Extended commit search schema with date of commit

rhodecode/lib/indexers/__init__.py

@@ -1,264 +1,265 b''
 # -*- coding: utf-8 -*-
 """
     rhodecode.lib.indexers.__init__
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
     Whoosh indexing module for RhodeCode
 
     :created_on: Aug 17, 2010
     :author: marcink
     :copyright: (C) 2010-2012 Marcin Kuzminski <[e-mail]>
     :license: GPLv3, see COPYING for more details.
 """
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
 # the Free Software Foundation, either version 3 of the License, or
 # (at your option) any later version.
 #
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 import os
 import sys
 import traceback
 import logging
 from os.path import dirname as dn, join as jn
 
 #to get the rhodecode import
 sys.path.append(dn(dn(dn(os.path.realpath(__file__)))))
 
 from string import strip
 from shutil import rmtree
 
 from whoosh.analysis import RegexTokenizer, LowercaseFilter, StopFilter
 from whoosh.fields import TEXT, ID, STORED, NUMERIC, BOOLEAN, Schema, FieldType
 from whoosh.index import create_in, open_dir
 from whoosh.formats import Characters
 from whoosh.highlight import highlight, HtmlFormatter, ContextFragmenter
 
 from webhelpers.html.builder import escape, literal
 from sqlalchemy import engine_from_config
 
 from rhodecode.model import init_model
 from rhodecode.model.scm import ScmModel
 from rhodecode.model.repo import RepoModel
 from rhodecode.config.environment import load_environment
 from rhodecode.lib.utils2 import LazyProperty
 from rhodecode.lib.utils import BasePasterCommand, Command, add_cache,\
     load_rcextensions
 
 log = logging.getLogger(__name__)
 
 # CUSTOM ANALYZER wordsplit + lowercase filter
 ANALYZER = RegexTokenizer(expression=r"\w+") | LowercaseFilter()
 
 #INDEX SCHEMA DEFINITION
 SCHEMA = Schema(
     fileid=ID(unique=True),
     owner=TEXT(),
     repository=TEXT(stored=True),
     path=TEXT(stored=True),
     content=FieldType(format=Characters(), analyzer=ANALYZER,
                       scorable=True, stored=True),
     modtime=STORED(),
     extension=TEXT(stored=True)
 )
 
 IDX_NAME = 'HG_INDEX'
 FORMATTER = HtmlFormatter('span', between='\n<span class="break">...</span>\n')
 FRAGMENTER = ContextFragmenter(200)
 
 CHGSETS_SCHEMA = Schema(
     raw_id=ID(unique=True, stored=True),
+    date=NUMERIC(stored=True),
     last=BOOLEAN(),
     owner=TEXT(),
     repository=ID(unique=True, stored=True),
     author=TEXT(stored=True),
     message=FieldType(format=Characters(), analyzer=ANALYZER,
                       scorable=True, stored=True),
     parents=TEXT(),
     added=TEXT(),
     removed=TEXT(),
     changed=TEXT(),
 )
 
 CHGSET_IDX_NAME = 'CHGSET_INDEX'
 
 class MakeIndex(BasePasterCommand):
 
     max_args = 1
     min_args = 1
 
     usage = "CONFIG_FILE"
     summary = "Creates index for full text search given configuration file"
     group_name = "RhodeCode"
     takes_config_file = -1
     parser = Command.standard_parser(verbose=True)
 
     def command(self):
         logging.config.fileConfig(self.path_to_ini_file)
         from pylons import config
         add_cache(config)
         engine = engine_from_config(config, 'sqlalchemy.db1.')
         init_model(engine)
         index_location = config['index_dir']
         repo_location = self.options.repo_location \
             if self.options.repo_location else RepoModel().repos_path
         repo_list = map(strip, self.options.repo_list.split(',')) \
             if self.options.repo_list else None
         repo_update_list = map(strip, self.options.repo_update_list.split(',')) \
             if self.options.repo_update_list else None
         load_rcextensions(config['here'])
         #======================================================================
         # WHOOSH DAEMON
         #======================================================================
         from rhodecode.lib.pidlock import LockHeld, DaemonLock
         from rhodecode.lib.indexers.daemon import WhooshIndexingDaemon
         try:
             l = DaemonLock(file_=jn(dn(dn(index_location)), 'make_index.lock'))
             WhooshIndexingDaemon(index_location=index_location,
                                  repo_location=repo_location,
                                  repo_list=repo_list,
                                  repo_update_list=repo_update_list)\
                 .run(full_index=self.options.full_index)
             l.release()
         except LockHeld:
             sys.exit(1)
 
