Added diff option into git and hg changeset objects, representing git formated patch against parent1

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

@@ -1,454 +1,459 b''
 import re
 from itertools import chain
 from dulwich import objects
 from subprocess import Popen, PIPE
 from rhodecode.lib.vcs.conf import settings
 from rhodecode.lib.vcs.exceptions import RepositoryError
 from rhodecode.lib.vcs.exceptions import ChangesetError
 from rhodecode.lib.vcs.exceptions import NodeDoesNotExistError
 from rhodecode.lib.vcs.exceptions import VCSError
 from rhodecode.lib.vcs.exceptions import ChangesetDoesNotExistError
 from rhodecode.lib.vcs.exceptions import ImproperArchiveTypeError
 from rhodecode.lib.vcs.backends.base import BaseChangeset
 from rhodecode.lib.vcs.nodes import FileNode, DirNode, NodeKind, RootNode, \
     RemovedFileNode, SubModuleNode
 from rhodecode.lib.vcs.utils import safe_unicode
 from rhodecode.lib.vcs.utils import date_fromtimestamp
 from rhodecode.lib.vcs.utils.lazy import LazyProperty
 
 
 class GitChangeset(BaseChangeset):
     """
     Represents state of the repository at single revision.
     """
 
     def __init__(self, repository, revision):
         self._stat_modes = {}
         self.repository = repository
         self.raw_id = revision
         self.revision = repository.revisions.index(revision)
 
         self.short_id = self.raw_id[:12]
         self.id = self.raw_id
         try:
             commit = self.repository._repo.get_object(self.raw_id)
         except KeyError:
             raise RepositoryError("Cannot get object with id %s" % self.raw_id)
         self._commit = commit
         self._tree_id = commit.tree
 
         self.message = safe_unicode(commit.message)
         #self.branch = None
         self.tags = []
         self.nodes = {}
         self._paths = {}
 
     @LazyProperty
     def author(self):
         return safe_unicode(self._commit.committer)
 
     @LazyProperty
     def date(self):
         return date_fromtimestamp(self._commit.commit_time,
                                   self._commit.commit_timezone)
 
     @LazyProperty
     def status(self):
         """
         Returns modified, added, removed, deleted files for current changeset
         """
         return self.changed, self.added, self.removed
 
     @LazyProperty
     def branch(self):
 
         heads = self.repository._heads(reverse=False)
 
         ref = heads.get(self.raw_id)
         if ref:
             return safe_unicode(ref)
 
     def _fix_path(self, path):
         """
         Paths are stored without trailing slash so we need to get rid off it if
         needed.
         """
         if path.endswith('/'):
             path = path.rstrip('/')
         return path
 
     def _get_id_for_path(self, path):
 
         # 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._commit.tree]
             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 %r at revision %r"
                     % (path, self.short_id))
         return self._paths[path]
 
     def _get_kind(self, path):
         id = self._get_id_for_path(path)
         obj = self.repository._repo[id]
         if isinstance(obj, objects.Blob):
             return NodeKind.FILE
         elif isinstance(obj, objects.Tree):
             return NodeKind.DIR
 
     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]
 
     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):
             try:
                 next_ = changeset.revision + 1
                 next_rev = changeset.repository.revisions[next_]
             except IndexError:
                 raise ChangesetDoesNotExistError
             cs = changeset.repository.get_changeset(next_rev)
 
             if branch and branch != cs.branch:
                 return _next(cs, branch)
 
             return cs
 
         return _next(self, branch)
 
     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):
             try:
                 prev_ = changeset.revision - 1
                 if prev_ < 0:
                     raise IndexError
                 prev_rev = changeset.repository.revisions[prev_]
             except IndexError:
                 raise ChangesetDoesNotExistError
 
             cs = changeset.repository.get_changeset(prev_rev)
 
             if branch and branch != cs.branch:
                 return _prev(cs, branch)
 
             return cs
 
         return _prev(self, branch)
 
