diff --git a/PKG-INFO b/PKG-INFO index b2c2a7a9..aa010bce 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,224 +1,224 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.27.1 +Version: 0.27.2 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 Project-URL: Documentation, https://docs.softwareheritage.org/devel/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. ## Quick start ### Dependencies Python tests for this module include tests that cannot be run without a local Postgresql database, so you need the Postgresql server executable on your machine (no need to have a running Postgresql server). They also expect a cassandra server. #### Debian-like host ``` $ sudo apt install libpq-dev postgresql-11 cassandra ``` #### Non Debian-like host The tests expects the path to `cassandra` to either be unspecified, it is then looked up at `/usr/sbin/cassandra`, either specified through the environment variable `SWH_CASSANDRA_BIN`. Optionally, you can avoid running the cassandra tests. ``` (swh) :~/swh-storage$ tox -- -m 'not cassandra' ``` ### Installation It is strongly recommended to use a virtualenv. In the following, we consider you work in a virtualenv named `swh`. See the [developer setup guide](https://docs.softwareheritage.org/devel/developer-setup.html#developer-setup) for a more details on how to setup a working environment. You can install the package directly from [pypi](https://pypi.org/p/swh.storage): ``` (swh) :~$ pip install swh.storage [...] ``` Or from sources: ``` (swh) :~$ git clone https://forge.softwareheritage.org/source/swh-storage.git [...] (swh) :~$ cd swh-storage (swh) :~/swh-storage$ pip install . [...] ``` Then you can check it's properly installed: ``` (swh) :~$ swh storage --help Usage: swh storage [OPTIONS] COMMAND [ARGS]... Software Heritage Storage tools. Options: -h, --help Show this message and exit. Commands: rpc-serve Software Heritage Storage RPC server. ``` ## Tests The best way of running Python tests for this module is to use [tox](https://tox.readthedocs.io/). ``` (swh) :~$ pip install tox ``` ### tox From the sources directory, simply use tox: ``` (swh) :~/swh-storage$ tox [...] ========= 315 passed, 6 skipped, 15 warnings in 40.86 seconds ========== _______________________________ summary ________________________________ flake8: commands succeeded py3: commands succeeded congratulations :) ``` Note: it is possible to set the `JAVA_HOME` environment variable to specify the version of the JVM to be used by Cassandra. For example, at the time of writing this, Cassandra does not support java 14, so one may want to use for example java 11: ``` (swh) :~/swh-storage$ export JAVA_HOME=/usr/lib/jvm/java-14-openjdk-amd64/bin/java (swh) :~/swh-storage$ tox [...] ``` ## Development The storage server can be locally started. It requires a configuration file and a running Postgresql database. ### Sample configuration A typical configuration `storage.yml` file is: ``` storage: cls: local db: "dbname=softwareheritage-dev user= password=" objstorage: cls: pathslicing root: /tmp/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 /tmp/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 before starting the server. ### Starting the storage server If the python package has been properly installed (e.g. in a virtual env), you should be able to use the command: ``` (swh) :~/swh-storage$ swh storage rpc-serve storage.yml ``` This runs a local swh-storage api at 5002 port. ``` (swh) :~/swh-storage$ curl http://127.0.0.1:5002 Software Heritage storage server

You have reached the Software Heritage storage server.
See its documentation and API for more information

``` ### And then what? In your upper layer ([loader-git](https://forge.softwareheritage.org/source/swh-loader-git/), [loader-svn](https://forge.softwareheritage.org/source/swh-loader-svn/), etc...), you can define a remote storage with this snippet of yaml configuration. ``` storage: cls: remote url: http://localhost:5002/ ``` You could directly define a local storage with the following snippet: ``` storage: cls: local db: service=swh-dev objstorage: cls: pathslicing 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 Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: testing Provides-Extra: schemata Provides-Extra: journal diff --git a/swh.storage.egg-info/PKG-INFO b/swh.storage.egg-info/PKG-INFO index b2c2a7a9..aa010bce 100644 --- a/swh.storage.egg-info/PKG-INFO +++ b/swh.storage.egg-info/PKG-INFO @@ -1,224 +1,224 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.27.1 +Version: 0.27.2 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 Project-URL: Documentation, https://docs.softwareheritage.org/devel/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. ## Quick start ### Dependencies Python tests for this module include tests that cannot be run without a local Postgresql database, so you need the Postgresql server executable on your machine (no need to have a running Postgresql server). They also expect a cassandra server. #### Debian-like host ``` $ sudo apt install libpq-dev postgresql-11 cassandra ``` #### Non Debian-like host The tests expects the path to `cassandra` to either be unspecified, it is then looked up at `/usr/sbin/cassandra`, either specified through the environment variable `SWH_CASSANDRA_BIN`. Optionally, you can avoid running the cassandra tests. ``` (swh) :~/swh-storage$ tox -- -m 'not cassandra' ``` ### Installation It is strongly recommended to use a virtualenv. In the following, we consider you work in a virtualenv named `swh`. See the [developer setup guide](https://docs.softwareheritage.org/devel/developer-setup.html#developer-setup) for a more details on how to setup a working environment. You can install the package directly from [pypi](https://pypi.org/p/swh.storage): ``` (swh) :~$ pip install swh.storage [...] ``` Or from sources: ``` (swh) :~$ git clone https://forge.softwareheritage.org/source/swh-storage.git [...] (swh) :~$ cd swh-storage (swh) :~/swh-storage$ pip install . [...] ``` Then you can check it's properly installed: ``` (swh) :~$ swh storage --help Usage: swh storage [OPTIONS] COMMAND [ARGS]... Software Heritage Storage tools. Options: -h, --help Show this message and exit. Commands: rpc-serve Software Heritage Storage RPC server. ``` ## Tests The best way of running Python tests for this module is to use [tox](https://tox.readthedocs.io/). ``` (swh) :~$ pip install tox ``` ### tox From the sources directory, simply use tox: ``` (swh) :~/swh-storage$ tox [...] ========= 315 passed, 6 skipped, 15 warnings in 40.86 seconds ========== _______________________________ summary ________________________________ flake8: commands succeeded py3: commands succeeded congratulations :) ``` Note: it is possible to set the `JAVA_HOME` environment variable to specify the version of the JVM to be used by Cassandra. For example, at the time of writing this, Cassandra does not support java 14, so one may want to use for example java 11: ``` (swh) :~/swh-storage$ export JAVA_HOME=/usr/lib/jvm/java-14-openjdk-amd64/bin/java (swh) :~/swh-storage$ tox [...] ``` ## Development The storage server can be locally started. It requires a configuration file and a running Postgresql database. ### Sample configuration A typical configuration `storage.yml` file is: ``` storage: cls: local db: "dbname=softwareheritage-dev user= password=" objstorage: cls: pathslicing root: /tmp/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 /tmp/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 before starting the server. ### Starting the storage server If the python package has been properly installed (e.g. in a virtual env), you should be able to use the command: ``` (swh) :~/swh-storage$ swh storage rpc-serve storage.yml ``` This runs a local swh-storage api at 5002 port. ``` (swh) :~/swh-storage$ curl http://127.0.0.1:5002 Software Heritage storage server

You have reached the Software Heritage storage server.
See its documentation and API for more information

``` ### And then what? In your upper layer ([loader-git](https://forge.softwareheritage.org/source/swh-loader-git/), [loader-svn](https://forge.softwareheritage.org/source/swh-loader-svn/), etc...), you can define a remote storage with this snippet of yaml configuration. ``` storage: cls: remote url: http://localhost:5002/ ``` You could directly define a local storage with the following snippet: ``` storage: cls: local db: service=swh-dev objstorage: cls: pathslicing 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 Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: testing Provides-Extra: schemata Provides-Extra: journal diff --git a/swh/storage/migrate_extrinsic_metadata.py b/swh/storage/migrate_extrinsic_metadata.py index f5a4a566..4b9bdd4e 100644 --- a/swh/storage/migrate_extrinsic_metadata.py +++ b/swh/storage/migrate_extrinsic_metadata.py @@ -1,1204 +1,1204 @@ #!/usr/bin/env python3 # Copyright (C) 2020 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 """This is an executable script to migrate extrinsic revision metadata from the revision table to the new extrinsic metadata storage. This is designed to be as conservative as possible, following this principle: for each revision the script reads (in "handle_row"), it will read some of the fields, write them directly to the metadata storage, and remove them. Then it checks all the remaining fields are in a hardcoded list of fields that are known not to require migration. This means that every field that isn't migrated was explicitly reviewed while writing this script. Additionally, this script contains many assertions to prevent false positives in its heuristics. """ import datetime import hashlib import json import os import re import sys import time from typing import Any, Dict, Optional from urllib.error import HTTPError from urllib.parse import unquote, urlparse from urllib.request import urlopen import iso8601 import psycopg2 from swh.core.db import BaseDb from swh.model.hashutil import hash_to_hex from swh.model.identifiers import ( CoreSWHID, ExtendedObjectType, ExtendedSWHID, ObjectType, QualifiedSWHID, ) from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, RawExtrinsicMetadata, Sha1Git, ) from swh.storage import get_storage from swh.storage.algos.origin import iter_origin_visit_statuses, iter_origin_visits from swh.storage.algos.snapshot import snapshot_get_all_branches # XML namespaces and fields for metadata coming from the deposit: CODEMETA_NS = "https://doi.org/10.5063/SCHEMA/CODEMETA-2.0" ATOM_NS = "http://www.w3.org/2005/Atom" ATOM_KEYS = ["id", "author", "external_identifier", "title"] # columns of the revision table (of the storage DB) REVISION_COLS = [ "id", "directory", "date", "committer_date", "type", "message", "metadata", ] # columns of the tables of the deposit DB DEPOSIT_COLS = [ "deposit.id", "deposit.external_id", "deposit.swhid_context", "deposit.status", "deposit_request.metadata", "deposit_request.date", "deposit_client.provider_url", "deposit_collection.name", "auth_user.username", ] # Formats we write to the extrinsic metadata storage OLD_DEPOSIT_FORMAT = ( "sword-v2-atom-codemeta-v2-in-json-with-expanded-namespaces" # before february 2018 ) NEW_DEPOSIT_FORMAT = "sword-v2-atom-codemeta-v2-in-json" # after february 2018 GNU_FORMAT = "gnu-tree-json" NIXGUIX_FORMAT = "nixguix-sources-json" NPM_FORMAT = "replicate-npm-package-json" ORIGINAL_ARTIFACT_FORMAT = "original-artifacts-json" PYPI_FORMAT = "pypi-project-json" # Information about this script, for traceability FETCHER = MetadataFetcher( name="migrate-extrinsic-metadata-from-revisions", version="0.0.1", ) # Authorities that we got the metadata from AUTHORITIES = { "npmjs": MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://npmjs.com/", metadata={} ), "pypi": MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://pypi.org/", metadata={} ), "gnu": MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://ftp.gnu.org/", metadata={} ), "swh": MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", metadata={}, ), # for original_artifact (which are checksums computed by SWH) } # Regular expression for the format of revision messages written by the # deposit loader deposit_revision_message_re = re.compile( b"(?P[a-z-]*): " b"Deposit (?P[0-9]+) in collection (?P[a-z-]+).*" ) # not reliable, because PyPI allows arbitrary names def pypi_project_from_filename(filename): original_filename = filename if filename.endswith(".egg"): return None elif filename == "mongomotor-0.13.0.n.tar.gz": return "mongomotor" elif re.match(r"datahaven-rev[0-9]+\.tar\.gz", filename): return "datahaven" elif re.match(r"Dtls-[0-9]\.[0-9]\.[0-9]\.sdist_with_openssl\..*", filename): return "Dtls" elif re.match(r"(gae)?pytz-20[0-9][0-9][a-z]\.