No OneTemporary
Actions

Size

102 KB

Subscribers

None

View Options

	diff --git a/PKG-INFO b/PKG-INFO
	index 6c4ec0502..285aac1d6 100644
	--- a/PKG-INFO
	+++ b/PKG-INFO
	@@ -1,10 +1,10 @@
	Metadata-Version: 1.0
	Name: swh.storage
	-Version: 0.0.19
	+Version: 0.0.20
	Summary: Software Heritage storage manager
	Home-page: https://forge.softwareheritage.org/diffusion/DSTO/
	Author: Software Heritage developers
	Author-email: swh-devel@inria.fr
	License: UNKNOWN
	Description: UNKNOWN
	Platform: UNKNOWN
	diff --git a/swh.storage.egg-info/PKG-INFO b/swh.storage.egg-info/PKG-INFO
	index 6c4ec0502..285aac1d6 100644
	--- a/swh.storage.egg-info/PKG-INFO
	+++ b/swh.storage.egg-info/PKG-INFO
	@@ -1,10 +1,10 @@
	Metadata-Version: 1.0
	Name: swh.storage
	-Version: 0.0.19
	+Version: 0.0.20
	Summary: Software Heritage storage manager
	Home-page: https://forge.softwareheritage.org/diffusion/DSTO/
	Author: Software Heritage developers
	Author-email: swh-devel@inria.fr
	License: UNKNOWN
	Description: UNKNOWN
	Platform: UNKNOWN
	diff --git a/swh.storage.egg-info/SOURCES.txt b/swh.storage.egg-info/SOURCES.txt
	index c9169c024..6e569154c 100644
	--- a/swh.storage.egg-info/SOURCES.txt
	+++ b/swh.storage.egg-info/SOURCES.txt
	@@ -1,63 +1,64 @@
	.gitignore
	AUTHORS
	LICENSE
	MANIFEST.in
	Makefile
	Makefile.local
	README.db_testing
	README.dev
	requirements.txt
	setup.py
	version.txt
	bin/swh-objstorage-add-dir
	bin/swh-objstorage-fsck
	bin/swh-storage-add-dir
	debian/changelog
	debian/compat
	debian/control
	debian/copyright
	debian/rules
	debian/source/format
	sql/.gitignore
	sql/Makefile
	sql/TODO
	sql/clusters.dot
	sql/swh-data.sql
	sql/swh-func.sql
	sql/swh-init.sql
	sql/swh-schema.sql
	sql/bin/db-upgrade
	sql/bin/dot_add_content
	sql/upgrades/015.sql
	sql/upgrades/016.sql
	sql/upgrades/017.sql
	sql/upgrades/018.sql
	sql/upgrades/019.sql
	sql/upgrades/020.sql
	sql/upgrades/021.sql
	sql/upgrades/022.sql
	sql/upgrades/023.sql
	sql/upgrades/024.sql
	sql/upgrades/025.sql
	sql/upgrades/026.sql
	sql/upgrades/027.sql
	sql/upgrades/028.sql
	sql/upgrades/029.sql
	sql/upgrades/030.sql
	sql/upgrades/032.sql
	swh.storage.egg-info/PKG-INFO
	swh.storage.egg-info/SOURCES.txt
	swh.storage.egg-info/dependency_links.txt
	swh.storage.egg-info/requires.txt
	swh.storage.egg-info/top_level.txt
	swh/storage/__init__.py
	+swh/storage/converters.py
	swh/storage/db.py
	swh/storage/objstorage.py
	swh/storage/storage.py
	swh/storage/api/__init__.py
	swh/storage/api/client.py
	swh/storage/api/server.py
	swh/storage/tests/test_api_client.py
	swh/storage/tests/test_db.py
	swh/storage/tests/test_objstorage.py
	swh/storage/tests/test_storage.py
	\ No newline at end of file
	diff --git a/swh/storage/api/client.py b/swh/storage/api/client.py
	index d6906f6d2..cbeb78c8b 100644
	--- a/swh/storage/api/client.py
	+++ b/swh/storage/api/client.py
	@@ -1,145 +1,148 @@
	# 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_get(self, content):
	return self.post('content/data', {'content': content})

	def content_find(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, recursive=False):
	return self.get('directory', {'directory': directory,
	'recursive': recursive})

	def revision_get(self, revisions):
	return self.post('revision', {'revisions': revisions})

	+ def revision_log(self, revisions):
	+ return self.post('revision/log', {'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_get(self, releases):
	return self.post('release', {'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):
	return self.post('origin/get', {'origin': origin})

	def origin_add_one(self, origin):
	return self.post('origin/add', {'origin': origin})

	def person_get(self, person):
	return self.post('person', {'person': person})

	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 c77dd05e7..c0d5cf3e1 100644
	--- a/swh/storage/api/server.py
	+++ b/swh/storage/api/server.py
	@@ -1,219 +1,224 @@
	# 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, 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_find():
	return encode_data(g.storage.content_find(**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('/content/data', methods=['POST'])
	def content_get():
	return encode_data(g.storage.content_get(**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')
	rec = json.loads(request.args.get('recursive', 'False').lower())
	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/log', methods=['POST'])
	+def revision_log():
	+ return encode_data(g.storage.revision_log(**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', methods=['POST'])
	def release_get():
	return encode_data(g.storage.release_get(**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/get', methods=['POST'])
	def origin_get():
	return encode_data(g.storage.origin_get(**decode_request(request)))


	@app.route('/origin/add', methods=['POST'])
	def origin_add_one():
	return encode_data(g.storage.origin_add_one(**decode_request(request)))


