diff --git a/.gitignore b/.gitignore index a1f7d837f..dda3e7a86 100644 --- a/.gitignore +++ b/.gitignore @@ -1,11 +1,12 @@ *.pyc *.sw? *~ .coverage .eggs/ __pycache__ build/ dist/ *.egg-info version.txt .vscode/ +.hypothesis/ diff --git a/MANIFEST.in b/MANIFEST.in index 2a92ebecc..808326604 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,8 +1,8 @@ include Makefile include Makefile.local -include README.db_testing -include README.dev +include README.md include requirements.txt include requirements-swh.txt include version.txt recursive-include sql * +recursive-include swh/storage/sql * diff --git a/PKG-INFO b/PKG-INFO index 390d8a2b3..1926a6943 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,156 +1,153 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.0.107 +Version: 0.0.108 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 Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-storage Description: swh-storage =========== Abstraction layer over the archive, allowing to access all stored source code artifacts as well as their metadata. See the [documentation](https://docs.softwareheritage.org/devel/swh-storage/index.html) for more details. Tests ----- Python tests for this module include tests that cannot be run without a local Postgres database. You are not obliged to run those tests though: - `make test`: will run all tests - `make test-nodb`: will run only tests that do not need a local DB - `make test-db`: will run only tests that do need a local DB If you do want to run DB-related tests, you should ensure you have access zith sufficient privileges to a Postgresql database. ### Using your system database - You need to: + You need to ensure that your user is authorized to create and drop DBs, and in + particular DBs named "softwareheritage-test" and "softwareheritage-dev" - - ensure that your user is authorized to create and drop DBs, and in particular - DBs named "softwareheritage-test" and "softwareheritage-dev" - - - ensure that you have the storage testdata repository checked out in - ../swh-storage-testdata + Note: the testdata repository (swh-storage-testdata) is not required any more. ### Using pifpaf [pifpaf](https://github.com/jd/pifpaf) is a suite of fixtures and a command-line tool that allows to start and stop daemons for a quick throw-away usage. It can be used to run tests that need a Postgres database without any other configuration reauired nor the need to have special access to a running database: ```bash $ pifpaf run postgresql make test-db [snip] ---------------------------------------------------------------------- Ran 124 tests in 56.203s OK ``` Note that pifpaf is not yet available as a Debian package, so you may have to install it in a venv. Development ----------- A test server could locally be running for tests. ### Sample configuration In either /etc/softwareheritage/storage/storage.yml, ~/.config/swh/storage.yml or ~/.swh/storage.yml: ``` storage: cls: local args: db: "dbname=softwareheritage-dev user=" objstorage: cls: pathslicing args: root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` which means, this uses: - a local storage instance whose db connection is to softwareheritage-dev local instance - the objstorage uses a local objstorage instance whose: - root path is /home/storage/swh-storage - slicing scheme is 0:2/2:4/4:6. This means that the identifier of the content (sha1) which will be stored on disk at first level with the first 2 hex characters, the second level with the next 2 hex characters and the third level with the next 2 hex characters. And finally the complete hash file holding the raw content. For example: 00062f8bd330715c4f819373653d97b3cd34394c will be stored at 00/06/2f/00062f8bd330715c4f819373653d97b3cd34394c Note that the 'root' path should exist on disk. ### Run server Command: ``` python3 -m swh.storage.api.server ~/.config/swh/storage.yml ``` This runs a local swh-storage api at 5002 port. ### And then what? In your upper layer (loader-git, loader-svn, etc...), you can define a remote storage with this snippet of yaml configuration. ``` storage: cls: remote args: url: http://localhost:5002/ ``` You could directly define a local storage with the following snippet: ``` storage: cls: local args: db: service=swh-dev objstorage: cls: pathslicing args: root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Description-Content-Type: text/markdown Provides-Extra: listener Provides-Extra: schemata Provides-Extra: testing diff --git a/README.md b/README.md index 53f5a62bd..0dbe6ac44 100644 --- a/README.md +++ b/README.md @@ -1,134 +1,131 @@ swh-storage =========== Abstraction layer over the archive, allowing to access all stored source code artifacts as well as their metadata. See the [documentation](https://docs.softwareheritage.org/devel/swh-storage/index.html) for more details. Tests ----- Python tests for this module include tests that cannot be run without a local Postgres database. You are not obliged to run those tests though: - `make test`: will run all tests - `make test-nodb`: will run only tests that do not need a local DB - `make test-db`: will run only tests that do need a local DB If you do want to run DB-related tests, you should ensure you have access zith sufficient privileges to a Postgresql database. ### Using your system database -You need to: +You need to ensure that your user is authorized to create and drop DBs, and in +particular DBs named "softwareheritage-test" and "softwareheritage-dev" -- ensure that your user is authorized to create and drop DBs, and in particular - DBs named "softwareheritage-test" and "softwareheritage-dev" - -- ensure that you have the storage testdata repository checked out in - ../swh-storage-testdata +Note: the testdata repository (swh-storage-testdata) is not required any more. ### Using pifpaf [pifpaf](https://github.com/jd/pifpaf) is a suite of fixtures and a command-line tool that allows to start and stop daemons for a quick throw-away usage. It can be used to run tests that need a Postgres database without any other configuration reauired nor the need to have special access to a running database: ```bash $ pifpaf run postgresql make test-db [snip] ---------------------------------------------------------------------- Ran 124 tests in 56.203s OK ``` Note that pifpaf is not yet available as a Debian package, so you may have to install it in a venv. Development ----------- A test server could locally be running for tests. ### Sample configuration In either /etc/softwareheritage/storage/storage.yml, ~/.config/swh/storage.yml or ~/.swh/storage.yml: ``` storage: cls: local args: db: "dbname=softwareheritage-dev user=" objstorage: cls: pathslicing args: root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` which means, this uses: - a local storage instance whose db connection is to softwareheritage-dev local instance - the objstorage uses a local objstorage instance whose: - root path is /home/storage/swh-storage - slicing scheme is 0:2/2:4/4:6. This means that the identifier of the content (sha1) which will be stored on disk at first level with the first 2 hex characters, the second level with the next 2 hex characters and the third level with the next 2 hex characters. And finally the complete hash file holding the raw content. For example: 00062f8bd330715c4f819373653d97b3cd34394c will be stored at 00/06/2f/00062f8bd330715c4f819373653d97b3cd34394c Note that the 'root' path should exist on disk. ### Run server Command: ``` python3 -m swh.storage.api.server ~/.config/swh/storage.yml ``` This runs a local swh-storage api at 5002 port. ### And then what? In your upper layer (loader-git, loader-svn, etc...), you can define a remote storage with this snippet of yaml configuration. ``` storage: cls: remote args: url: http://localhost:5002/ ``` You could directly define a local storage with the following snippet: ``` storage: cls: local args: db: service=swh-dev objstorage: cls: pathslicing args: root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` diff --git a/requirements-swh.txt b/requirements-swh.txt index b4673f274..3e809cceb 100644 --- a/requirements-swh.txt +++ b/requirements-swh.txt @@ -1,4 +1,4 @@ -swh.core >= 0.0.40 +swh.core >= 0.0.44 swh.model >= 0.0.27 swh.objstorage >= 0.0.17 swh.scheduler >= 0.0.14 diff --git a/requirements-test.txt b/requirements-test.txt index f3c7e8e6f..4af3b14a4 100644 --- a/requirements-test.txt +++ b/requirements-test.txt @@ -1 +1,2 @@ +hypothesis >= 3.11.0 nose diff --git a/sql/Makefile b/sql/Makefile index 5d52a958e..c7caa91da 100644 --- a/sql/Makefile +++ b/sql/Makefile @@ -1,61 +1,78 @@ # Depends: postgresql-client, postgresql-autodoc DBNAME = softwareheritage-dev DOCDIR = autodoc -SQL_INIT = swh-init.sql -SQL_ENUMS = swh-enums.sql -SQL_SCHEMA = swh-schema.sql -SQL_FUNC = swh-func.sql -SQL_INDEX = swh-indexes.sql -SQL_TRIGGER = swh-triggers.sql +SQL_INIT = 10-swh-init.sql +SQL_ENUMS = 20-swh-enums.sql +SQL_SCHEMA = 30-swh-schema.sql +SQL_FUNC = 40-swh-func.sql +SQL_INDEX = 60-swh-indexes.sql +SQL_TRIGGER = 70-swh-triggers.sql SQLS = $(SQL_INIT) $(SQL_ENUMS) $(SQL_SCHEMA) $(SQL_FUNC) $(SQL_INDEX) $(SQL_TRIGGER) +SQL_FILES = $(abspath $(addprefix $(CURDIR)/../swh/storage/sql/,$(SQLS))) PSQL_BIN = psql PSQL_FLAGS = --echo-all -X -v ON_ERROR_STOP=1 PSQL = $(PSQL_BIN) $(PSQL_FLAGS) +PIFPAF=$(findstring postgresql://,$(PIFPAF_URLS)) + all: createdb: createdb-stamp -createdb-stamp: $(SQL_INIT) +createdb-stamp: $(SQL_FILES) +ifndef PIFPAF -dropdb $(DBNAME) +endif createdb $(DBNAME) +ifndef PIFPAF touch $@ +else + rm -f $@ +endif filldb: filldb-stamp filldb-stamp: createdb-stamp - cat $(SQLS) | $(PSQL) $(DBNAME) + cat $(SQL_FILES) | $(PSQL) $(DBNAME) +ifndef PIFPAF touch $@ +else + rm -f $@ +endif dropdb: -dropdb $(DBNAME) dumpdb: swh.dump swh.dump: filldb-stamp pg_dump -Fc $(DBNAME) > $@ $(DOCDIR): test -d $(DOCDIR)/ || mkdir $(DOCDIR) doc: autodoc-stamp $(DOCDIR)/db-schema.pdf $(DOCDIR)/db-schema.svg autodoc-stamp: filldb-stamp $(DOCDIR) postgresql_autodoc -d $(DBNAME) -f $(DOCDIR)/db-schema cp -a $(DOCDIR)/db-schema.dot $(DOCDIR)/db-schema.dot.orig +ifndef PIFPAF touch $@ +else + rm -f $@ +endif $(DOCDIR)/db-schema.dot: clusters.dot autodoc-stamp $(DOCDIR) bin/dot_add_content $(DOCDIR)/db-schema.dot.orig clusters.dot > $(DOCDIR)/db-schema.dot $(DOCDIR)/db-schema.pdf: $(DOCDIR)/db-schema.dot autodoc-stamp dot -T pdf $< > $@ $(DOCDIR)/db-schema.svg: $(DOCDIR)/db-schema.dot autodoc-stamp dot -T svg $< > $@ clean: rm -rf *-stamp $(DOCDIR)/ distclean: clean dropdb rm -f swh.dump .PHONY: all initdb createdb dropdb doc clean diff --git a/sql/bin/db-init b/sql/bin/db-init deleted file mode 100755 index 7802eff61..000000000 --- a/sql/bin/db-init +++ /dev/null @@ -1,52 +0,0 @@ -#!/bin/bash -set -e - -# Must be run as (a) Postgres super user - -SQL_INIT=swh-init.sql -SQL_ENUMS=swh-enums.sql -SQL_SCHEMA=swh-schema.sql -SQL_FUNC=swh-func.sql -SQL_INDEX=swh-indexes.sql -SQL_TRIGGER=swh-triggers.sql -SQL_DATA=swh-data.sql -ROOT_SQLS="$SQL_INIT" -USER_SQLS="$SQL_ENUMS $SQL_SCHEMA $SQL_FUNC $SQL_INDEX $SQL_TRIGGER $SQL_DATA" -SQLS="$ROOT_SQLS $USER_SQLS" - -DB_ENCODING="UTF-8" -DB_LOCALE="C.UTF-8" -DB_TEMPLATE="template0" - -cd "$( dirname $0 )/.." - -if ! [ -f "$SQL_INIT" ] ; then - echo "Cannot find $SQL_INIT. Abort." - exit 2 -fi - -if [ -z "$1" ] ; then - echo "Usage: bin/db-init DB_NAME [DB_PORT]" - echo "Example: bin/db-init softwareheritage-dev" - echo "Note: DB_NAME should not exist and will be created" - exit 2 -fi -db_name="$1" -port=${2:-5432} - -conn_flags="--port $port" - -echo "I: creating Postgres database ${db_name} ..." -createdb $conn_flags \ - --encoding "$DB_ENCODING" --locale "$DB_LOCALE" \ - --template "$DB_TEMPLATE" "$db_name" - -sqls_flags='' -for f in $SQLS ; do - sqls_flags="${sqls_flags} --file ${f}" -done - -echo "I: initializing DB ${db_name} ..." -psql $conn_flags ${sqls_flags} "$db_name" - -echo "I: all done." diff --git a/swh.storage.egg-info/PKG-INFO b/swh.storage.egg-info/PKG-INFO index 390d8a2b3..1926a6943 100644 --- a/swh.storage.egg-info/PKG-INFO +++ b/swh.storage.egg-info/PKG-INFO @@ -1,156 +1,153 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.0.107 +Version: 0.0.108 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 Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-storage Description: swh-storage =========== Abstraction layer over the archive, allowing to access all stored source code artifacts as well as their metadata. See the [documentation](https://docs.softwareheritage.org/devel/swh-storage/index.html) for more details. Tests ----- Python tests for this module include tests that cannot be run without a local Postgres database. You are not obliged to run those tests though: - `make test`: will run all tests - `make test-nodb`: will run only tests that do not need a local DB - `make test-db`: will run only tests that do need a local DB If you do want to run DB-related tests, you should ensure you have access zith sufficient privileges to a Postgresql database. ### Using your system database - You need to: + You need to ensure that your user is authorized to create and drop DBs, and in + particular DBs named "softwareheritage-test" and "softwareheritage-dev" - - ensure that your user is authorized to create and drop DBs, and in particular - DBs named "softwareheritage-test" and "softwareheritage-dev" - - - ensure that you have the storage testdata repository checked out in - ../swh-storage-testdata + Note: the testdata repository (swh-storage-testdata) is not required any more. ### Using pifpaf [pifpaf](https://github.com/jd/pifpaf) is a suite of fixtures and a command-line tool that allows to start and stop daemons for a quick throw-away usage. It can be used to run tests that need a Postgres database without any other configuration