+    def diff(self, ignore_whitespace=True, context=3):
+        return ''.join(self.repository.get_diff(self, self.parents[0],
+                                    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
         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``.
         """
         node = self.get_node(path)
         return node.history[0]
 
     def get_file_history(self, path):
         """
         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.
         """
         cmd = 'log --pretty="format: %%H" -s -p %s -- "%s"' % (
                   self.id, path
                )
         so, se = self.repository.run_git_command(cmd)
         ids = re.findall(r'[0-9a-fA-F]{40}', so)
         return [self.repository.get_changeset(id) for id in ids]
 
     def get_file_annotate(self, path):
         """
         Returns a list of three element tuples with lineno,changeset 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)
         annotate = []
         for i, blame_line in enumerate(so.split('\n')[:-1]):
             ln_no = i + 1
             id, line = re.split(r' \(.+?\) ', blame_line, 1)
             annotate.append((ln_no, self.repository.get_changeset(id), line))
         return annotate
 
     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.keys()
         if kind not in allowed_kinds:
             raise ImproperArchiveTypeError('Archive kind not supported use one'
                 'of %s', allowed_kinds)
 
         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'
         cmd = 'git archive --format=%s --prefix=%s/ %s' % (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):
         if self._get_kind(path) != NodeKind.DIR:
             raise ChangesetError("Directory does not exist for revision %r at "
                 " %r" % (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 objects.S_ISGITLINK(stat):
                 dirnodes.append(SubModuleNode(name, url=None, changeset=id,
                                               alias=als))
                 continue
 
             obj = self.repository._repo.get_object(id)
             if path != '':
                 obj_path = '/'.join((path, name))
             else:
                 obj_path = name
             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:
                 raise ChangesetError("Requested object should be Tree "
                                      "or Blob, is %r" % type(obj))
         nodes = dirnodes + filenodes
         for node in nodes:
             if not node.path in self.nodes:
                 self.nodes[node.path] = node
         nodes.sort()
         return nodes
 
     def get_node(self, path):
         if isinstance(path, unicode):
             path = path.encode('utf-8')
         path = self._fix_path(path)
         if not path in self.nodes:
             try:
                 id_ = self._get_id_for_path(path)
             except ChangesetError:
                 raise NodeDoesNotExistError("Cannot find one of parents' "
                     "directories for a given path: %s" % path)
 
             als = self.repository.alias
             _GL = lambda m: m and objects.S_ISGITLINK(m)
             if _GL(self._stat_modes.get(path)):
                 node = SubModuleNode(path, url=None, changeset=id_, alias=als)
             else:
                 obj = self.repository._repo.get_object(id_)
 
                 if isinstance(obj, objects.Tree):
                     if path == '':
                         node = RootNode(changeset=self)
                     else:
                         node = DirNode(path, changeset=self)
                     node._tree = obj
                 elif isinstance(obj, objects.Blob):
                     node = FileNode(path, changeset=self)
                     node._blob = obj
                 else:
                     raise NodeDoesNotExistError("There is no file nor directory "
                         "at the given path %r at revision %r"
                         % (path, self.short_id))
             # cache node
             self.nodes[path] = node
         return self.nodes[path]
 
     @LazyProperty
     def affected_files(self):
         """
         Get's a fast accessible file changes for given changeset
         """
 
         return self.added + self.changed
 
     @LazyProperty
     def _diff_name_status(self):
         output = []
         for parent in self.parents:
             cmd = 'diff --name-status %s %s --encoding=utf8' % (parent.raw_id, self.raw_id)
             so, se = self.repository.run_git_command(cmd)
             output.append(so.strip())
         return '\n'.join(output)
 
     def _get_paths_for_status(self, status):
         """
         Returns sorted list of paths for given ``status``.
 