	@app.route('/person', methods=['POST'])
	def person_get():
	return encode_data(g.storage.person_get(**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/converters.py b/swh/storage/converters.py
	new file mode 100644
	index 000000000..206e5769b
	--- /dev/null
	+++ b/swh/storage/converters.py
	@@ -0,0 +1,217 @@
	+# 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 numbers
	+
	+
	+DEFAULT_AUTHOR = {
	+ 'name': b'',
	+ 'email': b'',
	+}
	+
	+DEFAULT_DATE = {
	+ 'timestamp': None,
	+ 'offset': 0,
	+}
	+
	+
	+def author_to_db(author):
	+ """Convert a swh-model author to its DB representation.
	+
	+ Args: a swh-model compatible author
	+ Returns:
	+ a dict containing two keys: author and email
	+ """
	+ if author is None:
	+ return DEFAULT_AUTHOR
	+
	+ return author
	+
	+
	+def db_to_author(name, email):
	+ """Convert the DB representation of an author to a swh-model author.
	+
	+ Args:
	+ name (bytes): the author's name
	+ email (bytes): the author's email
	+
	+ Returns:
	+ a dict with two keys: author and email.
	+ """
	+
	+ return {
	+ 'name': name,
	+ 'email': email,
	+ }
	+
	+
	+def db_to_date(date, offset):
	+ """Convert the DB representation of a date to a swh-model compatible date.
	+
	+ Args:
	+ date (datetime.datetime): a date pulled out of the database
	+ offset (int): an integer number of minutes representing an UTC offset
	+
	+ Returns:
	+ a datetime.datetime object, using a timezone with the proper offset.
	+ """
	+
	+ if date is None:
	+ return None
	+
	+ new_tz = datetime.timezone(datetime.timedelta(minutes=offset))
	+ return date.astimezone(tz=new_tz)
	+
	+
	+def date_to_db(date_offset):
	+ """Convert a swh-model date_offset to its DB representation.
	+
	+ Args: a swh-model compatible date_offset
	+ Returns:
	+ a dict containing a numeric timestamp and an integer offset
	+
	+ """
	+
	+ if date_offset is None:
	+ return DEFAULT_DATE
	+
	+ if isinstance(date_offset, numbers.Real):
	+ date_offset = datetime.datetime.fromtimestamp(date_offset,
	+ tz=datetime.timezone.utc)
	+
	+ if isinstance(date_offset, datetime.datetime):
	+ timestamp = date_offset
	+ utcoffset = date_offset.utcoffset()
	+ offset = int(utcoffset.total_seconds()) // 60
	+ else:
	+ if isinstance(date_offset['timestamp'], numbers.Real):
	+ timestamp = datetime.datetime.fromtimestamp(
	+ date_offset['timestamp'], tz=datetime.timezone.utc)
	+ else:
	+ timestamp = date_offset['timestamp']
	+ offset = date_offset['offset']
	+
	+ return {
	+ 'timestamp': timestamp.isoformat(),
	+ 'offset': offset,
	+ }
	+
	+
	+def revision_to_db(revision):
	+ """Convert a swh-model revision to its database representation.
	+ """
	+
	+ author = author_to_db(revision['author'])
	+ date = date_to_db(revision['date'])
	+ committer = author_to_db(revision['committer'])
	+ committer_date = date_to_db(revision['committer_date'])
	+
	+ return {
	+ 'id': revision['id'],
	+ 'author_name': author['name'],
	+ 'author_email': author['email'],
	+ 'date': date['timestamp'],
	+ 'date_offset': date['offset'],
	+ 'committer_name': committer['name'],
	+ 'committer_email': committer['email'],
	+ 'committer_date': committer_date['timestamp'],
	+ 'committer_date_offset': committer_date['offset'],
	+ 'type': revision['type'],
	+ 'directory': revision['directory'],
	+ 'message': revision['message'],
	+ 'metadata': revision['metadata'],
	+ 'synthetic': revision['synthetic'],
	+ 'parents': [
	+ {
	+ 'id': revision['id'],
	+ 'parent_id': parent,
	+ 'parent_rank': i,
	+ } for i, parent in enumerate(revision['parents'])
	+ ],
	+ }
	+
	+
	+def db_to_revision(db_revision):
	+ """Convert a database representation of a revision to its swh-model
	+ representation."""
	+
	+ author = db_to_author(
	+ db_revision['author_name'],
	+ db_revision['author_email'],
	+ )
	+ date = db_to_date(db_revision['date'], db_revision['date_offset'])
	+
	+ committer = db_to_author(
	+ db_revision['committer_name'],
	+ db_revision['committer_email'],
	+ )
	+ committer_date = db_to_date(
	+ db_revision['committer_date'],
	+ db_revision['committer_date_offset'],
	+ )
	+
	+ parents = []
	+ if 'parents' in db_revision:
	+ for parent in db_revision['parents']:
	+ if parent:
	+ parents.append(parent)
	+
	+ return {
	+ 'id': db_revision['id'],
	+ 'author': author,
	+ 'date': date,
	+ 'committer': committer,
	+ 'committer_date': committer_date,
	+ 'type': db_revision['type'],
	+ 'directory': db_revision['directory'],
	+ 'message': db_revision['message'],
	+ 'metadata': db_revision['metadata'],
	+ 'synthetic': db_revision['synthetic'],
	+ 'parents': parents,
	+ }
	+
	+
	+def release_to_db(release):
	+ """Convert a swh-model release to its database representation.
	+ """
	+
	+ author = author_to_db(release['author'])
	+ date = date_to_db(release['date'])
	+
	+ return {
	+ 'id': release['id'],
	+ 'author_name': author['name'],
	+ 'author_email': author['email'],
	+ 'date': date['timestamp'],
	+ 'date_offset': date['offset'],
	+ 'name': release['name'],
	+ 'revision': release['target'],
	+ 'comment': release['message'],
	+ 'synthetic': release['synthetic'],
	+ }
	+
	+
	+def db_to_release(db_release):
	+ """Convert a database representation of a release to its swh-model
	+ representation.
	+ """
	+
	+ author = db_to_author(
	+ db_release['author_name'],
	+ db_release['author_email'],
	+ )
	+ date = db_to_date(db_release['date'], db_release['date_offset'])
	+
	+ return {
	+ 'author': author,
	+ 'date': date,
	+ 'id': db_release['id'],
	+ 'name': db_release['name'],
	+ 'message': db_release['comment'],
	+ 'synthetic': db_release['synthetic'],
	+ 'target': db_release['revision'],
	+ 'target_type': 'revision',
	+ }
	diff --git a/swh/storage/db.py b/swh/storage/db.py
	index 1076c5cd5..d3d1814f3 100644
	--- a/swh/storage/db.py
	+++ b/swh/storage/db.py
	@@ -1,423 +1,435 @@
	# 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_release_get')
	def mktemp_release_get(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, length, ctime, status
	FROM swh_content_find(%s, %s, %s)
	LIMIT 1""", (sha1, sha1_git, sha256))

