+	struct ref *newlist = NULL;
+	struct ref **newtail = &newlist;
+	struct ref *ref, *next;
+	struct ref *fastarray[32];
 
-	for (prev = NULL, current = *refs; current; current = next) {
-		next = current->next;
-		if ((!memcmp(current->name, "refs/", 5) &&
-		     check_ref_format(current->name + 5)) ||
-		    (!fetch_all &&
-		     !path_match(current->name, nr_match, match))) {
-			if (prev == NULL)
-				*refs = next;
-			else
-				prev->next = next;
-			free(current);
-		} else
-			prev = current;
+	if (nr_match && !fetch_all) {
+		if (ARRAY_SIZE(fastarray) < nr_match)
+			return_refs = xcalloc(nr_match, sizeof(struct ref *));
+		else {
+			return_refs = fastarray;
+			memset(return_refs, 0, sizeof(struct ref *) * nr_match);
+		}
 	}
+	else
+		return_refs = NULL;
+
+	for (ref = *refs; ref; ref = next) {
+		next = ref->next;
+		if (!memcmp(ref->name, "refs/", 5) &&
+		    check_ref_format(ref->name + 5))
+			; /* trash */
+		else if (fetch_all) {
+			*newtail = ref;
+			ref->next = NULL;
+			newtail = &ref->next;
+			continue;
+		}
+		else {
+			int order = path_match(ref->name, nr_match, match);
+			if (order) {
+				return_refs[order-1] = ref;
+				continue; /* we will link it later */
+			}
+		}
+		free(ref);
+	}
+
+	if (!fetch_all) {
+		int i;
+		for (i = 0; i < nr_match; i++) {
+			ref = return_refs[i];
+			if (ref) {
+				*newtail = ref;
+				ref->next = NULL;
+				newtail = &ref->next;
+			}
+		}
+		if (return_refs != fastarray)
+			free(return_refs);
+	}
+	*refs = newlist;
 }
 
 static int everything_local(struct ref **refs, int nr_match, char **match)

fetch.c

@@ -10,8 +10,6 @@
 const char *write_ref = NULL;
 const char *write_ref_log_details = NULL;
 
-const unsigned char *current_ref = NULL;
-
 int get_tree = 0;
 int get_history = 0;
 int get_all = 0;
@@ -213,16 +211,15 @@ int pull(char *target)
 	save_commit_buffer = 0;
 	track_object_refs = 0;
 	if (write_ref) {
-		lock = lock_ref_sha1(write_ref, current_ref, 1);
+		lock = lock_ref_sha1(write_ref, NULL, 0);
 		if (!lock) {
 			error("Can't lock ref %s", write_ref);
 			return -1;
 		}
 	}
 
-	if (!get_recover) {
+	if (!get_recover)
 		for_each_ref(mark_complete);
-	}
 
 	if (interpret_target(target, sha1)) {
 		error("Could not interpret %s as something to pull", target);

fetch.h

@@ -28,9 +28,6 @@ extern const char *write_ref;
 /* If set additional text will appear in the ref log. */
 extern const char *write_ref_log_details;
 
-/* If set, the hash that the current value of write_ref must be. */
-extern const unsigned char *current_ref;
-
 /* Set to fetch the target tree. */
 extern int get_tree;
 

generate-cmdlist.sh

@@ -37,7 +37,6 @@ show-branch
 status
 tag
 verify-tag
-whatchanged
 EOF
 while read cmd
 do

git-add.sh

@@ -1,56 +0,0 @@
-#!/bin/sh
-
-USAGE='[-n] [-v] <file>...'
-SUBDIRECTORY_OK='Yes'
-. git-sh-setup
-
-show_only=
-verbose=
-while : ; do
-  case "$1" in
-    -n)
-	show_only=true
-	;;
-    -v)
-	verbose=--verbose
-	;;
-    --)
-	shift
-	break
-	;;
-    -*)
-	usage
-	;;
-    *)
-	break
-	;;
-  esac
-  shift
-done
-
-# Check misspelled pathspec
-case "$#" in
-0)	;;
-*)
-	git-ls-files --error-unmatch --others --cached -- "$@" >/dev/null || {
-		echo >&2 "Maybe you misspelled it?"
-		exit 1
-	}
-	;;
-esac
-
-if test -f "$GIT_DIR/info/exclude"
-then
-	git-ls-files -z \
-	--exclude-from="$GIT_DIR/info/exclude" \
-	--others --exclude-per-directory=.gitignore -- "$@"
-else
-	git-ls-files -z \
-	--others --exclude-per-directory=.gitignore -- "$@"
-fi |
-case "$show_only" in
-true)
-	xargs -0 echo ;;
-*)
-	git-update-index --add $verbose -z --stdin ;;
-esac

git-am.sh

@@ -59,46 +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" &&

git-clone.sh

@@ -199,7 +199,7 @@ dir="$2"
 [ -e "$dir" ] && echo "$dir already exists." && usage
 mkdir -p "$dir" &&
 D=$(cd "$dir" && pwd) &&
-trap 'err=$?; cd ..; rm -r "$D"; exit $err' exit
+trap 'err=$?; cd ..; rm -r "$D"; exit $err' 0
 case "$bare" in
 yes) GIT_DIR="$D" ;;
 *) GIT_DIR="$D/.git" ;;
@@ -407,5 +407,5 @@ Pull: refs/heads/$head_points_at:$origin_track" &&
 fi
 rm -f "$GIT_DIR/CLONE_HEAD" "$GIT_DIR/REMOTE_HEAD"
 
-trap - exit
+trap - 0
 

git-commit.sh

@@ -3,7 +3,7 @@
 # Copyright (c) 2005 Linus Torvalds
 # Copyright (c) 2006 Junio C Hamano
 
-USAGE='[-a] [-s] [-v] [--no-verify] [-m <message> | -F <logfile> | (-C|-c) <commit>) [--amend] [-e] [--author <author>] [[-i | -o] <path>...]'
+USAGE='[-a] [-s] [-v] [--no-verify] [-m <message> | -F <logfile> | (-C|-c) <commit>] [-u] [--amend] [-e] [--author <author>] [[-i | -o] <path>...]'
 SUBDIRECTORY_OK=Yes
 . git-sh-setup
 
@@ -134,13 +134,17 @@ run_status () {
 	report "Changed but not updated" \
 	    "use git-update-index to mark for commit"
 
