diff --git a/swh/loader/cli.py b/swh/loader/cli.py index 53c4a11..479aa33 100644 --- a/swh/loader/cli.py +++ b/swh/loader/cli.py @@ -1,134 +1,135 @@ # Copyright (C) 2019-2021 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 # WARNING: do not import unnecessary things here to keep cli startup time under # control import logging from typing import Any import click import pkg_resources from swh.core.cli import CONTEXT_SETTINGS from swh.core.cli import swh as swh_cli_group logger = logging.getLogger(__name__) LOADERS = { entry_point.name.split(".", 1)[1]: entry_point for entry_point in pkg_resources.iter_entry_points("swh.workers") if entry_point.name.split(".", 1)[0] == "loader" } SUPPORTED_LOADERS = sorted(list(LOADERS)) def get_loader(name: str, **kwargs) -> Any: """Given a loader name, instantiate it. Args: name: Loader's name kwargs: Configuration dict (url...) Returns: An instantiated loader """ if name not in LOADERS: raise ValueError( "Invalid loader %s: only supported loaders are %s" % (name, SUPPORTED_LOADERS) ) registry_entry = LOADERS[name].load()() logger.debug(f"registry: {registry_entry}") loader_cls = registry_entry["loader"] logger.debug(f"loader class: {loader_cls}") return loader_cls.from_config(**kwargs) @swh_cli_group.group(name="loader", context_settings=CONTEXT_SETTINGS) @click.option( "--config-file", "-C", default=None, - type=click.Path(exists=True, dir_okay=False,), + type=click.Path( + exists=True, + dir_okay=False, + ), help="Configuration file.", ) @click.pass_context def loader(ctx, config_file): - """Loader cli tools - - """ + """Loader cli tools""" from os import environ from swh.core.config import read ctx.ensure_object(dict) logger.debug("ctx: %s", ctx) if not config_file: config_file = environ.get("SWH_CONFIG_FILENAME") ctx.obj["config"] = read(config_file) logger.debug("config_file: %s", config_file) logger.debug("config: ", ctx.obj["config"]) @loader.command(name="run", context_settings=CONTEXT_SETTINGS) @click.argument("type", type=click.Choice(SUPPORTED_LOADERS)) @click.argument("url") @click.argument("options", nargs=-1) @click.pass_context def run(ctx, type, url, options): """Ingest with loader the origin located at """ import iso8601 from swh.scheduler.cli.utils import parse_options conf = ctx.obj.get("config", {}) if "storage" not in conf: raise ValueError("Missing storage configuration key") (_, kw) = parse_options(options) logger.debug(f"kw: {kw}") visit_date = kw.get("visit_date") if visit_date and isinstance(visit_date, str): visit_date = iso8601.parse_date(visit_date) kw["visit_date"] = visit_date loader = get_loader(type, url=url, storage=conf["storage"], **kw) result = loader.load() msg = f"{result} for origin '{url}'" directory = kw.get("directory") if directory: msg = msg + f" and directory '{directory}'" click.echo(msg) @loader.command(name="list", context_settings=CONTEXT_SETTINGS) @click.argument("type", default="all", type=click.Choice(["all"] + SUPPORTED_LOADERS)) @click.pass_context def list(ctx, type): """List supported loaders and optionally their arguments""" import inspect if type == "all": loaders = ", ".join(SUPPORTED_LOADERS) click.echo(f"Supported loaders: {loaders}") else: registry_entry = LOADERS[type].load()() loader_cls = registry_entry["loader"] doc = inspect.getdoc(loader_cls).strip() # Hack to get the signature of the class even though it subclasses # Generic, which reimplements __new__. # See signature = inspect.signature(loader_cls.__init__) signature_str = str(signature).replace("self, ", "") click.echo(f"Loader: {doc}\nsignature: {signature_str}") diff --git a/swh/loader/core/loader.py b/swh/loader/core/loader.py index 4763817..2e77fba 100644 --- a/swh/loader/core/loader.py +++ b/swh/loader/core/loader.py @@ -1,468 +1,462 @@ # Copyright (C) 2015-2021 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 datetime import hashlib import logging import os from typing import Any, Dict, Iterable, Optional from swh.core.config import load_from_envvar from swh.loader.exception import NotFound from swh.model.model import ( BaseContent, Content, Directory, Origin, OriginVisit, OriginVisitStatus, Release, Revision, Sha1Git, SkippedContent, Snapshot, ) from swh.storage import get_storage from swh.storage.interface import StorageInterface from swh.storage.utils import now DEFAULT_CONFIG: Dict[str, Any] = { "max_content_size": 100 * 1024 * 1024, } class BaseLoader: """Base class for (D)VCS loaders (e.g Svn, Git, Mercurial, ...) or PackageLoader (e.g PyPI, Npm, CRAN, ...) A loader retrieves origin information (git/mercurial/svn repositories, pypi/npm/... package artifacts), ingests the contents/directories/revisions/releases/snapshot read from those artifacts and send them to the archive through the storage backend. The main entry point for the loader is the :func:`load` function. 2 static methods (:func:`from_config`, :func:`from_configfile`) centralizes and eases the loader instantiation from either configuration dict or configuration file. Some class examples: - :class:`SvnLoader` - :class:`GitLoader` - :class:`PyPILoader` - :class:`NpmLoader` """ visit_date: Optional[datetime.datetime] origin: Optional[Origin] origin_metadata: Dict[str, Any] loaded_snapshot_id: Optional[Sha1Git] def __init__( self, storage: StorageInterface, logging_class: Optional[str] = None, save_data_path: Optional[str] = None, max_content_size: Optional[int] = None, ): super().__init__() self.storage = storage self.max_content_size = int(max_content_size) if max_content_size else None if logging_class is None: logging_class = "%s.%s" % ( self.__class__.__module__, self.__class__.__name__, ) self.log = logging.getLogger(logging_class) _log = logging.getLogger("requests.packages.urllib3.connectionpool") _log.setLevel(logging.WARN) # possibly overridden in self.prepare method self.visit_date = None self.origin = None if not hasattr(self, "visit_type"): self.visit_type: Optional[str] = None self.origin_metadata = {} self.loaded_snapshot_id = None if save_data_path: path = save_data_path os.stat(path) if not os.access(path, os.R_OK | os.W_OK): raise PermissionError("Permission denied: %r" % path) self.save_data_path = save_data_path @classmethod def from_config(cls, storage: Dict[str, Any], **config: Any): """Instantiate a loader from a configuration dict. This is basically a backwards-compatibility shim for the CLI. Args: storage: instantiation config for the storage config: the configuration dict for the loader, with the following keys: - credentials (optional): credentials list for the scheduler - any other kwargs passed to the loader. Returns: the instantiated loader """ # Drop the legacy config keys which aren't used for this generation of loader. for legacy_key in ("storage", "celery"): config.pop(legacy_key, None) # Instantiate the storage storage_instance = get_storage(**storage) return cls(storage=storage_instance, **config) @classmethod def from_configfile(cls, **kwargs: Any): """Instantiate a loader from the configuration loaded from the SWH_CONFIG_FILENAME envvar, with potential extra keyword arguments if their value is not None. Args: kwargs: kwargs passed to the loader instantiation """ config = dict(load_from_envvar(DEFAULT_CONFIG)) config.update({k: v for k, v in kwargs.items() if v is not None}) return cls.from_config(**config) def save_data(self) -> None: """Save the data associated to the current load""" raise NotImplementedError def get_save_data_path(self) -> str: """The path to which we archive the loader's raw data""" if not hasattr(self, "__save_data_path"): year = str(self.visit_date.year) # type: ignore assert self.origin url = self.origin.url.encode("utf-8") origin_url_hash = hashlib.sha1(url).hexdigest() path = "%s/sha1:%s/%s/%s" % ( self.save_data_path, origin_url_hash[0:2], origin_url_hash, year, ) os.makedirs(path, exist_ok=True) self.__save_data_path = path return self.__save_data_path def flush(self) -> None: - """Flush any potential buffered data not sent to swh-storage. - - """ + """Flush any potential buffered data not sent to swh-storage.""" self.storage.flush() def cleanup(self) -> None: - """Last step executed by the loader. - - """ + """Last step executed by the loader.""" raise NotImplementedError def prepare_origin_visit(self) -> None: """First step executed by the loader to prepare origin and visit - references. Set/update self.origin, and - optionally self.origin_url, self.visit_date. + references. Set/update self.origin, and + optionally self.origin_url, self.visit_date. """ raise NotImplementedError def _store_origin_visit(self) -> None: - """Store origin and visit references. Sets the self.visit references. - - """ + """Store origin and visit references. Sets the self.visit references.""" assert self.origin self.storage.origin_add([self.origin]) if not self.visit_date: # now as default visit_date if not provided self.visit_date = datetime.datetime.now(tz=datetime.timezone.utc) assert isinstance(self.visit_date, datetime.datetime) assert isinstance(self.visit_type, str) self.visit = list( self.storage.origin_visit_add( [ OriginVisit( origin=self.origin.url, date=self.visit_date, type=self.visit_type, ) ] ) )[0] def prepare(self) -> None: """Second step executed by the loader to prepare some state needed by the loader. Raises NotFound exception if the origin to ingest is not found. """ raise NotImplementedError def get_origin(self) -> Origin: """Get the origin that is currently being loaded. self.origin should be set in :func:`prepare_origin` Returns: dict: an origin ready to be sent to storage by :func:`origin_add`. """ assert self.origin return self.origin def fetch_data(self) -> bool: """Fetch the data from the source the loader is currently loading (ex: git/hg/svn/... repository). Returns: a value that is interpreted as a boolean. If True, fetch_data needs to be called again to complete loading. """ raise NotImplementedError def store_data(self): """Store fetched data in the database. Should call the :func:`maybe_load_xyz` methods, which handle the bundles sent to storage, rather than send directly. """ raise NotImplementedError def store_metadata(self) -> None: """Store fetched metadata in the database. For more information, see implementation in :class:`DepositLoader`. """ pass def load_status(self) -> Dict[str, str]: """Detailed loading status. Defaults to logging an eventful load. Returns: a dictionary that is eventually passed back as the task's result to the scheduler, allowing tuning of the task recurrence mechanism. """ return { "status": "eventful", } def post_load(self, success: bool = True) -> None: """Permit the loader to do some additional actions according to status after the loading is done. The flag success indicates the loading's status. Defaults to doing nothing. This is up to the implementer of this method to make sure this does not break. Args: success (bool): the success status of the loading """ pass def visit_status(self) -> str: """Detailed visit status. Defaults to logging a full visit. """ return "full" def pre_cleanup(self) -> None: """As a first step, will try and check for dangling data to cleanup. This should do its best to avoid raising issues. """ pass def load(self) -> Dict[str, str]: r"""Loading logic for the loader to follow: - 1. Call :meth:`prepare_origin_visit` to prepare the origin and visit we will associate loading data to - 2. Store the actual ``origin_visit`` to storage - 3. Call :meth:`prepare` to prepare any eventual state - 4. Call :meth:`get_origin` to get the origin we work with and store - while True: - 5. Call :meth:`fetch_data` to fetch the data to store - 6. Call :meth:`store_data` to store the data - 7. Call :meth:`cleanup` to clean up any eventual state put in place in :meth:`prepare` method. """ try: self.pre_cleanup() except Exception: msg = "Cleaning up dangling data failed! Continue loading." self.log.warning(msg) self.prepare_origin_visit() self._store_origin_visit() assert ( self.origin ), "The method `prepare_origin_visit` call should set the origin (Origin)" assert ( self.visit.visit ), "The method `_store_origin_visit` should set the visit (OriginVisit)" self.log.info( "Load origin '%s' with type '%s'", self.origin.url, self.visit.type ) try: self.prepare() while True: more_data_to_fetch = self.fetch_data() self.store_data() if not more_data_to_fetch: break self.store_metadata() visit_status = OriginVisitStatus( origin=self.origin.url, visit=self.visit.visit, type=self.visit_type, date=now(), status=self.visit_status(), snapshot=self.loaded_snapshot_id, ) self.storage.origin_visit_status_add([visit_status]) self.post_load() except Exception as e: if isinstance(e, NotFound): status = "not_found" task_status = "uneventful" else: status = "partial" if self.loaded_snapshot_id else "failed" task_status = "failed" self.log.exception( "Loading failure, updating to `%s` status", status, extra={ "swh_task_args": [], "swh_task_kwargs": {"origin": self.origin.url}, }, ) visit_status = OriginVisitStatus( origin=self.origin.url, visit=self.visit.visit, type=self.visit_type, date=now(), status=status, snapshot=self.loaded_snapshot_id, ) self.storage.origin_visit_status_add([visit_status]) self.post_load(success=False) return {"status": task_status} finally: self.flush() self.cleanup() return self.load_status() class DVCSLoader(BaseLoader): """This base class is a pattern for dvcs loaders (e.g. git, mercurial). Those loaders are able to load all the data in one go. For example, the loader defined in swh-loader-git :class:`BulkUpdater`. For other loaders (stateful one, (e.g :class:`SWHSvnLoader`), inherit directly from :class:`BaseLoader`. """ def cleanup(self) -> None: """Clean up an eventual state installed for computations.""" pass def has_contents(self) -> bool: """Checks whether we need to load contents""" return True def get_contents(self) -> Iterable[BaseContent]: """Get the contents that need to be loaded""" raise NotImplementedError def has_directories(self) -> bool: """Checks whether we need to load directories""" return True def get_directories(self) -> Iterable[Directory]: """Get the directories that need to be loaded""" raise NotImplementedError def has_revisions(self) -> bool: """Checks whether we need to load revisions""" return True def get_revisions(self) -> Iterable[Revision]: """Get the revisions that need to be loaded""" raise NotImplementedError def has_releases(self) -> bool: """Checks whether we need to load releases""" return True def get_releases(self) -> Iterable[Release]: """Get the releases that need to be loaded""" raise NotImplementedError def get_snapshot(self) -> Snapshot: """Get the snapshot that needs to be loaded""" raise NotImplementedError def eventful(self) -> bool: """Whether the load was eventful""" raise NotImplementedError def store_data(self) -> None: assert self.origin if self.save_data_path: self.save_data() if self.has_contents(): for obj in self.get_contents(): if isinstance(obj, Content): self.storage.content_add([obj]) elif isinstance(obj, SkippedContent): self.storage.skipped_content_add([obj]) else: raise TypeError(f"Unexpected content type: {obj}") if self.has_directories(): for directory in self.get_directories(): self.storage.directory_add([directory]) if self.has_revisions(): for revision in self.get_revisions(): self.storage.revision_add([revision]) if self.has_releases(): for release in self.get_releases(): self.storage.release_add([release]) snapshot = self.get_snapshot() self.storage.snapshot_add([snapshot]) self.flush() self.loaded_snapshot_id = snapshot.id diff --git a/swh/loader/core/tests/test_converters.py b/swh/loader/core/tests/test_converters.py index 8ef0a96..d9a76a6 100644 --- a/swh/loader/core/tests/test_converters.py +++ b/swh/loader/core/tests/test_converters.py @@ -1,111 +1,111 @@ # 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 import os import tempfile from swh.loader.core import converters from swh.model import from_disk from swh.model.model import Content, SkippedContent def tmpfile_with_content(fromdir, contentfile): - """Create a temporary file with content contentfile in directory fromdir. - - """ + """Create a temporary file with content contentfile in directory fromdir.""" tmpfilepath = tempfile.mktemp( suffix=".swh", prefix="tmp-file-for-test", dir=str(fromdir) ) with open(tmpfilepath, "wb") as f: f.write(contentfile) return tmpfilepath def test_content_for_storage_path(tmpdir): # given data = b"temp file for testing content storage conversion" tmpfile = tmpfile_with_content(tmpdir, data) obj = from_disk.Content.from_file(path=os.fsdecode(tmpfile)).get_data() expected_content = obj.copy() expected_content["data"] = data expected_content["status"] = "visible" del expected_content["path"] del expected_content["perms"] expected_content = Content.from_dict(expected_content) # when content = converters.content_for_storage(obj) # then assert content == expected_content def test_content_for_storage_data(tmpdir): # given data = b"temp file for testing content storage conversion" obj = from_disk.Content.from_bytes(data=data, mode=0o100644).get_data() del obj["perms"] expected_content = obj.copy() expected_content["status"] = "visible" expected_content = Content.from_dict(expected_content) # when content = converters.content_for_storage(obj) # then assert content == expected_content def test_content_for_storage_too_long(tmpdir): # given data = b"temp file for testing content storage conversion" obj = from_disk.Content.from_bytes(data=data, mode=0o100644).get_data() del obj["perms"] expected_content = obj.copy() expected_content.pop("data") expected_content["status"] = "absent" expected_content["origin"] = "http://example.org/" expected_content["reason"] = "Content too large" expected_content = SkippedContent.from_dict(expected_content) # when content = converters.content_for_storage( - obj, max_content_size=len(data) - 1, origin_url=expected_content.origin, + obj, + max_content_size=len(data) - 1, + origin_url=expected_content.origin, ) # then assert content == expected_content def test_prepare_contents(tmpdir): contents = [] data_fine = b"tmp file fine" max_size = len(data_fine) for data in [b"tmp file with too much data", data_fine]: obj = from_disk.Content.from_bytes(data=data, mode=0o100644).get_data() del obj["perms"] contents.append(obj) actual_contents, actual_skipped_contents = converters.prepare_contents( contents, max_content_size=max_size, origin_url="some-origin" ) assert len(actual_contents) == 1 assert len(actual_skipped_contents) == 1 actual_content = actual_contents[0] assert "reason" not in actual_content assert actual_content["status"] == "visible" actual_skipped_content = actual_skipped_contents[0] assert actual_skipped_content["reason"] == "Content too large" assert actual_skipped_content["status"] == "absent" assert actual_skipped_content["origin"] == "some-origin" diff --git a/swh/loader/core/tests/test_loader.py b/swh/loader/core/tests/test_loader.py index 2ac2636..3a195c4 100644 --- a/swh/loader/core/tests/test_loader.py +++ b/swh/loader/core/tests/test_loader.py @@ -1,237 +1,236 @@ # Copyright (C) 2018-2021 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 datetime import hashlib import logging from swh.loader.core.loader import BaseLoader, DVCSLoader from swh.loader.exception import NotFound from swh.loader.tests import assert_last_visit_matches from swh.model.hashutil import hash_to_bytes from swh.model.model import Origin, OriginVisit, Snapshot ORIGIN = Origin(url="some-url") class DummyLoader: """Base Loader to overload and simplify the base class (technical: to avoid repetition - in other *Loader classes)""" + in other *Loader classes)""" def cleanup(self): pass def prepare(self, *args, **kwargs): pass def fetch_data(self): pass def get_snapshot_id(self): return None def prepare_origin_visit(self, *args, **kwargs): self.origin = ORIGIN self.origin_url = ORIGIN.url self.visit_date = datetime.datetime.now(tz=datetime.timezone.utc) self.visit_type = "git" self.storage.origin_add([ORIGIN]) visit = OriginVisit( - origin=self.origin_url, date=self.visit_date, type=self.visit_type, + origin=self.origin_url, + date=self.visit_date, + type=self.visit_type, ) self.visit = self.storage.origin_visit_add([visit])[0] class DummyDVCSLoader(DummyLoader, DVCSLoader): - """DVCS Loader that does nothing in regards to DAG objects. - - """ + """DVCS Loader that does nothing in regards to DAG objects.""" def get_contents(self): return [] def get_directories(self): return [] def get_revisions(self): return [] def get_releases(self): return [] def get_snapshot(self): return Snapshot(branches={}) def eventful(self): return False class DummyBaseLoader(DummyLoader, BaseLoader): - """Buffered loader will send new data when threshold is reached - - """ + """Buffered loader will send new data when threshold is reached""" def store_data(self): pass def test_base_loader(swh_storage): loader = DummyBaseLoader(swh_storage) result = loader.load() assert result == {"status": "eventful"} def test_base_loader_with_config(swh_storage): loader = DummyBaseLoader(swh_storage, "logger-name") result = loader.load() assert result == {"status": "eventful"} def test_dvcs_loader(swh_storage): loader = DummyDVCSLoader(swh_storage) result = loader.load() assert result == {"status": "eventful"} def test_dvcs_loader_with_config(swh_storage): loader = DummyDVCSLoader(swh_storage, "another-logger") result = loader.load() assert result == {"status": "eventful"} def test_loader_logger_default_name(swh_storage): loader = DummyBaseLoader(swh_storage) assert isinstance(loader.log, logging.Logger) assert loader.log.name == "swh.loader.core.tests.test_loader.DummyBaseLoader" loader = DummyDVCSLoader(swh_storage) assert isinstance(loader.log, logging.Logger) assert loader.log.name == "swh.loader.core.tests.test_loader.DummyDVCSLoader" def test_loader_logger_with_name(swh_storage): loader = DummyBaseLoader(swh_storage, "some.logger.name") assert isinstance(loader.log, logging.Logger) assert loader.log.name == "some.logger.name" def test_loader_save_data_path(swh_storage, tmp_path): loader = DummyBaseLoader(swh_storage, "some.logger.name.1", save_data_path=tmp_path) url = "http://bitbucket.org/something" loader.origin = Origin(url=url) loader.visit_date = datetime.datetime(year=2019, month=10, day=1) hash_url = hashlib.sha1(url.encode("utf-8")).hexdigest() expected_save_path = "%s/sha1:%s/%s/2019" % (str(tmp_path), hash_url[0:2], hash_url) save_path = loader.get_save_data_path() assert save_path == expected_save_path def _check_load_failure(caplog, loader, exc_class, exc_text, status="partial"): """Check whether a failed load properly logged its exception, and that the snapshot didn't get referenced in storage""" assert isinstance(loader, DVCSLoader) # was implicit so far for record in caplog.records: if record.levelname != "ERROR": continue assert "Loading failure" in record.message assert record.exc_info exc = record.exc_info[1] assert isinstance(exc, exc_class) assert exc_text in exc.args[0] # Check that the get_snapshot operation would have succeeded assert loader.get_snapshot() is not None # And confirm that the visit doesn't reference a snapshot visit = assert_last_visit_matches(loader.storage, ORIGIN.url, status) if status != "partial": assert visit.snapshot is None # But that the snapshot didn't get loaded assert loader.loaded_snapshot_id is None class DummyDVCSLoaderExc(DummyDVCSLoader): """A loader which raises an exception when loading some contents""" def get_contents(self): raise RuntimeError("Failed to get contents!") def test_dvcs_loader_exc_partial_visit(swh_storage, caplog): logger_name = "dvcsloaderexc" caplog.set_level(logging.ERROR, logger=logger_name) loader = DummyDVCSLoaderExc(swh_storage, logging_class=logger_name) # fake the loading ending up in a snapshot loader.loaded_snapshot_id = hash_to_bytes( "9e4dd2b40d1b46b70917c0949aa2195c823a648e" ) result = loader.load() # loading failed assert result == {"status": "failed"} # still resulted in a partial visit with a snapshot (somehow) _check_load_failure( - caplog, loader, RuntimeError, "Failed to get contents!", + caplog, + loader, + RuntimeError, + "Failed to get contents!", ) class BrokenStorageProxy: def __init__(self, storage): self.storage = storage def __getattr__(self, attr): return getattr(self.storage, attr) def snapshot_add(self, snapshots): raise RuntimeError("Failed to add snapshot!") class DummyDVCSLoaderStorageExc(DummyDVCSLoader): """A loader which raises an exception when loading some contents""" def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) self.storage = BrokenStorageProxy(self.storage) def test_dvcs_loader_storage_exc_failed_visit(swh_storage, caplog): logger_name = "dvcsloaderexc" caplog.set_level(logging.ERROR, logger=logger_name) loader = DummyDVCSLoaderStorageExc(swh_storage, logging_class=logger_name) result = loader.load() assert result == {"status": "failed"} _check_load_failure( caplog, loader, RuntimeError, "Failed to add snapshot!", status="failed" ) class DummyDVCSLoaderNotFound(DummyDVCSLoader, BaseLoader): - """A loader which raises a not_found exception during the prepare method call - - """ + """A loader which raises a not_found exception during the prepare method call""" def prepare(*args, **kwargs): raise NotFound("Unknown origin!") def load_status(self): return { "status": "uneventful", } def test_loader_not_found(swh_storage, caplog): loader = DummyDVCSLoaderNotFound(swh_storage) result = loader.load() assert result == {"status": "uneventful"} _check_load_failure(caplog, loader, NotFound, "Unknown origin!", status="not_found") diff --git a/swh/loader/core/tests/test_utils.py b/swh/loader/core/tests/test_utils.py index 628243b..28d6c21 100644 --- a/swh/loader/core/tests/test_utils.py +++ b/swh/loader/core/tests/test_utils.py @@ -1,171 +1,187 @@ # Copyright (C) 2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from datetime import datetime import os import signal from time import sleep from unittest.mock import patch import pytest from swh.loader.core.utils import ( CloneFailure, CloneTimeout, clean_dangling_folders, clone_with_timeout, parse_visit_date, ) def prepare_arborescence_from(tmpdir, folder_names): """Prepare arborescence tree with folders Args: tmpdir (Either[LocalPath, str]): Root temporary directory folder_names (List[str]): List of folder names Returns: List of folders """ dangling_folders = [] for dname in folder_names: d = str(tmpdir / dname) os.mkdir(d) dangling_folders.append(d) return str(tmpdir), dangling_folders def assert_dirs(actual_dirs, expected_dirs): - """Assert that the directory actual and expected match - - """ + """Assert that the directory actual and expected match""" for d in actual_dirs: assert d in expected_dirs assert len(actual_dirs) == len(expected_dirs) def test_clean_dangling_folders_0(tmpdir): """Folder does not exist, do nothing""" r = clean_dangling_folders("/path/does/not/exist", "unused-pattern") assert r is None @patch("swh.loader.core.utils.psutil.pid_exists", return_value=False) def test_clean_dangling_folders_1(mock_pid_exists, tmpdir): - """Folder which matches pattern with dead pid are cleaned up - - """ + """Folder which matches pattern with dead pid are cleaned up""" rootpath, dangling = prepare_arborescence_from( - tmpdir, ["something", "swh.loader.svn-4321.noisynoise",] + tmpdir, + [ + "something", + "swh.loader.svn-4321.noisynoise", + ], ) clean_dangling_folders(rootpath, "swh.loader.svn") actual_dirs = os.listdir(rootpath) mock_pid_exists.assert_called_once_with(4321) assert_dirs(actual_dirs, ["something"]) @patch("swh.loader.core.utils.psutil.pid_exists", return_value=True) def test_clean_dangling_folders_2(mock_pid_exists, tmpdir): - """Folder which matches pattern with live pid are skipped - - """ + """Folder which matches pattern with live pid are skipped""" rootpath, dangling = prepare_arborescence_from( - tmpdir, ["something", "swh.loader.hg-1234.noisynoise",] + tmpdir, + [ + "something", + "swh.loader.hg-1234.noisynoise", + ], ) clean_dangling_folders(rootpath, "swh.loader.hg") actual_dirs = os.listdir(rootpath) mock_pid_exists.assert_called_once_with(1234) - assert_dirs(actual_dirs, ["something", "swh.loader.hg-1234.noisynoise",]) + assert_dirs( + actual_dirs, + [ + "something", + "swh.loader.hg-1234.noisynoise", + ], + ) @patch("swh.loader.core.utils.psutil.pid_exists", return_value=False) @patch( "swh.loader.core.utils.shutil.rmtree", side_effect=ValueError("Could not remove for reasons"), ) def test_clean_dangling_folders_3(mock_rmtree, mock_pid_exists, tmpdir): - """Error in trying to clean dangling folders are skipped - - """ + """Error in trying to clean dangling folders are skipped""" path1 = "thingy" path2 = "swh.loader.git-1468.noisy" - rootpath, dangling = prepare_arborescence_from(tmpdir, [path1, path2,]) + rootpath, dangling = prepare_arborescence_from( + tmpdir, + [ + path1, + path2, + ], + ) clean_dangling_folders(rootpath, "swh.loader.git") actual_dirs = os.listdir(rootpath) mock_pid_exists.assert_called_once_with(1468) mock_rmtree.assert_called_once_with(os.path.join(rootpath, path2)) assert_dirs(actual_dirs, [path2, path1]) def test_clone_with_timeout_no_error_no_timeout(): def succeed(): """This does nothing to simulate a successful clone""" clone_with_timeout("foo", "bar", succeed, timeout=0.5) def test_clone_with_timeout_no_error_timeout(): def slow(): """This lasts for more than the timeout""" sleep(1) with pytest.raises(CloneTimeout): clone_with_timeout("foo", "bar", slow, timeout=0.5) def test_clone_with_timeout_error(): def raise_something(): raise RuntimeError("panic!") with pytest.raises(CloneFailure): clone_with_timeout("foo", "bar", raise_something, timeout=0.5) def test_clone_with_timeout_sigkill(): """This also tests that the traceback is useful""" src = "https://www.mercurial-scm.org/repo/hello" dest = "/dev/null" timeout = 0.5 sleepy_time = 100 * timeout assert sleepy_time > timeout def ignores_sigterm(*args, **kwargs): # ignore SIGTERM to force sigkill signal.signal(signal.SIGTERM, lambda signum, frame: None) sleep(sleepy_time) # we make sure we exceed the timeout with pytest.raises(CloneTimeout) as e: clone_with_timeout(src, dest, ignores_sigterm, timeout) killed = True assert e.value.args == (src, timeout, killed) VISIT_DATE_STR = "2021-02-17 15:50:04.518963" VISIT_DATE = datetime(2021, 2, 17, 15, 50, 4, 518963) @pytest.mark.parametrize( "input_visit_date,expected_date", - [(None, None), (VISIT_DATE, VISIT_DATE), (VISIT_DATE_STR, VISIT_DATE),], + [ + (None, None), + (VISIT_DATE, VISIT_DATE), + (VISIT_DATE_STR, VISIT_DATE), + ], ) def test_utils_parse_visit_date(input_visit_date, expected_date): assert parse_visit_date(input_visit_date) == expected_date def test_utils_parse_visit_date_now(): actual_date = parse_visit_date("now") assert isinstance(actual_date, datetime) def test_utils_parse_visit_date_fails(): with pytest.raises(ValueError, match="invalid"): parse_visit_date(10) # not a string nor a date diff --git a/swh/loader/core/utils.py b/swh/loader/core/utils.py index 84be8ff..0e9b388 100644 --- a/swh/loader/core/utils.py +++ b/swh/loader/core/utils.py @@ -1,127 +1,127 @@ # Copyright (C) 2018-2022 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from datetime import datetime, timezone import io import os import shutil import signal import time import traceback from typing import Callable, Optional, Union from billiard import Process, Queue # type: ignore from dateutil.parser import parse import psutil def clean_dangling_folders(dirpath: str, pattern_check: str, log=None) -> None: """Clean up potential dangling temporary working folder rooted at `dirpath`. Those folders must match a dedicated pattern and not belonging to a live pid. Args: dirpath: Path to check for dangling files pattern_check: A dedicated pattern to check on first level directory (e.g `swh.loader.mercurial.`, `swh.loader.svn.`) log (Logger): Optional logger """ if not os.path.exists(dirpath): return for filename in os.listdir(dirpath): path_to_cleanup = os.path.join(dirpath, filename) try: # pattern: `swh.loader.{loader-type}-pid.{noise}` if ( pattern_check not in filename or "-" not in filename ): # silently ignore unknown patterns continue _, pid_ = filename.split("-") pid = int(pid_.split(".")[0]) if psutil.pid_exists(pid): if log: log.debug("PID %s is live, skipping", pid) continue # could be removed concurrently, so check before removal if os.path.exists(path_to_cleanup): shutil.rmtree(path_to_cleanup) except Exception as e: if log: log.warn("Fail to clean dangling path %s: %s", path_to_cleanup, e) class CloneTimeout(Exception): pass class CloneFailure(Exception): pass def _clone_task(clone_func: Callable[[], None], errors: Queue) -> None: try: clone_func() except Exception as e: exc_buffer = io.StringIO() traceback.print_exc(file=exc_buffer) errors.put_nowait(exc_buffer.getvalue()) raise e def clone_with_timeout( src: str, dest: str, clone_func: Callable[[], None], timeout: float ) -> None: """Clone a repository with timeout. Args: src: clone source dest: clone destination clone_func: callable that does the actual cloning timeout: timeout in seconds """ errors: Queue = Queue() process = Process(target=_clone_task, args=(clone_func, errors)) process.start() process.join(timeout) if process.is_alive(): process.terminate() # Give it literally a second (in successive steps of 0.1 second), # then kill it. # Can't use `process.join(1)` here, billiard appears to be bugged # https://github.com/celery/billiard/issues/270 killed = False for _ in range(10): time.sleep(0.1) if not process.is_alive(): break else: killed = True os.kill(process.pid, signal.SIGKILL) raise CloneTimeout(src, timeout, killed) if not errors.empty(): raise CloneFailure(src, dest, errors.get()) def parse_visit_date(visit_date: Optional[Union[datetime, str]]) -> Optional[datetime]: """Convert visit date from either None, a string or a datetime to either None or - datetime. + datetime. """ if visit_date is None: return None if isinstance(visit_date, datetime): return visit_date if visit_date == "now": return datetime.now(tz=timezone.utc) if isinstance(visit_date, str): return parse(visit_date) raise ValueError(f"invalid visit date {visit_date!r}") diff --git a/swh/loader/exception.py b/swh/loader/exception.py index fd28021..6a77fc9 100644 --- a/swh/loader/exception.py +++ b/swh/loader/exception.py @@ -1,13 +1,13 @@ # Copyright (C) 2021 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 class NotFound(ValueError): """An exception raised when some information to retrieve is not found (e.g origin, - artifact, ...) + artifact, ...) """ pass diff --git a/swh/loader/package/archive/loader.py b/swh/loader/package/archive/loader.py index 7e80cae..0c2d888 100644 --- a/swh/loader/package/archive/loader.py +++ b/swh/loader/package/archive/loader.py @@ -1,166 +1,164 @@ # Copyright (C) 2019-2021 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 datetime import hashlib import logging from os import path import string from typing import Any, Dict, Iterator, Mapping, Optional, Sequence, Tuple, Union import attr import iso8601 from swh.loader.package.loader import BasePackageInfo, PackageLoader, PartialExtID from swh.loader.package.utils import EMPTY_AUTHOR, release_name from swh.model.model import ObjectType, Release, Sha1Git, TimestampWithTimezone from swh.storage.interface import StorageInterface logger = logging.getLogger(__name__) @attr.s class ArchivePackageInfo(BasePackageInfo): raw_info = attr.ib(type=Dict[str, Any]) length = attr.ib(type=int) """Size of the archive file""" time = attr.ib(type=Union[str, datetime.datetime]) """Timestamp of the archive file on the server""" # default format for gnu MANIFEST_FORMAT = string.Template("$time $length $version $url") def extid(self, manifest_format: Optional[string.Template] = None) -> PartialExtID: """Returns a unique intrinsic identifier of this package info ``manifest_format`` allows overriding the class' default MANIFEST_FORMAT""" manifest_format = manifest_format or self.MANIFEST_FORMAT # TODO: use parsed attributes instead of self.raw_info manifest = manifest_format.substitute( {k: str(v) for (k, v) in self.raw_info.items()} ) return ( self.EXTID_TYPE, self.EXTID_VERSION, hashlib.sha256(manifest.encode()).digest(), ) @classmethod def from_metadata(cls, a_metadata: Dict[str, Any]) -> "ArchivePackageInfo": url = a_metadata["url"] filename = a_metadata.get("filename") return cls( url=url, filename=filename if filename else path.split(url)[-1], raw_info=a_metadata, length=a_metadata["length"], time=a_metadata["time"], version=a_metadata["version"], ) class ArchiveLoader(PackageLoader[ArchivePackageInfo]): - """Load archive origin's artifact files into swh archive - - """ + """Load archive origin's artifact files into swh archive""" visit_type = "tar" def __init__( self, storage: StorageInterface, url: str, artifacts: Sequence[Dict[str, Any]], extid_manifest_format: Optional[str] = None, max_content_size: Optional[int] = None, snapshot_append: bool = False, ): f"""Loader constructor. For now, this is the lister's task output. Args: url: Origin url artifacts: List of artifact information with keys: - **time**: last modification time as either isoformat date string or timestamp - **url**: the artifact url to retrieve filename - **filename**: optionally, the file's name - **version**: artifact's version - **length**: artifact's length extid_manifest_format: template string used to format a manifest, which is hashed to get the extid of a package. Defaults to {ArchivePackageInfo.MANIFEST_FORMAT!r} snapshot_append: if :const:`True`, append latest snapshot content to the new snapshot created by the loader """ super().