kallithea Changeset - 2c224062eba7

Changeset - 2c224062eba7

Parent rev.

Child rev.

[Not reviewed]

default

0 2 0

Mads Kiilerich - 6 years ago 2019-12-25 15:30:11
mads@kiilerich.com

Grafted from: e359f51a3bdc

vcs: fix get_file_annotate - consistently bind sha so it has the right value when executing

The Git implementation did *not* save the sha value in the lambda expression
for the "changeset lazy loader". Thus, if the generator had moved on and
assigned a different value to sha when the expression was executed, it would
use the "wrong" sha.

Fixed by doing as the Hg implementation: bind the sha value as value of a
default parameter when defining the lambda expression.

The Hg implementation did however also save the line - it is not used, and
there is no need for that.

2 files changed with 6 insertions and 8 deletions:

kallithea/lib/vcs/backends/git/changeset.py

kallithea/lib/vcs/backends/hg/changeset.py

0 comments (0 inline, 0 general)

kallithea/lib/vcs/backends/git/changeset.py

➞

Show inline comments

@@ @@ -228,207 +228,205 @@ class GitChangeset(BaseChangeset): @@
         cs = self
         while True:
             try:
                 prev_ = cs.revision - 1
                 if prev_ < 0:
                     raise IndexError
                 prev_rev = cs.repository.revisions[prev_]
             except IndexError:
                 raise ChangesetDoesNotExistError
             cs = cs.repository.get_changeset(prev_rev)
             if not branch or branch == cs.branch:
                 return cs
     def diff(self, ignore_whitespace=True, context=3):
         # Only used to feed diffstat
         rev1 = self.parents[0] if self.parents else self.repository.EMPTY_CHANGESET
         rev2 = self
         return b''.join(self.repository.get_diff(rev1, rev2,
                                     ignore_whitespace=ignore_whitespace,
                                     context=context))
     def get_file_mode(self, path):
         """
         Returns stat mode of the file at the given ``path``.
         """
         # ensure path is traversed
         path = safe_str(path)
         self._get_id_for_path(path)
         return self._stat_modes[path]
     def get_file_content(self, path):
         """
         Returns content of the file at given ``path``.
         """
         id = self._get_id_for_path(path)
         blob = self.repository._repo[id]
         return blob.as_pretty_string()
     def get_file_size(self, path):
         """
         Returns size of the file at given ``path``.
         """
         id = self._get_id_for_path(path)
         blob = self.repository._repo[id]
         return blob.raw_length()
     def get_file_changeset(self, path):
         """
         Returns last commit of the file at the given ``path``.
         """
         return self.get_file_history(path, limit=1)[0]
     def get_file_history(self, path, limit=None):
         """
         Returns history of file as reversed list of ``Changeset`` objects for
         which file at given ``path`` has been modified.
         TODO: This function now uses os underlying 'git' and 'grep' commands
         which is generally not good. Should be replaced with algorithm
         iterating commits.
         """
         self._get_filectx(path)
         cs_id = safe_str(self.id)
         f_path = safe_str(path)
         if limit is not None:
             cmd = ['log', '-n', str(safe_int(limit, 0)),
                    '--pretty=format:%H', '-s', cs_id, '--', f_path]
         else:
             cmd = ['log',
                    '--pretty=format:%H', '-s', cs_id, '--', f_path]
         so = self.repository.run_git_command(cmd)
         ids = re.findall(r'[0-9a-fA-F]{40}', so)
         return [self.repository.get_changeset(sha) for sha in ids]
     def get_file_history_2(self, path):
         """
         Returns history of file as reversed list of ``Changeset`` objects for
         which file at given ``path`` has been modified.
         """
         self._get_filectx(path)
         from dulwich.walk import Walker
         include = [self.id]
         walker = Walker(self.repository._repo.object_store, include,
                         paths=[path], max_entries=1)
         return [self.repository.get_changeset(ascii_str(x.commit.id.decode))
                 for x in walker]
     def get_file_annotate(self, path):
         """
         Returns a generator of four element tuples with
             lineno, sha, changeset lazy loader and line
         TODO: This function now uses os underlying 'git' command which is
         generally not good. Should be replaced with algorithm iterating
         commits.
         """
         # TODO: This function now uses os underlying 'git' command which is