	content = line_to_bytes(cur.fetchone())
	if set(content) == {None}:
	return None
	else:
	return 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 revision_log(self, root_revision, cur=None):
	+ cur = self._cursor(cur)
	+
	+ query = """SELECT id, date, date_offset, committer_date,
	+ committer_date_offset, type, directory, message,
	+ author_name, author_email, committer_name,
	+ committer_email, metadata, synthetic
	+ FROM swh_revision_log(%s)
	+ """
	+ cur.execute(query, (root_revision,))
	+ 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']

	def origin_add(self, type, url, cur=None):
	"""Insert a new origin and return the new identifier."""
	insert = """INSERT INTO origin (type, url) values (%s, %s)
	RETURNING id"""

	cur.execute(insert, (type, url))
	return cur.fetchone()[0]

	def origin_get_with(self, type, url, cur=None):
	"""Retrieve the origin id from its type and url if found."""
	cur = self._cursor(cur)

	query = """SELECT id, type, url, lister, project
	FROM origin
	WHERE type=%s AND url=%s"""

	cur.execute(query, (type, url))
	data = cur.fetchone()
	if data:
	return line_to_bytes(data)
	return None

	def origin_get(self, id, cur=None):
	"""Retrieve the origin per its identifier.

	"""
	cur = self._cursor(cur)

	query = "SELECT id, type, url, lister, project FROM origin WHERE id=%s"

	cur.execute(query, (id,))
	data = cur.fetchone()
	if data:
	return line_to_bytes(data)
	return None

	def person_add(self, name, email, cur=None):
	"""Add a person identified by its name and email.

	Returns:
	The new person's id

	"""
	cur = self._cursor(cur)

	query_new_person = '''INSERT INTO person(name, email)
	VALUES (%s, %s)
	RETURNING id'''
	cur.execute(query_new_person, (name, email))
	return cur.fetchone()[0]

	def person_get(self, ids, cur=None):
	"""Retrieve the persons identified by the list of ids.

	"""
	cur = self._cursor(cur)

	query = """SELECT id, name, email
	FROM person
	WHERE id IN %s"""
	cur.execute(query, (tuple(ids),))
	yield from cursor_to_bytes(cur)

	def release_get_from_temp(self, cur=None):
	cur = self._cursor(cur)
	cur.execute('SELECT * FROM swh_release_get()')
	yield from cursor_to_bytes(cur)
	diff --git a/swh/storage/storage.py b/swh/storage/storage.py
	index da2511818..1d0e2bbbc 100644
	--- a/swh/storage/storage.py
	+++ b/swh/storage/storage.py
	@@ -1,861 +1,870 @@
	# 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 . import converters
	from .db import Db
	-from .objstorage import ObjStorage
	+from .objstorage import ObjNotFoundError, ObjStorage

	from swh.core.hashutil import ALGORITHMS
	-from swh.storage.objstorage import ObjNotFoundError

	# Max block size of contents to return
	BULK_BLOCK_CONTENT_LEN_MAX = 10000


	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)

	def content_get(self, content):
	"""Retrieve in bulk contents and their data.

	Args:
	content: iterables of sha1

	Returns:
	Generates streams of contents as dict with their raw data:
	- sha1: sha1's content
	- data: bytes data of the content

	Raises:
	ValueError in case of too much contents are required.
	cf. BULK_BLOCK_CONTENT_LEN_MAX

	"""
	# FIXME: Improve on server module to slice the result
	if len(content) > BULK_BLOCK_CONTENT_LEN_MAX:
	raise ValueError(
	"Send at maximum %s contents." % BULK_BLOCK_CONTENT_LEN_MAX)

	for obj_id in content:
	try:
	data = self.objstorage.get_bytes(obj_id)
	except ObjNotFoundError:
	yield None
	continue

	yield {'sha1': obj_id, 'data': data}

	@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')

	c = db.content_find(sha1=content.get('sha1'),
	sha1_git=content.get('sha1_git'),
	sha256=content.get('sha256'),
	cur=cur)
	if c:
	keys = ['sha1', 'sha1_git', 'sha256', 'length', 'ctime', 'status']
	return dict(zip(keys, c))
	return 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 not c:
	return None

	sha1 = c['sha1']

	found_occ = db.content_find_occurrence(sha1, cur=cur)
	if found_occ:
	keys = ['origin_type', 'origin_url', 'branch', 'revision', 'path']
	return dict(zip(keys, found_occ))
	return None

	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']:
	+ for src_entry in cur_dir['entries']:
	+ entry = src_entry.copy()
	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]

	@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
	keys = ['dir_id', 'type', 'target', 'name', 'perms', 'status',
	'sha1', 'sha1_git', 'sha256']

	if recursive:
	res_gen = db.directory_walk(directory)
	else:
	res_gen = db.directory_walk_one(directory)

	for line in res_gen:
	yield dict(zip(keys, line))

	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()))
	+ revisions_missing = set(self.revision_missing(
	+ set(revision['id'] for revision in revisions)))

	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)
	+ revisions_filtered = (
	+ converters.revision_to_db(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)
	+ parents_filtered = []

	- db.revision_add_from_temp(cur)
	+ 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,
	+ lambda rev: parents_filtered.extend(rev['parents']))

	- parents_filtered = itertools.chain.from_iterable(
	- parents[id] for id in revisions_missing)
	+ db.revision_add_from_temp(cur)

	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))
	+ data = converters.db_to_revision(dict(zip(keys, line)))
	if not data['type']:
	yield None
	continue
	+ yield data

	- if 'parents' in data:
	- data['parents'] = list(filter(lambda x: x, data['parents']))
	+ @db_transaction_generator
	+ def revision_log(self, revisions, cur=None):
	+ """Fetch revision entry from the given revisions (root's revision hash).
	+
	+ """
	+ root_revision = revisions
	+ db = self.db

