diff --git a/swh/storage/api/client.py b/swh/storage/api/client.py index 6054942a..b08a91d0 100644 --- a/swh/storage/api/client.py +++ b/swh/storage/api/client.py @@ -1,141 +1,141 @@ # 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 pickle import requests from swh.core.serializers import msgpack_dumps, msgpack_loads, SWHJSONDecoder def encode_data(data): return msgpack_dumps(data) def decode_response(response): content_type = response.headers['content-type'] if content_type.startswith('application/x-msgpack'): r = msgpack_loads(response.content) elif content_type.startswith('application/json'): r = response.json(cls=SWHJSONDecoder) else: raise ValueError('Wrong content type `%s` for API response' % content_type) return r class RemoteStorage(): """Proxy to a remote storage API""" def __init__(self, base_url): self.base_url = base_url self.session = requests.Session() def url(self, endpoint): return '%s%s' % (self.base_url, endpoint) def post(self, endpoint, data): response = self.session.post( self.url(endpoint), data=encode_data(data), headers={'content-type': 'application/x-msgpack'}, ) # XXX: this breaks language-independence and should be # replaced by proper unserialization if response.status_code == 400: raise pickle.loads(decode_response(response)) return decode_response(response) def get(self, endpoint, data=None): response = self.session.get( self.url(endpoint), params=data, ) if response.status_code == 404: return None # XXX: this breaks language-independence and should be # replaced by proper unserialization if response.status_code == 400: raise pickle.loads(decode_response(response)) else: return decode_response(response) def content_add(self, content): return self.post('content/add', {'content': content}) def content_missing(self, content, key_hash='sha1'): return self.post('content/missing', {'content': content, 'key_hash': key_hash}) def content_exist(self, content): return self.post('content/present', {'content': content}) def content_find_occurrence(self, content): return self.post('content/occurrence', {'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 directory_get(self, directory, recursive=False): + return self.get('directory', {'directory': directory, + 'recursive': recursive}) def revision_get(self, revisions): return self.post('revision', {'revisions': revisions}) 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}) def fetch_history_start(self, origin_id): return self.post('fetch_history/start', {'origin_id': origin_id}) def fetch_history_end(self, fetch_history_id, data): return self.post('fetch_history/end', {'fetch_history_id': fetch_history_id, 'data': data}) def fetch_history_get(self, fetch_history_id): return self.get('fetch_history', {'id': fetch_history_id}) def entity_add(self, entities): return self.post('entity/add', {'entities': entities}) def entity_get_from_lister_metadata(self, entities): return self.post('entity/from_lister_metadata', {'entities': entities}) def stat_counters(self): return self.get('stat/counters') diff --git a/swh/storage/api/server.py b/swh/storage/api/server.py index a039752c..6ac3f9b1 100644 --- a/swh/storage/api/server.py +++ b/swh/storage/api/server.py @@ -1,214 +1,215 @@ # 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 import pickle from flask import Flask, Request, Response, abort, g, request from swh.core import config from swh.core.serializers import msgpack_dumps, msgpack_loads, SWHJSONDecoder 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.request_class = BytesRequest def encode_data(data): return Response( msgpack_dumps(data), mimetype='application/x-msgpack', ) def decode_request(request): content_type = request.mimetype data = request.get_data() if content_type == 'application/x-msgpack': r = msgpack_loads(data) elif content_type == 'application/json': r = json.loads(data, cls=SWHJSONDecoder) else: raise ValueError('Wrong content type `%s` for API request' % content_type) return r @app.errorhandler(Exception) def error_handler(exception): # XXX: this breaks language-independence and should be # replaced by proper serialization of errors response = encode_data(pickle.dumps(exception)) response.status_code = 400 return response @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 encode_data(g.storage.content_missing(**decode_request(request))) @app.route('/content/present', methods=['POST']) def content_exist(): return encode_data(g.storage.content_exist(**decode_request(request))) @app.route('/content/occurrence', methods=['POST']) def content_find_occurrence(): res = g.storage.content_find_occurrence(**decode_request(request)) return encode_data(res) @app.route('/content/add', methods=['POST']) def content_add(): return encode_data(g.storage.content_add(**decode_request(request))) @app.route('/directory/missing', methods=['POST']) def directory_missing(): return encode_data(g.storage.directory_missing(**decode_request(request))) @app.route('/directory/add', methods=['POST']) def directory_add(): return encode_data(g.storage.directory_add(**decode_request(request))) @app.route('/directory', methods=['GET']) def directory_get(): dir = request.args['directory'].encode('utf-8', 'surrogateescape') - return