diff --git a/swh/loader/svn/loader.py b/swh/loader/svn/loader.py index ad03594..9a7113b 100644 --- a/swh/loader/svn/loader.py +++ b/swh/loader/svn/loader.py @@ -1,543 +1,565 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information """Loader in charge of injecting either new or existing svn mirrors to swh-storage. """ import os import shutil import tempfile -from swh.core import utils from swh.model import hashutil from swh.model.from_disk import Directory from swh.model.identifiers import identifier_to_bytes, revision_identifier from swh.model.identifiers import snapshot_identifier from swh.loader.core.loader import SWHLoader from swh.loader.core.utils import clean_dangling_folders from . import svn, converters from .utils import init_svn_repo_from_archive_dump -from .exception import SvnLoaderEventful, SvnLoaderUneventful +from .exception import SvnLoaderUneventful from .exception import SvnLoaderHistoryAltered DEFAULT_BRANCH = b'master' def _revision_id(revision): return identifier_to_bytes(revision_identifier(revision)) def build_swh_snapshot(revision_id, branch=DEFAULT_BRANCH): """Build a swh snapshot from the revision id, origin id, and visit. """ return { 'id': None, 'branches': { branch: { 'target': revision_id, 'target_type': 'revision', } } } TEMPORARY_DIR_PREFIX_PATTERN = 'swh.loader.svn.' class SWHSvnLoader(SWHLoader): """Swh svn loader to load an svn repository The repository is either remote or local. The loader deals with update on an already previously loaded repository. Default policy: Keep data as close as possible from the original svn data. We only add information that are needed for update or continuing from last known revision (svn revision and svn repository's uuid). """ CONFIG_BASE_FILENAME = 'loader/svn' ADDITIONAL_CONFIG = { 'check_revision': ('int', 1000), 'temp_directory': ('str', '/tmp'), 'debug': ('bool', False), # NOT FOR PRODUCTION, False is mandatory } def __init__(self): super().__init__(logging_class='swh.loader.svn.SvnLoader') self.check_revision = self.config['check_revision'] self.origin_id = None self.debug = self.config['debug'] self.last_seen_revision = None self.temp_directory = self.config['temp_directory'] + self.done = False + # internal state used to store swh objects + self._contents = [] + self._directories = [] + self._revisions = [] + self._snapshot = None + self._last_revision = None + self._visit_status = 'full' + self._load_status = 'uneventful' def pre_cleanup(self): """Cleanup potential dangling files from prior runs (e.g. OOM killed tasks) """ clean_dangling_folders(self.temp_directory, pattern_check=TEMPORARY_DIR_PREFIX_PATTERN, log=self.log) def cleanup(self): """Clean up the svn repository's working representation on disk. """ + if not hasattr(self, 'svnrepo'): + # could happen if `prepare` fails + # nothing to do in that case + return if self.debug: self.log.error('''NOT FOR PRODUCTION - debug flag activated Local repository not cleaned up for investigation: %s''' % ( self.svnrepo.local_url.decode('utf-8'), )) return self.svnrepo.clean_fs() def swh_revision_hash_tree_at_svn_revision(self, revision): """Compute and return the hash tree at a given svn revision. Args: rev (int): the svn revision we want to check Returns: The hash tree directory as bytes. """ local_dirname, local_url = self.svnrepo.export_temporary(revision) h = Directory.from_disk(path=local_url).hash self.svnrepo.clean_fs(local_dirname) return h def get_svn_repo(self, svn_url, local_dirname, origin): """Instantiates the needed svnrepo collaborator to permit reading svn repository. Args: svn_url (str): the svn repository url to read from local_dirname (str): the local path on disk to compute data origin (int): the corresponding origin Returns: Instance of :mod:`swh.loader.svn.svn` clients """ return svn.SWHSvnRepo( svn_url, origin['id'], self.storage, local_dirname=local_dirname) def swh_latest_snapshot_revision(self, origin_id, previous_swh_revision=None): """Look for latest snapshot revision and returns it if any. Args: origin_id (int): Origin identifier previous_swh_revision: (optional) id of a possible previous swh revision Returns: dict: The latest known point in time. Dict with keys: 'revision': latest visited revision 'snapshot': latest snapshot If None is found, return an empty dict. """ storage = self.storage if not previous_swh_revision: # check latest snapshot's revision latest_snap = storage.snapshot_get_latest(origin_id) if latest_snap: branches = latest_snap.get('branches') if not branches: return {} branch = branches.get(DEFAULT_BRANCH) if not branch: return {} target_type = branch['target_type'] if target_type != 'revision': return {} previous_swh_revision = branch['target'] else: return {} - revs = list(storage.revision_get([previous_swh_revision])) + if isinstance(previous_swh_revision, dict): + swh_id = previous_swh_revision['id'] + else: + swh_id = previous_swh_revision + + revs = list(storage.revision_get([swh_id])) if revs: return { 'snapshot': latest_snap, 'revision': revs[0] } return {} def build_swh_revision(self, rev, commit, dir_id, parents): """Build the swh revision dictionary. This adds: - the `'synthetic`' flag to true - the '`extra_headers`' containing the repository's uuid and the svn revision number. Args: rev (dict): the svn revision commit (dict): the commit metadata dir_id (bytes): the upper tree's hash identifier parents ([bytes]): the parents' identifiers Returns: The swh revision corresponding to the svn revision. """ return converters.build_swh_revision(rev, commit, self.svnrepo.uuid, dir_id, parents) def check_history_not_altered(self, svnrepo, revision_start, swh_rev): """Given a svn repository, check if the history was not tampered with. """ revision_id = swh_rev['id'] parents = swh_rev['parents'] hash_data_per_revs = svnrepo.swh_hash_data_at_revision(revision_start) rev = revision_start rev, _, commit, _, root_dir = list(hash_data_per_revs)[0] dir_id = root_dir.hash swh_revision = self.build_swh_revision(rev, commit, dir_id, parents) swh_revision_id = _revision_id(swh_revision) return swh_revision_id == revision_id - def process_repository(self, origin_visit, - last_known_swh_revision=None, - start_from_scratch=False): - """The main idea of this function is to: + def _init_from(self, partial_swh_revision, previous_swh_revision): + """Function to determine from where to start from. - - iterate over the svn commit logs - - extract the svn commit log metadata - - compute the hashes from the current directory down to the file - - compute the equivalent swh revision - - send all those objects for storage - - create an swh occurrence pointing to the last swh revision seen - - send that occurrence for storage in swh-storage. + Args: + partial_swh_revision (dict): A known revision from which + the previous loading did not + finish. + known_previous_revision (dict): A known revision from + which the previous loading + did finish. + + Returns: + The revision from which to start or None if nothing (fresh + start). """ - svnrepo = self.svnrepo + if partial_swh_revision and not previous_swh_revision: + return partial_swh_revision + if not partial_swh_revision and previous_swh_revision: + return previous_swh_revision + if partial_swh_revision and previous_swh_revision: + # will determine from which to start from + extra_headers1 = dict( + partial_swh_revision['metadata']['extra_headers']) + extra_headers2 = dict( + previous_swh_revision['metadata']['extra_headers']) + rev_start1 = int(extra_headers1['svn_revision']) + rev_start2 = int(extra_headers2['svn_revision']) + if rev_start1 <= rev_start2: + return previous_swh_revision + return partial_swh_revision + + return None - revision_head = svnrepo.head_revision() + def start_from(self, last_known_swh_revision=None, + start_from_scratch=False): + """Determine from where to start the loading. + + Args: + last_known_swh_revision (dict): Last know swh revision or None + start_from_scratch (bool): To start loading from scratch or not + + Returns: + tuple (revision_start, revision_end, revision_parents) + + Raises: + + SvnLoaderHistoryAltered: When a hash divergence has been + detected (should not happen) + SvnLoaderUneventful: Nothing changed since last visit + + """ + revision_head = self.svnrepo.head_revision() if revision_head == 0: # empty repository case revision_start = 0 revision_end = 0 else: # default configuration - revision_start = svnrepo.initial_revision() + revision_start = self.svnrepo.initial_revision() revision_end = revision_head revision_parents = { revision_start: [] } if not start_from_scratch: # Check if we already know a previous revision for that origin if self.latest_snapshot: swh_rev = self.latest_snapshot['revision'] else: swh_rev = None # Determine from which known revision to start - swh_rev = self.init_from(last_known_swh_revision, - previous_swh_revision=swh_rev) + swh_rev = self._init_from(last_known_swh_revision, + previous_swh_revision=swh_rev) if swh_rev: # Yes, we know a previous revision. Try and update it. extra_headers = dict(swh_rev['metadata']['extra_headers']) revision_start = int(extra_headers['svn_revision']) revision_parents = { revision_start: swh_rev['parents'], } self.log.debug('svn export --ignore-keywords %s@%s' % ( - svnrepo.remote_url, + self.svnrepo.remote_url, revision_start)) if swh_rev and not self.check_history_not_altered( - svnrepo, + self.svnrepo, revision_start, swh_rev): msg = 'History of svn %s@%s altered. ' \ 'Skipping...' % ( - svnrepo.remote_url, revision_start) + self.svnrepo.remote_url, revision_start) raise SvnLoaderHistoryAltered(msg) # now we know history is ok, we start at next revision revision_start = revision_start + 1 # and the parent become the latest know revision for # that repository revision_parents[revision_start] = [swh_rev['id']] if revision_start > revision_end and revision_start is not 1: - msg = '%s@%s already injected.' % (svnrepo.remote_url, + msg = '%s@%s already injected.' % (self.svnrepo.remote_url, revision_end) raise SvnLoaderUneventful(msg) self.log.info('Processing revisions [%s-%s] for %s' % ( - revision_start, revision_end, svnrepo)) + revision_start, revision_end, self.svnrepo)) - # process and store revision to swh (sent by by blocks of - # 'revision_packet_size') - return self.process_swh_revisions( - svnrepo, revision_start, revision_end, revision_parents) + return revision_start, revision_end, revision_parents def process_svn_revisions(self, svnrepo, revision_start, revision_end, revision_parents): - """Process revisions from revision_start to revision_end and send to - swh for storage. + """Process svn revisions from revision_start to revision_end. At each svn revision, checkout the repository, compute the - tree hash and blobs and send for swh storage to store. - Then computes and yields the swh revision. + tree hash and blobs and send for swh storage to store. Then + computes and yields the computed swh contents, directories, + revision. Note that at every self.check_revision, an svn export is done and a hash tree is computed to check that no divergence occurred. Yields: - swh revision as a dictionary with keys, sha1_git, sha1, etc... + tuple (contents, directories, revision) of dict as a + dictionary with keys, sha1_git, sha1, etc... + + Raises: + ValueError in case of a hash divergence detection """ gen_revs = svnrepo.swh_hash_data_per_revision( revision_start, revision_end) swh_revision = None count = 0 for rev, nextrev, commit, new_objects, root_directory in gen_revs: count += 1 # Send the associated contents/directories - self.maybe_load_contents(new_objects.get('content', {}).values()) - self.maybe_load_directories( - new_objects.get('directory', {}).values()) + _contents = new_objects.get('content', {}).values() + _directories = new_objects.get('directory', {}).values() # compute the fs tree's checksums dir_id = root_directory.hash swh_revision = self.build_swh_revision( rev, commit, dir_id, revision_parents[rev]) swh_revision['id'] = _revision_id(swh_revision) self.log.debug('rev: %s, swhrev: %s, dir: %s' % ( rev, hashutil.hash_to_hex(swh_revision['id']), hashutil.hash_to_hex(dir_id))) + # FIXME: Is that still necessary? Rationale: T570 is now closed if (count % self.check_revision) == 0: # hash computation check self.log.debug('Checking hash computations on revision %s...' % rev) checked_dir_id = self.swh_revision_hash_tree_at_svn_revision( rev) if checked_dir_id != dir_id: err = 'Hash tree computation divergence detected ' \ '(%s != %s), stopping!' % ( hashutil.hash_to_hex(dir_id), hashutil.hash_to_hex(checked_dir_id)) raise ValueError(err) if nextrev: revision_parents[nextrev] = [swh_revision['id']] - yield swh_revision - - def process_swh_revisions(self, - svnrepo, - revision_start, - revision_end, - revision_parents): - """Process and store revision to swh (sent by blocks of - revision_packet_size) - - Returns: - The latest revision stored. - - """ - try: - swh_revision_gen = self.process_svn_revisions(svnrepo, - revision_start, - revision_end, - revision_parents) - revs = [] - for revisions in utils.grouper( - swh_revision_gen, - self.config['revision_packet_size']): - revs = list(revisions) - self.maybe_load_revisions(revs) - last_revision = revs[-1] - self.log.debug('Processed %s revisions: [..., %s]' % ( - len(revs), hashutil.hash_to_hex(last_revision['id']))) - self.last_seen_revision = last_revision - except Exception as e: - if revs: - # flush remaining revisions - self.maybe_load_revisions(revs) - # Take the last one as the last known revisions - known_swh_rev = revs[-1] - elif self.last_seen_revision: # We'll try to make a snapshot - known_swh_rev = self.last_seen_revision - else: - raise - - _id = known_swh_rev.get('id') - if not _id: - _id = _revision_id(known_swh_rev) - - # Then notify something is wrong, and we stopped at that rev. - raise SvnLoaderEventful(e, swh_revision={ - 'id': _id, - }) - - return last_revision - - def process_swh_snapshot(self, revision=None, snapshot=None): - """Create the snapshot either from existing snapshot or revision. - - """ - if snapshot: - snap = snapshot - elif revision: - snap = build_swh_snapshot(revision['id']) - snap['id'] = identifier_to_bytes(snapshot_identifier(snap)) - else: - return None - self.log.debug('snapshot: %s' % snap) - self.maybe_load_snapshot(snap) + yield _contents, _directories, swh_revision def prepare_origin_visit(self, *, svn_url, visit_date=None, origin_url=None, **kwargs): self.origin = { 'url': origin_url if origin_url else svn_url, 'type': 'svn', } self.visit_date = visit_date def prepare(self, *, svn_url, destination_path=None, swh_revision=None, start_from_scratch=False, **kwargs): self.start_from_scratch = start_from_scratch if swh_revision: - self.last_known_swh_revision = hashutil.hash_to_bytes( - swh_revision) + self.last_known_swh_revision = swh_revision else: self.last_known_swh_revision = None self.latest_snapshot = self.swh_latest_snapshot_revision( self.origin_id, self.last_known_swh_revision) if destination_path: local_dirname = destination_path else: local_dirname = tempfile.mkdtemp( suffix='-%s' % os.getpid(), prefix=TEMPORARY_DIR_PREFIX_PATTERN, dir=self.temp_directory) self.svnrepo = self.get_svn_repo(svn_url, local_dirname, self.origin) + try: + revision_start, revision_end, revision_parents = self.start_from( + self.last_known_swh_revision, self.start_from_scratch) + self.swh_revision_gen = self.process_svn_revisions( + self.svnrepo, revision_start, revision_end, revision_parents) + except SvnLoaderUneventful as e: + self.log.warn(e) + if self.latest_snapshot and 'snapshot' in self.latest_snapshot: + self._snapshot = self.latest_snapshot['snapshot'] + self.done = True + except SvnLoaderHistoryAltered as e: + self.log.error(e) + self.done = True + self._visit_status = 'partial' def fetch_data(self): - """We need to fetch and stream the data to store directly. So - fetch_data do actually nothing. The method ``store_data`` below is in - charge to do everything, fetch and store. + """Fetching svn revision information. - """ - pass + This will apply svn revision as patch on disk, and at the same + time, compute the swh hashes. - def store_data(self): - """We need to fetch and stream the data to store directly because - there is too much data and state changes. Everything is - intertwined together (We receive patch and apply on disk and - compute at the hashes at the same time) + In effect, fetch_data fetches those data and compute the + necessary swh objects. It's then stored in the internal state + instance variables (initialized in `_prepare_state`). - So every data to fetch and store is done here. + This is up to `store_data` to actually discuss with the + storage to store those objects. - Note: - origin_visit and last_known_swh_revision must have been set in the - prepare method. + Returns: + bool: True to continue fetching data (next svn revision), + False to stop. """ - origin_visit = {'origin': self.origin_id, 'visit': self.visit} + data = None + if self.done: + return False + try: - latest_rev = self.process_repository( - origin_visit, - last_known_swh_revision=self.last_known_swh_revision, - start_from_scratch=self.start_from_scratch) - except SvnLoaderEventful as e: - latest_rev = e.swh_revision - self.process_swh_snapshot(revision=latest_rev) - raise - except Exception as e: - if self.latest_snapshot and 'snapshot' in self.latest_snapshot: - snapshot = self.latest_snapshot['snapshot'] - self.process_swh_snapshot(snapshot=snapshot) - raise - else: - self.process_swh_snapshot(revision=latest_rev) + data = next(self.swh_revision_gen) + self._load_status = 'eventful' + except StopIteration: + self.done = True + self._visit_status = 'full' + return False # Stopping iteration + except Exception as e: # Potential: svn:external, i/o error... + self.done = True + self._visit_status = 'partial' + return False # Stopping iteration + self._contents, self._directories, revision = data + if revision: + self._last_revision = revision + self._revisions.append(revision) + return True # next svn revision - def init_from(self, partial_swh_revision, previous_swh_revision): - """Function to determine from where to start from. + def store_data(self): + """We store the data accumulated in internal instance variable. If + the iteration over the svn revisions is done, we create the + snapshot and flush to storage the data. - Args: - partial_swh_revision: A known revision from which - the previous loading did not finish. - known_previous_revision: A known revision from which the - previous loading did finish. + This also resets the internal instance variable state. - Returns: - The revision from which to start or None if nothing (fresh - start). + """ + self.maybe_load_contents(self._contents) + self.maybe_load_directories(self._directories) + self.maybe_load_revisions(self._revisions) + + if self.done: # finish line, snapshot! + self.generate_and_load_snapshot(revision=self._last_revision, + snapshot=self._snapshot) + self.flush() + + self._contents = [] + self._directories = [] + self._revisions = [] + + def generate_and_load_snapshot(self, revision=None, snapshot=None): + """Create the snapshot either from existing revision or snapshot. + + Revision (supposedly new) has priority over the snapshot + (supposedly existing one). + + Args: + revision (dict): Last revision seen if any (None by default) + snapshot (dict): Snapshot to use if any (None by default) """ - if partial_swh_revision and not previous_swh_revision: - return partial_swh_revision - if not partial_swh_revision and previous_swh_revision: - return previous_swh_revision - if partial_swh_revision and previous_swh_revision: - # will determine from which to start from - extra_headers1 = dict( - partial_swh_revision['metadata']['extra_headers']) - extra_headers2 = dict( - previous_swh_revision['metadata']['extra_headers']) - rev_start1 = int(extra_headers1['svn_revision']) - rev_start2 = int(extra_headers2['svn_revision']) - if rev_start1 <= rev_start2: - return previous_swh_revision - return partial_swh_revision + if revision: # Priority to the revision + snap = build_swh_snapshot(revision['id']) + snap['id'] = identifier_to_bytes(snapshot_identifier(snap)) + elif snapshot: # Fallback to prior snapshot + snap = snapshot + else: + return None + self.log.debug('snapshot: %s' % snap) + self.maybe_load_snapshot(snap) - return None + def load_status(self): + return { + 'status': self._load_status, + } + + def visit_status(self): + return self._visit_status class SWHSvnLoaderFromDumpArchive(SWHSvnLoader): """Uncompress an archive containing an svn dump, mount the svn dump as an svn repository and load said repository. """ def __init__(self, archive_path): super().__init__() self.log.info('Archive to mount and load %s' % archive_path) self.temp_dir, self.repo_path = init_svn_repo_from_archive_dump( archive_path, prefix=TEMPORARY_DIR_PREFIX_PATTERN, suffix='-%s' % os.getpid(), root_dir=self.temp_directory) def cleanup(self): super().cleanup() if self.temp_dir and os.path.exists(self.temp_dir): msg = 'Clean up temporary directory dump %s for project %s' % ( self.temp_dir, os.path.basename(self.repo_path)) self.log.debug(msg) shutil.rmtree(self.temp_dir) diff --git a/swh/loader/svn/svn.py b/swh/loader/svn/svn.py index 8bda250..a11b10a 100644 --- a/swh/loader/svn/svn.py +++ b/swh/loader/svn/svn.py @@ -1,267 +1,268 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information """SVN client in charge of iterating over svn logs and yield commit representations including the hash tree/content computations per svn commit. """ +import logging import os import tempfile import shutil from subvertpy.ra import RemoteAccess, Auth, get_username_provider from subvertpy import client, properties from swh.model.from_disk import Directory from . import ra, converters # When log message contains empty data DEFAULT_AUTHOR_MESSAGE = '' class SWHSvnRepo: """SWH's svn repository representation. Args: remote_url (str): origin_id (int): Associated origin identifier storage (Storage): Storage to use to execute storage statements local_dirname (str): Path to write intermediary svn action results """ def __init__(self, remote_url, origin_id, storage, local_dirname): self.remote_url = remote_url.rstrip('/') self.storage = storage self.origin_id = origin_id auth = Auth([get_username_provider()]) # one connection for log iteration self.conn_log = RemoteAccess(self.remote_url, auth=auth) # another for replay self.conn = RemoteAccess(self.remote_url, auth=auth) # one client for update operation self.client = client.Client(auth=auth) self.local_dirname = local_dirname local_name = os.path.basename(self.remote_url) self.local_url = os.path.join(self.local_dirname, local_name).encode( 'utf-8') self.uuid = self.conn.get_uuid().encode('utf-8') self.swhreplay = ra.SWHReplay(conn=self.conn, rootpath=self.local_url) def __str__(self): return str({ 'swh-origin': self.origin_id, 'remote_url': self.remote_url, 'local_url': self.local_url, 'uuid': self.uuid, }) def head_revision(self): """Retrieve current head revision. """ return self.conn.get_latest_revnum() def initial_revision(self): """Retrieve the initial revision from which the remote url appeared. """ return 1 def convert_commit_message(self, msg): """Simply encode the commit message. Args: msg (str): the commit message to convert. Returns: The transformed message as bytes. """ if isinstance(msg, bytes): return msg return msg.encode('utf-8') def convert_commit_date(self, date): """Convert the message commit date into a timestamp in swh format. The precision is kept. Args: date (str): the commit date to convert. Returns: The transformed date. """ return converters.svn_date_to_swh_date(date) def convert_commit_author(self, author): """Convert the commit author into an swh person. The user becomes a dictionary of the form:: { name: author, email: '', fullname: author } Args: author (str): the commit author to convert. Returns: The transformed author as dict. """ return converters.svn_author_to_swh_person(author) def __to_entry(self, log_entry): changed_paths, rev, revprops, has_children = log_entry author_date = self.convert_commit_date( revprops.get(properties.PROP_REVISION_DATE)) author = self.convert_commit_author( revprops.get(properties.PROP_REVISION_AUTHOR)) message = self.convert_commit_message( revprops.get(properties.PROP_REVISION_LOG, DEFAULT_AUTHOR_MESSAGE)) return { 'rev': rev, 'author_date': author_date, 'author_name': author, 'message': message, } def logs(self, revision_start, revision_end): """Stream svn logs between revision_start and revision_end by chunks of block_size logs. Yields revision and associated revision information between the revision start and revision_end. Args: revision_start: the svn revision starting bound revision_end: the svn revision ending bound Yields: tuple: tuple of revisions and logs: - revisions: list of revisions in order - logs: Dictionary with key revision number and value the log entry. The log entry is a dictionary with the following keys: - author_date: date of the commit - author_name: name of the author - message: commit message """ for log_entry in self.conn_log.iter_log(paths=None, start=revision_start, end=revision_end, discover_changed_paths=False): yield self.