         :param status: one of: *added*, *modified* or *deleted*
         """
         paths = set()
         char = status[0].upper()
         for line in self._diff_name_status.splitlines():
             if not line:
                 continue
 
             if line.startswith(char):
                 splitted = line.split(char, 1)
                 if not len(splitted) == 2:
                     raise VCSError("Couldn't parse diff result:\n%s\n\n and "
                         "particularly that line: %s" % (self._diff_name_status,
                         line))
                 _path = splitted[1].strip()
                 paths.add(_path)
         return sorted(paths)
 
     @LazyProperty
     def added(self):
         """
         Returns list of added ``FileNode`` objects.
         """
         if not self.parents:
             return list(self._get_file_nodes())
         return [self.get_node(path) for path in self._get_paths_for_status('added')]
 
     @LazyProperty
     def changed(self):
         """
         Returns list of modified ``FileNode`` objects.
         """
         if not self.parents:
             return []
         return [self.get_node(path) for path in self._get_paths_for_status('modified')]
 
     @LazyProperty
     def removed(self):
         """
         Returns list of removed ``FileNode`` objects.
         """
         if not self.parents:
             return []
         return [RemovedFileNode(path) for path in self._get_paths_for_status('deleted')]

rhodecode/lib/vcs/backends/git/repository.py

@@ -1,565 +1,571 b''
 # -*- coding: utf-8 -*-
 """
     vcs.backends.git
     ~~~~~~~~~~~~~~~~
 
     Git backend implementation.
 
     :created_on: Apr 8, 2010
     :copyright: (c) 2010-2011 by Marcin Kuzminski, Lukasz Balcerzak.
 """
 
 import os
 import re
 import time
 import posixpath
 from dulwich.repo import Repo, NotGitRepository
 #from dulwich.config import ConfigFile
 from string import Template
 from subprocess import Popen, PIPE
 from rhodecode.lib.vcs.backends.base import BaseRepository
 from rhodecode.lib.vcs.exceptions import BranchDoesNotExistError
 from rhodecode.lib.vcs.exceptions import ChangesetDoesNotExistError
 from rhodecode.lib.vcs.exceptions import EmptyRepositoryError
 from rhodecode.lib.vcs.exceptions import RepositoryError
 from rhodecode.lib.vcs.exceptions import TagAlreadyExistError
 from rhodecode.lib.vcs.exceptions import TagDoesNotExistError
 from rhodecode.lib.vcs.utils import safe_unicode, makedate, date_fromtimestamp
 from rhodecode.lib.vcs.utils.lazy import LazyProperty
 from rhodecode.lib.vcs.utils.ordered_dict import OrderedDict
 from rhodecode.lib.vcs.utils.paths import abspath
 from rhodecode.lib.vcs.utils.paths import get_user_home
 from .workdir import GitWorkdir
 from .changeset import GitChangeset
 from .inmemory import GitInMemoryChangeset
 from .config import ConfigFile
 
 
 class GitRepository(BaseRepository):
     """
     Git repository backend.
     """
     DEFAULT_BRANCH_NAME = 'master'
     scm = 'git'
 
     def __init__(self, repo_path, create=False, src_url=None,
                  update_after_clone=False, bare=False):
 
         self.path = abspath(repo_path)
         self._repo = self._get_repo(create, src_url, update_after_clone, bare)
         #temporary set that to now at later we will move it to constructor
         baseui = None
         if baseui is None:
             from mercurial.ui import ui
             baseui = ui()
         # patch the instance of GitRepo with an "FAKE" ui object to add
         # compatibility layer with Mercurial
         setattr(self._repo, 'ui', baseui)
 
         try:
             self.head = self._repo.head()
         except KeyError:
             self.head = None
 
         self._config_files = [
             bare and abspath(self.path, 'config') or abspath(self.path, '.git',
                 'config'),
             abspath(get_user_home(), '.gitconfig'),
         ]
         self.bare = self._repo.bare
 
     @LazyProperty
     def revisions(self):
         """
         Returns list of revisions' ids, in ascending order.  Being lazy
         attribute allows external tools to inject shas from cache.
         """
         return self._get_all_revisions()
 
     def run_git_command(self, cmd):
         """
         Runs given ``cmd`` as git command and returns tuple
         (returncode, stdout, stderr).
 
         .. note::
            This method exists only until log/blame functionality is implemented
            at Dulwich (see https://bugs.launchpad.net/bugs/645142). Parsing
            os command's output is road to hell...
 