	+ keys = ['id', 'date', 'date_offset', 'committer_date',
	+ 'committer_date_offset', 'type', 'directory', 'message',
	+ 'author_name', 'author_email', 'committer_name',
	+ 'committer_email', 'metadata', 'synthetic']
	+
	+ for line in db.revision_log(root_revision, cur):
	+ data = converters.db_to_revision(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))
	+ releases_missing = set(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)
	+ releases_filtered = (
	+ converters.release_to_db(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_generator
	def release_get(self, releases, cur=None):
	"""Given a list of sha1, return the releases's information

	Args:
	releases: list of sha1s

	Returns:
	Generates the list of releases dict with the following keys:
	- id: origin's id
	- revision: origin's type
	- url: origin's url
	- lister: lister's uuid
	- project: project's uuid (FIXME, retrieve this information)

	Raises:
	ValueError if the keys does not match (url and type) nor id.

	"""
	db = self.db

	keys = ['id', 'revision', 'date', 'date_offset', 'name', 'comment',
	'synthetic', 'author_name', 'author_email']

	db.mktemp_release_get(cur)

	releases_dicts = ({'id': rel} for rel in releases)

	db.copy_to(releases_dicts, 'tmp_release_get', ['id'], cur)

	for release in db.release_get_from_temp(cur):
	- yield dict(zip(keys, release))
	+ yield converters.db_to_release(dict(zip(keys, release)))

	@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 origin either identified by its id or its tuple
	(type, url).

	Args:
	origin: dictionary representing the individual
	origin to find.
	This dict has either the keys type and url:
	- type (FIXME: enum TBD): the origin type ('git', 'wget', ...)
	- url (bytes): the url the origin points to
	either the id:
	- id: the origin id

	Returns:
	the origin dict with the keys:
	- id: origin's id
	- type: origin's type
	- url: origin's url
	- lister: lister's uuid
	- project: project's uuid (FIXME, retrieve this information)

	Raises:
	ValueError if the keys does not match (url and type) nor id.

	"""
	db = self.db

	keys = ['id', 'type', 'url', 'lister', 'project']

	origin_id = origin.get('id')
	if origin_id: # check lookup per id first
	ori = db.origin_get(origin_id, cur)
	elif 'type' in origin and 'url' in origin: # or lookup per type, url
	ori = db.origin_get_with(origin['type'], origin['url'], cur)
	else: # unsupported lookup
	raise ValueError('Origin must have either id or (type and url).')

	if ori:
	return dict(zip(keys, ori))
	return None

	@db_transaction
	def _person_add(self, person, cur=None):
	"""Add a person in storage.

	BEWARE: Internal function for now.
	Do not do anything fancy in case a person already exists.
	Please adapt code if more checks are needed.

	Args:
	person dictionary with keys name and email.

	Returns:
	Id of the new person.

	"""
	db = self.db

	return db.person_add(person['name'], person['email'])

	@db_transaction_generator
	def person_get(self, person, cur=None):
	"""Return the persons identified by their ids.

	Args:
	person: array of ids.

	Returns:
	The array of persons corresponding of the ids.

	"""
	db = self.db

	keys = ['id', 'name', 'email']

	for person in db.person_get(person):
	yield dict(zip(keys, person))

	@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.

	"""
	db = self.db

	data = db.origin_get_with(origin['type'], origin['url'], cur)
	if data:
	return data[0]

	return db.origin_add(origin['type'], origin['url'], cur)

	@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()}
	diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py
	index a6795332a..bb4294420 100644
	--- a/swh/storage/tests/test_storage.py
	+++ b/swh/storage/tests/test_storage.py
	@@ -1,839 +1,878 @@
	# 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 os
	import psycopg2
	import shutil
	import tempfile
	import unittest

	from unittest.mock import patch

	from nose.tools import istest
	from nose.plugins.attrib import attr

	from swh.core.tests.db_testing import DbTestFixture
	from swh.core.hashutil import hex_to_hash
	from swh.storage import Storage


	TEST_DIR = os.path.dirname(os.path.abspath(__file__))
	TEST_DATA_DIR = os.path.join(TEST_DIR, '../../../../swh-storage-testdata')


	@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.

	"""
	TEST_DB_DUMP = os.path.join(TEST_DATA_DIR, 'dumps/swh.dump')

	def setUp(self):
	super().setUp()
	self.maxDiff = None
	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.skipped_cont2 = {
	'length': 1024 * 1024 * 300,
	'sha1_git': hex_to_hash(
	'33e45d56f88993aae6a0198013efa80716fd8921'),
	'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,
	},
	{
	'name': b'bar\xc3',
	'type': 'dir',
	'target': b'12345678901234567890',
	'perms': 0o2000,
	},
	],
	}

	self.dir2 = {
	'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa95',
	'entries': [
	{
	'name': b'oof',
	'type': 'file',
	'target': self.cont2['sha1_git'],
	'perms': 0o644,
	}
	],
	}

	+ self.minus_offset = datetime.timezone(datetime.timedelta(minutes=-120))
	+ self.plus_offset = datetime.timezone(datetime.timedelta(minutes=120))
	+
	self.revision = {
	'id': b'56789012345678901234',
	'message': b'hello',
	- 'author_name': b'Nicolas Dandrimont',
	- 'author_email': b'nicolas@example.com',
	- 'committer_name': b'St\xc3fano Zacchiroli',
	- 'committer_email': b'stefano@example.com',
	- 'parents': [b'01234567890123456789', b'23434512345123456789'],
	+ 'author': {
	+ 'name': b'Nicolas Dandrimont',
	+ 'email': b'nicolas@example.com',
	+ },
	'date': datetime.datetime(2015, 1, 1, 22, 0, 0,
	- tzinfo=datetime.timezone.utc),
	- 'date_offset': 120,
	+ tzinfo=self.plus_offset),
	+ 'committer': {
	+ 'name': b'St\xc3fano Zacchiroli',
	+ 'email': b'stefano@example.com',
	+ },
	'committer_date': datetime.datetime(2015, 1, 2, 22, 0, 0,
	- tzinfo=datetime.timezone.utc),
	- 'committer_date_offset': -120,
	+ tzinfo=self.minus_offset),
	+ 'parents': [b'01234567890123456789', b'23434512345123456789'],
	'type': 'git',
	'directory': self.dir['id'],
	'metadata': {'checksums': {'sha1': 'tarball-sha1',
	'sha256': 'tarball-sha256'},
	'signed-off-by': 'some-dude'},
	'synthetic': True
	}