+        option=""
+        if test -z "$untracked_files"; then
+            option="--directory --no-empty-directory"
+        fi
 	if test -f "$GIT_DIR/info/exclude"
 	then
-	    git-ls-files -z --others --directory \
+	    git-ls-files -z --others $option \
 		--exclude-from="$GIT_DIR/info/exclude" \
 		--exclude-per-directory=.gitignore
 	else
-	    git-ls-files -z --others --directory \
+	    git-ls-files -z --others $option \
 		--exclude-per-directory=.gitignore
 	fi |
 	perl -e '$/ = "\0";
@@ -203,6 +207,7 @@ verbose=
 signoff=
 force_author=
 only_include_assumed=
+untracked_files=
 while case "$#" in 0) break;; esac
 do
   case "$1" in
@@ -340,6 +345,12 @@ do
       verbose=t
       shift
       ;;
+  -u|--u|--un|--unt|--untr|--untra|--untrac|--untrack|--untracke|--untracked|\
+  --untracked-|--untracked-f|--untracked-fi|--untracked-fil|--untracked-file|\
+  --untracked-files)
+      untracked_files=t
+      shift
+      ;;
   --)
       shift
       break

git-cvsimport.perl

@@ -23,13 +23,13 @@ use File::Basename qw(basename dirname);
 use Time::Local;
 use IO::Socket;
 use IO::Pipe;
-use POSIX qw(strftime dup2);
+use POSIX qw(strftime dup2 :errno_h);
 use IPC::Open2;
 
 $SIG{'PIPE'}="IGNORE";
 $ENV{'TZ'}="UTC";
 
-our($opt_h,$opt_o,$opt_v,$opt_k,$opt_u,$opt_d,$opt_p,$opt_C,$opt_z,$opt_i,$opt_P, $opt_s,$opt_m,$opt_M,$opt_A,$opt_S);
+our($opt_h,$opt_o,$opt_v,$opt_k,$opt_u,$opt_d,$opt_p,$opt_C,$opt_z,$opt_i,$opt_P, $opt_s,$opt_m,$opt_M,$opt_A,$opt_S,$opt_L);
 my (%conv_author_name, %conv_author_email);
 
 sub usage() {
@@ -85,7 +85,7 @@ sub write_author_info($) {
 	close ($f);
 }
 
-getopts("hivmkuo:d:p:C:z:s:M:P:A:S:") or usage();
+getopts("hivmkuo:d:p:C:z:s:M:P:A:S:L:") or usage();
 usage if $opt_h;
 
 @ARGV <= 1 or usage();
@@ -315,15 +315,7 @@ sub _line {
 			chomp $cnt;
 			die "Duh: Filesize $cnt" if $cnt !~ /^\d+$/;
 			$line="";
-			$res=0;
-			while($cnt) {
-				my $buf;
-				my $num = $self->{'socketi'}->read($buf,$cnt);
-				die "Server: Filesize $cnt: $num: $!\n" if not defined $num or $num<=0;
-				print $fh $buf;
-				$res += $num;
-				$cnt -= $num;
-			}
+			$res = $self->_fetchfile($fh, $cnt);
 		} elsif($line =~ s/^ //) {
 			print $fh $line;
 			$res += length($line);
@@ -335,14 +327,7 @@ sub _line {
 			chomp $cnt;
 			die "Duh: Mbinary $cnt" if $cnt !~ /^\d+$/ or $cnt<1;
 			$line="";
-			while($cnt) {
-				my $buf;
-				my $num = $self->{'socketi'}->read($buf,$cnt);
-				die "S: Mbinary $cnt: $num: $!\n" if not defined $num or $num<=0;
-				print $fh $buf;
-				$res += $num;
-				$cnt -= $num;
-			}
+			$res += $self->_fetchfile($fh, $cnt);
 		} else {
 			chomp $line;
 			if($line eq "ok") {
@@ -350,7 +335,7 @@ 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;
@@ -384,6 +369,23 @@ sub file {
 
 	return ($name, $res);
 }
+sub _fetchfile {
+	my ($self, $fh, $cnt) = @_;
+	my $res = 0;
+	my $bufsize = 1024 * 1024;
+	while($cnt) {
+	    if ($bufsize > $cnt) {
+		$bufsize = $cnt;
+	    }
+	    my $buf;
+	    my $num = $self->{'socketi'}->read($buf,$bufsize);
+	    die "Server: Filesize $cnt: $num: $!\n" if not defined $num or $num<=0;
+	    print $fh $buf;
+	    $res += $num;
+	    $cnt -= $num;
+	}
+	return $res;
+}
 
 
 package main;
@@ -429,21 +431,24 @@ sub getwd() {
 	return $pwd;
 }
 
-
-sub get_headref($$) {
-    my $name    = shift;
-    my $git_dir = shift; 
-    my $sha;
-    
-    if (open(C,"$git_dir/refs/heads/$name")) {
-	chomp($sha = <C>);
-	close(C);
-	length($sha) == 40
-	    or die "Cannot get head id for $name ($sha): $!\n";
-    }
-    return $sha;
+sub is_sha1 {
+	my $s = shift;
+	return $s =~ /^[a-f0-9]{40}$/;
 }
 
+sub get_headref ($$) {
+    my $name    = shift;
+    my $git_dir = shift; 
+    
+    my $f = "$git_dir/refs/heads/$name";
+    if(open(my $fh, $f)) {
+	    chomp(my $r = <$fh>);
+	    is_sha1($r) or die "Cannot get head id for $name ($r): $!";
+	    return $r;
+    }
+    die "unable to open $f: $!" unless $! == POSIX::ENOENT;
+    return undef;
+}
 
 -d $git_tree
 	or mkdir($git_tree,0777)
@@ -561,98 +566,66 @@ unless($pid) {
 
 my $state = 0;
 
-my($patchset,$date,$author_name,$author_email,$branch,$ancestor,$tag,$logmsg);
-my(@old,@new,@skipped);
-my $commit = sub {
-	my $pid;
-	while(@old) {
-		my @o2;
-		if(@old > 55) {
-			@o2 = splice(@old,0,50);
-		} else {
-			@o2 = @old;
-			@old = ();
-		}
-		system("git-update-index","--force-remove","--",@o2);
-		die "Cannot remove files: $?\n" if $?;
-	}
-	while(@new) {
-		my @n2;
-		if(@new > 12) {
-			@n2 = splice(@new,0,10);
-		} else {
-			@n2 = @new;
-			@new = ();
-		}
-		system("git-update-index","--add",
-			(map { ('--cacheinfo', @$_) } @n2));
-		die "Cannot add files: $?\n" if $?;
-	}
+sub update_index (\@\@) {
+	my $old = shift;
+	my $new = shift;
+	open(my $fh, '|-', qw(git-update-index -z --index-info))
+		or die "unable to open git-update-index: $!";
+	print $fh
+		(map { "0 0000000000000000000000000000000000000000\t$_\0" }
+			@$old),
+		(map { '100' . sprintf('%o', $_->[0]) . " $_->[1]\t$_->[2]\0" }
+			@$new)
+		or die "unable to write to git-update-index: $!";
+	close $fh
+		or die "unable to write to git-update-index: $!";
+	$? and die "git-update-index reported error: $?";
+}
 