__init__(storage=storage, url=url, max_content_size=max_content_size) self.artifacts = artifacts # assume order is enforced in the lister self.extid_manifest_format = ( None if extid_manifest_format is None else string.Template(extid_manifest_format) ) self.snapshot_append = snapshot_append def get_versions(self) -> Sequence[str]: versions = [] for archive in self.artifacts: v = archive.get("version") if v: versions.append(v) return versions def get_default_version(self) -> str: # It's the most recent, so for this loader, it's the last one return self.artifacts[-1]["version"] def get_package_info( self, version: str ) -> Iterator[Tuple[str, ArchivePackageInfo]]: for a_metadata in self.artifacts: p_info = ArchivePackageInfo.from_metadata(a_metadata) if version == p_info.version: # FIXME: this code assumes we have only 1 artifact per # versioned package yield release_name(version), p_info def new_packageinfo_to_extid( self, p_info: ArchivePackageInfo ) -> Optional[PartialExtID]: return p_info.extid(manifest_format=self.extid_manifest_format) def build_release( self, p_info: ArchivePackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Release]: time = p_info.time # assume it's a timestamp if isinstance(time, str): # otherwise, assume it's a parsable date parsed_time = iso8601.parse_date(time) else: parsed_time = time normalized_time = TimestampWithTimezone.from_datetime(parsed_time) msg = f"Synthetic release for archive at {p_info.url}\n" return Release( name=p_info.version.encode(), message=msg.encode(), date=normalized_time, author=EMPTY_AUTHOR, target=directory, target_type=ObjectType.DIRECTORY, synthetic=True, ) def extra_branches(self) -> Dict[bytes, Mapping[str, Any]]: if not self.snapshot_append: return {} last_snapshot = self.last_snapshot() return last_snapshot.to_dict()["branches"] if last_snapshot else {} diff --git a/swh/loader/package/archive/tests/test_archive.py b/swh/loader/package/archive/tests/test_archive.py index 4529f90..a590c1d 100644 --- a/swh/loader/package/archive/tests/test_archive.py +++ b/swh/loader/package/archive/tests/test_archive.py @@ -1,489 +1,488 @@ # Copyright (C) 2019-2021 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 datetime import hashlib from io import BytesIO from pathlib import Path import string import attr import pytest from requests.exceptions import ContentDecodingError from swh.loader.package.archive.loader import ArchiveLoader, ArchivePackageInfo from swh.loader.tests import assert_last_visit_matches, check_snapshot, get_stats from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.model.model import ( ObjectType, Person, Release, Snapshot, SnapshotBranch, TargetType, TimestampWithTimezone, ) URL = "https://ftp.gnu.org/gnu/8sync/" GNU_ARTIFACTS = [ { "time": 944729610, "url": "https://ftp.gnu.org/gnu/8sync/8sync-0.1.0.tar.gz", "length": 221837, "filename": "8sync-0.1.0.tar.gz", "version": "0.1.0", }, { "time": 1480991830, "url": "https://ftp.gnu.org/gnu/8sync/8sync-0.2.0.tar.gz", "length": 238466, "filename": "8sync-0.2.0.tar.gz", "version": "0.2.0", }, ] _expected_new_contents_first_visit = [ "e9258d81faf5881a2f96a77ba609396f82cb97ad", "1170cf105b04b7e2822a0e09d2acf71da7b9a130", "fbd27c3f41f2668624ffc80b7ba5db9b92ff27ac", "0057bec9b5422aff9256af240b177ac0e3ac2608", "2b8d0d0b43a1078fc708930c8ddc2956a86c566e", "27de3b3bc6545d2a797aeeb4657c0e215a0c2e55", "2e6db43f5cd764e677f416ff0d0c78c7a82ef19b", "ae9be03bd2a06ed8f4f118d3fe76330bb1d77f62", "edeb33282b2bffa0e608e9d2fd960fd08093c0ea", "d64e64d4c73679323f8d4cde2643331ba6c20af9", "7a756602914be889c0a2d3952c710144b3e64cb0", "84fb589b554fcb7f32b806951dcf19518d67b08f", "8624bcdae55baeef00cd11d5dfcfa60f68710a02", "e08441aeab02704cfbd435d6445f7c072f8f524e", "f67935bc3a83a67259cda4b2d43373bd56703844", "809788434b433eb2e3cfabd5d591c9a659d5e3d8", "7d7c6c8c5ebaeff879f61f37083a3854184f6c41", "b99fec102eb24bffd53ab61fc30d59e810f116a2", "7d149b28eaa228b3871c91f0d5a95a2fa7cb0c68", "f0c97052e567948adf03e641301e9983c478ccff", "7fb724242e2b62b85ca64190c31dcae5303e19b3", "4f9709e64a9134fe8aefb36fd827b84d8b617ab5", "7350628ccf194c2c3afba4ac588c33e3f3ac778d", "0bb892d9391aa706dc2c3b1906567df43cbe06a2", "49d4c0ce1a16601f1e265d446b6c5ea6b512f27c", "6b5cc594ac466351450f7f64a0b79fdaf4435ad3", "3046e5d1f70297e2a507b98224b6222c9688d610", "1572607d456d7f633bc6065a2b3048496d679a31", ] _expected_new_directories_first_visit = [ "daabc65ec75d487b1335ffc101c0ac11c803f8fc", "263be23b4a8101d3ad0d9831319a3e0f2b065f36", "7f6e63ba6eb3e2236f65892cd822041f1a01dd5c", "4db0a3ecbc976083e2dac01a62f93729698429a3", "dfef1c80e1098dd5deda664bb44a9ab1f738af13", "eca971d346ea54d95a6e19d5051f900237fafdaa", "3aebc29ed1fccc4a6f2f2010fb8e57882406b528", ] _expected_new_releases_first_visit = { "c92b2ad9e70ef1dce455e8fe1d8e41b92512cc08": ( "3aebc29ed1fccc4a6f2f2010fb8e57882406b528" ) } def test_archive_visit_with_no_artifact_found(swh_storage, requests_mock_datadir): url = URL unknown_artifact_url = "https://ftp.g.o/unknown/8sync-0.1.0.tar.gz" loader = ArchiveLoader( swh_storage, url, artifacts=[ { "time": 944729610, "url": unknown_artifact_url, # unknown artifact "length": 221837, "filename": "8sync-0.1.0.tar.gz", "version": "0.1.0", } ], ) actual_load_status = loader.load() assert actual_load_status["status"] == "uneventful" assert actual_load_status["snapshot_id"] is not None stats = get_stats(swh_storage) assert { "content": 0, "directory": 0, "origin": 1, "origin_visit": 1, "release": 0, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats assert_last_visit_matches(swh_storage, url, status="partial", type="tar") def test_archive_visit_with_release_artifact_no_prior_visit( swh_storage, requests_mock_datadir ): - """With no prior visit, load a gnu project ends up with 1 snapshot - - """ + """With no prior visit, load a gnu project ends up with 1 snapshot""" loader = ArchiveLoader(swh_storage, URL, artifacts=GNU_ARTIFACTS[:1]) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" expected_snapshot_first_visit_id = hash_to_bytes( "9efecc835e8f99254934f256b5301b94f348fd17" ) assert actual_load_status["snapshot_id"] == hash_to_hex( expected_snapshot_first_visit_id ) assert_last_visit_matches(swh_storage, URL, status="full", type="tar") stats = get_stats(swh_storage) assert { "content": len(_expected_new_contents_first_visit), "directory": len(_expected_new_directories_first_visit), "origin": 1, "origin_visit": 1, "release": len(_expected_new_releases_first_visit), "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats release_id = hash_to_bytes(list(_expected_new_releases_first_visit)[0]) expected_snapshot = Snapshot( id=expected_snapshot_first_visit_id, branches={ b"HEAD": SnapshotBranch( - target_type=TargetType.ALIAS, target=b"releases/0.1.0", + target_type=TargetType.ALIAS, + target=b"releases/0.1.0", ), b"releases/0.1.0": SnapshotBranch( - target_type=TargetType.RELEASE, target=release_id, + target_type=TargetType.RELEASE, + target=release_id, ), }, ) check_snapshot(expected_snapshot, swh_storage) assert swh_storage.release_get([release_id])[0] == Release( id=release_id, name=b"0.1.0", message=( b"Synthetic release for archive at " b"https://ftp.gnu.org/gnu/8sync/8sync-0.1.0.tar.gz\n" ), target=hash_to_bytes("3aebc29ed1fccc4a6f2f2010fb8e57882406b528"), target_type=ObjectType.DIRECTORY, synthetic=True, author=Person.from_fullname(b""), date=TimestampWithTimezone.from_datetime( datetime.datetime(1999, 12, 9, 8, 53, 30, tzinfo=datetime.timezone.utc) ), ) expected_contents = map(hash_to_bytes, _expected_new_contents_first_visit) assert list(swh_storage.content_missing_per_sha1(expected_contents)) == [] expected_dirs = map(hash_to_bytes, _expected_new_directories_first_visit) assert list(swh_storage.directory_missing(expected_dirs)) == [] expected_rels = map(hash_to_bytes, _expected_new_releases_first_visit) assert list(swh_storage.release_missing(expected_rels)) == [] def test_archive_2_visits_without_change(swh_storage, requests_mock_datadir): - """With no prior visit, load a gnu project ends up with 1 snapshot - - """ + """With no prior visit, load a gnu project ends up with 1 snapshot""" url = URL loader = ArchiveLoader(swh_storage, url, artifacts=GNU_ARTIFACTS[:1]) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None assert_last_visit_matches(swh_storage, url, status="full", type="tar") actual_load_status2 = loader.load() assert actual_load_status2["status"] == "uneventful" assert actual_load_status2["snapshot_id"] is not None assert actual_load_status["snapshot_id"] == actual_load_status2["snapshot_id"] assert_last_visit_matches(swh_storage, url, status="full", type="tar") urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith("https://ftp.gnu.org") ] assert len(urls) == 1 def test_archive_2_visits_with_new_artifact(swh_storage, requests_mock_datadir): - """With no prior visit, load a gnu project ends up with 1 snapshot - - """ + """With no prior visit, load a gnu project ends up with 1 snapshot""" url = URL artifact1 = GNU_ARTIFACTS[0] loader = ArchiveLoader(swh_storage, url, [artifact1]) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None assert_last_visit_matches(swh_storage, url, status="full", type="tar") stats = get_stats(swh_storage) assert { "content": len(_expected_new_contents_first_visit), "directory": len(_expected_new_directories_first_visit), "origin": 1, "origin_visit": 1, "release": len(_expected_new_releases_first_visit), "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith("https://ftp.gnu.org") ] assert len(urls) == 1 artifact2 = GNU_ARTIFACTS[1] loader2 = ArchiveLoader(swh_storage, url, [artifact1, artifact2]) stats2 = get_stats(swh_storage) assert stats == stats2 # ensure we share the storage actual_load_status2 = loader2.load() assert actual_load_status2["status"] == "eventful" assert actual_load_status2["snapshot_id"] is not None stats2 = get_stats(swh_storage) assert { "content": len(_expected_new_contents_first_visit) + 14, "directory": len(_expected_new_directories_first_visit) + 8, "origin": 1, "origin_visit": 1 + 1, "release": len(_expected_new_releases_first_visit) + 1, "revision": 0, "skipped_content": 0, "snapshot": 1 + 1, } == stats2 assert_last_visit_matches(swh_storage, url, status="full", type="tar") urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith("https://ftp.gnu.org") ] # 1 artifact (2nd time no modification) + 1 new artifact assert len(urls) == 2 def test_archive_2_visits_without_change_not_gnu(swh_storage, requests_mock_datadir): - """Load a project archive (not gnu) ends up with 1 snapshot - - """ + """Load a project archive (not gnu) ends up with 1 snapshot""" url = "https://something.else.org/8sync/" artifacts = [ # this is not a gnu artifact { "time": "1999-12-09T09:53:30+00:00", # it's also not a timestamp "sha256": "d5d1051e59b2be6f065a9fc6aedd3a391e44d0274b78b9bb4e2b57a09134dbe4", # noqa # keep a gnu artifact reference to avoid adding other test files "url": "https://ftp.gnu.org/gnu/8sync/8sync-0.2.0.tar.gz", "length": 238466, "filename": "8sync-0.2.0.tar.gz", "version": "0.2.0", } ] # Here the loader defines the id_keys to use for existence in the snapshot # It's not the default archive loader which loader = ArchiveLoader( swh_storage, url, artifacts=artifacts, extid_manifest_format="$sha256 $length $url", ) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None assert_last_visit_matches(swh_storage, url, status="full", type="tar") actual_load_status2 = loader.load() assert actual_load_status2["status"] == "uneventful" assert actual_load_status2["snapshot_id"] == actual_load_status["snapshot_id"] assert_last_visit_matches(swh_storage, url, status="full", type="tar") urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith("https://ftp.gnu.org") ] assert len(urls) == 1 def test_archive_extid(): - """Compute primary key should return the right identity - - """ + """Compute primary key should return the right identity""" @attr.s class TestPackageInfo(ArchivePackageInfo): a = attr.ib() b = attr.ib() metadata = GNU_ARTIFACTS[0] p_info = TestPackageInfo( - raw_info={**metadata, "a": 1, "b": 2}, a=1, b=2, **metadata, + raw_info={**metadata, "a": 1, "b": 2}, + a=1, + b=2, + **metadata, ) for manifest_format, expected_manifest in [ (string.Template("$a $b"), b"1 2"), (string.Template(""), b""), (None, "{time} {length} {version} {url}".format(**metadata).encode()), ]: actual_id = p_info.extid(manifest_format=manifest_format) assert actual_id == ( "package-manifest-sha256", 0, hashlib.sha256(expected_manifest).digest(), ) with pytest.raises(KeyError): p_info.extid(manifest_format=string.Template("$a $unknown_key")) def test_archive_snapshot_append(swh_storage, requests_mock_datadir): # first loading with a first artifact artifact1 = GNU_ARTIFACTS[0] loader = ArchiveLoader(swh_storage, URL, [artifact1], snapshot_append=True) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None assert_last_visit_matches(swh_storage, URL, status="full", type="tar") # check expected snapshot snapshot = loader.last_snapshot() assert len(snapshot.branches) == 2 branch_artifact1_name = f"releases/{artifact1['version']}".encode() assert b"HEAD" in snapshot.branches assert branch_artifact1_name in snapshot.branches assert snapshot.branches[b"HEAD"].target == branch_artifact1_name # second loading with a second artifact artifact2 = GNU_ARTIFACTS[1] loader = ArchiveLoader(swh_storage, URL, [artifact2], snapshot_append=True) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None assert_last_visit_matches(swh_storage, URL, status="full", type="tar") # check expected snapshot, should contain a new branch and the # branch for the first artifact snapshot = loader.last_snapshot() assert len(snapshot.branches) == 3 branch_artifact2_name = f"releases/{artifact2['version']}".encode() assert b"HEAD" in snapshot.branches assert branch_artifact2_name in snapshot.branches assert branch_artifact1_name in snapshot.branches assert snapshot.branches[b"HEAD"].target == branch_artifact2_name def test_archive_snapshot_append_branch_override(swh_storage, requests_mock_datadir): # first loading for a first artifact artifact1 = GNU_ARTIFACTS[0] loader = ArchiveLoader(swh_storage, URL, [artifact1], snapshot_append=True) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None assert_last_visit_matches(swh_storage, URL, status="full", type="tar") # check expected snapshot snapshot = loader.last_snapshot() assert len(snapshot.branches) == 2 branch_artifact1_name = f"releases/{artifact1['version']}".encode() assert branch_artifact1_name in snapshot.branches branch_target_first_visit = snapshot.branches[branch_artifact1_name].target # second loading for a second artifact with same version as the first one # but with different tarball content artifact2 = dict(GNU_ARTIFACTS[0]) artifact2["url"] = GNU_ARTIFACTS[1]["url"] artifact2["time"] = GNU_ARTIFACTS[1]["time"] artifact2["length"] = GNU_ARTIFACTS[1]["length"] loader = ArchiveLoader(swh_storage, URL, [artifact2], snapshot_append=True) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None assert_last_visit_matches(swh_storage, URL, status="full", type="tar") # check expected snapshot, should contain the same branch as previously # but with different target snapshot = loader.last_snapshot() assert len(snapshot.branches) == 2 assert branch_artifact1_name in snapshot.branches branch_target_second_visit = snapshot.branches[branch_artifact1_name].target assert branch_target_first_visit != branch_target_second_visit @pytest.fixture def not_gzipped_tarball_bytes(datadir): return Path(datadir, "not_gzipped_tarball.tar.gz").read_bytes() def test_archive_not_gzipped_tarball( swh_storage, requests_mock, not_gzipped_tarball_bytes ): """Check that a tarball erroneously marked as gzip compressed can still be downloaded and processed. """ filename = "not_gzipped_tarball.tar.gz" url = f"https://example.org/ftp/{filename}" requests_mock.get( url, [ - {"exc": ContentDecodingError,}, - {"body": BytesIO(not_gzipped_tarball_bytes),}, + { + "exc": ContentDecodingError, + }, + { + "body": BytesIO(not_gzipped_tarball_bytes), + }, ], ) loader = ArchiveLoader( swh_storage, url, artifacts=[ { "time": 944729610, "url": url, "length": 221837, "filename": filename, "version": "0.1.0", } ], ) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None snapshot = loader.last_snapshot() assert len(snapshot.branches) == 2 assert b"releases/0.1.0" in snapshot.branches diff --git a/swh/loader/package/cran/loader.py b/swh/loader/package/cran/loader.py index 1bef983..0239ee2 100644 --- a/swh/loader/package/cran/loader.py +++ b/swh/loader/package/cran/loader.py @@ -1,181 +1,179 @@ # Copyright (C) 2019-2021 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 datetime from datetime import timezone import logging import os from os import path import re import string from typing import Any, Dict, Iterator, List, Optional, Tuple import attr import dateutil.parser from debian.deb822 import Deb822 from swh.loader.package.loader import BasePackageInfo, PackageLoader from swh.loader.package.utils import release_name from swh.model.model import ObjectType, Person, Release, Sha1Git, TimestampWithTimezone from swh.storage.interface import StorageInterface logger = logging.getLogger(__name__) DATE_PATTERN = re.compile(r"^(?P\d{4})-(?P\d{2})$") @attr.s class CRANPackageInfo(BasePackageInfo): raw_info = attr.ib(type=Dict[str, Any]) name = attr.ib(type=str) EXTID_TYPE = "cran-sha256" MANIFEST_FORMAT = string.Template("$version $url") @classmethod def from_metadata(cls, a_metadata: Dict[str, Any]) -> "CRANPackageInfo": url = a_metadata["url"] return CRANPackageInfo( url=url, filename=path.basename(url), raw_info=a_metadata, name=a_metadata["package"], version=a_metadata["version"], ) class CRANLoader(PackageLoader[CRANPackageInfo]): visit_type = "cran" def __init__( self, storage: StorageInterface, url: str, artifacts: List[Dict], max_content_size: Optional[int] = None, ): """Loader constructor. Args: url: Origin url to retrieve cran artifact(s) from artifacts: List of associated artifact for the origin url """ super().__init__(storage=storage, url=url, max_content_size=max_content_size) # explicit what we consider the artifact identity self.artifacts = artifacts def get_versions(self) -> List[str]: versions = [] for artifact in self.artifacts: versions.append(artifact["version"]) return versions def get_default_version(self) -> str: return self.artifacts[-1]["version"] def get_package_info(self, version: str) -> Iterator[Tuple[str, CRANPackageInfo]]: for a_metadata in self.artifacts: p_info = CRANPackageInfo.from_metadata(a_metadata) if version == p_info.version: yield release_name(version), p_info def build_release( self, p_info: CRANPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Release]: # a_metadata is empty metadata = extract_intrinsic_metadata(uncompressed_path) date = parse_date(metadata.get("Date")) author = Person.from_fullname(metadata.get("Maintainer", "").encode()) msg = ( f"Synthetic release for CRAN source package {p_info.name} " f"version {p_info.version}\n" ) return Release( name=p_info.version.encode(), message=msg.encode(), date=date, author=author, target_type=ObjectType.DIRECTORY, target=directory, synthetic=True, ) def parse_debian_control(filepath: str) -> Dict[str, Any]: """Parse debian control at filepath""" metadata: Dict = {} logger.debug("Debian control file %s", filepath) for paragraph in Deb822.iter_paragraphs(open(filepath, "rb")): logger.debug("paragraph: %s", paragraph) metadata.update(**paragraph) logger.debug("metadata parsed: %s", metadata) return metadata def extract_intrinsic_metadata(dir_path: str) -> Dict[str, Any]: """Given an uncompressed path holding the DESCRIPTION file, returns a DESCRIPTION parsed structure as a dict. Cran origins describes their intrinsic metadata within a DESCRIPTION file at the root tree of a tarball. This DESCRIPTION uses a simple file format called DCF, the Debian control format. The release artifact contains at their root one folder. For example: $ tar tvf zprint-0.0.6.tar.gz drwxr-xr-x root/root 0 2018-08-22 11:01 zprint-0.0.6/ ... Args: dir_path (str): Path to the uncompressed directory representing a release artifact from pypi. Returns: the DESCRIPTION parsed structure as a dict (or empty dict if missing) """ # Retrieve the root folder of the archive if not os.path.exists(dir_path): return {} lst = os.listdir(dir_path) if len(lst) != 1: return {} project_dirname = lst[0] description_path = os.path.join(dir_path, project_dirname, "DESCRIPTION") if not os.path.exists(description_path): return {} return parse_debian_control(description_path) def parse_date(date: Optional[str]) -> Optional[TimestampWithTimezone]: - """Parse a date into a datetime - - """ + """Parse a date into a datetime""" assert not date or isinstance(date, str) dt: Optional[datetime.datetime] = None if not date: return None try: specific_date = DATE_PATTERN.match(date) if specific_date: year = int(specific_date.group("year")) month = int(specific_date.group("month")) dt = datetime.datetime(year, month, 1) else: dt = dateutil.parser.parse(date) if not dt.tzinfo: # up for discussion the timezone needs to be set or # normalize_timestamp is not happy: ValueError: normalize_timestamp # received datetime without timezone: 2001-06-08 00:00:00 dt = dt.replace(tzinfo=timezone.utc) except Exception as e: logger.warning("Fail to parse date %s. Reason: %s", date, e) if dt: return TimestampWithTimezone.from_datetime(dt) else: return None diff --git a/swh/loader/package/cran/tests/test_cran.py b/swh/loader/package/cran/tests/test_cran.py index 526ecdc..b1518e6 100644 --- a/swh/loader/package/cran/tests/test_cran.py +++ b/swh/loader/package/cran/tests/test_cran.py @@ -1,420 +1,426 @@ # Copyright (C) 2019-2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from datetime import datetime, timezone import os from os import path from unittest.mock import patch from dateutil.tz import tzlocal import pytest from swh.core.tarball import uncompress from swh.loader.package.cran.loader import ( CRANLoader, extract_intrinsic_metadata, parse_date, parse_debian_control, ) from swh.loader.tests import assert_last_visit_matches, check_snapshot, get_stats from swh.model.hashutil import hash_to_bytes from swh.model.model import ( ObjectType, Person, Release, Snapshot, SnapshotBranch, TargetType, TimestampWithTimezone, ) RELEASE_ID = hash_to_bytes("daaf3cffedac946060de53648994631d0b3c63bc") SNAPSHOT = Snapshot( id=hash_to_bytes("c0ccd6452cbe9cd4f0a523b23f09c411bd92ef4e"), branches={ b"HEAD": SnapshotBranch( target=b"releases/2.22-6", target_type=TargetType.ALIAS ), b"releases/2.22-6": SnapshotBranch( - target=RELEASE_ID, target_type=TargetType.RELEASE, + target=RELEASE_ID, + target_type=TargetType.RELEASE, ), }, ) def test_cran_parse_date(): data = [ # parsable, some have debatable results though ("2001-June-08", datetime(2001, 6, 8, 0, 0, tzinfo=timezone.utc)), ( "Tue Dec 27 15:06:08 PST 2011", datetime(2011, 12, 27, 15, 6, 8, tzinfo=timezone.utc), ), ("8-14-2013", datetime(2013, 8, 14, 0, 0, tzinfo=timezone.utc)), ("2011-01", datetime(2011, 1, 1, 0, 0, tzinfo=timezone.utc)), ("201109", datetime(2009, 11, 20, 0, 0, tzinfo=timezone.utc)), ("04-12-2014", datetime(2014, 4, 12, 0, 0, tzinfo=timezone.utc)), ( "2018-08-24, 10:40:10", datetime(2018, 8, 24, 10, 40, 10, tzinfo=timezone.utc), ), ("2013-October-16", datetime(2013, 10, 16, 0, 0, tzinfo=timezone.utc)), ("Aug 23, 2013", datetime(2013, 8, 23, 0, 0, tzinfo=timezone.utc)), ("27-11-2014", datetime(2014, 11, 27, 0, 0, tzinfo=timezone.utc)), ("2019-09-26,", datetime(2019, 9, 26, 0, 0, tzinfo=timezone.utc)), ("9/25/2014", datetime(2014, 9, 25, 0, 0, tzinfo=timezone.utc)), ( "Fri Jun 27 17:23:53 2014", datetime(2014, 6, 27, 17, 23, 53, tzinfo=timezone.utc), ), ("28-04-2014", datetime(2014, 4, 28, 0, 0, tzinfo=timezone.utc)), ("04-14-2014", datetime(2014, 4, 14, 0, 0, tzinfo=timezone.utc)), ( "2019-05-08 14:17:31 UTC", datetime(2019, 5, 8, 14, 17, 31, tzinfo=timezone.utc), ), ( "Wed May 21 13:50:39 CEST 2014", datetime(2014, 5, 21, 13, 50, 39, tzinfo=tzlocal()), ), ( "2018-04-10 00:01:04 KST", datetime(2018, 4, 10, 0, 1, 4, tzinfo=timezone.utc), ), ("2019-08-25 10:45", datetime(2019, 8, 25, 10, 45, tzinfo=timezone.utc)), ("March 9, 2015", datetime(2015, 3, 9, 0, 0, tzinfo=timezone.utc)), ("Aug. 18, 2012", datetime(2012, 8, 18, 0, 0, tzinfo=timezone.utc)), ("2014-Dec-17", datetime(2014, 12, 17, 0, 0, tzinfo=timezone.utc)), ("March 01, 2013", datetime(2013, 3, 1, 0, 0, tzinfo=timezone.utc)), ("2017-04-08.", datetime(2017, 4, 8, 0, 0, tzinfo=timezone.utc)), ("2014-Apr-22", datetime(2014, 4, 22, 0, 0, tzinfo=timezone.utc)), ( "Mon Jan 12 19:54:04 2015", datetime(2015, 1, 12, 19, 54, 4, tzinfo=timezone.utc), ), ("May 22, 2014", datetime(2014, 5, 22, 0, 0, tzinfo=timezone.utc)), ( "2014-08-12 09:55:10 EDT", datetime(2014, 8, 12, 9, 55, 10, tzinfo=timezone.utc), ), # unparsable ("Fabruary 21, 2012", None), ('2019-05-28"', None), ("2017-03-01 today", None), ("2016-11-0110.1093/icesjms/fsw182", None), ("2019-07-010", None), ("2015-02.23", None), ("20013-12-30", None), ("2016-08-017", None), ("2019-02-07l", None), ("2018-05-010", None), ("2019-09-27 KST", None), ("$Date$", None), ("2019-09-27 KST", None), ("2019-06-22 $Date$", None), ("$Date: 2013-01-18 12:49:03 -0600 (Fri, 18 Jan 2013) $", None), ("2015-7-013", None), ("2018-05-023", None), ("Check NEWS file for changes: news(package='simSummary')", None), ] for date, expected_date in data: actual_tstz = parse_date(date) if expected_date is None: assert actual_tstz is None, date else: expected_tstz = TimestampWithTimezone.from_datetime(expected_date) assert actual_tstz == expected_tstz, date @pytest.mark.fs def test_cran_extract_intrinsic_metadata(tmp_path, datadir): """Parsing existing archive's PKG-INFO should yield results""" uncompressed_archive_path = str(tmp_path) # sample url # https://cran.r-project.org/src_contrib_1.4.0_Recommended_KernSmooth_2.22-6.tar.gz # noqa archive_path = path.join( datadir, "https_cran.r-project.org", "src_contrib_1.4.0_Recommended_KernSmooth_2.22-6.tar.gz", ) uncompress(archive_path, dest=uncompressed_archive_path) actual_metadata = extract_intrinsic_metadata(uncompressed_archive_path) expected_metadata = { "Package": "KernSmooth", "Priority": "recommended", "Version": "2.22-6", "Date": "2001-June-08", "Title": "Functions for kernel smoothing for Wand & Jones (1995)", "Author": "S original by Matt Wand.\n\tR port by Brian Ripley .", # noqa "Maintainer": "Brian Ripley ", "Description": 'functions for kernel smoothing (and density estimation)\n corresponding to the book: \n Wand, M.P. and Jones, M.C. (1995) "Kernel Smoothing".', # noqa "License": "Unlimited use and distribution (see LICENCE).", "URL": "http://www.biostat.harvard.edu/~mwand", } assert actual_metadata == expected_metadata @pytest.mark.fs def test_cran_extract_intrinsic_metadata_failures(tmp_path): """Parsing inexistent path/archive/PKG-INFO yield None""" # inexistent first level path assert extract_intrinsic_metadata("/something-inexistent") == {} # inexistent second level path (as expected by pypi archives) assert extract_intrinsic_metadata(tmp_path) == {} # inexistent PKG-INFO within second level path existing_path_no_pkginfo = str(tmp_path / "something") os.mkdir(existing_path_no_pkginfo) assert extract_intrinsic_metadata(tmp_path) == {} def test_cran_one_visit(swh_storage, requests_mock_datadir): version = "2.22-6" base_url = "https://cran.r-project.org" origin_url = f"{base_url}/Packages/Recommended_KernSmooth/index.html" artifact_url = ( f"{base_url}/src_contrib_1.4.0_Recommended_KernSmooth_{version}.tar.gz" # noqa ) loader = CRANLoader( swh_storage, origin_url, artifacts=[ { "url": artifact_url, "version": version, "package": "Recommended_KernSmooth", } ], ) actual_load_status = loader.load() assert actual_load_status == { "status": "eventful", "snapshot_id": SNAPSHOT.id.hex(), } assert_last_visit_matches( swh_storage, origin_url, status="full", type="cran", snapshot=SNAPSHOT.id ) check_snapshot(SNAPSHOT, swh_storage) assert swh_storage.release_get([RELEASE_ID])[0] == Release( id=RELEASE_ID, name=b"2.22-6", message=( b"Synthetic release for CRAN source package " b"Recommended_KernSmooth version 2.22-6\n" ), target=hash_to_bytes("ff64177fea3f4a5136b9caf7581a4f7d4cf65296"), target_type=ObjectType.DIRECTORY, synthetic=True, author=Person( fullname=b"Brian Ripley ", name=b"Brian Ripley", email=b"ripley@stats.ox.ac.uk", ), date=TimestampWithTimezone.from_datetime( datetime(2001, 6, 8, 0, 0, tzinfo=timezone.utc) ), ) visit_stats = get_stats(swh_storage) assert { "content": 33, "directory": 7, "origin": 1, "origin_visit": 1, "release": 1, "revision": 0, "skipped_content": 0, "snapshot": 1, } == visit_stats urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith(base_url) ] # visited each artifact once across 2 visits assert len(urls) == 1 def test_cran_2_visits_same_origin(swh_storage, requests_mock_datadir): """Multiple visits on the same origin, only 1 archive fetch""" version = "2.22-6" base_url = "https://cran.r-project.org" origin_url = f"{base_url}/Packages/Recommended_KernSmooth/index.html" artifact_url = ( f"{base_url}/src_contrib_1.4.0_Recommended_KernSmooth_{version}.tar.gz" # noqa ) loader = CRANLoader( swh_storage, origin_url, artifacts=[ { "url": artifact_url, "version": version, "package": "Recommended_KernSmooth", } ], ) # first visit actual_load_status = loader.load() assert actual_load_status == { "status": "eventful", "snapshot_id": SNAPSHOT.id.hex(), } check_snapshot(SNAPSHOT, swh_storage) assert_last_visit_matches( swh_storage, origin_url, status="full", type="cran", snapshot=SNAPSHOT.id ) visit_stats = get_stats(swh_storage) assert { "content": 33, "directory": 7, "origin": 1, "origin_visit": 1, "release": 1, "revision": 0, "skipped_content": 0, "snapshot": 1, } == visit_stats # second visit actual_load_status2 = loader.load() assert actual_load_status2 == { "status": "uneventful", "snapshot_id": SNAPSHOT.id.hex(), } assert_last_visit_matches( - swh_storage, origin_url, status="full", type="cran", snapshot=SNAPSHOT.id, + swh_storage, + origin_url, + status="full", + type="cran", + snapshot=SNAPSHOT.id, ) visit_stats2 = get_stats(swh_storage) visit_stats["origin_visit"] += 1 assert visit_stats2 == visit_stats, "same stats as 1st visit, +1 visit" urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith(base_url) ] assert len(urls) == 1, "visited one time artifact url (across 2 visits)" def test_cran_parse_debian_control(datadir): description_file = os.path.join(datadir, "description", "acepack") actual_metadata = parse_debian_control(description_file) assert actual_metadata == { "Package": "acepack", "Maintainer": "Shawn Garbett", "Version": "1.4.1", "Author": "Phil Spector, Jerome Friedman, Robert Tibshirani...", "Description": "Two nonparametric methods for multiple regression...", "Title": "ACE & AVAS 4 Selecting Multiple Regression Transformations", "License": "MIT + file LICENSE", "Suggests": "testthat", "Packaged": "2016-10-28 15:38:59 UTC; garbetsp", "Repository": "CRAN", "Date/Publication": "2016-10-29 00:11:52", "NeedsCompilation": "yes", } def test_cran_parse_debian_control_unicode_issue(datadir): # iso-8859-1 caused failure, now fixed description_file = os.path.join(datadir, "description", "KnownBR") actual_metadata = parse_debian_control(description_file) assert actual_metadata == { "Package": "KnowBR", "Version": "2.0", "Title": """Discriminating Well Surveyed Spatial Units from Exhaustive Biodiversity Databases""", "Author": "Cástor Guisande González and Jorge M. Lobo", "Maintainer": "Cástor Guisande González ", "Description": "It uses species accumulation curves and diverse estimators...", "License": "GPL (>= 2)", "Encoding": "latin1", "Depends": "R (>= 3.0), fossil, mgcv, plotrix, sp, vegan", "Suggests": "raster, rgbif", "NeedsCompilation": "no", "Packaged": "2019-01-30 13:27:29 UTC; castor", "Repository": "CRAN", "Date/Publication": "2019-01-31 20:53:50 UTC", } @pytest.mark.parametrize( "method_name", - ["build_extrinsic_snapshot_metadata", "build_extrinsic_origin_metadata",], + [ + "build_extrinsic_snapshot_metadata", + "build_extrinsic_origin_metadata", + ], ) def test_cran_fail_to_build_or_load_extrinsic_metadata( method_name, swh_storage, requests_mock_datadir ): - """problem during loading: {visit: failed, status: failed, no snapshot} - - """ + """problem during loading: {visit: failed, status: failed, no snapshot}""" version = "2.22-6" base_url = "https://cran.r-project.org" origin_url = f"{base_url}/Packages/Recommended_KernSmooth/index.html" artifact_url = ( f"{base_url}/src_contrib_1.4.0_Recommended_KernSmooth_{version}.tar.gz" # noqa ) full_method_name = f"swh.loader.package.cran.loader.CRANLoader.{method_name}" with patch( full_method_name, side_effect=ValueError("Fake to fail to build or load extrinsic metadata"), ): loader = CRANLoader( swh_storage, origin_url, artifacts=[ { "url": artifact_url, "version": version, "package": "Recommended_KernSmooth", } ], ) actual_load_status = loader.load() assert actual_load_status == { "status": "failed", "snapshot_id": SNAPSHOT.id.hex(), } visit_stats = get_stats(swh_storage) assert { "content": 33, "directory": 7, "origin": 1, "origin_visit": 1, "release": 1, "revision": 0, "skipped_content": 0, "snapshot": 1, } == visit_stats assert_last_visit_matches( swh_storage, origin_url, status="partial", type="cran", snapshot=SNAPSHOT.id ) diff --git a/swh/loader/package/cran/tests/test_tasks.py b/swh/loader/package/cran/tests/test_tasks.py index f944f0c..ae8a604 100644 --- a/swh/loader/package/cran/tests/test_tasks.py +++ b/swh/loader/package/cran/tests/test_tasks.py @@ -1,23 +1,24 @@ # Copyright (C) 2019-2021 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 def test_tasks_cran_loader( mocker, swh_scheduler_celery_app, swh_scheduler_celery_worker, swh_config ): mock_load = mocker.patch("swh.loader.package.cran.loader.CRANLoader.load") mock_load.return_value = {"status": "eventful"} res = swh_scheduler_celery_app.send_task( "swh.loader.package.cran.tasks.LoadCRAN", kwargs=dict( - url="some-url", artifacts=[{"version": "1.2.3", "url": "artifact-url"}], + url="some-url", + artifacts=[{"version": "1.2.3", "url": "artifact-url"}], ), ) assert res res.wait() assert res.successful() assert mock_load.called assert res.result == {"status": "eventful"} diff --git a/swh/loader/package/debian/loader.py b/swh/loader/package/debian/loader.py index b5ec9dc..284a473 100644 --- a/swh/loader/package/debian/loader.py +++ b/swh/loader/package/debian/loader.py @@ -1,462 +1,467 @@ # Copyright (C) 2017-2021 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 logging from os import path import re import subprocess from typing import Any, Dict, Iterator, List, Mapping, Optional, Sequence, Tuple import attr from dateutil.parser import parse as parse_date from debian.changelog import Changelog from debian.deb822 import Dsc from swh.loader.package.loader import BasePackageInfo, PackageLoader, PartialExtID from swh.loader.package.utils import download, release_name from swh.model.hashutil import hash_to_bytes from swh.model.model import ObjectType, Person, Release, Sha1Git, TimestampWithTimezone from swh.storage.interface import StorageInterface logger = logging.getLogger(__name__) UPLOADERS_SPLIT = re.compile(r"(?<=\>)\s*,\s*") EXTID_TYPE = "dsc-sha256" EXTID_VERSION = 1 class DscCountError(ValueError): """Raised when an unexpected number of .dsc files is seen""" pass @attr.s class DebianFileMetadata: name = attr.ib(type=str) """Filename""" size = attr.ib(type=int) uri = attr.ib(type=str) """URL of this specific file""" # all checksums are not always available, make them optional sha256 = attr.ib(type=str, default="") md5sum = attr.ib(type=str, default="") sha1 = attr.ib(type=str, default="") # Some of the DSC files imported in swh apparently had a Checksums-SHA512 # field which got recorded in the archive. Current versions of dpkg-source # don't seem to generate them, but keep the field available for # future-proofing. sha512 = attr.ib(type=str, default="") @attr.s class DebianPackageChangelog: person = attr.ib(type=Dict[str, str]) """A dict with fields like, model.Person, except they are str instead of bytes, and 'email' is optional.""" date = attr.ib(type=str) """Date of the changelog entry.""" history = attr.ib(type=List[Tuple[str, str]]) """List of tuples (package_name, version)""" @attr.s class DebianPackageInfo(BasePackageInfo): raw_info = attr.ib(type=Dict[str, Any]) files = attr.ib(type=Dict[str, DebianFileMetadata]) """Metadata of the files (.deb, .dsc, ...) of the package.""" name = attr.ib(type=str) intrinsic_version = attr.ib(type=str) """eg. ``0.7.2-3``, while :attr:`version` would be ``stretch/contrib/0.7.2-3``""" @classmethod def from_metadata( cls, a_metadata: Dict[str, Any], url: str, version: str ) -> "DebianPackageInfo": intrinsic_version = a_metadata["version"] assert "/" in version and "/" not in intrinsic_version, ( version, intrinsic_version, ) return cls( url=url, filename=None, version=version, raw_info=a_metadata, files={ file_name: DebianFileMetadata(**file_metadata) for (file_name, file_metadata) in a_metadata.get("files", {}).items() }, name=a_metadata["name"], intrinsic_version=intrinsic_version, ) def extid(self) -> Optional[PartialExtID]: dsc_files = [ file for (name, file) in self.files.items() if name.endswith(".dsc") ] if len(dsc_files) != 1: raise DscCountError( f"Expected exactly one .dsc file for package {self.name}, " f"got {len(dsc_files)}" ) return (EXTID_TYPE, EXTID_VERSION, hash_to_bytes(dsc_files[0].sha256)) @attr.s class IntrinsicPackageMetadata: """Metadata extracted from a package's .dsc file.""" name = attr.ib(type=str) version = attr.ib(type=str) changelog = attr.ib(type=DebianPackageChangelog) maintainers = attr.ib(type=List[Dict[str, str]]) """A list of dicts with fields like, model.Person, except they are str instead of bytes, and 'email' is optional.""" class DebianLoader(PackageLoader[DebianPackageInfo]): - """Load debian origins into swh archive. - - """ + """Load debian origins into swh archive.""" visit_type = "deb" def __init__( self, storage: StorageInterface, url: str, packages: Mapping[str, Any], max_content_size: Optional[int] = None, ): """Debian Loader implementation. Args: url: Origin url (e.g. deb://Debian/packages/cicero) date: Ignored packages: versioned packages and associated artifacts, example:: { 'stretch/contrib/0.7.2-3': { 'name': 'cicero', 'version': '0.7.2-3' 'files': { 'cicero_0.7.2-3.diff.gz': { 'md5sum': 'a93661b6a48db48d59ba7d26796fc9ce', 'name': 'cicero_0.7.2-3.diff.gz', 'sha256': 'f039c9642fe15c75bed5254315e2a29f...', 'size': 3964, 'uri': 'http://d.d.o/cicero_0.7.2-3.diff.gz', }, 'cicero_0.7.2-3.dsc': { 'md5sum': 'd5dac83eb9cfc9bb52a15eb618b4670a', 'name': 'cicero_0.7.2-3.dsc', 'sha256': '35b7f1048010c67adfd8d70e4961aefb...', 'size': 1864, 'uri': 'http://d.d.o/cicero_0.7.2-3.dsc', }, 'cicero_0.7.2.orig.tar.gz': { 'md5sum': '4353dede07c5728319ba7f5595a7230a', 'name': 'cicero_0.7.2.orig.tar.gz', 'sha256': '63f40f2436ea9f67b44e2d4bd669dbab...', 'size': 96527, 'uri': 'http://d.d.o/cicero_0.7.2.orig.tar.gz', } }, }, # ... } """ super().__init__(storage=storage, url=url, max_content_size=max_content_size) self.packages = packages def get_versions(self) -> Sequence[str]: """Returns the keys of the packages input (e.g. - stretch/contrib/0.7.2-3, etc...) + stretch/contrib/0.7.2-3, etc...) """ return list(self.packages.keys()) def get_package_info(self, version: str) -> Iterator[Tuple[str, DebianPackageInfo]]: meta = self.packages[version] p_info = DebianPackageInfo.from_metadata(meta, url=self.url, version=version) yield release_name(version), p_info def download_package( self, p_info: DebianPackageInfo, tmpdir: str ) -> List[Tuple[str, Mapping]]: """Contrary to other package loaders (1 package, 1 artifact), `p_info.files` represents the package's datafiles set to fetch: - .orig.tar.gz - .dsc - .diff.gz This is delegated to the `download_package` function. """ all_hashes = download_package(p_info, tmpdir) logger.debug("all_hashes: %s", all_hashes) res = [] for hashes in all_hashes.values(): res.append((tmpdir, hashes)) logger.debug("res: %s", res) return res def uncompress( self, dl_artifacts: List[Tuple[str, Mapping[str, Any]]], dest: str ) -> str: logger.debug("dl_artifacts: %s", dl_artifacts) return extract_package(dl_artifacts, dest=dest) def build_release( - self, p_info: DebianPackageInfo, uncompressed_path: str, directory: Sha1Git, + self, + p_info: DebianPackageInfo, + uncompressed_path: str, + directory: Sha1Git, ) -> Optional[Release]: dsc_url, dsc_name = dsc_information(p_info) if not dsc_name: raise ValueError("dsc name for url %s should not be None" % dsc_url) dsc_path = path.join(path.dirname(uncompressed_path), dsc_name) intrinsic_metadata = get_intrinsic_package_metadata( p_info, dsc_path, uncompressed_path ) logger.debug("intrinsic_metadata: %s", intrinsic_metadata) logger.debug("p_info: %s", p_info) msg = ( f"Synthetic release for Debian source package {p_info.name} " f"version {p_info.intrinsic_version}\n" ) author = prepare_person(intrinsic_metadata.changelog.person) date = TimestampWithTimezone.from_iso8601(intrinsic_metadata.changelog.date) # inspired from swh.loader.debian.converters.package_metadata_to_revision return Release( name=p_info.intrinsic_version.encode(), message=msg.encode(), author=author, date=date, target=directory, target_type=ObjectType.DIRECTORY, synthetic=True, ) def uid_to_person(uid: str) -> Dict[str, str]: """Convert an uid to a person suitable for insertion. Args: uid: an uid of the form "Name " Returns: a dictionary with the following keys: - name: the name associated to the uid - email: the mail associated to the uid - fullname: the actual uid input """ person = Person.from_fullname(uid.encode("utf-8")) return {k: v.decode("utf-8") for k, v in person.to_dict().items() if v is not None} def prepare_person(person: Mapping[str, str]) -> Person: """Prepare person for swh serialization... Args: A person dict Returns: A person ready for storage """ return Person.from_dict( {key: value.encode("utf-8") for (key, value) in person.items()} ) def download_package(p_info: DebianPackageInfo, tmpdir: Any) -> Mapping[str, Any]: """Fetch a source package in a temporary directory and check the checksums for all files. Args: p_info: Information on a package tmpdir: Where to download and extract the files to ingest Returns: Dict of swh hashes per filename key """ all_hashes = {} for filename, fileinfo in p_info.files.items(): uri = fileinfo.uri logger.debug("fileinfo: %s", fileinfo) extrinsic_hashes = {"md5": fileinfo.md5sum} if fileinfo.sha256: extrinsic_hashes["sha256"] = fileinfo.sha256 if fileinfo.sha1: extrinsic_hashes["sha1"] = fileinfo.sha1 logger.debug("extrinsic_hashes(%s): %s", filename, extrinsic_hashes) _, hashes = download( uri, dest=tmpdir, filename=filename, hashes=extrinsic_hashes ) all_hashes[filename] = hashes logger.debug("all_hashes: %s", all_hashes) return all_hashes def dsc_information(p_info: DebianPackageInfo) -> Tuple[Optional[str], Optional[str]]: """Retrieve dsc information from a package. Args: p_info: Package metadata information Returns: Tuple of dsc file's uri, dsc's full disk path """ dsc_name = None dsc_url = None for filename, fileinfo in p_info.files.items(): if filename.endswith(".dsc"): if dsc_name: raise DscCountError( "Package %s_%s references several dsc files." % (p_info.name, p_info.intrinsic_version) ) dsc_url = fileinfo.uri dsc_name = filename return dsc_url, dsc_name def extract_package(dl_artifacts: List[Tuple[str, Mapping]], dest: str) -> str: """Extract a Debian source package to a given directory. Note that after extraction the target directory will be the root of the extracted package, rather than containing it. Args: package: package information dictionary dest: directory where the package files are stored Returns: Package extraction directory """ a_path = dl_artifacts[0][0] logger.debug("dl_artifacts: %s", dl_artifacts) for _, hashes in dl_artifacts: logger.debug("hashes: %s", hashes) filename = hashes["filename"] if filename.endswith(".dsc"): dsc_name = filename break dsc_path = path.join(a_path, dsc_name) destdir = path.join(dest, "extracted") logfile = path.join(dest, "extract.log") logger.debug( "extract Debian source package %s in %s" % (dsc_path, destdir), - extra={"swh_type": "deb_extract", "swh_dsc": dsc_path, "swh_destdir": destdir,}, + extra={ + "swh_type": "deb_extract", + "swh_dsc": dsc_path, + "swh_destdir": destdir, + }, ) cmd = [ "dpkg-source", "--no-copy", "--no-check", "--ignore-bad-version", "-x", dsc_path, destdir, ] try: with open(logfile, "w") as stdout: subprocess.check_call(cmd, stdout=stdout, stderr=subprocess.STDOUT) except subprocess.CalledProcessError as e: logdata = open(logfile, "r").read() raise ValueError( "dpkg-source exited with code %s: %s" % (e.returncode, logdata) ) from None return destdir def get_intrinsic_package_metadata( p_info: DebianPackageInfo, dsc_path: str, extracted_path: str ) -> IntrinsicPackageMetadata: """Get the package metadata from the source package at dsc_path, extracted in extracted_path. Args: p_info: the package information dsc_path: path to the package's dsc file extracted_path: the path where the package got extracted Returns: dict: a dictionary with the following keys: - history: list of (package_name, package_version) tuples parsed from the package changelog """ with open(dsc_path, "rb") as dsc: parsed_dsc = Dsc(dsc) # Parse the changelog to retrieve the rest of the package information changelog_path = path.join(extracted_path, "debian/changelog") with open(changelog_path, "rb") as changelog_file: try: parsed_changelog = Changelog(changelog_file) except UnicodeDecodeError: logger.warning( "Unknown encoding for changelog %s," " falling back to iso" % changelog_path, extra={ "swh_type": "deb_changelog_encoding", "swh_name": p_info.name, "swh_version": str(p_info.version), "swh_changelog": changelog_path, }, ) # need to reset as Changelog scrolls to the end of the file changelog_file.seek(0) parsed_changelog = Changelog(changelog_file, encoding="iso-8859-15") history: List[Tuple[str, str]] = [] for block in parsed_changelog: assert block.package is not None history.append((block.package, str(block.version))) changelog = DebianPackageChangelog( person=uid_to_person(parsed_changelog.author), date=parse_date(parsed_changelog.date).isoformat(), history=history[1:], ) maintainers = [ uid_to_person(parsed_dsc["Maintainer"]), ] maintainers.extend( uid_to_person(person) for person in UPLOADERS_SPLIT.split(parsed_dsc.get("Uploaders", "")) ) return IntrinsicPackageMetadata( name=p_info.name, version=str(p_info.intrinsic_version), changelog=changelog, maintainers=maintainers, ) diff --git a/swh/loader/package/debian/tests/test_debian.py b/swh/loader/package/debian/tests/test_debian.py index 3042870..0864ac2 100644 --- a/swh/loader/package/debian/tests/test_debian.py +++ b/swh/loader/package/debian/tests/test_debian.py @@ -1,542 +1,551 @@ # Copyright (C) 2019-2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from copy import deepcopy import datetime import hashlib import logging from os import path import pytest import requests