	self.revision2 = {
	'id': b'87659012345678904321',
	'message': b'hello again',
	- 'author_name': 'Roberto Dicosmo',
	- 'author_email': 'roberto@example.com',
	- 'committer_name': 'tony',
	- 'committer_email': 'ar@dumont.fr',
	- 'parents': [b'01234567890123456789'],
	+ 'author': {
	+ 'name': b'Roberto Dicosmo',
	+ 'email': b'roberto@example.com',
	+ },
	'date': datetime.datetime(2015, 1, 1, 22, 0, 0,
	- tzinfo=datetime.timezone.utc),
	- 'date_offset': 120,
	+ tzinfo=self.plus_offset),
	+ 'committer': {
	+ 'name': b'tony',
	+ 'email': b'ar@dumont.fr',
	+ },
	'committer_date': datetime.datetime(2015, 1, 2, 22, 0, 0,
	- tzinfo=datetime.timezone.utc),
	- 'committer_date_offset': -120,
	+ tzinfo=self.minus_offset),
	+ 'parents': [b'01234567890123456789'],
	'type': 'git',
	'directory': self.dir2['id'],
	'metadata': None,
	'synthetic': False
	}

	self.revision3 = {
	- 'id': b'87659012345678904321',
	+ 'id': hex_to_hash('7026b7c1a2af56521e951c01ed20f255fa054238'),
	'message': b'a simple revision with no parents this time',
	- 'author_name': 'Roberto Dicosmo',
	- 'author_email': 'roberto@example.com',
	- 'committer_name': 'tony',
	- 'committer_email': 'ar@dumont.fr',
	- 'parents': [],
	+ 'author': {
	+ 'name': b'Roberto Dicosmo',
	+ 'email': b'roberto@example.com',
	+ },
	'date': datetime.datetime(2015, 10, 1, 22, 0, 0,
	- tzinfo=datetime.timezone.utc),
	- 'date_offset': 120,
	+ tzinfo=self.plus_offset),
	+ 'committer': {
	+ 'name': b'tony',
	+ 'email': b'ar@dumont.fr',
	+ },
	'committer_date': datetime.datetime(2015, 10, 2, 22, 0, 0,
	- tzinfo=datetime.timezone.utc),
	- 'committer_date_offset': -120,
	+ tzinfo=self.minus_offset),
	+ 'parents': [],
	'type': 'git',
	'directory': self.dir2['id'],
	'metadata': None,
	'synthetic': True
	}

	+ self.revision4 = {
	+ 'id': hex_to_hash('368a48fe15b7db2383775f97c6b247011b3f14f4'),
	+ 'message': b'parent of self.revision2',
	+ 'author': {
	+ 'name': b'me',
	+ 'email': b'me@soft.heri',
	+ },
	+ 'date': datetime.datetime(2015, 1, 1, 20, 0, 0,
	+ tzinfo=self.plus_offset),
	+ 'committer': {
	+ 'name': b'committer-dude',
	+ 'email': b'committer@dude.com',
	+ },
	+ 'committer_date': datetime.datetime(2015, 1, 2, 20, 0, 0,
	+ tzinfo=self.minus_offset),
	+ 'parents': [self.revision3['id']],
	+ 'type': 'git',
	+ 'directory': self.dir['id'],
	+ 'metadata': None,
	+ 'synthetic': False
	+ }
	+
	self.origin = {
	'url': 'file:///dev/null',
	'type': 'git',
	}

	self.origin2 = {
	'url': 'file:///dev/zero',
	'type': 'git',
	}

	self.occurrence = {
	'branch': 'master',
	'revision': b'67890123456789012345',
	'authority': '5f4d4c51-498a-4e28-88b3-b3e4e8396cba',
	'validity': datetime.datetime(2015, 1, 1, 23, 0, 0,
	tzinfo=datetime.timezone.utc),
	}

	self.occurrence2 = {
	'branch': 'master',
	'revision': self.revision2['id'],
	'authority': '5f4d4c51-498a-4e28-88b3-b3e4e8396cba',
	'validity': datetime.datetime(2015, 1, 1, 23, 0, 0,
	tzinfo=datetime.timezone.utc),
	}

	self.release = {
	'id': b'87659012345678901234',
	'name': 'v0.0.1',
	'date': datetime.datetime(2015, 1, 1, 22, 0, 0,
	- tzinfo=datetime.timezone.utc),
	- 'offset': 120,
	- 'author_name': 'olasd',
	- 'author_email': 'nic@olasd.fr',
	- 'comment': 'synthetic release',
	- 'synthetic': True
	+ tzinfo=self.plus_offset),
	+ 'author': {
	+ 'name': b'olasd',
	+ 'email': b'nic@olasd.fr',
	+ },
	+ 'target': b'43210987654321098765',
	+ 'target_type': 'revision',
	+ 'message': b'synthetic release',
	+ 'synthetic': True,
	}

	self.release2 = {
	'id': b'56789012348765901234',
	'name': 'v0.0.2',
	'date': datetime.datetime(2015, 1, 2, 23, 0, 0,
	- tzinfo=datetime.timezone.utc),
	- 'offset': 120,
	- 'author_name': 'tony',
	- 'author_email': 'ar@dumont.fr',
	- 'comment': 'v0.0.2\nMisc performance improvments + bug fixes',
	+ tzinfo=self.minus_offset),
	+ 'author': {
	+ 'name': b'tony',
	+ 'email': b'ar@dumont.fr',
	+ },
	+ 'target': b'432109\xa9765432\xc309\x00765',
	+ 'target_type': 'revision',
	+ 'message': b'v0.0.2\nMisc performance improvments + bug fixes',
	'synthetic': False
	}

