-#######->WARNING<-####### Directory structure changed, see commit message

If you use git-python as a submodule of your own project, which alters the sys.path to import it,
you will have to adjust your code to take the changed directory structure into consideration.

Previously, you would put the path
./git-python/lib

into your syspath. All modules moved one level up into the 'git' subdirectory, which means that the 'git-python' directory
now contains the 'git' root package. To allow git to be found, add ./git-python into your path.

To finalize your update, run the following commands

git submodule update --init --recursive

As there will be left-over directories, consider running git-clean

5 files changed, 1738 insertions, 0 deletions

diff --git a/git/index/__init__.py b/git/index/__init__.py
new file mode 100644
index 00000000..fe4a7f59
--- /dev/null
+++ b/git/index/__init__.py
@@ -0,0 +1,4 @@
+"""Initialize the index package"""
+
+from base import *
+from typ import *
\ No newline at end of file
diff --git a/git/index/base.py b/git/index/base.py
new file mode 100644
index 00000000..d813e6c1
--- /dev/null
+++ b/git/index/base.py
@@ -0,0 +1,1153 @@
+# index.py
+# Copyright (C) 2008, 2009 Michael Trier (mtrier@gmail.com) and contributors
+#
+# This module is part of GitPython and is released under
+# the BSD License: http://www.opensource.org/licenses/bsd-license.php
+import tempfile
+import os
+import sys
+import subprocess
+import glob
+from cStringIO import StringIO
+
+from stat import S_ISLNK
+
+from typ import (
+					BaseIndexEntry, 
+					IndexEntry, 
+				)
+
+from util import (
+					TemporaryFileSwap,
+					post_clear_cache, 
+					default_index,
+					git_working_dir
+				)
+
+import git.objects
+import git.diff as diff
+
+from git.exc import (
+							GitCommandError,
+							CheckoutError
+						)
+
+from git.objects import (
+							Blob,
+							Submodule,
+							Tree, 
+							Object, 
+							Commit,
+						)
+
+from git.objects.util import Serializable
+
+from git.util import (
+							IndexFileSHA1Writer, 
+							LazyMixin, 
+							LockedFD, 
+							join_path_native, 
+							file_contents_ro,
+							to_native_path_linux,
+							to_native_path
+						)
+
+from fun import (
+					entry_key,
+					write_cache,
+					read_cache,
+					aggressive_tree_merge,
+					write_tree_from_cache,
+					stat_mode_to_index_mode, 
+					S_IFGITLINK
+				)
+
+from gitdb.base import IStream
+from gitdb.db import MemoryDB
+from gitdb.util import to_bin_sha
+from itertools import izip
+
+__all__ = ( 'IndexFile', 'CheckoutError' )
+
+
+class IndexFile(LazyMixin, diff.Diffable, Serializable):
+	"""
+	Implements an Index that can be manipulated using a native implementation in
+	order to save git command function calls wherever possible.
+	
+	It provides custom merging facilities allowing to merge without actually changing
+	your index or your working tree. This way you can perform own test-merges based
+	on the index only without having to deal with the working copy. This is useful
+	in case of partial working trees.
+
+	``Entries``
+	
+	The index contains an entries dict whose keys are tuples of type IndexEntry
+	to facilitate access.
+
+	You may read the entries dict or manipulate it using IndexEntry instance, i.e.::
+	
+		index.entries[index.entry_key(index_entry_instance)] = index_entry_instance
+	
+	Make sure you use index.write() once you are done manipulating the index directly
+	before operating on it using the git command"""
+	__slots__ = ("repo", "version", "entries", "_extension_data", "_file_path")
+	_VERSION = 2			# latest version we support
+	S_IFGITLINK = S_IFGITLINK # a submodule
+
+	def __init__(self, repo, file_path=None):
+		"""Initialize this Index instance, optionally from the given ``file_path``.
+		If no file_path is given, we will be created from the current index file.
+
+		If a stream is not given, the stream will be initialized from the current
+		repository's index on demand."""
+		self.repo = repo
+		self.version = self._VERSION
+		self._extension_data = ''
+		self._file_path = file_path or self._index_path()
+
+	def _set_cache_(self, attr):
+		if attr == "entries":
+			# read the current index
+			# try memory map for speed
+			lfd = LockedFD(self._file_path)
+			try:
+				fd = lfd.open(write=False, stream=False)
+			except OSError:
+				lfd.rollback()
+				# in new repositories, there may be no index, which means we are empty
+				self.entries = dict()
+				return
+			# END exception handling
+
+			# Here it comes: on windows in python 2.5, memory maps aren't closed properly 
+			# Hence we are in trouble if we try to delete a file that is memory mapped, 
+			# which happens during read-tree.
+			# In this case, we will just read the memory in directly.
+			# Its insanely bad ... I am disappointed !
+			allow_mmap = (os.name != 'nt' or sys.version_info[1] > 5)  
+			stream = file_contents_ro(fd, stream=True, allow_mmap=allow_mmap)
+			
+			try:
+				self._deserialize(stream)
+			finally:
+				lfd.rollback()
+				# The handles will be closed on desctruction
+			# END read from default index on demand
+		else:
+			super(IndexFile, self)._set_cache_(attr)
+
+	def _index_path(self):
+		return join_path_native(self.repo.git_dir, "index")
+
+	@property
+	def path(self):
+		""" :return: Path to the index file we are representing """
+		return self._file_path
+
+	def _delete_entries_cache(self):
+		"""Safely clear the entries cache so it can be recreated"""
+		try:
+			del(self.entries)
+		except AttributeError:
+			# fails in python 2.6.5 with this exception
+			pass
+		# END exception handling
+
+	#{ Serializable Interface 
+
+	def _deserialize(self, stream):
+		"""Initialize this instance with index values read from the given stream"""
+		self.version, self.entries, self._extension_data, conten_sha = read_cache(stream)
+		return self
+		
+	def _entries_sorted(self):
+		""":return: list of entries, in a sorted fashion, first by path, then by stage"""
+		entries_sorted = self.entries.values()
+		entries_sorted.sort(key=lambda e: (e.path, e.stage))		# use path/stage as sort key
+		return entries_sorted
+		
+	def _serialize(self, stream, ignore_tree_extension_data=False):
+		entries = self._entries_sorted()
+		write_cache(entries,
+					stream,
+					(ignore_tree_extension_data and None) or self._extension_data) 
+		return self
+		
+		
+	#} END serializable interface
+
+	def write(self, file_path = None, ignore_tree_extension_data=False):
+		"""Write the current state to our file path or to the given one
+
+		:param file_path:
+			If None, we will write to our stored file path from which we have
+			been initialized. Otherwise we write to the given file path.
+			Please note that this will change the file_path of this index to
+			the one you gave.
+
+		:param ignore_tree_extension_data:
+			If True, the TREE type extension data read in the index will not
+			be written to disk. Use this if you have altered the index and
+			would like to use git-write-tree afterwards to create a tree
+			representing your written changes.
+			If this data is present in the written index, git-write-tree
+			will instead write the stored/cached tree.
+			Alternatively, use IndexFile.write_tree() to handle this case
+			automatically
+
+		:return: self"""
+		# make sure we have our entries read before getting a write lock
+		# else it would be done when streaming. This can happen 
+		# if one doesn't change the index, but writes it right away
+		self.entries
+		lfd = LockedFD(file_path or self._file_path)
+		stream = lfd.open(write=True, stream=True)
+		
+		self._serialize(stream, ignore_tree_extension_data)
+		
+		lfd.commit()
+
+		# make sure we represent what we have written
+		if file_path is not None:
+			self._file_path = file_path
+
+	@post_clear_cache
+	@default_index
+	def merge_tree(self, rhs, base=None):
+		"""Merge the given rhs treeish into the current index, possibly taking
+		a common base treeish into account.