from swh.loader.package.debian.loader import ( DebianLoader, DebianPackageChangelog, DebianPackageInfo, IntrinsicPackageMetadata, download_package, dsc_information, extract_package, get_intrinsic_package_metadata, prepare_person, uid_to_person, ) from swh.loader.tests import assert_last_visit_matches, check_snapshot, get_stats from swh.model.hashutil import hash_to_bytes from swh.model.model import ( ObjectType, Person, Release, Snapshot, SnapshotBranch, TargetType, TimestampWithTimezone, ) logger = logging.getLogger(__name__) URL = "deb://Debian/packages/cicero" PACKAGE_FILES = { "name": "cicero", "version": "0.7.2-3", "files": { "cicero_0.7.2-3.diff.gz": { "md5sum": "a93661b6a48db48d59ba7d26796fc9ce", "name": "cicero_0.7.2-3.diff.gz", "sha256": "f039c9642fe15c75bed5254315e2a29f9f2700da0e29d9b0729b3ffc46c8971c", # noqa "size": 3964, "uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-3.diff.gz", # noqa }, "cicero_0.7.2-3.dsc": { "md5sum": "d5dac83eb9cfc9bb52a15eb618b4670a", "name": "cicero_0.7.2-3.dsc", "sha256": "35b7f1048010c67adfd8d70e4961aefd8800eb9a83a4d1cc68088da0009d9a03", # noqa "size": 1864, "uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-3.dsc", # noqa }, # noqa "cicero_0.7.2.orig.tar.gz": { "md5sum": "4353dede07c5728319ba7f5595a7230a", "name": "cicero_0.7.2.orig.tar.gz", "sha256": "63f40f2436ea9f67b44e2d4bd669dbabe90e2635a204526c20e0b3c8ee957786", # noqa "size": 96527, "uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2.orig.tar.gz", # noqa }, }, } PACKAGE_FILES2 = { "name": "cicero", "version": "0.7.2-4", "files": { "cicero_0.7.2-4.diff.gz": { "md5sum": "1e7e6fc4a59d57c98082a3af78145734", "name": "cicero_0.7.2-4.diff.gz", "sha256": "2e6fa296ee7005473ff58d0971f4fd325617b445671480e9f2cfb738d5dbcd01", # noqa "size": 4038, "uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-4.diff.gz", # noqa }, "cicero_0.7.2-4.dsc": { "md5sum": "1a6c8855a73b4282bb31d15518f18cde", "name": "cicero_0.7.2-4.dsc", "sha256": "913ee52f7093913420de5cbe95d63cfa817f1a1daf997961149501894e754f8b", # noqa "size": 1881, "uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-4.dsc", # noqa }, # noqa "cicero_0.7.2.orig.tar.gz": { "md5sum": "4353dede07c5728319ba7f5595a7230a", "name": "cicero_0.7.2.orig.tar.gz", "sha256": "63f40f2436ea9f67b44e2d4bd669dbabe90e2635a204526c20e0b3c8ee957786", # noqa "size": 96527, "uri": "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2.orig.tar.gz", # noqa }, }, } PACKAGE_PER_VERSION = { "stretch/contrib/0.7.2-3": PACKAGE_FILES, } PACKAGES_PER_VERSION = { "stretch/contrib/0.7.2-3": PACKAGE_FILES, "buster/contrib/0.7.2-4": PACKAGE_FILES2, } def test_debian_first_visit(swh_storage, requests_mock_datadir): - """With no prior visit, load a gnu project ends up with 1 snapshot - - """ - loader = DebianLoader(swh_storage, URL, packages=PACKAGE_PER_VERSION,) + """With no prior visit, load a gnu project ends up with 1 snapshot""" + loader = DebianLoader( + swh_storage, + URL, + packages=PACKAGE_PER_VERSION, + ) actual_load_status = loader.load() expected_snapshot_id = "f9e4d0d200433dc998ad2ca40ee1244785fe6ed1" assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id, } assert_last_visit_matches( swh_storage, URL, status="full", type="deb", snapshot=hash_to_bytes(expected_snapshot_id), ) release_id = hash_to_bytes("de96ae3d3e136f5c1709117059e2a2c05b8ee5ae") expected_snapshot = Snapshot( id=hash_to_bytes(expected_snapshot_id), branches={ b"releases/stretch/contrib/0.7.2-3": SnapshotBranch( - target_type=TargetType.RELEASE, target=release_id, + target_type=TargetType.RELEASE, + target=release_id, ) }, ) # different than the previous loader as no release is done check_snapshot(expected_snapshot, swh_storage) assert swh_storage.release_get([release_id])[0] == Release( id=release_id, name=b"0.7.2-3", message=b"Synthetic release for Debian source package cicero version 0.7.2-3\n", target=hash_to_bytes("798df511408c53bf842a8e54d4d335537836bdc3"), target_type=ObjectType.DIRECTORY, synthetic=True, author=Person( fullname=b"Samuel Thibault ", name=b"Samuel Thibault", email=b"sthibault@debian.org", ), date=TimestampWithTimezone.from_datetime( datetime.datetime( 2014, 10, 19, 16, 52, 35, tzinfo=datetime.timezone(datetime.timedelta(seconds=7200)), ) ), ) stats = get_stats(swh_storage) assert { "content": 42, "directory": 2, "origin": 1, "origin_visit": 1, "release": 1, # all artifacts under 1 release "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats def test_debian_first_visit_then_another_visit(swh_storage, requests_mock_datadir): - """With no prior visit, load a debian project ends up with 1 snapshot - - """ - loader = DebianLoader(swh_storage, URL, packages=PACKAGE_PER_VERSION,) + """With no prior visit, load a debian project ends up with 1 snapshot""" + loader = DebianLoader( + swh_storage, + URL, + packages=PACKAGE_PER_VERSION, + ) actual_load_status = loader.load() expected_snapshot_id = "f9e4d0d200433dc998ad2ca40ee1244785fe6ed1" assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id, } assert_last_visit_matches( swh_storage, URL, status="full", type="deb", snapshot=hash_to_bytes(expected_snapshot_id), ) expected_snapshot = Snapshot( id=hash_to_bytes(expected_snapshot_id), branches={ b"releases/stretch/contrib/0.7.2-3": SnapshotBranch( target_type=TargetType.RELEASE, target=hash_to_bytes("de96ae3d3e136f5c1709117059e2a2c05b8ee5ae"), ) }, ) # different than the previous loader as no release is done check_snapshot(expected_snapshot, swh_storage) stats = get_stats(swh_storage) assert { "content": 42, "directory": 2, "origin": 1, "origin_visit": 1, "release": 1, # all artifacts under 1 release "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats # No change in between load actual_load_status2 = loader.load() assert actual_load_status2["status"] == "uneventful" assert_last_visit_matches( swh_storage, URL, status="full", type="deb", snapshot=hash_to_bytes(expected_snapshot_id), ) stats2 = get_stats(swh_storage) assert { "content": 42 + 0, "directory": 2 + 0, "origin": 1, "origin_visit": 1 + 1, # a new visit occurred "release": 1, "revision": 0, "skipped_content": 0, "snapshot": 1, # same snapshot across 2 visits } == stats2 urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith("http://deb.debian.org") ] # visited each package artifact twice across 2 visits assert len(urls) == len(set(urls)) def test_debian_uid_to_person(): uid = "Someone Name " actual_person = uid_to_person(uid) assert actual_person == { "name": "Someone Name", "email": "someone@orga.org", "fullname": uid, } def test_debian_prepare_person(): actual_author = prepare_person( { "name": "Someone Name", "email": "someone@orga.org", "fullname": "Someone Name ", } ) assert actual_author == Person( name=b"Someone Name", email=b"someone@orga.org", fullname=b"Someone Name ", ) def test_debian_download_package(datadir, tmpdir, requests_mock_datadir): tmpdir = str(tmpdir) # py3.5 work around (LocalPath issue) p_info = DebianPackageInfo.from_metadata( PACKAGE_FILES, url=URL, version="stretch/contrib/0.7.2-3" ) all_hashes = download_package(p_info, tmpdir) assert all_hashes == { "cicero_0.7.2-3.diff.gz": { "checksums": { "md5": "a93661b6a48db48d59ba7d26796fc9ce", "sha1": "0815282053f21601b0ec4adf7a8fe47eace3c0bc", "sha256": "f039c9642fe15c75bed5254315e2a29f9f2700da0e29d9b0729b3ffc46c8971c", # noqa }, "filename": "cicero_0.7.2-3.diff.gz", "length": 3964, "url": ( "http://deb.debian.org/debian/pool/contrib/c/cicero/" "cicero_0.7.2-3.diff.gz" ), }, "cicero_0.7.2-3.dsc": { "checksums": { "md5": "d5dac83eb9cfc9bb52a15eb618b4670a", "sha1": "abbec4e8efbbc80278236e1dd136831eac08accd", "sha256": "35b7f1048010c67adfd8d70e4961aefd8800eb9a83a4d1cc68088da0009d9a03", # noqa }, "filename": "cicero_0.7.2-3.dsc", "length": 1864, "url": ( "http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-3.dsc" ), }, "cicero_0.7.2.orig.tar.gz": { "checksums": { "md5": "4353dede07c5728319ba7f5595a7230a", "sha1": "a286efd63fe2c9c9f7bb30255c3d6fcdcf390b43", "sha256": "63f40f2436ea9f67b44e2d4bd669dbabe90e2635a204526c20e0b3c8ee957786", # noqa }, "filename": "cicero_0.7.2.orig.tar.gz", "length": 96527, "url": ( "http://deb.debian.org/debian/pool/contrib/c/cicero/" "cicero_0.7.2.orig.tar.gz" ), }, } def test_debian_dsc_information_ok(): fname = "cicero_0.7.2-3.dsc" p_info = DebianPackageInfo.from_metadata( PACKAGE_FILES, url=URL, version="stretch/contrib/0.7.2-3" ) dsc_url, dsc_name = dsc_information(p_info) assert dsc_url == PACKAGE_FILES["files"][fname]["uri"] assert dsc_name == PACKAGE_FILES["files"][fname]["name"] def test_debian_dsc_information_not_found(): fname = "cicero_0.7.2-3.dsc" p_info = DebianPackageInfo.from_metadata( PACKAGE_FILES, url=URL, version="stretch/contrib/0.7.2-3" ) p_info.files.pop(fname) dsc_url, dsc_name = dsc_information(p_info) assert dsc_url is None assert dsc_name is None def test_debian_dsc_information_missing_md5sum(): package_files = deepcopy(PACKAGE_FILES) for package_metadata in package_files["files"].values(): del package_metadata["md5sum"] p_info = DebianPackageInfo.from_metadata( package_files, url=URL, version="stretch/contrib/0.7.2-3" ) for debian_file_metadata in p_info.files.values(): assert not debian_file_metadata.md5sum def test_debian_dsc_information_extra_sha1(requests_mock_datadir): package_files = deepcopy(PACKAGE_FILES) for package_metadata in package_files["files"].values(): file_bytes = requests.get(package_metadata["uri"]).content package_metadata["sha1"] = hashlib.sha1(file_bytes).hexdigest() p_info = DebianPackageInfo.from_metadata( package_files, url=URL, version="stretch/contrib/0.7.2-3" ) for debian_file_metadata in p_info.files.values(): assert debian_file_metadata.sha1 def test_debian_dsc_information_too_many_dsc_entries(): # craft an extra dsc file fname = "cicero_0.7.2-3.dsc" p_info = DebianPackageInfo.from_metadata( PACKAGE_FILES, url=URL, version="stretch/contrib/0.7.2-3" ) data = p_info.files[fname] fname2 = fname.replace("cicero", "ciceroo") p_info.files[fname2] = data with pytest.raises( ValueError, match="Package %s_%s references several dsc" % (PACKAGE_FILES["name"], PACKAGE_FILES["version"]), ): dsc_information(p_info) def test_debian_get_intrinsic_package_metadata( requests_mock_datadir, datadir, tmp_path ): tmp_path = str(tmp_path) # py3.5 compat. p_info = DebianPackageInfo.from_metadata( PACKAGE_FILES, url=URL, version="stretch/contrib/0.7.2-3" ) logger.debug("p_info: %s", p_info) # download the packages all_hashes = download_package(p_info, tmp_path) # Retrieve information from package _, dsc_name = dsc_information(p_info) dl_artifacts = [(tmp_path, hashes) for hashes in all_hashes.values()] # Extract information from package extracted_path = extract_package(dl_artifacts, tmp_path) # Retrieve information on package dsc_path = path.join(path.dirname(extracted_path), dsc_name) actual_package_info = get_intrinsic_package_metadata( p_info, dsc_path, extracted_path ) logger.debug("actual_package_info: %s", actual_package_info) assert actual_package_info == IntrinsicPackageMetadata( changelog=DebianPackageChangelog( date="2014-10-19T16:52:35+02:00", history=[ ("cicero", "0.7.2-2"), ("cicero", "0.7.2-1"), ("cicero", "0.7-1"), ], person={ "email": "sthibault@debian.org", "fullname": "Samuel Thibault ", "name": "Samuel Thibault", }, ), maintainers=[ { "email": "debian-accessibility@lists.debian.org", "fullname": "Debian Accessibility Team " "", "name": "Debian Accessibility Team", }, { "email": "sthibault@debian.org", "fullname": "Samuel Thibault ", "name": "Samuel Thibault", }, ], name="cicero", version="0.7.2-3", ) def test_debian_multiple_packages(swh_storage, requests_mock_datadir): - loader = DebianLoader(swh_storage, URL, packages=PACKAGES_PER_VERSION,) + loader = DebianLoader( + swh_storage, + URL, + packages=PACKAGES_PER_VERSION, + ) actual_load_status = loader.load() expected_snapshot_id = "474c0e3d5796d15363031c333533527d659c559e" assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id, } assert_last_visit_matches( swh_storage, URL, status="full", type="deb", snapshot=hash_to_bytes(expected_snapshot_id), ) expected_snapshot = Snapshot( id=hash_to_bytes(expected_snapshot_id), branches={ b"releases/stretch/contrib/0.7.2-3": SnapshotBranch( target_type=TargetType.RELEASE, target=hash_to_bytes("de96ae3d3e136f5c1709117059e2a2c05b8ee5ae"), ), b"releases/buster/contrib/0.7.2-4": SnapshotBranch( target_type=TargetType.RELEASE, target=hash_to_bytes("11824484c585319302ea4fde4917faf78dfb1973"), ), }, ) check_snapshot(expected_snapshot, swh_storage) def test_debian_loader_only_md5_sum_in_dsc(swh_storage, requests_mock_datadir): packages_per_version = deepcopy(PACKAGES_PER_VERSION) for package_files in packages_per_version.values(): for package_data in package_files["files"].values(): del package_data["sha256"] loader = DebianLoader(swh_storage, URL, packages=packages_per_version) actual_load_status = loader.load() expected_snapshot_id = "474c0e3d5796d15363031c333533527d659c559e" assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id, } assert_last_visit_matches( swh_storage, URL, status="full", type="deb", snapshot=hash_to_bytes(expected_snapshot_id), ) expected_snapshot = Snapshot( id=hash_to_bytes(expected_snapshot_id), branches={ b"releases/stretch/contrib/0.7.2-3": SnapshotBranch( target_type=TargetType.RELEASE, target=hash_to_bytes("de96ae3d3e136f5c1709117059e2a2c05b8ee5ae"), ), b"releases/buster/contrib/0.7.2-4": SnapshotBranch( target_type=TargetType.RELEASE, target=hash_to_bytes("11824484c585319302ea4fde4917faf78dfb1973"), ), }, ) check_snapshot(expected_snapshot, swh_storage) diff --git a/swh/loader/package/deposit/loader.py b/swh/loader/package/deposit/loader.py index 794f33d..c679291 100644 --- a/swh/loader/package/deposit/loader.py +++ b/swh/loader/package/deposit/loader.py @@ -1,381 +1,376 @@ # Copyright (C) 2019-2021 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 datetime from datetime import timezone import json import logging from typing import Any, Dict, Iterator, List, Mapping, Optional, Sequence, Tuple, Union import attr import requests from swh.core.config import load_from_envvar from swh.loader.core.loader import DEFAULT_CONFIG from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, RawExtrinsicMetadataCore, ) from swh.loader.package.utils import cached_method, download from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, ObjectType, Person, Release, Sha1Git, TimestampWithTimezone, ) from swh.storage.algos.snapshot import snapshot_get_all_branches from swh.storage.interface import StorageInterface logger = logging.getLogger(__name__) def now() -> datetime.datetime: return datetime.datetime.now(tz=timezone.utc) @attr.s class DepositPackageInfo(BasePackageInfo): filename = attr.ib(type=str) # instead of Optional[str] author_date = attr.ib(type=datetime.datetime) """codemeta:dateCreated if any, deposit completed_date otherwise""" commit_date = attr.ib(type=datetime.datetime) """codemeta:datePublished if any, deposit completed_date otherwise""" client = attr.ib(type=str) id = attr.ib(type=int) """Internal ID of the deposit in the deposit DB""" collection = attr.ib(type=str) """The collection in the deposit; see SWORD specification.""" author = attr.ib(type=Person) committer = attr.ib(type=Person) release_notes = attr.ib(type=Optional[str]) @classmethod def from_metadata( cls, metadata: Dict[str, Any], url: str, filename: str, version: str ) -> "DepositPackageInfo": # Note: # `date` and `committer_date` are always transmitted by the deposit read api # which computes itself the values. The loader needs to use those to create the # release. raw_metadata: str = metadata["raw_metadata"] depo = metadata["deposit"] return cls( url=url, filename=filename, version=version, author_date=depo["author_date"], commit_date=depo["committer_date"], client=depo["client"], id=depo["id"], collection=depo["collection"], author=parse_author(depo["author"]), committer=parse_author(depo["committer"]), release_notes=depo["release_notes"], directory_extrinsic_metadata=[ RawExtrinsicMetadataCore( discovery_date=now(), metadata=raw_metadata.encode(), format="sword-v2-atom-codemeta-v2", ) ], ) def extid(self) -> None: # For now, we don't try to deduplicate deposits. There is little point anyway, # as it only happens when the exact same tarball was deposited twice. return None class DepositLoader(PackageLoader[DepositPackageInfo]): - """Load a deposited artifact into swh archive. - - """ + """Load a deposited artifact into swh archive.""" visit_type = "deposit" def __init__( self, storage: StorageInterface, url: str, deposit_id: str, deposit_client: "ApiClient", max_content_size: Optional[int] = None, default_filename: str = "archive.tar", ): """Constructor Args: url: Origin url to associate the artifacts/metadata to deposit_id: Deposit identity deposit_client: Deposit api client """ super().__init__(storage=storage, url=url, max_content_size=max_content_size) self.deposit_id = deposit_id self.client = deposit_client self.default_filename = default_filename @classmethod def from_configfile(cls, **kwargs: Any): """Instantiate a loader from the configuration loaded from the SWH_CONFIG_FILENAME envvar, with potential extra keyword arguments if their value is not None. Args: kwargs: kwargs passed to the loader instantiation """ config = dict(load_from_envvar(DEFAULT_CONFIG)) config.update({k: v for k, v in kwargs.items() if v is not None}) deposit_client = ApiClient(**config.pop("deposit")) return cls.from_config(deposit_client=deposit_client, **config) def get_versions(self) -> Sequence[str]: # only 1 branch 'HEAD' with no alias since we only have 1 snapshot # branch return ["HEAD"] def get_metadata_authority(self) -> MetadataAuthority: provider = self.metadata()["provider"] assert provider["provider_type"] == MetadataAuthorityType.DEPOSIT_CLIENT.value return MetadataAuthority( type=MetadataAuthorityType.DEPOSIT_CLIENT, url=provider["provider_url"], metadata={ "name": provider["provider_name"], **(provider["metadata"] or {}), }, ) def get_metadata_fetcher(self) -> MetadataFetcher: tool = self.metadata()["tool"] return MetadataFetcher( - name=tool["name"], version=tool["version"], metadata=tool["configuration"], + name=tool["name"], + version=tool["version"], + metadata=tool["configuration"], ) def get_package_info( self, version: str ) -> Iterator[Tuple[str, DepositPackageInfo]]: p_info = DepositPackageInfo.from_metadata( self.metadata(), url=self.url, filename=self.default_filename, version=version, ) yield "HEAD", p_info def download_package( self, p_info: DepositPackageInfo, tmpdir: str ) -> List[Tuple[str, Mapping]]: - """Override to allow use of the dedicated deposit client - - """ + """Override to allow use of the dedicated deposit client""" return [self.client.archive_get(self.deposit_id, tmpdir, p_info.filename)] def build_release( - self, p_info: DepositPackageInfo, uncompressed_path: str, directory: Sha1Git, + self, + p_info: DepositPackageInfo, + uncompressed_path: str, + directory: Sha1Git, ) -> Optional[Release]: message = ( f"{p_info.client}: Deposit {p_info.id} in collection {p_info.collection}" ) if p_info.release_notes: message += "\n\n" + p_info.release_notes if not message.endswith("\n"): message += "\n" return Release( name=p_info.version.encode(), message=message.encode(), author=p_info.author, date=TimestampWithTimezone.from_dict(p_info.author_date), target=directory, target_type=ObjectType.DIRECTORY, synthetic=True, ) def get_extrinsic_origin_metadata(self) -> List[RawExtrinsicMetadataCore]: metadata = self.metadata() raw_metadata: str = metadata["raw_metadata"] origin_metadata = json.dumps( { "metadata": [raw_metadata], "provider": metadata["provider"], "tool": metadata["tool"], } ).encode() return [ RawExtrinsicMetadataCore( discovery_date=now(), metadata=raw_metadata.encode(), format="sword-v2-atom-codemeta-v2", ), RawExtrinsicMetadataCore( discovery_date=now(), metadata=origin_metadata, format="original-artifacts-json", ), ] @cached_method def metadata(self): """Returns metadata from the deposit server""" return self.client.metadata_get(self.deposit_id) def load(self) -> Dict: # First making sure the deposit is known on the deposit's RPC server # prior to trigger a loading try: self.metadata() except ValueError: logger.error(f"Unknown deposit {self.deposit_id}, ignoring") return {"status": "failed"} # Then usual loading return super().load() def finalize_visit( self, status_visit: str, errors: Optional[List[str]] = None, **kwargs ) -> Dict[str, Any]: r = super().finalize_visit(status_visit=status_visit, **kwargs) success = status_visit == "full" # Update deposit status try: if not success: self.client.status_update( - self.deposit_id, status="failed", errors=errors, + self.deposit_id, + status="failed", + errors=errors, ) return r snapshot_id = hash_to_bytes(r["snapshot_id"]) snapshot = snapshot_get_all_branches(self.storage, snapshot_id) if not snapshot: return r branches = snapshot.branches logger.debug("branches: %s", branches) if not branches: return r rel_id = branches[b"HEAD"].target release = self.storage.release_get([rel_id])[0] if not release: return r # update the deposit's status to success with its # release-id and directory-id self.client.status_update( self.deposit_id, status="done", release_id=hash_to_hex(rel_id), directory_id=hash_to_hex(release.target), snapshot_id=r["snapshot_id"], origin_url=self.url, ) except Exception: logger.exception("Problem when trying to update the deposit's status") return {"status": "failed"} return r def parse_author(author) -> Person: - """See prior fixme - - """ + """See prior fixme""" return Person( fullname=author["fullname"].encode("utf-8"), name=author["name"].encode("utf-8"), email=author["email"].encode("utf-8"), ) class ApiClient: - """Private Deposit Api client - - """ + """Private Deposit Api client""" def __init__(self, url, auth: Optional[Mapping[str, str]]): self.base_url = url.rstrip("/") self.auth = None if not auth else (auth["username"], auth["password"]) def do(self, method: str, url: str, *args, **kwargs): """Internal method to deal with requests, possibly with basic http authentication. Args: method (str): supported http methods as in get/post/put Returns: The request's execution output """ method_fn = getattr(requests, method) if self.auth: kwargs["auth"] = self.auth return method_fn(url, *args, **kwargs) def archive_get( self, deposit_id: Union[int, str], tmpdir: str, filename: str ) -> Tuple[str, Dict]: - """Retrieve deposit's archive artifact locally - - """ + """Retrieve deposit's archive artifact locally""" url = f"{self.base_url}/{deposit_id}/raw/" return download(url, dest=tmpdir, filename=filename, auth=self.auth) def metadata_url(self, deposit_id: Union[int, str]) -> str: return f"{self.base_url}/{deposit_id}/meta/" def metadata_get(self, deposit_id: Union[int, str]) -> Dict[str, Any]: - """Retrieve deposit's metadata artifact as json - - """ + """Retrieve deposit's metadata artifact as json""" url = self.metadata_url(deposit_id) r = self.do("get", url) if r.ok: return r.json() msg = f"Problem when retrieving deposit metadata at {url}" logger.error(msg) raise ValueError(msg) def status_update( self, deposit_id: Union[int, str], status: str, errors: Optional[List[str]] = None, release_id: Optional[str] = None, directory_id: Optional[str] = None, snapshot_id: Optional[str] = None, origin_url: Optional[str] = None, ): """Update deposit's information including status, and persistent - identifiers result of the loading. + identifiers result of the loading. """ url = f"{self.base_url}/{deposit_id}/update/" payload: Dict[str, Any] = {"status": status} if release_id: payload["release_id"] = release_id if directory_id: payload["directory_id"] = directory_id if snapshot_id: payload["snapshot_id"] = snapshot_id if origin_url: payload["origin_url"] = origin_url if errors: payload["status_detail"] = {"loading": errors} self.do("put", url, json=payload) diff --git a/swh/loader/package/deposit/tests/conftest.py b/swh/loader/package/deposit/tests/conftest.py index a326aa1..6fa1d9b 100644 --- a/swh/loader/package/deposit/tests/conftest.py +++ b/swh/loader/package/deposit/tests/conftest.py @@ -1,30 +1,33 @@ # Copyright (C) 2019-2021 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 from typing import Any, Dict import pytest from swh.loader.package.deposit.loader import ApiClient @pytest.fixture def swh_loader_config(swh_loader_config) -> Dict[str, Any]: config = copy.deepcopy(swh_loader_config) config.update( { "deposit": { "url": "https://deposit.softwareheritage.org/1/private", - "auth": {"username": "user", "password": "pass",}, + "auth": { + "username": "user", + "password": "pass", + }, }, } ) return config @pytest.fixture def deposit_client(swh_loader_config): return ApiClient(**swh_loader_config["deposit"]) diff --git a/swh/loader/package/deposit/tests/test_deposit.py b/swh/loader/package/deposit/tests/test_deposit.py index 64476a4..f1a0921 100644 --- a/swh/loader/package/deposit/tests/test_deposit.py +++ b/swh/loader/package/deposit/tests/test_deposit.py @@ -1,557 +1,565 @@ # Copyright (C) 2019-2021 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 datetime import json import re import pytest from swh.core.pytest_plugin import requests_mock_datadir_factory from swh.loader.package.deposit.loader import ApiClient, DepositLoader from swh.loader.package.loader import now from swh.loader.tests import assert_last_visit_matches, check_snapshot, get_stats from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.model.model import ( Origin, Person, RawExtrinsicMetadata, Release, Snapshot, SnapshotBranch, TargetType, TimestampWithTimezone, ) from swh.model.model import MetadataAuthority, MetadataAuthorityType, MetadataFetcher from swh.model.model import ObjectType as ModelObjectType from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID, ObjectType DEPOSIT_URL = "https://deposit.softwareheritage.org/1/private" @pytest.fixture def requests_mock_datadir(requests_mock_datadir): """Enhance default mock data to mock put requests as the loader does some - internal update queries there. + internal update queries there. """ requests_mock_datadir.put(re.compile("https")) return requests_mock_datadir def test_deposit_init_ok(swh_storage, deposit_client, swh_loader_config): url = "some-url" deposit_id = 999 loader = DepositLoader( swh_storage, url, deposit_id, deposit_client, default_filename="archive.zip" ) # Something that does not exist assert loader.url == url assert loader.client is not None assert loader.client.base_url == swh_loader_config["deposit"]["url"] def test_deposit_from_configfile(swh_config): - """Ensure the deposit instantiation is ok - - """ + """Ensure the deposit instantiation is ok""" loader = DepositLoader.from_configfile( url="some-url", deposit_id="666", default_filename="archive.zip" ) assert isinstance(loader.client, ApiClient) def test_deposit_loading_unknown_deposit( swh_storage, deposit_client, requests_mock_datadir ): """Loading an unknown deposit should fail no origin, no visit, no snapshot """ # private api url form: 'https://deposit.s.o/1/private/hal/666/raw/' url = "some-url" unknown_deposit_id = 667 loader = DepositLoader( swh_storage, url, unknown_deposit_id, deposit_client, default_filename="archive.zip", ) # does not exist actual_load_status = loader.load() assert actual_load_status == {"status": "failed"} stats = get_stats(loader.storage) assert { "content": 0, "directory": 0, "origin": 0, "origin_visit": 0, "release": 0, "revision": 0, "skipped_content": 0, "snapshot": 0, } == stats requests_mock_datadir_missing_one = requests_mock_datadir_factory( - ignore_urls=[f"{DEPOSIT_URL}/666/raw/",] + ignore_urls=[ + f"{DEPOSIT_URL}/666/raw/", + ] ) def test_deposit_loading_failure_to_retrieve_1_artifact( swh_storage, deposit_client, requests_mock_datadir_missing_one ): - """Deposit with missing artifact ends up with an uneventful/partial visit - - """ + """Deposit with missing artifact ends up with an uneventful/partial visit""" # private api url form: 'https://deposit.s.o/1/private/hal/666/raw/' url = "some-url-2" deposit_id = 666 requests_mock_datadir_missing_one.put(re.compile("https")) loader = DepositLoader( swh_storage, url, deposit_id, deposit_client, default_filename="archive.zip" ) actual_load_status = loader.load() assert actual_load_status["status"] == "uneventful" assert actual_load_status["snapshot_id"] is not None assert_last_visit_matches(loader.storage, url, status="partial", type="deposit") stats = get_stats(loader.storage) assert { "content": 0, "directory": 0, "origin": 1, "origin_visit": 1, "release": 0, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats # Retrieve the information for deposit status update query to the deposit urls = [ m for m in requests_mock_datadir_missing_one.request_history if m.url == f"{DEPOSIT_URL}/{deposit_id}/update/" ] assert len(urls) == 1 update_query = urls[0] body = update_query.json() expected_body = { "status": "failed", "status_detail": { "loading": [ "Failed to load branch HEAD for some-url-2: Fail to query " "'https://deposit.softwareheritage.org/1/private/666/raw/'. Reason: 404" ] }, } assert body == expected_body def test_deposit_loading_ok(swh_storage, deposit_client, requests_mock_datadir): url = "https://hal-test.archives-ouvertes.fr/some-external-id" deposit_id = 666 loader = DepositLoader( swh_storage, url, deposit_id, deposit_client, default_filename="archive.zip" ) actual_load_status = loader.load() expected_snapshot_id = "338b45d87e02fb5cbf324694bc4a898623d6a30f" assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id, } assert_last_visit_matches( loader.storage, url, status="full", type="deposit", snapshot=hash_to_bytes(expected_snapshot_id), ) release_id_hex = "2566a64a27bc00362e265be9666d7606750530a1" release_id = hash_to_bytes(release_id_hex) expected_snapshot = Snapshot( id=hash_to_bytes(expected_snapshot_id), branches={ - b"HEAD": SnapshotBranch(target=release_id, target_type=TargetType.RELEASE,), + b"HEAD": SnapshotBranch( + target=release_id, + target_type=TargetType.RELEASE, + ), }, ) check_snapshot(expected_snapshot, storage=loader.storage) release = loader.storage.release_get([release_id])[0] date = TimestampWithTimezone.from_datetime( datetime.datetime(2017, 10, 7, 15, 17, 8, tzinfo=datetime.timezone.utc) ) person = Person( fullname=b"Software Heritage", name=b"Software Heritage", email=b"robot@softwareheritage.org", ) assert release == Release( id=release_id, name=b"HEAD", message=b"hal: Deposit 666 in collection hal\n", author=person, date=date, target_type=ModelObjectType.DIRECTORY, target=b"\xfd-\xf1-\xc5SL\x1d\xa1\xe9\x18\x0b\x91Q\x02\xfbo`\x1d\x19", synthetic=True, metadata=None, ) # check metadata - fetcher = MetadataFetcher(name="swh-deposit", version="0.0.1",) + fetcher = MetadataFetcher( + name="swh-deposit", + version="0.0.1", + ) authority = MetadataAuthority( type=MetadataAuthorityType.DEPOSIT_CLIENT, url="https://hal-test.archives-ouvertes.fr/", ) # Check origin metadata orig_meta = loader.storage.raw_extrinsic_metadata_get( Origin(url).swhid(), authority ) assert orig_meta.next_page_token is None raw_meta = loader.client.metadata_get(deposit_id) raw_metadata: str = raw_meta["raw_metadata"] # 2 raw metadata xml + 1 json dict assert len(orig_meta.results) == 2 orig_meta0 = orig_meta.results[0] assert orig_meta0.authority == authority assert orig_meta0.fetcher == fetcher # Check directory metadata assert release.target_type == ModelObjectType.DIRECTORY directory_swhid = CoreSWHID( object_type=ObjectType.DIRECTORY, object_id=release.target ) actual_dir_meta = loader.storage.raw_extrinsic_metadata_get( directory_swhid, authority ) assert actual_dir_meta.next_page_token is None assert len(actual_dir_meta.results) == 1 dir_meta = actual_dir_meta.results[0] assert dir_meta.authority == authority assert dir_meta.fetcher == fetcher assert dir_meta.metadata.decode() == raw_metadata # Retrieve the information for deposit status update query to the deposit urls = [ m for m in requests_mock_datadir.request_history if m.url == f"{DEPOSIT_URL}/{deposit_id}/update/" ] assert len(urls) == 1 update_query = urls[0] body = update_query.json() expected_body = { "status": "done", "release_id": release_id_hex, "directory_id": hash_to_hex(release.target), "snapshot_id": expected_snapshot_id, "origin_url": url, } assert body == expected_body stats = get_stats(loader.storage) assert { "content": 303, "directory": 12, "origin": 1, "origin_visit": 1, "release": 1, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats def test_deposit_loading_ok_2(swh_storage, deposit_client, requests_mock_datadir): - """Field dates should be se appropriately - - """ + """Field dates should be se appropriately""" external_id = "some-external-id" url = f"https://hal-test.archives-ouvertes.fr/{external_id}" deposit_id = 777 loader = DepositLoader( swh_storage, url, deposit_id, deposit_client, default_filename="archive.zip" ) actual_load_status = loader.load() expected_snapshot_id = "3449b8ff31abeacefd33cca60e3074c1649dc3a1" assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id, } assert_last_visit_matches( loader.storage, url, status="full", type="deposit", snapshot=hash_to_bytes(expected_snapshot_id), ) release_id = "ba6c9a59ae3256e765d32b211cc183dc2380aed7" expected_snapshot = Snapshot( id=hash_to_bytes(expected_snapshot_id), branches={ b"HEAD": SnapshotBranch( target=hash_to_bytes(release_id), target_type=TargetType.RELEASE ) }, ) check_snapshot(expected_snapshot, storage=loader.storage) raw_meta = loader.client.metadata_get(deposit_id) # Ensure the date fields are set appropriately in the release # Retrieve the release release = loader.storage.release_get([hash_to_bytes(release_id)])[0] assert release # swh-deposit uses the numeric 'offset_minutes' instead of the bytes offset # attribute, because its dates are always well-formed, and it can only send # JSON-serializable data. release_date_dict = { "timestamp": release.date.timestamp.to_dict(), "offset": release.date.offset_minutes(), } assert release_date_dict == raw_meta["deposit"]["author_date"] assert not release.metadata provider = { "provider_name": "hal", "provider_type": "deposit_client", "provider_url": "https://hal-test.archives-ouvertes.fr/", "metadata": None, } tool = { "name": "swh-deposit", "version": "0.0.1", "configuration": {"sword_version": "2"}, } - fetcher = MetadataFetcher(name="swh-deposit", version="0.0.1",) + fetcher = MetadataFetcher( + name="swh-deposit", + version="0.0.1", + ) authority = MetadataAuthority( type=MetadataAuthorityType.DEPOSIT_CLIENT, url="https://hal-test.archives-ouvertes.fr/", ) # Check the origin metadata swh side origin_extrinsic_metadata = loader.storage.raw_extrinsic_metadata_get( Origin(url).swhid(), authority ) assert origin_extrinsic_metadata.next_page_token is None raw_metadata: str = raw_meta["raw_metadata"] # 1 raw metadata xml + 1 json dict assert len(origin_extrinsic_metadata.results) == 2 origin_swhid = Origin(url).swhid() expected_metadata = [] origin_meta = origin_extrinsic_metadata.results[0] expected_metadata.append( RawExtrinsicMetadata( target=origin_swhid, discovery_date=origin_meta.discovery_date, metadata=raw_metadata.encode(), format="sword-v2-atom-codemeta-v2", authority=authority, fetcher=fetcher, ) ) origin_metadata = { "metadata": [raw_metadata], "provider": provider, "tool": tool, } expected_metadata.append( RawExtrinsicMetadata( target=origin_swhid, discovery_date=origin_extrinsic_metadata.results[-1].discovery_date, metadata=json.dumps(origin_metadata).encode(), format="original-artifacts-json", authority=authority, fetcher=fetcher, ) ) assert sorted(origin_extrinsic_metadata.results) == sorted(expected_metadata) # Check the release metadata swh side assert release.target_type == ModelObjectType.DIRECTORY directory_swhid = ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=release.target ) actual_directory_metadata = loader.storage.raw_extrinsic_metadata_get( directory_swhid, authority ) assert actual_directory_metadata.next_page_token is None assert len(actual_directory_metadata.results) == 1 release_swhid = CoreSWHID( object_type=ObjectType.RELEASE, object_id=hash_to_bytes(release_id) ) dir_metadata_template = RawExtrinsicMetadata( target=directory_swhid, format="sword-v2-atom-codemeta-v2", authority=authority, fetcher=fetcher, origin=url, release=release_swhid, # to satisfy the constructor discovery_date=now(), metadata=b"", ) expected_directory_metadata = [] dir_metadata = actual_directory_metadata.results[0] expected_directory_metadata.append( RawExtrinsicMetadata.from_dict( { **{ k: v for (k, v) in dir_metadata_template.to_dict().items() if k != "id" }, "discovery_date": dir_metadata.discovery_date, "metadata": raw_metadata.encode(), } ) ) assert sorted(actual_directory_metadata.results) == sorted( expected_directory_metadata ) # Retrieve the information for deposit status update query to the deposit urls = [ m for m in requests_mock_datadir.request_history if m.url == f"{DEPOSIT_URL}/{deposit_id}/update/" ] assert len(urls) == 1 update_query = urls[0] body = update_query.json() expected_body = { "status": "done", "release_id": release_id, "directory_id": hash_to_hex(release.target), "snapshot_id": expected_snapshot_id, "origin_url": url, } assert body == expected_body def test_deposit_loading_ok_3(swh_storage, deposit_client, requests_mock_datadir): """Deposit loading can happen on tarball artifacts as well The latest deposit changes introduce the internal change. """ external_id = "hal-123456" url = f"https://hal-test.archives-ouvertes.fr/{external_id}" deposit_id = 888 loader = DepositLoader(swh_storage, url, deposit_id, deposit_client) actual_load_status = loader.load() expected_snapshot_id = "4677843de89e398f1d6bfedc9ca9b89c451c55c8" assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id, } assert_last_visit_matches( loader.storage, url, status="full", type="deposit", snapshot=hash_to_bytes(expected_snapshot_id), ) def test_deposit_loading_ok_release_notes( swh_storage, deposit_client, requests_mock_datadir ): url = "https://hal-test.archives-ouvertes.fr/some-external-id" deposit_id = 999 loader = DepositLoader( swh_storage, url, deposit_id, deposit_client, default_filename="archive.zip" ) actual_load_status = loader.load() expected_snapshot_id = "a307acffb7c29bebb3daf1bcb680bb3f452890a8" assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id, } assert_last_visit_matches( loader.storage, url, status="full", type="deposit", snapshot=hash_to_bytes(expected_snapshot_id), ) release_id_hex = "f5e8ec02ede57edbe061afa7fc2a07bb7d14a700" release_id = hash_to_bytes(release_id_hex) expected_snapshot = Snapshot( id=hash_to_bytes(expected_snapshot_id), branches={ - b"HEAD": SnapshotBranch(target=release_id, target_type=TargetType.RELEASE,), + b"HEAD": SnapshotBranch( + target=release_id, + target_type=TargetType.RELEASE, + ), }, ) check_snapshot(expected_snapshot, storage=loader.storage) release = loader.storage.release_get([release_id])[0] date = TimestampWithTimezone.from_datetime( datetime.datetime(2017, 10, 7, 15, 17, 8, tzinfo=datetime.timezone.utc) ) person = Person( fullname=b"Software Heritage", name=b"Software Heritage", email=b"robot@softwareheritage.org", ) assert release == Release( id=release_id, name=b"HEAD", message=( b"hal: Deposit 999 in collection hal\n\nThis release adds this and that.\n" ), author=person, date=date, target_type=ModelObjectType.DIRECTORY, target=b"\xfd-\xf1-\xc5SL\x1d\xa1\xe9\x18\x0b\x91Q\x02\xfbo`\x1d\x19", synthetic=True, metadata=None, ) diff --git a/swh/loader/package/deposit/tests/test_tasks.py b/swh/loader/package/deposit/tests/test_tasks.py index 248b88b..cd63efd 100644 --- a/swh/loader/package/deposit/tests/test_tasks.py +++ b/swh/loader/package/deposit/tests/test_tasks.py @@ -1,24 +1,27 @@ # Copyright (C) 2019-2021 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 def test_tasks_deposit_loader( mocker, swh_scheduler_celery_app, swh_scheduler_celery_worker, swh_config ): mock_loader = mocker.patch( "swh.loader.package.deposit.loader.DepositLoader.from_configfile" ) mock_loader.return_value = mock_loader mock_loader.load.return_value = {"status": "eventful"} res = swh_scheduler_celery_app.send_task( "swh.loader.package.deposit.tasks.LoadDeposit", - kwargs=dict(url="some-url", deposit_id="some-d-id",), + kwargs=dict( + url="some-url", + deposit_id="some-d-id", + ), ) assert res res.wait() assert res.successful() assert mock_loader.called assert res.result == {"status": "eventful"} diff --git a/swh/loader/package/loader.py b/swh/loader/package/loader.py index 2a73d56..fe4344e 100644 --- a/swh/loader/package/loader.py +++ b/swh/loader/package/loader.py @@ -1,1100 +1,1110 @@ # Copyright (C) 2019-2021 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 datetime import hashlib from itertools import islice import json import logging import os import string import sys import tempfile from typing import ( Any, Dict, Generic, Iterable, Iterator, List, Mapping, Optional, Sequence, Set, Tuple, TypeVar, ) import attr from requests.exceptions import ContentDecodingError import sentry_sdk from swh.core.tarball import uncompress from swh.loader.core.loader import BaseLoader from swh.loader.exception import NotFound from swh.loader.package.utils import download from swh.model import from_disk from swh.model.hashutil import hash_to_hex from swh.model.model import ( ExtID, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, ) from swh.model.model import ( Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Release, Revision, Sha1Git, Snapshot, ) from swh.model.model import ObjectType as ModelObjectType from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID, ObjectType from swh.storage.algos.snapshot import snapshot_get_latest from swh.storage.interface import StorageInterface from swh.storage.utils import now logger = logging.getLogger(__name__) SWH_METADATA_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", metadata={}, ) """Metadata authority for extrinsic metadata generated by Software Heritage. Used for metadata on "original artifacts", ie. length, filename, and checksums of downloaded archive files.""" PartialExtID = Tuple[str, int, bytes] """The ``extid_type`` and ``extid`` fields of an :class:`ExtID` object.""" @attr.s class RawExtrinsicMetadataCore: """Contains the core of the metadata extracted by a loader, that will be used to build a full RawExtrinsicMetadata object by adding object identifier, context, and provenance information.""" format = attr.ib(type=str) metadata = attr.ib(type=bytes) discovery_date = attr.ib(type=Optional[datetime.datetime], default=None) """Defaults to the visit date.""" @attr.s class BasePackageInfo: """Compute the primary key for a dict using the id_keys as primary key composite. Args: d: A dict entry to compute the primary key on id_keys: Sequence of keys to use as primary key Returns: The identity for that dict entry """ url = attr.ib(type=str) filename = attr.ib(type=Optional[str]) version = attr.ib(type=str) """Version name/number.""" MANIFEST_FORMAT: Optional[string.Template] = None """If not None, used by the default extid() implementation to format a manifest, before hashing it to produce an ExtID.""" EXTID_TYPE: str = "package-manifest-sha256" EXTID_VERSION: int = 0 # The following attribute has kw_only=True in order to allow subclasses # to add attributes. Without kw_only, attributes without default values cannot # go after attributes with default values. # See directory_extrinsic_metadata = attr.ib( - type=List[RawExtrinsicMetadataCore], default=[], kw_only=True, + type=List[RawExtrinsicMetadataCore], + default=[], + kw_only=True, ) """:term:`extrinsic metadata` collected by the loader, that will be attached to the loaded directory and added to the Metadata storage.""" # TODO: add support for metadata for releases and contents def extid(self) -> Optional[PartialExtID]: """Returns a unique intrinsic identifier of this package info, or None if this package info is not 'deduplicatable' (meaning that we will always load it, instead of checking the ExtID storage to see if we already did)""" if self.MANIFEST_FORMAT is None: return None else: manifest = self.MANIFEST_FORMAT.substitute( {k: str(v) for (k, v) in attr.asdict(self).items()} ) return ( self.EXTID_TYPE, self.EXTID_VERSION, hashlib.sha256(manifest.encode()).digest(), ) TPackageInfo = TypeVar("TPackageInfo", bound=BasePackageInfo) class PackageLoader(BaseLoader, Generic[TPackageInfo]): # Origin visit type (str) set by the loader visit_type = "" visit_date: datetime.datetime def __init__( self, storage: StorageInterface, url: str, max_content_size: Optional[int] = None, ): """Loader's constructor. This raises exception if the minimal required configuration is missing (cf. fn:`check` method). Args: storage: Storage instance url: Origin url to load data from """ super().