         :param cmd: git command to be executed
         """
 
         _copts = ['-c', 'core.quotepath=false', ]
         _str_cmd = False
         if isinstance(cmd, basestring):
             cmd = [cmd]
             _str_cmd = True
 
         gitenv = os.environ
         gitenv['GIT_CONFIG_NOGLOBAL'] = '1'
 
         cmd = ['git'] + _copts + cmd
         if _str_cmd:
             cmd = ' '.join(cmd)
         try:
             opts = dict(
                 shell=isinstance(cmd, basestring),
                 stdout=PIPE,
                 stderr=PIPE,
                 env=gitenv,
             )
             if os.path.isdir(self.path):
                 opts['cwd'] = self.path
             p = Popen(cmd, **opts)
         except OSError, err:
             raise RepositoryError("Couldn't run git command (%s).\n"
                 "Original error was:%s" % (cmd, err))
         so, se = p.communicate()
         if not se.startswith("fatal: bad default revision 'HEAD'") and \
             p.returncode != 0:
             raise RepositoryError("Couldn't run git command (%s).\n"
                 "stderr:\n%s" % (cmd, se))
         return so, se
 
     def _check_url(self, url):
         """
         Functon will check given url and try to verify if it's a valid
         link. Sometimes it may happened that mercurial will issue basic
         auth request that can cause whole API to hang when used from python
         or other external calls.
 
         On failures it'll raise urllib2.HTTPError
         """
 
         #TODO: implement this
         pass
 
     def _get_repo(self, create, src_url=None, update_after_clone=False,
             bare=False):
         if create and os.path.exists(self.path):
             raise RepositoryError("Location already exist")
         if src_url and not create:
             raise RepositoryError("Create should be set to True if src_url is "
                                   "given (clone operation creates repository)")
         try:
             if create and src_url:
                 self._check_url(src_url)
                 self.clone(src_url, update_after_clone, bare)
                 return Repo(self.path)
             elif create:
                 os.mkdir(self.path)
                 if bare:
                     return Repo.init_bare(self.path)
                 else:
                     return Repo.init(self.path)
             else:
                 return Repo(self.path)
         except (NotGitRepository, OSError), err:
             raise RepositoryError(err)
 
     def _get_all_revisions(self):
         cmd = 'rev-list --all --date-order'
         try:
             so, se = self.run_git_command(cmd)
         except RepositoryError:
             # Can be raised for empty repositories
             return []
         revisions = so.splitlines()
         revisions.reverse()
         return revisions
 
     def _get_revision(self, revision):
         """
         For git backend we always return integer here. This way we ensure
         that changset's revision attribute would become integer.
         """
         pattern = re.compile(r'^[[0-9a-fA-F]{12}|[0-9a-fA-F]{40}]$')
         is_bstr = lambda o: isinstance(o, (str, unicode))
         is_null = lambda o: len(o) == revision.count('0')
 
         if len(self.revisions) == 0:
             raise EmptyRepositoryError("There are no changesets yet")
 
         if revision in (None, '', 'tip', 'HEAD', 'head', -1):
             revision = self.revisions[-1]
 
         if ((is_bstr(revision) and revision.isdigit() and len(revision) < 12)
             or isinstance(revision, int) or is_null(revision)):
             try:
                 revision = self.revisions[int(revision)]
             except:
                 raise ChangesetDoesNotExistError("Revision %r does not exist "
                     "for this repository %s" % (revision, self))
 
         elif is_bstr(revision):
             if not pattern.match(revision) or revision not in self.revisions:
                 raise ChangesetDoesNotExistError("Revision %r does not exist "
                     "for this repository %s" % (revision, self))
 
         # Ensure we return full id
         if not pattern.match(str(revision)):
             raise ChangesetDoesNotExistError("Given revision %r not recognized"
                 % revision)
         return revision
 
     def _get_archives(self, archive_name='tip'):
 
         for i in [('zip', '.zip'), ('gz', '.tar.gz'), ('bz2', '.tar.bz2')]:
                 yield {"type": i[0], "extension": i[1], "node": archive_name}
 
     def _get_url(self, url):
         """
         Returns normalized url. If schema is not given, would fall to
         filesystem (``file:///``) schema.
         """
         url = str(url)
         if url != 'default' and not '://' in url:
             url = ':///'.join(('file', url))
         return url
 
