diff --git a/dulwich/index.py b/dulwich/index.py index 3223b46d..4b464bde 100644 --- a/dulwich/index.py +++ b/dulwich/index.py @@ -1,982 +1,990 @@ # index.py -- File parser/writer for the git index file # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Parser for the git index file format.""" import collections import os import stat import struct import sys from typing import ( Any, BinaryIO, Callable, Dict, List, Optional, TYPE_CHECKING, Iterable, Iterator, Tuple, ) if TYPE_CHECKING: from dulwich.object_store import BaseObjectStore from dulwich.file import GitFile from dulwich.objects import ( Blob, S_IFGITLINK, S_ISGITLINK, Tree, hex_to_sha, sha_to_hex, ) from dulwich.pack import ( SHA1Reader, SHA1Writer, ) # TODO(jelmer): Switch to dataclass? IndexEntry = collections.namedtuple( "IndexEntry", [ "ctime", "mtime", "dev", "ino", "mode", "uid", "gid", "size", "sha", "flags", "extended_flags", ], ) # 2-bit stage (during merge) FLAG_STAGEMASK = 0x3000 # assume-valid FLAG_VALID = 0x8000 # extended flag (must be zero in version 2) FLAG_EXTENDED = 0x4000 # used by sparse checkout EXTENDED_FLAG_SKIP_WORKTREE = 0x4000 # used by "git add -N" EXTENDED_FLAG_INTEND_TO_ADD = 0x2000 DEFAULT_VERSION = 2 def pathsplit(path): """Split a /-delimited path into a directory part and a basename. Args: path: The path to split. Returns: Tuple with directory name and basename """ try: (dirname, basename) = path.rsplit(b"/", 1) except ValueError: return (b"", path) else: return (dirname, basename) def pathjoin(*args): """Join a /-delimited path.""" return b"/".join([p for p in args if p]) def read_cache_time(f): """Read a cache time. Args: f: File-like object to read from Returns: Tuple with seconds and nanoseconds """ return struct.unpack(">LL", f.read(8)) def write_cache_time(f, t): """Write a cache time. Args: f: File-like object to write to t: Time to write (as int, float or tuple with secs and nsecs) """ if isinstance(t, int): t = (t, 0) elif isinstance(t, float): (secs, nsecs) = divmod(t, 1.0) t = (int(secs), int(nsecs * 1000000000)) elif not isinstance(t, tuple): raise TypeError(t) f.write(struct.pack(">LL", *t)) def read_cache_entry(f, version: int) -> Tuple[str, IndexEntry]: """Read an entry from a cache file. Args: f: File-like object to read from Returns: tuple with: name, IndexEntry """ beginoffset = f.tell() ctime = read_cache_time(f) mtime = read_cache_time(f) ( dev, ino, mode, uid, gid, size, sha, flags, ) = struct.unpack(">LLLLLL20sH", f.read(20 + 4 * 6 + 2)) if flags & FLAG_EXTENDED: if version < 3: raise AssertionError( 'extended flag set in index with version < 3') extended_flags = struct.unpack(">H", f.read(2)) else: extended_flags = 0 name = f.read((flags & 0x0FFF)) # Padding: real_size = (f.tell() - beginoffset + 8) & ~7 f.read((beginoffset + real_size) - f.tell()) return ( name, IndexEntry( ctime, mtime, dev, ino, mode, uid, gid, size, sha_to_hex(sha), flags & ~0x0FFF, extended_flags, )) def write_cache_entry(f, name, entry, version=None): """Write an index entry to a file. Args: f: File object entry: IndexEntry to write, tuple with: """ beginoffset = f.tell() write_cache_time(f, entry.ctime) write_cache_time(f, entry.mtime) flags = len(name) | (entry.flags & ~0x0FFF) if entry.extended_flags: flags |= FLAG_EXTENDED if flags & FLAG_EXTENDED and version is not None and version < 3: raise AssertionError('unable to use extended flags in version < 3') f.write( struct.pack( b">LLLLLL20sH", entry.dev & 0xFFFFFFFF, entry.ino & 0xFFFFFFFF, entry.mode, entry.uid, entry.gid, entry.size, hex_to_sha(entry.sha), flags, ) ) if flags & FLAG_EXTENDED: f.write(struct.pack(b">H", entry.extended_flags)) f.write(name) real_size = (f.tell() - beginoffset + 8) & ~7 f.write(b"\0" * ((beginoffset + real_size) - f.tell())) def read_index(f: BinaryIO): """Read an index file, yielding the individual entries.""" header = f.read(4) if header != b"DIRC": raise AssertionError("Invalid index file header: %r" % header) (version, num_entries) = struct.unpack(b">LL", f.read(4 * 2)) assert version in (1, 2, 3), "index version is %r" % version for i in range(num_entries): yield read_cache_entry(f, version) def read_index_dict(f): """Read an index file and return it as a dictionary. Args: f: File object to read from """ ret = {} for name, entry in read_index(f): ret[name] = entry return ret def write_index(f: BinaryIO, entries: Iterable[Tuple[bytes, IndexEntry]], version: Optional[int] = None): """Write an index file. Args: f: File-like object to write to version: Version number to write entries: Iterable over the entries to write """ if version is None: version = DEFAULT_VERSION f.write(b"DIRC") f.write(struct.pack(b">LL", version, len(entries))) for name, entry in entries: write_cache_entry(f, name, entry, version) def write_index_dict( f: BinaryIO, entries: Dict[bytes, IndexEntry], version: Optional[int] = None, ) -> None: """Write an index file based on the contents of a dictionary.""" entries_list = [] for name in sorted(entries): entries_list.append((name, entries[name])) write_index(f, entries_list, version=version) def cleanup_mode(mode: int) -> int: """Cleanup a mode value. This will return a mode that can be stored in a tree object. Args: mode: Mode to clean up. Returns: mode """ if stat.S_ISLNK(mode): return stat.S_IFLNK elif stat.S_ISDIR(mode): return stat.S_IFDIR elif S_ISGITLINK(mode): return S_IFGITLINK ret = stat.S_IFREG | 0o644 if mode & 0o100: ret |= 0o111 return ret class Index(object): """A Git Index file.""" def __init__(self, filename): """Open an index file. Args: filename: Path to the index file """ self._filename = filename # TODO(jelmer): Store the version returned by read_index self._version = None self.clear() self.read() @property def path(self): return self._filename def __repr__(self): return "%s(%r)" % (self.__class__.__name__, self._filename) def write(self) -> None: """Write current contents of index to disk.""" f = GitFile(self._filename, "wb") try: f = SHA1Writer(f) write_index_dict(f, self._byname, version=self._version) finally: f.close() def read(self): """Read current contents of index from disk.""" if not os.path.exists(self._filename): return f = GitFile(self._filename, "rb") try: f = SHA1Reader(f) for name, entry in read_index(f): self[name] = entry # FIXME: Additional data? f.read(os.path.getsize(self._filename) - f.tell() - 20) f.check_sha() finally: f.close() def __len__(self) -> int: """Number of entries in this index file.""" return len(self._byname) def __getitem__(self, name: bytes) -> IndexEntry: """Retrieve entry by relative path. Returns: tuple with (ctime, mtime, dev, ino, mode, uid, gid, size, sha, flags) """ return self._byname[name] def __iter__(self) -> Iterator[bytes]: """Iterate over the paths in this index.""" return iter(self._byname) def get_sha1(self, path: bytes) -> bytes: """Return the (git object) SHA1 for the object at a path.""" return self[path].sha def get_mode(self, path: bytes) -> int: """Return the POSIX file mode for the object at a path.""" return self[path].mode def iterobjects(self) -> Iterable[Tuple[bytes, bytes, int]]: """Iterate over path, sha, mode tuples for use with commit_tree.""" for path in self: entry = self[path] yield path, entry.sha, cleanup_mode(entry.mode) def iterblobs(self): import warnings warnings.warn("Use iterobjects() instead.", PendingDeprecationWarning) return self.iterobjects() def clear(self): """Remove all contents from this index.""" self._byname = {} def __setitem__(self, name, x): assert isinstance(name, bytes) assert len(x) == len(IndexEntry._fields) # Remove the old entry if any self._byname[name] = IndexEntry(*x) def __delitem__(self, name): assert isinstance(name, bytes) del self._byname[name] def iteritems(self): return self._byname.items() def items(self): return self._byname.items() def update(self, entries): for name, value in entries.items(): self[name] = value def changes_from_tree(self, object_store, tree, want_unchanged=False): """Find the differences between the contents of this index and a tree. Args: object_store: Object store to use for retrieving tree contents tree: SHA1 of the root tree want_unchanged: Whether unchanged files should be reported Returns: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ def lookup_entry(path): entry = self[path] return entry.sha, cleanup_mode(entry.mode) for (name, mode, sha) in changes_from_tree( self._byname.keys(), lookup_entry, object_store, tree, want_unchanged=want_unchanged, ): yield (name, mode, sha) def commit(self, object_store): """Create a new tree from an index. Args: object_store: Object store to save the tree in Returns: Root tree SHA """ return commit_tree(object_store, self.iterobjects()) def commit_tree( object_store: "BaseObjectStore", blobs: Iterable[Tuple[bytes, bytes, int]] ) -> bytes: """Commit a new tree. Args: object_store: Object store to add trees to blobs: Iterable over blob path, sha, mode entries Returns: SHA1 of the created tree. """ trees = {b"": {}} # type: Dict[bytes, Any] def add_tree(path): if path in trees: return trees[path] dirname, basename = pathsplit(path) t = add_tree(dirname) assert isinstance(basename, bytes) newtree = {} t[basename] = newtree trees[path] = newtree return newtree for path, sha, mode in blobs: tree_path, basename = pathsplit(path) tree = add_tree(tree_path) tree[basename] = (mode, sha) def build_tree(path): tree = Tree() for basename, entry in trees[path].items(): if isinstance(entry, dict): mode = stat.S_IFDIR sha = build_tree(pathjoin(path, basename)) else: (mode, sha) = entry tree.add(basename, mode, sha) object_store.add_object(tree) return tree.id return build_tree(b"") def commit_index(object_store: "BaseObjectStore", index: Index) -> bytes: """Create a new tree from an index. Args: object_store: Object store to save the tree in index: Index file Note: This function is deprecated, use index.commit() instead. Returns: Root tree sha. """ return commit_tree(object_store, index.iterobjects()) def changes_from_tree( names: Iterable[bytes], lookup_entry: Callable[[bytes], Tuple[bytes, int]], object_store: "BaseObjectStore", tree: Optional[bytes], want_unchanged=False, ) -> Iterable[ Tuple[ Tuple[Optional[bytes], Optional[bytes]], Tuple[Optional[int], Optional[int]], Tuple[Optional[bytes], Optional[bytes]], ] ]: """Find the differences between the contents of a tree and a working copy. Args: names: Iterable of names in the working copy lookup_entry: Function to lookup an entry in the working copy object_store: Object store to use for retrieving tree contents tree: SHA1 of the root tree, or None for an empty tree want_unchanged: Whether unchanged files should be reported Returns: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ # TODO(jelmer): Support a include_trees option other_names = set(names) if tree is not None: for (name, mode, sha) in object_store.iter_tree_contents(tree): try: (other_sha, other_mode) = lookup_entry(name) except KeyError: # Was removed yield ((name, None), (mode, None), (sha, None)) else: other_names.remove(name) if want_unchanged or other_sha != sha or other_mode != mode: yield ((name, name), (mode, other_mode), (sha, other_sha)) # Mention added files for name in other_names: try: (other_sha, other_mode) = lookup_entry(name) except KeyError: pass else: yield ((None, name), (None, other_mode), (None, other_sha)) def index_entry_from_stat( stat_val, hex_sha: bytes, flags: int, mode: Optional[int] = None, extended_flags: Optional[int] =None ): """Create a new index entry from a stat value. Args: stat_val: POSIX stat_result instance hex_sha: Hex sha of the object flags: Index flags """ if mode is None: mode = cleanup_mode(stat_val.st_mode) return IndexEntry( stat_val.st_ctime, stat_val.st_mtime, stat_val.st_dev, stat_val.st_ino, mode, stat_val.st_uid, stat_val.st_gid, stat_val.st_size, hex_sha, flags, extended_flags ) def build_file_from_blob( blob, mode, target_path, honor_filemode=True, tree_encoding="utf-8" ): """Build a file or symlink on disk based on a Git object. Args: obj: The git object mode: File mode target_path: Path to write to honor_filemode: An optional flag to honor core.filemode setting in config file, default is core.filemode=True, change executable bit Returns: stat object for the file """ try: oldstat = os.lstat(target_path) except FileNotFoundError: oldstat = None contents = blob.as_raw_string() if stat.S_ISLNK(mode): # FIXME: This will fail on Windows. What should we do instead? if oldstat: os.unlink(target_path) if sys.platform == "win32": # os.readlink on Python3 on Windows requires a unicode string. contents = contents.decode(tree_encoding) target_path = target_path.decode(tree_encoding) os.symlink(contents, target_path) else: if oldstat is not None and oldstat.st_size == len(contents): with open(target_path, "rb") as f: if f.read() == contents: return oldstat with open(target_path, "wb") as f: # Write out file f.write(contents) if honor_filemode: os.chmod(target_path, mode) return os.lstat(target_path) INVALID_DOTNAMES = (b".git", b".", b"..", b"") def validate_path_element_default(element): return element.lower() not in INVALID_DOTNAMES def validate_path_element_ntfs(element): stripped = element.rstrip(b". ").lower() if stripped in INVALID_DOTNAMES: return False if stripped == b"git~1": return False return True def validate_path(path, element_validator=validate_path_element_default): """Default path validator that just checks for .git/.""" parts = path.split(b"/") for p in parts: if not element_validator(p): return False else: return True def build_index_from_tree( root_path, index_path, object_store, tree_id, honor_filemode=True, validate_path_element=validate_path_element_default, ): """Generate and materialize index from a tree Args: tree_id: Tree to materialize root_path: Target dir for materialized index files index_path: Target path for generated index object_store: Non-empty object store holding tree contents honor_filemode: An optional flag to honor core.filemode setting in config file, default is core.filemode=True, change executable bit validate_path_element: Function to validate path elements to check out; default just refuses .git and .. directories. Note: existing index is wiped and contents are not merged in a working dir. Suitable only for fresh clones. """ index = Index(index_path) if not isinstance(root_path, bytes): root_path = os.fsencode(root_path) for entry in object_store.iter_tree_contents(tree_id): if not validate_path(entry.path, validate_path_element): continue full_path = _tree_to_fs_path(root_path, entry.path) if not os.path.exists(os.path.dirname(full_path)): os.makedirs(os.path.dirname(full_path)) # TODO(jelmer): Merge new index into working tree if S_ISGITLINK(entry.mode): if not os.path.isdir(full_path): os.mkdir(full_path) st = os.lstat(full_path) # TODO(jelmer): record and return submodule paths else: obj = object_store[entry.sha] st = build_file_from_blob( obj, entry.mode, full_path, honor_filemode=honor_filemode ) # Add file to index if not honor_filemode or S_ISGITLINK(entry.mode): # we can not use tuple slicing to build a new tuple, # because on windows that will convert the times to # longs, which causes errors further along st_tuple = ( entry.mode, st.st_ino, st.st_dev, st.st_nlink, st.st_uid, st.st_gid, st.st_size, st.st_atime, st.st_mtime, st.st_ctime, ) st = st.__class__(st_tuple) index[entry.path] = index_entry_from_stat(st, entry.sha, 0) index.write() def blob_from_path_and_mode(fs_path, mode, tree_encoding="utf-8"): """Create a blob from a path and a stat object. Args: fs_path: Full file system path to file st: A stat object Returns: A `Blob` object """ assert isinstance(fs_path, bytes) blob = Blob() if stat.S_ISLNK(mode): if sys.platform == "win32": # os.readlink on Python3 on Windows requires a unicode string. fs_path = os.fsdecode(fs_path) blob.data = os.readlink(fs_path).encode(tree_encoding) else: blob.data = os.readlink(fs_path) else: with open(fs_path, "rb") as f: blob.data = f.read() return blob def blob_from_path_and_stat(fs_path, st, tree_encoding="utf-8"): """Create a blob from a path and a stat object. Args: fs_path: Full file system path to file st: A stat object Returns: A `Blob` object """ return blob_from_path_and_mode(fs_path, st.st_mode, tree_encoding) def read_submodule_head(path): """Read the head commit of a submodule. Args: path: path to the submodule Returns: HEAD sha, None if not a valid head/repository """ from dulwich.errors import NotGitRepository from dulwich.repo import Repo # Repo currently expects a "str", so decode if necessary. # TODO(jelmer): Perhaps move this into Repo() ? if not isinstance(path, str): path = os.fsdecode(path) try: repo = Repo(path) except NotGitRepository: return None try: return repo.head() except KeyError: return None def _has_directory_changed(tree_path, entry): """Check if a directory has changed after getting an error. When handling an error trying to create a blob from a path, call this function. It will check if the path is a directory. If it's a directory and a submodule, check the submodule head to see if it's has changed. If not, consider the file as changed as Git tracked a file and not a directory. Return true if the given path should be considered as changed and False otherwise or if the path is not a directory. """ # This is actually a directory if os.path.exists(os.path.join(tree_path, b".git")): # Submodule head = read_submodule_head(tree_path) if entry.sha != head: return True else: # The file was changed to a directory, so consider it removed. return True return False -def get_unstaged_changes(index: Index, root_path, filter_blob_callback=None): +def get_unstaged_changes(index: Index, repo, filter_blob_callback=None): """Walk through an index and check for differences against working tree. Args: index: index to check root_path: path in which to find files Returns: iterator over paths with unstaged changes """ + root_path = repo.path # For each entry in the index check the sha1 & ensure not staged if not isinstance(root_path, bytes): root_path = os.fsencode(root_path) for tree_path, entry in index.iteritems(): full_path = _tree_to_fs_path(root_path, tree_path) try: st = os.lstat(full_path) if stat.S_ISDIR(st.st_mode): if _has_directory_changed(tree_path, entry): yield tree_path continue if not stat.S_ISREG(st.st_mode) and not stat.S_ISLNK(st.st_mode): continue blob = blob_from_path_and_stat(full_path, st) if filter_blob_callback is not None: - blob = filter_blob_callback(blob, tree_path) + # Check if the file is already in the index + try: + index[tree_path] + new_file = False + except KeyError: + new_file = True + + blob = filter_blob_callback(blob, tree_path, new_file) except FileNotFoundError: # The file was removed, so we assume that counts as # different from whatever file used to exist. yield tree_path else: if blob.id != entry.sha: yield tree_path os_sep_bytes = os.sep.encode("ascii") def _tree_to_fs_path(root_path, tree_path: bytes): """Convert a git tree path to a file system path. Args: root_path: Root filesystem path tree_path: Git tree path as bytes Returns: File system path. """ assert isinstance(tree_path, bytes) if os_sep_bytes != b"/": sep_corrected_path = tree_path.replace(b"/", os_sep_bytes) else: sep_corrected_path = tree_path return os.path.join(root_path, sep_corrected_path) def _fs_to_tree_path(fs_path): """Convert a file system path to a git tree path. Args: fs_path: File system path. Returns: Git tree path as bytes """ if not isinstance(fs_path, bytes): fs_path_bytes = os.fsencode(fs_path) else: fs_path_bytes = fs_path if os_sep_bytes != b"/": tree_path = fs_path_bytes.replace(os_sep_bytes, b"/") else: tree_path = fs_path_bytes return tree_path def index_entry_from_path(path, object_store=None): """Create an index from a filesystem path. This returns an index value for files, symlinks and tree references. for directories and non-existant files it returns None Args: path: Path to create an index entry for object_store: Optional object store to save new blobs in Returns: An index entry; None for directories """ assert isinstance(path, bytes) st = os.lstat(path) if stat.S_ISDIR(st.st_mode): if os.path.exists(os.path.join(path, b".git")): head = read_submodule_head(path) if head is None: return None return index_entry_from_stat(st, head, 0, mode=S_IFGITLINK) return None if stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode): blob = blob_from_path_and_stat(path, st) if object_store is not None: object_store.add_object(blob) return index_entry_from_stat(st, blob.id, 0) return None def iter_fresh_entries( paths, root_path, object_store: Optional["BaseObjectStore"] = None ): """Iterate over current versions of index entries on disk. Args: paths: Paths to iterate over root_path: Root path to access from store: Optional store to save new blobs in Returns: Iterator over path, index_entry """ for path in paths: p = _tree_to_fs_path(root_path, path) try: entry = index_entry_from_path(p, object_store=object_store) except (FileNotFoundError, IsADirectoryError): entry = None yield path, entry def iter_fresh_blobs(index, root_path): """Iterate over versions of blobs on disk referenced by index. Don't use this function; it removes missing entries from index. Args: index: Index file root_path: Root path to access from include_deleted: Include deleted entries with sha and mode set to None Returns: Iterator over path, sha, mode """ import warnings warnings.warn(PendingDeprecationWarning, "Use iter_fresh_objects instead.") for entry in iter_fresh_objects(index, root_path, include_deleted=True): if entry[1] is None: del index[entry[0]] else: yield entry def iter_fresh_objects(paths, root_path, include_deleted=False, object_store=None): """Iterate over versions of objecs on disk referenced by index. Args: root_path: Root path to access from include_deleted: Include deleted entries with sha and mode set to None object_store: Optional object store to report new items to Returns: Iterator over path, sha, mode """ for path, entry in iter_fresh_entries(paths, root_path, object_store=object_store): if entry is None: if include_deleted: yield path, None, None else: entry = IndexEntry(*entry) yield path, entry.sha, cleanup_mode(entry.mode) def refresh_index(index, root_path): """Refresh the contents of an index. This is the equivalent to running 'git commit -a'. Args: index: Index to update root_path: Root filesystem path """ for path, entry in iter_fresh_entries(index, root_path): index[path] = path diff --git a/dulwich/line_ending.py b/dulwich/line_ending.py index 1d9e40d8..6f149a20 100644 --- a/dulwich/line_ending.py +++ b/dulwich/line_ending.py @@ -1,274 +1,293 @@ # line_ending.py -- Line ending conversion functions # Copyright (C) 2018-2018 Boris Feld # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """ All line-ending related functions, from conversions to config processing Line-ending normalization is a complex beast. Here is some notes and details about how it seems to work. The normalization is a two-fold process that happens at two moments: - When reading a file from the index and to the working directory. For example when doing a `git clone` or `git checkout` call. We call this process the read filter in this module. - When writing a file to the index from the working directory. For example when doing a `git add` call. We call this process the write filter in this module. +The normalization only happens when the resulting file does not exists yet. +For the write filter, they are files that are shown as added in status. + One thing to know is that Git does line-ending normalization only on text files. How does Git know that a file is text? We can either mark a file as a text file, a binary file or ask Git to automatically decides. Git has an heuristic to detect if a file is a text file or a binary file. It seems based on the percentage of non-printable characters in files. The code for this heuristic is here: https://git.kernel.org/pub/scm/git/git.git/tree/convert.c#n46 Dulwich have an implementation with a slightly different heuristic, the `is_binary` function in `dulwich.patch`. The binary detection heuristic implementation is close to the one in JGit: https://github.com/eclipse/jgit/blob/f6873ffe522bbc3536969a3a3546bf9a819b92bf/org.eclipse.jgit/src/org/eclipse/jgit/diff/RawText.java#L300 There is multiple variables that impact the normalization. First, a repository can contains a `.gitattributes` file (or more than one...) that can further customize the operation on some file patterns, for example: *.txt text Force all `.txt` files to be treated as text files and to have their lines endings normalized. *.jpg -text Force all `.jpg` files to be treated as binary files and to not have their lines endings converted. *.vcproj text eol=crlf Force all `.vcproj` files to be treated as text files and to have their lines endings converted into `CRLF` in working directory no matter the native EOL of the platform. *.sh text eol=lf Force all `.sh` files to be treated as text files and to have their lines endings converted into `LF` in working directory no matter the native EOL of the platform. If the `eol` attribute is not defined, Git uses the `core.eol` configuration value described later. * text=auto Force all files to be scanned by the text file heuristic detection and to have their line endings normalized in case they are detected as text files. Git also have a obsolete attribute named `crlf` that can be translated to the corresponding text attribute value. Then there are some configuration option (that can be defined at the repository or user level): - core.autocrlf - core.eol `core.autocrlf` is taken into account for all files that doesn't have a `text` attribute defined in `.gitattributes`; it takes three possible values: - `true`: This forces all files on the working directory to have CRLF line-endings in the working directory