Application: gvSIG desktop » gvSIG scripting

[Dolphin]

Timestamp=2017,10,11,19,8,11

Version=3

ViewMode=1

# lru_cache.py -- Simple LRU cache for dulwich

# Copyright (C) 2006, 2008 Canonical Ltd

#

# 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

# <http://www.gnu.org/licenses/> for a copy of the GNU General Public License

# and <http://www.apache.org/licenses/LICENSE-2.0> for a copy of the Apache

# License, Version 2.0.

#

"""A simple least-recently-used (LRU) cache."""

_null_key = object()

class _LRUNode(object):

    """This maintains the linked-list which is the lru internals."""

    __slots__ = ('prev', 'next_key', 'key', 'value', 'cleanup', 'size')

    def __init__(self, key, value, cleanup=None):

        self.prev = None

        self.next_key = _null_key

        self.key = key

        self.value = value

        self.cleanup = cleanup

        # TODO: We could compute this 'on-the-fly' like we used to, and remove

        #       one pointer from this object, we just need to decide if it

        #       actually costs us much of anything in normal usage

        self.size = None

    def __repr__(self):

        if self.prev is None:

            prev_key = None

        else:

            prev_key = self.prev.key

        return '%s(%r n:%r p:%r)' % (self.__class__.__name__, self.key,

                                     self.next_key, prev_key)

    def run_cleanup(self):

        if self.cleanup is not None:

            self.cleanup(self.key, self.value)

        self.cleanup = None

        # Just make sure to break any refcycles, etc

        self.value = None

class LRUCache(object):

    """A class which manages a cache of entries, removing unused ones."""

    def __init__(self, max_cache=100, after_cleanup_count=None):

        self._cache = {}

        # The "HEAD" of the lru linked list

        self._most_recently_used = None

        # The "TAIL" of the lru linked list

        self._least_recently_used = None

        self._update_max_cache(max_cache, after_cleanup_count)

    def __contains__(self, key):

        return key in self._cache

    def __getitem__(self, key):

        cache = self._cache

        node = cache[key]

        # Inlined from _record_access to decrease the overhead of __getitem__

        # We also have more knowledge about structure if __getitem__ is

        # succeeding, then we know that self._most_recently_used must not be

        # None, etc.

        mru = self._most_recently_used

        if node is mru:

            # Nothing to do, this node is already at the head of the queue

            return node.value

        # Remove this node from the old location

        node_prev = node.prev

        next_key = node.next_key

        # benchmarking shows that the lookup of _null_key in globals is faster

        # than the attribute lookup for (node is self._least_recently_used)

        if next_key is _null_key:

            # 'node' is the _least_recently_used, because it doesn't have a

            # 'next' item. So move the current lru to the previous node.

            self._least_recently_used = node_prev

        else:

            node_next = cache[next_key]

            node_next.prev = node_prev

        node_prev.next_key = next_key

        # Insert this node at the front of the list

        node.next_key = mru.key

        mru.prev = node

        self._most_recently_used = node

        node.prev = None

        return node.value

    def __len__(self):

        return len(self._cache)

    def _walk_lru(self):

        """Walk the LRU list, only meant to be used in tests."""

        node = self._most_recently_used

        if node is not None:

            if node.prev is not None:

                raise AssertionError('the _most_recently_used entry is not'

                                     ' supposed to have a previous entry'

                                     ' %s' % (node,))

        while node is not None:

            if node.next_key is _null_key:

                if node is not self._least_recently_used:

                    raise AssertionError('only the last node should have'

                                         ' no next value: %s' % (node,))

                node_next = None

            else:

                node_next = self._cache[node.next_key]

                if node_next.prev is not node:

                    raise AssertionError('inconsistency found, node.next.prev'

                                         ' != node: %s' % (node,))

            if node.prev is None:

                if node is not self._most_recently_used:

                    raise AssertionError('only the _most_recently_used should'

                                         ' not have a previous node: %s'

                                         % (node,))

            else:

                if node.prev.next_key != node.key:

                    raise AssertionError('inconsistency found, node.prev.next'

                                         ' != node: %s' % (node,))

            yield node

            node = node_next

    def add(self, key, value, cleanup=None):

        """Add a new value to the cache.

        Also, if the entry is ever removed from the cache, call

        cleanup(key, value).

        :param key: The key to store it under

        :param value: The object to store

        :param cleanup: None or a function taking (key, value) to indicate

                        'value' should be cleaned up.

