diff --git a/MANIFEST.in b/MANIFEST.in index e11ad0d6..d9b2665a 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,6 +1,7 @@ include Makefile include Makefile.local include README.db_testing +include README.dev include requirements.txt include version.txt recursive-include sql * diff --git a/PKG-INFO b/PKG-INFO index 4e60e026..80f0da26 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,10 +1,10 @@ Metadata-Version: 1.0 Name: swh.storage -Version: 0.0.3 +Version: 0.0.4 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/README.dev b/README.dev new file mode 100644 index 00000000..c0e68819 --- /dev/null +++ b/README.dev @@ -0,0 +1,13 @@ +# A test server should be running for tests + +Sample configuration (e.g. ~/.config/swh/storage.ini): + + [main] + db=dbname=softwareheritage-dev + storage_base=/tmp/swh/storage/ + +Note: `storage_base` entry referenced should exist. + +# Start + +python3 -m swh.storage.api ~/.config/swh/storage.ini diff --git a/debian/changelog b/debian/changelog new file mode 100644 index 00000000..d97d1939 --- /dev/null +++ b/debian/changelog @@ -0,0 +1,17 @@ +swh-storage (0.0.2-1~bpo8+1) jessie-backports; urgency=medium + + * Rebuild for jessie-backports. + + -- Nicolas Dandrimont Wed, 23 Sep 2015 13:22:50 +0200 + +swh-storage (0.0.2-1) unstable; urgency=medium + + * Update to v0.0.2 + + -- Nicolas Dandrimont Wed, 23 Sep 2015 13:19:44 +0200 + +swh-storage (0.0.1-1) unstable; urgency=low + + * Import initial source package. + + -- Nicolas Dandrimont Tue, 22 Sep 2015 12:05:09 +0200 diff --git a/debian/compat b/debian/compat new file mode 100644 index 00000000..ec635144 --- /dev/null +++ b/debian/compat @@ -0,0 +1 @@ +9 diff --git a/debian/control b/debian/control new file mode 100644 index 00000000..3a8b05d4 --- /dev/null +++ b/debian/control @@ -0,0 +1,21 @@ +Source: swh-storage +Maintainer: Software Heritage developers +Section: python +Priority: optional +Build-Depends: debhelper (>= 9), + dh-python, + python3-all, + python3-flask, + python3-nose, + python3-psycopg2, + python3-requests, + python3-setuptools, + python3-swh.core, + python3-vcversioner +Standards-Version: 3.9.6 +Homepage: https://forge.softwareheritage.org/diffusion/DCORE/ + +Package: python3-swh.storage +Architecture: all +Depends: ${misc:Depends}, ${python3:Depends} +Description: Software Heritage storage utilities diff --git a/debian/copyright b/debian/copyright new file mode 100644 index 00000000..81d037db --- /dev/null +++ b/debian/copyright @@ -0,0 +1,22 @@ +Format: http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/ + +Files: * +Copyright: 2015 The Software Heritage developers +License: GPL-3+ + +License: GPL-3+ + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 3 of the License, or + (at your option) any later version. + . + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + . + You should have received a copy of the GNU General Public License + along with this program. If not, see . + . + On Debian systems, the complete text of the GNU General Public + License version 3 can be found in `/usr/share/common-licenses/GPL-3'. diff --git a/debian/rules b/debian/rules new file mode 100755 index 00000000..9ad29f6a --- /dev/null +++ b/debian/rules @@ -0,0 +1,14 @@ +#!/usr/bin/make -f + +# This file was automatically generated by stdeb 0.8.5 at +# Tue, 22 Sep 2015 12:05:09 +0200 +export PYBUILD_NAME=swh-storage + +%: + dh $@ --with python3 --buildsystem=pybuild + + +override_dh_auto_test: + PYBUILD_SYSTEM=custom \ + PYBUILD_TEST_ARGS="python{version} -m nose swh -sva '!db'" \ + dh_auto_test diff --git a/debian/source/format b/debian/source/format new file mode 100644 index 00000000..163aaf8d --- /dev/null +++ b/debian/source/format @@ -0,0 +1 @@ +3.0 (quilt) diff --git a/requirements.txt b/requirements.txt index d212d44a..bfbf3d39 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,8 +1,11 @@ psycopg2 vcversioner # remote storage API client requests # remote storage API server flask + +# Internal dependencies +swh.core diff --git a/sql/clusters.dot b/sql/clusters.dot index 2c6c864b..d22b50f4 100644 --- a/sql/clusters.dot +++ b/sql/clusters.dot @@ -1,89 +1,91 @@ subgraph "logical_grouping" { style = rounded; bgcolor = gray95; color = gray; subgraph cluster_meta { label = <meta>; dbversion; } subgraph cluster_content { label = <content>; content; } subgraph cluster_directory { label = <directories>; directory; directory_entry_dir; directory_entry_file; directory_entry_rev; directory_list_dir; directory_list_file; directory_list_rev; {rank=same; directory_list_dir directory_list_file directory_list_rev} {rank=same; directory_entry_dir directory_entry_file directory_entry_rev} } subgraph cluster_revision { label = <revisions>; revision; revision_history; person; } subgraph cluster_release { label = <releases>; release; } subgraph cluster_occurrences { label = <occurrences>; occurrence; occurrence_history; } subgraph cluster_origins { label = <origins>; origin; fetch_history; } subgraph cluster_projects { label = <projects>; project; project_history; } subgraph cluster_organization { label = <organizations>; organization; list_history; } { edge [style = dashed]; # "rtcolN" identifies the N-th row in a table, as a source # "ltcolN" identifies the N-th row in a table, as a destination "directory_entry_dir":rtcol2 -> "directory":ltcol1; "directory_entry_file":rtcol2 -> "content":ltcol2; "directory_entry_rev":rtcol2 -> "revision":ltcol1; "directory_list_dir":rtcol2 -> "directory_entry_dir":ltcol1; "directory_list_file":rtcol2 -> "directory_entry_file":ltcol1; "directory_list_rev":rtcol2 -> "directory_entry_rev":ltcol1; + "occurrence":rtcol3 -> "revision":ltcol1; + "occurrence_history":rtcol3 -> "revision":ltcol1; "release":rtcol2 -> "revision":ltcol1; "revision":rtcol7 -> "directory":ltcol1; "revision_history":rtcol2 -> "revision":ltcol1; } } diff --git a/sql/swh-func.sql b/sql/swh-func.sql index d2bf5779..29201a28 100644 --- a/sql/swh-func.sql +++ b/sql/swh-func.sql @@ -1,400 +1,462 @@ -- create a temporary table called tmp_TBLNAME, mimicking existing table -- TBLNAME -- -- Args: -- tblname: name of the table to mimick create or replace function swh_mktemp(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table tmp_%I (like %I including defaults) on commit drop ', tblname, tblname); return; end $$; -- create a temporary table for directory entries called tmp_TBLNAME, -- mimicking existing table TBLNAME with an extra dir_id (sha1_git) -- column, and dropping the id column. -- -- This is used to create the tmp_directory_entry_ tables. -- -- Args: -- tblname: name of the table to mimick create or replace function swh_mktemp_dir_entry(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table tmp_%I (like %I including defaults, dir_id sha1_git) on commit drop; alter table tmp_%I drop column id; ', tblname, tblname, tblname, tblname); return; end $$; -- create a temporary table for revisions called tmp_revisions, -- mimicking existing table revision, replacing the foreign keys to -- people with an email and name field -- create or replace function swh_mktemp_revision() returns void language plpgsql as $$ begin create temporary table tmp_revision ( like revision including defaults, author_name text not null default '', author_email text not null default '', committer_name text not null default '', committer_email text not null default '' ) on commit drop; alter table tmp_revision drop column author; alter table tmp_revision drop column committer; return; end $$; -- create a temporary table for releases called tmp_release, -- mimicking existing table release, replacing the foreign keys to -- people with an email and name field -- create or replace function swh_mktemp_release() returns void language plpgsql as $$ begin create temporary table tmp_release ( like release including defaults, author_name text not null default '', author_email text not null default '' ) on commit drop; alter table tmp_release drop column author; return; end $$; -- a content signature is a set of cryptographic checksums that we use to -- uniquely identify content, for the purpose of verifying if we already have -- some content or not during content injection create type content_signature as ( sha1 sha1, sha1_git sha1_git, sha256 sha256 ); -- check which entries of tmp_content are missing from content -- -- operates in bulk: 0. swh_mktemp(content), 1. COPY to tmp_content, -- 2. call this function create or replace function swh_content_missing() returns setof content_signature language plpgsql as $$ begin return query select sha1, sha1_git, sha256 from tmp_content except select sha1, sha1_git, sha256 from content; return; end $$; -- add tmp_content entries to content, skipping duplicates -- -- operates in bulk: 0. swh_mktemp(content), 1. COPY to tmp_content, -- 2. call this function create or replace function swh_content_add() returns void language plpgsql as $$ declare rows bigint; begin insert into content (sha1, sha1_git, sha256, length, status) select distinct sha1, sha1_git, sha256, length, status from tmp_content where (sha1, sha1_git, sha256) in (select * from swh_content_missing()); -- TODO XXX use postgres 9.5 "UPSERT" support here, when available. -- Specifically, using "INSERT .. ON CONFLICT IGNORE" we can avoid -- the extra swh_content_missing() query here. return; end $$; -- check which entries of tmp_directory are missing from directory -- -- operates in bulk: 0. swh_mktemp(directory), 1. COPY to tmp_directory, -- 2. call this function create or replace function swh_directory_missing() returns setof directory language plpgsql as $$ begin return query select id from tmp_directory except select id from directory; return; end $$; -- Add tmp_directory_entry_dir entries to directory_entry_dir and -- directory_list_dir, skipping duplicates in directory_entry_dir. -- -- operates in bulk: 0. swh_mktemp_dir_entry('directory_entry_dir'), 1 COPY to -- tmp_directory_entry_dir, 2. call this function create or replace function swh_directory_entry_dir_add() returns void language plpgsql as $$ begin insert into directory_entry_dir (target, name, perms, atime, mtime, ctime) select distinct t.target, t.name, t.perms, t.atime, t.mtime, t.ctime from tmp_directory_entry_dir t where not exists ( select 1 from directory_entry_dir i where t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime); insert into directory_list_dir (dir_id, entry_ids) select t.dir_id, array_agg(i.id) from tmp_directory_entry_dir t inner join directory_entry_dir i on t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime group by t.dir_id; return; end $$; -- Add tmp_directory_entry_file entries to directory_entry_file and -- directory_list_file, skipping duplicates in directory_entry_file. -- -- operates in bulk: 0. swh_mktemp_dir_entry('directory_entry_file'), 1 COPY to -- tmp_directory_entry_file, 2. call this function create or replace function swh_directory_entry_file_add() returns void language plpgsql as $$ begin insert into directory_entry_file (target, name, perms, atime, mtime, ctime) select distinct t.target, t.name, t.perms, t.atime, t.mtime, t.ctime from tmp_directory_entry_file t where not exists ( select 1 from directory_entry_file i where t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime); insert into directory_list_file (dir_id, entry_ids) select t.dir_id, array_agg(i.id) from tmp_directory_entry_file t inner join directory_entry_file i on t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime group by t.dir_id; return; end $$; -- Add tmp_directory_entry_rev entries to directory_entry_rev and -- directory_list_rev, skipping duplicates in directory_entry_rev. -- -- operates in bulk: 0. swh_mktemp_dir_entry('directory_entry_rev'), 1 COPY to -- tmp_directory_entry_rev, 2. call this function create or replace function swh_directory_entry_rev_add() returns void language plpgsql as $$ begin insert into directory_entry_rev (target, name, perms, atime, mtime, ctime) select