diff --git a/MANIFEST.in b/MANIFEST.in index 7fac49c..fcd5ab3 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,5 +1,5 @@ include Makefile include requirements*.txt include version.txt -recursive-include swh/loader/svn/tests/resources * +recursive-include swh/loader/svn/tests/data * recursive-include swh py.typed diff --git a/PKG-INFO b/PKG-INFO index 259d086..7f8b41e 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,93 +1,93 @@ Metadata-Version: 2.1 Name: swh.loader.svn -Version: 0.2.0 +Version: 0.2.1 Summary: Software Heritage Loader SVN Home-page: https://forge.softwareheritage.org/diffusion/DLDSVN Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-loader-svn Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-loader-svn/ Description: swh-loader-svn ============== Documents are in the ./docs folder: - Specification: ./docs/swh-loader-svn.txt # Configuration file ## Location Either: - /etc/softwareheritage/ - ~/.config/swh/ - ~/.swh/ Note: Will call that location $SWH_CONFIG_PATH ## Configuration sample $SWH_CONFIG_PATH/loader/svn.yml: ``` storage: cls: remote args: url: http://localhost:5002/ ``` ## Local run ### local svn repository ``` $ python3 repo = 'pyang-repo-r343-eol-native-mixed-lf-crlf' #repo = 'zipeg-gae' origin_url = 'http://%s.googlecode.com' % repo local_repo_path = '/home/storage/svn/repo' svn_url = 'file://%s/%s' % (local_repo_path, repo) import logging logging.basicConfig(level=logging.DEBUG) from swh.loader.svn.tasks import LoadSvnRepository t = LoadSvnRepository() t.run(svn_url=svn_url, origin_url=origin_url, visit_date='2016-05-03T15:16:32+00:00', start_from_scratch=True) ``` ### Mount and load an archive repository dump ``` $ python3 repo = '0-512-md' archive_name = '%s-repo.svndump.gz' % repo archive_path = '/home/storage/svn/dumps/%s' % archive_name origin_url = 'http://%s.googlecode.com' % repo svn_url = 'file://%s' % repo import logging logging.basicConfig(level=logging.DEBUG) from swh.loader.svn.tasks import MountAndLoadSvnRepository t = MountAndLoadSvnRepository() t.run(archive_path=archive_path, origin_url=origin_url, visit_date='2016-05-03T15:16:32+00:00', start_from_scratch=True) ``` Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: testing diff --git a/requirements-swh.txt b/requirements-swh.txt index 3ae4cfd..3837fb5 100644 --- a/requirements-swh.txt +++ b/requirements-swh.txt @@ -1,4 +1,4 @@ swh.storage >= 0.7.0 -swh.model >= 0.3 +swh.model >= 0.3.7 swh.scheduler >= 0.0.39 swh.loader.core >= 0.3.2 diff --git a/requirements-test.txt b/requirements-test.txt index d9ea615..f0b8011 100644 --- a/requirements-test.txt +++ b/requirements-test.txt @@ -1,3 +1,4 @@ pytest pytest-mock +pytest-postgresql swh.core[http] >= 0.0.61 diff --git a/swh.loader.svn.egg-info/PKG-INFO b/swh.loader.svn.egg-info/PKG-INFO index 259d086..7f8b41e 100644 --- a/swh.loader.svn.egg-info/PKG-INFO +++ b/swh.loader.svn.egg-info/PKG-INFO @@ -1,93 +1,93 @@ Metadata-Version: 2.1 Name: swh.loader.svn -Version: 0.2.0 +Version: 0.2.1 Summary: Software Heritage Loader SVN Home-page: https://forge.softwareheritage.org/diffusion/DLDSVN Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-loader-svn Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-loader-svn/ Description: swh-loader-svn ============== Documents are in the ./docs folder: - Specification: ./docs/swh-loader-svn.txt # Configuration file ## Location Either: - /etc/softwareheritage/ - ~/.config/swh/ - ~/.swh/ Note: Will call that location $SWH_CONFIG_PATH ## Configuration sample $SWH_CONFIG_PATH/loader/svn.yml: ``` storage: cls: remote args: url: http://localhost:5002/ ``` ## Local run ### local svn repository ``` $ python3 repo = 'pyang-repo-r343-eol-native-mixed-lf-crlf' #repo = 'zipeg-gae' origin_url = 'http://%s.googlecode.com' % repo local_repo_path = '/home/storage/svn/repo' svn_url = 'file://%s/%s' % (local_repo_path, repo) import logging logging.basicConfig(level=logging.DEBUG) from swh.loader.svn.tasks import LoadSvnRepository t = LoadSvnRepository() t.run(svn_url=svn_url, origin_url=origin_url, visit_date='2016-05-03T15:16:32+00:00', start_from_scratch=True) ``` ### Mount and load an archive repository dump ``` $ python3 repo = '0-512-md' archive_name = '%s-repo.svndump.gz' % repo archive_path = '/home/storage/svn/dumps/%s' % archive_name origin_url = 'http://%s.googlecode.com' % repo svn_url = 'file://%s' % repo import logging logging.basicConfig(level=logging.DEBUG) from swh.loader.svn.tasks import MountAndLoadSvnRepository t = MountAndLoadSvnRepository() t.run(archive_path=archive_path, origin_url=origin_url, visit_date='2016-05-03T15:16:32+00:00', start_from_scratch=True) ``` Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: testing diff --git a/swh.loader.svn.egg-info/SOURCES.txt b/swh.loader.svn.egg-info/SOURCES.txt index 888158b..fe56d79 100644 --- a/swh.loader.svn.egg-info/SOURCES.txt +++ b/swh.loader.svn.egg-info/SOURCES.txt @@ -1,44 +1,45 @@ MANIFEST.in Makefile README.md pyproject.toml requirements-swh.txt requirements-test.txt requirements.txt setup.cfg setup.py version.txt swh/__init__.py swh.loader.svn.egg-info/PKG-INFO swh.loader.svn.egg-info/SOURCES.txt swh.loader.svn.egg-info/dependency_links.txt swh.loader.svn.egg-info/entry_points.txt swh.loader.svn.egg-info/requires.txt swh.loader.svn.egg-info/top_level.txt swh/loader/__init__.py swh/loader/svn/__init__.py swh/loader/svn/converters.py swh/loader/svn/exception.py swh/loader/svn/loader.py swh/loader/svn/py.typed swh/loader/svn/ra.py swh/loader/svn/svn.py swh/loader/svn/tasks.py swh/loader/svn/utils.py swh/loader/svn/tests/__init__.py swh/loader/svn/tests/conftest.py swh/loader/svn/tests/test_converters.py swh/loader/svn/tests/test_loader.py swh/loader/svn/tests/test_task.py swh/loader/svn/tests/test_utils.py -swh/loader/svn/tests/resources/httthttt.tgz -swh/loader/svn/tests/resources/mediawiki-repo-r407-eol-native-crlf.tgz -swh/loader/svn/tests/resources/pkg-doc-linux-r10.tgz -swh/loader/svn/tests/resources/pkg-doc-linux-r11.tgz -swh/loader/svn/tests/resources/pkg-doc-linux-r12.tgz -swh/loader/svn/tests/resources/pkg-gourmet-with-edge-case-links-and-files.tgz -swh/loader/svn/tests/resources/pkg-gourmet-with-external-id.tgz -swh/loader/svn/tests/resources/pkg-gourmet-with-updates.tgz -swh/loader/svn/tests/resources/pkg-gourmet-with-wrong-link-cases.tgz -swh/loader/svn/tests/resources/pkg-gourmet.tgz -swh/loader/svn/tests/resources/pyang-repo-r343-eol-native-mixed-lf-crlf.tgz \ No newline at end of file +swh/loader/svn/tests/data/httthttt.tgz +swh/loader/svn/tests/data/mediawiki-repo-r407-eol-native-crlf.tgz +swh/loader/svn/tests/data/pkg-doc-linux-r10.tgz +swh/loader/svn/tests/data/pkg-doc-linux-r11.tgz +swh/loader/svn/tests/data/pkg-doc-linux-r12.tgz +swh/loader/svn/tests/data/pkg-gourmet-tampered-rev6-log.tgz +swh/loader/svn/tests/data/pkg-gourmet-with-edge-case-links-and-files.tgz +swh/loader/svn/tests/data/pkg-gourmet-with-external-id.tgz +swh/loader/svn/tests/data/pkg-gourmet-with-updates.tgz +swh/loader/svn/tests/data/pkg-gourmet-with-wrong-link-cases.tgz +swh/loader/svn/tests/data/pkg-gourmet.tgz +swh/loader/svn/tests/data/pyang-repo-r343-eol-native-mixed-lf-crlf.tgz \ No newline at end of file diff --git a/swh.loader.svn.egg-info/requires.txt b/swh.loader.svn.egg-info/requires.txt index 62cb0f3..8e3fc62 100644 --- a/swh.loader.svn.egg-info/requires.txt +++ b/swh.loader.svn.egg-info/requires.txt @@ -1,14 +1,15 @@ vcversioner click retrying python-dateutil subvertpy>=0.9.4 swh.storage>=0.7.0 -swh.model>=0.3 +swh.model>=0.3.7 swh.scheduler>=0.0.39 swh.loader.core>=0.3.2 [testing] pytest pytest-mock +pytest-postgresql swh.core[http]>=0.0.61 diff --git a/swh/loader/svn/loader.py b/swh/loader/svn/loader.py index 0423615..b4b6874 100644 --- a/swh/loader/svn/loader.py +++ b/swh/loader/svn/loader.py @@ -1,813 +1,813 @@ # Copyright (C) 2015-2020 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 pty import re import shutil import tempfile from mmap import mmap, ACCESS_WRITE from subprocess import Popen from typing import Any, Dict, Iterator, List, Optional, Tuple, Union from swh.model import hashutil from swh.model.model import ( Content, Directory, Origin, SkippedContent, Revision, Snapshot, SnapshotBranch, TargetType, ) from swh.model import from_disk from swh.loader.core.loader import BaseLoader from swh.loader.core.utils import clean_dangling_folders from swh.storage.algos.snapshot import snapshot_get_latest from . import svn, converters from .utils import ( init_svn_repo_from_dump, init_svn_repo_from_archive_dump, OutputStream, ) from .exception import SvnLoaderUneventful from .exception import SvnLoaderHistoryAltered DEFAULT_BRANCH = b"HEAD" def build_swh_snapshot(revision_id, branch=DEFAULT_BRANCH): """Build a swh snapshot from the revision id, origin url, and visit. """ return Snapshot( branches={ branch: SnapshotBranch(target=revision_id, target_type=TargetType.REVISION) } ) TEMPORARY_DIR_PREFIX_PATTERN = "swh.loader.svn." class SvnLoader(BaseLoader): """Swh svn loader. The repository is either remote or local. The loader deals with update on an already previously loaded repository. """ CONFIG_BASE_FILENAME = "loader/svn" ADDITIONAL_CONFIG = { "temp_directory": ("str", "/tmp"), "debug": ("bool", False), # NOT FOR PRODUCTION, False for production "check_revision": ( "dict", { "status": False, # do we check the revision? "limit": 1000, # at which pace do we check it? }, ), } visit_type = "svn" def __init__( self, url, origin_url=None, visit_date=None, destination_path=None, swh_revision=None, start_from_scratch=False, ): super().