__to_entry(log_entry) def export(self, revision): """Export the repository to a given version. """ self.client.export(self.remote_url, to=self.local_url.decode('utf-8'), rev=revision, ignore_keywords=True) def export_temporary(self, revision): """Export the repository to a given revision in a temporary location. This is up to the caller of this function to clean up the temporary location when done (cf. self.clean_fs method) Args: revision: Revision to export at Returns: The tuple local_dirname the temporary location root folder, local_url where the repository was exported. """ local_dirname = tempfile.mkdtemp( prefix='check-revision-%s.' % revision, dir=self.local_dirname) local_name = os.path.basename(self.remote_url) local_url = os.path.join(local_dirname, local_name) self.client.export( self.remote_url, to=local_url, rev=revision, ignore_keywords=True) return local_dirname, os.fsencode(local_url) def swh_hash_data_per_revision(self, start_revision, end_revision): """Compute swh hash data per each revision between start_revision and end_revision. Args: start_revision: starting revision end_revision: ending revision Yields: tuple (rev, nextrev, commit, objects_per_path) - rev: current revision - nextrev: next revision - commit: commit data (author, date, message) for such revision - objects_per_path: dictionary of path, swh hash data with type """ for commit in self.logs(start_revision, end_revision): rev = commit['rev'] objects = self.swhreplay.compute_hashes(rev) if rev == end_revision: nextrev = None else: nextrev = rev + 1 yield rev, nextrev, commit, objects, self.swhreplay.directory def swh_hash_data_at_revision(self, revision): """Compute the hash data at revision. Expected to be used for update only. """ # Update the disk at revision self.export(revision) # Compute the current hashes on disk directory = Directory.from_disk(path=os.fsencode(self.local_url), save_path=True) # Update the replay collaborator with the right state self.swhreplay = ra.SWHReplay( conn=self.conn, rootpath=self.local_url, directory=directory) # Retrieve the commit information for revision commit = list(self.logs(revision, revision))[0] yield revision, revision + 1, commit, {}, directory def clean_fs(self, local_dirname=None): """Clean up the local working copy. Args: local_dirname (str): Path to remove recursively if provided. Otherwise, remove the temporary upper root tree used for svn repository loading. """ - if local_dirname: - shutil.rmtree(local_dirname) - else: - shutil.rmtree(self.local_dirname) + dirname = local_dirname if local_dirname else self.local_dirname + if os.path.exists(dirname): + logging.debug('cleanup %s' % dirname) + shutil.rmtree(dirname) diff --git a/swh/loader/svn/tests/test_loader.py b/swh/loader/svn/tests/test_loader.py index c587bc2..cd7374e 100644 --- a/swh/loader/svn/tests/test_loader.py +++ b/swh/loader/svn/tests/test_loader.py @@ -1,899 +1,905 @@ # Copyright (C) 2016-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from nose.tools import istest from test_base import BaseTestSvnLoader from unittest import TestCase from swh.model import hashutil from swh.loader.svn.loader import build_swh_snapshot, DEFAULT_BRANCH from swh.loader.svn.loader import SWHSvnLoader from swh.loader.svn.exception import SvnLoaderEventful, SvnLoaderUneventful from swh.loader.svn.exception import SvnLoaderHistoryAltered class TestSWHSnapshot(TestCase): @istest def build_swh_snapshot(self): actual_snap = build_swh_snapshot('revision-id') self.assertEquals(actual_snap, { 'id': None, 'branches': { DEFAULT_BRANCH: { 'target': 'revision-id', 'target_type': 'revision', } } }) # Define loaders with no storage # They'll just accumulate the data in place # Only for testing purposes. class TestSvnLoader: """Mixin class to inhibit the persistence and keep in memory the data sent for storage. cf. SWHSvnLoaderNoStorage """ def __init__(self): super().__init__() self.all_contents = [] self.all_directories = [] self.all_revisions = [] self.all_releases = [] + self.all_snapshots = [] + # Check at each svn revision that the hash tree computation # does not diverge self.check_revision = 10 # typed data self.objects = { 'content': self.all_contents, 'directory': self.all_directories, 'revision': self.all_revisions, 'release': self.all_releases, + 'snapshot': self.all_snapshots, } def _add(self, type, l): """Add without duplicates and keeping the insertion order. Args: type (str): Type of objects concerned by the action l ([object]): List of 'type' object """ col = self.objects[type] for o in l: if o in col: continue col.extend([o]) def maybe_load_contents(self, all_contents): self._add('content', all_contents) def maybe_load_directories(self, all_directories): self._add('directory', all_directories) def maybe_load_revisions(self, all_revisions): self._add('revision', all_revisions) def maybe_load_releases(self, releases): raise ValueError('If called, the test must break.') + def maybe_load_snapshot(self, snapshot): + self._add('snapshot', [snapshot]) + + def send_origin(self, origin): + return 1 + # Override to do nothing at the end def close_failure(self): pass def close_success(self): pass - def prepare(self, *args, **kwargs): - # Override to only prepare the svn repository - self.svnrepo = self.get_svn_repo(*args) - origin_id = 10 - self.latest_snapshot = self.swh_latest_snapshot_revision( - origin_id, None) + def pre_cleanup(self): + pass -class SWHSvnLoaderNoStorage(TestSvnLoader, SWHSvnLoader): +class SvnLoaderNoStorage(TestSvnLoader, SWHSvnLoader): """An SWHSVNLoader with no persistence. Context: Load a new svn repository using the swh policy (so no update). """ def swh_latest_snapshot_revision(self, origin_id, prev_swh_revision=None): """We do not know this repository so no revision. """ return {} -class SWHSvnLoaderUpdateNoStorage(TestSvnLoader, SWHSvnLoader): +class SvnLoaderUpdateNoStorage(TestSvnLoader, SWHSvnLoader): """An SWHSVNLoader with no persistence. Context: Load a known svn repository using the swh policy. We can either: - do nothing since it does not contain any new commit (so no change) - either check its history is not altered and update in consequence by loading the new revision """ def swh_latest_snapshot_revision(self, origin_id, prev_swh_revision=None): """Avoid the storage persistence call and return the expected previous revision for that repository. Check the following for explanation about the hashes: - test_loader.org for (swh policy). - cf. SWHSvnLoaderITTest """ return { - 'snapshot': None, + 'snapshot': 'something', # need a snapshot of sort 'revision': { 'id': hashutil.hash_to_bytes( '4876cb10aec6f708f7466dddf547567b65f6c39c'), 'parents': [hashutil.hash_to_bytes( 'a3a577948fdbda9d1061913b77a1588695eadb41')], 'directory': hashutil.hash_to_bytes( '0deab3023ac59398ae467fc4bff5583008af1ee2'), 'target_type': 'revision', 'metadata': { 'extra_headers': [ ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], ['svn_revision', '6'] ] } } } -class SWHSvnLoaderUpdateHistoryAlteredNoStorage(TestSvnLoader, SWHSvnLoader): +class SvnLoaderUpdateHistoryAlteredNoStorage(TestSvnLoader, SWHSvnLoader): """An SWHSVNLoader with no persistence. Context: Load a known svn repository using the swh policy with its history altered so we do not update it. """ def swh_latest_snapshot_revision(self, origin_id, prev_swh_revision=None): """Avoid the storage persistence call and return the expected previous revision for that repository. Check the following for explanation about the hashes: - test_loader.org for (swh policy). - cf. SWHSvnLoaderITTest """ return { 'snapshot': None, 'revision': { # Changed the revision id's hash to simulate history altered 'id': hashutil.hash_to_bytes( 'badbadbadbadf708f7466dddf547567b65f6c39d'), 'parents': [hashutil.hash_to_bytes( 'a3a577948fdbda9d1061913b77a1588695eadb41')], 'directory': hashutil.hash_to_bytes( '0deab3023ac59398ae467fc4bff5583008af1ee2'), 