     @LazyProperty
     def name(self):
         return os.path.basename(self.path)
 
     @LazyProperty
     def last_change(self):
         """
         Returns last change made on this repository as datetime object
         """
         return date_fromtimestamp(self._get_mtime(), makedate()[1])
 
     def _get_mtime(self):
         try:
             return time.mktime(self.get_changeset().date.timetuple())
         except RepositoryError:
             idx_loc = '' if self.bare else '.git'
             # fallback to filesystem
             in_path = os.path.join(self.path, idx_loc, "index")
             he_path = os.path.join(self.path, idx_loc, "HEAD")
             if os.path.exists(in_path):
                 return os.stat(in_path).st_mtime
             else:
                 return os.stat(he_path).st_mtime
 
     @LazyProperty
     def description(self):
         idx_loc = '' if self.bare else '.git'
         undefined_description = u'unknown'
         description_path = os.path.join(self.path, idx_loc, 'description')
         if os.path.isfile(description_path):
             return safe_unicode(open(description_path).read())
         else:
             return undefined_description
 
     @LazyProperty
     def contact(self):
         undefined_contact = u'Unknown'
         return undefined_contact
 
     @property
     def branches(self):
         if not self.revisions:
             return {}
         refs = self._repo.refs.as_dict()
         sortkey = lambda ctx: ctx[0]
         _branches = [('/'.join(ref.split('/')[2:]), head)
             for ref, head in refs.items()
             if ref.startswith('refs/heads/') and not ref.endswith('/HEAD')]
         return OrderedDict(sorted(_branches, key=sortkey, reverse=False))
 
     def _heads(self, reverse=False):
         refs = self._repo.get_refs()
         heads = {}
 
         for key, val in refs.items():
             for ref_key in ['refs/heads/', 'refs/remotes/origin/']:
                 if key.startswith(ref_key):
                     n = key[len(ref_key):]
                     if n not in ['HEAD']:
                         heads[n] = val
 
         return heads if reverse else dict((y,x) for x,y in heads.iteritems())
 
     def _get_tags(self):
         if not self.revisions:
             return {}
         sortkey = lambda ctx: ctx[0]
         _tags = [('/'.join(ref.split('/')[2:]), head) for ref, head in
             self._repo.get_refs().items() if ref.startswith('refs/tags/')]
         return OrderedDict(sorted(_tags, key=sortkey, reverse=True))
 
     @LazyProperty
     def tags(self):
         return self._get_tags()
 
     def tag(self, name, user, revision=None, message=None, date=None,
             **kwargs):
         """
         Creates and returns a tag for the given ``revision``.
 
         :param name: name for new tag
         :param user: full username, i.e.: "Joe Doe <[e-mail]>"
         :param revision: changeset id for which new tag would be created
         :param message: message of the tag's commit
         :param date: date of tag's commit
 
         :raises TagAlreadyExistError: if tag with same name already exists
         """
         if name in self.tags:
             raise TagAlreadyExistError("Tag %s already exists" % name)
         changeset = self.get_changeset(revision)
         message = message or "Added tag %s for commit %s" % (name,
             changeset.raw_id)
         self._repo.refs["refs/tags/%s" % name] = changeset._commit.id
 
         self.tags = self._get_tags()
         return changeset
 
     def remove_tag(self, name, user, message=None, date=None):
         """
         Removes tag with the given ``name``.
 
         :param name: name of the tag to be removed
         :param user: full username, i.e.: "Joe Doe <[e-mail]>"
         :param message: message of the tag's removal commit
         :param date: date of tag's removal commit
 
         :raises TagDoesNotExistError: if tag with given name does not exists
         """
         if name not in self.tags:
             raise TagDoesNotExistError("Tag %s does not exist" % name)
         tagpath = posixpath.join(self._repo.refs.path, 'refs', 'tags', name)
         try:
             os.remove(tagpath)
             self.tags = self._get_tags()
         except OSError, e:
             raise RepositoryError(e.strerror)
 
     def get_changeset(self, revision=None):
         """
         Returns ``GitChangeset`` object representing commit from git repository
         at the given revision or head (most recent commit) if None given.
         """
         if isinstance(revision, GitChangeset):
             return revision
         revision = self._get_revision(revision)
         changeset = GitChangeset(repository=self, revision=revision)
         return changeset
 
     def get_changesets(self, start=None, end=None, start_date=None,
            end_date=None, branch_name=None, reverse=False):
         """
         Returns iterator of ``GitChangeset`` objects from start to end (both
         are inclusive), in ascending date order (unless ``reverse`` is set).
 