and convert line-endings to LF when writing to the index. When autocrlf is set to true, eol value is ignored. - `input`: Quite similar to the `true` value but only force the write filter, ie line-ending of new files added to the index will get their line-endings converted to LF. - `false` (default): No normalization is done. `core.eol` is the top-level configuration to define the line-ending to use when applying the read_filer. It takes three possible values: - `lf`: When normalization is done, force line-endings to be `LF` in the working directory. - `crlf`: When normalization is done, force line-endings to be `CRLF` in the working directory. - `native` (default): When normalization is done, force line-endings to be the platform's native line ending. One thing to remember is when line-ending normalization is done on a file, Git always normalize line-ending to `LF` when writing to the index. There are sources that seems to indicate that Git won't do line-ending normalization when a file contains mixed line-endings. I think this logic might be in text / binary detection heuristic but couldn't find it yet. Sources: - https://git-scm.com/docs/git-config#git-config-coreeol - https://git-scm.com/docs/git-config#git-config-coreautocrlf - https://git-scm.com/docs/gitattributes#_checking_out_and_checking_in - https://adaptivepatchwork.com/2012/03/01/mind-the-end-of-your-line/ """ from dulwich.objects import Blob from dulwich.patch import is_binary CRLF = b"\r\n" LF = b"\n" def convert_crlf_to_lf(text_hunk): """Convert CRLF in text hunk into LF Args: text_hunk: A bytes string representing a text hunk Returns: The text hunk with the same type, with CRLF replaced into LF """ return text_hunk.replace(CRLF, LF) def convert_lf_to_crlf(text_hunk): """Convert LF in text hunk into CRLF Args: text_hunk: A bytes string representing a text hunk Returns: The text hunk with the same type, with LF replaced into CRLF """ # TODO find a more efficient way of doing it intermediary = text_hunk.replace(CRLF, LF) return intermediary.replace(LF, CRLF) def get_checkout_filter(core_eol, core_autocrlf, git_attributes): """Returns the correct checkout filter based on the passed arguments""" # TODO this function should process the git_attributes for the path and if # the text attribute is not defined, fallback on the # get_checkout_filter_autocrlf function with the autocrlf value return get_checkout_filter_autocrlf(core_autocrlf) def get_checkin_filter(core_eol, core_autocrlf, git_attributes): """Returns the correct checkin filter based on the passed arguments""" # TODO this function should process the git_attributes for the path and if # the text attribute is not defined, fallback on the # get_checkin_filter_autocrlf function with the autocrlf value return get_checkin_filter_autocrlf(core_autocrlf) def get_checkout_filter_autocrlf(core_autocrlf): """Returns the correct checkout filter base on autocrlf value Args: core_autocrlf: The bytes configuration value of core.autocrlf. Valid values are: b'true', b'false' or b'input'. Returns: Either None if no filter has to be applied or a function accepting a single argument, a binary text hunk """ if core_autocrlf == b"true": return convert_lf_to_crlf return None def get_checkin_filter_autocrlf(core_autocrlf): """Returns the correct checkin filter base on autocrlf value Args: core_autocrlf: The bytes configuration value of core.autocrlf. Valid values are: b'true', b'false' or b'input'. Returns: Either None if no filter has to be applied or a function accepting a single argument, a binary text hunk """ if core_autocrlf == b"true" or core_autocrlf == b"input": return convert_crlf_to_lf # Checking filter should never be `convert_lf_to_crlf` return None class BlobNormalizer(object): """An object to store computation result of which filter to apply based on configuration, gitattributes, path and operation (checkin or checkout) """ def __init__(self, config_stack, gitattributes): self.config_stack = config_stack self.gitattributes = gitattributes # Compute which filters we needs based on parameters try: core_eol = config_stack.get("core", "eol") except KeyError: core_eol = "native" try: core_autocrlf = config_stack.get("core", "autocrlf").lower() except KeyError: core_autocrlf = False self.fallback_read_filter = get_checkout_filter( core_eol, core_autocrlf, self.gitattributes ) self.fallback_write_filter = get_checkin_filter( core_eol, core_autocrlf, self.gitattributes ) - def checkin_normalize(self, blob, tree_path): - """Normalize a blob during a checkin operation""" + def checkin_normalize(self, blob, tree_path, new_file=True): + """ Normalize a blob during a checkin operation + + new_file is set to True by default for backward-compatibility + """ + if not new_file: + # Line-ending normalization only happens for new files, aka files + # not already commited + return blob + if self.fallback_write_filter is not None: return normalize_blob( blob, self.fallback_write_filter, binary_detection=True ) return blob - def checkout_normalize(self, blob, tree_path): - """Normalize a blob during a checkout operation""" + def checkout_normalize(self, blob, tree_path, new_file=True): + """ Normalize a blob during a checkout operation + + new_file is set to True by default for backward-compatibility + """ + if not new_file: + # Line-ending normalization only happens for new files, aka files + # not already commited + return blob + if self.fallback_read_filter is not None: return normalize_blob( blob, self.fallback_read_filter, binary_detection=True ) return blob def normalize_blob(blob, conversion, binary_detection): """Takes a blob as input returns either the original blob if binary_detection is True and the blob content looks like binary, else return a new blob with converted data """ # Read the original blob data = blob.data # If we need to detect if a file is binary and the file is detected as # binary, do not apply the conversion function and return the original # chunked text if binary_detection is True: if is_binary(data): return blob # Now apply the conversion converted_data = conversion(data) new_blob = Blob() new_blob.data = converted_data return new_blob diff --git a/dulwich/porcelain.py b/dulwich/porcelain.py index ea1722ed..0209c88c 100644 --- a/dulwich/porcelain.py +++ b/dulwich/porcelain.py @@ -1,1924 +1,1924 @@ # porcelain.py -- Porcelain-like layer on top of Dulwich # Copyright (C) 2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Simple wrapper that provides porcelain-like functions on top of Dulwich. Currently implemented: * archive * add * branch{_create,_delete,_list} * check-ignore * checkout * clone * commit * commit-tree * daemon * describe * diff-tree * fetch * init * ls-files * ls-remote * ls-tree * pull * push * rm * remote{_add} * receive-pack * reset * rev-list * tag{_create,_delete,_list} * upload-pack * update-server-info * status * symbolic-ref These functions are meant to behave similarly to the git subcommands. Differences in behaviour are considered bugs. Functions should generally accept both unicode strings and bytestrings """ from collections import namedtuple from contextlib import ( closing, contextmanager, ) from io import BytesIO, RawIOBase import datetime import os from pathlib import Path import posixpath import shutil import stat import sys import time from typing import ( Dict, Optional, Tuple, Union, ) from dulwich.archive import ( tar_stream, ) from dulwich.client import ( get_transport_and_path, ) from dulwich.config import ( StackedConfig, ) from dulwich.diff_tree import ( CHANGE_ADD, CHANGE_DELETE, CHANGE_MODIFY, CHANGE_RENAME, CHANGE_COPY, RENAME_CHANGE_TYPES, ) from dulwich.errors import ( SendPackError, ) from dulwich.graph import ( can_fast_forward, ) from dulwich.ignore import IgnoreFilterManager from dulwich.index import ( blob_from_path_and_stat, get_unstaged_changes, ) from dulwich.object_store import ( tree_lookup_path, ) from dulwich.objects import ( Commit, Tag, format_timezone, parse_timezone, pretty_format_tree_entry, ) from dulwich.objectspec import ( parse_commit, parse_object, parse_ref, parse_reftuples, parse_tree, ) from dulwich.pack import ( write_pack_index, write_pack_objects, ) from dulwich.patch import write_tree_diff from dulwich.protocol import ( Protocol, ZERO_SHA, ) from dulwich.refs import ( ANNOTATED_TAG_SUFFIX, LOCAL_BRANCH_PREFIX, strip_peeled_refs, RefsContainer, ) from dulwich.repo import BaseRepo, Repo from dulwich.server import ( FileSystemBackend, TCPGitServer, ReceivePackHandler, UploadPackHandler, update_server_info as server_update_server_info, ) # Module level tuple definition for status output GitStatus = namedtuple("GitStatus", "staged unstaged untracked") class NoneStream(RawIOBase): """Fallback if stdout or stderr are unavailable, does nothing.""" def read(self, size=-1): return None def readall(self): return None def readinto(self, b): return None def write(self, b): return None default_bytes_out_stream = getattr(sys.stdout, "buffer", None) or NoneStream() default_bytes_err_stream = getattr(sys.stderr, "buffer", None) or NoneStream() DEFAULT_ENCODING = "utf-8" class Error(Exception): """Porcelain-based error. """ def __init__(self, msg, inner=None): super(Error, self).__init__(msg) self.inner = inner class RemoteExists(Error): """Raised when the remote already exists.""" def open_repo(path_or_repo): """Open an argument that can be a repository or a path for a repository.""" if isinstance(path_or_repo, BaseRepo): return path_or_repo return Repo(path_or_repo) @contextmanager def _noop_context_manager(obj): """Context manager that has the same api as closing but does nothing.""" yield obj def open_repo_closing(path_or_repo): """Open an argument that can be a repository or a path for a repository. returns a context manager that will close the repo on exit if the argument is a path, else does nothing if the argument is a repo. """ if isinstance(path_or_repo, BaseRepo): return _noop_context_manager(path_or_repo) return closing(Repo(path_or_repo)) def path_to_tree_path(repopath, path, tree_encoding=DEFAULT_ENCODING): """Convert a path to a path usable in an index, e.g. bytes and relative to the repository root. Args: repopath: Repository path, absolute or relative to the cwd path: A path, absolute or relative to the cwd Returns: A path formatted for use in e.g. an index """ # Pathlib resolve before Python 3.6 could raises FileNotFoundError in case # there is no file matching the path so we reuse the old implementation for # Python 3.5 if sys.version_info < (3, 6): if not isinstance(path, bytes): path = os.fsencode(path) if not isinstance(repopath, bytes): repopath = os.fsencode(repopath) treepath = os.path.relpath(path, repopath) if treepath.startswith(b".."): err_msg = "Path %r not in repo path (%r)" % (path, repopath) raise ValueError(err_msg) if os.path.sep != "/": treepath = treepath.replace(os.path.sep.encode("ascii"), b"/") return treepath else: # Resolve might returns a relative path on Windows # https://bugs.python.org/issue38671 if sys.platform == "win32": path = os.path.abspath(path) path = Path(path) resolved_path = path.resolve() # Resolve and abspath seems to behave differently regarding symlinks, # as we are doing abspath on the file path, we need to do the same on # the repo path or they might not match if sys.platform == "win32": repopath = os.path.abspath(repopath) repopath = Path(repopath).resolve() try: relpath = resolved_path.relative_to(repopath) except ValueError: # If path is a symlink that points to a file outside the repo, we # want the relpath for the link itself, not the resolved target if path.is_symlink(): parent = path.parent.resolve() relpath = (parent / path.name).relative_to(repopath) else: raise if sys.platform == "win32": return str(relpath).replace(os.path.sep, "/").encode(tree_encoding) else: return bytes(relpath) class DivergedBranches(Error): """Branches have diverged and fast-forward is not possible.""" def check_diverged(repo, current_sha, new_sha): """Check if updating to a sha can be done with fast forwarding. Args: repo: Repository object current_sha: Current head sha new_sha: New head sha """ try: can = can_fast_forward(repo, current_sha, new_sha) except KeyError: can = False if not can: raise DivergedBranches(current_sha, new_sha) def archive( repo, committish=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream, ): """Create an archive. Args: repo: Path of repository for which to generate an archive. committish: Commit SHA1 or ref to use outstream: Output stream (defaults to stdout) errstream: Error stream (defaults to stderr) """ if committish is None: committish = "HEAD" with open_repo_closing(repo) as repo_obj: c = parse_commit(repo_obj, committish) for chunk in tar_stream( repo_obj.object_store, repo_obj.object_store[c.tree], c.commit_time ): outstream.write(chunk) def update_server_info(repo="."): """Update server info files for a repository. Args: repo: path to the repository """ with open_repo_closing(repo) as r: server_update_server_info(r) def symbolic_ref(repo, ref_name, force=False): """Set git symbolic ref into HEAD. Args: repo: path to the repository ref_name: short name of the new ref force: force settings without checking if it exists in refs/heads """ with open_repo_closing(repo) as repo_obj: ref_path = _make_branch_ref(ref_name) if not force and ref_path not in repo_obj.refs.keys(): raise Error("fatal: ref `%s` is not a ref" % ref_name) repo_obj.refs.set_symbolic_ref(b"HEAD", ref_path) def commit( repo=".", message=None, author=None, committer=None, encoding=None, no_verify=False, ): """Create a new commit. Args: repo: Path to repository message: Optional commit message author: Optional author name and email committer: Optional committer name and email no_verify: Skip pre-commit and commit-msg hooks Returns: SHA1 of the new commit """ # FIXME: Support --all argument # FIXME: Support --signoff argument if getattr(message, "encode", None): message = message.encode(encoding or DEFAULT_ENCODING) if getattr(author, "encode", None): author = author.encode(encoding or DEFAULT_ENCODING) if getattr(committer, "encode", None): committer = committer.encode(encoding or DEFAULT_ENCODING) with open_repo_closing(repo) as r: return r.do_commit( message=message, author=author, committer=committer, encoding=encoding, no_verify=no_verify, ) def commit_tree(repo, tree, message=None, author=None, committer=None): """Create a new commit object. Args: repo: Path to repository tree: An existing tree object author: Optional author name and email committer: Optional committer name and email """ with open_repo_closing(repo) as r: return r.do_commit( message=message, tree=tree, committer=committer, author=author ) def init(path=".", bare=False): """Create a new git repository. Args: path: Path to repository. bare: Whether to create a bare repository. Returns: A Repo instance """ if not os.path.exists(path): os.mkdir(path) if bare: return Repo.init_bare(path) else: return Repo.init(path) def clone( source, target=None, bare=False, checkout=None, errstream=default_bytes_err_stream, outstream=None, origin=b"origin", depth=None, **kwargs ): """Clone a local or remote git repository. Args: source: Path or URL for source repository target: Path to target repository (optional) bare: Whether or not to create a bare repository checkout: Whether or not to check-out HEAD after cloning errstream: Optional stream to write progress to outstream: Optional stream to write progress to (deprecated) origin: Name of remote from the repository used to clone depth: Depth to fetch at Returns: The new repository """ # TODO(jelmer): This code overlaps quite a bit with Repo.clone if outstream is not None: import warnings warnings.warn( "outstream= has been deprecated in favour of errstream=.", DeprecationWarning, stacklevel=3, ) errstream = outstream if checkout is None: checkout = not bare if checkout and bare: raise Error("checkout and bare are incompatible") if target is None: target = source.split("/")[-1] if not os.path.exists(target): os.mkdir(target) if bare: r = Repo.init_bare(target) else: r = Repo.init(target) reflog_message = b"clone: from " + source.encode("utf-8") try: target_config = r.get_config() if not isinstance(source, bytes): source = source.encode(DEFAULT_ENCODING) target_config.set((b"remote", origin), b"url", source) target_config.set( (b"remote", origin), b"fetch", b"+refs/heads/*:refs/remotes/" + origin + b"/*", ) target_config.write_to_path() fetch_result = fetch( r, origin, errstream=errstream, message=reflog_message, depth=depth, **kwargs ) for key, target in fetch_result.symrefs.items(): r.refs.set_symbolic_ref(key, target) try: head = r[fetch_result.refs[b"HEAD"]] except KeyError: head = None else: r[b"HEAD"] = head.id if checkout and not bare and head is not None: errstream.write(b"Checking out " + head.id + b"\n") r.reset_index(head.tree) except BaseException: shutil.rmtree(target) r.close() raise return r def add(repo=".", paths=None): """Add files to the staging area. Args: repo: Repository for the files paths: Paths to add. No value passed stages all modified files. Returns: Tuple with set of added files and ignored files If the repository contains ignored directories, the returned set will contain the path to an ignored directory (with trailing slash). Individual files within ignored directories will not be returned. """ ignored = set() with open_repo_closing(repo) as r: repo_path = Path(r.path).resolve() ignore_manager = IgnoreFilterManager.from_repo(r) if not paths: paths = list( get_untracked_paths( str(Path(os.getcwd()).resolve()), str(repo_path), r.open_index(), ) ) relpaths = [] if not isinstance(paths, list): paths = [paths] for p in paths: path = Path(p) relpath = str(path.resolve().relative_to(repo_path)) # FIXME: Support patterns if path.is_dir(): relpath = os.path.join(relpath, "") if ignore_manager.is_ignored(relpath): ignored.add(relpath) continue relpaths.append(relpath) r.stage(relpaths) return (relpaths, ignored) def _is_subdir(subdir, parentdir): """Check whether subdir is parentdir or a subdir of parentdir If parentdir or subdir is a relative path, it will be disamgibuated relative to the pwd. """ parentdir_abs = os.path.realpath(parentdir) + os.path.sep subdir_abs = os.path.realpath(subdir) + os.path.sep return subdir_abs.startswith(parentdir_abs) # TODO: option to remove ignored files also, in line with `git clean -fdx` def clean(repo=".", target_dir=None): """Remove any untracked files from the target directory recursively Equivalent to running `git clean -fd` in target_dir. Args: repo: Repository where the files may be tracked target_dir: Directory to clean - current directory if None """ if target_dir is None: target_dir = os.getcwd() with open_repo_closing(repo) as r: if not _is_subdir(target_dir, r.path): raise Error("target_dir must be in the repo's working dir") config = r.get_config_stack() require_force = config.get_boolean( # noqa: F841 (b"clean",), b"requireForce", True ) # TODO(jelmer): if require_force is set, then make sure that -f, -i or # -n is specified. index = r.open_index() ignore_manager = IgnoreFilterManager.from_repo(r) paths_in_wd = _walk_working_dir_paths(target_dir, r.path) # Reverse file visit order, so that files and subdirectories are # removed before containing directory for ap, is_dir in reversed(list(paths_in_wd)): if is_dir: # All subdirectories and files have been removed if untracked, # so dir contains no tracked files iff it is empty. is_empty = len(os.listdir(ap)) == 0 if is_empty: os.rmdir(ap) else: ip = path_to_tree_path(r.path, ap) is_tracked = ip in index rp = os.path.relpath(ap, r.path) is_ignored = ignore_manager.is_ignored(rp) if not is_tracked and not is_ignored: os.remove(ap) def remove(repo=".", paths=None, cached=False): """Remove files from the staging area. Args: repo: Repository for the files paths: Paths to remove """ with open_repo_closing(repo) as r: index = r.open_index() for p in paths: full_path = os.fsencode(os.path.abspath(p)) tree_path = path_to_tree_path(r.path, p) try: index_sha = index[tree_path].sha except KeyError: raise Error("%s did not match any files" % p) if not cached: try: st = os.lstat(full_path) except OSError: pass else: try: blob = blob_from_path_and_stat(full_path, st) except IOError: pass else: try: committed_sha = tree_lookup_path( r.__getitem__, r[r.head()].tree, tree_path )[1] except KeyError: committed_sha = None if blob.id != index_sha and index_sha != committed_sha: raise Error( "file has staged content differing " "from both the file and head: %s" % p ) if index_sha != committed_sha: raise Error("file has staged changes: %s" % p) os.remove(full_path) del index[tree_path] index.write() rm = remove def commit_decode(commit, contents, default_encoding=DEFAULT_ENCODING): if commit.encoding: encoding = commit.encoding.decode("ascii") else: encoding = default_encoding return contents.decode(encoding, "replace") def commit_encode(commit, contents, default_encoding=DEFAULT_ENCODING): if commit.encoding: encoding = commit.encoding.decode("ascii") else: encoding = default_encoding return contents.encode(encoding) def print_commit(commit, decode, outstream=sys.stdout): """Write a human-readable commit log entry. Args: commit: A `Commit` object outstream: A stream file to write to """ outstream.write("-" * 50 + "\n") outstream.write("commit: " + commit.id.decode("ascii") + "\n") if len(commit.parents) > 1: outstream.write( "merge: " + "...".join([c.decode("ascii") for c in commit.parents[1:]]) + "\n" ) outstream.write("Author: " + decode(commit.author) + "\n") if commit.author != commit.committer: outstream.write("Committer: " + decode(commit.committer) + "\n") time_tuple = time.gmtime(commit.author_time + commit.author_timezone) time_str = time.strftime("%a %b %d %Y %H:%M:%S", time_tuple) timezone_str = format_timezone(commit.author_timezone).decode("ascii") outstream.write("Date: " + time_str + " " + timezone_str + "\n") outstream.write("\n") outstream.write(decode(commit.message) + "\n") outstream.write("\n") def print_tag(tag, decode, outstream=sys.stdout): """Write a human-readable tag. Args: tag: A `Tag` object decode: Function for decoding bytes to unicode string outstream: A stream to write to """ outstream.write("Tagger: " + decode(tag.tagger) + "\n") time_tuple = time.gmtime(tag.tag_time + tag.tag_timezone) time_str = time.strftime("%a %b %d %Y %H:%M:%S", time_tuple) timezone_str = format_timezone(tag.tag_timezone).decode("ascii") outstream.write("Date: " + time_str + " " + timezone_str + "\n") outstream.write("\n") outstream.write(decode(tag.message)) outstream.write("\n") def show_blob(repo, blob, decode, outstream=sys.stdout): """Write a blob to a stream. Args: repo: A `Repo` object blob: A `Blob` object decode: Function for decoding bytes to unicode string outstream: A stream file to write to """ outstream.write(decode(blob.data)) def show_commit(repo, commit, decode, outstream=sys.stdout): """Show a commit to a stream. Args: repo: A `Repo` object commit: A `Commit` object decode: Function for decoding bytes to unicode string outstream: Stream to write to """ print_commit(commit, decode=decode, outstream=outstream) if commit.parents: parent_commit = repo[commit.parents[0]] base_tree = parent_commit.tree else: base_tree = None diffstream = BytesIO() write_tree_diff(diffstream, repo.object_store, base_tree, commit.tree) diffstream.seek(0) outstream.write(commit_decode(commit, diffstream.getvalue())) def show_tree(repo, tree, decode, outstream=sys.stdout): """Print a tree to a stream. Args: repo: A `Repo` object tree: A `Tree` object decode: Function for decoding bytes to unicode string outstream: Stream to write to """ for n in tree: outstream.write(decode(n) + "\n") def show_tag(repo, tag, decode, outstream=sys.stdout): """Print a tag to a stream. Args: repo: A `Repo` object tag: A `Tag` object decode: Function for decoding bytes to unicode string outstream: Stream to write to """ print_tag(tag, decode, outstream) show_object(repo, repo[tag.object[1]], decode, outstream) def show_object(repo, obj, decode, outstream): return { b"tree": show_tree, b"blob": show_blob, b"commit": show_commit, b"tag": show_tag, }[obj.type_name](repo, obj, decode, outstream) def print_name_status(changes): """Print a simple status summary, listing changed files.""" for change in changes: if not change: continue if isinstance(change, list): change = change[0] if change.type == CHANGE_ADD: path1 = change.new.path path2 = "" kind = "A" elif change.type == CHANGE_DELETE: path1 = change.old.path path2 = "" kind = "D" elif change.type == CHANGE_MODIFY: path1 = change.new.path path2 = "" kind = "M" elif change.type in RENAME_CHANGE_TYPES: path1 = change.old.path path2 = change.new.path if change.type == CHANGE_RENAME: kind = "R" elif change.type == CHANGE_COPY: kind = "C" yield "%-8s%-20s%-20s" % (kind, path1, path2) def log( repo=".", paths=None, outstream=sys.stdout, max_entries=None, reverse=False, name_status=False, ): """Write commit logs. Args: repo: Path to repository paths: Optional set of specific paths to print entries for outstream: Stream to write log output to reverse: Reverse order in which entries are printed name_status: Print name status max_entries: Optional maximum number of entries to display """ with open_repo_closing(repo) as r: walker = r.get_walker(max_entries=max_entries, paths=paths, reverse=reverse) for entry in walker: def decode(x): return commit_decode(entry.commit, x) print_commit(entry.commit, decode, outstream) if name_status: outstream.writelines( [line + "\n" for line in print_name_status(entry.changes())] ) # TODO(jelmer): better default for encoding? def show( repo=".", objects=None, outstream=sys.stdout, default_encoding=DEFAULT_ENCODING, ): """Print the changes in a commit. Args: repo: Path to repository objects: Objects to show (defaults to [HEAD]) outstream: Stream to write to default_encoding: Default encoding to use if none is set in the commit """ if objects is None: objects = ["HEAD"] if not isinstance(objects, list): objects = [objects] with open_repo_closing(repo) as r: for objectish in objects: o = parse_object(r, objectish) if isinstance(o, Commit): def decode(x): return commit_decode(o, x, default_encoding) else: def decode(x): return x.decode(default_encoding) show_object(r, o, decode, outstream) def diff_tree(repo, old_tree, new_tree, outstream=sys.stdout): """Compares the content and mode of blobs found via two tree objects. Args: repo: Path to repository old_tree: Id of old tree new_tree: Id of new tree outstream: Stream to write to """ with open_repo_closing(repo) as r: write_tree_diff(outstream, r.object_store, old_tree, new_tree) def rev_list(repo, commits, outstream=sys.stdout): """Lists commit objects in reverse chronological order. Args: repo: Path to repository commits: Commits over which to iterate outstream: Stream to write to """ with open_repo_closing(repo) as r: for entry in r.get_walker(include=[r[c].id for c in commits]): outstream.write(entry.commit.id + b"\n") def tag(*args, **kwargs): import warnings warnings.warn( "tag has been deprecated in favour of tag_create.", DeprecationWarning ) return tag_create(*args, **kwargs) def tag_create( repo, tag, author=None, message=None, annotated=False, objectish="HEAD", tag_time=None, tag_timezone=None, sign=False, ): """Creates a tag in git via dulwich calls: Args: repo: Path to repository tag: tag string author: tag author (optional, if annotated is set) message: tag message (optional) annotated: whether to create an annotated tag objectish: object the tag should point at, defaults to HEAD tag_time: Optional time for annotated tag tag_timezone: Optional timezone for annotated tag sign: GPG Sign the tag (bool, defaults to False, pass True to use default GPG key, pass a str containing Key ID to use a specific GPG key) """ with open_repo_closing(repo) as r: object = parse_object(r, objectish) if annotated: # Create the tag object tag_obj = Tag() if author is None: # TODO(jelmer): Don't use repo private method. author = r._get_user_identity(r.get_config_stack()) tag_obj.tagger = author tag_obj.message = message + "\n".encode() tag_obj.name = tag tag_obj.object = (type(object), object.id) if tag_time is None: tag_time = int(time.time()) tag_obj.tag_time = tag_time if tag_timezone is None: # TODO(jelmer) Use current user timezone rather than UTC tag_timezone = 0 elif isinstance(tag_timezone, str): tag_timezone = parse_timezone(tag_timezone) tag_obj.tag_timezone = tag_timezone if sign: tag_obj.sign(sign if isinstance(sign, str) else None) r.object_store.add_object(tag_obj) tag_id = tag_obj.id else: tag_id = object.id r.refs[_make_tag_ref(tag)] = tag_id def list_tags(*args, **kwargs): import warnings warnings.warn( "list_tags has been deprecated in favour of tag_list.", DeprecationWarning, ) return tag_list(*args, **kwargs) def tag_list(repo, outstream=sys.stdout): """List all tags. Args: repo: Path to repository outstream: Stream to write tags to """ with open_repo_closing(repo) as r: tags = sorted(r.refs.as_dict(b"refs/tags")) return tags def tag_delete(repo, name): """Remove a tag. Args: repo: Path to repository name: Name of tag to remove """ with open_repo_closing(repo) as r: if isinstance(name, bytes): names = [name] elif isinstance(name, list): names = name else: raise Error("Unexpected tag name type %r" % name) for name in names: del r.refs[_make_tag_ref(name)] def reset(repo, mode, treeish="HEAD"): """Reset current HEAD to the specified state. Args: repo: Path to repository mode: Mode ("hard", "soft", "mixed") treeish: Treeish to reset to """ if mode != "hard": raise Error("hard is the only mode currently supported") with open_repo_closing(repo) as r: tree = parse_tree(r, treeish) r.reset_index(tree.id) def get_remote_repo( repo: Repo, remote_location: Optional[Union[str, bytes]] = None ) -> Tuple[Optional[str], str]: config = repo.get_config() if remote_location is None: remote_location = get_branch_remote(repo) if isinstance(remote_location, str): encoded_location = remote_location.encode() else: encoded_location = remote_location section = (b"remote", encoded_location) remote_name = None # type: Optional[str] if config.has_section(section): remote_name = encoded_location.decode() url = config.get(section, "url") encoded_location = url else: remote_name = None return (remote_name, encoded_location.decode()) def push( repo, remote_location=None, refspecs=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream, force=False, **kwargs ): """Remote push with dulwich via dulwich.client Args: repo: Path to repository remote_location: Location of the remote refspecs: Refs to push to remote outstream: A stream file to write output errstream: A stream file to write errors force: Force overwriting refs """ # Open the repo with open_repo_closing(repo) as r: if refspecs is None: refspecs = [active_branch(r)] (remote_name, remote_location) = get_remote_repo(r, remote_location) # Get the client and path client, path = get_transport_and_path( remote_location, config=r.get_config_stack(), **kwargs ) selected_refs = [] remote_changed_refs = {} def update_refs(refs): selected_refs.extend(parse_reftuples(r.refs, refs, refspecs, force=force)) new_refs = {} # TODO: Handle selected_refs == {None: None} for (lh, rh, force_ref) in selected_refs: if lh is None: new_refs[rh] = ZERO_SHA remote_changed_refs[rh] = None else: try: localsha = r.refs[lh] except KeyError: raise Error("No valid ref %s in local repository" % lh) if not force_ref and rh in refs: check_diverged(r, refs[rh], localsha) new_refs[rh] = localsha remote_changed_refs[rh] = localsha return new_refs err_encoding = getattr(errstream, "encoding", None) or DEFAULT_ENCODING remote_location = client.get_url(path) try: result = client.send_pack( path, update_refs, generate_pack_data=r.generate_pack_data, progress=errstream.write, ) except SendPackError as e: raise Error( "Push to " + remote_location + " failed -> " + e.args[0].decode(), inner=e, ) else: errstream.write( b"Push to " + remote_location.encode(err_encoding) + b" successful.\n" ) for ref, error in (result.ref_status or {}).items(): if error is not None: errstream.write( b"Push of ref %s failed: %s\n" % (ref, error.encode(err_encoding)) ) else: errstream.write(b"Ref %s updated\n" % ref) if remote_name is not None: _import_remote_refs(r.refs, remote_name, remote_changed_refs) def pull( repo, remote_location=None, refspecs=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream, fast_forward=True, force=False, **kwargs ): """Pull from remote via dulwich.client Args: repo: Path to repository remote_location: Location of the remote refspec: refspecs to fetch outstream: A stream file to write to output errstream: A stream file to write to errors """ # Open the repo with open_repo_closing(repo) as r: (remote_name, remote_location) = get_remote_repo(r, remote_location) if refspecs is None: refspecs = [b"HEAD"] selected_refs = [] def determine_wants(remote_refs, **kwargs): selected_refs.extend( parse_reftuples(remote_refs, r.refs, refspecs, force=force) ) return [ remote_refs[lh] for (lh, rh, force_ref) in selected_refs if remote_refs[lh] not in r.object_store ] client, path = get_transport_and_path( remote_location, config=r.get_config_stack(), **kwargs ) fetch_result = client.fetch( path, r, progress=errstream.write, determine_wants=determine_wants ) for (lh, rh, force_ref) in selected_refs: try: check_diverged(r, r.refs[rh], fetch_result.refs[lh]) except DivergedBranches: if fast_forward: raise else: raise NotImplementedError("merge is not yet supported") r.refs[rh] = fetch_result.refs[lh] if selected_refs: r[b"HEAD"] = fetch_result.refs[selected_refs[0][1]] # Perform 'git checkout .' - syncs staged changes tree = r[b"HEAD"].tree r.reset_index(tree=tree) if remote_name is not None: _import_remote_refs(r.refs, remote_name, fetch_result.refs) def status(repo=".", ignored=False): """Returns staged, unstaged, and untracked changes relative to the HEAD. Args: repo: Path to repository or repository object ignored: Whether to include ignored files in `untracked` Returns: GitStatus tuple, staged - dict with lists of staged paths (diff index/HEAD) unstaged - list of unstaged paths (diff index/working-tree) untracked - list of untracked, un-ignored & non-.git paths """ with open_repo_closing(repo) as r: # 1. Get status of staged tracked_changes = get_tree_changes(r) # 2. Get status of unstaged index = r.open_index() normalizer = r.get_blob_normalizer() filter_callback = normalizer.checkin_normalize - unstaged_changes = list(get_unstaged_changes(index, r.path, filter_callback)) + unstaged_changes = list(get_unstaged_changes(index, r, filter_callback)) untracked_paths = get_untracked_paths( r.path, r.path, index, exclude_ignored=not ignored ) untracked_changes = list(untracked_paths) return GitStatus(tracked_changes, unstaged_changes, untracked_changes) def _walk_working_dir_paths(frompath, basepath, prune_dirnames=None): """Get path, is_dir for files in working dir from frompath Args: frompath: Path to begin walk basepath: Path to compare to prune_dirnames: Optional callback to prune dirnames during os.walk dirnames will be set to result of prune_dirnames(dirpath, dirnames) """ for dirpath, dirnames, filenames in os.walk(frompath): # Skip .git and below. if ".git" in dirnames: dirnames.remove(".git") if dirpath != basepath: continue if ".git" in filenames: filenames.remove(".git") if dirpath != basepath: continue if dirpath != frompath: yield dirpath, True for filename in filenames: filepath = os.path.join(dirpath, filename) yield filepath, False if prune_dirnames: dirnames[:] = prune_dirnames(dirpath, dirnames) def get_untracked_paths(frompath, basepath, index, exclude_ignored=False): """Get untracked paths. Args: frompath: Path to walk basepath: Path to compare to index: Index to check against exclude_ignored: Whether to exclude ignored paths Note: ignored directories will never be walked for performance reasons. If exclude_ignored is False, only the path to an ignored directory will be yielded, no files inside the directory will be returned """ with open_repo_closing(basepath) as r: ignore_manager = IgnoreFilterManager.from_repo(r) ignored_dirs = [] def prune_dirnames(dirpath, dirnames): for i in range(len(dirnames) - 1, -1, -1): path = os.path.join(dirpath, dirnames[i]) ip = os.path.join(os.path.relpath(path, basepath), "") if ignore_manager.is_ignored(ip): if not exclude_ignored: ignored_dirs.append( os.path.join(os.path.relpath(path, frompath), "") ) del dirnames[i] return dirnames for ap, is_dir in _walk_working_dir_paths( frompath, basepath, prune_dirnames=prune_dirnames ): if not is_dir: ip = path_to_tree_path(basepath, ap) if ip not in index: if ( not exclude_ignored or not ignore_manager.is_ignored( os.path.relpath(ap, basepath) ) ): yield os.path.relpath(ap, frompath) yield from ignored_dirs def get_tree_changes(repo): """Return add/delete/modify changes to tree by comparing index to HEAD. Args: repo: repo path or object Returns: dict with lists for each type of change """ with open_repo_closing(repo) as r: index = r.open_index() # Compares the Index to the HEAD & determines changes # Iterate through the changes and report add/delete/modify # TODO: call out to dulwich.diff_tree somehow. tracked_changes = { "add": [], "delete": [], "modify": [], } try: tree_id = r[b"HEAD"].tree except KeyError: tree_id = None for change in index.changes_from_tree(r.object_store, tree_id): if not change[0][0]: tracked_changes["add"].append(change[0][1]) elif not change[0][1]: tracked_changes["delete"].append(change[0][0]) elif change[0][0] == change[0][1]: tracked_changes["modify"].append(change[0][0]) else: raise NotImplementedError("git mv ops not yet supported") return tracked_changes def daemon(path=".", address=None, port=None): """Run a daemon serving Git requests over TCP/IP. Args: path: Path to the directory to serve. address: Optional address to listen on (defaults to ::) port: Optional port to listen on (defaults to TCP_GIT_PORT) """ # TODO(jelmer): Support git-daemon-export-ok and --export-all. backend = FileSystemBackend(path) server = TCPGitServer(backend, address, port) server.serve_forever() def web_daemon(path=".", address=None, port=None): """Run a daemon serving Git requests over HTTP. Args: path: Path to the directory to serve address: Optional address to listen on (defaults to ::) port: Optional port to listen on (defaults to 80) """ from dulwich.web import ( make_wsgi_chain, make_server, WSGIRequestHandlerLogger, WSGIServerLogger, ) backend = FileSystemBackend(path) app = make_wsgi_chain(backend) server = make_server( address, port, app, handler_class=WSGIRequestHandlerLogger, server_class=WSGIServerLogger, ) server.serve_forever() def upload_pack(path=".", inf=None, outf=None): """Upload a pack file after negotiating its contents using smart protocol. Args: path: Path to the repository inf: Input stream to communicate with client outf: Output stream to communicate with client """ if outf is None: outf = getattr(sys.stdout, "buffer", sys.stdout) if inf is None: inf = getattr(sys.stdin, "buffer", sys.stdin) path = os.path.expanduser(path) backend = FileSystemBackend(path) def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = UploadPackHandler(backend, [path], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def receive_pack(path=".", inf=None, outf=None): """Receive a pack file after negotiating its contents using smart protocol. Args: path: Path to the repository inf: Input stream to communicate with client outf: Output stream to communicate with client """ if outf is None: outf = getattr(sys.stdout, "buffer", sys.stdout) if inf is None: inf = getattr(sys.stdin, "buffer", sys.stdin) path = os.path.expanduser(path) backend = FileSystemBackend(path) def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = ReceivePackHandler(backend, [path], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def _make_branch_ref(name): if getattr(name, "encode", None): name = name.encode(DEFAULT_ENCODING) return LOCAL_BRANCH_PREFIX + name def _make_tag_ref(name): if getattr(name, "encode", None): name = name.encode(DEFAULT_ENCODING) return b"refs/tags/" + name def branch_delete(repo, name): """Delete a branch. Args: repo: Path to the repository name: Name of the branch """ with open_repo_closing(repo) as r: if isinstance(name, list): names = name else: names = [name] for name in names: del r.refs[_make_branch_ref(name)] def branch_create(repo, name, objectish=None, force=False): """Create a branch. Args: repo: Path to the repository name: Name of the new branch objectish: Target object to point new branch at (defaults to HEAD) force: Force creation of branch, even if it already exists """ with open_repo_closing(repo) as r: if objectish is None: objectish = "HEAD" object = parse_object(r, objectish) refname = _make_branch_ref(name) ref_message = b"branch: Created from " + objectish.encode("utf-8") if force: r.refs.set_if_equals(refname, None, object.id, message=ref_message) else: if not r.refs.add_if_new(refname, object.id, message=ref_message): raise Error("Branch with name %s already exists." % name) def branch_list(repo): """List all branches. Args: repo: Path to the repository """ with open_repo_closing(repo) as r: return r.refs.keys(base=LOCAL_BRANCH_PREFIX) def active_branch(repo): """Return the active branch in the repository, if any. Args: repo: Repository to open Returns: branch name Raises: KeyError: if the repository does not have a working tree IndexError: if HEAD is floating """ with open_repo_closing(repo) as r: active_ref = r.refs.follow(b"HEAD")[0][1] if not active_ref.startswith(LOCAL_BRANCH_PREFIX): raise ValueError(active_ref) return active_ref[len(LOCAL_BRANCH_PREFIX) :] def get_branch_remote(repo): """Return the active branch's remote name, if any. Args: repo: Repository to open Returns: remote name Raises: KeyError: if the repository does not have a working tree """ with open_repo_closing(repo) as r: branch_name = active_branch(r.path) config = r.get_config() try: remote_name = config.get((b"branch", branch_name), b"remote") except KeyError: remote_name = b"origin" return remote_name def _import_remote_refs( refs_container: RefsContainer, remote_name: str, refs: Dict[str, str], message: Optional[bytes] = None, prune: bool = False, prune_tags: bool = False, ): stripped_refs = strip_peeled_refs(refs) branches = { n[len(LOCAL_BRANCH_PREFIX) :]: v for (n, v) in stripped_refs.items() if n.startswith(LOCAL_BRANCH_PREFIX) } refs_container.import_refs( b"refs/remotes/" + remote_name.encode(), branches, message=message, prune=prune, ) tags = { n[len(b"refs/tags/") :]: v for (n, v) in stripped_refs.items() if n.startswith(b"refs/tags/") and not n.endswith(ANNOTATED_TAG_SUFFIX) } refs_container.import_refs(b"refs/tags", tags, message=message, prune=prune_tags) def fetch( repo, remote_location=None, outstream=sys.stdout, errstream=default_bytes_err_stream, message=None, depth=None, prune=False, prune_tags=False, force=False, **kwargs ): """Fetch objects from a remote server. Args: repo: Path to the repository remote_location: String identifying a remote server outstream: Output stream (defaults to stdout) errstream: Error stream (defaults to stderr) message: Reflog message (defaults to b"fetch: from ") depth: Depth to fetch at prune: Prune remote removed refs prune_tags: Prune reomte removed tags Returns: Dictionary with refs on the remote """ with open_repo_closing(repo) as r: (remote_name, remote_location) = get_remote_repo(r, remote_location) if message is None: message = b"fetch: from " + remote_location.encode("utf-8") client, path = get_transport_and_path( remote_location, config=r.get_config_stack(), **kwargs ) fetch_result = client.fetch(path, r, progress=errstream.write, depth=depth) if remote_name is not None: _import_remote_refs( r.refs, remote_name, fetch_result.refs, message, prune=prune, prune_tags=prune_tags, ) return fetch_result def ls_remote(remote, config=None, **kwargs): """List the refs in a remote. Args: remote: Remote repository location config: Configuration to use Returns: Dictionary with remote refs """ if config is None: config = StackedConfig.default() client, host_path = get_transport_and_path(remote, config=config, **kwargs) return client.get_refs(host_path) def repack(repo): """Repack loose files in a repository. Currently this only packs loose objects. Args: repo: Path to the repository """ with open_repo_closing(repo) as r: r.object_store.pack_loose_objects() def pack_objects(repo, object_ids, packf, idxf, delta_window_size=None): """Pack objects into a file. Args: repo: Path to the repository object_ids: List of object ids to write packf: File-like object to write to idxf: File-like object to write to (can be None) """ with open_repo_closing(repo) as r: entries, data_sum = write_pack_objects( packf, r.object_store.iter_shas((oid, None) for oid in object_ids), delta_window_size=delta_window_size, ) if idxf is not None: entries = sorted([(k, v[0], v[1]) for (k, v) in entries.items()]) write_pack_index(idxf, entries, data_sum) def ls_tree( repo, treeish=b"HEAD", outstream=sys.stdout, recursive=False, name_only=False, ): """List contents of a tree. Args: repo: Path to the repository tree_ish: Tree id to list outstream: Output stream (defaults to stdout) recursive: Whether to recursively list files name_only: Only print item name """ def list_tree(store, treeid, base): for (name, mode, sha) in store[treeid].iteritems(): if base: name = posixpath.join(base, name) if name_only: outstream.write(name + b"\n") else: outstream.write(pretty_format_tree_entry(name, mode, sha)) if stat.S_ISDIR(mode) and recursive: list_tree(store, sha, name) with open_repo_closing(repo) as r: tree = parse_tree(r, treeish) list_tree(r.object_store, tree.id, "") def remote_add(repo, name, url): """Add a remote. Args: repo: Path to the repository name: Remote name url: Remote URL """ if not isinstance(name, bytes): name = name.encode(DEFAULT_ENCODING) if not isinstance(url, bytes): url = url.encode(DEFAULT_ENCODING) with open_repo_closing(repo) as r: c = r.get_config() section = (b"remote", name) if c.has_section(section): raise RemoteExists(section) c.set(section, b"url", url) c.write_to_path() def check_ignore(repo, paths, no_index=False): """Debug gitignore files. Args: repo: Path to the repository paths: List of paths to check for no_index: Don't check index Returns: List of ignored files """ with open_repo_closing(repo) as r: index = r.open_index() ignore_manager = IgnoreFilterManager.from_repo(r) for path in paths: if not no_index and path_to_tree_path(r.path, path) in index: continue if os.path.isabs(path): path = os.path.relpath(path, r.path) if ignore_manager.is_ignored(path): yield path def update_head(repo, target, detached=False, new_branch=None): """Update HEAD to point at a new branch/commit. Note that this does not actually update the working tree. Args: repo: Path to the repository detach: Create a detached head target: Branch or committish to switch to new_branch: New branch to create """ with open_repo_closing(repo) as r: if new_branch is not None: to_set = _make_branch_ref(new_branch) else: to_set = b"HEAD" if detached: # TODO(jelmer): Provide some way so that the actual ref gets # updated rather than what it points to, so the delete isn't # necessary. del r.refs[to_set] r.refs[to_set] = parse_commit(r, target).id else: r.refs.set_symbolic_ref(to_set, parse_ref(r, target)) if new_branch is not None: r.refs.set_symbolic_ref(b"HEAD", to_set) def check_mailmap(repo, contact): """Check canonical name and email of contact. Args: repo: Path to the repository contact: Contact name and/or email Returns: Canonical contact data """ with open_repo_closing(repo) as r: from dulwich.mailmap import Mailmap try: mailmap = Mailmap.from_path(os.path.join(r.path, ".mailmap")) except FileNotFoundError: mailmap = Mailmap() return mailmap.lookup(contact) def fsck(repo): """Check a repository. Args: repo: A path to the repository Returns: Iterator over errors/warnings """ with open_repo_closing(repo) as r: # TODO(jelmer): check pack files # TODO(jelmer): check graph # TODO(jelmer): check refs for sha in r.object_store: o = r.object_store[sha] try: o.check() except Exception as e: yield (sha, e) def stash_list(repo): """List all stashes in a repository.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) return enumerate(list(stash.stashes())) def stash_push(repo): """Push a new stash onto the stack.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) stash.push() def stash_pop(repo): """Pop a new stash from the stack.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) stash.pop() def ls_files(repo): """List all files in an index.""" with open_repo_closing(repo) as r: return sorted(r.open_index()) def describe(repo): """Describe the repository version. Args: projdir: git repository root Returns: a string description of the current git revision Examples: "gabcdefh", "v0.1" or "v0.1-5-gabcdefh". """ # Get the repository with open_repo_closing(repo) as r: # Get a list of all tags refs = r.get_refs() tags = {} for key, value in refs.items(): key = key.decode() obj = r.get_object(value) if u"tags" not in key: continue _, tag = key.rsplit(u"/", 1) try: commit = obj.object except AttributeError: continue else: commit = r.get_object(commit[1]) tags[tag] = [ datetime.datetime(*time.gmtime(commit.commit_time)[:6]), commit.id.decode("ascii"), ] sorted_tags = sorted(tags.items(), key=lambda tag: tag[1][0], reverse=True) # If there are no tags, return the current commit if len(sorted_tags) == 0: return "g{}".format(r[r.head()].id.decode("ascii")[:7]) # We're now 0 commits from the top commit_count = 0 # Get the latest commit latest_commit = r[r.head()] # Walk through all commits walker = r.get_walker() for entry in walker: # Check if tag commit_id = entry.commit.id.decode("ascii") for tag in sorted_tags: tag_name = tag[0] tag_commit = tag[1][1] if commit_id == tag_commit: if commit_count == 0: return tag_name else: return "{}-{}-g{}".format( tag_name, commit_count, latest_commit.id.decode("ascii")[:7], ) commit_count += 1 # Return plain commit if no parent tag can be found return "g{}".format(latest_commit.id.decode("ascii")[:7]) def get_object_by_path(repo, path, committish=None): """Get an object by path. Args: repo: A path to the repository path: Path to look up committish: Commit to look up path in Returns: A `ShaFile` object """ if committish is None: committish = "HEAD" # Get the repository with open_repo_closing(repo) as r: commit = parse_commit(r, committish) base_tree = commit.tree if not isinstance(path, bytes): path = commit_encode(commit, path) (mode, sha) = tree_lookup_path(r.object_store.