diff --git a/swh/storage/api/client.py b/swh/storage/api/client.py index 6b0a5ce1..2d283d21 100644 --- a/swh/storage/api/client.py +++ b/swh/storage/api/client.py @@ -1,103 +1,103 @@ # 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 json import requests from swh.core.hashutil import hash_to_hex from swh.core.json import SWHJSONDecoder, SWHJSONEncoder class RemoteStorage(): """Proxy to a remote storage API""" def __init__(self, base_url): self.base_url = base_url def url(self, endpoint): return '%s%s' % (self.base_url, endpoint) def post(self, endpoint, data): raw_data = json.dumps(data, cls=SWHJSONEncoder) response = requests.post( self.url(endpoint), data=raw_data, headers={'content-type': 'application/json; charset=utf8'}, ) return response.json(cls=SWHJSONDecoder) def post_files(self, endpoint, data, files): raw_data = json.dumps(data, cls=SWHJSONEncoder) files['metadata'] = raw_data response = requests.post( self.url(endpoint), files=files, ) return response.json(cls=SWHJSONDecoder) def get(self, endpoint, data): response = requests.get( self.url(endpoint), params=data, ) if response.status_code == 404: return None else: return response.json(cls=SWHJSONDecoder) def content_add(self, content): files = {} for file in content: if file.get('status', 'visible') != 'visible': continue file_id = hash_to_hex(file['sha1']) files[file_id] = file.pop('data') return self.post_files('content/add', {'content': content}, files) def content_missing(self, content, key_hash='sha1'): return self.post('content/missing', {'content': content, 'key_hash': key_hash}) - def content_present(self, content): + def content_find(self, content): return self.post('content/present', {'content': content}) def directory_add(self, directories): return self.post('directory/add', {'directories': directories}) def directory_missing(self, directories): return self.post('directory/missing', {'directories': directories}) def directory_get(self, directory): return [tuple(entry) for entry in self.get('directory', {'directory': directory})] def revision_add(self, revisions): return self.post('revision/add', {'revisions': revisions}) def revision_missing(self, revisions): return self.post('revision/missing', {'revisions': revisions}) def release_add(self, releases): return self.post('release/add', {'releases': releases}) def release_missing(self, releases): return self.post('release/missing', {'releases': releases}) def occurrence_add(self, occurrences): return self.post('occurrence/add', {'occurrences': occurrences}) def origin_get(self, origin): origin = self.get('origin', origin) if not origin: return None else: return origin['id'] def origin_add_one(self, origin): return self.post('origin', {'origin': origin}) diff --git a/swh/storage/api/server.py b/swh/storage/api/server.py index 9e22fab9..3ba4c9a8 100644 --- a/swh/storage/api/server.py +++ b/swh/storage/api/server.py @@ -1,153 +1,153 @@ # 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 json import logging from flask import Flask, Request, Response, abort, g, request from swh.core import config from swh.core.json import SWHJSONDecoder, SWHJSONEncoder from swh.core.hashutil import hash_to_hex from swh.storage import Storage DEFAULT_CONFIG = { 'db': ('str', 'dbname=softwareheritage-dev'), 'storage_base': ('str', '/tmp/swh-storage/test'), } class BytesRequest(Request): """Request with proper escaping of arbitrary byte sequences.""" encoding = 'utf-8' encoding_errors = 'surrogateescape' app = Flask(__name__) app.json_encoder = SWHJSONEncoder app.json_decoder = SWHJSONDecoder app.request_class = BytesRequest def jsonify(data): return Response( json.dumps(data, cls=SWHJSONEncoder), mimetype='application/json', ) @app.before_request def before_request(): g.storage = Storage(app.config['db'], app.config['storage_base']) @app.route('/') def index(): return 'Hello' @app.route('/content/missing', methods=['POST']) def content_missing(): return jsonify(g.storage.content_missing(**request.json)) @app.route('/content/present', methods=['POST']) -def content_present(): - return jsonify(g.storage.content_present(**request.json)) +def