__init__(storage=storage, max_content_size=max_content_size) self.url = url self.visit_date = datetime.datetime.now(tz=datetime.timezone.utc) def get_versions(self) -> Sequence[str]: """Return the list of all published package versions. Raises: class:`swh.loader.exception.NotFound` error when failing to read the published package versions. Returns: Sequence of published versions """ return [] def get_package_info(self, version: str) -> Iterator[Tuple[str, TPackageInfo]]: """Given a release version of a package, retrieve the associated package information for such version. Args: version: Package version Returns: (branch name, package metadata) """ yield from {} def build_release( self, p_info: TPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Release]: """Build the release from the archive metadata (extrinsic artifact metadata) and the intrinsic metadata. Args: p_info: Package information uncompressed_path: Artifact uncompressed path on disk """ raise NotImplementedError("build_release") def get_default_version(self) -> str: """Retrieve the latest release version if any. Returns: Latest version """ return "" def last_snapshot(self) -> Optional[Snapshot]: - """Retrieve the last snapshot out of the last visit. - - """ + """Retrieve the last snapshot out of the last visit.""" return snapshot_get_latest(self.storage, self.url) def new_packageinfo_to_extid(self, p_info: TPackageInfo) -> Optional[PartialExtID]: return p_info.extid() def _get_known_extids( self, packages_info: List[TPackageInfo] ) -> Dict[PartialExtID, List[CoreSWHID]]: """Compute the ExtIDs from new PackageInfo objects, searches which are already loaded in the archive, and returns them if any.""" # Compute the ExtIDs of all the new packages, grouped by extid type new_extids: Dict[Tuple[str, int], List[bytes]] = {} for p_info in packages_info: res = p_info.extid() if res is not None: (extid_type, extid_version, extid_extid) = res new_extids.setdefault((extid_type, extid_version), []).append( extid_extid ) # For each extid type, call extid_get_from_extid() with all the extids of # that type, and store them in the '(type, extid) -> target' map. known_extids: Dict[PartialExtID, List[CoreSWHID]] = {} for ((extid_type, extid_version), extids) in new_extids.items(): for extid in self.storage.extid_get_from_extid( extid_type, extids, version=extid_version ): if extid is not None: key = (extid.extid_type, extid_version, extid.extid) known_extids.setdefault(key, []).append(extid.target) return known_extids def resolve_object_from_extids( self, known_extids: Dict[PartialExtID, List[CoreSWHID]], p_info: TPackageInfo, whitelist: Set[Sha1Git], ) -> Optional[CoreSWHID]: """Resolve the revision/release from known ExtIDs and a package info object. If the artifact has already been downloaded, this will return the existing release (or revision) targeting that uncompressed artifact directory. Otherwise, this returns None. Args: known_extids: Dict built from a list of ExtID, with the target as value p_info: Package information whitelist: Any ExtID with target not in this set is filtered out Returns: None or release/revision SWHID """ new_extid = p_info.extid() if new_extid is None: return None extid_targets = set() for extid_target in known_extids.get(new_extid, []): if extid_target.object_id not in whitelist: # There is a known ExtID for this package, but its target is not # in the snapshot. # This can happen for three reasons: # # 1. a loader crashed after writing the ExtID, but before writing # the snapshot # 2. some other loader loaded the same artifact, but produced # a different revision, causing an additional ExtID object # to be written. We will probably find this loader's ExtID # in a future iteration of this loop. # Note that for now, this is impossible, as each loader has a # completely different extid_type, but this is an implementation # detail of each loader. # 3. we took a snapshot, then the package disappeared, # then we took another snapshot, and the package reappeared # # In case of 1, we must actually load the package now, # so let's do it. # TODO: detect when we are in case 3 using release_missing # or revision_missing instead of the snapshot. continue elif extid_target.object_type in (ObjectType.RELEASE, ObjectType.REVISION): extid_targets.add(extid_target) else: # Note that this case should never be reached unless there is a # collision between a revision hash and some non-revision object's # hash, but better safe than sorry. logger.warning( "%s is in the whitelist, but is not a revision/release.", hash_to_hex(extid_target.object_type), ) if extid_targets: # This is a known package version, as we have an extid to reference it. # Let's return one of them. # If there is a release extid, return it. release_extid_targets = { extid_target for extid_target in extid_targets if extid_target.object_type == ObjectType.RELEASE } # Exclude missing targets missing_releases = { CoreSWHID(object_type=ObjectType.RELEASE, object_id=id_) for id_ in self.storage.release_missing( [swhid.object_id for swhid in release_extid_targets] ) } if missing_releases: logger.error( "Found ExtIDs pointing to missing releases: %s", missing_releases ) release_extid_targets -= missing_releases extid_target2 = self.select_extid_target(p_info, release_extid_targets) if extid_target2: return extid_target2 # If there is no release extid (ie. if the package was only loaded with # older versions of this loader, which produced revision objects instead # of releases), return a revision extid when possible. revision_extid_targets = { extid_target for extid_target in extid_targets if extid_target.object_type == ObjectType.REVISION } if revision_extid_targets: assert len(extid_targets) == 1, extid_targets extid_target = list(extid_targets)[0] return extid_target # No target found (this is probably a new package version) return None def select_extid_target( self, p_info: TPackageInfo, extid_targets: Set[CoreSWHID] ) -> Optional[CoreSWHID]: """Given a list of release extid targets, choses one appropriate for the given package info. Package loaders shyould implement this if their ExtIDs may map to multiple releases, so they can fetch releases from the storage and inspect their fields to select the right one for this ``p_info``. """ if extid_targets: # The base package loader does not have the domain-specific knowledge # to select the right release -> crash if there is more than one. assert len(extid_targets) == 1, extid_targets return list(extid_targets)[0] return None def download_package( self, p_info: TPackageInfo, tmpdir: str ) -> List[Tuple[str, Mapping]]: """Download artifacts for a specific package. All downloads happen in in the tmpdir folder. Default implementation expects the artifacts package info to be about one artifact per package. Note that most implementation have 1 artifact per package. But some implementation have multiple artifacts per package (debian), some have none, the package is the artifact (gnu). Args: artifacts_package_info: Information on the package artifacts to download (url, filename, etc...) tmpdir: Location to retrieve such artifacts Returns: List of (path, computed hashes) """ try: return [download(p_info.url, dest=tmpdir, filename=p_info.filename)] except ContentDecodingError: # package might be erroneously marked as gzip compressed while is is not, # try to download its raw bytes again without attempting to uncompress # the input stream return [ download( p_info.url, dest=tmpdir, filename=p_info.filename, extra_request_headers={"Accept-Encoding": "identity"}, ) ] def uncompress( self, dl_artifacts: List[Tuple[str, Mapping[str, Any]]], dest: str ) -> str: """Uncompress the artifact(s) in the destination folder dest. Optionally, this could need to use the p_info dict for some more information (debian). """ uncompressed_path = os.path.join(dest, "src") for a_path, _ in dl_artifacts: uncompress(a_path, dest=uncompressed_path) return uncompressed_path def extra_branches(self) -> Dict[bytes, Mapping[str, Any]]: """Return an extra dict of branches that are used to update the set of branches. """ return {} def finalize_visit( self, *, snapshot: Optional[Snapshot], visit: OriginVisit, status_visit: str, status_load: str, failed_branches: List[str], errors: Optional[List[str]] = None, ) -> Dict[str, Any]: """Finalize the visit: - flush eventual unflushed data to storage - update origin visit's status - return the task's status """ self.storage.flush() snapshot_id: Optional[bytes] = None if snapshot and snapshot.id: # to prevent the snapshot.id to b"" snapshot_id = snapshot.id assert visit.visit visit_status = OriginVisitStatus( origin=self.url, visit=visit.visit, type=self.visit_type, date=now(), status=status_visit, snapshot=snapshot_id, ) self.storage.origin_visit_status_add([visit_status]) result: Dict[str, Any] = { "status": status_load, } if snapshot_id: result["snapshot_id"] = hash_to_hex(snapshot_id) if failed_branches: logger.warning("%d failed branches", len(failed_branches)) for i, urls in enumerate(islice(failed_branches, 50)): prefix_url = "Failed branches: " if i == 0 else "" logger.warning("%s%s", prefix_url, urls) return result def load(self) -> Dict: """Load for a specific origin the associated contents. 1. Get the list of versions in an origin. 2. Get the snapshot from the previous run of the loader, and filter out versions that were already loaded, if their :term:`extids ` match Then, for each remaining version in the origin 3. Fetch the files for one package version By default, this can be implemented as a simple HTTP request. Loaders with more specific requirements can override this, e.g.: the PyPI loader checks the integrity of the downloaded files; the Debian loader has to download and check several files for one package version. 4. Extract the downloaded files. By default, this would be a universal archive/tarball extraction. Loaders for specific formats can override this method (for instance, the Debian loader uses dpkg-source -x). 5. Convert the extracted directory to a set of Software Heritage objects Using swh.model.from_disk. 6. Extract the metadata from the unpacked directories This would only be applicable for "smart" loaders like npm (parsing the package.json), PyPI (parsing the PKG-INFO file) or Debian (parsing debian/changelog and debian/control). On "minimal-metadata" sources such as the GNU archive, the lister should provide the minimal set of metadata needed to populate the revision/release objects (authors, dates) as an argument to the task. 7. Generate the revision/release objects for the given version. From the data generated at steps 3 and 4. end for each 8. Generate and load the snapshot for the visit Using the revisions/releases collected at step 7., and the branch information from step 2., generate a snapshot and load it into the Software Heritage archive """ status_load = "uneventful" # either: eventful, uneventful, failed status_visit = "full" # see swh.model.model.OriginVisitStatus snapshot = None failed_branches: List[str] = [] # Prepare origin and origin_visit origin = Origin(url=self.url) try: self.storage.origin_add([origin]) visit = list( self.storage.origin_visit_add( [ OriginVisit( - origin=self.url, date=self.visit_date, type=self.visit_type, + origin=self.url, + date=self.visit_date, + type=self.visit_type, ) ] ) )[0] except Exception as e: logger.exception("Failed to initialize origin_visit for %s", self.url) sentry_sdk.capture_exception(e) return {"status": "failed"} # Get the previous snapshot for this origin. It is then used to see which # of the package's versions are already loaded in the archive. try: last_snapshot = self.last_snapshot() logger.debug("last snapshot: %s", last_snapshot) except Exception as e: logger.exception("Failed to get previous state for %s", self.url) sentry_sdk.capture_exception(e) return self.finalize_visit( snapshot=snapshot, visit=visit, failed_branches=failed_branches, status_visit="failed", status_load="failed", errors=[str(e)], ) load_exceptions: List[Exception] = [] # Get the list of all version names try: versions = self.get_versions() except NotFound as e: return self.finalize_visit( snapshot=snapshot, visit=visit, failed_branches=failed_branches, status_visit="not_found", status_load="failed", errors=[str(e)], ) except Exception as e: return self.finalize_visit( snapshot=snapshot, visit=visit, failed_branches=failed_branches, status_visit="failed", status_load="failed", errors=[str(e)], ) # Get the metadata of each version's package packages_info: List[Tuple[str, TPackageInfo]] = [ (branch_name, p_info) for version in versions for (branch_name, p_info) in self.get_package_info(version) ] # Compute the ExtID of each of these packages known_extids = self._get_known_extids([p_info for (_, p_info) in packages_info]) if last_snapshot is None: last_snapshot_targets: Set[Sha1Git] = set() else: last_snapshot_targets = { branch.target for branch in last_snapshot.branches.values() } new_extids: Set[ExtID] = set() tmp_releases: Dict[str, List[Tuple[str, Sha1Git]]] = { version: [] for version in versions } errors = [] for (branch_name, p_info) in packages_info: logger.debug("package_info: %s", p_info) # Check if the package was already loaded, using its ExtID swhid = self.resolve_object_from_extids( known_extids, p_info, last_snapshot_targets ) if swhid is not None and swhid.object_type == ObjectType.REVISION: # This package was already loaded, but by an older version # of this loader, which produced revisions instead of releases. # Let's fetch the revision's data, and "upgrade" it into a release. (rev,) = self.storage.revision_get([swhid.object_id]) if not rev: logger.error( "Failed to upgrade branch %s from revision to " "release, %s is missing from the storage. " "Falling back to re-loading from the origin.", branch_name, swhid, ) else: rev = None if swhid is None or (swhid.object_type == ObjectType.REVISION and not rev): # No matching revision or release found in the last snapshot, load it. release_id = None try: res = self._load_release(p_info, origin) if res: (release_id, directory_id) = res assert release_id assert directory_id self._load_extrinsic_directory_metadata( p_info, release_id, directory_id ) self.storage.flush() status_load = "eventful" except Exception as e: self.storage.clear_buffers() load_exceptions.append(e) sentry_sdk.capture_exception(e) error = f"Failed to load branch {branch_name} for {self.url}" logger.exception(error) failed_branches.append(branch_name) errors.append(f"{error}: {e}") continue if release_id is None: continue add_extid = True elif swhid.object_type == ObjectType.REVISION: # If 'rev' was None, the previous block would have run. assert rev is not None rel = rev2rel(rev, p_info.version) self.storage.release_add([rel]) logger.debug("Upgraded %s to %s", swhid, rel.swhid()) release_id = rel.id # Create a new extid for this package, so the next run of this loader # will be able to find the new release, and use it (instead of the # old revision) add_extid = True elif swhid.object_type == ObjectType.RELEASE: # This package was already loaded, nothing to do. release_id = swhid.object_id add_extid = False else: assert False, f"Unexpected object type: {swhid}" assert release_id is not None if add_extid: partial_extid = p_info.extid() if partial_extid is not None: (extid_type, extid_version, extid) = partial_extid release_swhid = CoreSWHID( object_type=ObjectType.RELEASE, object_id=release_id ) new_extids.add( ExtID( extid_type=extid_type, extid_version=extid_version, extid=extid, target=release_swhid, ) ) tmp_releases[p_info.version].append((branch_name, release_id)) if load_exceptions: status_visit = "partial" if not tmp_releases: # We could not load any releases; fail completely return self.finalize_visit( snapshot=snapshot, visit=visit, failed_branches=failed_branches, status_visit="failed", status_load="failed", errors=errors, ) try: # Retrieve the default release version (the "latest" one) default_version = self.get_default_version() logger.debug("default version: %s", default_version) # Retrieve extra branches extra_branches = self.extra_branches() logger.debug("extra branches: %s", extra_branches) snapshot = self._load_snapshot( default_version, tmp_releases, extra_branches ) self.storage.flush() except Exception as e: error = f"Failed to build snapshot for origin {self.url}" logger.exception(error) errors.append(f"{error}: {e}") sentry_sdk.capture_exception(e) status_visit = "failed" status_load = "failed" if snapshot: try: metadata_objects = self.build_extrinsic_snapshot_metadata(snapshot.id) self._load_metadata_objects(metadata_objects) except Exception as e: error = f"Failed to load extrinsic snapshot metadata for {self.url}" logger.exception(error) errors.append(f"{error}: {e}") sentry_sdk.capture_exception(e) status_visit = "partial" status_load = "failed" try: metadata_objects = self.build_extrinsic_origin_metadata() self._load_metadata_objects(metadata_objects) except Exception as e: error = f"Failed to load extrinsic origin metadata for {self.url}" logger.exception(error) errors.append(f"{error}: {e}") sentry_sdk.capture_exception(e) status_visit = "partial" status_load = "failed" if status_load != "failed": self._load_extids(new_extids) return self.finalize_visit( snapshot=snapshot, visit=visit, failed_branches=failed_branches, status_visit=status_visit, status_load=status_load, errors=errors, ) def _load_directory( self, dl_artifacts: List[Tuple[str, Mapping[str, Any]]], tmpdir: str ) -> Tuple[str, from_disk.Directory]: uncompressed_path = self.uncompress(dl_artifacts, dest=tmpdir) logger.debug("uncompressed_path: %s", uncompressed_path) directory = from_disk.Directory.from_disk( path=uncompressed_path.encode("utf-8"), max_content_length=self.max_content_size, ) contents, skipped_contents, directories = from_disk.iter_directory(directory) logger.debug("Number of skipped contents: %s", len(skipped_contents)) self.storage.skipped_content_add(skipped_contents) logger.debug("Number of contents: %s", len(contents)) self.storage.content_add(contents) logger.debug("Number of directories: %s", len(directories)) self.storage.directory_add(directories) return (uncompressed_path, directory) def _load_release( self, p_info: TPackageInfo, origin ) -> Optional[Tuple[Sha1Git, Sha1Git]]: """Does all the loading of a release itself: * downloads a package and uncompresses it * loads it from disk * adds contents, directories, and release to self.storage * returns (release_id, directory_id) Raises exception when unable to download or uncompress artifacts """ with tempfile.TemporaryDirectory() as tmpdir: dl_artifacts = self.download_package(p_info, tmpdir) (uncompressed_path, directory) = self._load_directory(dl_artifacts, tmpdir) # FIXME: This should be release. cf. D409 release = self.build_release( p_info, uncompressed_path, directory=directory.hash ) if not release: # Some artifacts are missing intrinsic metadata # skipping those return None metadata = [metadata for (filepath, metadata) in dl_artifacts] assert release.target is not None, release assert release.target_type == ModelObjectType.DIRECTORY, release metadata_target = ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=release.target ) original_artifact_metadata = RawExtrinsicMetadata( target=metadata_target, discovery_date=self.visit_date, authority=SWH_METADATA_AUTHORITY, fetcher=self.get_metadata_fetcher(), format="original-artifacts-json", metadata=json.dumps(metadata).encode(), origin=self.url, release=release.swhid(), ) self._load_metadata_objects([original_artifact_metadata]) logger.debug("Release: %s", release) self.storage.release_add([release]) assert directory.hash return (release.id, directory.hash) def _load_snapshot( self, default_version: str, releases: Dict[str, List[Tuple[str, bytes]]], extra_branches: Dict[bytes, Mapping[str, Any]], ) -> Optional[Snapshot]: """Build snapshot out of the current releases stored and extra branches. - Then load it in the storage. + Then load it in the storage. """ logger.debug("releases: %s", releases) # Build and load the snapshot branches = {} # type: Dict[bytes, Mapping[str, Any]] for version, branch_name_releases in releases.items(): if version == default_version and len(branch_name_releases) == 1: # only 1 branch (no ambiguity), we can create an alias # branch 'HEAD' branch_name, _ = branch_name_releases[0] # except for some corner case (deposit) if branch_name != "HEAD": branches[b"HEAD"] = { "target_type": "alias", "target": branch_name.encode("utf-8"), } for branch_name, target in branch_name_releases: branches[branch_name.encode("utf-8")] = { "target_type": "release", "target": target, } # Deal with extra-branches for name, branch_target in extra_branches.items(): if name in branches: logger.error("Extra branch '%s' has been ignored", name) else: branches[name] = branch_target snapshot_data = {"branches": branches} logger.debug("snapshot: %s", snapshot_data) snapshot = Snapshot.from_dict(snapshot_data) logger.debug("snapshot: %s", snapshot) self.storage.snapshot_add([snapshot]) return snapshot def get_loader_name(self) -> str: """Returns a fully qualified name of this loader.""" return f"{self.__class__.__module__}.{self.__class__.__name__}" def get_loader_version(self) -> str: """Returns the version of the current loader.""" module_name = self.__class__.__module__ or "" module_name_parts = module_name.split(".") # Iterate rootward through the package hierarchy until we find a parent of this # loader's module with a __version__ attribute. for prefix_size in range(len(module_name_parts), 0, -1): package_name = ".".join(module_name_parts[0:prefix_size]) module = sys.modules[package_name] if hasattr(module, "__version__"): return module.__version__ # type: ignore # If this loader's class has no parent package with a __version__, # it should implement it itself. raise NotImplementedError( f"Could not dynamically find the version of {self.get_loader_name()}." ) def get_metadata_fetcher(self) -> MetadataFetcher: """Returns a MetadataFetcher instance representing this package loader; which is used to for adding provenance information to extracted extrinsic metadata, if any.""" return MetadataFetcher( - name=self.get_loader_name(), version=self.get_loader_version(), metadata={}, + name=self.get_loader_name(), + version=self.get_loader_version(), + metadata={}, ) def get_metadata_authority(self) -> MetadataAuthority: """For package loaders that get extrinsic metadata, returns the authority the metadata are coming from. """ raise NotImplementedError("get_metadata_authority") def get_extrinsic_origin_metadata(self) -> List[RawExtrinsicMetadataCore]: """Returns metadata items, used by build_extrinsic_origin_metadata.""" return [] def build_extrinsic_origin_metadata(self) -> List[RawExtrinsicMetadata]: """Builds a list of full RawExtrinsicMetadata objects, using metadata returned by get_extrinsic_origin_metadata.""" metadata_items = self.get_extrinsic_origin_metadata() if not metadata_items: # If this package loader doesn't write metadata, no need to require # an implementation for get_metadata_authority. return [] authority = self.get_metadata_authority() fetcher = self.get_metadata_fetcher() metadata_objects = [] for item in metadata_items: metadata_objects.append( RawExtrinsicMetadata( target=Origin(self.url).swhid(), discovery_date=item.discovery_date or self.visit_date, authority=authority, fetcher=fetcher, format=item.format, metadata=item.metadata, ) ) return metadata_objects def get_extrinsic_snapshot_metadata(self) -> List[RawExtrinsicMetadataCore]: """Returns metadata items, used by build_extrinsic_snapshot_metadata.""" return [] def build_extrinsic_snapshot_metadata( self, snapshot_id: Sha1Git ) -> List[RawExtrinsicMetadata]: """Builds a list of full RawExtrinsicMetadata objects, using metadata returned by get_extrinsic_snapshot_metadata.""" metadata_items = self.get_extrinsic_snapshot_metadata() if not metadata_items: # If this package loader doesn't write metadata, no need to require # an implementation for get_metadata_authority. return [] authority = self.get_metadata_authority() fetcher = self.get_metadata_fetcher() metadata_objects = [] for item in metadata_items: metadata_objects.append( RawExtrinsicMetadata( target=ExtendedSWHID( object_type=ExtendedObjectType.SNAPSHOT, object_id=snapshot_id ), discovery_date=item.discovery_date or self.visit_date, authority=authority, fetcher=fetcher, format=item.format, metadata=item.metadata, origin=self.url, ) ) return metadata_objects def build_extrinsic_directory_metadata( - self, p_info: TPackageInfo, release_id: Sha1Git, directory_id: Sha1Git, + self, + p_info: TPackageInfo, + release_id: Sha1Git, + directory_id: Sha1Git, ) -> List[RawExtrinsicMetadata]: if not p_info.directory_extrinsic_metadata: # If this package loader doesn't write metadata, no need to require # an implementation for get_metadata_authority. return [] authority = self.get_metadata_authority() fetcher = self.get_metadata_fetcher() metadata_objects = [] for item in p_info.directory_extrinsic_metadata: metadata_objects.append( RawExtrinsicMetadata( target=ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=directory_id ), discovery_date=item.discovery_date or self.visit_date, authority=authority, fetcher=fetcher, format=item.format, metadata=item.metadata, origin=self.url, release=CoreSWHID( object_type=ObjectType.RELEASE, object_id=release_id ), ) ) return metadata_objects def _load_extrinsic_directory_metadata( - self, p_info: TPackageInfo, release_id: Sha1Git, directory_id: Sha1Git, + self, + p_info: TPackageInfo, + release_id: Sha1Git, + directory_id: Sha1Git, ) -> None: metadata_objects = self.build_extrinsic_directory_metadata( p_info, release_id, directory_id ) self._load_metadata_objects(metadata_objects) def _load_metadata_objects( self, metadata_objects: List[RawExtrinsicMetadata] ) -> None: if not metadata_objects: # If this package loader doesn't write metadata, no need to require # an implementation for get_metadata_authority. return self._create_authorities(mo.authority for mo in metadata_objects) self._create_fetchers(mo.fetcher for mo in metadata_objects) self.storage.raw_extrinsic_metadata_add(metadata_objects) def _create_authorities(self, authorities: Iterable[MetadataAuthority]) -> None: deduplicated_authorities = { (authority.type, authority.url): authority for authority in authorities } if authorities: self.storage.metadata_authority_add(list(deduplicated_authorities.values())) def _create_fetchers(self, fetchers: Iterable[MetadataFetcher]) -> None: deduplicated_fetchers = { (fetcher.name, fetcher.version): fetcher for fetcher in fetchers } if fetchers: self.storage.metadata_fetcher_add(list(deduplicated_fetchers.values())) def _load_extids(self, extids: Set[ExtID]) -> None: if not extids: return try: self.storage.extid_add(list(extids)) except Exception as e: logger.exception("Failed to load new ExtIDs for %s", self.url) sentry_sdk.capture_exception(e) # No big deal, it just means the next visit will load the same versions # again. def rev2rel(rev: Revision, version: str) -> Release: """Converts a revision to a release.""" message = rev.message if message and not message.endswith(b"\n"): message += b"\n" return Release( name=version.encode(), message=message, target=rev.directory, target_type=ModelObjectType.DIRECTORY, synthetic=rev.synthetic, author=rev.author, date=rev.date, ) diff --git a/swh/loader/package/maven/loader.py b/swh/loader/package/maven/loader.py index f2403d0..2029e0e 100644 --- a/swh/loader/package/maven/loader.py +++ b/swh/loader/package/maven/loader.py @@ -1,198 +1,205 @@ # Copyright (C) 2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from datetime import datetime, timezone import json import logging from os import path import string from typing import Iterator, List, Optional, Sequence, Tuple import attr import iso8601 import requests from typing_extensions import TypedDict from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, RawExtrinsicMetadataCore, ) from swh.loader.package.utils import EMPTY_AUTHOR, release_name from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, ObjectType, RawExtrinsicMetadata, Release, Sha1Git, TimestampWithTimezone, ) from swh.storage.interface import StorageInterface logger = logging.getLogger(__name__) class ArtifactDict(TypedDict): """Data about a Maven artifact, passed by the Maven Lister.""" time: str """the time of the last update of jar file on the server as an iso8601 date string """ url: str """the artifact url to retrieve filename""" filename: Optional[str] """optionally, the file's name""" gid: str """artifact's groupId""" aid: str """artifact's artifactId""" version: str """artifact's version""" base_url: str """root URL of the Maven instance""" @attr.s class MavenPackageInfo(BasePackageInfo): time = attr.ib(type=datetime) """Timestamp of the last update of jar file on the server.""" gid = attr.ib(type=str) """Group ID of the maven artifact""" aid = attr.ib(type=str) """Artifact ID of the maven artifact""" version = attr.ib(type=str) """Version of the maven artifact""" base_url = attr.ib(type=str) """Root URL of the Maven instance""" # default format for maven artifacts MANIFEST_FORMAT = string.Template("$gid $aid $version $url $time") EXTID_TYPE = "maven-jar" EXTID_VERSION = 0 @classmethod def from_metadata(cls, a_metadata: ArtifactDict) -> "MavenPackageInfo": url = a_metadata["url"] time = iso8601.parse_date(a_metadata["time"]).astimezone(tz=timezone.utc) return cls( url=url, filename=a_metadata.get("filename") or path.split(url)[-1], time=time, gid=a_metadata["gid"], aid=a_metadata["aid"], version=a_metadata["version"], base_url=a_metadata["base_url"], directory_extrinsic_metadata=[ RawExtrinsicMetadataCore( - format="maven-json", metadata=json.dumps(a_metadata).encode(), + format="maven-json", + metadata=json.dumps(a_metadata).encode(), ), ], ) class MavenLoader(PackageLoader[MavenPackageInfo]): - """Load source code jar origin's artifact files into swh archive - - """ + """Load source code jar origin's artifact files into swh archive""" visit_type = "maven" def __init__( self, storage: StorageInterface, url: str, artifacts: Sequence[ArtifactDict], max_content_size: Optional[int] = None, ): """Loader constructor. For now, this is the lister's task output. There is one, and only one, artefact (jar or zip) per version, as guaranteed by the Maven coordinates system. Args: url: Origin url artifacts: List of single artifact information """ super().__init__(storage=storage, url=url, max_content_size=max_content_size) self.artifacts = artifacts # assume order is enforced in the lister self.version_artifact = { jar["version"]: jar for jar in artifacts if jar["version"] } if artifacts: base_urls = {jar["base_url"] for jar in artifacts} try: (self.base_url,) = base_urls except ValueError: raise ValueError( "Artifacts originate from more than one Maven instance: " + ", ".join(base_urls) ) from None else: # There is no artifact, so self.metadata_authority won't be called, # so self.base_url won't be accessed. pass def get_versions(self) -> Sequence[str]: return list(self.version_artifact) def get_default_version(self) -> str: # Default version is the last item return self.artifacts[-1]["version"] def get_metadata_authority(self): return MetadataAuthority(type=MetadataAuthorityType.FORGE, url=self.base_url) def build_extrinsic_directory_metadata( - self, p_info: MavenPackageInfo, release_id: Sha1Git, directory_id: Sha1Git, + self, + p_info: MavenPackageInfo, + release_id: Sha1Git, + directory_id: Sha1Git, ) -> List[RawExtrinsicMetadata]: # Rebuild POM URL. pom_url = path.dirname(p_info.url) pom_url = f"{pom_url}/{p_info.aid}-{p_info.version}.pom" r = requests.get(pom_url, allow_redirects=True) if r.status_code == 200: metadata_pom = r.content else: metadata_pom = b"" p_info.directory_extrinsic_metadata.append( - RawExtrinsicMetadataCore(format="maven-pom", metadata=metadata_pom,) + RawExtrinsicMetadataCore( + format="maven-pom", + metadata=metadata_pom, + ) ) return super().build_extrinsic_directory_metadata( - p_info=p_info, release_id=release_id, directory_id=directory_id, + p_info=p_info, + release_id=release_id, + directory_id=directory_id, ) def get_package_info(self, version: str) -> Iterator[Tuple[str, MavenPackageInfo]]: a_metadata = self.version_artifact[version] yield release_name(a_metadata["version"]), MavenPackageInfo.from_metadata( a_metadata ) def build_release( self, p_info: MavenPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Release]: msg = f"Synthetic release for archive at {p_info.url}\n".encode("utf-8") normalized_time = TimestampWithTimezone.from_datetime(p_info.time) return Release( name=p_info.version.encode(), message=msg, date=normalized_time, author=EMPTY_AUTHOR, target=directory, target_type=ObjectType.DIRECTORY, synthetic=True, ) diff --git a/swh/loader/package/maven/tests/test_maven.py b/swh/loader/package/maven/tests/test_maven.py index 5958ad3..0153dbb 100644 --- a/swh/loader/package/maven/tests/test_maven.py +++ b/swh/loader/package/maven/tests/test_maven.py @@ -1,615 +1,618 @@ # Copyright (C) 2019-2021 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 datetime import hashlib import json from pathlib import Path import pytest from swh.loader.package import __version__ from swh.loader.package.maven.loader import MavenLoader, MavenPackageInfo from swh.loader.package.utils import EMPTY_AUTHOR from swh.loader.tests import assert_last_visit_matches, check_snapshot, get_stats from swh.model.hashutil import hash_to_bytes from swh.model.model import ( RawExtrinsicMetadata, Release, Snapshot, SnapshotBranch, TargetType, TimestampWithTimezone, ) from swh.model.model import MetadataAuthority, MetadataAuthorityType, MetadataFetcher from swh.model.model import ObjectType as ModelObjectType from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID, ObjectType from swh.storage.algos.snapshot import snapshot_get_all_branches URL = "https://repo1.maven.org/maven2/" MVN_ARTIFACTS = [ { "time": "2021-07-12 19:06:59.335000", "url": "https://repo1.maven.org/maven2/al/aldi/sprova4j/0.1.0/" + "sprova4j-0.1.0-sources.jar", "gid": "al.aldi", "aid": "sprova4j", "filename": "sprova4j-0.1.0-sources.jar", "version": "0.1.0", "base_url": "https://repo1.maven.org/maven2/", }, { "time": "2021-07-12 19:37:05.534000", "url": "https://repo1.maven.org/maven2/al/aldi/sprova4j/0.1.1/" + "sprova4j-0.1.1-sources.jar", "gid": "al.aldi", "aid": "sprova4j", "filename": "sprova4j-0.1.1-sources.jar", "version": "0.1.1", "base_url": "https://repo1.maven.org/maven2/", }, ] MVN_ARTIFACTS_POM = [ "https://repo1.maven.org/maven2/al/aldi/sprova4j/0.1.0/sprova4j-0.1.0.pom", "https://repo1.maven.org/maven2/al/aldi/sprova4j/0.1.1/sprova4j-0.1.1.pom", ] _expected_new_contents_first_visit = [ "cd807364cd7730022b3849f90ccf4bababbada84", "79e33dd52ebdf615e6696ae69add91cb990d81e2", "8002bd514156f05a0940ae14ef86eb0179cbd510", "23479553a6ccec30d377dee0496123a65d23fd8c", "07ffbebb933bc1660e448f07d8196c2b083797f9", "abf021b581f80035b56153c9aa27195b8d7ebbb8", "eec70ba80a6862ed2619727663b17eb0d9dfe131", "81a493dacb44dedf623f29ecf62c0e035bf698de", "bda85ed0bbecf8cddfea04234bee16f476f64fe4", "1ec91d561f5bdf59acb417086e04c54ead94e94e", "d517b423da707fa21378623f35facebff53cb59d", "3f0f21a764972d79e583908991c893c999613354", "a2dd4d7dfe6043baf9619081e4e29966989211af", "f62685cf0c6825a4097c949280b584cf0e16d047", "56afc1ea60cef6548ce0a34f44e91b0e4b063835", "cf7c740926e7ebc9ac8978a5c4f0e1e7a0e9e3af", "86ff828bea1c22ca3d50ed82569b9c59ce2c41a1", "1d0fa04454d9fec31d8ee3f35b58158ca1e28b15", "e90239a2c8d9ede61a29671a8b397a743e18fa34", "ce8851005d084aea089bcd8cf01052f4b234a823", "2c34ce622aa7fa68d104900840f66671718e6249", "e6a6fec32dcb3bee93c34fc11b0174a6b0b0ec6d", "405d3e1be4b658bf26de37f2c90c597b2796b9d7", "d0d2f5848721e04300e537826ef7d2d6d9441df0", "399c67e33e38c475fd724d283dd340f6a2e8dc91", "dea10c1111cc61ac1809fb7e88857e3db054959f", ] _expected_json_metadata = { "time": "2021-07-12 19:06:59.335000", "url": ( "https://repo1.maven.org/maven2/al/aldi/sprova4j/0.1.0/" "sprova4j-0.1.0-sources.jar" ), "gid": "al.aldi", "aid": "sprova4j", "filename": "sprova4j-0.1.0-sources.jar", "version": "0.1.0", "base_url": "https://repo1.maven.org/maven2/", } _expected_pom_metadata = ( """ 4.0.0 al.aldi sprova4j 0.1.0 sprova4j Java client for Sprova Test Management https://github.com/aldialimucaj/sprova4j 2018 The Apache Software License, Version 2.0 http://www.apache.org/licenses/LICENSE-2.0.txt repo aldi Aldi Alimucaj aldi.alimucaj@gmail.com scm:git:git://github.com/aldialimucaj/sprova4j.git scm:git:git://github.com/aldialimucaj/sprova4j.git https://github.com/aldialimucaj/sprova4j ch.qos.logback logback-classic 1.2.3 runtime com.google.code.gson gson 2.8.3 runtime com.squareup.okhttp3 okhttp 3.10.0 runtime com.squareup.okio okio 1.0.0 runtime org.glassfish javax.json 1.1.2 runtime javax.json javax.json-api 1.1.2 runtime javax.validation validation-api 2.0.1.Final runtime junit junit 4.12 test com.squareup.okhttp3 mockwebserver 3.10.0 test """ ) _expected_new_directories_first_visit = [ "6c9de41e4cebb91a8368da1d89ae9873bd540ec3", "c1a2ee97fc47426d0179f94d223405336b5cd075", "9e1bdca292765a9528af18743bd793b80362c768", "193a7af634592ef27fb341762806f61e8fb8eab3", "a297aa21e3dbf138b370be3aae7a852dd403bbbb", "da84026119ae04022f007d5b3362e98d46d09045", "75bb915942a9c441ca62aeffc3b634f1ec9ce5e2", "0851d359283b2ad82b116c8d1b55ab14b1ec219c", "2bcbb8b723a025ee9a36b719cea229ed38c37e46", ] _expected_new_release_first_visit = "02e83c29ec094db581f939d2e238d0613a4f59ac" REL_MSG = ( b"Synthetic release for archive at https://repo1.maven.org/maven2/al/aldi/" b"sprova4j/0.1.0/sprova4j-0.1.0-sources.jar\n" ) REVISION_DATE = TimestampWithTimezone.from_datetime( datetime.datetime(2021, 7, 12, 19, 6, 59, 335000, tzinfo=datetime.timezone.utc) ) @pytest.fixture def data_jar_1(datadir): content = Path( datadir, "https_maven.org", "sprova4j-0.1.0-sources.jar" ).read_bytes() return content @pytest.fixture def data_pom_1(datadir): content = Path(datadir, "https_maven.org", "sprova4j-0.1.0.pom").read_bytes() return content @pytest.fixture def data_jar_2(datadir): content = Path( datadir, "https_maven.org", "sprova4j-0.1.1-sources.jar" ).read_bytes() return content @pytest.fixture def data_pom_2(datadir): content = Path(datadir, "https_maven.org", "sprova4j-0.1.1.pom").read_bytes() return content def test_jar_visit_with_no_artifact_found(swh_storage, requests_mock_datadir): unknown_artifact_url = "https://ftp.g.o/unknown/8sync-0.1.0.tar.gz" loader = MavenLoader( swh_storage, unknown_artifact_url, artifacts=[ { "time": "2021-07-18 08:05:05.187000", "url": unknown_artifact_url, # unknown artifact "filename": "8sync-0.1.0.tar.gz", "gid": "al/aldi", "aid": "sprova4j", "version": "0.1.0", "base_url": "https://repo1.maven.org/maven2/", } ], ) actual_load_status = loader.load() assert actual_load_status["status"] == "uneventful" assert actual_load_status["snapshot_id"] is not None expected_snapshot_id = "1a8893e6a86f444e8be8e7bda6cb34fb1735a00e" assert actual_load_status["snapshot_id"] == expected_snapshot_id stats = get_stats(swh_storage) assert_last_visit_matches( swh_storage, unknown_artifact_url, status="partial", type="maven" ) assert { "content": 0, "directory": 0, "origin": 1, "origin_visit": 1, "release": 0, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats def test_jar_visit_inconsistent_base_url( swh_storage, requests_mock, data_jar_1, data_pom_1 ): - """With no prior visit, loading a jar ends up with 1 snapshot - - """ + """With no prior visit, loading a jar ends up with 1 snapshot""" with pytest.raises(ValueError, match="more than one Maven instance"): MavenLoader( swh_storage, MVN_ARTIFACTS[0]["url"], artifacts=[ MVN_ARTIFACTS[0], {**MVN_ARTIFACTS[1], "base_url": "http://maven.example/"}, ], ) def test_jar_visit_with_release_artifact_no_prior_visit( swh_storage, requests_mock, data_jar_1, data_pom_1 ): - """With no prior visit, loading a jar ends up with 1 snapshot - - """ + """With no prior