__getitem__, base_tree, path) return r[sha] def write_tree(repo): """Write a tree object from the index. Args: repo: Repository for which to write tree Returns: tree id for the tree that was written """ with open_repo_closing(repo) as r: return r.open_index().commit(r.object_store) diff --git a/dulwich/repo.py b/dulwich/repo.py index 2f086ffb..89d7ab5c 100644 --- a/dulwich/repo.py +++ b/dulwich/repo.py @@ -1,1634 +1,1641 @@ # repo.py -- For dealing with git repositories. # Copyright (C) 2007 James Westby # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Repository access. This module contains the base class for git repositories (BaseRepo) and an implementation which uses a repository on local disk (Repo). """ from io import BytesIO import os import sys import stat import time from typing import Optional, Tuple, TYPE_CHECKING, List, Dict, Union, Iterable if TYPE_CHECKING: # There are no circular imports here, but we try to defer imports as long # as possible to reduce start-up time for anything that doesn't need # these imports. from dulwich.config import StackedConfig, ConfigFile from dulwich.index import Index from dulwich.errors import ( NoIndexPresent, NotBlobError, NotCommitError, NotGitRepository, NotTreeError, NotTagError, CommitError, RefFormatError, HookError, ) from dulwich.file import ( GitFile, ) from dulwich.object_store import ( DiskObjectStore, MemoryObjectStore, BaseObjectStore, ObjectStoreGraphWalker, ) from dulwich.objects import ( check_hexsha, valid_hexsha, Blob, Commit, ShaFile, Tag, Tree, ) from dulwich.pack import ( pack_objects_to_data, ) from dulwich.hooks import ( Hook, PreCommitShellHook, PostCommitShellHook, CommitMsgShellHook, PostReceiveShellHook, ) from dulwich.line_ending import BlobNormalizer from dulwich.refs import ( # noqa: F401 ANNOTATED_TAG_SUFFIX, check_ref_format, RefsContainer, DictRefsContainer, InfoRefsContainer, DiskRefsContainer, read_packed_refs, read_packed_refs_with_peeled, write_packed_refs, SYMREF, ) import warnings CONTROLDIR = ".git" OBJECTDIR = "objects" REFSDIR = "refs" REFSDIR_TAGS = "tags" REFSDIR_HEADS = "heads" INDEX_FILENAME = "index" COMMONDIR = "commondir" GITDIR = "gitdir" WORKTREES = "worktrees" BASE_DIRECTORIES = [ ["branches"], [REFSDIR], [REFSDIR, REFSDIR_TAGS], [REFSDIR, REFSDIR_HEADS], ["hooks"], ["info"], ] DEFAULT_REF = b"refs/heads/master" class InvalidUserIdentity(Exception): """User identity is not of the format 'user '""" def __init__(self, identity): self.identity = identity def _get_default_identity() -> Tuple[str, str]: import getpass import socket username = getpass.getuser() try: import pwd except ImportError: fullname = None else: try: gecos = pwd.getpwnam(username).pw_gecos except KeyError: fullname = None else: fullname = gecos.split(",")[0] if not fullname: fullname = username email = os.environ.get("EMAIL") if email is None: email = "{}@{}".format(username, socket.gethostname()) return (fullname, email) def get_user_identity(config: "StackedConfig", kind: Optional[str] = None) -> bytes: """Determine the identity to use for new commits. If kind is set, this first checks GIT_${KIND}_NAME and GIT_${KIND}_EMAIL. If those variables are not set, then it will fall back to reading the user.name and user.email settings from the specified configuration. If that also fails, then it will fall back to using the current users' identity as obtained from the host system (e.g. the gecos field, $EMAIL, $USER@$(hostname -f). Args: kind: Optional kind to return identity for, usually either "AUTHOR" or "COMMITTER". Returns: A user identity """ user = None # type: Optional[bytes] email = None # type: Optional[bytes] if kind: user_uc = os.environ.get("GIT_" + kind + "_NAME") if user_uc is not None: user = user_uc.encode("utf-8") email_uc = os.environ.get("GIT_" + kind + "_EMAIL") if email_uc is not None: email = email_uc.encode("utf-8") if user is None: try: user = config.get(("user",), "name") except KeyError: user = None if email is None: try: email = config.get(("user",), "email") except KeyError: email = None default_user, default_email = _get_default_identity() if user is None: user = default_user.encode("utf-8") if email is None: email = default_email.encode("utf-8") if email.startswith(b"<") and email.endswith(b">"): email = email[1:-1] return user + b" <" + email + b">" def check_user_identity(identity): """Verify that a user identity is formatted correctly. Args: identity: User identity bytestring Raises: InvalidUserIdentity: Raised when identity is invalid """ try: fst, snd = identity.split(b" <", 1) except ValueError: raise InvalidUserIdentity(identity) if b">" not in snd: raise InvalidUserIdentity(identity) def parse_graftpoints( graftpoints: Iterable[bytes], ) -> Dict[bytes, List[bytes]]: """Convert a list of graftpoints into a dict Args: graftpoints: Iterator of graftpoint lines Each line is formatted as: []* Resulting dictionary is: : [*] https://git.wiki.kernel.org/index.php/GraftPoint """ grafts = {} for line in graftpoints: raw_graft = line.split(None, 1) commit = raw_graft[0] if len(raw_graft) == 2: parents = raw_graft[1].split() else: parents = [] for sha in [commit] + parents: check_hexsha(sha, "Invalid graftpoint") grafts[commit] = parents return grafts def serialize_graftpoints(graftpoints: Dict[bytes, List[bytes]]) -> bytes: """Convert a dictionary of grafts into string The graft dictionary is: : [*] Each line is formatted as: []* https://git.wiki.kernel.org/index.php/GraftPoint """ graft_lines = [] for commit, parents in graftpoints.items(): if parents: graft_lines.append(commit + b" " + b" ".join(parents)) else: graft_lines.append(commit) return b"\n".join(graft_lines) def _set_filesystem_hidden(path): """Mark path as to be hidden if supported by platform and filesystem. On win32 uses SetFileAttributesW api: """ if sys.platform == "win32": import ctypes from ctypes.wintypes import BOOL, DWORD, LPCWSTR FILE_ATTRIBUTE_HIDDEN = 2 SetFileAttributesW = ctypes.WINFUNCTYPE(BOOL, LPCWSTR, DWORD)( ("SetFileAttributesW", ctypes.windll.kernel32) ) if isinstance(path, bytes): path = os.fsdecode(path) if not SetFileAttributesW(path, FILE_ATTRIBUTE_HIDDEN): pass # Could raise or log `ctypes.WinError()` here # Could implement other platform specific filesytem hiding here class ParentsProvider(object): def __init__(self, store, grafts={}, shallows=[]): self.store = store self.grafts = grafts self.shallows = set(shallows) def get_parents(self, commit_id, commit=None): try: return self.grafts[commit_id] except KeyError: pass if commit_id in self.shallows: return [] if commit is None: commit = self.store[commit_id] return commit.parents class BaseRepo(object): """Base class for a git repository. :ivar object_store: Dictionary-like object for accessing the objects :ivar refs: Dictionary-like object with the refs in this repository """ def __init__(self, object_store: BaseObjectStore, refs: RefsContainer): """Open a repository. This shouldn't be called directly, but rather through one of the base classes, such as MemoryRepo or Repo. Args: object_store: Object store to use refs: Refs container to use """ self.object_store = object_store self.refs = refs self._graftpoints = {} # type: Dict[bytes, List[bytes]] self.hooks = {} # type: Dict[str, Hook] def _determine_file_mode(self) -> bool: """Probe the file-system to determine whether permissions can be trusted. Returns: True if permissions can be trusted, False otherwise. """ raise NotImplementedError(self._determine_file_mode) def _init_files(self, bare: bool) -> None: """Initialize a default set of named files.""" from dulwich.config import ConfigFile self._put_named_file("description", b"Unnamed repository") f = BytesIO() cf = ConfigFile() cf.set("core", "repositoryformatversion", "0") if self._determine_file_mode(): cf.set("core", "filemode", True) else: cf.set("core", "filemode", False) cf.set("core", "bare", bare) cf.set("core", "logallrefupdates", True) cf.write_to_file(f) self._put_named_file("config", f.getvalue()) self._put_named_file(os.path.join("info", "exclude"), b"") def get_named_file(self, path): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-based Repo, the object returned need not be pointing to a file in that location. Args: path: The path to the file, relative to the control dir. Returns: An open file object, or None if the file does not exist. """ raise NotImplementedError(self.get_named_file) def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. Args: path: The path to the file, relative to the control dir. contents: A string to write to the file. """ raise NotImplementedError(self._put_named_file) def _del_named_file(self, path): """Delete a file in the contrl directory with the given name.""" raise NotImplementedError(self._del_named_file) def open_index(self): """Open the index for this repository. Raises: NoIndexPresent: If no index is present Returns: The matching `Index` """ raise NotImplementedError(self.open_index) def fetch(self, target, determine_wants=None, progress=None, depth=None): """Fetch objects into another repository. Args: target: The target repository determine_wants: Optional function to determine what refs to fetch. progress: Optional progress function depth: Optional shallow fetch depth Returns: The local refs """ if determine_wants is None: determine_wants = target.object_store.determine_wants_all count, pack_data = self.fetch_pack_data( determine_wants, target.get_graph_walker(), progress=progress, depth=depth, ) target.object_store.add_pack_data(count, pack_data, progress) return self.get_refs() def fetch_pack_data( self, determine_wants, graph_walker, progress, get_tagged=None, depth=None, ): """Fetch the pack data required for a set of revisions. Args: determine_wants: Function that takes a dictionary with heads and returns the list of heads to fetch. graph_walker: Object that can iterate over the list of revisions to fetch and has an "ack" method that will be called to acknowledge that a revision is present. progress: Simple progress function that will be called with updated progress strings. get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. depth: Shallow fetch depth Returns: count and iterator over pack data """ # TODO(jelmer): Fetch pack data directly, don't create objects first. objects = self.fetch_objects( determine_wants, graph_walker, progress, get_tagged, depth=depth ) return pack_objects_to_data(objects) def fetch_objects( self, determine_wants, graph_walker, progress, get_tagged=None, depth=None, ): """Fetch the missing objects required for a set of revisions. Args: determine_wants: Function that takes a dictionary with heads and returns the list of heads to fetch. graph_walker: Object that can iterate over the list of revisions to fetch and has an "ack" method that will be called to acknowledge that a revision is present. progress: Simple progress function that will be called with updated progress strings. get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. depth: Shallow fetch depth Returns: iterator over objects, with __len__ implemented """ if depth not in (None, 0): raise NotImplementedError("depth not supported yet") refs = {} for ref, sha in self.get_refs().items(): try: obj = self.object_store[sha] except KeyError: warnings.warn( "ref %s points at non-present sha %s" % (ref.decode("utf-8", "replace"), sha.decode("ascii")), UserWarning, ) continue else: if isinstance(obj, Tag): refs[ref + ANNOTATED_TAG_SUFFIX] = obj.object[1] refs[ref] = sha wants = determine_wants(refs) if not isinstance(wants, list): raise TypeError("determine_wants() did not return a list") shallows = getattr(graph_walker, "shallow", frozenset()) unshallows = getattr(graph_walker, "unshallow", frozenset()) if wants == []: # TODO(dborowitz): find a way to short-circuit that doesn't change # this interface. if shallows or unshallows: # Do not send a pack in shallow short-circuit path return None return [] # If the graph walker is set up with an implementation that can # ACK/NAK to the wire, it will write data to the client through # this call as a side-effect. haves = self.object_store.find_common_revisions(graph_walker) # Deal with shallow requests separately because the haves do # not reflect what objects are missing if shallows or unshallows: # TODO: filter the haves commits from iter_shas. the specific # commits aren't missing. haves = [] parents_provider = ParentsProvider(self.object_store, shallows=shallows) def get_parents(commit): return parents_provider.get_parents(commit.id, commit) return self.object_store.iter_shas( self.object_store.find_missing_objects( haves, wants, self.get_shallow(), progress, get_tagged, get_parents=get_parents, ) ) def generate_pack_data(self, have, want, progress=None, ofs_delta=None): """Generate pack data objects for a set of wants/haves. Args: have: List of SHA1s of objects that should not be sent want: List of SHA1s of objects that should be sent ofs_delta: Whether OFS deltas can be included progress: Optional progress reporting method """ return self.object_store.generate_pack_data( have, want, shallow=self.get_shallow(), progress=progress, ofs_delta=ofs_delta, ) def get_graph_walker(self, heads=None): """Retrieve a graph walker. A graph walker is used by a remote repository (or proxy) to find out which objects are present in this repository. Args: heads: Repository heads to use (optional) Returns: A graph walker object """ if heads is None: heads = [ sha for sha in self.refs.as_dict(b"refs/heads").values() if sha in self.object_store ] parents_provider = ParentsProvider(self.object_store) return ObjectStoreGraphWalker( heads, parents_provider.get_parents, shallow=self.get_shallow() ) def get_refs(self) -> Dict[bytes, bytes]: """Get dictionary with all refs. Returns: A ``dict`` mapping ref names to SHA1s """ return self.refs.as_dict() def head(self) -> bytes: """Return the SHA1 pointed at by HEAD.""" return self.refs[b"HEAD"] def _get_object(self, sha, cls): assert len(sha) in (20, 40) ret = self.get_object(sha) if not isinstance(ret, cls): if cls is Commit: raise NotCommitError(ret) elif cls is Blob: raise NotBlobError(ret) elif cls is Tree: raise NotTreeError(ret) elif cls is Tag: raise NotTagError(ret) else: raise Exception( "Type invalid: %r != %r" % (ret.type_name, cls.type_name) ) return ret def get_object(self, sha: bytes) -> ShaFile: """Retrieve the object with the specified SHA. Args: sha: SHA to retrieve Returns: A ShaFile object Raises: KeyError: when the object can not be found """ return self.object_store[sha] def parents_provider(self): return ParentsProvider( self.object_store, grafts=self._graftpoints, shallows=self.get_shallow(), ) def get_parents(self, sha: bytes, commit: Commit = None) -> List[bytes]: """Retrieve the parents of a specific commit. If the specific commit is a graftpoint, the graft parents will be returned instead. Args: sha: SHA of the commit for which to retrieve the parents commit: Optional commit matching the sha Returns: List of parents """ return self.parents_provider().get_parents(sha, commit) def get_config(self): """Retrieve the config object. Returns: `ConfigFile` object for the ``.git/config`` file. """ raise NotImplementedError(self.get_config) def get_description(self): """Retrieve the description for this repository. Returns: String with the description of the repository as set by the user. """ raise NotImplementedError(self.get_description) def set_description(self, description): """Set the description for this repository. Args: description: Text to set as description for this repository. """ raise NotImplementedError(self.set_description) def get_config_stack(self) -> "StackedConfig": """Return a config stack for this repository. This stack accesses the configuration for both this repository itself (.git/config) and the global configuration, which usually lives in ~/.gitconfig. Returns: `Config` instance for this repository """ from dulwich.config import StackedConfig backends = [self.get_config()] + StackedConfig.default_backends() return StackedConfig(backends, writable=backends[0]) def get_shallow(self): """Get the set of shallow commits. Returns: Set of shallow commits. """ f = self.get_named_file("shallow") if f is None: return set() with f: return {line.strip() for line in f} def update_shallow(self, new_shallow, new_unshallow): """Update the list of shallow objects. Args: new_shallow: Newly shallow objects new_unshallow: Newly no longer shallow objects """ shallow = self.get_shallow() if new_shallow: shallow.update(new_shallow) if new_unshallow: shallow.difference_update(new_unshallow) if shallow: self._put_named_file( "shallow", b"".join([sha + b"\n" for sha in shallow]) ) else: self._del_named_file("shallow") def get_peeled(self, ref): """Get the peeled value of a ref. Args: ref: The refname to peel. Returns: The fully-peeled SHA1 of a tag object, after peeling all intermediate tags; if the original ref does not point to a tag, this will equal the original SHA1. """ cached = self.refs.get_peeled(ref) if cached is not None: return cached return self.object_store.peel_sha(self.refs[ref]).id def get_walker(self, include=None, *args, **kwargs): """Obtain a walker for this repository. Args: include: Iterable of SHAs of commits to include along with their ancestors. Defaults to [HEAD] exclude: Iterable of SHAs of commits to exclude along with their ancestors, overriding includes. order: ORDER_* constant specifying the order of results. Anything other than ORDER_DATE may result in O(n) memory usage. reverse: If True, reverse the order of output, requiring O(n) memory. max_entries: The maximum number of entries to yield, or None for no limit. paths: Iterable of file or subtree paths to show entries for. rename_detector: diff.RenameDetector object for detecting renames. follow: If True, follow path across renames/copies. Forces a default rename_detector. since: Timestamp to list commits after. until: Timestamp to list commits before. queue_cls: A class to use for a queue of commits, supporting the iterator protocol. The constructor takes a single argument, the Walker. Returns: A `Walker` object """ from dulwich.walk import Walker if include is None: include = [self.head()] if isinstance(include, str): include = [include] kwargs["get_parents"] = lambda commit: self.get_parents(commit.id, commit) return Walker(self.object_store, include, *args, **kwargs) def __getitem__(self, name): """Retrieve a Git object by SHA1 or ref. Args: name: A Git object SHA1 or a ref name Returns: A `ShaFile` object, such as a Commit or Blob Raises: KeyError: when the specified ref or object does not exist """ if not isinstance(name, bytes): raise TypeError( "'name' must be bytestring, not %.80s" % type(name).__name__ ) if len(name) in (20, 40): try: return self.object_store[name] except (KeyError, ValueError): pass try: return self.object_store[self.refs[name]] except RefFormatError: raise KeyError(name) def __contains__(self, name: bytes) -> bool: """Check if a specific Git object or ref is present. Args: name: Git object SHA1 or ref name """ if len(name) == 20 or (len(name) == 40 and valid_hexsha(name)): return name in self.object_store or name in self.refs else: return name in self.refs def __setitem__(self, name: bytes, value: Union[ShaFile, bytes]): """Set a ref. Args: name: ref name value: Ref value - either a ShaFile object, or a hex sha """ if name.startswith(b"refs/") or name == b"HEAD": if isinstance(value, ShaFile): self.refs[name] = value.id elif isinstance(value, bytes): self.refs[name] = value else: raise TypeError(value) else: raise ValueError(name) def __delitem__(self, name: bytes): """Remove a ref. Args: name: Name of the ref to remove """ if name.startswith(b"refs/") or name == b"HEAD": del self.refs[name] else: raise ValueError(name) def _get_user_identity(self, config: "StackedConfig", kind: str = None) -> bytes: """Determine the identity to use for new commits.""" # TODO(jelmer): Deprecate this function in favor of get_user_identity return get_user_identity(config) def _add_graftpoints(self, updated_graftpoints: Dict[bytes, List[bytes]]): """Add or modify graftpoints Args: updated_graftpoints: Dict of commit shas to list of parent shas """ # Simple validation for commit, parents in updated_graftpoints.items(): for sha in [commit] + parents: check_hexsha(sha, "Invalid graftpoint") self._graftpoints.update(updated_graftpoints) def _remove_graftpoints(self, to_remove: List[bytes] = []) -> None: """Remove graftpoints Args: to_remove: List of commit shas """ for sha in to_remove: del self._graftpoints[sha] def _read_heads(self, name): f = self.get_named_file(name) if f is None: return [] with f: return [line.strip() for line in f.readlines() if line.strip()] def do_commit( # noqa: C901 self, message=None, committer=None, author=None, commit_timestamp=None, commit_timezone=None, author_timestamp=None, author_timezone=None, tree=None, encoding=None, ref=b"HEAD", merge_heads=None, no_verify=False, ): """Create a new commit. If not specified, `committer` and `author` default to get_user_identity(..., 'COMMITTER') and get_user_identity(..., 'AUTHOR') respectively. Args: message: Commit message committer: Committer fullname author: Author fullname commit_timestamp: Commit timestamp (defaults to now) commit_timezone: Commit timestamp timezone (defaults to GMT) author_timestamp: Author timestamp (defaults to commit timestamp) author_timezone: Author timestamp timezone (defaults to commit timestamp timezone) tree: SHA1 of the tree root to use (if not specified the current index will be committed). encoding: Encoding ref: Optional ref to commit to (defaults to current branch) merge_heads: Merge heads (defaults to .git/MERGE_HEAD) no_verify: Skip pre-commit and commit-msg hooks Returns: New commit SHA1 """ c = Commit() if tree is None: index = self.open_index() c.tree = index.commit(self.object_store) else: if len(tree) != 40: raise ValueError("tree must be a 40-byte hex sha string") c.tree = tree try: if not no_verify: self.hooks["pre-commit"].execute() except HookError as e: raise CommitError(e) except KeyError: # no hook defined, silent fallthrough pass config = self.get_config_stack() if merge_heads is None: merge_heads = self._read_heads("MERGE_HEAD") if committer is None: committer = get_user_identity(config, kind="COMMITTER") check_user_identity(committer) c.committer = committer if commit_timestamp is None: # FIXME: Support GIT_COMMITTER_DATE environment variable commit_timestamp = time.time() c.commit_time = int(commit_timestamp) if commit_timezone is None: # FIXME: Use current user timezone rather than UTC commit_timezone = 0 c.commit_timezone = commit_timezone if author is None: author = get_user_identity(config, kind="AUTHOR") c.author = author check_user_identity(author) if author_timestamp is None: # FIXME: Support GIT_AUTHOR_DATE environment variable author_timestamp = commit_timestamp c.author_time = int(author_timestamp) if author_timezone is None: author_timezone = commit_timezone c.author_timezone = author_timezone if encoding is None: try: encoding = config.get(("i18n",), "commitEncoding") except KeyError: pass # No dice if encoding is not None: c.encoding = encoding if message is None: # FIXME: Try to read commit message from .git/MERGE_MSG raise ValueError("No commit message specified") try: if no_verify: c.message = message else: c.message = self.hooks["commit-msg"].execute(message) if c.message is None: c.message = message except HookError as e: raise CommitError(e) except KeyError: # no hook defined, message not modified c.message = message if ref is None: # Create a dangling commit c.parents = merge_heads self.object_store.add_object(c) else: try: old_head = self.refs[ref] c.parents = [old_head] + merge_heads self.object_store.add_object(c) ok = self.refs.set_if_equals( ref, old_head, c.id, message=b"commit: " + message, committer=committer, timestamp=commit_timestamp, timezone=commit_timezone, ) except KeyError: c.parents = merge_heads self.object_store.add_object(c) ok = self.refs.add_if_new( ref, c.id, message=b"commit: " + message, committer=committer, timestamp=commit_timestamp, timezone=commit_timezone, ) if not ok: # Fail if the atomic compare-and-swap failed, leaving the # commit and all its objects as garbage. raise CommitError("%s changed during commit" % (ref,)) self._del_named_file("MERGE_HEAD") try: self.hooks["post-commit"].execute() except HookError as e: # silent failure warnings.warn("post-commit hook failed: %s" % e, UserWarning) except KeyError: # no hook defined, silent fallthrough pass return c.id def read_gitfile(f): """Read a ``.git`` file. The first line of the file should start with "gitdir: " Args: f: File-like object to read from Returns: A path """ cs = f.read() if not cs.startswith("gitdir: "): raise ValueError("Expected file to start with 'gitdir: '") return cs[len("gitdir: ") :].rstrip("\n") class UnsupportedVersion(Exception): """Unsupported repository version.""" def __init__(self, version): self.version = version class Repo(BaseRepo): """A git repository backed by local disk. To open an existing repository, call the contructor with the path of the repository. To create a new repository, use the Repo.init class method. """ def __init__(self, root, object_store=None, bare=None): hidden_path = os.path.join(root, CONTROLDIR) if bare is None: if (os.path.isfile(hidden_path) or os.path.isdir(os.path.join(hidden_path, OBJECTDIR))): bare = False elif (os.path.isdir(os.path.join(root, OBJECTDIR)) and os.path.isdir(os.path.join(root, REFSDIR))): bare = True else: raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=root) ) self.bare = bare if bare is False: if os.path.isfile(hidden_path): with open(hidden_path, "r") as f: path = read_gitfile(f) self.bare = False self._controldir = os.path.join(root, path) else: self._controldir = hidden_path else: self._controldir = root commondir = self.get_named_file(COMMONDIR) if commondir is not None: with commondir: self._commondir = os.path.join( self.controldir(), os.fsdecode(commondir.read().rstrip(b"\r\n")), ) else: self._commondir = self._controldir self.path = root config = self.get_config() try: format_version = int(config.get("core", "repositoryformatversion")) except KeyError: format_version = 0 if format_version != 0: raise UnsupportedVersion(format_version) if object_store is None: object_store = DiskObjectStore.from_config( os.path.join(self.commondir(), OBJECTDIR), config ) refs = DiskRefsContainer( self.commondir(), self._controldir, logger=self._write_reflog ) BaseRepo.