kallithea Changeset - 184159c21be2

Changeset - 184159c21be2

Parent rev.

Child rev.

[Not reviewed]

default

0 2 0

Mads Kiilerich - 11 years ago 2014-08-01 20:28:42
madski@unity3d.com

vcs: replace recursive implementation of prev&next with iterative

It was recursing over the repo and could give "maximum recursion depth
exceeded".

The implementation is still inefficient.

2 files changed with 28 insertions and 44 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

@@ @@ -108,234 +108,226 @@ class GitChangeset(BaseChangeset): @@
         # FIXME: Please, spare a couple of minutes and make those codes cleaner;
         if not path in self._paths:
             path = path.strip('/')
             # set root tree
             tree = self.repository._repo[self._tree_id]
             if path == '':
                 self._paths[''] = tree.id
                 return tree.id
             splitted = path.split('/')
             dirs, name = splitted[:-1], splitted[-1]
             curdir = ''
             # initially extract things from root dir
             for item, stat, id in tree.iteritems():
                 if curdir:
                     name = '/'.join((curdir, item))
                 else:
                     name = item
                 self._paths[name] = id
                 self._stat_modes[name] = stat
             for dir in dirs:
                 if curdir:
                     curdir = '/'.join((curdir, dir))
                 else:
                     curdir = dir
                 dir_id = None
                 for item, stat, id in tree.iteritems():
                     if dir == item:
                         dir_id = id
                 if dir_id:
                     # Update tree
                     tree = self.repository._repo[dir_id]
                     if not isinstance(tree, objects.Tree):
                         raise ChangesetError('%s is not a directory' % curdir)
                 else:
                     raise ChangesetError('%s have not been found' % curdir)
                 # cache all items from the given traversed tree
                 for item, stat, id in tree.iteritems():
                     if curdir:
                         name = '/'.join((curdir, item))
                     else:
                         name = item
                     self._paths[name] = id
                     self._stat_modes[name] = stat
             if not path in self._paths:
                 raise NodeDoesNotExistError("There is no file nor directory "
                     "at the given path '%s' at revision %s"
                     % (path, safe_str(self.short_id)))
         return self._paths[path]
     def _get_kind(self, path):
         obj = self.repository._repo[self._get_id_for_path(path)]
         if isinstance(obj, objects.Blob):
             return NodeKind.FILE
         elif isinstance(obj, objects.Tree):
             return NodeKind.DIR
     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 path
     def _get_file_nodes(self):
         return chain(*(t[2] for t in self.walk()))
     @LazyProperty
     def parents(self):
         """
         Returns list of parents changesets.
         """
         return [self.repository.get_changeset(parent)
                 for parent in self._commit.parents]
     @LazyProperty
     def children(self):
         """
         Returns list of children changesets.
         """
         rev_filter = _git_path = settings.GIT_REV_FILTER
         so, se = self.repository.run_git_command(
             "rev-list %s --children" % (rev_filter)
+        )
         children = []
         pat = re.compile(r'^%s' % self.raw_id)
         for l in so.splitlines():
             if pat.match(l):
                 childs = l.split(' ')[1:]
                 children.extend(childs)
         return [self.repository.get_changeset(cs) for cs in children]
     def next(self, branch=None):
         if branch and self.branch != branch:
             raise VCSError('Branch option used on changeset not belonging '
                            'to that branch')
         def _next(changeset, branch):
         cs = self
         while True:
             try:
                 next_ = changeset.revision + 1
                 next_rev = changeset.repository.revisions[next_]
                 next_ = cs.revision + 1
                 next_rev = cs.repository.revisions[next_]
             except IndexError:
                 raise ChangesetDoesNotExistError
-            cs = changeset.repository.get_changeset(next_rev)
+            cs = cs.repository.get_changeset(next_rev)
             if branch and branch != cs.branch:
                 return _next(cs, branch)
             return cs
         return _next(self, branch)
             if not branch or branch == cs.branch:
                 return cs
     def prev(self, branch=None):
         if branch and self.branch != branch:
             raise VCSError('Branch option used on changeset not belonging '
                            'to that branch')
         def _prev(changeset, branch):
         cs = self
         while True:
             try:
-                prev_ = changeset.revision - 1
+                prev_ = cs.revision - 1
                 if prev_ < 0:
                     raise IndexError
-                prev_rev = changeset.repository.revisions[prev_]
+                prev_rev = cs.repository.revisions[prev_]
             except IndexError:
                 raise ChangesetDoesNotExistError
             cs = changeset.repository.get_changeset(prev_rev)
             cs = cs.repository.get_changeset(prev_rev)
             if branch and branch != cs.branch:
                 return _prev(cs, branch)
             return cs
         return _prev(self, branch)
             if not branch or branch == cs.branch:
                 return cs
     def diff(self, ignore_whitespace=True, context=3):
         rev1 = self.parents[0] if self.parents else self.repository.EMPTY_CHANGESET
         rev2 = self
         return ''.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:
             cmd = 'log -n %s --pretty="format: %%H" -s %s -- "%s"' % (
                       safe_int(limit, 0), cs_id, f_path)
         else:
             cmd = 'log --pretty="format: %%H" -s %s -- "%s"' % (
                       cs_id, f_path)
         so, se = 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(sha)
                 for sha in (x.commit.id 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.
         """
         cmd = 'blame -l --root -r %s -- "%s"' % (self.id, path)
         # -l     ==> outputs long shas (and we need all 40 characters)
         # --root ==> doesn't put '^' character for bounderies
         # -r sha ==> blames for the given revision
         so, se = 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)