-	$pid = open(C,"-|");
-	die "Cannot fork: $!" unless defined $pid;
-	unless($pid) {
-		exec("git-write-tree");
-		die "Cannot exec git-write-tree: $!\n";
-	}
-	chomp(my $tree = <C>);
-	length($tree) == 40
-		or die "Cannot get tree id ($tree): $!\n";
-	close(C)
+sub write_tree () {
+	open(my $fh, '-|', qw(git-write-tree))
+		or die "unable to open git-write-tree: $!";
+	chomp(my $tree = <$fh>);
+	is_sha1($tree)
+		or die "Cannot get tree id ($tree): $!";
+	close($fh)
 		or die "Error running git-write-tree: $?\n";
 	print "Tree ID $tree\n" if $opt_v;
+	return $tree;
+}
 
-	my $parent = "";
-	if(open(C,"$git_dir/refs/heads/$last_branch")) {
-		chomp($parent = <C>);
-		close(C);
-		length($parent) == 40
-			or die "Cannot get parent id ($parent): $!\n";
-		print "Parent ID $parent\n" if $opt_v;
-	}
+my($patchset,$date,$author_name,$author_email,$branch,$ancestor,$tag,$logmsg);
+my(@old,@new,@skipped);
+sub commit {
+	update_index(@old, @new);
+	@old = @new = ();
+	my $tree = write_tree();
+	my $parent = get_headref($last_branch, $git_dir);
+	print "Parent ID " . ($parent ? $parent : "(empty)") . "\n" if $opt_v;
 
-	my $pr = IO::Pipe->new() or die "Cannot open pipe: $!\n";
-	my $pw = IO::Pipe->new() or die "Cannot open pipe: $!\n";
-	$pid = fork();
-	die "Fork: $!\n" unless defined $pid;
-	unless($pid) {
-		$pr->writer();
-		$pw->reader();
-		open(OUT,">&STDOUT");
-		dup2($pw->fileno(),0);
-		dup2($pr->fileno(),1);
-		$pr->close();
-		$pw->close();
+	my @commit_args;
+	push @commit_args, ("-p", $parent) if $parent;
 
-		my @par = ();
-		@par = ("-p",$parent) if $parent;
-
-		# loose detection of merges
-		# based on the commit msg
-		foreach my $rx (@mergerx) {
-			if ($logmsg =~ $rx) {
-				my $mparent = $1;
-				if ($mparent eq 'HEAD') { $mparent = $opt_o };
-				if ( -e "$git_dir/refs/heads/$mparent") {
-					$mparent = get_headref($mparent, $git_dir);
-					push @par, '-p', $mparent;
-					print OUT "Merge parent branch: $mparent\n" if $opt_v;
-				}
-			}
+	# loose detection of merges
+	# based on the commit msg
+	foreach my $rx (@mergerx) {
+		next unless $logmsg =~ $rx && $1;
+		my $mparent = $1 eq 'HEAD' ? $opt_o : $1;
+		if(my $sha1 = get_headref($mparent, $git_dir)) {
+			push @commit_args, '-p', $mparent;
+			print "Merge parent branch: $mparent\n" if $opt_v;
 		}
-
-		exec("env",
-			"GIT_AUTHOR_NAME=$author_name",
-			"GIT_AUTHOR_EMAIL=$author_email",
-			"GIT_AUTHOR_DATE=".strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date)),
-			"GIT_COMMITTER_NAME=$author_name",
-			"GIT_COMMITTER_EMAIL=$author_email",
-			"GIT_COMMITTER_DATE=".strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date)),
-			"git-commit-tree", $tree,@par);
-		die "Cannot exec git-commit-tree: $!\n";
 	}
-	$pw->writer();
-	$pr->reader();
+
+	my $commit_date = strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date));
+	$ENV{GIT_AUTHOR_NAME} = $author_name;
+	$ENV{GIT_AUTHOR_EMAIL} = $author_email;
+	$ENV{GIT_AUTHOR_DATE} = $commit_date;
+	$ENV{GIT_COMMITTER_NAME} = $author_name;
+	$ENV{GIT_COMMITTER_EMAIL} = $author_email;
+	$ENV{GIT_COMMITTER_DATE} = $commit_date;
+	my $pid = open2(my $commit_read, my $commit_write,
+		'git-commit-tree', $tree, @commit_args);
 
 	# compatibility with git2cvs
 	substr($logmsg,32767) = "" if length($logmsg) > 32767;
@@ -661,18 +634,17 @@ my $commit = sub {
 	if (@skipped) {
 	    $logmsg .= "\n\n\nSKIPPED:\n\t";
 	    $logmsg .= join("\n\t", @skipped) . "\n";
+	    @skipped = ();
 	}
 
-	print $pw "$logmsg\n"
+	print($commit_write "$logmsg\n") && close($commit_write)
 		or die "Error writing to git-commit-tree: $!\n";
-	$pw->close();
 
-	print "Committed patch $patchset ($branch ".strftime("%Y-%m-%d %H:%M:%S",gmtime($date)).")\n" if $opt_v;
-	chomp(my $cid = <$pr>);
-	length($cid) == 40
-		or die "Cannot get commit id ($cid): $!\n";
+	print "Committed patch $patchset ($branch $commit_date)\n" if $opt_v;
+	chomp(my $cid = <$commit_read>);
+	is_sha1($cid) or die "Cannot get commit id ($cid): $!\n";
 	print "Commit ID $cid\n" if $opt_v;
-	$pr->close();
+	close($commit_read);
 
 	waitpid($pid,0);
 	die "Error running git-commit-tree: $?\n" if $?;
@@ -716,6 +688,7 @@ my $commit = sub {
 	}
 };
 
+my $commitcount = 1;
 while(<CVS>) {
 	chomp;
 	if($state == 0 and /^-+$/) {
@@ -849,7 +822,14 @@ while(<CVS>) {
 	} elsif($state == 9 and /^\s*$/) {
 		$state = 10;
 	} elsif(($state == 9 or $state == 10) and /^-+$/) {
-		&$commit();
+		$commitcount++;
+		if ($opt_L && $commitcount > $opt_L) {
+			last;
+		}
+		commit();
+		if (($commitcount & 1023) == 0) {
+			system("git repack -a -d");
+		}
 		$state = 1;
 	} elsif($state == 11 and /^-+$/) {
 		$state = 1;
@@ -859,7 +839,7 @@ while(<CVS>) {
 		print "* UNKNOWN LINE * $_\n";
 	}
 }
-&$commit() if $branch and $state != 11;
+commit() if $branch and $state != 11;
 
 unlink($git_index);
 