__init__(self, object_store, refs) self._graftpoints = {} graft_file = self.get_named_file( os.path.join("info", "grafts"), basedir=self.commondir() ) if graft_file: with graft_file: self._graftpoints.update(parse_graftpoints(graft_file)) graft_file = self.get_named_file("shallow", basedir=self.commondir()) if graft_file: with graft_file: self._graftpoints.update(parse_graftpoints(graft_file)) self.hooks["pre-commit"] = PreCommitShellHook(self.controldir()) self.hooks["commit-msg"] = CommitMsgShellHook(self.controldir()) self.hooks["post-commit"] = PostCommitShellHook(self.controldir()) self.hooks["post-receive"] = PostReceiveShellHook(self.controldir()) def _write_reflog( self, ref, old_sha, new_sha, committer, timestamp, timezone, message ): from .reflog import format_reflog_line path = os.path.join(self.controldir(), "logs", os.fsdecode(ref)) try: os.makedirs(os.path.dirname(path)) except FileExistsError: pass if committer is None: config = self.get_config_stack() committer = self._get_user_identity(config) check_user_identity(committer) if timestamp is None: timestamp = int(time.time()) if timezone is None: timezone = 0 # FIXME with open(path, "ab") as f: f.write( format_reflog_line( old_sha, new_sha, committer, timestamp, timezone, message ) + b"\n" ) @classmethod def discover(cls, start="."): """Iterate parent directories to discover a repository Return a Repo object for the first parent directory that looks like a Git repository. Args: start: The directory to start discovery from (defaults to '.') """ remaining = True path = os.path.abspath(start) while remaining: try: return cls(path) except NotGitRepository: path, remaining = os.path.split(path) raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=start) ) def controldir(self): """Return the path of the control directory.""" return self._controldir def commondir(self): """Return the path of the common directory. For a main working tree, it is identical to controldir(). For a linked working tree, it is the control directory of the main working tree.""" return self._commondir def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. Returns: True if permissions can be trusted, False otherwise. """ fname = os.path.join(self.path, ".probe-permissions") with open(fname, "w") as f: f.write("") st1 = os.lstat(fname) try: os.chmod(fname, st1.st_mode ^ stat.S_IXUSR) except PermissionError: return False st2 = os.lstat(fname) os.unlink(fname) mode_differs = st1.st_mode != st2.st_mode st2_has_exec = (st2.st_mode & stat.S_IXUSR) != 0 return mode_differs and st2_has_exec def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. Args: path: The path to the file, relative to the control dir. contents: A string to write to the file. """ path = path.lstrip(os.path.sep) with GitFile(os.path.join(self.controldir(), path), "wb") as f: f.write(contents) def _del_named_file(self, path): try: os.unlink(os.path.join(self.controldir(), path)) except FileNotFoundError: return def get_named_file(self, path, basedir=None): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-based Repo, the object returned need not be pointing to a file in that location. Args: path: The path to the file, relative to the control dir. basedir: Optional argument that specifies an alternative to the control dir. Returns: An open file object, or None if the file does not exist. """ # TODO(dborowitz): sanitize filenames, since this is used directly by # the dumb web serving code. if basedir is None: basedir = self.controldir() path = path.lstrip(os.path.sep) try: return open(os.path.join(basedir, path), "rb") except FileNotFoundError: return None def index_path(self): """Return path to the index file.""" return os.path.join(self.controldir(), INDEX_FILENAME) def open_index(self) -> "Index": """Open the index for this repository. Raises: NoIndexPresent: If no index is present Returns: The matching `Index` """ from dulwich.index import Index if not self.has_index(): raise NoIndexPresent() return Index(self.index_path()) def has_index(self): """Check if an index is present.""" # Bare repos must never have index files; non-bare repos may have a # missing index file, which is treated as empty. return not self.bare def stage(self, fs_paths): """Stage a set of paths. Args: fs_paths: List of paths, relative to the repository path """ root_path_bytes = os.fsencode(self.path) if not isinstance(fs_paths, list): fs_paths = [fs_paths] from dulwich.index import ( blob_from_path_and_stat, index_entry_from_stat, _fs_to_tree_path, ) index = self.open_index() blob_normalizer = self.get_blob_normalizer() for fs_path in fs_paths: if not isinstance(fs_path, bytes): fs_path = os.fsencode(fs_path) if os.path.isabs(fs_path): raise ValueError( "path %r should be relative to " "repository root, not absolute" % fs_path ) tree_path = _fs_to_tree_path(fs_path) full_path = os.path.join(root_path_bytes, fs_path) try: st = os.lstat(full_path) except OSError: # File no longer exists try: del index[tree_path] except KeyError: pass # already removed else: if not stat.S_ISREG(st.st_mode) and not stat.S_ISLNK(st.st_mode): try: del index[tree_path] except KeyError: pass else: + # Check if the file is already in the index + try: + index[tree_path] + new_file = False + except KeyError: + new_file = True + blob = blob_from_path_and_stat(full_path, st) - blob = blob_normalizer.checkin_normalize(blob, fs_path) + blob = blob_normalizer.checkin_normalize(blob, fs_path, new_file) self.object_store.add_object(blob) index[tree_path] = index_entry_from_stat(st, blob.id, 0) index.write() def clone( self, target_path, mkdir=True, bare=False, origin=b"origin", checkout=None, ): """Clone this repository. Args: target_path: Target path mkdir: Create the target directory bare: Whether to create a bare repository origin: Base name for refs in target repository cloned from this repository Returns: Created repository as `Repo` """ if not bare: target = self.init(target_path, mkdir=mkdir) else: if checkout: raise ValueError("checkout and bare are incompatible") target = self.init_bare(target_path, mkdir=mkdir) self.fetch(target) encoded_path = self.path if not isinstance(encoded_path, bytes): encoded_path = os.fsencode(encoded_path) ref_message = b"clone: from " + encoded_path target.refs.import_refs( b"refs/remotes/" + origin, self.refs.as_dict(b"refs/heads"), message=ref_message, ) target.refs.import_refs( b"refs/tags", self.refs.as_dict(b"refs/tags"), message=ref_message ) try: target.refs.add_if_new( DEFAULT_REF, self.refs[DEFAULT_REF], message=ref_message ) except KeyError: pass target_config = target.get_config() target_config.set(("remote", "origin"), "url", encoded_path) target_config.set( ("remote", "origin"), "fetch", "+refs/heads/*:refs/remotes/origin/*", ) target_config.write_to_path() # Update target head head_chain, head_sha = self.refs.follow(b"HEAD") if head_chain and head_sha is not None: target.refs.set_symbolic_ref(b"HEAD", head_chain[-1], message=ref_message) target[b"HEAD"] = head_sha if checkout is None: checkout = not bare if checkout: # Checkout HEAD to target dir target.reset_index() return target def reset_index(self, tree=None): """Reset the index back to a specific tree. Args: tree: Tree SHA to reset to, None for current HEAD tree. """ from dulwich.index import ( build_index_from_tree, validate_path_element_default, validate_path_element_ntfs, ) if tree is None: tree = self[b"HEAD"].tree config = self.get_config() honor_filemode = config.get_boolean(b"core", b"filemode", os.name != "nt") if config.get_boolean(b"core", b"core.protectNTFS", os.name == "nt"): validate_path_element = validate_path_element_ntfs else: validate_path_element = validate_path_element_default return build_index_from_tree( self.path, self.index_path(), self.object_store, tree, honor_filemode=honor_filemode, validate_path_element=validate_path_element, ) def get_config(self) -> "ConfigFile": """Retrieve the config object. Returns: `ConfigFile` object for the ``.git/config`` file. """ from dulwich.config import ConfigFile path = os.path.join(self._controldir, "config") try: return ConfigFile.from_path(path) except FileNotFoundError: ret = ConfigFile() ret.path = path return ret def get_description(self): """Retrieve the description of this repository. Returns: A string describing the repository or None. """ path = os.path.join(self._controldir, "description") try: with GitFile(path, "rb") as f: return f.read() except FileNotFoundError: return None def __repr__(self): return "" % self.path def set_description(self, description): """Set the description for this repository. Args: description: Text to set as description for this repository. """ self._put_named_file("description", description) @classmethod def _init_maybe_bare(cls, path, controldir, bare, object_store=None): for d in BASE_DIRECTORIES: os.mkdir(os.path.join(controldir, *d)) if object_store is None: object_store = DiskObjectStore.init(os.path.join(controldir, OBJECTDIR)) ret = cls(path, bare=bare, object_store=object_store) ret.refs.set_symbolic_ref(b"HEAD", DEFAULT_REF) ret._init_files(bare) return ret @classmethod def init(cls, path, mkdir=False): """Create a new repository. Args: path: Path in which to create the repository mkdir: Whether to create the directory Returns: `Repo` instance """ if mkdir: os.mkdir(path) controldir = os.path.join(path, CONTROLDIR) os.mkdir(controldir) _set_filesystem_hidden(controldir) return cls._init_maybe_bare(path, controldir, False) @classmethod def _init_new_working_directory(cls, path, main_repo, identifier=None, mkdir=False): """Create a new working directory linked to a repository. Args: path: Path in which to create the working tree. main_repo: Main repository to reference identifier: Worktree identifier mkdir: Whether to create the directory Returns: `Repo` instance """ if mkdir: os.mkdir(path) if identifier is None: identifier = os.path.basename(path) main_worktreesdir = os.path.join(main_repo.controldir(), WORKTREES) worktree_controldir = os.path.join(main_worktreesdir, identifier) gitdirfile = os.path.join(path, CONTROLDIR) with open(gitdirfile, "wb") as f: f.write(b"gitdir: " + os.fsencode(worktree_controldir) + b"\n") try: os.mkdir(main_worktreesdir) except FileExistsError: pass try: os.mkdir(worktree_controldir) except FileExistsError: pass with open(os.path.join(worktree_controldir, GITDIR), "wb") as f: f.write(os.fsencode(gitdirfile) + b"\n") with open(os.path.join(worktree_controldir, COMMONDIR), "wb") as f: f.write(b"../..\n") with open(os.path.join(worktree_controldir, "HEAD"), "wb") as f: f.write(main_repo.head() + b"\n") r = cls(path) r.reset_index() return r @classmethod def init_bare(cls, path, mkdir=False, object_store=None): """Create a new bare repository. ``path`` should already exist and be an empty directory. Args: path: Path to create bare repository in Returns: a `Repo` instance """ if mkdir: os.mkdir(path) return cls._init_maybe_bare(path, path, True, object_store=object_store) create = init_bare def close(self): """Close any files opened by this repository.""" self.object_store.close() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() def get_blob_normalizer(self): """Return a BlobNormalizer object""" # TODO Parse the git attributes files git_attributes = {} return BlobNormalizer(self.get_config_stack(), git_attributes) class MemoryRepo(BaseRepo): """Repo that stores refs, objects, and named files in memory. MemoryRepos are always bare: they have no working tree and no index, since those have a stronger dependency on the filesystem. """ def __init__(self): from dulwich.config import ConfigFile self._reflog = [] refs_container = DictRefsContainer({}, logger=self._append_reflog) BaseRepo.__init__(self, MemoryObjectStore(), refs_container) self._named_files = {} self.bare = True self._config = ConfigFile() self._description = None def _append_reflog(self, *args): self._reflog.append(args) def set_description(self, description): self._description = description def get_description(self): return self._description def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. Returns: True if permissions can be trusted, False otherwise. """ return sys.platform != "win32" def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. Args: path: The path to the file, relative to the control dir. contents: A string to write to the file. """ self._named_files[path] = contents def _del_named_file(self, path): try: del self._named_files[path] except KeyError: pass def get_named_file(self, path, basedir=None): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-baked Repo, the object returned need not be pointing to a file in that location. Args: path: The path to the file, relative to the control dir. Returns: An open file object, or None if the file does not exist. """ contents = self._named_files.get(path, None) if contents is None: return None return BytesIO(contents) def open_index(self): """Fail to open index for this repo, since it is bare. Raises: NoIndexPresent: Raised when no index is present """ raise NoIndexPresent() def get_config(self): """Retrieve the config object. Returns: `ConfigFile` object. """ return self._config @classmethod def init_bare(cls, objects, refs): """Create a new bare repository in memory. Args: objects: Objects for the new repository, as iterable refs: Refs as dictionary, mapping names to object SHA1s """ ret = cls() for obj in objects: ret.object_store.add_object(obj) for refname, sha in refs.items(): ret.refs.add_if_new(refname, sha) ret._init_files(bare=True) return ret diff --git a/dulwich/tests/test_index.py b/dulwich/tests/test_index.py index a187bd26..9a91cb93 100644 --- a/dulwich/tests/test_index.py +++ b/dulwich/tests/test_index.py @@ -1,841 +1,841 @@ # -*- coding: utf-8 -*- # test_index.py -- Tests for the git index # encoding: utf-8 # Copyright (C) 2008-2009 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for the index.""" from io import BytesIO import os import shutil import stat import struct import sys import tempfile import warnings from dulwich.index import ( Index, build_index_from_tree, cleanup_mode, commit_tree, get_unstaged_changes, index_entry_from_stat, read_index, read_index_dict, validate_path_element_default, validate_path_element_ntfs, write_cache_time, write_index, write_index_dict, _tree_to_fs_path, _fs_to_tree_path, IndexEntry, ) from dulwich.object_store import ( MemoryObjectStore, ) from dulwich.objects import ( Blob, Commit, Tree, S_IFGITLINK, ) from dulwich.repo import Repo from dulwich.tests import ( TestCase, skipIf, ) from dulwich.tests.utils import ( setup_warning_catcher, ) def can_symlink(): """Return whether running process can create symlinks.""" if sys.platform != "win32": # Platforms other than Windows should allow symlinks without issues. return True if not hasattr(os, "symlink"): # Older Python versions do not have `os.symlink` on Windows. return False test_source = tempfile.mkdtemp() test_target = test_source + "can_symlink" try: os.symlink(test_source, test_target) except (NotImplementedError, OSError): return False return True class IndexTestCase(TestCase): datadir = os.path.join(os.path.dirname(__file__), "data/indexes") def get_simple_index(self, name): return Index(os.path.join(self.datadir, name)) class SimpleIndexTestCase(IndexTestCase): def test_len(self): self.assertEqual(1, len(self.get_simple_index("index"))) def test_iter(self): self.assertEqual([b"bla"], list(self.get_simple_index("index"))) def test_iterobjects(self): self.assertEqual( [(b"bla", b"e69de29bb2d1d6434b8b29ae775ad8c2e48c5391", 33188)], list(self.get_simple_index("index").iterobjects()), ) def test_iterblobs(self): warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) self.assertEqual( [(b"bla", b"e69de29bb2d1d6434b8b29ae775ad8c2e48c5391", 33188)], list(self.get_simple_index("index").iterblobs()), ) expected_warning = PendingDeprecationWarning("Use iterobjects() instead.") for w in warnings_list: if type(w) == type(expected_warning) and w.args == expected_warning.args: break else: raise AssertionError( "Expected warning %r not in %r" % (expected_warning, warnings_list) ) def test_getitem(self): self.assertEqual( ( (1230680220, 0), (1230680220, 0), 2050, 3761020, 33188, 1000, 1000, 0, b"e69de29bb2d1d6434b8b29ae775ad8c2e48c5391", 0, 0, ), self.get_simple_index("index")[b"bla"], ) def test_empty(self): i = self.get_simple_index("notanindex") self.assertEqual(0, len(i)) self.assertFalse(os.path.exists(i._filename)) def test_against_empty_tree(self): i = self.get_simple_index("index") changes = list(i.changes_from_tree(MemoryObjectStore(), None)) self.assertEqual(1, len(changes)) (oldname, newname), (oldmode, newmode), (oldsha, newsha) = changes[0] self.assertEqual(b"bla", newname) self.assertEqual(b"e69de29bb2d1d6434b8b29ae775ad8c2e48c5391", newsha) class SimpleIndexWriterTestCase(IndexTestCase): def setUp(self): IndexTestCase.setUp(self) self.tempdir = tempfile.mkdtemp() def tearDown(self): IndexTestCase.tearDown(self) shutil.rmtree(self.tempdir) def test_simple_write(self): entries = [ ( b"barbla", IndexEntry( (1230680220, 0), (1230680220, 0), 2050, 3761020, 33188, 1000, 1000, 0, b"e69de29bb2d1d6434b8b29ae775ad8c2e48c5391", 0, 0) ) ] filename = os.path.join(self.tempdir, "test-simple-write-index") with open(filename, "wb+") as x: write_index(x, entries) with open(filename, "rb") as x: self.assertEqual(entries, list(read_index(x))) class ReadIndexDictTests(IndexTestCase): def setUp(self): IndexTestCase.setUp(self) self.tempdir = tempfile.mkdtemp() def tearDown(self): IndexTestCase.tearDown(self) shutil.rmtree(self.tempdir) def test_simple_write(self): entries = { b"barbla": IndexEntry( (1230680220, 0), (1230680220, 0), 2050, 3761020, 33188, 1000, 1000, 0, b"e69de29bb2d1d6434b8b29ae775ad8c2e48c5391", 0, 0, ) } filename = os.path.join(self.tempdir, "test-simple-write-index") with open(filename, "wb+") as x: write_index_dict(x, entries) with open(filename, "rb") as x: self.assertEqual(entries, read_index_dict(x)) class CommitTreeTests(TestCase): def setUp(self): super(CommitTreeTests, self).setUp() self.store = MemoryObjectStore() def test_single_blob(self): blob = Blob() blob.data = b"foo" self.store.add_object(blob) blobs = [(b"bla", blob.id, stat.S_IFREG)] rootid = commit_tree(self.store, blobs) self.assertEqual(rootid, b"1a1e80437220f9312e855c37ac4398b68e5c1d50") self.assertEqual((stat.S_IFREG, blob.id), self.store[rootid][b"bla"]) self.assertEqual(set([rootid, blob.id]), set(self.store._data.keys())) def test_nested(self): blob = Blob() blob.data = b"foo" self.store.add_object(blob) blobs = [(b"bla/bar", blob.id, stat.S_IFREG)] rootid = commit_tree(self.store, blobs) self.assertEqual(rootid, b"d92b959b216ad0d044671981196781b3258fa537") dirid = self.store[rootid][b"bla"][1] self.assertEqual(dirid, b"c1a1deb9788150829579a8b4efa6311e7b638650") self.assertEqual((stat.S_IFDIR, dirid), self.store[rootid][b"bla"]) self.assertEqual((stat.S_IFREG, blob.id), self.store[dirid][b"bar"]) self.assertEqual(set([rootid, dirid, blob.id]), set(self.store._data.keys())) class CleanupModeTests(TestCase): def assertModeEqual(self, expected, got): self.assertEqual(expected, got, "%o != %o" % (expected, got)) def test_file(self): self.assertModeEqual(0o100644, cleanup_mode(0o100000)) def test_executable(self): self.assertModeEqual(0o100755, cleanup_mode(0o100711)) self.assertModeEqual(0o100755, cleanup_mode(0o100700)) def test_symlink(self): self.assertModeEqual(0o120000, cleanup_mode(0o120711)) def test_dir(self): self.assertModeEqual(0o040000, cleanup_mode(0o40531)) def test_submodule(self): self.assertModeEqual(0o160000, cleanup_mode(0o160744)) class WriteCacheTimeTests(TestCase): def test_write_string(self): f = BytesIO() self.assertRaises(TypeError, write_cache_time, f, "foo") def test_write_int(self): f = BytesIO() write_cache_time(f, 434343) self.assertEqual(struct.pack(">LL", 434343, 0), f.getvalue()) def test_write_tuple(self): f = BytesIO() write_cache_time(f, (434343, 21)) self.assertEqual(struct.pack(">LL", 434343, 21), f.getvalue()) def test_write_float(self): f = BytesIO() write_cache_time(f, 434343.000000021) self.assertEqual(struct.pack(">LL", 434343, 21), f.getvalue()) class IndexEntryFromStatTests(TestCase): def test_simple(self): st = os.stat_result( ( 16877, 131078, 64769, 154, 1000, 1000, 12288, 1323629595, 1324180496, 1324180496, ) ) entry = index_entry_from_stat(st, "22" * 20, 0) self.assertEqual( entry, IndexEntry( 1324180496, 1324180496, 64769, 131078, 16384, 1000, 1000, 12288, "2222222222222222222222222222222222222222", 0, None, ), ) def test_override_mode(self): st = os.stat_result( ( stat.S_IFREG + 0o644, 131078, 64769, 154, 1000, 1000, 12288, 1323629595, 1324180496, 1324180496, ) ) entry = index_entry_from_stat(st, "22" * 20, 0, mode=stat.S_IFREG + 0o755) self.assertEqual( entry, IndexEntry( 1324180496, 1324180496, 64769, 131078, 33261, 1000, 1000, 12288, "2222222222222222222222222222222222222222", 0, None, ), ) class BuildIndexTests(TestCase): def assertReasonableIndexEntry(self, index_entry, mode, filesize, sha): self.assertEqual(index_entry[4], mode) # mode self.assertEqual(index_entry[7], filesize) # filesize self.assertEqual(index_entry[8], sha) # sha def assertFileContents(self, path, contents, symlink=False): if symlink: self.assertEqual(os.readlink(path), contents) else: with open(path, "rb") as f: self.assertEqual(f.read(), contents) def test_empty(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: tree = Tree() repo.object_store.add_object(tree) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id ) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 0) # Verify no files self.assertEqual([".git"], os.listdir(repo.path)) def test_git_dir(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filea = Blob.from_string(b"file a") filee = Blob.from_string(b"d") tree = Tree() tree[b".git/a"] = (stat.S_IFREG | 0o644, filea.id) tree[b"c/e"] = (stat.S_IFREG | 0o644, filee.id) repo.object_store.add_objects([(o, None) for o in [filea, filee, tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id ) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 1) # filea apath = os.path.join(repo.path, ".git", "a") self.assertFalse(os.path.exists(apath)) # filee epath = os.path.join(repo.path, "c", "e") self.assertTrue(os.path.exists(epath)) self.assertReasonableIndexEntry( index[b"c/e"], stat.S_IFREG | 0o644, 1, filee.id ) self.assertFileContents(epath, b"d") def test_nonempty(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filea = Blob.from_string(b"file a") fileb = Blob.from_string(b"file b") filed = Blob.from_string(b"file d") tree = Tree() tree[b"a"] = (stat.S_IFREG | 0o644, filea.id) tree[b"b"] = (stat.S_IFREG | 0o644, fileb.id) tree[b"c/d"] = (stat.S_IFREG | 0o644, filed.id) repo.object_store.add_objects( [(o, None) for o in [filea, fileb, filed, tree]] ) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id ) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 3) # filea apath = os.path.join(repo.path, "a") self.assertTrue(os.path.exists(apath)) self.assertReasonableIndexEntry( index[b"a"], stat.S_IFREG | 0o644, 6, filea.id ) self.assertFileContents(apath, b"file a") # fileb bpath = os.path.join(repo.path, "b") self.assertTrue(os.path.exists(bpath)) self.assertReasonableIndexEntry( index[b"b"], stat.S_IFREG | 0o644, 6, fileb.id ) self.assertFileContents(bpath, b"file b") # filed dpath = os.path.join(repo.path, "c", "d") self.assertTrue(os.path.exists(dpath)) self.assertReasonableIndexEntry( index[b"c/d"], stat.S_IFREG | 0o644, 6, filed.id ) self.assertFileContents(dpath, b"file d") # Verify no extra files self.assertEqual([".git", "a", "b", "c"], sorted(os.listdir(repo.path))) self.assertEqual(["d"], sorted(os.listdir(os.path.join(repo.path, "c")))) @skipIf(not getattr(os, "sync", None), "Requires sync support") def test_norewrite(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filea = Blob.from_string(b"file a") filea_path = os.path.join(repo_dir, "a") tree = Tree() tree[b"a"] = (stat.S_IFREG | 0o644, filea.id) repo.object_store.add_objects([(o, None) for o in [filea, tree]]) # First Write build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id ) # Use sync as metadata can be cached on some FS os.sync() mtime = os.stat(filea_path).st_mtime # Test Rewrite build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id ) os.sync() self.assertEqual(mtime, os.stat(filea_path).st_mtime) # Modify content with open(filea_path, "wb") as fh: fh.write(b"test a") os.sync() mtime = os.stat(filea_path).st_mtime # Test rewrite build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id ) os.sync() with open(filea_path, "rb") as fh: self.assertEqual(b"file a", fh.read()) @skipIf(not can_symlink(), "Requires symlink support") def test_symlink(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filed = Blob.from_string(b"file d") filee = Blob.from_string(b"d") tree = Tree() tree[b"c/d"] = (stat.S_IFREG | 0o644, filed.id) tree[b"c/e"] = (stat.S_IFLNK, filee.id) # symlink repo.object_store.add_objects([(o, None) for o in [filed, filee, tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id ) # Verify index entries index = repo.open_index() # symlink to d epath = os.path.join(repo.path, "c", "e") self.assertTrue(os.path.exists(epath)) self.assertReasonableIndexEntry( index[b"c/e"], stat.S_IFLNK, 0 if sys.platform == "win32" else 1, filee.id, ) self.assertFileContents(epath, "d", symlink=True) def test_no_decode_encode(self): repo_dir = tempfile.mkdtemp() repo_dir_bytes = os.fsencode(repo_dir) self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo file = Blob.from_string(b"foo") tree = Tree() latin1_name = u"À".encode("latin1") latin1_path = os.path.join(repo_dir_bytes, latin1_name) utf8_name = u"À".encode("utf8") utf8_path = os.path.join(repo_dir_bytes, utf8_name) tree[latin1_name] = (stat.S_IFREG | 0o644, file.id) tree[utf8_name] = (stat.S_IFREG | 0o644, file.id) repo.object_store.add_objects([(o, None) for o in [file, tree]]) try: build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id ) except OSError as e: if e.errno == 92 and sys.platform == "darwin": # Our filename isn't supported by the platform :( self.skipTest("can not write filename %r" % e.filename) else: raise except UnicodeDecodeError: # This happens e.g. with python3.6 on Windows. # It implicitly decodes using utf8, which doesn't work. self.skipTest("can not implicitly convert as utf8") # Verify index entries index = repo.open_index() self.assertIn(latin1_name, index) self.assertIn(utf8_name, index) self.assertTrue(os.path.exists(latin1_path)) self.assertTrue(os.path.exists(utf8_path)) def test_git_submodule(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: filea = Blob.from_string(b"file alalala") subtree = Tree() subtree[b"a"] = (stat.S_IFREG | 0o644, filea.id) c = Commit() c.tree = subtree.id c.committer = c.author = b"Somebody " c.commit_time = c.author_time = 42342 c.commit_timezone = c.author_timezone = 0 c.parents = [] c.message = b"Subcommit" tree = Tree() tree[b"c"] = (S_IFGITLINK, c.id) repo.object_store.add_objects([(o, None) for o in [tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id ) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 1) # filea apath = os.path.join(repo.path, "c/a") self.assertFalse(os.path.exists(apath)) # dir c cpath = os.path.join(repo.path, "c") self.assertTrue(os.path.isdir(cpath)) self.assertEqual(index[b"c"][4], S_IFGITLINK) # mode self.assertEqual(index[b"c"][8], c.id) # sha def test_git_submodule_exists(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: filea = Blob.from_string(b"file alalala") subtree = Tree() subtree[b"a"] = (stat.S_IFREG | 0o644, filea.id) c = Commit() c.tree = subtree.id c.committer = c.author = b"Somebody " c.commit_time = c.author_time = 42342 c.commit_timezone = c.author_timezone = 0 c.parents = [] c.message = b"Subcommit" tree = Tree() tree[b"c"] = (S_IFGITLINK, c.id) os.mkdir(os.path.join(repo_dir, "c")) repo.object_store.add_objects([(o, None) for o in [tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id ) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 1) # filea apath = os.path.join(repo.path, "c/a") self.assertFalse(os.path.exists(apath)) # dir c cpath = os.path.join(repo.path, "c") self.assertTrue(os.path.isdir(cpath)) self.assertEqual(index[b"c"][4], S_IFGITLINK) # mode self.assertEqual(index[b"c"][8], c.id) # sha class GetUnstagedChangesTests(TestCase): def test_get_unstaged_changes(self): """Unit test for get_unstaged_changes.""" repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Commit a dummy file then modify it foo1_fullpath = os.path.join(repo_dir, "foo1") with open(foo1_fullpath, "wb") as f: f.write(b"origstuff") foo2_fullpath = os.path.join(repo_dir, "foo2") with open(foo2_fullpath, "wb") as f: f.write(b"origstuff") repo.stage(["foo1", "foo2"]) repo.do_commit( b"test status", author=b"author ", committer=b"committer ", ) with open(foo1_fullpath, "wb") as f: f.write(b"newstuff") # modify access and modify time of path os.utime(foo1_fullpath, (0, 0)) - changes = get_unstaged_changes(repo.open_index(), repo_dir) + changes = get_unstaged_changes(repo.open_index(), repo) self.assertEqual(list(changes), [b"foo1"]) def test_get_unstaged_deleted_changes(self): """Unit test for get_unstaged_changes.""" repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Commit a dummy file then remove it foo1_fullpath = os.path.join(repo_dir, "foo1") with open(foo1_fullpath, "wb") as f: f.write(b"origstuff") repo.stage(["foo1"]) repo.do_commit( b"test status", author=b"author ", committer=b"committer ", ) os.unlink(foo1_fullpath) - changes = get_unstaged_changes(repo.open_index(), repo_dir) + changes = get_unstaged_changes(repo.open_index(), repo) self.assertEqual(list(changes), [b"foo1"]) def test_get_unstaged_changes_removed_replaced_by_directory(self): """Unit test for get_unstaged_changes.""" repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Commit a dummy file then modify it foo1_fullpath = os.path.join(repo_dir, "foo1") with open(foo1_fullpath, "wb") as f: f.write(b"origstuff") repo.stage(["foo1"]) repo.do_commit( b"test status", author=b"author ", committer=b"committer ", ) os.remove(foo1_fullpath) os.mkdir(foo1_fullpath) - changes = get_unstaged_changes(repo.open_index(), repo_dir) + changes = get_unstaged_changes(repo.open_index(), repo) self.assertEqual(list(changes), [b"foo1"]) @skipIf(not can_symlink(), "Requires symlink support") def test_get_unstaged_changes_removed_replaced_by_link(self): """Unit test for get_unstaged_changes.""" repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Commit a dummy file then modify it foo1_fullpath = os.path.join(repo_dir, "foo1") with open(foo1_fullpath, "wb") as f: f.write(b"origstuff") repo.stage(["foo1"]) repo.do_commit( b"test status", author=b"author ", committer=b"committer ", ) os.remove(foo1_fullpath) os.symlink(os.path.dirname(foo1_fullpath), foo1_fullpath) - changes = get_unstaged_changes(repo.open_index(), repo_dir) + changes = get_unstaged_changes(repo.open_index(), repo) self.assertEqual(list(changes), [b"foo1"]) class TestValidatePathElement(TestCase): def test_default(self): self.assertTrue(validate_path_element_default(b"bla")) self.assertTrue(validate_path_element_default(b".bla")) self.assertFalse(validate_path_element_default(b".git")) self.assertFalse(validate_path_element_default(b".giT")) self.assertFalse(validate_path_element_default(b"..")) self.assertTrue(validate_path_element_default(b"git~1")) def test_ntfs(self): self.assertTrue(validate_path_element_ntfs(b"bla")) self.assertTrue(validate_path_element_ntfs(b".bla")) self.assertFalse(validate_path_element_ntfs(b".git")) self.assertFalse(validate_path_element_ntfs(b".giT")) self.assertFalse(validate_path_element_ntfs(b"..")) self.assertFalse(validate_path_element_ntfs(b"git~1")) class TestTreeFSPathConversion(TestCase): def test_tree_to_fs_path(self): tree_path = u"délwíçh/foo".encode("utf8") fs_path = _tree_to_fs_path(b"/prefix/path", tree_path) self.assertEqual( fs_path, os.fsencode(os.path.join(u"/prefix/path", u"délwíçh", u"foo")), ) def test_fs_to_tree_path_str(self): fs_path = os.path.join(os.path.join(u"délwíçh", u"foo")) tree_path = _fs_to_tree_path(fs_path) self.assertEqual(tree_path, u"délwíçh/foo".encode("utf-8")) def test_fs_to_tree_path_bytes(self): fs_path = os.path.join(os.fsencode(os.path.join(u"délwíçh", u"foo"))) tree_path = _fs_to_tree_path(fs_path) self.assertEqual(tree_path, u"délwíçh/foo".encode("utf-8")) diff --git a/dulwich/tests/test_porcelain.py b/dulwich/tests/test_porcelain.py index e6442b73..55007294 100644 --- a/dulwich/tests/test_porcelain.py +++ b/dulwich/tests/test_porcelain.py @@ -1,2710 +1,2750 @@ # test_porcelain.py -- porcelain tests # Copyright (C) 2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for dulwich.porcelain.""" from io import BytesIO, StringIO import os import platform import re import shutil import stat import subprocess import sys import tarfile import tempfile import time from unittest import skipIf from dulwich import porcelain from dulwich.diff_tree import tree_changes from dulwich.errors import CommitError from dulwich.objects import ( Blob, Tag, Tree, ZERO_SHA, ) from dulwich.repo import ( NoIndexPresent, Repo, ) from dulwich.tests import ( TestCase, ) from dulwich.tests.utils import ( build_commit_graph, make_commit, make_object, ) def flat_walk_dir(dir_to_walk): for dirpath, _, filenames in os.walk(dir_to_walk): rel_dirpath = os.path.relpath(dirpath, dir_to_walk) if not dirpath == dir_to_walk: yield rel_dirpath for filename in filenames: if dirpath == dir_to_walk: yield filename else: yield os.path.join(rel_dirpath, filename) class PorcelainTestCase(TestCase): def setUp(self): super(PorcelainTestCase, self).setUp() self.test_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.test_dir) self.repo_path = os.path.join(self.test_dir, "repo") self.repo = Repo.init(self.repo_path, mkdir=True) self.addCleanup(self.repo.close) class PorcelainGpgTestCase(PorcelainTestCase): DEFAULT_KEY = """ -----BEGIN PGP PRIVATE KEY BLOCK----- lQVYBGBjIyIBDADAwydvMPQqeEiK54FG1DHwT5sQejAaJOb+PsOhVa4fLcKsrO3F g5CxO+/9BHCXAr8xQAtp/gOhDN05fyK3MFyGlL9s+Cd8xf34S3R4rN/qbF0oZmaa FW0MuGnniq54HINs8KshadVn1Dhi/GYSJ588qNFRl/qxFTYAk+zaGsgX/QgFfy0f djWXJLypZXu9D6DlyJ0cPSzUlfBkI2Ytx6grzIquRjY0FbkjK3l+iGsQ+ebRMdcP Sqd5iTN9XuzIUVoBFAZBRjibKV3N2wxlnCbfLlzCyDp7rktzSThzjJ2pVDuLrMAx 6/L9hIhwmFwdtY4FBFGvMR0b0Ugh3kCsRWr8sgj9I7dUoLHid6ObYhJFhnD3GzRc U+xX1uy3iTCqJDsG334aQIhC5Giuxln4SUZna2MNbq65ksh38N1aM/t3+Dc/TKVB rb5KWicRPCQ4DIQkHMDCSPyj+dvRLCPzIaPvHD7IrCfHYHOWuvvPGCpwjo0As3iP IecoMeguPLVaqgcAEQEAAQAL/i5/pQaUd4G7LDydpbixPS6r9UrfPrU/y5zvBP/p DCynPDutJ1oq539pZvXQ2VwEJJy7x0UVKkjyMndJLNWly9wHC7o8jkHx/NalVP47 LXR+GWbCdOOcYYbdAWcCNB3zOtzPnWhdAEagkc2G9xRQDIB0dLHLCIUpCbLP/CWM qlHnDsVMrVTWjgzcpsnyGgw8NeLYJtYGB8dsN+XgCCjo7a9LEvUBKNgdmWBbf14/ iBw7PCugazFcH9QYfZwzhsi3nqRRagTXHbxFRG0LD9Ro9qCEutHYGP2PJ59Nj8+M zaVkJj/OxWxVOGvn2q16mQBCjKpbWfqXZVVl+G5DGOmiSTZqXy+3j6JCKdOMy6Qd JBHOHhFZXYmWYaaPzoc33T/C3QhMfY5sOtUDLJmV05Wi4dyBeNBEslYgUuTk/jXb 5ZAie25eDdrsoqkcnSs2ZguMF7AXhe6il2zVhUUMs/6UZgd6I7I4Is0HXT/pnxEp uiTRFu4v8E+u+5a8O3pffe5boQYA3TsIxceen20qY+kRaTOkURHMZLn/y6KLW8bZ rNJyXWS9hBAcbbSGhfOwYfzbDCM17yPQO3E2zo8lcGdRklUdIIaCxQwtu36N5dfx OLCCQc5LmYdl/EAm91iAhrr7dNntZ18MU09gdzUu+ONZwu4CP3cJT83+qYZULso8 4Fvd/X8IEfGZ7kM+ylrdqBwtlrn8yYXtom+ows2M2UuNR53B+BUOd73kVLTkTCjE JH63+nE8BqG7tDLCMws+23SAA3xxBgDfDrr0x7zCozQKVQEqBzQr9Uoo/c/ZjAfi syzNSrDz+g5gqJYtuL9XpPJVWf6V1GXVyJlSbxR9CjTkBxmlPxpvV25IsbVSsh0o aqkf2eWpbCL6Qb2E0jd1rvf8sGeTTohzYfiSVVsC2t9ngRO/CmetizwQBvRzLGMZ 4mtAPiy7ZEDc2dFrPp7zlKISYmJZUx/DJVuZWuOrVMpBP+bSgJXoMTlICxZUqUnE 2VKVStb/L+Tl8XCwIWdrZb9BaDnHqfcGAM2B4HNPxP88Yj1tEDly/vqeb3vVMhj+ S1lunnLdgxp46YyuTMYAzj88eCGurRtzBsdxxlGAsioEnZGebEqAHQbieKq/DO6I MOMZHMSVBDqyyIx3assGlxSX8BSFW0lhKyT7i0XqnAgCJ9f/5oq0SbFGq+01VQb7 jIx9PbcYJORxsE0JG/CXXPv27bRtQXsudkWGSYvC0NLOgk4z8+kQpQtyFh16lujq WRwMeriu0qNDjCa1/eHIKDovhAZ3GyO5/9m1tBlUZXN0IFVzZXIgPHRlc3RAdGVz dC5jb20+iQHUBBMBCAA+FiEEjrR8MQ4fJK44PYMvfN2AClLmXiYFAmBjIyICGwMF CQPCZwAFCwkIBwIGFQoJCAsCBBYCAwECHgECF4AACgkQfN2AClLmXiZeGQwAoma6 2OJuX+OROtZR3eK6laY39FS2a8RgA6MTwU0htM4keSWBbDrQD05vUx1D/paD6XEu S2OUo8pGsarP6TE3S3yRT4ImHpnt52TiOemMErGCHACmmyDCOkvGV2Sg/pb0zINN sBMHMvDYBSZ2Xcvy5LGXbo5C/lja0Jjg5PsCWWuhrAVaNqJ8IqxhiHIy1F2H5RXj c++pjl2GyBIDR8IdQlG0EGNNpUgnL1zvUkr5Tbk/H8KJh+PgcBlgip9ocdADcSKI ITvxjingp16LGgo2jPpCqyfjp43n71FRJTJbuTqOZzGL9c5DwYoCt1BgX379ZLYx luzeGKu3Vz+L8fpM5fiTg35lXSpzw2mJdhVrBSt54oF+kjs0pON93OOW0TF3z8Oi 1FmJ6bMUHFrxp63/sTnryGCuYFgbWpb0QPP9i9TQvn3aajlLll19JkgoIh750JGh QH4JZixX9k32jzr38kzy9RA5FBqhz2egp7Z22uiIhmeR/2zhpFpAdX1uroF9nQVY BGBjIyIBDADghIo9wXnRxzfdDTvwnP8dHpLAIaPokgdpyLswqUCixJWiW2xcV6we UjEWwH6neN/t1uZYVehbrotxVPla+MPvzhxp6/cmG+2lhzEBOp6zRwnL1wIB6HoK JfpREhyMc8rLR0zMso1L1bJTyydvnu07a7BWo3VWKjilb0rEZZUSD/2hidx5HxMO JSoidLWed/PPuv6yht3NtA4UThlcfldm9G6PbqCdm1kMEKAkq0wVJvhPJ6gEFRNJ imgygfUwMDFXEIhQtxjgdV5Uoz3O5452VLoRsDlgpi3E0WDGj7WXDaO5uSU0T5aJ gVgHCP/fxZhHuQFk2YYIl5nCBpOZyWWI0IKmscTuEwzpkhICQDQFvcMZ5ibsl7wA 2P7YTrQfFDMjjzuaK80GYPfxDFlyKUyLqFt8w/QzsZLDLX7+jxIEpbRAaMw/JsWq m5BMxxbS3CIQiS5S3oSKDsNINelqWFfwvLhvlQra8gIxyNTlek25OdgG66BiiX+s eH8A/ql+F+MAEQEAAQAL/1jrNSLjMt9pwo6qFKClVQZP2vf7+sH7v7LeHIDXr3En YUnVYnOqB1FU5PspTp/+J9W25DB9CZLx7Gj8qeslFdiuLSOoIBB4RCToB3kAoeTH 0DHqW/GshFTrmJkuDp9zpo/ek6SIXJx5rHAyR9KVw0fizQprH2f6PcgLbTWeM61d Juqowmg37eCOyIKv7VQvFqEhYokLD+JNmrvg+Htg0DXGvdjRjAwPf/NezEXpj67a 6cHTp1/Chwp7pevG+3fTxaCJFesl5/TxxtnaBLE8m2uo/S6Hxgn9l0edonroe1Ql TjEqGLy27qi2z5Rem+v6GWNDRgvAWur13v8FNdyduHlioG/NgRsU9mE2MYeFsfi3 cfNpJQp/wC9PSCIXrb/45mkS8KyjZpCrIPB9RV/m0MREq01TPom7rstZc4A1pD0O t7AtUYS3e95zLyEmeLziPJ9fV4fgPmEudDr1uItnmV0LOskKlpg5sc0hhdrwYoob fkKt2dx6DqfMlcM1ZkUbLQYA4jwfpFJG4HmYvjL2xCJxM0ycjvMbqFN+4UjgYWVl RfOrm1V4Op86FjbRbV6OOCNhznotAg7mul4xtzrrTkK8o3YLBeJseDgl4AWuzXtN a9hE0XpK9gJoEHUuBOOsamVh2HpXESFyE5CclOV7JSh541TlZKfnqfZYCg4JSbp0 UijkawCL5bJJUiGGMD9rZUxIAKQO1DvUEzptS7Jl6S3y5sbIIhilp4KfYWbSk3PP u9CnZD5bLhEQp0elxnb/IL8PBgD+DpTeC8unkGKXUpbe9x0ISI6V1D6FmJq/FxNg 7fMa3QChfGiAyoTm80ZETynj+blRaDO3gY4lTLa3Opubof1EqK2QmwXmpyvXEZNY cQfQ2CCSGOWUCK8jEQamUPf1PWndZXJUmROI1WukhlL71V/ir6zQeVCv1wcwPwcl JPnAe87upEklnCYpvsEldwHUX9u0BWzoULIEsi+ddtHmT0KTeF/DHRy0W15jIHbj Fqhqckj1/6fmr7l7kIi/kN4vWe0F/0Q8IXX+cVMgbl3aIuaGcvENLGcoAsAtPGx8 8SfRgmfuHK64Y7hx1m+Bo215rxJzZRjqHTBPp0BmCi+JKkaavIBrYRbsx20gveI4 dzhLcUhBkiT4Q7oz0/VbGHS1CEf9KFeS/YOGj57s4yHauSVI0XdP9kBRTWmXvBkz sooB2cKHhwhUN7iiT1k717CiTNUT6Q/pcPFCyNuMoBBGQTU206JEgIjQvI3f8xMU MGmGVVQz9/k716ycnhb2JZ/Q/AyQIeHJiQG8BBgBCAAmFiEEjrR8MQ4fJK44PYMv fN2AClLmXiYFAmBjIyICGwwFCQPCZwAACgkQfN2AClLmXibetAwAi7KnMpFR2DOu JKMa+PyCLpaXFVp/Y3uzGXSmDZJ9PFJ8CzQlY4S61Zkfesq8woTmvk58SSxSgBAp UixUK0uFO/s0q5ibODgBXpUQIFW0uhrDpbA08pGunPo/E06Q+5kVocSh9raI1R16 7ke/FcFd5P7BNuXT1CJW70jcK3jh/L3SFZa+PewKwcgrNkQIg2411vek1VSQB+DP URb/OCqD7gFkj1/BaQgMxO1tZUx9tIt/YuwqnxIOOxjnD13aRinZ2bK1SEsG/dyx y19ZB0d6d7eTGdYNWIAClHbnzbsEm5QzcYsDBqGiRS6Je38Wc5qD+z0h/R1GJXjW d9QAenkb7v9v10yLZH0udW8PY5OQ5IjtcUMVppvAn5ZWsApw/eCFEEsvcNuYSnY2 FO+dmjq6Fc8XdqR12jaSaiaSFIdhkTN83HSdZ/luDBqP4mVDLhRnOkLnDZF1HDeR BcZYEcqkDeW64mdTo65ILOPQ+HMCK12AnnBsbyfbsWAUczkQ7GVq =YPjc -----END PGP PRIVATE KEY BLOCK----- """ DEFAULT_KEY_ID = "8EB47C310E1F24AE383D832F7CDD800A52E65E26" NON_DEFAULT_KEY = """ -----BEGIN PGP PRIVATE KEY BLOCK----- lQVYBGBjI0ABDADGWBRp+t02emfzUlhrc1psqIhhecFm6Em0Kv33cfDpnfoMF1tK Yy/4eLYIR7FmpdbFPcDThFNHbXJzBi00L1mp0XQE2l50h/2bDAAgREdZ+NVo5a7/ RSZjauNU1PxW6pnXMehEh1tyIQmV78jAukaakwaicrpIenMiFUN3fAKHnLuFffA6 t0f3LqJvTDhUw/o2vPgw5e6UDQhA1C+KTv1KXVrhJNo88a3hZqCZ76z3drKR411Q zYgT4DUb8lfnbN+z2wfqT9oM5cegh2k86/mxAA3BYOeQrhmQo/7uhezcgbxtdGZr YlbuaNDTSBrn10ZoaxLPo2dJe2zWxgD6MpvsGU1w3tcRW508qo/+xoWp2/pDzmok +uhOh1NAj9zB05VWBz1r7oBgCOIKpkD/LD4VKq59etsZ/UnrYDwKdXWZp7uhshkU M7N35lUJcR76a852dlMdrgpmY18+BP7+o7M+5ElHTiqQbMuE1nHTg8RgVpdV+tUx dg6GWY/XHf5asm8AEQEAAQAL/A85epOp+GnymmEQfI3+5D178D//Lwu9n86vECB6 xAHCqQtdjZnXpDp/1YUsL59P8nzgYRk7SoMskQDoQ/cB/XFuDOhEdMSgHaTVlnrj ktCCq6rqGnUosyolbb64vIfVaSqd/5SnCStpAsnaBoBYrAu4ZmV4xfjDQWwn0q5s u+r56mD0SkjPgbwk/b3qTVagVmf2OFzUgWwm1e/X+bA1oPag1NV8VS4hZPXswT4f qhiyqUFOgP6vUBcqehkjkIDIl/54xII7/P5tp3LIZawvIXqHKNTqYPCqaCqCj+SL vMYDIb6acjescfZoM71eAeHAANeFZzr/rwfBT+dEP6qKmPXNcvgE11X44ZCr04nT zOV/uDUifEvKT5qgtyJpSFEVr7EXubJPKoNNhoYqq9z1pYU7IedX5BloiVXKOKTY 0pk7JkLqf3g5fYtXh/wol1owemITJy5V5PgaqZvk491LkI6S+kWC7ANYUg+TDPIW afxW3E5N1CYV6XDAl0ZihbLcoQYAy0Ky/p/wayWKePyuPBLwx9O89GSONK2pQljZ yaAgxPQ5/i1vx6LIMg7k/722bXR9W3zOjWOin4eatPM3d2hkG96HFvnBqXSmXOPV 03Xqy1/B5Tj8E9naLKUHE/OBQEc363DgLLG9db5HfPlpAngeppYPdyWkhzXyzkgS PylaE5eW3zkdjEbYJ6RBTecTZEgBaMvJNPdWbn//frpP7kGvyiCg5Es+WjLInUZ6 0sdifcNTCewzLXK80v/y5mVOdJhPBgD5zs9cYdyiQJayqAuOr+He1eMHMVUbm9as qBmPrst398eBW9ZYF7eBfTSlUf6B+WnvyLKEGsUf/7IK0EWDlzoBuWzWiHjUAY1g m9eTV2MnvCCCefqCErWwfFo2nWOasAZA9sKD+ICIBY4tbtvSl4yfLBzTMwSvs9ZS K1ocPSYUnhm2miSWZ8RLZPH7roHQasNHpyq/AX7DahFf2S/bJ+46ZGZ8Pigr7hA+ MjmpQ4qVdb5SaViPmZhAKO+PjuCHm+EF/2H0Y3Sl4eXgxZWoQVOUeXdWg9eMfYrj XDtUMIFppV/QxbeztZKvJdfk64vt/crvLsOp0hOky9cKwY89r4QaHfexU3qR+qDq UlMvR1rHk7dS5HZAtw0xKsFJNkuDxvBkMqv8Los8zp3nUl+U99dfZOArzNkW38wx FPa0ixkC9za2BkDrWEA8vTnxw0A2upIFegDUhwOByrSyfPPnG3tKGeqt3Izb/kDk Q9vmo+HgxBOguMIvlzbBfQZwtbd/gXzlvPqCtCJBbm90aGVyIFRlc3QgVXNlciA8 dGVzdDJAdGVzdC5jb20+iQHUBBMBCAA+FiEEapM5P1DF5qzT1vtFuTYhLttOFMAF AmBjI0ACGwMFCQPCZwAFCwkIBwIGFQoJCAsCBBYCAwECHgECF4AACgkQuTYhLttO FMBRlAwAwVQJbAhR39vlSKh2ksjZvM+dZhNEP0UVtE+5D0Ukx3OHPY+zqe6Orkf9 FgXY0h6byr6gudsEnBs4wZ7LgJDiBY/qQBtq93Fy/hZurvDTsMdv9qpSjDroCfTO O1Q40aqlucoaTjtIGwFNXRmd6Xi9IB+dGnFgM0l68MXhkSVnj0LfAK5UxdIQ/4tq MdE0pWn1x+ebdjpBHO6Q4XY+vXfSqO2rOg3uxL54GR9IqNeWUNqIMvNyBO0XkGq5 93bCi4s1dDr101RQsb6MQxYDdZ5tdChyXBQnx5nMWaUALm0GRF8FoFEB4oMoF5gD 2nqSCdnMNVkWich46xvL2h10EzOujvaob+c4FZc+n8gk5GnkuigMOqMJ1xY/QrC6 Ce//RHm2k0NoEPFQaRsHJIQxwZZwmHkzREDnfeEj8hSExM1anQirmIsMtI8knD/8 Vl9HzNfeLCDPtcC28a1vXjsJCF7j4LRInpSgDzovFdARYvCs6equsb3UYRA17O9W bVHhX54dnQVXBGBjI0ABDADJMBYIcG0Yil9YxFs7aYzNbd7alUAr89VbY8eIGPHP 3INFPM1wlBQCu+4j6xdEbhMpppLBZ9A5TEylP4C6qLtPa+oLtPeuSw8gHDE10XE4 lbgPs376rL60XdImSOHhiduACUefYjqpcmFH9Bim1CC+koArYrSQJQx1Jri+OpnT aL/8UID0KzD/kEgMVGlHIVj9oJmb4+j9pW8I/g0wDSnIaEKFMxqu6SIVJ1GWj+MU MvZigjLCsNCZd7PnbOC5VeU3SsXj6he74Jx0AmGMPWIHi9M0DjHO5d1cCbXTnud8 xxM1bOh47aCTnMK5cVyIr+adihgJpVVhrndSM8aklBPRgtozrGNCgF2CkYU2P1bl xfloNr/8UZpM83o+s1aObBszzRNLxnpNORqoLqjfPtLEPQnagxE+4EapCq0NZ/x6 yO5VTwwpNljdFAEk40uGuKyn1QA3uNMHy5DlpLl+tU7t1KEovdZ+OVYsYKZhVzw0 MTpKogk9JI7AN0q62ronPskAEQEAAQAL+O8BUSt1ZCVjPSIXIsrR+ZOSkszZwgJ1 CWIoh0IHYD2vmcMHGIhFYgBdgerpvhptKhaw7GcXDScEnYkyh5s4GE2hxclik1tb j/x1gYCN8BNoyeDdPFxQG73qN12D99QYEctpOsz9xPLIDwmL0j1ehAfhwqHIAPm9 Ca+i8JYMx/F+35S/jnKDXRI+NVlwbiEyXKXxxIqNlpy9i8sDBGexO5H5Sg0zSN/B 1duLekGDbiDw6gLc6bCgnS+0JOUpU07Z2fccMOY9ncjKGD2uIb/ePPUaek92GCQy q0eorCIVbrcQsRc5sSsNtnRKQTQtxioROeDg7kf2oWySeHTswlXW/219ihrSXgte HJd+rPm7DYLEeGLRny8bRKv8rQdAtApHaJE4dAATXeY4RYo4NlXHYaztGYtU6kiM /3zCfWAe9Nn+Wh9jMTZrjefUCagS5r6ZqAh7veNo/vgIGaCLh0a1Ypa0Yk9KFrn3 LYEM3zgk3m3bn+7qgy5cUYXoJ3DGJJEhBgDPonpW0WElqLs5ZMem1ha85SC38F0I kAaSuzuzv3eORiKWuyJGF32Q2XHa1RHQs1JtUKd8rxFer3b8Oq71zLz6JtVc9dmR udvgcJYX0PC11F6WGjZFSSp39dajFp0A5DKUs39F3w7J1yuDM56TDIN810ywufGA HARY1pZbUJAy/dTqjFnCbNjpAakor3hVzqxcmUG+7Y2X9c2AGncT1MqAQC3M8JZc uZvkK8A9cMk8B914ryYE7VsZMdMhyTwHmykGAPgNLLa3RDETeGeGCKWI+ZPOoU0i b5JtJZ1dP3tNwfZKuZBZXKW9gqYqyBa/qhMip84SP30pr/TvulcdAFC759HK8sQZ yJ6Vw24Pc+5ssRxrQUEw1rvJPWhmQCmCOZHBMQl5T6eaTOpR5u3aUKTMlxPKhK9e C1dCSTnI/nyL8An3VKnLy+K/LI42YGphBVLLJmBewuTVDIJviWRdntiG8dElyEJM OywUltk32CEmqgsD9tPO8rXZjnMrMn3gfsiaoQYA6/6/e2utkHr7gAoWBgrBBdqV Hsvqh5Ro2DjLAOpZItO/EdCJfDAmbTYOa04535sBDP2tcH/vipPOPpbr1Y9Y/mNs KCulNxedyqAmEkKOcerLUP5UHju0AB6VBjHJFdU2mqT+UjPyBk7WeKXgFomyoYMv 3KpNOFWRxi0Xji4kKHbttA6Hy3UcGPr9acyUAlDYeKmxbSUYIPhw32bbGrX9+F5Y riTufRsG3jftQVo9zqdcQSD/5pUTMn3EYbEcohYB2YWJAbwEGAEIACYWIQRqkzk/ UMXmrNPW+0W5NiEu204UwAUCYGMjQAIbDAUJA8JnAAAKCRC5NiEu204UwDICC/9o q0illSIAuBHCImbNcOAJmno6ZZ1OkqtQrEmmKjIxUEkMZDvEaAUuGwCyfn3RcaWQ m3HAv0HRtYiBebN9rgfMGEEp9prmTuAOxc4vWfMOoYgo2vLNfaKwLREHrm7NzHSo ovb+ZwWpm724DU6IMdaVpc5LzBPArG0nUcOTZ15Lc2akpbhFjxBHKKimkk0V1YwU lIyn7I5wHbJ5qz1YjaCjUYi6xLwHDxStIE2vR2dzHiVKNZBKfhRd7BIYfpBEvNGS RKR1moy3QUKw71Q1fE+TcbK6eFsbjROxq2OZSTy371zG9hLccroM0cZl8pBlnRpX sn3g7h5kZVzZ0VnOM3A8f29v0P9LE6r+p4oaWnBh9QuNq50hYPyA6CJNF73A+Shc AanKpb2pqswnk1CVhAzh+l7JhOR5RUVOMCv9mb3TwYQcE7qhMovHWhLmpFhlfO4a +AMn3f/774DKYGUigIzR45dhZFFkGvvb85uEP67GqgSv/zTISviuuc4A6Ze9ALs= =kOKh -----END PGP PRIVATE KEY BLOCK----- """ NON_DEFAULT_KEY_ID = "6A93393F50C5E6ACD3D6FB45B936212EDB4E14C0" def setUp(self): super(PorcelainGpgTestCase, self).setUp() self.gpg_dir = os.path.join(self.test_dir, "gpg") os.mkdir(self.gpg_dir, mode=0o700) self.addCleanup(shutil.rmtree, self.gpg_dir) self._old_gnupghome = os.environ.get("GNUPGHOME") os.environ["GNUPGHOME"] = self.gpg_dir if self._old_gnupghome is None: self.addCleanup(os.environ.__delitem__, "GNUPGHOME") else: self.addCleanup(os.environ.__setitem__, "GNUPGHOME", self._old_gnupghome) def import_default_key(self): subprocess.run( ["gpg", "--import"], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, input=PorcelainGpgTestCase.DEFAULT_KEY, universal_newlines=True, ) def import_non_default_key(self): subprocess.run( ["gpg", "--import"], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, input=PorcelainGpgTestCase.NON_DEFAULT_KEY, universal_newlines=True, ) class ArchiveTests(PorcelainTestCase): """Tests for the archive command.""" def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"refs/heads/master"] = c3.id out = BytesIO() err = BytesIO() porcelain.archive( self.repo.path, b"refs/heads/master", outstream=out, errstream=err ) self.assertEqual(b"", err.getvalue()) tf = tarfile.TarFile(fileobj=out) self.addCleanup(tf.close) self.assertEqual([], tf.getnames()) class UpdateServerInfoTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"refs/heads/foo"] = c3.id porcelain.update_server_info(self.repo.path) self.assertTrue( os.path.exists(os.path.join(self.repo.controldir(), "info", "refs")) ) class CommitTests(PorcelainTestCase): def test_custom_author(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"refs/heads/foo"] = c3.id sha = porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ", ) self.assertTrue(isinstance(sha, bytes)) self.assertEqual(len(sha), 40) def test_unicode(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"refs/heads/foo"] = c3.id sha = porcelain.commit( self.repo.path, message="Some message", author="Joe ", committer="Bob ", ) self.assertTrue(isinstance(sha, bytes)) self.assertEqual(len(sha), 40) def test_no_verify(self): if os.name != "posix": self.skipTest("shell hook tests requires POSIX shell") self.assertTrue(os.path.exists("/bin/sh")) hooks_dir = os.path.join(self.repo.controldir(), "hooks") os.makedirs(hooks_dir, exist_ok=True) self.addCleanup(shutil.rmtree, hooks_dir) c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) hook_fail = "#!/bin/sh\nexit 1" # hooks are executed in pre-commit, commit-msg order # test commit-msg failure first, then pre-commit failure, then # no_verify to skip both hooks commit_msg = os.path.join(hooks_dir, "commit-msg") with open(commit_msg, "w") as f: f.write(hook_fail) os.chmod(commit_msg, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) with self.assertRaises(CommitError): porcelain.commit( self.repo.path, message="Some message", author="Joe ", committer="Bob ", ) pre_commit = os.path.join(hooks_dir, "pre-commit") with open(pre_commit, "w") as f: f.write(hook_fail) os.chmod(pre_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) with self.assertRaises(CommitError): porcelain.commit( self.repo.path, message="Some message", author="Joe ", committer="Bob ", ) sha = porcelain.commit( self.repo.path, message="Some message", author="Joe ", committer="Bob ", no_verify=True, ) self.assertTrue(isinstance(sha, bytes)) self.assertEqual(len(sha), 40) class CleanTests(PorcelainTestCase): def put_files(self, tracked, ignored, untracked, empty_dirs): """Put the described files in the wd""" all_files = tracked | ignored | untracked for file_path in all_files: abs_path = os.path.join(self.repo.path, file_path) # File may need to be written in a dir that doesn't exist yet, so # create the parent dir(s) as necessary parent_dir = os.path.dirname(abs_path) try: os.makedirs(parent_dir) except FileExistsError: pass with open(abs_path, "w") as f: f.write("") with open(os.path.join(self.repo.path, ".gitignore"), "w") as f: f.writelines(ignored) for dir_path in empty_dirs: os.mkdir(os.path.join(self.repo.path, "empty_dir")) files_to_add = [os.path.join(self.repo.path, t) for t in tracked] porcelain.add(repo=self.repo.path, paths=files_to_add) porcelain.commit(repo=self.repo.path, message="init commit") def assert_wd(self, expected_paths): """Assert paths of files and dirs in wd are same as expected_paths""" control_dir_rel = os.path.relpath(self.repo._controldir, self.repo.path) # normalize paths to simplify comparison across platforms found_paths = { os.path.normpath(p) for p in flat_walk_dir(self.repo.path) if not p.split(os.sep)[0] == control_dir_rel } norm_expected_paths = {os.path.normpath(p) for p in expected_paths} self.assertEqual(found_paths, norm_expected_paths) def test_from_root(self): self.put_files( tracked={"tracked_file", "tracked_dir/tracked_file", ".gitignore"}, ignored={"ignored_file"}, untracked={ "untracked_file", "tracked_dir/untracked_dir/untracked_file", "untracked_dir/untracked_dir/untracked_file", }, empty_dirs={"empty_dir"}, ) porcelain.clean(repo=self.repo.path, target_dir=self.repo.path) self.assert_wd( { "tracked_file", "tracked_dir/tracked_file", ".gitignore", "ignored_file", "tracked_dir", } ) def test_from_subdir(self): self.put_files( tracked={"tracked_file", "tracked_dir/tracked_file", ".gitignore"}, ignored={"ignored_file"}, untracked={ "untracked_file", "tracked_dir/untracked_dir/untracked_file", "untracked_dir/untracked_dir/untracked_file", }, empty_dirs={"empty_dir"}, ) porcelain.clean( repo=self.repo, target_dir=os.path.join(self.repo.path, "untracked_dir"), ) self.assert_wd( { "tracked_file", "tracked_dir/tracked_file", ".gitignore", "ignored_file", "untracked_file", "tracked_dir/untracked_dir/untracked_file", "empty_dir", "untracked_dir", "tracked_dir", "tracked_dir/untracked_dir", } ) class CloneTests(PorcelainTestCase): def test_simple_local(self): f1_1 = make_object(Blob, data=b"f1") commit_spec = [[1], [2, 1], [3, 1, 2]] trees = { 1: [(b"f1", f1_1), (b"f2", f1_1)], 2: [(b"f1", f1_1), (b"f2", f1_1)], 3: [(b"f1", f1_1), (b"f2", f1_1)], } c1, c2, c3 = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c3.id self.repo.refs[b"refs/tags/foo"] = c3.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) r = porcelain.clone( self.repo.path, target_path, checkout=False, errstream=errstream ) self.addCleanup(r.close) self.assertEqual(r.path, target_path) target_repo = Repo(target_path) self.assertEqual(0, len(target_repo.open_index())) self.assertEqual(c3.id, target_repo.refs[b"refs/tags/foo"]) self.assertTrue(b"f1" not in os.listdir(target_path)) self.assertTrue(b"f2" not in os.listdir(target_path)) c = r.get_config() encoded_path = self.repo.path if not isinstance(encoded_path, bytes): encoded_path = encoded_path.encode("utf-8") self.assertEqual(encoded_path, c.get((b"remote", b"origin"), b"url")) self.assertEqual( b"+refs/heads/*:refs/remotes/origin/*", c.get((b"remote", b"origin"), b"fetch"), ) def test_simple_local_with_checkout(self): f1_1 = make_object(Blob, data=b"f1") commit_spec = [[1], [2, 1], [3, 1, 2]] trees = { 1: [(b"f1", f1_1), (b"f2", f1_1)], 2: [(b"f1", f1_1), (b"f2", f1_1)], 3: [(b"f1", f1_1), (b"f2", f1_1)], } c1, c2, c3 = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c3.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) with porcelain.clone( self.repo.path, target_path, checkout=True, errstream=errstream ) as r: self.assertEqual(r.path, target_path) with Repo(target_path) as r: self.assertEqual(r.head(), c3.id) self.assertTrue("f1" in os.listdir(target_path)) self.assertTrue("f2" in os.listdir(target_path)) def test_bare_local_with_checkout(self): f1_1 = make_object(Blob, data=b"f1") commit_spec = [[1], [2, 1], [3, 1, 2]] trees = { 1: [(b"f1", f1_1), (b"f2", f1_1)], 2: [(b"f1", f1_1), (b"f2", f1_1)], 3: [(b"f1", f1_1), (b"f2", f1_1)], } c1, c2, c3 = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c3.