__init__(logging_class="swh.loader.svn.SvnLoader") # technical svn uri to act on svn repository self.svn_url = url # origin url as unique identifier for origin in swh archive self.origin_url = origin_url if origin_url else self.svn_url self.debug = self.config["debug"] self.last_seen_revision = None self.temp_directory = self.config["temp_directory"] self.done = False self.svnrepo = None # Revision check is configurable check_revision = self.config["check_revision"] if check_revision["status"]: self.check_revision = check_revision["limit"] else: self.check_revision = None # internal state used to store swh objects self._contents = [] self._skipped_contents = [] self._directories = [] self._revisions = [] - self._snapshot = None + self._snapshot: Optional[Snapshot] = None self._last_revision = None self._visit_status = "full" self._load_status = "uneventful" self.visit_date = visit_date self.destination_path = destination_path self.start_from_scratch = start_from_scratch self.swh_revision = swh_revision self.max_content_length = self.config["max_content_size"] self.snapshot = None 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 self.svnrepo: # could happen if `prepare` fails 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 = from_disk.Directory.from_disk(path=local_url).hash self.svnrepo.clean_fs(local_dirname) return h def swh_latest_snapshot_revision( self, origin_url: str, previous_swh_revision: Optional[Union[bytes, dict]] = None, ) -> Dict[str, Any]: """Look for latest snapshot revision and returns it if any. Args: origin_url: Origin identifier previous_swh_revision: possible previous swh revision (either a dict or revision identifier) Returns: dict: The latest known point in time as dict with keys (if any): 'revision': latest visited revision 'snapshot': latest snapshot If no snapshot matching criteria is found, returns an empty dict. """ storage = self.storage + latest_snapshot: Optional[Snapshot] = None - latest_snapshot_d = {} if not previous_swh_revision: latest_snapshot = snapshot_get_latest(storage, origin_url) if not latest_snapshot: return {} - latest_snapshot_d = latest_snapshot.to_dict() branches = latest_snapshot.branches if not branches: return {} branch = branches.get(DEFAULT_BRANCH) if not branch: return {} target_type = branch.target_type.value if target_type != "revision": return {} previous_swh_revision = branch.target 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_snapshot_d, "revision": revs[0]} + return {"snapshot": latest_snapshot, "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 = swh_revision.id return swh_revision_id == revision_id def _init_from(self, partial_swh_revision, previous_swh_revision): """Function to determine from where to start from. 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). """ 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 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 = 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 ) 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" % (self.svnrepo.remote_url, revision_start) ) if swh_rev and not self.check_history_not_altered( self.svnrepo, revision_start, swh_rev ): msg = "History of svn %s@%s altered. " "Skipping..." % ( 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 != 1: 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, self.svnrepo) ) return revision_start, revision_end, revision_parents def _check_revision_divergence(self, count, rev, dir_id): """Check for hash revision computation divergence. The Rationale behind this is that svn can trigger unknown edge cases (mixed CRLF, svn properties, etc...). Those are not always easy to spot. Adding a check will help in spotting missing edge cases. Args: count (int): The number of revisions done so far rev (dict): The actual revision we are computing from dir_id (bytes): The actual directory for the given revision Returns: False if no hash divergence detected Raises ValueError if a hash divergence is detected """ 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) def process_svn_revisions( self, svnrepo, revision_start, revision_end, revision_parents ) -> Iterator[ Tuple[List[Content], List[SkippedContent], List[Directory], Revision] ]: """Process svn revisions from revision_start to revision_end. At each svn revision, apply new diffs and simultaneously compute swh hashes. This yields those computed swh hashes as a tuple (contents, directories, revision). Note that at every `self.check_revision`, a supplementary check takes place to check for hash-tree divergence (related T570). Yields: 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 _contents, _skipped_contents, _directories = new_objects # compute the fs tree's checksums dir_id = root_directory.hash swh_revision = self.build_swh_revision( rev, commit, dir_id, revision_parents[rev] ) self.log.debug( "rev: %s, swhrev: %s, dir: %s" % ( rev, hashutil.hash_to_hex(swh_revision.id), hashutil.hash_to_hex(dir_id), ) ) if self.check_revision: self._check_revision_divergence(count, rev, dir_id) if nextrev: revision_parents[nextrev] = [swh_revision.id] yield _contents, _skipped_contents, _directories, swh_revision def prepare_origin_visit(self, *args, **kwargs): self.origin = Origin(url=self.origin_url if self.origin_url else self.svn_url) def prepare(self, *args, **kwargs): if self.swh_revision: self.last_known_swh_revision = self.swh_revision else: self.last_known_swh_revision = None self.latest_snapshot = self.swh_latest_snapshot_revision( self.origin_url, self.last_known_swh_revision ) if self.destination_path: local_dirname = self.destination_path else: local_dirname = tempfile.mkdtemp( suffix="-%s" % os.getpid(), prefix=TEMPORARY_DIR_PREFIX_PATTERN, dir=self.temp_directory, ) self.svnrepo = svn.SvnRepo( self.svn_url, self.origin_url, local_dirname, self.max_content_length ) 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.warning(e) if self.latest_snapshot and "snapshot" in self.latest_snapshot: self._snapshot = self.latest_snapshot["snapshot"] self.done = True + self._load_status = "uneventful" except SvnLoaderHistoryAltered as e: self.log.error(e) self.done = True self._visit_status = "partial" def fetch_data(self): """Fetching svn revision information. This will apply svn revision as patch on disk, and at the same time, compute the swh hashes. 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`). This is up to `store_data` to actually discuss with the storage to store those objects. Returns: bool: True to continue fetching data (next svn revision), False to stop. """ data = None if self.done: return False try: 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: # svn:external, hash divergence, i/o error... self.log.exception(e) self.done = True self._visit_status = "partial" return False # Stopping iteration self._contents, self._skipped_contents, self._directories, rev = data if rev: self._last_revision = rev self._revisions.append(rev) return True # next svn revision 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. This also resets the internal instance variable state. """ self.storage.skipped_content_add(self._skipped_contents) self.storage.content_add(self._contents) self.storage.directory_add(self._directories) self.storage.revision_add(self._revisions) if self.done: # finish line, snapshot! self.snapshot = self.generate_and_load_snapshot( revision=self._last_revision, snapshot=self._snapshot ) self.flush() self.loaded_snapshot_id = self.snapshot.id # reset internal state for next iteration self._revisions = [] def generate_and_load_snapshot( self, revision: Optional[Revision] = None, snapshot: Optional[Snapshot] = None ) -> Snapshot: """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) Returns: Optional[Snapshot] The newly created snapshot """ if revision: # Priority to the revision snap = build_swh_snapshot(revision.id) elif snapshot: # Fallback to prior snapshot snap = snapshot else: raise ValueError( "generate_and_load_snapshot called with null revision and snapshot!" ) self.log.debug("snapshot: %s" % snap) self.storage.snapshot_add([snap]) return snap def load_status(self): return { "status": self._load_status, } def visit_status(self): return self._visit_status class SvnLoaderFromDumpArchive(SvnLoader): """Uncompress an archive containing an svn dump, mount the svn dump as an svn repository and load said repository. """ def __init__( self, url, archive_path, origin_url=None, destination_path=None, swh_revision=None, start_from_scratch=None, visit_date=None, ): super().__init__( url, origin_url=origin_url, destination_path=destination_path, swh_revision=swh_revision, start_from_scratch=start_from_scratch, visit_date=visit_date, ) self.archive_path = archive_path self.temp_dir = None self.repo_path = None def prepare(self, *args, **kwargs): self.log.info("Archive to mount and load %s" % self.archive_path) self.temp_dir, self.repo_path = init_svn_repo_from_archive_dump( self.archive_path, prefix=TEMPORARY_DIR_PREFIX_PATTERN, suffix="-%s" % os.getpid(), root_dir=self.temp_directory, ) super().prepare(*args, **kwargs) 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) class SvnLoaderFromRemoteDump(SvnLoader): """ Create a subversion repository dump using the svnrdump utility, mount it locally and load the repository from it. """ def __init__( self, url, origin_url=None, destination_path=None, swh_revision=None, start_from_scratch=False, visit_date=None, ): super().