reauired nor the need to have special access to a running database: ```bash $ pifpaf run postgresql make test-db [snip] ---------------------------------------------------------------------- Ran 124 tests in 56.203s OK ``` Note that pifpaf is not yet available as a Debian package, so you may have to install it in a venv. Development ----------- A test server could locally be running for tests. ### Sample configuration In either /etc/softwareheritage/storage/storage.yml, ~/.config/swh/storage.yml or ~/.swh/storage.yml: ``` storage: cls: local args: db: "dbname=softwareheritage-dev user=" objstorage: cls: pathslicing args: root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` which means, this uses: - a local storage instance whose db connection is to softwareheritage-dev local instance - the objstorage uses a local objstorage instance whose: - root path is /home/storage/swh-storage - slicing scheme is 0:2/2:4/4:6. This means that the identifier of the content (sha1) which will be stored on disk at first level with the first 2 hex characters, the second level with the next 2 hex characters and the third level with the next 2 hex characters. And finally the complete hash file holding the raw content. For example: 00062f8bd330715c4f819373653d97b3cd34394c will be stored at 00/06/2f/00062f8bd330715c4f819373653d97b3cd34394c Note that the 'root' path should exist on disk. ### Run server Command: ``` python3 -m swh.storage.api.server ~/.config/swh/storage.yml ``` This runs a local swh-storage api at 5002 port. ### And then what? In your upper layer (loader-git, loader-svn, etc...), you can define a remote storage with this snippet of yaml configuration. ``` storage: cls: remote args: url: http://localhost:5002/ ``` You could directly define a local storage with the following snippet: ``` storage: cls: local args: db: service=swh-dev objstorage: cls: pathslicing args: root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Description-Content-Type: text/markdown Provides-Extra: listener Provides-Extra: schemata Provides-Extra: testing diff --git a/swh.storage.egg-info/SOURCES.txt b/swh.storage.egg-info/SOURCES.txt index e00eb9914..0b23e3c35 100644 --- a/swh.storage.egg-info/SOURCES.txt +++ b/swh.storage.egg-info/SOURCES.txt @@ -1,214 +1,215 @@ .gitignore AUTHORS LICENSE MANIFEST.in Makefile Makefile.local README.md requirements-swh.txt requirements-test.txt requirements.txt setup.py version.txt bin/swh-storage-add-dir debian/changelog debian/compat debian/control debian/copyright debian/rules debian/source/format docs/.gitignore docs/Makefile docs/Makefile.local docs/archive-copies.rst docs/conf.py docs/index.rst docs/sql-storage.rst docs/_static/.placeholder docs/_templates/.placeholder docs/images/.gitignore docs/images/Makefile docs/images/swh-archive-copies.dia docs/images/swh-archive-copies.pdf docs/images/swh-archive-copies.svg sql/.gitignore sql/Makefile sql/TODO sql/clusters.dot -sql/swh-enums.sql -sql/swh-func.sql -sql/swh-indexes.sql -sql/swh-init.sql -sql/swh-schema.sql -sql/swh-triggers.sql -sql/bin/db-init sql/bin/db-upgrade sql/bin/dot_add_content sql/doc/json sql/doc/json/.gitignore sql/doc/json/Makefile sql/doc/json/entity.lister_metadata.schema.json sql/doc/json/entity.metadata.schema.json sql/doc/json/entity_history.lister_metadata.schema.json sql/doc/json/entity_history.metadata.schema.json sql/doc/json/fetch_history.result.schema.json sql/doc/json/list_history.result.schema.json sql/doc/json/listable_entity.list_params.schema.json sql/doc/json/origin_visit.metadata.json sql/doc/json/tool.tool_configuration.schema.json sql/json/.gitignore sql/json/Makefile sql/json/entity.lister_metadata.schema.json sql/json/entity.metadata.schema.json sql/json/entity_history.lister_metadata.schema.json sql/json/entity_history.metadata.schema.json sql/json/fetch_history.result.schema.json sql/json/list_history.result.schema.json sql/json/listable_entity.list_params.schema.json sql/json/origin_visit.metadata.json sql/json/tool.tool_configuration.schema.json 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 sql/upgrades/033.sql sql/upgrades/034.sql sql/upgrades/035.sql sql/upgrades/036.sql sql/upgrades/037.sql sql/upgrades/038.sql sql/upgrades/039.sql sql/upgrades/040.sql sql/upgrades/041.sql sql/upgrades/042.sql sql/upgrades/043.sql sql/upgrades/044.sql sql/upgrades/045.sql sql/upgrades/046.sql sql/upgrades/047.sql sql/upgrades/048.sql sql/upgrades/049.sql sql/upgrades/050.sql sql/upgrades/051.sql sql/upgrades/052.sql sql/upgrades/053.sql sql/upgrades/054.sql sql/upgrades/055.sql sql/upgrades/056.sql sql/upgrades/057.sql sql/upgrades/058.sql sql/upgrades/059.sql sql/upgrades/060.sql sql/upgrades/061.sql sql/upgrades/062.sql sql/upgrades/063.sql sql/upgrades/064.sql sql/upgrades/065.sql sql/upgrades/066.sql sql/upgrades/067.sql sql/upgrades/068.sql sql/upgrades/069.sql sql/upgrades/070.sql sql/upgrades/071.sql sql/upgrades/072.sql sql/upgrades/073.sql sql/upgrades/074.sql sql/upgrades/075.sql sql/upgrades/076.sql sql/upgrades/077.sql sql/upgrades/078.sql sql/upgrades/079.sql sql/upgrades/080.sql sql/upgrades/081.sql sql/upgrades/082.sql sql/upgrades/083.sql sql/upgrades/084.sql sql/upgrades/085.sql sql/upgrades/086.sql sql/upgrades/087.sql sql/upgrades/088.sql sql/upgrades/089.sql sql/upgrades/090.sql sql/upgrades/091.sql sql/upgrades/092.sql sql/upgrades/093.sql sql/upgrades/094.sql sql/upgrades/095.sql sql/upgrades/096.sql sql/upgrades/097.sql sql/upgrades/098.sql sql/upgrades/099.sql sql/upgrades/100.sql sql/upgrades/101.sql sql/upgrades/102.sql sql/upgrades/103.sql sql/upgrades/104.sql sql/upgrades/105.sql sql/upgrades/106.sql sql/upgrades/107.sql sql/upgrades/108.sql sql/upgrades/109.sql sql/upgrades/110.sql sql/upgrades/111.sql sql/upgrades/112.sql sql/upgrades/113.sql sql/upgrades/114.sql sql/upgrades/115.sql sql/upgrades/116.sql sql/upgrades/117.sql sql/upgrades/118.sql sql/upgrades/119.sql sql/upgrades/120.sql sql/upgrades/121.sql sql/upgrades/122.sql sql/upgrades/123.sql sql/upgrades/124.sql sql/upgrades/125.sql sql/upgrades/126.sql sql/upgrades/127.sql swh/__init__.py 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/common.py swh/storage/converters.py swh/storage/db.py swh/storage/db_utils.py swh/storage/exc.py swh/storage/listener.py swh/storage/storage.py swh/storage/algos/__init__.py swh/storage/algos/diff.py swh/storage/algos/dir_iterators.py +swh/storage/algos/snapshot.py swh/storage/api/__init__.py swh/storage/api/client.py swh/storage/api/server.py swh/storage/schemata/__init__.py swh/storage/schemata/distribution.py +swh/storage/sql/10-swh-init.sql +swh/storage/sql/20-swh-enums.sql +swh/storage/sql/30-swh-schema.sql +swh/storage/sql/40-swh-func.sql +swh/storage/sql/60-swh-indexes.sql +swh/storage/sql/70-swh-triggers.sql swh/storage/tests/__init__.py swh/storage/tests/storage_testing.py swh/storage/tests/test_api_client.py swh/storage/tests/test_converters.py swh/storage/tests/test_db.py swh/storage/tests/test_storage.py swh/storage/tests/algos/__init__.py swh/storage/tests/algos/test_diff.py swh/storage/tests/algos/test_dir_iterator.py +swh/storage/tests/algos/test_snapshot.py utils/dump_revisions.py utils/fix_revisions_from_dump.py \ No newline at end of file diff --git a/swh.storage.egg-info/requires.txt b/swh.storage.egg-info/requires.txt index b3c903a36..18155fc81 100644 --- a/swh.storage.egg-info/requires.txt +++ b/swh.storage.egg-info/requires.txt @@ -1,19 +1,20 @@ aiohttp click flask psycopg2 python-dateutil -swh.core>=0.0.40 +swh.core>=0.0.44 swh.model>=0.0.27 swh.objstorage>=0.0.17 swh.scheduler>=0.0.14 vcversioner [listener] kafka_python [schemata] SQLAlchemy [testing] +hypothesis>=3.11.0 nose diff --git a/swh/storage/algos/snapshot.py b/swh/storage/algos/snapshot.py new file mode 100644 index 000000000..76eca6183 --- /dev/null +++ b/swh/storage/algos/snapshot.py @@ -0,0 +1,31 @@ +# Copyright (C) 2018 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 + + +def snapshot_get_all_branches(storage, snapshot_id): + """Get all the branches for a given snapshot + + Args: + storage (swh.storage.storage.Storage): the storage instance + snapshot_id (bytes): the snapshot's identifier + Returns: + dict: a dict with two keys: + * **id**: identifier of the snapshot + * **branches**: a dict of branches contained in the snapshot + whose keys are the branches' names. + """ + ret = storage.snapshot_get(snapshot_id) + + if not ret: + return + + next_branch = ret.pop('next_branch', None) + while next_branch: + data = storage.snapshot_get_branches(snapshot_id, + branches_from=next_branch) + ret['branches'].update(data['branches']) + next_branch = data.get('next_branch') + + return ret diff --git a/swh/storage/api/client.py b/swh/storage/api/client.py index 2460ff54f..038a3a66f 100644 --- a/swh/storage/api/client.py +++ b/swh/storage/api/client.py @@ -1,233 +1,233 @@ # Copyright (C) 2015-2017 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 swh.core.api import SWHRemoteAPI from ..exc import StorageAPIError class RemoteStorage(SWHRemoteAPI): """Proxy to a remote storage API""" def __init__(self, url, timeout=None): super().__init__( api_exception=StorageAPIError, url=url, timeout=timeout) def check_config(self, *, check_write): return self.post('check_config', {'check_write': check_write}) def content_add(self, content): return self.post('content/add', {'content': content}) def content_update(self, content, keys=[]): return self.post('content/update', {'content': content, 'keys': keys}) def content_missing(self, content, key_hash='sha1'): return self.post('content/missing', {'content': content, 'key_hash': key_hash}) def content_missing_per_sha1(self, contents): return self.post('content/missing/sha1', {'contents': contents}) def content_get(self, content): return self.post('content/data', {'content': content}) def content_get_metadata(self, content): return self.post('content/metadata', {'content': content}) def content_find(self, content): return self.post('content/present', {'content': content}) def directory_add(self, directories): return self.post('directory/add', {'directories': directories}) def directory_missing(self, directories): return self.post('directory/missing', {'directories': directories}) def directory_ls(self, directory, recursive=False): return self.get('directory/ls', {'directory': directory, 'recursive': recursive}) def revision_get(self, revisions): return self.post('revision', {'revisions': revisions}) def revision_log(self, revisions, limit=None): return self.post('revision/log', {'revisions': revisions, 'limit': limit}) def revision_shortlog(self, revisions, limit=None): return self.post('revision/shortlog', {'revisions': revisions, 'limit': limit}) 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 object_find_by_sha1_git(self, ids): return self.post('object/find_by_sha1_git', {'ids': ids}) def snapshot_add(self, origin, visit, snapshot): return self.post('snapshot/add', { 'origin': origin, 'visit': visit, 'snapshot': snapshot, }) def snapshot_get(self, snapshot_id): return self.post('snapshot', { 'snapshot_id': snapshot_id }) def snapshot_get_by_origin_visit(self, origin, visit): return self.post('snapshot/by_origin_visit', { 'origin': origin, 'visit': visit }) def snapshot_get_latest(self, origin, allowed_statuses=None): return self.post('snapshot/latest', { 'origin': origin, 'allowed_statuses': allowed_statuses }) def snapshot_count_branches(self, snapshot_id): return self.post('snapshot/count_branches', { 'snapshot_id': snapshot_id }) def snapshot_get_branches(self, snapshot_id, branches_from=b'', - branches_count=None, target_types=None): + branches_count=1000, target_types=None): return self.post('snapshot/get_branches', { 'snapshot_id': snapshot_id, 'branches_from': branches_from, 'branches_count': branches_count, 'target_types': target_types }) def origin_get(self, origin): return self.post('origin/get', {'origin': origin}) def origin_search(self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False): return self.post('origin/search', {'url_pattern': url_pattern, 'offset': offset, 'limit': limit, 'regexp': regexp, 'with_visit': with_visit}) def origin_add(self, origins): return self.post('origin/add_multi', {'origins': origins}) def origin_add_one(self, origin): return self.post('origin/add', {'origin': origin}) def origin_visit_add(self, origin, ts): return self.post('origin/visit/add', {'origin': origin, 'ts': ts}) def origin_visit_update(self, origin, visit_id, status, metadata=None): return self.post('origin/visit/update', {'origin': origin, 'visit_id': visit_id, 'status': status, 'metadata': metadata}) def origin_visit_get(self, origin, last_visit=None, limit=None): return self.post('origin/visit/get', { 'origin': origin, 'last_visit': last_visit, 'limit': limit}) def origin_visit_get_by(self, origin, visit): return self.post('origin/visit/getby', {'origin': origin, 'visit': visit}) 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(self, uuid): return self.post('entity/get', {'uuid': uuid}) def entity_get_one(self, uuid): return self.get('entity', {'uuid': uuid}) 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') def directory_entry_get_by_path(self, directory, paths): return self.post('directory/path', dict(directory=directory, paths=paths)) def tool_add(self, tools): return self.post('tool/add', {'tools': tools}) def tool_get(self, tool): return self.post('tool/data', {'tool': tool}) def origin_metadata_add(self, origin_id, ts, provider, tool, metadata): return self.post('origin/metadata/add', {'origin_id': origin_id, 'ts': ts, 'provider': provider, 'tool': tool, 'metadata': metadata}) def origin_metadata_get_by(self, origin_id, provider_type=None): return self.post('origin/metadata/get', { 'origin_id': origin_id, 'provider_type': provider_type }) def metadata_provider_add(self, provider_name, provider_type, provider_url, metadata): return self.post('provider/add', {'provider_name': provider_name, 'provider_type': provider_type, 'provider_url': provider_url, 'metadata': metadata}) def metadata_provider_get(self, provider_id): return self.post('provider/get', {'provider_id': provider_id}) def metadata_provider_get_by(self, provider): return self.post('provider/getby', {'provider': provider}) def diff_directories(self, from_dir, to_dir, track_renaming=False): return self.post('algos/diff_directories', {'from_dir': from_dir, 'to_dir': to_dir, 'track_renaming': track_renaming}) def diff_revisions(self, from_rev, to_rev, track_renaming=False): return self.post('algos/diff_revisions', {'from_rev': from_rev, 'to_rev': to_rev, 'track_renaming': track_renaming}) def diff_revision(self, revision, track_renaming=False): return self.post('algos/diff_revision', {'revision': revision, 'track_renaming': track_renaming}) diff --git a/sql/swh-init.sql b/swh/storage/sql/10-swh-init.sql similarity index 100% rename from sql/swh-init.sql rename to swh/storage/sql/10-swh-init.sql diff --git a/sql/swh-enums.sql b/swh/storage/sql/20-swh-enums.sql similarity index 100% rename from sql/swh-enums.sql rename to swh/storage/sql/20-swh-enums.sql diff --git a/sql/swh-schema.sql b/swh/storage/sql/30-swh-schema.sql similarity index 100% rename from sql/swh-schema.sql rename to swh/storage/sql/30-swh-schema.sql diff --git a/sql/swh-func.sql b/swh/storage/sql/40-swh-func.sql similarity index 100% rename from sql/swh-func.sql rename to swh/storage/sql/40-swh-func.sql diff --git a/sql/swh-indexes.sql b/swh/storage/sql/60-swh-indexes.sql similarity index 100% rename from sql/swh-indexes.sql rename to swh/storage/sql/60-swh-indexes.sql diff --git a/sql/swh-triggers.sql b/swh/storage/sql/70-swh-triggers.sql similarity index 100% rename from sql/swh-triggers.sql rename to swh/storage/sql/70-swh-triggers.sql diff --git a/swh/storage/storage.py b/swh/storage/storage.py index 7726895cc..6d7942f44 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,1373 +1,1357 @@ # Copyright (C) 2015-2018 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 from concurrent.futures import ThreadPoolExecutor import datetime import itertools import json import dateutil.parser import psycopg2 import psycopg2.pool from . import converters from .common import db_transaction_generator, db_transaction from .db import Db from .exc import StorageDBError from .algos import diff -from swh.model.hashutil import ALGORITHMS +from swh.model.hashutil import ALGORITHMS, hash_to_bytes from swh.objstorage import get_objstorage from swh.objstorage.exc import ObjNotFoundError # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 +EMPTY_SNAPSHOT_ID = hash_to_bytes('1a8893e6a86f444e8be8e7bda6cb34fb1735a00e') +"""Identifier for the empty snapshot""" + class Storage(): """SWH storage proxy, encompassing DB and object storage """ def __init__(self, db, objstorage, min_pool_conns=1, max_pool_conns=10): """ Args: db_conn: either a libpq connection string, or a psycopg2 connection obj_root: path to the root of the object storage """ try: if isinstance(db, psycopg2.extensions.connection): self._pool = None self._db = Db(db) else: self._pool = psycopg2.pool.ThreadedConnectionPool( min_pool_conns, max_pool_conns, db ) self._db = None except psycopg2.OperationalError as e: raise StorageDBError(e) self.objstorage = get_objstorage(**objstorage) def get_db(self): if self._db: return self._db else: return Db.from_pool(self._pool) def check_config(self, *, check_write): """Check that the storage is configured and ready to go.""" if not self.objstorage.check_config(check_write=check_write): return False # Check permissions on one of the tables with self.get_db().transaction() as cur: if check_write: check = 'INSERT' else: check = 'SELECT' cur.execute( "select has_table_privilege(current_user, 'content', %s)", (check,) ) return cur.fetchone()[0] return True 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): 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 :data:`swh.model.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.get_db() def _unique_key(hash, keys=db.content_hash_keys): """Given a hash (tuple or dict), return a unique key from the aggregation of keys. """ if isinstance(hash, tuple): return hash return tuple([hash[k] for k in keys]) 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(_unique_key(hashes) for hashes in self.skipped_content_missing( content_without_data)) def add_to_objstorage(): data = { cont['sha1']: cont['data'] for cont in content_with_data if cont['sha1'] in missing_content } self.objstorage.add_batch(data) with db.transaction() as cur: with ThreadPoolExecutor(max_workers=1) as executor: added_to_objstorage = executor.submit(add_to_objstorage) if missing_content: # create temporary table for metadata injection db.mktemp('content', cur) content_filtered = (cont for cont in content_with_data if cont['sha1'] in missing_content) db.copy_to(content_filtered, 'tmp_content', db.content_get_metadata_keys, cur) # move metadata in place db.content_add_from_temp(cur) if missing_skipped: missing_filtered = ( cont for cont in content_without_data if _unique_key(cont) in missing_skipped ) db.mktemp('skipped_content', cur) db.copy_to(missing_filtered, 'tmp_skipped_content', db.skipped_content_keys, cur) # move metadata in place db.skipped_content_add_from_temp(cur) # Wait for objstorage addition before returning from the # transaction, bubbling up any exception added_to_objstorage.result() @db_transaction() def content_update(self, content, keys=[], db=None, cur=None): """Update content blobs to the storage. Does nothing for unknown contents or skipped ones. Args: content (iterable): iterable of dictionaries representing individual pieces of content to update. Each dictionary has the following keys: - data (bytes): the actual content - length (int): content length (default: -1) - one key for each checksum algorithm in :data:`swh.model.hashutil.ALGORITHMS`, mapped to the corresponding checksum - status (str): one of visible, hidden, absent keys (list): List of keys (str) whose values needs an update, e.g., new hash column """ # TODO: Add a check on input keys. How to properly implement # this? We don't know yet the new columns. db.mktemp('content', cur) select_keys = list(set(db.content_get_metadata_keys).union(set(keys))) db.copy_to(content, 'tmp_content', select_keys, cur) db.content_update_from_temp(keys_to_update=keys, cur=cur) def content_get(self, content): """Retrieve in bulk contents and their data. Args: content: iterables of sha1 Yields: dict: 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(obj_id) except ObjNotFoundError: yield None continue yield {'sha1': obj_id, 'data': data} @db_transaction_generator(statement_timeout=500) def content_get_metadata(self, content, db=None, cur=None): """Retrieve content metadata in bulk Args: content: iterable of content identifiers (sha1) Returns: an iterable with content metadata corresponding to the given ids """ for metadata in db.content_get_metadata_from_sha1s(content, cur): yield dict(zip(db.content_get_metadata_keys, metadata)) @db_transaction_generator() def content_missing(self, content, key_hash='sha1', db=None, cur=None): """List content missing from storage Args: content ([dict]): iterable of dictionaries containing one key for each checksum algorithm in :data:`swh.model.hashutil.ALGORITHMS`, mapped to the corresponding checksum, and a length key mapped to the content length. key_hash (str): name of the column to use as hash id result (default: 'sha1') Returns: iterable ([bytes]): missing content ids (as per the key_hash column) Raises: TODO: an exception when we get a hash collision. """ keys = db.content_hash_keys if key_hash not in keys: raise ValueError("key_hash should be one of %s" % keys) key_hash_idx = keys.index(key_hash) if not content: return for obj in db.content_missing_from_list(content, cur): yield obj[key_hash_idx] @db_transaction_generator() def content_missing_per_sha1(self, contents, db=None, cur=None): """List content missing from storage based only on sha1. Args: contents: Iterable of sha1 to check for absence. Returns: iterable: missing ids Raises: TODO: an exception when we get a hash collision. """ for obj in db.content_missing_per_sha1(contents, cur): yield obj[0] @db_transaction_generator() def skipped_content_missing(self, content, db=None, cur=None): """List skipped_content missing from storage Args: content: iterable of dictionaries containing the data for each checksum algorithm. Returns: iterable: missing signatures """ keys = db.content_hash_keys 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, db=None, cur=None): """Find a content hash in db. Args: content: a dictionary representing one content hash, mapping checksum algorithm names (see swh.model.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. """ if not set(content).intersection(ALGORITHMS): raise ValueError('content keys must contain at least one of: ' 'sha1, sha1_git, sha256, blake2s256') c = db.content_find(sha1=content.get('sha1'), sha1_git=content.get('sha1_git'), sha256=content.get('sha256'), blake2s256=content.get('blake2s256'), cur=cur) if c: return dict(zip(db.content_find_cols, c)) return None def directory_add(self, directories): """Add directories to the storage Args: directories (iterable): 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 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.get_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, db=None, cur=None): """List directories missing from storage Args: directories (iterable): an iterable of directory ids Yields: missing directory ids """ for obj in db.directory_missing_from_list(directories, cur): yield obj[0] @db_transaction_generator(statement_timeout=20000) def directory_ls(self, directory, recursive=False, db=None, 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. """ if recursive: res_gen = db.directory_walk(directory, cur=cur) else: res_gen = db.directory_walk_one(directory, cur=cur) for line in res_gen: yield dict(zip(db.directory_ls_cols, line)) @db_transaction(statement_timeout=2000) def directory_entry_get_by_path(self, directory, paths, db=None, cur=None): """Get the directory entry (either file or dir) from directory with path. Args: - directory: sha1 of the top level directory - paths: path to lookup from the top level directory. From left (top) to right (bottom). Returns: The corresponding directory entry if found, None otherwise. """ res = db.directory_entry_get_by_path(directory, paths, cur) if res: return dict(zip(db.directory_ls_cols, res)) def revision_add(self, revisions): """Add revisions to the storage Args: revisions (iterable): 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 - date_neg_utc_offset (boolean): whether a null date_offset represents a negative UTC offset - 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 - committer_date_neg_utc_offset (boolean): whether a null committer_date_offset represents a negative UTC offset - 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.get_db() 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 = ( converters.revision_to_db(revision) for revision in revisions if revision['id'] in revisions_missing) parents_filtered = [] db.copy_to( revisions_filtered, 'tmp_revision', db.revision_add_cols, cur, lambda rev: parents_filtered.extend(rev['parents'])) 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, db=None, cur=None): """List revisions missing from storage Args: revisions (iterable): revision ids Yields: missing revision ids """ if not revisions: return for obj in db.revision_missing_from_list(revisions, cur): yield obj[0] @db_transaction_generator(statement_timeout=500) def revision_get(self, revisions, db=None, cur=None): """Get all revisions from storage Args: revisions: an iterable of revision ids Returns: iterable: an iterable of revisions as dictionaries (or None if the revision doesn't exist) """ for line in db.revision_get_from_list(revisions, cur): data = converters.db_to_revision( dict(zip(db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data @db_transaction_generator(statement_timeout=2000) def revision_log(self, revisions, limit=None, db=None, cur=None): """Fetch revision entry from the given root revisions. Args: revisions: array of root revision to lookup limit: limitation on the output result. Default to None. Yields: List of revision log from such revisions root. """ for line in db.revision_log(revisions, limit, cur): data = converters.db_to_revision( dict(zip(db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data @db_transaction_generator(statement_timeout=2000) def revision_shortlog(self, revisions, limit=None, db=None, cur=None): """Fetch the shortlog for the given revisions Args: revisions: list of root revisions to lookup limit: depth limitation for the output Yields: a list of (id, parents) tuples. """ yield from db.revision_shortlog(revisions, limit, cur) def release_add(self, releases): """Add releases to the storage Args: releases (iterable): 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 - date_neg_utc_offset (boolean): whether a null date_offset represents a negative UTC offset - 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.get_db() release_ids = set(release['id'] for release in releases) releases_missing = set(self.release_missing(release_ids)) if not releases_missing: return with db.transaction() as cur: db.mktemp_release(cur) releases_filtered = ( converters.release_to_db(release) for release in releases if release['id'] in releases_missing ) db.copy_to(releases_filtered, 'tmp_release', db.release_add_cols, cur) db.release_add_from_temp(cur) @db_transaction_generator() def