content_find(): + return jsonify(g.storage.content_find(**request.json)) @app.route('/content/add', methods=['POST']) def content_add(): json_data = request.files['metadata'].read().decode('utf-8') metadata = json.loads(json_data, cls=SWHJSONDecoder)['content'] for file_data in metadata: if file_data.get('status', 'visible') == 'visible': file_id = hash_to_hex(file_data['sha1']) file = request.files[file_id] file_data['data'] = file.read() file.close() return jsonify(g.storage.content_add(content=metadata)) @app.route('/directory/missing', methods=['POST']) def directory_missing(): return jsonify(g.storage.directory_missing(**request.json)) @app.route('/directory/add', methods=['POST']) def directory_add(): return jsonify(g.storage.directory_add(**request.json)) @app.route('/directory', methods=['GET']) def directory_get(): dir = request.args['directory'].encode('utf-8', 'surrogateescape') return jsonify(g.storage.directory_get(dir)) @app.route('/revision/add', methods=['POST']) def revision_add(): return jsonify(g.storage.revision_add(**request.json)) @app.route('/revision/missing', methods=['POST']) def revision_missing(): return jsonify(g.storage.revision_missing(**request.json)) @app.route('/release/add', methods=['POST']) def release_add(): return jsonify(g.storage.release_add(**request.json)) @app.route('/release/missing', methods=['POST']) def release_missing(): return jsonify(g.storage.release_missing(**request.json)) @app.route('/occurrence/add', methods=['POST']) def occurrence_add(): return jsonify(g.storage.occurrence_add(**request.json)) @app.route('/origin', methods=['GET']) def origin_get(): origin = { 'type': request.args['type'], 'url': request.args['url'], } id = g.storage.origin_get(origin) if not id: abort(404) else: origin['id'] = id return jsonify(origin) @app.route('/origin', methods=['POST']) def origin_add_one(): return jsonify(g.storage.origin_add_one(**request.json)) def run_from_webserver(environ, start_response): """Run the WSGI app from the webserver, loading the configuration.""" config_path = '/etc/softwareheritage/storage/storage.ini' app.config.update(config.read(config_path, DEFAULT_CONFIG)) handler = logging.StreamHandler() app.logger.addHandler(handler) return app(environ, start_response) if __name__ == '__main__': import sys app.config.update(config.read(sys.argv[1], DEFAULT_CONFIG)) app.run(debug=True) diff --git a/swh/storage/db.py b/swh/storage/db.py index aebc571b..07200db1 100644 --- a/swh/storage/db.py +++ b/swh/storage/db.py @@ -1,208 +1,218 @@ # 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 binascii import functools import psycopg2 import tempfile from contextlib import contextmanager TMP_CONTENT_TABLE = 'tmp_content' def stored_procedure(stored_proc): """decorator to execute remote stored procedure, specified as argument Generally, the body of the decorated function should be empty. If it is not, the stored procedure will be executed first; the function body then. """ def wrap(meth): @functools.wraps(meth) def _meth(self, *args, **kwargs): cur = kwargs.get('cur', None) self._cursor(cur).execute('SELECT %s()' % stored_proc) meth(self, *args, **kwargs) return _meth return wrap def entry_to_bytes(entry): """Convert an entry coming from the database to bytes""" if isinstance(entry, memoryview): return entry.tobytes() return entry def line_to_bytes(line): """Convert a line coming from the database to bytes""" return line.__class__(entry_to_bytes(entry) for entry in line) def cursor_to_bytes(cursor): """Yield all the data from a cursor as bytes""" yield from (line_to_bytes(line) for line in cursor) class Db: """Proxy to the SWH DB, with wrappers around stored procedures """ @classmethod def connect(cls, *args, **kwargs): """factory method to create a DB proxy Accepts all arguments of psycopg2.connect; only some specific possibilities are reported below. Args: connstring: libpq2 connection string """ conn = psycopg2.connect(*args, **kwargs) return cls(conn) def _cursor(self, cur_arg): """get a cursor: from cur_arg if given, or a fresh one otherwise