git-format-patch.sh

@@ -1,344 +0,0 @@
-#!/bin/sh
-#
-# Copyright (c) 2005 Junio C Hamano
-#
-
-USAGE='[-n | -k] [-o <dir> | --stdout] [--signoff] [--check] [--diff-options] [--attach] <his> [<mine>]'
-LONG_USAGE='Prepare each commit with its patch since <mine> head forked from
-<his> head, one file per patch formatted to resemble UNIX mailbox
-format, for e-mail submission or use with git-am.
-
-Each output file is numbered sequentially from 1, and uses the
-first line of the commit message (massaged for pathname safety)
-as the filename.
-
-When -o is specified, output files are created in <dir>; otherwise
-they are created in the current working directory.  This option
-is ignored if --stdout is specified.
-
-When -n is specified, instead of "[PATCH] Subject", the first
-line is formatted as "[PATCH N/M] Subject", unless you have only
-one patch.
-
-When --attach is specified, patches are attached, not inlined.'
-
-. git-sh-setup
-
-# Force diff to run in C locale.
-LANG=C LC_ALL=C
-export LANG LC_ALL
-
-diff_opts=
-LF='
-'
-
-outdir=./
-while case "$#" in 0) break;; esac
-do
-    case "$1" in
-    -c|--c|--ch|--che|--chec|--check)
-    check=t ;;
-    -a|--a|--au|--aut|--auth|--autho|--author|\
-    -d|--d|--da|--dat|--date|\
-    -m|--m|--mb|--mbo|--mbox) # now noop
-    ;;
-    --at|--att|--atta|--attac|--attach)
-    attach=t ;;
-    -k|--k|--ke|--kee|--keep|--keep-|--keep-s|--keep-su|--keep-sub|\
-    --keep-subj|--keep-subje|--keep-subjec|--keep-subject)
-    keep_subject=t ;;
-    -n|--n|--nu|--num|--numb|--numbe|--number|--numbere|--numbered)
-    numbered=t ;;
-    -s|--s|--si|--sig|--sign|--signo|--signof|--signoff)
-    signoff=t ;;
-    --st|--std|--stdo|--stdou|--stdout)
-    stdout=t ;;
-    -o=*|--o=*|--ou=*|--out=*|--outp=*|--outpu=*|--output=*|--output-=*|\
-    --output-d=*|--output-di=*|--output-dir=*|--output-dire=*|\
-    --output-direc=*|--output-direct=*|--output-directo=*|\
-    --output-director=*|--output-directory=*)
-    outdir=`expr "$1" : '-[^=]*=\(.*\)'` ;;
-    -o|--o|--ou|--out|--outp|--outpu|--output|--output-|--output-d|\
-    --output-di|--output-dir|--output-dire|--output-direc|--output-direct|\
-    --output-directo|--output-director|--output-directory)
-    case "$#" in 1) usage ;; esac; shift
-    outdir="$1" ;;
-    -h|--h|--he|--hel|--help)
-        usage
-	;;
-    -*' '* | -*"$LF"* | -*'	'*)
-	# Ignore diff option that has whitespace for now.
-	;;
-    -*)	diff_opts="$diff_opts$1 " ;;
-    *) break ;;
-    esac
-    shift
-done
-
-case "$keep_subject$numbered" in
-tt)
-	die '--keep-subject and --numbered are incompatible.' ;;
-esac
-
-tmp=.tmp-series$$
-trap 'rm -f $tmp-*' 0 1 2 3 15
-
-series=$tmp-series
-commsg=$tmp-commsg
-filelist=$tmp-files
-
-# Backward compatible argument parsing hack.
-#
-# Historically, we supported:
-# 1. "rev1"		is equivalent to "rev1..HEAD"
-# 2. "rev1..rev2"
-# 3. "rev1" "rev2	is equivalent to "rev1..rev2"
-#
-# We want to take a sequence of "rev1..rev2" in general.
-# Also, "rev1.." should mean "rev1..HEAD"; git-diff users are
-# familiar with that syntax.
-
-case "$#,$1$2" in
-1,?*..?*)
-	# single "rev1..rev2"
-	;;
-1,?*..)
-	# single "rev1.." should mean "rev1..HEAD"
-	set x "$1"HEAD
-	shift
-	;;
-1,*)
-	# single rev1
-	set x "$1..HEAD"
-	shift
-	;;
-2,?*..?*)
-	# not traditional "rev1" "rev2"
-	;;
-2,*)
-	set x "$1..$2"
-	shift
-	;;
-esac
-
-# Now we have what we want in $@
-for revpair
-do
-	case "$revpair" in
-	?*..?*)
-		rev1=`expr "z$revpair" : 'z\(.*\)\.\.'`
-		rev2=`expr "z$revpair" : 'z.*\.\.\(.*\)'`
-		;;
-	*)
-		rev1="$revpair^"
-		rev2="$revpair"
-		;;
-	esac
-	git-rev-parse --verify "$rev1^0" >/dev/null 2>&1 ||
-		die "Not a valid rev $rev1 ($revpair)"
-	git-rev-parse --verify "$rev2^0" >/dev/null 2>&1 ||
-		die "Not a valid rev $rev2 ($revpair)"
-	git-cherry -v "$rev1" "$rev2" |
-	while read sign rev comment
-	do
-		case "$sign" in
-		'-')
-			echo >&2 "Merged already: $comment"
-			;;
-		*)
-			echo $rev
-			;;
-		esac
-	done
-done >$series
-
-me=`git-var GIT_AUTHOR_IDENT | sed -e 's/>.*/>/'`
-headers=`git-repo-config --get format.headers`
-case "$attach" in
-"") ;;
-*)
-	mimemagic="050802040500080604070107"
-esac
-
-case "$outdir" in
-*/) ;;
-*) outdir="$outdir/" ;;
-esac
-test -d "$outdir" || mkdir -p "$outdir" || exit
-
-titleScript='
-	/./d
-	/^$/n
-	s/^\[PATCH[^]]*\] *//
-	s/[^-a-z.A-Z_0-9]/-/g
-        s/\.\.\.*/\./g
-	s/\.*$//
-	s/--*/-/g
-	s/^-//
-	s/-$//
-	s/$/./
-	p
-	q
-'
-
-process_one () {
-	perl -w -e '
-my ($keep_subject, $num, $signoff, $headers, $mimemagic, $commsg) = @ARGV;
-my ($signoff_pattern, $done_header, $done_subject, $done_separator, $signoff_seen,
-    $last_was_signoff);
-
-if ($signoff) {
-	$signoff = "Signed-off-by: " . `git-var GIT_COMMITTER_IDENT`;
-	$signoff =~ s/>.*/>/;
-	$signoff_pattern = quotemeta($signoff);
-}
-
-my @weekday_names = qw(Sun Mon Tue Wed Thu Fri Sat);
-my @month_names = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
-
-sub show_date {
-    my ($time, $tz) = @_;
-    my $minutes = abs($tz);
-    $minutes = int($minutes / 100) * 60 + ($minutes % 100);
-    if ($tz < 0) {
-        $minutes = -$minutes;
-    }
-    my $t = $time + $minutes * 60;
-    my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday) = gmtime($t);
-    return sprintf("%s, %d %s %d %02d:%02d:%02d %+05d",
-		   $weekday_names[$wday], $mday,
-		   $month_names[$mon], $year+1900,
-		   $hour, $min, $sec, $tz);
-}
-
-print "From nobody Mon Sep 17 00:00:00 2001\n";
-open FH, "git stripspace <$commsg |" or die "open $commsg pipe";
-while (<FH>) {
-    unless ($done_header) {
-	if (/^$/) {
-	    $done_header = 1;
-	}
-	elsif (/^author (.*>) (.*)$/) {
-	    my ($author_ident, $author_date) = ($1, $2);
-	    my ($utc, $off) = ($author_date =~ /^(\d+) ([-+]?\d+)$/);
-	    $author_date = show_date($utc, $off);
-
-	    print "From: $author_ident\n";
-	    print "Date: $author_date\n";
-	}
-	next;
-    }
-    unless ($done_subject) {
-	unless ($keep_subject) {
-	    s/^\[PATCH[^]]*\]\s*//;
-	    s/^/[PATCH$num] /;
-	}
-	if ($headers) {
-	    print "$headers\n";
-	}
-        print "Subject: $_";
-	if ($mimemagic) {
-	    print "MIME-Version: 1.0\n";
-	    print "Content-Type: multipart/mixed;\n";
-	    print " boundary=\"------------$mimemagic\"\n";
-	    print "\n";
-	    print "This is a multi-part message in MIME format.\n";
-	    print "--------------$mimemagic\n";
-	    print "Content-Type: text/plain; charset=UTF-8; format=fixed\n";
-	    print "Content-Transfer-Encoding: 8bit\n";
-	}
-	$done_subject = 1;
-	next;
-    }
-    unless ($done_separator) {
-        print "\n";
-        $done_separator = 1;
-        next if (/^$/);
-    }
-
-    $last_was_signoff = 0;
-    if (/Signed-off-by:/i) {
-        if ($signoff ne "" && /Signed-off-by:\s*$signoff_pattern$/i) {
-	    $signoff_seen = 1;
-	}
-    }
-    print $_;
-}
-if (!$signoff_seen && $signoff ne "") {
-    if (!$last_was_signoff) {
-        print "\n";
-    }
-    print "$signoff\n";
-}
-print "\n---\n\n";
-close FH or die "close $commsg pipe";
-' "$keep_subject" "$num" "$signoff" "$headers" "$mimemagic" $commsg
-
-	git-diff-tree -p --stat --summary $diff_opts "$commit"
-	echo
-	case "$mimemagic" in
-	'');;
-	*)
-		echo "--------------$mimemagic"
-		echo "Content-Type: text/x-patch;"
-		echo " name=\"$commit.diff\""
-		echo "Content-Transfer-Encoding: 8bit"
-		echo "Content-Disposition: inline;"
-		echo " filename=\"$commit.diff\""
-		echo
-	esac
-	git-diff-tree -p $diff_opts "$commit"
-	case "$mimemagic" in
-	'')
-		echo "-- "
-		echo "@@GIT_VERSION@@"
-		;;
-	*)
-		echo
-		echo "--------------$mimemagic--"
-		echo
-		;;
-	esac
-	echo
-}
-
-total=`wc -l <$series | tr -dc "[0-9]"`
-case "$total,$numbered" in
-1,*)
-	numfmt='' ;;
-*,t)
-	numfmt=`echo "$total" | wc -c`
-	numfmt=$(($numfmt-1))
-	numfmt=" %0${numfmt}d/$total"
-esac
-
-i=1
-while read commit
-do
-    git-cat-file commit "$commit" | git-stripspace >$commsg
-    title=`sed -ne "$titleScript" <$commsg`
-    case "$numbered" in
-    '') num= ;;
-    *)
-        num=`printf "$numfmt" $i` ;;
-    esac
-
-    file=`printf '%04d-%stxt' $i "$title"`
-    if test '' = "$stdout"
-    then
-	    echo "$file"
-	    process_one >"$outdir$file"
-	    if test t = "$check"
-	    then
-		# This is slightly modified from Andrew Morton's Perfect Patch.
-		# Lines you introduce should not have trailing whitespace.
-		# Also check for an indentation that has SP before a TAB.
-		grep -n '^+\([ 	]* 	.*\|.*[ 	]\)$' "$outdir$file"
-		:
-	    fi
-    else
-	    echo >&2 "$file"
-	    process_one
-    fi
-    i=`expr "$i" + 1`
-done <$series