     def update_parser(self):
         self.parser.add_option('--repo-location',
                           action='store',
                           dest='repo_location',
                           help="Specifies repositories location to index OPTIONAL",
                           )
         self.parser.add_option('--index-only',
                           action='store',
                           dest='repo_list',
                           help="Specifies a comma separated list of repositores "
                                 "to build index on. If not given all repositories "
                                 "are scanned for indexing. OPTIONAL",
                           )
         self.parser.add_option('--update-only',
                           action='store',
                           dest='repo_update_list',
                           help="Specifies a comma separated list of repositores "
                                 "to re-build index on. OPTIONAL",
                           )
         self.parser.add_option('-f',
                           action='store_true',
                           dest='full_index',
                           help="Specifies that index should be made full i.e"
                                 " destroy old and build from scratch",
                           default=False)
 
 
 class WhooshResultWrapper(object):
     def __init__(self, search_type, searcher, matcher, highlight_items,
                  repo_location):
         self.search_type = search_type
         self.searcher = searcher
         self.matcher = matcher
         self.highlight_items = highlight_items
         self.fragment_size = 200
         self.repo_location = repo_location
 
     @LazyProperty
     def doc_ids(self):
         docs_id = []
         while self.matcher.is_active():
             docnum = self.matcher.id()
             chunks = [offsets for offsets in self.get_chunks()]
             docs_id.append([docnum, chunks])
             self.matcher.next()
         return docs_id
 
     def __str__(self):
         return '<%s at %s>' % (self.__class__.__name__, len(self.doc_ids))
 
     def __repr__(self):
         return self.__str__()
 
     def __len__(self):
         return len(self.doc_ids)
 
     def __iter__(self):
         """
         Allows Iteration over results,and lazy generate content
 
         *Requires* implementation of ``__getitem__`` method.
         """
         for docid in self.doc_ids:
             yield self.get_full_content(docid)
 
     def __getitem__(self, key):
         """
         Slicing of resultWrapper
         """
         i, j = key.start, key.stop
 
         slices = []
         for docid in self.doc_ids[i:j]:
             slices.append(self.get_full_content(docid))
         return slices
 
     def get_full_content(self, docid):
         res = self.searcher.stored_fields(docid[0])
         log.debug('result: %s' % res)
         if self.search_type == 'content':
             full_repo_path = jn(self.repo_location, res['repository'])
             f_path = res['path'].split(full_repo_path)[-1]
             f_path = f_path.lstrip(os.sep)
             content_short = self.get_short_content(res, docid[1])
             res.update({'content_short': content_short,
                         'content_short_hl': self.highlight(content_short),
                         'f_path': f_path
                       })
         elif self.search_type == 'message':
             res.update({'message_hl': self.highlight(res['message'])})
 
         log.debug('result: %s' % res)
 
         return res
 
     def get_short_content(self, res, chunks):
 
         return ''.join([res['content'][chunk[0]:chunk[1]] for chunk in chunks])
 
     def get_chunks(self):
         """
         Smart function that implements chunking the content
         but not overlap chunks so it doesn't highlight the same
         close occurrences twice.
 