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

➞

Show inline comments

@@ @@ -22,234 +22,226 @@ class MercurialChangeset(BaseChangeset): @@
     Represents state of the repository at the single revision.
     """
     def __init__(self, repository, revision):
         self.repository = repository
         assert isinstance(revision, basestring), repr(revision)
         self.raw_id = revision
         self._ctx = repository._repo[revision]
         self.revision = self._ctx._rev
         self.nodes = {}
     @LazyProperty
     def tags(self):
         return map(safe_unicode, self._ctx.tags())
     @LazyProperty
     def branch(self):
         return  safe_unicode(self._ctx.branch())
     @LazyProperty
     def closesbranch(self):
         return  self._ctx.closesbranch()
     @LazyProperty
     def bookmarks(self):
         return map(safe_unicode, self._ctx.bookmarks())
     @LazyProperty
     def message(self):
         return safe_unicode(self._ctx.description())
     @LazyProperty
     def committer(self):
         return safe_unicode(self.author)
     @LazyProperty
     def author(self):
         return safe_unicode(self._ctx.user())
     @LazyProperty
     def date(self):
         return date_fromtimestamp(*self._ctx.date())
     @LazyProperty
     def _timestamp(self):
         return self._ctx.date()[0]
     @LazyProperty
     def status(self):
         """
         Returns modified, added, removed, deleted files for current changeset
         """
         return self.repository._repo.status(self._ctx.p1().node(),
                                             self._ctx.node())
     @LazyProperty
     def _file_paths(self):
         return list(self._ctx)
     @LazyProperty
     def _dir_paths(self):
         p = list(set(get_dirs_for_path(*self._file_paths)))
         p.insert(0, '')
         return p
     @LazyProperty
     def _paths(self):
         return self._dir_paths + self._file_paths
     @LazyProperty
     def id(self):
         if self.last:
             return u'tip'
         return self.short_id
     @LazyProperty
     def short_id(self):
         return self.raw_id[:12]
     @LazyProperty
     def parents(self):
         """
         Returns list of parents changesets.
         """
         return [self.repository.get_changeset(parent.rev())
                 for parent in self._ctx.parents() if parent.rev() >= 0]
     @LazyProperty
     def children(self):
         """
         Returns list of children changesets.
         """
         return [self.repository.get_changeset(child.rev())
                 for child in self._ctx.children() if child.rev() >= 0]
     def next(self, branch=None):
         if branch and self.branch != branch:
             raise VCSError('Branch option used on changeset not belonging '
                            'to that branch')
         def _next(changeset, branch):
         cs = self
         while True:
             try:
                 next_ = changeset.revision + 1
                 next_rev = changeset.repository.revisions[next_]
                 next_ = cs.revision + 1
                 next_rev = cs.repository.revisions[next_]
             except IndexError:
                 raise ChangesetDoesNotExistError
-            cs = changeset.repository.get_changeset(next_rev)
+            cs = cs.repository.get_changeset(next_rev)
             if branch and branch != cs.branch:
                 return _next(cs, branch)
             return cs
         return _next(self, branch)
             if not branch or branch == cs.branch:
                 return cs
     def prev(self, branch=None):
         if branch and self.branch != branch:
             raise VCSError('Branch option used on changeset not belonging '
                            'to that branch')
         def _prev(changeset, branch):
         cs = self
         while True:
             try:
-                prev_ = changeset.revision - 1
+                prev_ = cs.revision - 1
                 if prev_ < 0:
                     raise IndexError
-                prev_rev = changeset.repository.revisions[prev_]
+                prev_rev = cs.repository.revisions[prev_]
             except IndexError:
                 raise ChangesetDoesNotExistError
             cs = changeset.repository.get_changeset(prev_rev)
             cs = cs.repository.get_changeset(prev_rev)
             if branch and branch != cs.branch:
                 return _prev(cs, branch)
             return cs
         return _prev(self, branch)
             if not branch or branch == cs.branch:
                 return cs
     def diff(self, ignore_whitespace=True, context=3):
         return ''.join(self._ctx.diff(git=True,
                                       ignore_whitespace=ignore_whitespace,
                                       context=context))
     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 'x' in fctx.flags():
             return 0100755
         else:
             return 0100644
     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(hex(fctx.filectx(cs).node()))
             if limit 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
         """
         fctx = self._get_filectx(path)
         for i, annotate_data in enumerate(fctx.annotate()):
             ln_no = i + 1

0 comments (0 inline, 0 general)