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

@@ -152,6 +152,6 @@ then
 	exit 0
 fi
 
-git-format-patch -k --stdout --full-index "$upstream" ORIG_HEAD |
+git-format-patch -k --stdout --full-index "$upstream"..ORIG_HEAD |
 git am --binary -3 -k --resolvemsg="$RESOLVEMSG"
 

git-rm.sh

@@ -1,70 +0,0 @@
-#!/bin/sh
-
-USAGE='[-f] [-n] [-v] [--] <file>...'
-SUBDIRECTORY_OK='Yes'
-. git-sh-setup
-
-remove_files=
-show_only=
-verbose=
-while : ; do
-  case "$1" in
-    -f)
-	remove_files=true
-	;;
-    -n)
-	show_only=true
-	;;
-    -v)
-	verbose=--verbose
-	;;
-    --)
-	shift; break
-	;;
-    -*)
-	usage
-	;;
-    *)
-	break
-	;;
-  esac
-  shift
-done
-
-# This is typo-proofing. If some paths match and some do not, we want
-# to do nothing.
-case "$#" in
-0)	;;
-*)
-	git-ls-files --error-unmatch -- "$@" >/dev/null || {
-		echo >&2 "Maybe you misspelled it?"
-		exit 1
-	}
-	;;
-esac
-
-if test -f "$GIT_DIR/info/exclude"
-then
-	git-ls-files -z \
-	--exclude-from="$GIT_DIR/info/exclude" \
-	--exclude-per-directory=.gitignore -- "$@"
-else
-	git-ls-files -z \
-	--exclude-per-directory=.gitignore -- "$@"
-fi |
-case "$show_only,$remove_files" in
-true,*)
-	xargs -0 echo
-	;;
-*,true)
-	xargs -0 sh -c "
-		while [ \$# -gt 0 ]; do
-			file=\$1; shift
-			rm -- \"\$file\" && git-update-index --remove $verbose \"\$file\"
-		done
-	" inline
-	;;
-*)
-	git-update-index --force-remove $verbose -z --stdin
-	;;
-esac