+
+		As opposed to the from_tree_ method, this allows you to use an already
+		existing tree as the left side of the merge
+
+		:param rhs:
+			treeish reference pointing to the 'other' side of the merge.
+
+		:param base:
+			optional treeish reference pointing to the common base of 'rhs' and
+			this index which equals lhs
+
+		:return:
+			self ( containing the merge and possibly unmerged entries in case of
+			conflicts )
+
+		:raise GitCommandError:
+			If there is a merge conflict. The error will
+			be raised at the first conflicting path. If you want to have proper
+			merge resolution to be done by yourself, you have to commit the changed
+			index ( or make a valid tree from it ) and retry with a three-way
+			index.from_tree call. """
+		# -i : ignore working tree status
+		# --aggressive : handle more merge cases
+		# -m : do an actual merge
+		args = ["--aggressive", "-i", "-m"]
+		if base is not None:
+			args.append(base)
+		args.append(rhs)
+
+		self.repo.git.read_tree(args)
+		return self
+
+	@classmethod
+	def new(cls, repo, *tree_sha):
+		""" Merge the given treeish revisions into a new index which is returned.
+		This method behaves like git-read-tree --aggressive when doing the merge.
+
+		:param repo: The repository treeish are located in.
+
+		:param tree_sha:
+			20 byte or 40 byte tree sha or tree objects 
+
+		:return:
+			New IndexFile instance. Its path will be undefined. 
+			If you intend to write such a merged Index, supply an alternate file_path 
+			to its 'write' method."""
+		base_entries = aggressive_tree_merge(repo.odb, [to_bin_sha(str(t)) for t in tree_sha])
+		
+		inst = cls(repo)
+		# convert to entries dict
+		entries = dict(izip(((e.path, e.stage) for e in base_entries), 
+							(IndexEntry.from_base(e) for e in base_entries)))
+		
+		inst.entries = entries
+		return inst
+
+
+	@classmethod
+	def from_tree(cls, repo, *treeish, **kwargs):
+		"""Merge the given treeish revisions into a new index which is returned.
+		The original index will remain unaltered
+
+		:param repo:
+			The repository treeish are located in.
+
+		:param treeish:
+			One, two or three Tree Objects, Commits or 40 byte hexshas. The result
+			changes according to the amount of trees.
+			If 1 Tree is given, it will just be read into a new index
+			If 2 Trees are given, they will be merged into a new index using a
+			 two way merge algorithm. Tree 1 is the 'current' tree, tree 2 is the 'other'
+			 one. It behaves like a fast-forward.
+			 If 3 Trees are given, a 3-way merge will be performed with the first tree
+			 being the common ancestor of tree 2 and tree 3. Tree 2 is the 'current' tree,
+			 tree 3 is the 'other' one
+
+		:param kwargs:
+			Additional arguments passed to git-read-tree
+
+		:return:
+			New IndexFile instance. It will point to a temporary index location which
+			does not exist anymore. If you intend to write such a merged Index, supply
+			an alternate file_path to its 'write' method.
+
+		:note:
+			In the three-way merge case, --aggressive will be specified to automatically
+			resolve more cases in a commonly correct manner. Specify trivial=True as kwarg
+			to override that.
+
+			As the underlying git-read-tree command takes into account the current index,
+			it will be temporarily moved out of the way to assure there are no unsuspected
+			interferences."""
+		if len(treeish) == 0 or len(treeish) > 3:
+			raise ValueError("Please specify between 1 and 3 treeish, got %i" % len(treeish))
+
+		arg_list = list()
+		# ignore that working tree and index possibly are out of date
+		if len(treeish)>1:
+			# drop unmerged entries when reading our index and merging
+			arg_list.append("--reset")
+			# handle non-trivial cases the way a real merge does
+			arg_list.append("--aggressive")
+		# END merge handling
+
+		# tmp file created in git home directory to be sure renaming
+		# works - /tmp/ dirs could be on another device
+		tmp_index = tempfile.mktemp('','',repo.git_dir)
+		arg_list.append("--index-output=%s" % tmp_index)
+		arg_list.extend(treeish)
+
+		# move current index out of the way - otherwise the merge may fail
+		# as it considers existing entries. moving it essentially clears the index.
+		# Unfortunately there is no 'soft' way to do it.
+		# The TemporaryFileSwap assure the original file get put back
+		index_handler = TemporaryFileSwap(join_path_native(repo.git_dir, 'index'))
+		try:
+			repo.git.read_tree(*arg_list, **kwargs)
+			index = cls(repo, tmp_index)
+			index.entries		# force it to read the file as we will delete the temp-file
+			del(index_handler)	# release as soon as possible
+		finally:
+			if os.path.exists(tmp_index):
+				os.remove(tmp_index)
+		# END index merge handling
+
+		return index
+
+	# UTILITIES
+	def _iter_expand_paths(self, paths):
+		"""Expand the directories in list of paths to the corresponding paths accordingly,
+
+		Note: git will add items multiple times even if a glob overlapped
+		with manually specified paths or if paths where specified multiple
+		times - we respect that and do not prune"""
+		def raise_exc(e):
+			raise e
+		r = self.repo.working_tree_dir
+		rs = r + os.sep
+		for path in paths:
+			abs_path = path
+			if not os.path.isabs(abs_path):
+				abs_path = os.path.join(r, path)
+			# END make absolute path
+
+			# resolve globs if possible
+			if '?' in path or '*' in path or '[' in path:
+				for f in self._iter_expand_paths(glob.glob(abs_path)):
+					yield f.replace(rs, '')
+				continue
+			# END glob handling
+			try:
+				for root, dirs, files in os.walk(abs_path, onerror=raise_exc):
+					for rela_file in files:
+						# add relative paths only
+						yield os.path.join(root.replace(rs, ''), rela_file)
+					# END for each file in subdir
+				# END for each subdirectory
+			except OSError:
+				# was a file or something that could not be iterated
+				yield path.replace(rs, '')
+			# END path exception handling
+		# END for each path
+
+	def _write_path_to_stdin(self, proc, filepath, item, fmakeexc, fprogress, 
+								read_from_stdout=True):
+		"""Write path to proc.stdin and make sure it processes the item, including progress.
+
+		:return: stdout string
+		:param read_from_stdout: if True, proc.stdout will be read after the item
+			was sent to stdin. In that case, it will return None
+		:note: There is a bug in git-update-index that prevents it from sending
+			reports just in time. This is why we have a version that tries to
+			read stdout and one which doesn't. In fact, the stdout is not
+			important as the piped-in files are processed anyway and just in time
+		:note: Newlines are essential here, gits behaviour is somewhat inconsistent
+			on this depending on the version, hence we try our best to deal with
+			newlines carefully. Usually the last newline will not be sent, instead
+			we will close stdin to break the pipe."""
+
+		fprogress(filepath, False, item)
+		rval = None
+		try:
+			proc.stdin.write("%s\n" % filepath)
+		except IOError:
+			# pipe broke, usually because some error happend
+			raise fmakeexc()
+		# END write exception handling
+		proc.stdin.flush()
+		if read_from_stdout:
+			rval = proc.stdout.readline().strip()
+		fprogress(filepath, True, item)
+		return rval
+
+	def iter_blobs(self, predicate = lambda t: True):
+		"""
+		:return: Iterator yielding tuples of Blob objects and stages, tuple(stage, Blob)
+
+		:param predicate:
+			Function(t) returning True if tuple(stage, Blob) should be yielded by the
+			iterator. A default filter, the BlobFilter, allows you to yield blobs
+			only if they match a given list of paths. """
+		for entry in self.entries.itervalues():
+			# TODO: is it necessary to convert the mode ? We did that when adding 
+			# it to the index, right ?