visit, loading a jar ends up with 1 snapshot""" requests_mock.get(MVN_ARTIFACTS[0]["url"], content=data_jar_1) requests_mock.get(MVN_ARTIFACTS_POM[0], content=data_pom_1) loader = MavenLoader( swh_storage, MVN_ARTIFACTS[0]["url"], artifacts=[MVN_ARTIFACTS[0]] ) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" expected_snapshot_first_visit_id = hash_to_bytes( "c5195b8ebd148649bf094561877964b131ab27e0" ) expected_snapshot = Snapshot( id=expected_snapshot_first_visit_id, branches={ b"HEAD": SnapshotBranch( - target_type=TargetType.ALIAS, target=b"releases/0.1.0", + target_type=TargetType.ALIAS, + target=b"releases/0.1.0", ), b"releases/0.1.0": SnapshotBranch( target_type=TargetType.RELEASE, target=hash_to_bytes(_expected_new_release_first_visit), ), }, ) actual_snapshot = snapshot_get_all_branches( swh_storage, hash_to_bytes(actual_load_status["snapshot_id"]) ) assert actual_snapshot == expected_snapshot check_snapshot(expected_snapshot, swh_storage) assert ( hash_to_bytes(actual_load_status["snapshot_id"]) == expected_snapshot_first_visit_id ) stats = get_stats(swh_storage) assert_last_visit_matches( swh_storage, MVN_ARTIFACTS[0]["url"], status="full", type="maven" ) expected_contents = map(hash_to_bytes, _expected_new_contents_first_visit) assert list(swh_storage.content_missing_per_sha1(expected_contents)) == [] expected_dirs = map(hash_to_bytes, _expected_new_directories_first_visit) assert list(swh_storage.directory_missing(expected_dirs)) == [] expected_rels = map(hash_to_bytes, {_expected_new_release_first_visit}) assert list(swh_storage.release_missing(expected_rels)) == [] rel_id = actual_snapshot.branches[b"releases/0.1.0"].target (rel,) = swh_storage.release_get([rel_id]) assert rel == Release( id=hash_to_bytes(_expected_new_release_first_visit), name=b"0.1.0", message=REL_MSG, author=EMPTY_AUTHOR, date=REVISION_DATE, target_type=ModelObjectType.DIRECTORY, target=hash_to_bytes("6c9de41e4cebb91a8368da1d89ae9873bd540ec3"), synthetic=True, metadata=None, ) assert { "content": len(_expected_new_contents_first_visit), "directory": len(_expected_new_directories_first_visit), "origin": 1, "origin_visit": 1, "release": 1, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats def test_jar_2_visits_without_change( swh_storage, requests_mock_datadir, requests_mock, data_jar_2, data_pom_2 ): - """With no prior visit, load a gnu project ends up with 1 snapshot - - """ + """With no prior visit, load a gnu project ends up with 1 snapshot""" requests_mock.get(MVN_ARTIFACTS[1]["url"], content=data_jar_2) requests_mock.get(MVN_ARTIFACTS_POM[1], content=data_pom_2) loader = MavenLoader( swh_storage, MVN_ARTIFACTS[1]["url"], artifacts=[MVN_ARTIFACTS[1]] ) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" expected_snapshot_first_visit_id = hash_to_bytes( "91dcacee7a6d2b54f9cab14bc14cb86d22d2ac2b" ) assert ( hash_to_bytes(actual_load_status["snapshot_id"]) == expected_snapshot_first_visit_id ) assert_last_visit_matches( swh_storage, MVN_ARTIFACTS[1]["url"], status="full", type="maven" ) actual_load_status2 = loader.load() assert actual_load_status2["status"] == "uneventful" assert actual_load_status2["snapshot_id"] is not None assert actual_load_status["snapshot_id"] == actual_load_status2["snapshot_id"] assert_last_visit_matches( swh_storage, MVN_ARTIFACTS[1]["url"], status="full", type="maven" ) # Make sure we have only one entry in history for the pom fetch, one for # the actual download of jar, and that they're correct. urls_history = [str(req.url) for req in list(requests_mock_datadir.request_history)] assert urls_history == [ MVN_ARTIFACTS[1]["url"], MVN_ARTIFACTS_POM[1], ] def test_metadatata(swh_storage, requests_mock, data_jar_1, data_pom_1): """With no prior visit, loading a jar ends up with 1 snapshot. Extrinsic metadata is the pom file associated to the source jar. """ requests_mock.get(MVN_ARTIFACTS[0]["url"], content=data_jar_1) requests_mock.get(MVN_ARTIFACTS_POM[0], content=data_pom_1) loader = MavenLoader( swh_storage, MVN_ARTIFACTS[0]["url"], artifacts=[MVN_ARTIFACTS[0]] ) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" expected_release_id = hash_to_bytes(_expected_new_release_first_visit) release = swh_storage.release_get([expected_release_id])[0] assert release is not None release_swhid = CoreSWHID( object_type=ObjectType.RELEASE, object_id=expected_release_id ) directory_swhid = ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=release.target ) metadata_authority = MetadataAuthority( - type=MetadataAuthorityType.FORGE, url="https://repo1.maven.org/maven2/", + type=MetadataAuthorityType.FORGE, + url="https://repo1.maven.org/maven2/", ) expected_metadata = [ RawExtrinsicMetadata( target=directory_swhid, authority=metadata_authority, fetcher=MetadataFetcher( - name="swh.loader.package.maven.loader.MavenLoader", version=__version__, + name="swh.loader.package.maven.loader.MavenLoader", + version=__version__, ), discovery_date=loader.visit_date, format="maven-pom", metadata=_expected_pom_metadata.encode(), origin=MVN_ARTIFACTS[0]["url"], release=release_swhid, ), RawExtrinsicMetadata( target=directory_swhid, authority=metadata_authority, fetcher=MetadataFetcher( - name="swh.loader.package.maven.loader.MavenLoader", version=__version__, + name="swh.loader.package.maven.loader.MavenLoader", + version=__version__, ), discovery_date=loader.visit_date, format="maven-json", metadata=json.dumps(_expected_json_metadata).encode(), origin=MVN_ARTIFACTS[0]["url"], release=release_swhid, ), ] res = swh_storage.raw_extrinsic_metadata_get(directory_swhid, metadata_authority) assert res.next_page_token is None assert set(res.results) == set(expected_metadata) def test_metadatata_no_pom(swh_storage, requests_mock, data_jar_1): """With no prior visit, loading a jar ends up with 1 snapshot. Extrinsic metadata is None if the pom file cannot be retrieved. """ requests_mock.get(MVN_ARTIFACTS[0]["url"], content=data_jar_1) requests_mock.get(MVN_ARTIFACTS_POM[0], status_code="404") loader = MavenLoader( swh_storage, MVN_ARTIFACTS[0]["url"], artifacts=[MVN_ARTIFACTS[0]] ) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" expected_release_id = hash_to_bytes(_expected_new_release_first_visit) release = swh_storage.release_get([expected_release_id])[0] assert release is not None release_swhid = CoreSWHID( object_type=ObjectType.RELEASE, object_id=expected_release_id ) directory_swhid = ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=release.target ) metadata_authority = MetadataAuthority( - type=MetadataAuthorityType.FORGE, url="https://repo1.maven.org/maven2/", + type=MetadataAuthorityType.FORGE, + url="https://repo1.maven.org/maven2/", ) expected_metadata = [ RawExtrinsicMetadata( target=directory_swhid, authority=metadata_authority, fetcher=MetadataFetcher( - name="swh.loader.package.maven.loader.MavenLoader", version=__version__, + name="swh.loader.package.maven.loader.MavenLoader", + version=__version__, ), discovery_date=loader.visit_date, format="maven-pom", metadata=b"", origin=MVN_ARTIFACTS[0]["url"], release=release_swhid, ), RawExtrinsicMetadata( target=directory_swhid, authority=metadata_authority, fetcher=MetadataFetcher( - name="swh.loader.package.maven.loader.MavenLoader", version=__version__, + name="swh.loader.package.maven.loader.MavenLoader", + version=__version__, ), discovery_date=loader.visit_date, format="maven-json", metadata=json.dumps(_expected_json_metadata).encode(), origin=MVN_ARTIFACTS[0]["url"], release=release_swhid, ), ] res = swh_storage.raw_extrinsic_metadata_get(directory_swhid, metadata_authority) assert res.next_page_token is None assert set(res.results) == set(expected_metadata) def test_jar_extid(): - """Compute primary key should return the right identity - - """ + """Compute primary key should return the right identity""" metadata = MVN_ARTIFACTS[0] p_info = MavenPackageInfo(**metadata) expected_manifest = "{gid} {aid} {version} {url} {time}".format(**metadata).encode() actual_id = p_info.extid() - assert actual_id == ("maven-jar", 0, hashlib.sha256(expected_manifest).digest(),) + assert actual_id == ( + "maven-jar", + 0, + hashlib.sha256(expected_manifest).digest(), + ) def test_jar_snapshot_append( swh_storage, requests_mock_datadir, requests_mock, data_jar_1, data_pom_1, data_jar_2, data_pom_2, ): # first loading with a first artifact artifact1 = MVN_ARTIFACTS[0] url1 = artifact1["url"] requests_mock.get(url1, content=data_jar_1) requests_mock.get(MVN_ARTIFACTS_POM[0], content=data_pom_1) loader = MavenLoader(swh_storage, url1, [artifact1]) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None assert_last_visit_matches(swh_storage, url1, status="full", type="maven") # check expected snapshot snapshot = loader.last_snapshot() assert len(snapshot.branches) == 2 branch_artifact1_name = f"releases/{artifact1['version']}".encode() assert b"HEAD" in snapshot.branches assert branch_artifact1_name in snapshot.branches assert snapshot.branches[b"HEAD"].target == branch_artifact1_name # second loading with a second artifact artifact2 = MVN_ARTIFACTS[1] url2 = artifact2["url"] requests_mock.get(url2, content=data_jar_2) requests_mock.get(MVN_ARTIFACTS_POM[1], content=data_pom_2) loader = MavenLoader(swh_storage, url2, [artifact2]) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None assert_last_visit_matches(swh_storage, url2, status="full", type="maven") # check expected snapshot, should contain a new branch and the # branch for the first artifact snapshot = loader.last_snapshot() assert len(snapshot.branches) == 2 branch_artifact2_name = f"releases/{artifact2['version']}".encode() assert b"HEAD" in snapshot.branches assert branch_artifact2_name in snapshot.branches assert branch_artifact1_name not in snapshot.branches assert snapshot.branches[b"HEAD"].target == branch_artifact2_name diff --git a/swh/loader/package/maven/tests/test_tasks.py b/swh/loader/package/maven/tests/test_tasks.py index 2335af6..479dce0 100644 --- a/swh/loader/package/maven/tests/test_tasks.py +++ b/swh/loader/package/maven/tests/test_tasks.py @@ -1,51 +1,54 @@ # Copyright (C) 2019-2021 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 MVN_ARTIFACTS = [ { "time": 1626109619335, "url": "https://repo1.maven.org/maven2/al/aldi/sprova4j/0.1.0/" + "sprova4j-0.1.0.jar", "gid": "al.aldi", "aid": "sprova4j", "filename": "sprova4j-0.1.0.jar", "version": "0.1.0", "base_url": "https://repo1.maven.org/maven2/", }, ] def test_tasks_maven_loader( mocker, swh_scheduler_celery_app, swh_scheduler_celery_worker, swh_config ): mock_load = mocker.patch("swh.loader.package.maven.loader.MavenLoader.load") mock_load.return_value = {"status": "eventful"} res = swh_scheduler_celery_app.send_task( "swh.loader.package.maven.tasks.LoadMaven", - kwargs=dict(url=MVN_ARTIFACTS[0]["url"], artifacts=MVN_ARTIFACTS,), + kwargs=dict( + url=MVN_ARTIFACTS[0]["url"], + artifacts=MVN_ARTIFACTS, + ), ) assert res res.wait() assert res.successful() assert mock_load.called assert res.result == {"status": "eventful"} def test_tasks_maven_loader_snapshot_append( mocker, swh_scheduler_celery_app, swh_scheduler_celery_worker, swh_config ): mock_load = mocker.patch("swh.loader.package.maven.loader.MavenLoader.load") mock_load.return_value = {"status": "eventful"} res = swh_scheduler_celery_app.send_task( "swh.loader.package.maven.tasks.LoadMaven", kwargs=dict(url=MVN_ARTIFACTS[0]["url"], artifacts=[]), ) assert res res.wait() assert res.successful() assert mock_load.called assert res.result == {"status": "eventful"} diff --git a/swh/loader/package/nixguix/loader.py b/swh/loader/package/nixguix/loader.py index 2497010..f2cc1d5 100644 --- a/swh/loader/package/nixguix/loader.py +++ b/swh/loader/package/nixguix/loader.py @@ -1,303 +1,308 @@ # Copyright (C) 2020-2021 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 json import logging import re from typing import Any, Dict, Iterator, List, Mapping, Optional, Set, Tuple import attr from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, PartialExtID, RawExtrinsicMetadataCore, ) from swh.loader.package.utils import EMPTY_AUTHOR, api_info, cached_method from swh.model import hashutil from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, ObjectType, Release, Sha1Git, ) from swh.model.swhids import CoreSWHID from swh.storage.interface import StorageInterface logger = logging.getLogger(__name__) EXTID_TYPE = "subresource-integrity" """The ExtID is an ASCII string, as defined by https://w3c.github.io/webappsec-subresource-integrity/""" EXTID_VERSION = 0 @attr.s class NixGuixPackageInfo(BasePackageInfo): raw_info = attr.ib(type=Dict[str, Any]) integrity = attr.ib(type=str) """Hash of the archive, formatted as in the Subresource Integrity specification.""" @classmethod def from_metadata( cls, metadata: Dict[str, Any], version: str ) -> "NixGuixPackageInfo": return cls( url=metadata["url"], filename=None, version=version, integrity=metadata["integrity"], raw_info=metadata, ) def extid(self) -> PartialExtID: return (EXTID_TYPE, EXTID_VERSION, self.integrity.encode("ascii")) class NixGuixLoader(PackageLoader[NixGuixPackageInfo]): """Load sources from a sources.json file. This loader is used to load sources used by functional package manager (eg. Nix and Guix). """ visit_type = "nixguix" def __init__( self, storage: StorageInterface, url: str, unsupported_file_extensions: List[str] = [], max_content_size: Optional[int] = None, ): super().__init__(storage=storage, url=url, max_content_size=max_content_size) self.provider_url = url self.unsupported_file_extensions = unsupported_file_extensions # Note: this could be renamed get_artifacts in the PackageLoader # base class. @cached_method def raw_sources(self): return retrieve_sources(self.url) @cached_method def supported_sources(self): raw_sources = self.raw_sources() return clean_sources( parse_sources(raw_sources), self.unsupported_file_extensions ) @cached_method def integrity_by_url(self) -> Dict[str, str]: sources = self.supported_sources() return {s["urls"][0]: s["integrity"] for s in sources["sources"]} def get_versions(self) -> List[str]: """The first mirror of the mirror list is used as branch name in the snapshot. """ return list(self.integrity_by_url().keys()) def get_metadata_authority(self): return MetadataAuthority( - type=MetadataAuthorityType.FORGE, url=self.url, metadata={}, + type=MetadataAuthorityType.FORGE, + url=self.url, + metadata={}, ) def get_extrinsic_snapshot_metadata(self): return [ RawExtrinsicMetadataCore( - format="nixguix-sources-json", metadata=self.raw_sources(), + format="nixguix-sources-json", + metadata=self.raw_sources(), ), ] # Note: this could be renamed get_artifact_info in the PackageLoader # base class. def get_package_info(self, url) -> Iterator[Tuple[str, NixGuixPackageInfo]]: # TODO: try all mirrors and not only the first one. A source # can be fetched from several urls, called mirrors. We # currently only use the first one, but if the first one # fails, we should try the second one and so on. integrity = self.integrity_by_url()[url] p_info = NixGuixPackageInfo.from_metadata( {"url": url, "integrity": integrity}, version=url ) yield url, p_info def select_extid_target( self, p_info: NixGuixPackageInfo, extid_targets: Set[CoreSWHID] ) -> Optional[CoreSWHID]: if extid_targets: # The archive URL is part of the release name. As that URL is not # intrinsic metadata, it means different releases may be created for # the same SRI so they have the same extid. # Therefore, we need to pick the one with the right URL. releases = self.storage.release_get( [target.object_id for target in extid_targets] ) extid_targets = { release.swhid() for release in releases if release is not None and release.name == p_info.version.encode() } return super().select_extid_target(p_info, extid_targets) def extra_branches(self) -> Dict[bytes, Mapping[str, Any]]: """We add a branch to the snapshot called 'evaluation' pointing to the revision used to generate the sources.json file. This revision is specified in the sources.json file itself. For the nixpkgs origin, this revision is coming from the github.com/nixos/nixpkgs repository. Note this repository is not loaded explicitly. So, this pointer can target a nonexistent revision for a time. However, the github and gnu loaders are supposed to load this revision and should create the revision pointed by this branch. This branch can be used to identify the snapshot associated to a Nix/Guix evaluation. """ # The revision used to create the sources.json file. For Nix, # this revision belongs to the github.com/nixos/nixpkgs # repository revision = self.supported_sources()["revision"] return { b"evaluation": { "target_type": "revision", "target": hashutil.hash_to_bytes(revision), } } def build_release( self, p_info: NixGuixPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Release]: return Release( name=p_info.version.encode(), message=None, author=EMPTY_AUTHOR, date=None, target=directory, target_type=ObjectType.DIRECTORY, synthetic=True, ) def retrieve_sources(url: str) -> bytes: """Retrieve sources. Potentially raise NotFound error.""" return api_info(url, allow_redirects=True) def parse_sources(raw_sources: bytes) -> Dict[str, Any]: return json.loads(raw_sources.decode("utf-8")) -def make_pattern_unsupported_file_extension(unsupported_file_extensions: List[str],): +def make_pattern_unsupported_file_extension( + unsupported_file_extensions: List[str], +): """Make a regexp pattern for unsupported file extension out of a list of unsupported archive extension list. """ return re.compile( rf".*\.({'|'.join(map(re.escape, unsupported_file_extensions))})$", re.DOTALL ) def clean_sources( sources: Dict[str, Any], unsupported_file_extensions=[] ) -> Dict[str, Any]: """Validate and clean the sources structure. First, ensure all top level keys are present. Then, walk the sources list and remove sources that do not contain required keys. Filter out source entries whose: - required keys are missing - source type is not supported - urls attribute type is not a list - extension is known not to be supported by the loader Raises: ValueError if: - a required top level key is missing - top-level version is not 1 Returns: source Dict cleaned up """ pattern_unsupported_file = make_pattern_unsupported_file_extension( unsupported_file_extensions ) # Required top level keys required_keys = ["version", "revision", "sources"] missing_keys = [] for required_key in required_keys: if required_key not in sources: missing_keys.append(required_key) if missing_keys != []: raise ValueError( f"sources structure invalid, missing: {','.join(missing_keys)}" ) # Only the version 1 is currently supported version = int(sources["version"]) if version != 1: raise ValueError( f"The sources structure version '{sources['version']}' is not supported" ) # If a source doesn't contain required attributes, this source is # skipped but others could still be archived. verified_sources = [] for source in sources["sources"]: valid = True required_keys = ["urls", "integrity", "type"] for required_key in required_keys: if required_key not in source: logger.info( f"Skip source '{source}' because key '{required_key}' is missing", ) valid = False if valid and source["type"] != "url": logger.info( f"Skip source '{source}' because the type {source['type']} " "is not supported", ) valid = False if valid and not isinstance(source["urls"], list): logger.info( f"Skip source {source} because the urls attribute is not a list" ) valid = False if valid and len(source["urls"]) > 0: # Filter out unsupported archives supported_sources: List[str] = [] for source_url in source["urls"]: if pattern_unsupported_file.match(source_url): logger.info(f"Skip unsupported artifact url {source_url}") continue supported_sources.append(source_url) if len(supported_sources) == 0: logger.info( f"Skip source {source} because urls only reference " "unsupported artifacts. Unsupported " f"artifacts so far: {pattern_unsupported_file}" ) continue new_source = copy.deepcopy(source) new_source["urls"] = supported_sources verified_sources.append(new_source) sources["sources"] = verified_sources return sources diff --git a/swh/loader/package/nixguix/tests/test_nixguix.py b/swh/loader/package/nixguix/tests/test_nixguix.py index f9904f6..e7de3b7 100644 --- a/swh/loader/package/nixguix/tests/test_nixguix.py +++ b/swh/loader/package/nixguix/tests/test_nixguix.py @@ -1,649 +1,655 @@ # Copyright (C) 2020-2021 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 json import logging import os from typing import Dict, Optional, Tuple import pytest from swh.loader.package import __version__ from swh.loader.package.archive.loader import ArchiveLoader from swh.loader.package.nixguix.loader import ( NixGuixLoader, clean_sources, make_pattern_unsupported_file_extension, parse_sources, retrieve_sources, ) from swh.loader.package.utils import download from swh.loader.tests import assert_last_visit_matches from swh.loader.tests import check_snapshot as check_snapshot_full from swh.loader.tests import get_stats from swh.model.hashutil import hash_to_bytes from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, ObjectType, Person, RawExtrinsicMetadata, Release, Snapshot, SnapshotBranch, TargetType, ) from swh.model.swhids import ExtendedObjectType, ExtendedSWHID from swh.storage.algos.origin import origin_get_latest_visit_status from swh.storage.algos.snapshot import snapshot_get_all_branches from swh.storage.exc import HashCollision from swh.storage.interface import PagedResult, StorageInterface sources_url = "https://nix-community.github.io/nixpkgs-swh/sources.json" @pytest.fixture def raw_sources(datadir) -> bytes: with open( os.path.join( datadir, "https_nix-community.github.io", "nixpkgs-swh_sources.json" ), "rb", ) as f: return f.read() SNAPSHOT1 = Snapshot( id=hash_to_bytes("fafcfe32016d018bd892114fce211f37a36a092a"), branches={ b"evaluation": SnapshotBranch( target=hash_to_bytes("cc4e04c26672dd74e5fd0fecb78b435fb55368f7"), target_type=TargetType.REVISION, ), b"https://github.com/owner-1/repository-1/revision-1.tgz": SnapshotBranch( target=hash_to_bytes("df7811b9644ed8ef088e2e7add62ed32b0bab15f"), target_type=TargetType.RELEASE, ), b"https://github.com/owner-3/repository-1/revision-1.tgz": SnapshotBranch( target=hash_to_bytes("dc7dc10a664396d5c88adc56352904db231bde14"), target_type=TargetType.RELEASE, ), }, ) def check_snapshot(snapshot: Snapshot, storage: StorageInterface): # The `evaluation` branch is allowed to be unresolvable. It's possible at current # nixguix visit time, it is not yet visited (the git loader is in charge of its # visit for now). For more details, check the # swh.loader.package.nixguix.NixGuixLoader.extra_branches docstring. check_snapshot_full( snapshot, storage, allowed_empty=[(TargetType.REVISION, b"evaluation")] ) assert isinstance(snapshot, Snapshot) # then ensure the snapshot revisions are structurally as expected revision_ids = [] for name, branch in snapshot.branches.items(): if name == b"evaluation": continue # skipping that particular branch (cf. previous comment) if branch.target_type == TargetType.REVISION: revision_ids.append(branch.target) revisions = storage.revision_get(revision_ids) for rev in revisions: assert rev is not None metadata = rev.metadata assert not metadata def test_retrieve_sources(swh_storage, requests_mock_datadir): j = parse_sources(retrieve_sources(sources_url)) assert "sources" in j.keys() assert len(j["sources"]) == 3 def test_nixguix_url_not_found(swh_storage, requests_mock_datadir): """When failing to read from the url, the visit is marked as not_found. Here the sources url does not exist, so requests_mock_datadir returns a 404. Resulting in a NotFound raised within the package loader's main loop. This results in the task with status failed and a visit_status with status "not_found". """ unknown_url = "https://non-existing-url/" loader = NixGuixLoader(swh_storage, unknown_url) # during the retrieval step load_status = loader.load() assert load_status == {"status": "failed"} assert_last_visit_matches( swh_storage, unknown_url, status="not_found", type="nixguix", snapshot=None ) assert len(requests_mock_datadir.request_history) == 1 assert requests_mock_datadir.request_history[0].url == unknown_url def test_nixguix_url_with_decoding_error(swh_storage, requests_mock_datadir): """Other errors during communication with the url, the visit is marked as failed requests_mock_datadir will intercept the requests to sources_url. Since the file exists, returns a 200 with the requested content of the query. As file.txt is no json, fails do decode and raises a JSONDecodeError. In effect failing the visit. """ sources_url = "https://example.com/file.txt" loader = NixGuixLoader(swh_storage, sources_url) load_status = loader.load() assert load_status == {"status": "failed"} assert_last_visit_matches( swh_storage, sources_url, status="failed", type="nixguix", snapshot=None ) assert len(requests_mock_datadir.request_history) == 1 assert requests_mock_datadir.request_history[0].url == sources_url def test_clean_sources_invalid_schema(swh_storage, requests_mock_datadir): sources = {} with pytest.raises(ValueError, match="sources structure invalid, missing: .*"): clean_sources(sources) def test_clean_sources_invalid_version(swh_storage, requests_mock_datadir): for version_ok in [1, "1"]: # Check those versions are fine clean_sources({"version": version_ok, "sources": [], "revision": "my-revision"}) for version_ko in [0, "0", 2, "2"]: # Check version != 1 raise an error with pytest.raises( ValueError, match="sources structure version .* is not supported" ): clean_sources( {"version": version_ko, "sources": [], "revision": "my-revision"} ) def test_clean_sources_invalid_sources(swh_storage, requests_mock_datadir): valid_sources = [ # 1 valid source {"type": "url", "urls": ["my-url.tar.gz"], "integrity": "my-integrity"}, ] sources = { "version": 1, "sources": valid_sources + [ # integrity is missing - {"type": "url", "urls": ["my-url.tgz"],}, + { + "type": "url", + "urls": ["my-url.tgz"], + }, # urls is not a list {"type": "url", "urls": "my-url.zip", "integrity": "my-integrity"}, # type is not url {"type": "git", "urls": ["my-url.zip"], "integrity": "my-integrity"}, # missing fields which got double-checked nonetheless... {"integrity": "my-integrity"}, ], "revision": "my-revision", } clean = clean_sources(sources) assert len(clean["sources"]) == len(valid_sources) def test_make_pattern_unsupported_file_extension(): unsupported_extensions = ["el", "c", "txt"] supported_extensions = ["Z", "7z"] # for test actual_unsupported_pattern = make_pattern_unsupported_file_extension( unsupported_extensions ) for supported_ext in supported_extensions: assert supported_ext not in unsupported_extensions supported_filepath = f"anything.{supported_ext}" actual_match = actual_unsupported_pattern.match(supported_filepath) assert not actual_match for unsupported_ext in unsupported_extensions: unsupported_filepath = f"something.{unsupported_ext}" actual_match = actual_unsupported_pattern.match(unsupported_filepath) assert actual_match def test_clean_sources_unsupported_artifacts(swh_storage, requests_mock_datadir): unsupported_file_extensions = [ "iso", "whl", "gem", "pom", "msi", "pod", "png", "rock", "ttf", "jar", "c", "el", "rpm", "diff", "patch", ] supported_sources = [ { "type": "url", "urls": [f"https://server.org/my-url.{ext}"], "integrity": "my-integrity", } for ext in [ "known-unknown-but-ok", # this is fine as well with the current approach "zip", "tar.gz", "tgz", "tar.bz2", "tbz", "tbz2", "tar.xz", "tar", "zip", "7z", "Z", ] ] unsupported_sources = [ { "type": "url", "urls": [f"https://server.org/my-url.{ext}"], "integrity": "my-integrity", } for ext in unsupported_file_extensions ] sources = { "version": 1, "sources": supported_sources + unsupported_sources, "revision": "my-revision", } clean = clean_sources(sources, unsupported_file_extensions) assert len(clean["sources"]) == len(supported_sources) def test_loader_one_visit(swh_storage, requests_mock_datadir, raw_sources): loader = NixGuixLoader(swh_storage, sources_url) load_status = loader.load() expected_snapshot_id = SNAPSHOT1.id expected_snapshot_id_hex = expected_snapshot_id.hex() assert load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id_hex, } release_id = SNAPSHOT1.branches[ b"https://github.com/owner-1/repository-1/revision-1.tgz" ].target check_snapshot(SNAPSHOT1, storage=swh_storage) assert swh_storage.release_get([release_id])[0] == Release( id=release_id, name=b"https://github.com/owner-1/repository-1/revision-1.tgz", message=None, target=hash_to_bytes("4de2e07d3742718d928e974b8a4c721b9f7b33bf"), target_type=ObjectType.DIRECTORY, synthetic=True, author=Person.from_fullname(b""), date=None, ) stats = get_stats(swh_storage) assert { "content": 1, "directory": 3, "origin": 1, "origin_visit": 1, "release": 2, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats # The visit is partial because urls pointing to non tarball file # are not handled yet assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix" ) visit_status = origin_get_latest_visit_status(swh_storage, sources_url) snapshot_swhid = ExtendedSWHID( object_type=ExtendedObjectType.SNAPSHOT, object_id=visit_status.snapshot ) metadata_authority = MetadataAuthority( - type=MetadataAuthorityType.FORGE, url=sources_url, + type=MetadataAuthorityType.FORGE, + url=sources_url, ) expected_metadata = [ RawExtrinsicMetadata( target=snapshot_swhid, authority=metadata_authority, fetcher=MetadataFetcher( name="swh.loader.package.nixguix.loader.NixGuixLoader", version=__version__, ), discovery_date=loader.visit_date, format="nixguix-sources-json", metadata=raw_sources, origin=sources_url, ) ] assert swh_storage.raw_extrinsic_metadata_get( - snapshot_swhid, metadata_authority, - ) == PagedResult(next_page_token=None, results=expected_metadata,) + snapshot_swhid, + metadata_authority, + ) == PagedResult( + next_page_token=None, + results=expected_metadata, + ) def test_uncompress_failure(swh_storage, requests_mock_datadir): """Non tarball files are currently not supported and the uncompress function fails on such kind of files. However, even in this case of failure (because of the url https://example.com/file.txt), a snapshot and a visit has to be created (with a status partial since all files are not archived). """ loader = NixGuixLoader(swh_storage, sources_url) loader_status = loader.load() sources = loader.supported_sources()["sources"] urls = [s["urls"][0] for s in sources] assert "https://example.com/file.txt" in urls assert loader_status["status"] == "eventful" # The visit is partial because urls pointing to non tarball files # are not handled yet assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix" ) def test_loader_incremental(swh_storage, requests_mock_datadir): """Ensure a second visit do not download artifact already downloaded by the previous visit. """ loader = NixGuixLoader(swh_storage, sources_url) load_status = loader.load() loader.load() assert load_status == {"status": "eventful", "snapshot_id": SNAPSHOT1.id.hex()} assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix", snapshot=SNAPSHOT1.id, ) check_snapshot(SNAPSHOT1, storage=swh_storage) urls = [ m.url for m in requests_mock_datadir.request_history if m.url == ("https://github.com/owner-1/repository-1/revision-1.tgz") ] # The artifact # 'https://github.com/owner-1/repository-1/revision-1.tgz' is only # visited one time assert len(urls) == 1 def test_loader_two_visits(swh_storage, requests_mock_datadir_visits): """To ensure there is only one origin, but two visits, two revisions and two snapshots are created. The first visit creates a snapshot containing one tarball. The second visit creates a snapshot containing the same tarball and another tarball. """ loader = NixGuixLoader(swh_storage, sources_url) load_status = loader.load() assert load_status == {"status": "eventful", "snapshot_id": SNAPSHOT1.id.hex()} assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix", snapshot=SNAPSHOT1.id, ) check_snapshot(SNAPSHOT1, storage=swh_storage) stats = get_stats(swh_storage) assert { "content": 1, "directory": 3, "origin": 1, "origin_visit": 1, "release": 2, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats loader = NixGuixLoader(swh_storage, sources_url) load_status = loader.load() expected_snapshot_id_hex = "c1983a0a3f647548e1fb92f30339da6848fe9f7a" expected_snapshot_id = hash_to_bytes(expected_snapshot_id_hex) assert load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id_hex, } assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix", snapshot=expected_snapshot_id, ) # This ensures visits are incremental. Indeed, if we request a # second time an url, because of the requests_mock_datadir_visits # fixture, the file has to end with `_visit1`. expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"evaluation": SnapshotBranch( target=hash_to_bytes("602140776b2ce6c9159bcf52ada73a297c063d5e"), target_type=TargetType.REVISION, ), b"https://github.com/owner-1/repository-1/revision-1.tgz": SnapshotBranch( target=hash_to_bytes("df7811b9644ed8ef088e2e7add62ed32b0bab15f"), target_type=TargetType.RELEASE, ), b"https://github.com/owner-2/repository-1/revision-1.tgz": SnapshotBranch( target=hash_to_bytes("5cc0115cd643902b837cb6cfbc9f5865bc5a7cb2"), target_type=TargetType.RELEASE, ), }, ) check_snapshot(expected_snapshot, storage=swh_storage) stats = get_stats(swh_storage) assert { "content": 2, "directory": 5, "origin": 1, "origin_visit": 2, "release": 3, "revision": 0, "skipped_content": 0, "snapshot": 2, } == stats def test_evaluation_branch(swh_storage, requests_mock_datadir): loader = NixGuixLoader(swh_storage, sources_url) res = loader.load() assert res["status"] == "eventful" assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix", snapshot=SNAPSHOT1.id, ) check_snapshot(SNAPSHOT1, storage=swh_storage) def test_eoferror(swh_storage, requests_mock_datadir): """Load a truncated archive which is invalid to make the uncompress function raising the exception EOFError. We then check if a snapshot is created, meaning this error is well managed. """ sources = ( "https://nix-community.github.io/nixpkgs-swh/sources-EOFError.json" # noqa ) loader = NixGuixLoader(swh_storage, sources) loader.load() expected_snapshot = Snapshot( id=hash_to_bytes("4257fa2350168c6bfec726a06452ea27a2c0cb33"), branches={ b"evaluation": SnapshotBranch( target=hash_to_bytes("cc4e04c26672dd74e5fd0fecb78b435fb55368f7"), target_type=TargetType.REVISION, ), }, ) check_snapshot(expected_snapshot, storage=swh_storage) def fake_download( url: str, dest: str, hashes: Dict = {}, filename: Optional[str] = None, auth: Optional[Tuple[str, str]] = None, ) -> Tuple[str, Dict]: """Fake download which raises HashCollision (for the sake of test simpliciy, let's accept that makes sense) For tests purpose only. """ if url == "https://example.com/file.txt": # instead of failing because it's a file not dealt with by the nix guix # loader, make it raise a hash collision raise HashCollision("sha1", "f92d74e3874587aaf443d1db961d4e26dde13e9c", []) return download(url, dest, hashes, filename, auth) def test_raise_exception(swh_storage, requests_mock_datadir, mocker): mock_download = mocker.patch("swh.loader.package.loader.download") mock_download.side_effect = fake_download loader = NixGuixLoader(swh_storage, sources_url) res = loader.load() assert res == { "status": "eventful", "snapshot_id": SNAPSHOT1.id.hex(), } # The visit is partial because some artifact downloads failed assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix", snapshot=SNAPSHOT1.id, ) check_snapshot(SNAPSHOT1, storage=swh_storage) assert len(mock_download.mock_calls) == 3 def test_load_nixguix_one_common_artifact_from_other_loader( swh_storage, datadir, requests_mock_datadir_visits, caplog ): - """Misformatted revision should be caught and logged, then loading continues - - """ + """Misformatted revision should be caught and logged, then loading continues""" caplog.set_level(logging.ERROR, "swh.loader.package.nixguix.loader") # 1. first ingest with for example the archive loader gnu_url = "https://ftp.gnu.org/gnu/8sync/" release = "0.1.0" artifact_url = f"https://ftp.gnu.org/gnu/8sync/8sync-{release}.tar.gz" gnu_artifacts = [ { "time": 944729610, "url": artifact_url, "length": 221837, "filename": f"8sync-{release}.tar.gz", "version": release, } ] archive_loader = ArchiveLoader(swh_storage, url=gnu_url, artifacts=gnu_artifacts) actual_load_status = archive_loader.load() expected_snapshot_id = "9efecc835e8f99254934f256b5301b94f348fd17" assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] == expected_snapshot_id # noqa assert_last_visit_matches( archive_loader.storage, gnu_url, status="full", type="tar", snapshot=hash_to_bytes(expected_snapshot_id), ) # 2. Then ingest with the nixguix loader which lists the same artifact within its # sources.json # ensure test setup is ok data_sources = os.path.join( datadir, "https_nix-community.github.io", "nixpkgs-swh_sources_special.json" ) all_sources = json.loads(open(data_sources).read()) found = False for source in all_sources["sources"]: if source["urls"][0] == artifact_url: found = True assert ( found is True ), f"test setup error: {artifact_url} must be in {data_sources}" # first visit with a snapshot, ok sources_url = "https://nix-community.github.io/nixpkgs-swh/sources_special.json" loader = NixGuixLoader(swh_storage, sources_url) actual_load_status2 = loader.load() assert actual_load_status2["status"] == "eventful" snapshot_id = actual_load_status2["snapshot_id"] assert_last_visit_matches( swh_storage, sources_url, status="full", type="nixguix", snapshot=hash_to_bytes(snapshot_id), ) snapshot = snapshot_get_all_branches(swh_storage, hash_to_bytes(snapshot_id)) assert snapshot diff --git a/swh/loader/package/npm/loader.py b/swh/loader/package/npm/loader.py index b082a0f..bca39c3 100644 --- a/swh/loader/package/npm/loader.py +++ b/swh/loader/package/npm/loader.py @@ -1,309 +1,305 @@ # Copyright (C) 2019-2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from codecs import BOM_UTF8 import json import logging import os import string from typing import Any, Dict, Iterator, List, Optional, Sequence, Tuple, Union from urllib.parse import quote import attr import chardet from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, RawExtrinsicMetadataCore, ) from swh.loader.package.utils import api_info, cached_method, release_name from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, ObjectType, Person, Release, Sha1Git, TimestampWithTimezone, ) from swh.storage.interface import StorageInterface logger = logging.getLogger(__name__) EMPTY_PERSON = Person.from_fullname(b"") @attr.s class NpmPackageInfo(BasePackageInfo): raw_info = attr.ib(type=Dict[str, Any]) package_name = attr.ib(type=str) date = attr.ib(type=Optional[str]) shasum = attr.ib(type=str) """sha1 checksum""" # we cannot rely only on $shasum, as it is technically possible for two versions # of the same package to have the exact same tarball. # But the release data (message and date) are extrinsic to the content of the # package, so they differ between versions. # So we need every attribute used to build the release object to be part of the # manifest. MANIFEST_FORMAT = string.Template( "date $date\nname $package_name\nshasum $shasum\nurl $url\nversion $version" ) EXTID_TYPE = "npm-manifest-sha256" EXTID_VERSION = 0 @classmethod def from_metadata( cls, project_metadata: Dict[str, Any], version: str ) -> "NpmPackageInfo": package_metadata = project_metadata["versions"][version] url = package_metadata["dist"]["tarball"] assert package_metadata["name"] == project_metadata["name"] # No date available in intrinsic metadata: retrieve it from the API # metadata, using the version number that the API claims this package # has. extrinsic_version = package_metadata["version"] if "time" in project_metadata: date = project_metadata["time"][extrinsic_version] elif "mtime" in package_metadata: date = package_metadata["mtime"] else: date = None return cls( package_name=package_metadata["name"], url=url, filename=os.path.basename(url), date=date, shasum=package_metadata["dist"]["shasum"], version=extrinsic_version, raw_info=package_metadata, directory_extrinsic_metadata=[ RawExtrinsicMetadataCore( format="replicate-npm-package-json", metadata=json.dumps(package_metadata).encode(), ) ], ) class NpmLoader(PackageLoader[NpmPackageInfo]): - """Load npm origin's artifact releases into swh archive. - - """ + """Load npm origin's artifact releases into swh archive.""" visit_type = "npm" def __init__( self, storage: StorageInterface, url: str, max_content_size: Optional[int] = None, ): """Constructor Args str: origin url (e.g. https://www.npmjs.com/package/) """ super().