__init__( url, origin_url=origin_url, destination_path=destination_path, swh_revision=swh_revision, start_from_scratch=start_from_scratch, visit_date=visit_date, ) self.temp_dir = tempfile.mkdtemp(dir=self.temp_directory) self.repo_path = None self.truncated_dump = False def get_last_loaded_svn_rev(self, svn_url): """ Check if the svn repository has already been visited and return the last loaded svn revision number or -1 otherwise. """ last_loaded_svn_rev = -1 try: origin = self.storage.origin_get({"url": svn_url}) last_swh_rev = self.swh_latest_snapshot_revision(origin["url"])["revision"] last_swh_rev_headers = dict(last_swh_rev["metadata"]["extra_headers"]) last_loaded_svn_rev = int(last_swh_rev_headers["svn_revision"]) except Exception: pass return last_loaded_svn_rev def dump_svn_revisions(self, svn_url, last_loaded_svn_rev=-1): """ Generate a subversion dump file using the svnrdump tool. If the svnrdump command failed somehow, the produced dump file is analyzed to determine if a partial loading is still feasible. """ # Build the svnrdump command line svnrdump_cmd = ["svnrdump", "dump", svn_url] # Launch the svnrdump command while capturing stderr as # successfully dumped revision numbers are printed to it dump_temp_dir = tempfile.mkdtemp(dir=self.temp_dir) dump_name = "".join(c for c in svn_url if c.isalnum()) dump_path = "%s/%s.svndump" % (dump_temp_dir, dump_name) stderr_lines = [] self.log.debug("Executing %s" % " ".join(svnrdump_cmd)) with open(dump_path, "wb") as dump_file: stderr_r, stderr_w = pty.openpty() svnrdump = Popen(svnrdump_cmd, stdout=dump_file, stderr=stderr_w) os.close(stderr_w) stderr_stream = OutputStream(stderr_r) readable = True while readable: lines, readable = stderr_stream.read_lines() stderr_lines += lines for line in lines: self.log.debug(line) svnrdump.wait() os.close(stderr_r) if svnrdump.returncode == 0: return dump_path # There was an error but it does not mean that no revisions # can be loaded. # Get the stderr line with latest dumped revision last_dumped_rev = None if len(stderr_lines) > 1: last_dumped_rev = stderr_lines[-2] if last_dumped_rev: # Get the latest dumped revision number matched_rev = re.search(".*revision ([0-9]+)", last_dumped_rev) last_dumped_rev = int(matched_rev.group(1)) if matched_rev else -1 # Check if revisions inside the dump file can be loaded anyway if last_dumped_rev > last_loaded_svn_rev: self.log.debug( ( "svnrdump did not dump all expected revisions " "but revisions range %s:%s are available in " "the generated dump file and will be loaded " "into the archive." ) % (last_loaded_svn_rev + 1, last_dumped_rev) ) # Truncate the dump file after the last successfully dumped # revision to avoid the loading of corrupted data self.log.debug( ( "Truncating dump file after the last " "successfully dumped revision (%s) to avoid " "the loading of corrupted data" ) % last_dumped_rev ) with open(dump_path, "r+b") as f: with mmap(f.fileno(), 0, access=ACCESS_WRITE) as s: pattern = ( "Revision-number: %s" % (last_dumped_rev + 1) ).encode() n = s.rfind(pattern) if n != -1: s.resize(n) self.truncated_dump = True return dump_path elif last_dumped_rev != -1: raise Exception( ( "Last dumped subversion revision (%s) is " "lesser than the last one loaded into the " "archive (%s)." ) % (last_dumped_rev, last_loaded_svn_rev) ) raise Exception( "An error occurred when running svnrdump and " "no exploitable dump file has been generated." ) def prepare(self, *args, **kwargs): # First, check if previous revisions have been loaded for the # subversion origin and get the number of the last one last_loaded_svn_rev = self.get_last_loaded_svn_rev(self.svn_url) # Then try to generate a dump file containing relevant svn revisions # to load, an exception will be thrown if something wrong happened dump_path = self.dump_svn_revisions(self.svn_url, last_loaded_svn_rev) # Finally, mount the dump and load the repository self.log.debug('Mounting dump file with "svnadmin load".') _, self.repo_path = init_svn_repo_from_dump( dump_path, prefix=TEMPORARY_DIR_PREFIX_PATTERN, suffix="-%s" % os.getpid(), root_dir=self.temp_dir, ) self.svn_url = "file://%s" % self.repo_path super().prepare(*args, **kwargs) def cleanup(self): super().cleanup() if self.temp_dir and os.path.exists(self.temp_dir): shutil.rmtree(self.temp_dir) def visit_status(self): if self.truncated_dump: return "partial" else: return super().visit_status() diff --git a/swh/loader/svn/ra.py b/swh/loader/svn/ra.py index 30f6a09..16de7a3 100644 --- a/swh/loader/svn/ra.py +++ b/swh/loader/svn/ra.py @@ -1,550 +1,534 @@ # Copyright (C) 2016-2020 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 """Remote Access client to svn server. """ import click import codecs import os import shutil import tempfile from typing import List, Tuple from subvertpy import delta, properties from subvertpy.ra import RemoteAccess, Auth, get_username_provider from swh.model import hashutil from swh.model import from_disk from swh.model.model import Content, Directory, SkippedContent _eol_style = {"native": b"\n", "CRLF": b"\r\n", "LF": b"\n", "CR": b"\r"} def _normalize_line_endings(lines, eol_style="native"): r"""Normalize line endings to unix (\\n), windows (\\r\\n) or mac (\\r). Args: lines (bytes): The lines to normalize line_ending (str): The line ending format as defined for svn:eol-style property. Acceptable values are 'native', 'CRLF', 'LF' and 'CR' Returns: bytes: lines with endings normalized """ lines = lines.replace(_eol_style["CRLF"], _eol_style["LF"]).replace( _eol_style["CR"], _eol_style["LF"] ) if _eol_style[eol_style] != _eol_style["LF"]: lines = lines.replace(_eol_style["LF"], _eol_style[eol_style]) return lines def apply_txdelta_handler(sbuf, target_stream): """Return a function that can be called repeatedly with txdelta windows. When done, closes the target_stream. Adapted from subvertpy.delta.apply_txdelta_handler to close the stream when done. Args: sbuf: Source buffer target_stream: Target stream to write to. Returns: Function to be called to apply txdelta windows """ def apply_window(window, sbuf=sbuf, target_stream=target_stream): if window is None: target_stream.close() return # Last call patch = delta.apply_txdelta_window(sbuf, window) target_stream.write(patch) return apply_window def read_svn_link(data): """Read the svn link's content. Args: data (bytes): svn link's raw content Returns: The tuple of (filetype, destination path) """ split_byte = b" " filetype, *src = data.split(split_byte) src = split_byte.join(src) return filetype, src def is_file_an_svnlink_p(fullpath): """Determine if a filepath is an svnlink or something else. Args: fullpath (str/bytes): Full path to the potential symlink to check Returns: boolean value to determine if it's indeed a symlink (as per svn) or not. """ with open(fullpath, "rb") as f: filetype, src = read_svn_link(f.read()) return filetype == b"link", src def _ra_codecs_error_handler(e): """Subvertpy may fail to decode to utf-8 the user svn properties. As they are not used by the loader, return an empty string instead of the decoded content. Args: e (UnicodeDecodeError): exception raised during the svn properties decoding. """ return "", e.end DEFAULT_FLAG = 0 EXEC_FLAG = 1 NOEXEC_FLAG = 2 SVN_PROPERTY_EOL = "svn:eol-style" # EOL state check mess EOL_STYLE = {} class FileEditor: """File Editor in charge of updating file on disk and memory objects. """ __slots__ = ["directory", "path", "fullpath", "executable", "link"] def __init__(self, directory, rootpath, path): self.directory = directory self.path = path # default value: 0, 1: set the flag, 2: remove the exec flag self.executable = DEFAULT_FLAG self.link = None self.fullpath = os.path.join(rootpath, path) def change_prop(self, key, value): if key == properties.PROP_EXECUTABLE: if value is None: # bit flip off self.executable = NOEXEC_FLAG else: self.executable = EXEC_FLAG elif key == properties.PROP_SPECIAL: # Possibly a symbolic link. We cannot check further at # that moment though, patch(s) not being applied yet self.link = True elif key == SVN_PROPERTY_EOL: # backup end of line style for file EOL_STYLE[self.fullpath] = value def __make_symlink(self, src): """Convert the svnlink to a symlink on disk. This function expects self.fullpath to be a svn link. Args: src (bytes): Path to the link's source Return: tuple: The svnlink's data tuple: - type (should be only 'link') - """ os.remove(self.fullpath) os.symlink(src=src, dst=self.fullpath) def __make_svnlink(self): """Convert the symlink to a svnlink on disk. Return: The symlink's svnlink data (``b'type '``) """ # we replace the symlink by a svnlink # to be able to patch the file on future commits src = os.readlink(self.fullpath) os.remove(self.fullpath) sbuf = b"link " + src with open(self.fullpath, "wb") as f: f.write(sbuf) return sbuf def apply_textdelta(self, base_checksum): if os.path.lexists(self.fullpath): if os.path.islink(self.fullpath): # svn does not deal with symlink so we transform into # real svn symlink for potential patching in later # commits sbuf = self.__make_svnlink() self.link = True else: with open(self.fullpath, "rb") as f: sbuf = f.read() else: sbuf = b"" t = open(self.fullpath, "wb") return apply_txdelta_handler(sbuf, target_stream=t) def close(self): """When done with the file, this is called. So the file exists and is updated, we can: - adapt accordingly its execution flag if any - compute the objects' checksums - replace the svnlink with a real symlink (for disk computation purposes) """ is_link = None if self.link: # can only check now that the link is a real one # since patch has been applied is_link, src = is_file_an_svnlink_p(self.fullpath) if is_link: self.