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) with porcelain.clone( self.repo.path, target_path, bare=True, errstream=errstream ) as r: self.assertEqual(r.path, target_path) with Repo(target_path) as r: r.head() self.assertRaises(NoIndexPresent, r.open_index) self.assertFalse(b"f1" in os.listdir(target_path)) self.assertFalse(b"f2" in os.listdir(target_path)) def test_no_checkout_with_bare(self): f1_1 = make_object(Blob, data=b"f1") commit_spec = [[1]] trees = {1: [(b"f1", f1_1), (b"f2", f1_1)]} (c1,) = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c1.id self.repo.refs[b"HEAD"] = c1.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) self.assertRaises( porcelain.Error, porcelain.clone, self.repo.path, target_path, checkout=True, bare=True, errstream=errstream, ) def test_no_head_no_checkout(self): f1_1 = make_object(Blob, data=b"f1") commit_spec = [[1]] trees = {1: [(b"f1", f1_1), (b"f2", f1_1)]} (c1,) = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c1.id target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) errstream = BytesIO() r = porcelain.clone( self.repo.path, target_path, checkout=True, errstream=errstream ) r.close() def test_no_head_no_checkout_outstream_errstream_autofallback(self): f1_1 = make_object(Blob, data=b"f1") commit_spec = [[1]] trees = {1: [(b"f1", f1_1), (b"f2", f1_1)]} (c1,) = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c1.id target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) errstream = porcelain.NoneStream() r = porcelain.clone( self.repo.path, target_path, checkout=True, errstream=errstream ) r.close() def test_source_broken(self): target_path = tempfile.mkdtemp() self.assertRaises(Exception, porcelain.clone, "/nonexistant/repo", target_path) self.assertFalse(os.path.exists(target_path)) def test_fetch_symref(self): f1_1 = make_object(Blob, data=b"f1") trees = {1: [(b"f1", f1_1), (b"f2", f1_1)]} [c1] = build_commit_graph(self.repo.object_store, [[1]], trees) self.repo.refs.set_symbolic_ref(b"HEAD", b"refs/heads/else") self.repo.refs[b"refs/heads/else"] = c1.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) r = porcelain.clone( self.repo.path, target_path, checkout=False, errstream=errstream ) self.addCleanup(r.close) self.assertEqual(r.path, target_path) target_repo = Repo(target_path) self.assertEqual(0, len(target_repo.open_index())) self.assertEqual(c1.id, target_repo.refs[b"refs/heads/else"]) self.assertEqual(c1.id, target_repo.refs[b"HEAD"]) self.assertEqual({b"HEAD": b"refs/heads/else"}, target_repo.refs.get_symrefs()) class InitTests(TestCase): def test_non_bare(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) porcelain.init(repo_dir) def test_bare(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) porcelain.init(repo_dir, bare=True) class AddTests(PorcelainTestCase): def test_add_default_paths(self): # create a file for initial commit fullpath = os.path.join(self.repo.path, "blah") with open(fullpath, "w") as f: f.write("\n") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( repo=self.repo.path, message=b"test", author=b"test ", committer=b"test ", ) # Add a second test file and a file in a directory with open(os.path.join(self.repo.path, "foo"), "w") as f: f.write("\n") os.mkdir(os.path.join(self.repo.path, "adir")) with open(os.path.join(self.repo.path, "adir", "afile"), "w") as f: f.write("\n") cwd = os.getcwd() try: os.chdir(self.repo.path) self.assertEqual(set(["foo", "blah", "adir", ".git"]), set(os.listdir("."))) self.assertEqual( (["foo", os.path.join("adir", "afile")], set()), porcelain.add(self.repo.path), ) finally: os.chdir(cwd) # Check that foo was added and nothing in .git was modified index = self.repo.open_index() self.assertEqual(sorted(index), [b"adir/afile", b"blah", b"foo"]) def test_add_default_paths_subdir(self): os.mkdir(os.path.join(self.repo.path, "foo")) with open(os.path.join(self.repo.path, "blah"), "w") as f: f.write("\n") with open(os.path.join(self.repo.path, "foo", "blie"), "w") as f: f.write("\n") cwd = os.getcwd() try: os.chdir(os.path.join(self.repo.path, "foo")) porcelain.add(repo=self.repo.path) porcelain.commit( repo=self.repo.path, message=b"test", author=b"test ", committer=b"test ", ) finally: os.chdir(cwd) index = self.repo.open_index() self.assertEqual(sorted(index), [b"foo/blie"]) def test_add_file(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) self.assertIn(b"foo", self.repo.open_index()) def test_add_ignored(self): with open(os.path.join(self.repo.path, ".gitignore"), "w") as f: f.write("foo\nsubdir/") with open(os.path.join(self.repo.path, "foo"), "w") as f: f.write("BAR") with open(os.path.join(self.repo.path, "bar"), "w") as f: f.write("BAR") os.mkdir(os.path.join(self.repo.path, "subdir")) with open(os.path.join(self.repo.path, "subdir", "baz"), "w") as f: f.write("BAZ") (added, ignored) = porcelain.add( self.repo.path, paths=[ os.path.join(self.repo.path, "foo"), os.path.join(self.repo.path, "bar"), os.path.join(self.repo.path, "subdir"), ], ) self.assertIn(b"bar", self.repo.open_index()) self.assertEqual(set(["bar"]), set(added)) self.assertEqual(set(["foo", os.path.join("subdir", "")]), ignored) def test_add_file_absolute_path(self): # Absolute paths are (not yet) supported with open(os.path.join(self.repo.path, "foo"), "w") as f: f.write("BAR") porcelain.add(self.repo, paths=[os.path.join(self.repo.path, "foo")]) self.assertIn(b"foo", self.repo.open_index()) def test_add_not_in_repo(self): with open(os.path.join(self.test_dir, "foo"), "w") as f: f.write("BAR") self.assertRaises( ValueError, porcelain.add, self.repo, paths=[os.path.join(self.test_dir, "foo")], ) self.assertRaises( (ValueError, FileNotFoundError), porcelain.add, self.repo, paths=["../foo"], ) self.assertEqual([], list(self.repo.open_index())) def test_add_file_clrf_conversion(self): # Set the right configuration to the repo c = self.repo.get_config() c.set("core", "autocrlf", "input") c.write_to_path() # Add a file with CRLF line-ending fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "wb") as f: f.write(b"line1\r\nline2") porcelain.add(self.repo.path, paths=[fullpath]) # The line-endings should have been converted to LF index = self.repo.open_index() self.assertIn(b"foo", index) entry = index[b"foo"] blob = self.repo[entry.sha] self.assertEqual(blob.data, b"line1\nline2") class RemoveTests(PorcelainTestCase): def test_remove_file(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) porcelain.commit( repo=self.repo, message=b"test", author=b"test ", committer=b"test ", ) self.assertTrue(os.path.exists(os.path.join(self.repo.path, "foo"))) cwd = os.getcwd() try: os.chdir(self.repo.path) porcelain.remove(self.repo.path, paths=["foo"]) finally: os.chdir(cwd) self.assertFalse(os.path.exists(os.path.join(self.repo.path, "foo"))) def test_remove_file_staged(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") cwd = os.getcwd() try: os.chdir(self.repo.path) porcelain.add(self.repo.path, paths=[fullpath]) self.assertRaises(Exception, porcelain.rm, self.repo.path, paths=["foo"]) finally: os.chdir(cwd) def test_remove_file_removed_on_disk(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) cwd = os.getcwd() try: os.chdir(self.repo.path) os.remove(fullpath) porcelain.remove(self.repo.path, paths=["foo"]) finally: os.chdir(cwd) self.assertFalse(os.path.exists(os.path.join(self.repo.path, "foo"))) class LogTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.log(self.repo.path, outstream=outstream) self.assertEqual(3, outstream.getvalue().count("-" * 50)) def test_max_entries(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.log(self.repo.path, outstream=outstream, max_entries=1) self.assertEqual(1, outstream.getvalue().count("-" * 50)) class ShowTests(PorcelainTestCase): def test_nolist(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.show(self.repo.path, objects=c3.id, outstream=outstream) self.assertTrue(outstream.getvalue().startswith("-" * 50)) def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.show(self.repo.path, objects=[c3.id], outstream=outstream) self.assertTrue(outstream.getvalue().startswith("-" * 50)) def test_blob(self): b = Blob.from_string(b"The Foo\n") self.repo.object_store.add_object(b) outstream = StringIO() porcelain.show(self.repo.path, objects=[b.id], outstream=outstream) self.assertEqual(outstream.getvalue(), "The Foo\n") def test_commit_no_parent(self): a = Blob.from_string(b"The Foo\n") ta = Tree() ta.add(b"somename", 0o100644, a.id) ca = make_commit(tree=ta.id) self.repo.object_store.add_objects([(a, None), (ta, None), (ca, None)]) outstream = StringIO() porcelain.show(self.repo.path, objects=[ca.id], outstream=outstream) self.assertMultiLineEqual( outstream.getvalue(), """\ -------------------------------------------------- commit: 344da06c1bb85901270b3e8875c988a027ec087d Author: Test Author Committer: Test Committer Date: Fri Jan 01 2010 00:00:00 +0000 Test message. diff --git a/somename b/somename new file mode 100644 index 0000000..ea5c7bf --- /dev/null +++ b/somename @@ -0,0 +1 @@ +The Foo """, ) def test_tag(self): a = Blob.from_string(b"The Foo\n") ta = Tree() ta.add(b"somename", 0o100644, a.id) ca = make_commit(tree=ta.id) self.repo.object_store.add_objects([(a, None), (ta, None), (ca, None)]) porcelain.tag_create( self.repo.path, b"tryme", b"foo ", b"bar", annotated=True, objectish=ca.id, tag_time=1552854211, tag_timezone=0, ) outstream = StringIO() porcelain.show(self.repo, objects=[b"refs/tags/tryme"], outstream=outstream) self.maxDiff = None self.assertMultiLineEqual( outstream.getvalue(), """\ Tagger: foo Date: Sun Mar 17 2019 20:23:31 +0000 bar -------------------------------------------------- commit: 344da06c1bb85901270b3e8875c988a027ec087d Author: Test Author Committer: Test Committer Date: Fri Jan 01 2010 00:00:00 +0000 Test message. diff --git a/somename b/somename new file mode 100644 index 0000000..ea5c7bf --- /dev/null +++ b/somename @@ -0,0 +1 @@ +The Foo """, ) def test_commit_with_change(self): a = Blob.from_string(b"The Foo\n") ta = Tree() ta.add(b"somename", 0o100644, a.id) ca = make_commit(tree=ta.id) b = Blob.from_string(b"The Bar\n") tb = Tree() tb.add(b"somename", 0o100644, b.id) cb = make_commit(tree=tb.id, parents=[ca.id]) self.repo.object_store.add_objects( [ (a, None), (b, None), (ta, None), (tb, None), (ca, None), (cb, None), ] ) outstream = StringIO() porcelain.show(self.repo.path, objects=[cb.id], outstream=outstream) self.assertMultiLineEqual( outstream.getvalue(), """\ -------------------------------------------------- commit: 2c6b6c9cb72c130956657e1fdae58e5b103744fa Author: Test Author Committer: Test Committer Date: Fri Jan 01 2010 00:00:00 +0000 Test message. diff --git a/somename b/somename index ea5c7bf..fd38bcb 100644 --- a/somename +++ b/somename @@ -1 +1 @@ -The Foo +The Bar """, ) class SymbolicRefTests(PorcelainTestCase): def test_set_wrong_symbolic_ref(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id self.assertRaises( porcelain.Error, porcelain.symbolic_ref, self.repo.path, b"foobar" ) def test_set_force_wrong_symbolic_ref(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id porcelain.symbolic_ref(self.repo.path, b"force_foobar", force=True) # test if we actually changed the file with self.repo.get_named_file("HEAD") as f: new_ref = f.read() self.assertEqual(new_ref, b"ref: refs/heads/force_foobar\n") def test_set_symbolic_ref(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id porcelain.symbolic_ref(self.repo.path, b"master") def test_set_symbolic_ref_other_than_master(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]], attrs=dict(refs="develop"), ) self.repo.refs[b"HEAD"] = c3.id self.repo.refs[b"refs/heads/develop"] = c3.id porcelain.symbolic_ref(self.repo.path, b"develop") # test if we actually changed the file with self.repo.get_named_file("HEAD") as f: new_ref = f.read() self.assertEqual(new_ref, b"ref: refs/heads/develop\n") class DiffTreeTests(PorcelainTestCase): def test_empty(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id outstream = BytesIO() porcelain.diff_tree(self.repo.path, c2.tree, c3.tree, outstream=outstream) self.assertEqual(outstream.getvalue(), b"") class CommitTreeTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) b = Blob() b.data = b"foo the bar" t = Tree() t.add(b"somename", 0o100644, b.id) self.repo.object_store.add_object(t) self.repo.object_store.add_object(b) sha = porcelain.commit_tree( self.repo.path, t.id, message=b"Withcommit.", author=b"Joe ", committer=b"Jane ", ) self.assertTrue(isinstance(sha, bytes)) self.assertEqual(len(sha), 40) class RevListTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) outstream = BytesIO() porcelain.rev_list(self.repo.path, [c3.id], outstream=outstream) self.assertEqual( c3.id + b"\n" + c2.id + b"\n" + c1.id + b"\n", outstream.getvalue() ) @skipIf(platform.python_implementation() == "PyPy" or sys.platform == "win32", "gpgme not easily available or supported on Windows and PyPy") class TagCreateSignTests(PorcelainGpgTestCase): def test_default_key(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id cfg = self.repo.get_config() cfg.set(("user",), "signingKey", PorcelainGpgTestCase.DEFAULT_KEY_ID) self.import_default_key() porcelain.tag_create( self.repo.path, b"tryme", b"foo ", b"bar", annotated=True, sign=True, ) tags = self.repo.refs.as_dict(b"refs/tags") self.assertEqual(list(tags.keys()), [b"tryme"]) tag = self.repo[b"refs/tags/tryme"] self.assertTrue(isinstance(tag, Tag)) self.assertEqual(b"foo ", tag.tagger) self.assertEqual(b"bar\n", tag.message) self.assertLess(time.time() - tag.tag_time, 5) # GPG Signatures aren't deterministic, so we can't do a static assertion. # Instead we need to check the signature can be verified by git tag = self.repo[b'refs/tags/tryme'] # TODO(jelmer): Remove calls to C git, and call tag.verify() instead - # perhaps moving git call to compat testsuite? subprocess.run( ["git", "--git-dir={}".format(self.repo.controldir()), "tag", "-v", "tryme"], check=True, stderr=subprocess.DEVNULL, stdout=subprocess.DEVNULL, ) def test_non_default_key(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id cfg = self.repo.get_config() cfg.set(("user",), "signingKey", PorcelainGpgTestCase.DEFAULT_KEY_ID) self.import_non_default_key() porcelain.tag_create( self.repo.path, b"tryme", b"foo ", b"bar", annotated=True, sign=PorcelainGpgTestCase.NON_DEFAULT_KEY_ID, ) tags = self.repo.refs.as_dict(b"refs/tags") self.assertEqual(list(tags.keys()), [b"tryme"]) tag = self.repo[b"refs/tags/tryme"] self.assertTrue(isinstance(tag, Tag)) self.assertEqual(b"foo ", tag.tagger) self.assertEqual(b"bar\n", tag.message) self.assertLess(time.time() - tag.tag_time, 5) tag = self.repo[b'refs/tags/tryme'] # GPG Signatures aren't deterministic, so we can't do a static assertion. # Instead we need to check the signature can be verified by git # TODO(jelmer): Remove calls to C git, and call tag.verify() instead - # perhaps moving git call to compat testsuite? subprocess.run( ["git", "--git-dir={}".format(self.repo.controldir()), "tag", "-v", "tryme"], check=True, stderr=subprocess.DEVNULL, stdout=subprocess.DEVNULL, ) class TagCreateTests(PorcelainTestCase): def test_annotated(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id porcelain.tag_create( self.repo.path, b"tryme", b"foo ", b"bar", annotated=True, ) tags = self.repo.refs.as_dict(b"refs/tags") self.assertEqual(list(tags.keys()), [b"tryme"]) tag = self.repo[b"refs/tags/tryme"] self.assertTrue(isinstance(tag, Tag)) self.assertEqual(b"foo ", tag.tagger) self.assertEqual(b"bar\n", tag.message) self.assertLess(time.time() - tag.tag_time, 5) def test_unannotated(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id porcelain.tag_create(self.repo.path, b"tryme", annotated=False) tags = self.repo.refs.as_dict(b"refs/tags") self.assertEqual(list(tags.keys()), [b"tryme"]) self.repo[b"refs/tags/tryme"] self.assertEqual(list(tags.values()), [self.repo.head()]) def test_unannotated_unicode(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]] ) self.repo.refs[b"HEAD"] = c3.id porcelain.tag_create(self.repo.path, "tryme", annotated=False) tags = self.repo.refs.as_dict(b"refs/tags") self.assertEqual(list(tags.keys()), [b"tryme"]) self.repo[b"refs/tags/tryme"] self.assertEqual(list(tags.values()), [self.repo.head()]) class TagListTests(PorcelainTestCase): def test_empty(self): tags = porcelain.tag_list(self.repo.path) self.assertEqual([], tags) def test_simple(self): self.repo.refs[b"refs/tags/foo"] = b"aa" * 20 self.repo.refs[b"refs/tags/bar/bla"] = b"bb" * 20 tags = porcelain.tag_list(self.repo.path) self.assertEqual([b"bar/bla", b"foo"], tags) class TagDeleteTests(PorcelainTestCase): def test_simple(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.tag_create(self.repo, b"foo") self.assertTrue(b"foo" in porcelain.tag_list(self.repo)) porcelain.tag_delete(self.repo, b"foo") self.assertFalse(b"foo" in porcelain.tag_list(self.repo)) class ResetTests(PorcelainTestCase): def test_hard_head(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some message", committer=b"Jane ", author=b"John ", ) with open(os.path.join(self.repo.path, "foo"), "wb") as f: f.write(b"OOH") porcelain.reset(self.repo, "hard", b"HEAD") index = self.repo.open_index() changes = list( tree_changes( self.repo, index.commit(self.repo.object_store), self.repo[b"HEAD"].tree, ) ) self.assertEqual([], changes) def test_hard_commit(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) sha = porcelain.commit( self.repo.path, message=b"Some message", committer=b"Jane ", author=b"John ", ) with open(fullpath, "wb") as f: f.write(b"BAZ") porcelain.add(self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some other message", committer=b"Jane ", author=b"John ", ) porcelain.reset(self.repo, "hard", sha) index = self.repo.open_index() changes = list( tree_changes( self.repo, index.commit(self.repo.object_store), self.repo[sha].tree, ) ) self.assertEqual([], changes) class PushTests(PorcelainTestCase): def test_simple(self): """ Basic test of porcelain push where self.repo is the remote. First clone the remote, commit a file to the clone, then push the changes back to the remote. """ outstream = BytesIO() errstream = BytesIO() porcelain.commit( repo=self.repo.path, message=b"init", author=b"author ", committer=b"committer ", ) # Setup target repo cloned from temp test repo clone_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, clone_path) target_repo = porcelain.clone( self.repo.path, target=clone_path, errstream=errstream ) try: self.assertEqual(target_repo[b"HEAD"], self.repo[b"HEAD"]) finally: target_repo.close() # create a second file to be pushed back to origin handle, fullpath = tempfile.mkstemp(dir=clone_path) os.close(handle) porcelain.add(repo=clone_path, paths=[fullpath]) porcelain.commit( repo=clone_path, message=b"push", author=b"author ", committer=b"committer ", ) # Setup a non-checked out branch in the remote refs_path = b"refs/heads/foo" new_id = self.repo[b"HEAD"].id self.assertNotEqual(new_id, ZERO_SHA) self.repo.refs[refs_path] = new_id # Push to the remote porcelain.push( clone_path, "origin", b"HEAD:" + refs_path, outstream=outstream, errstream=errstream, ) self.assertEqual( target_repo.refs[b"refs/remotes/origin/foo"], target_repo.refs[b"HEAD"], ) # Check that the target and source with Repo(clone_path) as r_clone: self.assertEqual( { b"HEAD": new_id, b"refs/heads/foo": r_clone[b"HEAD"].id, b"refs/heads/master": new_id, }, self.repo.get_refs(), ) self.assertEqual(r_clone[b"HEAD"].id, self.repo[refs_path].id) # Get the change in the target repo corresponding to the add # this will be in the foo branch. change = list( tree_changes( self.repo, self.repo[b"HEAD"].tree, self.repo[b"refs/heads/foo"].tree, ) )[0] self.assertEqual( os.path.basename(fullpath), change.new.path.decode("ascii") ) def test_local_missing(self): """Pushing a new branch.""" outstream = BytesIO() errstream = BytesIO() # Setup target repo cloned from temp test repo clone_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, clone_path) target_repo = porcelain.init(clone_path) target_repo.close() self.assertRaises( porcelain.Error, porcelain.push, self.repo, clone_path, b"HEAD:refs/heads/master", outstream=outstream, errstream=errstream, ) def test_new(self): """Pushing a new branch.""" outstream = BytesIO() errstream = BytesIO() # Setup target repo cloned from temp test repo clone_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, clone_path) target_repo = porcelain.init(clone_path) target_repo.close() # create a second file to be pushed back to origin handle, fullpath = tempfile.mkstemp(dir=clone_path) os.close(handle) porcelain.add(repo=clone_path, paths=[fullpath]) new_id = porcelain.commit( repo=self.repo, message=b"push", author=b"author ", committer=b"committer ", ) # Push to the remote porcelain.push( self.repo, clone_path, b"HEAD:refs/heads/master", outstream=outstream, errstream=errstream, ) with Repo(clone_path) as r_clone: self.assertEqual( { b"HEAD": new_id, b"refs/heads/master": new_id, }, r_clone.get_refs(), ) def test_delete(self): """Basic test of porcelain push, removing a branch.""" outstream = BytesIO() errstream = BytesIO() porcelain.commit( repo=self.repo.path, message=b"init", author=b"author ", committer=b"committer ", ) # Setup target repo cloned from temp test repo clone_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, clone_path) target_repo = porcelain.clone( self.repo.path, target=clone_path, errstream=errstream ) target_repo.close() # Setup a non-checked out branch in the remote refs_path = b"refs/heads/foo" new_id = self.repo[b"HEAD"].id self.assertNotEqual(new_id, ZERO_SHA) self.repo.refs[refs_path] = new_id # Push to the remote porcelain.push( clone_path, self.repo.path, b":" + refs_path, outstream=outstream, errstream=errstream, ) self.assertEqual( { b"HEAD": new_id, b"refs/heads/master": new_id, }, self.repo.get_refs(), ) def test_diverged(self): outstream = BytesIO() errstream = BytesIO() porcelain.commit( repo=self.repo.path, message=b"init", author=b"author ", committer=b"committer ", ) # Setup target repo cloned from temp test repo clone_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, clone_path) target_repo = porcelain.clone( self.repo.path, target=clone_path, errstream=errstream ) target_repo.close() remote_id = porcelain.commit( repo=self.repo.path, message=b"remote change", author=b"author ", committer=b"committer ", ) local_id = porcelain.commit( repo=clone_path, message=b"local change", author=b"author ", committer=b"committer ", ) outstream = BytesIO() errstream = BytesIO() # Push to the remote self.assertRaises( porcelain.DivergedBranches, porcelain.push, clone_path, self.repo.path, b"refs/heads/master", outstream=outstream, errstream=errstream, ) self.assertEqual( { b"HEAD": remote_id, b"refs/heads/master": remote_id, }, self.repo.get_refs(), ) self.assertEqual(b"", outstream.getvalue()) self.assertEqual(b"", errstream.getvalue()) outstream = BytesIO() errstream = BytesIO() # Push to the remote with --force porcelain.push( clone_path, self.repo.path, b"refs/heads/master", outstream=outstream, errstream=errstream, force=True, ) self.assertEqual( { b"HEAD": local_id, b"refs/heads/master": local_id, }, self.repo.get_refs(), ) self.assertEqual(b"", outstream.getvalue()) self.assertTrue(re.match(b"Push to .* successful.