(tar\.gz|zip)", filename): return filename.split("-", 1)[0] elif filename.startswith(("powny-", "obedient.powny-",)): return filename.split("-")[0] elif filename.startswith("devpi-theme-16-"): return "devpi-theme-16" elif re.match("[^-]+-[0-9]+.tar.gz", filename): return filename.split("-")[0] elif filename == "ohai-1!0.tar.gz": return "ohai" elif filename == "collective.topicitemsevent-0.1dvl.tar.gz": return "collective.topicitemsevent" elif filename.startswith( ("SpiNNStorageHandlers-1!", "sPyNNakerExternalDevicesPlugin-1!") ): return filename.split("-")[0] elif filename.startswith("limnoria-201"): return "limnoria" elif filename.startswith("pytz-20"): return "pytz" elif filename.startswith("youtube_dl_server-alpha."): return "youtube_dl_server" elif filename == "json-extensions-b76bc7d.tar.gz": return "json-extensions" elif filename == "LitReview-0.6989ev.tar.gz": # typo of "dev" return "LitReview" elif filename.startswith("django_options-r"): return "django_options" elif filename == "Greater than, equal, or less Library-0.1.tar.gz": return "Greater-than-equal-or-less-Library" elif filename.startswith("upstart--main-"): return "upstart" elif filename == "duckduckpy0.1.tar.gz": return "duckduckpy" elif filename == "QUI for MPlayer snapshot_9-14-2011.zip": return "QUI-for-MPlayer" elif filename == "Eddy's Memory Game-1.0.zip": return "Eddy-s-Memory-Game" elif filename == "jekyll2nikola-0-0-1.tar.gz": return "jekyll2nikola" elif filename.startswith("ore.workflowed"): return "ore.workflowed" elif re.match("instancemanager-[0-9]*", filename): return "instancemanager" elif filename == "OrzMC_W&L-1.0.0.tar.gz": return "OrzMC-W-L" elif filename == "use0mk.tar.gz": return "use0mk" elif filename == "play-0-develop-1-gd67cd85.tar.gz": return "play" filename = filename.replace(" ", "-") match = re.match( r"^(?P[a-z_.-]+)" # project name r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension filename, re.I, ) if match: return match.group("project_name") # First try with a rather strict format, but that allows accidentally # matching the version as part of the package name match = re.match( r"^(?P[a-z0-9_.]+?([-_][a-z][a-z0-9.]+?)*?)" # project name r"-v?" r"([0-9]+!)?" # epoch r"[0-9_.]+([a-z]+[0-9]+)?" # "main" version r"([.-]?(alpha|beta|dev|post|pre|rc)(\.?[0-9]+)?)*" # development status r"([.-]?20[012][0-9]{5,9})?" # date r"([.-]g?[0-9a-f]+)?" # git commit r"([-+]py(thon)?(3k|[23](\.?[0-9]{1,2})?))?" # python version r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension filename, re.I, ) if match: return match.group("project_name") # If that doesn't work, give up on trying to parse version suffixes, # and just find the first version-like occurrence in the file name match = re.match( r"^(?P[a-z0-9_.-]+?)" # project name r"[-_.]v?" r"([0-9]+!)?" # epoch r"(" # "main" version r"[0-9_]+\.[0-9_.]+([a-z]+[0-9]+)?" # classic version number r"|20[012][0-9]{5,9}" # date as integer r"|20[012][0-9]-[01][0-9]-[0-3][0-9]" # date as ISO 8601 r")" # end of "main" version r"[a-z]?(dev|pre)?" # direct version suffix r"([._-].*)?" # extra suffixes r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension filename, re.I, ) if match: return match.group("project_name") # If that still doesn't work, give one last chance if there's only one # dash or underscore in the name match = re.match( r"^(?P[^_-]+)" # project name r"[_-][^_-]+" # version r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension filename, ) assert match, original_filename return match.group("project_name") def pypi_origin_from_project_name(project_name: str) -> str: return f"https://pypi.org/project/{project_name}/" def pypi_origin_from_filename(storage, rev_id: bytes, filename: str) -> Optional[str]: project_name = pypi_project_from_filename(filename) origin = pypi_origin_from_project_name(project_name) # But unfortunately, the filename is user-provided, and doesn't # necessarily match the package name on pypi. Therefore, we need # to check it. if _check_revision_in_origin(storage, origin, rev_id): return origin # if the origin we guessed does not exist, query the PyPI API with the # project name we guessed. If only the capitalisation and dash/underscores # are wrong (by far the most common case), PyPI kindly corrects them. try: resp = urlopen(f"https://pypi.org/pypi/{project_name}/json/") except HTTPError as e: assert e.code == 404 # nope; PyPI couldn't correct the wrong project name return None assert resp.code == 200, resp.code project_name = json.load(resp)["info"]["name"] origin = pypi_origin_from_project_name(project_name) if _check_revision_in_origin(storage, origin, rev_id): return origin else: # The origin exists, but the revision does not belong in it. # This happens sometimes, as the filename we guessed the origin # from is user-provided. return None def cran_package_from_url(filename): match = re.match( r"^https://cran\.r-project\.org/src/contrib/" r"(?P[a-zA-Z0-9.]+)_[0-9.-]+(\.tar\.gz)?$", filename, ) assert match, filename return match.group("package_name") def npm_package_from_source_url(package_source_url): match = re.match( "^https://registry.npmjs.org/(?P.*)/-/[^/]+.tgz$", package_source_url, ) assert match, package_source_url return unquote(match.group("package_name")) def remove_atom_codemeta_metadata_with_xmlns(metadata): """Removes all known Atom and Codemeta metadata fields from the dict, assuming this is a dict generated by xmltodict without expanding namespaces. """ keys_to_remove = ATOM_KEYS + ["@xmlns", "@xmlns:codemeta"] for key in list(metadata): if key.startswith("codemeta:") or key in keys_to_remove: del metadata[key] def remove_atom_codemeta_metadata_without_xmlns(metadata): """Removes all known Atom and Codemeta metadata fields from the dict, assuming this is a dict generated by xmltodict with expanded namespaces. """ for key in list(metadata): if key.startswith(("{%s}" % ATOM_NS, "{%s}" % CODEMETA_NS)): del metadata[key] def _check_revision_in_origin(storage, origin, revision_id): seen_snapshots = set() # no need to visit them again seen_revisions = set() for visit in iter_origin_visits(storage, origin): for status in iter_origin_visit_statuses(storage, origin, visit.visit): if status.snapshot is None: continue if status.snapshot in seen_snapshots: continue seen_snapshots.add(status.snapshot) snapshot = snapshot_get_all_branches(storage, status.snapshot) for (branch_name, branch) in snapshot.branches.items(): if branch is None: continue # If it's the revision passed as argument, then it is indeed in the # origin if branch.target == revision_id: return True # Else, let's make sure the branch doesn't have any other revision # Get the revision at the top of the branch. if branch.target in seen_revisions: continue seen_revisions.add(branch.target) revision = storage.revision_get([branch.target])[0] if revision is None: # https://forge.softwareheritage.org/T997 continue # Check it doesn't have parents (else we would have to # recurse) assert revision.parents == (), "revision with parents" return False def debian_origins_from_row(row, storage): """Guesses a Debian origin from a row. May return an empty list if it cannot reliably guess it, but all results are guaranteed to be correct.""" filenames = [entry["filename"] for entry in row["metadata"]["original_artifact"]] package_names = {filename.split("_")[0] for filename in filenames} assert len(package_names) == 1, package_names (package_name,) = package_names candidate_origins = [ f"deb://Debian/packages/{package_name}", f"deb://Debian-Security/packages/{package_name}", f"http://snapshot.debian.org/package/{package_name}/", ] return [ origin for origin in candidate_origins if _check_revision_in_origin(storage, origin, row["id"]) ] # Cache of origins that are known to exist _origins = set() def assert_origin_exists(storage, origin): assert check_origin_exists(storage, origin), origin def check_origin_exists(storage, origin): return ( ( hashlib.sha1(origin.encode()).digest() in _origins # very fast or storage.origin_get([origin])[0] is not None # slow, but up to date ), origin, ) def load_metadata( storage, revision_id, directory_id, discovery_date: datetime.datetime, metadata: Dict[str, Any], format: str, authority: MetadataAuthority, origin: Optional[str], dry_run: bool, ): """Does the actual loading to swh-storage.""" directory_swhid = ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=directory_id ) revision_swhid = CoreSWHID(object_type=ObjectType.REVISION, object_id=revision_id) obj = RawExtrinsicMetadata( target=directory_swhid, discovery_date=discovery_date, authority=authority, fetcher=FETCHER, format=format, metadata=json.dumps(metadata).encode(), origin=origin, revision=revision_swhid, ) if not dry_run: storage.raw_extrinsic_metadata_add([obj]) def handle_deposit_row( row, discovery_date: Optional[datetime.datetime], origin, storage, deposit_cur, dry_run: bool, ): """Loads metadata from the deposit database (which is more reliable as the metadata on the revision object, as some versions of the deposit loader were a bit lossy; and they used very different format for the field in the revision table). """ parsed_message = deposit_revision_message_re.match(row["message"]) assert parsed_message is not None, row["message"] deposit_id = int(parsed_message.group("deposit_id")) collection = parsed_message.group("collection").decode() client_name = parsed_message.group("client").decode() deposit_cur.execute( f"SELECT {', '.join(DEPOSIT_COLS)} FROM deposit " f"INNER JOIN deposit_collection " f" ON (deposit.collection_id=deposit_collection.id) " f"INNER JOIN deposit_client ON (deposit.client_id=deposit_client.user_ptr_id) " f"INNER JOIN auth_user ON (deposit.client_id=auth_user.id) " f"INNER JOIN deposit_request ON (deposit.id=deposit_request.deposit_id) " f"WHERE deposit.id = %s", (deposit_id,), ) provider_urls = set() swhids = set() metadata_entries = [] dates = set() external_identifiers = set() for deposit_request_row in deposit_cur: deposit_request = dict(zip(DEPOSIT_COLS, deposit_request_row)) # Sanity checks to make sure we selected the right deposit assert deposit_request["deposit.id"] == deposit_id assert deposit_request["deposit_collection.name"] == collection, deposit_request if client_name != "": # Sometimes it's missing from the commit message assert deposit_request["auth_user.username"] == client_name # Date of the deposit request (either the initial request, of subsequent ones) date = deposit_request["deposit_request.date"] dates.add(date) assert deposit_request["deposit.swhid_context"], deposit_request external_identifiers.add(deposit_request["deposit.external_id"]) swhids.add(deposit_request["deposit.swhid_context"]) # Client of the deposit provider_urls.add(deposit_request["deposit_client.provider_url"]) metadata = deposit_request["deposit_request.metadata"] if metadata is not None: json.dumps(metadata).encode() # check it's valid if "@xmlns" in metadata: assert metadata["@xmlns"] == ATOM_NS assert metadata["@xmlns:codemeta"] in (CODEMETA_NS, [CODEMETA_NS]) format = NEW_DEPOSIT_FORMAT elif "{http://www.w3.org/2005/Atom}id" in metadata: assert ( "{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author" in metadata or "{http://www.w3.org/2005/Atom}author" in metadata ) format = OLD_DEPOSIT_FORMAT else: # new format introduced in # https://forge.softwareheritage.org/D4065 # it's the same as the first case, but with the @xmlns # declarations stripped # Most of them should have the "id", but some revisions, # like 4d3890004fade1f4ec3bf7004a4af0c490605128, are missing # this field assert "id" in metadata or "title" in metadata assert "codemeta:author" in metadata format = NEW_DEPOSIT_FORMAT metadata_entries.append((date, format, metadata)) if discovery_date is None: discovery_date = max(dates) # Sanity checks to make sure deposit requests are consistent with each other assert len(metadata_entries) >= 1, deposit_id assert len(provider_urls) == 1, f"expected 1 provider url, got {provider_urls}" (provider_url,) = provider_urls assert len(swhids) == 1 (swhid,) = swhids assert ( len(external_identifiers) == 1 ), f"expected 1 external identifier, got {external_identifiers}" (external_identifier,) = external_identifiers # computed the origin from the external_identifier if we don't have one if origin is None: origin = f"{provider_url.strip('/')}/{external_identifier}" # explicit list of mistakes that happened in the past, but shouldn't # happen again: if origin == "https://hal.archives-ouvertes.fr/hal-01588781": # deposit id 75 origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588781" elif origin == "https://hal.archives-ouvertes.fr/hal-01588782": # deposit id 76 origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588782" elif origin == "https://hal.archives-ouvertes.fr/hal-01592430": # deposit id 143 origin = "https://hal-preprod.archives-ouvertes.fr/hal-01592430" elif origin == "https://hal.archives-ouvertes.fr/hal-01588927": origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588927" elif origin == "https://hal.archives-ouvertes.fr/hal-01593875": # deposit id 175 origin = "https://hal-preprod.archives-ouvertes.fr/hal-01593875" elif deposit_id == 160: assert origin == "https://www.softwareheritage.org/je-suis-gpl", origin origin = "https://forge.softwareheritage.org/source/jesuisgpl/" elif origin == "https://hal.archives-ouvertes.fr/hal-01588942": # deposit id 90 origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588942" elif origin == "https://hal.archives-ouvertes.fr/hal-01592499": # deposit id 162 origin = "https://hal-preprod.archives-ouvertes.fr/hal-01592499" elif origin == "https://hal.archives-ouvertes.fr/hal-01588935": # deposit id 89 origin = "https://hal-preprod.archives-ouvertes.fr/hal-01588935" assert_origin_exists(storage, origin) # check the origin we computed matches the one in the deposit db swhid_origin = QualifiedSWHID.from_string(swhid).origin if origin is not None: # explicit list of mistakes that happened in the past, but shouldn't # happen again: exceptions = [ ( # deposit id 229 "https://hal.archives-ouvertes.fr/hal-01243573", "https://hal-test.archives-ouvertes.fr/hal-01243573", ), ( # deposit id 199 "https://hal.archives-ouvertes.fr/hal-01243065", "https://hal-test.archives-ouvertes.fr/hal-01243065", ), ( # deposit id 164 "https://hal.archives-ouvertes.fr/hal-01593855", "https://hal-preprod.archives-ouvertes.fr/hal-01593855", ), ] if (origin, swhid_origin) not in exceptions: assert origin == swhid_origin, ( f"the origin we guessed from the deposit db or revision ({origin}) " f"doesn't match the one in the deposit db's SWHID ({swhid})" ) authority = MetadataAuthority( type=MetadataAuthorityType.DEPOSIT_CLIENT, url=provider_url, metadata={}, ) for (date, format, metadata) in metadata_entries: load_metadata( storage, row["id"], row["directory"], date, metadata, format, authority=authority, origin=origin, dry_run=dry_run, ) return (origin, discovery_date) def handle_row(row: Dict[str, Any], storage, deposit_cur, dry_run: bool): type_ = row["type"] # default date in case we can't find a better one discovery_date = row["date"] or row["committer_date"] metadata = row["metadata"] if metadata is None: return if type_ == "dsc": origin = None # it will be defined later, using debian_origins_from_row # TODO: the debian loader writes the changelog date as the revision's # author date and committer date. Instead, we should use the visit's date if "extrinsic" in metadata: extrinsic_files = metadata["extrinsic"]["raw"]["files"] for artifact_entry in metadata["original_artifact"]: extrinsic_file = extrinsic_files[artifact_entry["filename"]] for key in ("sha256",): assert artifact_entry["checksums"][key] == extrinsic_file[key] artifact_entry["url"] = extrinsic_file["uri"] del metadata["extrinsic"] elif type_ == "tar": provider = metadata.get("extrinsic", {}).get("provider") if provider is not None: # This is the format all the package loaders currently write, and # it is the easiest, thanks to the 'provider' and 'when' fields, # which have all the information we need to tell them easily # and generate accurate metadata discovery_date = iso8601.parse_date(metadata["extrinsic"]["when"]) # New versions of the loaders write the provider; use it. if provider.startswith("https://replicate.npmjs.com/"): # npm loader format 1 parsed_url = urlparse(provider) assert re.match("^/[^/]+/?$", parsed_url.path), parsed_url package_name = unquote(parsed_url.path.strip("/")) origin = "https://www.npmjs.com/package/" + package_name assert_origin_exists(storage, origin) load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["extrinsic"]["raw"], NPM_FORMAT, authority=AUTHORITIES["npmjs"], origin=origin, dry_run=dry_run, ) del metadata["extrinsic"] elif provider.startswith("https://pypi.org/"): # pypi loader format 1 match = re.match( "https://pypi.org/pypi/(?P.*)/json", provider ) assert match, f"unexpected provider URL format: {provider}" project_name = match.group("project_name") origin = f"https://pypi.org/project/{project_name}/" assert_origin_exists(storage, origin) load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["extrinsic"]["raw"], PYPI_FORMAT, authority=AUTHORITIES["pypi"], origin=origin, dry_run=dry_run, ) del metadata["extrinsic"] elif provider.startswith("https://cran.r-project.org/"): # cran loader provider = metadata["extrinsic"]["provider"] if provider.startswith("https://cran.r-project.org/package="): origin = metadata["extrinsic"]["provider"] else: package_name = cran_package_from_url(provider) origin = f"https://cran.r-project.org/package={package_name}" assert origin is not None # Ideally we should assert the origin exists, but we can't: # https://forge.softwareheritage.org/T2536 if ( hashlib.sha1(origin.encode()).digest() not in _origins and storage.origin_get([origin])[0] is None ): return raw_extrinsic_metadata = metadata["extrinsic"]["raw"] # this is actually intrinsic, ignore it if "version" in raw_extrinsic_metadata: del raw_extrinsic_metadata["version"] # Copy the URL to the original_artifacts metadata assert len(metadata["original_artifact"]) == 1 if "url" in metadata["original_artifact"][0]: assert ( metadata["original_artifact"][0]["url"] == raw_extrinsic_metadata["url"] ), row else: metadata["original_artifact"][0]["url"] = raw_extrinsic_metadata[ "url" ] del raw_extrinsic_metadata["url"] assert ( raw_extrinsic_metadata == {} ), f"Unexpected metadata keys: {list(raw_extrinsic_metadata)}" del metadata["extrinsic"] elif ( provider.startswith("https://nix-community.github.io/nixpkgs-swh/") or provider == "https://guix.gnu.org/sources.json" ): # nixguix loader origin = provider assert_origin_exists(storage, origin) authority = MetadataAuthority( type=MetadataAuthorityType.FORGE, url=provider, metadata={}, ) assert row["date"] is None # the nixguix loader does not write dates load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["extrinsic"]["raw"], NIXGUIX_FORMAT, authority=authority, origin=origin, dry_run=dry_run, ) del metadata["extrinsic"] elif provider.startswith("https://ftp.gnu.org/"): # archive loader format 1 origin = provider assert_origin_exists(storage, origin) assert len(metadata["original_artifact"]) == 1 metadata["original_artifact"][0]["url"] = metadata["extrinsic"]["raw"][ "url" ] # Remove duplicate keys of original_artifacts for key in ("url", "time", "length", "version", "filename"): del metadata["extrinsic"]["raw"][key] assert metadata["extrinsic"]["raw"] == {} del metadata["extrinsic"] elif provider.startswith("https://deposit.softwareheritage.org/"): origin = metadata["extrinsic"]["raw"]["origin"]["url"] assert_origin_exists(storage, origin) if "@xmlns" in metadata: assert metadata["@xmlns"] == ATOM_NS assert metadata["@xmlns:codemeta"] in (CODEMETA_NS, [CODEMETA_NS]) assert "intrinsic" not in metadata assert "extra_headers" not in metadata # deposit loader format 1 # in this case, the metadata seems to be both directly in metadata # and in metadata["extrinsic"]["raw"]["metadata"] (origin, discovery_date) = handle_deposit_row( row, discovery_date, origin, storage, deposit_cur, dry_run ) remove_atom_codemeta_metadata_with_xmlns(metadata) if "client" in metadata: del metadata["client"] del metadata["extrinsic"] else: # deposit loader format 2 actual_metadata = metadata["extrinsic"]["raw"]["origin_metadata"][ "metadata" ] if isinstance(actual_metadata, str): # new format introduced in # https://forge.softwareheritage.org/D4105 actual_metadata = json.loads(actual_metadata) if "@xmlns" in actual_metadata: assert actual_metadata["@xmlns"] == ATOM_NS assert actual_metadata["@xmlns:codemeta"] in ( CODEMETA_NS, [CODEMETA_NS], ) elif "{http://www.w3.org/2005/Atom}id" in actual_metadata: assert ( "{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author" in actual_metadata ) else: # new format introduced in # https://forge.softwareheritage.org/D4065 # it's the same as the first case, but with the @xmlns # declarations stripped # Most of them should have the "id", but some revisions, # like 4d3890004fade1f4ec3bf7004a4af0c490605128, are missing # this field assert "id" in actual_metadata or "title" in actual_metadata assert "codemeta:author" in actual_metadata (origin, discovery_date) = handle_deposit_row( row, discovery_date, origin, storage, deposit_cur, dry_run ) del metadata["extrinsic"] else: assert False, f"unknown provider {provider}" # Older versions don't write the provider; use heuristics instead. elif ( metadata.get("package_source", {}) .get("url", "") .startswith("https://registry.npmjs.org/") ): # npm loader format 2 package_source_url = metadata["package_source"]["url"] package_name = npm_package_from_source_url(package_source_url) origin = "https://www.npmjs.com/package/" + package_name assert_origin_exists(storage, origin) load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["package"], NPM_FORMAT, authority=AUTHORITIES["npmjs"], origin=origin, dry_run=dry_run, ) del metadata["package"] assert "original_artifact" not in metadata # rebuild an "original_artifact"-like metadata dict from what we # can salvage of "package_source" package_source_metadata = metadata["package_source"] keep_keys = {"blake2s256", "filename", "sha1", "sha256", "url"} discard_keys = { "date", # is equal to the revision date "name", # was loaded above "version", # same } assert ( set(package_source_metadata) == keep_keys | discard_keys ), package_source_metadata # will be loaded below metadata["original_artifact"] = [ { "filename": package_source_metadata["filename"], "checksums": { "sha1": package_source_metadata["sha1"], "sha256": package_source_metadata["sha256"], "blake2s256": package_source_metadata["blake2s256"], }, "url": package_source_metadata["url"], } ] del metadata["package_source"] elif "@xmlns" in metadata: assert metadata["@xmlns:codemeta"] in (CODEMETA_NS, [CODEMETA_NS]) assert "intrinsic" not in metadata assert "extra_headers" not in metadata # deposit loader format 3 if row["message"] == b"swh: Deposit 159 in collection swh": # There is no deposit 159 in the deposit DB, for some reason assert ( hash_to_hex(row["id"]) == "8e9cee14a6ad39bca4347077b87fb5bbd8953bb1" ) return elif row["message"] == b"hal: Deposit 342 in collection hal": # They have status 'failed' and no swhid return origin = None # TODO discovery_date = None # TODO (origin, discovery_date) = handle_deposit_row( row, discovery_date, origin, storage, deposit_cur, dry_run ) remove_atom_codemeta_metadata_with_xmlns(metadata) if "client" in metadata: del metadata["client"] # found in the deposit db if "committer" in metadata: del metadata["committer"] # found on the revision object elif "{http://www.w3.org/2005/Atom}id" in metadata: assert ( "{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author" in metadata or "{http://www.w3.org/2005/Atom}author" in metadata ) assert "intrinsic" not in metadata assert "extra_headers" not in metadata # deposit loader format 4 origin = None discovery_date = None # TODO (origin, discovery_date) = handle_deposit_row( row, discovery_date, origin, storage, deposit_cur, dry_run ) remove_atom_codemeta_metadata_without_xmlns(metadata) elif hash_to_hex(row["id"]) == "a86747d201ab8f8657d145df4376676d5e47cf9f": # deposit 91, is missing "{http://www.w3.org/2005/Atom}id" for some # reason, and has an invalid oririn return elif ( isinstance(metadata.get("original_artifact"), dict) and metadata["original_artifact"]["url"].startswith( "https://files.pythonhosted.org/" ) ) or ( isinstance(metadata.get("original_artifact"), list) and len(metadata.get("original_artifact")) == 1 and metadata["original_artifact"][0] .get("url", "") .startswith("https://files.pythonhosted.org/") ): if isinstance(metadata.get("original_artifact"), dict): metadata["original_artifact"] = [metadata["original_artifact"]] assert len(metadata["original_artifact"]) == 1 origin = pypi_origin_from_filename( storage, row["id"], metadata["original_artifact"][0]["filename"] ) if "project" in metadata: # pypi loader format 2 load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["project"], PYPI_FORMAT, authority=AUTHORITIES["pypi"], origin=origin, dry_run=dry_run, ) del metadata["project"] else: assert set(metadata) == {"original_artifact"}, set(metadata) # pypi loader format 3 pass # nothing to do, there's no metadata elif row["message"] == b"synthetic revision message": assert isinstance(metadata["original_artifact"], list), metadata assert not any("url" in d for d in metadata["original_artifact"]) # archive loader format 2 origin = None elif deposit_revision_message_re.match(row["message"]): # deposit without metadata in the revision assert set(metadata) == {"original_artifact"}, metadata origin = None # TODO discovery_date = None (origin, discovery_date) = handle_deposit_row( row, discovery_date, origin, storage, deposit_cur, dry_run ) else: assert False, f"Unable to detect type of metadata for row: {row}" # Ignore common intrinsic metadata keys for key in ("intrinsic", "extra_headers"): if key in metadata: del metadata[key] # Ignore loader-specific intrinsic metadata keys if type_ == "hg": del metadata["node"] elif type_ == "dsc": if "package_info" in metadata: del metadata["package_info"] if "original_artifact" in metadata: for original_artifact in metadata["original_artifact"]: # Rename keys to the expected format of original-artifacts-json. rename_keys = [ ("name", "filename"), # eg. from old Debian loader ("size", "length"), # eg. from old PyPI loader ] for (old_name, new_name) in rename_keys: if old_name in original_artifact: assert new_name not in original_artifact original_artifact[new_name] = original_artifact.pop(old_name) # Move the checksums to their own subdict, which is the expected format # of original-artifacts-json. if "sha1" in original_artifact: assert "checksums" not in original_artifact original_artifact["checksums"] = {} for key in ("sha1", "sha256", "sha1_git", "blake2s256"): if key in original_artifact: original_artifact["checksums"][key] = original_artifact.pop(key) if "date" in original_artifact: # The information comes from the package repository rather than SWH, # so it shouldn't be in the 'original-artifacts' metadata # (which has SWH as authority). # Moreover, it's not a very useful information, so let's just drop it. del original_artifact["date"] allowed_keys = { "checksums", "filename", "length", "url", "archive_type", } assert set(original_artifact) <= allowed_keys, set(original_artifact) if type_ == "dsc": assert origin is None origins = debian_origins_from_row(row, storage) if not origins: print("Missing Debian origin for revision: {hash_to_hex(row['id'])}") else: origins = [origin] for origin in origins: load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["original_artifact"], ORIGINAL_ARTIFACT_FORMAT, authority=AUTHORITIES["swh"], origin=origin, dry_run=dry_run, ) del metadata["original_artifact"] assert metadata == {}, ( f"remaining metadata keys for {row['id'].hex()} (type: {row['type']}): " f"{metadata}" ) def create_fetchers(db): with db.cursor() as cur: cur.execute( """ INSERT INTO metadata_fetcher (name, version, metadata) VALUES (%s, %s, %s) ON CONFLICT DO NOTHING """, (FETCHER.name, FETCHER.version, FETCHER.metadata), ) def iter_revision_rows(storage_dbconn: str, first_id: Sha1Git): after_id = first_id failures = 0 while True: try: storage_db = BaseDb.connect(storage_dbconn) with storage_db.cursor() as cur: while True: cur.execute( f"SELECT {', '.join(REVISION_COLS)} FROM revision " - f"WHERE id > %s AND metadata IS NOT NULL " + f"WHERE id > %s AND metadata IS NOT NULL AND type != 'git'" f"ORDER BY id LIMIT 1000", (after_id,), ) new_rows = 0 for row in cur: new_rows += 1 row_d = dict(zip(REVISION_COLS, row)) yield row_d after_id = row_d["id"] if new_rows == 0: return except psycopg2.OperationalError as e: print(e) # most likely a temporary error, try again if failures >= 60: raise else: time.sleep(60) failures += 1 def main(storage_dbconn, storage_url, deposit_dbconn, first_id, dry_run): storage_db = BaseDb.connect(storage_dbconn) deposit_db = BaseDb.connect(deposit_dbconn) storage = get_storage( "pipeline", steps=[ {"cls": "retry"}, { "cls": "local", "db": storage_dbconn, "objstorage": {"cls": "memory", "args": {}}, }, ], ) if not dry_run: create_fetchers(storage_db) # Not creating authorities, as the loaders are presumably already running # and created them already. # This also helps make sure this script doesn't accidentally create # authorities that differ from what the loaders use. total_rows = 0 with deposit_db.cursor() as deposit_cur: for row in iter_revision_rows(storage_dbconn, first_id): handle_row(row, storage, deposit_cur, dry_run) total_rows += 1 if total_rows % 1000 == 0: percents = ( int.from_bytes(row["id"][0:4], byteorder="big") * 100 / (1 << 32) ) print( f"Processed {total_rows/1000000.:.2f}M rows " f"(~{percents:.1f}%, last revision: {row['id'].hex()})" ) if __name__ == "__main__": if len(sys.argv) == 4: (_, storage_dbconn, storage_url, deposit_dbconn) = sys.argv first_id = "00" * 20 elif len(sys.argv) == 5: (_, storage_dbconn, storage_url, deposit_dbconn, first_id) = sys.argv else: print( f"Syntax: {sys.argv[0]} " f" []" ) exit(1) if os.path.isfile("./origins.txt"): # You can generate this file with: # psql service=swh-replica \ # -c "\copy (select digest(url, 'sha1') from origin) to stdout" \ # | pv -l > origins.txt print("Loading origins...") with open("./origins.txt") as fd: for line in fd: digest = line.strip()[3:] _origins.add(bytes.fromhex(digest)) print("Done loading origins.") main(storage_dbconn, storage_url, deposit_dbconn, bytes.fromhex(first_id), True) diff --git a/swh/storage/postgresql/storage.py b/swh/storage/postgresql/storage.py index a672a7d1..28d23051 100644 --- a/swh/storage/postgresql/storage.py +++ b/swh/storage/postgresql/storage.py @@ -1,1472 +1,1474 @@ # Copyright (C) 2015-2021 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 base64 from collections import defaultdict import contextlib from contextlib import contextmanager import datetime import itertools from typing import Any, Counter, Dict, Iterable, List, Optional, Sequence, Tuple import attr import psycopg2 import psycopg2.errors import psycopg2.pool from swh.core.api.serializers import msgpack_dumps, msgpack_loads from swh.core.db.common import db_transaction, db_transaction_generator from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex from swh.model.identifiers import ExtendedObjectType, ExtendedSWHID, ObjectType from swh.model.model import ( SHA1_SIZE, Content, Directory, ExtID, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Release, Revision, Sha1, Sha1Git, SkippedContent, Snapshot, SnapshotBranch, TargetType, ) from swh.storage.exc import HashCollision, StorageArgumentException, StorageDBError from swh.storage.interface import ( VISIT_STATUSES, ListOrder, PagedResult, PartialBranches, ) from swh.storage.metrics import process_metrics, send_metric, timed from swh.storage.objstorage import ObjStorage from swh.storage.utils import ( extract_collision_hash, get_partition_bounds_bytes, map_optional, now, ) from swh.storage.writer import JournalWriter from . import converters from .db import Db # 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""" VALIDATION_EXCEPTIONS = ( KeyError, TypeError, ValueError, psycopg2.errors.CheckViolation, psycopg2.errors.IntegrityError, psycopg2.errors.InvalidTextRepresentation, psycopg2.errors.NotNullViolation, psycopg2.errors.NumericValueOutOfRange, psycopg2.errors.UndefinedFunction, # (raised on wrong argument typs) ) """Exceptions raised by postgresql when validation of the arguments failed.""" @contextlib.contextmanager def convert_validation_exceptions(): """Catches postgresql errors related to invalid arguments, and re-raises a StorageArgumentException.""" try: yield except tuple(VALIDATION_EXCEPTIONS) as e: raise StorageArgumentException(str(e)) class Storage: """SWH storage proxy, encompassing DB and object storage """ def __init__( self, db, objstorage, min_pool_conns=1, max_pool_conns=10, journal_writer=None ): """ 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.journal_writer = JournalWriter(journal_writer) self.objstorage = ObjStorage(objstorage) def get_db(self): if self._db: return self._db else: return Db.from_pool(self._pool) def put_db(self, db): if db is not self._db: db.put_conn() @contextmanager def db(self): db = None try: db = self.get_db() yield db finally: if db: self.put_db(db) @timed @db_transaction() def check_config(self, *, check_write: bool, db=None, cur=None) -> bool: if not self.objstorage.check_config(check_write=check_write): return False if not db.check_dbversion(): return False # Check permissions on one of the tables if check_write: check = "INSERT" else: check = "SELECT" cur.execute("select has_table_privilege(current_user, 'content', %s)", (check,)) return cur.fetchone()[0] def _content_unique_key(self, hash, db): """Given a hash (tuple or dict), return a unique key from the aggregation of keys. """ keys = db.content_hash_keys if isinstance(hash, tuple): return hash return tuple([hash[k] for k in keys]) def _content_add_metadata(self, db, cur, content): """Add content to the postgresql database but not the object storage. """ # create temporary table for metadata injection db.mktemp("content", cur) db.copy_to( (c.to_dict() for c in content), "tmp_content", db.content_add_keys, cur ) # move metadata in place try: db.content_add_from_temp(cur) except psycopg2.IntegrityError as e: if e.diag.sqlstate == "23505" and e.diag.table_name == "content": message_detail = e.diag.message_detail if message_detail: hash_name, hash_id = extract_collision_hash(message_detail) collision_contents_hashes = [ c.hashes() for c in content if c.get_hash(hash_name) == hash_id ] else: constraint_to_hash_name = { "content_pkey": "sha1", "content_sha1_git_idx": "sha1_git", "content_sha256_idx": "sha256", } hash_name = constraint_to_hash_name.get(e.diag.constraint_name) hash_id = None collision_contents_hashes = None raise HashCollision( hash_name, hash_id, collision_contents_hashes ) from None else: raise @timed @process_metrics def content_add(self, content: List[Content]) -> Dict: ctime = now() contents = [attr.evolve(c, ctime=ctime) for c in content] # Must add to the objstorage before the DB and journal. Otherwise: # 1. in case of a crash the DB may "believe" we have the content, but # we didn't have time to write to the objstorage before the crash # 2. the objstorage mirroring, which reads from the journal, may attempt to # read from the objstorage before we finished writing it objstorage_summary = self.objstorage.content_add(contents) with self.db() as db: with db.transaction() as cur: missing = list( self.content_missing( map(Content.to_dict, contents), key_hash="sha1_git", db=db, cur=cur, ) ) contents = [c for c in contents if c.sha1_git in missing] self.journal_writer.content_add(contents) self._content_add_metadata(db, cur, contents) return { "content:add": len(contents), "content:add:bytes": objstorage_summary["content:add:bytes"], } @timed @db_transaction() def content_update( self, contents: List[Dict[str, Any]], keys: List[str] = [], db=None, cur=None ) -> None: # TODO: Add a check on input keys. How to properly implement # this? We don't know yet the new columns. self.journal_writer.content_update(contents) db.mktemp("content", cur) select_keys = list(set(db.content_get_metadata_keys).union(set(keys))) with convert_validation_exceptions(): db.copy_to(contents, "tmp_content", select_keys, cur) db.content_update_from_temp(keys_to_update=keys, cur=cur) @timed @process_metrics @db_transaction() def content_add_metadata(self, content: List[Content], db=None, cur=None) -> Dict: missing = self.content_missing( (c.to_dict() for c in content), key_hash="sha1_git", db=db, cur=cur, ) contents = [c for c in content if c.sha1_git in missing] self.journal_writer.content_add_metadata(contents) self._content_add_metadata(db, cur, contents) return { "content:add": len(contents), } @timed def content_get_data(self, content: Sha1) -> Optional[bytes]: # FIXME: Make this method support slicing the `data` return self.objstorage.content_get(content) @timed @db_transaction() def content_get_partition( self, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, db=None, cur=None, ) -> PagedResult[Content]: if limit is None: raise StorageArgumentException("limit should not be None") (start, end) = get_partition_bounds_bytes( partition_id, nb_partitions, SHA1_SIZE ) if page_token: start = hash_to_bytes(page_token) if end is None: end = b"\xff" * SHA1_SIZE next_page_token: Optional[str] = None contents = [] for counter, row in enumerate(db.content_get_range(start, end, limit + 1, cur)): row_d = dict(zip(db.content_get_metadata_keys, row)) content = Content(**row_d) if counter >= limit: # take the last content for the next page starting from this next_page_token = hash_to_hex(content.sha1) break contents.append(content) assert len(contents) <= limit return PagedResult(results=contents, next_page_token=next_page_token) @timed @db_transaction(statement_timeout=500) def content_get( self, contents: List[Sha1], db=None, cur=None ) -> List[Optional[Content]]: contents_by_sha1: Dict[Sha1, Optional[Content]] = {} for row in db.content_get_metadata_from_sha1s(contents, cur): row_d = dict(zip(db.content_get_metadata_keys, row)) content = Content(**row_d) contents_by_sha1[content.sha1] = content return [contents_by_sha1.get(sha1) for sha1 in contents] @timed @db_transaction_generator() def content_missing( self, contents: List[Dict[str, Any]], key_hash: str = "sha1", db=None, cur=None ) -> Iterable[bytes]: if key_hash not in DEFAULT_ALGORITHMS: raise StorageArgumentException( "key_hash should be one of {','.join(DEFAULT_ALGORITHMS)}" ) keys = db.content_hash_keys key_hash_idx = keys.index(key_hash) for obj in db.content_missing_from_list(contents, cur): yield obj[key_hash_idx] @timed @db_transaction_generator() def content_missing_per_sha1( self, contents: List[bytes], db=None, cur=None ) -> Iterable[bytes]: for obj in db.content_missing_per_sha1(contents, cur): yield obj[0] @timed @db_transaction_generator() def content_missing_per_sha1_git( self, contents: List[bytes], db=None, cur=None ) -> Iterable[Sha1Git]: for obj in db.content_missing_per_sha1_git(contents, cur): yield obj[0] @timed @db_transaction() def content_find(self, content: Dict[str, Any], db=None, cur=None) -> List[Content]: if not set(content).intersection(DEFAULT_ALGORITHMS): raise StorageArgumentException( "content keys must contain at least one " f"of: {', '.join(sorted(DEFAULT_ALGORITHMS))}" ) rows = db.content_find( sha1=content.get("sha1"), sha1_git=content.get("sha1_git"), sha256=content.get("sha256"), blake2s256=content.get("blake2s256"), cur=cur, ) contents = [] for row in rows: row_d = dict(zip(db.content_find_cols, row)) contents.append(Content(**row_d)) return contents @timed @db_transaction() def content_get_random(self, db=None, cur=None) -> Sha1Git: return db.content_get_random(cur) @staticmethod def _skipped_content_normalize(d): d = d.copy() if d.get("status") is None: d["status"] = "absent" if d.get("length") is None: d["length"] = -1 return d def _skipped_content_add_metadata(self, db, cur, content: List[SkippedContent]): origin_ids = db.origin_id_get_by_url([cont.origin for cont in content], cur=cur) content = [ attr.evolve(c, origin=origin_id) for (c, origin_id) in zip(content, origin_ids) ] db.mktemp("skipped_content", cur) db.copy_to( [c.to_dict() for c in content], "tmp_skipped_content", db.skipped_content_keys, cur, ) # move metadata in place db.skipped_content_add_from_temp(cur) @timed @process_metrics @db_transaction() def skipped_content_add( self, content: List[SkippedContent], db=None, cur=None ) -> Dict: ctime = now() content = [attr.evolve(c, ctime=ctime) for c in content] missing_contents = self.skipped_content_missing( (c.to_dict() for c in content), db=db, cur=cur, ) content = [ c for c in content if any( all( c.get_hash(algo) == missing_content.get(algo) for algo in DEFAULT_ALGORITHMS ) for missing_content in missing_contents ) ] self.journal_writer.skipped_content_add(content) self._skipped_content_add_metadata(db, cur, content) return { "skipped_content:add": len(content), } @timed @db_transaction_generator() def skipped_content_missing( self, contents: List[Dict[str, Any]], db=None, cur=None ) -> Iterable[Dict[str, Any]]: contents = list(contents) for content in db.skipped_content_missing(contents, cur): yield dict(zip(db.content_hash_keys, content)) @timed @process_metrics @db_transaction() def directory_add(self, directories: List[Directory], db=None, cur=None) -> Dict: summary = {"directory:add": 0} dirs = set() dir_entries: Dict[str, defaultdict] = { "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.to_dict() entry["dir_id"] = dir_id dir_entries[entry["type"]][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs, db=db, cur=cur)) if not dirs_missing: return summary self.journal_writer.directory_add( dir_ for dir_ in directories if dir_.id in dirs_missing ) # 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) summary["directory:add"] = len(dirs_missing) return summary @timed @db_transaction_generator() def directory_missing( self, directories: List[Sha1Git], db=None, cur=None ) -> Iterable[Sha1Git]: for obj in db.directory_missing_from_list(directories, cur): yield obj[0] @timed @db_transaction_generator(statement_timeout=20000) def directory_ls( self, directory: Sha1Git, recursive: bool = False, db=None, cur=None ) -> Iterable[Dict[str, Any]]: 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)) @timed @db_transaction(statement_timeout=2000) def directory_entry_get_by_path( self, directory: Sha1Git, paths: List[bytes], db=None, cur=None ) -> Optional[Dict[str, Any]]: res = db.directory_entry_get_by_path(directory, paths, cur) return dict(zip(db.directory_ls_cols, res)) if res else None @timed @db_transaction() def directory_get_random(self, db=None, cur=None) -> Sha1Git: return db.directory_get_random(cur) @timed @process_metrics @db_transaction() def revision_add(self, revisions: List[Revision], db=None, cur=None) -> Dict: summary = {"revision:add": 0} revisions_missing = set( self.revision_missing( set(revision.id for revision in revisions), db=db, cur=cur ) ) if not revisions_missing: return summary db.mktemp_revision(cur) revisions_filtered = [ revision for revision in revisions if revision.id in revisions_missing ] self.journal_writer.revision_add(revisions_filtered) db_revisions_filtered = list(map(converters.revision_to_db, revisions_filtered)) parents_filtered: List[bytes] = [] with convert_validation_exceptions(): db.copy_to( db_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, ) return {"revision:add": len(revisions_missing)} @timed @db_transaction_generator() def revision_missing( self, revisions: List[Sha1Git], db=None, cur=None ) -> Iterable[Sha1Git]: if not revisions: return None for obj in db.revision_missing_from_list(revisions, cur): yield obj[0] @timed @db_transaction(statement_timeout=1000) def revision_get( self, revision_ids: List[Sha1Git], db=None, cur=None ) -> List[Optional[Revision]]: revisions = [] for line in db.revision_get_from_list(revision_ids, cur): revision = converters.db_to_revision(dict(zip(db.revision_get_cols, line))) revisions.append(revision) return revisions @timed @db_transaction_generator(statement_timeout=2000) def revision_log( self, revisions: List[Sha1Git], limit: Optional[int] = None, db=None, cur=None ) -> Iterable[Optional[Dict[str, Any]]]: for line in db.revision_log(revisions, limit, cur): data = converters.db_to_revision(dict(zip(db.revision_get_cols, line))) if not data: yield None continue yield data.to_dict() @timed @db_transaction_generator(statement_timeout=2000) def revision_shortlog( self, revisions: List[Sha1Git], limit: Optional[int] = None, db=None, cur=None ) -> Iterable[Optional[Tuple[Sha1Git, Tuple[Sha1Git, ...]]]]: yield from db.revision_shortlog(revisions, limit, cur) @timed @db_transaction() def revision_get_random(self, db=None, cur=None) -> Sha1Git: return db.revision_get_random(cur) @timed @db_transaction() def extid_get_from_extid( self, id_type: str, ids: List[bytes], db=None, cur=None ) -> List[ExtID]: extids = [] for row in db.extid_get_from_extid_list(id_type, ids, cur): if row[0] is not None: extids.append(converters.db_to_extid(dict(zip(db.extid_cols, row)))) return extids @timed @db_transaction() def extid_get_from_target( self, target_type: ObjectType, ids: List[Sha1Git], db=None, cur=None ) -> List[ExtID]: extids = [] for row in db.extid_get_from_swhid_list(target_type.value, ids, cur): if row[0] is not None: extids.append(converters.db_to_extid(dict(zip(db.extid_cols, row)))) return extids @timed @db_transaction() def extid_add(self, ids: List[ExtID], db=None, cur=None) -> Dict[str, int]: extid = [ { "extid": extid.extid, "extid_type": extid.extid_type, "target": extid.target.object_id, "target_type": extid.target.object_type.name.lower(), # arghh } for extid in ids ] db.mktemp("extid", cur) + self.journal_writer.extid_add(ids) + db.copy_to(extid, "tmp_extid", db.extid_cols, cur) # move metadata in place db.extid_add_from_temp(cur) return {"extid:add": len(extid)} @timed @process_metrics @db_transaction() def release_add(self, releases: List[Release], db=None, cur=None) -> Dict: summary = {"release:add": 0} release_ids = set(release.id for release in releases) releases_missing = set(self.release_missing(release_ids, db=db, cur=cur)) if not releases_missing: return summary db.mktemp_release(cur) releases_filtered = [ release for release in releases if release.id in releases_missing ] self.journal_writer.release_add(releases_filtered) db_releases_filtered = list(map(converters.release_to_db, releases_filtered)) with convert_validation_exceptions(): db.copy_to(db_releases_filtered, "tmp_release", db.release_add_cols, cur) db.release_add_from_temp(cur) return {"release:add": len(releases_missing)} @timed @db_transaction_generator() def release_missing( self, releases: List[Sha1Git], db=None, cur=None ) -> Iterable[Sha1Git]: if not releases: return for obj in db.release_missing_from_list(releases, cur): yield obj[0] @timed @db_transaction(statement_timeout=500) def release_get( self, releases: List[Sha1Git], db=None, cur=None ) -> List[Optional[Release]]: rels = [] for release in db.release_get_from_list(releases, cur): data = converters.db_to_release(dict(zip(db.release_get_cols, release))) rels.append(data if data else None) return rels @timed @db_transaction() def release_get_random(self, db=None, cur=None) -> Sha1Git: return db.release_get_random(cur) @timed @process_metrics @db_transaction() def snapshot_add(self, snapshots: List[Snapshot], db=None, cur=None) -> Dict: created_temp_table = False count = 0 for snapshot in snapshots: if not db.snapshot_exists(snapshot.id, cur): if not created_temp_table: db.mktemp_snapshot_branch(cur) created_temp_table = True with convert_validation_exceptions(): db.copy_to( ( { "name": name, "target": info.target if info else None, "target_type": ( info.target_type.value if info else None ), } for name, info in snapshot.branches.items() ), "tmp_snapshot_branch", ["name", "target", "target_type"], cur, ) self.journal_writer.snapshot_add([snapshot]) db.snapshot_add(snapshot.id, cur) count += 1 return {"snapshot:add": count} @timed @db_transaction_generator() def snapshot_missing( self, snapshots: List[Sha1Git], db=None, cur=None ) -> Iterable[Sha1Git]: for obj in db.snapshot_missing_from_list(snapshots, cur): yield obj[0] @timed @db_transaction(statement_timeout=2000) def snapshot_get( self, snapshot_id: Sha1Git, db=None, cur=None ) -> Optional[Dict[str, Any]]: d = self.snapshot_get_branches(snapshot_id) if d is None: return d return { "id": d["id"], "branches": { name: branch.to_dict() if branch else None for (name, branch) in d["branches"].items() }, "next_branch": d["next_branch"], } @timed @db_transaction(statement_timeout=2000) def snapshot_count_branches( self, snapshot_id: Sha1Git, branch_name_exclude_prefix: Optional[bytes] = None, db=None, cur=None, ) -> Optional[Dict[Optional[str], int]]: return dict( [ bc for bc in db.snapshot_count_branches( snapshot_id, branch_name_exclude_prefix, cur, ) ] ) @timed @db_transaction(statement_timeout=2000) def snapshot_get_branches( self, snapshot_id: Sha1Git, branches_from: bytes = b"", branches_count: int = 1000, target_types: Optional[List[str]] = None, branch_name_include_substring: Optional[bytes] = None, branch_name_exclude_prefix: Optional[bytes] = None, db=None, cur=None, ) -> Optional[PartialBranches]: if snapshot_id == EMPTY_SNAPSHOT_ID: return PartialBranches(id=snapshot_id, branches={}, next_branch=None,) branches = {} next_branch = None fetched_branches = list( db.snapshot_get_by_id( snapshot_id, branches_from=branches_from, # the underlying SQL query can be quite expensive to execute for small # branches_count value, so we ensure a minimum branches limit of 10 for # optimal performances branches_count=max(branches_count + 1, 10), target_types=target_types, branch_name_include_substring=branch_name_include_substring, branch_name_exclude_prefix=branch_name_exclude_prefix, cur=cur, ) ) for row in fetched_branches[:branches_count]: branch_d = dict(zip(db.snapshot_get_cols, row)) del branch_d["snapshot_id"] name = branch_d.pop("name") if branch_d["target"] is None and branch_d["target_type"] is None: branch = None else: assert branch_d["target_type"] is not None branch = SnapshotBranch( target=branch_d["target"], target_type=TargetType(branch_d["target_type"]), ) branches[name] = branch if len(fetched_branches) > branches_count: next_branch = dict( zip(db.snapshot_get_cols, fetched_branches[branches_count]) )["name"] if branches: return PartialBranches( id=snapshot_id, branches=branches, next_branch=next_branch, ) return None @timed @db_transaction() def snapshot_get_random(self, db=None, cur=None) -> Sha1Git: return db.snapshot_get_random(cur) @timed @db_transaction() def origin_visit_add( self, visits: List[OriginVisit], db=None, cur=None ) -> Iterable[OriginVisit]: for visit in visits: origin = self.origin_get([visit.origin], db=db, cur=cur)[0] if not origin: # Cannot add a visit without an origin raise StorageArgumentException("Unknown origin %s", visit.origin) all_visits = [] nb_visits = 0 for visit in visits: nb_visits += 1 if not visit.visit: with convert_validation_exceptions(): visit_id = db.origin_visit_add( visit.origin, visit.date, visit.type, cur=cur ) visit = attr.evolve(visit, visit=visit_id) else: db.origin_visit_add_with_id(visit, cur=cur) assert visit.visit is not None all_visits.append(visit) # Forced to write after for the case when the visit has no id self.journal_writer.origin_visit_add([visit]) visit_status = OriginVisitStatus( origin=visit.origin, visit=visit.visit, date=visit.date, type=visit.type, status="created", snapshot=None, ) self._origin_visit_status_add(visit_status, db=db, cur=cur) send_metric("origin_visit:add", count=nb_visits, method_name="origin_visit") return all_visits def _origin_visit_status_add( self, visit_status: OriginVisitStatus, db, cur ) -> None: """Add an origin visit status""" self.journal_writer.origin_visit_status_add([visit_status]) db.origin_visit_status_add(visit_status, cur=cur) send_metric( "origin_visit_status:add", count=1, method_name="origin_visit_status" ) @timed @db_transaction() def origin_visit_status_add( self, visit_statuses: List[OriginVisitStatus], db=None, cur=None, ) -> None: visit_statuses_ = [] # First round to check existence (fail early if any is ko) for visit_status in visit_statuses: origin_url = self.origin_get([visit_status.origin], db=db, cur=cur)[0] if not origin_url: raise StorageArgumentException(f"Unknown origin {visit_status.origin}") if visit_status.type is None: origin_visit = self.origin_visit_get_by( visit_status.origin, visit_status.visit, db=db, cur=cur ) if origin_visit is None: raise StorageArgumentException( f"Unknown origin visit {visit_status.visit} " f"of origin {visit_status.origin}" ) origin_visit_status = attr.evolve(visit_status, type=origin_visit.type) else: origin_visit_status = visit_status visit_statuses_.append(origin_visit_status) for visit_status in visit_statuses_: self._origin_visit_status_add(visit_status, db, cur) @timed @db_transaction() def origin_visit_status_get_latest( self, origin_url: str, visit: int, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, db=None, cur=None, ) -> Optional[OriginVisitStatus]: if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES): raise StorageArgumentException( f"Unknown allowed statuses {','.join(allowed_statuses)}, only " f"{','.join(VISIT_STATUSES)} authorized" ) row_d = db.origin_visit_status_get_latest( origin_url, visit, allowed_statuses, require_snapshot, cur=cur ) if not row_d: return None return OriginVisitStatus(**row_d) @timed @db_transaction(statement_timeout=500) def origin_visit_get( self, origin: str, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, db=None, cur=None, ) -> PagedResult[OriginVisit]: page_token = page_token or "0" if not isinstance(order, ListOrder): raise StorageArgumentException("order must be a ListOrder value") if not isinstance(page_token, str): raise StorageArgumentException("page_token must be a string.") next_page_token = None visit_from = int(page_token) visits: List[OriginVisit] = [] extra_limit = limit + 1 for row in db.origin_visit_get_range( origin, visit_from=visit_from, order=order, limit=extra_limit, cur=cur ): row_d = dict(zip(db.origin_visit_cols, row)) visits.append( OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) ) assert