	self.fetch_history_date = datetime.datetime(
	2015, 1, 2, 21, 0, 0,
	tzinfo=datetime.timezone.utc)
	self.fetch_history_end = datetime.datetime(
	2015, 1, 2, 23, 0, 0,
	tzinfo=datetime.timezone.utc)

	self.fetch_history_duration = (self.fetch_history_end -
	self.fetch_history_date)

	self.fetch_history_data = {
	'status': True,
	'result': {'foo': 'bar'},
	'stdout': 'blabla',
	'stderr': 'blablabla',
	}

	self.entity1 = {
	'uuid': 'f96a7ec1-0058-4920-90cc-7327e4b5a4bf',
	# GitHub users
	'parent': 'ad6df473-c1d2-4f40-bc58-2b091d4a750e',
	'name': 'github:user:olasd',
	'type': 'person',
	'description': 'Nicolas Dandrimont',
	'homepage': 'http://example.com',
	'active': True,
	'generated': True,
	# swh.lister.github
	'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
	'lister_metadata': {
	'id': 12877,
	'type': 'user',
	'last_activity': '2015-11-03',
	},
	'doap': None,
	'validity': [
	datetime.datetime(2015, 11, 3, 11, 0, 0,
	tzinfo=datetime.timezone.utc),
	]
	}

	self.entity1_query = {
	'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
	'lister_metadata': {
	'id': 12877,
	'type': 'user',
	},
	}

	self.entity2 = {
	'uuid': '3903d075-32d6-46d4-9e29-0aef3612c4eb',
	# GitHub users
	'parent': 'ad6df473-c1d2-4f40-bc58-2b091d4a750e',
	'name': 'github:user:zacchiro',
	'type': 'person',
	'description': 'Stefano Zacchiroli',
	'homepage': 'http://example.com',
	'active': True,
	'generated': True,
	# swh.lister.github
	'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
	'lister_metadata': {
	'id': 216766,
	'type': 'user',
	'last_activity': '2015-11-03',
	},
	'doap': None,
	'validity': [
	datetime.datetime(2015, 11, 3, 11, 0, 0,
	tzinfo=datetime.timezone.utc),
	]
	}

	self.entity2_query = {
	'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
	'lister_metadata': {
	'id': 216766,
	'type': 'user',
	},
	}

	def tearDown(self):
	shutil.rmtree(self.objroot)

	self.cursor.execute("""SELECT table_name FROM information_schema.tables
	WHERE table_schema = %s""", ('public',))

	tables = set(table for (table,) in self.cursor.fetchall())
	tables -= {'dbversion', 'entity', 'entity_history', 'listable_entity'}

	for table in tables:
	self.cursor.execute('truncate table %s cascade' % table)

	self.cursor.execute('delete from entity where generated=true')
	self.cursor.execute('delete from entity_history where generated=true')
	self.conn.commit()

	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 content_add_collision(self):
	cont1 = self.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 self.assertRaises(psycopg2.IntegrityError):
	self.storage.content_add([cont1, cont1b])

	@istest
	def skipped_content_add(self):
	cont = self.skipped_cont
	cont2 = self.skipped_cont2

	self.storage.content_add([cont])
	self.storage.content_add([cont2])

	self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status,'
	'reason FROM skipped_content ORDER BY 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'))

	datum2 = self.cursor.fetchone()
	self.assertEqual(
	(datum2[0], datum2[1].tobytes(), datum2[2],
	datum2[3], datum2[4], datum2[5]),
	(None, cont2['sha1_git'], None,
	cont2['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 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 = [{
	'dir_id': self.dir['id'],
	'type': ent['type'],
	'target': ent['target'],
	'name': ent['name'],
	'perms': ent['perms'],
	'status': None,
	'sha1': None,
	'sha1_git': None,
	'sha256': None,
	}
	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 revision_log(self):
	+ # given
	+ # self.revision4 -is-child-of-> self.revision3
	+ self.storage.revision_add([self.revision3,
	+ self.revision4])
	+
	+ # when
	+ actual_result = self.storage.revision_log(self.revision4['id'])
	+
	+ res = list(actual_result)
	+ self.assertEqual(len(res), 2) # revision4 is a child of revision3
	+
	+ revision3_copy = self.revision3.copy()
	+ revision4_copy = self.revision4.copy()
	+
	+ # parents property is not returned here
	+ revision3_copy['parents'] = []
	+ revision4_copy['parents'] = []
	+
	+ self.assertEquals(res[0], revision4_copy)
	+ self.assertEquals(res[1], revision3_copy)
	+
	@istest
	def revision_get(self):
	self.storage.revision_add([self.revision])

	get = list(self.storage.revision_get([self.revision['id'],
	self.revision2['id']]))

	self.assertEqual(len(get), 2)
	self.assertEqual(get[0], self.revision)
	+ self.assertEqual(get[0]['date'].utcoffset(),
	+ self.revision['date'].utcoffset())
	+ self.assertEqual(get[0]['committer_date'].utcoffset(),
	+ self.revision['committer_date'].utcoffset())
	self.assertEqual(get[1], None)

	@istest
	def revision_get_no_parents(self):
	self.storage.revision_add([self.revision3])

	get = list(self.storage.revision_get([self.revision3['id']]))

	self.assertEqual(len(get), 1)
	self.assertEqual(get[0]['parents'], []) # no parents on this one

	@istest
	def release_add(self):
	init_missing = self.storage.release_missing([self.release['id'],
	self.release2['id']])
	self.assertEqual([self.release['id'], self.release2['id']],
	list(init_missing))

	self.storage.release_add([self.release, self.release2])

	end_missing = self.storage.release_missing([self.release['id'],
	self.release2['id']])
	self.assertEqual([], list(end_missing))

	@istest
	def release_get(self):
	# given
	self.storage.release_add([self.release, self.release2])

	# when
	actual_releases = self.storage.release_get([self.release['id'],
	self.release2['id']])

	actual_releases = list(actual_releases)