        """

        if key is _null_key:

            raise ValueError('cannot use _null_key as a key')

        if key in self._cache:

            node = self._cache[key]

            node.run_cleanup()

            node.value = value

            node.cleanup = cleanup

        else:

            node = _LRUNode(key, value, cleanup=cleanup)

            self._cache[key] = node

        self._record_access(node)

        if len(self._cache) > self._max_cache:

            # Trigger the cleanup

            self.cleanup()

    def cache_size(self):

        """Get the number of entries we will cache."""

        return self._max_cache

    def get(self, key, default=None):

        node = self._cache.get(key, None)

        if node is None:

            return default

        self._record_access(node)

        return node.value

    def keys(self):

        """Get the list of keys currently cached.

        Note that values returned here may not be available by the time you

        request them later. This is simply meant as a peak into the current

        state.

        :return: An unordered list of keys that are currently cached.

        """

        return self._cache.keys()

    def items(self):

        """Get the key:value pairs as a dict."""

        return dict((k, n.value) for k, n in self._cache.items())

    def cleanup(self):

        """Clear the cache until it shrinks to the requested size.

        This does not completely wipe the cache, just makes sure it is under

        the after_cleanup_count.

        """

        # Make sure the cache is shrunk to the correct size

        while len(self._cache) > self._after_cleanup_count:

            self._remove_lru()

    def __setitem__(self, key, value):

        """Add a value to the cache, there will be no cleanup function."""

        self.add(key, value, cleanup=None)

    def _record_access(self, node):

        """Record that key was accessed."""

        # Move 'node' to the front of the queue

        if self._most_recently_used is None:

            self._most_recently_used = node

            self._least_recently_used = node

            return

        elif node is self._most_recently_used:

            # Nothing to do, this node is already at the head of the queue

            return

        # We've taken care of the tail pointer, remove the node, and insert it

        # at the front

        # REMOVE

        if node is self._least_recently_used:

            self._least_recently_used = node.prev

        if node.prev is not None:

            node.prev.next_key = node.next_key

        if node.next_key is not _null_key:

            node_next = self._cache[node.next_key]

            node_next.prev = node.prev

        # INSERT

        node.next_key = self._most_recently_used.key

        self._most_recently_used.prev = node

        self._most_recently_used = node

        node.prev = None

    def _remove_node(self, node):

        if node is self._least_recently_used:

            self._least_recently_used = node.prev

        self._cache.pop(node.key)

        # If we have removed all entries, remove the head pointer as well

        if self._least_recently_used is None:

            self._most_recently_used = None

        node.run_cleanup()

        # Now remove this node from the linked list

        if node.prev is not None:

            node.prev.next_key = node.next_key

        if node.next_key is not _null_key:

            node_next = self._cache[node.next_key]

            node_next.prev = node.prev

        # And remove this node's pointers

        node.prev = None

        node.next_key = _null_key

    def _remove_lru(self):

        """Remove one entry from the lru, and handle consequences.

        If there are no more references to the lru, then this entry should be

        removed from the cache.

        """

        self._remove_node(self._least_recently_used)

    def clear(self):

        """Clear out all of the cache."""

        # Clean up in LRU order

        while self._cache:

            self._remove_lru()

    def resize(self, max_cache, after_cleanup_count=None):

        """Change the number of entries that will be cached."""

        self._update_max_cache(max_cache,

                               after_cleanup_count=after_cleanup_count)

    def _update_max_cache(self, max_cache, after_cleanup_count=None):

        self._max_cache = max_cache

        if after_cleanup_count is None:

            self._after_cleanup_count = self._max_cache * 8 / 10

        else:

            self._after_cleanup_count = min(after_cleanup_count,

                                            self._max_cache)

        self.cleanup()

class LRUSizeCache(LRUCache):

    """An LRUCache that removes things based on the size of the values.

    This differs in that it doesn't care how many actual items there are,

    it just restricts the cache to be cleaned up after so much data is stored.

    The size of items added will be computed using compute_size(value), which

    defaults to len() if not supplied.

    """

    def __init__(self, max_size=1024*1024, after_cleanup_size=None,

                 compute_size=None):

        """Create a new LRUSizeCache.

        :param max_size: The max number of bytes to store before we start

            clearing out entries.

        :param after_cleanup_size: After cleaning up, shrink everything to this

            size.

        :param compute_size: A function to compute the size of the values. We

            use a function here, so that you can pass 'len' if you are just

            using simple strings, or a more complex function if you are using

            something like a list of strings, or even a custom object.

