# Copyright (C) 2008, 2009 Michael Trier ([email protected]) and contributors
#
# This module is part of GitPython and is released under the
# 3-Clause BSD License: https://opensource.org/license/bsd-3-clause/
import re
from git.cmd import handle_process_output
from git.compat import defenc
from git.util import finalize_process, hex_to_bin
from .objects.blob import Blob
from .objects.util import mode_str_to_int
# typing ------------------------------------------------------------------
from typing import (
Any,
Iterator,
List,
Match,
Optional,
Tuple,
Type,
TypeVar,
Union,
TYPE_CHECKING,
cast,
)
from git.types import PathLike, Literal
if TYPE_CHECKING:
from .objects.tree import Tree
from .objects import Commit
from git.repo.base import Repo
from git.objects.base import IndexObject
from subprocess import Popen
from git import Git
Lit_change_type = Literal["A", "D", "C", "M", "R", "T", "U"]
# def is_change_type(inp: str) -> TypeGuard[Lit_change_type]:
# # return True
# return inp in ['A', 'D', 'C', 'M', 'R', 'T', 'U']
# ------------------------------------------------------------------------
__all__ = ("Diffable", "DiffIndex", "Diff", "NULL_TREE")
NULL_TREE = object()
"""Special object to compare against the empty tree in diffs."""
_octal_byte_re = re.compile(rb"\\([0-9]{3})")
def _octal_repl(matchobj: Match) -> bytes:
value = matchobj.group(1)
value = int(value, 8)
value = bytes(bytearray((value,)))
return value
def decode_path(path: bytes, has_ab_prefix: bool = True) -> Optional[bytes]:
if path == b"/dev/null":
return None
if path.startswith(b'"') and path.endswith(b'"'):
path = path[1:-1].replace(b"\\n", b"\n").replace(b"\\t", b"\t").replace(b'\\"', b'"').replace(b"\\\\", b"\\")
path = _octal_byte_re.sub(_octal_repl, path)
if has_ab_prefix:
assert path.startswith(b"a/") or path.startswith(b"b/")
path = path[2:]
return path
class Diffable:
"""Common interface for all objects that can be diffed against another object of
compatible type.
:note:
Subclasses require a repo member as it is the case for Object instances, for
practical reasons we do not derive from Object.
"""
__slots__ = ()
class Index:
"""Stand-in indicating you want to diff against the index."""
def _process_diff_args(
self, args: List[Union[str, "Diffable", Type["Diffable.Index"], object]]
) -> List[Union[str, "Diffable", Type["Diffable.Index"], object]]:
"""
:return:
Possibly altered version of the given args list.
This method is called right before git command execution.
Subclasses can use it to alter the behaviour of the superclass.
"""
return args
def diff(
self,
other: Union[Type["Index"], "Tree", "Commit", None, str, object] = Index,
paths: Union[PathLike, List[PathLike], Tuple[PathLike, ...], None] = None,
create_patch: bool = False,
**kwargs: Any,
) -> "DiffIndex":
"""Create diffs between two items being trees, trees and index or an
index and the working tree. Detects renames automatically.
:param other:
This the item to compare us with.
* If None, we will be compared to the working tree.
* If :class:`~git.index.base.Treeish`, it will be compared against the
respective tree.
* If :class:`~Diffable.Index`, it will be compared against the index.
* If :attr:`git.NULL_TREE`, it will compare against the empty tree.
* It defaults to :class:`~Diffable.Index` so that the method will not by
default fail on bare repositories.
:param paths:
This a list of paths or a single path to limit the diff to. It will only
include at least one of the given path or paths.
:param create_patch:
If True, the returned :class:`Diff` contains a detailed patch that if
applied makes the self to other. Patches are somewhat costly as blobs have
to be read and diffed.
:param kwargs:
Additional arguments passed to git-diff, such as ``R=True`` to swap both
sides of the diff.
:return: git.DiffIndex
:note:
On a bare repository, 'other' needs to be provided as
:class:`~Diffable.Index`, or as :class:`~git.objects.tree.Tree` or
:class:`~git.objects.commit.Commit`, or a git command error will occur.
