diff --git a/dulwich/diff_tree.py b/dulwich/diff_tree.py index 167cb28e..7166c97a 100644 --- a/dulwich/diff_tree.py +++ b/dulwich/diff_tree.py @@ -1,608 +1,623 @@ # diff_tree.py -- Utilities for diffing files and trees. # Copyright (C) 2010 Google, Inc. # # 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. # """Utilities for diffing files and trees.""" import sys from collections import ( defaultdict, namedtuple, ) from io import BytesIO from itertools import chain import stat from dulwich.objects import ( S_ISGITLINK, TreeEntry, ) # TreeChange type constants. CHANGE_ADD = 'add' CHANGE_MODIFY = 'modify' CHANGE_DELETE = 'delete' CHANGE_RENAME = 'rename' CHANGE_COPY = 'copy' CHANGE_UNCHANGED = 'unchanged' RENAME_CHANGE_TYPES = (CHANGE_RENAME, CHANGE_COPY) _NULL_ENTRY = TreeEntry(None, None, None) _MAX_SCORE = 100 RENAME_THRESHOLD = 60 MAX_FILES = 200 REWRITE_THRESHOLD = None class TreeChange(namedtuple('TreeChange', ['type', 'old', 'new'])): """Named tuple a single change between two trees.""" @classmethod def add(cls, new): return cls(CHANGE_ADD, _NULL_ENTRY, new) @classmethod def delete(cls, old): return cls(CHANGE_DELETE, old, _NULL_ENTRY) def _tree_entries(path, tree): result = [] if not tree: return result for entry in tree.iteritems(name_order=True): result.append(entry.in_path(path)) return result def _merge_entries(path, tree1, tree2): """Merge the entries of two trees. - :param path: A path to prepend to all tree entry names. - :param tree1: The first Tree object to iterate, or None. - :param tree2: The second Tree object to iterate, or None. - :return: A list of pairs of TreeEntry objects for each pair of entries in + Args: + path: A path to prepend to all tree entry names. + tree1: The first Tree object to iterate, or None. + tree2: The second Tree object to iterate, or None. + Returns: + A list of pairs of TreeEntry objects for each pair of entries in the trees. If an entry exists in one tree but not the other, the other entry will have all attributes set to None. If neither entry's path is None, they are guaranteed to match. """ entries1 = _tree_entries(path, tree1) entries2 = _tree_entries(path, tree2) i1 = i2 = 0 len1 = len(entries1) len2 = len(entries2) result = [] while i1 < len1 and i2 < len2: entry1 = entries1[i1] entry2 = entries2[i2] if entry1.path < entry2.path: result.append((entry1, _NULL_ENTRY)) i1 += 1 elif entry1.path > entry2.path: result.append((_NULL_ENTRY, entry2)) i2 += 1 else: result.append((entry1, entry2)) i1 += 1 i2 += 1 for i in range(i1, len1): result.append((entries1[i], _NULL_ENTRY)) for i in range(i2, len2): result.append((_NULL_ENTRY, entries2[i])) return result def _is_tree(entry): mode = entry.mode if mode is None: return False return stat.S_ISDIR(mode) def walk_trees(store, tree1_id, tree2_id, prune_identical=False): """Recursively walk all the entries of two trees. Iteration is depth-first pre-order, as in e.g. os.walk. - :param store: An ObjectStore for looking up objects. - :param tree1_id: The SHA of the first Tree object to iterate, or None. - :param tree2_id: The SHA of the second Tree object to iterate, or None. - :param prune_identical: If True, identical subtrees will not be walked. - :return: Iterator over Pairs of TreeEntry objects for each pair of entries + Args: + store: An ObjectStore for looking up objects. + tree1_id: The SHA of the first Tree object to iterate, or None. + tree2_id: The SHA of the second Tree object to iterate, or None. + param prune_identical: If True, identical subtrees will not be walked. + Returns: + Iterator over Pairs of TreeEntry objects for each pair of entries in the trees and their subtrees recursively. If an entry exists in one tree but not the other, the other entry will have all attributes set to None. If neither entry's path is None, they are guaranteed to match. """ # This could be fairly easily generalized to >2 trees if we find a use # case. mode1 = tree1_id and stat.S_IFDIR or None mode2 = tree2_id and stat.S_IFDIR or None todo = [(TreeEntry(b'', mode1, tree1_id), TreeEntry(b'', mode2, tree2_id))] while todo: entry1, entry2 = todo.pop() is_tree1 = _is_tree(entry1) is_tree2 = _is_tree(entry2) if