            The function should take the form "compute_size(value) => integer".

            If not supplied, it defaults to 'len()'

        """

        self._value_size = 0

        self._compute_size = compute_size

        if compute_size is None:

            self._compute_size = len

        self._update_max_size(max_size, after_cleanup_size=after_cleanup_size)

        LRUCache.__init__(self, max_cache=max(int(max_size/512), 1))

    def add(self, key, value, cleanup=None):

        """Add a new value to the cache.

        Also, if the entry is ever removed from the cache, call

        cleanup(key, value).

        :param key: The key to store it under

        :param value: The object to store

        :param cleanup: None or a function taking (key, value) to indicate

                        'value' should be cleaned up.

        """

        if key is _null_key:

            raise ValueError('cannot use _null_key as a key')

        node = self._cache.get(key, None)

        value_len = self._compute_size(value)

        if value_len >= self._after_cleanup_size:

            # The new value is 'too big to fit', as it would fill up/overflow

            # the cache all by itself

            if node is not None:

                # We won't be replacing the old node, so just remove it

                self._remove_node(node)

            if cleanup is not None:

                cleanup(key, value)

            return

        if node is None:

            node = _LRUNode(key, value, cleanup=cleanup)

            self._cache[key] = node

        else:

            self._value_size -= node.size

        node.size = value_len

        self._value_size += value_len

        self._record_access(node)

        if self._value_size > self._max_size:

            # Time to cleanup

            self.cleanup()

    def cleanup(self):

        """Clear the cache until it shrinks to the requested size.

        This does not completely wipe the cache, just makes sure it is under

        the after_cleanup_size.

        """

        # Make sure the cache is shrunk to the correct size

        while self._value_size > self._after_cleanup_size:

            self._remove_lru()

    def _remove_node(self, node):

        self._value_size -= node.size

        LRUCache._remove_node(self, node)

    def resize(self, max_size, after_cleanup_size=None):

        """Change the number of bytes that will be cached."""

        self._update_max_size(max_size, after_cleanup_size=after_cleanup_size)

        max_cache = max(int(max_size/512), 1)

        self._update_max_cache(max_cache)

    def _update_max_size(self, max_size, after_cleanup_size=None):

        self._max_size = max_size

        if after_cleanup_size is None:

            self._after_cleanup_size = self._max_size * 8 // 10

        else:

            self._after_cleanup_size = min(after_cleanup_size, self._max_size)

# 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

# <http://www.gnu.org/licenses/> for a copy of the GNU General Public License

# and <http://www.apache.org/licenses/LICENSE-2.0> 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

        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

        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):

    if entry.mode is None or stat.S_ISDIR(entry.mode):

        return _NULL_ENTRY

    return entry

def tree_changes(store, tree1_id, tree2_id, want_unchanged=False,

                 rename_detector=None):

    """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

        as well.

    :param rename_detector: RenameDetector object for detecting renames.

    :return: Iterator over TreeChange instances for each change between the

        source and target tree.

    """

    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)

        entry2 = _skip_tree(entry2)

        if entry1 != _NULL_ENTRY and entry2 != _NULL_ENTRY:

            if stat.S_IFMT(entry1.mode) != stat.S_IFMT(entry2.mode):

                # 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.

    :return: 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.

        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

    old_sha = lambda c: c.old.sha

    change_type = lambda c: 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.

    """

    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.

    """

    # 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

        results between calls.

    :return: 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

            an add/delete pair to be a rename/copy; see _similarity_score.

        :param 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

            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

            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

# objects.py -- Access to base git objects

# Copyright (C) 2007 James Westby <jw+debian@jameswestby.net>

# Copyright (C) 2008-2013 Jelmer Vernooij <jelmer@samba.org>

#

# 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

# <http://www.gnu.org/licenses/> for a copy of the GNU General Public License

# and <http://www.apache.org/licenses/LICENSE-2.0> for a copy of the Apache

# License, Version 2.0.

#

"""Access to base git objects."""

import binascii

from io import BytesIO

from collections import namedtuple

import os

import posixpath

import stat

import warnings

import zlib

from hashlib import sha1

from dulwich.errors import (

    ChecksumMismatch,

    NotBlobError,

    NotCommitError,

    NotTagError,

    NotTreeError,

    ObjectFormatException,

    )

from dulwich.file import GitFile

ZERO_SHA = b'0' * 40

# Header fields for commits

_TREE_HEADER = b'tree'

_PARENT_HEADER = b'parent'

_AUTHOR_HEADER = b'author'

_COMMITTER_HEADER = b'committer'

_ENCODING_HEADER = b'encoding'

_MERGETAG_HEADER = b'mergetag'

_GPGSIG_HEADER = b'gpgsig'

# Header fields for objects

_OBJECT_HEADER = b'object'

_TYPE_HEADER = b'type'

_TAG_HEADER = b'tag'

_TAGGER_HEADER = b'tagger'

S_IFGITLINK = 0o160000

def S_ISGITLINK(m):

    """Check if a mode indicates a submodule.