	# then
	- expected_release0 = {
	- 'id': b'87659012345678901234',
	- 'revision': None,
	- 'date': datetime.datetime(2015, 1, 1, 22, 0, 0,
	- tzinfo=datetime.timezone.utc),
	- 'date_offset': None,
	- 'name': 'v0.0.1',
	- 'comment': b'synthetic release',
	- 'synthetic': True,
	- 'author_name': self.release['author_name'].encode('utf-8'),
	- 'author_email': self.release['author_email'].encode('utf-8'),
	- }
	- expected_release1 = {
	- 'id': b'56789012348765901234',
	- 'revision': None,
	- 'date': datetime.datetime(2015, 1, 2, 23, 0, 0,
	- tzinfo=datetime.timezone.utc),
	- 'date_offset': None,
	- 'name': 'v0.0.2',
	- 'comment': b'v0.0.2\nMisc performance improvments + bug fixes',
	- 'synthetic': False,
	- 'author_name': self.release2['author_name'].encode('utf-8'),
	- 'author_email': self.release2['author_email'].encode('utf-8'),
	- }
	-
	- self.assertEquals([expected_release0, expected_release1],
	+ self.assertEquals([self.release, self.release2],
	[actual_releases[0], actual_releases[1]])

	@istest
	def origin_add_one(self):
	origin0 = self.storage.origin_get(self.origin)
	self.assertIsNone(origin0)

	id = self.storage.origin_add_one(self.origin)

	actual_origin = self.storage.origin_get({'url': self.origin['url'],
	'type': self.origin['type']})
	self.assertEqual(actual_origin['id'], id)

	id2 = self.storage.origin_add_one(self.origin)

	self.assertEqual(id, id2)

	@istest
	def origin_get(self):
	self.assertIsNone(self.storage.origin_get(self.origin))
	id = self.storage.origin_add_one(self.origin)

	# lookup per type and url (returns id)
	actual_origin0 = self.storage.origin_get({'url': self.origin['url'],
	'type': self.origin['type']})
	self.assertEqual(actual_origin0['id'], id)

	# lookup per id (returns dict)
	actual_origin1 = self.storage.origin_get({'id': id})

	self.assertEqual(actual_origin1, {'id': id,
	'type': self.origin['type'],
	'url': self.origin['url'],
	'lister': None,
	'project': None})

	@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])

	occur = self.occurrence
	occur['origin'] = origin_id
	self.storage.occurrence_add([occur])
	self.storage.occurrence_add([occur])

	test_query = '''select origin, branch, revision, authority, validity
	from occurrence_history
	order by origin, validity'''

	self.cursor.execute(test_query)
	ret = self.cursor.fetchall()
	self.assertEqual(len(ret), 1)
	self.assertEqual((ret[0][0], ret[0][1], ret[0][2].tobytes(),
	ret[0][3]), (occur['origin'],
	occur['branch'], occur['revision'],
	occur['authority']))

	self.assertEqual(ret[0][4].lower, occur['validity'])
	self.assertEqual(ret[0][4].lower_inc, True)
	self.assertEqual(ret[0][4].upper, datetime.datetime.max)

	orig_validity = occur['validity']
	occur['validity'] += datetime.timedelta(hours=10)
	self.storage.occurrence_add([occur])

	self.cursor.execute(test_query)
	ret = self.cursor.fetchall()
	self.assertEqual(len(ret), 2)
	self.assertEqual(ret[0][4].lower, orig_validity)
	self.assertEqual(ret[0][4].lower_inc, True)
	self.assertEqual(ret[0][4].upper, occur['validity'])
	self.assertEqual(ret[0][4].upper_inc, False)
	self.assertEqual(ret[1][4].lower, occur['validity'])
	self.assertEqual(ret[1][4].lower_inc, True)
	self.assertEqual(ret[1][4].upper, datetime.datetime.max)

	@istest
	def content_find_occurrence_with_present_content(self):
	# 1. with something to find
	# given
	self.storage.content_add([self.cont2])
	self.storage.directory_add([self.dir2]) # point to self.cont
	self.storage.revision_add([self.revision2]) # points to self.dir
	origin_id = self.storage.origin_add_one(self.origin2)
	occurrence = self.occurrence2
	occurrence.update({'origin': origin_id})
	self.storage.occurrence_add([occurrence])

	# when
	occ = self.storage.content_find_occurrence(
	{'sha1': self.cont2['sha1']})

	# then
	self.assertEquals(occ['origin_type'], self.origin2['type'])
	self.assertEquals(occ['origin_url'], self.origin2['url'])
	self.assertEquals(occ['branch'], self.occurrence2['branch'])
	self.assertEquals(occ['revision'], self.revision2['id'])
	self.assertEquals(occ['path'], self.dir2['entries'][0]['name'])

	occ2 = self.storage.content_find_occurrence(
	{'sha1_git': self.cont2['sha1_git']})

	self.assertEquals(occ2['origin_type'], self.origin2['type'])
	self.assertEquals(occ2['origin_url'], self.origin2['url'])
	self.assertEquals(occ2['branch'], self.occurrence2['branch'])
	self.assertEquals(occ2['revision'], self.revision2['id'])
	self.assertEquals(occ2['path'], self.dir2['entries'][0]['name'])

	occ3 = self.storage.content_find_occurrence(
	{'sha256': self.cont2['sha256']})

	self.assertEquals(occ3['origin_type'], self.origin2['type'])
	self.assertEquals(occ3['origin_url'], self.origin2['url'])
	self.assertEquals(occ3['branch'], self.occurrence2['branch'])
	self.assertEquals(occ3['revision'], self.revision2['id'])
	self.assertEquals(occ3['path'], self.dir2['entries'][0]['name'])

	@istest
	def content_find_occurrence_with_non_present_content(self):
	# 1. with something that does not exist
	missing_cont = self.missing_cont

	occ = self.storage.content_find_occurrence(
	{'sha1': missing_cont['sha1']})

	self.assertEquals(occ, None,
	"Content does not exist so no occurrence")

	# 2. with something that does not exist
	occ = self.storage.content_find_occurrence(
	{'sha1_git': missing_cont['sha1_git']})

	self.assertEquals(occ, None,
	"Content does not exist so no occurrence")

	# 3. with something that does not exist
	occ = self.storage.content_find_occurrence(
	{'sha256': missing_cont['sha256']})

	self.assertEquals(occ, None,
	"Content does not exist so no occurrence")