'target_type': 'revision', 'metadata': { 'extra_headers': [ ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], ['svn_revision', b'6'] ] } } } -class SWHSvnLoaderNewRepositoryITTest(BaseTestSvnLoader): +class SvnLoaderITest1(BaseTestSvnLoader): + """Load an unknown svn repository results in new data. + + """ def setUp(self): super().setUp() - - self.origin = {'id': 2, 'type': 'svn', 'url': 'file:///dev/null'} - - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 2, - } - - self.loader = SWHSvnLoaderNoStorage() - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + self.loader = SvnLoaderNoStorage() @istest - def process_repository(self): - """Process a new repository with swh policy should be ok. + def load(self): + """Load a new repository results in new swh object and snapshot """ # when - self.loader.process_repository(self.origin_visit) + self.loader.load( + svn_url=self.svn_mirror_url, + destination_path=self.destination_path) # then self.assertEquals(len(self.loader.all_revisions), 6) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '4876cb10aec6f708f7466dddf547567b65f6c39c' # cf. test_loader.org for explaining from where those hashes # come from expected_revisions = { # revision hash | directory hash '0d7dd5f751cef8fe17e8024f7d6b0e3aac2cfd71': '669a71cce6c424a81ba42b7dc5d560d32252f0ca', # noqa '95edacc8848369d6fb1608e887d6d2474fd5224f': '008ac97a1118560797c50e3392fa1443acdaa349', # noqa 'fef26ea45a520071711ba2b9d16a2985ee837021': '3780effbe846a26751a95a8c95c511fb72be15b4', # noqa '3f51abf3b3d466571be0855dfa67e094f9ceff1b': 'ffcca9b09c5827a6b8137322d4339c8055c3ee1e', # noqa 'a3a577948fdbda9d1061913b77a1588695eadb41': '7dc52cc04c3b8bd7c085900d60c159f7b846f866', # noqa last_revision: '0deab3023ac59398ae467fc4bff5583008af1ee2', # noqa } self.assertRevisionsOk(expected_revisions) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + # self.assertEquals(self.loader.all_snapshots[0], {}) + self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) + self.assertEqual(self.loader.visit_status(), 'full') + +class SvnLoaderITest2(BaseTestSvnLoader): + """Load a visited repository with no new change results in no data + change. -class SWHSvnLoaderUpdateWithNoChangeITTest(BaseTestSvnLoader): + """ def setUp(self): super().setUp() - - self.origin = {'id': 2, 'type': 'svn', 'url': 'file:///dev/null'} - - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 3, - } - - self.loader = SWHSvnLoaderUpdateNoStorage() - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + self.loader = SvnLoaderUpdateNoStorage() @istest - def process_repository(self): - """Process a known repository with swh policy and no new data should - be ok. + def load(self): + """Load a repository without new changes results in same snapshot """ # when - with self.assertRaises(SvnLoaderUneventful): - self.loader.process_repository(self.origin_visit) + self.loader.load( + svn_url=self.svn_mirror_url, + destination_path=self.destination_path) # then + + self.assertEquals(len(self.loader.all_contents), 0) + self.assertEquals(len(self.loader.all_directories), 0) self.assertEquals(len(self.loader.all_revisions), 0) self.assertEquals(len(self.loader.all_releases), 0) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + # self.assertEquals(self.loader.all_snapshots[0], {}) + self.assertEqual(self.loader.load_status(), {'status': 'uneventful'}) + self.assertEqual(self.loader.visit_status(), 'full') -class SWHSvnLoaderUpdateWithHistoryAlteredITTest(BaseTestSvnLoader): +class SvnLoaderITest3(BaseTestSvnLoader): + """In this scenario, the dump has been tampered with to modify the + commit log. This results in a hash divergence which is + detected at startup. + + In effect, that stops the loading and do nothing. + + """ def setUp(self): # the svn repository pkg-gourmet has been updated with changes super().setUp(archive_name='pkg-gourmet-with-updates.tgz') - - self.origin = {'id': 2, 'type': 'svn', 'url': 'file:///dev/null'} - - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 4, - } - - self.loader = SWHSvnLoaderUpdateHistoryAlteredNoStorage() - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + self.loader = SvnLoaderUpdateHistoryAlteredNoStorage() @istest - def process_repository(self): - """Process a known repository with swh policy and history altered - should stop and do nothing. + def load(self): + """Load known repository with history altered should do nothing """ # when - with self.assertRaises(SvnLoaderHistoryAltered): - self.loader.args = (self.origin_visit,) - self.loader.process_repository(self.origin_visit) + self.loader.load(svn_url=self.svn_mirror_url, + destination_path=self.destination_path) # then # we got the previous run's last revision (rev 6) # so 2 news + 1 old + self.assertEquals(len(self.loader.all_contents), 0) + self.assertEquals(len(self.loader.all_directories), 0) self.assertEquals(len(self.loader.all_revisions), 0) self.assertEquals(len(self.loader.all_releases), 0) + self.assertEquals(len(self.loader.all_snapshots), 0) + # FIXME: Check the snapshot's state + # self.assertEquals(self.loader.all_snapshots[0], {}) + self.assertEqual(self.loader.load_status(), {'status': 'uneventful'}) + self.assertEqual(self.loader.visit_status(), 'partial') -class SWHSvnLoaderUpdateWithChangesITTest(BaseTestSvnLoader): +class SvnLoaderITest4(BaseTestSvnLoader): + """In this scenario, the repository has been updated with new changes. + The loading visit should result in new objects stored and 1 new + snapshot. + + """ def setUp(self): # the svn repository pkg-gourmet has been updated with changes super().setUp(archive_name='pkg-gourmet-with-updates.tgz') - - self.origin = {'id': 2, 'type': 'svn', 'url': 'file:///dev/null'} - - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 5, - } - - self.loader = SWHSvnLoaderUpdateNoStorage() - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + self.loader = SvnLoaderUpdateNoStorage() @istest def process_repository(self): - """Process updated repository should yield new revisions + """Process updated repository should yield new objects """ # when - self.loader.process_repository(self.origin_visit) + self.loader.load(svn_url=self.svn_mirror_url, + destination_path=self.destination_path) # then # we got the previous run's last revision (rev 6) # so 2 new self.assertEquals(len(self.loader.all_revisions), 5) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '171dc35522bfd17dda4e90a542a0377fb2fc707a' # cf. test_loader.org for explaining from where those hashes # come from expected_revisions = { # revision hash | directory hash '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa last_revision: 'fd24a76c87a3207428e06612b49860fc78e9f6dc' # noqa } self.assertRevisionsOk(expected_revisions) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + # self.assertEquals(self.loader.all_snapshots[0], {}) + self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) + self.assertEqual(self.loader.visit_status(), 'full') -class SWHSvnLoaderUpdateWithChangesStartFromScratchITTest(BaseTestSvnLoader): - def setUp(self): - # the svn repository pkg-gourmet has been updated with changes - super().setUp(archive_name='pkg-gourmet-with-updates.tgz') - self.origin = {'id': 2, 'type': 'svn', 'url': 'file:///dev/null'} +class SvnLoaderITTest5(BaseTestSvnLoader): + """Context: - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 5, - } + - Repository already injected with successfull data + - New visit from scratch done with successfull load - self.loader = SWHSvnLoaderUpdateNoStorage() - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + """ + def setUp(self): + # the svn repository pkg-gourmet has been updated with changes + super().setUp(archive_name='pkg-gourmet-with-updates.tgz') + self.loader = SvnLoaderUpdateNoStorage() @istest - def process_repository(self): - """Process known repository from scratch should yield revisions again + def load(self): + """Load an existing repository from scratch yields same swh objects """ # when - self.loader.process_repository(self.origin_visit, - start_from_scratch=True) + self.loader.load(svn_url=self.svn_mirror_url, + destination_path=self.destination_path, + start_from_scratch=True) # then # we got the previous run's last revision (rev 6) # but we do not