prune_identical and is_tree1 and is_tree2 and entry1 == entry2: continue tree1 = is_tree1 and store[entry1.sha] or None tree2 = is_tree2 and store[entry2.sha] or None path = entry1.path or entry2.path todo.extend(reversed(_merge_entries(path, tree1, tree2))) yield entry1, entry2 def _skip_tree(entry, include_trees): if entry.mode is None or (not include_trees and stat.S_ISDIR(entry.mode)): return _NULL_ENTRY return entry def tree_changes(store, tree1_id, tree2_id, want_unchanged=False, rename_detector=None, include_trees=False, change_type_same=False): """Find the differences between the contents of two trees. - :param store: An ObjectStore for looking up objects. - :param tree1_id: The SHA of the source tree. - :param tree2_id: The SHA of the target tree. - :param want_unchanged: If True, include TreeChanges for unmodified entries + Args: + store: An ObjectStore for looking up objects. + tree1_id: The SHA of the source tree. + tree2_id: The SHA of the target tree. + want_unchanged: If True, include TreeChanges for unmodified entries as well. - :param include_trees: Whether to include trees - :param rename_detector: RenameDetector object for detecting renames. - :param change_type_same: Whether to report change types in the same + include_trees: Whether to include trees + rename_detector: RenameDetector object for detecting renames. + change_type_same: Whether to report change types in the same entry or as delete+add. - :return: Iterator over TreeChange instances for each change between the + Returns: + Iterator over TreeChange instances for each change between the source and target tree. """ if include_trees and rename_detector is not None: raise NotImplementedError( 'rename_detector and include_trees are mutually exclusive') if (rename_detector is not None and tree1_id is not None and tree2_id is not None): for change in rename_detector.changes_with_renames( tree1_id, tree2_id, want_unchanged=want_unchanged): yield change return entries = walk_trees(store, tree1_id, tree2_id, prune_identical=(not want_unchanged)) for entry1, entry2 in entries: if entry1 == entry2 and not want_unchanged: continue # Treat entries for trees as missing. entry1 = _skip_tree(entry1, include_trees) entry2 = _skip_tree(entry2, include_trees) if entry1 != _NULL_ENTRY and entry2 != _NULL_ENTRY: if (stat.S_IFMT(entry1.mode) != stat.S_IFMT(entry2.mode) and not change_type_same): # File type changed: report as delete/add. yield TreeChange.delete(entry1) entry1 = _NULL_ENTRY change_type = CHANGE_ADD elif entry1 == entry2: change_type = CHANGE_UNCHANGED else: change_type = CHANGE_MODIFY elif entry1 != _NULL_ENTRY: change_type = CHANGE_DELETE elif entry2 != _NULL_ENTRY: change_type = CHANGE_ADD else: # Both were None because at least one was a tree. continue yield TreeChange(change_type, entry1, entry2) def _all_eq(seq, key, value): for e in seq: if key(e) != value: return False return True def _all_same(seq, key): return _all_eq(seq[1:], key, key(seq[0])) def tree_changes_for_merge(store, parent_tree_ids, tree_id, rename_detector=None): """Get the tree changes for a merge tree relative to all its parents. - :param store: An ObjectStore for looking up objects. - :param parent_tree_ids: An iterable of the SHAs of the parent trees. - :param tree_id: The SHA of the merge tree. - :param rename_detector: RenameDetector object for detecting renames. + Args: + store: An ObjectStore for looking up objects. + parent_tree_ids: An iterable of the SHAs of the parent trees. + tree_id: The SHA of the merge tree. + rename_detector: RenameDetector object for detecting renames. - :return: Iterator over lists of TreeChange objects, one per conflicted path - in the merge. + Returns: + Iterator over lists of TreeChange objects, one per conflicted path + in the merge. - Each list contains one element per parent, with the TreeChange for that - path relative to that parent. An element may be None if it never - existed in one parent and was deleted in two others. + Each list contains one element per parent, with the TreeChange for that + path relative to that parent. An element may be None if it never + existed in one parent and was deleted in