git.c

@@ -47,10 +47,29 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "whatchanged", cmd_whatchanged },
 		{ "show", cmd_show },
 		{ "push", cmd_push },
-		{ "fmt-patch", cmd_format_patch },
+		{ "format-patch", cmd_format_patch },
 		{ "count-objects", cmd_count_objects },
 		{ "diff", cmd_diff },
 		{ "grep", cmd_grep },
+		{ "rm", cmd_rm },
+		{ "add", cmd_add },
+		{ "rev-list", cmd_rev_list },
+		{ "init-db", cmd_init_db },
+		{ "tar-tree", cmd_tar_tree },
+		{ "upload-tar", cmd_upload_tar },
+		{ "check-ref-format", cmd_check_ref_format },
+		{ "ls-files", cmd_ls_files },
+		{ "ls-tree", cmd_ls_tree },
+		{ "tar-tree", cmd_tar_tree },
+		{ "read-tree", cmd_read_tree },
+		{ "commit-tree", cmd_commit_tree },
+		{ "apply", cmd_apply },
+		{ "show-branch", cmd_show_branch },
+		{ "diff-files", cmd_diff_files },
+		{ "diff-index", cmd_diff_index },
+		{ "diff-stages", cmd_diff_stages },
+		{ "diff-tree", cmd_diff_tree },
+		{ "cat-file", cmd_cat_file }
 	};
 	int i;
 

log-tree.c

@@ -20,6 +20,7 @@ void show_log(struct rev_info *opt, struct log_info *log, const char *sep)
 	int abbrev_commit = opt->abbrev_commit ? opt->abbrev : 40;
 	const char *extra;
 	int len;
+	char *subject = NULL, *after_subject = NULL;
 
 	opt->loginfo = NULL;
 	if (!opt->verbose_header) {
@@ -50,10 +51,50 @@ void show_log(struct rev_info *opt, struct log_info *log, const char *sep)
 	 * Print header line of header..
 	 */
 
-	if (opt->commit_format == CMIT_FMT_EMAIL)
-		printf("From %s  Thu Apr 7 15:13:13 2005\n",
-		       sha1_to_hex(commit->object.sha1));
-	else {
+	if (opt->commit_format == CMIT_FMT_EMAIL) {
+		char *sha1 = sha1_to_hex(commit->object.sha1);
+		if (opt->total > 0) {
+			static char buffer[64];
+			snprintf(buffer, sizeof(buffer),
+					"Subject: [PATCH %d/%d] ",
+					opt->nr, opt->total);
+			subject = buffer;
+		} else if (opt->total == 0)
+			subject = "Subject: [PATCH] ";
+		else
+			subject = "Subject: ";
+
+		printf("From %s Mon Sep 17 00:00:00 2001\n", sha1);
+		if (opt->mime_boundary) {
+			static char subject_buffer[1024];
+			static char buffer[1024];
+			snprintf(subject_buffer, sizeof(subject_buffer) - 1,
+				 "MIME-Version: 1.0\n"
+				 "Content-Type: multipart/mixed;\n"
+				 " boundary=\"%s%s\"\n"
+				 "\n"
+				 "This is a multi-part message in MIME "
+				 "format.\n"
+				 "--%s%s\n"
+				 "Content-Type: text/plain; "
+				 "charset=UTF-8; format=fixed\n"
+				 "Content-Transfer-Encoding: 8bit\n\n",
+				 mime_boundary_leader, opt->mime_boundary,
+				 mime_boundary_leader, opt->mime_boundary);
+			after_subject = subject_buffer;
+
+			snprintf(buffer, sizeof(buffer) - 1,
+				 "--%s%s\n"
+				 "Content-Type: text/x-patch;\n"
+				 " name=\"%s.diff\"\n"
+				 "Content-Transfer-Encoding: 8bit\n"
+				 "Content-Disposition: inline;\n"
+				 " filename=\"%s.diff\"\n\n",
+				 mime_boundary_leader, opt->mime_boundary,
+				 sha1, sha1);
+			opt->diffopt.stat_sep = buffer;
+		}
+	} else {
 		printf("%s%s",
 		       opt->commit_format == CMIT_FMT_ONELINE ? "" : "commit ",
 		       diff_unique_abbrev(commit->object.sha1, abbrev_commit));
@@ -69,7 +110,7 @@ void show_log(struct rev_info *opt, struct log_info *log, const char *sep)
 	/*
 	 * And then the pretty-printed message itself
 	 */
-	len = pretty_print_commit(opt->commit_format, commit, ~0u, this_header, sizeof(this_header), abbrev);
+	len = pretty_print_commit(opt->commit_format, commit, ~0u, this_header, sizeof(this_header), abbrev, subject, after_subject);
 	printf("%s%s%s", this_header, extra, sep);
 }
 

mktag.c

@@ -45,42 +45,46 @@ static int verify_tag(char *buffer, unsigned long size)
 	unsigned char sha1[20];
 	const char *object, *type_line, *tag_line, *tagger_line;
 
-	if (size < 64 || size > MAXSIZE-1)
-		return -1;
+	if (size < 64)
+		return error("wanna fool me ? you obviously got the size wrong !\n");
+
 	buffer[size] = 0;
 
 	/* Verify object line */
 	object = buffer;
 	if (memcmp(object, "object ", 7))
-		return -1;
+		return error("char%d: does not start with \"object \"\n", 0);
+
 	if (get_sha1_hex(object + 7, sha1))
-		return -1;
+		return error("char%d: could not get SHA1 hash\n", 7);
 
 	/* Verify type line */
 	type_line = object + 48;
 	if (memcmp(type_line - 1, "\ntype ", 6))
-		return -1;
+		return error("char%d: could not find \"\\ntype \"\n", 47);
 
 	/* Verify tag-line */
 	tag_line = strchr(type_line, '\n');
 	if (!tag_line)
-		return -1;
+		return error("char%td: could not find next \"\\n\"\n", type_line - buffer);
 	tag_line++;
 	if (memcmp(tag_line, "tag ", 4) || tag_line[4] == '\n')
-		return -1;
+		return error("char%td: no \"tag \" found\n", tag_line - buffer);
 
 	/* Get the actual type */
 	typelen = tag_line - type_line - strlen("type \n");
 	if (typelen >= sizeof(type))
-		return -1;
+		return error("char%td: type too long\n", type_line+5 - buffer);
+
 	memcpy(type, type_line+5, typelen);
 	type[typelen] = 0;
 
 	/* Verify that the object matches */
 	if (get_sha1_hex(object + 7, sha1))
-		return -1;
+		return error("char%d: could not get SHA1 hash but this is really odd since i got it before !\n", 7);
+
 	if (verify_object(sha1, type))
-		return -1;
+		return error("char%d: could not verify object %s\n", 7, sha1);
 
 	/* Verify the tag-name: we don't allow control characters or spaces in it */
 	tag_line += 4;
@@ -90,14 +94,14 @@ static int verify_tag(char *buffer, unsigned long size)
 			break;
 		if (c > ' ')
 			continue;
-		return -1;
+		return error("char%td: could not verify tag name\n", tag_line - buffer);
 	}
 