    :param m: Mode to check

    :return: a ``boolean``

    """

    return (stat.S_IFMT(m) == S_IFGITLINK)

def _decompress(string):

    dcomp = zlib.decompressobj()

    dcomped = dcomp.decompress(string)

    dcomped += dcomp.flush()

    return dcomped

def sha_to_hex(sha):

    """Takes a string and returns the hex of the sha within"""

    hexsha = binascii.hexlify(sha)

    assert len(hexsha) == 40, "Incorrect length of sha1 string: %d" % hexsha

    return hexsha

def hex_to_sha(hex):

    """Takes a hex sha and returns a binary sha"""

    assert len(hex) == 40, "Incorrect length of hexsha: %s" % hex

    try:

        return binascii.unhexlify(hex)

    except TypeError as exc:

        if not isinstance(hex, bytes):

            raise

        raise ValueError(exc.args[0])

def valid_hexsha(hex):

    if len(hex) != 40:

        return False

    try:

        binascii.unhexlify(hex)

    except (TypeError, binascii.Error):

        return False

    else:

        return True

def hex_to_filename(path, hex):

    """Takes a hex sha and returns its filename relative to the given path."""

    # os.path.join accepts bytes or unicode, but all args must be of the same

    # type. Make sure that hex which is expected to be bytes, is the same type

    # as path.

    if getattr(path, 'encode', None) is not None:

        hex = hex.decode('ascii')

    dir = hex[:2]

    file = hex[2:]

    # Check from object dir

    return os.path.join(path, dir, file)

def filename_to_hex(filename):

    """Takes an object filename and returns its corresponding hex sha."""

    # grab the last (up to) two path components

    names = filename.rsplit(os.path.sep, 2)[-2:]

    errmsg = "Invalid object filename: %s" % filename

    assert len(names) == 2, errmsg

    base, rest = names

    assert len(base) == 2 and len(rest) == 38, errmsg

    hex = (base + rest).encode('ascii')

    hex_to_sha(hex)

    return hex

def object_header(num_type, length):

    """Return an object header for the given numeric type and text length."""

    return object_class(num_type).type_name + b' ' + str(length).encode('ascii') + b'\0'

def serializable_property(name, docstring=None):

    """A property that helps tracking whether serialization is necessary.

    """

    def set(obj, value):

        setattr(obj, "_"+name, value)

        obj._needs_serialization = True

    def get(obj):

        return getattr(obj, "_"+name)

    return property(get, set, doc=docstring)

def object_class(type):

    """Get the object class corresponding to the given type.

    :param type: Either a type name string or a numeric type.

    :return: The ShaFile subclass corresponding to the given type, or None if

        type is not a valid type name/number.

    """

    return _TYPE_MAP.get(type, None)

def check_hexsha(hex, error_msg):

    """Check if a string is a valid hex sha string.

    :param hex: Hex string to check

    :param error_msg: Error message to use in exception

    :raise ObjectFormatException: Raised when the string is not valid

    """

    if not valid_hexsha(hex):

        raise ObjectFormatException("%s %s" % (error_msg, hex))

def check_identity(identity, error_msg):

    """Check if the specified identity is valid.

    This will raise an exception if the identity is not valid.

    :param identity: Identity string

    :param error_msg: Error message to use in exception

    """

    email_start = identity.find(b'<')

    email_end = identity.find(b'>')

    if (email_start < 0 or email_end < 0 or email_end <= email_start

        or identity.find(b'<', email_start + 1) >= 0

        or identity.find(b'>', email_end + 1) >= 0

        or not identity.endswith(b'>')):

        raise ObjectFormatException(error_msg)

def git_line(*items):

    """Formats items into a space sepreated line."""

    return b' '.join(items) + b'\n'

class FixedSha(object):

    """SHA object that behaves like hashlib's but is given a fixed value."""

