diff --git a/swh/storage/storage.py b/swh/storage/storage.py index ed503a58..8d6efe17 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,81 +1,81 @@ # Copyright (C) 2015 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 psycopg2 import tempfile from .db import Db from .objstorage import ObjStorage def db_transaction(meth): """decorator to execute Storage methods within DB transactions Decorated methods will have access to the following attributes: self.cur: psycopg2 DB cursor """ def _meth(self, *args, **kwargs): with self.db.transaction() as cur: try: self.cur = cur meth(self, *args, **kwargs) finally: self.cur = None return _meth class Storage(): """SWH storage proxy, encompassing DB and object storage """ def __init__(self, db_conn, obj_root): """ Args: db_conn: either a libpq connection string, or a psycopg2 connection obj_root: path to the root of the object storage """ if isinstance(db_conn, psycopg2.extensions.connection): self.db = Db(db_conn) else: self.db = Db.connect(db_conn) self.objstorage = ObjStorage(obj_root) @db_transaction - def add_content(self, content): + def content_add(self, content): """Add content blobs to the storage Note: in case of DB errors, objects might have already been added to the object storage and will not be removed. Since addition to the object storage is idempotent, that should not be a problem. Args: content: iterable of dictionaries representing individual pieces of content to add. Each dictionary has the following keys: - data (bytes): the actual content - length (int): content length - one key for each checksum algorithm in swh.core.hashutil(ALGORITHMS), mapped to the corresponding checksum """ (db, cur) = (self.db, self.cur) # create temporary table for metadata injection db.mktemp('content', cur) def add_to_objstorage(cont): self.objstorage.add_bytes(cont['data'], obj_id=cont['sha1']) db.copy_to(content, 'tmp_content', ['sha1', 'sha1_git', 'sha256', 'length'], cur, item_cb=add_to_objstorage) # move metadata in place db.content_add_from_temp(cur) db.conn.commit() diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index 94c7f3ae..6fde0b48 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,45 +1,45 @@ # Copyright (C) 2015 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 shutil import tempfile import unittest from nose.tools import istest from nose.plugins.attrib import attr from .db_testing import DbTestFixture from swh.storage import Storage @attr('db') class TestStorage(DbTestFixture, unittest.TestCase): def setUp(self): super().setUp() self.objroot = tempfile.mkdtemp() self.storage = Storage(self.conn, self.objroot) def tearDown(self): shutil.rmtree(self.objroot) super().tearDown() @istest - def add_content(self): + def content_add(self): cont = { 'data': b'42\n', 'length': 3, 'sha1': '34973274ccef6ab4dfaaf86599792fa9c3fe4689', 'sha1_git': 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd', 'sha256': '673650f936cb3b0a2f93ce09d81be10748b1b203c19e8176b4eefc1964a0cf3a' # NOQA } - self.storage.add_content([cont]) + self.storage.content_add([cont]) self.assertIn(cont['sha1'], self.storage.objstorage) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) self.assertEqual(self.cursor.fetchone(), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible'))