inspect that as we start from from scratch so # we should have all revisions so 11 self.assertEquals(len(self.loader.all_revisions), 11) self.assertEquals(len(self.loader.all_releases), 0) expected_revisions = { '0d7dd5f751cef8fe17e8024f7d6b0e3aac2cfd71': '669a71cce6c424a81ba42b7dc5d560d32252f0ca', # noqa '95edacc8848369d6fb1608e887d6d2474fd5224f': '008ac97a1118560797c50e3392fa1443acdaa349', # noqa 'fef26ea45a520071711ba2b9d16a2985ee837021': '3780effbe846a26751a95a8c95c511fb72be15b4', # noqa '3f51abf3b3d466571be0855dfa67e094f9ceff1b': 'ffcca9b09c5827a6b8137322d4339c8055c3ee1e', # noqa 'a3a577948fdbda9d1061913b77a1588695eadb41': '7dc52cc04c3b8bd7c085900d60c159f7b846f866', # noqa '4876cb10aec6f708f7466dddf547567b65f6c39c': '0deab3023ac59398ae467fc4bff5583008af1ee2', # noqa '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa '171dc35522bfd17dda4e90a542a0377fb2fc707a': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa } self.assertRevisionsOk(expected_revisions) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + # self.assertEquals(self.loader.all_snapshots[0], {}) + self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) + self.assertEqual(self.loader.visit_status(), 'full') -class SWHSvnLoaderUpdateWithUnfinishedLoadingChangesITTest(BaseTestSvnLoader): - def setUp(self): - super().setUp(archive_name='pkg-gourmet-with-updates.tgz') - self.origin = {'id': 2, 'type': 'svn', 'url': 'file:///dev/null'} +class SvnLoaderWithPreviousRevisionNoStorage(TestSvnLoader, SWHSvnLoader): + """An SWHSVNLoader with no persistence. - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 6 - } + Context: Load a known svn repository using the swh policy with its + history altered so we do not update it. - self.loader = SWHSvnLoaderNoStorage() - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + """ + def swh_latest_snapshot_revision(self, origin_id, prev_swh_revision=None): + """Avoid the storage persistence call and return the expected previous + revision for that repository. - @istest - def process_repository(self): - """Process partially visited repository should finish loading + Check the following for explanation about the hashes: + - test_loader.org for (swh policy). + - cf. SWHSvnLoaderITTest """ - previous_unfinished_revision = { - 'id': hashutil.hash_to_bytes( - '4876cb10aec6f708f7466dddf547567b65f6c39c'), - 'parents': [hashutil.hash_to_bytes( - 'a3a577948fdbda9d1061913b77a1588695eadb41')], - 'directory': hashutil.hash_to_bytes( - '0deab3023ac59398ae467fc4bff5583008af1ee2'), - 'target_type': 'revision', - 'metadata': { - 'extra_headers': [ - ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], - ['svn_revision', '6'] - ] + return { + 'snapshot': None, + 'revision': { + 'id': hashutil.hash_to_bytes( + '4876cb10aec6f708f7466dddf547567b65f6c39c'), + 'parents': [hashutil.hash_to_bytes( + 'a3a577948fdbda9d1061913b77a1588695eadb41')], + 'directory': hashutil.hash_to_bytes( + '0deab3023ac59398ae467fc4bff5583008af1ee2'), + 'target_type': 'revision', + 'metadata': { + 'extra_headers': [ + ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], # noqa + ['svn_revision', '6'] + ] + } } } + + +class SvnLoaderITTest6(BaseTestSvnLoader): + """Context: + - repository already visited with load successfull + - Changes on existing repository + - New Visit done with successful new data + + """ + def setUp(self): + super().setUp(archive_name='pkg-gourmet-with-updates.tgz') + self.loader = SvnLoaderWithPreviousRevisionNoStorage() + + @istest + def load(self): + """Load from partial previous visit result in new changes + + """ # when - self.loader.process_repository( - self.origin_visit, - last_known_swh_revision=previous_unfinished_revision) + self.loader.load( + svn_url=self.svn_mirror_url, + destination_path=self.destination_path) # then # we got the previous run's last revision (rev 6) # so 2 new self.assertEquals(len(self.loader.all_revisions), 5) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '171dc35522bfd17dda4e90a542a0377fb2fc707a' # cf. test_loader.org for explaining from where those hashes # come from expected_revisions = { # revision hash | directory hash '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa last_revision: 'fd24a76c87a3207428e06612b49860fc78e9f6dc' # noqa } self.assertRevisionsOk(expected_revisions) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + # self.assertEquals(self.loader.all_snapshots[0], {}) + self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) + self.assertEqual(self.loader.visit_status(), 'full') + +class SvnLoaderITest7(BaseTestSvnLoader): + """Context: + - repository already visited with load successfull + - Changes on existing repository + - New Visit done with successful new data -class SWHSvnLoaderUpdateWithUnfinishedLoadingChangesButVisitDoneITTest( - BaseTestSvnLoader): + """ def setUp(self): super().setUp(archive_name='pkg-gourmet-with-updates.tgz') - - self.origin = {'id': 2, 'type': 'svn', 'url': 'file:///dev/null'} - - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 9, - } - - self.loader = SWHSvnLoaderUpdateNoStorage() - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + self.loader = SvnLoaderUpdateNoStorage() @istest - def process_repository(self): - """Process known and partial repository should start from last visit + def load(self): + """Load known and partial repository should start from last visit """ previous_unfinished_revision = { 'id': hashutil.hash_to_bytes( 'a3a577948fdbda9d1061913b77a1588695eadb41'), 'parents': [hashutil.hash_to_bytes( '3f51abf3b3d466571be0855dfa67e094f9ceff1b')], 'directory': hashutil.hash_to_bytes( '7dc52cc04c3b8bd7c085900d60c159f7b846f866'), 'target_type': 'revision', 'metadata': { 'extra_headers': [ ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], ['svn_revision', '5'] ] } } # when - self.loader.process_repository( - self.origin_visit, - last_known_swh_revision=previous_unfinished_revision) + self.loader.load( + svn_url=self.svn_mirror_url, + destination_path=self.destination_path, + swh_revision=previous_unfinished_revision) # then # we got the previous run's last revision (rev 6) # so 2 new self.assertEquals(len(self.loader.all_revisions), 5) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '171dc35522bfd17dda4e90a542a0377fb2fc707a' # cf. test_loader.org for explaining from where those hashes # come from expected_revisions = { # revision hash | directory hash '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa last_revision: 'fd24a76c87a3207428e06612b49860fc78e9f6dc' # noqa } self.assertRevisionsOk(expected_revisions) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + # self.assertEquals(self.loader.all_snapshots[0], {}) + self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) + self.assertEqual(self.loader.visit_status(), 'full') -class SWHSvnLoaderUpdateLessRecentNoStorage(TestSvnLoader, SWHSvnLoader): - """An SWHSVNLoader with no persistence. - - Context: - Load a known svn repository using the swh policy. The last - visit seen is less recent than a previous unfinished crawl. +class SvnLoaderUpdateLessRecentNoStorage(TestSvnLoader, SWHSvnLoader): + """Context: + Load a known svn repository. The last visit seen is less + recent than a previous unfinished crawl. """ def swh_latest_snapshot_revision(self, origin_id, prev_swh_revision=None): """Avoid the storage persistence call and return the expected previous revision for that repository. Check the following for explanation about the hashes: - test_loader.org for (swh policy). - cf. SWHSvnLoaderITTest """ return { 'snapshot': None, 'revision': { 'id': hashutil.hash_to_bytes( 'a3a577948fdbda9d1061913b77a1588695eadb41'), 'parents': [hashutil.hash_to_bytes( '3f51abf3b3d466571be0855dfa67e094f9ceff1b')], 'directory': hashutil.hash_to_bytes( '7dc52cc04c3b8bd7c085900d60c159f7b846f866'), 'target_type': 'revision', 'metadata': { 'extra_headers': [ ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], ['svn_revision', '5'] ] } } } -class SWHSvnLoaderUnfinishedLoadingChangesSinceLastVisitITTest( - BaseTestSvnLoader): - def setUp(self): - super().setUp(archive_name='pkg-gourmet-with-updates.tgz') +class SvnLoaderITest8(BaseTestSvnLoader): + """Context: - self.origin = {'id': 2, 'type': 'svn', 'url': 'file:///dev/null'} - - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 