distinct t.target, t.name, t.perms, t.atime, t.mtime, t.ctime from tmp_directory_entry_rev t where not exists ( select 1 from directory_entry_rev i where t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime); insert into directory_list_rev (dir_id, entry_ids) select t.dir_id, array_agg(i.id) from tmp_directory_entry_rev t inner join directory_entry_rev i on t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime group by t.dir_id; return; end $$; +create type directory_entry_type as enum('file', 'dir', 'rev'); + -- a directory listing entry with all the metadata -- -- can be used to list a directory, and retrieve all the data in one go. create type directory_entry as ( dir_id sha1_git, -- id of the parent directory - type text, -- type of entry (one of 'dir', 'file', 'rev') + type directory_entry_type, -- type of entry target sha1_git, -- id of target name unix_path, -- path name, relative to containing dir perms file_perms, -- unix-like permissions atime timestamptz, -- time of last access mtime timestamptz, -- time of last modification ctime timestamptz -- time of last status change ); -- List a single level of directory walked_dir_id create or replace function swh_directory_walk_one(walked_dir_id sha1_git) returns setof directory_entry language plpgsql as $$ begin return query ( (with l as (select dir_id, unnest(entry_ids) as entry_id from directory_list_dir where dir_id = walked_dir_id) - select dir_id, 'dir' as type, target, name, perms, atime, mtime, ctime + select dir_id, 'dir'::directory_entry_type as type, target, name, perms, atime, mtime, ctime from l left join directory_entry_dir d on l.entry_id = d.id) union (with l as (select dir_id, unnest(entry_ids) as entry_id from directory_list_file where dir_id = walked_dir_id) - select dir_id, 'file' as type, target, name, perms, atime, mtime, ctime + select dir_id, 'file'::directory_entry_type as type, target, name, perms, atime, mtime, ctime from l left join directory_entry_file d on l.entry_id = d.id) union (with l as (select dir_id, unnest(entry_ids) as entry_id from directory_list_rev where dir_id = walked_dir_id) - select dir_id, 'rev' as type, target, name, perms, atime, mtime, ctime + select dir_id, 'rev'::directory_entry_type as type, target, name, perms, atime, mtime, ctime from l left join directory_entry_rev d on l.entry_id = d.id) ) order by name; return; end $$; +-- List all revision IDs starting from a given revision, going back in time +-- +-- TODO ordering: should be breadth-first right now (what do we want?) +-- TODO ordering: ORDER BY parent_rank somewhere? +create or replace function swh_revision_list(root_revision sha1_git) + returns setof sha1_git + language plpgsql +as $$ +begin + return query + with recursive rev_list(id) as ( + (select id from revision where id = root_revision) + union + (select parent_id + from revision_history as h + join rev_list on h.id = rev_list.id) + ) + select * from rev_list; + return; +end +$$; + +-- Detailed entry in a revision log +create type revision_log_entry as +( + id sha1_git, + date timestamptz, + date_offset smallint, + committer_date timestamptz, + committer_date_offset smallint, + type revision_type, + directory sha1_git, + message bytea, + author_name text, + author_email text, + committer_name text, + committer_email text +); + +-- "git style" revision log. Similar to swh_revision_list(), but returning all +-- information associated to each revision, and expanding authors/committers +create or replace function swh_revision_log(root_revision sha1_git) + returns setof revision_log_entry + language plpgsql +as $$ +begin + return query + select revision.id, date, date_offset, + committer_date, committer_date_offset, + type, directory, message, + author.name as author_name, author.email as author_email, + committer.name as committer_name, committer.email as committer_email + from swh_revision_list(root_revision) as rev_list + join revision on revision.id = rev_list + join person as author on revision.author = author.id + join person as committer on revision.committer = committer.id; + return; +end +$$; + -- List missing revisions from tmp_revision create or replace function swh_revision_missing() returns setof sha1_git language plpgsql as $$ begin return query select id from tmp_revision except select id from revision; return; end $$; -- Create entries in person from tmp_revision create or replace function swh_person_add_from_revision() returns void language plpgsql as $$ begin with t as ( select author_name as name, author_email as email from tmp_revision union select committer_name as name, committer_email as email from tmp_revision ) insert into person (name, email) select distinct name, email from t where not exists ( select 1 from person p where t.name = p.name and t.email = p.email ); return; end $$; -- Create entries in revision from tmp_revision create or replace function swh_revision_add() returns void language plpgsql as $$ begin perform swh_person_add_from_revision(); insert into revision (id, date, date_offset, committer_date, committer_date_offset, type, directory, message, author, committer) select t.id, t.date, t.date_offset, t.committer_date, t.committer_date_offset, t.type, t.directory, t.message, a.id, c.id from tmp_revision t left join person a on a.name = t.author_name and a.email = t.author_email left join person c on c.name = t.committer_name and c.email = t.committer_email; return; end $$; -- List missing releases from tmp_release create or replace function swh_release_missing() returns setof sha1_git language plpgsql as $$ begin return query select id from tmp_release except select id from release; return; end $$; -- Create entries in person from tmp_release create or replace function swh_person_add_from_release() returns void language plpgsql as $$ begin with t as ( select distinct author_name as name, author_email as email from tmp_release ) insert into person (name, email) select name, email from t where not exists ( select 