two others. - A path is only included in the output if it is a conflict, i.e. its SHA - in the merge tree is not found in any of the parents, or in the case of - deletes, if not all of the old SHAs match. + A path is only included in the output if it is a conflict, i.e. its SHA + in the merge tree is not found in any of the parents, or in the case of + deletes, if not all of the old SHAs match. """ all_parent_changes = [tree_changes(store, t, tree_id, rename_detector=rename_detector) for t in parent_tree_ids] num_parents = len(parent_tree_ids) changes_by_path = defaultdict(lambda: [None] * num_parents) # Organize by path. for i, parent_changes in enumerate(all_parent_changes): for change in parent_changes: if change.type == CHANGE_DELETE: path = change.old.path else: path = change.new.path changes_by_path[path][i] = change def old_sha(c): return c.old.sha def change_type(c): return c.type # Yield only conflicting changes. for _, changes in sorted(changes_by_path.items()): assert len(changes) == num_parents have = [c for c in changes if c is not None] if _all_eq(have, change_type, CHANGE_DELETE): if not _all_same(have, old_sha): yield changes elif not _all_same(have, change_type): yield changes elif None not in changes: # If no change was found relative to one parent, that means the SHA # must have matched the SHA in that parent, so it is not a # conflict. yield changes _BLOCK_SIZE = 64 def _count_blocks(obj): """Count the blocks in an object. Splits the data into blocks either on lines or <=64-byte chunks of lines. - :param obj: The object to count blocks for. - :return: A dict of block hashcode -> total bytes occurring. + Args: + obj: The object to count blocks for. + Returns: + A dict of block hashcode -> total bytes occurring. """ block_counts = defaultdict(int) block = BytesIO() n = 0 # Cache attrs as locals to avoid expensive lookups in the inner loop. block_write = block.write block_seek = block.seek block_truncate = block.truncate block_getvalue = block.getvalue for c in chain(*obj.as_raw_chunks()): if sys.version_info[0] == 3: c = c.to_bytes(1, 'big') block_write(c) n += 1 if c == b'\n' or n == _BLOCK_SIZE: value = block_getvalue() block_counts[hash(value)] += len(value) block_seek(0) block_truncate() n = 0 if n > 0: last_block = block_getvalue() block_counts[hash(last_block)] += len(last_block) return block_counts def _common_bytes(blocks1, blocks2): """Count the number of common bytes in two block count dicts. - :param block1: The first dict of block hashcode -> total bytes. - :param block2: The second dict of block hashcode -> total bytes. - :return: The number of bytes in common between blocks1 and blocks2. This is - only approximate due to possible hash collisions. + Args: + block1: The first dict of block hashcode -> total bytes. + block2: The second dict of block hashcode -> total bytes. + Returns: + The number of bytes in common between blocks1 and blocks2. This is + only approximate due to possible hash collisions. """ # Iterate over the smaller of the two dicts, since this is symmetrical. if len(blocks1) > len(blocks2): blocks1, blocks2 = blocks2, blocks1 score = 0 for block, count1 in blocks1.items(): count2 = blocks2.get(block) if count2: score += min(count1, count2) return score def _similarity_score(obj1, obj2, block_cache=None): """Compute a similarity score for two objects. - :param obj1: The first object to score. - :param obj2: The second object to score. - :param block_cache: An optional dict of SHA to block counts to cache + Args: + obj1: The first object to score. + obj2: The second object to score. + block_cache: An optional dict of SHA to block counts to cache results between calls. - :return: The similarity score between the two objects, defined as the + Returns: + The similarity score between the two objects, defined as the number of bytes in common between the two objects divided by the maximum size, scaled to the range 0-100. """ if block_cache is None: block_cache = {} if obj1.id not in block_cache: block_cache[obj1.id] = _count_blocks(obj1) if obj2.id not in block_cache: block_cache[obj2.id] = _count_blocks(obj2) common_bytes = _common_bytes(block_cache[obj1.id], block_cache[obj2.id]) max_size = max(obj1.raw_length(), obj2.raw_length()) if not max_size: return _MAX_SCORE return int(float(common_bytes) * _MAX_SCORE / max_size) def _tree_change_key(entry): # Sort by old path then new path. If only one exists, use it for both keys. path1 = entry.old.path path2 = entry.new.path if path1 is None: path1 = path2 if path2 is None: path2 = path1 return (path1, path2) class RenameDetector(object): """Object for handling rename detection between two trees.""" def __init__(self, store, rename_threshold=RENAME_THRESHOLD, max_files=MAX_FILES, rewrite_threshold=REWRITE_THRESHOLD, find_copies_harder=False): """Initialize the rename detector. - :param store: An ObjectStore for looking up objects. - :param rename_threshold: The threshold similarity score for considering + Args: + store: An ObjectStore for looking up objects. + rename_threshold: The threshold similarity score for considering an add/delete pair to be a rename/copy; see _similarity_score. - :param max_files: The maximum number of adds and deletes to consider, + max_files: The maximum number of adds and deletes to consider, or None for no limit. The detector is guaranteed to compare no more than max_files ** 2 add/delete pairs. This limit is provided because rename detection can be quadratic in the project size. If the limit is exceeded, no content rename detection is attempted. - :param rewrite_threshold: The threshold similarity score below which a + rewrite_threshold: The threshold similarity score below which a modify should be considered a delete/add, or None to not break modifies; see _similarity_score. - :param find_copies_harder: If True, consider unmodified files when + find_copies_harder: If True, consider unmodified files when detecting copies. """ self._store = store self._rename_threshold = rename_threshold self._rewrite_threshold = rewrite_threshold self._max_files = max_files self._find_copies_harder = find_copies_harder self._want_unchanged = False def _reset(self): self._adds = [] self._deletes = [] self._changes = [] def _should_split(self, change): if (self._rewrite_threshold is None or change.type != CHANGE_MODIFY or change.old.sha == change.new.sha): return False old_obj = self._store[change.old.sha] new_obj = self._store[change.new.sha] return _similarity_score(old_obj, new_obj) < self._rewrite_threshold def _add_change(self, change): if change.type == CHANGE_ADD: self._adds.append(change) elif change.type == CHANGE_DELETE: self._deletes.append(change) elif self._should_split(change): self._deletes.append(TreeChange.delete(change.old)) self._adds.append(TreeChange.add(change.new)) elif ((self._find_copies_harder and change.type == CHANGE_UNCHANGED) or change.type == CHANGE_MODIFY): # Treat all modifies as potential deletes for rename detection, # but don't split them (to avoid spurious renames). Setting # find_copies_harder means we treat unchanged the same as # modified. self._deletes.append(change) else: self._changes.append(change) def _collect_changes(self, tree1_id, tree2_id): want_unchanged = self._find_copies_harder or self._want_unchanged for change in tree_changes(self._store, tree1_id, tree2_id, want_unchanged=want_unchanged): self._add_change(change) def _prune(self, add_paths, delete_paths): self._adds = [a for a in self._adds if a.new.path not in add_paths] self._deletes = [d for d in self._deletes if d.old.path not in delete_paths] def _find_exact_renames(self): add_map = defaultdict(list) for add in self._adds: add_map[add.new.sha].append(add.new) delete_map = defaultdict(list) for delete in self._deletes: # Keep track of whether the delete was actually marked as a delete. # If not, it needs to be marked as a copy. is_delete = delete.type == CHANGE_DELETE delete_map[delete.old.sha].append((delete.old, is_delete)) add_paths = set() delete_paths = set() for sha, sha_deletes in delete_map.items(): sha_adds = add_map[sha] for (old, is_delete), new in zip(sha_deletes, sha_adds): if stat.S_IFMT(old.mode) != stat.S_IFMT(new.mode): continue if is_delete: delete_paths.add(old.path) add_paths.add(new.path) new_type = is_delete and CHANGE_RENAME or CHANGE_COPY