+			mode = stat_mode_to_index_mode(entry.mode)
+			blob = entry.to_blob(self.repo)
+			blob.size = entry.size
+			output = (entry.stage, blob)
+			if predicate(output):
+				yield output
+		# END for each entry
+
+	def unmerged_blobs(self):
+		"""
+		:return:
+			Iterator yielding dict(path : list( tuple( stage, Blob, ...))), being
+			a dictionary associating a path in the index with a list containing
+			sorted stage/blob pairs
+
+		:note:
+			Blobs that have been removed in one side simply do not exist in the
+			given stage. I.e. a file removed on the 'other' branch whose entries
+			are at stage 3 will not have a stage 3 entry.
+		"""
+		is_unmerged_blob = lambda t: t[0] != 0
+		path_map = dict()
+		for stage, blob in self.iter_blobs(is_unmerged_blob):
+			path_map.setdefault(blob.path, list()).append((stage, blob))
+		# END for each unmerged blob
+		for l in path_map.itervalues():
+			l.sort()
+		return path_map
+
+	@classmethod
+	def entry_key(cls, *entry):
+		return entry_key(*entry)
+
+	def resolve_blobs(self, iter_blobs):
+		"""Resolve the blobs given in blob iterator. This will effectively remove the
+		index entries of the respective path at all non-null stages and add the given
+		blob as new stage null blob.
+
+		For each path there may only be one blob, otherwise a ValueError will be raised
+		claiming the path is already at stage 0.
+
+		:raise ValueError: if one of the blobs already existed at stage 0
+		:return: self
+
+		:note:
+			You will have to write the index manually once you are done, i.e.
+			index.resolve_blobs(blobs).write()
+		"""
+		for blob in iter_blobs:
+			stage_null_key = (blob.path, 0)
+			if stage_null_key in self.entries:
+				raise ValueError( "Path %r already exists at stage 0" % blob.path )
+			# END assert blob is not stage 0 already
+
+			# delete all possible stages
+			for stage in (1, 2, 3):
+				try:
+					del( self.entries[(blob.path, stage)])
+				except KeyError:
+					pass
+				# END ignore key errors
+			# END for each possible stage
+
+			self.entries[stage_null_key] = IndexEntry.from_blob(blob)
+		# END for each blob
+
+		return self
+
+	def update(self):
+		"""Reread the contents of our index file, discarding all cached information
+		we might have.
+
+		:note: This is a possibly dangerious operations as it will discard your changes
+			to index.entries
+		:return: self"""
+		self._delete_entries_cache()
+		# allows to lazily reread on demand
+		return self
+
+	def write_tree(self):
+		"""Writes this index to a corresponding Tree object into the repository's
+		object database and return it.
+		
+		:return: Tree object representing this index
+		:note: The tree will be written even if one or more objects the tree refers to 
+			does not yet exist in the object database. This could happen if you added
+			Entries to the index directly.
+		:raise ValueError: if there are no entries in the cache
+		:raise UnmergedEntriesError: """
+		# we obtain no lock as we just flush our contents to disk as tree
+		# If we are a new index, the entries access will load our data accordingly
+		mdb = MemoryDB()
+		entries = self._entries_sorted()
+		binsha, tree_items = write_tree_from_cache(entries, mdb, slice(0, len(entries)))
+		
+		# copy changed trees only
+		mdb.stream_copy(mdb.sha_iter(), self.repo.odb)
+		
+		
+		# note: additional deserialization could be saved if write_tree_from_cache
+		# would return sorted tree entries
+		root_tree = Tree(self.repo, binsha, path='')
+		root_tree._cache = tree_items
+		return root_tree
+		
+	def _process_diff_args(self, args):
+		try:
+			args.pop(args.index(self))
+		except IndexError:
+			pass
+		# END remove self
+		return args
+
+	def _to_relative_path(self, path):
+		""":return: Version of path relative to our git directory or raise ValueError
+		if it is not within our git direcotory"""
+		if not os.path.isabs(path):
+			return path
+		relative_path = path.replace(self.repo.working_tree_dir+os.sep, "")
+		if relative_path == path:
+			raise ValueError("Absolute path %r is not in git repository at %r" % (path,self.repo.working_tree_dir))
+		return relative_path
+
+	def _preprocess_add_items(self, items):
+		""" Split the items into two lists of path strings and BaseEntries. """
+		paths = list()
+		entries = list()
+
+		for item in items:
+			if isinstance(item, basestring):
+				paths.append(self._to_relative_path(item))
+			elif isinstance(item, (Blob, Submodule)):
+				entries.append(BaseIndexEntry.from_blob(item))
+			elif isinstance(item, BaseIndexEntry):
+				entries.append(item)
+			else:
+				raise TypeError("Invalid Type: %r" % item)
+		# END for each item
+		return (paths, entries)
+
+	@git_working_dir
+	def add(self, items, force=True, fprogress=lambda *args: None, path_rewriter=None, 
+				write=True):
+		"""Add files from the working tree, specific blobs or BaseIndexEntries
+		to the index. 
+
+		:param items:
+			Multiple types of items are supported, types can be mixed within one call.
+			Different types imply a different handling. File paths may generally be
+			relative or absolute.
+
+			- path string
+				strings denote a relative or absolute path into the repository pointing to
+				an existing file, i.e. CHANGES, lib/myfile.ext, '/home/gitrepo/lib/myfile.ext'.
+
+				Paths provided like this must exist. When added, they will be written
+				into the object database.
+
+				PathStrings may contain globs, such as 'lib/__init__*' or can be directories
+				like 'lib', the latter ones will add all the files within the dirctory and
+				subdirectories.
+
+				This equals a straight git-add.
+
+				They are added at stage 0
+
+			- Blob or Submodule object
+				Blobs are added as they are assuming a valid mode is set.
+				The file they refer to may or may not exist in the file system, but
+				must be a path relative to our repository.
+
+				If their sha is null ( 40*0 ), their path must exist in the file system
+				relative to the git repository as an object will be created from 
+				the data at the path.
+				The handling now very much equals the way string paths are processed, except that
+				the mode you have set will be kept. This allows you to create symlinks
+				by settings the mode respectively and writing the target of the symlink
+				directly into the file. This equals a default Linux-Symlink which
+				is not dereferenced automatically, except that it can be created on
+				filesystems not supporting it as well.
+
+				Please note that globs or directories are not allowed in Blob objects.
+
+				They are added at stage 0
+
+			- BaseIndexEntry or type
+				Handling equals the one of Blob objects, but the stage may be
+				explicitly set. Please note that Index Entries require binary sha's.
+
+		:param force:
+			**CURRENTLY INEFFECTIVE**
+			If True, otherwise ignored or excluded files will be
+			added anyway.
+			As opposed to the git-add command, we enable this flag by default
+			as the API user usually wants the item to be added even though
+			they might be excluded.
+
+		:param fprogress:
+			Function with signature f(path, done=False, item=item) called for each
+			path to be added, one time once it is about to be added where done==False
+			and once after it was added where done=True.
+			item is set to the actual item we handle, either a Path or a BaseIndexEntry
+			Please note that the processed path is not guaranteed to be present
+			in the index already as the index is currently being processed.
+
+		:param path_rewriter:
+			Function with signature (string) func(BaseIndexEntry) function returning a path
+			for each passed entry which is the path to be actually recorded for the
+			object created from entry.path. This allows you to write an index which
+			is not identical to the layout of the actual files on your hard-dist.
+			If not None and ``items`` contain plain paths, these paths will be
+			converted to Entries beforehand and passed to the path_rewriter.
+			Please note that entry.path is relative to the git repository.
+
+		:param write:
+				If True, the index will be written once it was altered. Otherwise
+				the changes only exist in memory and are not available to git commands.
+		
+		:return:
+			List(BaseIndexEntries) representing the entries just actually added.