1 from person p where t.name = p.name and t.email = p.email ); return; end $$; -- Create entries in release from tmp_release create or replace function swh_release_add() returns void language plpgsql as $$ begin perform swh_person_add_from_release(); insert into release (id, revision, date, date_offset, name, comment, author) select t.id, t.revision, t.date, t.date_offset, t.name, t.comment, a.id from tmp_release t left join person a on a.name = t.author_name and a.email = t.author_email; return; end $$; diff --git a/swh.storage.egg-info/PKG-INFO b/swh.storage.egg-info/PKG-INFO index 4e60e026..80f0da26 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: 0.0.3 +Version: 0.0.4 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 9cd43e04..5c22e35e 100644 --- a/swh.storage.egg-info/SOURCES.txt +++ b/swh.storage.egg-info/SOURCES.txt @@ -1,37 +1,44 @@ .gitignore 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/dot_add_content 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/api.py swh/storage/db.py swh/storage/objstorage.py swh/storage/remote_storage.py swh/storage/storage.py swh/storage/tests/__init__.py swh/storage/tests/db_testing.py swh/storage/tests/test_db.py swh/storage/tests/test_objstorage.py swh/storage/tests/test_remote_storage.py swh/storage/tests/test_storage.py \ No newline at end of file diff --git a/swh.storage.egg-info/requires.txt b/swh.storage.egg-info/requires.txt index 306b5cef..51783a3d 100644 --- a/swh.storage.egg-info/requires.txt +++ b/swh.storage.egg-info/requires.txt @@ -1,4 +1,5 @@ flask psycopg2 requests +swh.core vcversioner diff --git a/swh/storage/api.py b/swh/storage/api.py index 45556f24..9f311a78 100644 --- a/swh/storage/api.py +++ b/swh/storage/api.py @@ -1,147 +1,152 @@ # Copyright (C) 2015 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import json import logging from flask import Flask, Request, Response, abort, g, request from swh.core import config from swh.core.json import SWHJSONDecoder, SWHJSONEncoder from swh.core.hashutil import hash_to_hex from swh.storage import Storage DEFAULT_CONFIG = { 'db': ('str', 'dbname=softwareheritage-dev'), 'storage_base': ('str', '/tmp/swh-storage/test'), } class BytesRequest(Request): """Request with proper escaping of arbitrary byte sequences.""" encoding = 'utf-8' encoding_errors = 'surrogateescape' app = Flask(__name__) app.json_encoder = SWHJSONEncoder app.json_decoder = SWHJSONDecoder app.request_class = BytesRequest def jsonify(data): return Response( json.dumps(data, cls=SWHJSONEncoder), mimetype='application/json', ) @app.before_request def before_request(): g.storage = Storage(app.config['db'], app.config['storage_base']) @app.route('/') def index(): return 'Hello' @app.route('/content/missing', methods=['POST']) def content_missing(): return jsonify(g.storage.content_missing(**request.json)) +@app.route('/content/present', methods=['POST']) +def content_present(): + return jsonify(g.storage.content_present(**request.json)) + + @app.route('/content/add', methods=['POST']) def content_add(): json_data = request.files['metadata'].read().decode('utf-8') metadata = json.loads(json_data, cls=SWHJSONDecoder)['content'] for file_data in metadata: file_id = hash_to_hex(file_data['sha1']) file = request.files[file_id] file_data['data'] = file.read() file.close() return jsonify(g.storage.content_add(content=metadata)) @app.route('/directory/missing', methods=['POST']) def directory_missing(): return jsonify(g.storage.directory_missing(**request.json)) @app.route('/directory/add', methods=['POST']) def directory_add(): return jsonify(g.storage.directory_add(**request.json)) @app.route('/directory', methods=['GET']) def directory_get(): dir = request.args['directory'].encode('utf-8', 'surrogateescape') return jsonify(g.storage.directory_get(dir)) @app.route('/revision/add', methods=['POST']) def revision_add(): return jsonify(g.storage.revision_add(**request.json)) @app.route('/revision/missing', methods=['POST']) def revision_missing(): return jsonify(g.storage.revision_missing(**request.json)) @app.route('/release/add', methods=['POST']) def release_add(): return jsonify(g.storage.release_add(**request.json)) @app.route('/release/missing', methods=['POST']) def release_missing(): return jsonify(g.storage.release_missing(**request.json)) @app.route('/occurrence/add', methods=['POST']) def occurrence_add(): return jsonify(g.storage.occurrence_add(**request.json)) @app.route('/origin', methods=['GET']) def origin_get(): origin = { 'type': request.args['type'], 'url': request.args['url'], } id = g.storage.origin_get(origin) if not id: abort(404) else: origin['id'] = id return jsonify(origin) @app.route('/origin', methods=['POST']) def origin_add_one(): return jsonify(g.storage.origin_add_one(**request.json)) def run_from_webserver(environ, start_response): """Run the WSGI app from the webserver, loading the configuration.""" config_path = '/etc/softwareheritage/storage/storage.ini' app.config.update(config.read(config_path, DEFAULT_CONFIG)) handler = logging.StreamHandler() app.logger.addHandler(handler) return app(environ, start_response) if __name__ == '__main__': import sys app.config.update(config.read(sys.argv[1], DEFAULT_CONFIG)) app.run(debug=True) diff --git a/swh/storage/db.py b/swh/storage/db.py index ffedfd66..3c08c53a 100644 --- a/swh/storage/db.py +++ b/swh/storage/db.py @@ -1,186 +1,197 @@ # Copyright (C) 2015 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import binascii import functools import psycopg2 import tempfile from contextlib import contextmanager TMP_CONTENT_TABLE = 'tmp_content' def stored_procedure(stored_proc): """decorator to execute remote stored procedure, specified as argument Generally, the body of the decorated function should be empty. If it is not, the stored procedure will be executed first; the function body then. """ def wrap(meth): @functools.wraps(meth) def _meth(self, *args, **kwargs): cur = kwargs.get('cur', None) self._cursor(cur).execute('SELECT %s()' % stored_proc) meth(self, *args, **kwargs) return _meth return wrap def entry_to_bytes(entry): """Convert an entry coming from the database to bytes""" if isinstance(entry, memoryview): return entry.tobytes() return entry def line_to_bytes(line): """Convert a line coming from the database to bytes""" return line.