         :param matcher:
         :param size:
         """
         memory = [(0, 0)]
         if self.matcher.supports('positions'):
             for span in self.matcher.spans():
                 start = span.startchar or 0
                 end = span.endchar or 0
                 start_offseted = max(0, start - self.fragment_size)
                 end_offseted = end + self.fragment_size
 
                 if start_offseted < memory[-1][1]:
                     start_offseted = memory[-1][1]
                 memory.append((start_offseted, end_offseted,))
                 yield (start_offseted, end_offseted,)
 
     def highlight(self, content, top=5):
         if self.search_type not in ['content', 'message']:
             return ''
         hl = highlight(
             text=content,
             terms=self.highlight_items,
             analyzer=ANALYZER,
             fragmenter=FRAGMENTER,
             formatter=FORMATTER,
             top=top
         )
         return hl

rhodecode/lib/indexers/daemon.py

@@ -1,412 +1,413 b''
 # -*- coding: utf-8 -*-
 """
     rhodecode.lib.indexers.daemon
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
     A daemon will read from task table and run tasks
 
     :created_on: Jan 26, 2010
     :author: marcink
     :copyright: (C) 2010-2012 Marcin Kuzminski <[e-mail]>
     :license: GPLv3, see COPYING for more details.
 """
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
 # the Free Software Foundation, either version 3 of the License, or
 # (at your option) any later version.
 #
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 from __future__ import with_statement
 
 import os
 import sys
 import logging
 import traceback
 
 from shutil import rmtree
 from time import mktime
 
 from os.path import dirname as dn
 from os.path import join as jn
 
 #to get the rhodecode import
 project_path = dn(dn(dn(dn(os.path.realpath(__file__)))))
 sys.path.append(project_path)
 
 from rhodecode.config.conf import INDEX_EXTENSIONS
 from rhodecode.model.scm import ScmModel
 from rhodecode.lib.utils2 import safe_unicode
 from rhodecode.lib.indexers import SCHEMA, IDX_NAME, CHGSETS_SCHEMA, \
     CHGSET_IDX_NAME
 
 from rhodecode.lib.vcs.exceptions import ChangesetError, RepositoryError, \
     NodeDoesNotExistError
 
 from whoosh.index import create_in, open_dir, exists_in
 from whoosh.query import *
 from whoosh.qparser import QueryParser
 
 log = logging.getLogger('whoosh_indexer')
 
 
 class WhooshIndexingDaemon(object):
     """
     Daemon for atomic indexing jobs
     """
 
     def __init__(self, indexname=IDX_NAME, index_location=None,
                  repo_location=None, sa=None, repo_list=None,
                  repo_update_list=None):
         self.indexname = indexname
 
         self.index_location = index_location
         if not index_location:
             raise Exception('You have to provide index location')
 
         self.repo_location = repo_location
         if not repo_location:
             raise Exception('You have to provide repositories location')
 
         self.repo_paths = ScmModel(sa).repo_scan(self.repo_location)
 
         #filter repo list
         if repo_list:
             self.filtered_repo_paths = {}
             for repo_name, repo in self.repo_paths.items():
                 if repo_name in repo_list:
                     self.filtered_repo_paths[repo_name] = repo
 
             self.repo_paths = self.filtered_repo_paths
 
         #filter update repo list
         self.filtered_repo_update_paths = {}
         if repo_update_list:
             self.filtered_repo_update_paths = {}
             for repo_name, repo in self.repo_paths.items():
                 if repo_name in repo_update_list:
                     self.filtered_repo_update_paths[repo_name] = repo
             self.repo_paths = self.filtered_repo_update_paths
 
         self.initial = True
         if not os.path.isdir(self.index_location):
             os.makedirs(self.index_location)
             log.info('Cannot run incremental index since it does not'
                      ' yet exist running full build')
         elif not exists_in(self.index_location, IDX_NAME):
             log.info('Running full index build as the file content'
                      ' index does not exist')
         elif not exists_in(self.index_location, CHGSET_IDX_NAME):
             log.info('Running full index build as the changeset'
                      ' index does not exist')
         else:
             self.initial = False
 
     def get_paths(self, repo):
         """
         recursive walk in root dir and return a set of all path in that dir
         based on repository walk function
         """
         index_paths_ = set()
         try:
             tip = repo.get_changeset('tip')
             for _topnode, _dirs, files in tip.walk('/'):
                 for f in files:
                     index_paths_.add(jn(repo.path, f.path))
 