__make_symlink(src) else: # not a real link... self.link = False if not is_link: # if a link, do nothing regarding flag if self.executable == EXEC_FLAG: os.chmod(self.fullpath, 0o755) elif self.executable == NOEXEC_FLAG: os.chmod(self.fullpath, 0o644) # And now compute file's checksums eol_style = EOL_STYLE.get(self.fullpath, None) if eol_style: # ensure to normalize line endings as defined by svn:eol-style # property to get the same file checksum as after an export # or checkout operation with subversion with open(self.fullpath, "rb") as f: data = f.read() data = _normalize_line_endings(data, eol_style) mode = os.lstat(self.fullpath).st_mode self.directory[self.path] = from_disk.Content.from_bytes( mode=mode, data=data ) else: self.directory[self.path] = from_disk.Content.from_file(path=self.fullpath) class BaseDirEditor: """Base class implementation of dir editor. see :class:`DirEditor` for an implementation that hashes every directory encountered. Instantiate a new class inheriting from this class and define the following functions:: def update_checksum(self): # Compute the checksums at current state def open_directory(self, *args): # Update an existing folder. def add_directory(self, *args): # Add a new one. """ __slots__ = ["directory", "rootpath"] def __init__(self, directory, rootpath): self.directory = directory self.rootpath = rootpath # build directory on init os.makedirs(rootpath, exist_ok=True) def remove_child(self, path): """Remove a path from the current objects. The path can be resolved as link, file or directory. This function takes also care of removing the link between the child and the parent. Args: path: to remove from the current objects. """ try: entry_removed = self.directory[path] except KeyError: entry_removed = None else: del self.directory[path] fpath = os.path.join(self.rootpath, path) if isinstance(entry_removed, Directory): shutil.rmtree(fpath) else: os.remove(fpath) if path in EOL_STYLE: del EOL_STYLE[path] def update_checksum(self): raise NotImplementedError("This should be implemented.") def open_directory(self, *args): raise NotImplementedError("This should be implemented.") def add_directory(self, *args): raise NotImplementedError("This should be implemented.") def open_file(self, *args): """Updating existing file. """ path = os.fsencode(args[0]) self.directory[path] = from_disk.Content() return FileEditor(self.directory, rootpath=self.rootpath, path=path) def add_file(self, path, copyfrom_path=None, copyfrom_rev=-1): """Creating a new file. """ path = os.fsencode(path) self.directory[path] = from_disk.Content() return FileEditor(self.directory, self.rootpath, path) def change_prop(self, key, value): """Change property callback on directory. """ if key == properties.PROP_EXTERNALS: raise ValueError("Property '%s' detected. Not implemented yet." % key) def delete_entry(self, path, revision): """Remove a path. """ self.remove_child(path.encode("utf-8")) def close(self): """Function called when we finish walking a repository. """ self.update_checksum() class DirEditor(BaseDirEditor): """Directory Editor in charge of updating directory hashes computation. This implementation includes empty folder in the hash computation. """ def update_checksum(self): """Update the root path self.path's checksums according to the children's objects. This function is expected to be called when the folder has been completely 'walked'. """ pass def open_directory(self, *args): """Updating existing directory. """ return self def add_directory(self, path, copyfrom_path=None, copyfrom_rev=-1): """Adding a new directory. """ path = os.fsencode(path) os.makedirs(os.path.join(self.rootpath, path), exist_ok=True) self.directory[path] = from_disk.Directory() return self class Editor: """Editor in charge of replaying svn events and computing objects along. This implementation accounts for empty folder during hash computations. """ def __init__(self, rootpath, directory): self.rootpath = rootpath self.directory = directory def set_target_revision(self, revnum): pass def abort(self): pass def close(self): pass def open_root(self, base_revnum): return DirEditor(self.directory, rootpath=self.rootpath) class Replay: """Replay class. """ def __init__(self, conn, rootpath, directory=None): self.conn = conn self.rootpath = rootpath if directory is None: directory = from_disk.Directory() self.directory = directory self.editor = Editor(rootpath=rootpath, directory=directory) def replay(self, rev): """Replay svn actions between rev and rev+1. This method updates in place the self.editor.directory, as well as the filesystem. Returns: The updated root directory """ codecs.register_error("strict", _ra_codecs_error_handler) self.conn.replay(rev, rev + 1, self.editor) codecs.register_error("strict", codecs.strict_errors) return self.editor.directory def compute_objects( self, rev: int ) -> Tuple[List[Content], List[SkippedContent], List[Directory]]: """Compute objects at revisions rev. Expects the state to be at previous revision's objects. Args: rev: The revision to start the replay from. Returns: The updated objects between rev and rev+1. Beware that this mutates the filesystem at rootpath accordingly. """ self.replay(rev) - # TODO: Move this listing up in swh.model - contents: List[Content] = [] - skipped_contents: List[SkippedContent] = [] - directories: List[Directory] = [] - for obj in self.directory.iter_tree(): - obj = obj.to_model() - if isinstance(obj, Content): - obj = obj.with_data() - contents.append(obj) - elif isinstance(obj, SkippedContent): - skipped_contents.append(obj) - elif isinstance(obj, Directory): - directories.append(obj) - else: - raise TypeError(f"Unexpected content type from disk: {obj}") - - return contents, skipped_contents, directories + return from_disk.iter_directory(self.directory) @click.command() @click.option("--local-url", default="/tmp", help="local svn working copy") @click.option( "--svn-url", default="file:///home/storage/svn/repos/pkg-fox", help="svn repository's url.", ) @click.option( "--revision-start", default=1, type=click.INT, help="svn repository's starting revision.", ) @click.option( "--revision-end", default=-1, type=click.INT, help="svn repository's ending revision.", ) @click.option( "--debug/--nodebug", default=True, help="Indicates if the server should run in debug mode.", ) @click.option( "--cleanup/--nocleanup", default=True, help="Indicates whether to cleanup disk when done or not.", ) def main(local_url, svn_url, revision_start, revision_end, debug, cleanup): """Script to present how to use Replay class. """ conn = RemoteAccess(svn_url.encode("utf-8"), auth=Auth([get_username_provider()])) os.makedirs(local_url, exist_ok=True) rootpath = tempfile.mkdtemp( prefix=local_url, suffix="-" + os.path.basename(svn_url) ) rootpath = os.fsencode(rootpath) # Do not go beyond the repository's latest revision revision_end_max = conn.get_latest_revnum() if revision_end == -1: revision_end = revision_end_max revision_end = min(revision_end, revision_end_max) try: replay = Replay(conn, rootpath) for rev in range(revision_start, revision_end + 1): contents, skipped_contents, directories = replay.compute_objects(rev) print( "r%s %s (%s new contents, %s new directories)" % ( rev, hashutil.hash_to_hex(replay.directory.hash), len(contents) + len(skipped_contents), len(directories), ) ) if debug: print("%s" % rootpath.decode("utf-8")) finally: if cleanup: if os.path.exists(rootpath): shutil.rmtree(rootpath) if __name__ == "__main__": main() diff --git a/swh/loader/svn/tests/conftest.py b/swh/loader/svn/tests/conftest.py index c330b11..d7f7fb8 100644 --- a/swh/loader/svn/tests/conftest.py +++ b/swh/loader/svn/tests/conftest.py @@ -1,58 +1,59 @@ -# Copyright (C) 2019 The Software Heritage developers +# Copyright (C) 2019-2020 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 import os import pytest import yaml from typing import Any, Dict from swh.scheduler.tests.conftest import swh_app # noqa +from swh.storage.tests.conftest import * # noqa @pytest.fixture -def swh_loader_config() -> Dict[str, Any]: +def swh_loader_config(swh_storage_backend_config) -> Dict[str, Any]: + swh_storage_backend_config["journal_writer"] = {} return { "storage": { "cls": "pipeline", "steps": [ - {"cls": "validate"}, {"cls": "filter"}, { "cls": "buffer", "min_batch_size": { "content": 10000, "content_bytes": 1073741824, "directory": 2500, "revision": 10, "release": 100, }, }, - {"cls": "memory"}, + swh_storage_backend_config, ], }, "check_revision": {"limit": 100, "status": False}, "debug": False, "log_db": "dbname=softwareheritage-log", "save_data": False, "save_data_path": "", "temp_directory": "/tmp", } @pytest.fixture def swh_config(swh_loader_config, monkeypatch, tmp_path): conffile = os.path.join(str(tmp_path), "loader.yml") with open(conffile, "w") as f: f.write(yaml.dump(swh_loader_config)) monkeypatch.setenv("SWH_CONFIG_FILENAME", conffile) return conffile @pytest.fixture(scope="session") def celery_includes(): return [ "swh.loader.svn.tasks", ] diff --git a/swh/loader/svn/tests/resources/httthttt.tgz b/swh/loader/svn/tests/data/httthttt.tgz similarity index 100% rename from swh/loader/svn/tests/resources/httthttt.tgz rename to swh/loader/svn/tests/data/httthttt.tgz diff --git a/swh/loader/svn/tests/resources/mediawiki-repo-r407-eol-native-crlf.tgz b/swh/loader/svn/tests/data/mediawiki-repo-r407-eol-native-crlf.tgz similarity index 100% rename from swh/loader/svn/tests/resources/mediawiki-repo-r407-eol-native-crlf.tgz rename to swh/loader/svn/tests/data/mediawiki-repo-r407-eol-native-crlf.tgz diff --git a/swh/loader/svn/tests/resources/pkg-doc-linux-r10.tgz b/swh/loader/svn/tests/data/pkg-doc-linux-r10.tgz similarity index 100% rename from swh/loader/svn/tests/resources/pkg-doc-linux-r10.tgz rename to swh/loader/svn/tests/data/pkg-doc-linux-r10.tgz diff --git a/swh/loader/svn/tests/resources/pkg-doc-linux-r11.tgz b/swh/loader/svn/tests/data/pkg-doc-linux-r11.tgz similarity index 100% rename from swh/loader/svn/tests/resources/pkg-doc-linux-r11.tgz rename to swh/loader/svn/tests/data/pkg-doc-linux-r11.tgz diff --git a/swh/loader/svn/tests/resources/pkg-doc-linux-r12.tgz b/swh/loader/svn/tests/data/pkg-doc-linux-r12.tgz similarity index 100% rename from swh/loader/svn/tests/resources/pkg-doc-linux-r12.tgz rename to swh/loader/svn/tests/data/pkg-doc-linux-r12.tgz diff --git a/swh/loader/svn/tests/resources/pkg-gourmet-with-edge-case-links-and-files.tgz