+
+		:raise OSError:
+			if a supplied Path did not exist. Please note that BaseIndexEntry
+			Objects that do not have a null sha will be added even if their paths
+			do not exist.
+		"""
+		# sort the entries into strings and Entries, Blobs are converted to entries
+		# automatically
+		# paths can be git-added, for everything else we use git-update-index
+		entries_added = list()
+		paths, entries = self._preprocess_add_items(items)
+		if paths and path_rewriter:
+			for path in paths:
+				abspath = os.path.abspath(path)
+				gitrelative_path = abspath[len(self.repo.working_tree_dir)+1:]
+				blob = Blob(self.repo, Blob.NULL_BIN_SHA, 
+							stat_mode_to_index_mode(os.stat(abspath).st_mode), 
+							to_native_path_linux(gitrelative_path))
+				entries.append(BaseIndexEntry.from_blob(blob))
+			# END for each path
+			del(paths[:])
+		# END rewrite paths
+
+
+		def store_path(filepath):
+			"""Store file at filepath in the database and return the base index entry"""
+			st = os.lstat(filepath)		# handles non-symlinks as well
+			stream = None
+			if S_ISLNK(st.st_mode):
+				stream = StringIO(os.readlink(filepath))
+			else:
+				stream = open(filepath, 'rb')
+			# END handle stream
+			fprogress(filepath, False, filepath)
+			istream = self.repo.odb.store(IStream(Blob.type, st.st_size, stream))
+			fprogress(filepath, True, filepath)
+			return BaseIndexEntry((stat_mode_to_index_mode(st.st_mode), 
+									istream.binsha, 0, to_native_path_linux(filepath)))
+		# END utility method
+
+
+		# HANDLE PATHS
+		if paths:
+			assert len(entries_added) == 0
+			added_files = list()
+			for filepath in self._iter_expand_paths(paths):
+				entries_added.append(store_path(filepath))
+			# END for each filepath
+		# END path handling
+
+
+		# HANDLE ENTRIES
+		if entries:
+			null_mode_entries = [ e for e in entries if e.mode == 0 ]
+			if null_mode_entries:
+				raise ValueError("At least one Entry has a null-mode - please use index.remove to remove files for clarity")
+			# END null mode should be remove
+
+			# HANLDE ENTRY OBJECT CREATION
+			# create objects if required, otherwise go with the existing shas
+			null_entries_indices = [ i for i,e in enumerate(entries) if e.binsha == Object.NULL_BIN_SHA ]
+			if null_entries_indices:
+				for ei in null_entries_indices:
+					null_entry = entries[ei]
+					new_entry = store_path(null_entry.path)
+					
+					# update null entry
+					entries[ei] = BaseIndexEntry((null_entry.mode, new_entry.binsha, null_entry.stage, null_entry.path))
+				# END for each entry index
+			# END null_entry handling
+
+			# REWRITE PATHS
+			# If we have to rewrite the entries, do so now, after we have generated
+			# all object sha's
+			if path_rewriter:
+				for i,e in enumerate(entries):
+					entries[i] = BaseIndexEntry((e.mode, e.binsha, e.stage, path_rewriter(e)))
+				# END for each entry
+			# END handle path rewriting
+
+			# just go through the remaining entries and provide progress info
+			for i, entry in enumerate(entries):
+				progress_sent = i in null_entries_indices
+				if not progress_sent:
+					fprogress(entry.path, False, entry)
+					fprogress(entry.path, True, entry)
+				# END handle progress
+			# END for each enty
+			entries_added.extend(entries)
+		# END if there are base entries
+
+		# FINALIZE
+		# add the new entries to this instance
+		for entry in entries_added:
+			self.entries[(entry.path, 0)] = IndexEntry.from_base(entry)
+			
+		if write:
+			self.write()
+		# END handle write
+		
+		return entries_added
+
+	def _items_to_rela_paths(self, items):
+		"""Returns a list of repo-relative paths from the given items which
+		may be absolute or relative paths, entries or blobs"""
+		paths = list()
+		for item in items:
+			if isinstance(item, (BaseIndexEntry,(Blob, Submodule))):
+				paths.append(self._to_relative_path(item.path))
+			elif isinstance(item, basestring):
+				paths.append(self._to_relative_path(item))
+			else:
+				raise TypeError("Invalid item type: %r" % item)
+		# END for each item
+		return paths
+
+	@post_clear_cache
+	@default_index
+	def remove(self, items, working_tree=False, **kwargs):
+		"""Remove the given items from the index and optionally from
+		the working tree as well.
+
+		:param items:
+			Multiple types of items are supported which may be be freely mixed.
+
+			- path string
+				Remove the given path at all stages. If it is a directory, you must
+				specify the r=True keyword argument to remove all file entries
+				below it. If absolute paths are given, they will be converted
+				to a path relative to the git repository directory containing
+				the working tree
+
+				The path string may include globs, such as *.c.
+
+			- Blob Object
+				Only the path portion is used in this case.
+
+			- BaseIndexEntry or compatible type
+				The only relevant information here Yis the path. The stage is ignored.
+
+		:param working_tree:
+			If True, the entry will also be removed from the working tree, physically
+			removing the respective file. This may fail if there are uncommited changes
+			in it.
+
+		:param kwargs:
+			Additional keyword arguments to be passed to git-rm, such
+			as 'r' to allow recurive removal of
+
+		:return:
+			List(path_string, ...) list of repository relative paths that have
+			been removed effectively.
+			This is interesting to know in case you have provided a directory or
+			globs. Paths are relative to the repository. """
+		args = list()
+		if not working_tree:
+			args.append("--cached")
+		args.append("--")
+
+		# preprocess paths
+		paths = self._items_to_rela_paths(items)
+		removed_paths = self.repo.git.rm(args, paths, **kwargs).splitlines()
+
+		# process output to gain proper paths
+		# rm 'path'
+		return [ p[4:-1] for p in removed_paths ]
+
+	@post_clear_cache
+	@default_index
+	def move(self, items, skip_errors=False, **kwargs):
+		"""Rename/move the items, whereas the last item is considered the destination of
+		the move operation. If the destination is a file, the first item ( of two )
+		must be a file as well. If the destination is a directory, it may be preceeded
+		by one or more directories or files.
+
+		The working tree will be affected in non-bare repositories.
+
+		:parma items:
+			Multiple types of items are supported, please see the 'remove' method
+			for reference.
+		:param skip_errors:
+			If True, errors such as ones resulting from missing source files will
+			be skpped.
+		:param kwargs:
+			Additional arguments you would like to pass to git-mv, such as dry_run
+			or force.
+
+		:return:List(tuple(source_path_string, destination_path_string), ...)
+			A list of pairs, containing the source file moved as well as its
+			actual destination. Relative to the repository root.
+
+		:raise ValueErorr: If only one item was given
+			GitCommandError: If git could not handle your request"""
+		args = list()
+		if skip_errors:
+			args.append('-k')
+
+		paths = self._items_to_rela_paths(items)
+		if len(paths) < 2:
+			raise ValueError("Please provide at least one source and one destination of the move operation")
+
+		was_dry_run = kwargs.pop('dry_run', kwargs.pop('n', None))
+		kwargs['dry_run'] = True
+
+		# first execute rename in dryrun so the command tells us what it actually does
+		# ( for later output )
+		out = list()
+		mvlines = self.repo.git.mv(args, paths, **kwargs).splitlines()
+
+		# parse result - first 0:n/2 lines are 'checking ', the remaining ones
+		# are the 'renaming' ones which we parse
+		for ln in xrange(len(mvlines)/2, len(mvlines)):
+			tokens = mvlines[ln].split(' to ')
+			assert len(tokens) == 2, "Too many tokens in %s" % mvlines[ln]
+
+			# [0] = Renaming x
+			# [1] = y
+			out.append((tokens[0][9:], tokens[1]))
+		# END for each line to parse
+
+		# either prepare for the real run, or output the dry-run result
+		if was_dry_run:
+			return out
+		# END handle dryrun
+
+
+		# now apply the actual operation
+		kwargs.pop('dry_run')
+		self.repo.git.mv(args, paths, **kwargs)
+
+		return out
+
+	def commit(self, message, parent_commits=None, head=True):
+		"""Commit the current default index file, creating a commit object.