__class__(entry_to_bytes(entry) for entry in line) def cursor_to_bytes(cursor): """Yield all the data from a cursor as bytes""" yield from (line_to_bytes(line) for line in cursor) class Db: """Proxy to the SWH DB, with wrappers around stored procedures """ @classmethod def connect(cls, *args, **kwargs): """factory method to create a DB proxy Accepts all arguments of psycopg2.connect; only some specific possibilities are reported below. Args: connstring: libpq2 connection string """ conn = psycopg2.connect(*args, **kwargs) return cls(conn) def _cursor(self, cur_arg): """get a cursor: from cur_arg if given, or a fresh one otherwise meant to avoid boilerplate if/then/else in methods that proxy stored procedures """ if cur_arg is not None: return cur_arg # elif self.cur is not None: # return self.cur else: return self.conn.cursor() def __init__(self, conn): """create a DB proxy Args: conn: psycopg2 connection to the SWH DB """ self.conn = conn @contextmanager def transaction(self): """context manager to execute within a DB transaction Yields: a psycopg2 cursor """ with self.conn.cursor() as cur: try: yield cur self.conn.commit() except: if not self.conn.closed: self.conn.rollback() raise def mktemp(self, tblname, cur=None): self._cursor(cur).execute('SELECT swh_mktemp(%s)', (tblname,)) def mktemp_dir_entry(self, entry_type, cur=None): self._cursor(cur).execute('SELECT swh_mktemp_dir_entry(%s)', (('directory_entry_%s' % entry_type),)) @stored_procedure('swh_mktemp_revision') def mktemp_revision(self, cur=None): pass @stored_procedure('swh_mktemp_release') def mktemp_release(self, cur=None): pass def copy_to(self, items, tblname, columns, cur=None, item_cb=None): def escape(data): if data is None: return '' if isinstance(data, bytes): return '\\x%s' % binascii.hexlify(data).decode('ascii') elif isinstance(data, str): return '"%s"' % data.replace('"', '""') else: return str(data) with tempfile.TemporaryFile('w+') as f: for d in items: if item_cb is not None: item_cb(d) line = [escape(d.get(k)) for k in columns] f.write(','.join(line)) f.write('\n') f.seek(0) self._cursor(cur).copy_expert('COPY %s (%s) FROM STDIN CSV' % ( tblname, ', '.join(columns)), f) @stored_procedure('swh_content_add') def content_add_from_temp(self, cur=None): pass @stored_procedure('swh_revision_add') def revision_add_from_temp(self, cur=None): pass @stored_procedure('swh_release_add') def release_add_from_temp(self, cur=None): pass def content_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute("""SELECT sha1, sha1_git, sha256 FROM swh_content_missing()""") yield from cursor_to_bytes(cur) + def content_present(self, column_key, hash, cur=None): + cur = self._cursor(cur) + + escaped_query = """SELECT {0} + FROM content + WHERE {0}=%s + LIMIT 1""".format(column_key) + cur.execute(escaped_query, (hash, )) + + yield from cursor_to_bytes(cur) + def directory_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT id FROM swh_directory_missing()') yield from cursor_to_bytes(cur) def directory_walk_one(self, directory, cur=None): cur = self._cursor(cur) cur.execute('SELECT * FROM swh_directory_walk_one(%s)', (directory,)) yield from cursor_to_bytes(cur) def revision_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT id FROM swh_revision_missing() as r(id)') yield from cursor_to_bytes(cur) def release_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT id FROM swh_release_missing() as r(id)') yield from cursor_to_bytes(cur) diff --git a/swh/storage/remote_storage.py b/swh/storage/remote_storage.py index 67858c9f..07cb4851 100644 --- a/swh/storage/remote_storage.py +++ b/swh/storage/remote_storage.py @@ -1,98 +1,101 @@ # Copyright (C) 2015 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import json import requests from swh.core.hashutil import hash_to_hex from swh.core.json import SWHJSONDecoder, SWHJSONEncoder class RemoteStorage(): """Proxy to a remote storage API""" def __init__(self, base_url): self.base_url = base_url def url(self, endpoint): return '%s%s' % (self.base_url, endpoint) def post(self, endpoint, data): raw_data = json.dumps(data, cls=SWHJSONEncoder) response = requests.post( self.url(endpoint), data=raw_data, headers={'content-type': 'application/json; charset=utf8'}, ) return response.json(cls=SWHJSONDecoder) def post_files(self, endpoint, data, files): raw_data = json.dumps(data, cls=SWHJSONEncoder) files['metadata'] = raw_data response = requests.post( self.url(endpoint), files=files, ) return response.json(cls=SWHJSONDecoder) def get(self, endpoint, data): response = requests.get( self.url(endpoint), params=data, ) if response.status_code == 404: return None else: return response.json(cls=SWHJSONDecoder) def content_add(self, content): files = {} for file in content: file_id = hash_to_hex(file['sha1']) files[file_id] = file.pop('data') return self.post_files('content/add', {'content': content}, files) def content_missing(self, content, key_hash='sha1'): return self.post('content/missing', {'content': content, 'key_hash': key_hash}) + def content_present(self, content): + return self.post('content/present', {'content': content}) + def directory_add(self, directories): return self.post('directory/add', {'directories': directories}) def directory_missing(self, directories): return self.post('directory/missing', {'directories': directories}) def directory_get(self, directory): return [tuple(entry) for entry in self.get('directory', {'directory': directory})] def revision_add(self, revisions): return self.post('revision/add', {'revisions': revisions}) def revision_missing(self, revisions): return self.post('revision/missing', {'revisions': revisions}) def