         except RepositoryError:
             log.debug(traceback.format_exc())
             pass
         return index_paths_
 
     def get_node(self, repo, path):
         n_path = path[len(repo.path) + 1:]
         node = repo.get_changeset().get_node(n_path)
         return node
 
     def get_node_mtime(self, node):
         return mktime(node.last_changeset.date.timetuple())
 
     def add_doc(self, writer, path, repo, repo_name):
         """
         Adding doc to writer this function itself fetches data from
         the instance of vcs backend
         """
 
         node = self.get_node(repo, path)
         indexed = indexed_w_content = 0
         # we just index the content of chosen files, and skip binary files
         if node.extension in INDEX_EXTENSIONS and not node.is_binary:
             u_content = node.content
             if not isinstance(u_content, unicode):
                 log.warning('  >> %s Could not get this content as unicode '
                             'replacing with empty content' % path)
                 u_content = u''
             else:
                 log.debug('    >> %s [WITH CONTENT]' % path)
                 indexed_w_content += 1
 
         else:
             log.debug('    >> %s' % path)
             # just index file name without it's content
             u_content = u''
             indexed += 1
 
         p = safe_unicode(path)
         writer.add_document(
             fileid=p,
             owner=unicode(repo.contact),
             repository=safe_unicode(repo_name),
             path=p,
             content=u_content,
             modtime=self.get_node_mtime(node),
             extension=node.extension
         )
         return indexed, indexed_w_content
 
     def index_changesets(self, writer, repo_name, repo, start_rev=None):
         """
         Add all changeset in the vcs repo starting at start_rev
         to the index writer
 
         :param writer: the whoosh index writer to add to
         :param repo_name: name of the repository from whence the
           changeset originates including the repository group
         :param repo: the vcs repository instance to index changesets for,
           the presumption is the repo has changesets to index
         :param start_rev=None: the full sha id to start indexing from
           if start_rev is None then index from the first changeset in
           the repo
         """
 
         if start_rev is None:
             start_rev = repo[0].raw_id
 
         log.debug('indexing changesets in %s starting at rev: %s' %
                   (repo_name, start_rev))
 
         indexed = 0
         for cs in repo.get_changesets(start=start_rev):
             log.debug('    >> %s' % cs)
             writer.add_document(
                 raw_id=unicode(cs.raw_id),
                 owner=unicode(repo.contact),
+                date=cs._timestamp,
                 repository=safe_unicode(repo_name),
                 author=cs.author,
                 message=cs.message,
                 last=cs.last,
                 added=u' '.join([node.path for node in cs.added]).lower(),
                 removed=u' '.join([node.path for node in cs.removed]).lower(),
                 changed=u' '.join([node.path for node in cs.changed]).lower(),
                 parents=u' '.join([cs.raw_id for cs in cs.parents]),
             )
             indexed += 1
 
         log.debug('indexed %d changesets for repo %s' % (indexed, repo_name))
         return indexed
 
     def index_files(self, file_idx_writer, repo_name, repo):
         """
         Index files for given repo_name
 
         :param file_idx_writer: the whoosh index writer to add to
         :param repo_name: name of the repository we're indexing
         :param repo: instance of vcs repo
         """
         i_cnt = iwc_cnt = 0
         log.debug('building index for [%s]' % repo.path)
         for idx_path in self.get_paths(repo):
             i, iwc = self.add_doc(file_idx_writer, idx_path, repo, repo_name)
             i_cnt += i
             iwc_cnt += iwc
 
         log.debug('added %s files %s with content for repo %s' %
                   (i_cnt + iwc_cnt, iwc_cnt, repo.path))
         return i_cnt, iwc_cnt
 
     def update_changeset_index(self):
         idx = open_dir(self.index_location, indexname=CHGSET_IDX_NAME)
 
         with idx.searcher() as searcher:
             writer = idx.writer()
             writer_is_dirty = False
             try:
                 indexed_total = 0
                 for repo_name, repo in self.repo_paths.items():
                     # skip indexing if there aren't any revs in the repo
                     num_of_revs = len(repo)
                     if num_of_revs < 1:
                         continue
 
                     qp = QueryParser('repository', schema=CHGSETS_SCHEMA)
                     q = qp.parse(u"last:t AND %s" % repo_name)
 
                     results = searcher.search(q)
 