+
+		For more information on the arguments, see tree.commit.
+		:note:
+			If you have manually altered the .entries member of this instance,
+			don't forget to write() your changes to disk beforehand.
+
+		:return:
+			Commit object representing the new commit"""
+		tree = self.write_tree()
+		return Commit.create_from_tree(self.repo, tree, message, parent_commits, head)
+
+	@classmethod
+	def _flush_stdin_and_wait(cls, proc, ignore_stdout = False):
+		proc.stdin.flush()
+		proc.stdin.close()
+		stdout = ''
+		if not ignore_stdout:
+			stdout = proc.stdout.read()
+		proc.stdout.close()
+		proc.wait()
+		return stdout
+
+	@default_index
+	def checkout(self, paths=None, force=False, fprogress=lambda *args: None, **kwargs):
+		"""Checkout the given paths or all files from the version known to the index into
+		the working tree.
+		
+		:note: Be sure you have written pending changes using the ``write`` method
+			in case you have altered the enties dictionary directly
+
+		:param paths:
+			If None, all paths in the index will be checked out. Otherwise an iterable
+			of relative or absolute paths or a single path pointing to files or directories
+			in the index is expected.
+
+		:param force:
+			If True, existing files will be overwritten even if they contain local modifications.
+			If False, these will trigger a CheckoutError.
+
+		:param fprogress:
+			see Index.add_ for signature and explanation.
+			The provided progress information will contain None as path and item if no
+			explicit paths are given. Otherwise progress information will be send
+			prior and after a file has been checked out
+
+		:param kwargs:
+			Additional arguments to be pasesd to git-checkout-index
+
+		:return:
+			iterable yielding paths to files which have been checked out and are
+			guaranteed to match the version stored in the index
+
+		:raise CheckoutError:
+			If at least one file failed to be checked out. This is a summary,
+			hence it will checkout as many files as it can anyway.
+			If one of files or directories do not exist in the index
+			( as opposed to the	 original git command who ignores them ).
+			Raise GitCommandError if error lines could not be parsed - this truly is
+			an exceptional state
+			
+		.. note:: The checkout is limited to checking out the files in the 
+			index. Files which are not in the index anymore and exist in 
+			the working tree will not be deleted. This behaviour is fundamentally
+			different to *head.checkout*, i.e. if you want git-checkout like behaviour, 
+			use head.checkout instead of index.checkout.
+			"""
+		args = ["--index"]
+		if force:
+			args.append("--force")
+
+		def handle_stderr(proc, iter_checked_out_files):
+			stderr = proc.stderr.read()
+			if not stderr:
+				return
+			# line contents:
+			# git-checkout-index: this already exists
+			failed_files = list()
+			failed_reasons = list()
+			unknown_lines = list()
+			endings = (' already exists', ' is not in the cache', ' does not exist at stage', ' is unmerged')
+			for line in stderr.splitlines():
+				if not line.startswith("git checkout-index: ") and not line.startswith("git-checkout-index: "):
+					is_a_dir = " is a directory"
+					unlink_issue = "unable to unlink old '"
+					if line.endswith(is_a_dir):
+						failed_files.append(line[:-len(is_a_dir)])
+						failed_reasons.append(is_a_dir)
+					elif line.startswith(unlink_issue):
+						failed_files.append(line[len(unlink_issue):line.rfind("'")])
+						failed_reasons.append(unlink_issue)
+					else:
+						unknown_lines.append(line)
+					continue
+				# END special lines parsing
+
+				for e in endings:
+					if line.endswith(e):
+						failed_files.append(line[20:-len(e)])
+						failed_reasons.append(e)
+						break
+					# END if ending matches
+				# END for each possible ending
+			# END for each line
+			if unknown_lines:
+				raise GitCommandError(("git-checkout-index", ), 128, stderr)
+			if failed_files:
+				valid_files = list(set(iter_checked_out_files) - set(failed_files))
+				raise CheckoutError("Some files could not be checked out from the index due to local modifications", failed_files, valid_files, failed_reasons)
+		# END stderr handler
+
+
+		if paths is None:
+			args.append("--all")
+			kwargs['as_process'] = 1
+			fprogress(None, False, None)
+			proc = self.repo.git.checkout_index(*args, **kwargs)
+			proc.wait()
+			fprogress(None, True, None)
+			rval_iter = ( e.path for e in self.entries.itervalues() )
+			handle_stderr(proc, rval_iter)
+			return rval_iter
+		else:
+			if isinstance(paths, basestring):
+				paths = [paths]
+
+			# make sure we have our entries loaded before we start checkout_index
+			# which will hold a lock on it. We try to get the lock as well during 
+			# our entries initialization
+			self.entries
+			
+			args.append("--stdin")
+			kwargs['as_process'] = True
+			kwargs['istream'] = subprocess.PIPE
+			proc = self.repo.git.checkout_index(args, **kwargs)
+			make_exc = lambda : GitCommandError(("git-checkout-index",)+tuple(args), 128, proc.stderr.read())
+			checked_out_files = list()
+
+			for path in paths:
+				co_path = to_native_path_linux(self._to_relative_path(path))
+				# if the item is not in the index, it could be a directory
+				path_is_directory = False
+
+				try:
+					self.entries[(co_path, 0)]
+				except KeyError:
+					dir = co_path
+					if not dir.endswith('/'):
+						dir += '/'
+					for entry in self.entries.itervalues():
+						if entry.path.startswith(dir):
+							p = entry.path
+							self._write_path_to_stdin(proc, p, p, make_exc, 
+														fprogress, read_from_stdout=False)
+							checked_out_files.append(p)
+							path_is_directory = True
+						# END if entry is in directory
+					# END for each entry
+				# END path exception handlnig
+
+				if not path_is_directory:
+					self._write_path_to_stdin(proc, co_path, path, make_exc, 
+												fprogress, read_from_stdout=False)
+					checked_out_files.append(co_path)
+				# END path is a file
+			# END for each path
+			self._flush_stdin_and_wait(proc, ignore_stdout=True)
+
+			handle_stderr(proc, checked_out_files)
+			return checked_out_files
+		# END paths handling
+		assert "Should not reach this point"
+
+	@default_index
+	def reset(self, commit='HEAD', working_tree=False, paths=None, head=False, **kwargs):
+		"""Reset the index to reflect the tree at the given commit. This will not
+		adjust our HEAD reference as opposed to HEAD.reset by default.
+
+		:param commit:
+			Revision, Reference or Commit specifying the commit we should represent.
+			If you want to specify a tree only, use IndexFile.from_tree and overwrite
+			the default index.
+
+		:param working_tree:
+			If True, the files in the working tree will reflect the changed index.
+			If False, the working tree will not be touched
+			Please note that changes to the working copy will be discarded without
+			warning !
+			
+		:param head:
+			If True, the head will be set to the given commit. This is False by default,
+			but if True, this method behaves like HEAD.reset.
+			
+		:param paths: if given as an iterable of absolute or repository-relative paths,
+			only these will be reset to their state at the given commit'ish.
+			The paths need to exist at the commit, otherwise an exception will be 
+			raised.
+
+		:param kwargs:
+			Additional keyword arguments passed to git-reset
+			
+		.. note:: IndexFile.reset, as opposed to HEAD.reset, will not delete anyfiles
+			in order to maintain a consistent working tree. Instead, it will just
+			checkout the files according to their state in the index.
