diff --git a/mypy.ini b/mypy.ini index 4a09c588..2949be58 100644 --- a/mypy.ini +++ b/mypy.ini @@ -1,36 +1,39 @@ [mypy] namespace_packages = True # due to the conditional import logic on swh.journal, in some cases a specific # type: ignore is needed, in other it isn't... warn_unused_ignores = False # support for sqlalchemy magic: see https://github.com/dropbox/sqlalchemy-stubs plugins = sqlmypy # 3rd party libraries without stubs (yet) +[mypy-cassandra.*] +ignore_missing_imports = True + # only shipped indirectly via hypothesis [mypy-django.*] ignore_missing_imports = True [mypy-pkg_resources.*] ignore_missing_imports = True [mypy-psycopg2.*] ignore_missing_imports = True [mypy-pytest.*] ignore_missing_imports = True [mypy-tenacity.*] ignore_missing_imports = True # temporary work-around for landing typing support in spite of the current # journal<->storage dependency loop [mypy-swh.journal.*] ignore_missing_imports = True [mypy-pytest_postgresql.*] ignore_missing_imports = True diff --git a/pytest.ini b/pytest.ini index e8154090..6005f361 100644 --- a/pytest.ini +++ b/pytest.ini @@ -1,8 +1,9 @@ [pytest] norecursedirs = docs filterwarnings = ignore:.*the imp module.*:PendingDeprecationWarning markers = db: execute tests using a postgresql database + cassandra: execute tests using a cassandra database (which are slow) property_based: execute tests generating data with hypothesis (potentially long run time) network: execute tests using a socket between two threads diff --git a/requirements-test.txt b/requirements-test.txt index a61e13d0..f6de91f7 100644 --- a/requirements-test.txt +++ b/requirements-test.txt @@ -1,10 +1,11 @@ hypothesis >= 3.11.0 pytest pytest-mock pytest-postgresql >= 2.1.0 sqlalchemy-stubs # pytz is in fact a dep of swh.model[testing] and should not be necessary, but # the dep on swh.model in the main requirements-swh.txt file shadows this one # adding the [testing] extra. swh.model[testing] >= 0.0.50 pytz +pytest-xdist diff --git a/requirements.txt b/requirements.txt index daf673a8..ebedade6 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,7 +1,8 @@ click flask psycopg2 python-dateutil vcversioner aiohttp tenacity +cassandra-driver >= 3.19.0, < 3.21.0 diff --git a/swh/storage/__init__.py b/swh/storage/__init__.py index 83c1ae25..16a10f6e 100644 --- a/swh/storage/__init__.py +++ b/swh/storage/__init__.py @@ -1,97 +1,96 @@ # 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 warnings -from . import storage - -Storage = storage.Storage - class HashCollision(Exception): pass STORAGE_IMPLEMENTATION = { 'pipeline', 'local', 'remote', 'memory', 'filter', 'buffer', 'retry', + 'cassandra', } def get_storage(cls, **kwargs): """Get a storage object of class `storage_class` with arguments `storage_args`. Args: storage (dict): dictionary with keys: - cls (str): storage's class, either local, remote, memory, filter, buffer - args (dict): dictionary with keys Returns: an instance of swh.storage.Storage or compatible class Raises: ValueError if passed an unknown storage class. """ if cls not in STORAGE_IMPLEMENTATION: raise ValueError('Unknown storage class `%s`. Supported: %s' % ( cls, ', '.join(STORAGE_IMPLEMENTATION))) if 'args' in kwargs: warnings.warn( 'Explicit "args" key is deprecated, use keys directly instead.', DeprecationWarning) kwargs = kwargs['args'] if cls == 'pipeline': return get_storage_pipeline(**kwargs) if cls == 'remote': from .api.client import RemoteStorage as Storage elif cls == 'local': from .storage import Storage + elif cls == 'cassandra': + from .cassandra import CassandraStorage as Storage elif cls == 'memory': from .in_memory import InMemoryStorage as Storage elif cls == 'filter': from .filter import FilteringProxyStorage as Storage elif cls == 'buffer': from .buffer import BufferingProxyStorage as Storage elif cls == 'retry': from .retry import RetryingProxyStorage as Storage return Storage(**kwargs) def get_storage_pipeline(steps): """Recursively get a storage object that may use other storage objects as backends. Args: steps (List[dict]): List of dicts that may be used as kwargs for `get_storage`. Returns: an instance of swh.storage.Storage or compatible class Raises: ValueError if passed an unknown storage class. """ storage_config = None for step in reversed(steps): if 'args' in step: warnings.warn( 'Explicit "args" key is deprecated, use keys directly ' 'instead.', DeprecationWarning) step = { 'cls': step['cls'], **step['args'], } if storage_config: step['storage'] = storage_config storage_config = step return get_storage(**storage_config) diff --git a/swh/storage/cassandra/__init__.py b/swh/storage/cassandra/__init__.py new file mode 100644 index 00000000..b3ab634c --- /dev/null +++ b/swh/storage/cassandra/__init__.py @@ -0,0 +1,11 @@ +# Copyright (C) 2019-2020 The Software Heritage developers +# See the AUTHORS file at the top-level directory of this distribution +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + + +from .cql import create_keyspace +from .storage import CassandraStorage + + +__all__ = ['create_keyspace', 'CassandraStorage'] diff --git a/swh/storage/cassandra/common.py b/swh/storage/cassandra/common.py new file mode 100644 index 00000000..65bf67e0 --- /dev/null +++ b/swh/storage/cassandra/common.py @@ -0,0 +1,20 @@ +# Copyright (C) 2019-2020 The Software Heritage developers +# See the AUTHORS file at the top-level directory of this distribution +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + + +import hashlib + + +Row = tuple + + +TOKEN_BEGIN = -(2**63) +'''Minimum value returned by the CQL function token()''' +TOKEN_END = 2**63-1 +'''Maximum value returned by the CQL function token()''' + + +def hash_url(url: str) -> bytes: + return hashlib.sha1(url.encode('ascii')).digest() diff --git a/swh/storage/cassandra/converters.py b/swh/storage/cassandra/converters.py new file mode 100644 index 00000000..2231985b --- /dev/null +++ b/swh/storage/cassandra/converters.py @@ -0,0 +1,72 @@ +# Copyright (C) 2019-2020 The Software Heritage developers +# See the AUTHORS file at the top-level directory of this distribution +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + + +import json +from typing import Any, Dict + +import attr + +from swh.model.model import ( + RevisionType, ObjectType, Revision, Release, +) + + +from ..converters import git_headers_to_db, db_to_git_headers + + +def revision_to_db(revision: Dict[str, Any]) -> Revision: + metadata = revision.get('metadata') + if metadata and 'extra_headers' in metadata: + extra_headers = git_headers_to_db( + metadata['extra_headers']) + revision = { + **revision, + 'metadata': { + **metadata, + 'extra_headers': extra_headers + } + } + + rev = Revision.from_dict(revision) + rev = attr.evolve( + rev, + type=rev.type.value, + metadata=json.dumps(rev.metadata), + ) + + return rev + + +def revision_from_db(revision) -> Revision: + metadata = json.loads(revision.metadata) + if metadata and 'extra_headers' in metadata: + extra_headers = db_to_git_headers( + metadata['extra_headers']) + metadata['extra_headers'] = extra_headers + rev = attr.evolve( + revision, + type=RevisionType(revision.type), + metadata=metadata, + ) + + return rev + + +def release_to_db(release: Dict[str, Any]) -> Release: + rel = Release.from_dict(release) + rel = attr.evolve( + rel, + target_type=rel.target_type.value, + ) + return rel + + +def release_from_db(release: Release) -> Release: + release = attr.evolve( + release, + target_type=ObjectType(release.target_type), + ) + return release diff --git a/swh/storage/cassandra/cql.py b/swh/storage/cassandra/cql.py new file mode 100644 index 00000000..d059411b --- /dev/null +++ b/swh/storage/cassandra/cql.py @@ -0,0 +1,619 @@ +# Copyright (C) 2019-2020 The Software Heritage developers +# See the AUTHORS file at the top-level directory of this distribution +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +import functools +import json +import logging +import random +from typing import ( + Any, Callable, Dict, Generator, Iterable, List, Optional, TypeVar +) + +from cassandra.cluster import ( + Cluster, EXEC_PROFILE_DEFAULT, ExecutionProfile, ResultSet) +from cassandra.policies import DCAwareRoundRobinPolicy, TokenAwarePolicy +from cassandra.query import PreparedStatement +from tenacity import retry, stop_after_attempt, wait_random_exponential + +from swh.model.model import ( + Sha1Git, TimestampWithTimezone, Timestamp, Person, Content, +) + +from .common import Row, TOKEN_BEGIN, TOKEN_END, hash_url +from .schema import CREATE_TABLES_QUERIES, HASH_ALGORITHMS + + +logger = logging.getLogger(__name__) + + +_execution_profiles = { + EXEC_PROFILE_DEFAULT: ExecutionProfile( + load_balancing_policy=TokenAwarePolicy(DCAwareRoundRobinPolicy())), +} +# Configuration for cassandra-driver's access to servers: +# * hit the right server directly when sending a query (TokenAwarePolicy), +# * if there's more than one, then pick one at random that's in the same +# datacenter as the client (DCAwareRoundRobinPolicy) + + +def create_keyspace(hosts: List[str], keyspace: str, port: int = 9042): + cluster = Cluster( + hosts, port=port, execution_profiles=_execution_profiles) + session = cluster.connect() + session.execute('''CREATE KEYSPACE IF NOT EXISTS "%s" + WITH REPLICATION = { + 'class' : 'SimpleStrategy', + 'replication_factor' : 1 + }; + ''' % keyspace) + session.execute('USE "%s"' % keyspace) + for query in CREATE_TABLES_QUERIES: + session.execute(query) + + +T = TypeVar('T') + + +def _prepared_statement( + query: str) -> Callable[[Callable[..., T]], Callable[..., T]]: + """Returns a decorator usable on methods of CqlRunner, to + inject them with a 'statement' argument, that is a prepared + statement corresponding to the query. + + This only works on methods of CqlRunner, as preparing a + statement requires a connection to a Cassandra server.""" + def decorator(f): + @functools.wraps(f) + def newf(self, *args, **kwargs) -> T: + if f.__name__ not in self._prepared_statements: + statement: PreparedStatement = self._session.prepare(query) + self._prepared_statements[f.__name__] = statement + return f(self, *args, **kwargs, + statement=self._prepared_statements[f.__name__]) + return newf + return decorator + + +def _prepared_insert_statement(table_name: str, columns: List[str]): + """Shorthand for using `_prepared_statement` for `INSERT INTO` + statements.""" + return _prepared_statement( + 'INSERT INTO %s (%s) VALUES (%s)' % ( + table_name, + ', '.join(columns), ', '.join('?' for _ in columns), + ) + ) + + +def _prepared_exists_statement(table_name: str): + """Shorthand for using `_prepared_statement` for queries that only + check which ids in a list exist in the table.""" + return _prepared_statement(f'SELECT id FROM {table_name} WHERE id IN ?') + + +class CqlRunner: + """Class managing prepared statements and building queries to be sent + to Cassandra.""" + def __init__(self, hosts: List[str], keyspace: str, port: int): + self._cluster = Cluster( + hosts, port=port, execution_profiles=_execution_profiles) + self._session = self._cluster.connect(keyspace) + self._cluster.register_user_type( + keyspace, 'microtimestamp_with_timezone', TimestampWithTimezone) + self._cluster.register_user_type( + keyspace, 'microtimestamp', Timestamp) + self._cluster.register_user_type( + keyspace, 'person', Person) + + self._prepared_statements: Dict[str, PreparedStatement] = {} + + ########################## + # Common utility functions + ########################## + + MAX_RETRIES = 3 + + @retry(wait=wait_random_exponential(multiplier=1, max=10), + stop=stop_after_attempt(MAX_RETRIES)) + def _execute_with_retries(self, statement, args) -> ResultSet: + return self._session.execute(statement, args, timeout=100.) + + @_prepared_statement('UPDATE object_count SET count = count + ? ' + 'WHERE partition_key = 0 AND object_type = ?') + def _increment_counter( + self, object_type: str, nb: int, *, statement: PreparedStatement + ) -> None: + self._execute_with_retries(statement, [nb, object_type]) + + def _add_one( + self, statement, object_type: str, obj, keys: List[str] + ) -> None: + self._increment_counter(object_type, 1) + self._execute_with_retries( + statement, [getattr(obj, key) for key in keys]) + + def _get_random_row(self, statement) -> Optional[Row]: + """Takes a prepared statement of the form + "SELECT * FROM WHERE token() > ? LIMIT 1" + and uses it to return a random row""" + token = random.randint(TOKEN_BEGIN, TOKEN_END) + rows = self._execute_with_retries(statement, [token]) + if not rows: + # There are no row with a greater token; wrap around to get + # the row with the smallest token + rows = self._execute_with_retries(statement, [TOKEN_BEGIN]) + if rows: + return rows.one() + else: + return None + + def _missing(self, statement, ids): + res = self._execute_with_retries(statement, [ids]) + found_ids = {id_ for (id_,) in res} + return [id_ for id_ in ids if id_ not in found_ids] + + ########################## + # 'content' table + ########################## + + _content_pk = ['sha1', 'sha1_git', 'sha256', 'blake2s256'] + _content_keys = [ + 'sha1', 'sha1_git', 'sha256', 'blake2s256', 'length', + 'ctime', 'status'] + + @_prepared_statement('SELECT * FROM content WHERE ' + + ' AND '.join(map('%s = ?'.__mod__, HASH_ALGORITHMS))) + def content_get_from_pk( + self, content_hashes: Dict[str, bytes], *, statement + ) -> Optional[Row]: + rows = list(self._execute_with_retries( + statement, [content_hashes[algo] for algo in HASH_ALGORITHMS])) + assert len(rows) <= 1 + if rows: + return rows[0] + else: + return None + + @_prepared_statement('SELECT * FROM content WHERE token(%s) > ? LIMIT 1' + % ', '.join(_content_pk)) + def content_get_random(self, *, statement) -> Optional[Row]: + return self._get_random_row(statement) + + @_prepared_statement(('SELECT token({0}) AS tok, {1} FROM content ' + 'WHERE token({0}) >= ? AND token({0}) <= ? LIMIT ?') + .format(', '.join(_content_pk), + ', '.join(_content_keys))) + def content_get_token_range( + self, start: int, end: int, limit: int, *, statement) -> Row: + return self._execute_with_retries(statement, [start, end, limit]) + + ########################## + # 'content_by_*' tables + ########################## + + @_prepared_statement('SELECT sha1_git FROM content_by_sha1_git ' + 'WHERE sha1_git IN ?') + def content_missing_by_sha1_git( + self, ids: List[bytes], *, statement) -> List[bytes]: + return self._missing(statement, ids) + + @_prepared_insert_statement('content', _content_keys) + def content_add_one(self, content, *, statement) -> None: + self._add_one(statement, 'content', content, self._content_keys) + + def content_index_add_one(self, main_algo: str, content: Content) -> None: + query = 'INSERT INTO content_by_{algo} ({cols}) VALUES ({values})' \ + .format(algo=main_algo, cols=', '.join(self._content_pk), + values=', '.join('%s' for _ in self._content_pk)) + self._execute_with_retries( + query, [content.get_hash(algo) for algo in self._content_pk]) + + def content_get_pks_from_single_hash( + self, algo: str, hash_: bytes) -> List[Row]: + assert algo in HASH_ALGORITHMS + query = 'SELECT * FROM content_by_{algo} WHERE {algo} = %s'.format( + algo=algo) + return list(self._execute_with_retries(query, [hash_])) + + ########################## + # 'revision' table + ########################## + + _revision_keys = [ + 'id', 'date', 'committer_date', 'type', 'directory', 'message', + 'author', 'committer', + 'synthetic', 'metadata'] + + @_prepared_exists_statement('revision') + def revision_missing(self, ids: List[bytes], *, statement) -> List[bytes]: + return self._missing(statement, ids) + + @_prepared_insert_statement('revision', _revision_keys) + def revision_add_one(self, revision: Dict[str, Any], *, statement) -> None: + self._add_one(statement, 'revision', revision, self._revision_keys) + + @_prepared_statement('SELECT id FROM revision WHERE id IN ?') + def revision_get_ids(self, revision_ids, *, statement) -> ResultSet: + return self._execute_with_retries( + statement, [revision_ids]) + + @_prepared_statement('SELECT * FROM revision WHERE id IN ?') + def revision_get(self, revision_ids, *, statement) -> ResultSet: + return self._execute_with_retries( + statement, [revision_ids]) + + @_prepared_statement('SELECT * FROM revision WHERE token(id) > ? LIMIT 1') + def revision_get_random(self, *, statement) -> Optional[Row]: + return self._get_random_row(statement) + + ########################## + # 'revision_parent' table + ########################## + + _revision_parent_keys = ['id', 'parent_rank', 'parent_id'] + + @_prepared_insert_statement('revision_parent', _revision_parent_keys) + def revision_parent_add_one( + self, id_: Sha1Git, parent_rank: int, parent_id: Sha1Git, *, + statement) -> None: + self._execute_with_retries( + statement, [id_, parent_rank, parent_id]) + + @_prepared_statement('SELECT parent_id FROM revision_parent WHERE id = ?') + def revision_parent_get( + self, revision_id: Sha1Git, *, statement) -> ResultSet: + return self._execute_with_retries( + statement, [revision_id]) + + ########################## + # 'release' table + ########################## + + _release_keys = [ + 'id', 'target', 'target_type', 'date', 'name', 'message', 'author', + 'synthetic'] + + @_prepared_exists_statement('release') + def release_missing(self, ids: List[bytes], *, statement) -> List[bytes]: + return self._missing(statement, ids) + + @_prepared_insert_statement('release', _release_keys) + def release_add_one(self, release: Dict[str, Any], *, statement) -> None: + self._add_one(statement, 'release', release, self._release_keys) + + @_prepared_statement('SELECT * FROM release WHERE id in ?') + def release_get(self, release_ids: List[str], *, statement) -> None: + return self._execute_with_retries(statement, [release_ids]) + + @_prepared_statement('SELECT * FROM release WHERE token(id) > ? LIMIT 1') + def release_get_random(self, *, statement) -> Optional[Row]: + return self._get_random_row(statement) + + ########################## + # 'directory' table + ########################## + + _directory_keys = ['id'] + + @_prepared_exists_statement('directory') + def directory_missing(self, ids: List[bytes], *, statement) -> List[bytes]: + return self._missing(statement, ids) + + @_prepared_insert_statement('directory', _directory_keys) + def directory_add_one(self, directory_id: Sha1Git, *, statement) -> None: + """Called after all calls to directory_entry_add_one, to + commit/finalize the directory.""" + self._execute_with_retries(statement, [directory_id]) + self._increment_counter('directory', 1) + + @_prepared_statement('SELECT * FROM directory WHERE token(id) > ? LIMIT 1') + def directory_get_random(self, *, statement) -> Optional[Row]: + return self._get_random_row(statement) + + ########################## + # 'directory_entry' table + ########################## + + _directory_entry_keys = ['directory_id', 'name', 'type', 'target', 'perms'] + + @_prepared_insert_statement('directory_entry', _directory_entry_keys) + def directory_entry_add_one( + self, entry: Dict[str, Any], *, statement) -> None: + self._execute_with_retries( + statement, [entry[key] for key in self._directory_entry_keys]) + + @_prepared_statement('SELECT * FROM directory_entry ' + 'WHERE directory_id IN ?') + def directory_entry_get(self, directory_ids, *, statement) -> ResultSet: + return