meant to avoid boilerplate if/then/else in methods that proxy stored procedures """ if cur_arg is not None: return cur_arg # elif self.cur is not None: # return self.cur else: return self.conn.cursor() def __init__(self, conn): """create a DB proxy Args: conn: psycopg2 connection to the SWH DB """ self.conn = conn @contextmanager def transaction(self): """context manager to execute within a DB transaction Yields: a psycopg2 cursor """ with self.conn.cursor() as cur: try: yield cur self.conn.commit() except: if not self.conn.closed: self.conn.rollback() raise def mktemp(self, tblname, cur=None): self._cursor(cur).execute('SELECT swh_mktemp(%s)', (tblname,)) def mktemp_dir_entry(self, entry_type, cur=None): self._cursor(cur).execute('SELECT swh_mktemp_dir_entry(%s)', (('directory_entry_%s' % entry_type),)) @stored_procedure('swh_mktemp_revision') def mktemp_revision(self, cur=None): pass @stored_procedure('swh_mktemp_release') def mktemp_release(self, cur=None): pass def copy_to(self, items, tblname, columns, cur=None, item_cb=None): def escape(data): if data is None: return '' if isinstance(data, bytes): return '\\x%s' % binascii.hexlify(data).decode('ascii') elif isinstance(data, str): return '"%s"' % data.replace('"', '""') else: return str(data) with tempfile.TemporaryFile('w+') as f: for d in items: if item_cb is not None: item_cb(d) line = [escape(d.get(k)) for k in columns] f.write(','.join(line)) f.write('\n') f.seek(0) self._cursor(cur).copy_expert('COPY %s (%s) FROM STDIN CSV' % ( tblname, ', '.join(columns)), f) @stored_procedure('swh_content_add') def content_add_from_temp(self, cur=None): pass @stored_procedure('swh_skipped_content_add') def skipped_content_add_from_temp(self, cur=None): pass @stored_procedure('swh_revision_add') def revision_add_from_temp(self, cur=None): pass @stored_procedure('swh_release_add') def release_add_from_temp(self, cur=None): pass def content_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute("""SELECT sha1, sha1_git, sha256 FROM swh_content_missing()""") yield from cursor_to_bytes(cur) def skipped_content_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute("""SELECT sha1, sha1_git, sha256 FROM swh_skipped_content_missing()""") yield from cursor_to_bytes(cur) - def content_present(self, column_key, hash, cur=None): + def content_find(self, sha1=None, sha1_git=None, sha256=None, cur=None): + """Find the content optionally on a combination of the following + checksums sha1, sha1_git or sha256. + + Args: + sha1: sha1 content + git_sha1: the sha1 computed `a la git` sha1 of the content + sha256: sha256 content + + Returns: + The content if found or null. + + """ cur = self._cursor(cur) - escaped_query = """SELECT {0} - FROM content - WHERE {0}=%s - LIMIT 1""".format(column_key) - cur.execute(escaped_query, (hash, )) + cur.execute("""SELECT sha1, sha1_git, sha256 + FROM swh_content_find(%s, %s, %s) + LIMIT 1""", (sha1, sha1_git, sha256)) yield from cursor_to_bytes(cur) def directory_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT * FROM swh_directory_missing()') yield from cursor_to_bytes(cur) def directory_walk_one(self, directory, cur=None): cur = self._cursor(cur) cur.execute('SELECT * FROM swh_directory_walk_one(%s)', (directory,)) yield from cursor_to_bytes(cur) def revision_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT id FROM swh_revision_missing() as r(id)') yield from cursor_to_bytes(cur) def release_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT id FROM swh_release_missing() as r(id)') yield from cursor_to_bytes(cur) diff --git a/swh/storage/storage.py b/swh/storage/storage.py index d1381a91..8b4aded2 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,520 +1,526 @@ # 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 functools import itertools import psycopg2 from collections import defaultdict from operator import itemgetter from .db import Db from .objstorage import ObjStorage def db_transaction(meth): """decorator to execute Storage methods within DB transactions The decorated method must accept a `cur` keyword argument """ @functools.wraps(meth) def _meth(self, *args, **kwargs): with self.db.transaction() as cur: return meth(self, *args, cur=cur, **kwargs) return _meth def db_transaction_generator(meth): """decorator to execute Storage methods within DB transactions, while returning a generator The decorated method must accept a `cur` keyword argument """ @functools.wraps(meth) def _meth(self, *args, **kwargs): with self.db.transaction() as cur: yield from meth(self, *args, cur=cur, **kwargs) 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) 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 (default: -1) - one key for each checksum algorithm in swh.core.hashutil.ALGORITHMS, mapped to the corresponding checksum - status (str): one of visible, hidden, absent - reason (str): if status = absent, the reason why - origin (int): if status = absent, the origin we saw the content in """ db = self.db content_by_status = defaultdict(list) for d in content: if 'status' not in d: d['status'] = 'visible' if 'length' not in d: d['length'] = -1 content_by_status[d['status']].append(d) content_with_data = content_by_status['visible'] content_without_data = content_by_status['absent'] missing_content = set(self.content_missing(content_with_data)) missing_skipped = set( sha1_git for sha1, sha1_git, sha256 in self.skipped_content_missing(content_without_data)) with db.transaction() as cur: if missing_content: # 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']) content_filtered = (cont for cont in content_with_data if cont['sha1'] in missing_content) db.copy_to(content_filtered, 'tmp_content', ['sha1', 'sha1_git', 'sha256', 'length', 'status'], cur, item_cb=add_to_objstorage) # move metadata in place db.content_add_from_temp(cur) if missing_skipped: missing_filtered = (cont for cont in content_without_data if cont['sha1_git'] in missing_skipped) db.mktemp('skipped_content', cur) db.copy_to(missing_filtered, 'tmp_skipped_content', ['sha1', 'sha1_git', 'sha256', 'length', 'reason', 'status', 'origin'], cur) # move metadata in place db.skipped_content_add_from_temp(cur) @db_transaction_generator def content_missing(self, content, key_hash='sha1', cur=None): """List content missing from storage Args: content: iterable of dictionaries containing one key for each checksum algorithm in swh.core.hashutil.ALGORITHMS, mapped to the corresponding checksum, and a length key mapped to the content length. key_hash: the name of the hash used as key (default: 'sha1') Returns: an iterable of `key_hash`es missing from the storage Raises: TODO: an exception when we get a hash collision. """ db = self.db keys = ['sha1', 'sha1_git', 'sha256'] if key_hash not in keys: raise ValueError("key_hash should be one of %s" % keys) key_hash_idx = keys.index(key_hash) # Create temporary table for metadata injection db.mktemp('content', cur) db.copy_to(content, 'tmp_content', keys + ['length'], cur) for obj in db.content_missing_from_temp(cur): yield obj[key_hash_idx] @db_transaction_generator def skipped_content_missing(self, content, cur=None): """List skipped_content missing from storage Args: content: iterable of dictionaries containing the data for each checksum algorithm. Returns: an iterable of signatures missing from the storage """ keys = ['sha1', 'sha1_git', 'sha256'] db = self.db db.mktemp('skipped_content', cur) db.copy_to(content, 'tmp_skipped_content', keys + ['length', 'reason'], cur) yield from db.skipped_content_missing_from_temp(cur) @db_transaction - def content_present(self, content, cur=None): + def content_find(self, content, cur=None): """Predicate to check the presence of a content's hashes. Args: hashes: iterable of dictionaries representing individual pieces of hash. Each dictionary has the following keys: - - a key for each checksum algorithm in swh.core.hashutil.ALGORITHMS, + - a key for each checksum algorithm in swh.core.hashutil.ALGORITHMS mapped to the corresponding checksum Returns: a boolean indicator of presence Raises: ValueError in case the key of the dictionary is not sha1 nor sha256 """ db = self.db # filter out the checksums - if 'sha1' in