+			If you want git-reset like behaviour, use *HEAD.reset* instead.
+
+		:return: self """
+		# what we actually want to do is to merge the tree into our existing
+		# index, which is what git-read-tree does
+		new_inst = type(self).from_tree(self.repo, commit)
+		if not paths:
+			self.entries = new_inst.entries
+		else:
+			nie = new_inst.entries
+			for path in paths:
+				path = self._to_relative_path(path)
+				try:
+					key = entry_key(path, 0)
+					self.entries[key] = nie[key]
+				except KeyError:
+					# if key is not in theirs, it musn't be in ours
+					try:
+						del(self.entries[key])
+					except KeyError:
+						pass
+					# END handle deletion keyerror
+				# END handle keyerror
+			# END for each path
+		# END handle paths
+		self.write()
+		
+		if working_tree:
+			self.checkout(paths=paths, force=True)
+		# END handle working tree
+		
+		if head:
+			self.repo.head.set_commit(self.repo.commit(commit), logmsg="%s: Updating HEAD" % commit)
+		# END handle head change
+
+		return self
+
+	@default_index
+	def diff(self, other=diff.Diffable.Index, paths=None, create_patch=False, **kwargs):
+		"""Diff this index against the working copy or a Tree or Commit object
+
+		For a documentation of the parameters and return values, see
+		Diffable.diff
+
+		:note:
+			Will only work with indices that represent the default git index as
+			they have not been initialized with a stream.
+		"""
+		# index against index is always empty
+		if other is self.Index:
+			return diff.DiffIndex()
+
+		# index against anything but None is a reverse diff with the respective
+		# item. Handle existing -R flags properly. Transform strings to the object
+		# so that we can call diff on it
+		if isinstance(other, basestring):
+			other = self.repo.rev_parse(other)
+		# END object conversion
+
+		if isinstance(other, Object):
+			# invert the existing R flag
+			cur_val = kwargs.get('R', False)
+			kwargs['R'] = not cur_val
+			return other.diff(self.Index, paths, create_patch, **kwargs)
+		# END diff against other item handlin
+
+		# if other is not None here, something is wrong
+		if other is not None:
+			raise ValueError( "other must be None, Diffable.Index, a Tree or Commit, was %r" % other )
+
+		# diff against working copy - can be handled by superclass natively
+		return super(IndexFile, self).diff(other, paths, create_patch, **kwargs)
+
diff --git a/git/index/fun.py b/git/index/fun.py
new file mode 100644
index 00000000..9b35bf04
--- /dev/null
+++ b/git/index/fun.py
@@ -0,0 +1,322 @@
+# Contains standalone functions to accompany the index implementation and make it
+# more versatile
+# NOTE: Autodoc hates it if this is a docstring
+from stat import (
+					S_IFDIR,
+					S_IFLNK,
+					S_ISLNK,
+					S_IFDIR,
+					S_ISDIR,
+					S_IFMT,
+					S_IFREG,
+				)
+
+S_IFGITLINK = S_IFLNK | S_IFDIR		# a submodule
+
+from cStringIO import StringIO
+
+from git.util import IndexFileSHA1Writer
+from git.exc import UnmergedEntriesError
+from git.objects.fun import (
+								tree_to_stream,
+								traverse_tree_recursive,
+								traverse_trees_recursive
+							)
+
+from typ import (
+					BaseIndexEntry,
+					IndexEntry,
+					CE_NAMEMASK, 
+					CE_STAGESHIFT
+				)
+CE_NAMEMASK_INV = ~CE_NAMEMASK
+
+from util import 	(
+					pack, 
+					unpack
+					)
+
+from gitdb.base import IStream
+from gitdb.typ import str_tree_type
+
+__all__ = ('write_cache', 'read_cache', 'write_tree_from_cache', 'entry_key', 
+			'stat_mode_to_index_mode', 'S_IFGITLINK')
+
+
+def stat_mode_to_index_mode(mode):
+	"""Convert the given mode from a stat call to the corresponding index mode
+	and return it"""
+	if S_ISLNK(mode):	# symlinks
+		return S_IFLNK
+	if S_ISDIR(mode) or S_IFMT(mode) == S_IFGITLINK:	# submodules
+		return S_IFGITLINK
+	return S_IFREG | 0644 | (mode & 0100) 		# blobs with or without executable bit
+
+
+def write_cache(entries, stream, extension_data=None, ShaStreamCls=IndexFileSHA1Writer):
+	"""Write the cache represented by entries to a stream
+	
+	:param entries: **sorted** list of entries
+	:param stream: stream to wrap into the AdapterStreamCls - it is used for
+		final output.
+		
+	:param ShaStreamCls: Type to use when writing to the stream. It produces a sha
+		while writing to it, before the data is passed on to the wrapped stream
+		
+	:param extension_data: any kind of data to write as a trailer, it must begin
+		a 4 byte identifier, followed by its size ( 4 bytes )"""
+	# wrap the stream into a compatible writer
+	stream = ShaStreamCls(stream)
+	
+	tell = stream.tell
+	write = stream.write
+
+	# header
+	version = 2
+	write("DIRC")
+	write(pack(">LL", version, len(entries)))
+
+	# body
+	for entry in entries:
+		beginoffset = tell()
+		write(entry[4])			# ctime
+		write(entry[5])			# mtime
+		path = entry[3]
+		plen = len(path) & CE_NAMEMASK		# path length
+		assert plen == len(path), "Path %s too long to fit into index" % entry[3]
+		flags = plen | (entry[2] & CE_NAMEMASK_INV)		# clear possible previous values
+		write(pack(">LLLLLL20sH", entry[6], entry[7], entry[0],
+									entry[8], entry[9], entry[10], entry[1], flags))
+		write(path)
+		real_size = ((tell() - beginoffset + 8) & ~7)
+		write("\0" * ((beginoffset + real_size) - tell()))
+	# END for each entry
+
+	# write previously cached extensions data
+	if extension_data is not None:
+		stream.write(extension_data)
+
+	# write the sha over the content
+	stream.write_sha()
+	
+def read_header(stream):
+		"""Return tuple(version_long, num_entries) from the given stream"""
+		type_id = stream.read(4)
+		if type_id != "DIRC":
+			raise AssertionError("Invalid index file header: %r" % type_id)
+		version, num_entries = unpack(">LL", stream.read(4 * 2))
+		
+		# TODO: handle version 3: extended data, see read-cache.c
+		assert version in (1, 2)
+		return version, num_entries
+
+def entry_key(*entry):
+	""":return: Key suitable to be used for the index.entries dictionary
+	:param entry: One instance of type BaseIndexEntry or the path and the stage"""
+	if len(entry) == 1:
+		return (entry[0].path, entry[0].stage)
+	else:
+		return tuple(entry)
+	# END handle entry
+
+def read_cache(stream):
+	"""Read a cache file from the given stream
+	:return: tuple(version, entries_dict, extension_data, content_sha)
+		* version is the integer version number
+		* entries dict is a dictionary which maps IndexEntry instances to a path
+			at a stage
+		* extension_data is '' or 4 bytes of type + 4 bytes of size + size bytes
+		* content_sha is a 20 byte sha on all cache file contents"""
+	version, num_entries = read_header(stream)
+	count = 0
+	entries = dict()
+	
+	read = stream.read
+	tell = stream.tell
+	while count < num_entries:
+		beginoffset = tell()
+		ctime = unpack(">8s", read(8))[0]
+		mtime = unpack(">8s", read(8))[0]
+		(dev, ino, mode, uid, gid, size, sha, flags) = \
+			unpack(">LLLLLL20sH", read(20 + 4 * 6 + 2))
+		path_size = flags & CE_NAMEMASK
+		path = read(path_size)
+	
+		real_size = ((tell() - beginoffset + 8) & ~7)
+		data = read((beginoffset + real_size) - tell())