self._execute_with_retries( + statement, [directory_ids]) + + ########################## + # 'snapshot' table + ########################## + + _snapshot_keys = ['id'] + + @_prepared_exists_statement('snapshot') + def snapshot_missing(self, ids: List[bytes], *, statement) -> List[bytes]: + return self._missing(statement, ids) + + @_prepared_insert_statement('snapshot', _snapshot_keys) + def snapshot_add_one(self, snapshot_id: Sha1Git, *, statement) -> None: + self._execute_with_retries(statement, [snapshot_id]) + self._increment_counter('snapshot', 1) + + @_prepared_statement('SELECT * FROM snapshot ' + 'WHERE id = ?') + def snapshot_get(self, snapshot_id: Sha1Git, *, statement) -> ResultSet: + return self._execute_with_retries(statement, [snapshot_id]) + + @_prepared_statement('SELECT * FROM snapshot WHERE token(id) > ? LIMIT 1') + def snapshot_get_random(self, *, statement) -> Optional[Row]: + return self._get_random_row(statement) + + ########################## + # 'snapshot_branch' table + ########################## + + _snapshot_branch_keys = ['snapshot_id', 'name', 'target_type', 'target'] + + @_prepared_insert_statement('snapshot_branch', _snapshot_branch_keys) + def snapshot_branch_add_one( + self, branch: Dict[str, Any], *, statement) -> None: + self._execute_with_retries( + statement, [branch[key] for key in self._snapshot_branch_keys]) + + @_prepared_statement('SELECT ascii_bins_count(target_type) AS counts ' + 'FROM snapshot_branch ' + 'WHERE snapshot_id = ? ') + def snapshot_count_branches( + self, snapshot_id: Sha1Git, *, statement) -> ResultSet: + return self._execute_with_retries(statement, [snapshot_id]) + + @_prepared_statement('SELECT * FROM snapshot_branch ' + 'WHERE snapshot_id = ? AND name >= ?' + 'LIMIT ?') + def snapshot_branch_get( + self, snapshot_id: Sha1Git, from_: bytes, limit: int, *, + statement) -> None: + return self._execute_with_retries( + statement, [snapshot_id, from_, limit]) + + ########################## + # 'origin' table + ########################## + + origin_keys = ['sha1', 'url', 'type', 'next_visit_id'] + + @_prepared_statement('INSERT INTO origin (sha1, url, next_visit_id) ' + 'VALUES (?, ?, 1) IF NOT EXISTS') + def origin_add_one(self, origin: Dict[str, Any], *, statement) -> None: + self._execute_with_retries( + statement, [hash_url(origin['url']), origin['url']]) + self._increment_counter('origin', 1) + + @_prepared_statement('SELECT * FROM origin WHERE sha1 = ?') + def origin_get_by_sha1(self, sha1: bytes, *, statement) -> ResultSet: + return self._execute_with_retries(statement, [sha1]) + + def origin_get_by_url(self, url: str) -> ResultSet: + return self.origin_get_by_sha1(hash_url(url)) + + @_prepared_statement( + f'SELECT token(sha1) AS tok, {", ".join(origin_keys)} ' + f'FROM origin WHERE token(sha1) >= ? LIMIT ?') + def origin_list( + self, start_token: int, limit: int, *, statement) -> ResultSet: + return self._execute_with_retries( + statement, [start_token, limit]) + + @_prepared_statement('SELECT * FROM origin') + def origin_iter_all(self, *, statement) -> ResultSet: + return self._execute_with_retries(statement, []) + + @_prepared_statement('SELECT next_visit_id FROM origin WHERE sha1 = ?') + def _origin_get_next_visit_id( + self, origin_sha1: bytes, *, statement) -> int: + rows = list(self._execute_with_retries(statement, [origin_sha1])) + assert len(rows) == 1 # TODO: error handling + return rows[0].next_visit_id + + @_prepared_statement('UPDATE origin SET next_visit_id=? ' + 'WHERE sha1 = ? IF next_visit_id=?') + def origin_generate_unique_visit_id( + self, origin_url: str, *, statement) -> int: + origin_sha1 = hash_url(origin_url) + next_id = self._origin_get_next_visit_id(origin_sha1) + while True: + res = list(self._execute_with_retries( + statement, [next_id+1, origin_sha1, next_id])) + assert len(res) == 1 + if res[0].applied: + # No data race + return next_id + else: + # Someone else updated it before we did, let's try again + next_id = res[0].next_visit_id + # TODO: abort after too many attempts + + return next_id + + ########################## + # 'origin_visit' table + ########################## + + _origin_visit_keys = [ + 'origin', 'visit', 'type', 'date', 'status', 'metadata', 'snapshot'] + _origin_visit_update_keys = [ + 'type', 'date', 'status', 'metadata', 'snapshot'] + + @_prepared_statement('SELECT * FROM origin_visit ' + 'WHERE origin = ? AND visit > ?') + def _origin_visit_get_no_limit( + self, origin_url: str, last_visit: int, *, statement) -> ResultSet: + return self._execute_with_retries(statement, [origin_url, last_visit]) + + @_prepared_statement('SELECT * FROM origin_visit ' + 'WHERE origin = ? AND visit > ? LIMIT ?') + def _origin_visit_get_limit( + self, origin_url: str, last_visit: int, limit: int, *, statement + ) -> ResultSet: + return self._execute_with_retries( + statement, [origin_url, last_visit, limit]) + + def origin_visit_get( + self, origin_url: str, last_visit: Optional[int], + limit: Optional[int]) -> ResultSet: + if last_visit is None: + last_visit = -1 + + if limit is None: + return self._origin_visit_get_no_limit(origin_url, last_visit) + else: + return self._origin_visit_get_limit(origin_url, last_visit, limit) + + def origin_visit_update( + self, origin_url: str, visit_id: int, updates: Dict[str, Any] + ) -> None: + set_parts = [] + args: List[Any] = [] + for (column, value) in updates.items(): + set_parts.append(f'{column} = %s') + if column == 'metadata': + args.append(json.dumps(value)) + else: + args.append(value) + + if not set_parts: + return + + query = ('UPDATE origin_visit SET ' + ', '.join(set_parts) + + ' WHERE origin = %s AND visit = %s') + self._execute_with_retries( + query, args + [origin_url, visit_id]) + + @_prepared_insert_statement('origin_visit', _origin_visit_keys) + def origin_visit_add_one( + self, visit: Dict[str, Any], *, statement) -> None: + self._execute_with_retries( + statement, [visit[key] for key in self._origin_visit_keys]) + self._increment_counter('origin_visit', 1) + + @_prepared_statement( + 'UPDATE origin_visit SET ' + + ', '.join('%s = ?' % key for key in _origin_visit_update_keys) + + ' WHERE origin = ? AND visit = ?') + def origin_visit_upsert( + self, visit: Dict[str, Any], *, statement) -> None: + self._execute_with_retries( + statement, + [visit.get(key) for key in self._origin_visit_update_keys] + + [visit['origin'], visit['visit']]) + # TODO: check if there is already one + self._increment_counter('origin_visit', 1) + + @_prepared_statement('SELECT * FROM origin_visit ' + 'WHERE origin = ? AND visit = ?') + def origin_visit_get_one( + self, origin_url: str, visit_id: int, *, + statement) -> Optional[Row]: + # TODO: error handling + rows = list(self._execute_with_retries( + statement, [origin_url, visit_id])) + if rows: + return rows[0] + else: + return None + + @_prepared_statement('SELECT * FROM origin_visit ' + 'WHERE origin = ?') + def origin_visit_get_all(self, origin_url: str, *, statement) -> ResultSet: + return self._execute_with_retries( + statement, [origin_url]) + + @_prepared_statement('SELECT * FROM origin_visit WHERE origin = ?') + def origin_visit_get_latest( + self, origin: str, allowed_statuses: Optional[Iterable[str]], + require_snapshot: bool, *, statement) -> Optional[Row]: + # TODO: do the ordering and filtering in Cassandra + rows = list(self._execute_with_retries(statement, [origin])) + + rows.sort(key=lambda row: (row.date, row.visit), reverse=True) + + for row in rows: + if require_snapshot and row.snapshot is None: + continue + if allowed_statuses is not None \ + and row.status not in allowed_statuses: + continue + if row.snapshot is not None and \ + self.snapshot_missing([row.snapshot]): + raise ValueError('visit references unknown snapshot') + return row + else: + return None + + @_prepared_statement('SELECT * FROM origin_visit WHERE token(origin) >= ?') + def _origin_visit_iter_from( + self, min_token: int, *, statement) -> Generator[Row, None, None]: + yield from self._execute_with_retries(statement, [min_token]) + + @_prepared_statement('SELECT * FROM origin_visit WHERE token(origin) < ?') + def _origin_visit_iter_to( + self, max_token: int, *, statement) -> Generator[Row, None, None]: + yield from self._execute_with_retries(statement, [max_token]) + + def origin_visit_iter( + self, start_token: int) -> Generator[Row, None, None]: + """Returns all origin visits in order from this token, + and wraps around the token space.""" + yield from self._origin_visit_iter_from(start_token) + yield from self._origin_visit_iter_to(start_token) + + ########################## + # 'tool' table + ########################## + + _tool_keys = ['id', 'name', 'version', 'configuration'] + + @_prepared_insert_statement('tool_by_uuid', _tool_keys) + def tool_by_uuid_add_one(self, tool: Dict[str, Any], *, statement) -> None: + self._execute_with_retries( + statement, [tool[key] for key in self._tool_keys]) + + @_prepared_insert_statement('tool', _tool_keys) + def tool_add_one(self, tool: Dict[str, Any], *, statement) -> None: + self._execute_with_retries( + statement, [tool[key] for key in self._tool_keys]) + self._increment_counter('tool', 1) + + @_prepared_statement('SELECT id FROM tool ' + 'WHERE name = ? AND version = ? ' + 'AND configuration = ?') + def tool_get_one_uuid( + self, name: str, version: str, configuration: Dict[str, Any], *, + statement) -> Optional[str]: + rows = list(self._execute_with_retries( + statement, [name, version, configuration])) + if rows: + assert len(rows) == 1 + return rows[0].id + else: + return None + + ########################## + # Miscellaneous + ########################## + + @_prepared_statement('SELECT uuid() FROM revision LIMIT 1;') + def check_read(self, *, statement): + self._execute_with_retries(statement, []) + + @_prepared_statement('SELECT object_type, count FROM object_count ' + 'WHERE partition_key=0') + def stat_counters(self, *, statement) -> ResultSet: + return self._execute_with_retries( + statement, []) diff --git a/swh/storage/cassandra/schema.py b/swh/storage/cassandra/schema.py new file mode 100644 index 00000000..dc7e4249 --- /dev/null +++ b/swh/storage/cassandra/schema.py @@ -0,0 +1,196 @@ +# Copyright (C) 2019-2020 The Software Heritage developers +# See the AUTHORS file at the top-level directory of this distribution +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + + +CREATE_TABLES_QUERIES = ''' +CREATE OR REPLACE FUNCTION ascii_bins_count_sfunc ( + state tuple>, -- (nb_none, map) + bin_name ascii +) +CALLED ON NULL INPUT +RETURNS tuple> +LANGUAGE java AS +$$ + if (bin_name == null) { + state.setInt(0, state.getInt(0) + 1); + } + else { + Map counters = state.getMap( + 1, String.class, Integer.class); + Integer nb = counters.get(bin_name); + if (nb == null) { + nb = 0; + } + counters.put(bin_name, nb + 1); + state.setMap(1, counters, String.class, Integer.class); + } + return state; +$$ +; + +CREATE OR REPLACE AGGREGATE ascii_bins_count ( ascii ) +SFUNC ascii_bins_count_sfunc +STYPE tuple> +INITCOND (0, {}) +; + +CREATE TYPE IF NOT EXISTS microtimestamp ( + seconds bigint, + microseconds int +); + +CREATE TYPE IF NOT EXISTS microtimestamp_with_timezone ( + timestamp frozen, + offset smallint, + negative_utc boolean +); + +CREATE TYPE IF NOT EXISTS person ( + fullname blob, + name blob, + email blob +); + +CREATE TABLE IF NOT EXISTS content ( + sha1 blob, + sha1_git blob, + sha256 blob, + blake2s256 blob, + length bigint, + ctime timestamp, + -- creation time, i.e. time of (first) injection into the storage + status ascii, + PRIMARY KEY ((sha1, sha1_git, sha256, blake2s256)) +); + +CREATE TABLE IF NOT EXISTS revision ( + id blob PRIMARY KEY, + date microtimestamp_with_timezone, + committer_date microtimestamp_with_timezone, + type ascii, + directory blob, -- source code "root" directory + message blob, + author person, + committer person, + synthetic boolean, + -- true iff revision has been created by Software Heritage + metadata text + -- extra metadata as JSON(tarball checksums, + -- extra commit information, etc...) +); + +CREATE TABLE IF NOT EXISTS revision_parent ( + id blob, + parent_rank int, + -- parent position in merge commits, 0-based + parent_id blob, + PRIMARY KEY ((id), parent_rank) +); + +CREATE TABLE IF NOT EXISTS release +( + id blob PRIMARY KEY, + target_type ascii, + target blob, + date microtimestamp_with_timezone, + name blob, + message blob, + author person, + synthetic boolean, + -- true iff release has been created by Software Heritage +); + +CREATE TABLE IF NOT EXISTS directory ( + id blob PRIMARY KEY, +); + +CREATE TABLE IF NOT EXISTS directory_entry ( + directory_id blob, + name blob, -- path name, relative to containing dir + target blob, + perms int, -- unix-like permissions + type ascii, -- target type + PRIMARY KEY ((directory_id), name) +); + +CREATE TABLE IF NOT EXISTS snapshot ( + id blob PRIMARY KEY, +); + +-- For a given snapshot_id, branches are sorted by their name, +-- allowing easy pagination. +CREATE TABLE IF NOT EXISTS snapshot_branch ( + snapshot_id blob, + name blob, + target_type ascii, + target blob, + PRIMARY KEY ((snapshot_id), name) +); + +CREATE TABLE IF NOT EXISTS origin_visit ( + origin text, + visit bigint, + date timestamp, + type text, + status ascii, + metadata text, + snapshot blob, + PRIMARY KEY ((origin), visit) +); + + +CREATE TABLE IF NOT EXISTS origin ( + sha1 blob PRIMARY KEY, + url text, + type text, + next_visit_id int, + -- We need integer visit ids for compatibility with the pgsql + -- storage, so we're using lightweight transactions with this trick: + -- https://stackoverflow.com/a/29391877/539465 +); + + +CREATE TABLE IF NOT EXISTS tool_by_uuid ( + id timeuuid PRIMARY KEY, + name ascii, + version ascii, + configuration blob, +); + + +CREATE TABLE IF NOT EXISTS tool ( + id timeuuid, + name ascii, + version ascii, + configuration blob, + PRIMARY KEY ((name, version, configuration)) +) + + +CREATE TABLE IF NOT EXISTS object_count ( + partition_key smallint, -- Constant, must always be 0 + object_type ascii, + count counter, + PRIMARY KEY ((partition_key), object_type) +); +'''.split('\n\n') + +CONTENT_INDEX_TEMPLATE = ''' +CREATE TABLE IF NOT EXISTS content_by_{main_algo} ( + sha1 blob, + sha1_git blob, + sha256 blob, + blake2s256 blob, + PRIMARY KEY (({main_algo}), {other_algos}) +);''' + +HASH_ALGORITHMS = ['sha1', 'sha1_git', 'sha256', 'blake2s256'] + +for main_algo in HASH_ALGORITHMS: + CREATE_TABLES_QUERIES.append(CONTENT_INDEX_TEMPLATE.format( + main_algo=main_algo, + other_algos=', '.join( + [algo for algo in HASH_ALGORITHMS if algo != main_algo]) + )) diff --git a/swh/storage/cassandra/storage.py b/swh/storage/cassandra/storage.py new file mode 100644 index 00000000..92449780 --- /dev/null +++ b/swh/storage/cassandra/storage.py @@ -0,0 +1,952 @@ +# Copyright (C) 2019-2020 The Software Heritage developers +# See the AUTHORS file at the top-level directory of this distribution +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +import datetime +import json +import random +import re +from typing import Any, Dict, List, Optional +import uuid + +import attr +import dateutil + +from swh.model.model import ( + Revision, Release, Directory, DirectoryEntry, Content, OriginVisit, +) +from swh.objstorage import get_objstorage +from swh.objstorage.exc import ObjNotFoundError +try: + from swh.journal.writer import get_journal_writer +except ImportError: + get_journal_writer = None # type: ignore + # mypy limitation, see https://github.com/python/mypy/issues/1153 + + +from .common import TOKEN_BEGIN, TOKEN_END +from .converters import ( + revision_to_db, revision_from_db, release_to_db, release_from_db, +) +from .cql import CqlRunner +from .schema import HASH_ALGORITHMS + + +# Max block size of contents to return +BULK_BLOCK_CONTENT_LEN_MAX = 10000 + + +def now(): + return datetime.datetime.now(tz=datetime.timezone.utc) + + +class CassandraStorage: + def __init__(self, hosts, keyspace, objstorage, + port=9042, journal_writer=None): + self._cql_runner = CqlRunner(hosts, keyspace, port) + + self.objstorage = get_objstorage(**objstorage) + + if journal_writer: + self.journal_writer = get_journal_writer(**journal_writer) + else: + self.journal_writer = None + + def check_config(self, *, check_write): + self._cql_runner.check_read() + + return True + + def _content_add(self, contents, with_data): + contents = [Content.from_dict(c) for c in contents] + + # Filter-out content already in the database. + contents = [c for c in contents + if not self._cql_runner.content_get_from_pk(c.to_dict())] + + if self.journal_writer: + for content in contents: + content = content.to_dict() + if 'data' in content: + del content['data'] + self.journal_writer.write_addition('content', content) + + count_contents = 0 + count_content_added = 0 + count_content_bytes_added = 0 + + for content in contents: + # First insert to the objstorage, if the endpoint is + # `content_add` (as opposed to `content_add_metadata`). + # TODO: this should probably be done in concurrently to inserting + # in index tables (but still before the main table; so an entry is + # only added to the main table after everything else was + # successfully inserted. + count_contents += 1 + if content.status != 'absent': + count_content_added += 1 + if with_data: + content_data = content.data + count_content_bytes_added += len(content_data) + self.objstorage.add(content_data, content.sha1) + + # Then add to index tables + for algo in HASH_ALGORITHMS: + self._cql_runner.content_index_add_one(algo, content) + + # Then to the main table + self._cql_runner.content_add_one(content) + + # Note that we check for collisions *after* inserting. This + # differs significantly from the pgsql storage, but checking + # before insertion does not provide any guarantee in case + # another thread inserts the colliding hash at the same time. + # + # The proper way to do it would probably be a BATCH, but this + # would be inefficient because of the number of partitions we + # need to affect (len(HASH_ALGORITHMS)+1, which is currently 5) + for algo in {'sha1', 'sha1_git'}: + pks = self._cql_runner.content_get_pks_from_single_hash( + algo, content.get_hash(algo)) + if len(pks) > 1: + # There are more than the one we just inserted. + from .. import HashCollision + raise HashCollision(algo, content.get_hash(algo), pks) + + summary = { + 'content:add': count_content_added, + 'skipped_content:add': count_contents - count_content_added, + } + + if with_data: + summary['content:add:bytes'] = count_content_bytes_added + + return summary + + def content_add(self, content): + content = [c.copy() for c in content] # semi-shallow copy + for item in content: + item['ctime'] = now() + return self._content_add(content, with_data=True) + + def content_update(self, content, keys=[]): + raise NotImplementedError( + 'content_update is not supported by the Cassandra backend') + + def content_add_metadata(self, content): + return self._content_add(content, with_data=False) + + def content_get(self, content): + if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: + raise ValueError( + "Sending at most %s contents." % BULK_BLOCK_CONTENT_LEN_MAX) + for obj_id in content: + try: + data = self.objstorage.get(obj_id) + except ObjNotFoundError: + yield None + continue + + yield {'sha1': obj_id, 'data': data} + + def content_get_partition( + self, partition_id: int, nb_partitions: int, limit: int = 1000, + page_token: str = None): + if limit is None: + raise ValueError('Development error: limit should not be None') + + # Compute start and end of the range of tokens covered by the + # requested partition + partition_size = (TOKEN_END-TOKEN_BEGIN)//nb_partitions + range_start = TOKEN_BEGIN + partition_id*partition_size + range_end = TOKEN_BEGIN + (partition_id+1)*partition_size + + # offset the range start according to the `page_token`. + if page_token is not None: + if not (range_start <= int(page_token) <= range_end): + raise ValueError('Invalid page_token.') + range_start = int(page_token) + + # Get the first rows of the range + rows = self._cql_runner.content_get_token_range( + range_start, range_end, limit) + rows = list(rows) + + if len(rows) == limit: + next_page_token: Optional[str] = str(rows[-1].tok+1) + else: + next_page_token = None + + return { + 'contents': [row._asdict() for row in rows + if row.status != 'absent'], + 'next_page_token': next_page_token, + } + + def content_get_metadata( + self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: + result: Dict[bytes, List[Dict]] = {sha1: [] for sha1 in contents} + for sha1 in contents: + # Get all (sha1, sha1_git, sha256, blake2s256) whose sha1 + # matches the argument, from the index table ('content_by_sha1') + pks = self._cql_runner.content_get_pks_from_single_hash( + 'sha1', sha1) + + if pks: + # TODO: what to do if there are more than one? + pk = pks[0] + + # Query the main table ('content') + res = self._cql_runner.content_get_from_pk(pk._asdict()) + + # Rows in 'content' are inserted after corresponding + # rows in 'content_by_*', so we might be missing it + if res: + content_metadata = res._asdict() + content_metadata.pop('ctime') + result[content_metadata['sha1']].append(content_metadata) + return result + + def skipped_content_missing(self, contents): + # TODO + raise NotImplementedError('not yet supported for Cassandra') + + def content_find(self, content): + # Find an algorithm that is common to all the requested contents. + # It will be used to do an initial filtering efficiently. + filter_algos = list(set(content).intersection(HASH_ALGORITHMS)) + if not filter_algos: + raise ValueError('content keys must contain at least one of: ' + '%s' % ', '.join(sorted(HASH_ALGORITHMS))) + common_algo = filter_algos[0] + + # Find all contents whose common_algo matches at least one + # of the requests. + found_pks = self._cql_runner.content_get_pks_from_single_hash( + common_algo, content[common_algo]) + found_pks = [pk._asdict() for pk in found_pks] + + # Filter with the other hash algorithms. + for algo in filter_algos[1:]: + found_pks = [pk for pk in found_pks if pk[algo] == content[algo]] + + results = [] + for pk in found_pks: + # Query the main table ('content'). + res = self._cql_runner.content_get_from_pk(pk) + + # Rows in 'content' are inserted after corresponding + # rows in 'content_by_*', so we might be missing it + if res: + results.append({ + **res._asdict(), + 'ctime': res.ctime.replace(tzinfo=datetime.timezone.utc) + }) + return results + + def content_missing(self, content, key_hash='sha1'): + for cont in content: + res = self.content_find(cont) + if not res: + yield cont[key_hash] + if any(c['status'] == 'missing' for c in res): + yield cont[key_hash] + + def content_missing_per_sha1(self, contents): + return self.content_missing([{'sha1': c for c in contents}]) + + def content_missing_per_sha1_git(self, contents): + return self.content_missing([{'sha1_git': c for c in contents}], + key_hash='sha1_git') + + def content_get_random(self): + return self._cql_runner.content_get_random().sha1_git + + def directory_add(self, directories): + directories = list(directories) + + # Filter out directories that are already inserted. + missing = self.directory_missing([dir_['id'] for dir_ in directories]) + directories = [dir_ for dir_ in directories if dir_['id'] in missing] + + if self.journal_writer: + self.journal_writer.write_additions('directory', directories) + + for directory in directories: + directory = Directory.from_dict(directory) + + # Add directory entries to the 'directory_entry' table + for entry in directory.entries: + entry = entry.to_dict() + entry['directory_id'] = directory.id + self._cql_runner.directory_entry_add_one(entry) + + # Add the directory *after* adding all the entries, so someone + # calling snapshot_get_branch in the meantime won't end up + # with half the entries. + self._cql_runner.directory_add_one(directory.id) + + return {'directory:add': len(missing)} + + def directory_missing(self, directories): + return self._cql_runner.directory_missing(directories) + + def _join_dentry_to_content(self, dentry): + keys = ( + 'status', + 'sha1', + 'sha1_git', + 'sha256', + 'length', + ) + ret = dict.fromkeys(keys) + ret.update(dentry.to_dict()) + if ret['type'] == 'file': + content = self.content_find({'sha1_git': ret['target']}) + if content: + content = content[0] + for key in keys: + ret[key] = content[key] + return ret + + def _directory_ls(self, directory_id, recursive, prefix=b''): + if self.directory_missing([directory_id]): + return + rows = list(self._cql_runner.directory_entry_get([directory_id])) + + for row in rows: + # Build and yield the directory entry dict + entry = row._asdict() + del entry['directory_id'] + entry = DirectoryEntry.from_dict(entry) + ret = self._join_dentry_to_content(entry) + ret['name'] = prefix + ret['name'] + ret['dir_id'] = directory_id + yield ret + + if recursive and ret['type'] == 'dir': + yield from self._directory_ls( + ret['target'], True, prefix + ret['name'] + b'/') + + def directory_entry_get_by_path(self, directory, paths): + return self._directory_entry_get_by_path(directory, paths, b'') + + def _directory_entry_get_by_path(self, directory, paths, prefix): + if not paths: + return + + contents = list(self.directory_ls(directory)) + + if not contents: + return + + def _get_entry(entries, name): + """Finds the entry with the requested name, prepends the + prefix (to get its full path), and returns it. + + If no entry has that name, returns None.""" + for entry in entries: + if entry['name'] == name: + entry = entry.copy() + entry['name'] = prefix + entry['name'] + return entry + + first_item = _get_entry(contents, paths[0]) + + if len(paths) == 1: + return first_item + + if not first_item or first_item['type'] != 'dir': + return + + return self._directory_entry_get_by_path( + first_item['target'], paths[1:], prefix + paths[0] + b'/') + + def directory_ls(self, directory, recursive=False): + yield from self._directory_ls(directory, recursive) + + def directory_get_random(self): + return self._cql_runner.directory_get_random().id + + def revision_add(self, revisions): + revisions = list(revisions) + + # Filter-out revisions already in the database + missing = self.revision_missing([rev['id'] for rev in revisions]) + revisions = [rev for rev in revisions if rev['id'] in missing] + + if self.journal_writer: + self.journal_writer.write_additions('revision', revisions) + + for revision in revisions: + revision = revision_to_db(revision) + + if revision: + # Add parents first + for (rank, parent) in enumerate(revision.parents): + self._cql_runner.revision_parent_add_one( + revision.id, rank, parent) + + # Then write the main revision row. + # Writing this after all parents were written ensures that + # read endpoints don't return a partial view while writing + # the parents + self._cql_runner.revision_add_one(revision) + + return {'revision:add': len(revisions)} + + def revision_missing(self, revisions): + return self._cql_runner.revision_missing(revisions) + + def revision_get(self, revisions): + rows = self._cql_runner.revision_get(revisions) + revs = {} + for row in rows: + # TODO: use a single query to get all parents? + # (it might have lower latency, but requires more code and more + # bandwidth, because revision id would be part of each returned + # row) + parent_rows = self._cql_runner.revision_parent_get(row.id) + # parent_rank is the clustering key, so results are already + # sorted by rank. + parents = [row.parent_id for row in parent_rows] + + rev = Revision(**row._asdict(), parents=parents) + + rev = revision_from_db(rev) + revs[rev.id] = rev.to_dict() + + for rev_id in revisions: + yield revs.get(rev_id) + + def _get_parent_revs(self, rev_ids, seen, limit, short): + if limit and len(seen) >= limit: + return + rev_ids = [id_ for id_ in rev_ids if id_ not in seen] + if not rev_ids: + return + seen |= set(rev_ids) + + # We need this query, even if short=True, to return consistent + # results (ie. not return only a subset of a revision's parents + # if it is being written) + if short: + rows = self._cql_runner.revision_get_ids(rev_ids) + else: + rows = self._cql_runner.revision_get(rev_ids) + + for row in rows: + # TODO: use a single query to get all parents? + # (it might have less latency, but requires less code and more + # bandwidth (because revision id would be part of each returned + # row) + parent_rows = self._cql_runner.revision_parent_get(row.id) + + # parent_rank is the clustering key, so results are already + # sorted by rank. + parents = [row.parent_id for row in parent_rows] + + if short: + yield (row.id, parents) + else: + rev = revision_from_db(Revision( + **row._asdict(), parents=parents)) + yield rev.to_dict() + yield from self._get_parent_revs(parents, seen, limit, short) + + def revision_log(self, revisions, limit=None): + seen = set() + yield from self._get_parent_revs(revisions, seen, limit, False) + + def revision_shortlog(self, revisions, limit=None): + seen = set() + yield from self._get_parent_revs(revisions, seen, limit, True) + + def revision_get_random(self): + return self._cql_runner.revision_get_random().id + + def release_add(self, releases): + releases = list(releases) + missing = self.release_missing([rel['id'] for rel in releases]) + releases = [rel for rel in releases if rel['id'] in missing] + + if self.journal_writer: + self.journal_writer.write_additions('release', releases) + + for release in releases: + release = release_to_db(release) + + if release: + self._cql_runner.release_add_one(release) + + return {'release:add': len(missing)} + + def release_missing(self, releases): + return self._cql_runner.release_missing(releases) + + def release_get(self, releases): + rows = self._cql_runner.release_get(releases) + rels = {} + for row in rows: + release = Release(**row._asdict()) + release = release_from_db(release) + rels[row.id] = release.to_dict() + + for rel_id in releases: + yield rels.get(rel_id) + + def release_get_random(self): + return self._cql_runner.release_get_random().id + + def snapshot_add(self, snapshots): + snapshots = list(snapshots) + missing = self._cql_runner.snapshot_missing( + [snp['id'] for snp in snapshots]) + snapshots = [snp for snp in snapshots if snp['id'] in missing] + + for snapshot in snapshots: + if self.journal_writer: + self.journal_writer.write_addition('snapshot', snapshot) + + # Add branches + for (branch_name, branch) in snapshot['branches'].items(): + if branch is None: + branch = {'target_type': None, 'target': None} + self._cql_runner.snapshot_branch_add_one({ + 'snapshot_id': snapshot['id'], + 'name': branch_name, + 'target_type': branch['target_type'], + 'target': branch['target'], + }) + + # Add the snapshot *after* adding all the branches, so someone + # calling snapshot_get_branch in the meantime won't end up + # with half the branches. + self._cql_runner.snapshot_add_one(snapshot['id']) + + return {'snapshot:add': len(snapshots)} + + def snapshot_missing(self, snapshots): + return self._cql_runner.snapshot_missing(snapshots) + + def snapshot_get(self, snapshot_id): + return self.snapshot_get_branches(snapshot_id) + + def snapshot_get_by_origin_visit(self, origin, visit): + try: + visit = self._cql_runner.origin_visit_get_one(origin, visit) + except IndexError: + return None + + return self.snapshot_get(visit.snapshot) + + def snapshot_get_latest(self, origin, allowed_statuses=None): + visit = self.origin_visit_get_latest( + origin, + allowed_statuses=allowed_statuses, + require_snapshot=True) + + if visit: + assert visit['snapshot'] + if self._cql_runner.snapshot_missing([visit['snapshot']]): + raise ValueError('Visit references unknown snapshot') + return self.snapshot_get_branches(visit['snapshot']) + + def snapshot_count_branches(self, snapshot_id): + if self._cql_runner.snapshot_missing([snapshot_id]): + # Makes sure we don't fetch branches for a snapshot that is + # being added. + return None + rows = list(self._cql_runner.snapshot_count_branches(snapshot_id)) + assert len(rows) == 1 + (nb_none, counts) = rows[0].counts + counts = dict(counts) + if nb_none: + counts[None] = nb_none + return counts + + def snapshot_get_branches(self, snapshot_id, branches_from=b'', + branches_count=1000, target_types=None): + if self._cql_runner.snapshot_missing([snapshot_id]): + # Makes sure we don't fetch branches for a snapshot that is + # being added. + return None + + branches = [] + while len(branches) < branches_count+1: + new_branches = list(self._cql_runner.snapshot_branch_get( + snapshot_id, branches_from, branches_count+1)) + + if not new_branches: + break + + branches_from = new_branches[-1].name + + new_branches_filtered = new_branches + + # Filter by target_type + if target_types: + new_branches_filtered = [ + branch for branch in new_branches_filtered + if branch.target is not None + and branch.target_type in target_types] + + branches.extend(new_branches_filtered) + + if len(new_branches) < branches_count+1: + break + + if len(branches) > branches_count: + last_branch = branches.pop(-1).name + else: + last_branch = None + + branches = { + branch.name: { + 'target': branch.target, + 'target_type': branch.target_type, + } if branch.target else None + for branch in branches + } + + return { + 'id': snapshot_id, + 'branches': branches, + 'next_branch': last_branch, + } + + def snapshot_get_random(self): + return self._cql_runner.snapshot_get_random().id + + def object_find_by_sha1_git(self, ids): + results = {id_: [] for id_ in ids} + missing_ids = set(ids) + + # Mind the order, revision is the most likely one for a given ID, + # so we check revisions first. + queries = [ + ('revision', self._cql_runner.revision_missing), + ('release', self._cql_runner.release_missing), + ('content', self._cql_runner.content_missing_by_sha1_git), + ('directory', self._cql_runner.directory_missing), + ] + + for (object_type, query_fn) in queries: + found_ids = missing_ids - set(query_fn(missing_ids)) + for sha1_git in found_ids: + results[sha1_git].append({ + 'sha1_git': sha1_git, + 'type': object_type, + }) + missing_ids.remove(sha1_git) + + if not missing_ids: + # We found everything, skipping the next queries. + break + + return results + + def origin_get(self, origins): + if isinstance(origins, dict): + # Old API + return_single = True + origins = [origins] + else: + return_single = False + + if any('id' in origin for origin in origins): + raise ValueError('Origin ids are not supported.') + + results = [self.origin_get_one(origin) for origin in origins] + + if return_single: + assert len(results) == 1 + return results[0] + else: + return results + + def origin_get_one(self, origin): + if 'id' in origin: + raise ValueError('Origin ids are not supported.') + rows = self._cql_runner.origin_get_by_url(origin['url']) + + rows = list(rows) + if rows: + assert len(rows) == 1 + result = rows[0]._asdict() + return { + 'url': result['url'], + } + else: + return None + + def origin_get_by_sha1(self, sha1s): + results = [] + for sha1 in sha1s: + rows = self._cql_runner.origin_get_by_sha1(sha1) + if rows: + results.append({'url': rows.one().url}) + else: + results.append(None) + return results + + def origin_list(self, page_token: Optional[str] = None, limit: int = 100 + ) -> dict: + # Compute what token to begin the listing from + start_token = TOKEN_BEGIN + if page_token: + start_token = int(page_token) + if not (TOKEN_BEGIN <= start_token <= TOKEN_END): + raise ValueError('Invalid page_token.') + + rows = self._cql_runner.origin_list(start_token, limit) + rows = list(rows) + + if len(rows) == limit: + next_page_token: Optional[str] = str(rows[-1].tok+1) + else: + next_page_token = None + + return { + 'origins': [{'url': row.url} for row in rows], + 'next_page_token': next_page_token, + } + + def origin_search(self, url_pattern, offset=0, limit=50, + regexp=False, with_visit=False): + # TODO: remove this endpoint, swh-search should be used instead. + origins = self._cql_runner.origin_iter_all() + if regexp: + pat = re.compile(url_pattern) + origins = [orig for orig in origins if pat.search(orig.url)] + else: + origins = [orig for orig in origins if url_pattern in orig.url] + + if with_visit: + origins = [orig for orig in origins + if orig.next_visit_id > 1] + + return [ + { + 'url': orig.url, + } + for orig in origins[offset:offset+limit]] + + def origin_add(self, origins): + origins = list(origins) + if any('id' in origin for origin in origins): + raise ValueError('Origins must not already have an id.') + results = [] + for origin in origins: + self.origin_add_one(origin) + results.append(origin) + return results + + def origin_add_one(self, origin): + known_origin = self.origin_get_one(origin) + + if known_origin: + origin_url = known_origin['url'] + else: + if self.journal_writer: + self.journal_writer.write_addition('origin', origin) + + self._cql_runner.origin_add_one(origin) + origin_url = origin['url'] + + return origin_url + + def origin_visit_add(self, origin, date, type): + origin_url = origin # TODO: rename the argument + + if isinstance(date, str): + date = dateutil.parser.parse(date) + + origin = self.origin_get_one({'url': origin_url}) + + if not origin: + return None + + visit_id = self._cql_runner.origin_generate_unique_visit_id(origin_url) + + visit = { + 'origin': origin_url, + 'date': date, + 'type': type, + 'status': 'ongoing', + 'snapshot': None, + 'metadata': None, + 'visit': visit_id + } + + if self.journal_writer: + self.journal_writer.write_addition('origin_visit', visit) + + self._cql_runner.origin_visit_add_one(visit) + + return { + 'origin': origin_url, + 'visit': visit_id, + } + + def origin_visit_update(self, origin, visit_id, status=None, + metadata=None, snapshot=None): + origin_url = origin # TODO: rename the argument + + # Get the existing data of the visit + row = self._cql_runner.origin_visit_get_one(origin_url, visit_id) + if not row: + raise ValueError('This origin visit does not exist.') + visit = OriginVisit.from_dict(self._format_origin_visit_row(row)) + + updates = {} + if status: + updates['status'] = status + if metadata: + updates['metadata'] = metadata + if snapshot: + updates['snapshot'] = snapshot + + visit = attr.evolve(visit, **updates) + + if self.journal_writer: + self.journal_writer.write_update('origin_visit', visit) + + self._cql_runner.origin_visit_update(origin_url, visit_id, updates) + + def origin_visit_upsert(self, visits): + visits = [visit.copy() for visit in visits] + for visit in visits: + if isinstance(visit['date'], str): + visit['date'] = dateutil.parser.parse(visit['date']) + + if self.journal_writer: + for visit in visits: + self.journal_writer.write_addition('origin_visit', visit) + + for visit in visits: + visit = visit.copy() + if