         # generally not good. Should be replaced with algorithm iterating
         # commits.
         cmd = ['blame', '-l', '--root', '-r', self.id, '--', path]
         # -l     ==> outputs long shas (and we need all 40 characters)
         # --root ==> doesn't put '^' character for boundaries
         # -r sha ==> blames for the given revision
         so = self.repository.run_git_command(cmd)
         for i, blame_line in enumerate(so.split('\n')[:-1]):
             ln_no = i + 1
             sha, line = re.split(r' ', blame_line, 1)
-            yield (ln_no, sha, lambda: self.repository.get_changeset(sha), line)
+            yield (i + 1, sha, lambda sha=sha: self.repository.get_changeset(sha), line)
     def fill_archive(self, stream=None, kind='tgz', prefix=None,
                      subrepos=False):
         """
         Fills up given stream.
         :param stream: file like object.
         :param kind: one of following: ``zip``, ``tgz`` or ``tbz2``.
             Default: ``tgz``.
         :param prefix: name of root directory in archive.
             Default is repository name and changeset's raw_id joined with dash
             (``repo-tip.<KIND>``).
         :param subrepos: include subrepos in this archive.
         :raise ImproperArchiveTypeError: If given kind is wrong.
         :raise VcsError: If given stream is None
         """
         allowed_kinds = settings.ARCHIVE_SPECS
         if kind not in allowed_kinds:
             raise ImproperArchiveTypeError('Archive kind not supported use one'
                 'of %s' % ' '.join(allowed_kinds))
         if stream is None:
             raise VCSError('You need to pass in a valid stream for filling'
                            ' with archival data')
         if prefix is None:
             prefix = '%s-%s' % (self.repository.name, self.short_id)
         elif prefix.startswith('/'):
             raise VCSError("Prefix cannot start with leading slash")
         elif prefix.strip() == '':
             raise VCSError("Prefix cannot be empty")
         if kind == 'zip':
             frmt = 'zip'
         else:
             frmt = 'tar'
         _git_path = settings.GIT_EXECUTABLE_PATH
         cmd = '%s archive --format=%s --prefix=%s/ %s' % (_git_path,
                                                 frmt, prefix, self.raw_id)
         if kind == 'tgz':
             cmd += ' | gzip -9'
         elif kind == 'tbz2':
             cmd += ' | bzip2 -9'
         if stream is None:
             raise VCSError('You need to pass in a valid stream for filling'
                            ' with archival data')
         popen = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True,
                       cwd=self.repository.path)
         buffer_size = 1024 * 8
         chunk = popen.stdout.read(buffer_size)
         while chunk:
             stream.write(chunk)
             chunk = popen.stdout.read(buffer_size)
         # Make sure all descriptors would be read
         popen.communicate()
     def get_nodes(self, path):
         """
         Returns combined ``DirNode`` and ``FileNode`` objects list representing
         state of changeset at the given ``path``. If node at the given ``path``
         is not instance of ``DirNode``, ChangesetError would be raised.
         """
         if self._get_kind(path) != NodeKind.DIR:
             raise ChangesetError("Directory does not exist for revision %s at "
                 " '%s'" % (self.revision, path))
         path = self._fix_path(path)
         id = self._get_id_for_path(path)
         tree = self.repository._repo[id]
         dirnodes = []
         filenodes = []
         als = self.repository.alias
         for name, stat, id in tree.iteritems():
             if path != '':
                 obj_path = '/'.join((path, name))
             else:
                 obj_path = name
             if objects.S_ISGITLINK(stat):
                 root_tree = self.repository._repo[self._tree_id]
                 cf = ConfigFile.from_file(BytesIO(self.repository._repo.get_object(root_tree[b'.gitmodules'][1]).data))
                 url = ascii_str(cf.get(('submodule', obj_path), 'url'))
                 dirnodes.append(SubModuleNode(obj_path, url=url, changeset=ascii_str(id),
                                               alias=als))
                 continue
             obj = self.repository._repo.get_object(id)
             if obj_path not in self._stat_modes:
                 self._stat_modes[obj_path] = stat
             if isinstance(obj, objects.Tree):
                 dirnodes.append(DirNode(obj_path, changeset=self))
             elif isinstance(obj, objects.Blob):
                 filenodes.append(FileNode(obj_path, changeset=self, mode=stat))
             else:

kallithea/lib/vcs/backends/hg/changeset.py

➞

Show inline comments

@@ @@ -194,195 +194,195 @@ class MercurialChangeset(BaseChangeset): @@
             if not branch or branch == cs.branch:
                 return cs
     def diff(self):
         # Only used to feed diffstat
         return b''.join(self._ctx.diff())
     def _fix_path(self, path):
         """
         Paths are stored without trailing slash so we need to get rid off it if
         needed. Also mercurial keeps filenodes as str so we need to decode
         from unicode to str
         """
         if path.endswith('/'):
             path = path.rstrip('/')
         return safe_str(path)
     def _get_kind(self, path):
         path = self._fix_path(path)
         if path in self._file_paths:
             return NodeKind.FILE
         elif path in self._dir_paths:
             return NodeKind.DIR
         else:
             raise ChangesetError("Node does not exist at the given path '%s'"
                 % (path))
     def _get_filectx(self, path):
         path = self._fix_path(path)
         if self._get_kind(path) != NodeKind.FILE:
             raise ChangesetError("File does not exist for revision %s at "
                 " '%s'" % (self.raw_id, path))
         return self._ctx.filectx(path)
     def _extract_submodules(self):
         """
         returns a dictionary with submodule information from substate file
         of hg repository
         """
         return self._ctx.substate
     def get_file_mode(self, path):
         """
         Returns stat mode of the file at the given ``path``.
         """
         fctx = self._get_filectx(path)
         if b'x' in fctx.flags():
             return 0o100755
         else:
             return 0o100644
     def get_file_content(self, path):
         """
         Returns content of the file at given ``path``.
         """
         fctx = self._get_filectx(path)
         return fctx.data()
     def get_file_size(self, path):
         """
         Returns size of the file at given ``path``.
         """
         fctx = self._get_filectx(path)
         return fctx.size()
     def get_file_changeset(self, path):
         """
         Returns last commit of the file at the given ``path``.
         """
         return self.get_file_history(path, limit=1)[0]
     def get_file_history(self, path, limit=None):
         """
         Returns history of file as reversed list of ``Changeset`` objects for
         which file at given ``path`` has been modified.
         """
         fctx = self._get_filectx(path)
         hist = []
         cnt = 0
         for cs in reversed([x for x in fctx.filelog()]):
             cnt += 1
             hist.append(mercurial.node.hex(fctx.filectx(cs).node()))
             if limit is not None and cnt == limit:
                 break
         return [self.repository.get_changeset(node) for node in hist]
     def get_file_annotate(self, path):
         """
         Returns a generator of four element tuples with
             lineno, sha, changeset lazy loader and line
         """
         annotations = self._get_filectx(path).annotate()
         annotation_lines = [(annotateline.fctx, annotateline.text) for annotateline in annotations]
-        for i, (fctx, l) in enumerate(annotation_lines):
+        for i, (fctx, line) in enumerate(annotation_lines):
             sha = ascii_str(fctx.hex())
-            yield (i + 1, sha, lambda sha=sha, l=l: self.repository.get_changeset(sha), l)
+            yield (i + 1, sha, lambda sha=sha: self.repository.get_changeset(sha), line)
     def fill_archive(self, stream=None, kind='tgz', prefix=None,
                      subrepos=False):
         """
         Fills up given stream.
         :param stream: file like object.
         :param kind: one of following: ``zip``, ``tgz`` or ``tbz2``.
             Default: ``tgz``.
         :param prefix: name of root directory in archive.
             Default is repository name and changeset's raw_id joined with dash
             (``repo-tip.<KIND>``).
         :param subrepos: include subrepos in this archive.
         :raise ImproperArchiveTypeError: If given kind is wrong.
         :raise VcsError: If given stream is None
         """
         allowed_kinds = settings.ARCHIVE_SPECS
         if kind not in allowed_kinds:
             raise ImproperArchiveTypeError('Archive kind not supported use one'
                 'of %s' % ' '.join(allowed_kinds))
         if stream is None:
             raise VCSError('You need to pass in a valid stream for filling'
                            ' with archival data')
         if prefix is None:
             prefix = '%s-%s' % (self.repository.name, self.short_id)
         elif prefix.startswith('/'):
             raise VCSError("Prefix cannot start with leading slash")
         elif prefix.strip() == '':
             raise VCSError("Prefix cannot be empty")
         mercurial.archival.archive(self.repository._repo, stream, ascii_bytes(self.raw_id),
                          kind, prefix=prefix, subrepos=subrepos)
     def get_nodes(self, path):
         """
         Returns combined ``DirNode`` and ``FileNode`` objects list representing
         state of changeset at the given ``path``. If node at the given ``path``
         is not instance of ``DirNode``, ChangesetError would be raised.
         """
         if self._get_kind(path) != NodeKind.DIR:
             raise ChangesetError("Directory does not exist for revision %s at "
                 " '%s'" % (self.revision, path))
         path = self._fix_path(path)
         filenodes = [FileNode(f, changeset=self) for f in self._file_paths
             if os.path.dirname(f) == path]
         dirs = path == '' and '' or [d for d in self._dir_paths
             if d and posixpath.dirname(d) == path]
         dirnodes = [DirNode(d, changeset=self) for d in dirs
             if os.path.dirname(d) == path]
         als = self.repository.alias
         for k, vals in self._extract_submodules().iteritems():
             #vals = url,rev,type
             loc = vals[0]
             cs = vals[1]
             dirnodes.append(SubModuleNode(k, url=loc, changeset=cs,
                                           alias=als))
         nodes = dirnodes + filenodes
         for node in nodes:
             self.nodes[node.path] = node
         nodes.sort()
         return nodes
     def get_node(self, path):
         """
         Returns ``Node`` object from the given ``path``. If there is no node at
         the given ``path``, ``ChangesetError`` would be raised.
         """
         path = self._fix_path(path)
         if path not in self.nodes:
             if path in self._file_paths:
                 node = FileNode(path, changeset=self)
             elif path in self._dir_paths or path in self._dir_paths:
                 if path == '':
                     node = RootNode(changeset=self)
                 else:
                     node = DirNode(path, changeset=self)
             else:
                 raise NodeDoesNotExistError("There is no file nor directory "
                     "at the given path: '%s' at revision %s"
                     % (path, self.short_id))
             # cache node
             self.nodes[path] = node
         return self.nodes[path]
     @LazyProperty
     def affected_files(self):
         """
         Gets a fast accessible file changes for given changeset
         """
         return self._ctx.files()

0 comments (0 inline, 0 general)