+		entry = IndexEntry((mode, sha, flags, path, ctime, mtime, dev, ino, uid, gid, size))
+		# entry_key would be the method to use, but we safe the effort
+		entries[(path, entry.stage)] = entry
+		count += 1
+	# END for each entry
+
+	# the footer contains extension data and a sha on the content so far
+	# Keep the extension footer,and verify we have a sha in the end
+	# Extension data format is:
+	# 4 bytes ID
+	# 4 bytes length of chunk
+	# repeated 0 - N times
+	extension_data = stream.read(~0)
+	assert len(extension_data) > 19, "Index Footer was not at least a sha on content as it was only %i bytes in size" % len(extension_data)
+
+	content_sha = extension_data[-20:]
+
+	# truncate the sha in the end as we will dynamically create it anyway
+	extension_data = extension_data[:-20]
+	
+	return (version, entries, extension_data, content_sha)
+	
+def write_tree_from_cache(entries, odb, sl, si=0):
+	"""Create a tree from the given sorted list of entries and put the respective
+	trees into the given object database
+	
+	:param entries: **sorted** list of IndexEntries
+	:param odb: object database to store the trees in
+	:param si: start index at which we should start creating subtrees
+	:param sl: slice indicating the range we should process on the entries list
+	:return: tuple(binsha, list(tree_entry, ...)) a tuple of a sha and a list of 
+		tree entries being a tuple of hexsha, mode, name"""
+	tree_items = list()
+	tree_items_append = tree_items.append
+	ci = sl.start
+	end = sl.stop
+	while ci < end:
+		entry = entries[ci]
+		if entry.stage != 0:
+			raise UnmergedEntriesError(entry)
+		# END abort on unmerged
+		ci += 1
+		rbound = entry.path.find('/', si)
+		if rbound == -1:
+			# its not a tree
+			tree_items_append((entry.binsha, entry.mode, entry.path[si:]))
+		else:
+			# find common base range
+			base = entry.path[si:rbound]
+			xi = ci
+			while xi < end:
+				oentry = entries[xi]
+				orbound = oentry.path.find('/', si)
+				if orbound == -1 or oentry.path[si:orbound] != base:
+					break
+				# END abort on base mismatch
+				xi += 1
+			# END find common base
+			
+			# enter recursion
+			# ci - 1 as we want to count our current item as well
+			sha, tree_entry_list = write_tree_from_cache(entries, odb, slice(ci-1, xi), rbound+1)
+			tree_items_append((sha, S_IFDIR, base))
+			
+			# skip ahead
+			ci = xi
+		# END handle bounds 
+	# END for each entry
+	
+	# finally create the tree
+	sio = StringIO()
+	tree_to_stream(tree_items, sio.write)
+	sio.seek(0)
+	
+	istream = odb.store(IStream(str_tree_type, len(sio.getvalue()), sio))
+	return (istream.binsha, tree_items)
+	
+def _tree_entry_to_baseindexentry(tree_entry, stage):
+	return BaseIndexEntry((tree_entry[1], tree_entry[0], stage <<CE_STAGESHIFT, tree_entry[2]))
+	
+def aggressive_tree_merge(odb, tree_shas):
+	"""
+	:return: list of BaseIndexEntries representing the aggressive merge of the given
+		trees. All valid entries are on stage 0, whereas the conflicting ones are left 
+		on stage 1, 2 or 3, whereas stage 1 corresponds to the common ancestor tree, 
+		2 to our tree and 3 to 'their' tree.
+	:param tree_shas: 1, 2 or 3 trees as identified by their binary 20 byte shas
+		If 1 or two, the entries will effectively correspond to the last given tree
+		If 3 are given, a 3 way merge is performed"""
+	out = list()
+	out_append = out.append
+	
+	# one and two way is the same for us, as we don't have to handle an existing
+	# index, instrea
+	if len(tree_shas) in (1,2):
+		for entry in traverse_tree_recursive(odb, tree_shas[-1], ''):
+			out_append(_tree_entry_to_baseindexentry(entry, 0))
+		# END for each entry
+		return out
+	# END handle single tree 
+	
+	if len(tree_shas) > 3:
+		raise ValueError("Cannot handle %i trees at once" % len(tree_shas))
+
+	# three trees
+	for base, ours, theirs in traverse_trees_recursive(odb, tree_shas, ''):
+		if base is not None:
+			# base version exists
+			if ours is not None:
+				# ours exists
+				if theirs is not None:
+					# it exists in all branches, if it was changed in both
+					# its a conflict, otherwise we take the changed version
+					# This should be the most common branch, so it comes first
+					if( base[0] != ours[0] and base[0] != theirs[0] and ours[0] != theirs[0] ) or \
+						( base[1] != ours[1] and base[1] != theirs[1] and ours[1] != theirs[1] ):
+						# changed by both
+						out_append(_tree_entry_to_baseindexentry(base, 1))
+						out_append(_tree_entry_to_baseindexentry(ours, 2))
+						out_append(_tree_entry_to_baseindexentry(theirs, 3))
+					elif base[0] != ours[0] or base[1] != ours[1]:
+						# only we changed it
+						out_append(_tree_entry_to_baseindexentry(ours, 0))
+					else:
+						# either nobody changed it, or they did. In either
+						# case, use theirs
+						out_append(_tree_entry_to_baseindexentry(theirs, 0))
+					# END handle modification 
+				else:
+					
+					if ours[0] != base[0] or ours[1] != base[1]:
+						# they deleted it, we changed it, conflict 
+						out_append(_tree_entry_to_baseindexentry(base, 1))
+						out_append(_tree_entry_to_baseindexentry(ours, 2))
+					# else:
+					#	we didn't change it, ignore
+					#	pass
+					# END handle our change
+				# END handle theirs
+			else:
+				if theirs is None:
+					# deleted in both, its fine - its out
+					pass
+				else:
+					if theirs[0] != base[0] or theirs[1] != base[1]:
+						# deleted in ours, changed theirs, conflict
+						out_append(_tree_entry_to_baseindexentry(base, 1))
+						out_append(_tree_entry_to_baseindexentry(theirs, 3))
+					# END theirs changed
+					#else:
+					# 	theirs didnt change
+					#	pass
+				# END handle theirs
+			# END handle ours
+		else:
+			# all three can't be None
+			if ours is None:
+				# added in their branch
+				out_append(_tree_entry_to_baseindexentry(theirs, 0))
+			elif theirs is None:
+				# added in our branch
+				out_append(_tree_entry_to_baseindexentry(ours, 0))
+			else:
+				# both have it, except for the base, see whether it changed
+				if ours[0] != theirs[0] or ours[1] != theirs[1]:
+					out_append(_tree_entry_to_baseindexentry(ours, 2))
+					out_append(_tree_entry_to_baseindexentry(theirs, 3))
+				else:
+					# it was added the same in both
+					out_append(_tree_entry_to_baseindexentry(ours, 0))
+				# END handle two items
+			# END handle heads
+		# END handle base exists
+	# END for each entries tuple
+
+	return out
diff --git a/git/index/typ.py b/git/index/typ.py
new file mode 100644
index 00000000..ad988285
--- /dev/null
+++ b/git/index/typ.py
@@ -0,0 +1,173 @@
+"""Module with additional types used by the index"""
+
+from util import (
+					pack, 
+					unpack
+				)
+
+from binascii import (
+						b2a_hex,
+					)
+
+from git.objects import Blob
+__all__ = ('BlobFilter', 'BaseIndexEntry', 'IndexEntry')
+
+#{ Invariants
+CE_NAMEMASK = 0x0fff
+CE_STAGEMASK = 0x3000
+CE_EXTENDED = 0x4000
+CE_VALID = 0x8000
+CE_STAGESHIFT = 12
+
+#} END invariants
+
+class BlobFilter(object):
+	"""
+	Predicate to be used by iter_blobs allowing to filter only return blobs which
+	match the given list of directories or files.