release_missing(self, releases, db=None, cur=None): """List releases missing from storage Args: releases: an iterable of release ids Returns: a list of missing release ids """ if not releases: return for obj in db.release_missing_from_list(releases, cur): yield obj[0] @db_transaction_generator(statement_timeout=500) def release_get(self, releases, db=None, cur=None): """Given a list of sha1, return the releases's information Args: releases: list of sha1s Yields: releases: list of releases as dicts with the following keys: - id: origin's id - revision: origin's type - url: origin's url Raises: ValueError: if the keys does not match (url and type) nor id. """ for release in db.release_get_from_list(releases, cur): yield converters.db_to_release( dict(zip(db.release_get_cols, release)) ) @db_transaction() def snapshot_add(self, origin, visit, snapshot, db=None, cur=None): """Add a snapshot for the given origin/visit couple Args: origin (int): id of the origin visit (int): id of the visit snapshot (dict): the snapshot to add to the visit, containing the following keys: - **id** (:class:`bytes`): id of the snapshot - **branches** (:class:`dict`): branches the snapshot contains, mapping the branch name (:class:`bytes`) to the branch target, itself a :class:`dict` (or ``None`` if the branch points to an unknown object) - **target_type** (:class:`str`): one of ``content``, ``directory``, ``revision``, ``release``, ``snapshot``, ``alias`` - **target** (:class:`bytes`): identifier of the target (currently a ``sha1_git`` for all object kinds, or the name of the target branch for aliases) """ if not db.snapshot_exists(snapshot['id'], cur): db.mktemp_snapshot_branch(cur) db.copy_to( ( { 'name': name, 'target': info['target'] if info else None, 'target_type': info['target_type'] if info else None, } for name, info in snapshot['branches'].items() ), 'tmp_snapshot_branch', ['name', 'target', 'target_type'], cur, ) db.snapshot_add(origin, visit, snapshot['id'], cur) @db_transaction(statement_timeout=2000) def snapshot_get(self, snapshot_id, db=None, cur=None): """Get the content, possibly partial, of a snapshot with the given id The branches of the snapshot are iterated in the lexicographical order of their names. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. In order to browse the whole set of branches, the method :meth:`snapshot_get_branches` should be used instead. Args: snapshot_id (bytes): identifier of the snapshot Returns: dict: a dict with three keys: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. * **next_branch**: the name of the first branch not returned or :const:`None` if the snapshot has less than 1000 branches. """ - max_branches = 1000 - branches = {} - next_branch = None - fetched_branches = list(db.snapshot_get_by_id( - snapshot_id, branches_count=max_branches+1, cur=cur)) - for branch in fetched_branches[:max_branches]: - branch = dict(zip(db.snapshot_get_cols, branch)) - del branch['snapshot_id'] - name = branch.pop('name') - if branch == {'target': None, 'target_type': None}: - branch = None - branches[name] = branch - - if len(fetched_branches) > max_branches: - branch = dict(zip(db.snapshot_get_cols, fetched_branches[-1])) - next_branch = branch['name'] - - if branches: - return { - 'id': snapshot_id, - 'branches': branches, - 'next_branch': next_branch - } - - if db.snapshot_exists(snapshot_id, cur): - # empty snapshot - return { - 'id': snapshot_id, - 'branches': {}, - 'next_branch': None - } - return None + return self.snapshot_get_branches(snapshot_id, db=db, cur=cur) @db_transaction(statement_timeout=2000) def snapshot_get_by_origin_visit(self, origin, visit, db=None, cur=None): """Get the content, possibly partial, of a snapshot for the given origin visit The branches of the snapshot are iterated in the lexicographical order of their names. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. In order to browse the whole set of branches, the method :meth:`snapshot_get_branches` should be used instead. Args: origin (int): the origin identifier visit (int): the visit identifier Returns: dict: a dict with three keys: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. * **next_branch**: the name of the first branch not returned or :const:`None` if the snapshot has less than 1000 branches. """ snapshot_id = db.snapshot_get_by_origin_visit(origin, visit, cur) if snapshot_id: return self.snapshot_get(snapshot_id, db=db, cur=cur) - else: - # compatibility code during the snapshot migration - origin_visit_info = self.origin_visit_get_by(origin, visit, - db=db, cur=cur) - if origin_visit_info is None: - return None - ret = {'id': None} - ret['branches'] = origin_visit_info['occurrences'] - return ret return None @db_transaction(statement_timeout=2000) def snapshot_get_latest(self, origin, allowed_statuses=None, db=None, cur=None): """Get the content, possibly partial, of the latest snapshot for the given origin, optionally only from visits that have one of the given allowed_statuses The branches of the snapshot are iterated in the lexicographical order of their names. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. In order to browse the whole set of branches, the method :meth:`snapshot_get_branches` should be used instead. Args: origin (int): the origin identifier allowed_statuses (list of str): list of visit statuses considered to find the latest snapshot for the visit. For instance, ``allowed_statuses=['full']`` will only consider visits that have successfully run to completion. Returns: dict: a dict with three keys: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. * **next_branch**: the name of the first branch not returned or :const:`None` if the snapshot has less than 1000 branches. """ origin_visit = db.origin_visit_get_latest_snapshot( origin, allowed_statuses=allowed_statuses, cur=cur) if origin_visit: origin_visit = dict(zip(db.origin_visit_get_cols, origin_visit)) return self.snapshot_get(origin_visit['snapshot'], db=db, cur=cur) @db_transaction(statement_timeout=2000) def snapshot_count_branches(self, snapshot_id, db=None, cur=None): """Count the number of branches in the snapshot with the given id Args: snapshot_id (bytes): identifier of the snapshot Returns: dict: A dict whose keys are the target types of branches and values their corresponding amount """ return dict([bc for bc in db.snapshot_count_branches(snapshot_id, cur)]) @db_transaction(statement_timeout=2000) def snapshot_get_branches(self, snapshot_id, branches_from=b'', - branches_count=None, target_types=None, + branches_count=1000, target_types=None, db=None, cur=None): """Get the content, possibly partial, of a snapshot with the given id The branches of the snapshot are iterated in the lexicographical order of their names. Args: snapshot_id (bytes): identifier of the snapshot branches_from (bytes): optional parameter used to skip branches whose name is lesser than it before returning them branches_count (int): optional parameter used to restrain the amount of returned branches target_types (list): optional parameter used to filter the target types of branch to return (possible values that can be contained in that list are `'content', 'directory', 'revision', 'release', 'snapshot', 'alias'`) Returns: - dict: a dict with two keys: + dict: a dict with three keys: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. + * **next_branch**: the name of the first branch not returned + or :const:`None` if the snapshot has less than + `branches_count` branches after `branches_from` included. """ + if snapshot_id == EMPTY_SNAPSHOT_ID: + return { + 'id': snapshot_id, + 'branches': {}, + 'next_branch': None, + } + branches = {} - for branch in db.snapshot_get_by_id(snapshot_id, branches_from, - branches_count, target_types, cur): + next_branch = None + + fetched_branches = list(db.snapshot_get_by_id( + snapshot_id, branches_from=branches_from, + branches_count=branches_count+1, target_types=target_types, + cur=cur, + )) + for branch in fetched_branches[:branches_count]: branch = dict(zip(db.snapshot_get_cols, branch)) del branch['snapshot_id'] name = branch.pop('name') if branch == {'target': None, 'target_type': None}: branch = None branches[name] = branch - if branches: - return {'id': snapshot_id, 'branches': branches} + if len(fetched_branches) > branches_count: + branch = dict(zip(db.snapshot_get_cols, fetched_branches[-1])) + next_branch = branch['name'] - if db.snapshot_exists(snapshot_id, cur): - return {'id': snapshot_id, 'branches': {}} + if branches: + return { + 'id': snapshot_id, + 'branches': branches, + 'next_branch': next_branch, + } return None @db_transaction() def origin_visit_add(self, origin, ts, db=None, cur=None): """Add an origin_visit for the origin at ts with status 'ongoing'. Args: origin: Visited Origin id ts: timestamp of such visit Returns: dict: dictionary with keys origin and visit where: - origin: origin identifier - visit: the visit identifier for the new visit occurrence - ts (datetime.DateTime): the visit date """ if isinstance(ts, str): ts = dateutil.parser.parse(ts) return { 'origin': origin, 'visit': db.origin_visit_add(origin, ts, cur) } @db_transaction() def origin_visit_update(self, origin, visit_id, status, metadata=None, db=None, cur=None): """Update an origin_visit's status. Args: origin: Visited Origin id visit_id: Visit's id status: Visit's new status metadata: Data associated to the visit Returns: None """ return db.origin_visit_update(origin, visit_id, status, metadata, cur) @db_transaction_generator(statement_timeout=500) def origin_visit_get(self, origin, last_visit=None, limit=None, db=None, cur=None): """Retrieve all the origin's visit's information. Args: origin (int): The occurrence's origin (identifier). last_visit (int): Starting point from which listing the next visits Default to None limit (int): Number of results to return from the last visit. Default to None Yields: List of visits. """ for line in db.origin_visit_get_all( origin, last_visit=last_visit, limit=limit, cur=cur): data = dict(zip(db.origin_visit_get_cols, line)) yield data @db_transaction(statement_timeout=500) def origin_visit_get_by(self, origin, visit, db=None, cur=None): """Retrieve origin visit's information. Args: origin: The occurrence's origin (identifier). Returns: The information on that particular (origin, visit) """ ori_visit = db.origin_visit_get(origin, visit, cur) if not ori_visit: return None return dict(zip(db.origin_visit_get_cols, ori_visit)) @db_transaction(statement_timeout=2000) def object_find_by_sha1_git(self, ids, db=None, cur=None): """Return the objects found with the given ids. Args: ids: a generator of sha1_gits Returns: dict: a mapping from id to the list of objects found. Each object found is itself a dict with keys: - sha1_git: the input id - type: the type of object found - id: the id of the object found - object_id: the numeric id of the object found. """ ret = {id: [] for id in ids} for retval in db.object_find_by_sha1_git(ids, cur=cur): if retval[1]: ret[retval[0]].append(dict(zip(db.object_find_by_sha1_git_cols, retval))) return ret origin_keys = ['id', 'type', 'url'] @db_transaction(statement_timeout=500) def origin_get(self, origin, db=None, 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 or the id: - id: the origin id Returns: dict: the origin dictionary with the keys: - id: origin's id - type: origin's type - url: origin's url Raises: ValueError: if the keys does not match (url and type) nor id. """ 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(self.origin_keys, ori)) return None @db_transaction_generator() def origin_search(self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False, db=None, cur=None): """Search for origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. Args: url_pattern (str): the string pattern to search for in origin urls offset (int): number of found origins to skip before returning results limit (int): the maximum number of found origins to return regexp (bool): if True, consider the provided pattern as a regular expression and return origins whose urls match it with_visit (bool): if True, filter out origins with no visit Returns: An iterable of dict containing origin information as returned by :meth:`swh.storage.storage.Storage.origin_get`. """ for origin in db.origin_search(url_pattern, offset, limit, regexp, with_visit, cur): yield dict(zip(self.origin_keys, origin)) @db_transaction() def _person_add(self, person, db=None, cur=None): """Add a person in storage. Note: Internal function for now, do not use outside of this module. 