release_add(self, releases): return self.post('release/add', {'releases': releases}) def release_missing(self, releases): return self.post('release/missing', {'releases': releases}) def occurrence_add(self, occurrences): return self.post('occurrence/add', {'occurrences': occurrences}) def origin_get(self, origin): origin = self.get('origin', origin) if not origin: return None else: return origin['id'] def origin_add_one(self, origin): return self.post('origin', {'origin': origin}) diff --git a/swh/storage/storage.py b/swh/storage/storage.py index 56104807..dc1ba3d1 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,429 +1,472 @@ # Copyright (C) 2015 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import functools import itertools import psycopg2 from collections import defaultdict from operator import itemgetter from .db import Db from .objstorage import ObjStorage def db_transaction(meth): """decorator to execute Storage methods within DB transactions The decorated method must accept a `cur` keyword argument """ @functools.wraps(meth) def _meth(self, *args, **kwargs): with self.db.transaction() as cur: return meth(self, *args, cur=cur, **kwargs) return _meth def db_transaction_generator(meth): """decorator to execute Storage methods within DB transactions, while returning a generator The decorated method must accept a `cur` keyword argument """ @functools.wraps(meth) def _meth(self, *args, **kwargs): with self.db.transaction() as cur: yield from meth(self, *args, cur=cur, **kwargs) return _meth class Storage(): """SWH storage proxy, encompassing DB and object storage """ def __init__(self, db_conn, obj_root): """ Args: db_conn: either a libpq connection string, or a psycopg2 connection obj_root: path to the root of the object storage """ if isinstance(db_conn, psycopg2.extensions.connection): self.db = Db(db_conn) else: self.db = Db.connect(db_conn) self.objstorage = ObjStorage(obj_root) def content_add(self, content): """Add content blobs to the storage Note: in case of DB errors, objects might have already been added to the object storage and will not be removed. Since addition to the object storage is idempotent, that should not be a problem. Args: content: iterable of dictionaries representing individual pieces of content to add. Each dictionary has the following keys: - data (bytes): the actual content - length (int): content length - one key for each checksum algorithm in swh.core.hashutil.ALGORITHMS, mapped to the corresponding checksum """ db = self.db missing_content = set(self.content_missing(content)) if not missing_content: return with db.transaction() as cur: # create temporary table for metadata injection db.mktemp('content', cur) def add_to_objstorage(cont): self.objstorage.add_bytes(cont['data'], obj_id=cont['sha1']) content_filtered = sorted(( cont for cont in content if cont['sha1'] in missing_content), key=itemgetter('sha1')) db.copy_to(content_filtered, 'tmp_content', ['sha1', 'sha1_git', 'sha256', 'length'], cur, item_cb=add_to_objstorage) # move metadata in place db.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 + def content_present(self, content, cur=None): + """Predicate to check the presence of a content's hashes. + + Args: + hashes: iterable of dictionaries representing individual pieces of + hash. Each dictionary has the following keys: + - a key for each checksum algorithm in swh.core.hashutil.ALGORITHMS, + mapped to the corresponding checksum + + Returns: + a boolean indicator of presence + + Raises: + ValueError in case the key of the dictionary is not sha1 nor sha256 + + """ + db = self.db + + # filter out the checksums + if 'sha1' in content: + column_key = 'sha1' + elif 'sha256' in content: + column_key = 'sha256' + else: + raise ValueError('Key must be one of sha1, sha256.') + + # format the output + found_hashes = db.content_present(column_key, + content[column_key], + cur) + + return len(list(found_hashes)) > 0 + def directory_add(self, directories): """Add directories to the storage Args: directories: iterable of dictionaries representing the individual directories to add. Each dict has the following keys: - id (sha1_git): the id of the directory to add - entries (list): list of dicts for each entry in the directory. Each dict has the following keys: - name (bytes) - type (one of 'file', 'dir', 'rev'): type of the directory entry (file, directory, revision) - target (sha1_git): id of the object pointed at by the directory entry - perms (int): entry permissions - atime (datetime.DateTime): entry access time - ctime (datetime.DateTime): entry creation time - mtime (datetime.DateTime): entry modification time """ dirs = set() dir_entries = { 'file': defaultdict(list), 'dir': defaultdict(list), 'rev': defaultdict(list), } for cur_dir in directories: dir_id = cur_dir['id'] dirs.add(dir_id) for entry in cur_dir['entries']: entry['dir_id'] = dir_id dir_entries[entry['type']][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs)) if not dirs_missing: return db = self.db with db.transaction() as cur: dirs_missing_dict = ({'id': dir} for dir in dirs_missing) db.copy_to(dirs_missing_dict, 'directory', ['id'], cur) for entry_type, entry_list in dir_entries.items(): entries = itertools.chain.from_iterable( entries_for_dir for dir_id, entries_for_dir in entry_list.items() if dir_id in dirs_missing) db.mktemp_dir_entry(entry_type) db.copy_to( entries, 'tmp_directory_entry_%s' % entry_type, ['target', 'name', 'perms', 'atime', 'mtime', 'ctime', 'dir_id'], cur, ) cur.execute('SELECT swh_directory_entry_%s_add()' % entry_type) @db_transaction_generator def directory_missing(self, directories, cur): """List directories missing from storage Args: an iterable of directory ids Returns: a list of missing directory ids """ db = self.db # Create temporary table for metadata injection db.mktemp('directory', cur) directories_dicts = ({'id': dir} for dir in directories) db.copy_to(directories_dicts, 'tmp_directory', ['id'], cur) for obj in