\n", errstream.getvalue())) class PullTests(PorcelainTestCase): def setUp(self): super(PullTests, self).setUp() # create a file for initial commit handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit( repo=self.repo.path, message=b"test", author=b"test ", committer=b"test ", ) # Setup target repo self.target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.target_path) target_repo = porcelain.clone( self.repo.path, target=self.target_path, errstream=BytesIO() ) target_repo.close() # create a second file to be pushed handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit( repo=self.repo.path, message=b"test2", author=b"test2 ", committer=b"test2 ", ) self.assertIn(b"refs/heads/master", self.repo.refs) self.assertIn(b"refs/heads/master", target_repo.refs) def test_simple(self): outstream = BytesIO() errstream = BytesIO() # Pull changes into the cloned repo porcelain.pull( self.target_path, self.repo.path, b"refs/heads/master", outstream=outstream, errstream=errstream, ) # Check the target repo for pushed changes with Repo(self.target_path) as r: self.assertEqual(r[b"HEAD"].id, self.repo[b"HEAD"].id) def test_diverged(self): outstream = BytesIO() errstream = BytesIO() c3a = porcelain.commit( repo=self.target_path, message=b"test3a", author=b"test2 ", committer=b"test2 ", ) porcelain.commit( repo=self.repo.path, message=b"test3b", author=b"test2 ", committer=b"test2 ", ) # Pull changes into the cloned repo self.assertRaises( porcelain.DivergedBranches, porcelain.pull, self.target_path, self.repo.path, b"refs/heads/master", outstream=outstream, errstream=errstream, ) # Check the target repo for pushed changes with Repo(self.target_path) as r: self.assertEqual(r[b"refs/heads/master"].id, c3a) self.assertRaises( NotImplementedError, porcelain.pull, self.target_path, self.repo.path, b"refs/heads/master", outstream=outstream, errstream=errstream, fast_forward=False, ) # Check the target repo for pushed changes with Repo(self.target_path) as r: self.assertEqual(r[b"refs/heads/master"].id, c3a) def test_no_refspec(self): outstream = BytesIO() errstream = BytesIO() # Pull changes into the cloned repo porcelain.pull( self.target_path, self.repo.path, outstream=outstream, errstream=errstream, ) # Check the target repo for pushed changes with Repo(self.target_path) as r: self.assertEqual(r[b"HEAD"].id, self.repo[b"HEAD"].id) def test_no_remote_location(self): outstream = BytesIO() errstream = BytesIO() # Pull changes into the cloned repo porcelain.pull( self.target_path, refspecs=b"refs/heads/master", outstream=outstream, errstream=errstream, ) # Check the target repo for pushed changes with Repo(self.target_path) as r: self.assertEqual(r[b"HEAD"].id, self.repo[b"HEAD"].id) class StatusTests(PorcelainTestCase): def test_empty(self): results = porcelain.status(self.repo) self.assertEqual({"add": [], "delete": [], "modify": []}, results.staged) self.assertEqual([], results.unstaged) def test_status_base(self): """Integration test for `status` functionality.""" # Commit a dummy file then modify it fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("origstuff") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( repo=self.repo.path, message=b"test status", author=b"author ", committer=b"committer ", ) # modify access and modify time of path os.utime(fullpath, (0, 0)) with open(fullpath, "wb") as f: f.write(b"stuff") # Make a dummy file and stage it filename_add = "bar" fullpath = os.path.join(self.repo.path, filename_add) with open(fullpath, "w") as f: f.write("stuff") porcelain.add(repo=self.repo.path, paths=fullpath) results = porcelain.status(self.repo) self.assertEqual(results.staged["add"][0], filename_add.encode("ascii")) self.assertEqual(results.unstaged, [b"foo"]) def test_status_all(self): del_path = os.path.join(self.repo.path, "foo") mod_path = os.path.join(self.repo.path, "bar") add_path = os.path.join(self.repo.path, "baz") us_path = os.path.join(self.repo.path, "blye") ut_path = os.path.join(self.repo.path, "blyat") with open(del_path, "w") as f: f.write("origstuff") with open(mod_path, "w") as f: f.write("origstuff") with open(us_path, "w") as f: f.write("origstuff") porcelain.add(repo=self.repo.path, paths=[del_path, mod_path, us_path]) porcelain.commit( repo=self.repo.path, message=b"test status", author=b"author ", committer=b"committer ", ) porcelain.remove(self.repo.path, [del_path]) with open(add_path, "w") as f: f.write("origstuff") with open(mod_path, "w") as f: f.write("more_origstuff") with open(us_path, "w") as f: f.write("more_origstuff") porcelain.add(repo=self.repo.path, paths=[add_path, mod_path]) with open(us_path, "w") as f: f.write("\norigstuff") with open(ut_path, "w") as f: f.write("origstuff") results = porcelain.status(self.repo.path) self.assertDictEqual( {"add": [b"baz"], "delete": [b"foo"], "modify": [b"bar"]}, results.staged, ) self.assertListEqual(results.unstaged, [b"blye"]) self.assertListEqual(results.untracked, ["blyat"]) def test_status_crlf_mismatch(self): # First make a commit as if the file has been added on a Linux system # or with core.autocrlf=True file_path = os.path.join(self.repo.path, "crlf") with open(file_path, "wb") as f: f.write(b"line1\nline2") porcelain.add(repo=self.repo.path, paths=[file_path]) porcelain.commit( repo=self.repo.path, message=b"test status", author=b"author ", committer=b"committer ", ) # Then update the file as if it was created by CGit on a Windows # system with core.autocrlf=true with open(file_path, "wb") as f: f.write(b"line1\r\nline2") results = porcelain.status(self.repo) self.assertDictEqual({"add": [], "delete": [], "modify": []}, results.staged) self.assertListEqual(results.unstaged, [b"crlf"]) self.assertListEqual(results.untracked, []) - def test_status_crlf_convert(self): + def test_status_crlf_no_convert(self): # First make a commit as if the file has been added on a Linux system # or with core.autocrlf=True file_path = os.path.join(self.repo.path, "crlf") with open(file_path, "wb") as f: f.write(b"line1\nline2") porcelain.add(repo=self.repo.path, paths=[file_path]) porcelain.commit( repo=self.repo.path, message=b"test status", author=b"author ", committer=b"committer ", ) # Then update the file as if it was created by CGit on a Windows # system with core.autocrlf=true with open(file_path, "wb") as f: f.write(b"line1\r\nline2") # TODO: It should be set automatically by looking at the configuration c = self.repo.get_config() c.set("core", "autocrlf", True) c.write_to_path() + # The file should be seen as modified as the line-ending conversion + # will NOT be applied since the file is already in the store and in + # the staging area results = porcelain.status(self.repo) self.assertDictEqual({"add": [], "delete": [], "modify": []}, results.staged) + self.assertListEqual(results.unstaged, [b"crlf"]) + self.assertListEqual(results.untracked, []) + + def test_status_crlf_convert(self): + # With an empty repo + file_path = os.path.join(self.repo.path, 'crlf') + repo = Repo(self.repo_path) + + c = self.repo.get_config() + c.set("core", "autocrlf", True) + c.write_to_path() + + # Write the file as it would be on Windows + with open(file_path, 'wb') as f: + f.write(b'line1\r\nline2') + + # Stage the file, the conversion should happens as the file is new + repo.stage([b"crlf"]) + + # So far, the file should be seen only as added + results = porcelain.status(self.repo) + self.assertDictEqual( + {'add': [b"crlf"], 'delete': [], 'modify': []}, + results.staged) + self.assertListEqual(results.unstaged, []) + self.assertListEqual(results.untracked, []) + + # Then update the file line-ending to Unix line endings + with open(file_path, 'wb') as f: + f.write(b'line1\nline2') + + # It should match the blob in staging area, so the file shouldn't be + # shown as unstaged + results = porcelain.status(self.repo) + self.assertDictEqual( + {'add': [b"crlf"], 'delete': [], 'modify': []}, + results.staged) self.assertListEqual(results.unstaged, []) self.assertListEqual(results.untracked, []) def test_get_tree_changes_add(self): """Unit test for get_tree_changes add.""" # Make a dummy file, stage filename = "bar" fullpath = os.path.join(self.repo.path, filename) with open(fullpath, "w") as f: f.write("stuff") porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit( repo=self.repo.path, message=b"test status", author=b"author ", committer=b"committer ", ) filename = "foo" fullpath = os.path.join(self.repo.path, filename) with open(fullpath, "w") as f: f.write("stuff") porcelain.add(repo=self.repo.path, paths=fullpath) changes = porcelain.get_tree_changes(self.repo.path) self.assertEqual(changes["add"][0], filename.encode("ascii")) self.assertEqual(len(changes["add"]), 1) self.assertEqual(len(changes["modify"]), 0) self.assertEqual(len(changes["delete"]), 0) def test_get_tree_changes_modify(self): """Unit test for get_tree_changes modify.""" # Make a dummy file, stage, commit, modify filename = "foo" fullpath = os.path.join(self.repo.path, filename) with open(fullpath, "w") as f: f.write("stuff") porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit( repo=self.repo.path, message=b"test status", author=b"author ", committer=b"committer ", ) with open(fullpath, "w") as f: f.write("otherstuff") porcelain.add(repo=self.repo.path, paths=fullpath) changes = porcelain.get_tree_changes(self.repo.path) self.assertEqual(changes["modify"][0], filename.encode("ascii")) self.assertEqual(len(changes["add"]), 0) self.assertEqual(len(changes["modify"]), 1) self.assertEqual(len(changes["delete"]), 0) def test_get_tree_changes_delete(self): """Unit test for get_tree_changes delete.""" # Make a dummy file, stage, commit, remove filename = "foo" fullpath = os.path.join(self.repo.path, filename) with open(fullpath, "w") as f: f.write("stuff") porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit( repo=self.repo.path, message=b"test status", author=b"author ", committer=b"committer ", ) cwd = os.getcwd() try: os.chdir(self.repo.path) porcelain.remove(repo=self.repo.path, paths=[filename]) finally: os.chdir(cwd) changes = porcelain.get_tree_changes(self.repo.path) self.assertEqual(changes["delete"][0], filename.encode("ascii")) self.assertEqual(len(changes["add"]), 0) self.assertEqual(len(changes["modify"]), 0) self.assertEqual(len(changes["delete"]), 1) def test_get_untracked_paths(self): with open(os.path.join(self.repo.path, ".gitignore"), "w") as f: f.write("ignored\n") with open(os.path.join(self.repo.path, "ignored"), "w") as f: f.write("blah\n") with open(os.path.join(self.repo.path, "notignored"), "w") as f: f.write("blah\n") os.symlink( os.path.join(self.repo.path, os.pardir, "external_target"), os.path.join(self.repo.path, "link"), ) self.assertEqual( set(["ignored", "notignored", ".gitignore", "link"]), set( porcelain.get_untracked_paths( self.repo.path, self.repo.path, self.repo.open_index() ) ), ) self.assertEqual( set([".gitignore", "notignored", "link"]), set(porcelain.status(self.repo).untracked), ) self.assertEqual( set([".gitignore", "notignored", "ignored", "link"]), set(porcelain.status(self.repo, ignored=True).untracked), ) def test_get_untracked_paths_subrepo(self): with open(os.path.join(self.repo.path, ".gitignore"), "w") as f: f.write("nested/\n") with open(os.path.join(self.repo.path, "notignored"), "w") as f: f.write("blah\n") subrepo = Repo.init(os.path.join(self.repo.path, "nested"), mkdir=True) with open(os.path.join(subrepo.path, "ignored"), "w") as f: f.write("bleep\n") with open(os.path.join(subrepo.path, "with"), "w") as f: f.write("bloop\n") with open(os.path.join(subrepo.path, "manager"), "w") as f: f.write("blop\n") self.assertEqual( set([".gitignore", "notignored", os.path.join("nested", "")]), set( porcelain.get_untracked_paths( self.repo.path, self.repo.path, self.repo.open_index() ) ), ) self.assertEqual( set([".gitignore", "notignored"]), set( porcelain.get_untracked_paths( self.repo.path, self.repo.path, self.repo.open_index(), exclude_ignored=True, ) ), ) self.assertEqual( set(["ignored", "with", "manager"]), set( porcelain.get_untracked_paths( subrepo.path, subrepo.path, subrepo.open_index() ) ), ) self.assertEqual( set(), set( porcelain.get_untracked_paths( subrepo.path, self.repo.path, self.repo.open_index(), ) ), ) self.assertEqual( set([os.path.join('nested', 'ignored'), os.path.join('nested', 'with'), os.path.join('nested', 'manager')]), set( porcelain.get_untracked_paths( self.repo.path, subrepo.path, self.repo.open_index(), ) ), ) def test_get_untracked_paths_subdir(self): with open(os.path.join(self.repo.path, ".gitignore"), "w") as f: f.write("subdir/\nignored") with open(os.path.join(self.repo.path, "notignored"), "w") as f: f.write("blah\n") os.mkdir(os.path.join(self.repo.path, "subdir")) with open(os.path.join(self.repo.path, "ignored"), "w") as f: f.write("foo") with open(os.path.join(self.repo.path, "subdir", "ignored"), "w") as f: f.write("foo") self.assertEqual( set( [ ".gitignore", "notignored", "ignored", os.path.join("subdir", ""), ] ), set( porcelain.get_untracked_paths( self.repo.path, self.repo.path, self.repo.open_index(), ) ) ) self.assertEqual( set([".gitignore", "notignored"]), set( porcelain.get_untracked_paths( self.repo.path, self.repo.path, self.repo.open_index(), exclude_ignored=True, ) ) ) # TODO(jelmer): Add test for dulwich.porcelain.daemon class UploadPackTests(PorcelainTestCase): """Tests for upload_pack.""" def test_upload_pack(self): outf = BytesIO() exitcode = porcelain.upload_pack(self.repo.path, BytesIO(b"0000"), outf) outlines = outf.getvalue().splitlines() self.assertEqual([b"0000"], outlines) self.assertEqual(0, exitcode) class ReceivePackTests(PorcelainTestCase): """Tests for receive_pack.""" def test_receive_pack(self): filename = "foo" fullpath = os.path.join(self.repo.path, filename) with open(fullpath, "w") as f: f.write("stuff") porcelain.add(repo=self.repo.path, paths=fullpath) self.repo.do_commit( message=b"test status", author=b"author ", committer=b"committer ", author_timestamp=1402354300, commit_timestamp=1402354300, author_timezone=0, commit_timezone=0, ) outf = BytesIO() exitcode = porcelain.receive_pack(self.repo.path, BytesIO(b"0000"), outf) outlines = outf.getvalue().splitlines() self.assertEqual( [ b"0091319b56ce3aee2d489f759736a79cc552c9bb86d9 HEAD\x00 report-status " # noqa: E501 b"delete-refs quiet ofs-delta side-band-64k " b"no-done symref=HEAD:refs/heads/master", b"003f319b56ce3aee2d489f759736a79cc552c9bb86d9 refs/heads/master", b"0000", ], outlines, ) self.assertEqual(0, exitcode) class BranchListTests(PorcelainTestCase): def test_standard(self): self.assertEqual(set([]), set(porcelain.branch_list(self.repo))) def test_new_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b"foo") self.assertEqual( set([b"master", b"foo"]), set(porcelain.branch_list(self.repo)) ) class BranchCreateTests(PorcelainTestCase): def test_branch_exists(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b"foo") self.assertRaises(porcelain.Error, porcelain.branch_create, self.repo, b"foo") porcelain.branch_create(self.repo, b"foo", force=True) def test_new_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b"foo") self.assertEqual( set([b"master", b"foo"]), set(porcelain.branch_list(self.repo)) ) class BranchDeleteTests(PorcelainTestCase): def test_simple(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b"foo") self.assertTrue(b"foo" in porcelain.branch_list(self.repo)) porcelain.branch_delete(self.repo, b"foo") self.assertFalse(b"foo" in porcelain.branch_list(self.repo)) def test_simple_unicode(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, "foo") self.assertTrue(b"foo" in porcelain.branch_list(self.repo)) porcelain.branch_delete(self.repo, "foo") self.assertFalse(b"foo" in porcelain.branch_list(self.repo)) class FetchTests(PorcelainTestCase): def test_simple(self): outstream = BytesIO() errstream = BytesIO() # create a file for initial commit handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit( repo=self.repo.path, message=b"test", author=b"test ", committer=b"test ", ) # Setup target repo target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) target_repo = porcelain.clone( self.repo.path, target=target_path, errstream=errstream ) # create a second file to be pushed handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit( repo=self.repo.path, message=b"test2", author=b"test2 ", committer=b"test2 ", ) self.assertFalse(self.repo[b"HEAD"].id in target_repo) target_repo.close() # Fetch changes into the cloned repo porcelain.fetch(target_path, "origin", outstream=outstream, errstream=errstream) # Assert that fetch updated the local image of the remote self.assert_correct_remote_refs(target_repo.get_refs(), self.repo.get_refs()) # Check the target repo for pushed changes with Repo(target_path) as r: self.assertTrue(self.repo[b"HEAD"].id in r) def test_with_remote_name(self): remote_name = "origin" outstream = BytesIO() errstream = BytesIO() # create a file for initial commit handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit( repo=self.repo.path, message=b"test", author=b"test ", committer=b"test ", ) # Setup target repo target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) target_repo = porcelain.clone( self.repo.path, target=target_path, errstream=errstream ) # Capture current refs target_refs = target_repo.get_refs() # create a second file to be pushed handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit( repo=self.repo.path, message=b"test2", author=b"test2 ", committer=b"test2 ", ) self.assertFalse(self.repo[b"HEAD"].id in target_repo) target_config = target_repo.get_config() target_config.set( (b"remote", remote_name.encode()), b"url", self.repo.path.encode() ) target_repo.close() # Fetch changes into the cloned repo porcelain.fetch( target_path, remote_name, outstream=outstream, errstream=errstream ) # Assert that fetch updated the local image of the remote self.assert_correct_remote_refs(target_repo.get_refs(), self.repo.get_refs()) # Check the target repo for pushed changes, as well as updates # for the refs with Repo(target_path) as r: self.assertTrue(self.repo[b"HEAD"].id in r) self.assertNotEqual(self.repo.get_refs(), target_refs) def assert_correct_remote_refs( self, local_refs, remote_refs, remote_name=b"origin" ): """Assert that known remote refs corresponds to actual remote refs.""" local_ref_prefix = b"refs/heads" remote_ref_prefix = b"refs/remotes/" + remote_name locally_known_remote_refs = { k[len(remote_ref_prefix) + 1 :]: v for k, v in local_refs.items() if k.startswith(remote_ref_prefix) } normalized_remote_refs = { k[len(local_ref_prefix) + 1 :]: v for k, v in remote_refs.items() if k.startswith(local_ref_prefix) } self.assertEqual(locally_known_remote_refs, normalized_remote_refs) class RepackTests(PorcelainTestCase): def test_empty(self): porcelain.repack(self.repo) def test_simple(self): handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.repack(self.repo) class LsTreeTests(PorcelainTestCase): def test_empty(self): porcelain.commit( repo=self.repo.path, message=b"test status", author=b"author ", committer=b"committer ", ) f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f) self.assertEqual(f.getvalue(), "") def test_simple(self): # Commit a dummy file then modify it fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("origstuff") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( repo=self.repo.path, message=b"test status", author=b"author ", committer=b"committer ", ) f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f) self.assertEqual( f.getvalue(), "100644 blob 8b82634d7eae019850bb883f06abf428c58bc9aa\tfoo\n", ) def test_recursive(self): # Create a directory then write a dummy file in it dirpath = os.path.join(self.repo.path, "adir") filepath = os.path.join(dirpath, "afile") os.mkdir(dirpath) with open(filepath, "w") as f: f.write("origstuff") porcelain.add(repo=self.repo.path, paths=[filepath]) porcelain.commit( repo=self.repo.path, message=b"test status", author=b"author ", committer=b"committer ", ) f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f) self.assertEqual( f.getvalue(), "40000 tree b145cc69a5e17693e24d8a7be0016ed8075de66d\tadir\n", ) f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f, recursive=True) self.assertEqual( f.getvalue(), "40000 tree b145cc69a5e17693e24d8a7be0016ed8075de66d\tadir\n" "100644 blob 8b82634d7eae019850bb883f06abf428c58bc9aa\tadir" "/afile\n", ) class LsRemoteTests(PorcelainTestCase): def test_empty(self): self.assertEqual({}, porcelain.ls_remote(self.repo.path)) def test_some(self): cid = porcelain.commit( repo=self.repo.path, message=b"test status", author=b"author ", committer=b"committer ", ) self.assertEqual( {b"refs/heads/master": cid, b"HEAD": cid}, porcelain.ls_remote(self.repo.path), ) class LsFilesTests(PorcelainTestCase): def test_empty(self): self.assertEqual([], list(porcelain.ls_files(self.repo))) def test_simple(self): # Commit a dummy file then modify it fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("origstuff") porcelain.add(repo=self.repo.path, paths=[fullpath]) self.assertEqual([b"foo"], list(porcelain.ls_files(self.repo))) class RemoteAddTests(PorcelainTestCase): def test_new(self): porcelain.remote_add(self.repo, "jelmer", "git://jelmer.uk/code/dulwich") c = self.repo.get_config() self.assertEqual( c.get((b"remote", b"jelmer"), b"url"), b"git://jelmer.uk/code/dulwich", ) def test_exists(self): porcelain.remote_add(self.repo, "jelmer", "git://jelmer.uk/code/dulwich") self.assertRaises( porcelain.RemoteExists, porcelain.remote_add, self.repo, "jelmer", "git://jelmer.uk/code/dulwich", ) class CheckIgnoreTests(PorcelainTestCase): def test_check_ignored(self): with open(os.path.join(self.repo.path, ".gitignore"), "w") as f: f.write("foo") foo_path = os.path.join(self.repo.path, "foo") with open(foo_path, "w") as f: f.write("BAR") bar_path = os.path.join(self.repo.path, "bar") with open(bar_path, "w") as f: f.write("BAR") self.assertEqual(["foo"], list(porcelain.check_ignore(self.repo, [foo_path]))) self.assertEqual([], list(porcelain.check_ignore(self.repo, [bar_path]))) def test_check_added_abs(self): path = os.path.join(self.repo.path, "foo") with open(path, "w") as f: f.write("BAR") self.repo.stage(["foo"]) with open(os.path.join(self.repo.path, ".gitignore"), "w") as f: f.write("foo\n") self.assertEqual([], list(porcelain.check_ignore(self.repo, [path]))) self.assertEqual( ["foo"], list(porcelain.check_ignore(self.repo, [path], no_index=True)), ) def test_check_added_rel(self): with open(os.path.join(self.repo.path, "foo"), "w") as f: f.write("BAR") self.repo.stage(["foo"]) with open(os.path.join(self.repo.path, ".gitignore"), "w") as f: f.write("foo\n") cwd = os.getcwd() os.mkdir(os.path.join(self.repo.path, "bar")) os.chdir(os.path.join(self.repo.path, "bar")) try: self.assertEqual(list(porcelain.check_ignore(self.repo, ["../foo"])), []) self.assertEqual( ["../foo"], list(porcelain.check_ignore(self.repo, ["../foo"], no_index=True)), ) finally: os.chdir(cwd) class UpdateHeadTests(PorcelainTestCase): def test_set_to_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, "blah") self.assertEqual(c1.id, self.repo.head()) self.assertEqual(b"ref: refs/heads/blah", self.repo.refs.read_ref(b"HEAD")) def test_set_to_branch_detached(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, "blah", detached=True) self.assertEqual(c1.id, self.repo.head()) self.assertEqual(c1.id, self.repo.refs.read_ref(b"HEAD")) def test_set_to_commit_detached(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, c1.id, detached=True) self.assertEqual(c1.id, self.repo.head()) self.assertEqual(c1.id, self.repo.refs.read_ref(b"HEAD")) def test_set_new_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, "blah", new_branch="bar") self.assertEqual(c1.id, self.repo.head()) self.assertEqual(b"ref: refs/heads/bar", self.repo.refs.read_ref(b"HEAD")) class MailmapTests(PorcelainTestCase): def test_no_mailmap(self): self.assertEqual( b"Jelmer Vernooij ", porcelain.check_mailmap(self.repo, b"Jelmer Vernooij "), ) def test_mailmap_lookup(self): with open(os.path.join(self.repo.path, ".mailmap"), "wb") as f: f.write( b"""\ Jelmer Vernooij """ ) self.assertEqual( b"Jelmer Vernooij ", porcelain.check_mailmap(self.repo, b"Jelmer Vernooij "), ) class FsckTests(PorcelainTestCase): def test_none(self): self.assertEqual([], list(porcelain.fsck(self.repo))) def test_git_dir(self): obj = Tree() a = Blob() a.data = b"foo" obj.add(b".git", 0o100644, a.id) self.repo.object_store.add_objects([(a, None), (obj, None)]) self.assertEqual( [(obj.id, "invalid name .git")], [(sha, str(e)) for (sha, e) in porcelain.fsck(self.repo)], ) class DescribeTests(PorcelainTestCase): def test_no_commits(self): self.assertRaises(KeyError, porcelain.describe, self.repo.path) def test_single_commit(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) sha = porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ", ) self.assertEqual( "g{}".format(sha[:7].decode("ascii")), porcelain.describe(self.repo.path), ) def test_tag(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ", ) porcelain.tag_create( self.repo.path, b"tryme", b"foo ", b"bar", annotated=True, ) self.assertEqual("tryme", porcelain.describe(self.repo.path)) def test_tag_and_commit(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ", ) porcelain.tag_create( self.repo.path, b"tryme", b"foo ", b"bar", annotated=True, ) with open(fullpath, "w") as f: f.write("BAR2") porcelain.add(repo=self.repo.path, paths=[fullpath]) sha = porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ", ) self.assertEqual( "tryme-1-g{}".format(sha[:7].decode("ascii")), porcelain.describe(self.repo.path), ) class PathToTreeTests(PorcelainTestCase): def setUp(self): super(PathToTreeTests, self).setUp() self.fp = os.path.join(self.test_dir, "bar") with open(self.fp, "w") as f: f.write("something") oldcwd = os.getcwd() self.addCleanup(os.chdir, oldcwd) os.chdir(self.test_dir) def test_path_to_tree_path_base(self): self.assertEqual(b"bar", porcelain.path_to_tree_path(self.test_dir, self.fp)) self.assertEqual(b"bar", porcelain.path_to_tree_path(".", "./bar")) self.assertEqual(b"bar", porcelain.path_to_tree_path(".", "bar")) cwd = os.getcwd() self.assertEqual( b"bar", porcelain.path_to_tree_path(".", os.path.join(cwd, "bar")) ) self.assertEqual(b"bar", porcelain.path_to_tree_path(cwd, "bar")) def test_path_to_tree_path_syntax(self): self.assertEqual(b"bar", porcelain.path_to_tree_path(".", "./bar")) def test_path_to_tree_path_error(self): with self.assertRaises(ValueError): with tempfile.TemporaryDirectory() as od: porcelain.path_to_tree_path(od, self.fp) def test_path_to_tree_path_rel(self): cwd = os.getcwd() os.mkdir(os.path.join(self.repo.path, "foo")) os.mkdir(os.path.join(self.repo.path, "foo/bar")) try: os.chdir(os.path.join(self.repo.path, "foo/bar")) with open("baz", "w") as f: f.write("contents") self.assertEqual(b"bar/baz", porcelain.path_to_tree_path("..", "baz")) self.assertEqual( b"bar/baz", porcelain.path_to_tree_path( os.path.join(os.getcwd(), ".."), os.path.join(os.getcwd(), "baz"), ), ) self.assertEqual( b"bar/baz", porcelain.path_to_tree_path("..", os.path.join(os.getcwd(), "baz")), ) self.assertEqual( b"bar/baz", porcelain.path_to_tree_path(os.path.join(os.getcwd(), ".."), "baz"), ) finally: os.chdir(cwd) class GetObjectByPathTests(PorcelainTestCase): def test_simple(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ", ) self.assertEqual(b"BAR", porcelain.get_object_by_path(self.repo, "foo").data) self.assertEqual(b"BAR", porcelain.get_object_by_path(self.repo, b"foo").data) def test_encoding(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ", encoding=b"utf-8", ) self.assertEqual(b"BAR", porcelain.get_object_by_path(self.repo, "foo").data) self.assertEqual(b"BAR", porcelain.get_object_by_path(self.repo, b"foo").data) def test_missing(self): self.assertRaises(KeyError, porcelain.get_object_by_path, self.repo, "foo") class WriteTreeTests(PorcelainTestCase): def test_simple(self): fullpath = os.path.join(self.repo.path, "foo") with open(fullpath, "w") as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) self.assertEqual( b"d2092c8a9f311f0311083bf8d177f2ca0ab5b241", porcelain.write_tree(self.repo), ) class ActiveBranchTests(PorcelainTestCase): def test_simple(self): self.assertEqual(b"master", porcelain.active_branch(self.repo))