b/swh/loader/svn/tests/data/pkg-gourmet-tampered-rev6-log.tgz similarity index 75% copy from swh/loader/svn/tests/resources/pkg-gourmet-with-edge-case-links-and-files.tgz copy to swh/loader/svn/tests/data/pkg-gourmet-tampered-rev6-log.tgz index 1b87c52..a29df58 100644 Binary files a/swh/loader/svn/tests/resources/pkg-gourmet-with-edge-case-links-and-files.tgz and b/swh/loader/svn/tests/data/pkg-gourmet-tampered-rev6-log.tgz differ diff --git a/swh/loader/svn/tests/resources/pkg-gourmet-with-edge-case-links-and-files.tgz b/swh/loader/svn/tests/data/pkg-gourmet-with-edge-case-links-and-files.tgz similarity index 100% rename from swh/loader/svn/tests/resources/pkg-gourmet-with-edge-case-links-and-files.tgz rename to swh/loader/svn/tests/data/pkg-gourmet-with-edge-case-links-and-files.tgz diff --git a/swh/loader/svn/tests/resources/pkg-gourmet-with-external-id.tgz b/swh/loader/svn/tests/data/pkg-gourmet-with-external-id.tgz similarity index 100% rename from swh/loader/svn/tests/resources/pkg-gourmet-with-external-id.tgz rename to swh/loader/svn/tests/data/pkg-gourmet-with-external-id.tgz diff --git a/swh/loader/svn/tests/data/pkg-gourmet-with-updates.tgz b/swh/loader/svn/tests/data/pkg-gourmet-with-updates.tgz new file mode 100644 index 0000000..18e3f33 Binary files /dev/null and b/swh/loader/svn/tests/data/pkg-gourmet-with-updates.tgz differ diff --git a/swh/loader/svn/tests/resources/pkg-gourmet-with-wrong-link-cases.tgz b/swh/loader/svn/tests/data/pkg-gourmet-with-wrong-link-cases.tgz similarity index 100% rename from swh/loader/svn/tests/resources/pkg-gourmet-with-wrong-link-cases.tgz rename to swh/loader/svn/tests/data/pkg-gourmet-with-wrong-link-cases.tgz diff --git a/swh/loader/svn/tests/data/pkg-gourmet.tgz b/swh/loader/svn/tests/data/pkg-gourmet.tgz new file mode 100644 index 0000000..57c7013 Binary files /dev/null and b/swh/loader/svn/tests/data/pkg-gourmet.tgz differ diff --git a/swh/loader/svn/tests/resources/pyang-repo-r343-eol-native-mixed-lf-crlf.tgz b/swh/loader/svn/tests/data/pyang-repo-r343-eol-native-mixed-lf-crlf.tgz similarity index 100% rename from swh/loader/svn/tests/resources/pyang-repo-r343-eol-native-mixed-lf-crlf.tgz rename to swh/loader/svn/tests/data/pyang-repo-r343-eol-native-mixed-lf-crlf.tgz diff --git a/swh/loader/svn/tests/resources/pkg-gourmet-with-updates.tgz b/swh/loader/svn/tests/resources/pkg-gourmet-with-updates.tgz deleted file mode 100644 index 6478e2b..0000000 Binary files a/swh/loader/svn/tests/resources/pkg-gourmet-with-updates.tgz and /dev/null differ diff --git a/swh/loader/svn/tests/resources/pkg-gourmet.tgz b/swh/loader/svn/tests/resources/pkg-gourmet.tgz deleted file mode 100644 index 9bf6534..0000000 Binary files a/swh/loader/svn/tests/resources/pkg-gourmet.tgz and /dev/null differ diff --git a/swh/loader/svn/tests/test_loader.py b/swh/loader/svn/tests/test_loader.py index cb38107..562e795 100644 --- a/swh/loader/svn/tests/test_loader.py +++ b/swh/loader/svn/tests/test_loader.py @@ -1,1029 +1,679 @@ # Copyright (C) 2016-2020 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 -import copy import os +import subprocess + +from typing import Optional -from swh.loader.core.tests import BaseLoaderTest from swh.loader.tests.common import assert_last_visit_matches +from swh.loader.package.tests.common import check_snapshot, get_stats from swh.loader.svn.loader import ( DEFAULT_BRANCH, SvnLoader, SvnLoaderFromRemoteDump, build_swh_snapshot, ) from swh.model import hashutil -from swh.model.model import Origin, Snapshot +from swh.model.model import Snapshot def test_build_swh_snapshot(): rev_id = hashutil.hash_to_bytes("3f51abf3b3d466571be0855dfa67e094f9ceff1b") snap = build_swh_snapshot(rev_id) assert isinstance(snap, Snapshot) expected_snapshot = Snapshot.from_dict( {"branches": {DEFAULT_BRANCH: {"target": rev_id, "target_type": "revision",}}} ) assert snap == expected_snapshot -_LOADER_TEST_CONFIG = { - "check_revision": {"limit": 100, "status": False}, - "debug": False, - "log_db": "dbname=softwareheritage-log", - "save_data": False, - "save_data_path": "", - "temp_directory": "/tmp", - "max_content_size": 100 * 1024 * 1024, - "storage": { - "cls": "pipeline", - "steps": [ - {"cls": "retry",}, - {"cls": "filter",}, - { - "cls": "buffer", - "min_batch_size": { - "content": 10000, - "content_bytes": 1073741824, - "directory": 2500, - "revision": 10, - "release": 100, - }, - }, - {"cls": "memory"}, - ], - }, -} - GOURMET_SNAPSHOT = hashutil.hash_to_bytes("889cacc2731e3312abfb2b1a0c18ade82a949e07") -GOURMET_FLAG_SNAPSHOT = hashutil.hash_to_bytes( - "0011223344556677889900112233445566778899" -) - GOURMET_UPDATES_SNAPSHOT = hashutil.hash_to_bytes( "11086d15317014e43d2438b7ffc712c44f1b8afe" ) GOURMET_EXTERNALS_SNAPSHOT = hashutil.hash_to_bytes( "19cb68d0a3f22372e2b7017ea5e2a2ea5ae3e09a" ) GOURMET_EDGE_CASES_SNAPSHOT = hashutil.hash_to_bytes( "18e60982fe521a2546ab8c3c73a535d80462d9d0" ) GOURMET_WRONG_LINKS_SNAPSHOT = hashutil.hash_to_bytes( "b17f38acabb90f066dedd30c29f01a02af88a5c4" ) MEDIAWIKI_SNAPSHOT = hashutil.hash_to_bytes("d6d6e9703f157c5702d9a4a5dec878926ed4ab76") PYANG_SNAPSHOT = hashutil.hash_to_bytes("6d9590de11b00a5801de0ff3297c5b44bbbf7d24") -class SvnLoaderTest(SvnLoader): - """An SVNLoader with no persistence. - - Context: - Load a new svn repository using the swh policy (so no update). - - """ - - def __init__( - self, - url, - last_snp_rev={}, - destination_path=None, - start_from_scratch=False, - swh_revision=None, - ): - super().__init__( - url, - destination_path=destination_path, - start_from_scratch=start_from_scratch, - swh_revision=swh_revision, - ) - self.origin = Origin(url=url) - self.last_snp_rev = last_snp_rev +def prepare_repository_from_archive( + archive_path: str, filename: Optional[str] = None, tmp_path: str = "/tmp" +) -> str: + # uncompress folder/repositories/dump for the loader to ingest + subprocess.check_output(["tar", "xf", archive_path, "-C", tmp_path]) + # build the origin url (or some derivative form) + _fname = filename if filename else os.path.basename(archive_path) + repo_url = f"file://{tmp_path}/{_fname}" + return repo_url - def parse_config_file(self, *args, **kwargs): - return _LOADER_TEST_CONFIG - def swh_latest_snapshot_revision(self, origin_url, prev_swh_revision=None): - """Avoid the storage persistence call and return the expected previous - revision for that repository. +def test_loader_svn_new_visit(swh_config, datadir, tmp_path): + """Eventful visit should yield 1 snapshot""" + archive_name = "pkg-gourmet" + archive_path = os.path.join(datadir, f"{archive_name}.tgz") + repo_url = prepare_repository_from_archive(archive_path, archive_name, tmp_path) - Check the following for explanation about the hashes: - - test_loader.org for (swh policy). - - cf. SvnLoaderTest + loader = SvnLoader(repo_url, destination_path=tmp_path) - """ - return self.last_snp_rev + assert loader.load() == {"status": "eventful"} + assert_last_visit_matches( + loader.storage, repo_url, status="full", type="svn", snapshot=GOURMET_SNAPSHOT, + ) -class BaseSvnLoaderTest(BaseLoaderTest): - """Base test loader class. + stats = get_stats(loader.storage) + assert stats == { + "content": 19, + "directory": 17, + "origin": 1, + "origin_visit": 1, + "person": 1, + "release": 0, + "revision": 6, + "skipped_content": 0, + "snapshot": 1, + } + + expected_snapshot = { + "id": GOURMET_SNAPSHOT, + "branches": { + "HEAD": { + "target": "4876cb10aec6f708f7466dddf547567b65f6c39c", + "target_type": "revision", + } + }, + } - In its setup, it's uncompressing a local svn mirror to /tmp. + check_snapshot(expected_snapshot, loader.storage) - """ - def setUp( - self, - archive_name="pkg-gourmet.tgz", - filename="pkg-gourmet", - loader=None, - snapshot=None, - type="default", - start_from_scratch=False, - swh_revision=None, - ): - super().setUp( - archive_name=archive_name, - filename=filename, - prefix_tmp_folder_name="swh.loader.svn.", - start_path=os.path.dirname(__file__), - ) - self.svn_mirror_url = self.repo_url - if type == "default": - loader_test_class = SvnLoaderTest - else: - loader_test_class = SvnLoaderTestFromRemoteDump - - if loader: - self.loader = loader - elif snapshot: - self.loader = loader_test_class( - self.svn_mirror_url, - destination_path=self.destination_path, - start_from_scratch=start_from_scratch, - swh_revision=swh_revision, - last_snp_rev=snapshot, - ) - else: - self.loader = loader_test_class( - self.svn_mirror_url, - destination_path=self.destination_path, - start_from_scratch=start_from_scratch, - swh_revision=swh_revision, - ) - self.storage = self.loader.storage - - -class SvnLoaderTest1(BaseSvnLoaderTest): - """Load an unknown svn repository results in new data. +def test_loader_svn_2_visits_no_change(swh_config, datadir, tmp_path): + """Visit multiple times a repository with no change should yield the same snapshot """ + archive_name = "pkg-gourmet" + archive_path = os.path.join(datadir, f"{archive_name}.tgz") + repo_url = prepare_repository_from_archive(archive_path, archive_name, tmp_path) - def test_load(self): - """Load a new repository results in new swh object and snapshot - - """ - # when - assert self.loader.load() == {"status": "eventful"} - # then - self.assertCountRevisions(6) - self.assertCountReleases(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.assertRevisionsContain(expected_revisions) - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "full") - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=GOURMET_SNAPSHOT, - ) - + loader = SvnLoader(repo_url) -_LAST_SNP_REV = { - "snapshot": Snapshot.from_dict({"id": GOURMET_FLAG_SNAPSHOT, "branches": {}}), - "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 SvnLoaderTest2(BaseSvnLoaderTest): - """Load a visited repository with no new change results