__init__(storage=storage, url=url, max_content_size=max_content_size) self.package_name = url.split("https://www.npmjs.com/package/")[1] safe_name = quote(self.package_name, safe="") self.provider_url = f"https://replicate.npmjs.com/{safe_name}/" self._info: Dict[str, Any] = {} self._versions = None @cached_method def _raw_info(self) -> bytes: return api_info(self.provider_url) @cached_method def info(self) -> Dict: - """Return the project metadata information (fetched from npm registry) - - """ + """Return the project metadata information (fetched from npm registry)""" return json.loads(self._raw_info()) def get_versions(self) -> Sequence[str]: return sorted(list(self.info()["versions"].keys())) def get_default_version(self) -> str: return self.info()["dist-tags"].get("latest", "") def get_metadata_authority(self): return MetadataAuthority( - type=MetadataAuthorityType.FORGE, url="https://npmjs.com/", metadata={}, + type=MetadataAuthorityType.FORGE, + url="https://npmjs.com/", + metadata={}, ) def get_package_info(self, version: str) -> Iterator[Tuple[str, NpmPackageInfo]]: p_info = NpmPackageInfo.from_metadata( project_metadata=self.info(), version=version ) yield release_name(version), p_info def build_release( self, p_info: NpmPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Release]: # Metadata from NPM is not intrinsic to tarballs. # This means two package versions can have the same tarball, but different # metadata. To avoid mixing up releases, every field used to build the # release object must be part of NpmPackageInfo.MANIFEST_FORMAT. i_metadata = extract_intrinsic_metadata(uncompressed_path) if not i_metadata: return None author = extract_npm_package_author(i_metadata) assert self.package_name == p_info.package_name msg = ( f"Synthetic release for NPM source package {p_info.package_name} " f"version {p_info.version}\n" ) if p_info.date is None: url = p_info.url artifact_name = os.path.basename(url) raise ValueError( "Origin %s: Cannot determine upload time for artifact %s." % (p_info.url, artifact_name) ) date = TimestampWithTimezone.from_iso8601(p_info.date) # FIXME: this is to remain bug-compatible with earlier versions: date = attr.evolve(date, timestamp=attr.evolve(date.timestamp, microseconds=0)) r = Release( name=p_info.version.encode(), message=msg.encode(), author=author, date=date, target=directory, target_type=ObjectType.DIRECTORY, synthetic=True, ) return r def _author_str(author_data: Union[Dict, List, str]) -> str: - """Parse author from package.json author fields - - """ + """Parse author from package.json author fields""" if isinstance(author_data, dict): author_str = "" name = author_data.get("name") if name is not None: if isinstance(name, str): author_str += name elif isinstance(name, list): author_str += _author_str(name[0]) if len(name) > 0 else "" email = author_data.get("email") if email is not None: author_str += f" <{email}>" result = author_str elif isinstance(author_data, list): result = _author_str(author_data[0]) if len(author_data) > 0 else "" else: result = author_data return result def extract_npm_package_author(package_json: Dict[str, Any]) -> Person: """ Extract package author from a ``package.json`` file content and return it in swh format. Args: package_json: Dict holding the content of parsed ``package.json`` file Returns: Person """ for author_key in ("author", "authors"): if author_key in package_json: author_data = package_json[author_key] if author_data is None: return EMPTY_PERSON author_str = _author_str(author_data) return Person.from_fullname(author_str.encode()) return EMPTY_PERSON def _lstrip_bom(s, bom=BOM_UTF8): if s.startswith(bom): return s[len(bom) :] else: return s def load_json(json_bytes): """ Try to load JSON from bytes and return a dictionary. First try to decode from utf-8. If the decoding failed, try to detect the encoding and decode again with replace error handling. If JSON is malformed, an empty dictionary will be returned. Args: json_bytes (bytes): binary content of a JSON file Returns: dict: JSON data loaded in a dictionary """ json_data = {} try: json_str = _lstrip_bom(json_bytes).decode("utf-8") except UnicodeDecodeError: encoding = chardet.detect(json_bytes)["encoding"] if encoding: json_str = json_bytes.decode(encoding, "replace") try: json_data = json.loads(json_str) except json.decoder.JSONDecodeError: pass return json_data def extract_intrinsic_metadata(dir_path: str) -> Dict: """Given an uncompressed path holding the pkginfo file, returns a pkginfo parsed structure as a dict. The release artifact contains at their root one folder. For example: $ tar tvf zprint-0.0.6.tar.gz drwxr-xr-x root/root 0 2018-08-22 11:01 zprint-0.0.6/ ... Args: dir_path (str): Path to the uncompressed directory representing a release artifact from npm. Returns: the pkginfo parsed structure as a dict if any or None if none was present. """ # Retrieve the root folder of the archive if not os.path.exists(dir_path): return {} lst = os.listdir(dir_path) if len(lst) == 0: return {} project_dirname = lst[0] package_json_path = os.path.join(dir_path, project_dirname, "package.json") if not os.path.exists(package_json_path): return {} with open(package_json_path, "rb") as package_json_file: package_json_bytes = package_json_file.read() return load_json(package_json_bytes) diff --git a/swh/loader/package/npm/tests/test_npm.py b/swh/loader/package/npm/tests/test_npm.py index 63e5924..61fe75b 100644 --- a/swh/loader/package/npm/tests/test_npm.py +++ b/swh/loader/package/npm/tests/test_npm.py @@ -1,729 +1,773 @@ # Copyright (C) 2019-2021 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 datetime import json import os import pytest from swh.loader.package import __version__ from swh.loader.package.npm.loader import ( NpmLoader, _author_str, extract_npm_package_author, ) from swh.loader.tests import assert_last_visit_matches, check_snapshot, get_stats from swh.model.hashutil import hash_to_bytes from swh.model.model import ( Person, RawExtrinsicMetadata, Release, Snapshot, SnapshotBranch, TargetType, TimestampWithTimezone, ) from swh.model.model import MetadataAuthority, MetadataAuthorityType, MetadataFetcher from swh.model.model import ObjectType as ModelObjectType from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID, ObjectType from swh.storage.interface import PagedResult @pytest.fixture def org_api_info(datadir) -> bytes: - with open(os.path.join(datadir, "https_replicate.npmjs.com", "org"), "rb",) as f: + with open( + os.path.join(datadir, "https_replicate.npmjs.com", "org"), + "rb", + ) as f: return f.read() def test_npm_author_str(): for author, expected_author in [ ("author", "author"), ( ["Al from quantum leap", "hal from 2001 space odyssey"], "Al from quantum leap", ), ([], ""), - ({"name": "groot", "email": "groot@galaxy.org",}, "groot "), - ({"name": "somebody",}, "somebody"), + ( + { + "name": "groot", + "email": "groot@galaxy.org", + }, + "groot ", + ), + ( + { + "name": "somebody", + }, + "somebody", + ), ({"email": "no@one.org"}, " "), # note first elt is an extra blank - ({"name": "no one", "email": None,}, "no one"), - ({"email": None,}, ""), + ( + { + "name": "no one", + "email": None, + }, + "no one", + ), + ( + { + "email": None, + }, + "", + ), ({"name": None}, ""), - ({"name": None, "email": None,}, ""), + ( + { + "name": None, + "email": None, + }, + "", + ), ({}, ""), (None, None), - ({"name": []}, "",), ( - {"name": ["Susan McSween", "William H. Bonney", "Doc Scurlock",]}, + {"name": []}, + "", + ), + ( + { + "name": [ + "Susan McSween", + "William H. Bonney", + "Doc Scurlock", + ] + }, "Susan McSween", ), (None, None), ]: assert _author_str(author) == expected_author def test_npm_extract_npm_package_author(datadir): package_metadata_filepath = os.path.join( datadir, "https_replicate.npmjs.com", "org_visit1" ) with open(package_metadata_filepath) as json_file: package_metadata = json.load(json_file) extract_npm_package_author(package_metadata["versions"]["0.0.2"]) == Person( fullname=b"mooz ", name=b"mooz", email=b"stillpedant@gmail.com", ) assert extract_npm_package_author(package_metadata["versions"]["0.0.3"]) == Person( fullname=b"Masafumi Oyamada ", name=b"Masafumi Oyamada", email=b"stillpedant@gmail.com", ) package_json = json.loads( """ { "name": "highlightjs-line-numbers.js", "version": "2.7.0", "description": "Highlight.js line numbers plugin.", "main": "src/highlightjs-line-numbers.js", "dependencies": {}, "devDependencies": { "gulp": "^4.0.0", "gulp-rename": "^1.4.0", "gulp-replace": "^0.6.1", "gulp-uglify": "^1.2.0" }, "repository": { "type": "git", "url": "https://github.com/wcoder/highlightjs-line-numbers.js.git" }, "author": "Yauheni Pakala ", "license": "MIT", "bugs": { "url": "https://github.com/wcoder/highlightjs-line-numbers.js/issues" }, "homepage": "http://wcoder.github.io/highlightjs-line-numbers.js/" }""" ) assert extract_npm_package_author(package_json) == Person( fullname=b"Yauheni Pakala ", name=b"Yauheni Pakala", email=b"evgeniy.pakalo@gmail.com", ) package_json = json.loads( """ { "name": "3-way-diff", "version": "0.0.1", "description": "3-way diffing of JavaScript objects", "main": "index.js", "authors": [ { "name": "Shawn Walsh", "url": "https://github.com/shawnpwalsh" }, { "name": "Markham F Rollins IV", "url": "https://github.com/mrollinsiv" } ], "keywords": [ "3-way diff", "3 way diff", "three-way diff", "three way diff" ], "devDependencies": { "babel-core": "^6.20.0", "babel-preset-es2015": "^6.18.0", "mocha": "^3.0.2" }, "dependencies": { "lodash": "^4.15.0" } }""" ) assert extract_npm_package_author(package_json) == Person( fullname=b"Shawn Walsh", name=b"Shawn Walsh", email=None ) package_json = json.loads( """ { "name": "yfe-ynpm", "version": "1.0.0", "homepage": "http://gitlab.ywwl.com/yfe/yfe-ynpm", "repository": { "type": "git", "url": "git@gitlab.ywwl.com:yfe/yfe-ynpm.git" }, "author": [ "fengmk2 (https://fengmk2.com)", "xufuzi (https://7993.org)" ], "license": "MIT" }""" ) assert extract_npm_package_author(package_json) == Person( fullname=b"fengmk2 (https://fengmk2.com)", name=b"fengmk2", email=b"fengmk2@gmail.com", ) package_json = json.loads( """ { "name": "umi-plugin-whale", "version": "0.0.8", "description": "Internal contract component", "authors": { "name": "xiaohuoni", "email": "448627663@qq.com" }, "repository": "alitajs/whale", "devDependencies": { "np": "^3.0.4", "umi-tools": "*" }, "license": "MIT" }""" ) assert extract_npm_package_author(package_json) == Person( fullname=b"xiaohuoni <448627663@qq.com>", name=b"xiaohuoni", email=b"448627663@qq.com", ) package_json_no_authors = json.loads( """{ "authors": null, "license": "MIT" }""" ) assert extract_npm_package_author(package_json_no_authors) == Person.from_fullname( b"" ) def normalize_hashes(hashes): if isinstance(hashes, str): return hash_to_bytes(hashes) if isinstance(hashes, list): return [hash_to_bytes(x) for x in hashes] return {hash_to_bytes(k): hash_to_bytes(v) for k, v in hashes.items()} _expected_new_contents_first_visit = normalize_hashes( [ "4ce3058e16ab3d7e077f65aabf855c34895bf17c", "858c3ceee84c8311adc808f8cdb30d233ddc9d18", "0fa33b4f5a4e0496da6843a38ff1af8b61541996", "85a410f8ef8eb8920f2c384a9555566ad4a2e21b", "9163ac8025923d5a45aaac482262893955c9b37b", "692cf623b8dd2c5df2c2998fd95ae4ec99882fb4", "18c03aac6d3e910efb20039c15d70ab5e0297101", "41265c42446aac17ca769e67d1704f99e5a1394d", "783ff33f5882813dca9239452c4a7cadd4dba778", "b029cfb85107aee4590c2434a3329bfcf36f8fa1", "112d1900b4c2e3e9351050d1b542c9744f9793f3", "5439bbc4bd9a996f1a38244e6892b71850bc98fd", "d83097a2f994b503185adf4e719d154123150159", "d0939b4898e83090ee55fd9d8a60e312cfadfbaf", "b3523a26f7147e4af40d9d462adaae6d49eda13e", "cd065fb435d6fb204a8871bcd623d0d0e673088c", "2854a40855ad839a54f4b08f5cff0cf52fca4399", "b8a53bbaac34ebb8c6169d11a4b9f13b05c583fe", "0f73d56e1cf480bded8a1ecf20ec6fc53c574713", "0d9882b2dfafdce31f4e77fe307d41a44a74cefe", "585fc5caab9ead178a327d3660d35851db713df1", "e8cd41a48d79101977e3036a87aeb1aac730686f", "5414efaef33cceb9f3c9eb5c4cc1682cd62d14f7", "9c3cc2763bf9e9e37067d3607302c4776502df98", "3649a68410e354c83cd4a38b66bd314de4c8f5c9", "e96ed0c091de1ebdf587104eaf63400d1974a1fe", "078ca03d2f99e4e6eab16f7b75fbb7afb699c86c", "38de737da99514de6559ff163c988198bc91367a", ] ) _expected_new_directories_first_visit = normalize_hashes( [ "3370d20d6f96dc1c9e50f083e2134881db110f4f", "42753c0c2ab00c4501b552ac4671c68f3cf5aece", "d7895533ef5edbcffdea3f057d9fef3a1ef845ce", "80579be563e2ef3e385226fe7a3f079b377f142c", "3b0ddc6a9e58b4b53c222da4e27b280b6cda591c", "bcad03ce58ac136f26f000990fc9064e559fe1c0", "5fc7e82a1bc72e074665c6078c6d3fad2f13d7ca", "e3cd26beba9b1e02f6762ef54bd9ac80cc5f25fd", "584b5b4b6cf7f038095e820b99386a9c232de931", "184c8d6d0d242f2b1792ef9d3bf396a5434b7f7a", "bb5f4ee143c970367eb409f2e4c1104898048b9d", "1b95491047add1103db0dfdfa84a9735dcb11e88", "a00c6de13471a2d66e64aca140ddb21ef5521e62", "5ce6c1cd5cda2d546db513aaad8c72a44c7771e2", "c337091e349b6ac10d38a49cdf8c2401ef9bb0f2", "202fafcd7c0f8230e89d5496ad7f44ab12b807bf", "775cc516543be86c15c1dc172f49c0d4e6e78235", "ff3d1ead85a14f891e8b3fa3a89de39db1b8de2e", ] ) _expected_new_releases_first_visit = normalize_hashes( { "d38cc0b571cd41f3c85513864e049766b42032a7": ( "42753c0c2ab00c4501b552ac4671c68f3cf5aece" ), "62bf7076bae9aa2cb4d6cb3bf7ce0ea4fdd5b295": ( "3370d20d6f96dc1c9e50f083e2134881db110f4f" ), "6e976db82f6c310596b21fb0ed8b11f507631434": ( "d7895533ef5edbcffdea3f057d9fef3a1ef845ce" ), } ) def package_url(package): return "https://www.npmjs.com/package/%s" % package def package_metadata_url(package): return "https://replicate.npmjs.com/%s/" % package def test_npm_loader_first_visit(swh_storage, requests_mock_datadir, org_api_info): package = "org" url = package_url(package) loader = NpmLoader(swh_storage, url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("0996ca28d6280499abcf485b51c4e3941b057249") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="npm", snapshot=expected_snapshot_id ) release_id = "d38cc0b571cd41f3c85513864e049766b42032a7" versions = [ ("0.0.2", release_id), ("0.0.3", "62bf7076bae9aa2cb4d6cb3bf7ce0ea4fdd5b295"), ("0.0.4", "6e976db82f6c310596b21fb0ed8b11f507631434"), ] expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"HEAD": SnapshotBranch( target=b"releases/0.0.4", target_type=TargetType.ALIAS ), **{ b"releases/" + version_name.encode(): SnapshotBranch( - target=hash_to_bytes(version_id), target_type=TargetType.RELEASE, + target=hash_to_bytes(version_id), + target_type=TargetType.RELEASE, ) for (version_name, version_id) in versions }, }, ) check_snapshot(expected_snapshot, swh_storage) assert swh_storage.release_get([hash_to_bytes(release_id)])[0] == Release( name=b"0.0.2", message=b"Synthetic release for NPM source package org version 0.0.2\n", target=hash_to_bytes("42753c0c2ab00c4501b552ac4671c68f3cf5aece"), target_type=ModelObjectType.DIRECTORY, synthetic=True, author=Person( fullname=b"mooz ", name=b"mooz", email=b"stillpedant@gmail.com", ), date=TimestampWithTimezone.from_datetime( datetime.datetime(2014, 1, 1, 15, 40, 33, tzinfo=datetime.timezone.utc) ), id=hash_to_bytes(release_id), ) contents = swh_storage.content_get(_expected_new_contents_first_visit) count = sum(0 if content is None else 1 for content in contents) assert count == len(_expected_new_contents_first_visit) assert ( list(swh_storage.directory_missing(_expected_new_directories_first_visit)) == [] ) assert list(swh_storage.release_missing(_expected_new_releases_first_visit)) == [] metadata_authority = MetadataAuthority( - type=MetadataAuthorityType.FORGE, url="https://npmjs.com/", + type=MetadataAuthorityType.FORGE, + url="https://npmjs.com/", ) for (version_name, release_id) in versions: release = swh_storage.release_get([hash_to_bytes(release_id)])[0] assert release.target_type == ModelObjectType.DIRECTORY directory_id = release.target directory_swhid = ExtendedSWHID( - object_type=ExtendedObjectType.DIRECTORY, object_id=directory_id, + object_type=ExtendedObjectType.DIRECTORY, + object_id=directory_id, ) release_swhid = CoreSWHID( - object_type=ObjectType.RELEASE, object_id=hash_to_bytes(release_id), + object_type=ObjectType.RELEASE, + object_id=hash_to_bytes(release_id), ) expected_metadata = [ RawExtrinsicMetadata( target=directory_swhid, authority=metadata_authority, fetcher=MetadataFetcher( - name="swh.loader.package.npm.loader.NpmLoader", version=__version__, + name="swh.loader.package.npm.loader.NpmLoader", + version=__version__, ), discovery_date=loader.visit_date, format="replicate-npm-package-json", metadata=json.dumps( json.loads(org_api_info)["versions"][version_name] ).encode(), origin="https://www.npmjs.com/package/org", release=release_swhid, ) ] assert swh_storage.raw_extrinsic_metadata_get( - directory_swhid, metadata_authority, - ) == PagedResult(next_page_token=None, results=expected_metadata,) + directory_swhid, + metadata_authority, + ) == PagedResult( + next_page_token=None, + results=expected_metadata, + ) stats = get_stats(swh_storage) assert { "content": len(_expected_new_contents_first_visit), "directory": len(_expected_new_directories_first_visit), "origin": 1, "origin_visit": 1, "release": len(_expected_new_releases_first_visit), "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats def test_npm_loader_incremental_visit(swh_storage, requests_mock_datadir_visits): package = "org" url = package_url(package) loader = NpmLoader(swh_storage, url) expected_snapshot_id = hash_to_bytes("0996ca28d6280499abcf485b51c4e3941b057249") actual_load_status = loader.load() assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="npm", snapshot=expected_snapshot_id ) stats = get_stats(swh_storage) assert { "content": len(_expected_new_contents_first_visit), "directory": len(_expected_new_directories_first_visit), "origin": 1, "origin_visit": 1, "release": len(_expected_new_releases_first_visit), "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats # reset loader internal state del loader._cached_info del loader._cached__raw_info actual_load_status2 = loader.load() assert actual_load_status2["status"] == "eventful" snap_id2 = actual_load_status2["snapshot_id"] assert snap_id2 is not None assert snap_id2 != actual_load_status["snapshot_id"] assert_last_visit_matches(swh_storage, url, status="full", type="npm") stats = get_stats(swh_storage) assert { # 3 new releases artifacts "content": len(_expected_new_contents_first_visit) + 14, "directory": len(_expected_new_directories_first_visit) + 15, "origin": 1, "origin_visit": 2, "release": len(_expected_new_releases_first_visit) + 3, "revision": 0, "skipped_content": 0, "snapshot": 2, } == stats urls = [ m.url for m in requests_mock_datadir_visits.request_history if m.url.startswith("https://registry.npmjs.org") ] assert len(urls) == len(set(urls)) # we visited each artifact once across @pytest.mark.usefixtures("requests_mock_datadir") def test_npm_loader_version_divergence(swh_storage): package = "@aller/shared" url = package_url(package) loader = NpmLoader(swh_storage, url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("68eed3d3bc852e7f435a84f18ee77e23f6884be2") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="npm", snapshot=expected_snapshot_id ) expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"HEAD": SnapshotBranch( target_type=TargetType.ALIAS, target=b"releases/0.1.0" ), b"releases/0.1.0": SnapshotBranch( target_type=TargetType.RELEASE, target=hash_to_bytes("0c486b50b407f847ef7581f595c2b6c2062f1089"), ), b"releases/0.1.1-alpha.14": SnapshotBranch( target_type=TargetType.RELEASE, target=hash_to_bytes("79d80c87c0a8d104a216cc539baad962a454802a"), ), }, ) check_snapshot(expected_snapshot, swh_storage) stats = get_stats(swh_storage) assert { # 1 new releases artifacts "content": 534, "directory": 153, "origin": 1, "origin_visit": 1, "release": 2, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats def test_npm_loader_duplicate_shasum(swh_storage, requests_mock_datadir): """Test with two versions that have exactly the same tarball""" package = "org_version_mismatch" url = package_url(package) loader = NpmLoader(swh_storage, url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("ac867a4c22ba4e22a022d319f309714477412a5a") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="npm", snapshot=expected_snapshot_id ) beta_release_id = "e6d5490a02ac2a8dcd49702f9ccd5a64c90a46f1" release_id = "f6985f437e28db6eb1b7533230e05ed99f2c91f0" versions = [ ("0.0.3-beta", beta_release_id), ("0.0.3", release_id), ] expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"HEAD": SnapshotBranch( target=b"releases/0.0.3", target_type=TargetType.ALIAS ), **{ b"releases/" + version_name.encode(): SnapshotBranch( - target=hash_to_bytes(version_id), target_type=TargetType.RELEASE, + target=hash_to_bytes(version_id), + target_type=TargetType.RELEASE, ) for (version_name, version_id) in versions }, }, ) check_snapshot(expected_snapshot, swh_storage) assert swh_storage.release_get([hash_to_bytes(beta_release_id)])[0] == Release( name=b"0.0.3-beta", message=( b"Synthetic release for NPM source package org_version_mismatch " b"version 0.0.3-beta\n" ), target=hash_to_bytes("3370d20d6f96dc1c9e50f083e2134881db110f4f"), target_type=ModelObjectType.DIRECTORY, synthetic=True, author=Person.from_fullname(b"Masafumi Oyamada "), date=TimestampWithTimezone.from_datetime( datetime.datetime(2014, 1, 1, 15, 40, 33, tzinfo=datetime.timezone.utc) ), id=hash_to_bytes(beta_release_id), ) assert swh_storage.release_get([hash_to_bytes(release_id)])[0] == Release( name=b"0.0.3", message=( b"Synthetic release for NPM source package org_version_mismatch " b"version 0.0.3\n" ), target=hash_to_bytes("3370d20d6f96dc1c9e50f083e2134881db110f4f"), target_type=ModelObjectType.DIRECTORY, synthetic=True, author=Person.from_fullname(b"Masafumi Oyamada "), date=TimestampWithTimezone.from_datetime( datetime.datetime(2014, 1, 1, 15, 55, 45, tzinfo=datetime.timezone.utc) ), id=hash_to_bytes(release_id), ) # Check incremental re-load keeps it unchanged loader = NpmLoader(swh_storage, url) actual_load_status = loader.load() assert actual_load_status == { "status": "uneventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="npm", snapshot=expected_snapshot_id ) def test_npm_artifact_with_no_intrinsic_metadata(swh_storage, requests_mock_datadir): - """Skip artifact with no intrinsic metadata during ingestion - - """ + """Skip artifact with no intrinsic metadata during ingestion""" package = "nativescript-telerik-analytics" url = package_url(package) loader = NpmLoader(swh_storage, url) actual_load_status = loader.load() # no branch as one artifact without any intrinsic metadata expected_snapshot = Snapshot( - id=hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), branches={}, + id=hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), + branches={}, ) assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot.id.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="npm", snapshot=expected_snapshot.id ) check_snapshot(expected_snapshot, swh_storage) def test_npm_artifact_with_no_upload_time(swh_storage, requests_mock_datadir): - """With no time upload, artifact is skipped - - """ + """With no time upload, artifact is skipped""" package = "jammit-no-time" url = package_url(package) loader = NpmLoader(swh_storage, url) actual_load_status = loader.load() # no branch as one artifact without any intrinsic metadata expected_snapshot = Snapshot( - id=hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), branches={}, + id=hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), + branches={}, ) assert actual_load_status == { "status": "uneventful", "snapshot_id": expected_snapshot.id.hex(), } assert_last_visit_matches( swh_storage, url, status="partial", type="npm", snapshot=expected_snapshot.id ) check_snapshot(expected_snapshot, swh_storage) def test_npm_artifact_use_mtime_if_no_time(swh_storage, requests_mock_datadir): - """With no time upload, artifact is skipped - - """ + """With no time upload, artifact is skipped""" package = "jammit-express" url = package_url(package) loader = NpmLoader(swh_storage, url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("33b8f105d48ce16b6c59158af660e0cc78bcbef4") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } # artifact is used expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"HEAD": SnapshotBranch( target_type=TargetType.ALIAS, target=b"releases/0.0.1" ), b"releases/0.0.1": SnapshotBranch( target_type=TargetType.RELEASE, target=hash_to_bytes("3e3b800570869fa9b3dbc302500553e62400cc06"), ), }, ) assert_last_visit_matches( swh_storage, url, status="full", type="npm", snapshot=expected_snapshot.id ) check_snapshot(expected_snapshot, swh_storage) def test_npm_no_artifact(swh_storage, requests_mock_datadir): - """If no artifacts at all is found for origin, the visit fails completely - - """ + """If no artifacts at all is found for origin, the visit fails completely""" package = "catify" url = package_url(package) loader = NpmLoader(swh_storage, url) actual_load_status = loader.load() assert actual_load_status == { "status": "failed", } assert_last_visit_matches(swh_storage, url, status="failed", type="npm") def test_npm_origin_not_found(swh_storage, requests_mock_datadir): url = package_url("non-existent-url") loader = NpmLoader(swh_storage, url) assert loader.load() == {"status": "failed"} assert_last_visit_matches( swh_storage, url, status="not_found", type="npm", snapshot=None ) diff --git a/swh/loader/package/opam/loader.py b/swh/loader/package/opam/loader.py index a2bb808..8fb4482 100644 --- a/swh/loader/package/opam/loader.py +++ b/swh/loader/package/opam/loader.py @@ -1,261 +1,265 @@ # Copyright (C) 2021 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 io import os from subprocess import PIPE, Popen, call from typing import Iterator, List, Optional, Tuple import attr from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, RawExtrinsicMetadataCore, ) from swh.loader.package.utils import cached_method from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, ObjectType, Person, Release, Sha1Git, ) from swh.storage.interface import StorageInterface @attr.s class OpamPackageInfo(BasePackageInfo): author = attr.ib(type=Person) committer = attr.ib(type=Person) def opam_read( cmd: List[str], init_error_msg_if_any: Optional[str] = None ) -> Optional[str]: """This executes an opam command and returns the first line of the output. Args: cmd: Opam command to execute as a list of string init_error_msg_if_any: Error message to raise in case a problem occurs during initialization Raises: ValueError with the init_error_msg_if_any content in case stdout is not consumable and the variable is provided with non empty value. Returns: the first line of the executed command output """ with Popen(cmd, stdout=PIPE) as proc: if proc.stdout is not None: for line in io.TextIOWrapper(proc.stdout): # care only for the first line output result (mostly blank separated # values, callers will deal with the parsing of the line) return line elif init_error_msg_if_any: raise ValueError(init_error_msg_if_any) return None class OpamLoader(PackageLoader[OpamPackageInfo]): """Load all versions of a given package in a given opam repository. The state of the opam repository is stored in a directory called an opam root. This folder is a requisite for the opam binary to actually list information on package. When initialize_opam_root is False (the default for production workers), the opam root must already have been configured outside of the loading process. If not an error is raised, thus failing the loading. For standalone workers, initialize_opam_root must be set to True, so the ingestion can take care of installing the required opam root properly. The remaining ingestion uses the opam binary to give the versions of the given package. Then, for each version, the loader uses the opam binary to list the tarball url to fetch and ingest. """ visit_type = "opam" def __init__( self, storage: StorageInterface, url: str, opam_root: str, opam_instance: str, opam_url: str, opam_package: str, max_content_size: Optional[int] = None, initialize_opam_root: bool = False, ): super().__init__(storage=storage, url=url, max_content_size=max_content_size) self.opam_root = opam_root self.opam_instance = opam_instance self.opam_url = opam_url self.opam_package = opam_package self.initialize_opam_root = initialize_opam_root def get_package_dir(self) -> str: return ( f"{self.opam_root}/repo/{self.opam_instance}/packages/{self.opam_package}" ) def get_package_name(self, version: str) -> str: return f"{self.opam_package}.{version}" def get_package_file(self, version: str) -> str: return f"{self.get_package_dir()}/{self.get_package_name(version)}/opam" def get_metadata_authority(self): return MetadataAuthority(type=MetadataAuthorityType.FORGE, url=self.opam_url) @cached_method def _compute_versions(self) -> List[str]: """Compute the versions using opam internals Raises: ValueError in case the lister is not able to determine the list of versions Returns: The list of versions for the package """ # TODO: use `opam show` instead of this workaround when it support the `--repo` # flag package_dir = self.get_package_dir() if not os.path.exists(package_dir): raise ValueError( f"can't get versions for package {self.opam_package} " f"(at url {self.url})." ) versions = [ ".".join(version.split(".")[1:]) for version in os.listdir(package_dir) ] if not versions: raise ValueError( f"can't get versions for package {self.opam_package} " f"(at url {self.url})" ) versions.sort() return versions def get_versions(self) -> List[str]: """First initialize the opam root directory if needed then start listing the package versions. Raises: ValueError in case the lister is not able to determine the list of versions or if the opam root directory is invalid. """ if self.initialize_opam_root: # for standalone loader (e.g docker), loader must initialize the opam root # folder call( [ "opam", "init", "--reinit", "--bare", "--no-setup", "--root", self.opam_root, self.opam_instance, self.opam_url, ] ) else: # for standard/production loaders, no need to initialize the opam root # folder. It must be present though so check for it, if not present, raise if not os.path.isfile(os.path.join(self.opam_root, "config")): # so if not correctly setup, raise immediately raise ValueError("Invalid opam root") return self._compute_versions() def get_default_version(self) -> str: """Return the most recent version of the package as default.""" return self._compute_versions()[-1] def _opam_show_args(self, version: str): package_file = self.get_package_file(version) return [ "opam", "show", "--color", "never", "--safe", "--normalise", "--root", self.opam_root, "--file", package_file, ] def get_enclosed_single_line_field(self, field, version) -> Optional[str]: result = opam_read(self._opam_show_args(version) + ["--field", field]) # Sanitize the result if any (remove trailing \n and enclosing ") return result.strip().strip('"') if result else None def get_package_info(self, version: str) -> Iterator[Tuple[str, OpamPackageInfo]]: url = self.get_enclosed_single_line_field("url.src:", version) if url is None: raise ValueError( - f"can't get field url.src: for version {version} of package {self.opam_package} \ - (at url {self.url}) from `opam show`" + f"can't get field url.src: for version {version} of package {self.opam_package}" + f" (at url {self.url}) from `opam show`" ) authors_field = self.get_enclosed_single_line_field("authors:", version) fullname = b"" if authors_field is None else str.encode(authors_field) author = Person.from_fullname(fullname) maintainer_field = self.get_enclosed_single_line_field("maintainer:", version) fullname = b"" if maintainer_field is None else str.encode(maintainer_field) committer = Person.from_fullname(fullname) with Popen(self._opam_show_args(version) + ["--raw"], stdout=PIPE) as proc: assert proc.stdout is not None metadata = proc.stdout.read() yield self.get_package_name(version), OpamPackageInfo( url=url, filename=None, author=author, committer=committer, version=version, directory_extrinsic_metadata=[ RawExtrinsicMetadataCore( - metadata=metadata, format="opam-package-definition", + metadata=metadata, + format="opam-package-definition", ) ], ) def build_release( - self, p_info: OpamPackageInfo, uncompressed_path: str, directory: Sha1Git, + self, + p_info: OpamPackageInfo, + uncompressed_path: str, + directory: Sha1Git, ) -> Optional[Release]: msg = ( f"Synthetic release for OPAM source package {self.opam_package} " f"version {p_info.version}\n" ) return Release( name=p_info.version.encode(), author=p_info.author, message=msg.encode(), date=None, target=directory, target_type=ObjectType.DIRECTORY, synthetic=True, ) diff --git a/swh/loader/package/opam/tests/test_opam.py b/swh/loader/package/opam/tests/test_opam.py index b37d971..1ab1cdc 100644 --- a/swh/loader/package/opam/tests/test_opam.py +++ b/swh/loader/package/opam/tests/test_opam.py @@ -1,394 +1,414 @@ # Copyright (C) 2019-2022 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from os.path import exists import shutil import pytest from swh.loader.package import __version__ from swh.loader.package.loader import RawExtrinsicMetadataCore from swh.loader.package.opam.loader import OpamLoader, OpamPackageInfo from swh.loader.tests import assert_last_visit_matches, check_snapshot, get_stats from swh.model.hashutil import hash_to_bytes from swh.model.model import ( Person, RawExtrinsicMetadata, Release, Snapshot, SnapshotBranch, TargetType, ) from swh.model.model import MetadataAuthority, MetadataAuthorityType, MetadataFetcher from swh.model.model import ObjectType as ModelObjectType from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID, ObjectType from swh.storage.interface import PagedResult OCB_METADATA = b"""\ opam-version: "2.0" name: "ocb" version: "0.1" synopsis: "SVG badge generator" description: "An OCaml library for SVG badge generation. There\'s also a command-line tool provided." maintainer: "OCamlPro " authors: "OCamlPro " license: "ISC" homepage: "https://ocamlpro.github.io/ocb/" doc: "https://ocamlpro.github.io/ocb/api/" bug-reports: "https://github.com/OCamlPro/ocb/issues" depends: [ "ocaml" {>= "4.05"} "dune" {>= "2.0"} "odoc" {with-doc} ] build: [ ["dune" "subst"] {dev} [ "dune" "build" "-p" name "-j" jobs "@install" "@runtest" {with-test} "@doc" {with-doc} ] ] dev-repo: "git+https://github.com/OCamlPro/ocb.git" url { src: "https://github.com/OCamlPro/ocb/archive/0.1.tar.gz" checksum: [ "sha256=aa27684fbda1b8036ae7e3c87de33a98a9cd2662bcc91c8447e00e41476b6a46" "sha512=1260344f184dd8c8074b0439dbcc8a5d59550a654c249cd61913d4c150c664f37b76195ddca38f7f6646d08bddb320ceb8d420508450b4f09a233cd5c22e6b9b" ] } """ # noqa @pytest.fixture def fake_opam_root(mocker, tmpdir, datadir): """Fixture to initialize the actual opam in test context. It mocks the actual opam init calls and installs a fake opam root out of the one present in datadir. """ # inhibits the real `subprocess.call` which prepares the required internal opam # state module_name = "swh.loader.package.opam.loader" mock_init = mocker.patch(f"{module_name}.call", return_value=None) # Installs the fake opam root for the tests to use fake_opam_root_src = f"{datadir}/fake_opam_repo" fake_opam_root_dst = f"{tmpdir}/opam" # old version does not support dirs_exist_ok... # TypeError: copytree() got an unexpected keyword argument 'dirs_exist_ok' # see: https://docs.python.org/3.7/library/shutil.html if exists(fake_opam_root_dst): shutil.rmtree(fake_opam_root_dst) shutil.copytree(fake_opam_root_src, fake_opam_root_dst) yield fake_opam_root_dst # loader are initialized with `initialize_opam_root=True` so this should be called assert mock_init.called, "This should be called when loader use this fixture" def test_opam_loader_no_opam_repository_fails(swh_storage, tmpdir, datadir): """Running opam loader without a prepared opam repository fails""" opam_url = f"file://{datadir}/fake_opam_repo" opam_root = tmpdir opam_instance = "loadertest" opam_package = "agrid" url = f"opam+{opam_url}/packages/{opam_package}" loader = OpamLoader( swh_storage, url, opam_root, opam_instance, opam_url, opam_package, initialize_opam_root=False, # The opam directory must be present and no init... ) # No opam root directory init directory from loader. So, at the opam root does not # exist, the loading fails. That's the expected use for the production workers # (whose opam_root maintenance will be externally managed). actual_load_status = loader.load() assert actual_load_status == {"status": "failed"} def test_opam_loader_one_version( tmpdir, requests_mock_datadir, fake_opam_root, datadir, swh_storage ): opam_url = f"file://{datadir}/fake_opam_repo" opam_root = fake_opam_root opam_instance = "loadertest" opam_package = "agrid" url = f"opam+{opam_url}/packages/{opam_package}" loader = OpamLoader( swh_storage, url, opam_root, opam_instance, opam_url, opam_package, initialize_opam_root=True, # go through the initialization while mocking it ) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("e1159446b00745ba4daa7ee26d74fbd81ecc081c") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="opam", snapshot=expected_snapshot_id ) release_id = hash_to_bytes("d4d8d3df4f34609a3eeabd48aea49002c5f54f41") expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ - b"HEAD": SnapshotBranch(target=b"agrid.0.1", target_type=TargetType.ALIAS,), + b"HEAD": SnapshotBranch( + target=b"agrid.0.1", + target_type=TargetType.ALIAS, + ), b"agrid.0.1": SnapshotBranch( - target=release_id, target_type=TargetType.RELEASE, + target=release_id, + target_type=TargetType.RELEASE, ), }, ) check_snapshot(expected_snapshot, swh_storage) assert swh_storage.release_get([release_id])[0] == Release( name=b"0.1", message=b"Synthetic release for OPAM source package agrid version 0.1\n", target=hash_to_bytes("00412ee5bc601deb462e55addd1004715116785e"), target_type=ModelObjectType.DIRECTORY, synthetic=True, author=Person.from_fullname(b"OCamlPro "), date=None, id=release_id, ) stats = get_stats(swh_storage) assert { "content": 18, "directory": 8, "origin": 1, "origin_visit": 1, "release": 1, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats def test_opam_loader_many_version( tmpdir, requests_mock_datadir, fake_opam_root, datadir, swh_storage ): opam_url = f"file://{datadir}/fake_opam_repo" opam_root = fake_opam_root opam_instance = "loadertest" opam_package = "directories" url = f"opam+{opam_url}/packages/{opam_package}" loader = OpamLoader( swh_storage, url, opam_root, opam_instance, opam_url, opam_package, initialize_opam_root=True, ) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("f498f7f3b0edbce5cf5834b487a4f8360f6a6a43") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"HEAD": SnapshotBranch( - target=b"directories.0.3", target_type=TargetType.ALIAS, + target=b"directories.0.3", + target_type=TargetType.ALIAS, ), b"directories.0.1": SnapshotBranch( target=hash_to_bytes("1c88d466b3d57a619e296999322d096fa37bb1c2"), target_type=TargetType.RELEASE, ), b"directories.0.2": SnapshotBranch( target=hash_to_bytes("d6f30684039ad485511a138e2ae504ff67a13075"), target_type=TargetType.RELEASE, ), b"directories.0.3": SnapshotBranch( target=hash_to_bytes("6cf92c0ff052074e69ac18809a9c8198bcc2e746"), target_type=TargetType.RELEASE, ), }, ) assert_last_visit_matches( swh_storage, url, status="full", type="opam", snapshot=expected_snapshot_id ) check_snapshot(expected_snapshot, swh_storage) def test_opam_release( tmpdir, requests_mock_datadir, fake_opam_root, swh_storage, datadir ): opam_url = f"file://{datadir}/fake_opam_repo" opam_root = fake_opam_root opam_instance = "loadertest" opam_package = "ocb" url = f"opam+{opam_url}/packages/{opam_package}" loader = OpamLoader( swh_storage, url, opam_root, opam_instance, opam_url, opam_package, initialize_opam_root=True, ) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("8ba39f050243a72ca667c5587a87413240cbaa47") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } info_iter = loader.get_package_info("0.1") branch_name, package_info = next(info_iter) expected_branch_name = "ocb.0.1" expected_package_info = OpamPackageInfo( url="https://github.com/OCamlPro/ocb/archive/0.1.tar.gz", filename=None, author=Person.from_fullname(b"OCamlPro "), committer=Person.from_fullname(b"OCamlPro "), version="0.1", directory_extrinsic_metadata=[ RawExtrinsicMetadataCore( - metadata=OCB_METADATA, format="opam-package-definition", + metadata=OCB_METADATA, + format="opam-package-definition", ) ], ) assert branch_name == expected_branch_name assert package_info == expected_package_info release_id = hash_to_bytes("c231e541eb29c712635ada394b04127ac69e9fb0") expected_snapshot = Snapshot( id=hash_to_bytes(actual_load_status["snapshot_id"]), branches={ - b"HEAD": SnapshotBranch(target=b"ocb.0.1", target_type=TargetType.ALIAS,), + b"HEAD": SnapshotBranch( + target=b"ocb.0.1", + target_type=TargetType.ALIAS, + ), b"ocb.0.1": SnapshotBranch( - target=release_id, target_type=TargetType.RELEASE, + target=release_id, + target_type=TargetType.RELEASE, ), }, ) assert_last_visit_matches( swh_storage, url, status="full", type="opam", snapshot=expected_snapshot.id ) check_snapshot(expected_snapshot, swh_storage) release = swh_storage.release_get([release_id])[0] assert release is not None assert release.author == expected_package_info.author def test_opam_metadata( tmpdir, requests_mock_datadir, fake_opam_root, swh_storage, datadir ): opam_url = f"file://{datadir}/fake_opam_repo" opam_root = fake_opam_root opam_instance = "loadertest" opam_package = "ocb" url = f"opam+{opam_url}/packages/{opam_package}" loader = OpamLoader( swh_storage, url, opam_root, opam_instance, opam_url, opam_package, initialize_opam_root=True, ) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" expected_release_id = hash_to_bytes("c231e541eb29c712635ada394b04127ac69e9fb0") expected_snapshot = Snapshot( id=hash_to_bytes(actual_load_status["snapshot_id"]), branches={ - b"HEAD": SnapshotBranch(target=b"ocb.0.1", target_type=TargetType.ALIAS,), + b"HEAD": SnapshotBranch( + target=b"ocb.0.1", + target_type=TargetType.ALIAS, + ), b"ocb.0.1": SnapshotBranch( - target=expected_release_id, target_type=TargetType.RELEASE, + target=expected_release_id, + target_type=TargetType.RELEASE, ), }, ) assert_last_visit_matches( swh_storage, url, status="full", type="opam", snapshot=expected_snapshot.id ) check_snapshot(expected_snapshot, swh_storage) release = swh_storage.release_get([expected_release_id])[0] assert release is not None release_swhid = CoreSWHID( object_type=ObjectType.RELEASE, object_id=expected_release_id ) directory_swhid = ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=release.target ) metadata_authority = MetadataAuthority( - type=MetadataAuthorityType.FORGE, url=opam_url, + type=MetadataAuthorityType.FORGE, + url=opam_url, ) expected_metadata = [ RawExtrinsicMetadata( target=directory_swhid, authority=metadata_authority, fetcher=MetadataFetcher( - name="swh.loader.package.opam.loader.OpamLoader", version=__version__, + name="swh.loader.package.opam.loader.OpamLoader", + version=__version__, ), discovery_date=loader.visit_date, format="opam-package-definition", metadata=OCB_METADATA, origin=url, release=release_swhid, ) ] assert swh_storage.raw_extrinsic_metadata_get( - directory_swhid, metadata_authority, - ) == PagedResult(next_page_token=None, results=expected_metadata,) + directory_swhid, + metadata_authority, + ) == PagedResult( + next_page_token=None, + results=expected_metadata, + ) diff --git a/swh/loader/package/pypi/loader.py b/swh/loader/package/pypi/loader.py index 3ceca15..d50e19d 100644 --- a/swh/loader/package/pypi/loader.py +++ b/swh/loader/package/pypi/loader.py @@ -1,251 +1,248 @@ # Copyright (C) 2019-2021 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 json import logging import os from typing import Any, Dict, Iterator, Optional, Sequence, Tuple from urllib.parse import urlparse import attr from pkginfo import UnpackedSDist from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, PartialExtID, RawExtrinsicMetadataCore, ) from swh.loader.package.utils import EMPTY_AUTHOR, api_info, cached_method, release_name from swh.model.hashutil import hash_to_bytes from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, ObjectType, Person, Release, Sha1Git, TimestampWithTimezone, ) from swh.storage.interface import StorageInterface logger = logging.getLogger(__name__) EXTID_TYPE = "pypi-archive-sha256" EXTID_VERSION = 0 @attr.s class PyPIPackageInfo(BasePackageInfo): raw_info = attr.ib(type=Dict[str, Any]) name = attr.ib(type=str) comment_text = attr.ib(type=Optional[str]) sha256 = attr.ib(type=str) upload_time = attr.ib(type=str) @classmethod def from_metadata( cls, metadata: Dict[str, Any], name: str, version: str ) -> "PyPIPackageInfo": return cls( url=metadata["url"], filename=metadata["filename"], version=version, raw_info=metadata, name=name, comment_text=metadata.get("comment_text"), sha256=metadata["digests"]["sha256"], upload_time=metadata["upload_time"], directory_extrinsic_metadata=[ RawExtrinsicMetadataCore( - format="pypi-project-json", metadata=json.dumps(metadata).encode(), + format="pypi-project-json", + metadata=json.dumps(metadata).encode(), ) ], ) def extid(self) -> PartialExtID: return (EXTID_TYPE, EXTID_VERSION, hash_to_bytes(self.sha256)) class PyPILoader(PackageLoader[PyPIPackageInfo]): - """Load pypi origin's artifact releases into swh archive. - - """ + """Load pypi origin's artifact releases into swh archive.""" visit_type = "pypi" def __init__( self, storage: StorageInterface, url: str, max_content_size: Optional[int] = None, ): super().