         :param start: changeset ID, as str; first returned changeset
         :param end: changeset ID, as str; last returned changeset
         :param start_date: if specified, changesets with commit date less than
           ``start_date`` would be filtered out from returned set
         :param end_date: if specified, changesets with commit date greater than
           ``end_date`` would be filtered out from returned set
         :param branch_name: if specified, changesets not reachable from given
           branch would be filtered out from returned set
         :param reverse: if ``True``, returned generator would be reversed
           (meaning that returned changesets would have descending date order)
 
         :raise BranchDoesNotExistError: If given ``branch_name`` does not
             exist.
         :raise ChangesetDoesNotExistError: If changeset for given ``start`` or
           ``end`` could not be found.
 
         """
         if branch_name and branch_name not in self.branches:
             raise BranchDoesNotExistError("Branch '%s' not found" \
                                           % branch_name)
         # %H at format means (full) commit hash, initial hashes are retrieved
         # in ascending date order
         cmd_template = 'log --date-order --reverse --pretty=format:"%H"'
         cmd_params = {}
         if start_date:
             cmd_template += ' --since "$since"'
             cmd_params['since'] = start_date.strftime('%m/%d/%y %H:%M:%S')
         if end_date:
             cmd_template += ' --until "$until"'
             cmd_params['until'] = end_date.strftime('%m/%d/%y %H:%M:%S')
         if branch_name:
             cmd_template += ' $branch_name'
             cmd_params['branch_name'] = branch_name
         else:
             cmd_template += ' --all'
 
         cmd = Template(cmd_template).safe_substitute(**cmd_params)
         revs = self.run_git_command(cmd)[0].splitlines()
         start_pos = 0
         end_pos = len(revs)
         if start:
             _start = self._get_revision(start)
             try:
                 start_pos = revs.index(_start)
             except ValueError:
                 pass
 
         if end is not None:
             _end = self._get_revision(end)
             try:
                 end_pos = revs.index(_end)
             except ValueError:
                 pass
 
         if None not in [start, end] and start_pos > end_pos:
             raise RepositoryError('start cannot be after end')
 
         if end_pos is not None:
             end_pos += 1
 
         revs = revs[start_pos:end_pos]
         if reverse:
             revs = reversed(revs)
         for rev in revs:
             yield self.get_changeset(rev)
 
     def get_diff(self, rev1, rev2, path=None, ignore_whitespace=False,
                  context=3):
         """
         Returns (git like) *diff*, as plain text. Shows changes introduced by
         ``rev2`` since ``rev1``.
 
         :param rev1: Entry point from which diff is shown. Can be
           ``self.EMPTY_CHANGESET`` - in this case, patch showing all
           the changes since empty state of the repository until ``rev2``
         :param rev2: Until which revision changes should be shown.
         :param ignore_whitespace: If set to ``True``, would not show whitespace
           changes. Defaults to ``False``.
         :param context: How many lines before/after changed lines should be
           shown. Defaults to ``3``.
         """
         flags = ['-U%s' % context]
         if ignore_whitespace:
             flags.append('-w')
 