 	/* Verify the tagger line */
 	tagger_line = tag_line;
 
 	if (memcmp(tagger_line, "tagger", 6) || (tagger_line[6] == '\n'))
-		return -1;
+		return error("char%td: could not find \"tagger\"\n", tagger_line - buffer);
 
 	/* The actual stuff afterwards we don't care about.. */
 	return 0;
@@ -105,8 +109,8 @@ static int verify_tag(char *buffer, unsigned long size)
 
 int main(int argc, char **argv)
 {
-	unsigned long size;
-	char buffer[MAXSIZE];
+	unsigned long size = 4096;
+	char *buffer = malloc(size);
 	unsigned char result_sha1[20];
 
 	if (argc != 1)
@@ -114,13 +118,9 @@ int main(int argc, char **argv)
 
 	setup_git_directory();
 
-	// Read the signature
-	size = 0;
-	for (;;) {
-		int ret = xread(0, buffer + size, MAXSIZE - size);
-		if (ret <= 0)
-			break;
-		size += ret;
+	if (read_pipe(0, &buffer, &size)) {
+		free(buffer);
+		die("could not read from stdin");
 	}
 
 	// Verify it for some basic sanity: it needs to start with "object <sha1>\ntype\ntagger "
@@ -129,6 +129,9 @@ int main(int argc, char **argv)
 
 	if (write_sha1_file(buffer, size, tag_type, result_sha1) < 0)
 		die("unable to write tag file");
+
+	free(buffer);
+
 	printf("%s\n", sha1_to_hex(result_sha1));
 	return 0;
 }

read-cache.c

@@ -331,6 +331,70 @@ int ce_path_match(const struct cache_entry *ce, const char **pathspec)
 	return 0;
 }
 
+/*
+ * We fundamentally don't like some paths: we don't want
+ * dot or dot-dot anywhere, and for obvious reasons don't
+ * want to recurse into ".git" either.
+ *
+ * Also, we don't want double slashes or slashes at the
+ * end that can make pathnames ambiguous.
+ */
+static int verify_dotfile(const char *rest)
+{
+	/*
+	 * The first character was '.', but that
+	 * has already been discarded, we now test
+	 * the rest.
+	 */
+	switch (*rest) {
+	/* "." is not allowed */
+	case '\0': case '/':
+		return 0;
+
+	/*
+	 * ".git" followed by  NUL or slash is bad. This
+	 * shares the path end test with the ".." case.
+	 */
+	case 'g':
+		if (rest[1] != 'i')
+			break;
+		if (rest[2] != 't')
+			break;
+		rest += 2;
+	/* fallthrough */
+	case '.':
+		if (rest[1] == '\0' || rest[1] == '/')
+			return 0;
+	}
+	return 1;
+}
+
+int verify_path(const char *path)
+{
+	char c;
+
+	goto inside;
+	for (;;) {
+		if (!c)
+			return 1;
+		if (c == '/') {
+inside:
+			c = *path++;
+			switch (c) {
+			default:
+				continue;
+			case '/': case '\0':
+				break;
+			case '.':
+				if (verify_dotfile(path))
+					continue;
+			}
+			return 0;
+		}
+		c = *path++;
+	}
+}
+
 /*
  * Do we have another file that has the beginning components being a
  * proper superset of the name we're trying to add?
@@ -472,6 +536,8 @@ int add_cache_entry(struct cache_entry *ce, int option)
 
 	if (!ok_to_add)
 		return -1;
+	if (!verify_path(ce->name))
+		return -1;
 
 	if (!skip_df_check &&
 	    check_file_directory_conflict(ce, pos, ok_to_replace)) {
@@ -496,6 +562,123 @@ 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;

revision.h

@@ -58,6 +58,8 @@ struct rev_info {
 	unsigned int	abbrev;
 	enum cmit_fmt	commit_format;
 	struct log_info *loginfo;
+	int		nr, total;
+	const char	*mime_boundary;
 
 	/* special limits */
 	int max_count;

sha1_file.c

@@ -1399,6 +1399,25 @@ int move_temp_to_file(const char *tmpfile, char *filename)
 	return 0;
 }
 
+static int write_buffer(int fd, const void *buf, size_t len)
+{
+	while (len) {
+		ssize_t size;
+
+		size = write(fd, buf, len);
+		if (!size)
+			return error("file write: disk full");
+		if (size < 0) {
+			if (errno == EINTR || errno == EAGAIN)
+				continue;
+			return error("file write error (%s)", strerror(errno));
+		}
+		len -= size;
+		buf += size;
+	}
+	return 0;
+}
+
 int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
 {
 	int size;
@@ -1465,8 +1484,8 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha
 	deflateEnd(&stream);
 	size = stream.total_out;
 
-	if (write(fd, compressed, size) != size)
-		die("unable to write file");
+	if (write_buffer(fd, compressed, size) < 0)
+		die("unable to write sha1 file");
 	fchmod(fd, 0444);
 	close(fd);
 	free(compressed);
@@ -1474,73 +1493,70 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha
 	return move_temp_to_file(tmpfile, filename);
 }
 
+/*
+ * We need to unpack and recompress the object for writing
+ * it out to a different file.
+ */
+static void *repack_object(const unsigned char *sha1, unsigned long *objsize)
+{
+	size_t size;
+	z_stream stream;
+	unsigned char *unpacked;
+	unsigned long len;
+	char type[20];
+	char hdr[50];
+	int hdrlen;
+	void *buf;
+
+	// need to unpack and recompress it by itself
+	unpacked = read_packed_sha1(sha1, type, &len);
+
+	hdrlen = sprintf(hdr, "%s %lu", type, len) + 1;
+
+	/* Set it up */
+	memset(&stream, 0, sizeof(stream));
+	deflateInit(&stream, Z_BEST_COMPRESSION);
+	size = deflateBound(&stream, len + hdrlen);
+	buf = xmalloc(size);
+
+	/* Compress it */
+	stream.next_out = buf;
+	stream.avail_out = size;
+
+	/* First header.. */
+	stream.next_in = (void *)hdr;
+	stream.avail_in = hdrlen;
+	while (deflate(&stream, 0) == Z_OK)
+		/* nothing */;
+
+	/* Then the data itself.. */
+	stream.next_in = unpacked;
+	stream.avail_in = len;
+	while (deflate(&stream, Z_FINISH) == Z_OK)
+		/* nothing */;
+	deflateEnd(&stream);
+	free(unpacked);
+
+	*objsize = stream.total_out;
+	return buf;
+}
+
 int write_sha1_to_fd(int fd, const unsigned char *sha1)
 {
-	ssize_t size;
+	int retval;
 	unsigned long objsize;
-	int posn = 0;
-	void *map = map_sha1_file_internal(sha1, &objsize);
-	void *buf = map;
-	void *temp_obj = NULL;
-	z_stream stream;
+	void *buf = map_sha1_file_internal(sha1, &objsize);
 