len(visits) <= extra_limit if len(visits) == extra_limit: visits = visits[:limit] next_page_token = str(visits[-1].visit) return PagedResult(results=visits, next_page_token=next_page_token) @timed @db_transaction(statement_timeout=500) def origin_visit_find_by_date( self, origin: str, visit_date: datetime.datetime, db=None, cur=None ) -> Optional[OriginVisit]: row_d = db.origin_visit_find_by_date(origin, visit_date, cur=cur) if not row_d: return None return OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) @timed @db_transaction(statement_timeout=500) def origin_visit_get_by( self, origin: str, visit: int, db=None, cur=None ) -> Optional[OriginVisit]: row = db.origin_visit_get(origin, visit, cur) if row: row_d = dict(zip(db.origin_visit_get_cols, row)) return OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) return None @timed @db_transaction(statement_timeout=4000) def origin_visit_get_latest( self, origin: str, type: Optional[str] = None, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, db=None, cur=None, ) -> Optional[OriginVisit]: if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES): raise StorageArgumentException( f"Unknown allowed statuses {','.join(allowed_statuses)}, only " f"{','.join(VISIT_STATUSES)} authorized" ) row = db.origin_visit_get_latest( origin, type=type, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, cur=cur, ) if row: row_d = dict(zip(db.origin_visit_get_cols, row)) visit = OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) return visit return None @timed @db_transaction(statement_timeout=500) def origin_visit_status_get( self, origin: str, visit: int, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, db=None, cur=None, ) -> PagedResult[OriginVisitStatus]: next_page_token = None date_from = None if page_token is not None: date_from = datetime.datetime.fromisoformat(page_token) visit_statuses: List[OriginVisitStatus] = [] # Take one more visit status so we can reuse it as the next page token if any for row in db.origin_visit_status_get_range( origin, visit, date_from=date_from, order=order, limit=limit + 1, cur=cur, ): row_d = dict(zip(db.origin_visit_status_cols, row)) visit_statuses.append(OriginVisitStatus(**row_d)) if len(visit_statuses) > limit: # last visit status date is the next page token next_page_token = str(visit_statuses[-1].date) # excluding that visit status from the result to respect the limit size visit_statuses = visit_statuses[:limit] return PagedResult(results=visit_statuses, next_page_token=next_page_token) @timed @db_transaction() def origin_visit_status_get_random( self, type: str, db=None, cur=None ) -> Optional[OriginVisitStatus]: row = db.origin_visit_get_random(type, cur) if row is not None: row_d = dict(zip(db.origin_visit_status_cols, row)) return OriginVisitStatus(**row_d) return None @timed @db_transaction(statement_timeout=2000) def object_find_by_sha1_git( self, ids: List[Sha1Git], db=None, cur=None ) -> Dict[Sha1Git, List[Dict]]: ret: Dict[Sha1Git, List[Dict]] = {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 @timed @db_transaction(statement_timeout=500) def origin_get( self, origins: List[str], db=None, cur=None ) -> Iterable[Optional[Origin]]: rows = db.origin_get_by_url(origins, cur) result: List[Optional[Origin]] = [] for row in rows: origin_d = dict(zip(db.origin_cols, row)) url = origin_d["url"] result.append(None if url is None else Origin(url=url)) return result @timed @db_transaction(statement_timeout=500) def origin_get_by_sha1( self, sha1s: List[bytes], db=None, cur=None ) -> List[Optional[Dict[str, Any]]]: return [ dict(zip(db.origin_cols, row)) if row[0] else None for row in db.origin_get_by_sha1(sha1s, cur) ] @timed @db_transaction_generator() def origin_get_range(self, origin_from=1, origin_count=100, db=None, cur=None): for origin in db.origin_get_range(origin_from, origin_count, cur): yield dict(zip(db.origin_get_range_cols, origin)) @timed @db_transaction() def origin_list( self, page_token: Optional[str] = None, limit: int = 100, *, db=None, cur=None ) -> PagedResult[Origin]: page_token = page_token or "0" if not isinstance(page_token, str): raise StorageArgumentException("page_token must be a string.") origin_from = int(page_token) next_page_token = None origins: List[Origin] = [] # Take one more origin so we can reuse it as the next page token if any for row_d in self.origin_get_range(origin_from, limit + 1, db=db, cur=cur): origins.append(Origin(url=row_d["url"])) # keep the last_id for the pagination if needed last_id = row_d["id"] if len(origins) > limit: # data left for subsequent call # last origin id is the next page token next_page_token = str(last_id) # excluding that origin from the result to respect the limit size origins = origins[:limit] assert len(origins) <= limit return PagedResult(results=origins, next_page_token=next_page_token) @timed @db_transaction() def origin_search( self, url_pattern: str, page_token: Optional[str] = None, limit: int = 50, regexp: bool = False, with_visit: bool = False, visit_types: Optional[List[str]] = None, db=None, cur=None, ) -> PagedResult[Origin]: next_page_token = None offset = int(page_token) if page_token else 0 origins = [] # Take one more origin so we can reuse it as the next page token if any for origin in db.origin_search( url_pattern, offset, limit + 1, regexp, with_visit, visit_types, cur ): row_d = dict(zip(db.origin_cols, origin)) origins.append(Origin(url=row_d["url"])) if len(origins) > limit: # next offset next_page_token = str(offset + limit) # excluding that origin from the result to respect the limit size origins = origins[:limit] assert len(origins) <= limit return PagedResult(results=origins, next_page_token=next_page_token) @timed @db_transaction() def origin_count( self, url_pattern: str, regexp: bool = False, with_visit: bool = False, db=None, cur=None, ) -> int: return db.origin_count(url_pattern, regexp, with_visit, cur) @timed @process_metrics @db_transaction() def origin_add(self, origins: List[Origin], db=None, cur=None) -> Dict[str, int]: urls = [o.url for o in origins] known_origins = set(url for (url,) in db.origin_get_by_url(urls, cur)) # keep only one occurrence of each given origin while keeping the list # sorted as originally given to_add = sorted(set(urls) - known_origins, key=urls.index) self.journal_writer.origin_add([Origin(url=url) for url in to_add]) added = 0 for url in to_add: if db.origin_add(url, cur): added += 1 return {"origin:add": added} @db_transaction(statement_timeout=500) def stat_counters(self, db=None, cur=None): return {k: v for (k, v) in db.stat_counters()} @db_transaction() def refresh_stat_counters(self, db=None, cur=None): keys = [ "content", "directory", "directory_entry_dir", "directory_entry_file", "directory_entry_rev", "origin", "origin_visit", "person", "release", "revision", "revision_history", "skipped_content", "snapshot", ] for key in keys: cur.execute("select * from swh_update_counter(%s)", (key,)) @db_transaction() def raw_extrinsic_metadata_add( self, metadata: List[RawExtrinsicMetadata], db, cur, ) -> None: metadata = list(metadata) self.journal_writer.raw_extrinsic_metadata_add(metadata) counter = Counter[ExtendedObjectType]() for metadata_entry in metadata: authority_id = self._get_authority_id(metadata_entry.authority, db, cur) fetcher_id = self._get_fetcher_id(metadata_entry.fetcher, db, cur) db.raw_extrinsic_metadata_add( id=metadata_entry.id, type=metadata_entry.target.object_type.name.lower(), target=str(metadata_entry.target), discovery_date=metadata_entry.discovery_date, authority_id=authority_id, fetcher_id=fetcher_id, format=metadata_entry.format, metadata=metadata_entry.metadata, origin=metadata_entry.origin, visit=metadata_entry.visit, snapshot=map_optional(str, metadata_entry.snapshot), release=map_optional(str, metadata_entry.release), revision=map_optional(str, metadata_entry.revision), path=metadata_entry.path, directory=map_optional(str, metadata_entry.directory), cur=cur, ) counter[metadata_entry.target.object_type] += 1 for (type, count) in counter.items(): send_metric( f"{type.value}_metadata:add", count=count, method_name=f"{type.name.lower()}_metadata_add", ) @db_transaction() def raw_extrinsic_metadata_get( self, target: ExtendedSWHID, authority: MetadataAuthority, after: Optional[datetime.datetime] = None, page_token: Optional[bytes] = None, limit: int = 1000, db=None, cur=None, ) -> PagedResult[RawExtrinsicMetadata]: if page_token: (after_time, after_fetcher) = msgpack_loads(base64.b64decode(page_token)) if after and after_time < after: raise StorageArgumentException( "page_token is inconsistent with the value of 'after'." ) else: after_time = after after_fetcher = None authority_id = self._get_authority_id(authority, db, cur) if not authority_id: return PagedResult(next_page_token=None, results=[],) rows = db.raw_extrinsic_metadata_get( type, str(target), authority_id, after_time, after_fetcher, limit + 1, cur, ) rows = [dict(zip(db.raw_extrinsic_metadata_get_cols, row)) for row in rows] results = [] for row in rows: assert str(target) == row["raw_extrinsic_metadata.target"] results.append(converters.db_to_raw_extrinsic_metadata(row)) if len(results) > limit: results.pop() assert len(results) == limit last_returned_row = rows[-2] # rows[-1] corresponds to the popped result next_page_token: Optional[str] = base64.b64encode( msgpack_dumps( ( last_returned_row["discovery_date"], last_returned_row["metadata_fetcher.id"], ) ) ).decode() else: next_page_token = None return PagedResult(next_page_token=next_page_token, results=results,) @timed @db_transaction() def metadata_fetcher_add( self, fetchers: List[MetadataFetcher], db=None, cur=None ) -> None: fetchers = list(fetchers) self.journal_writer.metadata_fetcher_add(fetchers) count = 0 for fetcher in fetchers: if fetcher.metadata is None: raise StorageArgumentException( "MetadataFetcher.metadata may not be None in metadata_fetcher_add." ) db.metadata_fetcher_add( fetcher.name, fetcher.version, dict(fetcher.metadata), cur=cur ) count += 1 send_metric("metadata_fetcher:add", count=count, method_name="metadata_fetcher") @timed @db_transaction(statement_timeout=500) def metadata_fetcher_get( self, name: str, version: str, db=None, cur=None ) -> Optional[MetadataFetcher]: row = db.metadata_fetcher_get(name, version, cur=cur) if not row: return None return MetadataFetcher.from_dict(dict(zip(db.metadata_fetcher_cols, row))) @timed @db_transaction() def metadata_authority_add( self, authorities: List[MetadataAuthority], db=None, cur=None ) -> None: authorities = list(authorities) self.journal_writer.metadata_authority_add(authorities) count = 0 for authority in authorities: if authority.metadata is None: raise StorageArgumentException( "MetadataAuthority.metadata may not be None in " "metadata_authority_add." ) db.metadata_authority_add( authority.type.value, authority.url, dict(authority.metadata), cur=cur ) count += 1 send_metric( "metadata_authority:add", count=count, method_name="metadata_authority" ) @timed @db_transaction() def metadata_authority_get( self, type: MetadataAuthorityType, url: str, db=None, cur=None ) -> Optional[MetadataAuthority]: row = db.metadata_authority_get(type.value, url, cur=cur) if not row: return None return MetadataAuthority.from_dict(dict(zip(db.metadata_authority_cols, row))) def clear_buffers(self, object_types: Sequence[str] = ()) -> None: """Do nothing """ return None def flush(self, object_types: Sequence[str] = ()) -> Dict[str, int]: return {} def _get_authority_id(self, authority: MetadataAuthority, db, cur): authority_id = db.metadata_authority_get_id( authority.type.value, authority.url, cur ) if not authority_id: raise StorageArgumentException(f"Unknown authority {authority}") return authority_id def _get_fetcher_id(self, fetcher: MetadataFetcher, db, cur): fetcher_id = db.metadata_fetcher_get_id(fetcher.name, fetcher.version, cur) if not fetcher_id: raise StorageArgumentException(f"Unknown fetcher {fetcher}") return fetcher_id diff --git a/swh/storage/replay.py b/swh/storage/replay.py index 0516ba85..52ce8dd1 100644 --- a/swh/storage/replay.py +++ b/swh/storage/replay.py @@ -1,162 +1,179 @@ # Copyright (C) 2019-2020 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 logging -from typing import Any, Callable, Dict, Iterable, List +from typing import Any, Callable, Container, Dict, Iterable, List try: from systemd.daemon import notify except ImportError: notify = None from swh.core.statsd import statsd from swh.model.model import ( BaseContent, BaseModel, Content, Directory, ExtID, MetadataAuthority, MetadataFetcher, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Release, Revision, SkippedContent, Snapshot, ) from swh.storage.exc import HashCollision from swh.storage.fixer import fix_objects logger = logging.getLogger(__name__) GRAPH_OPERATIONS_METRIC = "swh_graph_replayer_operations_total" GRAPH_DURATION_METRIC = "swh_graph_replayer_duration_seconds" object_converter_fn: Dict[str, Callable[[Dict], BaseModel]] = { "origin": Origin.from_dict, "origin_visit": OriginVisit.from_dict, "origin_visit_status": OriginVisitStatus.from_dict, "snapshot": Snapshot.from_dict, "revision": Revision.from_dict, "release": Release.from_dict, "directory": Directory.from_dict, "content": Content.from_dict, "skipped_content": SkippedContent.from_dict, "metadata_authority": MetadataAuthority.from_dict, "metadata_fetcher": MetadataFetcher.from_dict, "raw_extrinsic_metadata": RawExtrinsicMetadata.from_dict, "extid": ExtID.from_dict, } def