visit.get('metadata'): + visit['metadata'] = json.dumps(visit['metadata']) + self._cql_runner.origin_visit_upsert(visit) + + @staticmethod + def _format_origin_visit_row(visit): + return { + **visit._asdict(), + 'origin': visit.origin, + 'date': visit.date.replace(tzinfo=datetime.timezone.utc), + 'metadata': (json.loads(visit.metadata) + if visit.metadata else None), + } + + def origin_visit_get(self, origin, last_visit=None, limit=None): + rows = self._cql_runner.origin_visit_get(origin, last_visit, limit) + + yield from map(self._format_origin_visit_row, rows) + + def origin_visit_find_by_date(self, origin, visit_date): + # Iterator over all the visits of the origin + # This should be ok for now, as there aren't too many visits + # per origin. + visits = list(self._cql_runner.origin_visit_get_all(origin)) + + def key(visit): + dt = visit.date.replace(tzinfo=datetime.timezone.utc) - visit_date + return (abs(dt), -visit.visit) + + if visits: + visit = min(visits, key=key) + return visit._asdict() + + def origin_visit_get_by(self, origin, visit): + visit = self._cql_runner.origin_visit_get_one(origin, visit) + if visit: + return self._format_origin_visit_row(visit) + + def origin_visit_get_latest( + self, origin, allowed_statuses=None, require_snapshot=False): + visit = self._cql_runner.origin_visit_get_latest( + origin, + allowed_statuses=allowed_statuses, + require_snapshot=require_snapshot) + if visit: + return self._format_origin_visit_row(visit) + + def origin_visit_get_random(self, type: str) -> Optional[Dict[str, Any]]: + back_in_the_day = now() - datetime.timedelta(weeks=12) # 3 months back + + # Random position to start iteration at + start_token = random.randint(TOKEN_BEGIN, TOKEN_END) + + # Iterator over all visits, ordered by token(origins) then visit_id + rows = self._cql_runner.origin_visit_iter(start_token) + for row in rows: + visit = self._format_origin_visit_row(row) + if visit['date'] > back_in_the_day \ + and visit['status'] == 'full': + return visit + else: + return None + + def tool_add(self, tools): + inserted = [] + for tool in tools: + tool = tool.copy() + tool_json = tool.copy() + tool_json['configuration'] = json.dumps( + tool['configuration'], sort_keys=True).encode() + id_ = self._cql_runner.tool_get_one_uuid(**tool_json) + if not id_: + id_ = uuid.uuid1() + tool_json['id'] = id_ + self._cql_runner.tool_by_uuid_add_one(tool_json) + self._cql_runner.tool_add_one(tool_json) + tool['id'] = id_ + inserted.append(tool) + return inserted + + def tool_get(self, tool): + id_ = self._cql_runner.tool_get_one_uuid( + tool['name'], tool['version'], + json.dumps(tool['configuration'], sort_keys=True).encode()) + if id_: + tool = tool.copy() + tool['id'] = id_ + return tool + else: + return None + + def stat_counters(self): + rows = self._cql_runner.stat_counters() + keys = ( + 'content', 'directory', 'origin', 'origin_visit', + 'release', 'revision', 'skipped_content', 'snapshot') + stats = {key: 0 for key in keys} + stats.update({row.object_type: row.count for row in rows}) + return stats + + def refresh_stat_counters(self): + pass + + def origin_metadata_add(self, origin_url, ts, provider, tool, metadata): + # TODO + raise NotImplementedError('not yet supported for Cassandra') + + def origin_metadata_get_by(self, origin_url, provider_type=None): + # TODO + raise NotImplementedError('not yet supported for Cassandra') + + def metadata_provider_add(self, provider_name, provider_type, provider_url, + metadata): + # TODO + raise NotImplementedError('not yet supported for Cassandra') + + def metadata_provider_get(self, provider_id): + # TODO + raise NotImplementedError('not yet supported for Cassandra') + + def metadata_provider_get_by(self, provider): + # TODO + raise NotImplementedError('not yet supported for Cassandra') diff --git a/swh/storage/tests/test_cassandra.py b/swh/storage/tests/test_cassandra.py new file mode 100644 index 00000000..565881bd --- /dev/null +++ b/swh/storage/tests/test_cassandra.py @@ -0,0 +1,260 @@ +# Copyright (C) 2018-2019 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 + +import os +import signal +import socket +import subprocess +import time + +import pytest + +from swh.storage import get_storage +from swh.storage.cassandra import create_keyspace + +from swh.storage.tests.test_storage import TestStorage as _TestStorage +from swh.storage.tests.test_storage import TestStorageGeneratedData \ + as _TestStorageGeneratedData + + +CONFIG_TEMPLATE = ''' +data_file_directories: + - {data_dir}/data +commitlog_directory: {data_dir}/commitlog +hints_directory: {data_dir}/hints +saved_caches_directory: {data_dir}/saved_caches + +commitlog_sync: periodic +commitlog_sync_period_in_ms: 1000000 +partitioner: org.apache.cassandra.dht.Murmur3Partitioner +endpoint_snitch: SimpleSnitch +seed_provider: + - class_name: org.apache.cassandra.locator.SimpleSeedProvider + parameters: + - seeds: "127.0.0.1" + +storage_port: {storage_port} +native_transport_port: {native_transport_port} +start_native_transport: true +listen_address: 127.0.0.1 + +enable_user_defined_functions: true +''' + + +def free_port(): + sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + sock.bind(('127.0.0.1', 0)) + port = sock.getsockname()[1] + sock.close() + return port + + +def wait_for_peer(addr, port): + wait_until = time.time() + 20 + while time.time() < wait_until: + try: + sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + sock.connect((addr, port)) + except ConnectionRefusedError: + time.sleep(0.1) + else: + sock.close() + return True + return False + + +@pytest.fixture(scope='session') +def cassandra_cluster(tmpdir_factory): + cassandra_conf = tmpdir_factory.mktemp('cassandra_conf') + cassandra_data = tmpdir_factory.mktemp('cassandra_data') + cassandra_log = tmpdir_factory.mktemp('cassandra_log') + native_transport_port = free_port() + storage_port = free_port() + jmx_port = free_port() + + with open(str(cassandra_conf.join('cassandra.yaml')), 'w') as fd: + fd.write(CONFIG_TEMPLATE.format( + data_dir=str(cassandra_data), + storage_port=storage_port, + native_transport_port=native_transport_port, + )) + + if os.environ.get('LOG_CASSANDRA'): + stdout = stderr = None + else: + stdout = stderr = subprocess.DEVNULL + proc = subprocess.Popen( + [ + '/usr/sbin/cassandra', + '-Dcassandra.config=file://%s/cassandra.yaml' % cassandra_conf, + '-Dcassandra.logdir=%s' % cassandra_log, + '-Dcassandra.jmx.local.port=%d' % jmx_port, + '-Dcassandra-foreground=yes', + ], + start_new_session=True, + env={ + 'MAX_HEAP_SIZE': '300M', + 'HEAP_NEWSIZE': '50M', + 'JVM_OPTS': '-Xlog:gc=error:file=%s/gc.log' % cassandra_log, + }, + stdout=stdout, + stderr=stderr, + ) + + running = wait_for_peer('127.0.0.1', native_transport_port) + + if running: + yield (['127.0.0.1'], native_transport_port) + + if not running or os.environ.get('LOG_CASSANDRA'): + with open(str(cassandra_log.join('debug.log'))) as fd: + print(fd.read()) + + if not running: + raise Exception('cassandra process stopped unexpectedly.') + + pgrp = os.getpgid(proc.pid) + os.killpg(pgrp, signal.SIGKILL) + + +class RequestHandler: + def on_request(self, rf): + if hasattr(rf.message, 'query'): + print() + print(rf.message.query) + + +# tests are executed using imported classes (TestStorage and +# TestStorageGeneratedData) using overloaded swh_storage fixture +# below + +@pytest.fixture +def swh_storage(cassandra_cluster): + (hosts, port) = cassandra_cluster + keyspace = os.urandom(10).hex() + + create_keyspace(hosts, keyspace, port) + + storage = get_storage( + 'cassandra', + hosts=hosts, port=port, + keyspace=keyspace, + journal_writer={ + 'cls': 'memory', + }, + objstorage={ + 'cls': 'memory', + 'args': {}, + }, + ) + + yield storage + + storage._cql_runner._session.execute( + 'DROP KEYSPACE "%s"' % keyspace) + + +@pytest.mark.cassandra +class TestCassandraStorage(_TestStorage): + @pytest.mark.skip('content_update is not yet implemented for Cassandra') + def test_content_update(self): + pass + + @pytest.mark.skip( + 'not implemented, see https://forge.softwareheritage.org/T1633') + def test_skipped_content_add(self): + pass + + @pytest.mark.skip( + 'The "person" table of the pgsql is a legacy thing, and not ' + 'supported by the cassandra backend.') + def test_person_fullname_unicity(self): + pass + + @pytest.mark.skip( + 'The "person" table of the pgsql is a legacy thing, and not ' + 'supported by the cassandra backend.') + def test_person_get(self): + pass + + @pytest.mark.skip('Not yet implemented') + def test_metadata_provider_add(self): + pass + + @pytest.mark.skip('Not yet implemented') + def test_metadata_provider_get(self): + pass + + @pytest.mark.skip('Not yet implemented') + def test_metadata_provider_get_by(self): + pass + + @pytest.mark.skip('Not yet implemented') + def test_origin_metadata_add(self): + pass + + @pytest.mark.skip('Not yet implemented') + def test_origin_metadata_get(self): + pass + + @pytest.mark.skip('Not yet implemented') + def test_origin_metadata_get_by_provider_type(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_origin_count(self): + pass + + +@pytest.mark.cassandra +class TestCassandraStorageGeneratedData(_TestStorageGeneratedData): + @pytest.mark.skip('Not supported by Cassandra') + def test_origin_count(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_origin_get_range(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_origin_get_range_from_zero(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_generate_content_get_range_limit(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_generate_content_get_range_no_limit(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_generate_content_get_range(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_generate_content_get_range_empty(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_generate_content_get_range_limit_none(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_generate_content_get_range_full(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_origin_count_with_visit_no_visits(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_origin_count_with_visit_with_visits_and_snapshot(self): + pass + + @pytest.mark.skip('Not supported by Cassandra') + def test_origin_count_with_visit_with_visits_no_snapshot(self): + pass diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index af91aaa6..94e70961 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,3782 +1,3803 @@ # 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 copy from contextlib import contextmanager import datetime import inspect import itertools import math import queue import random import threading from collections import defaultdict from datetime import timedelta from unittest.mock import Mock import psycopg2 import pytest from hypothesis import given, strategies, settings, HealthCheck from typing import ClassVar, Optional from swh.model import from_disk, identifiers from swh.model.hashutil import hash_to_bytes from swh.model.hypothesis_strategies import objects from swh.storage import HashCollision from swh.storage.converters import origin_url_to_sha1 as sha1 from swh.storage.interface import StorageInterface from .storage_data import data @contextmanager def db_transaction(storage): with storage.db() as db: with db.transaction() as cur: yield db, cur def normalize_entity(entity): entity = copy.deepcopy(entity) for key in ('date', 'committer_date'): if key in entity: entity[key] = identifiers.normalize_timestamp(entity[key]) return entity def transform_entries(dir_, *, prefix=b''): for ent in dir_['entries']: yield { 'dir_id': dir_['id'], 'type': ent['type'], 'target': ent['target'], 'name': prefix + ent['name'], 'perms': ent['perms'], 'status': None, 'sha1': None, 'sha1_git': None, 'sha256': None, 'length': None, } def cmpdir(directory): return (directory['type'], directory['dir_id']) def short_revision(revision): return [revision['id'], revision['parents']] def assert_contents_ok(expected_contents, actual_contents, keys_to_check={'sha1', 'data'}): """Assert that a given list of contents matches on a given set of keys. """ for k in keys_to_check: expected_list = set([c.get(k) for c in expected_contents]) actual_list = set([c.get(k) for c in actual_contents]) assert actual_list == expected_list, k class TestStorage: """Main class for Storage testing. This class is used as-is to test local storage (see TestLocalStorage below) and remote storage (see TestRemoteStorage in test_remote_storage.py. We need to have the two classes inherit from this base class separately to avoid nosetests running the tests from the base class twice. """ maxDiff = None # type: ClassVar[Optional[int]] def test_types(self, swh_storage): """Checks all methods of StorageInterface are implemented by this backend, and that they have the same signature.""" # Create an instance of the protocol (which cannot be instantiated # directly, so this creates a subclass, then instantiates it) interface = type('_', (StorageInterface,), {})() assert 'content_add' in dir(interface) missing_methods = [] for meth_name in dir(interface): if meth_name.startswith('_'): continue interface_meth = getattr(interface, meth_name) try: concrete_meth = getattr(swh_storage, meth_name) except AttributeError: if not getattr(interface_meth, 'deprecated_endpoint', False): # The backend is missing a (non-deprecated) endpoint missing_methods.append(meth_name) continue expected_signature = inspect.signature(interface_meth) actual_signature = inspect.signature(concrete_meth) assert expected_signature == actual_signature, meth_name assert missing_methods == [] def test_check_config(self, swh_storage): assert swh_storage.check_config(check_write=True) assert swh_storage.check_config(check_write=False) def test_content_add(self, swh_storage): cont = data.cont insertion_start_time = datetime.datetime.now(tz=datetime.timezone.utc) actual_result = swh_storage.content_add([cont]) insertion_end_time = datetime.datetime.now(tz=datetime.timezone.utc) assert actual_result == { 'content:add': 1, 'content:add:bytes': cont['length'], 'skipped_content:add': 0 } assert list(swh_storage.content_get([cont['sha1']])) == \ [{'sha1': cont['sha1'], 'data': cont['data']}] expected_cont = data.cont del expected_cont['data'] journal_objects = list(swh_storage.journal_writer.objects) for (obj_type, obj) in journal_objects: assert insertion_start_time <= obj['ctime'] assert obj['ctime'] <= insertion_end_time del obj['ctime'] assert journal_objects == [('content', expected_cont)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['content'] == 1 def test_content_add_from_generator(self, swh_storage): def _cnt_gen(): yield data.cont actual_result = swh_storage.content_add(_cnt_gen()) assert actual_result == { 'content:add': 1, 'content:add:bytes': data.cont['length'], 'skipped_content:add': 0 } swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['content'] == 1 def test_content_add_validation(self, swh_storage): cont = data.cont with pytest.raises(ValueError, match='status'): swh_storage.content_add([{**cont, 'status': 'foobar'}]) with pytest.raises(ValueError, match="(?i)length"): swh_storage.content_add([{**cont, 'length': -2}]) with pytest.raises((ValueError, psycopg2.IntegrityError), match='reason') as cm: swh_storage.content_add([{**cont, 'status': 'absent'}]) if type(cm.value) == psycopg2.IntegrityError: assert cm.exception.pgcode == \ psycopg2.errorcodes.NOT_NULL_VIOLATION with pytest.raises( ValueError, match="^Must not provide a reason if content is not absent.$"): swh_storage.content_add([{**cont, 'reason': 'foobar'}]) def test_content_get_missing(self, swh_storage): cont = data.cont swh_storage.content_add([cont]) # Query a single missing content results = list(swh_storage.content_get( [data.cont2['sha1']])) assert results == [None] # Check content_get does not abort after finding a missing content results = list(swh_storage.content_get( [data.cont['sha1'], data.cont2['sha1']])) assert results == [{'sha1': cont['sha1'], 'data': cont['data']}, None] # Check content_get does not discard found countent when it finds # a missing content. results = list(swh_storage.content_get( [data.cont2['sha1'], data.cont['sha1']])) assert results == [None, {'sha1': cont['sha1'], 'data': cont['data']}] def test_content_add_different_input(self, swh_storage): cont = data.cont cont2 = data.cont2 actual_result = swh_storage.content_add([cont, cont2]) assert actual_result == { 'content:add': 2, 'content:add:bytes': cont['length'] + cont2['length'], 'skipped_content:add': 0 } def test_content_add_twice(self, swh_storage): actual_result = swh_storage.content_add([data.cont]) assert actual_result == { 'content:add': 1, 'content:add:bytes': data.cont['length'], 'skipped_content:add': 0 } assert len(swh_storage.journal_writer.objects) == 1 actual_result = swh_storage.content_add([data.cont, data.cont2]) assert actual_result == { 'content:add': 1, 'content:add:bytes': data.cont2['length'], 'skipped_content:add': 0 } assert len(swh_storage.journal_writer.objects) == 2 assert len(swh_storage.content_find(data.cont)) == 1 assert len(swh_storage.content_find(data.cont2)) == 1 def test_content_add_collision(self, swh_storage): cont1 = data.cont # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() sha256_array = bytearray(cont1b['sha256']) sha256_array[0] += 1 cont1b['sha256'] = bytes(sha256_array) with pytest.raises(HashCollision) as cm: swh_storage.content_add([cont1, cont1b]) assert cm.value.args[0] in ['sha1', 'sha1_git', 'blake2s256'] def test_content_update(self, swh_storage): swh_storage.journal_writer = None # TODO, not supported cont = copy.deepcopy(data.cont) swh_storage.content_add([cont]) # alter the sha1_git for example cont['sha1_git'] = hash_to_bytes( '3a60a5275d0333bf13468e8b3dcab90f4046e654') swh_storage.content_update([cont], keys=['sha1_git']) results = swh_storage.content_get_metadata([cont['sha1']]) del cont['data'] assert results == {cont['sha1']: [cont]} def test_content_add_metadata(self, swh_storage): cont = data.cont del cont['data'] cont['ctime'] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { 'content:add': 1, 'skipped_content:add': 0 } expected_cont = cont.copy() del expected_cont['ctime'] assert swh_storage.content_get_metadata([cont['sha1']]) == { cont['sha1']: [expected_cont] } assert list(swh_storage.journal_writer.objects) == [('content', cont)] def test_content_add_metadata_different_input(self, swh_storage): cont = data.cont del cont['data'] cont['ctime'] = datetime.datetime.now() cont2 = data.cont2 del cont2['data'] cont2['ctime'] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont, cont2]) assert actual_result == { 'content:add': 2, 'skipped_content:add': 0 } def test_content_add_metadata_collision(self, swh_storage): cont1 = data.cont del cont1['data'] cont1['ctime'] = datetime.datetime.now() # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() sha256_array = bytearray(cont1b['sha256']) sha256_array[0] += 1 cont1b['sha256'] = bytes(sha256_array) with pytest.raises(HashCollision) as cm: swh_storage.content_add_metadata([cont1, cont1b]) assert cm.value.args[0] in ['sha1', 'sha1_git', 'blake2s256'] def test_skipped_content_add(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 cont2['blake2s256'] = None missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert len(missing) == 2 actual_result = swh_storage.content_add([cont, cont, cont2]) assert actual_result == { 'content:add': 0, 'content:add:bytes': 0, 'skipped_content:add': 2, } missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert missing == [] @pytest.mark.property_based @settings(deadline=None) # this test is very slow @given(strategies.sets( elements=strategies.sampled_from( ['sha256', 'sha1_git', 'blake2s256']), min_size=0)) def test_content_missing(self, swh_storage, algos): algos |= {'sha1'} cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) test_contents = [cont2] missing_per_hash = defaultdict(list) for i in range(256): test_content = missing_cont.copy() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_contents.append(test_content) assert set(swh_storage.content_missing(test_contents)) == \ set(missing_per_hash['sha1']) for hash in algos: assert set(swh_storage.content_missing( test_contents, key_hash=hash)) == set(missing_per_hash[hash]) @pytest.mark.property_based @given(strategies.sets( elements=strategies.sampled_from( ['sha256', 'sha1_git', 'blake2s256']), min_size=0)) def test_content_missing_unknown_algo(self, swh_storage, algos): algos |= {'sha1'} cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) test_contents = [cont2] missing_per_hash = defaultdict(list) for i in range(16): test_content = missing_cont.copy() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_content['nonexisting_algo'] = b'\x00' test_contents.append(test_content) assert set( swh_storage.content_missing(test_contents)) == set( missing_per_hash['sha1']) for hash in algos: assert set(swh_storage.content_missing( test_contents, key_hash=hash)) == set( missing_per_hash[hash]) def test_content_missing_per_sha1(self, swh_storage): # given cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) # when gen = swh_storage.content_missing_per_sha1([cont2['sha1'], missing_cont['sha1']]) # then assert list(gen) == [missing_cont['sha1']] def test_content_missing_per_sha1_git(self, swh_storage): cont = data.cont cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont, cont2]) contents = [cont['sha1_git'], cont2['sha1_git'], missing_cont['sha1_git']] missing_contents = swh_storage.content_missing_per_sha1_git(contents) assert list(missing_contents) == [missing_cont['sha1_git']] def test_content_get_partition(self, swh_storage, swh_contents): """content_get_partition paginates results if limit exceeded""" expected_contents = [c for c in swh_contents if c['status'] != 'absent'] actual_contents = [] for i in range(16): actual_result = swh_storage.content_get_partition(i, 16) assert actual_result['next_page_token'] is None actual_contents.extend(actual_result['contents']) assert_contents_ok( expected_contents, actual_contents, ['sha1']) def test_content_get_partition_full(self, swh_storage, swh_contents): """content_get_partition for a single partition returns all available contents""" expected_contents = [c for c in swh_contents if c['status'] != 'absent'] actual_result = swh_storage.content_get_partition(0, 1) assert actual_result['next_page_token'] is None actual_contents = actual_result['contents'] assert_contents_ok( expected_contents, actual_contents, ['sha1']) def test_content_get_partition_empty(self, swh_storage, swh_contents): """content_get_partition when at least one of the partitions is empty""" expected_contents = {cont['sha1'] for cont in swh_contents if cont['status'] != 'absent'} # nb_partitions = smallest power of 2 such that at least one of # the partitions is empty nb_partitions = 1 << math.floor(math.log2(len(swh_contents)) + 1) seen_sha1s = [] for i in range(nb_partitions): actual_result = swh_storage.content_get_partition( i, nb_partitions, limit=len(swh_contents)+1) for cont in actual_result['contents']: seen_sha1s.append(cont['sha1']) # Limit is higher than the max number of results assert actual_result['next_page_token'] is None assert set(seen_sha1s) == expected_contents def test_content_get_partition_limit_none(self, swh_storage): """content_get_partition call with wrong limit input should fail""" with pytest.raises(ValueError) as e: swh_storage.content_get_partition(1, 16, limit=None) assert e.value.args == ('Development error: limit should not be None',) def test_generate_content_get_partition_pagination( self, swh_storage, swh_contents): """content_get_partition returns contents within range provided""" expected_contents = [c for c in swh_contents if c['status'] != 'absent'] # retrieve contents actual_contents = [] for i in range(4): page_token = None while True: actual_result = swh_storage.content_get_partition( i, 4, limit=3, page_token=page_token) actual_contents.extend(actual_result['contents']) page_token = actual_result['next_page_token'] if page_token is None: break assert_contents_ok( expected_contents, actual_contents, ['sha1']) def test_content_get_metadata(self, swh_storage): cont1 = data.cont cont2 = data.cont2 swh_storage.content_add([cont1, cont2]) actual_md = swh_storage.content_get_metadata( [cont1['sha1'], cont2['sha1']]) # we only retrieve the metadata cont1.pop('data') cont2.pop('data') assert actual_md[cont1['sha1']] == [cont1] assert actual_md[cont2['sha1']] == [cont2] assert len(actual_md.keys()) == 2 def test_content_get_metadata_missing_sha1(self, swh_storage): cont1 = data.cont cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get_metadata( [missing_cont['sha1']]) assert actual_contents == {missing_cont['sha1']: []} def test_content_get_random(self, swh_storage): swh_storage.content_add([data.cont, data.cont2, data.cont3]) assert swh_storage.content_get_random() in { data.cont['sha1_git'], data.cont2['sha1_git'], data.cont3['sha1_git']} def test_directory_add(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir['id']])) assert [data.dir['id']] == init_missing actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {'directory:add': 1} assert list(swh_storage.journal_writer.objects) == \ [('directory', data.dir)] actual_data = list(swh_storage.directory_ls(data.dir['id'])) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) after_missing = list(swh_storage.directory_missing([data.dir['id']])) assert after_missing == [] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['directory'] == 1 def test_directory_add_from_generator(self, swh_storage): def _dir_gen(): yield data.dir actual_result = swh_storage.directory_add(directories=_dir_gen()) assert actual_result == {'directory:add': 1} assert list(swh_storage.journal_writer.objects) == \ [('directory', data.dir)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['directory'] == 1 def test_directory_add_validation(self, swh_storage): dir_ = copy.deepcopy(data.dir) dir_['entries'][0]['type'] = 'foobar' with pytest.raises(ValueError, match='type.*foobar'): swh_storage.directory_add([dir_]) dir_ = copy.deepcopy(data.dir) del dir_['entries'][0]['target'] with pytest.raises((TypeError, psycopg2.IntegrityError), match='target') as cm: swh_storage.directory_add([dir_]) if type(cm.value) == psycopg2.IntegrityError: assert cm.value.pgcode == psycopg2.errorcodes.NOT_NULL_VIOLATION def test_directory_add_twice(self, swh_storage): actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {'directory:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('directory', data.dir)] actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {'directory:add': 0} assert list(swh_storage.journal_writer.objects) \ == [('directory', data.dir)] def test_directory_get_recursive(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir['id']])) assert init_missing == [data.dir['id']] actual_result = swh_storage.directory_add( [data.dir, data.dir2, data.dir3]) assert actual_result == {'directory:add': 3} assert list(swh_storage.journal_writer.objects) == [ ('directory', data.dir), ('directory', data.dir2), ('directory', data.dir3)] # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls( data.dir['id'], recursive=True)) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls( data.dir2['id'], recursive=True)) expected_data = list(transform_entries(data.dir2)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory containing a known subdirectory, entries should # be both those of the directory and of the subdir actual_data = list(swh_storage.directory_ls( data.dir3['id'], recursive=True)) expected_data = list(itertools.chain( transform_entries(data.dir3), transform_entries(data.dir, prefix=b'subdir/'))) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) def test_directory_get_non_recursive(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir['id']])) assert init_missing == [data.dir['id']] actual_result = swh_storage.directory_add( [data.dir, data.dir2, data.dir3]) assert actual_result == {'directory:add': 3} assert list(swh_storage.journal_writer.objects) == [ ('directory', data.dir), ('directory', data.dir2), ('directory', data.dir3)] # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(data.dir['id'])) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory contaiining a single file actual_data = list(swh_storage.directory_ls(data.dir2['id'])) expected_data = list(transform_entries(data.dir2)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory containing a known subdirectory, entries should # only be those of the parent directory, not of the subdir actual_data = list(swh_storage.directory_ls(data.dir3['id'])) expected_data = list(transform_entries(data.dir3)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) def test_directory_entry_get_by_path(self, swh_storage): # given init_missing = list(swh_storage.directory_missing([data.dir3['id']])) assert [data.dir3['id']] == init_missing actual_result = swh_storage.directory_add([data.dir3, data.dir4]) assert actual_result == {'directory:add': 2} expected_entries = [ { 'dir_id': data.dir3['id'], 'name': b'foo', 'type': 'file', 'target': data.cont['sha1_git'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, { 'dir_id': data.dir3['id'], 'name': b'subdir', 'type': 'dir', 'target': data.dir['id'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.directory, 'length': None, }, { 'dir_id': data.dir3['id'], 'name': b'hello', 'type': 'file', 'target': b'12345678901234567890', 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, ] # when (all must be found here) for entry, expected_entry in zip( data.dir3['entries'], expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( data.dir3['id'], [entry['name']]) assert actual_entry == expected_entry # same, but deeper for entry, expected_entry in zip( data.dir3['entries'], expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( data.dir4['id'], [b'subdir1', entry['name']]) expected_entry = expected_entry.copy() expected_entry['name'] = b'subdir1/' + expected_entry['name'] assert actual_entry == expected_entry # when (nothing should be found here since data.dir is not persisted.) for entry in data.dir['entries']: actual_entry = swh_storage.directory_entry_get_by_path( data.dir['id'], [entry['name']]) assert actual_entry is None def test_directory_get_random(self, swh_storage): swh_storage.directory_add([data.dir, data.dir2, data.dir3]) assert swh_storage.directory_get_random() in \ {data.dir['id'], data.dir2['id'], data.dir3['id']} def test_revision_add(self, swh_storage): init_missing = swh_storage.revision_missing([data.revision['id']]) assert list(init_missing) == [data.revision['id']] actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {'revision:add': 1} end_missing = swh_storage.revision_missing([data.revision['id']]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.objects) \ == [('revision', data.revision)] # already there so nothing added actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {'revision:add': 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['revision'] == 1 def test_revision_add_from_generator(self, swh_storage): def _rev_gen(): yield data.revision actual_result = swh_storage.revision_add(_rev_gen()) assert actual_result == {'revision:add': 1} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['revision'] == 1 def test_revision_add_validation(self, swh_storage): rev = copy.deepcopy(data.revision) rev['date']['offset'] = 2**16 with pytest.raises((ValueError, psycopg2.DataError), match='offset') as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode \ == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rev = copy.deepcopy(data.revision) rev['committer_date']['offset'] = 2**16 with pytest.raises((ValueError, psycopg2.DataError), match='offset') as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode \ == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rev = copy.deepcopy(data.revision) rev['type'] = 'foobar' with pytest.raises((ValueError, psycopg2.DataError), match='(?i)type') as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == \ psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION def test_revision_add_twice(self, swh_storage): actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {'revision:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('revision', data.revision)] actual_result = swh_storage.revision_add( [data.revision, data.revision2]) assert actual_result == {'revision:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('revision', data.revision), ('revision', data.revision2)] def test_revision_add_name_clash(self, swh_storage): revision1 = data.revision revision2 = data.revision2 revision1['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe', 'email': b'john.doe@example.com' } revision2['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe ', 'email': b'john.doe@example.com ' } actual_result = swh_storage.revision_add([revision1, revision2]) assert actual_result == {'revision:add': 2} def test_revision_log(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) # when actual_results = list(swh_storage.revision_log( [data.revision4['id']])) # hack: ids generated for actual_result in actual_results: if 'id' in actual_result['author']: del actual_result['author']['id'] if 'id' in actual_result['committer']: del actual_result['committer']['id'] assert len(actual_results) == 2 # rev4 -child-> rev3 assert actual_results[0] == normalize_entity(data.revision4) assert actual_results[1] == normalize_entity(data.revision3) assert list(swh_storage.journal_writer.objects) == [ ('revision', data.revision3), ('revision', data.revision4)] def test_revision_log_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) actual_results = list(swh_storage.revision_log( [data.revision4['id']], 1)) # hack: ids generated for actual_result in actual_results: if 'id' in actual_result['author']: del actual_result['author']['id'] if 'id' in actual_result['committer']: del actual_result['committer']['id'] assert len(actual_results) == 1 assert actual_results[0] == data.revision4 def test_revision_log_unknown_revision(self, swh_storage): rev_log = list(swh_storage.revision_log([data.revision['id']])) assert rev_log == [] def test_revision_shortlog(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) # when actual_results = list(swh_storage.revision_shortlog( [data.revision4['id']])) assert len(actual_results) == 2 # rev4 -child-> rev3 assert list(actual_results[0]) == short_revision(data.revision4) assert list(actual_results[1]) == short_revision(data.revision3) def test_revision_shortlog_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) actual_results = list(swh_storage.revision_shortlog( [data.revision4['id']], 1)) assert len(actual_results) == 1 assert list(actual_results[0]) == short_revision(data.revision4) def test_revision_get(self, swh_storage): swh_storage.revision_add([data.revision]) actual_revisions = list(swh_storage.revision_get( [data.revision['id'], data.revision2['id']])) # when if 'id' in actual_revisions[0]['author']: del actual_revisions[0]['author']['id'] # hack: ids are generated if 'id' in actual_revisions[0]['committer']: del actual_revisions[0]['committer']['id'] assert len(actual_revisions) == 2 assert actual_revisions[0] == normalize_entity(data.revision) assert actual_revisions[1] is None def test_revision_get_no_parents(self, swh_storage): swh_storage.revision_add([data.revision3]) get = list(swh_storage.revision_get([data.revision3['id']])) assert len(get) == 1 assert get[0]['parents'] == [] # no parents on this one def test_revision_get_random(self, swh_storage): swh_storage.revision_add( [data.revision, data.revision2, data.revision3]) assert swh_storage.revision_get_random() in \ {data.revision['id'], data.revision2['id'], data.revision3['id']} def test_release_add(self, swh_storage): init_missing = swh_storage.release_missing([data.release['id'], data.release2['id']]) assert [data.release['id'], data.release2['id']] == list(init_missing) actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 2} end_missing = swh_storage.release_missing([data.release['id'], data.release2['id']]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.objects) == [ ('release', data.release), ('release', data.release2)] # already present so nothing added actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['release'] == 2 def test_release_add_from_generator(self, swh_storage): def _rel_gen(): yield data.release yield data.release2 actual_result = swh_storage.release_add(_rel_gen()) assert actual_result == {'release:add': 2} assert list(swh_storage.journal_writer.objects) == [ ('release', data.release), ('release', data.release2)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['release'] == 2 def test_release_add_no_author_date(self, swh_storage): release = data.release release['author'] = None release['date'] = None actual_result = swh_storage.release_add([release]) assert actual_result == {'release:add': 1} end_missing = swh_storage.release_missing([data.release['id']]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.objects) \ == [('release', release)] def test_release_add_validation(self, swh_storage): rel = copy.deepcopy(data.release) rel['date']['offset'] = 2**16 with pytest.raises((ValueError, psycopg2.DataError), match='offset') as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode \ == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rel = copy.deepcopy(data.release) rel['author'] = None with pytest.raises((ValueError, psycopg2.IntegrityError), match='date') as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.IntegrityError: assert cm.value.pgcode == psycopg2.errorcodes.CHECK_VIOLATION def test_release_add_twice(self, swh_storage): actual_result = swh_storage.release_add([data.release]) assert actual_result == {'release:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('release', data.release)] actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('release', data.release), ('release', data.release2)] def test_release_add_name_clash(self, swh_storage): release1 = data.release.copy() release2 = data.release2.copy() release1['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe', 'email': b'john.doe@example.com' } release2['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe ', 'email': b'john.doe@example.com ' } actual_result = swh_storage.release_add([release1, release2]) assert actual_result == {'release:add': 2} def test_release_get(self, swh_storage): # given swh_storage.release_add([data.release, data.release2]) # when actual_releases = list(swh_storage.release_get([data.release['id'], data.release2['id']])) # then for actual_release in actual_releases: if 'id' in actual_release['author']: del actual_release['author']['id'] # hack: ids are