__init__(storage=storage, url=url, max_content_size=max_content_size) self.provider_url = pypi_api_url(self.url) @cached_method def _raw_info(self) -> bytes: return api_info(self.provider_url) @cached_method def info(self) -> Dict: - """Return the project metadata information (fetched from pypi registry) - - """ + """Return the project metadata information (fetched from pypi registry)""" return json.loads(self._raw_info()) def get_versions(self) -> Sequence[str]: return self.info()["releases"].keys() def get_default_version(self) -> str: return self.info()["info"]["version"] def get_metadata_authority(self): p_url = urlparse(self.url) return MetadataAuthority( type=MetadataAuthorityType.FORGE, url=f"{p_url.scheme}://{p_url.netloc}/", metadata={}, ) def get_package_info(self, version: str) -> Iterator[Tuple[str, PyPIPackageInfo]]: res = [] for meta in self.info()["releases"][version]: # process only standard sdist archives if meta["packagetype"] != "sdist" or meta["filename"].lower().endswith( (".deb", ".egg", ".rpm", ".whl") ): continue p_info = PyPIPackageInfo.from_metadata( meta, name=self.info()["info"]["name"], version=version ) res.append((version, p_info)) if len(res) == 1: version, p_info = res[0] yield release_name(version), p_info else: for version, p_info in res: yield release_name(version, p_info.filename), p_info def build_release( self, p_info: PyPIPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Release]: i_metadata = extract_intrinsic_metadata(uncompressed_path) if not i_metadata: return None # from intrinsic metadata version_ = i_metadata.get("version", p_info.version) author_ = author(i_metadata) if p_info.comment_text: msg = p_info.comment_text else: msg = ( f"Synthetic release for PyPI source package {p_info.name} " f"version {version_}\n" ) date = TimestampWithTimezone.from_iso8601(p_info.upload_time) return Release( name=p_info.version.encode(), message=msg.encode(), author=author_, date=date, target=directory, target_type=ObjectType.DIRECTORY, synthetic=True, ) def pypi_api_url(url: str) -> str: """Compute api url from a project url Args: url (str): PyPI instance's url (e.g: https://pypi.org/project/requests) This deals with correctly transforming the project's api url (e.g https://pypi.org/pypi/requests/json) Returns: api url """ p_url = urlparse(url) project_name = p_url.path.rstrip("/").split("/")[-1] url = "%s://%s/pypi/%s/json" % (p_url.scheme, p_url.netloc, project_name) return url def extract_intrinsic_metadata(dir_path: str) -> Dict: """Given an uncompressed path holding the pkginfo file, returns a pkginfo parsed structure as a dict. The release artifact contains at their root one folder. For example: $ tar tvf zprint-0.0.6.tar.gz drwxr-xr-x root/root 0 2018-08-22 11:01 zprint-0.0.6/ ... Args: dir_path (str): Path to the uncompressed directory representing a release artifact from pypi. Returns: the pkginfo parsed structure as a dict if any or None if none was present. """ # Retrieve the root folder of the archive if not os.path.exists(dir_path): return {} lst = os.listdir(dir_path) if len(lst) != 1: return {} project_dirname = lst[0] pkginfo_path = os.path.join(dir_path, project_dirname, "PKG-INFO") if not os.path.exists(pkginfo_path): return {} pkginfo = UnpackedSDist(pkginfo_path) raw = pkginfo.__dict__ raw.pop("filename") # this gets added with the ondisk location return raw def author(data: Dict) -> Person: """Given a dict of project/release artifact information (coming from PyPI), returns an author subset. Args: data (dict): Representing either artifact information or release information. Returns: swh-model dict representing a person. """ name = data.get("author") email = data.get("author_email") fullname = None # type: Optional[str] if email: fullname = "%s <%s>" % (name, email) else: fullname = name if not fullname: return EMPTY_AUTHOR if name is not None: name = name.encode("utf-8") if email is not None: email = email.encode("utf-8") return Person(fullname=fullname.encode("utf-8"), name=name, email=email) diff --git a/swh/loader/package/pypi/tests/test_pypi.py b/swh/loader/package/pypi/tests/test_pypi.py index 7cb487a..971d275 100644 --- a/swh/loader/package/pypi/tests/test_pypi.py +++ b/swh/loader/package/pypi/tests/test_pypi.py @@ -1,806 +1,815 @@ # Copyright (C) 2019-2021 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 json import os from os import path from unittest.mock import patch import pytest from swh.core.pytest_plugin import requests_mock_datadir_factory from swh.core.tarball import uncompress from swh.loader.package import __version__ from swh.loader.package.pypi.loader import ( PyPILoader, PyPIPackageInfo, author, extract_intrinsic_metadata, pypi_api_url, ) from swh.loader.tests import assert_last_visit_matches, check_snapshot, get_stats from swh.model.hashutil import hash_to_bytes from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, Person, RawExtrinsicMetadata, Snapshot, SnapshotBranch, TargetType, ) from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID, ObjectType from swh.storage.interface import PagedResult @pytest.fixture def _0805nexter_api_info(datadir) -> bytes: with open( - os.path.join(datadir, "https_pypi.org", "pypi_0805nexter_json"), "rb", + os.path.join(datadir, "https_pypi.org", "pypi_0805nexter_json"), + "rb", ) as f: return f.read() def test_pypi_author_basic(): data = { "author": "i-am-groot", "author_email": "iam@groot.org", } actual_author = author(data) expected_author = Person( fullname=b"i-am-groot ", name=b"i-am-groot", email=b"iam@groot.org", ) assert actual_author == expected_author def test_pypi_author_empty_email(): data = { "author": "i-am-groot", "author_email": "", } actual_author = author(data) - expected_author = Person(fullname=b"i-am-groot", name=b"i-am-groot", email=b"",) + expected_author = Person( + fullname=b"i-am-groot", + name=b"i-am-groot", + email=b"", + ) assert actual_author == expected_author def test_pypi_author_empty_name(): data = { "author": "", "author_email": "iam@groot.org", } actual_author = author(data) expected_author = Person( - fullname=b" ", name=b"", email=b"iam@groot.org", + fullname=b" ", + name=b"", + email=b"iam@groot.org", ) assert actual_author == expected_author def test_pypi_author_malformed(): data = { "author": "['pierre', 'paul', 'jacques']", "author_email": None, } actual_author = author(data) expected_author = Person( fullname=b"['pierre', 'paul', 'jacques']", name=b"['pierre', 'paul', 'jacques']", email=None, ) assert actual_author == expected_author def test_pypi_author_malformed_2(): data = { "author": "[marie, jeanne]", "author_email": "[marie@some, jeanne@thing]", } actual_author = author(data) expected_author = Person( fullname=b"[marie, jeanne] <[marie@some, jeanne@thing]>", name=b"[marie, jeanne]", email=b"[marie@some, jeanne@thing]", ) assert actual_author == expected_author def test_pypi_author_malformed_3(): data = { "author": "[marie, jeanne, pierre]", "author_email": "[marie@somewhere.org, jeanne@somewhere.org]", } actual_author = author(data) expected_author = Person( fullname=( b"[marie, jeanne, pierre] " b"<[marie@somewhere.org, jeanne@somewhere.org]>" ), name=b"[marie, jeanne, pierre]", email=b"[marie@somewhere.org, jeanne@somewhere.org]", ) actual_author == expected_author # configuration error # def test_pypi_api_url(): """Compute pypi api url from the pypi project url should be ok""" url = pypi_api_url("https://pypi.org/project/requests") assert url == "https://pypi.org/pypi/requests/json" def test_pypi_api_url_with_slash(): """Compute pypi api url from the pypi project url should be ok""" url = pypi_api_url("https://pypi.org/project/requests/") assert url == "https://pypi.org/pypi/requests/json" @pytest.mark.fs def test_pypi_extract_intrinsic_metadata(tmp_path, datadir): """Parsing existing archive's PKG-INFO should yield results""" uncompressed_archive_path = str(tmp_path) archive_path = path.join( datadir, "https_files.pythonhosted.org", "0805nexter-1.1.0.zip" ) uncompress(archive_path, dest=uncompressed_archive_path) actual_metadata = extract_intrinsic_metadata(uncompressed_archive_path) expected_metadata = { "metadata_version": "1.0", "name": "0805nexter", "version": "1.1.0", "summary": "a simple printer of nested lest", "home_page": "http://www.hp.com", "author": "hgtkpython", "author_email": "2868989685@qq.com", "platforms": ["UNKNOWN"], } assert actual_metadata == expected_metadata @pytest.mark.fs def test_pypi_extract_intrinsic_metadata_failures(tmp_path): """Parsing inexistent path/archive/PKG-INFO yield None""" tmp_path = str(tmp_path) # py3.5 work around (PosixPath issue) # inexistent first level path assert extract_intrinsic_metadata("/something-inexistent") == {} # inexistent second level path (as expected by pypi archives) assert extract_intrinsic_metadata(tmp_path) == {} # inexistent PKG-INFO within second level path existing_path_no_pkginfo = path.join(tmp_path, "something") os.mkdir(existing_path_no_pkginfo) assert extract_intrinsic_metadata(tmp_path) == {} # LOADER SCENARIO # # "edge" cases (for the same origin) # # no release artifact: # {visit full, status: uneventful, no contents, etc...} requests_mock_datadir_missing_all = requests_mock_datadir_factory( ignore_urls=[ "https://files.pythonhosted.org/packages/ec/65/c0116953c9a3f47de89e71964d6c7b0c783b01f29fa3390584dbf3046b4d/0805nexter-1.1.0.zip", # noqa "https://files.pythonhosted.org/packages/c4/a0/4562cda161dc4ecbbe9e2a11eb365400c0461845c5be70d73869786809c4/0805nexter-1.2.0.zip", # noqa ] ) def test_pypi_no_release_artifact(swh_storage, requests_mock_datadir_missing_all): - """Load a pypi project with all artifacts missing ends up with no snapshot - - """ + """Load a pypi project with all artifacts missing ends up with no snapshot""" url = "https://pypi.org/project/0805nexter" loader = PyPILoader(swh_storage, url) actual_load_status = loader.load() assert actual_load_status["status"] == "uneventful" assert actual_load_status["snapshot_id"] is not None empty_snapshot = Snapshot(branches={}) assert_last_visit_matches( swh_storage, url, status="partial", type="pypi", snapshot=empty_snapshot.id ) stats = get_stats(swh_storage) assert { "content": 0, "directory": 0, "origin": 1, "origin_visit": 1, "release": 0, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats def test_pypi_fail__load_snapshot(swh_storage, requests_mock_datadir): - """problem during loading: {visit: failed, status: failed, no snapshot} - - """ + """problem during loading: {visit: failed, status: failed, no snapshot}""" url = "https://pypi.org/project/0805nexter" with patch( "swh.loader.package.pypi.loader.PyPILoader._load_snapshot", side_effect=ValueError("Fake problem to fail visit"), ): loader = PyPILoader(swh_storage, url) actual_load_status = loader.load() assert actual_load_status == {"status": "failed"} assert_last_visit_matches(swh_storage, url, status="failed", type="pypi") stats = get_stats(loader.storage) assert { "content": 6, "directory": 4, "origin": 1, "origin_visit": 1, "release": 2, "revision": 0, "skipped_content": 0, "snapshot": 0, } == stats # problem during loading: # {visit: partial, status: uneventful, no snapshot} def test_pypi_release_with_traceback(swh_storage, requests_mock_datadir): url = "https://pypi.org/project/0805nexter" with patch( "swh.loader.package.pypi.loader.PyPILoader.last_snapshot", side_effect=ValueError("Fake problem to fail the visit"), ): loader = PyPILoader(swh_storage, url) actual_load_status = loader.load() assert actual_load_status == {"status": "failed"} assert_last_visit_matches(swh_storage, url, status="failed", type="pypi") stats = get_stats(swh_storage) assert { "content": 0, "directory": 0, "origin": 1, "origin_visit": 1, "release": 0, "revision": 0, "skipped_content": 0, "snapshot": 0, } == stats # problem during loading: failure early enough in between swh contents... # some contents (contents, directories, etc...) have been written in storage # {visit: partial, status: eventful, no snapshot} # problem during loading: failure late enough we can have snapshots (some # revisions are written in storage already) # {visit: partial, status: eventful, snapshot} # "normal" cases (for the same origin) # requests_mock_datadir_missing_one = requests_mock_datadir_factory( ignore_urls=[ "https://files.pythonhosted.org/packages/ec/65/c0116953c9a3f47de89e71964d6c7b0c783b01f29fa3390584dbf3046b4d/0805nexter-1.1.0.zip", # noqa ] ) # some missing release artifacts: # {visit partial, status: eventful, 1 snapshot} def test_pypi_release_metadata_structure( swh_storage, requests_mock_datadir, _0805nexter_api_info ): url = "https://pypi.org/project/0805nexter" loader = PyPILoader(swh_storage, url) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None expected_release_id = hash_to_bytes("fbbcb817f01111b06442cdcc93140ab3cc777d68") expected_snapshot = Snapshot( id=hash_to_bytes(actual_load_status["snapshot_id"]), branches={ b"HEAD": SnapshotBranch( - target=b"releases/1.2.0", target_type=TargetType.ALIAS, + target=b"releases/1.2.0", + target_type=TargetType.ALIAS, ), b"releases/1.1.0": SnapshotBranch( target=hash_to_bytes("f8789ff3ed70a5f570c35d885c7bcfda7b23b091"), target_type=TargetType.RELEASE, ), b"releases/1.2.0": SnapshotBranch( - target=expected_release_id, target_type=TargetType.RELEASE, + target=expected_release_id, + target_type=TargetType.RELEASE, ), }, ) assert_last_visit_matches( swh_storage, url, status="full", type="pypi", snapshot=expected_snapshot.id ) check_snapshot(expected_snapshot, swh_storage) release = swh_storage.release_get([expected_release_id])[0] assert release is not None release_swhid = CoreSWHID( object_type=ObjectType.RELEASE, object_id=expected_release_id ) directory_swhid = ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=release.target ) metadata_authority = MetadataAuthority( - type=MetadataAuthorityType.FORGE, url="https://pypi.org/", + type=MetadataAuthorityType.FORGE, + url="https://pypi.org/", ) expected_metadata = [ RawExtrinsicMetadata( target=directory_swhid, authority=metadata_authority, fetcher=MetadataFetcher( - name="swh.loader.package.pypi.loader.PyPILoader", version=__version__, + name="swh.loader.package.pypi.loader.PyPILoader", + version=__version__, ), discovery_date=loader.visit_date, format="pypi-project-json", metadata=json.dumps( json.loads(_0805nexter_api_info)["releases"]["1.2.0"][0] ).encode(), origin=url, release=release_swhid, ) ] assert swh_storage.raw_extrinsic_metadata_get( - directory_swhid, metadata_authority, - ) == PagedResult(next_page_token=None, results=expected_metadata,) + directory_swhid, + metadata_authority, + ) == PagedResult( + next_page_token=None, + results=expected_metadata, + ) def test_pypi_visit_with_missing_artifact( swh_storage, requests_mock_datadir_missing_one ): - """Load a pypi project with some missing artifacts ends up with 1 snapshot - - """ + """Load a pypi project with some missing artifacts ends up with 1 snapshot""" url = "https://pypi.org/project/0805nexter" loader = PyPILoader(swh_storage, url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("00785a38479abe5fbfa402df96be26d2ddf89c97") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( - swh_storage, url, status="partial", type="pypi", snapshot=expected_snapshot_id, + swh_storage, + url, + status="partial", + type="pypi", + snapshot=expected_snapshot_id, ) expected_snapshot = Snapshot( id=hash_to_bytes(expected_snapshot_id), branches={ b"releases/1.2.0": SnapshotBranch( target=hash_to_bytes("fbbcb817f01111b06442cdcc93140ab3cc777d68"), target_type=TargetType.RELEASE, ), b"HEAD": SnapshotBranch( - target=b"releases/1.2.0", target_type=TargetType.ALIAS, + target=b"releases/1.2.0", + target_type=TargetType.ALIAS, ), }, ) check_snapshot(expected_snapshot, storage=swh_storage) stats = get_stats(swh_storage) assert { "content": 3, "directory": 2, "origin": 1, "origin_visit": 1, "release": 1, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats def test_pypi_visit_with_1_release_artifact(swh_storage, requests_mock_datadir): - """With no prior visit, load a pypi project ends up with 1 snapshot - - """ + """With no prior visit, load a pypi project ends up with 1 snapshot""" url = "https://pypi.org/project/0805nexter" loader = PyPILoader(swh_storage, url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("3dd50c1a0e48a7625cf1427e3190a65b787c774e") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="pypi", snapshot=expected_snapshot_id ) expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"releases/1.1.0": SnapshotBranch( target=hash_to_bytes("f8789ff3ed70a5f570c35d885c7bcfda7b23b091"), target_type=TargetType.RELEASE, ), b"releases/1.2.0": SnapshotBranch( target=hash_to_bytes("fbbcb817f01111b06442cdcc93140ab3cc777d68"), target_type=TargetType.RELEASE, ), b"HEAD": SnapshotBranch( - target=b"releases/1.2.0", target_type=TargetType.ALIAS, + target=b"releases/1.2.0", + target_type=TargetType.ALIAS, ), }, ) check_snapshot(expected_snapshot, swh_storage) stats = get_stats(swh_storage) assert { "content": 6, "directory": 4, "origin": 1, "origin_visit": 1, "release": 2, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats def test_pypi_multiple_visits_with_no_change(swh_storage, requests_mock_datadir): - """Multiple visits with no changes results in 1 same snapshot - - """ + """Multiple visits with no changes results in 1 same snapshot""" url = "https://pypi.org/project/0805nexter" loader = PyPILoader(swh_storage, url) actual_load_status = loader.load() snapshot_id = hash_to_bytes("3dd50c1a0e48a7625cf1427e3190a65b787c774e") assert actual_load_status == { "status": "eventful", "snapshot_id": snapshot_id.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="pypi", snapshot=snapshot_id ) expected_snapshot = Snapshot( id=snapshot_id, branches={ b"releases/1.1.0": SnapshotBranch( target=hash_to_bytes("f8789ff3ed70a5f570c35d885c7bcfda7b23b091"), target_type=TargetType.RELEASE, ), b"releases/1.2.0": SnapshotBranch( target=hash_to_bytes("fbbcb817f01111b06442cdcc93140ab3cc777d68"), target_type=TargetType.RELEASE, ), b"HEAD": SnapshotBranch( - target=b"releases/1.2.0", target_type=TargetType.ALIAS, + target=b"releases/1.2.0", + target_type=TargetType.ALIAS, ), }, ) check_snapshot(expected_snapshot, swh_storage) stats = get_stats(swh_storage) assert { "content": 6, "directory": 4, "origin": 1, "origin_visit": 1, "release": 2, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats actual_load_status2 = loader.load() assert actual_load_status2 == { "status": "uneventful", "snapshot_id": actual_load_status2["snapshot_id"], } visit_status2 = assert_last_visit_matches( swh_storage, url, status="full", type="pypi" ) stats2 = get_stats(swh_storage) expected_stats2 = stats.copy() expected_stats2["origin_visit"] = 1 + 1 assert expected_stats2 == stats2 # same snapshot assert visit_status2.snapshot == snapshot_id def test_pypi_incremental_visit(swh_storage, requests_mock_datadir_visits): - """With prior visit, 2nd load will result with a different snapshot - - """ + """With prior visit, 2nd load will result with a different snapshot""" url = "https://pypi.org/project/0805nexter" loader = PyPILoader(swh_storage, url) visit1_actual_load_status = loader.load() visit1_stats = get_stats(swh_storage) expected_snapshot_id = hash_to_bytes("3dd50c1a0e48a7625cf1427e3190a65b787c774e") assert visit1_actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="pypi", snapshot=expected_snapshot_id ) assert { "content": 6, "directory": 4, "origin": 1, "origin_visit": 1, "release": 2, "revision": 0, "skipped_content": 0, "snapshot": 1, } == visit1_stats # Reset internal state del loader._cached__raw_info del loader._cached_info visit2_actual_load_status = loader.load() visit2_stats = get_stats(swh_storage) assert visit2_actual_load_status["status"] == "eventful", visit2_actual_load_status expected_snapshot_id2 = hash_to_bytes("77febe6ff0faf6cc00dd015a6c9763579a9fb6c7") assert visit2_actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id2.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="pypi", snapshot=expected_snapshot_id2 ) expected_snapshot = Snapshot( id=expected_snapshot_id2, branches={ b"releases/1.1.0": SnapshotBranch( target=hash_to_bytes("f8789ff3ed70a5f570c35d885c7bcfda7b23b091"), target_type=TargetType.RELEASE, ), b"releases/1.2.0": SnapshotBranch( target=hash_to_bytes("fbbcb817f01111b06442cdcc93140ab3cc777d68"), target_type=TargetType.RELEASE, ), b"releases/1.3.0": SnapshotBranch( target=hash_to_bytes("a21b09cbec8e31f47307f196bb1f939effc26e11"), target_type=TargetType.RELEASE, ), b"HEAD": SnapshotBranch( - target=b"releases/1.3.0", target_type=TargetType.ALIAS, + target=b"releases/1.3.0", + target_type=TargetType.ALIAS, ), }, ) assert_last_visit_matches( swh_storage, url, status="full", type="pypi", snapshot=expected_snapshot.id ) check_snapshot(expected_snapshot, swh_storage) assert { "content": 6 + 1, # 1 more content "directory": 4 + 2, # 2 more directories "origin": 1, "origin_visit": 1 + 1, "release": 2 + 1, # 1 more release "revision": 0, "skipped_content": 0, "snapshot": 1 + 1, # 1 more snapshot } == visit2_stats urls = [ m.url for m in requests_mock_datadir_visits.request_history if m.url.startswith("https://files.pythonhosted.org") ] # visited each artifact once across 2 visits assert len(urls) == len(set(urls)) # release artifact, no new artifact # {visit full, status uneventful, same snapshot as before} # release artifact, old artifact with different checksums # {visit full, status full, new snapshot with shared history and some new # different history} # release with multiple sdist artifacts per pypi "version" # snapshot branch output is different def test_pypi_visit_1_release_with_2_artifacts(swh_storage, requests_mock_datadir): - """With no prior visit, load a pypi project ends up with 1 snapshot - - """ + """With no prior visit, load a pypi project ends up with 1 snapshot""" url = "https://pypi.org/project/nexter" loader = PyPILoader(swh_storage, url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("1394b2e59351a944cc763bd9d26d90ce8e8121a8") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( swh_storage, url, status="full", type="pypi", snapshot=expected_snapshot_id ) expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"releases/1.1.0/nexter-1.1.0.zip": SnapshotBranch( target=hash_to_bytes("f7d43faeb65b64d3faa67e4f46559db57d26b9a4"), target_type=TargetType.RELEASE, ), b"releases/1.1.0/nexter-1.1.0.tar.gz": SnapshotBranch( target=hash_to_bytes("732bb9dc087e6015884daaebb8b82559be729b5a"), target_type=TargetType.RELEASE, ), }, ) check_snapshot(expected_snapshot, swh_storage) def test_pypi_artifact_with_no_intrinsic_metadata(swh_storage, requests_mock_datadir): - """Skip artifact with no intrinsic metadata during ingestion - - """ + """Skip artifact with no intrinsic metadata during ingestion""" url = "https://pypi.org/project/upymenu" loader = PyPILoader(swh_storage, url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } # no branch as one artifact without any intrinsic metadata expected_snapshot = Snapshot(id=expected_snapshot_id, branches={}) assert_last_visit_matches( swh_storage, url, status="full", type="pypi", snapshot=expected_snapshot.id ) check_snapshot(expected_snapshot, swh_storage) def test_pypi_origin_not_found(swh_storage, requests_mock_datadir): url = "https://pypi.org/project/unknown" loader = PyPILoader(swh_storage, url) assert loader.load() == {"status": "failed"} assert_last_visit_matches( swh_storage, url, status="not_found", type="pypi", snapshot=None ) def test_pypi_build_release_missing_version_in_pkg_info(swh_storage, tmp_path): """Simulate release build when Version field is missing in PKG-INFO file.""" url = "https://pypi.org/project/GermlineFilter" # create package info p_info = PyPIPackageInfo( url=url, filename="GermlineFilter-1.2.tar.gz", version="1.2", name="GermlineFilter", directory_extrinsic_metadata=[], raw_info={}, comment_text="", sha256="e4982353c544d94b34f02c5690ab3d3ebc93480d5b62fe6f3317f23c515acc05", upload_time="2015-02-18T20:39:13", ) # create PKG-INFO file with missing Version field package_path = tmp_path / "GermlineFilter-1.2" pkg_info_path = package_path / "PKG-INFO" package_path.mkdir() pkg_info_path.write_text( """Metadata-Version: 1.2 Name: germline_filter Home-page: Author: Cristian Caloian (OICR) Author-email: cristian.caloian@oicr.on.ca License: UNKNOWN Description: UNKNOWN Platform: UNKNOWN""" ) directory = hash_to_bytes("8b864d66f356afe35033d58f8e03b7c23a66751f") # attempt to build release loader = PyPILoader(swh_storage, url) release = loader.build_release(p_info, str(tmp_path), directory) # without comment_text and version in PKG-INFO, message should be empty assert ( release.message == b"Synthetic release for PyPI source package GermlineFilter version 1.2\n" ) def test_filter_out_invalid_sdists(swh_storage, requests_mock): project_name = "swh-test-sdist-filtering" version = "1.0.0" url = f"https://pypi.org/project/{project_name}" json_url = f"https://pypi.org/pypi/{project_name}/json" common_sdist_entries = { "url": "", "comment_text": "", "digests": {"sha256": ""}, "upload_time": "", "packagetype": "sdist", } requests_mock.get( json_url, json={ - "info": {"name": project_name,}, + "info": { + "name": project_name, + }, "releases": { version: [ { **common_sdist_entries, "filename": f"{project_name}-{version}.{ext}", } for ext in ("tar.gz", "deb", "egg", "rpm", "whl") ] }, }, ) loader = PyPILoader(swh_storage, url) packages = list(loader.get_package_info(version=version)) assert len(packages) == 1 assert packages[0][1].filename.endswith(".tar.gz") diff --git a/swh/loader/package/tests/test_loader.py b/swh/loader/package/tests/test_loader.py index 9851a22..be329c7 100644 --- a/swh/loader/package/tests/test_loader.py +++ b/swh/loader/package/tests/test_loader.py @@ -1,508 +1,518 @@ # Copyright (C) 2019-2021 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 datetime import hashlib import logging import string from unittest.mock import Mock, call, patch import attr import pytest from swh.loader.package.loader import BasePackageInfo, PackageLoader from swh.model.model import ( Origin, OriginVisit, OriginVisitStatus, Person, Release, Revision, RevisionType, Snapshot, SnapshotBranch, TargetType, TimestampWithTimezone, ) from swh.model.model import ExtID from swh.model.model import ObjectType as ModelObjectType from swh.model.swhids import CoreSWHID, ObjectType from swh.storage import get_storage from swh.storage.algos.snapshot import snapshot_get_latest class FakeStorage: def origin_add(self, origins): raise ValueError("We refuse to add an origin") def origin_visit_get_latest(self, origin): return None class FakeStorage2(FakeStorage): def origin_add(self, origins): pass def origin_visit_add(self, visits): raise ValueError("We refuse to add an origin visit") class StubPackageInfo(BasePackageInfo): pass class StubPackageLoader(PackageLoader[StubPackageInfo]): def get_versions(self): return ["v1.0", "v2.0", "v3.0", "v4.0"] def get_package_info(self, version): p_info = StubPackageInfo( "http://example.org", f"example-{version}.tar", version=version ) extid_type = "extid-type1" if version in ("v1.0", "v2.0") else "extid-type2" # Versions 1.0 and 2.0 have an extid of a given type, v3.0 has an extid # of a different type patch.object( p_info, "extid", return_value=(extid_type, 0, f"extid-of-{version}".encode()), autospec=True, ).start() yield (f"branch-{version}", p_info) def _load_release(self, p_info, origin): return None def test_loader_origin_visit_failure(swh_storage): - """Failure to add origin or origin visit should failed immediately - - """ + """Failure to add origin or origin visit should failed immediately""" loader = PackageLoader(swh_storage, "some-url") loader.storage = FakeStorage() actual_load_status = loader.load() assert actual_load_status == {"status": "failed"} loader.storage = FakeStorage2() actual_load_status2 = loader.load() assert actual_load_status2 == {"status": "failed"} def test_resolve_object_from_extids() -> None: storage = get_storage("memory") target = b"\x01" * 20 rel1 = Release( name=b"aaaa", message=b"aaaa", target=target, target_type=ModelObjectType.DIRECTORY, synthetic=False, ) rel2 = Release( name=b"bbbb", message=b"bbbb", target=target, target_type=ModelObjectType.DIRECTORY, synthetic=False, ) storage.release_add([rel1, rel2]) loader = PackageLoader(storage, "http://example.org/") # type: ignore p_info = Mock(wraps=BasePackageInfo(None, None, None)) # type: ignore # The PackageInfo does not support extids p_info.extid.return_value = None known_extids = {("extid-type", 0, b"extid-of-aaaa"): [rel1.swhid()]} whitelist = {b"unused"} assert loader.resolve_object_from_extids(known_extids, p_info, whitelist) is None # Some known extid, and the PackageInfo is not one of them (ie. cache miss) p_info.extid.return_value = ("extid-type", 0, b"extid-of-cccc") assert loader.resolve_object_from_extids(known_extids, p_info, whitelist) is None # Some known extid, and the PackageInfo is one of them (ie. cache hit), # but the target release was not in the previous snapshot p_info.extid.return_value = ("extid-type", 0, b"extid-of-aaaa") assert loader.resolve_object_from_extids(known_extids, p_info, whitelist) is None # Some known extid, and the PackageInfo is one of them (ie. cache hit), # and the target release was in the previous snapshot whitelist = {rel1.id} assert ( loader.resolve_object_from_extids(known_extids, p_info, whitelist) == rel1.swhid() ) # Same as before, but there is more than one extid, and only one is an allowed # release whitelist = {rel1.id} known_extids = {("extid-type", 0, b"extid-of-aaaa"): [rel2.swhid(), rel1.swhid()]} assert ( loader.resolve_object_from_extids(known_extids, p_info, whitelist) == rel1.swhid() ) def test_resolve_object_from_extids_missing_target() -> None: storage = get_storage("memory") target = b"\x01" * 20 rel = Release( name=b"aaaa", message=b"aaaa", target=target, target_type=ModelObjectType.DIRECTORY, synthetic=False, ) loader = PackageLoader(storage, "http://example.org/") # type: ignore p_info = Mock(wraps=BasePackageInfo(None, None, None)) # type: ignore known_extids = {("extid-type", 0, b"extid-of-aaaa"): [rel.swhid()]} p_info.extid.return_value = ("extid-type", 0, b"extid-of-aaaa") whitelist = {rel.id} # Targeted release is missing from the storage assert loader.resolve_object_from_extids(known_extids, p_info, whitelist) is None storage.release_add([rel]) # Targeted release now exists assert ( loader.resolve_object_from_extids(known_extids, p_info, whitelist) == rel.swhid() ) def test_load_get_known_extids() -> None: """Checks PackageLoader.load() fetches known extids efficiently""" storage = Mock(wraps=get_storage("memory")) loader = StubPackageLoader(storage, "http://example.org") loader.load() # Calls should be grouped by extid type storage.extid_get_from_extid.assert_has_calls( [ call("extid-type1", [b"extid-of-v1.0", b"extid-of-v2.0"], version=0), call("extid-type2", [b"extid-of-v3.0", b"extid-of-v4.0"], version=0), ], any_order=True, ) def test_load_extids() -> None: """Checks PackageLoader.load() skips iff it should, and writes (only) the new ExtIDs""" storage = get_storage("memory") dir_swhid = CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=b"e" * 20) rels = [ Release( name=f"v{i}.0".encode(), message=b"blah\n", target=dir_swhid.object_id, target_type=ModelObjectType.DIRECTORY, synthetic=True, ) for i in (1, 2, 3, 4) ] storage.release_add(rels[0:3]) origin = "http://example.org" rel1_swhid = rels[0].swhid() rel2_swhid = rels[1].swhid() rel3_swhid = rels[2].swhid() rel4_swhid = rels[3].swhid() # Results of a previous load storage.extid_add( [ ExtID("extid-type1", b"extid-of-v1.0", rel1_swhid), ExtID("extid-type2", b"extid-of-v2.0", rel2_swhid), ] ) last_snapshot = Snapshot( branches={ b"v1.0": SnapshotBranch( target_type=TargetType.RELEASE, target=rel1_swhid.object_id ), b"v2.0": SnapshotBranch( target_type=TargetType.RELEASE, target=rel2_swhid.object_id ), b"v3.0": SnapshotBranch( target_type=TargetType.RELEASE, target=rel3_swhid.object_id ), } ) storage.snapshot_add([last_snapshot]) date = datetime.datetime.now(tz=datetime.timezone.utc) storage.origin_add([Origin(url=origin)]) storage.origin_visit_add( [OriginVisit(origin="http://example.org", visit=1, date=date, type="tar")] ) storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin, visit=1, status="full", date=date, snapshot=last_snapshot.id, ) ] ) loader = StubPackageLoader(storage, "http://example.org") patch.object( loader, "_load_release", return_value=(rel4_swhid.object_id, dir_swhid.object_id), autospec=True, ).start() loader.load() assert loader._load_release.mock_calls == [ # type: ignore # v1.0: not loaded because there is already its (extid_type, extid, rel) # in the storage. # v2.0: loaded, because there is already a similar extid, but different type - call(StubPackageInfo(origin, "example-v2.0.tar", "v2.0"), Origin(url=origin),), + call( + StubPackageInfo(origin, "example-v2.0.tar", "v2.0"), + Origin(url=origin), + ), # v3.0: loaded despite having an (extid_type, extid) in storage, because # the target of the extid is not in the previous snapshot - call(StubPackageInfo(origin, "example-v3.0.tar", "v3.0"), Origin(url=origin),), + call( + StubPackageInfo(origin, "example-v3.0.tar", "v3.0"), + Origin(url=origin), + ), # v4.0: loaded, because there isn't its extid - call(StubPackageInfo(origin, "example-v4.0.tar", "v4.0"), Origin(url=origin),), + call( + StubPackageInfo(origin, "example-v4.0.tar", "v4.0"), + Origin(url=origin), + ), ] # then check the snapshot has all the branches. # versions 2.0 to 4.0 all point to rel4_swhid (instead of the value of the last # snapshot), because they had to be loaded (mismatched extid), and the mocked # _load_release always returns rel4_swhid. snapshot = Snapshot( branches={ b"branch-v1.0": SnapshotBranch( target_type=TargetType.RELEASE, target=rel1_swhid.object_id ), b"branch-v2.0": SnapshotBranch( target_type=TargetType.RELEASE, target=rel4_swhid.object_id ), b"branch-v3.0": SnapshotBranch( target_type=TargetType.RELEASE, target=rel4_swhid.object_id ), b"branch-v4.0": SnapshotBranch( target_type=TargetType.RELEASE, target=rel4_swhid.object_id ), } ) assert snapshot_get_latest(storage, origin) == snapshot extids = storage.extid_get_from_target( ObjectType.RELEASE, [ rel1_swhid.object_id, rel2_swhid.object_id, rel3_swhid.object_id, rel4_swhid.object_id, ], ) assert set(extids) == { # What we inserted at the beginning of the test: ExtID("extid-type1", b"extid-of-v1.0", rel1_swhid), ExtID("extid-type2", b"extid-of-v2.0", rel2_swhid), # Added by the loader: ExtID("extid-type1", b"extid-of-v2.0", rel4_swhid), ExtID("extid-type2", b"extid-of-v3.0", rel4_swhid), ExtID("extid-type2", b"extid-of-v4.0", rel4_swhid), } def test_load_upgrade_from_revision_extids(caplog): """Tests that, when loading incrementally based on a snapshot made by an old version of the loader, the loader will convert revisions to releases and add them to the storage. Also checks that, if an extid exists pointing to a non-existent revision (which should never happen, but you never know...), the release is loaded from scratch.""" storage = get_storage("memory") origin = "http://example.org" dir1_swhid = CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=b"d" * 20) dir2_swhid = CoreSWHID(object_type=ObjectType.DIRECTORY, object_id=b"e" * 20) date = TimestampWithTimezone.from_datetime( datetime.datetime.now(tz=datetime.timezone.utc) ) person = Person.from_fullname(b"Jane Doe ") rev1 = Revision( message=b"blah", author=person, date=date, committer=person, committer_date=date, directory=dir1_swhid.object_id, type=RevisionType.TAR, synthetic=True, ) rel1 = Release( name=b"v1.0", message=b"blah\n", author=person, date=date, target=dir1_swhid.object_id, target_type=ModelObjectType.DIRECTORY, synthetic=True, ) rev1_swhid = rev1.swhid() rel1_swhid = rel1.swhid() rev2_swhid = CoreSWHID(object_type=ObjectType.REVISION, object_id=b"b" * 20) rel2_swhid = CoreSWHID(object_type=ObjectType.RELEASE, object_id=b"c" * 20) # Results of a previous load storage.extid_add( [ ExtID("extid-type1", b"extid-of-v1.0", rev1_swhid, 0), ExtID("extid-type1", b"extid-of-v2.0", rev2_swhid, 0), ] ) storage.revision_add([rev1]) last_snapshot = Snapshot( branches={ b"v1.0": SnapshotBranch( target_type=TargetType.REVISION, target=rev1_swhid.object_id ), b"v2.0": SnapshotBranch( target_type=TargetType.REVISION, target=rev2_swhid.object_id ), } ) storage.snapshot_add([last_snapshot]) date = datetime.datetime.now(tz=datetime.timezone.utc) storage.origin_add([Origin(url=origin)]) storage.origin_visit_add( [OriginVisit(origin="http://example.org", visit=1, date=date, type="tar")] ) storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin, visit=1, status="full", date=date, snapshot=last_snapshot.id, ) ] ) loader = StubPackageLoader(storage, "http://example.org") patch.object( loader, "_load_release", return_value=(rel2_swhid.object_id, dir2_swhid.object_id), autospec=True, ).start() patch.object( - loader, "get_versions", return_value=["v1.0", "v2.0", "v3.0"], autospec=True, + loader, + "get_versions", + return_value=["v1.0", "v2.0", "v3.0"], + autospec=True, ).start() caplog.set_level(logging.ERROR) loader.load() assert len(caplog.records) == 1 (record,) = caplog.records assert record.levelname == "ERROR" assert "Failed to upgrade branch branch-v2.0" in record.message assert loader._load_release.mock_calls == [ # v1.0: not loaded because there is already a revision matching it # v2.0: loaded, as the revision is missing from the storage even though there # is an extid call(StubPackageInfo(origin, "example-v2.0.tar", "v2.0"), Origin(url=origin)), # v3.0: loaded (did not exist yet) call(StubPackageInfo(origin, "example-v3.0.tar", "v3.0"), Origin(url=origin)), ] snapshot = Snapshot( branches={ b"branch-v1.0": SnapshotBranch( target_type=TargetType.RELEASE, target=rel1_swhid.object_id ), b"branch-v2.0": SnapshotBranch( target_type=TargetType.RELEASE, target=rel2_swhid.object_id ), b"branch-v3.0": SnapshotBranch( target_type=TargetType.RELEASE, target=rel2_swhid.object_id ), } ) assert snapshot_get_latest(storage, origin) == snapshot extids = storage.extid_get_from_target( - ObjectType.RELEASE, [rel1_swhid.object_id, rel2_swhid.object_id,], + ObjectType.RELEASE, + [ + rel1_swhid.object_id, + rel2_swhid.object_id, + ], ) assert set(extids) == { ExtID("extid-type1", b"extid-of-v1.0", rel1_swhid), ExtID("extid-type1", b"extid-of-v2.0", rel2_swhid), ExtID("extid-type2", b"extid-of-v3.0", rel2_swhid), } def test_manifest_extid(): - """Compute primary key should return the right identity - - """ + """Compute primary key should return the right identity""" @attr.s class TestPackageInfo(BasePackageInfo): a = attr.ib() b = attr.ib() length = attr.ib() filename = attr.ib() MANIFEST_FORMAT = string.Template("$a $b") p_info = TestPackageInfo( url="http://example.org/", a=1, b=2, length=221837, filename="8sync-0.1.0.tar.gz", version="0.1.0", ) actual_id = p_info.extid() assert actual_id == ("package-manifest-sha256", 0, hashlib.sha256(b"1 2").digest()) def test_no_env_swh_config_filename_raise(monkeypatch): - """No SWH_CONFIG_FILENAME environment variable makes package loader init raise - - """ + """No SWH_CONFIG_FILENAME environment variable makes package loader init raise""" class DummyPackageLoader(PackageLoader): """A dummy package loader for test purpose""" pass monkeypatch.delenv("SWH_CONFIG_FILENAME", raising=False) with pytest.raises( AssertionError, match="SWH_CONFIG_FILENAME environment variable is undefined" ): DummyPackageLoader.from_configfile(url="some-url") diff --git a/swh/loader/package/tests/test_loader_metadata.py b/swh/loader/package/tests/test_loader_metadata.py index 76c38aa..527a72d 100644 --- a/swh/loader/package/tests/test_loader_metadata.py +++ b/swh/loader/package/tests/test_loader_metadata.py @@ -1,215 +1,235 @@ # Copyright (C) 2019-2021 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 datetime from typing import Iterator, List, Sequence, Tuple import attr from swh.loader.package import __version__ from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, RawExtrinsicMetadataCore, ) from swh.model.hashutil import hash_to_bytes from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, ObjectType, Origin, Person, RawExtrinsicMetadata, Release, Sha1Git, ) from swh.model.swhids import CoreSWHID, ExtendedSWHID EMPTY_SNAPSHOT_ID = "1a8893e6a86f444e8be8e7bda6cb34fb1735a00e" FULL_SNAPSHOT_ID = "4ac5730a9393f5099b63a35a17b6c33d36d70c3a" AUTHORITY = MetadataAuthority( - type=MetadataAuthorityType.FORGE, url="http://example.org/", + type=MetadataAuthorityType.FORGE, + url="http://example.org/", ) ORIGIN_URL = "http://example.org/archive.tgz" ORIGIN_SWHID = Origin(ORIGIN_URL).swhid() REVISION_ID = hash_to_bytes("8ff44f081d43176474b267de5451f2c2e88089d0") RELEASE_ID = hash_to_bytes("9477a708196b44e59efb4e47b7d979a4146bd428") RELEASE_SWHID = CoreSWHID.from_string(f"swh:1:rel:{RELEASE_ID.hex()}") DIRECTORY_ID = hash_to_bytes("aa" * 20) DIRECTORY_SWHID = ExtendedSWHID.from_string(f"swh:1:dir:{DIRECTORY_ID.hex()}") FETCHER = MetadataFetcher( name="swh.loader.package.tests.test_loader_metadata.MetadataTestLoader", version=__version__, ) DISCOVERY_DATE = datetime.datetime.now(tz=datetime.timezone.utc) DIRECTORY_METADATA = [ RawExtrinsicMetadata( target=DIRECTORY_SWHID, discovery_date=DISCOVERY_DATE, authority=AUTHORITY, fetcher=FETCHER, format="test-format1", metadata=b"foo bar", origin=ORIGIN_URL, release=RELEASE_SWHID, ), RawExtrinsicMetadata( target=DIRECTORY_SWHID, discovery_date=DISCOVERY_DATE + datetime.timedelta(seconds=1), authority=AUTHORITY, fetcher=FETCHER, format="test-format2", metadata=b"bar baz", origin=ORIGIN_URL, release=RELEASE_SWHID, ), ] ORIGIN_METADATA = [ RawExtrinsicMetadata( target=ORIGIN_SWHID, discovery_date=datetime.datetime.now(tz=datetime.timezone.utc), authority=AUTHORITY, fetcher=FETCHER, format="test-format3", metadata=b"baz qux", ), ] class MetadataTestLoader(PackageLoader[BasePackageInfo]): def get_versions(self) -> Sequence[str]: return ["v1.0.0"] def _load_directory(self, dl_artifacts, tmpdir): class directory: hash = DIRECTORY_ID return (None, directory) # just enough for _load_release to work def download_package(self, p_info: BasePackageInfo, tmpdir: str): return [("path", {"artifact_key": "value", "length": 0})] def build_release( - self, p_info: BasePackageInfo, uncompressed_path: str, directory: Sha1Git, + self, + p_info: BasePackageInfo, + uncompressed_path: str, + directory: Sha1Git, ): return Release( name=p_info.version.encode(), message=b"", author=Person.from_fullname(b""), date=None, target=DIRECTORY_ID, target_type=ObjectType.DIRECTORY, synthetic=False, ) def get_metadata_authority(self): return attr.evolve(AUTHORITY, metadata={}) def get_package_info(self, version: str) -> Iterator[Tuple[str, BasePackageInfo]]: m0 = DIRECTORY_METADATA[0] m1 = DIRECTORY_METADATA[1] p_info = BasePackageInfo( url=ORIGIN_URL, filename="archive.tgz", version=version, directory_extrinsic_metadata=[ RawExtrinsicMetadataCore(m0.format, m0.metadata, m0.discovery_date), RawExtrinsicMetadataCore(m1.format, m1.metadata, m1.discovery_date), ], ) yield (version, p_info) def get_extrinsic_origin_metadata(self) -> List[RawExtrinsicMetadataCore]: m = ORIGIN_METADATA[0] return [RawExtrinsicMetadataCore(m.format, m.metadata, m.discovery_date)] def test_load_artifact_metadata(swh_storage, caplog): loader = MetadataTestLoader(swh_storage, ORIGIN_URL) load_status = loader.load() assert load_status == { "status": "eventful", "snapshot_id": FULL_SNAPSHOT_ID, } authority = MetadataAuthority( - type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", + type=MetadataAuthorityType.REGISTRY, + url="https://softwareheritage.org/", ) - result = swh_storage.raw_extrinsic_metadata_get(DIRECTORY_SWHID, authority,) + result = swh_storage.raw_extrinsic_metadata_get( + DIRECTORY_SWHID, + authority, + ) assert result.next_page_token is None assert len(result.results) == 1 assert result.results[0] == RawExtrinsicMetadata( target=DIRECTORY_SWHID, discovery_date=result.results[0].discovery_date, authority=authority, fetcher=FETCHER, format="original-artifacts-json", metadata=b'[{"artifact_key": "value", "length": 0}]', origin=ORIGIN_URL, release=RELEASE_SWHID, ) def test_load_metadata(swh_storage, caplog): loader = MetadataTestLoader(swh_storage, ORIGIN_URL) load_status = loader.load() assert load_status == { "status": "eventful", "snapshot_id": FULL_SNAPSHOT_ID, } - result = swh_storage.raw_extrinsic_metadata_get(DIRECTORY_SWHID, AUTHORITY,) + result = swh_storage.raw_extrinsic_metadata_get( + DIRECTORY_SWHID, + AUTHORITY, + ) assert result.next_page_token is None assert result.results == DIRECTORY_METADATA - result = swh_storage.raw_extrinsic_metadata_get(ORIGIN_SWHID, AUTHORITY,) + result = swh_storage.raw_extrinsic_metadata_get( + ORIGIN_SWHID, + AUTHORITY, + ) assert result.next_page_token is None assert result.results == ORIGIN_METADATA assert caplog.text == "" def test_existing_authority(swh_storage, caplog): loader = MetadataTestLoader(swh_storage, ORIGIN_URL) load_status = loader.load() assert load_status == { "status": "eventful", "snapshot_id": FULL_SNAPSHOT_ID, } - result = swh_storage.raw_extrinsic_metadata_get(DIRECTORY_SWHID, AUTHORITY,) + result = swh_storage.raw_extrinsic_metadata_get( + DIRECTORY_SWHID, + AUTHORITY, + ) assert result.next_page_token is None assert result.results == DIRECTORY_METADATA assert caplog.text == "" def test_existing_fetcher(swh_storage, caplog): loader = MetadataTestLoader(swh_storage, ORIGIN_URL) load_status = loader.load() assert load_status == { "status": "eventful", "snapshot_id": FULL_SNAPSHOT_ID, } - result = swh_storage.raw_extrinsic_metadata_get(DIRECTORY_SWHID, AUTHORITY,) + result = swh_storage.raw_extrinsic_metadata_get( + DIRECTORY_SWHID, + AUTHORITY, + ) assert result.next_page_token is None assert result.results == DIRECTORY_METADATA assert caplog.text == "" diff --git a/swh/loader/package/tests/test_utils.py b/swh/loader/package/tests/test_utils.py index 772379f..75373e7 100644 --- a/swh/loader/package/tests/test_utils.py +++ b/swh/loader/package/tests/test_utils.py @@ -1,238 +1,236 @@ # Copyright (C) 2019-2021 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 json import os from unittest.mock import MagicMock from urllib.error import URLError from urllib.parse import quote import pytest from swh.loader.exception import NotFound import swh.loader.package from swh.loader.package.utils import api_info, download, release_name def test_version_generation(): assert ( swh.loader.package.