self._changes.append(TreeChange(new_type, old, new)) num_extra_adds = len(sha_adds) - len(sha_deletes) # TODO(dborowitz): Less arbitrary way of dealing with extra copies. old = sha_deletes[0][0] if num_extra_adds > 0: for new in sha_adds[-num_extra_adds:]: add_paths.add(new.path) self._changes.append(TreeChange(CHANGE_COPY, old, new)) self._prune(add_paths, delete_paths) def _should_find_content_renames(self): return len(self._adds) * len(self._deletes) <= self._max_files ** 2 def _rename_type(self, check_paths, delete, add): if check_paths and delete.old.path == add.new.path: # If the paths match, this must be a split modify, so make sure it # comes out as a modify. return CHANGE_MODIFY elif delete.type != CHANGE_DELETE: # If it's in deletes but not marked as a delete, it must have been # added due to find_copies_harder, and needs to be marked as a # copy. return CHANGE_COPY return CHANGE_RENAME def _find_content_rename_candidates(self): candidates = self._candidates = [] # TODO: Optimizations: # - Compare object sizes before counting blocks. # - Skip if delete's S_IFMT differs from all adds. # - Skip if adds or deletes is empty. # Match C git's behavior of not attempting to find content renames if # the matrix size exceeds the threshold. if not self._should_find_content_renames(): return block_cache = {} check_paths = self._rename_threshold is not None for delete in self._deletes: if S_ISGITLINK(delete.old.mode): continue # Git links don't exist in this repo. old_sha = delete.old.sha old_obj = self._store[old_sha] block_cache[old_sha] = _count_blocks(old_obj) for add in self._adds: if stat.S_IFMT(delete.old.mode) != stat.S_IFMT(add.new.mode): continue new_obj = self._store[add.new.sha] score = _similarity_score(old_obj, new_obj, block_cache=block_cache) if score > self._rename_threshold: new_type = self._rename_type(check_paths, delete, add) rename = TreeChange(new_type, delete.old, add.new) candidates.append((-score, rename)) def _choose_content_renames(self): # Sort scores from highest to lowest, but keep names in ascending # order. self._candidates.sort() delete_paths = set() add_paths = set() for _, change in self._candidates: new_path = change.new.path if new_path in add_paths: continue old_path = change.old.path orig_type = change.type if old_path in delete_paths: change = TreeChange(CHANGE_COPY, change.old, change.new) # If the candidate was originally a copy, that means it came from a # modified or unchanged path, so we don't want to prune it. if orig_type != CHANGE_COPY: delete_paths.add(old_path) add_paths.add(new_path) self._changes.append(change) self._prune(add_paths, delete_paths) def _join_modifies(self): if self._rewrite_threshold is None: return modifies = {} delete_map = dict((d.old.path, d) for d in self._deletes) for add in self._adds: path = add.new.path delete = delete_map.get(path) if (delete is not None and stat.S_IFMT(delete.old.mode) == stat.S_IFMT(add.new.mode)): modifies[path] = TreeChange(CHANGE_MODIFY, delete.old, add.new) self._adds = [a for a in self._adds if a.new.path not in modifies] self._deletes = [a for a in self._deletes if a.new.path not in modifies] self._changes += modifies.values() def _sorted_changes(self): result = [] result.extend(self._adds) result.extend(self._deletes) result.extend(self._changes) result.sort(key=_tree_change_key) return result def _prune_unchanged(self): if self._want_unchanged: return self._deletes = [ d for d in self._deletes if d.type != CHANGE_UNCHANGED] def changes_with_renames(self, tree1_id, tree2_id, want_unchanged=False): """Iterate TreeChanges between two tree SHAs, with rename detection.""" self._reset() self._want_unchanged = want_unchanged self._collect_changes(tree1_id, tree2_id) self._find_exact_renames() self._find_content_rename_candidates() self._choose_content_renames() self._join_modifies() self._prune_unchanged() return self._sorted_changes() # Hold on to the pure-python implementations for testing. _is_tree_py = _is_tree _merge_entries_py = _merge_entries _count_blocks_py = _count_blocks try: # Try to import C versions from dulwich._diff_tree import _is_tree, _merge_entries, _count_blocks except ImportError: pass diff --git a/dulwich/hooks.py b/dulwich/hooks.py index 9ff0ba21..def9c600 100644 --- a/dulwich/hooks.py +++ b/dulwich/hooks.py @@ -1,156 +1,162 @@ # hooks.py -- for dealing with git hooks # Copyright (C) 2012-2013 Jelmer Vernooij and others. # # 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. # """Access to hooks.""" import os import subprocess import sys import tempfile from dulwich.errors import ( HookError, ) class Hook(object): """Generic hook object.""" def execute(self, *args): """Execute the hook with the given args - :param args: argument list to hook - :raise HookError: hook execution failure - :return: a hook may return a useful value + Args: + args: argument list to hook + Raises: + HookError: hook execution failure + Returns: + a hook may return a useful value """ raise NotImplementedError(self.execute) class ShellHook(Hook): """Hook by executable file Implements standard githooks(5) [0]: [0] http://www.kernel.org/pub/software/scm/git/docs/githooks.html """ def __init__(self, name, path, numparam, pre_exec_callback=None, post_exec_callback=None, cwd=None): """Setup shell hook definition - :param name: name of hook for error messages - :param path: absolute path to executable file - :param numparam: number of requirements parameters - :param pre_exec_callback: closure for setup before execution + Args: + name: name of hook for error messages + path: absolute path to executable file + numparam: number of requirements parameters + pre_exec_callback: closure for setup before execution Defaults to None. Takes in the variable argument list from the execute functions and returns a modified argument list for the shell hook. - :param post_exec_callback: closure for cleanup after execution + post_exec_callback: closure for cleanup after execution Defaults to None. Takes in a boolean for hook success and the modified argument list and returns the final hook return value if applicable - :param cwd: working directory to switch to when executing the hook + cwd: working directory to switch to when executing the hook """ self.name = name self.filepath = path self.numparam = numparam self.pre_exec_callback = pre_exec_callback self.post_exec_callback = post_exec_callback self.cwd = cwd if sys.version_info[0] == 2 and sys.platform == 'win32': # Python 2 on windows does not support unicode file paths # http://bugs.python.org/issue1759845 self.filepath = self.filepath.encode(sys.getfilesystemencoding()) def execute(self, *args): """Execute the hook with given args""" if len(args) != self.numparam: raise HookError("Hook %s executed with wrong number of args. \ Expected %d. Saw %d. args: %s" % (self.name, self.numparam, len(args), args)) if (self.pre_exec_callback is not None): args = self.pre_exec_callback(*args) try: ret = subprocess.call([self.filepath] + list(args), cwd=self.cwd) if ret != 0: if (self.post_exec_callback is not None): self.post_exec_callback(0, *args) raise HookError("Hook %s exited with non-zero status" % (self.name)) if (self.post_exec_callback is not None): return self.post_exec_callback(1, *args) except OSError: # no file. silent failure. if (self.post_exec_callback is not None): self.post_exec_callback(0, *args) class PreCommitShellHook(ShellHook): """pre-commit shell hook""" def __init__(self, controldir): filepath = os.path.join(controldir, 'hooks', 'pre-commit') ShellHook.__init__(self, 'pre-commit', filepath, 0, cwd=controldir) class PostCommitShellHook(ShellHook): """post-commit shell hook""" def __init__(self, controldir): filepath = os.path.join(controldir, 'hooks', 'post-commit') ShellHook.__init__(self, 'post-commit', filepath, 0, cwd=controldir) class CommitMsgShellHook(ShellHook): """commit-msg shell hook - :param args[0]: commit message - :return: new commit message or None + Args: + args[0]: commit message + Returns: + new commit message or None """ def __init__(self, controldir): filepath = os.path.join(controldir, 'hooks', 'commit-msg') def prepare_msg(*args): (fd, path) = tempfile.mkstemp() with os.fdopen(fd, 'wb') as f: f.write(args[0]) return (path,) def clean_msg(success, *args): if success: with open(args[0], 'rb') as f: new_msg = f.read() os.unlink(args[0]) return new_msg os.unlink(args[0]) ShellHook.