-	if (!buf) {
-		unsigned char *unpacked;
-		unsigned long len;
-		char type[20];
-		char hdr[50];
-		int hdrlen;
-		// need to unpack and recompress it by itself
-		unpacked = read_packed_sha1(sha1, type, &len);
-
-		hdrlen = sprintf(hdr, "%s %lu", type, len) + 1;
-
-		/* Set it up */
-		memset(&stream, 0, sizeof(stream));
-		deflateInit(&stream, Z_BEST_COMPRESSION);
-		size = deflateBound(&stream, len + hdrlen);
-		temp_obj = buf = xmalloc(size);
-
-		/* Compress it */
-		stream.next_out = buf;
-		stream.avail_out = size;
-		
-		/* First header.. */
-		stream.next_in = (void *)hdr;
-		stream.avail_in = hdrlen;
-		while (deflate(&stream, 0) == Z_OK)
-			/* nothing */;
-
-		/* Then the data itself.. */
-		stream.next_in = unpacked;
-		stream.avail_in = len;
-		while (deflate(&stream, Z_FINISH) == Z_OK)
-			/* nothing */;
-		deflateEnd(&stream);
-		free(unpacked);
-		
-		objsize = stream.total_out;
+	if (buf) {
+		retval = write_buffer(fd, buf, objsize);
+		munmap(buf, objsize);
+		return retval;
 	}
 
-	do {
-		size = write(fd, buf + posn, objsize - posn);
-		if (size <= 0) {
-			if (!size) {
-				fprintf(stderr, "write closed\n");
-			} else {
-				perror("write ");
-			}
-			return -1;
-		}
-		posn += size;
-	} while (posn < objsize);
-
-	if (map)
-		munmap(map, objsize);
-	if (temp_obj)
-		free(temp_obj);
-
-	return 0;
+	buf = repack_object(sha1, &objsize);
+	retval = write_buffer(fd, buf, objsize);
+	free(buf);
+	return retval;
 }
 
 int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer,
@@ -1579,7 +1595,8 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer,
 				SHA1_Update(&c, discard, sizeof(discard) -
 					    stream.avail_out);
 			} while (stream.avail_in && ret == Z_OK);
-			write(local, buffer, *bufposn - stream.avail_in);
+			if (write_buffer(local, buffer, *bufposn - stream.avail_in) < 0)
+				die("unable to write sha1 file");
 			memmove(buffer, buffer + *bufposn - stream.avail_in,
 				stream.avail_in);
 			*bufposn = stream.avail_in;
@@ -1645,16 +1662,24 @@ int has_sha1_file(const unsigned char *sha1)
 	return find_sha1_file(sha1, &st) ? 1 : 0;
 }
 
-int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object)
+/*
+ * reads from fd as long as possible into a supplied buffer of size bytes.
+ * If neccessary the buffer's size is increased using realloc()
+ *
+ * returns 0 if anything went fine and -1 otherwise
+ *
+ * NOTE: both buf and size may change, but even when -1 is returned
+ * you still have to free() it yourself.
+ */
+int read_pipe(int fd, char** return_buf, unsigned long* return_size)
 {
-	unsigned long size = 4096;
-	char *buf = malloc(size);
-	int iret, ret;
+	char* buf = *return_buf;
+	unsigned long size = *return_size;
+	int iret;
 	unsigned long off = 0;
-	unsigned char hdr[50];
-	int hdrlen;
+
 	do {
-		iret = read(fd, buf + off, size - off);
+		iret = xread(fd, buf + off, size - off);
 		if (iret > 0) {
 			off += iret;
 			if (off == size) {
@@ -1663,16 +1688,34 @@ int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object)
 			}
 		}
 	} while (iret > 0);
-	if (iret < 0) {
+
+	*return_buf = buf;
+	*return_size = off;
+
+	if (iret < 0)
+		return -1;
+	return 0;
+}
+
+int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object)
+{
+	unsigned long size = 4096;
+	char *buf = malloc(size);
+	int ret;
+	unsigned char hdr[50];
+	int hdrlen;
+
+	if (read_pipe(fd, &buf, &size)) {
 		free(buf);
 		return -1;
 	}
+
 	if (!type)
 		type = blob_type;
 	if (write_object)
-		ret = write_sha1_file(buf, off, type, sha1);
+		ret = write_sha1_file(buf, size, type, sha1);
 	else {
-		write_sha1_file_prepare(buf, off, type, sha1, hdr, &hdrlen);
+		write_sha1_file_prepare(buf, size, type, sha1, hdr, &hdrlen);
 		ret = 0;
 	}
 	free(buf);

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/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/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 && {

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;
@@ -140,167 +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
- * want to recurse into ".git" either.
- *
- * Also, we don't want double slashes or slashes at the
- * end that can make pathnames ambiguous.
- */
-static int verify_dotfile(const char *rest)
-{
-	/*
-	 * The first character was '.', but that
-	 * has already been discarded, we now test
-	 * the rest.
-	 */
-	switch (*rest) {
-	/* "." is not allowed */
-	case '\0': case '/':
-		return 0;
-
-	/*
-	 * ".git" followed by  NUL or slash is bad. This
-	 * shares the path end test with the ".." case.
-	 */
-	case 'g':
-		if (rest[1] != 'i')
-			break;
-		if (rest[2] != 't')
-			break;
-		rest += 2;
-	/* fallthrough */
-	case '.':
-		if (rest[1] == '\0' || rest[1] == '/')
-			return 0;
-	}
-	return 1;
-}
-
-static int verify_path(const char *path)
-{
-	char c;
-
-	goto inside;
-	for (;;) {
-		if (!c)
-			return 1;
-		if (c == '/') {
-inside:
-			c = *path++;
-			switch (c) {
-			default:
-				continue;
-			case '/': case '\0':
-				break;
-			case '.':
-				if (verify_dotfile(path))
-					continue;
-			}
-			return 0;
-		}
-		c = *path++;
-	}
-}
-
 static int add_cacheinfo(unsigned int mode, const unsigned char *sha1,
 			 const char *path, int stage)
 {
@@ -653,6 +472,7 @@ 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);
 
@@ -673,7 +493,7 @@ int main(int argc, const char **argv)
 				continue;
 			}
 			if (!strcmp(path, "-q")) {
-				quiet = 1;
+				refresh_flags |= REFRESH_QUIET;
 				continue;
 			}
 			if (!strcmp(path, "--add")) {
@@ -689,15 +509,15 @@ 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")) {
@@ -770,7 +590,7 @@ int main(int argc, const char **argv)
 				goto finish;
 			}
 			if (!strcmp(path, "--ignore-missing")) {
-				not_new = 1;
+				refresh_flags |= REFRESH_IGNORE_MISSING;
 				continue;
 			}
 			if (!strcmp(path, "--verbose")) {