    __slots__ = ('_hexsha', '_sha')

    def __init__(self, hexsha):

        if getattr(hexsha, 'encode', None) is not None:

            hexsha = hexsha.encode('ascii')

        if not isinstance(hexsha, bytes):

            raise TypeError('Expected bytes for hexsha, got %r' % hexsha)

        self._hexsha = hexsha

        self._sha = hex_to_sha(hexsha)

    def digest(self):

        """Return the raw SHA digest."""

        return self._sha

    def hexdigest(self):

        """Return the hex SHA digest."""

        return self._hexsha.decode('ascii')

class ShaFile(object):

    """A git SHA file."""

    __slots__ = ('_chunked_text', '_sha', '_needs_serialization')

    @staticmethod

    def _parse_legacy_object_header(magic, f):

        """Parse a legacy object, creating it but not reading the file."""

        bufsize = 1024

        decomp = zlib.decompressobj()

        header = decomp.decompress(magic)

        start = 0

        end = -1

        while end < 0:

            extra = f.read(bufsize)

            header += decomp.decompress(extra)

            magic += extra

            end = header.find(b'\0', start)

            start = len(header)

        header = header[:end]

        type_name, size = header.split(b' ', 1)

        size = int(size)  # sanity check

        obj_class = object_class(type_name)

        if not obj_class:

            raise ObjectFormatException("Not a known type: %s" % type_name)

        return obj_class()

    def _parse_legacy_object(self, map):

        """Parse a legacy object, setting the raw string."""

        text = _decompress(map)

        header_end = text.find(b'\0')

        if header_end < 0:

            raise ObjectFormatException("Invalid object header, no \\0")

        self.set_raw_string(text[header_end+1:])

    def as_legacy_object_chunks(self):

        """Return chunks representing the object in the experimental format.

        :return: List of strings

        """

        compobj = zlib.compressobj()

        yield compobj.compress(self._header())

        for chunk in self.as_raw_chunks():

            yield compobj.compress(chunk)

        yield compobj.flush()

    def as_legacy_object(self):

        """Return string representing the object in the experimental format.

        """

        return b''.join(self.as_legacy_object_chunks())

    def as_raw_chunks(self):

        """Return chunks with serialization of the object.

        :return: List of strings, not necessarily one per line

        """

        if self._needs_serialization:

            self._sha = None

            self._chunked_text = self._serialize()

            self._needs_serialization = False

        return self._chunked_text

    def as_raw_string(self):

        """Return raw string with serialization of the object.

        :return: String object

        """

        return b''.join(self.as_raw_chunks())

    def __str__(self):

        """Return raw string serialization of this object."""

        return self.as_raw_string()

    def __hash__(self):

        """Return unique hash for this object."""

        return hash(self.id)

    def as_pretty_string(self):

        """Return a string representing this object, fit for display."""

        return self.as_raw_string()

    def set_raw_string(self, text, sha=None):

        """Set the contents of this object from a serialized string."""

        if not isinstance(text, bytes):

            raise TypeError('Expected bytes for text, got %r' % text)

        self.set_raw_chunks([text], sha)

    def set_raw_chunks(self, chunks, sha=None):

        """Set the contents of this object from a list of chunks."""

        self._chunked_text = chunks

        self._deserialize(chunks)

        if sha is None:

            self._sha = None

        else:

            self._sha = FixedSha(sha)

        self._needs_serialization = False

    @staticmethod

    def _parse_object_header(magic, f):

        """Parse a new style object, creating it but not reading the file."""

        num_type = (ord(magic[0:1]) >> 4) & 7

        obj_class = object_class(num_type)

        if not obj_class:

            raise ObjectFormatException("Not a known type %d" % num_type)

        return obj_class()

    def _parse_object(self, map):

        """Parse a new style object, setting self._text."""

        # skip type and size; type must have already been determined, and

        # we trust zlib to fail if it's otherwise corrupted

        byte = ord(map[0:1])

        used = 1

        while (byte & 0x80) != 0:

            byte = ord(map[used:used+1])

            used += 1

        raw = map[used:]

        self.set_raw_string(_decompress(raw))

    @classmethod

    def _is_legacy_object(cls, magic):

        b0 = ord(magic[0:1])

        b1 = ord(magic[1:2])

        word = (b0 << 8) + b1

        return (b0 & 0x8F) == 0x08 and (word % 31) == 0

    @classmethod

    def _parse_file(cls, f):

        map = f.read()

        if cls._is_legacy_object(map):

            obj = cls._parse_legacy_object_header(map, f)

            obj._parse_legacy_object(map)

        else:

            obj = cls._parse_object_header(map, f)

            obj._parse_object(map)

        return obj

    def __init__(self):