db.directory_missing_from_temp(cur): yield obj[0] def directory_get(self, directory): """Get the entries for one directory""" yield from self.db.directory_walk_one(directory) def revision_add(self, revisions): """Add revisions to the storage Args: revisions: iterable of dictionaries representing the individual revisions to add. Each dict has the following keys: - id (sha1_git): id of the revision to add - date (datetime.DateTime): date the revision was written - date_offset (int): offset from UTC in minutes the revision was written - committer_date (datetime.DateTime): date the revision got added to the origin - committer_date_offset (int): offset from UTC in minutes the revision was added to the origin - type (one of 'git', 'tar'): type of the revision added - directory (sha1_git): the directory the revision points at - message (bytes): the message associated with the revision - author_name (bytes): the name of the revision author - author_email (bytes): the email of the revision author - committer_name (bytes): the name of the revision committer - committer_email (bytes): the email of the revision committer - parents (list of sha1_git): the parents of this revision """ db = self.db parents = {} for revision in revisions: id = revision['id'] cur_parents = enumerate(revision.get('parents', [])) parents[id] = [{ 'id': id, 'parent_id': parent, 'parent_rank': i } for i, parent in cur_parents] revisions_missing = list(self.revision_missing(parents.keys())) if not revisions_missing: return with db.transaction() as cur: db.mktemp_revision(cur) revisions_filtered = (revision for revision in revisions if revision['id'] in revisions_missing) db.copy_to(revisions_filtered, 'tmp_revision', ['id', 'date', 'date_offset', 'committer_date', 'committer_date_offset', 'type', 'directory', 'message', 'author_name', 'author_email', 'committer_name', 'committer_email'], cur) db.revision_add_from_temp(cur) parents_filtered = itertools.chain.from_iterable( parents[id] for id in revisions_missing) db.copy_to(parents_filtered, 'revision_history', ['id', 'parent_id', 'parent_rank'], cur) @db_transaction_generator def revision_missing(self, revisions, cur): """List revisions missing from storage Args: an iterable of revision ids Returns: a list of missing revision ids """ db = self.db # Create temporary table for metadata injection db.mktemp('revision', cur) revisions_dicts = ({'id': dir, 'type': 'git'} for dir in revisions) db.copy_to(revisions_dicts, 'tmp_revision', ['id', 'type'], cur) for obj in db.revision_missing_from_temp(cur): yield obj[0] def release_add(self, releases): """Add releases to the storage Args: releases: iterable of dictionaries representing the individual releases to add. Each dict has the following keys: - id (sha1_git): id of the release to add - revision (sha1_git): id of the revision the release points to - date (datetime.DateTime): the date the release was made - date_offset (int): offset from UTC in minutes the release was made - name (bytes): the name of the release - comment (bytes): the comment associated with the release - author_name (bytes): the name of the release author - author_email (bytes): the email of the release author """ db = self.db release_ids = set(release['id'] for release in releases) releases_missing = list(self.release_missing(release_ids)) if not releases_missing: return with db.transaction() as cur: db.mktemp_release(cur) releases_filtered = (release for release in releases if release['id'] in releases_missing) db.copy_to(releases_filtered, 'tmp_release', ['id', 'revision', 'date', 'date_offset', 'name', 'comment', 'author_name', 'author_email'], cur) db.release_add_from_temp(cur) @db_transaction_generator def release_missing(self, releases, cur=None): """List releases missing from storage Args: an iterable of release ids Returns: a list of missing release ids """ db = self.db # Create temporary table for metadata injection db.mktemp('release', cur) releases_dicts = ({'id': rel} for rel in releases) db.copy_to(releases_dicts, 'tmp_release', ['id'], cur) for obj in db.release_missing_from_temp(cur): yield obj[0] @db_transaction def occurrence_add(self, occurrences, cur=None): """Add occurrences to the storage Args: occurrences: iterable of dictionaries representing the individual occurrences to add. Each dict has the following keys: - origin (int): id of the origin corresponding to the occurrence - branch (str): the reference name of the occurrence - revision (sha1_git): the id of the revision pointed to by the occurrence - authority (int): id of the authority giving the validity - validity (datetime.DateTime): the validity date for the given occurrence """ db = self.db processed = [] for occurrence in occurrences: occ = occurrence.copy() occ['validity'] = '[%s,infinity)' % str(occ['validity']) processed.append(occ) # XXX: will fail on second execution db.copy_to(processed, 'occurrence_history', ['origin', 'branch', 'revision', 'authority', 'validity'], cur) @db_transaction def origin_get(self, origin, cur=None): """Return the id of the given origin Args: origin: dictionary representing the individual origin to find. This dict has the following keys: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to Returns: the id of the queried origin """ query = "select id from origin where type=%s and url=%s" cur.execute(query, (origin['type'], origin['url'])) data = cur.fetchone() if not data: return None else: return data[0] @db_transaction def origin_add_one(self, origin, cur=None): """Add origin to the storage Args: origin: dictionary representing the individual origin to add. This dict has the following keys: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to Returns: - the id of the added origin + the id of the added origin, or of the identical one that already + exists. """ - query = "insert into origin (type, url) values (%s, %s) returning id" + query = "select id from origin where type=%s and url=%s" cur.execute(query, (origin['type'], origin['url'])) + data = cur.fetchone() + if data: + return data[0] + + insert = """insert into origin (type, url) values (%s, %s) + returning id""" + + cur.execute(insert, (origin['type'], origin['url'])) return cur.fetchone()[0] diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index b3d21f44..107a38e7 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,210 +1,236 @@ # Copyright (C) 2015 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import shutil import tempfile import unittest from nose.tools import istest from nose.plugins.attrib import attr from .db_testing import DbTestFixture from swh.core.hashutil import hex_to_hash from swh.storage import Storage @attr('db') class AbstractTestStorage(DbTestFixture): """Base class for Storage testing. This class is used as-is to test local storage (see TestStorage below) and remote storage (see TestRemoteStorage in test_remote_storage.py. We need to have the two classes inherit from this base class separately to avoid nosetests running the tests from the base class twice. """ def setUp(self): super().setUp() self.objroot = tempfile.mkdtemp() self.storage = Storage(self.conn, self.objroot) self.cont = { 'data': b'42\n', 'length': 3, 'sha1': hex_to_hash( '34973274ccef6ab4dfaaf86599792fa9c3fe4689'), 'sha1_git': hex_to_hash( 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), 'sha256': hex_to_hash( '673650f936cb3b0a2f93ce09d81be107' '48b1b203c19e8176b4eefc1964a0cf3a'), } self.cont2 = { 'data': b'4242\n', 'length': 5, 'sha1': hex_to_hash( '61c2b3a30496d329e21af70dd2d7e097046d07b7'), 'sha1_git': hex_to_hash( '36fade77193cb6d2bd826161a0979d64c28ab4fa'), 'sha256': hex_to_hash( '859f0b154fdb2d630f45e1ecae4a8629' '15435e663248bb8461d914696fc047cd'), } self.missing_cont = { 'data': b'missing\n', 'length': 8, 'sha1': hex_to_hash( 'f9c24e2abb82063a3ba2c44efd2d3c797f28ac90'), 'sha1_git': hex_to_hash( '33e45d56f88993aae6a0198013efa80716fd8919'), 'sha256': hex_to_hash( '6bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), } self.dir = { 'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa90', 'entries': [ { 'name': 'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': 0o644, 'atime': None, 'ctime': None, 'mtime': None, }, { 'name': 'bar', 'type': 'dir', 'target': b'12345678901234567890', 'perms': 0o2000, 'atime': None, 'ctime': None, 'mtime': None, }, ], } self.revision = { 'id': b'56789012345678901234', 'message': 'hello', 'author_name': 'Nicolas Dandrimont', 'author_email': 'nicolas@example.com', 'committer_name': 'Stefano Zacchiroli', 'committer_email': 'stefano@example.com', 'parents': [b'01234567890123456789'], 'date': datetime.datetime(2015, 1, 1, 22, 0, 0), 'date_offset': 120, 'committer_date': datetime.datetime(2015, 1, 2, 22, 0, 0), 'committer_date_offset': -120, 'type': 'git', 'directory': self.dir['id'], } self.origin = { 'url': 'file:///dev/null', 'type': 'git', } self.origin2 = { 'url': 'file:///dev/zero', 'type': 'git', } self.occurrence = { 'branch': 'master', 'revision': b'67890123456789012345', 'authority': 1, 'validity': datetime.datetime(2015, 1, 1, 23, 0, 0), } def tearDown(self): shutil.rmtree(self.objroot) super().tearDown() @istest def content_add(self): cont = self.cont self.storage.content_add([cont]) if hasattr(self.storage, 'objstorage'): self.assertIn(cont['sha1'], self.storage.objstorage) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = self.cursor.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) @istest def content_missing(self): cont2 = self.cont2 missing_cont = self.missing_cont self.storage.content_add([cont2]) gen = self.storage.content_missing([cont2, missing_cont]) self.assertEqual(list(gen), [missing_cont['sha1']]) + @istest + def content_present(self): + ### with something to find + cont = self.cont + self.storage.content_add([cont]) + + actually_present = self.storage.content_present({'sha1': cont['sha1']}) + + self.assertEquals(actually_present, True, "Should be present") + + ### with something that does not exist + missing_cont = self.missing_cont + + actually_present = self.storage.content_present( + {'sha256': missing_cont['sha256']}) + + self.assertEquals(actually_present, False, "Should be missing") + + ### 1. with bad input + with self.assertRaises(ValueError): + self.storage.content_present({}) + + ### 2. with bad input + with self.assertRaises(ValueError): + self.storage.content_present({'sha-bla': '123'}) # only sha1 and sha256 + @istest def directory_add(self): init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) self.storage.directory_add([self.dir]) stored_data = list(self.storage.directory_get(self.dir['id'])) data_to_store = [ (self.dir['id'], ent['type'], ent['target'], ent['name'], ent['perms'], ent['atime'], ent['ctime'], ent['mtime']) for ent in sorted(self.dir['entries'], key=lambda ent: ent['name']) ] self.assertEqual(data_to_store, stored_data) after_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([], after_missing) @istest def revision_add(self): init_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([self.revision['id']], list(init_missing)) self.storage.revision_add([self.revision]) end_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([], list(end_missing)) @istest def origin_add(self): self.assertIsNone(self.storage.origin_get(self.origin)) id = self.storage.origin_add_one(self.origin) self.assertEqual(self.storage.origin_get(self.origin), id) @istest def occurrence_add(self): origin_id = self.storage.origin_add_one(self.origin2) revision = self.revision.copy() revision['id'] = self.occurrence['revision'] self.storage.revision_add([revision]) self.occurrence['origin'] = origin_id self.storage.occurrence_add([self.occurrence]) class TestStorage(AbstractTestStorage, unittest.TestCase): """Test the local storage""" pass diff --git a/version.txt b/version.txt index a6b360b5..4ac54c33 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -v0.0.3-0-gd88a775 \ No newline at end of file +v0.0.4-0-g372ee30 \ No newline at end of file