+
+	The given paths are given relative to the repository.
+	"""
+	__slots__ = 'paths'
+
+	def __init__(self, paths):
+		""":param paths:
+			tuple or list of paths which are either pointing to directories or
+			to files relative to the current repository
+		"""
+		self.paths = paths
+
+	def __call__(self, stage_blob):
+		path = stage_blob[1].path
+		for p in self.paths:
+			if path.startswith(p):
+				return True
+		# END for each path in filter paths
+		return False
+
+
+class BaseIndexEntry(tuple):
+	"""Small Brother of an index entry which can be created to describe changes
+	done to the index in which case plenty of additional information is not requried.
+
+	As the first 4 data members match exactly to the IndexEntry type, methods
+	expecting a BaseIndexEntry can also handle full IndexEntries even if they
+	use numeric indices for performance reasons. """
+
+	def __str__(self):
+		return "%o %s %i\t%s" % (self.mode, self.hexsha, self.stage, self.path)
+		
+	def __repr__(self):
+		return "(%o, %s, %i, %s)" % (self.mode, self.hexsha, self.stage, self.path)
+
+	@property
+	def mode(self):
+		""" File Mode, compatible to stat module constants """
+		return self[0]
+
+	@property
+	def binsha(self):
+		"""binary sha of the blob """
+		return self[1]
+		
+	@property
+	def hexsha(self):
+		"""hex version of our sha"""
+		return b2a_hex(self[1])
+
+	@property
+	def stage(self):
+		"""Stage of the entry, either:
+		
+			* 0 = default stage
+			* 1 = stage before a merge or common ancestor entry in case of a 3 way merge
+			* 2 = stage of entries from the 'left' side of the merge
+			* 3 = stage of entries from the right side of the merge
+		
+		:note: For more information, see http://www.kernel.org/pub/software/scm/git/docs/git-read-tree.html
+		"""
+		return (self[2] & CE_STAGEMASK) >> CE_STAGESHIFT
+
+	@property
+	def path(self):
+		""":return: our path relative to the repository working tree root"""
+		return self[3]
+
+	@property
+	def flags(self):
+		""":return: flags stored with this entry"""
+		return self[2]
+
+	@classmethod
+	def from_blob(cls, blob, stage = 0):
+		""":return: Fully equipped BaseIndexEntry at the given stage"""
+		return cls((blob.mode, blob.binsha, stage << CE_STAGESHIFT, blob.path))
+		
+	def to_blob(self, repo):
+		""":return: Blob using the information of this index entry"""
+		return Blob(repo, self.binsha, self.mode, self.path) 
+
+
+class IndexEntry(BaseIndexEntry):
+	"""Allows convenient access to IndexEntry data without completely unpacking it.
+
+	Attributes usully accessed often are cached in the tuple whereas others are
+	unpacked on demand.
+
+	See the properties for a mapping between names and tuple indices. """
+	@property
+	def ctime(self):
+		"""
+		:return:
+			Tuple(int_time_seconds_since_epoch, int_nano_seconds) of the
+			file's creation time"""
+		return unpack(">LL", self[4])
+
+	@property
+	def mtime(self):
+		"""See ctime property, but returns modification time """
+		return unpack(">LL", self[5])
+
+	@property
+	def dev(self):
+		""" Device ID """
+		return self[6]
+
+	@property
+	def inode(self):
+		""" Inode ID """
+		return self[7]
+
+	@property
+	def uid(self):
+		""" User ID """
+		return self[8]
+
+	@property
+	def gid(self):
+		""" Group ID """
+		return self[9]
+
+	@property
+	def size(self):
+		""":return: Uncompressed size of the blob """
+		return self[10]
+		
+	@classmethod
+	def from_base(cls, base):
+		""" 
+		:return:
+			Minimal entry as created from the given BaseIndexEntry instance.
+			Missing values will be set to null-like values
+
+		:param base: Instance of type BaseIndexEntry"""
+		time = pack(">LL", 0, 0)
+		return IndexEntry((base.mode, base.binsha, base.flags, base.path, time, time, 0, 0, 0, 0, 0))
+
+	@classmethod
+	def from_blob(cls, blob, stage = 0):
+		""":return: Minimal entry resembling the given blob object"""
+		time = pack(">LL", 0, 0)
+		return IndexEntry((blob.mode, blob.binsha, stage << CE_STAGESHIFT, blob.path, time, time, 0, 0, 0, 0, blob.size))
+
+
diff --git a/git/index/util.py b/git/index/util.py
new file mode 100644
index 00000000..bd5fcc03
--- /dev/null
+++ b/git/index/util.py
@@ -0,0 +1,86 @@
+"""Module containing index utilities"""
+import struct
+import tempfile
+import os
+
+__all__ = ( 'TemporaryFileSwap', 'post_clear_cache', 'default_index', 'git_working_dir' )
+
+#{ Aliases 
+pack = struct.pack
+unpack = struct.unpack
+
+
+#} END aliases
+
+class TemporaryFileSwap(object):
+	"""Utility class moving a file to a temporary location within the same directory
+	and moving it back on to where on object deletion."""
+	__slots__ = ("file_path", "tmp_file_path")
+
+	def __init__(self, file_path):
+		self.file_path = file_path
+		self.tmp_file_path = self.file_path + tempfile.mktemp('','','')
+		# it may be that the source does not exist
+		try:
+			os.rename(self.file_path, self.tmp_file_path)
+		except OSError:
+			pass
+
+	def __del__(self):
+		if os.path.isfile(self.tmp_file_path):
+			if os.name == 'nt' and os.path.exists(self.file_path):
+				os.remove(self.file_path)
+			os.rename(self.tmp_file_path, self.file_path)
+		# END temp file exists
+
+
+#{ Decorators 
+
+def post_clear_cache(func):
+	"""Decorator for functions that alter the index using the git command. This would
+	invalidate our possibly existing entries dictionary which is why it must be
+	deleted to allow it to be lazily reread later.
+
+	:note:
+		This decorator will not be required once all functions are implemented
+		natively which in fact is possible, but probably not feasible performance wise.
+	"""
+	def post_clear_cache_if_not_raised(self, *args, **kwargs):
+		rval = func(self, *args, **kwargs)
+		self._delete_entries_cache()
+		return rval
+
+	# END wrapper method
+	post_clear_cache_if_not_raised.__name__ = func.__name__
+	return post_clear_cache_if_not_raised
+
+def default_index(func):
+	"""Decorator assuring the wrapped method may only run if we are the default
+	repository index. This is as we rely on git commands that operate
+	on that index only. """
+	def check_default_index(self, *args, **kwargs):
+		if self._file_path != self._index_path():
+			raise AssertionError( "Cannot call %r on indices that do not represent the default git index" % func.__name__ )
+		return func(self, *args, **kwargs)
+	# END wrpaper method
+
+	check_default_index.__name__ = func.__name__
+	return check_default_index
+
+def git_working_dir(func):
+	"""Decorator which changes the current working dir to the one of the git 
+	repository in order to assure relative paths are handled correctly"""
+	def set_git_working_dir(self, *args, **kwargs):
+		cur_wd = os.getcwd()
+		os.chdir(self.repo.working_tree_dir)
+		try:
+			return func(self, *args, **kwargs)
+		finally:
+			os.chdir(cur_wd)
+		# END handle working dir
+	# END wrapper
+	
+	set_git_working_dir.__name__ = func.__name__
+	return set_git_working_dir
+
+#} END decorators