in no data - change. + assert loader.load() == {"status": "eventful"} + visit_status1 = assert_last_visit_matches( + loader.storage, repo_url, status="full", type="svn", snapshot=GOURMET_SNAPSHOT, + ) - """ + assert loader.load() == {"status": "uneventful"} + visit_status2 = assert_last_visit_matches( + loader.storage, repo_url, status="full", type="svn", snapshot=GOURMET_SNAPSHOT, + ) - def setUp(self): - super().setUp(snapshot=_LAST_SNP_REV) + assert visit_status1.date < visit_status2.date + assert visit_status1.snapshot == visit_status2.snapshot - def test_load(self): - """Load a repository without new changes results in same snapshot + stats = get_stats(loader.storage) + assert stats["origin_visit"] == 1 + 1 # computed twice the same snapshot + assert stats["snapshot"] == 1 - """ - # when - assert self.loader.load() == {"status": "uneventful"} + # even starting from previous revision... + revs = list( + loader.storage.revision_get( + [hashutil.hash_to_bytes("95edacc8848369d6fb1608e887d6d2474fd5224f")] + ) + ) + start_revision = revs[0] + assert start_revision is not None - # then + loader = SvnLoader(repo_url, swh_revision=start_revision) + assert loader.load() == {"status": "eventful"} - self.assertCountContents(0) - self.assertCountDirectories(0) - self.assertCountRevisions(0) - self.assertCountReleases(0) - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "full") + stats = get_stats(loader.storage) + assert stats["origin_visit"] == 2 + 1 + # ... with no change in repository, this yields the same snapshot + assert stats["snapshot"] == 1 - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=GOURMET_FLAG_SNAPSHOT, - ) + assert_last_visit_matches( + loader.storage, repo_url, status="full", type="svn", snapshot=GOURMET_SNAPSHOT, + ) -class SvnLoaderTest3(BaseSvnLoaderTest): +def test_loader_tampered_repository(swh_config, datadir, tmp_path): """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. + commit log [1]. This results in a hash divergence which is + detected at startup after a new run for the same origin. In effect, that stops the loading and do nothing. + [1] Tampering with revision 6 log message following: + + ``` + tar xvf pkg-gourmet.tgz # initial repository ingested + cd pkg-gourmet/ + echo "Tampering with commit log message for fun and profit" > log.txt + svnadmin setlog . -r 6 log.txt --bypass-hooks + tar cvf pkg-gourmet-tampered-rev6-log.tgz pkg-gourmet/ + ``` """ + archive_name = "pkg-gourmet" + archive_path = os.path.join(datadir, f"{archive_name}.tgz") + repo_url = prepare_repository_from_archive(archive_path, archive_name, tmp_path) + + loader = SvnLoader(repo_url) + assert loader.load() == {"status": "eventful"} + expected_snapshot = { + "id": GOURMET_SNAPSHOT, + "branches": { + "HEAD": { + "target": "4876cb10aec6f708f7466dddf547567b65f6c39c", + "target_type": "revision", + } + }, + } + check_snapshot(expected_snapshot, loader.storage) - def setUp(self): - last_snp_rev = copy.deepcopy(_LAST_SNP_REV) - last_snp_rev["snapshot"] = None - # Changed the revision id's hash to simulate history altered - last_snp_rev["revision"]["id"] = hashutil.hash_to_bytes( - "badbadbadbadf708f7466dddf547567b65f6c39d" - ) - # the svn repository pkg-gourmet has been updated with changes - super().setUp( - archive_name="pkg-gourmet-with-updates.tgz", snapshot=last_snp_rev - ) + archive_path2 = os.path.join(datadir, "pkg-gourmet-tampered-rev6-log.tgz") + repo_tampered_url = prepare_repository_from_archive( + archive_path2, archive_name, tmp_path + ) - def test_load(self): - """Load known repository with history altered should do nothing - - """ - # when - assert self.loader.load() == {"status": "failed"} - - # then - # we got the previous run's last revision (rev 6) - # so 2 news + 1 old - self.assertCountContents(0) - self.assertCountDirectories(0) - self.assertCountRevisions(0) - self.assertCountReleases(0) - self.assertCountSnapshots(0) - self.assertEqual(self.loader.visit_status(), "partial") - - visit_status = assert_last_visit_matches( - self.storage, self.repo_url, status="partial", type="svn" - ) - assert visit_status.snapshot is None + loader2 = SvnLoader(repo_tampered_url, origin_url=repo_url) + assert loader2.load() == {"status": "failed"} + + assert_last_visit_matches( + loader2.storage, repo_url, status="partial", type="svn", snapshot=None, + ) + + stats = get_stats(loader.storage) + assert stats["origin"] == 1 + assert stats["origin_visit"] == 2 + assert stats["snapshot"] == 1 -class SvnLoaderTest4(BaseSvnLoaderTest): +def test_loader_svn_visit_with_changes(swh_config, datadir, tmp_path): """In this scenario, the repository has been updated with new changes. The loading visit should result in new objects stored and 1 new snapshot. """ + archive_name = "pkg-gourmet" + archive_path = os.path.join(datadir, f"{archive_name}.tgz") + repo_initial_url = prepare_repository_from_archive( + archive_path, archive_name, tmp_path + ) - def setUp(self): - # the svn repository pkg-gourmet has been updated with changes - super().setUp( - archive_name="pkg-gourmet-with-updates.tgz", snapshot=_LAST_SNP_REV - ) - - def test_process_repository(self): - """Process updated repository should yield new objects - - """ - # when - assert self.loader.load() == {"status": "eventful"} - - # then - # we got the previous run's last revision (rev 6) - # so 2 new - self.assertCountRevisions(5) - self.assertCountReleases(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.assertRevisionsContain(expected_revisions) - - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "full") - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=GOURMET_UPDATES_SNAPSHOT, - ) - - -class SvnLoaderTest5(BaseSvnLoaderTest): - """Context: + # repo_initial_url becomes the origin_url we want to visit some more below + loader = SvnLoader(repo_initial_url) - - Repository already injected with successful data - - New visit from scratch done with successful load + assert loader.load() == {"status": "eventful"} + visit_status1 = assert_last_visit_matches( + loader.storage, + repo_initial_url, + status="full", + type="svn", + snapshot=GOURMET_SNAPSHOT, + ) - """ + archive_path = os.path.join(datadir, "pkg-gourmet-with-updates.tgz") + repo_updated_url = prepare_repository_from_archive( + archive_path, "pkg-gourmet", tmp_path + ) - def setUp(self): - # the svn repository pkg-gourmet has been updated with changes - super().setUp( - archive_name="pkg-gourmet-with-updates.tgz", - snapshot=_LAST_SNP_REV, - start_from_scratch=True, - ) + loader = SvnLoader(repo_updated_url, origin_url=repo_initial_url,) - def test_load(self): - """Load an existing repository from scratch yields same swh objects - - """ - # when - assert self.loader.load() == {"status": "eventful"} - - # 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.assertCountRevisions(11) - self.assertCountReleases(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.assertRevisionsContain(expected_revisions) - - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "full") - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=GOURMET_UPDATES_SNAPSHOT, - ) + assert loader.load() == {"status": "eventful"} + visit_status2 = assert_last_visit_matches( + loader.storage, + repo_updated_url, + status="full", + type="svn", + snapshot=GOURMET_UPDATES_SNAPSHOT, + ) + assert visit_status1.date < visit_status2.date + assert visit_status1.snapshot != visit_status2.snapshot + + stats = get_stats(loader.storage) + assert stats == { + "content": 22, + "directory": 28, + "origin": 1, + "origin_visit": 2, + "person": 2, + "release": 0, + "revision": 11, + "skipped_content": 0, + "snapshot": 2, + } + + expected_snapshot = { + "id": GOURMET_UPDATES_SNAPSHOT, + "branches": { + "HEAD": { + "target": "171dc35522bfd17dda4e90a542a0377fb2fc707a", + "target_type": "revision", + } + }, + } -class SvnLoaderTest6(BaseSvnLoaderTest): - """Context: - - repository already visited with load successful - - Changes on existing repository - - New Visit done with successful new data + check_snapshot(expected_snapshot, loader.storage) - """ + # Start from scratch loading yields the same result - def setUp(self): - last_snp_rev = { - "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"], - ] - }, - }, - } - super().setUp( - archive_name="pkg-gourmet-with-updates.tgz", snapshot=last_snp_rev - ) + loader = SvnLoader( + repo_updated_url, origin_url=repo_initial_url, start_from_scratch=True + ) + assert loader.load() == {"status": "eventful"} + visit_status3 = assert_last_visit_matches( + loader.storage, + repo_updated_url, + status="full", + type="svn", + snapshot=GOURMET_UPDATES_SNAPSHOT, + ) + assert visit_status2.date < visit_status3.date + assert visit_status3.snapshot == visit_status2.snapshot + check_snapshot(expected_snapshot, loader.storage) - def test_load(self): - """Load from partial previous visit result in new changes - - """ - # when - assert self.loader.load() == {"status": "eventful"} - - # then - # we got the previous run's last revision (rev 6) - # so 2 new - self.assertCountRevisions(5) - self.assertCountReleases(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.assertRevisionsContain(expected_revisions) - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "full") - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=GOURMET_UPDATES_SNAPSHOT, - ) + stats = get_stats(loader.storage) + assert stats["origin"] == 1 # always the same visit + assert stats["origin_visit"] == 2 + 1 # 1 more visit + assert stats["snapshot"] == 2 # no new snapshot -class SvnLoaderTest7(BaseSvnLoaderTest): - """Context: - - repository already visited with load successful - - Changes on existing repository - - New Visit done with successful new data +def test_loader_svn_visit_start_from_revision(swh_config, datadir, tmp_path): + """Starting