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. """ return db.person_add(person) @db_transaction_generator(statement_timeout=500) def person_get(self, person, db=None, cur=None): """Return the persons identified by their ids. Args: person: array of ids. Returns: The array of persons corresponding of the ids. """ for person in db.person_get(person): yield dict(zip(db.person_get_cols, person)) @db_transaction() def origin_add(self, origins, db=None, cur=None): """Add origins to the storage Args: origins: list of dictionaries representing the individual origins, with the following keys: - type: the origin type ('git', 'svn', 'deb', ...) - url (bytes): the url the origin points to Returns: list: given origins as dict updated with their id """ for origin in origins: origin['id'] = self.origin_add_one(origin, db=db, cur=cur) return origins @db_transaction() def origin_add_one(self, origin, db=None, 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. """ 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, db=None, 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 db.create_fetch_history(fetch_history, cur) @db_transaction() def fetch_history_end(self, fetch_history_id, data, db=None, 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 = 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) db.update_fetch_history(fetch_history, cur) @db_transaction() def fetch_history_get(self, fetch_history_id, db=None, cur=None): """Get the fetch_history entry with id `fetch_history_id`. """ return db.get_fetch_history(fetch_history_id, cur) @db_transaction(statement_timeout=500) def stat_counters(self, db=None, cur=None): """compute statistics about the number of tuples in various tables Returns: dict: 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 db.stat_counters()} @db_transaction() def origin_metadata_add(self, origin_id, ts, provider, tool, metadata, db=None, cur=None): """ Add an origin_metadata for the origin at ts with provenance and metadata. Args: origin_id (int): the origin's id for which the metadata is added ts (datetime): timestamp of the found metadata provider (int): the provider of metadata (ex:'hal') tool (int): tool used to extract metadata metadata (jsonb): the metadata retrieved at the time and location Returns: id (int): the origin_metadata unique id """ if isinstance(ts, str): ts = dateutil.parser.parse(ts) return db.origin_metadata_add(origin_id, ts, provider, tool, metadata, cur) @db_transaction_generator(statement_timeout=500) def origin_metadata_get_by(self, origin_id, provider_type=None, db=None, cur=None): """Retrieve list of all origin_metadata entries for the origin_id Args: origin_id (int): the unique origin identifier provider_type (str): (optional) type of provider Returns: list of dicts: the origin_metadata dictionary with the keys: - id (int): origin_metadata's id - origin_id (int): origin's id - discovery_date (datetime): timestamp of discovery - tool_id (int): metadata's extracting tool - metadata (jsonb) - provider_id (int): metadata's provider - provider_name (str) - provider_type (str) - provider_url (str) """ for line in db.origin_metadata_get_by(origin_id, provider_type, cur): yield dict(zip(db.origin_metadata_get_cols, line)) @db_transaction_generator() def tool_add(self, tools, db=None, cur=None): """Add new tools to the storage. Args: tools (iterable of :class:`dict`): Tool information to add to storage. Each tool is a :class:`dict` with the following keys: - name (:class:`str`): name of the tool - version (:class:`str`): version of the tool - configuration (:class:`dict`): configuration of the tool, must be json-encodable Returns: `iterable` of :class:`dict`: All the tools inserted in storage (including the internal ``id``). The order of the list is not guaranteed to match the order of the initial list. """ db.mktemp_tool(cur) db.copy_to(tools, 'tmp_tool', ['name', 'version', 'configuration'], cur) tools = db.tool_add_from_temp(cur) for line in tools: yield dict(zip(db.tool_cols, line)) @db_transaction(statement_timeout=500) def tool_get(self, tool, db=None, cur=None): """Retrieve tool information. Args: tool (dict): Tool information we want to retrieve from storage. The dicts have the same keys as those used in :func:`tool_add`. Returns: dict: The full tool information if it exists (``id`` included), None otherwise. """ tool_conf = tool['configuration'] if isinstance(tool_conf, dict): tool_conf = json.dumps(tool_conf) idx = db.tool_get(tool['name'], tool['version'], tool_conf) if not idx: return None return dict(zip(db.tool_cols, idx)) @db_transaction() def metadata_provider_add(self, provider_name, provider_type, provider_url, metadata, db=None, cur=None): return db.metadata_provider_add(provider_name, provider_type, provider_url, metadata, cur) @db_transaction() def metadata_provider_get(self, provider_id, db=None, cur=None): result = db.metadata_provider_get(provider_id) if not result: return None return dict(zip(db.metadata_provider_cols, result)) @db_transaction() def metadata_provider_get_by(self, provider, db=None, cur=None): result = db.metadata_provider_get_by(provider['provider_name'], provider['provider_url']) if not result: return None return dict(zip(db.metadata_provider_cols, result)) def diff_directories(self, from_dir, to_dir, track_renaming=False): """Compute the list of file changes introduced between two arbitrary directories (insertion / deletion / modification / renaming of files). Args: from_dir (bytes): identifier of the directory to compare from to_dir (bytes): identifier of the directory to compare to track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ return diff.diff_directories(self, from_dir, to_dir, track_renaming) def diff_revisions(self, from_rev, to_rev, track_renaming=False): """Compute the list of file changes introduced between two arbitrary revisions (insertion / deletion / modification / renaming of files). Args: from_rev (bytes): identifier of the revision to compare from to_rev (bytes): identifier of the revision to compare to track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ return diff.diff_revisions(self, from_rev, to_rev, track_renaming) def diff_revision(self, revision, track_renaming=False): """Compute the list of file changes introduced by a specific revision (insertion / deletion / modification / renaming of files) by comparing it against its first parent. Args: revision (bytes): identifier of the revision from which to compute the list of files changes track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ return diff.diff_revision(self, revision, track_renaming) diff --git a/swh/storage/tests/__init__.py b/swh/storage/tests/__init__.py index e69de29bb..68b15fce7 100644 --- a/swh/storage/tests/__init__.py +++ b/swh/storage/tests/__init__.py @@ -0,0 +1,5 @@ +from os import path +import swh.storage + + +SQL_DIR = path.join(path.dirname(swh.storage.__file__), 'sql') diff --git a/swh/storage/tests/algos/test_snapshot.py b/swh/storage/tests/algos/test_snapshot.py new file mode 100644 index 000000000..ceff24376 --- /dev/null +++ b/swh/storage/tests/algos/test_snapshot.py @@ -0,0 +1,128 @@ +# Copyright (C) 2018 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 unittest + +from nose.plugins.attrib import attr + +from hypothesis import given, settings +from hypothesis.strategies import (binary, composite, datetimes, dictionaries, + from_regex, none, one_of, sampled_from) + +from swh.model.identifiers import snapshot_identifier, identifier_to_bytes +from swh.storage.tests.storage_testing import StorageTestFixture + +from swh.storage.algos.snapshot import snapshot_get_all_branches + + +def branch_names(): + return binary(min_size=5, max_size=10) + + +@composite +def branch_targets_object(draw): + return { + 'target': draw(binary(min_size=20, max_size=20)), + 'target_type': draw( + sampled_from([ + 'content', 'directory', 'revision', 'release', 'snapshot', + ]) + ), + } + + +@composite +def branch_targets_alias(draw): + return { + 'target': draw(branch_names()), + 'target_type': 'alias', + } + + +def branch_targets(*, only_objects=False): + if only_objects: + return branch_targets_object() + else: + return one_of(none(), branch_targets_alias(), branch_targets_object()) + + +@composite +def snapshots(draw, *, min_size=0, max_size=100, only_objects=False): + branches = draw(dictionaries( + keys=branch_names(), + values=branch_targets(only_objects=only_objects), + min_size=min_size, + max_size=max_size, + )) + + if not only_objects: + # Make sure aliases point to actual branches + unresolved_aliases = { + target['target'] + for target in branches.values() + if (target + and target['target_type'] == 'alias' + and target['target'] not in branches) + } + + for alias in unresolved_aliases: + branches[alias] = draw(branch_targets(only_objects=True)) + + ret = { + 'branches': branches, + } + ret['id'] = identifier_to_bytes(snapshot_identifier(ret)) + return ret + + +@composite +def urls(draw): + protocol = draw(sampled_from(['git', 'http', 'https', 'deb'])) + domain = draw(from_regex(r'\A([a-z]([a-z0-9-]*)\.){1,3}[a-z0-9]+\Z')) + + return '%s://%s' % (protocol, domain) + + +@composite +def origins(draw): + return { + 'type': draw(sampled_from(['git', 'hg', 'svn', 'pypi', 'deb'])), + 'url': draw(urls()), + } + + +@attr('db') +class TestSnapshotAllBranches(StorageTestFixture, unittest.TestCase): + @given(origins(), datetimes(), snapshots(min_size=0, max_size=10, + only_objects=False)) + def test_snapshot_small(self, origin, ts, snapshot): + origin_id = self.storage.origin_add_one(origin) + visit = self.storage.origin_visit_add(origin_id, ts) + self.storage.snapshot_add(origin_id, visit['visit'], snapshot) + + returned_snapshot = snapshot_get_all_branches(self.storage, + snapshot['id']) + self.assertEquals(snapshot, returned_snapshot) + + @settings(max_examples=5, deadline=1000) + @given(origins(), datetimes(), + branch_names(), branch_targets(only_objects=True)) + def test_snapshot_large(self, origin, ts, branch_name, branch_target): + origin_id = self.storage.origin_add_one(origin) + visit = self.storage.origin_visit_add(origin_id, ts) + + snapshot = { + 'branches': { + b'%s%05d' % (branch_name, i): branch_target + for i in range(10000) + } + } + snapshot['id'] = identifier_to_bytes(snapshot_identifier(snapshot)) + + self.storage.snapshot_add(origin_id, visit['visit'], snapshot) + + returned_snapshot = snapshot_get_all_branches(self.storage, + snapshot['id']) + self.assertEquals(snapshot, returned_snapshot) diff --git a/swh/storage/tests/storage_testing.py b/swh/storage/tests/storage_testing.py index bc6d471ce..338a0aecd 100644 --- a/swh/storage/tests/storage_testing.py +++ b/swh/storage/tests/storage_testing.py @@ -1,63 +1,57 @@ # Copyright (C) 2015-2017 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 os import tempfile -import pathlib from swh.storage import get_storage +from swh.core.tests.db_testing import SingleDbTestFixture +from swh.storage.tests import SQL_DIR -class StorageTestFixture: + +class StorageTestFixture(SingleDbTestFixture): """Mix this in a test subject class to get Storage testing support. - This fixture requires to come before DbTestFixture in the inheritance list - as it uses its methods to setup its own internal database. + This fixture requires to come before SingleDbTestFixture in the + inheritance list as it uses its methods to setup its own + internal database. Usage example: - class TestStorage(StorageTestFixture, DbTestFixture): + class MyTestStorage(StorageTestFixture, unittest.TestCase): ... - """ - TEST_STORAGE_DB_NAME = 'softwareheritage-test-storage' - @classmethod - def setUpClass(cls): - if not hasattr(cls, 'DB_TEST_FIXTURE_IMPORTED'): - raise RuntimeError("StorageTestFixture needs to be followed by " - "DbTestFixture in the inheritance list.") - - test_dir = pathlib.Path(__file__).absolute().parent - test_data_dir = test_dir / '../../../../swh-storage-testdata' - test_db_dump = (test_data_dir / 'dumps/swh.dump').absolute() - cls.add_db(cls.TEST_STORAGE_DB_NAME, str(test_db_dump), 'pg_dump') - super().setUpClass() + """ + TEST_DB_NAME = 'softwareheritage-test-storage' + TEST_DB_DUMP = os.path.join(SQL_DIR, '*.sql') def setUp(self): super().setUp() self.objtmp = tempfile.TemporaryDirectory() self.storage_config = { 'cls': 'local', 'args': { - 'db': 'dbname=%s' % self.TEST_STORAGE_DB_NAME, + 'db': 'dbname=%s' % self.TEST_DB_NAME, 'objstorage': { 'cls': 'pathslicing', 'args': { 'root': self.objtmp.name, 'slicing': '0:1/1:5', }, }, }, } self.storage = get_storage(**self.storage_config) def tearDown(self): self.objtmp.cleanup() self.storage = None super().tearDown() def reset_storage_tables(self): excluded = {'dbversion', 'tool'} - self.reset_db_tables(self.TEST_STORAGE_DB_NAME, excluded=excluded) + self.reset_db_tables(self.TEST_DB_NAME, excluded=excluded) diff --git a/swh/storage/tests/test_api_client.py b/swh/storage/tests/test_api_client.py index 2a49e39d2..6735541e5 100644 --- a/swh/storage/tests/test_api_client.py +++ b/swh/storage/tests/test_api_client.py @@ -1,54 +1,54 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import shutil import tempfile import unittest from swh.core.tests.server_testing import ServerTestFixture from swh.storage.api.client import RemoteStorage from swh.storage.api.server import app from swh.storage.tests.test_storage import CommonTestStorage class TestRemoteStorage(CommonTestStorage, ServerTestFixture, unittest.TestCase): """Test the remote storage API. This class doesn't define any tests as we want identical functionality between local and remote storage. All the tests are therefore defined in CommonTestStorage. """ def setUp(self): # ServerTestFixture needs to have self.objroot for # setUp() method, but this field is defined in # AbstractTestStorage's setUp() # To avoid confusion, override the self.objroot to a # one chosen in this class. self.storage_base = tempfile.mkdtemp() self.config = { 'storage': { 'cls': 'local', 'args': { - 'db': 'dbname=%s' % self.TEST_STORAGE_DB_NAME, + 'db': 'dbname=%s' % self.TEST_DB_NAME, 'objstorage': { 'cls': 'pathslicing', 'args': { 'root': self.storage_base, 'slicing': '0:2', }, }, } } } self.app = app super().setUp() self.storage = RemoteStorage(self.url()) self.objroot = self.storage_base def tearDown(self): super().tearDown() shutil.rmtree(self.storage_base) diff --git a/swh/storage/tests/test_db.py b/swh/storage/tests/test_db.py index f0952ffca..5b3c2ec0e 100644 --- a/swh/storage/tests/test_db.py +++ b/swh/storage/tests/test_db.py @@ -1,52 +1,50 @@ # Copyright (C) 2015-2017 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 os import unittest from nose.plugins.attrib import attr from swh.core.tests.db_testing import SingleDbTestFixture from swh.model.hashutil import hash_to_bytes from swh.storage.db import Db - -TEST_DIR = os.path.dirname(os.path.abspath(__file__)) -TEST_DATA_DIR = os.path.join(TEST_DIR, '../../../../swh-storage-testdata') +from . import SQL_DIR @attr('db') class