                     # default to scanning the entire repo
                     last_rev = 0
                     start_id = None
 
                     if len(results) > 0:
                         # assuming that there is only one result, if not this
                         # may require a full re-index.
                         start_id = results[0]['raw_id']
                         last_rev = repo.get_changeset(revision=start_id).revision
 
                     # there are new changesets to index or a new repo to index
                     if last_rev == 0 or num_of_revs > last_rev + 1:
                         # delete the docs in the index for the previous
                         # last changeset(s)
                         for hit in results:
                             q = qp.parse(u"last:t AND %s AND raw_id:%s" %
                                             (repo_name, hit['raw_id']))
                             writer.delete_by_query(q)
 
                         # index from the previous last changeset + all new ones
                         indexed_total += self.index_changesets(writer,
                                                 repo_name, repo, start_id)
                         writer_is_dirty = True
                 log.debug('indexed %s changesets for repo %s' % (
                              indexed_total, repo_name)
                 )
             finally:
                 if writer_is_dirty:
                     log.debug('>> COMMITING CHANGES TO CHANGESET INDEX<<')
                     writer.commit(merge=True)
                     log.debug('>> COMMITTED CHANGES TO CHANGESET INDEX<<')
                 else:
                     writer.cancel
                     log.debug('>> NOTHING TO COMMIT<<')
 
     def update_file_index(self):
         log.debug((u'STARTING INCREMENTAL INDEXING UPDATE FOR EXTENSIONS %s '
                    'AND REPOS %s') % (INDEX_EXTENSIONS, self.repo_paths.keys()))
 
         idx = open_dir(self.index_location, indexname=self.indexname)
         # The set of all paths in the index
         indexed_paths = set()
         # The set of all paths we need to re-index
         to_index = set()
 
         writer = idx.writer()
         writer_is_dirty = False
         try:
             with idx.reader() as reader:
 
                 # Loop over the stored fields in the index
                 for fields in reader.all_stored_fields():
                     indexed_path = fields['path']
                     indexed_repo_path = fields['repository']
                     indexed_paths.add(indexed_path)
 
                     if not indexed_repo_path in self.filtered_repo_update_paths:
                         continue
 
                     repo = self.repo_paths[indexed_repo_path]
 
                     try:
                         node = self.get_node(repo, indexed_path)
                         # Check if this file was changed since it was indexed
                         indexed_time = fields['modtime']
                         mtime = self.get_node_mtime(node)
                         if mtime > indexed_time:
                             # The file has changed, delete it and add it to
                             # the list of files to reindex
                             log.debug(
                                 'adding to reindex list %s mtime: %s vs %s' % (
                                     indexed_path, mtime, indexed_time)
                             )
                             writer.delete_by_term('fileid', indexed_path)
                             writer_is_dirty = True
 
                             to_index.add(indexed_path)
                     except (ChangesetError, NodeDoesNotExistError):
                         # This file was deleted since it was indexed
                         log.debug('removing from index %s' % indexed_path)
                         writer.delete_by_term('path', indexed_path)
                         writer_is_dirty = True
 
             # Loop over the files in the filesystem
             # Assume we have a function that gathers the filenames of the
             # documents to be indexed
             ri_cnt_total = 0  # indexed
             riwc_cnt_total = 0  # indexed with content
             for repo_name, repo in self.repo_paths.items():
                 # skip indexing if there aren't any revisions
                 if len(repo) < 1:
                     continue
                 ri_cnt = 0   # indexed
                 riwc_cnt = 0  # indexed with content
                 for path in self.get_paths(repo):
                     path = safe_unicode(path)
                     if path in to_index or path not in indexed_paths:
 