	@istest
	def content_find_occurrence_bad_input(self):
	# 1. with bad input
	with self.assertRaises(ValueError) as cm:
	self.storage.content_find_occurrence({}) # empty is bad
	self.assertIn('content keys', cm.exception.args[0])

	# 2. with bad input
	with self.assertRaises(ValueError) as cm:
	self.storage.content_find_occurrence(
	{'unknown-sha1': 'something'}) # not the right key
	self.assertIn('content keys', cm.exception.args[0])

	@istest
	def entity_get_from_lister_metadata(self):
	self.storage.entity_add([self.entity1])

	fetched_entities = list(
	self.storage.entity_get_from_lister_metadata(
	[self.entity1_query, self.entity2_query]))

	# Entity 1 should have full metadata, with last_seen/last_id instead
	# of validity
	entity1 = self.entity1.copy()
	entity1['last_seen'] = entity1['validity'][0]
	del fetched_entities[0]['last_id']
	del entity1['validity']
	# Entity 2 should have no metadata
	entity2 = self.entity2_query.copy()
	entity2['uuid'] = None

	self.assertEquals(fetched_entities, [entity1, entity2])

	@istest
	def stat_counters(self):
	expected_keys = ['content', 'directory', 'directory_entry_dir',
	'occurrence', 'origin', 'person', 'revision']
	counters = self.storage.stat_counters()

	self.assertTrue(set(expected_keys) <= set(counters))
	self.assertIsInstance(counters[expected_keys[0]], int)


	class TestStorage(AbstractTestStorage, unittest.TestCase):
	"""Test the local storage"""

	# Can only be tested with local storage as you can't mock
	# datetimes for the remote server
	@istest
	def fetch_history(self):
	origin = self.storage.origin_add_one(self.origin)
	with patch('datetime.datetime'):
	datetime.datetime.now.return_value = self.fetch_history_date
	fetch_history_id = self.storage.fetch_history_start(origin)
	datetime.datetime.now.assert_called_with(tz=datetime.timezone.utc)

	with patch('datetime.datetime'):
	datetime.datetime.now.return_value = self.fetch_history_end
	self.storage.fetch_history_end(fetch_history_id,
	self.fetch_history_data)

	fetch_history = self.storage.fetch_history_get(fetch_history_id)
	expected_fetch_history = self.fetch_history_data.copy()

	expected_fetch_history['id'] = fetch_history_id
	expected_fetch_history['origin'] = origin
	expected_fetch_history['date'] = self.fetch_history_date
	expected_fetch_history['duration'] = self.fetch_history_duration

	self.assertEqual(expected_fetch_history, fetch_history)

	@istest
	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_find({'sha1': cont['sha1']})

	actually_present.pop('ctime')
	self.assertEqual(actually_present, {
	'sha1': cont['sha1'],
	'sha256': cont['sha256'],
	'sha1_git': cont['sha1_git'],
	'length': cont['length'],
	'status': 'visible'
	})

	# 2. with something to find
	actually_present = self.storage.content_find(
	{'sha1_git': cont['sha1_git']})

	actually_present.pop('ctime')
	self.assertEqual(actually_present, {
	'sha1': cont['sha1'],
	'sha256': cont['sha256'],
	'sha1_git': cont['sha1_git'],
	'length': cont['length'],
	'status': 'visible'
	})

	# 3. with something to find
	actually_present = self.storage.content_find(
	{'sha256': cont['sha256']})

	actually_present.pop('ctime')
	self.assertEqual(actually_present, {
	'sha1': cont['sha1'],
	'sha256': cont['sha256'],
	'sha1_git': cont['sha1_git'],
	'length': cont['length'],
	'status': 'visible'
	})

	# 4. with something to find
	actually_present = self.storage.content_find(
	{'sha1': cont['sha1'],
	'sha1_git': cont['sha1_git'],
	'sha256': cont['sha256']})

	actually_present.pop('ctime')
	self.assertEqual(actually_present, {
	'sha1': cont['sha1'],
	'sha256': cont['sha256'],
	'sha1_git': cont['sha1_git'],
	'length': cont['length'],
	'status': 'visible'
	})

	@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_find(
	{'sha1': missing_cont['sha1']})

	self.assertIsNone(actually_present)

	# 2. with something that does not exist
	actually_present = self.storage.content_find(
	{'sha1_git': missing_cont['sha1_git']})

	self.assertIsNone(actually_present)

	# 3. with something that does not exist
	actually_present = self.storage.content_find(
	{'sha256': missing_cont['sha256']})

	self.assertIsNone(actually_present)

	@istest
	def content_find_bad_input(self):
	# 1. with bad input
	with self.assertRaises(ValueError):
	self.storage.content_find({}) # empty is bad

	# 2. with bad input
	with self.assertRaises(ValueError):
	self.storage.content_find(
	{'unknown-sha1': 'something'}) # not the right key

	@istest
	def person_get(self):
	# given
	person0 = {'name': b'bob', 'email': b'alice@bob'}
	id0 = self.storage._person_add(person0)
	person1 = {'name': b'tony', 'email': b'tony@bob'}
	id1 = self.storage._person_add(person1)

	# when
	actual_persons = self.storage.person_get([id0, id1])

	# given (person injection through release for example)
	self.assertEqual(list(actual_persons), [{'id': id0,
	'name': person0['name'],
	'email': person0['email']},
	{'id': id1,
	'name': person1['name'],
	'email': person1['email']}])
	diff --git a/version.txt b/version.txt
	index 382157200..b9e1ad5c0 100644
	--- a/version.txt
	+++ b/version.txt
	@@ -1 +1 @@
	-v0.0.19-0-ga499554
	\ No newline at end of file
	+v0.0.20-0-g691e24a
	\ No newline at end of file

File Metadata

Mime Type: text/x-diff
Expires: Jul 4 2025, 8:50 AM (7 w, 1 h ago)
Storage Engine: blob
Storage Format: Raw Data
Storage Handle: 3450936

No OneTemporaryActions

View Options

File Metadata

Event Timeline

No OneTemporary
Actions