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 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 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 read_entry(stream):
"""Return: One entry of the given stream"""
beginoffset = stream.tell()
read = stream.read
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 = ((stream.tell() - beginoffset + 8) & ~7)
data = read((beginoffset + real_size) - stream.tell())
return IndexEntry(
(mode, sha, flags, path, ctime, mtime, dev, ino, uid, gid, size))
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
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
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-disk.
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 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