                         # This is either a file that's changed, or a new file
                         # that wasn't indexed before. So index it!
                         i, iwc = self.add_doc(writer, path, repo, repo_name)
                         writer_is_dirty = True
                         log.debug('re indexing %s' % path)
                         ri_cnt += i
                         ri_cnt_total += 1
                         riwc_cnt += iwc
                         riwc_cnt_total += iwc
                 log.debug('added %s files %s with content for repo %s' % (
                              ri_cnt + riwc_cnt, riwc_cnt, repo.path)
                 )
             log.debug('indexed %s files in total and %s with content' % (
                         ri_cnt_total, riwc_cnt_total)
             )
         finally:
             if writer_is_dirty:
                 log.debug('>> COMMITING CHANGES <<')
                 writer.commit(merge=True)
                 log.debug('>>> FINISHED REBUILDING INDEX <<<')
             else:
                 log.debug('>> NOTHING TO COMMIT<<')
                 writer.cancel()
 
     def build_indexes(self):
         if os.path.exists(self.index_location):
             log.debug('removing previous index')
             rmtree(self.index_location)
 
         if not os.path.exists(self.index_location):
             os.mkdir(self.index_location)
 
         chgset_idx = create_in(self.index_location, CHGSETS_SCHEMA,
                                indexname=CHGSET_IDX_NAME)
         chgset_idx_writer = chgset_idx.writer()
 
         file_idx = create_in(self.index_location, SCHEMA, indexname=IDX_NAME)
         file_idx_writer = file_idx.writer()
         log.debug('BUILDING INDEX FOR EXTENSIONS %s '
                   'AND REPOS %s' % (INDEX_EXTENSIONS, self.repo_paths.keys()))
 
         for repo_name, repo in self.repo_paths.items():
             # skip indexing if there aren't any revisions
             if len(repo) < 1:
                 continue
 
             self.index_files(file_idx_writer, repo_name, repo)
             self.index_changesets(chgset_idx_writer, repo_name, repo)
 
         log.debug('>> COMMITING CHANGES <<')
         file_idx_writer.commit(merge=True)
         chgset_idx_writer.commit(merge=True)
         log.debug('>>> FINISHED BUILDING INDEX <<<')
 
     def update_indexes(self):
         self.update_file_index()
         self.update_changeset_index()
 
     def run(self, full_index=False):
         """Run daemon"""
         if full_index or self.initial:
             self.build_indexes()
         else:
             self.update_indexes()

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

@@ -1,468 +1,472 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
 
         try:
             commit = self.repository._repo.get_object(revision)
             if isinstance(commit, objects.Tag):
                 revision = commit.object[1]
                 commit = self.repository._repo.get_object(commit.object[1])
         except KeyError:
             raise RepositoryError("Cannot get object with id %s" % revision)
         self.raw_id = revision
         self.id = self.raw_id
         self.short_id = self.raw_id[:12]
         self._commit = commit
 
         self._tree_id = commit.tree
         self._commiter_property = 'committer'
         self._date_property = 'commit_time'
         self._date_tz_property = 'commit_timezone'
         self.revision = repository.revisions.index(revision)
 
         self.message = safe_unicode(commit.message)
         #self.branch = None
         self.tags = []
         self.nodes = {}
         self._paths = {}
 
     @LazyProperty
     def author(self):
         return safe_unicode(getattr(self._commit, self._commiter_property))
 
     @LazyProperty
     def date(self):
         return date_fromtimestamp(getattr(self._commit, self._date_property),
                                   getattr(self._commit, self._date_tz_property))
 
     @LazyProperty
+    def _timestamp(self):
+        return getattr(self._commit, self._date_property)
+
+    @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._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 %r at revision %r"
                     % (path, 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_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):
         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
         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)
 
             _GL = lambda m: m and objects.S_ISGITLINK(m)
             if _GL(self._stat_modes.get(path)):
                 node = SubModuleNode(path, url=None, changeset=id_,
                                      alias=self.repository.alias)
             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/hg/changeset.py

@@ -1,361 +1,365 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 rhodecode.lib.vcs.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 _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]
 
     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)