generated assert [ normalize_entity(data.release), normalize_entity(data.release2)] \ == [actual_releases[0], actual_releases[1]] unknown_releases = \ list(swh_storage.release_get([data.release3['id']])) assert unknown_releases[0] is None def test_release_get_random(self, swh_storage): swh_storage.release_add([data.release, data.release2, data.release3]) assert swh_storage.release_get_random() in \ {data.release['id'], data.release2['id'], data.release3['id']} def test_origin_add_one(self, swh_storage): origin0 = swh_storage.origin_get(data.origin) assert origin0 is None id = swh_storage.origin_add_one(data.origin) actual_origin = swh_storage.origin_get({'url': data.origin['url']}) assert actual_origin['url'] == data.origin['url'] id2 = swh_storage.origin_add_one(data.origin) assert id == id2 def test_origin_add(self, swh_storage): origin0 = swh_storage.origin_get([data.origin])[0] assert origin0 is None origin1, origin2 = swh_storage.origin_add([data.origin, data.origin2]) actual_origin = swh_storage.origin_get([{ 'url': data.origin['url'], }])[0] assert actual_origin['url'] == origin1['url'] actual_origin2 = swh_storage.origin_get([{ 'url': data.origin2['url'], }])[0] assert actual_origin2['url'] == origin2['url'] if 'id' in actual_origin: del actual_origin['id'] del actual_origin2['id'] assert list(swh_storage.journal_writer.objects) \ == [('origin', actual_origin), ('origin', actual_origin2)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['origin'] == 2 def test_origin_add_from_generator(self, swh_storage): def _ori_gen(): yield data.origin yield data.origin2 origin1, origin2 = swh_storage.origin_add(_ori_gen()) actual_origin = swh_storage.origin_get([{ 'url': data.origin['url'], }])[0] assert actual_origin['url'] == origin1['url'] actual_origin2 = swh_storage.origin_get([{ 'url': data.origin2['url'], }])[0] assert actual_origin2['url'] == origin2['url'] if 'id' in actual_origin: del actual_origin['id'] del actual_origin2['id'] assert list(swh_storage.journal_writer.objects) \ == [('origin', actual_origin), ('origin', actual_origin2)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['origin'] == 2 def test_origin_add_twice(self, swh_storage): add1 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.objects) \ == [('origin', data.origin), ('origin', data.origin2)] add2 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.objects) \ == [('origin', data.origin), ('origin', data.origin2)] assert add1 == add2 def test_origin_add_validation(self, swh_storage): with pytest.raises((TypeError, KeyError), match='url'): swh_storage.origin_add([{'type': 'git'}]) def test_origin_get_legacy(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) actual_origin0 = swh_storage.origin_get( {'url': data.origin['url']}) assert actual_origin0['url'] == data.origin['url'] def test_origin_get(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) actual_origin0 = swh_storage.origin_get( [{'url': data.origin['url']}]) assert len(actual_origin0) == 1 assert actual_origin0[0]['url'] == data.origin['url'] def _generate_random_visits(self, nb_visits=100, start=0, end=7): """Generate random visits within the last 2 months (to avoid computations) """ visits = [] today = datetime.datetime.now(tz=datetime.timezone.utc) for weeks in range(nb_visits, 0, -1): hours = random.randint(0, 24) minutes = random.randint(0, 60) seconds = random.randint(0, 60) days = random.randint(0, 28) weeks = random.randint(start, end) date_visit = today - timedelta( weeks=weeks, hours=hours, minutes=minutes, seconds=seconds, days=days) visits.append(date_visit) return visits def test_origin_visit_get_random(self, swh_storage): swh_storage.origin_add(data.origins) # Add some random visits within the selection range visits = self._generate_random_visits() visit_type = 'git' # Add visits to those origins for origin in data.origins: for date_visit in visits: visit = swh_storage.origin_visit_add( origin['url'], date=date_visit, type=visit_type) swh_storage.origin_visit_update( origin['url'], visit_id=visit['visit'], status='full') swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() assert stats['origin'] == len(data.origins) assert stats['origin_visit'] == len(data.origins) * len(visits) random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit assert random_origin_visit['origin'] is not None original_urls = [o['url'] for o in data.origins] assert random_origin_visit['origin'] in original_urls def test_origin_visit_get_random_nothing_found(self, swh_storage): swh_storage.origin_add(data.origins) visit_type = 'hg' # Add some visits outside of the random generation selection so nothing # will be found by the random selection visits = self._generate_random_visits(nb_visits=3, start=13, end=24) for origin in data.origins: for date_visit in visits: visit = swh_storage.origin_visit_add( origin['url'], date=date_visit, type=visit_type) swh_storage.origin_visit_update( origin['url'], visit_id=visit['visit'], status='full') random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit is None def test_origin_get_by_sha1(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) origins = list(swh_storage.origin_get_by_sha1([ sha1(data.origin['url']) ])) assert len(origins) == 1 assert origins[0]['url'] == data.origin['url'] def test_origin_get_by_sha1_not_found(self, swh_storage): assert swh_storage.origin_get(data.origin) is None origins = list(swh_storage.origin_get_by_sha1([ sha1(data.origin['url']) ])) assert len(origins) == 1 assert origins[0] is None def test_origin_search_single_result(self, swh_storage): found_origins = list(swh_storage.origin_search(data.origin['url'])) assert len(found_origins) == 0 found_origins = list(swh_storage.origin_search(data.origin['url'], regexp=True)) assert len(found_origins) == 0 swh_storage.origin_add_one(data.origin) origin_data = { 'url': data.origin['url']} found_origins = list(swh_storage.origin_search(data.origin['url'])) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin_data found_origins = list(swh_storage.origin_search( '.' + data.origin['url'][1:-1] + '.', regexp=True)) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin_data swh_storage.origin_add_one(data.origin2) origin2_data = {'url': data.origin2['url']} found_origins = list(swh_storage.origin_search(data.origin2['url'])) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin2_data found_origins = list(swh_storage.origin_search( '.' + data.origin2['url'][1:-1] + '.', regexp=True)) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin2_data def test_origin_search_no_regexp(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('/')) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('/', offset=0, limit=1)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('/', offset=1, limit=1)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_substring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('/', regexp=True)) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('/', offset=0, limit=1, regexp=True)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('/', offset=1, limit=1, regexp=True)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_fullstring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('.*/.*', regexp=True)) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('.*/.*', offset=0, limit=1, regexp=True)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('.*/.*', offset=1, limit=1, regexp=True)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_visit_add(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] + date_visit = datetime.datetime.now(datetime.timezone.utc) + + # Round to milliseconds before insertion, so equality doesn't fail + # after a round-trip through a DB (eg. Cassandra) + date_visit = date_visit.replace( + microsecond=round(date_visit.microsecond, -3)) # when - date_visit = datetime.datetime.now(datetime.timezone.utc) origin_visit1 = swh_storage.origin_visit_add( origin_url, type=data.type_visit1, date=date_visit) actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) assert { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } in actual_origin_visits origin_visit = { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } objects = list(swh_storage.journal_writer.objects) assert ('origin', data.origin2) in objects assert ('origin_visit', origin_visit) in objects def test_origin_visit_get__unknown_origin(self, swh_storage): assert [] == list(swh_storage.origin_visit_get('foo')) def test_origin_visit_add_default_type(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] # when date_visit = datetime.datetime.now(datetime.timezone.utc) date_visit2 = date_visit + datetime.timedelta(minutes=1) + + # Round to milliseconds before insertion, so equality doesn't fail + # after a round-trip through a DB (eg. Cassandra) + date_visit = date_visit.replace( + microsecond=round(date_visit.microsecond, -3)) + date_visit2 = date_visit2.replace( + microsecond=round(date_visit2.microsecond, -3)) + origin_visit1 = swh_storage.origin_visit_add( origin_url, date=date_visit, type=data.type_visit1, ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=date_visit2, type=data.type_visit2, ) # then assert origin_visit1['origin'] == origin_url assert origin_visit1['visit'] is not None actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) expected_visits = [ { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }, { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }, ] for visit in expected_visits: assert visit in actual_origin_visits objects = list(swh_storage.journal_writer.objects) assert ('origin', data.origin2) in objects for visit in expected_visits: assert ('origin_visit', visit) in objects def test_origin_visit_add_validation(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin2) with pytest.raises((TypeError, psycopg2.ProgrammingError)) as cm: swh_storage.origin_visit_add(origin_url, date=[b'foo']) if type(cm.value) == psycopg2.ProgrammingError: assert cm.value.pgcode \ == psycopg2.errorcodes.UNDEFINED_FUNCTION def test_origin_visit_update(self, swh_storage): # given swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] date_visit = datetime.datetime.now(datetime.timezone.utc) + date_visit2 = date_visit + datetime.timedelta(minutes=1) + + # Round to milliseconds before insertion, so equality doesn't fail + # after a round-trip through a DB (eg. Cassandra) + date_visit = date_visit.replace( + microsecond=round(date_visit.microsecond, -3)) + date_visit2 = date_visit2.replace( + microsecond=round(date_visit2.microsecond, -3)) + origin_visit1 = swh_storage.origin_visit_add( origin_url, date=date_visit, type=data.type_visit1, ) - date_visit2 = date_visit + datetime.timedelta(minutes=1) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=date_visit2, type=data.type_visit2 ) swh_storage.origin_add_one(data.origin2) origin_url2 = data.origin2['url'] origin_visit3 = swh_storage.origin_visit_add( origin_url2, date=date_visit2, type=data.type_visit3 ) # when visit1_metadata = { 'contents': 42, 'directories': 22, } swh_storage.origin_visit_update( origin_url, origin_visit1['visit'], status='full', metadata=visit1_metadata) swh_storage.origin_visit_update( origin_url2, origin_visit3['visit'], status='partial') # then actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) expected_visits = [{ 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }, { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }] for visit in expected_visits: assert visit in actual_origin_visits actual_origin_visits_bis = list(swh_storage.origin_visit_get( origin_url, limit=1)) assert actual_origin_visits_bis == [ { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }] actual_origin_visits_ter = list(swh_storage.origin_visit_get( origin_url, last_visit=origin_visit1['visit'])) assert actual_origin_visits_ter == [ { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }] actual_origin_visits2 = list(swh_storage.origin_visit_get( origin_url2)) assert actual_origin_visits2 == [ { 'origin': origin_url2, 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'partial', 'metadata': None, 'snapshot': None, }] data1 = { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data3 = { 'origin': origin_url2, 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data4 = { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'metadata': visit1_metadata, 'status': 'full', 'snapshot': None, } data5 = { 'origin': origin_url2, 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'partial', 'metadata': None, 'snapshot': None, } objects = list(swh_storage.journal_writer.objects) assert ('origin', data.origin) in objects assert ('origin', data.origin2) in objects assert ('origin_visit', data1) in objects assert ('origin_visit', data2) in objects assert ('origin_visit', data3) in objects assert ('origin_visit', data4) in objects assert ('origin_visit', data5) in objects def test_origin_visit_update_validation(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) visit = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2, ) with pytest.raises((ValueError, psycopg2.DataError), match='status') as cm: swh_storage.origin_visit_update( origin_url, visit['visit'], status='foobar') if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == \ psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION def test_origin_visit_find_by_date(self, swh_storage): # given swh_storage.origin_add_one(data.origin) swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit2, type=data.type_visit1, ) origin_visit2 = swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit3, type=data.type_visit2, ) origin_visit3 = swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit2, type=data.type_visit3, ) # Simple case visit = swh_storage.origin_visit_find_by_date( data.origin['url'], data.date_visit3) assert visit['visit'] == origin_visit2['visit'] # There are two visits at the same date, the latest must be returned visit = swh_storage.origin_visit_find_by_date( data.origin['url'], data.date_visit2) assert visit['visit'] == origin_visit3['visit'] def test_origin_visit_find_by_date__unknown_origin(self, swh_storage): swh_storage.origin_visit_find_by_date('foo', data.date_visit2) def test_origin_visit_update_missing_snapshot(self, swh_storage): # given swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] origin_visit = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1, ) # when swh_storage.origin_visit_update( origin_url, origin_visit['visit'], snapshot=data.snapshot['id']) # then actual_origin_visit = swh_storage.origin_visit_get_by( origin_url, origin_visit['visit']) assert actual_origin_visit['snapshot'] == data.snapshot['id'] # when swh_storage.snapshot_add([data.snapshot]) assert actual_origin_visit['snapshot'] == data.snapshot['id'] def test_origin_visit_get_by(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin_url = data.origin['url'] origin2_url = data.origin2['url'] origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2, ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1['visit'], snapshot=data.snapshot['id']) # Add some other {origin, visit} entries swh_storage.origin_visit_add( origin_url, date=data.date_visit3, type=data.type_visit3, ) swh_storage.origin_visit_add( origin2_url, date=data.date_visit3, type=data.type_visit3, ) # when visit1_metadata = { 'contents': 42, 'directories': 22, } swh_storage.origin_visit_update( origin_url, origin_visit1['visit'], status='full', metadata=visit1_metadata) expected_origin_visit = origin_visit1.copy() expected_origin_visit.update({ 'origin': origin_url, 'visit': origin_visit1['visit'], 'date': data.date_visit2, 'type': data.type_visit2, 'metadata': visit1_metadata, 'status': 'full', 'snapshot': data.snapshot['id'], }) # when actual_origin_visit1 = swh_storage.origin_visit_get_by( origin_url, origin_visit1['visit']) # then assert actual_origin_visit1 == expected_origin_visit def test_origin_visit_get_by__unknown_origin(self, swh_storage): assert swh_storage.origin_visit_get_by('foo', 10) is None def test_origin_visit_upsert_new(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] # when swh_storage.origin_visit_upsert([ { 'origin': origin_url, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, { 'origin': origin_url, 'date': '2018-01-01 23:00:00+00', 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, ]) # then actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) assert actual_origin_visits == [ { 'origin': origin_url, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, { 'origin': origin_url, 'date': data.date_visit3, 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, ] data1 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit3, 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, } assert list(swh_storage.journal_writer.objects) == [ ('origin', data.origin2), ('origin_visit', data1), ('origin_visit', data2)] def test_origin_visit_upsert_existing(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] # when origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit1, ) swh_storage.origin_visit_upsert([{ 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, }]) # then assert origin_visit1['origin'] == origin_url assert origin_visit1['visit'] is not None actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) assert actual_origin_visits == [ { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, }] data1 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, } assert list(swh_storage.journal_writer.objects) == [ ('origin', data.origin2), ('origin_visit', data1), ('origin_visit', data2)] def test_origin_visit_get_by_no_result(self, swh_storage): swh_storage.origin_add([data.origin]) actual_origin_visit = swh_storage.origin_visit_get_by( data.origin['url'], 999) assert actual_origin_visit is None def test_origin_visit_get_latest(self, swh_storage): swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit3_id = origin_visit3['visit'] origin_visit1 = swh_storage.origin_visit_get_by(origin_url, visit1_id) origin_visit2 = swh_storage.origin_visit_get_by(origin_url, visit2_id) origin_visit3 = swh_storage.origin_visit_get_by(origin_url, visit3_id) # Two visits, both with no snapshot assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) assert swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) is None # Add snapshot to visit1; require_snapshot=True makes it return # visit1 and require_snapshot=False still returns visit2 swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.complete_snapshot['id']) assert {**origin_visit1, 'snapshot': data.complete_snapshot['id']} \ == swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no visit # returned assert swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update( origin_url, visit1_id, status='full') assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.empty_snapshot['id']) assert {**origin_visit2, 'snapshot': data.empty_snapshot['id']} == \ swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Check that the status filter is still working assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit3 (same date as visit2) swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit3_id, snapshot=data.complete_snapshot['id']) assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full'], require_snapshot=True) assert { **origin_visit3, 'snapshot': data.complete_snapshot['id'] } == swh_storage.origin_visit_get_latest(origin_url) assert { **origin_visit3, 