TestDb(SingleDbTestFixture, unittest.TestCase): - - TEST_DB_DUMP = os.path.join(TEST_DATA_DIR, 'dumps/swh.dump') + TEST_DB_NAME = 'softwareheritage-test-storage' + TEST_DB_DUMP = os.path.join(SQL_DIR, '*.sql') def setUp(self): super().setUp() self.db = Db(self.conn) def tearDown(self): self.db.conn.close() super().tearDown() def test_add_content(self): cur = self.cursor sha1 = hash_to_bytes('34973274ccef6ab4dfaaf86599792fa9c3fe4689') self.db.mktemp('content', cur) self.db.copy_to([{ 'sha1': sha1, 'sha1_git': hash_to_bytes( 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), 'sha256': hash_to_bytes( '673650f936cb3b0a2f93ce09d81be107' '48b1b203c19e8176b4eefc1964a0cf3a'), 'blake2s256': hash_to_bytes('69217a3079908094e11121d042354a7c' '1f55b6482ca1a51e1b250dfd1ed0eef9'), 'length': 3}], 'tmp_content', ['sha1', 'sha1_git', 'sha256', 'blake2s256', 'length'], cur) self.db.content_add_from_temp(cur) self.cursor.execute('SELECT sha1 FROM content WHERE sha1 = %s', (sha1,)) self.assertEqual(self.cursor.fetchone()[0].tobytes(), sha1) diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index d65f85a10..e002e0e7c 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,1960 +1,1982 @@ # Copyright (C) 2015-2017 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 copy import datetime import unittest from collections import defaultdict from operator import itemgetter from unittest.mock import Mock, patch import psycopg2 from nose.plugins.attrib import attr from swh.core.tests.db_testing import DbTestFixture from swh.model import from_disk, identifiers from swh.model.hashutil import hash_to_bytes from swh.storage.tests.storage_testing import StorageTestFixture @attr('db') -class BaseTestStorage(StorageTestFixture, DbTestFixture): +class BaseTestStorage(StorageTestFixture): def setUp(self): super().setUp() - db = self.test_db[self.TEST_STORAGE_DB_NAME] + db = self.test_db[self.TEST_DB_NAME] self.conn = db.conn self.cursor = db.cursor self.maxDiff = None self.cont = { 'data': b'42\n', 'length': 3, 'sha1': hash_to_bytes( '34973274ccef6ab4dfaaf86599792fa9c3fe4689'), 'sha1_git': hash_to_bytes( 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), 'sha256': hash_to_bytes( '673650f936cb3b0a2f93ce09d81be107' '48b1b203c19e8176b4eefc1964a0cf3a'), 'blake2s256': hash_to_bytes('d5fe1939576527e42cfd76a9455a2' '432fe7f56669564577dd93c4280e76d661d'), 'status': 'visible', } self.cont2 = { 'data': b'4242\n', 'length': 5, 'sha1': hash_to_bytes( '61c2b3a30496d329e21af70dd2d7e097046d07b7'), 'sha1_git': hash_to_bytes( '36fade77193cb6d2bd826161a0979d64c28ab4fa'), 'sha256': hash_to_bytes( '859f0b154fdb2d630f45e1ecae4a8629' '15435e663248bb8461d914696fc047cd'), 'blake2s256': hash_to_bytes('849c20fad132b7c2d62c15de310adfe87be' '94a379941bed295e8141c6219810d'), 'status': 'visible', } self.cont3 = { 'data': b'424242\n', 'length': 7, 'sha1': hash_to_bytes( '3e21cc4942a4234c9e5edd8a9cacd1670fe59f13'), 'sha1_git': hash_to_bytes( 'c932c7649c6dfa4b82327d121215116909eb3bea'), 'sha256': hash_to_bytes( '92fb72daf8c6818288a35137b72155f5' '07e5de8d892712ab96277aaed8cf8a36'), 'blake2s256': hash_to_bytes('76d0346f44e5a27f6bafdd9c2befd304af' 'f83780f93121d801ab6a1d4769db11'), 'status': 'visible', } self.missing_cont = { 'data': b'missing\n', 'length': 8, 'sha1': hash_to_bytes( 'f9c24e2abb82063a3ba2c44efd2d3c797f28ac90'), 'sha1_git': hash_to_bytes( '33e45d56f88993aae6a0198013efa80716fd8919'), 'sha256': hash_to_bytes( '6bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes('306856b8fd879edb7b6f1aeaaf8db9bbecc9' '93cd7f776c333ac3a782fa5c6eba'), 'status': 'absent', } self.skipped_cont = { 'length': 1024 * 1024 * 200, 'sha1_git': hash_to_bytes( '33e45d56f88993aae6a0198013efa80716fd8920'), 'sha1': hash_to_bytes( '43e45d56f88993aae6a0198013efa80716fd8920'), 'sha256': hash_to_bytes( '7bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes( 'ade18b1adecb33f891ca36664da676e1' '2c772cc193778aac9a137b8dc5834b9b'), 'reason': 'Content too long', 'status': 'absent', } self.skipped_cont2 = { 'length': 1024 * 1024 * 300, 'sha1_git': hash_to_bytes( '44e45d56f88993aae6a0198013efa80716fd8921'), 'sha1': hash_to_bytes( '54e45d56f88993aae6a0198013efa80716fd8920'), 'sha256': hash_to_bytes( '8cbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes( '9ce18b1adecb33f891ca36664da676e1' '2c772cc193778aac9a137b8dc5834b9b'), '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': from_disk.DentryPerms.content, }, { 'name': b'bar\xc3', 'type': 'dir', 'target': b'12345678901234567890', 'perms': from_disk.DentryPerms.directory, }, ], } 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': from_disk.DentryPerms.content, } ], } self.dir3 = { 'id': hash_to_bytes('33e45d56f88993aae6a0198013efa80716fd8921'), 'entries': [ { 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': from_disk.DentryPerms.content, }, { 'name': b'bar', 'type': 'dir', 'target': b'12345678901234560000', 'perms': from_disk.DentryPerms.directory, }, { 'name': b'hello', 'type': 'file', 'target': b'12345678901234567890', 'perms': from_disk.DentryPerms.content, }, ], } 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', 'email': b'nicolas@example.com', 'fullname': b'Nicolas Dandrimont ', }, 'date': { 'timestamp': 1234567890, 'offset': 120, 'negative_utc': None, }, 'committer': { 'name': b'St\xc3fano Zacchiroli', 'email': b'stefano@example.com', 'fullname': b'St\xc3fano Zacchiroli ' }, 'committer_date': { 'timestamp': 1123456789, 'offset': 0, 'negative_utc': True, }, 'parents': [b'01234567890123456789', b'23434512345123456789'], 'type': 'git', 'directory': self.dir['id'], 'metadata': { 'checksums': { 'sha1': 'tarball-sha1', 'sha256': 'tarball-sha256', }, 'signed-off-by': 'some-dude', 'extra_headers': [ ['gpgsig', b'test123'], ['mergetags', [b'foo\\bar', b'\x22\xaf\x89\x80\x01\x00']], ], }, 'synthetic': True } self.revision2 = { 'id': b'87659012345678904321', 'message': b'hello again', 'author': { 'name': b'Roberto Dicosmo', 'email': b'roberto@example.com', 'fullname': b'Roberto Dicosmo ', }, 'date': { 'timestamp': { 'seconds': 1234567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'committer_date': { 'timestamp': 1123456789, 'offset': 0, 'negative_utc': False, }, 'parents': [b'01234567890123456789'], 'type': 'git', 'directory': self.dir2['id'], 'metadata': None, 'synthetic': False } self.revision3 = { 'id': hash_to_bytes('7026b7c1a2af56521e951c01ed20f255fa054238'), 'message': b'a simple revision with no parents this time', 'author': { 'name': b'Roberto Dicosmo', 'email': b'roberto@example.com', 'fullname': b'Roberto Dicosmo ', }, 'date': { 'timestamp': { 'seconds': 1234567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'committer_date': { 'timestamp': 1127351742, 'offset': 0, 'negative_utc': False, }, 'parents': [], 'type': 'git', 'directory': self.dir2['id'], 'metadata': None, 'synthetic': True } self.revision4 = { 'id': hash_to_bytes('368a48fe15b7db2383775f97c6b247011b3f14f4'), 'message': b'parent of self.revision2', 'author': { 'name': b'me', 'email': b'me@soft.heri', 'fullname': b'me ', }, 'date': { 'timestamp': { 'seconds': 1244567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'committer-dude', 'email': b'committer@dude.com', 'fullname': b'committer-dude ', }, 'committer_date': { 'timestamp': { 'seconds': 1244567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, '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.provider = { 'name': 'hal', 'type': 'deposit-client', 'url': 'http:///hal/inria', 'metadata': { 'location': 'France' } } self.metadata_tool = { 'name': 'swh-deposit', 'version': '0.0.1', 'configuration': { 'sword_version': '2' } } self.origin_metadata = { 'origin': self.origin, 'discovery_date': datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc), 'provider': self.provider, 'tool': 'swh-deposit', 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' } } self.origin_metadata2 = { 'origin': self.origin, 'discovery_date': datetime.datetime(2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc), 'provider': self.provider, 'tool': 'swh-deposit', 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' } } self.date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.date_visit2 = datetime.datetime(2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.date_visit3 = datetime.datetime(2018, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.release = { 'id': b'87659012345678901234', 'name': b'v0.0.1', 'author': { 'name': b'olasd', 'email': b'nic@olasd.fr', 'fullname': b'olasd ', }, 'date': { 'timestamp': 1234567890, 'offset': 42, 'negative_utc': None, }, 'target': b'43210987654321098765', 'target_type': 'revision', 'message': b'synthetic release', 'synthetic': True, } self.release2 = { 'id': b'56789012348765901234', 'name': b'v0.0.2', 'author': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'date': { 'timestamp': 1634366813, 'offset': -120, 'negative_utc': None, }, 'target': b'432109\xa9765432\xc309\x00765', 'target_type': 'revision', 'message': b'v0.0.2\nMisc performance improvements + bug fixes', 'synthetic': False } self.release3 = { 'id': b'87659012345678904321', 'name': b'v0.0.2', 'author': { 'name': b'tony', 'email': b'tony@ardumont.fr', 'fullname': b'tony ', }, 'date': { 'timestamp': 1634336813, 'offset': 0, 'negative_utc': False, }, 'target': self.revision2['id'], 'target_type': 'revision', 'message': b'yet another synthetic release', 'synthetic': True, } 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.snapshot = { 'id': hash_to_bytes('2498dbf535f882bc7f9a18fb16c9ad27fda7bab7'), 'branches': { b'master': { 'target': self.revision['id'], 'target_type': 'revision', }, }, 'next_branch': None } self.empty_snapshot = { 'id': hash_to_bytes('1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'), 'branches': {}, 'next_branch': None } self.complete_snapshot = { 'id': hash_to_bytes('6e65b86363953b780d92b0a928f3e8fcdd10db36'), 'branches': { b'directory': { 'target': hash_to_bytes( '1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8'), 'target_type': 'directory', }, b'content': { 'target': hash_to_bytes( 'fe95a46679d128ff167b7c55df5d02356c5a1ae1'), 'target_type': 'content', }, b'alias': { 'target': b'revision', 'target_type': 'alias', }, b'revision': { 'target': hash_to_bytes( 'aafb16d69fd30ff58afdd69036a26047f3aebdc6'), 'target_type': 'revision', }, b'release': { 'target': hash_to_bytes( '7045404f3d1c54e6473c71bbb716529fbad4be24'), 'target_type': 'release', }, b'snapshot': { 'target': hash_to_bytes( '1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'), 'target_type': 'snapshot', }, b'dangling': None, }, 'next_branch': None } def tearDown(self): self.reset_storage_tables() super().tearDown() class CommonTestStorage(BaseTestStorage): """Base class for Storage testing. This class is used as-is to test local storage (see TestLocalStorage 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. """ @staticmethod def normalize_entity(entity): entity = copy.deepcopy(entity) for key in ('date', 'committer_date'): if key in entity: entity[key] = identifiers.normalize_timestamp(entity[key]) return entity def test_check_config(self): self.assertTrue(self.storage.check_config(check_write=True)) self.assertTrue(self.storage.check_config(check_write=False)) def test_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')) def test_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]) def test_skipped_content_add(self): cont = self.skipped_cont.copy() cont2 = self.skipped_cont2.copy() cont2['blake2s256'] = None self.storage.content_add([cont, cont, cont2]) self.cursor.execute('SELECT sha1, sha1_git, sha256, blake2s256, ' 'length, status, reason ' 'FROM skipped_content ORDER BY sha1_git') datums = self.cursor.fetchall() self.assertEquals(2, len(datums)) datum = datums[0] self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3].tobytes(), datum[4], datum[5], datum[6]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['blake2s256'], cont['length'], 'absent', 'Content too long') ) datum2 = datums[1] self.assertEqual( (datum2[0].tobytes(), datum2[1].tobytes(), datum2[2].tobytes(), datum2[3], datum2[4], datum2[5], datum2[6]), (cont2['sha1'], cont2['sha1_git'], cont2['sha256'], cont2['blake2s256'], cont2['length'], 'absent', 'Content too long') ) def test_content_missing(self): cont2 = self.cont2 missing_cont = self.missing_cont self.storage.content_add([cont2]) test_contents = [cont2] missing_per_hash = defaultdict(list) for i in range(256): test_content = missing_cont.copy() for hash in ['sha1', 'sha256', 'sha1_git', 'blake2s256']: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_contents.append(test_content) self.assertCountEqual( self.storage.content_missing(test_contents), missing_per_hash['sha1'] ) for hash in ['sha1', 'sha256', 'sha1_git', 'blake2s256']: self.assertCountEqual( self.storage.content_missing(test_contents, key_hash=hash), missing_per_hash[hash] ) def test_content_missing_per_sha1(self): # given cont2 = self.cont2 missing_cont = self.missing_cont self.storage.content_add([cont2]) # when gen = self.storage.content_missing_per_sha1([cont2['sha1'], missing_cont['sha1']]) # then self.assertEqual(list(gen), [missing_cont['sha1']]) def test_content_get_metadata(self): cont1 = self.cont.copy() cont2 = self.cont2.copy() self.storage.content_add([cont1, cont2]) gen = self.storage.content_get_metadata([cont1['sha1'], cont2['sha1']]) # we only retrieve the metadata cont1.pop('data') cont2.pop('data') self.assertCountEqual(list(gen), [cont1, cont2]) def test_content_get_metadata_missing_sha1(self): cont1 = self.cont.copy() cont2 = self.cont2.copy() missing_cont = self.missing_cont.copy() self.storage.content_add([cont1, cont2]) gen = self.storage.content_get_metadata([missing_cont['sha1']]) # All the metadata keys are None missing_cont.pop('data') for key in list(missing_cont): if