__init__(self, 'commit-msg', filepath, 1, prepare_msg, clean_msg, controldir) diff --git a/dulwich/ignore.py b/dulwich/ignore.py index 9c426727..51dcf178 100644 --- a/dulwich/ignore.py +++ b/dulwich/ignore.py @@ -1,358 +1,362 @@ # Copyright (C) 2017 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. # """Parsing of gitignore files. For details for the matching rules, see https://git-scm.com/docs/gitignore """ import os.path import re import sys def _translate_segment(segment): if segment == b"*": return b'[^/]+' res = b"" i, n = 0, len(segment) while i < n: c = segment[i:i+1] i = i+1 if c == b'*': res += b'[^/]*' elif c == b'?': res += b'[^/]' elif c == b'[': j = i if j < n and segment[j:j+1] == b'!': j = j+1 if j < n and segment[j:j+1] == b']': j = j+1 while j < n and segment[j:j+1] != b']': j = j+1 if j >= n: res += b'\\[' else: stuff = segment[i:j].replace(b'\\', b'\\\\') i = j+1 if stuff.startswith(b'!'): stuff = b'^' + stuff[1:] elif stuff.startswith(b'^'): stuff = b'\\' + stuff res += b'[' + stuff + b']' else: res += re.escape(c) return res def translate(pat): """Translate a shell PATTERN to a regular expression. There is no way to quote meta-characters. Originally copied from fnmatch in Python 2.7, but modified for Dulwich to cope with features in Git ignore patterns. """ res = b'(?ms)' if b'/' not in pat[:-1]: # If there's no slash, this is a filename-based match res += b'(.*/)?' if pat.startswith(b'**/'): # Leading **/ pat = pat[2:] res += b'(.*/)?' if pat.startswith(b'/'): pat = pat[1:] for i, segment in enumerate(pat.split(b'/')): if segment == b'**': res += b'(/.*)?' continue else: res += ((re.escape(b'/') if i > 0 else b'') + _translate_segment(segment)) if not pat.endswith(b'/'): res += b'/?' return res + b'\\Z' def read_ignore_patterns(f): """Read a git ignore file. - :param f: File-like object to read from - :return: List of patterns + Args: + f: File-like object to read from + Returns: List of patterns """ for line in f: line = line.rstrip(b"\r\n") # Ignore blank lines, they're used for readability. if not line: continue if line.startswith(b'#'): # Comment continue # Trailing spaces are ignored unless they are quoted with a backslash. while line.endswith(b' ') and not line.endswith(b'\\ '): line = line[:-1] line = line.replace(b'\\ ', b' ') yield line def match_pattern(path, pattern, ignorecase=False): """Match a gitignore-style pattern against a path. - :param path: Path to match - :param pattern: Pattern to match - :param ignorecase: Whether to do case-sensitive matching - :return: bool indicating whether the pattern matched + Args: + path: Path to match + pattern: Pattern to match + ignorecase: Whether to do case-sensitive matching + Returns: + bool indicating whether the pattern matched """ return Pattern(pattern, ignorecase).match(path) class Pattern(object): """A single ignore pattern.""" def __init__(self, pattern, ignorecase=False): self.pattern = pattern self.ignorecase = ignorecase if pattern[0:1] == b'!': self.is_exclude = False pattern = pattern[1:] else: if pattern[0:1] == b'\\': pattern = pattern[1:] self.is_exclude = True flags = 0 if self.ignorecase: flags = re.IGNORECASE self._re = re.compile(translate(pattern), flags) def __bytes__(self): return self.pattern def __str__(self): return self.pattern.decode(sys.getfilesystemencoding()) def __eq__(self, other): return (type(self) == type(other) and self.pattern == other.pattern and self.ignorecase == other.ignorecase) def __repr__(self): return "%s(%s, %r)" % ( type(self).