from existing revision, next visit on changed repo should yield 1 new + snapshot. """ + archive_name = "pkg-gourmet" + archive_path = os.path.join(datadir, f"{archive_name}.tgz") + repo_initial_url = prepare_repository_from_archive( + archive_path, archive_name, tmp_path + ) - def setUp(self): - 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"], - ] - }, - } - super().setUp( - archive_name="pkg-gourmet-with-updates.tgz", - snapshot=_LAST_SNP_REV, - swh_revision=previous_unfinished_revision, - ) + # repo_initial_url becomes the origin_url we want to visit some more below + loader = SvnLoader(repo_initial_url) - def test_load(self): - """Load known and partial repository should start from last visit - - """ - - # when - assert self.loader.load() == {"status": "eventful"} - - # then - # we got the previous run's last revision (rev 6) - # so 2 new - self.assertCountRevisions(5) - self.assertCountReleases(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.assertRevisionsContain(expected_revisions) - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "full") - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=GOURMET_UPDATES_SNAPSHOT, + assert loader.load() == {"status": "eventful"} + visit_status1 = assert_last_visit_matches( + loader.storage, + repo_initial_url, + status="full", + type="svn", + snapshot=GOURMET_SNAPSHOT, + ) + + revs = list( + loader.storage.revision_get( + [hashutil.hash_to_bytes("95edacc8848369d6fb1608e887d6d2474fd5224f")] ) + ) + start_revision = revs[0] + assert start_revision is not None + archive_path = os.path.join(datadir, "pkg-gourmet-with-updates.tgz") + repo_updated_url = prepare_repository_from_archive( + archive_path, "pkg-gourmet", tmp_path + ) -class SvnLoaderTest8(BaseSvnLoaderTest): - """Context: + # we'll start from start_revision + loader = SvnLoader( + repo_updated_url, origin_url=repo_initial_url, swh_revision=start_revision + ) - - Previous visit on existing repository done - - Starting the loading from the last unfinished visit - - New objects are created (1 new snapshot) + assert loader.load() == {"status": "eventful"} - """ + # nonetheless, we obtain the same snapshot (as previous tests on that repository) + visit_status2 = assert_last_visit_matches( + loader.storage, + repo_updated_url, + status="full", + type="svn", + snapshot=GOURMET_UPDATES_SNAPSHOT, + ) - def setUp(self): - last_snp_rev = { - "snapshot": None, - "revision": { - "id": hashutil.hash_to_bytes( - "a3a577948fdbda9d1061913b77a1588695eadb41" - ), - "parents": ( - hashutil.hash_to_bytes("3f51abf3b3d466571be0855dfa67e094f9ceff1b"), - ), - "directory": hashutil.hash_to_bytes( - "7dc52cc04c3b8bd7c085900d60c159f7b846f866" - ), + assert visit_status1.date < visit_status2.date + assert visit_status1.snapshot != visit_status2.snapshot + + stats = get_stats(loader.storage) + assert stats == { + "content": 22, + "directory": 28, + "origin": 1, + "origin_visit": 2, + "person": 2, + "release": 0, + "revision": 11, + "skipped_content": 0, + "snapshot": 2, + } + + expected_snapshot = { + "id": GOURMET_UPDATES_SNAPSHOT, + "branches": { + "HEAD": { + "target": "171dc35522bfd17dda4e90a542a0377fb2fc707a", "target_type": "revision", - "metadata": { - "extra_headers": [ - ["svn_repo_uuid", "3187e211-bb14-4c82-9596-0b59d67cd7f4"], - ["svn_revision", "5"], - ] - }, - }, - } - 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"], - ] - }, - } - super().setUp( - archive_name="pkg-gourmet-with-updates.tgz", - snapshot=last_snp_rev, - swh_revision=previous_unfinished_revision, - ) + } + }, + } - def test_load(self): - """Load repository should yield revisions starting from last visit - - """ - # when - assert self.loader.load() == {"status": "eventful"} - - # then - # we got the previous run's last revision (rev 6) - # so 2 new - self.assertCountRevisions(5) - self.assertCountReleases(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.assertRevisionsContain(expected_revisions) - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "full") - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=GOURMET_UPDATES_SNAPSHOT, - ) + check_snapshot(expected_snapshot, loader.storage) -class SvnLoaderTest9(BaseSvnLoaderTest): +def test_loader_svn_visit_with_eol_style(swh_config, datadir, tmp_path): """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. """ + archive_name = "mediawiki-repo-r407-eol-native-crlf" + archive_path = os.path.join(datadir, f"{archive_name}.tgz") + repo_url = prepare_repository_from_archive(archive_path, archive_name, tmp_path) + + loader = SvnLoader(repo_url) + + assert loader.load() == {"status": "eventful"} + expected_snapshot = { + "id": MEDIAWIKI_SNAPSHOT, + "branches": { + "HEAD": { + "target": "7da4975c363101b819756d33459f30a866d01b1b", + "target_type": "revision", + } + }, + } + check_snapshot(expected_snapshot, loader.storage) + + assert_last_visit_matches( + loader.storage, + repo_url, + status="full", + type="svn", + snapshot=MEDIAWIKI_SNAPSHOT, + ) - def setUp(self): - super().setUp( - archive_name="mediawiki-repo-r407-eol-native-crlf.tgz", - filename="mediawiki-repo-r407-eol-native-crlf", - ) - - def test_process_repository(self): - """Load repository with CRLF endings (svn:eol-style: native) is ok - - """ - # when - assert self.loader.load() == {"status": "eventful"} - - expected_revisions = { - "7da4975c363101b819756d33459f30a866d01b1b": "f63637223ee0f7d4951ffd2d4d9547a4882c5d8b" # noqa - } - self.assertRevisionsContain(expected_revisions) - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "full") - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=MEDIAWIKI_SNAPSHOT, - ) + stats = get_stats(loader.storage) + assert stats["origin"] == 1 + assert stats["origin_visit"] == 1 + assert stats["snapshot"] == 1 -class SvnLoaderTest10(BaseSvnLoaderTest): # noqa +def test_loader_svn_visit_with_mixed_crlf_lf(swh_config, datadir, tmp_path): """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. """ + archive_name = "pyang-repo-r343-eol-native-mixed-lf-crlf" + archive_path = os.path.join(datadir, f"{archive_name}.tgz") + repo_url = prepare_repository_from_archive(archive_path, archive_name, tmp_path) + + loader = SvnLoader(repo_url) + + assert loader.load() == {"status": "eventful"} + expected_snapshot = { + "id": PYANG_SNAPSHOT, + "branches": { + "HEAD": { + "target": "9c6962eeb9164a636c374be700672355e34a98a7", + "target_type": "revision", + } + }, + } + check_snapshot(expected_snapshot, loader.storage) - def setUp(self): - super().setUp( - archive_name="pyang-repo-r343-eol-native-mixed-lf-crlf.tgz", - filename="pyang-repo-r343-eol-native-mixed-lf-crlf", - ) - - def test_load(self): - """Load repo with mixed CRLF/LF endings (svn:eol-style:native) is ok - - """ - assert self.loader.load() == {"status": "eventful"} - - expected_revisions = { - "9c6962eeb9164a636c374be700672355e34a98a7": "16aa6b6271f3456d4643999d234cf39fe3d0cc5a" # noqa - } - - self.assertRevisionsContain(expected_revisions) - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "full") - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=PYANG_SNAPSHOT, - ) + assert_last_visit_matches( + loader.storage, repo_url, status="full", type="svn", snapshot=PYANG_SNAPSHOT, + ) + stats = get_stats(loader.storage) + assert stats["origin"] == 1 + assert stats["origin_visit"] == 1 + assert stats["snapshot"] == 1 -class SvnLoaderTest11(BaseSvnLoaderTest): - """Context: - - Repository with svn:external (which is not deal with for now) - - Visit is partial with as much data loaded as possible +def test_loader_svn_with_external_properties(swh_config, datadir, tmp_path): + """Repository with svn:external properties cannot be fully ingested yet """ + archive_name = "pkg-gourmet" + archive_path = os.path.join(datadir, "pkg-gourmet-with-external-id.tgz") + repo_url = prepare_repository_from_archive(archive_path, archive_name, tmp_path) + + loader = SvnLoader(repo_url) + + assert loader.load() == {"status": "eventful"} + # repositoy holds 21 revisions, but the last commit holds an 'svn:externals' + # property which will make the loader-svn stops at the last revision prior to the + # bad one + expected_snapshot = { + "id": GOURMET_EXTERNALS_SNAPSHOT, + "branches": { + "HEAD": { + "target": "82a7a4a09f9549223429143ba36ad77375e33c5c", + "target_type": "revision", + } + }, + } + check_snapshot(expected_snapshot, loader.storage) + + assert_last_visit_matches( + loader.storage, + repo_url, + status="partial", + type="svn", + snapshot=GOURMET_EXTERNALS_SNAPSHOT, + ) - def setUp(self): - previous_unfinished_revision = None - super().setUp( - archive_name="pkg-gourmet-with-external-id.tgz", - swh_revision=previous_unfinished_revision, - ) + stats = get_stats(loader.storage) + assert stats["origin"] == 1 + assert stats["origin_visit"] == 1 + assert stats["snapshot"] == 1 + assert stats["revision"] == 21 - 1 # commit with the svn:external property - def test_load(self): - """Repository with svn:externals property, will stop raising an error - - """ - - # when - assert self.loader.load() == {"status": "eventful"} - - # then repositories holds 21 revisions, but the last commit - # one holds an 'svn:externals' property which will make the - # loader-svn stops at the last revision prior to the bad one - self.assertCountRevisions(20) - self.assertCountReleases(0) - - 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 - "ffa901b69ca0f46a2261f42948838d19709cb9f8": "c3c98df624733fef4e592bef983f93e2ed02b179", # noqa - "0148ae3eaa520b73a50802c59f3f416b7a36cf8c": "844d4646d6c2b4f3a3b2b22ab0ee38c7df07bab2", # noqa - last_revision: "0de6e75d2b79ec90d00a3a7611aa3861b2e4aa5e", # noqa - } - - # The last revision being the one used later to start back from - self.assertRevisionsContain(expected_revisions) - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "partial") - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="partial", - type="svn", - snapshot=GOURMET_EXTERNALS_SNAPSHOT, - ) +def test_loader_svn_with_symlink(swh_config, datadir, tmp_path): + """Repository with symlinks should be ingested ok -class SvnLoaderTest12(BaseSvnLoaderTest): - """Edge cases: + Edge case: - 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) """ + archive_name = "pkg-gourmet" + archive_path = os.path.join( + datadir, "pkg-gourmet-with-edge-case-links-and-files.tgz" + ) + repo_url = prepare_repository_from_archive(archive_path, archive_name, tmp_path) - def setUp(self): - previous_unfinished_revision = None - super().setUp( - archive_name="pkg-gourmet-with-edge-case-links-and-files.tgz", - swh_revision=previous_unfinished_revision, - ) - - def test_load(self): - """File/Link removed prior to folder with same name creation is ok - - """ - - # when - assert self.loader.load() == {"status": "eventful"} - - # then repositories holds 14 revisions, but the last commit - self.assertCountRevisions(19) - self.assertCountReleases(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.assertRevisionsContain(expected_revisions) - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "full") - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=GOURMET_EDGE_CASES_SNAPSHOT, - ) - - -class SvnLoaderTest13(BaseSvnLoaderTest): - """Edge cases: - - wrong symbolic link - - wrong symbolic link with empty space names + loader = SvnLoader(repo_url) - """ + assert loader.load() == {"status": "eventful"} + expected_snapshot = { + "id": GOURMET_EDGE_CASES_SNAPSHOT, + "branches": { + "HEAD": { + "target": "3f43af2578fccf18b0d4198e48563da7929dc608", + "target_type": "revision", + } + }, + } + check_snapshot(expected_snapshot, loader.storage) + + assert_last_visit_matches( + loader.storage, + repo_url, + status="full", + type="svn", + snapshot=GOURMET_EDGE_CASES_SNAPSHOT, + ) - def setUp(self): - super().setUp(archive_name="pkg-gourmet-with-wrong-link-cases.tgz") - - def test_load(self): - """Wrong link or empty space-named link should be ok - - """ - # when - assert self.loader.load() == {"status": "eventful"} - - # then repositories holds 14 revisions, but the last commit - self.assertCountRevisions(21) - self.assertCountReleases(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.assertRevisionsContain(expected_revisions) - self.assertCountSnapshots(1) - self.assertEqual(self.loader.visit_status(), "full") - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=GOURMET_WRONG_LINKS_SNAPSHOT, - ) + stats = get_stats(loader.storage) + assert stats["origin"] == 1 + assert stats["origin_visit"] == 1 + assert stats["snapshot"] == 1 + assert stats["revision"] == 19 -class SvnLoaderTestFromRemoteDump(SvnLoaderTest, SvnLoaderFromRemoteDump): - pass +def test_loader_svn_with_wrong_symlinks(swh_config, datadir, tmp_path): + """Repository with wrong symlinks should be ingested ok nonetheless + Edge case: + - wrong symbolic link + - wrong symbolic link with empty space names -class SvnLoaderFromRemoteDumpTest(BaseSvnLoaderTest): - """ - Check that the results obtained with the remote svn dump loader - and the base svn loader are the same. """ + archive_name = "pkg-gourmet" + archive_path = os.path.join(datadir, "pkg-gourmet-with-wrong-link-cases.tgz") + repo_url = prepare_repository_from_archive(archive_path, archive_name, tmp_path) + + loader = SvnLoader(repo_url) + + assert loader.load() == {"status": "eventful"} + expected_snapshot = { + "id": GOURMET_WRONG_LINKS_SNAPSHOT, + "branches": { + "HEAD": { + "target": "cf30d3bb9d5967d0a2bbeacc405f10a5dd9b138a", + "target_type": "revision", + } + }, + } + check_snapshot(expected_snapshot, loader.storage) + + assert_last_visit_matches( + loader.storage, + repo_url, + status="full", + type="svn", + snapshot=GOURMET_WRONG_LINKS_SNAPSHOT, + ) - def setUp(self): - _LOADER_TEST_CONFIG["debug"] = True # to avoid cleanup in between load - super().setUp(archive_name="pkg-gourmet.tgz", type="remote") - - def test_load(self): - """ - Compare results of remote dump loader and base loader - """ - dump_loader = self.loader - dump_loader.load() - - self.assertCountContents(19) - self.assertCountDirectories(17) - self.assertCountRevisions(6) - self.assertCountSnapshots(1) - - base_loader = SvnLoaderTest(self.svn_mirror_url) - base_loader.load() - - dump_storage_stat = dump_loader.storage.stat_counters() - base_storage_stat = base_loader.storage.stat_counters() - self.assertEqual(dump_storage_stat, base_storage_stat) - - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=GOURMET_SNAPSHOT, - ) + stats = get_stats(loader.storage) + assert stats["origin"] == 1 + assert stats["origin_visit"] == 1 + assert stats["snapshot"] == 1 + assert stats["revision"] == 21 - assert_last_visit_matches( - base_loader.storage, - self.repo_url, - status="full", - type="svn", - snapshot=GOURMET_SNAPSHOT, - ) +def test_loader_svn_loader_from_dump_archive(swh_config, datadir, tmp_path): + """Repository with wrong symlinks should be ingested ok nonetheless -class SvnLoaderTest14(BaseSvnLoaderTest): - """Edge cases: The repository held some user defined svn-properties - with special encodings, this prevented the repository from - being loaded even though we do not ingest those information. + Edge case: + - wrong symbolic link + - wrong symbolic link with empty space names """ + archive_name = "pkg-gourmet" + archive_path = os.path.join(datadir, f"{archive_name}.tgz") + repo_url = prepare_repository_from_archive(archive_path, archive_name, tmp_path) + + loaderFromDump = SvnLoaderFromRemoteDump(repo_url) + assert loaderFromDump.load() == {"status": "eventful"} + assert_last_visit_matches( + loaderFromDump.storage, + repo_url, + status="full", + type="svn", + snapshot=GOURMET_SNAPSHOT, + ) - def setUp(self): - super().setUp(archive_name="httthttt.tgz", filename="httthttt") - - def test_load(self): - """Decoding user defined svn properties error should not fail loading - - """ - # when - assert self.loader.load() == {"status": "eventful"} + origin_url = repo_url + "2" # rename to another origin + loader = SvnLoader(repo_url, origin_url=origin_url) + assert loader.load() == {"status": "eventful"} # because are working on new origin + assert_last_visit_matches( + loader.storage, origin_url, status="full", type="svn", snapshot=GOURMET_SNAPSHOT + ) - self.assertCountRevisions(7, "7 svn commits") - self.assertCountReleases(0) + expected_snapshot = { + "id": GOURMET_SNAPSHOT, + "branches": { + "HEAD": { + "target": "4876cb10aec6f708f7466dddf547567b65f6c39c", + "target_type": "revision", + } + }, + } + check_snapshot(expected_snapshot, loader.storage) + + stats = get_stats(loader.storage) + assert stats["origin"] == 2 # created one more origin + assert stats["origin_visit"] == 2 + assert stats["snapshot"] == 1 + + loader = SvnLoader(repo_url) # no change on the origin-url + assert loader.load() == {"status": "uneventful"} + assert_last_visit_matches( + loader.storage, origin_url, status="full", type="svn", snapshot=GOURMET_SNAPSHOT + ) - last_revision = "604a17dbb15e8d7ecb3e9f3768d09bf493667a93" + stats = get_stats(loader.storage) + assert stats["origin"] == 2 + assert stats["origin_visit"] == 3 + assert stats["snapshot"] == 1 - expected_revisions = { - "e6ae8487c6d14df9e6cb7196c6aac045798fd5be": "75ed58f260bfa4102d0e09657803511f5f0ab372", # noqa - "e1e3314e0e9c9d17e6a3f60d6662f48f0e3c2fa3": "7bfb95cef68c1affe8d7f786353213d92abbb2b7", # noqa - "1632fd38a8653e9b607c00feb93a41faddfb544c": "cd6de65c84d9405e7ca45fead02aa10162e30727", # noqa - "0ad1ebbb92d00721644b0a46d6322d18dbcba848": "cd6de65c84d9405e7ca45fead02aa10162e30727", # noqa - "94b87c97697d178a9311b018daa5179f7d4ba31e": "c2128108adecb59a0144339c2e701cd8118cff5a", # noqa - "bd741cf22f0642d88cd0d8b545e8896b898c692d": "c2128108adecb59a0144339c2e701cd8118cff5a", # noqa - last_revision: "f051d60256b2d89a0ca2704d6f91ad1b0ab44e02", - } - self.assertRevisionsContain(expected_revisions) +def test_loader_user_defined_svn_properties(swh_config, datadir, tmp_path): + """Edge cases: The repository held some user defined svn-properties with special + encodings, this prevented the repository from being loaded even though we do not + ingest those information. - expected_snapshot_id = "70487267f682c07e52a2371061369b6cf5bffa47" - expected_branches = { - "HEAD": {"target": last_revision, "target_type": "revision"} - } + """ + archive_name = "httthttt" + archive_path = os.path.join(datadir, f"{archive_name}.tgz") + repo_url = prepare_repository_from_archive(archive_path, archive_name, tmp_path) - self.assertSnapshotEqual(expected_snapshot_id, expected_branches) + loader = SvnLoader(repo_url) - self.assertEqual(self.loader.visit_status(), "full") + assert loader.load() == {"status": "eventful"} + expected_snapshot_id = hashutil.hash_to_bytes( + "70487267f682c07e52a2371061369b6cf5bffa47" + ) + expected_snapshot = { + "id": expected_snapshot_id, + "branches": { + "HEAD": { + "target": "604a17dbb15e8d7ecb3e9f3768d09bf493667a93", + "target_type": "revision", + } + }, + } + check_snapshot(expected_snapshot, loader.storage) + + assert_last_visit_matches( + loader.storage, + repo_url, + status="full", + type="svn", + snapshot=expected_snapshot_id, + ) - assert_last_visit_matches( - self.storage, - self.repo_url, - status="full", - type="svn", - snapshot=hashutil.hash_to_bytes(expected_snapshot_id), - ) + stats = get_stats(loader.storage) + assert stats["origin"] == 1 + assert stats["origin_visit"] == 1 + assert stats["snapshot"] == 1 + assert stats["revision"] == 7 diff --git a/version.txt b/version.txt index d14052d..db6b456 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -v0.2.0-0-g782690b \ No newline at end of file +v0.2.1-0-ga9ae83b \ No newline at end of file