key != 'sha1': missing_cont[key] = None self.assertEqual(list(gen), [missing_cont]) def test_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_ls(self.dir['id'])) data_to_store = [] for ent in sorted(self.dir['entries'], key=itemgetter('name')): data_to_store.append({ '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, 'length': None, }) self.assertEqual(data_to_store, stored_data) after_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([], after_missing) def test_directory_entry_get_by_path(self): # given init_missing = list(self.storage.directory_missing([self.dir3['id']])) self.assertEqual([self.dir3['id']], init_missing) self.storage.directory_add([self.dir3]) expected_entries = [ { 'dir_id': self.dir3['id'], 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, { 'dir_id': self.dir3['id'], 'name': b'bar', 'type': 'dir', 'target': b'12345678901234560000', 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.directory, 'length': None, }, { 'dir_id': self.dir3['id'], 'name': b'hello', 'type': 'file', 'target': b'12345678901234567890', 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, ] # when (all must be found here) for entry, expected_entry in zip(self.dir3['entries'], expected_entries): actual_entry = self.storage.directory_entry_get_by_path( self.dir3['id'], [entry['name']]) self.assertEqual(actual_entry, expected_entry) # when (nothing should be found here since self.dir is not persisted.) for entry in self.dir['entries']: actual_entry = self.storage.directory_entry_get_by_path( self.dir['id'], [entry['name']]) self.assertIsNone(actual_entry) def test_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)) def test_revision_log(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) # when actual_results = list(self.storage.revision_log( [self.revision4['id']])) # hack: ids generated for actual_result in actual_results: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3 self.assertEquals(actual_results[0], self.normalize_entity(self.revision4)) self.assertEquals(actual_results[1], self.normalize_entity(self.revision3)) def test_revision_log_with_limit(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) actual_results = list(self.storage.revision_log( [self.revision4['id']], 1)) # hack: ids generated for actual_result in actual_results: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEqual(len(actual_results), 1) self.assertEquals(actual_results[0], self.revision4) @staticmethod def _short_revision(revision): return [revision['id'], revision['parents']] def test_revision_shortlog(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) # when actual_results = list(self.storage.revision_shortlog( [self.revision4['id']])) self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3 self.assertEquals(list(actual_results[0]), self._short_revision(self.revision4)) self.assertEquals(list(actual_results[1]), self._short_revision(self.revision3)) def test_revision_shortlog_with_limit(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) actual_results = list(self.storage.revision_shortlog( [self.revision4['id']], 1)) self.assertEqual(len(actual_results), 1) self.assertEquals(list(actual_results[0]), self._short_revision(self.revision4)) def test_revision_get(self): self.storage.revision_add([self.revision]) actual_revisions = list(self.storage.revision_get( [self.revision['id'], self.revision2['id']])) # when del actual_revisions[0]['author']['id'] # hack: ids are generated del actual_revisions[0]['committer']['id'] self.assertEqual(len(actual_revisions), 2) self.assertEqual(actual_revisions[0], self.normalize_entity(self.revision)) self.assertIsNone(actual_revisions[1]) def test_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 def test_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)) def test_release_get(self): # given self.storage.release_add([self.release, self.release2]) # when actual_releases = list(self.storage.release_get([self.release['id'], self.release2['id']])) # then for actual_release in actual_releases: del actual_release['author']['id'] # hack: ids are generated self.assertEquals([self.normalize_entity(self.release), self.normalize_entity(self.release2)], [actual_releases[0], actual_releases[1]]) def test_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) def test_origin_add(self): origin0 = self.storage.origin_get(self.origin) self.assertIsNone(origin0) origin1, origin2 = self.storage.origin_add([self.origin, self.origin2]) actual_origin = self.storage.origin_get({ 'url': self.origin['url'], 'type': self.origin['type'], }) self.assertEqual(actual_origin['id'], origin1['id']) actual_origin2 = self.storage.origin_get({ 'url': self.origin2['url'], 'type': self.origin2['type'], }) self.assertEqual(actual_origin2['id'], origin2['id']) def test_origin_add_twice(self): add1 = self.storage.origin_add([self.origin, self.origin2]) add2 = self.storage.origin_add([self.origin, self.origin2]) self.assertEqual(add1, add2) def test_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']}) def test_origin_search(self): found_origins = list(self.storage.origin_search(self.origin['url'])) self.assertEqual(len(found_origins), 0) found_origins = list(self.storage.origin_search(self.origin['url'], regexp=True)) self.assertEqual(len(found_origins), 0) id = self.storage.origin_add_one(self.origin) origin_data = {'id': id, 'type': self.origin['type'], 'url': self.origin['url']} found_origins = list(self.storage.origin_search(self.origin['url'])) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search( '.' + self.origin['url'][1:-1] + '.', regexp=True)) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) id2 = self.storage.origin_add_one(self.origin2) origin2_data = {'id': id2, 'type': self.origin2['type'], 'url': self.origin2['url']} found_origins = list(self.storage.origin_search(self.origin2['url'])) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) found_origins = list(self.storage.origin_search( '.' + self.origin2['url'][1:-1] + '.', regexp=True)) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) found_origins = list(self.storage.origin_search('/')) self.assertEqual(len(found_origins), 2) found_origins = list(self.storage.origin_search('.*/.*', regexp=True)) self.assertEqual(len(found_origins), 2) found_origins = list(self.storage.origin_search('/', offset=0, limit=1)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search('.*/.*', offset=0, limit=1, regexp=True)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search('/', offset=1, limit=1)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) found_origins = list(self.storage.origin_search('.*/.*', offset=1, limit=1, regexp=True)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) def test_origin_visit_add(self): # given self.assertIsNone(self.storage.origin_get(self.origin2)) origin_id = self.storage.origin_add_one(self.origin2) self.assertIsNotNone(origin_id) # when origin_visit1 = self.storage.origin_visit_add( origin_id, ts=self.date_visit2) # then self.assertEquals(origin_visit1['origin'], origin_id) self.assertIsNotNone(origin_visit1['visit']) self.assertTrue(origin_visit1['visit'] > 0) actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEquals(actual_origin_visits, [{ 'origin': origin_id, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) def test_origin_visit_update(self): # given origin_id = self.storage.origin_add_one(self.origin2) origin_id2 = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add( origin_id, ts=self.date_visit2) origin_visit2 = self.storage.origin_visit_add( origin_id, ts=self.date_visit3) origin_visit3 = self.storage.origin_visit_add( origin_id2, ts=self.date_visit3) # when visit1_metadata = { 'contents': 42, 'directories': 22, } self.storage.origin_visit_update( origin_id, origin_visit1['visit'], status='full', metadata=visit1_metadata) self.storage.origin_visit_update(origin_id2, origin_visit3['visit'], status='partial') # then actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEquals(actual_origin_visits, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }, { 'origin': origin_visit2['origin'], 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) actual_origin_visits_bis = list(self.storage.origin_visit_get( origin_id, limit=1)) self.assertEquals(actual_origin_visits_bis, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }]) actual_origin_visits_ter = list(self.storage.origin_visit_get( origin_id, last_visit=origin_visit1['visit'])) self.assertEquals(actual_origin_visits_ter, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) actual_origin_visits2 = list(self.storage.origin_visit_get(origin_id2)) self.assertEquals(actual_origin_visits2, [{ 'origin': origin_visit3['origin'], 'date': self.date_visit3, 'visit': origin_visit3['visit'], 'status': 'partial', 'metadata': None, 'snapshot': None, }]) def test_origin_visit_get_by(self): origin_id = self.storage.origin_add_one(self.origin2) origin_id2 = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add( origin_id, ts=self.date_visit2) self.storage.snapshot_add(origin_id, origin_visit1['visit'], self.snapshot) # Add some other {origin, visit} entries self.storage.origin_visit_add(origin_id, ts=self.date_visit3) self.storage.origin_visit_add(origin_id2, ts=self.date_visit3) # when visit1_metadata = { 'contents': 42, 'directories': 22, } self.storage.origin_visit_update( origin_id, origin_visit1['visit'], status='full', metadata=visit1_metadata) expected_origin_visit = origin_visit1.copy() expected_origin_visit.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], 'date': self.date_visit2, 'metadata': visit1_metadata, 'status': 'full', 'snapshot': self.snapshot['id'], }) # when actual_origin_visit1 = self.storage.origin_visit_get_by( origin_visit1['origin'], origin_visit1['visit']) # then self.assertEquals(actual_origin_visit1, expected_origin_visit) def test_origin_visit_get_by_no_result(self): # No result actual_origin_visit = self.storage.origin_visit_get_by( 10, 999) self.assertIsNone(actual_origin_visit) def test_snapshot_add_get_empty(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.empty_snapshot) by_id = self.storage.snapshot_get(self.empty_snapshot['id']) self.assertEqual(by_id, self.empty_snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.empty_snapshot) def test_snapshot_add_get_complete(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) by_id = self.storage.snapshot_get(self.complete_snapshot['id']) self.assertEqual(by_id, self.complete_snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.complete_snapshot) def test_snapshot_add_count_branches(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) snp_id = self.complete_snapshot['id'] snp_size = self.storage.snapshot_count_branches(snp_id) expected_snp_size = { 'alias': 1, 'content': 1, 'directory': 1, 'release': 1, 'revision': 1, 'snapshot': 1, None: 1 } self.assertEqual(snp_size, expected_snp_size) def test_snapshot_add_get_paginated(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) snp_id = self.complete_snapshot['id'] + branches = self.complete_snapshot['branches'] + branch_names = list(sorted(branches)) snapshot = self.storage.snapshot_get_branches(snp_id, branches_from=b'release') - expected_snapshot = copy.deepcopy(self.complete_snapshot) - del expected_snapshot['next_branch'] - for name in [b'alias', b'content', b'dangling', b'directory']: - del expected_snapshot['branches'][name] + rel_idx = branch_names.index(b'release') + expected_snapshot = { + 'id': snp_id, + 'branches': { + name: branches[name] + for name in branch_names[rel_idx:] + }, + 'next_branch': None, + } self.assertEqual(snapshot, expected_snapshot) snapshot = self.storage.snapshot_get_branches(snp_id, branches_count=1) - expected_snapshot = copy.deepcopy(self.complete_snapshot) - del expected_snapshot['next_branch'] - for name in [b'content', b'dangling', b'directory', - b'release', b'revision', b'snapshot']: - del expected_snapshot['branches'][name] - + expected_snapshot = { + 'id': snp_id, + 'branches': { + branch_names[0]: branches[branch_names[0]], + }, + 'next_branch': b'content', + } self.assertEqual(snapshot, expected_snapshot) snapshot = self.storage.snapshot_get_branches( snp_id, branches_from=b'directory', branches_count=3) - expected_snapshot = copy.deepcopy(self.complete_snapshot) - del expected_snapshot['next_branch'] - for name in [b'alias', b'content', b'dangling', b'snapshot']: - del expected_snapshot['branches'][name] + dir_idx = branch_names.index(b'directory') + expected_snapshot = { + 'id': snp_id, + 'branches': { + name: branches[name] + for name in branch_names[dir_idx:dir_idx + 3] + }, + 'next_branch': branch_names[dir_idx + 3], + } self.assertEqual(snapshot, expected_snapshot) def test_snapshot_add_get_filtered(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) snp_id = self.complete_snapshot['id'] + branches = self.complete_snapshot['branches'] snapshot = self.storage.snapshot_get_branches( snp_id, target_types=['release', 'revision']) - expected_snapshot = copy.deepcopy(self.complete_snapshot) - del expected_snapshot['next_branch'] - for name in [b'alias', b'content', b'dangling', b'directory', - b'snapshot']: - del expected_snapshot['branches'][name] + expected_snapshot = { + 'id': snp_id, + 'branches': { + name: tgt + for name, tgt in branches.items() + if tgt and tgt['target_type'] in ['release', 'revision'] + }, + 'next_branch': None, + } self.assertEqual(snapshot, expected_snapshot) snapshot = self.storage.snapshot_get_branches(snp_id, target_types=['alias']) - expected_snapshot = copy.deepcopy(self.complete_snapshot) - del expected_snapshot['next_branch'] - for name in [b'content', b'dangling', b'directory', b'release', - b'revision', b'snapshot']: - del expected_snapshot['branches'][name] + expected_snapshot = { + 'id': snp_id, + 