+        if hasattr(rev1, 'raw_id'):
+            rev1 = getattr(rev1, 'raw_id')
+
+        if hasattr(rev2, 'raw_id'):
+            rev2 = getattr(rev2, 'raw_id')
+
         if rev1 == self.EMPTY_CHANGESET:
             rev2 = self.get_changeset(rev2).raw_id
             cmd = ' '.join(['show'] + flags + [rev2])
         else:
             rev1 = self.get_changeset(rev1).raw_id
             rev2 = self.get_changeset(rev2).raw_id
             cmd = ' '.join(['diff'] + flags + [rev1, rev2])
 
         if path:
             cmd += ' -- "%s"' % path
         stdout, stderr = self.run_git_command(cmd)
         # If we used 'show' command, strip first few lines (until actual diff
         # starts)
         if rev1 == self.EMPTY_CHANGESET:
             lines = stdout.splitlines()
             x = 0
             for line in lines:
                 if line.startswith('diff'):
                     break
                 x += 1
             # Append new line just like 'diff' command do
             stdout = '\n'.join(lines[x:]) + '\n'
         return stdout
 
     @LazyProperty
     def in_memory_changeset(self):
         """
         Returns ``GitInMemoryChangeset`` object for this repository.
         """
         return GitInMemoryChangeset(self)
 
     def clone(self, url, update_after_clone=True, bare=False):
         """
         Tries to clone changes from external location.
 
         :param update_after_clone: If set to ``False``, git won't checkout
           working directory
         :param bare: If set to ``True``, repository would be cloned into
           *bare* git repository (no working directory at all).
         """
         url = self._get_url(url)
         cmd = ['clone']
         if bare:
             cmd.append('--bare')
         elif not update_after_clone:
             cmd.append('--no-checkout')
         cmd += ['--', '"%s"' % url, '"%s"' % self.path]
         cmd = ' '.join(cmd)
         # If error occurs run_git_command raises RepositoryError already
         self.run_git_command(cmd)
 
     def pull(self, url):
         """
         Tries to pull changes from external location.
         """
         url = self._get_url(url)
         cmd = ['pull']
         cmd.append("--ff-only")
         cmd.append(url)
         cmd = ' '.join(cmd)
         # If error occurs run_git_command raises RepositoryError already
         self.run_git_command(cmd)
 
     def fetch(self, url):
         """
         Tries to pull changes from external location.
         """
         url = self._get_url(url)
         cmd = ['fetch']
         cmd.append(url)
         cmd = ' '.join(cmd)
         # If error occurs run_git_command raises RepositoryError already
         self.run_git_command(cmd)
 
     @LazyProperty
     def workdir(self):
         """
         Returns ``Workdir`` instance for this repository.
         """
         return GitWorkdir(self)
 
     def get_config_value(self, section, name, config_file=None):
         """
         Returns configuration value for a given [``section``] and ``name``.
 
         :param section: Section we want to retrieve value from
         :param name: Name of configuration we want to retrieve
         :param config_file: A path to file which should be used to retrieve
           configuration from (might also be a list of file paths)
         """
         if config_file is None:
             config_file = []
         elif isinstance(config_file, basestring):
             config_file = [config_file]
 
         def gen_configs():
             for path in config_file + self._config_files:
                 try:
                     yield ConfigFile.from_path(path)
                 except (IOError, OSError, ValueError):
                     continue
 
         for config in gen_configs():
             try:
                 return config.get(section, name)
             except KeyError:
                 continue
         return None
 
     def get_user_name(self, config_file=None):
         """
         Returns user's name from global configuration file.
 
         :param config_file: A path to file which should be used to retrieve
           configuration from (might also be a list of file paths)
         """
         return self.get_config_value('user', 'name', config_file)
 
     def get_user_email(self, config_file=None):
         """
         Returns user's email from global configuration file.
 
         :param config_file: A path to file which should be used to retrieve
           configuration from (might also be a list of file paths)
         """
         return self.get_config_value('user', 'email', config_file)

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

@@ -1,357 +1,362 b''
 import os
 import posixpath
 
 from rhodecode.lib.vcs.backends.base import BaseChangeset
 from rhodecode.lib.vcs.conf import settings
 from rhodecode.lib.vcs.exceptions import  ChangesetDoesNotExistError, \
     ChangesetError, ImproperArchiveTypeError, NodeDoesNotExistError, VCSError
 from rhodecode.lib.vcs.nodes import AddedFileNodesGenerator, \
     ChangedFileNodesGenerator, DirNode, FileNode, NodeKind, \
     RemovedFileNodesGenerator, RootNode, SubModuleNode
 
 from rhodecode.lib.vcs.utils import safe_str, safe_unicode, date_fromtimestamp
 from rhodecode.lib.vcs.utils.lazy import LazyProperty
 from rhodecode.lib.vcs.utils.paths import get_dirs_for_path
 
 from ...utils.hgcompat import archival, hex
 
 
 class MercurialChangeset(BaseChangeset):
     """
     Represents state of the repository at the single revision.
     """
 
     def __init__(self, repository, revision):
         self.repository = repository
         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 bookmarks(self):
         return map(safe_unicode, self._ctx.bookmarks())
 