"""
args: List[Union[PathLike, Diffable, Type["Diffable.Index"], object]] = []
args.append("--abbrev=40") # We need full shas.
args.append("--full-index") # Get full index paths, not only filenames.
# Remove default '-M' arg (check for renames) if user is overriding it.
if not any(x in kwargs for x in ("find_renames", "no_renames", "M")):
args.append("-M")
if create_patch:
args.append("-p")
else:
args.append("--raw")
args.append("-z")
# Ensure we never see colored output.
# Fixes: https://github.com/gitpython-developers/GitPython/issues/172
args.append("--no-color")
if paths is not None and not isinstance(paths, (tuple, list)):
paths = [paths]
if hasattr(self, "Has_Repo"):
self.repo: "Repo" = self.repo
diff_cmd = self.repo.git.diff
if other is self.Index:
args.insert(0, "--cached")
elif other is NULL_TREE:
args.insert(0, "-r") # Recursive diff-tree.
args.insert(0, "--root")
diff_cmd = self.repo.git.diff_tree
elif other is not None:
args.insert(0, "-r") # Recursive diff-tree.
args.insert(0, other)
diff_cmd = self.repo.git.diff_tree
args.insert(0, self)
# paths is list here, or None.
if paths:
args.append("--")
args.extend(paths)
# END paths handling
kwargs["as_process"] = True
proc = diff_cmd(*self._process_diff_args(args), **kwargs)
diff_method = Diff._index_from_patch_format if create_patch else Diff._index_from_raw_format
index = diff_method(self.repo, proc)
proc.wait()
return index
T_Diff = TypeVar("T_Diff", bound="Diff")
class DiffIndex(List[T_Diff]):
"""An Index for diffs, allowing a list of Diffs to be queried by the diff
properties.
The class improves the diff handling convenience.
"""
change_type = ("A", "C", "D", "R", "M", "T")
"""Change type invariant identifying possible ways a blob can have changed:
* ``A`` = Added
* ``D`` = Deleted
* ``R`` = Renamed
* ``M`` = Modified
* ``T`` = Changed in the type
"""
def iter_change_type(self, change_type: Lit_change_type) -> Iterator[T_Diff]:
"""
:return:
Iterator yielding :class:`Diff` instances that match the given `change_type`
:param change_type:
Member of :attr:`DiffIndex.change_type`, namely:
* 'A' for added paths
* 'D' for deleted paths
* 'R' for renamed paths
* 'M' for paths with modified data
* 'T' for changed in the type paths
"""
if change_type not in self.change_type:
raise ValueError("Invalid change type: %s" % change_type)
for diffidx in self:
if diffidx.change_type == change_type:
yield diffidx
elif change_type == "A" and diffidx.new_file:
yield diffidx
elif change_type == "D" and diffidx.deleted_file:
yield diffidx
elif change_type == "C" and diffidx.copied_file:
yield diffidx
elif change_type == "R" and diffidx.renamed:
yield diffidx
elif change_type == "M" and diffidx.a_blob and diffidx.b_blob and diffidx.a_blob != diffidx.b_blob:
yield diffidx
# END for each diff
class Diff:
"""A Diff contains diff information between two Trees.
It contains two sides a and b of the diff, members are prefixed with
"a" and "b" respectively to indicate that.
Diffs keep information about the changed blob objects, the file mode, renames,
deletions and new files.
There are a few cases where None has to be expected as member variable value:
``New File``::
a_mode is None
a_blob is None
a_path is None
``Deleted File``::
b_mode is None
b_blob is None
b_path is None
``Working Tree Blobs``
When comparing to working trees, the working tree blob will have a null hexsha
as a corresponding object does not yet exist. The mode will be null as well.
The path will be available, though.
If it is listed in a diff, the working tree version of the file must
differ from the version in the index or tree, and hence has been modified.
"""
# Precompiled regex.
re_header = re.compile(
rb"""
^diff[ ]--git
[ ](?P