'branches': { + name: tgt + for name, tgt in branches.items() + if tgt and tgt['target_type'] == 'alias' + }, + 'next_branch': None, + } self.assertEqual(snapshot, expected_snapshot) def test_snapshot_add_get(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.snapshot) by_id = self.storage.snapshot_get(self.snapshot['id']) self.assertEqual(by_id, self.snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.snapshot) origin_visit_info = self.storage.origin_visit_get_by(origin_id, visit_id) self.assertEqual(origin_visit_info['snapshot'], self.snapshot['id']) def test_snapshot_add_twice(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit1_id, self.snapshot) by_ov1 = self.storage.snapshot_get_by_origin_visit(origin_id, visit1_id) self.assertEqual(by_ov1, self.snapshot) origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] self.storage.snapshot_add(origin_id, visit2_id, self.snapshot) by_ov2 = self.storage.snapshot_get_by_origin_visit(origin_id, visit2_id) self.assertEqual(by_ov2, self.snapshot) def test_snapshot_get_nonexistent(self): bogus_snapshot_id = b'bogus snapshot id 00' bogus_origin_id = 1 bogus_visit_id = 1 by_id = self.storage.snapshot_get(bogus_snapshot_id) self.assertIsNone(by_id) by_ov = self.storage.snapshot_get_by_origin_visit(bogus_origin_id, bogus_visit_id) self.assertIsNone(by_ov) def test_snapshot_get_latest(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] # Two visits, both with no snapshot: latest snapshot is None self.assertIsNone(self.storage.snapshot_get_latest(origin_id)) # Add snapshot to visit1, latest snapshot = visit 1 snapshot self.storage.snapshot_add(origin_id, visit1_id, self.complete_snapshot) self.assertEquals(self.complete_snapshot, self.storage.snapshot_get_latest(origin_id)) # Status filter: both visits are status=ongoing, so no snapshot # returned self.assertIsNone( self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']) ) # Mark the first visit as completed and check status filter again self.storage.origin_visit_update(origin_id, visit1_id, status='full') self.assertEquals( self.complete_snapshot, self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']), ) # Add snapshot to visit2 and check that the new snapshot is returned self.storage.snapshot_add(origin_id, visit2_id, self.empty_snapshot) self.assertEquals(self.empty_snapshot, self.storage.snapshot_get_latest(origin_id)) # Check that the status filter is still working self.assertEquals( self.complete_snapshot, self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']), ) def test_stat_counters(self): expected_keys = ['content', 'directory', 'directory_entry_dir', 'origin', 'person', 'revision'] for key in expected_keys: self.cursor.execute('select * from swh_update_counter(%s)', (key,)) self.conn.commit() counters = self.storage.stat_counters() self.assertTrue(set(expected_keys) <= set(counters)) self.assertIsInstance(counters[expected_keys[0]], int) def test_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'], 'blake2s256': cont['blake2s256'], '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'], 'blake2s256': cont['blake2s256'], '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'], 'blake2s256': cont['blake2s256'], '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'], 'blake2s256': cont['blake2s256'], }) actually_present.pop('ctime') self.assertEqual(actually_present, { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' }) def test_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) def test_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 def test_object_find_by_sha1_git(self): sha1_gits = [b'00000000000000000000'] expected = { b'00000000000000000000': [], } self.storage.content_add([self.cont]) sha1_gits.append(self.cont['sha1_git']) expected[self.cont['sha1_git']] = [{ 'sha1_git': self.cont['sha1_git'], 'type': 'content', 'id': self.cont['sha1'], }] self.storage.directory_add([self.dir]) sha1_gits.append(self.dir['id']) expected[self.dir['id']] = [{ 'sha1_git': self.dir['id'], 'type': 'directory', 'id': self.dir['id'], }] self.storage.revision_add([self.revision]) sha1_gits.append(self.revision['id']) expected[self.revision['id']] = [{ 'sha1_git': self.revision['id'], 'type': 'revision', 'id': self.revision['id'], }] self.storage.release_add([self.release]) sha1_gits.append(self.release['id']) expected[self.release['id']] = [{ 'sha1_git': self.release['id'], 'type': 'release', 'id': self.release['id'], }] ret = self.storage.object_find_by_sha1_git(sha1_gits) for val in ret.values(): for obj in val: del obj['object_id'] self.assertEqual(expected, ret) def test_tool_add(self): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) # does not exist # add it actual_tools = list(self.storage.tool_add([tool])) self.assertEquals(len(actual_tools), 1) actual_tool = actual_tools[0] self.assertIsNotNone(actual_tool) # now it exists new_id = actual_tool.pop('id') self.assertEquals(actual_tool, tool) actual_tools2 = list(self.storage.tool_add([tool])) actual_tool2 = actual_tools2[0] self.assertIsNotNone(actual_tool2) # now it exists new_id2 = actual_tool2.pop('id') self.assertEqual(new_id, new_id2) self.assertEqual(actual_tool, actual_tool2) def test_tool_add_multiple(self): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tools = list(self.storage.tool_add([tool])) self.assertEqual(len(actual_tools), 1) new_tools = [tool, { 'name': 'yet-another-tool', 'version': 'version', 'configuration': {}, }] actual_tools = list(self.storage.tool_add(new_tools)) self.assertEqual(len(actual_tools), 2) # order not guaranteed, so we iterate over results to check for tool in actual_tools: _id = tool.pop('id') self.assertIsNotNone(_id) self.assertIn(tool, new_tools) def test_tool_get_missing(self): tool = { 'name': 'unknown-tool', 'version': '3.1.0rc2-31-ga2cbb8c', 'configuration': {"command_line": "nomossa "}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) def test_tool_metadata_get_missing_context(self): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"context": "unknown-context"}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) def test_tool_metadata_get(self): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"type": "local", "context": "npm"}, } tools = list(self.storage.tool_add([tool])) expected_tool = tools[0] # when actual_tool = self.storage.tool_get(tool) # then self.assertEqual(expected_tool, actual_tool) def test_metadata_provider_get_by(self): # given no_provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) self.assertIsNone(no_provider) # when provider_id = self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) actual_provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) # then self.assertTrue(provider_id, actual_provider['id']) def test_origin_metadata_add(self): # given origin_id = self.storage.origin_add([self.origin])[0]['id'] origin_metadata0 = list(self.storage.origin_metadata_get_by(origin_id)) self.assertTrue(len(origin_metadata0) == 0) tools = list(self.storage.tool_add([self.metadata_tool])) tool = tools[0] self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) tool = self.storage.tool_get(self.metadata_tool) # when adding for the same origin 2 metadatas o_m1 = self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider['id'], tool['id'], self.origin_metadata['metadata']) actual_om1 = list(self.storage.origin_metadata_get_by(origin_id)) # then self.assertEqual(actual_om1[0]['id'], o_m1) self.assertEqual(len(actual_om1), 1) self.assertEqual(actual_om1[0]['origin_id'], origin_id) def test_origin_metadata_get(self): # given origin_id = self.storage.origin_add([self.origin])[0]['id'] origin_id2 = self.storage.origin_add([self.origin2])[0]['id'] self.storage.metadata_provider_add(self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) tool = self.storage.tool_get(self.metadata_tool) # when adding for the same origin 2 metadatas o_m1 = self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider['id'], tool['id'], self.origin_metadata['metadata']) o_m2 = self.storage.origin_metadata_add( origin_id2, self.origin_metadata2['discovery_date'], provider['id'], tool['id'], self.origin_metadata2['metadata']) o_m3 = self.storage.origin_metadata_add( origin_id, self.origin_metadata2['discovery_date'], provider['id'], tool['id'], self.origin_metadata2['metadata']) all_metadatas = list(self.storage.origin_metadata_get_by(origin_id)) metadatas_for_origin2 = list(self.storage.origin_metadata_get_by( origin_id2)) expected_results = [{ 'origin_id': origin_id, 'discovery_date': datetime.datetime( 2017, 1, 2, 0, 0, tzinfo=psycopg2.tz.FixedOffsetTimezone( offset=60, name=None)), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'id': o_m3, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }, { 'origin_id': origin_id, 'discovery_date': datetime.datetime( 2015, 1, 2, 0, 0, tzinfo=psycopg2.tz.FixedOffsetTimezone( offset=60, name=None)), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'id': o_m1, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }] # then self.assertEqual(len(all_metadatas), 2) self.assertEqual(len(metadatas_for_origin2), 1) self.assertEqual(metadatas_for_origin2[0]['id'], o_m2) self.assertEqual(all_metadatas, expected_results) def test_origin_metadata_get_by_provider_type(self): # given origin_id = self.storage.origin_add([self.origin])[0]['id'] origin_id2 = self.storage.origin_add([self.origin2])[0]['id'] self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider1 = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) self.storage.metadata_provider_add( 'swMATH', 'registry', 'http://www.swmath.org/', {'email': 'contact@swmath.org', 'license': 'All rights reserved'}) provider2 = self.storage.metadata_provider_get_by({ 'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/' }) # using the only tool now inserted in the data.sql, but for this # provider should be a crawler tool (not yet implemented) tool = self.storage.tool_get(self.metadata_tool) # when adding for the same origin 2 metadatas o_m1 = self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider1['id'], tool['id'], self.origin_metadata['metadata']) o_m2 = self.storage.origin_metadata_add( origin_id2, self.origin_metadata2['discovery_date'], provider2['id'], tool['id'], self.origin_metadata2['metadata']) provider_type = 'registry' m_by_provider = list(self.storage. origin_metadata_get_by( origin_id2, provider_type)) expected_results = [{ 'origin_id': origin_id2, 'discovery_date': datetime.datetime( 2017, 1, 2, 0, 0, tzinfo=psycopg2.tz.FixedOffsetTimezone( offset=60, name=None)), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'id': o_m2, 'provider_id': provider2['id'], 'provider_name': 'swMATH', 'provider_type': provider_type, 'provider_url': 'http://www.swmath.org/', 'tool_id': tool['id'] }] # then self.assertEqual(len(m_by_provider), 1) self.assertEqual(m_by_provider, expected_results) self.assertEqual(m_by_provider[0]['id'], o_m2) self.assertIsNotNone(o_m1) class TestLocalStorage(CommonTestStorage, unittest.TestCase): """Test the local storage""" # Can only be tested with local storage as you can't mock # datetimes for the remote server def test_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) # The remote API doesn't expose _person_add def test_person_get(self): # given person0 = { 'fullname': b'bob ', 'name': b'bob', 'email': b'alice@bob', } id0 = self.storage._person_add(person0) person1 = { 'fullname': b'tony ', '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, 'fullname': person0['fullname'], 'name': person0['name'], 'email': person0['email'], }, { 'id': id1, 'fullname': person1['fullname'], 'name': person1['name'], 'email': person1['email'], }, ]) # This test is only relevant on the local storage, with an actual # objstorage raising an exception def test_content_add_objstorage_exception(self): self.storage.objstorage.add = Mock( side_effect=Exception('mocked broken objstorage') ) with self.assertRaises(Exception) as e: self.storage.content_add([self.cont]) self.assertEqual(e.exception.args, ('mocked broken objstorage',)) missing = list(self.storage.content_missing([self.cont])) self.assertEqual(missing, [self.cont['sha1']]) class AlteringSchemaTest(BaseTestStorage, unittest.TestCase): """This class is dedicated for the rare case where the schema needs to be altered dynamically. Otherwise, the tests could be blocking when ran altogether. """ def test_content_update(self): cont = copy.deepcopy(self.cont) self.storage.content_add([cont]) # alter the sha1_git for example cont['sha1_git'] = hash_to_bytes( '3a60a5275d0333bf13468e8b3dcab90f4046e654') self.storage.content_update([cont], keys=['sha1_git']) with self.storage.get_db().transaction() as cur: cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.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')) def test_content_update_with_new_cols(self): with self.storage.get_db().transaction() as cur: cur.execute("""alter table content add column test text default null, add column test2 text default null""") cont = copy.deepcopy(self.cont2) self.storage.content_add([cont]) cont['test'] = 'value-1' cont['test2'] = 'value-2' self.storage.content_update([cont], keys=['test', 'test2']) with self.storage.get_db().transaction() as cur: cur.execute( 'SELECT sha1, sha1_git, sha256, length, status, test, test2' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4], datum[5], datum[6]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible', cont['test'], cont['test2'])) with self.storage.get_db().transaction() as cur: cur.execute("""alter table content drop column test, drop column test2""") diff --git a/version.txt b/version.txt index 969c2f5a9..1cea4f661 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -v0.0.107-0-g2d5efac \ No newline at end of file +v0.0.108-0-gd211615 \ No newline at end of file