     @LazyProperty
     def message(self):
         return safe_unicode(self._ctx.description())
 
     @LazyProperty
     def author(self):
         return safe_unicode(self._ctx.user())
 
     @LazyProperty
     def date(self):
         return date_fromtimestamp(*self._ctx.date())
 
     @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]
 
     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):
             try:
                 next_ = changeset.revision + 1
                 next_rev = changeset.repository.revisions[next_]
             except IndexError:
                 raise ChangesetDoesNotExistError
             cs = changeset.repository.get_changeset(next_rev)
 
             if branch and branch != cs.branch:
                 return _next(cs, branch)
 
             return cs
 
         return _next(self, branch)
 
     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):
             try:
                 prev_ = changeset.revision - 1
                 if prev_ < 0:
                     raise IndexError
                 prev_rev = changeset.repository.revisions[prev_]
             except IndexError:
                 raise ChangesetDoesNotExistError
 
             cs = changeset.repository.get_changeset(prev_rev)
 
             if branch and branch != cs.branch:
                 return _prev(cs, branch)
 
             return cs
 
         return _prev(self, branch)
 
+    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 %r"
                 % (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 %r at "
                 " %r" % (self.revision, 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``.
         """
         node = self.get_node(path)
         return node.history[0]
 
     def get_file_history(self, path):
         """
         Returns history of file as reversed list of ``Changeset`` objects for
         which file at given ``path`` has been modified.
         """
         fctx = self._get_filectx(path)
         nodes = [fctx.filectx(x).node() for x in fctx.filelog()]
         changesets = [self.repository.get_changeset(hex(node))
             for node in reversed(nodes)]
         return changesets
 
     def get_file_annotate(self, path):
         """
         Returns a list of three element tuples with lineno,changeset and line
         """
         fctx = self._get_filectx(path)
         annotate = []
         for i, annotate_data in enumerate(fctx.annotate()):
             ln_no = i + 1
             annotate.append((ln_no, self.repository\
                              .get_changeset(hex(annotate_data[0].node())),
                              annotate_data[1],))
 
         return annotate
 
     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.keys()
         if kind not in allowed_kinds:
             raise ImproperArchiveTypeError('Archive kind not supported use one'
                 'of %s', 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")
 
         archival.archive(self.repository._repo, stream, self.raw_id,
                          kind, prefix=prefix, subrepos=subrepos)
 
         if stream.closed and hasattr(stream, 'name'):
             stream = open(stream.name, 'rb')
         elif hasattr(stream, 'mode') and 'r' not in stream.mode:
             stream = open(stream.name, 'rb')
         else:
             stream.seek(0)
 
     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 %r at "
                 " %r" % (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
         # cache nodes
         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 not path 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: %r at revision %r"
                     % (path, self.short_id))
             # cache node
             self.nodes[path] = node
         return self.nodes[path]
 
     @LazyProperty
     def affected_files(self):
         """
         Get's a fast accessible file changes for given changeset
         """
         return self._ctx.files()
 
     @property
     def added(self):
         """
         Returns list of added ``FileNode`` objects.
         """
         return AddedFileNodesGenerator([n for n in self.status[1]], self)
 
     @property
     def changed(self):
         """
         Returns list of modified ``FileNode`` objects.
         """
         return ChangedFileNodesGenerator([n for n in  self.status[0]], self)
 
     @property
     def removed(self):
         """
         Returns list of removed ``FileNode`` objects.
         """
         return RemovedFileNodesGenerator([n for n in self.status[2]], self)