content: - column_key = 'sha1' - elif 'sha256' in content: - column_key = 'sha256' - else: - raise ValueError('Key must be one of sha1, sha256.') + keys = ['sha1', 'sha1_git', 'sha256'] - # format the output - found_hashes = db.content_present(column_key, - content[column_key], - cur) + if content == {}: + raise ValueError('Key must be one of sha1, git_sha1, sha256.') - return len(list(found_hashes)) > 0 + for key in content.keys(): + if key not in keys: + raise ValueError('Key must be one of sha1, git_sha1, sha256.') + + # format the output + found_hashes = db.content_find(sha1=content.get('sha1'), + sha1_git=content.get('sha1_git'), + sha256=content.get('sha256'), + cur=cur) + + hashes = list(found_hashes) + if len(hashes) > 0: + return hashes[0] != (None, None, None) + return False def directory_add(self, directories): """Add directories to the storage Args: directories: iterable of dictionaries representing the individual directories to add. Each dict has the following keys: - id (sha1_git): the id of the directory to add - entries (list): list of dicts for each entry in the directory. Each dict has the following keys: - name (bytes) - type (one of 'file', 'dir', 'rev'): type of the directory entry (file, directory, revision) - target (sha1_git): id of the object pointed at by the directory entry - perms (int): entry permissions - atime (datetime.DateTime): entry access time - ctime (datetime.DateTime): entry creation time - mtime (datetime.DateTime): entry modification time """ dirs = set() dir_entries = { 'file': defaultdict(list), 'dir': defaultdict(list), 'rev': defaultdict(list), } for cur_dir in directories: dir_id = cur_dir['id'] dirs.add(dir_id) for entry in cur_dir['entries']: entry['dir_id'] = dir_id dir_entries[entry['type']][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs)) if not dirs_missing: return db = self.db with db.transaction() as cur: dirs_missing_dict = ({'id': dir} for dir in dirs_missing) db.copy_to(dirs_missing_dict, 'directory', ['id'], cur) for entry_type, entry_list in dir_entries.items(): entries = itertools.chain.from_iterable( entries_for_dir for dir_id, entries_for_dir in entry_list.items() if dir_id in dirs_missing) db.mktemp_dir_entry(entry_type) db.copy_to( entries, 'tmp_directory_entry_%s' % entry_type, ['target', 'name', 'perms', 'atime', 'mtime', 'ctime', 'dir_id'], cur, ) cur.execute('SELECT swh_directory_entry_%s_add()' % entry_type) @db_transaction_generator def directory_missing(self, directories, cur): """List directories missing from storage Args: an iterable of directory ids Returns: a list of missing directory ids """ db = self.db # Create temporary table for metadata injection db.mktemp('directory', cur) directories_dicts = ({'id': dir} for dir in directories) db.copy_to(directories_dicts, 'tmp_directory', ['id'], cur) for obj in db.directory_missing_from_temp(cur): yield obj[0] def directory_get(self, directory): """Get the entries for one directory""" yield from self.db.directory_walk_one(directory) def revision_add(self, revisions): """Add revisions to the storage Args: revisions: iterable of dictionaries representing the individual revisions to add. Each dict has the following keys: - id (sha1_git): id of the revision to add - date (datetime.DateTime): date the revision was written - date_offset (int): offset from UTC in minutes the revision was written - committer_date (datetime.DateTime): date the revision got added to the origin - committer_date_offset (int): offset from UTC in minutes the revision was added to the origin - type (one of 'git', 'tar'): type of the revision added - directory (sha1_git): the directory the revision points at - message (bytes): the message associated with the revision - author_name (bytes): the name of the revision author - author_email (bytes): the email of the revision author - committer_name (bytes): the name of the revision committer - committer_email (bytes): the email of the revision committer - parents (list of sha1_git): the parents of this revision """ db = self.db parents = {} for revision in revisions: id = revision['id'] cur_parents = enumerate(revision.get('parents', [])) parents[id] = [{ 'id': id, 'parent_id': parent, 'parent_rank': i } for i, parent in cur_parents] revisions_missing = list(self.revision_missing(parents.keys())) if not revisions_missing: return with db.transaction() as cur: db.mktemp_revision(cur) revisions_filtered = (revision for revision in revisions if revision['id'] in revisions_missing) db.copy_to(revisions_filtered, 'tmp_revision', ['id', 'date', 'date_offset', 'committer_date', 'committer_date_offset', 'type', 'directory', 'message', 'author_name', 'author_email', 'committer_name', 'committer_email'], cur) db.revision_add_from_temp(cur) parents_filtered = itertools.chain.from_iterable( parents[id] for id in revisions_missing) db.copy_to(parents_filtered, 'revision_history', ['id', 'parent_id', 'parent_rank'], cur) @db_transaction_generator def revision_missing(self, revisions, cur): """List revisions missing from storage Args: an iterable of revision ids Returns: a list of missing revision ids """ db = self.db # Create temporary table for metadata injection db.mktemp('revision', cur) revisions_dicts = ({'id': dir, 'type': 'git'} for dir in revisions) db.copy_to(revisions_dicts, 'tmp_revision', ['id', 'type'], cur) for obj in db.revision_missing_from_temp(cur): yield obj[0] def release_add(self, releases): """Add releases to the storage Args: releases: iterable of dictionaries representing the individual releases to add. Each dict has the following keys: - id (sha1_git): id of the release to add - revision (sha1_git): id of the revision the release points to - date (datetime.DateTime): the date the release was made - date_offset (int): offset from UTC in minutes the release was made - name (bytes): the name of the release - comment (bytes): the comment associated with the release - author_name (bytes): the name of the release author - author_email (bytes): the email of the release author """ db = self.db release_ids = set(release['id'] for release in releases) releases_missing = list(self.release_missing(release_ids)) if not releases_missing: return with db.transaction() as cur: db.mktemp_release(cur) releases_filtered = (release for release in releases if release['id'] in releases_missing) db.copy_to(releases_filtered, 'tmp_release', ['id', 'revision', 'date', 'date_offset', 'name', 'comment', 'author_name', 'author_email'], cur) db.release_add_from_temp(cur) @db_transaction_generator def release_missing(self, releases, cur=None): """List releases missing from storage Args: an iterable of release ids Returns: a list of missing release ids """ db = self.db # Create temporary table for metadata injection db.mktemp('release', cur) releases_dicts = ({'id': rel} for rel in releases) db.copy_to(releases_dicts, 'tmp_release', ['id'], cur) for obj in db.release_missing_from_temp(cur): yield obj[0] @db_transaction def occurrence_add(self, occurrences, cur=None): """Add occurrences to the storage Args: occurrences: iterable of dictionaries representing the individual occurrences to add. Each dict has the following keys: - origin (int): id of the origin corresponding to the occurrence - branch (str): the reference name of the occurrence - revision (sha1_git): the id of the revision pointed to by the occurrence - authority (int): id of the authority giving the validity - validity (datetime.DateTime): the validity date for the given occurrence """ db = self.db processed = [] for occurrence in occurrences: occ = occurrence.copy() occ['validity'] = '[%s,infinity)' % str(occ['validity']) processed.append(occ) # XXX: will fail on second execution db.copy_to(processed, 'occurrence_history', ['origin', 'branch', 'revision', 'authority', 'validity'], cur) @db_transaction def origin_get(self, origin, cur=None): """Return the id of the given origin Args: origin: dictionary representing the individual origin to find. This dict has the following keys: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to Returns: the id of the queried origin """ query = "select id from origin where type=%s and url=%s" cur.execute(query, (origin['type'], origin['url'])) data = cur.fetchone() if not data: return None else: return data[0] @db_transaction def origin_add_one(self, origin, cur=None): """Add origin to the storage Args: origin: dictionary representing the individual origin to add. This dict has the following keys: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to Returns: the id of the added origin, or of the identical one that already exists. """ query = "select id from origin where type=%s and url=%s" cur.execute(query, (origin['type'], origin['url'])) data = cur.fetchone() if data: return data[0] insert = """insert into origin (type, url) values (%s, %s) returning id""" cur.execute(insert, (origin['type'], origin['url'])) return cur.fetchone()[0] diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index c9416e8c..e62966a9 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,261 +1,298 @@ # 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 datetime import shutil import tempfile import unittest from nose.tools import istest from nose.plugins.attrib import attr from .db_testing import DbTestFixture from swh.core.hashutil import hex_to_hash from swh.storage import Storage @attr('db') class AbstractTestStorage(DbTestFixture): """Base class for Storage testing. This class is used as-is to test local storage (see TestStorage 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. """ def setUp(self): super().setUp() self.objroot = tempfile.mkdtemp() self.storage = Storage(self.conn, self.objroot) self.cont = { 'data': b'42\n', 'length': 3, 'sha1': hex_to_hash( '34973274ccef6ab4dfaaf86599792fa9c3fe4689'), 'sha1_git': hex_to_hash( 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), 'sha256': hex_to_hash( '673650f936cb3b0a2f93ce09d81be107' '48b1b203c19e8176b4eefc1964a0cf3a'), } self.cont2 = { 'data': b'4242\n', 'length': 5, 'sha1': hex_to_hash( '61c2b3a30496d329e21af70dd2d7e097046d07b7'), 'sha1_git': hex_to_hash( '36fade77193cb6d2bd826161a0979d64c28ab4fa'), 'sha256': hex_to_hash( '859f0b154fdb2d630f45e1ecae4a8629' '15435e663248bb8461d914696fc047cd'), } self.missing_cont = { 'data': b'missing\n', 'length': 8, 'sha1': hex_to_hash( 'f9c24e2abb82063a3ba2c44efd2d3c797f28ac90'), 'sha1_git': hex_to_hash( '33e45d56f88993aae6a0198013efa80716fd8919'), 'sha256': hex_to_hash( '6bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), } self.skipped_cont = { 'length': 1024 * 1024 * 200, 'sha1_git': hex_to_hash( '33e45d56f88993aae6a0198013efa80716fd8920'), 'reason': 'Content too long', 'status': 'absent', } self.dir = { 'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa90', 'entries': [ { 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': 0o644, 'atime': None, 'ctime': None, 'mtime': None, }, { 'name': b'bar\xc3', 'type': 'dir', 'target': b'12345678901234567890', 'perms': 0o2000, 'atime': None, 'ctime': None, 'mtime': None, }, ], } self.revision = { 'id': b'56789012345678901234', 'message': 'hello', 'author_name': 'Nicolas Dandrimont', 'author_email': 'nicolas@example.com', 'committer_name': 'Stefano Zacchiroli', 'committer_email': 'stefano@example.com', 'parents': [b'01234567890123456789'], 'date': datetime.datetime(2015, 1, 1, 22, 0, 0), 'date_offset': 120, 'committer_date': datetime.datetime(2015, 1, 2, 22, 0, 0), 'committer_date_offset': -120, 'type': 'git', 'directory': self.dir['id'], } self.origin = { 'url': 'file:///dev/null', 'type': 'git', } self.origin2 = { 'url': 'file:///dev/zero', 'type': 'git', } self.occurrence = { 'branch': 'master', 'revision': b'67890123456789012345', 'authority': 1, 'validity': datetime.datetime(2015, 1, 1, 23, 0, 0), } def tearDown(self): shutil.rmtree(self.objroot) super().tearDown() @istest def content_add(self): cont = self.cont self.storage.content_add([cont]) if hasattr(self.storage, 'objstorage'): self.assertIn(cont['sha1'], self.storage.objstorage) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = self.cursor.