__name__, self.pattern, self.ignorecase) def match(self, path): """Try to match a path against this ignore pattern. - :param path: Path to match (relative to ignore location) - :return: boolean + Args: + path: Path to match (relative to ignore location) + Returns: boolean """ return bool(self._re.match(path)) class IgnoreFilter(object): def __init__(self, patterns, ignorecase=False): self._patterns = [] self._ignorecase = ignorecase for pattern in patterns: self.append_pattern(pattern) def append_pattern(self, pattern): """Add a pattern to the set.""" self._patterns.append(Pattern(pattern, self._ignorecase)) def find_matching(self, path): """Yield all matching patterns for path. :param path: Path to match :return: Iterator over iterators """ if not isinstance(path, bytes): path = path.encode(sys.getfilesystemencoding()) for pattern in self._patterns: if pattern.match(path): yield pattern def is_ignored(self, path): """Check whether a path is ignored. For directories, include a trailing slash. :return: status is None if file is not mentioned, True if it is included, False if it is explicitly excluded. """ status = None for pattern in self.find_matching(path): status = pattern.is_exclude return status @classmethod def from_path(cls, path, ignorecase=False): with open(path, 'rb') as f: ret = cls(read_ignore_patterns(f), ignorecase) ret._path = path return ret def __repr__(self): if getattr(self, '_path', None) is None: return "<%s>" % (type(self).__name__) else: return "%s.from_path(%r)" % (type(self).__name__, self._path) class IgnoreFilterStack(object): """Check for ignore status in multiple filters.""" def __init__(self, filters): self._filters = filters def is_ignored(self, path): """Check whether a path is explicitly included or excluded in ignores. :param path: Path to check :return: None if the file is not mentioned, True if it is included, False if it is explicitly excluded. """ status = None for filter in self._filters: status = filter.is_ignored(path) if status is not None: return status return status def default_user_ignore_filter_path(config): """Return default user ignore filter path. :param config: A Config object :return: Path to a global ignore file """ try: return config.get((b'core', ), b'excludesFile') except KeyError: pass xdg_config_home = os.environ.get( "XDG_CONFIG_HOME", os.path.expanduser("~/.config/"), ) return os.path.join(xdg_config_home, 'git', 'ignore') class IgnoreFilterManager(object): """Ignore file manager.""" def __init__(self, top_path, global_filters, ignorecase): self._path_filters = {} self._top_path = top_path self._global_filters = global_filters self._ignorecase = ignorecase def __repr__(self): return "%s(%s, %r, %r)" % ( type(self).__name__, self._top_path, self._global_filters, self._ignorecase) def _load_path(self, path): try: return self._path_filters[path] except KeyError: pass p = os.path.join(self._top_path, path, '.gitignore') try: self._path_filters[path] = IgnoreFilter.from_path( p, self._ignorecase) except IOError: self._path_filters[path] = None return self._path_filters[path] def find_matching(self, path): """Find matching patterns for path. Stops after the first ignore file with matches. :param path: Path to check :return: Iterator over Pattern instances """ if os.path.isabs(path): raise ValueError('%s is an absolute path' % path) filters = [(0, f) for f in self._global_filters] if os.path.sep != '/': path = path.replace(os.path.sep, '/') parts = path.split('/') for i in range(len(parts)+1): dirname = '/'.join(parts[:i]) for s, f in filters: relpath = '/'.join(parts[s:i]) if i < len(parts): # Paths leading up to the final part are all directories, # so need a trailing slash. relpath += '/' matches = list(f.find_matching(relpath)) if matches: return iter(matches) ignore_filter = self._load_path(dirname) if ignore_filter is not None: filters.insert(0, (i, ignore_filter)) return iter([]) def is_ignored(self, path): """Check whether a path is explicitly included or excluded in ignores. :param path: Path to check :return: None if the file is not mentioned, True if it is included, False if it is explicitly excluded. """ matches = list(self.find_matching(path)) if matches: return matches[-1].is_exclude return None @classmethod def from_repo(cls, repo): """Create a IgnoreFilterManager from a repository. :param repo: Repository object :return: A `IgnoreFilterManager` object """ global_filters = [] for p in [ os.path.join(repo.controldir(), 'info', 'exclude'), default_user_ignore_filter_path(repo.get_config_stack())]: try: global_filters.append(IgnoreFilter.from_path(p)) except IOError: pass config = repo.get_config_stack() ignorecase = config.get_boolean((b'core'), (b'ignorecase'), False) return cls(repo.path, global_filters, ignorecase)