1, - } + - Previous visit on existing repository done + - Starting the loading from the last unfinished visit + - New objects are created (1 new snapshot) - self.loader = SWHSvnLoaderUpdateLessRecentNoStorage() - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + """ + def setUp(self): + super().setUp(archive_name='pkg-gourmet-with-updates.tgz') + self.loader = SvnLoaderUpdateLessRecentNoStorage() @istest - def process_repository(self): - """Process updated repository should yield revisions from last visit + def load(self): + """Load repository should yield revisions starting from last visit """ previous_unfinished_revision = { 'id': hashutil.hash_to_bytes( '4876cb10aec6f708f7466dddf547567b65f6c39c'), 'parents': [hashutil.hash_to_bytes( 'a3a577948fdbda9d1061913b77a1588695eadb41')], 'directory': hashutil.hash_to_bytes( '0deab3023ac59398ae467fc4bff5583008af1ee2'), 'target_type': 'revision', 'metadata': { 'extra_headers': [ ['svn_repo_uuid', '3187e211-bb14-4c82-9596-0b59d67cd7f4'], ['svn_revision', '6'] ] } } # when - self.loader.process_repository( - self.origin_visit, - last_known_swh_revision=previous_unfinished_revision) + self.loader.load( + svn_url=self.svn_mirror_url, + destination_path=self.destination_path, + swh_revision=previous_unfinished_revision) # then # we got the previous run's last revision (rev 6) # so 2 new self.assertEquals(len(self.loader.all_revisions), 5) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '171dc35522bfd17dda4e90a542a0377fb2fc707a' # cf. test_loader.org for explaining from where those hashes # come from expected_revisions = { # revision hash | directory hash '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa last_revision: 'fd24a76c87a3207428e06612b49860fc78e9f6dc' # noqa } self.assertRevisionsOk(expected_revisions) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + # self.assertEquals(self.loader.all_snapshots[0], {}) + self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) + self.assertEqual(self.loader.visit_status(), 'full') -class SWHSvnLoaderTestCornerCaseAboutCrlfEolInRepoITTest(BaseTestSvnLoader): - """ - Check that a svn repo containing a versioned file with CRLF line - endings with svn:eol-style property set to 'native' (this is - a violation of svn specification as the file should have been - stored with LF line endings) can be loaded anyway. +class SvnLoaderTTest9(BaseTestSvnLoader): + """Check that a svn repo containing a versioned file with CRLF line + endings with svn:eol-style property set to 'native' (this is a + violation of svn specification as the file should have been + stored with LF line endings) can be loaded anyway. + """ def setUp(self): super().setUp(archive_name='mediawiki-repo-r407-eol-native-crlf.tgz', filename='mediawiki-repo-r407-eol-native-crlf') - - self.origin = {'id': 1, 'type': 'svn', - 'url': 'https://code.google.com/p/pyang/pyang-repo'} - - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 1, - } - - self.loader = SWHSvnLoaderNoStorage() - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + self.loader = SvnLoaderNoStorage() @istest def process_repository(self): - """ - Process repository with CRLF line endings and svn:eol-style set to 'native' + """Load repository with CRLF endings (svn:eol-style: native) is ok + """ # noqa # when - self.loader.process_repository(self.origin_visit) + self.loader.load(svn_url=self.svn_mirror_url, + destination_path=self.destination_path) expected_revisions = { '7da4975c363101b819756d33459f30a866d01b1b': 'f63637223ee0f7d4951ffd2d4d9547a4882c5d8b' # noqa } - self.assertRevisionsOk(expected_revisions) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + # self.assertEquals(self.loader.all_snapshots[0], {}) + self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) + self.assertEqual(self.loader.visit_status(), 'full') -class SWHSvnLoaderTestCornerCaseAboutMixedCrlfLfEolInRepoITTest(BaseTestSvnLoader): # noqa - """ - Check that a svn repo containing a versioned file with mixed +class SvnLoaderITest10(BaseTestSvnLoader): # noqa + """Check that a svn repo containing a versioned file with mixed CRLF/LF line endings with svn:eol-style property set to 'native' (this is a violation of svn specification as mixed line endings for textual content should not be stored when the svn:eol-style property is set) can be loaded anyway. + """ def setUp(self): - super().setUp(archive_name='pyang-repo-r343-eol-native-mixed-lf-crlf.tgz', # noqa - filename='pyang-repo-r343-eol-native-mixed-lf-crlf') - - self.origin = {'id': 1, 'type': 'svn', - 'url': 'https://code.google.com/m/mediawiki/mediawiki-repo'} # noqa - - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 1, - } - - self.loader = SWHSvnLoaderNoStorage() - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + super().setUp( + archive_name='pyang-repo-r343-eol-native-mixed-lf-crlf.tgz', + filename='pyang-repo-r343-eol-native-mixed-lf-crlf') + self.loader = SvnLoaderNoStorage() @istest - def process_repository(self): + def load(self): + """Load repo with mixed CRLF/LF endings (svn:eol-style:native) is ok + """ - Process repository with mixed CRLF/LF line endings and svn:eol-style set to 'native' - """ # noqa - self.loader.process_repository(self.origin_visit) + self.loader.load(svn_url=self.svn_mirror_url, + destination_path=self.destination_path) expected_revisions = { '9c6962eeb9164a636c374be700672355e34a98a7': '16aa6b6271f3456d4643999d234cf39fe3d0cc5a' # noqa } self.assertRevisionsOk(expected_revisions) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + # self.assertEquals(self.loader.all_snapshots[0], {}) + self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) + self.assertEqual(self.loader.visit_status(), 'full') -class SWHSvnLoaderExternalIdCornerCaseITTest(BaseTestSvnLoader): - def setUp(self): - super().setUp(archive_name='pkg-gourmet-with-external-id.tgz') - - self.origin = {'id': 2, 'type': 'svn', 'url': 'file:///dev/null'} +class SvnLoaderITest11(BaseTestSvnLoader): + """Context: - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 1, - } + - Repository with svn:external (which is not deal with for now) + - Visit is partial with as much data loaded as possible - self.loader = SWHSvnLoaderNoStorage() - # override revision-block size - self.loader.config['revision_packet_size'] = 3 - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + """ + def setUp(self): + super().setUp(archive_name='pkg-gourmet-with-external-id.tgz') + self.loader = SvnLoaderNoStorage() @istest - def process_repository(self): + def load(self): """Repository with svn:externals property, will stop raising an error """ previous_unfinished_revision = None # when - with self.assertRaises(SvnLoaderEventful) as exc: - self.loader.process_repository( - self.origin_visit, - last_known_swh_revision=previous_unfinished_revision) - - actual_raised_revision = exc.exception.swh_revision + self.loader.load( + svn_url=self.svn_mirror_url, + destination_path=self.destination_path, + swh_revision=previous_unfinished_revision) # then repositories holds 21 revisions, but the last commit # one holds an 'svn:externals' property which will make the - # loader-svn stops. This will then stop at the 6th iterations - # of 3-revision block size, so only 18 revisions will be - # flushed - self.assertEquals(len(self.loader.all_revisions), 18) + # loader-svn stops at the last revision prior to the bad one + self.assertEquals(len(self.loader.all_revisions), 20) self.assertEquals(len(self.loader.all_releases), 0) - last_revision = 'ffa901b69ca0f46a2261f42948838d19709cb9f8' - + last_revision = '82a7a4a09f9549223429143ba36ad77375e33c5c' expected_revisions = { # revision hash | directory hash '0d7dd5f751cef8fe17e8024f7d6b0e3aac2cfd71': '669a71cce6c424a81ba42b7dc5d560d32252f0ca', # noqa '95edacc8848369d6fb1608e887d6d2474fd5224f': '008ac97a1118560797c50e3392fa1443acdaa349', # noqa 'fef26ea45a520071711ba2b9d16a2985ee837021': '3780effbe846a26751a95a8c95c511fb72be15b4', # noqa '3f51abf3b3d466571be0855dfa67e094f9ceff1b': 'ffcca9b09c5827a6b8137322d4339c8055c3ee1e', # noqa 'a3a577948fdbda9d1061913b77a1588695eadb41': '7dc52cc04c3b8bd7c085900d60c159f7b846f866', # noqa '4876cb10aec6f708f7466dddf547567b65f6c39c': '0deab3023ac59398ae467fc4bff5583008af1ee2', # noqa '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa '171dc35522bfd17dda4e90a542a0377fb2fc707a': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa '027e8769f4786597436ab94a91f85527d04a6cbb': '2d9ca72c6afec6284fb01e459588cbb007017c8c', # noqa '4474d96018877742d9697d5c76666c9693353bfc': 'ab111577e0ab39e4a157c476072af48f2641d93f', # noqa '97ad21eab92961e2a22ca0285f09c6d1e9a7ffbc': 'ab111577e0ab39e4a157c476072af48f2641d93f', # noqa 'd04ea8afcee6205cc8384c091bfc578931c169fd': 'b0a648b02e55a4dce356ac35187a058f89694ec7', # noqa 'ded78810401fd354ffe894aa4a1e5c7d30a645d1': 'b0a648b02e55a4dce356ac35187a058f89694ec7', # noqa '4ee95e39358712f53c4fc720da3fafee9249ed19': 'c3c98df624733fef4e592bef983f93e2ed02b179', # noqa - last_revision : 'c3c98df624733fef4e592bef983f93e2ed02b179', # noqa + 'ffa901b69ca0f46a2261f42948838d19709cb9f8': 'c3c98df624733fef4e592bef983f93e2ed02b179', # noqa + '0148ae3eaa520b73a50802c59f3f416b7a36cf8c': '844d4646d6c2b4f3a3b2b22ab0ee38c7df07bab2', # noqa + last_revision: '0de6e75d2b79ec90d00a3a7611aa3861b2e4aa5e', # noqa } # The last revision being the one used later to start back from - self.assertEquals(hashutil.hash_to_hex(actual_raised_revision['id']), - last_revision) - self.assertRevisionsOk(expected_revisions) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) + self.assertEqual(self.loader.visit_status(), 'partial') + +class SvnLoaderITest12(BaseTestSvnLoader): + """Edge cases: + - first create a file and commit it. + Remove it, then add folder holding the same name, commit. + - do the same scenario with symbolic link (instead of file) -class SWHSvnLoaderLinkFileAndFolderWithSameNameITTest(BaseTestSvnLoader): + """ def setUp(self): - # edge cases: - # - first create a file and commit it. - # Remove it, then add folder holding the same name, commit. - # - do the same scenario with symbolic link (instead of file) super().setUp( archive_name='pkg-gourmet-with-edge-case-links-and-files.tgz') - - self.origin = {'id': 2, 'type': 'svn', 'url': 'file:///dev/null'} - - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 1, - } - - self.loader = SWHSvnLoaderNoStorage() - # override revision-block size - self.loader.config['revision_packet_size'] = 3 - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + self.loader = SvnLoaderNoStorage() @istest - def process_repository(self): - """File/Link destroyed prior to folder with same name creation should be ok + def load(self): + """File/Link removed prior to folder with same name creation is ok """ previous_unfinished_revision = None # when - self.loader.process_repository( - self.origin_visit, - last_known_swh_revision=previous_unfinished_revision) + self.loader.load( + svn_url=self.svn_mirror_url, + destination_path=self.destination_path, + swh_revision=previous_unfinished_revision) # then repositories holds 14 revisions, but the last commit self.assertEquals(len(self.loader.all_revisions), 19) self.assertEquals(len(self.loader.all_releases), 0) last_revision = '3f43af2578fccf18b0d4198e48563da7929dc608' expected_revisions = { # revision hash | directory hash '0d7dd5f751cef8fe17e8024f7d6b0e3aac2cfd71': '669a71cce6c424a81ba42b7dc5d560d32252f0ca', # noqa '95edacc8848369d6fb1608e887d6d2474fd5224f': '008ac97a1118560797c50e3392fa1443acdaa349', # noqa 'fef26ea45a520071711ba2b9d16a2985ee837021': '3780effbe846a26751a95a8c95c511fb72be15b4', # noqa '3f51abf3b3d466571be0855dfa67e094f9ceff1b': 'ffcca9b09c5827a6b8137322d4339c8055c3ee1e', # noqa 'a3a577948fdbda9d1061913b77a1588695eadb41': '7dc52cc04c3b8bd7c085900d60c159f7b846f866', # noqa '4876cb10aec6f708f7466dddf547567b65f6c39c': '0deab3023ac59398ae467fc4bff5583008af1ee2', # noqa '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa '171dc35522bfd17dda4e90a542a0377fb2fc707a': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa '9231f9a98a9051a0cd34231cddd4e11773f8348e': '6c07f4f4ac780eaf99a247fbfd0897533598dd36', # noqa 'c309bd3b57796696d6655ab3ab0b438fdd2d8201': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa 'bb78300cc1ac9119eb6fffa9e9fa04a7f9340b11': 'ee995a0d85f6917c75bcee3aa448bea7726b265d', # noqa 'f2e01111329f84580dc3febb1fd45515692c5886': 'e2baec7b6a5543758e9c73695bc847db0a4f7941', # noqa '1a0f70c34e211f073e1be3435ecf6f0dd7700267': 'e7536e721fa806c19971b749c091c144b2f2b88e', # noqa '0c612a23d293cc3100496a54ae4ad13d750efe4c': '2123d12749294bbfb54e73f9d73fac658aabb266', # noqa '69a53d972e2f863acbbbda546d9da96287af6a88': '13896cb96ec004140ce5be8852fee8c29830d9c7', # noqa last_revision: '6b1e0243768ff9ac060064b2eeade77e764ffc82', # noqa } self.assertRevisionsOk(expected_revisions) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) + self.assertEqual(self.loader.visit_status(), 'full') + +class SvnLoaderITTest13(BaseTestSvnLoader): + """Edge cases: + - wrong symbolic link + - wrong symbolic link with empty space names -class SWHSvnLoaderWrongLinkCasesITTest(BaseTestSvnLoader): + """ def setUp(self): - # edge cases: - # - wrong symbolic link - # - wrong symbolic link with empty space names super().setUp( archive_name='pkg-gourmet-with-wrong-link-cases.tgz') - - self.origin = {'id': 2, 'type': 'svn', 'url': 'file:///dev/null'} - - self.origin_visit = { - 'origin': self.origin['id'], - 'visit': 1, - } - - self.loader = SWHSvnLoaderNoStorage() - # override revision-block size - self.loader.config['revision_packet_size'] = 3 - self.loader.prepare( - self.svn_mirror_url, self.destination_path, self.origin) + self.loader = SvnLoaderNoStorage() @istest - def process_repository(self): + def load(self): """Wrong link or empty space-named link should be ok """ - previous_unfinished_revision = None - # when - self.loader.process_repository( - self.origin_visit, - last_known_swh_revision=previous_unfinished_revision) + self.loader.load( + svn_url=self.svn_mirror_url, + destination_path=self.destination_path) # then repositories holds 14 revisions, but the last commit self.assertEquals(len(self.loader.all_revisions), 21) self.assertEquals(len(self.loader.all_releases), 0) last_revision = 'cf30d3bb9d5967d0a2bbeacc405f10a5dd9b138a' expected_revisions = { # revision hash | directory hash '0d7dd5f751cef8fe17e8024f7d6b0e3aac2cfd71': '669a71cce6c424a81ba42b7dc5d560d32252f0ca', # noqa '95edacc8848369d6fb1608e887d6d2474fd5224f': '008ac97a1118560797c50e3392fa1443acdaa349', # noqa 'fef26ea45a520071711ba2b9d16a2985ee837021': '3780effbe846a26751a95a8c95c511fb72be15b4', # noqa '3f51abf3b3d466571be0855dfa67e094f9ceff1b': 'ffcca9b09c5827a6b8137322d4339c8055c3ee1e', # noqa 'a3a577948fdbda9d1061913b77a1588695eadb41': '7dc52cc04c3b8bd7c085900d60c159f7b846f866', # noqa '4876cb10aec6f708f7466dddf547567b65f6c39c': '0deab3023ac59398ae467fc4bff5583008af1ee2', # noqa '7f5bc909c29d4e93d8ccfdda516e51ed44930ee1': '752c52134dcbf2fff13c7be1ce4e9e5dbf428a59', # noqa '38d81702cb28db4f1a6821e64321e5825d1f7fd6': '39c813fb4717a4864bacefbd90b51a3241ae4140', # noqa '99c27ebbd43feca179ac0e895af131d8314cafe1': '3397ca7f709639cbd36b18a0d1b70bce80018c45', # noqa '902f29b4323a9b9de3af6d28e72dd581e76d9397': 'c4e12483f0a13e6851459295a4ae735eb4e4b5c4', # noqa '171dc35522bfd17dda4e90a542a0377fb2fc707a': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa '9231f9a98a9051a0cd34231cddd4e11773f8348e': '6c07f4f4ac780eaf99a247fbfd0897533598dd36', # noqa 'c309bd3b57796696d6655ab3ab0b438fdd2d8201': 'fd24a76c87a3207428e06612b49860fc78e9f6dc', # noqa 'bb78300cc1ac9119eb6fffa9e9fa04a7f9340b11': 'ee995a0d85f6917c75bcee3aa448bea7726b265d', # noqa 'f2e01111329f84580dc3febb1fd45515692c5886': 'e2baec7b6a5543758e9c73695bc847db0a4f7941', # noqa '1a0f70c34e211f073e1be3435ecf6f0dd7700267': 'e7536e721fa806c19971b749c091c144b2f2b88e', # noqa '0c612a23d293cc3100496a54ae4ad13d750efe4c': '2123d12749294bbfb54e73f9d73fac658aabb266', # noqa '69a53d972e2f863acbbbda546d9da96287af6a88': '13896cb96ec004140ce5be8852fee8c29830d9c7', # noqa '3f43af2578fccf18b0d4198e48563da7929dc608': '6b1e0243768ff9ac060064b2eeade77e764ffc82', # noqa '4ab5fc264732cd474d2e695c5ac66e4933bdad74': '9a1f5e3961db89422250ce6c1441476f40d65205', # noqa last_revision: 'd853d9628f6f0008d324fed27dadad00ce48bc62', # noqa } self.assertRevisionsOk(expected_revisions) + self.assertEquals(len(self.loader.all_snapshots), 1) + # FIXME: Check the snapshot's state + self.assertEqual(self.loader.load_status(), {'status': 'eventful'}) + self.assertEqual(self.loader.visit_status(), 'full')