encode_data(g.storage.directory_get(dir)) + rec = request.args.get('recursive', False) + return encode_data(g.storage.directory_get(dir, recursive=rec)) @app.route('/revision/add', methods=['POST']) def revision_add(): return encode_data(g.storage.revision_add(**decode_request(request))) @app.route('/revision', methods=['POST']) def revision_get(): return encode_data(g.storage.revision_get(**decode_request(request))) @app.route('/revision/missing', methods=['POST']) def revision_missing(): return encode_data(g.storage.revision_missing(**decode_request(request))) @app.route('/release/add', methods=['POST']) def release_add(): return encode_data(g.storage.release_add(**decode_request(request))) @app.route('/release/missing', methods=['POST']) def release_missing(): return encode_data(g.storage.release_missing(**decode_request(request))) @app.route('/occurrence/add', methods=['POST']) def occurrence_add(): return encode_data(g.storage.occurrence_add(**decode_request(request))) @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 encode_data(origin) @app.route('/origin', methods=['POST']) def origin_add_one(): return encode_data(g.storage.origin_add_one(**decode_request(request))) @app.route('/fetch_history', methods=['GET']) def fetch_history_get(): return encode_data(g.storage.fetch_history_get(request.args['id'])) @app.route('/fetch_history/start', methods=['POST']) def fetch_history_start(): return encode_data( g.storage.fetch_history_start(**decode_request(request))) @app.route('/fetch_history/end', methods=['POST']) def fetch_history_end(): return encode_data( g.storage.fetch_history_end(**decode_request(request))) @app.route('/entity/add', methods=['POST']) def entity_add(): return encode_data( g.storage.entity_add(**decode_request(request))) @app.route('/entity/from_lister_metadata', methods=['POST']) def entity_from_lister_metadata(): return encode_data( g.storage.entity_get_from_lister_metadata(**decode_request(request))) @app.route('/stat/counters', methods=['GET']) def stat_counters(): return encode_data(g.storage.stat_counters()) 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)) host = sys.argv[2] if len(sys.argv) >= 3 else '127.0.0.1' app.run(host, debug=True) diff --git a/swh/storage/db.py b/swh/storage/db.py index cb291a3a..ec1743e2 100644 --- a/swh/storage/db.py +++ b/swh/storage/db.py @@ -1,344 +1,349 @@ # 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 datetime import functools import json 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 jsonize(value): """Convert a value to a psycopg2 JSON object if necessary""" if isinstance(value, dict): return psycopg2.extras.Json(value) return value def entry_to_bytes(entry): """Convert an entry coming from the database to bytes""" if isinstance(entry, memoryview): return entry.tobytes() if isinstance(entry, list): return [entry_to_bytes(value) for value in entry] 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 @stored_procedure('swh_mktemp_entity_lister') def mktemp_entity_lister(self, cur=None): pass @stored_procedure('swh_mktemp_entity_history') def mktemp_entity_history(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('"', '""') elif isinstance(data, datetime.datetime): # We escape twice to make sure the string generated by # isoformat gets escaped return escape(data.isoformat()) elif isinstance(data, dict): return escape(json.dumps(data)) elif isinstance(data, list): return escape("{%s}" % ','.join(escape(d) for d in data)) elif isinstance(data, psycopg2.extras.Range): # We escape twice here too, so that we make sure # everything gets passed to copy properly return escape( '%s%s,%s%s' % ( '[' if data.lower_inc else '(', '-infinity' if data.lower_inf else escape(data.lower), 'infinity' if data.upper_inf else escape(data.upper), ']' if data.upper_inc else ')', ) ) else: # We don't escape here to make sure we pass literals properly 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_directory_add') def directory_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 @stored_procedure('swh_occurrence_history_add') def occurrence_history_add_from_temp(self, cur=None): pass @stored_procedure('swh_entity_history_add') def entity_history_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_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 triplet (sha1, sha1_git, sha256) if found or None. """ cur = self._cursor(cur) cur.execute("""SELECT sha1, sha1_git, sha256 FROM swh_content_find(%s, %s, %s) LIMIT 1""", (sha1, sha1_git, sha256)) content = line_to_bytes(cur.fetchone()) return None if content == (None, None, None) else content def content_find_occurrence(self, sha1, cur=None): """Find one content's occurrence. Args: sha1: sha1 content cur: cursor to use Returns: One occurrence for that particular sha1 """ cur = self._cursor(cur) cur.execute("""SELECT * FROM swh_content_find_occurrence(%s) LIMIT 1""", (sha1, )) return line_to_bytes(cur.fetchone()) 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 directory_walk(self, directory, cur=None): + cur = self._cursor(cur) + cur.execute('SELECT * FROM swh_directory_walk(%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 revision_get_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT * FROM swh_revision_get()') 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) def stat_counters(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT * FROM swh_stat_counters()') yield from cur fetch_history_cols = ['origin', 'date', 'status', 'result', 'stdout', 'stderr', 'duration'] def create_fetch_history(self, fetch_history, cur=None): """Create a fetch_history entry with the data in fetch_history""" cur = self._cursor(cur) query = '''INSERT INTO fetch_history (%s) VALUES (%s) RETURNING id''' % ( ','.join(self.fetch_history_cols), ','.join(['%s'] * len(self.fetch_history_cols)) ) cur.execute(query, [fetch_history.get(col) for col in self.fetch_history_cols]) return cur.fetchone()[0] def get_fetch_history(self, fetch_history_id, cur=None): """Get a fetch_history entry with the given id""" cur = self._cursor(cur) query = '''SELECT %s FROM fetch_history WHERE id=%%s''' % ( ', '.join(self.fetch_history_cols), ) cur.execute(query, (fetch_history_id,)) data = cur.fetchone() if not data: return None ret = {'id': fetch_history_id} for i, col in enumerate(self.fetch_history_cols): ret[col] = data[i] return ret def update_fetch_history(self, fetch_history, cur=None): """Update the fetch_history entry from the data in fetch_history""" cur = self._cursor(cur) query = '''UPDATE fetch_history SET %s WHERE id=%%s''' % ( ','.join('%s=%%s' % col for col in self.fetch_history_cols) ) cur.execute(query, [jsonize(fetch_history.get(col)) for col in self.fetch_history_cols + ['id']]) base_entity_cols = ['uuid', 'parent', 'name', 'type', 'description', 'homepage', 'active', 'generated', 'lister', 'lister_metadata', 'doap'] entity_cols = base_entity_cols + ['last_seen', 'last_id'] entity_history_cols = base_entity_cols + ['id', 'validity'] diff --git a/swh/storage/storage.py b/swh/storage/storage.py index 2548afd7..c7ace07c 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,742 +1,757 @@ # 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 from collections import defaultdict import datetime import functools import itertools import dateutil.parser import psycopg2 from psycopg2.extras import DateTimeTZRange from .db import Db from .objstorage import ObjStorage from swh.core.hashutil import ALGORITHMS 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_find(self, content, cur=None): """Find a content hash in db. Args: content: a dictionary representing one content hash, mapping checksum algorithm names (see swh.core.hashutil.ALGORITHMS) to checksum values Returns: a triplet (sha1, sha1_git, sha256) if the content exist or None otherwise. Raises: ValueError in case the key of the dictionary is not sha1, sha1_git nor sha256. """ db = self.db if not set(content).intersection(ALGORITHMS): raise ValueError('content keys must contain at least one of: ' 'sha1, sha1_git, sha256') # format the output found_hash = db.content_find(sha1=content.get('sha1'), sha1_git=content.get('sha1_git'), sha256=content.get('sha256'), cur=cur) return found_hash @db_transaction def content_exist(self, content, cur=None): """Predicate to check the presence of a content's hashes. Args: content: a dictionary entry representing one content hash. The dictionary key is one of swh.core.hashutil.ALGORITHMS. The value mapped to the corresponding checksum. Returns: a boolean indicator of presence Raises: ValueError in case the key of the dictionary is not sha1, sha1_git nor sha256. """ return self.content_find(content) is not None @db_transaction def content_find_occurrence(self, content, cur=None): """Find the content's occurrence. Args: content: a dictionary entry representing one content hash. The dictionary key is one of swh.core.hashutil.ALGORITHMS. The value mapped to the corresponding checksum. Returns: The occurrence of the content. Raises: ValueError in case the key of the dictionary is not sha1, sha1_git nor sha256. """ db = self.db c = self.content_find(content) if c is None: return None sha1, _, _ = c found_occ = db.content_find_occurrence(sha1, cur=cur) if found_occ is None: return None return {'origin_type': found_occ[0], 'origin_url': found_occ[1], 'branch': found_occ[2], 'revision': found_occ[3], 'path': found_occ[4]} 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 """ 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: # Copy directory ids dirs_missing_dict = ({'id': dir} for dir in dirs_missing) db.mktemp('directory', cur) db.copy_to(dirs_missing_dict, 'tmp_directory', ['id'], cur) # Copy entries 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', 'dir_id'], cur, ) # Do the final copy db.directory_add_from_temp(cur) @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) + @db_transaction_generator + def directory_get(self, directory, recursive=False, cur=None): + """Get entries for one directory. + + Args: + - directory: the directory to list entries from. + - recursive: if flag on, this list recursively from this directory. + + Returns: + List of entries for such directory. + + """ + db = self.db + + if recursive: + yield from db.directory_walk(directory) + else: + yield from 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 - metadata (jsonb): extra information as dictionary - synthetic (bool): revision's nature (tarball, directory creates synthetic revision) - 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', 'metadata', 'synthetic'], 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] @db_transaction_generator def revision_get(self, revisions, cur): """Get all revisions from storage Args: an iterable of revision ids Returns: an iterable of revisions as dictionaries (or None if the revision doesn't exist) """ keys = ('id', 'date', 'date_offset', 'committer_date', 'committer_date_offset', 'type', 'directory', 'message', 'author_name', 'author_email', 'committer_name', 'committer_email', 'metadata', 'synthetic', 'parents') db = self.db # Create temporary table for metadata injection db.mktemp('revision', cur) revisions_dicts = ({'id': rev, 'type': 'git'} for rev in revisions) db.copy_to(revisions_dicts, 'tmp_revision', ['id', 'type'], cur) for line in self.db.revision_get_from_temp(cur): data = dict(zip(keys, line)) if not data['type']: yield None continue yield data 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', 'synthetic'], 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 (uuid): 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: validity = occurrence['validity'] if isinstance(validity, str): validity = dateutil.parser.parse(validity) if isinstance(validity, datetime.datetime): occurrence = occurrence.copy() occurrence['validity'] = DateTimeTZRange(lower=validity) processed.append(occurrence) db.mktemp('occurrence_history', cur) db.copy_to(processed, 'tmp_occurrence_history', ['origin', 'branch', 'revision', 'authority', 'validity'], cur) db.occurrence_history_add_from_temp(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] @db_transaction def fetch_history_start(self, origin_id, cur=None): """Add an entry for origin origin_id in fetch_history. Returns the id of the added fetch_history entry """ fetch_history = { 'origin': origin_id, 'date': datetime.datetime.now(tz=datetime.timezone.utc), } return self.db.create_fetch_history(fetch_history, cur) @db_transaction def fetch_history_end(self, fetch_history_id, data, cur=None): """Close the fetch_history entry with id `fetch_history_id`, replacing its data with `data`. """ now = datetime.datetime.now(tz=datetime.timezone.utc) fetch_history = self.db.get_fetch_history(fetch_history_id, cur) if not fetch_history: raise ValueError('No fetch_history with id %d' % fetch_history_id) fetch_history['duration'] = now - fetch_history['date'] fetch_history.update(data) self.db.update_fetch_history(fetch_history, cur) @db_transaction def fetch_history_get(self, fetch_history_id, cur=None): """Get the fetch_history entry with id `fetch_history_id`. """ return self.db.get_fetch_history(fetch_history_id, cur) @db_transaction def entity_add(self, entities, cur=None): """Add the given entitites to the database (in entity_history). Args: - entities: iterable of dictionaries containing the following keys: - uuid (uuid): id of the entity - parent (uuid): id of the parent entity - name (str): name of the entity - type (str): type of entity (one of 'organization', 'group_of_entities', 'hosting', 'group_of_persons', 'person', 'project') - description (str, optional): description of the entity - homepage (str): url of the entity's homepage - active (bool): whether the entity is active - generated (bool): whether the entity was generated - lister (uuid): the uuid of the generating entity - lister_metadata (dict): lister-specific entity metadata - doap (dict): DOAP data for the entity - validity (datetime.DateTime array): timestamps at which we listed the entity. """ db = self.db cols = list(db.entity_history_cols) cols.remove('id') db.mktemp_entity_history() db.copy_to(entities, 'tmp_entity_history', cols, cur) db.entity_history_add_from_temp() @db_transaction_generator def entity_get_from_lister_metadata(self, entities, cur=None): """Fetch entities from the database, matching with the lister and associated metadata. Args: - entities: iterable of dictionaries containing the following keys: - lister (uuid): uuid of the lister - lister_metadata (dict): subset of the lister metadata used for matching the entity Returns: A generator of fetched entities with all their attributes. If no match was found, the returned entity's uuid is None. """ db = self.db db.mktemp_entity_lister(cur) mapped_entities = [] for i, entity in enumerate(entities): mapped_entity = entity.copy() mapped_entity['id'] = i mapped_entities.append(mapped_entity) db.copy_to(mapped_entities, 'tmp_entity_lister', ['id', 'lister', 'lister_metadata'], cur) cur.execute('''select id, %s from swh_entity_from_tmp_entity_lister() order by id''' % ','.join(db.entity_cols)) for id, *entity_vals in cur: returned_entity = entities[id].copy() fetched_entity = dict(zip(db.entity_cols, entity_vals)) returned_entity['uuid'] = fetched_entity['uuid'] if fetched_entity['uuid']: returned_entity.update(fetched_entity) yield returned_entity @db_transaction def stat_counters(self, cur=None): """compute statistics about the number of tuples in various tables Returns: a dictionary mapping textual labels (e.g., content) to integer values (e.g., the number of tuples in table content) """ return {k: v for (k, v) in self.db.stat_counters()}