__version__ != "devel" ), "Make sure swh.loader.core is installed (e.g. pip install -e .)" @pytest.mark.fs def test_download_fail_to_download(tmp_path, requests_mock): url = "https://pypi.org/pypi/arrow/json" status_code = 404 requests_mock.get(url, status_code=status_code) with pytest.raises(ValueError) as e: download(url, tmp_path) assert e.value.args[0] == "Fail to query '%s'. Reason: %s" % (url, status_code) _filename = "requests-0.0.1.tar.gz" _data = "this is something" def _check_download_ok(url, dest, filename=_filename, hashes={}): actual_filepath, actual_hashes = download(url, dest, hashes=hashes) actual_filename = os.path.basename(actual_filepath) assert actual_filename == filename assert actual_hashes["length"] == len(_data) assert ( actual_hashes["checksums"]["sha1"] == "fdd1ce606a904b08c816ba84f3125f2af44d92b2" ) assert ( actual_hashes["checksums"]["sha256"] == "1d9224378d77925d612c9f926eb9fb92850e6551def8328011b6a972323298d5" ) @pytest.mark.fs def test_download_ok(tmp_path, requests_mock): """Download without issue should provide filename and hashes""" url = f"https://pypi.org/pypi/requests/{_filename}" requests_mock.get(url, text=_data, headers={"content-length": str(len(_data))}) _check_download_ok(url, dest=str(tmp_path)) @pytest.mark.fs def test_download_ok_no_header(tmp_path, requests_mock): """Download without issue should provide filename and hashes""" url = f"https://pypi.org/pypi/requests/{_filename}" requests_mock.get(url, text=_data) # no header information _check_download_ok(url, dest=str(tmp_path)) @pytest.mark.fs def test_download_ok_with_hashes(tmp_path, requests_mock): """Download without issue should provide filename and hashes""" url = f"https://pypi.org/pypi/requests/{_filename}" requests_mock.get(url, text=_data, headers={"content-length": str(len(_data))}) # good hashes for such file good = { "sha1": "fdd1ce606a904b08c816ba84f3125f2af44d92b2", "sha256": "1d9224378d77925d612c9f926eb9fb92850e6551def8328011b6a972323298d5", # noqa } _check_download_ok(url, dest=str(tmp_path), hashes=good) @pytest.mark.fs def test_download_fail_hashes_mismatch(tmp_path, requests_mock): - """Mismatch hash after download should raise - - """ + """Mismatch hash after download should raise""" url = f"https://pypi.org/pypi/requests/{_filename}" requests_mock.get(url, text=_data, headers={"content-length": str(len(_data))}) # good hashes for such file good = { "sha1": "fdd1ce606a904b08c816ba84f3125f2af44d92b2", "sha256": "1d9224378d77925d612c9f926eb9fb92850e6551def8328011b6a972323298d5", # noqa } for hash_algo in good.keys(): wrong_hash = good[hash_algo].replace("1", "0") expected_hashes = good.copy() expected_hashes[hash_algo] = wrong_hash # set the wrong hash expected_msg = "Failure when fetching %s. " "Checksum mismatched: %s != %s" % ( url, wrong_hash, good[hash_algo], ) with pytest.raises(ValueError, match=expected_msg): download(url, dest=str(tmp_path), hashes=expected_hashes) @pytest.mark.fs def test_ftp_download_ok(tmp_path, mocker): """Download without issue should provide filename and hashes""" url = f"ftp://pypi.org/pypi/requests/{_filename}" cm = MagicMock() cm.getstatus.return_value = 200 cm.read.side_effect = [_data.encode(), b""] cm.__enter__.return_value = cm mocker.patch("swh.loader.package.utils.urlopen").return_value = cm _check_download_ok(url, dest=str(tmp_path)) @pytest.mark.fs def test_ftp_download_ko(tmp_path, mocker): """Download without issue should provide filename and hashes""" filename = "requests-0.0.1.tar.gz" url = "ftp://pypi.org/pypi/requests/%s" % filename mocker.patch("swh.loader.package.utils.urlopen").side_effect = URLError("FTP error") with pytest.raises(URLError): download(url, dest=str(tmp_path)) @pytest.mark.fs def test_download_with_redirection(tmp_path, requests_mock): """Download with redirection should use the targeted URL to extract filename""" url = "https://example.org/project/requests/download" redirection_url = f"https://example.org/project/requests/files/{_filename}" requests_mock.get(url, status_code=302, headers={"location": redirection_url}) requests_mock.get( redirection_url, text=_data, headers={"content-length": str(len(_data))} ) _check_download_ok(url, dest=str(tmp_path)) def test_download_extracting_filename_from_url(tmp_path, requests_mock): """Extracting filename from url must sanitize the filename first""" url = "https://example.org/project/requests-0.0.1.tar.gz?a=b&c=d&foo=bar" requests_mock.get( url, status_code=200, text=_data, headers={"content-length": str(len(_data))} ) _check_download_ok(url, dest=str(tmp_path)) @pytest.mark.fs @pytest.mark.parametrize( "filename", [f'"{_filename}"', _filename, '"filename with spaces.tar.gz"'] ) def test_download_filename_from_content_disposition(tmp_path, requests_mock, filename): """Filename should be extracted from content-disposition request header when available.""" url = "https://example.org/download/requests/tar.gz/v0.0.1" requests_mock.get( url, text=_data, headers={ "content-length": str(len(_data)), "content-disposition": f"attachment; filename={filename}", }, ) _check_download_ok(url, dest=str(tmp_path), filename=filename.strip('"')) @pytest.mark.fs @pytest.mark.parametrize("filename", ['"archive école.tar.gz"', "archive_école.tgz"]) def test_download_utf8_filename_from_content_disposition( tmp_path, requests_mock, filename ): """Filename should be extracted from content-disposition request header when available.""" url = "https://example.org/download/requests/tar.gz/v0.0.1" data = "this is something" requests_mock.get( url, text=data, headers={ "content-length": str(len(data)), "content-disposition": f"attachment; filename*=utf-8''{quote(filename)}", }, ) _check_download_ok(url, dest=str(tmp_path), filename=filename.strip('"')) def test_api_info_failure(requests_mock): """Failure to fetch info/release information should raise""" url = "https://pypi.org/pypi/requests/json" status_code = 400 requests_mock.get(url, status_code=status_code) with pytest.raises(NotFound) as e0: api_info(url) assert e0.value.args[0] == "Fail to query '%s'. Reason: %s" % (url, status_code) def test_api_info(requests_mock): """Fetching json info from pypi project should be ok""" url = "https://pypi.org/pypi/requests/json" requests_mock.get(url, text='{"version": "0.0.1"}') actual_info = json.loads(api_info(url)) assert actual_info == { "version": "0.0.1", } def test_release_name(): for version, filename, expected_release in [ ("0.0.1", None, "releases/0.0.1"), ("0.0.2", "something", "releases/0.0.2/something"), ]: assert release_name(version, filename) == expected_release diff --git a/swh/loader/pytest_plugin.py b/swh/loader/pytest_plugin.py index 7f90c40..e501f02 100644 --- a/swh/loader/pytest_plugin.py +++ b/swh/loader/pytest_plugin.py @@ -1,54 +1,54 @@ # Copyright (C) 2019-2021 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 from typing import Any, Dict import pytest import yaml @pytest.fixture def swh_storage_backend_config(swh_storage_postgresql) -> Dict[str, Any]: return { "cls": "retry", "storage": { "cls": "filter", "storage": { "cls": "buffer", "storage": { "cls": "postgresql", "db": swh_storage_postgresql.dsn, "objstorage": {"cls": "memory"}, }, }, }, } @pytest.fixture def swh_loader_config(swh_storage_backend_config) -> Dict[str, Any]: return { "storage": swh_storage_backend_config, } @pytest.fixture def swh_config(swh_loader_config, monkeypatch, tmp_path) -> str: 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(autouse=True, scope="session") def swh_proxy(): """Automatically inject this fixture in all tests to ensure no outside - connection takes place. + connection takes place. """ os.environ["http_proxy"] = "http://localhost:999" os.environ["https_proxy"] = "http://localhost:999" diff --git a/swh/loader/tests/__init__.py b/swh/loader/tests/__init__.py index f5970fe..32adfed 100644 --- a/swh/loader/tests/__init__.py +++ b/swh/loader/tests/__init__.py @@ -1,265 +1,263 @@ # Copyright (C) 2018-2020 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 from collections import defaultdict import os from pathlib import PosixPath import subprocess from typing import Dict, Iterable, List, Optional, Tuple, Union from swh.model.hashutil import hash_to_bytes from swh.model.model import OriginVisitStatus, Snapshot, TargetType from swh.storage.algos.origin import origin_get_latest_visit_status from swh.storage.algos.snapshot import snapshot_get_all_branches from swh.storage.interface import StorageInterface def assert_last_visit_matches( storage, url: str, status: str, type: Optional[str] = None, snapshot: Optional[bytes] = None, ) -> OriginVisitStatus: """This retrieves the last visit and visit_status which are expected to exist. This also checks that the {visit|visit_status} have their respective properties correctly set. This returns the last visit_status for that given origin. Args: url: Origin url status: Check that the visit status has the given status type: Check that the returned visit has the given type snapshot: Check that the visit status points to the given snapshot Raises: AssertionError in case visit or visit status is not found, or any of the type, status and snapshot mismatch Returns: the visit status for further check during the remaining part of the test. """ __tracebackhide__ = True # Hide from pytest tracebacks on failure visit_status = origin_get_latest_visit_status(storage, url) assert visit_status is not None, f"Origin {url} has no visits" if type: assert ( visit_status.type == type ), f"Visit has type {visit_status.type} instead of {type}" assert ( visit_status.status == status ), f"Visit_status has status {visit_status.status} instead of {status}" if snapshot is not None: assert visit_status.snapshot is not None assert visit_status.snapshot == snapshot, ( f"Visit_status points to snapshot {visit_status.snapshot.hex()} " f"instead of {snapshot.hex()}" ) return visit_status def prepare_repository_from_archive( archive_path: str, filename: Optional[str] = None, tmp_path: Union[PosixPath, str] = "/tmp", ) -> str: """Given an existing archive_path, uncompress it. Returns a file repo url which can be used as origin url. This does not deal with the case where the archive passed along does not exist. """ if not isinstance(tmp_path, str): tmp_path = str(tmp_path) # 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 encode_target(target: Dict) -> Dict: - """Test helper to ease readability in test - - """ + """Test helper to ease readability in test""" if not target: return target target_type = target["target_type"] target_data = target["target"] if target_type == "alias" and isinstance(target_data, str): encoded_target = target_data.encode("utf-8") elif isinstance(target_data, str): encoded_target = hash_to_bytes(target_data) else: encoded_target = target_data return {"target": encoded_target, "target_type": target_type} class InconsistentAliasBranchError(AssertionError): """When an alias branch targets an inexistent branch.""" pass class InexistentObjectsError(AssertionError): """When a targeted branch reference does not exist in the storage""" pass def check_snapshot( expected_snapshot: Snapshot, storage: StorageInterface, allowed_empty: Iterable[Tuple[TargetType, bytes]] = [], ) -> Snapshot: """Check that: - snapshot exists in the storage and match - each object reference up to the revision/release targets exists Args: expected_snapshot: full snapshot to check for existence and consistency storage: storage to lookup information into allowed_empty: Iterable of branch we allow to be empty (some edge case loaders allows this case to happen, nixguix for example allows the branch evaluation" to target the nixpkgs git commit reference, which may not yet be resolvable at loading time) Returns: the snapshot stored in the storage for further test assertion if any is needed. """ __tracebackhide__ = True # Hide from pytest tracebacks on failure if not isinstance(expected_snapshot, Snapshot): raise AssertionError( f"argument 'expected_snapshot' must be a snapshot: {expected_snapshot!r}" ) snapshot = snapshot_get_all_branches(storage, expected_snapshot.id) if snapshot is None: raise AssertionError(f"Snapshot {expected_snapshot.id.hex()} is not found") assert snapshot == expected_snapshot objects_by_target_type = defaultdict(list) object_to_branch = {} for branch, target in expected_snapshot.branches.items(): if (target.target_type, branch) in allowed_empty: # safe for those elements to not be checked for existence continue objects_by_target_type[target.target_type].append(target.target) object_to_branch[target.target] = branch # check that alias references target something that exists, otherwise raise aliases: List[bytes] = objects_by_target_type.get(TargetType.ALIAS, []) for alias in aliases: if alias not in expected_snapshot.branches: raise InconsistentAliasBranchError( f"Alias branch {alias.decode('utf-8')} " f"should be in {list(expected_snapshot.branches)}" ) revs = objects_by_target_type.get(TargetType.REVISION) if revs: revisions = storage.revision_get(revs) not_found = [rev_id for rev_id, rev in zip(revs, revisions) if rev is None] if not_found: missing_objs = ", ".join( str((object_to_branch[rev], rev.hex())) for rev in not_found ) raise InexistentObjectsError( f"Branch/Revision(s) {missing_objs} should exist in storage" ) # retrieve information from revision for revision in revisions: assert revision is not None objects_by_target_type[TargetType.DIRECTORY].append(revision.directory) object_to_branch[revision.directory] = revision.id rels = objects_by_target_type.get(TargetType.RELEASE) if rels: not_found = list(storage.release_missing(rels)) if not_found: missing_objs = ", ".join( str((object_to_branch[rel], rel.hex())) for rel in not_found ) raise InexistentObjectsError( f"Branch/Release(s) {missing_objs} should exist in storage" ) # first level dirs exist? dirs = objects_by_target_type.get(TargetType.DIRECTORY) if dirs: not_found = list(storage.directory_missing(dirs)) if not_found: missing_objs = ", ".join( str((object_to_branch[dir_].hex(), dir_.hex())) for dir_ in not_found ) raise InexistentObjectsError( f"Missing directories {missing_objs}: " "(revision exists, directory target does not)" ) for dir_ in dirs: # retrieve new objects to check for existence paths = storage.directory_ls(dir_, recursive=True) for path in paths: if path["type"] == "dir": target_type = TargetType.DIRECTORY else: target_type = TargetType.CONTENT target = path["target"] objects_by_target_type[target_type].append(target) object_to_branch[target] = dir_ # check nested directories dirs = objects_by_target_type.get(TargetType.DIRECTORY) if dirs: not_found = list(storage.directory_missing(dirs)) if not_found: missing_objs = ", ".join( str((object_to_branch[dir_].hex(), dir_.hex())) for dir_ in not_found ) raise InexistentObjectsError( f"Missing directories {missing_objs}: " "(revision exists, directory target does not)" ) # check contents directories cnts = objects_by_target_type.get(TargetType.CONTENT) if cnts: not_found = list(storage.content_missing_per_sha1_git(cnts)) if not_found: missing_objs = ", ".join( str((object_to_branch[cnt].hex(), cnt.hex())) for cnt in not_found ) raise InexistentObjectsError(f"Missing contents {missing_objs}") return snapshot def get_stats(storage) -> Dict: """Adaptation utils to unify the stats counters across storage - implementation. + implementation. """ storage.refresh_stat_counters() stats = storage.stat_counters() keys = [ "content", "directory", "origin", "origin_visit", "release", "revision", "skipped_content", "snapshot", ] return {k: stats.get(k) for k in keys} diff --git a/swh/loader/tests/conftest.py b/swh/loader/tests/conftest.py index 6639b5d..0494f2b 100644 --- a/swh/loader/tests/conftest.py +++ b/swh/loader/tests/conftest.py @@ -1,19 +1,24 @@ # Copyright (C) 2019-2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from typing import Any, Dict import pytest @pytest.fixture def swh_loader_config() -> Dict[str, Any]: return { - "storage": {"cls": "memory",}, + "storage": { + "cls": "memory", + }, "deposit": { "url": "https://deposit.softwareheritage.org/1/private", - "auth": {"username": "user", "password": "pass",}, + "auth": { + "username": "user", + "password": "pass", + }, }, } diff --git a/swh/loader/tests/test_cli.py b/swh/loader/tests/test_cli.py index 151d0ea..9f43735 100644 --- a/swh/loader/tests/test_cli.py +++ b/swh/loader/tests/test_cli.py @@ -1,152 +1,156 @@ # Copyright (C) 2019-2021 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 datetime import os from click.formatting import HelpFormatter from click.testing import CliRunner import pytest import yaml from swh.loader.cli import SUPPORTED_LOADERS, get_loader from swh.loader.cli import loader as loader_cli from swh.loader.package.loader import PackageLoader def test_get_loader_wrong_input(swh_config): - """Unsupported loader should raise - - """ + """Unsupported loader should raise""" loader_type = "unknown" assert loader_type not in SUPPORTED_LOADERS with pytest.raises(ValueError, match="Invalid loader"): get_loader(loader_type, url="db-url") def test_get_loader(swh_loader_config): - """Instantiating a supported loader should be ok - - """ + """Instantiating a supported loader should be ok""" loader_input = { "archive": {"url": "some-url", "artifacts": []}, - "debian": {"url": "some-url", "packages": [],}, - "npm": {"url": "https://www.npmjs.com/package/onepackage",}, - "pypi": {"url": "some-url",}, + "debian": { + "url": "some-url", + "packages": [], + }, + "npm": { + "url": "https://www.npmjs.com/package/onepackage", + }, + "pypi": { + "url": "some-url", + }, } for loader_type, kwargs in loader_input.items(): kwargs["storage"] = swh_loader_config["storage"] loader = get_loader(loader_type, **kwargs) assert isinstance(loader, PackageLoader) def _write_usage(command, args, max_width=80): hf = HelpFormatter(width=max_width) hf.write_usage(command, args) return hf.getvalue()[:-1] def test_run_help(swh_config): - """Usage message should contain list of available loaders - - """ + """Usage message should contain list of available loaders""" runner = CliRunner() result = runner.invoke(loader_cli, ["run", "-h"]) assert result.exit_code == 0 # Syntax depends on dependencies' versions supported_loaders = "|".join(SUPPORTED_LOADERS) usage_prefix = _write_usage("loader run", "[OPTIONS] [%s]\n" % supported_loaders) usage_prefix2 = _write_usage("loader run", "[OPTIONS] {%s}\n" % supported_loaders) assert result.output.startswith((usage_prefix, usage_prefix2)) def test_run_with_configuration_failure(tmp_path): - """Triggering a load should fail since configuration is incomplete - - """ + """Triggering a load should fail since configuration is incomplete""" runner = CliRunner() conf_path = os.path.join(str(tmp_path), "cli.yml") with open(conf_path, "w") as f: f.write(yaml.dump({})) with pytest.raises(ValueError, match="Missing storage"): runner.invoke( loader_cli, - ["-C", conf_path, "run", "pypi", "url=https://some-url",], + [ + "-C", + conf_path, + "run", + "pypi", + "url=https://some-url", + ], catch_exceptions=False, ) def test_run_pypi(mocker, swh_config): - """Triggering a load should be ok - - """ + """Triggering a load should be ok""" mock_loader = mocker.patch("swh.loader.package.pypi.loader.PyPILoader.load") runner = CliRunner() result = runner.invoke( - loader_cli, ["-C", swh_config, "run", "pypi", "url=https://some-url",] + loader_cli, + [ + "-C", + swh_config, + "run", + "pypi", + "url=https://some-url", + ], ) assert result.exit_code == 0 mock_loader.assert_called_once_with() def test_run_with_visit_date(mocker, swh_config): - """iso visit_date parameter should be parsed as datetime - - """ + """iso visit_date parameter should be parsed as datetime""" mock_loader = mocker.patch("swh.loader.cli.get_loader") runner = CliRunner() input_date = "2016-05-03 15:16:32+00" result = runner.invoke( loader_cli, ["run", "npm", "https://some-url", f"visit_date='{input_date}'"] ) assert result.exit_code == 0 expected_parsed_date = datetime.datetime( 2016, 5, 3, 15, 16, 32, tzinfo=datetime.timezone.utc ) mock_loader.assert_called_once_with( "npm", storage={"cls": "memory"}, url="https://some-url", visit_date=expected_parsed_date, ) def test_list_help(mocker, swh_config): - """Usage message should contain list of available loaders - - """ + """Usage message should contain list of available loaders""" runner = CliRunner() result = runner.invoke(loader_cli, ["list", "--help"]) assert result.exit_code == 0 usage_prefix = _write_usage( "loader list", f"[OPTIONS] [[{'|'.join(['all'] + SUPPORTED_LOADERS)}]]" ) expected_help_msg = f"""{usage_prefix} List supported loaders and optionally their arguments Options: -h, --help Show this message and exit. """ assert result.output.startswith(expected_help_msg) def test_list_help_npm(mocker, swh_config): - """Triggering a load should be ok - - """ + """Triggering a load should be ok""" runner = CliRunner() result = runner.invoke(loader_cli, ["list", "npm"]) assert result.exit_code == 0 expected_help_msg = """ Loader: Load npm origin's artifact releases into swh archive. """ assert result.output.startswith(expected_help_msg[1:]) diff --git a/swh/loader/tests/test_init.py b/swh/loader/tests/test_init.py index bb1fed9..64655c7 100644 --- a/swh/loader/tests/test_init.py +++ b/swh/loader/tests/test_init.py @@ -1,510 +1,533 @@ # Copyright (C) 2020-2021 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 datetime import os import subprocess import attr import pytest from swh.loader.tests import ( InconsistentAliasBranchError, InexistentObjectsError, assert_last_visit_matches, check_snapshot, encode_target, prepare_repository_from_archive, ) from swh.model.from_disk import DentryPerms from swh.model.hashutil import hash_to_bytes from swh.model.model import ( Content, Directory, DirectoryEntry, ObjectType, OriginVisit, OriginVisitStatus, Person, Release, Revision, RevisionType, Snapshot, SnapshotBranch, TargetType, Timestamp, TimestampWithTimezone, ) hash_hex = "43e45d56f88993aae6a0198013efa80716fd8920" ORIGIN_VISIT = OriginVisit( origin="some-url", visit=1, date=datetime.datetime.now(tz=datetime.timezone.utc), type="archive", ) ORIGIN_VISIT_STATUS = OriginVisitStatus( origin="some-url", visit=1, type="archive", date=datetime.datetime.now(tz=datetime.timezone.utc), status="full", snapshot=hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"), metadata=None, ) CONTENT = Content( data=b"42\n", length=3, sha1=hash_to_bytes("34973274ccef6ab4dfaaf86599792fa9c3fe4689"), sha1_git=hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"), sha256=hash_to_bytes( "673650f936cb3b0a2f93ce09d81be10748b1b203c19e8176b4eefc1964a0cf3a" ), blake2s256=hash_to_bytes( "d5fe1939576527e42cfd76a9455a2432fe7f56669564577dd93c4280e76d661d" ), status="visible", ) DIRECTORY = Directory( id=hash_to_bytes("34f335a750111ca0a8b64d8034faec9eedc396be"), entries=tuple( [ DirectoryEntry( name=b"foo", type="file", target=CONTENT.sha1_git, perms=DentryPerms.content, ) ] ), ) REVISION = Revision( id=hash_to_bytes("066b1b62dbfa033362092af468bf6cfabec230e7"), message=b"hello", author=Person( name=b"Nicolas Dandrimont", email=b"nicolas@example.com", fullname=b"Nicolas Dandrimont ", ), date=TimestampWithTimezone(Timestamp(1234567890, 0), offset_bytes=b"+0200"), committer=Person( name=b"St\xc3fano Zacchiroli", email=b"stefano@example.com", fullname=b"St\xc3fano Zacchiroli ", ), committer_date=TimestampWithTimezone( Timestamp(1123456789, 0), offset_bytes=b"-0000" ), parents=(), type=RevisionType.GIT, directory=DIRECTORY.id, metadata={ - "checksums": {"sha1": "tarball-sha1", "sha256": "tarball-sha256",}, + "checksums": { + "sha1": "tarball-sha1", + "sha256": "tarball-sha256", + }, "signed-off-by": "some-dude", }, extra_headers=( (b"gpgsig", b"test123"), (b"mergetag", b"foo\\bar"), (b"mergetag", b"\x22\xaf\x89\x80\x01\x00"), ), synthetic=True, ) RELEASE = Release( id=hash_to_bytes("3e9050196aa288264f2a9d279d6abab8b158448b"), name=b"v0.0.2", author=Person( - name=b"tony", email=b"tony@ardumont.fr", fullname=b"tony ", + name=b"tony", + email=b"tony@ardumont.fr", + fullname=b"tony ", ), date=TimestampWithTimezone.from_datetime( datetime.datetime(2021, 10, 15, 22, 26, 53, tzinfo=datetime.timezone.utc) ), target=REVISION.id, target_type=ObjectType.REVISION, message=b"yet another synthetic release", synthetic=True, ) SNAPSHOT = Snapshot( id=hash_to_bytes("2498dbf535f882bc7f9a18fb16c9ad27fda7bab7"), branches={ b"release/0.1.0": SnapshotBranch( - target=RELEASE.id, target_type=TargetType.RELEASE, + target=RELEASE.id, + target_type=TargetType.RELEASE, + ), + b"HEAD": SnapshotBranch( + target=REVISION.id, + target_type=TargetType.REVISION, + ), + b"alias": SnapshotBranch( + target=b"HEAD", + target_type=TargetType.ALIAS, ), - b"HEAD": SnapshotBranch(target=REVISION.id, target_type=TargetType.REVISION,), - b"alias": SnapshotBranch(target=b"HEAD", target_type=TargetType.ALIAS,), b"evaluation": SnapshotBranch( # branch dedicated to not exist in storage target=hash_to_bytes("cc4e04c26672dd74e5fd0fecb78b435fb55368f7"), target_type=TargetType.REVISION, ), }, ) @pytest.fixture def swh_storage_backend_config(swh_storage_postgresql): return { "cls": "postgresql", "db": swh_storage_postgresql.dsn, "objstorage": {"cls": "memory"}, } @pytest.fixture def mock_storage(mocker): mock_storage = mocker.patch("swh.loader.tests.origin_get_latest_visit_status") mock_storage.return_value = ORIGIN_VISIT_STATUS return mock_storage def test_assert_last_visit_matches_raise(mock_storage, mocker): - """Not finding origin visit_and_statu should raise - - """ + """Not finding origin visit_and_statu should raise""" # overwrite so we raise because we do not find the right visit mock_storage.return_value = None with pytest.raises(AssertionError, match="Origin url has no visits"): assert_last_visit_matches(mock_storage, "url", status="full") assert mock_storage.called is True def test_assert_last_visit_matches_wrong_status(mock_storage, mocker): - """Wrong visit detected should raise AssertionError - - """ + """Wrong visit detected should raise AssertionError""" expected_status = "partial" assert ORIGIN_VISIT_STATUS.status != expected_status with pytest.raises(AssertionError, match="Visit_status has status"): assert_last_visit_matches(mock_storage, "url", status=expected_status) assert mock_storage.called is True def test_assert_last_visit_matches_wrong_type(mock_storage, mocker): - """Wrong visit detected should raise AssertionError - - """ + """Wrong visit detected should raise AssertionError""" expected_type = "git" assert ORIGIN_VISIT.type != expected_type with pytest.raises(AssertionError, match="Visit has type"): assert_last_visit_matches( mock_storage, "url", status=ORIGIN_VISIT_STATUS.status, type=expected_type, # mismatched type will raise ) assert mock_storage.called is True def test_assert_last_visit_matches_wrong_snapshot(mock_storage, mocker): - """Wrong visit detected should raise AssertionError - - """ + """Wrong visit detected should raise AssertionError""" expected_snapshot_id = hash_to_bytes("e92cc0710eb6cf9efd5b920a8453e1e07157b6cd") assert ORIGIN_VISIT_STATUS.snapshot != expected_snapshot_id with pytest.raises(AssertionError, match="Visit_status points to snapshot"): assert_last_visit_matches( mock_storage, "url", status=ORIGIN_VISIT_STATUS.status, snapshot=expected_snapshot_id, # mismatched snapshot will raise ) assert mock_storage.called is True def test_assert_last_visit_matches(mock_storage, mocker): - """Correct visit detected should return the visit_status - - """ + """Correct visit detected should return the visit_status""" visit_type = ORIGIN_VISIT.type visit_status = ORIGIN_VISIT_STATUS.status visit_snapshot = ORIGIN_VISIT_STATUS.snapshot actual_visit_status = assert_last_visit_matches( mock_storage, "url", type=visit_type, status=visit_status, snapshot=visit_snapshot, ) assert actual_visit_status == ORIGIN_VISIT_STATUS assert mock_storage.called is True def test_prepare_repository_from_archive_failure(): # does not deal with inexistent archive so raise assert os.path.exists("unknown-archive") is False with pytest.raises(subprocess.CalledProcessError, match="exit status 2"): prepare_repository_from_archive("unknown-archive") def test_prepare_repository_from_archive(datadir, tmp_path): archive_name = "0805nexter-1.1.0" archive_path = os.path.join(str(datadir), f"{archive_name}.tar.gz") assert os.path.exists(archive_path) is True tmp_path = str(tmp_path) # deals with path string repo_url = prepare_repository_from_archive( archive_path, filename=archive_name, tmp_path=tmp_path ) expected_uncompressed_archive_path = os.path.join(tmp_path, archive_name) assert repo_url == f"file://{expected_uncompressed_archive_path}" assert os.path.exists(expected_uncompressed_archive_path) def test_prepare_repository_from_archive_no_filename(datadir, tmp_path): archive_name = "0805nexter-1.1.0" archive_path = os.path.join(str(datadir), f"{archive_name}.tar.gz") assert os.path.exists(archive_path) is True # deals with path as posix path (for tmp_path) repo_url = prepare_repository_from_archive(archive_path, tmp_path=tmp_path) tmp_path = str(tmp_path) expected_uncompressed_archive_path = os.path.join(tmp_path, archive_name) expected_repo_url = os.path.join(tmp_path, f"{archive_name}.tar.gz") assert repo_url == f"file://{expected_repo_url}" # passing along the filename does not influence the on-disk extraction # just the repo-url computation assert os.path.exists(expected_uncompressed_archive_path) def test_encode_target(): assert encode_target(None) is None for target_alias in ["something", b"something"]: target = { "target_type": "alias", "target": target_alias, } actual_alias_encode_target = encode_target(target) assert actual_alias_encode_target == { "target_type": "alias", "target": b"something", } for hash_ in [hash_hex, hash_to_bytes(hash_hex)]: target = {"target_type": "revision", "target": hash_} actual_encode_target = encode_target(target) assert actual_encode_target == { "target_type": "revision", "target": hash_to_bytes(hash_hex), } def test_check_snapshot(swh_storage): """Everything should be fine when snapshot is found and the snapshot reference up to the revision exist in the storage. """ # Create a consistent snapshot arborescence tree in storage found = False for entry in DIRECTORY.entries: if entry.target == CONTENT.sha1_git: found = True break assert found is True assert REVISION.directory == DIRECTORY.id assert RELEASE.target == REVISION.id for branch, target in SNAPSHOT.branches.items(): if branch == b"alias": assert target.target in SNAPSHOT.branches elif branch == b"evaluation": # this one does not exist and we are safelisting its check below continue else: assert target.target in [REVISION.id, RELEASE.id] swh_storage.content_add([CONTENT]) swh_storage.directory_add([DIRECTORY]) swh_storage.revision_add([REVISION]) swh_storage.release_add([RELEASE]) s = swh_storage.snapshot_add([SNAPSHOT]) assert s == { "snapshot:add": 1, } # all should be fine! check_snapshot( SNAPSHOT, swh_storage, allowed_empty=[(TargetType.REVISION, b"evaluation")] ) def test_check_snapshot_failures(swh_storage): """Failure scenarios: 0. snapshot parameter is not a snapshot 1. snapshot id is correct but branches mismatched 2. snapshot id is not correct, it's not found in the storage 3. snapshot reference an alias which does not exist 4. snapshot is found in storage, targeted revision does not exist 5. snapshot is found in storage, targeted revision exists but the directory the revision targets does not exist 6. snapshot is found in storage, target revision exists, targeted directory by the revision exist. Content targeted by the directory does not exist. 7. snapshot is found in storage, targeted release does not exist """ snap_id_hex = "2498dbf535f882bc7f9a18fb16c9ad27fda7bab7" snapshot = Snapshot( id=hash_to_bytes(snap_id_hex), branches={ b"master": SnapshotBranch( - target=hash_to_bytes(hash_hex), target_type=TargetType.REVISION, + target=hash_to_bytes(hash_hex), + target_type=TargetType.REVISION, ), }, ) s = swh_storage.snapshot_add([snapshot]) assert s == { "snapshot:add": 1, } unexpected_snapshot = Snapshot( branches={ b"tip": SnapshotBranch( # wrong branch target=hash_to_bytes(hash_hex), target_type=TargetType.RELEASE ) }, ) # 0. not a Snapshot object, raise! with pytest.raises( AssertionError, match="argument 'expected_snapshot' must be a snapshot" ): check_snapshot(ORIGIN_VISIT, swh_storage) # 1. snapshot id is correct but branches mismatched with pytest.raises(AssertionError): # sadly debian build raises only assertion check_snapshot(attr.evolve(unexpected_snapshot, id=snapshot.id), swh_storage) # 2. snapshot id is not correct, it's not found in the storage wrong_snap_id = hash_to_bytes("999666f535f882bc7f9a18fb16c9ad27fda7bab7") with pytest.raises(AssertionError, match="is not found"): check_snapshot(attr.evolve(unexpected_snapshot, id=wrong_snap_id), swh_storage) # 3. snapshot references an inexistent alias snapshot0 = Snapshot( id=hash_to_bytes("123666f535f882bc7f9a18fb16c9ad27fda7bab7"), branches={ - b"alias": SnapshotBranch(target=b"HEAD", target_type=TargetType.ALIAS,), + b"alias": SnapshotBranch( + target=b"HEAD", + target_type=TargetType.ALIAS, + ), }, ) swh_storage.snapshot_add([snapshot0]) with pytest.raises(InconsistentAliasBranchError, match="Alias branch HEAD"): check_snapshot(snapshot0, swh_storage) # 4. snapshot is found in storage, targeted revision does not exist rev_not_found = list(swh_storage.revision_missing([REVISION.id])) assert len(rev_not_found) == 1 snapshot1 = Snapshot( id=hash_to_bytes("456666f535f882bc7f9a18fb16c9ad27fda7bab7"), branches={ - b"alias": SnapshotBranch(target=b"HEAD", target_type=TargetType.ALIAS,), + b"alias": SnapshotBranch( + target=b"HEAD", + target_type=TargetType.ALIAS, + ), b"HEAD": SnapshotBranch( - target=REVISION.id, target_type=TargetType.REVISION, + target=REVISION.id, + target_type=TargetType.REVISION, ), }, ) swh_storage.snapshot_add([snapshot1]) with pytest.raises(InexistentObjectsError, match="Branch/Revision"): check_snapshot(snapshot1, swh_storage) # 5. snapshot is found in storage, targeted revision exists but the directory the # revision targets does not exist swh_storage.revision_add([REVISION]) dir_not_found = list(swh_storage.directory_missing([REVISION.directory])) assert len(dir_not_found) == 1 snapshot2 = Snapshot( id=hash_to_bytes("987123f535f882bc7f9a18fb16c9ad27fda7bab7"), branches={ - b"alias": SnapshotBranch(target=b"HEAD", target_type=TargetType.ALIAS,), + b"alias": SnapshotBranch( + target=b"HEAD", + target_type=TargetType.ALIAS, + ), b"HEAD": SnapshotBranch( - target=REVISION.id, target_type=TargetType.REVISION, + target=REVISION.id, + target_type=TargetType.REVISION, ), }, ) swh_storage.snapshot_add([snapshot2]) with pytest.raises(InexistentObjectsError, match="Missing directories"): check_snapshot(snapshot2, swh_storage) assert DIRECTORY.id == REVISION.directory swh_storage.directory_add([DIRECTORY]) # 6. snapshot is found in storage, target revision exists, targeted directory by the # revision exist. Content targeted by the directory does not exist. assert DIRECTORY.entries[0].target == CONTENT.sha1_git not_found = list(swh_storage.content_missing_per_sha1_git([CONTENT.sha1_git])) assert len(not_found) == 1 swh_storage.directory_add([DIRECTORY]) snapshot3 = Snapshot( id=hash_to_bytes("091456f535f882bc7f9a18fb16c9ad27fda7bab7"), branches={ - b"alias": SnapshotBranch(target=b"HEAD", target_type=TargetType.ALIAS,), + b"alias": SnapshotBranch( + target=b"HEAD", + target_type=TargetType.ALIAS, + ), b"HEAD": SnapshotBranch( - target=REVISION.id, target_type=TargetType.REVISION, + target=REVISION.id, + target_type=TargetType.REVISION, ), }, ) swh_storage.snapshot_add([snapshot3]) with pytest.raises(InexistentObjectsError, match="Missing content(s)"): check_snapshot(snapshot3, swh_storage) # 7. snapshot is found in storage, targeted release does not exist # release targets the revisions which exists assert RELEASE.target == REVISION.id snapshot4 = Snapshot( id=hash_to_bytes("789666f535f882bc7f9a18fb16c9ad27fda7bab7"), branches={ - b"alias": SnapshotBranch(target=b"HEAD", target_type=TargetType.ALIAS,), + b"alias": SnapshotBranch( + target=b"HEAD", + target_type=TargetType.ALIAS, + ), b"HEAD": SnapshotBranch( - target=REVISION.id, target_type=TargetType.REVISION, + target=REVISION.id, + target_type=TargetType.REVISION, ), b"release/0.1.0": SnapshotBranch( - target=RELEASE.id, target_type=TargetType.RELEASE, + target=RELEASE.id, + target_type=TargetType.RELEASE, ), }, ) swh_storage.snapshot_add([snapshot4]) with pytest.raises(InexistentObjectsError, match="Branch/Release"): check_snapshot(snapshot4, swh_storage)