        """Don't call this directly"""

        self._sha = None

        self._chunked_text = []

        self._needs_serialization = True

    def _deserialize(self, chunks):

        raise NotImplementedError(self._deserialize)

    def _serialize(self):

        raise NotImplementedError(self._serialize)

    @classmethod

    def from_path(cls, path):

        """Open a SHA file from disk."""

        with GitFile(path, 'rb') as f:

            return cls.from_file(f)

    @classmethod

    def from_file(cls, f):

        """Get the contents of a SHA file on disk."""

        try:

            obj = cls._parse_file(f)

            obj._sha = None

            return obj

        except (IndexError, ValueError):

            raise ObjectFormatException("invalid object header")

    @staticmethod

    def from_raw_string(type_num, string, sha=None):

        """Creates an object of the indicated type from the raw string given.

        :param type_num: The numeric type of the object.

        :param string: The raw uncompressed contents.

        :param sha: Optional known sha for the object

        """

        obj = object_class(type_num)()

        obj.set_raw_string(string, sha)

        return obj

    @staticmethod

    def from_raw_chunks(type_num, chunks, sha=None):

        """Creates an object of the indicated type from the raw chunks given.

        :param type_num: The numeric type of the object.

        :param chunks: An iterable of the raw uncompressed contents.

        :param sha: Optional known sha for the object

        """

        obj = object_class(type_num)()

        obj.set_raw_chunks(chunks, sha)

        return obj

    @classmethod

    def from_string(cls, string):

        """Create a ShaFile from a string."""

        obj = cls()

        obj.set_raw_string(string)

        return obj

    def _check_has_member(self, member, error_msg):

        """Check that the object has a given member variable.

        :param member: the member variable to check for

        :param error_msg: the message for an error if the member is missing

        :raise ObjectFormatException: with the given error_msg if member is

            missing or is None

        """

        if getattr(self, member, None) is None:

            raise ObjectFormatException(error_msg)

    def check(self):

        """Check this object for internal consistency.

        :raise ObjectFormatException: if the object is malformed in some way

        :raise ChecksumMismatch: if the object was created with a SHA that does

            not match its contents

        """

        # TODO: if we find that error-checking during object parsing is a

        # performance bottleneck, those checks should be moved to the class's

        # check() method during optimization so we can still check the object

        # when necessary.

        old_sha = self.id

        try:

            self._deserialize(self.as_raw_chunks())

            self._sha = None

            new_sha = self.id

        except Exception as e:

            raise ObjectFormatException(e)

        if old_sha != new_sha:

            raise ChecksumMismatch(new_sha, old_sha)

    def _header(self):

        return object_header(self.type, self.raw_length())

    def raw_length(self):

        """Returns the length of the raw string of this object."""

        ret = 0

        for chunk in self.as_raw_chunks():

            ret += len(chunk)

        return ret

    def sha(self):

        """The SHA1 object that is the name of this object."""

        if self._sha is None or self._needs_serialization:

            # this is a local because as_raw_chunks() overwrites self._sha

            new_sha = sha1()

            new_sha.update(self._header())

            for chunk in self.as_raw_chunks():

                new_sha.update(chunk)

            self._sha = new_sha

        return self._sha

    def copy(self):

        """Create a new copy of this SHA1 object from its raw string"""

        obj_class = object_class(self.get_type())

        return obj_class.from_raw_string(

            self.get_type(),

            self.as_raw_string(),

            self.id)

    @property

    def id(self):

        """The hex SHA of this object."""

        return self.sha().hexdigest().encode('ascii')

    def get_type(self):

        """Return the type number for this object class."""

        return self.type_num

    def set_type(self, type):

        """Set the type number for this object class."""

        self.type_num = type

    # DEPRECATED: use type_num or type_name as needed.

    type = property(get_type, set_type)

    def __repr__(self):

        return "<%s %s>" % (self.__class__.__name__, self.id)

    def __ne__(self, other):

        return not isinstance(other, ShaFile) or self.id != other.id

    def __eq__(self, other):

        """Return True if the SHAs of the two objects match.

        It doesn't make sense to talk about an order on ShaFiles, so we don't

        override the rich comparison methods (__le__, etc.).

        """

        return isinstance(other, ShaFile) and self.id == other.id

    def __lt__(self, other):

        if not isinstance(other, ShaFile):

            raise TypeError

        return self.id < other.id

    def __le__(self, other):

        if not isinstance(other, ShaFile):