'snapshot': data.complete_snapshot['id'] } == swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) def test_person_fullname_unicity(self, swh_storage): # given (person injection through revisions for example) revision = data.revision # create a revision with same committer fullname but wo name and email revision2 = copy.deepcopy(data.revision2) revision2['committer'] = dict(revision['committer']) revision2['committer']['email'] = None revision2['committer']['name'] = None swh_storage.revision_add([revision]) swh_storage.revision_add([revision2]) # when getting added revisions revisions = list( swh_storage.revision_get([revision['id'], revision2['id']])) # then # check committers are the same assert revisions[0]['committer'] == revisions[1]['committer'] def test_snapshot_add_get_empty(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] actual_result = swh_storage.snapshot_add([data.empty_snapshot]) assert actual_result == {'snapshot:add': 1} swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.empty_snapshot['id']) by_id = swh_storage.snapshot_get(data.empty_snapshot['id']) assert by_id == {**data.empty_snapshot, 'next_branch': None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.empty_snapshot, 'next_branch': None} data1 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': data.empty_snapshot['id'], } assert list(swh_storage.journal_writer.objects) == \ [('origin', data.origin), ('origin_visit', data1), ('snapshot', data.empty_snapshot), ('origin_visit', data2)] def test_snapshot_add_get_complete(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] actual_result = swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.complete_snapshot['id']) assert actual_result == {'snapshot:add': 1} by_id = swh_storage.snapshot_get(data.complete_snapshot['id']) assert by_id == {**data.complete_snapshot, 'next_branch': None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.complete_snapshot, 'next_branch': None} def test_snapshot_add_many(self, swh_storage): actual_result = swh_storage.snapshot_add( [data.snapshot, data.complete_snapshot]) assert actual_result == {'snapshot:add': 2} assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.complete_snapshot['id']) assert {**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.snapshot['id']) swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['snapshot'] == 2 def test_snapshot_add_many_from_generator(self, swh_storage): def _snp_gen(): yield data.snapshot yield data.complete_snapshot actual_result = swh_storage.snapshot_add(_snp_gen()) assert actual_result == {'snapshot:add': 2} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['snapshot'] == 2 def test_snapshot_add_many_incremental(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) assert actual_result == {'snapshot:add': 1} actual_result2 = swh_storage.snapshot_add( [data.snapshot, data.complete_snapshot]) assert actual_result2 == {'snapshot:add': 1} assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.complete_snapshot['id']) assert {**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.snapshot['id']) def test_snapshot_add_twice(self, swh_storage): actual_result = swh_storage.snapshot_add([data.empty_snapshot]) assert actual_result == {'snapshot:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('snapshot', data.empty_snapshot)] actual_result = swh_storage.snapshot_add([data.snapshot]) assert actual_result == {'snapshot:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('snapshot', data.empty_snapshot), ('snapshot', data.snapshot)] def test_snapshot_add_validation(self, swh_storage): snap = copy.deepcopy(data.snapshot) snap['branches'][b'foo'] = {'target_type': 'revision'} with pytest.raises(KeyError, match='target'): swh_storage.snapshot_add([snap]) snap = copy.deepcopy(data.snapshot) snap['branches'][b'foo'] = {'target': b'\x42'*20} with pytest.raises(KeyError, match='target_type'): swh_storage.snapshot_add([snap]) def test_snapshot_add_count_branches(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) assert actual_result == {'snapshot:add': 1} snp_id = data.complete_snapshot['id'] snp_size = swh_storage.snapshot_count_branches(snp_id) expected_snp_size = { 'alias': 1, 'content': 1, 'directory': 2, 'release': 1, 'revision': 1, 'snapshot': 1, None: 1 } assert snp_size == expected_snp_size def test_snapshot_add_get_paginated(self, swh_storage): swh_storage.snapshot_add([data.complete_snapshot]) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches( snp_id, branches_from=b'release') rel_idx = branch_names.index(b'release') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in branch_names[rel_idx:] }, 'next_branch': None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, branches_count=1) expected_snapshot = { 'id': snp_id, 'branches': { branch_names[0]: branches[branch_names[0]], }, 'next_branch': b'content', } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, branches_from=b'directory', branches_count=3) dir_idx = branch_names.index(b'directory') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in branch_names[dir_idx:dir_idx + 3] }, 'next_branch': branch_names[dir_idx + 3], } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.complete_snapshot['id']) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['release', 'revision']) expected_snapshot = { 'id': snp_id, 'branches': { name: tgt for name, tgt in branches.items() if tgt and tgt['target_type'] in ['release', 'revision'] }, 'next_branch': None, } assert snapshot == expected_snapshot snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['alias']) expected_snapshot = { 'id': snp_id, 'branches': { name: tgt for name, tgt in branches.items() if tgt and tgt['target_type'] == 'alias' }, 'next_branch': None, } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered_and_paginated(self, swh_storage): swh_storage.snapshot_add([data.complete_snapshot]) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_from=b'directory2') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in (b'directory2', b'release') }, 'next_branch': None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_count=1) expected_snapshot = { 'id': snp_id, 'branches': { b'directory': branches[b'directory'] }, 'next_branch': b'directory2', } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_count=2) expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in (b'directory', b'directory2') }, 'next_branch': b'release', } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_from=b'directory2', branches_count=1) dir_idx = branch_names.index(b'directory2') expected_snapshot = { 'id': snp_id, 'branches': { branch_names[dir_idx]: branches[branch_names[dir_idx]], }, 'next_branch': b'release', } assert snapshot == expected_snapshot def test_snapshot_add_get(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.snapshot['id']) by_id = swh_storage.snapshot_get(data.snapshot['id']) assert by_id == {**data.snapshot, 'next_branch': None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.snapshot, 'next_branch': None} origin_visit_info = swh_storage.origin_visit_get_by( origin_url, visit_id) assert origin_visit_info['snapshot'] == data.snapshot['id'] def test_snapshot_add_nonexistent_visit(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) visit_id = 54164461156 swh_storage.journal_writer.objects[:] = [] swh_storage.snapshot_add([data.snapshot]) with pytest.raises(ValueError): swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.snapshot['id']) assert list(swh_storage.journal_writer.objects) == [ ('snapshot', data.snapshot)] def test_snapshot_add_twice__by_origin_visit(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.snapshot['id']) by_ov1 = swh_storage.snapshot_get_by_origin_visit( origin_url, visit1_id) assert by_ov1 == {**data.snapshot, 'next_branch': None} origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.snapshot['id']) by_ov2 = swh_storage.snapshot_get_by_origin_visit( origin_url, visit2_id) assert by_ov2 == {**data.snapshot, 'next_branch': None} data1 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': data.snapshot['id'], } data3 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data4 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': data.snapshot['id'], } assert list(swh_storage.journal_writer.objects) \ == [('origin', data.origin), ('origin_visit', data1), ('snapshot', data.snapshot), ('origin_visit', data2), ('origin_visit', data3), ('origin_visit', data4)] def test_snapshot_get_latest(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit3, ) visit3_id = origin_visit3['visit'] # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add snapshot to visit1, latest snapshot = visit 1 snapshot swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.complete_snapshot['id']) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no snapshot # returned assert swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update(origin_url, visit1_id, status='full') assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.empty_snapshot['id']) assert {**data.empty_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) # Check that the status filter is still working assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit3 (same date as visit2) and check that # the new snapshot is returned swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit3_id, snapshot=data.complete_snapshot['id']) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) def test_snapshot_get_latest__missing_snapshot(self, swh_storage): # Origin does not exist origin_url = data.origin['url'] assert swh_storage.snapshot_get_latest(origin_url) is None swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add unknown snapshot to visit1, check that the inconsistency is # detected swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.complete_snapshot['id']) with pytest.raises(ValueError): swh_storage.snapshot_get_latest( origin_url) # Status filter: both visits are status=ongoing, so no snapshot # returned assert swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update( origin_url, visit1_id, status='full') with pytest.raises(ValueError): swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']), # Actually add the snapshot and check status filter again swh_storage.snapshot_add([data.complete_snapshot]) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) # Add unknown snapshot to visit2 and check that the inconsistency # is detected swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.snapshot['id']) with pytest.raises(ValueError): swh_storage.snapshot_get_latest( origin_url) # Actually add that snapshot and check that the new one is returned swh_storage.snapshot_add([data.snapshot]) assert{**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) def test_snapshot_get_random(self, swh_storage): swh_storage.snapshot_add( [data.snapshot, data.empty_snapshot, data.complete_snapshot]) assert swh_storage.snapshot_get_random() in { data.snapshot['id'], data.empty_snapshot['id'], data.complete_snapshot['id']} def test_snapshot_missing(self, swh_storage): snap = data.snapshot missing_snap = data.empty_snapshot snapshots = [snap['id'], missing_snap['id']] swh_storage.snapshot_add([snap]) missing_snapshots = swh_storage.snapshot_missing(snapshots) assert list(missing_snapshots) == [missing_snap['id']] def test_stat_counters(self, swh_storage): expected_keys = ['content', 'directory', 'origin', 'revision'] # Initially, all counters are 0 swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: assert counters[key] == 0 # Add a content. Only the content counter should increase. swh_storage.content_add([data.cont]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: if key != 'content': assert counters[key] == 0 assert counters['content'] == 1 # Add other objects. Check their counter increased as well. swh_storage.origin_add_one(data.origin2) origin_visit1 = swh_storage.origin_visit_add( origin=data.origin2['url'], date=data.date_visit2, type=data.type_visit2, ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( data.origin2['url'], origin_visit1['visit'], snapshot=data.snapshot['id']) swh_storage.directory_add([data.dir]) swh_storage.revision_add([data.revision]) swh_storage.release_add([data.release]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert counters['content'] == 1 assert counters['directory'] == 1 assert counters['snapshot'] == 1 assert counters['origin'] == 1 assert counters['origin_visit'] == 1 assert counters['revision'] == 1 assert counters['release'] == 1 assert counters['snapshot'] == 1 if 'person' in counters: assert counters['person'] == 3 def test_content_find_ctime(self, swh_storage): cont = data.cont.copy() del cont['data'] now = datetime.datetime.now(tz=datetime.timezone.utc) cont['ctime'] = now swh_storage.content_add_metadata([cont]) actually_present = swh_storage.content_find({'sha1': cont['sha1']}) # check ctime up to one second dt = actually_present[0]['ctime'] - now assert abs(dt.total_seconds()) <= 1 del actually_present[0]['ctime'] assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } def test_content_find_with_present_content(self, swh_storage): # 1. with something to find cont = data.cont swh_storage.content_add([cont, data.cont2]) actually_present = swh_storage.content_find( {'sha1': cont['sha1']} ) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } # 2. with something to find actually_present = swh_storage.content_find( {'sha1_git': cont['sha1_git']}) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } # 3. with something to find actually_present = swh_storage.content_find( {'sha256': cont['sha256']}) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } # 4. with something to find actually_present = swh_storage.content_find({ 'sha1': cont['sha1'], 'sha1_git': cont['sha1_git'], 'sha256': cont['sha256'], 'blake2s256': cont['blake2s256'], }) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } def test_content_find_with_non_present_content(self, swh_storage): # 1. with something that does not exist missing_cont = data.missing_cont actually_present = swh_storage.content_find( {'sha1': missing_cont['sha1']}) assert actually_present == [] # 2. with something that does not exist actually_present = swh_storage.content_find( {'sha1_git': missing_cont['sha1_git']}) assert actually_present == [] # 3. with something that does not exist actually_present = swh_storage.content_find( {'sha256': missing_cont['sha256']}) assert actually_present == [] def test_content_find_with_duplicate_input(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(duplicate_cont['sha1']) sha1_array[0] += 1 duplicate_cont['sha1'] = bytes(sha1_array) sha1git_array = bytearray(duplicate_cont['sha1_git']) sha1git_array[0] += 1 duplicate_cont['sha1_git'] = bytes(sha1git_array) # Inject the data swh_storage.content_add([cont1, duplicate_cont]) finder = {'blake2s256': duplicate_cont['blake2s256'], 'sha256': duplicate_cont['sha256']} actual_result = list(swh_storage.content_find(finder)) cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] for result in expected_result: assert result in actual_result def test_content_find_with_duplicate_sha256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 for hashalgo in ('sha1', 'sha1_git', 'blake2s256'): value = bytearray(duplicate_cont[hashalgo]) value[0] += 1 duplicate_cont[hashalgo] = bytes(value) swh_storage.content_add([cont1, duplicate_cont]) finder = { 'sha256': duplicate_cont['sha256'] } actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 2 cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] assert expected_result == sorted(actual_result, key=lambda x: x['sha1']) # Find with both sha256 and blake2s256 finder = { 'sha256': duplicate_cont['sha256'], 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 1 actual_result[0].pop('ctime') expected_result = [duplicate_cont] assert actual_result[0] == duplicate_cont def test_content_find_with_duplicate_blake2s256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(duplicate_cont['sha1']) sha1_array[0] += 1 duplicate_cont['sha1'] = bytes(sha1_array) sha1git_array = bytearray(duplicate_cont['sha1_git']) sha1git_array[0] += 1 duplicate_cont['sha1_git'] = bytes(sha1git_array) sha256_array = bytearray(duplicate_cont['sha256']) sha256_array[0] += 1 duplicate_cont['sha256'] = bytes(sha256_array) swh_storage.content_add([cont1, duplicate_cont]) finder = { 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] for result in expected_result: assert result in actual_result # Find with both sha256 and blake2s256 finder = { 'sha256': duplicate_cont['sha256'], 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) actual_result[0].pop('ctime') expected_result = [ duplicate_cont ] assert expected_result == actual_result def test_content_find_bad_input(self, swh_storage): # 1. with bad input with pytest.raises(ValueError): swh_storage.content_find({}) # empty is bad # 2. with bad input with pytest.raises(ValueError): swh_storage.content_find( {'unknown-sha1': 'something'}) # not the right key def test_object_find_by_sha1_git(self, swh_storage): sha1_gits = [b'00000000000000000000'] expected = { b'00000000000000000000': [], } swh_storage.content_add([data.cont]) sha1_gits.append(data.cont['sha1_git']) expected[data.cont['sha1_git']] = [{ 'sha1_git': data.cont['sha1_git'], 'type': 'content', }] swh_storage.directory_add([data.dir]) sha1_gits.append(data.dir['id']) expected[data.dir['id']] = [{ 'sha1_git': data.dir['id'], 'type': 'directory', }] swh_storage.revision_add([data.revision]) sha1_gits.append(data.revision['id']) expected[data.revision['id']] = [{ 'sha1_git': data.revision['id'], 'type': 'revision', }] swh_storage.release_add([data.release]) sha1_gits.append(data.release['id']) expected[data.release['id']] = [{ 'sha1_git': data.release['id'], 'type': 'release', }] ret = swh_storage.object_find_by_sha1_git(sha1_gits) assert expected == ret def test_tool_add(self, swh_storage): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None # does not exist # add it actual_tools = swh_storage.tool_add([tool]) assert len(actual_tools) == 1 actual_tool = actual_tools[0] assert actual_tool is not None # now it exists new_id = actual_tool.pop('id') assert actual_tool == tool actual_tools2 = swh_storage.tool_add([tool]) actual_tool2 = actual_tools2[0] assert actual_tool2 is not None # now it exists new_id2 = actual_tool2.pop('id') assert new_id == new_id2 assert actual_tool == actual_tool2 def test_tool_add_multiple(self, swh_storage): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tools = list(swh_storage.tool_add([tool])) assert len(actual_tools) == 1 new_tools = [tool, { 'name': 'yet-another-tool', 'version': 'version', 'configuration': {}, }] actual_tools = swh_storage.tool_add(new_tools) assert len(actual_tools) == 2 # order not guaranteed, so we iterate over results to check for tool in actual_tools: _id = tool.pop('id') assert _id is not None assert tool in new_tools def test_tool_get_missing(self, swh_storage): tool = { 'name': 'unknown-tool', 'version': '3.1.0rc2-31-ga2cbb8c', 'configuration': {"command_line": "nomossa "}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None def test_tool_metadata_get_missing_context(self, swh_storage): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"context": "unknown-context"}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None def test_tool_metadata_get(self, swh_storage): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"type": "local", "context": "npm"}, } expected_tool = swh_storage.tool_add([tool])[0] # when actual_tool = swh_storage.tool_get(tool) # then assert expected_tool == actual_tool def test_metadata_provider_get(self, swh_storage): # given no_provider = swh_storage.metadata_provider_get(6459456445615) assert no_provider is None # when provider_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) actual_provider = swh_storage.metadata_provider_get(provider_id) expected_provider = { 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] } # then del actual_provider['id'] assert actual_provider, expected_provider def test_metadata_provider_get_by(self, swh_storage): # given no_provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) assert no_provider is None # when provider_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) actual_provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) # then assert provider_id, actual_provider['id'] def test_origin_metadata_add(self, swh_storage): # given origin = data.origin swh_storage.origin_add([origin])[0] tools = swh_storage.tool_add([data.metadata_tool]) tool = tools[0] swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) # when adding for the same origin 2 metadatas n_om = len(list(swh_storage.origin_metadata_get_by(origin['url']))) swh_storage.origin_metadata_add( origin['url'], data.origin_metadata['discovery_date'], provider['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( origin['url'], '2015-01-01 23:00:00+00', provider['id'], tool['id'], data.origin_metadata2['metadata']) n_actual_om = len(list( swh_storage.origin_metadata_get_by(origin['url']))) # then assert n_actual_om == n_om + 2 def test_origin_metadata_get(self, swh_storage): # given origin_url = data.origin['url'] origin_url2 = data.origin2['url'] swh_storage.origin_add([data.origin]) swh_storage.origin_add([data.origin2]) swh_storage.metadata_provider_add(data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) tool = swh_storage.tool_add([data.metadata_tool])[0] # when adding for the same origin 2 metadatas swh_storage.origin_metadata_add( origin_url, data.origin_metadata['discovery_date'], provider['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( origin_url2, data.origin_metadata2['discovery_date'], provider['id'], tool['id'], data.origin_metadata2['metadata']) swh_storage.origin_metadata_add( origin_url, data.origin_metadata2['discovery_date'], provider['id'], tool['id'], data.origin_metadata2['metadata']) all_metadatas = list(sorted(swh_storage.origin_metadata_get_by( origin_url), key=lambda x: x['discovery_date'])) metadatas_for_origin2 = list(swh_storage.origin_metadata_get_by( origin_url2)) expected_results = [{ 'origin_url': origin_url, 'discovery_date': datetime.datetime( 2015, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }, { 'origin_url': origin_url, 'discovery_date': datetime.datetime( 2017, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }] # then assert len(all_metadatas) == 2 assert len(metadatas_for_origin2) == 1 assert all_metadatas == expected_results def test_metadata_provider_add(self, swh_storage): provider = { 'provider_name': 'swMATH', 'provider_type': 'registry', 'provider_url': 'http://www.swmath.org/', 'metadata': { 'email': 'contact@swmath.org', 'license': 'All rights reserved' } } provider['id'] = provider_id = swh_storage.metadata_provider_add( **provider) assert provider == swh_storage.metadata_provider_get_by( {'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/'}) assert provider == swh_storage.metadata_provider_get(provider_id) def test_origin_metadata_get_by_provider_type(self, swh_storage): # given origin_url = data.origin['url'] origin_url2 = data.origin2['url'] swh_storage.origin_add([data.origin]) swh_storage.origin_add([data.origin2]) provider1_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider1 = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) assert provider1 == swh_storage.metadata_provider_get(provider1_id) provider2_id = swh_storage.metadata_provider_add( 'swMATH', 'registry', 'http://www.swmath.org/', {'email': 'contact@swmath.org', 'license': 'All rights reserved'}) provider2 = swh_storage.metadata_provider_get_by({ 'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/' }) assert provider2 == swh_storage.metadata_provider_get(provider2_id) # using the only tool now inserted in the data.sql, but for this # provider should be a crawler tool (not yet implemented) tool = swh_storage.tool_add([data.metadata_tool])[0] # when adding for the same origin 2 metadatas swh_storage.origin_metadata_add( origin_url, data.origin_metadata['discovery_date'], provider1['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( origin_url2, data.origin_metadata2['discovery_date'], provider2['id'], tool['id'], data.origin_metadata2['metadata']) provider_type = 'registry' m_by_provider = list(swh_storage.origin_metadata_get_by( origin_url2, provider_type)) for item in m_by_provider: if 'id' in item: del item['id'] expected_results = [{ 'origin_url': origin_url2, 'discovery_date': datetime.datetime( 2017, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider2['id'], 'provider_name': 'swMATH', 'provider_type': provider_type, 'provider_url': 'http://www.swmath.org/', 'tool_id': tool['id'] }] # then assert len(m_by_provider) == 1 assert m_by_provider == expected_results class TestStorageGeneratedData: def test_generate_content_get(self, swh_storage, swh_contents): contents_with_data = [c for c in swh_contents if c['status'] != 'absent'] # input the list of sha1s we want from storage get_sha1s = [c['sha1'] for c in contents_with_data] # retrieve contents actual_contents = list(swh_storage.content_get(get_sha1s)) assert None not in actual_contents assert_contents_ok(contents_with_data, actual_contents) def test_generate_content_get_metadata(self, swh_storage, swh_contents): # input the list of sha1s we want from storage expected_contents = [c for c in swh_contents if c['status'] != 'absent'] get_sha1s = [c['sha1'] for c in expected_contents] # retrieve contents meta_contents = swh_storage.content_get_metadata(get_sha1s) assert len(list(meta_contents)) == len(get_sha1s) actual_contents = [] for contents in meta_contents.values(): actual_contents.extend(contents) keys_to_check = {'length', 'status', 'sha1', 'sha1_git', 'sha256', 'blake2s256'} assert_contents_ok(expected_contents, actual_contents, keys_to_check=keys_to_check) def test_generate_content_get_range(self, swh_storage, swh_contents): """content_get_range returns complete range""" present_contents = [c for c in swh_contents if c['status'] != 'absent'] get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[2] end = get_sha1s[-2] actual_result = swh_storage.content_get_range(start, end) assert actual_result['next'] is None actual_contents = actual_result['contents'] expected_contents = [c for c in present_contents if start <= c['sha1'] <= end] if expected_contents: assert_contents_ok( expected_contents, actual_contents, ['sha1']) else: assert actual_contents == [] def test_generate_content_get_range_full(self, swh_storage, swh_contents): """content_get_range for a full range returns all available contents""" present_contents = [c for c in swh_contents if c['status'] != 'absent'] start = b'0' * 40 end = b'f' * 40 actual_result = swh_storage.content_get_range(start, end) assert actual_result['next'] is None actual_contents = actual_result['contents'] expected_contents = [c for c in present_contents if start <= c['sha1'] <= end] if expected_contents: assert_contents_ok( expected_contents, actual_contents, ['sha1']) else: assert actual_contents == [] def test_generate_content_get_range_empty(self, swh_storage, swh_contents): """content_get_range for an empty range returns nothing""" start = b'0' * 40 end = b'f' * 40 actual_result = swh_storage.content_get_range(end, start) assert actual_result['next'] is None assert len(actual_result['contents']) == 0 def test_generate_content_get_range_limit_none(self, swh_storage): """content_get_range call with wrong limit input should fail""" with pytest.raises(ValueError) as e: swh_storage.content_get_range(start=None, end=None, limit=None) assert e.value.args == ('Development error: limit should not be None',) def test_generate_content_get_range_no_limit( self, swh_storage, swh_contents): """content_get_range returns contents within range provided""" # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents actual_result = swh_storage.content_get_range(start, end) actual_contents = actual_result['contents'] assert actual_result['next'] is None assert len(actual_contents) == len(get_sha1s) expected_contents = [c for c in swh_contents if c['status'] != 'absent'] assert_contents_ok( expected_contents, actual_contents, ['sha1']) def test_generate_content_get_range_limit(self, swh_storage, swh_contents): """content_get_range paginates results if limit exceeded""" contents_map = {c['sha1']: c for c in swh_contents} # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents limited to n-1 results limited_results = len(get_sha1s) - 1 actual_result = swh_storage.content_get_range( start, end, limit=limited_results) actual_contents = actual_result['contents'] assert actual_result['next'] == get_sha1s[-1] assert len(actual_contents) == limited_results expected_contents = [contents_map[sha1] for sha1 in get_sha1s[:-1]] assert_contents_ok( expected_contents, actual_contents, ['sha1']) # retrieve next part actual_results2 = swh_storage.content_get_range(start=end, end=end) assert actual_results2['next'] is None actual_contents2 = actual_results2['contents'] assert len(actual_contents2) == 1 assert_contents_ok( [contents_map[get_sha1s[-1]]], actual_contents2, ['sha1']) def test_origin_get_range_from_zero(self, swh_storage, swh_origins): actual_origins = list( swh_storage.origin_get_range(origin_from=0, origin_count=0)) assert len(actual_origins) == 0 actual_origins = list( swh_storage.origin_get_range(origin_from=0, origin_count=1)) assert len(actual_origins) == 1 assert actual_origins[0]['id'] == 1 assert actual_origins[0]['url'] == swh_origins[0]['url'] @pytest.mark.parametrize('origin_from,origin_count', [ (1, 1), (1, 10), (1, 20), (1, 101), (11, 0), (11, 10), (91, 11)]) def test_origin_get_range( self, swh_storage, swh_origins, origin_from, origin_count): actual_origins = list( swh_storage.origin_get_range(origin_from=origin_from, origin_count=origin_count)) origins_with_id = list(enumerate(swh_origins, start=1)) expected_origins = [ { 'url': origin['url'], 'id': origin_id, } for (origin_id, origin) in origins_with_id[origin_from-1:origin_from+origin_count-1] ] assert actual_origins == expected_origins @pytest.mark.parametrize('limit', [1, 7, 10, 100, 1000]) def test_origin_list(self, swh_storage, swh_origins, limit): returned_origins = [] page_token = None i = 0 while True: result = swh_storage.origin_list( page_token=page_token, limit=limit) assert len(result['origins']) <= limit returned_origins.extend( origin['url'] for origin in result['origins']) i += 1 page_token = result.get('next_page_token') if page_token is None: assert i*limit >= len(swh_origins) break else: assert len(result['origins']) == limit expected_origins = [origin['url'] for origin in swh_origins] assert sorted(returned_origins) == sorted(expected_origins) ORIGINS = [ 'https://github.com/user1/repo1', 'https://github.com/user2/repo1', 'https://github.com/user3/repo1', 'https://gitlab.com/user1/repo1', 'https://gitlab.com/user2/repo1', 'https://forge.softwareheritage.org/source/repo1', ] def test_origin_count(self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) assert swh_storage.origin_count('github') == 3 assert swh_storage.origin_count('gitlab') == 2 assert swh_storage.origin_count('.*user.*', regexp=True) == 5 assert swh_storage.origin_count('.*user.*', regexp=False) == 0 assert swh_storage.origin_count('.*user1.*', regexp=True) == 2 assert swh_storage.origin_count('.*user1.*', regexp=False) == 0 def test_origin_count_with_visit_no_visits(self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) # none of them have visits, so with_visit=True => 0 assert swh_storage.origin_count('github', with_visit=True) == 0 assert swh_storage.origin_count('gitlab', with_visit=True) == 0 assert swh_storage.origin_count('.*user.*', regexp=True, with_visit=True) == 0 assert swh_storage.origin_count('.*user.*', regexp=False, with_visit=True) == 0 assert swh_storage.origin_count('.*user1.*', regexp=True, with_visit=True) == 0 assert swh_storage.origin_count('.*user1.*', regexp=False, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_no_snapshot( self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) now = datetime.datetime.now(tz=datetime.timezone.utc) swh_storage.origin_visit_add( origin='https://github.com/user1/repo1', date=now, type='git') assert swh_storage.origin_count('github', with_visit=False) == 3 # it has a visit, but no snapshot, so with_visit=True => 0 assert swh_storage.origin_count('github', with_visit=True) == 0 assert swh_storage.origin_count('gitlab', with_visit=False) == 2 # these gitlab origins have no visit assert swh_storage.origin_count('gitlab', with_visit=True) == 0 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=False) == 1 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=True) == 0 assert swh_storage.origin_count('github', regexp=True, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_and_snapshot( self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) now = datetime.datetime.now(tz=datetime.timezone.utc) swh_storage.snapshot_add([data.snapshot]) visit = swh_storage.origin_visit_add( origin='https://github.com/user1/repo1', date=now, type='git') swh_storage.origin_visit_update( origin='https://github.com/user1/repo1', visit_id=visit['visit'], snapshot=data.snapshot['id']) assert swh_storage.origin_count('github', with_visit=False) == 3 # github/user1 has a visit and a snapshot, so with_visit=True => 1 assert swh_storage.origin_count('github', with_visit=True) == 1 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=False) == 1 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=True) == 1 assert swh_storage.origin_count('github', regexp=True, with_visit=True) == 1 @settings(suppress_health_check=[HealthCheck.too_slow]) @given(strategies.lists(objects(), max_size=2)) def test_add_arbitrary(self, swh_storage, objects): for (obj_type, obj) in objects: obj = obj.to_dict() if obj_type == 'origin_visit': origin = obj.pop('origin') swh_storage.origin_add_one({'url': origin}) if 'visit' in obj: del obj['visit'] swh_storage.origin_visit_add( origin, obj['date'], obj['type']) else: method = getattr(swh_storage, obj_type + '_add') try: method([obj]) except HashCollision: pass @pytest.mark.db class TestLocalStorage: """Test the local storage""" # This test is only relevant on the local storage, with an actual # objstorage raising an exception def test_content_add_objstorage_exception(self, swh_storage): swh_storage.objstorage.add = Mock( side_effect=Exception('mocked broken objstorage') ) with pytest.raises(Exception) as e: swh_storage.content_add([data.cont]) assert e.value.args == ('mocked broken objstorage',) missing = list(swh_storage.content_missing([data.cont])) assert missing == [data.cont['sha1']] @pytest.mark.db class TestStorageRaceConditions: @pytest.mark.xfail def test_content_add_race(self, swh_storage): results = queue.Queue() def thread(): try: with db_transaction(swh_storage) as (db, cur): ret = swh_storage.content_add([data.cont], db=db, cur=cur) results.put((threading.get_ident(), 'data', ret)) except Exception as e: results.put((threading.get_ident(), 'exc', e)) t1 = threading.Thread(target=thread) t2 = threading.Thread(target=thread) t1.start() # this avoids the race condition # import time # time.sleep(1) t2.start() t1.join() t2.join() r1 = results.get(block=False) r2 = results.get(block=False) with pytest.raises(queue.Empty): results.get(block=False) assert r1[0] != r2[0] assert r1[1] == 'data', 'Got exception %r in Thread%s' % (r1[2], r1[0]) assert r2[1] == 'data', 'Got exception %r in Thread%s' % (r2[2], r2[0]) @pytest.mark.db class TestPgStorage: """This class is dedicated for the rare case where the schema needs to be altered dynamically. Otherwise, the tests could be blocking when ran altogether. """ def test_content_update_with_new_cols(self, swh_storage): swh_storage.journal_writer = None # TODO, not supported with db_transaction(swh_storage) as (_, cur): cur.execute("""alter table content add column test text default null, add column test2 text default null""") cont = copy.deepcopy(data.cont2) swh_storage.content_add([cont]) cont['test'] = 'value-1' cont['test2'] = 'value-2' swh_storage.content_update([cont], keys=['test', 'test2']) with db_transaction(swh_storage) as (_, cur): cur.execute( '''SELECT sha1, sha1_git, sha256, length, status, test, test2 FROM content WHERE sha1 = %s''', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible', cont['test'], cont['test2']) with db_transaction(swh_storage) as (_, cur): cur.execute("""alter table content drop column test, drop column test2""") def test_content_add_db(self, swh_storage): cont = data.cont actual_result = swh_storage.content_add([cont]) assert actual_result == { 'content:add': 1, 'content:add:bytes': cont['length'], 'skipped_content:add': 0 } if hasattr(swh_storage, 'objstorage'): assert cont['sha1'] in swh_storage.objstorage with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible') expected_cont = cont.copy() del expected_cont['data'] journal_objects = list(swh_storage.journal_writer.objects) for (obj_type, obj) in journal_objects: del obj['ctime'] assert journal_objects == [('content', expected_cont)] def test_content_add_metadata_db(self, swh_storage): cont = data.cont del cont['data'] cont['ctime'] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { 'content:add': 1, 'skipped_content:add': 0 } if hasattr(swh_storage, 'objstorage'): assert cont['sha1'] not in swh_storage.objstorage with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible') assert list(swh_storage.journal_writer.objects) == [('content', cont)] def test_skipped_content_add_db(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 cont2['blake2s256'] = None actual_result = swh_storage.content_add([cont, cont, cont2]) assert actual_result == { 'content:add': 0, 'content:add:bytes': 0, 'skipped_content:add': 2, } with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, blake2s256, ' 'length, status, reason ' 'FROM skipped_content ORDER BY sha1_git') dbdata = cur.fetchall() assert len(dbdata) == 2 assert dbdata[0] == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['blake2s256'], cont['length'], 'absent', 'Content too long') assert dbdata[1] == (cont2['sha1'], cont2['sha1_git'], cont2['sha256'], cont2['blake2s256'], cont2['length'], 'absent', 'Content too long') diff --git a/tox.ini b/tox.ini index 53070466..fe5c8492 100644 --- a/tox.ini +++ b/tox.ini @@ -1,32 +1,34 @@ [tox] envlist=flake8,mypy,py3 [testenv] extras = testing deps = pytest-cov dev: ipdb +passenv = + LOG_CASSANDRA commands = pytest \ !slow: --hypothesis-profile=fast \ slow: --hypothesis-profile=slow \ --cov={envsitepackagesdir}/swh/storage \ {envsitepackagesdir}/swh/storage \ --doctest-modules \ --cov-branch {posargs} [testenv:flake8] skip_install = true deps = flake8 commands = {envpython} -m flake8 [testenv:mypy] extras = testing deps = mypy commands = mypy swh