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) @istest def skipped_content_add(self): cont = self.skipped_cont self.storage.content_add([self.skipped_cont]) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status,' 'reason FROM skipped_content WHERE sha1_git = %s', (cont['sha1_git'],)) datum = self.cursor.fetchone() self.assertEqual( (datum[0], datum[1].tobytes(), datum[2], datum[3], datum[4], datum[5]), (None, cont['sha1_git'], None, cont['length'], 'absent', 'Content too long')) @istest def content_missing(self): cont2 = self.cont2 missing_cont = self.missing_cont self.storage.content_add([cont2]) gen = self.storage.content_missing([cont2, missing_cont]) self.assertEqual(list(gen), [missing_cont['sha1']]) @istest - def content_present(self): - ### with something to find + def content_find_with_present_content(self): + # 1. with something to find cont = self.cont self.storage.content_add([cont]) - actually_present = self.storage.content_present({'sha1': cont['sha1']}) + actually_present = self.storage.content_find({'sha1': cont['sha1']}) self.assertEquals(actually_present, True, "Should be present") - ### with something that does not exist + # 2. with something to find + actually_present = self.storage.content_find( + {'sha1_git': cont['sha1_git']}) + + self.assertEquals(actually_present, True, "Should be present") + + # 3. with something to find + actually_present = self.storage.content_find( + {'sha256': cont['sha256']}) + + self.assertEquals(actually_present, True, "Should be present") + + # 4. with something to find + actually_present = self.storage.content_find( + {'sha1': cont['sha1'], + 'sha1_git': cont['sha1_git'], + 'sha256': cont['sha256']}) + + self.assertEquals(actually_present, True, "Should be present") + + @istest + def content_find_with_non_present_content(self): + # 1. with something that does not exist missing_cont = self.missing_cont - actually_present = self.storage.content_present( + actually_present = self.storage.content_find( + {'sha1': missing_cont['sha1']}) + + self.assertEquals(actually_present, False, "Should be missing") + + # 2. with something that does not exist + actually_present = self.storage.content_find( + {'sha1_git': missing_cont['sha1_git']}) + + self.assertEquals(actually_present, False, "Should be missing") + + # 3. with something that does not exist + actually_present = self.storage.content_find( {'sha256': missing_cont['sha256']}) self.assertEquals(actually_present, False, "Should be missing") - ### 1. with bad input + @istest + def content_find_bad_input(self): + # 1. with bad input with self.assertRaises(ValueError): - self.storage.content_present({}) + self.storage.content_find({}) # empty is bad - ### 2. with bad input + # 2. with bad input with self.assertRaises(ValueError): - self.storage.content_present({'sha-bla': '123'}) # only sha1 and sha256 + self.storage.content_find( + {'unknown-sha1': 'something'}) # not the right key @istest def directory_add(self): init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) self.storage.directory_add([self.dir]) stored_data = list(self.storage.directory_get(self.dir['id'])) data_to_store = [ (self.dir['id'], ent['type'], ent['target'], ent['name'], ent['perms'], ent['atime'], ent['ctime'], ent['mtime']) for ent in sorted(self.dir['entries'], key=lambda ent: ent['name']) ] self.assertEqual(data_to_store, stored_data) after_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([], after_missing) @istest def revision_add(self): init_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([self.revision['id']], list(init_missing)) self.storage.revision_add([self.revision]) end_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([], list(end_missing)) @istest def origin_add(self): self.assertIsNone(self.storage.origin_get(self.origin)) id = self.storage.origin_add_one(self.origin) self.assertEqual(self.storage.origin_get(self.origin), id) @istest def occurrence_add(self): origin_id = self.storage.origin_add_one(self.origin2) revision = self.revision.copy() revision['id'] = self.occurrence['revision'] self.storage.revision_add([revision]) self.occurrence['origin'] = origin_id self.storage.occurrence_add([self.occurrence]) class TestStorage(AbstractTestStorage, unittest.TestCase): """Test the local storage""" pass