process_replay_objects(all_objects, *, storage): for (object_type, objects) in all_objects.items(): logger.debug("Inserting %s %s objects", len(objects), object_type) with statsd.timed(GRAPH_DURATION_METRIC, tags={"object_type": object_type}): _insert_objects(object_type, objects, storage) statsd.increment( GRAPH_OPERATIONS_METRIC, len(objects), tags={"object_type": object_type} ) if notify: notify("WATCHDOG=1") def collision_aware_content_add( content_add_fn: Callable[[Iterable[Any]], None], contents: List[BaseContent] ) -> None: """Add contents to storage. If a hash collision is detected, an error is logged. Then this adds the other non colliding contents to the storage. Args: content_add_fn: Storage content callable contents: List of contents or skipped contents to add to storage """ if not contents: return colliding_content_hashes: List[Dict[str, Any]] = [] while True: try: content_add_fn(contents) except HashCollision as e: colliding_content_hashes.append( { "algo": e.algo, "hash": e.hash_id, # hex hash id "objects": e.colliding_contents, # hex hashes } ) colliding_hashes = e.colliding_content_hashes() # Drop the colliding contents from the transaction contents = [c for c in contents if c.hashes() not in colliding_hashes] else: # Successfully added contents, we are done break if colliding_content_hashes: for collision in colliding_content_hashes: logger.error("Collision detected: %(collision)s", {"collision": collision}) +def dict_key_dropper(d: Dict, keys_to_drop: Container) -> Dict: + """Returns a copy of the dict d without any key listed in keys_to_drop""" + return {k: v for (k, v) in d.items() if k not in keys_to_drop} + + def _insert_objects(object_type: str, objects: List[Dict], storage) -> None: """Insert objects of type object_type in the storage. """ objects = fix_objects(object_type, objects) if object_type == "content": # for bw compat, skipped content should now be delivered in the skipped_content # topic contents: List[BaseContent] = [] skipped_contents: List[BaseContent] = [] for content in objects: c = BaseContent.from_dict(content) if isinstance(c, SkippedContent): logger.warning( "Received a series of skipped_content in the " "content topic, this should not happen anymore" ) skipped_contents.append(c) else: contents.append(c) collision_aware_content_add(storage.skipped_content_add, skipped_contents) collision_aware_content_add(storage.content_add_metadata, contents) elif object_type == "skipped_content": skipped_contents = [SkippedContent.from_dict(obj) for obj in objects] collision_aware_content_add(storage.skipped_content_add, skipped_contents) elif object_type in ("origin_visit", "origin_visit_status"): origins: List[Origin] = [] converter_fn = object_converter_fn[object_type] model_objs = [] for obj in objects: origins.append(Origin(url=obj["origin"])) model_objs.append(converter_fn(obj)) storage.origin_add(origins) method = getattr(storage, f"{object_type}_add") method(model_objs) elif object_type == "raw_extrinsic_metadata": converted = [RawExtrinsicMetadata.from_dict(o) for o in objects] authorities = {emd.authority for emd in converted} fetchers = {emd.fetcher for emd in converted} storage.metadata_authority_add(authorities) storage.metadata_fetcher_add(fetchers) storage.raw_extrinsic_metadata_add(converted) + elif object_type == "revision": + # drop the metadata field from the revision (is any); this field is + # about to be dropped from the data model (in favor of + # raw_extrinsic_metadata) and there can be bogus values in the existing + # journal (metadata with \0000 in it) + method = getattr(storage, object_type + "_add") + method( + [ + object_converter_fn[object_type](dict_key_dropper(o, ("metadata",))) + for o in objects + ] + ) elif object_type in ( "directory", "extid", "revision", "release", "snapshot", "origin", "metadata_fetcher", "metadata_authority", ): method = getattr(storage, object_type + "_add") method([object_converter_fn[object_type](o) for o in objects]) else: logger.warning("Received a series of %s, this should not happen", object_type) diff --git a/swh/storage/tests/storage_tests.py b/swh/storage/tests/storage_tests.py index 4904f14c..f5c904db 100644 --- a/swh/storage/tests/storage_tests.py +++ b/swh/storage/tests/storage_tests.py @@ -1,4347 +1,4363 @@ # Copyright (C) 2015-2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from collections import defaultdict import datetime from datetime import timedelta import inspect import itertools import math import random from typing import Any, ClassVar, Dict, Iterator, Optional from unittest.mock import MagicMock import attr from hypothesis import HealthCheck, given, settings, strategies import pytest from swh.model import from_disk from swh.model.hashutil import hash_to_bytes from swh.model.hypothesis_strategies import objects from swh.model.identifiers import CoreSWHID, ObjectType from swh.model.model import ( Content, Directory, ExtID, Origin, OriginVisit, OriginVisitStatus, Person, RawExtrinsicMetadata, Revision, SkippedContent, Snapshot, SnapshotBranch, TargetType, ) from swh.storage import get_storage from swh.storage.common import origin_url_to_sha1 as sha1 from swh.storage.exc import HashCollision, StorageArgumentException from swh.storage.interface import ListOrder, PagedResult, StorageInterface from swh.storage.tests.conftest import function_scoped_fixture_check from swh.storage.utils import ( content_hex_hashes, now, remove_keys, round_to_milliseconds, ) def transform_entries( storage: StorageInterface, dir_: Directory, *, prefix: bytes = b"" ) -> Iterator[Dict[str, Any]]: """Iterate through a directory's entries, and yields the items 'directory_ls' is expected to return; including content metadata for file entries.""" for ent in dir_.entries: if ent.type == "dir": yield { "dir_id": dir_.id, "type": ent.type, "target": ent.target, "name": prefix + ent.name, "perms": ent.perms, "status": None, "sha1": None, "sha1_git": None, "sha256": None, "length": None, } elif ent.type == "file": contents = storage.content_find({"sha1_git": ent.target}) assert contents ent_dict = contents[0].to_dict() for key in ["ctime", "blake2s256"]: ent_dict.pop(key, None) ent_dict.update( { "dir_id": dir_.id, "type": ent.type, "target": ent.target, "name": prefix + ent.name, "perms": ent.perms, } ) yield ent_dict def assert_contents_ok( expected_contents, actual_contents, keys_to_check={"sha1", "data"} ): """Assert that a given list of contents matches on a given set of keys. """ for k in keys_to_check: expected_list = set([c.get(k) for c in expected_contents]) actual_list = set([c.get(k) for c in actual_contents]) assert actual_list == expected_list, k class LazyContent(Content): def with_data(self): return Content.from_dict({**self.to_dict(), "data": b"42\n"}) class TestStorage: """Main 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. """ maxDiff = None # type: ClassVar[Optional[int]] def test_types(self, swh_storage_backend_config): """Checks all methods of StorageInterface are implemented by this backend, and that they have the same signature.""" # Create an instance of the protocol (which cannot be instantiated # directly, so this creates a subclass, then instantiates it) interface = type("_", (StorageInterface,), {})() storage = get_storage(**swh_storage_backend_config) assert "content_add" in dir(interface) missing_methods = [] for meth_name in dir(interface): if meth_name.startswith("_"): continue interface_meth = getattr(interface, meth_name) try: concrete_meth = getattr(storage, meth_name) except AttributeError: if not getattr(interface_meth, "deprecated_endpoint", False): # The backend is missing a (non-deprecated) endpoint missing_methods.append(meth_name) continue expected_signature = inspect.signature(interface_meth) actual_signature = inspect.signature(concrete_meth) assert expected_signature == actual_signature, meth_name assert missing_methods == [] # If all the assertions above succeed, then this one should too. # But there's no harm in double-checking. # And we could replace the assertions above by this one, but unlike # the assertions above, it doesn't explain what is missing. assert isinstance(storage, StorageInterface) def test_check_config(self, swh_storage): assert swh_storage.check_config(check_write=True) assert swh_storage.check_config(check_write=False) def test_content_add(self, swh_storage, sample_data): cont = sample_data.content insertion_start_time = now() actual_result = swh_storage.content_add([cont]) insertion_end_time = now() assert actual_result == { "content:add": 1, "content:add:bytes": cont.length, } assert swh_storage.content_get_data(cont.sha1) == cont.data expected_cont = attr.evolve(cont, data=None) contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: assert insertion_start_time <= obj.ctime assert obj.ctime <= insertion_end_time assert obj == expected_cont swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_add_from_lazy_content(self, swh_storage, sample_data): cont = sample_data.content lazy_content = LazyContent.from_dict(cont.to_dict()) insertion_start_time = now() actual_result = swh_storage.content_add([lazy_content]) insertion_end_time = now() assert actual_result == { "content:add": 1, "content:add:bytes": cont.length, } # the fact that we retrieve the content object from the storage with # the correct 'data' field ensures it has been 'called' assert swh_storage.content_get_data(cont.sha1) == cont.data expected_cont = attr.evolve(lazy_content, data=None, ctime=None) contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: assert insertion_start_time <= obj.ctime assert obj.ctime <= insertion_end_time assert attr.evolve(obj, ctime=None).to_dict() == expected_cont.to_dict() swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_get_data_missing(self, swh_storage, sample_data): cont, cont2 = sample_data.contents[:2] swh_storage.content_add([cont]) # Query a single missing content actual_content_data = swh_storage.content_get_data(cont2.sha1) assert actual_content_data is None # Check content_get does not abort after finding a missing content actual_content_data = swh_storage.content_get_data(cont.sha1) assert actual_content_data == cont.data actual_content_data = swh_storage.content_get_data(cont2.sha1) assert actual_content_data is None def test_content_add_different_input(self, swh_storage, sample_data): cont, cont2 = sample_data.contents[:2] actual_result = swh_storage.content_add([cont, cont2]) assert actual_result == { "content:add": 2, "content:add:bytes": cont.length + cont2.length, } def test_content_add_twice(self, swh_storage, sample_data): cont, cont2 = sample_data.contents[:2] actual_result = swh_storage.content_add([cont]) assert actual_result == { "content:add": 1, "content:add:bytes": cont.length, } assert len(swh_storage.journal_writer.journal.objects) == 1 actual_result = swh_storage.content_add([cont, cont2]) assert actual_result == { "content:add": 1, "content:add:bytes": cont2.length, } assert 2 <= len(swh_storage.journal_writer.journal.objects) <= 3 assert len(swh_storage.content_find(cont.to_dict())) == 1 assert len(swh_storage.content_find(cont2.to_dict())) == 1 def test_content_add_collision(self, swh_storage, sample_data): cont1 = sample_data.content # create (corrupted) content with same sha1{,_git} but != sha256 sha256_array = bytearray(cont1.sha256) sha256_array[0] += 1 cont1b = attr.evolve(cont1, sha256=bytes(sha256_array)) with pytest.raises(HashCollision) as cm: swh_storage.content_add([cont1, cont1b]) exc = cm.value actual_algo = exc.algo assert actual_algo in ["sha1", "sha1_git"] actual_id = exc.hash_id assert actual_id == getattr(cont1, actual_algo).hex() collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(cont1.hashes()), content_hex_hashes(cont1b.hashes()), ] assert exc.colliding_content_hashes() == [ cont1.hashes(), cont1b.hashes(), ] def test_content_add_duplicate(self, swh_storage, sample_data): cont = sample_data.content swh_storage.content_add([cont, cont]) assert swh_storage.content_get_data(cont.sha1) == cont.data def test_content_update(self, swh_storage, sample_data): cont1 = sample_data.content if hasattr(swh_storage, "journal_writer"): swh_storage.journal_writer.journal = None # TODO, not supported swh_storage.content_add([cont1]) # alter the sha1_git for example cont1b = attr.evolve( cont1, sha1_git=hash_to_bytes("3a60a5275d0333bf13468e8b3dcab90f4046e654") ) swh_storage.content_update([cont1b.to_dict()], keys=["sha1_git"]) actual_contents = swh_storage.content_get([cont1.sha1]) expected_content = attr.evolve(cont1b, data=None) assert actual_contents == [expected_content] def test_content_add_metadata(self, swh_storage, sample_data): cont = attr.evolve(sample_data.content, data=None, ctime=now()) actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { "content:add": 1, } expected_cont = cont assert swh_storage.content_get([cont.sha1]) == [expected_cont] contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: obj = attr.evolve(obj, ctime=None) assert obj == cont def test_content_add_metadata_different_input(self, swh_storage, sample_data): contents = sample_data.contents[:2] cont = attr.evolve(contents[0], data=None, ctime=now()) cont2 = attr.evolve(contents[1], data=None, ctime=now()) actual_result = swh_storage.content_add_metadata([cont, cont2]) assert actual_result == { "content:add": 2, } def test_content_add_metadata_collision(self, swh_storage, sample_data): cont1 = attr.evolve(sample_data.content, data=None, ctime=now()) # create (corrupted) content with same sha1{,_git} but != sha256 sha1_git_array = bytearray(cont1.sha256) sha1_git_array[0] += 1 cont1b = attr.evolve(cont1, sha256=bytes(sha1_git_array)) with pytest.raises(HashCollision) as cm: swh_storage.content_add_metadata([cont1, cont1b]) exc = cm.value actual_algo = exc.algo assert actual_algo in ["sha1", "sha1_git", "blake2s256"] actual_id = exc.hash_id assert actual_id == getattr(cont1, actual_algo).hex() collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(cont1.hashes()), content_hex_hashes(cont1b.hashes()), ] assert exc.colliding_content_hashes() == [ cont1.hashes(), cont1b.hashes(), ] def test_content_add_objstorage_first(self, swh_storage, sample_data): """Tests the objstorage is written to before the DB and journal""" cont = sample_data.content swh_storage.objstorage.content_add = MagicMock(side_effect=Exception("Oops")) # Try to add, but the objstorage crashes try: swh_storage.content_add([cont]) except Exception: pass # The DB must be written to after the objstorage, so the DB should be # unchanged if the objstorage crashed assert swh_storage.content_get_data(cont.sha1) is None # The journal too assert list(swh_storage.journal_writer.journal.objects) == [] def test_skipped_content_add(self, swh_storage, sample_data): contents = sample_data.skipped_contents[:2] cont = contents[0] cont2 = attr.evolve(contents[1], blake2s256=None) contents_dict = [c.to_dict() for c in [cont, cont2]] missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [cont.hashes(), cont2.hashes()] actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [] def test_skipped_content_add_missing_hashes(self, swh_storage, sample_data): cont, cont2 = [ attr.evolve(c, sha1_git=None) for c in sample_data.skipped_contents[:2] ] contents_dict = [c.to_dict() for c in [cont, cont2]] missing = list(swh_storage.skipped_content_missing(contents_dict)) assert len(missing) == 2 actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [] def test_skipped_content_missing_partial_hash(self, swh_storage, sample_data): cont = sample_data.skipped_content cont2 = attr.evolve(cont, sha1_git=None) contents_dict = [c.to_dict() for c in [cont, cont2]] missing = list(swh_storage.skipped_content_missing(contents_dict)) assert len(missing) == 2 actual_result = swh_storage.skipped_content_add([cont]) assert actual_result.pop("skipped_content:add") == 1 assert actual_result == {} missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [cont2.hashes()] @pytest.mark.property_based @settings( deadline=None, # this test is very slow suppress_health_check=function_scoped_fixture_check, ) @given( strategies.sets( elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), min_size=0, ) ) def test_content_missing(self, swh_storage, sample_data, algos): algos |= {"sha1"} content, missing_content = [sample_data.content2, sample_data.skipped_content] swh_storage.content_add([content]) test_contents = [content.to_dict()] missing_per_hash = defaultdict(list) for i in range(256): test_content = missing_content.to_dict() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_contents.append(test_content) assert set(swh_storage.content_missing(test_contents)) == set( missing_per_hash["sha1"] ) for hash in algos: assert set( swh_storage.content_missing(test_contents, key_hash=hash) ) == set(missing_per_hash[hash]) @pytest.mark.property_based @settings(suppress_health_check=function_scoped_fixture_check,) @given( strategies.sets( elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), min_size=0, ) ) def test_content_missing_unknown_algo(self, swh_storage, sample_data, algos): algos |= {"sha1"} content, missing_content = [sample_data.content2, sample_data.skipped_content] swh_storage.content_add([content]) test_contents = [content.to_dict()] missing_per_hash = defaultdict(list) for i in range(16): test_content = missing_content.to_dict() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_content["nonexisting_algo"] = b"\x00" test_contents.append(test_content) assert set(swh_storage.content_missing(test_contents)) == set( missing_per_hash["sha1"] ) for hash in algos: assert set( swh_storage.content_missing(test_contents, key_hash=hash) ) == set(missing_per_hash[hash]) def test_content_missing_per_sha1(self, swh_storage, sample_data): # given cont = sample_data.content cont2 = sample_data.content2 missing_cont = sample_data.skipped_content missing_cont2 = sample_data.skipped_content2 swh_storage.content_add([cont, cont2]) # when gen = swh_storage.content_missing_per_sha1( [cont.sha1, missing_cont.sha1, cont2.sha1, missing_cont2.sha1] ) # then assert list(gen) == [missing_cont.sha1, missing_cont2.sha1] def test_content_missing_per_sha1_git(self, swh_storage, sample_data): cont, cont2 = sample_data.contents[:2] missing_cont = sample_data.skipped_content missing_cont2 = sample_data.skipped_content2 swh_storage.content_add([cont, cont2]) contents = [ cont.sha1_git, cont2.sha1_git, missing_cont.sha1_git, missing_cont2.sha1_git, ] missing_contents = swh_storage.content_missing_per_sha1_git(contents) assert list(missing_contents) == [missing_cont.sha1_git, missing_cont2.sha1_git] missing_contents = swh_storage.content_missing_per_sha1_git([]) assert list(missing_contents) == [] def test_content_get_partition(self, swh_storage, swh_contents): """content_get_partition paginates results if limit exceeded""" expected_contents = [ attr.evolve(c, data=None) for c in swh_contents if c.status != "absent" ] actual_contents = [] for i in range(16): actual_result = swh_storage.content_get_partition(i, 16) assert actual_result.next_page_token is None actual_contents.extend(actual_result.results) assert len(actual_contents) == len(expected_contents) for content in actual_contents: assert content in expected_contents assert content.ctime is None def test_content_get_partition_full(self, swh_storage, swh_contents): """content_get_partition for a single partition returns all available contents """ expected_contents = [ attr.evolve(c, data=None) for c in swh_contents if c.status != "absent" ] actual_result = swh_storage.content_get_partition(0, 1) assert actual_result.next_page_token is None actual_contents = actual_result.results assert len(actual_contents) == len(expected_contents) for content in actual_contents: assert content in expected_contents def test_content_get_partition_empty(self, swh_storage, swh_contents): """content_get_partition when at least one of the partitions is empty""" expected_contents = { cont.sha1 for cont in swh_contents if cont.status != "absent" } # nb_partitions = smallest power of 2 such that at least one of # the partitions is empty nb_partitions = 1 << math.floor(math.log2(len(swh_contents)) + 1) seen_sha1s = [] for i in range(nb_partitions): actual_result = swh_storage.content_get_partition( i, nb_partitions, limit=len(swh_contents) + 1 ) for content in actual_result.results: seen_sha1s.append(content.sha1) # Limit is higher than the max number of results assert actual_result.next_page_token is None assert set(seen_sha1s) == expected_contents def test_content_get_partition_limit_none(self, swh_storage): """content_get_partition call with wrong limit input should fail""" with pytest.raises(StorageArgumentException, match="limit should not be None"): swh_storage.content_get_partition(1, 16, limit=None) def test_content_get_partition_pagination_generate(self, swh_storage, swh_contents): """content_get_partition returns contents within range provided""" expected_contents = [ attr.evolve(c, data=None) for c in swh_contents if c.status != "absent" ] # retrieve contents actual_contents = [] for i in range(4): page_token = None while True: actual_result = swh_storage.content_get_partition( i, 4, limit=3, page_token=page_token ) actual_contents.extend(actual_result.results) page_token = actual_result.next_page_token if page_token is None: break assert len(actual_contents) == len(expected_contents) for content in actual_contents: assert content in expected_contents def test_content_get(self, swh_storage, sample_data): cont1, cont2 = sample_data.contents[:2] swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get([cont1.sha1, cont2.sha1]) # we only retrieve the metadata so no data nor ctime within expected_contents = [attr.evolve(c, data=None) for c in [cont1, cont2]] assert actual_contents == expected_contents for content in actual_contents: assert content.ctime is None def test_content_get_missing_sha1(self, swh_storage, sample_data): cont1, cont2 = sample_data.contents[:2] assert cont1.sha1 != cont2.sha1 missing_cont = sample_data.skipped_content swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get( [cont1.sha1, cont2.sha1, missing_cont.sha1] ) expected_contents = [ attr.evolve(c, data=None) if c else None for c in [cont1, cont2, None] ] assert actual_contents == expected_contents def test_content_get_random(self, swh_storage, sample_data): cont, cont2, cont3 = sample_data.contents[:3] swh_storage.content_add([cont, cont2, cont3]) assert swh_storage.content_get_random() in { cont.sha1_git, cont2.sha1_git, cont3.sha1_git, } def test_directory_add(self, swh_storage, sample_data): content = sample_data.content directory = sample_data.directories[1] assert directory.entries[0].target == content.sha1_git swh_storage.content_add([content]) init_missing = list(swh_storage.directory_missing([directory.id])) assert [directory.id] == init_missing actual_result = swh_storage.directory_add([directory]) assert actual_result == {"directory:add": 1} assert ("directory", directory) in list( swh_storage.journal_writer.journal.objects ) actual_data = list(swh_storage.directory_ls(directory.id)) expected_data = list(transform_entries(swh_storage, directory)) for data in actual_data: assert data in expected_data after_missing = list(swh_storage.directory_missing([directory.id])) assert after_missing == [] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["directory"] == 1 def test_directory_add_twice(self, swh_storage, sample_data): directory = sample_data.directories[1] actual_result = swh_storage.directory_add([directory]) assert actual_result == {"directory:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", directory) ] actual_result = swh_storage.directory_add([directory]) assert actual_result == {"directory:add": 0} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", directory) ] def test_directory_ls_recursive(self, swh_storage, sample_data): # create consistent dataset regarding the directories we want to list content, content2 = sample_data.contents[:2] swh_storage.content_add([content, content2]) dir1, dir2, dir3 = sample_data.directories[:3] dir_ids = [d.id for d in [dir1, dir2, dir3]] init_missing = list(swh_storage.directory_missing(dir_ids)) assert init_missing == dir_ids actual_result = swh_storage.directory_add([dir1, dir2, dir3]) assert actual_result == {"directory:add": 3} # List directory containing one file actual_data = list(swh_storage.directory_ls(dir1.id, recursive=True)) expected_data = list(transform_entries(swh_storage, dir1)) for data in actual_data: assert data in expected_data # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(dir2.id, recursive=True)) expected_data = list(transform_entries(swh_storage, dir2)) for data in actual_data: assert data in expected_data # List directory containing both a known and unknown subdirectory, entries # should be both those of the directory and of the known subdir (up to contents) actual_data = list(swh_storage.directory_ls(dir3.id, recursive=True)) expected_data = list( itertools.chain( transform_entries(swh_storage, dir3), transform_entries(swh_storage, dir2, prefix=b"subdir/"), ) ) for data in actual_data: assert data in expected_data def test_directory_ls_non_recursive(self, swh_storage, sample_data): # create consistent dataset regarding the directories we want to list content, content2 = sample_data.contents[:2] swh_storage.content_add([content, content2]) dir1, dir2, dir3, _, dir5 = sample_data.directories[:5] dir_ids = [d.id for d in [dir1, dir2, dir3, dir5]] init_missing = list(swh_storage.directory_missing(dir_ids)) assert init_missing == dir_ids actual_result = swh_storage.directory_add([dir1, dir2, dir3, dir5]) assert actual_result == {"directory:add": 4} # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(dir1.id)) expected_data = list(transform_entries(swh_storage, dir1)) for data in actual_data: assert data in expected_data # List directory containing a single file actual_data = list(swh_storage.directory_ls(dir2.id)) expected_data = list(transform_entries(swh_storage, dir2)) for data in actual_data: assert data in expected_data # List directory containing a known subdirectory, entries should # only be those of the parent directory, not of the subdir actual_data = list(swh_storage.directory_ls(dir3.id)) expected_data = list(transform_entries(swh_storage, dir3)) for data in actual_data: assert data in expected_data def test_directory_ls_missing_content(self, swh_storage, sample_data): swh_storage.directory_add([sample_data.directory2]) assert list(swh_storage.directory_ls(sample_data.directory2.id)) == [ { "dir_id": sample_data.directory2.id, "length": None, "name": b"oof", "perms": 33188, "sha1": None, "sha1_git": None, "sha256": None, "status": None, "target": sample_data.directory2.entries[0].target, "type": "file", }, ] def test_directory_ls_skipped_content(self, swh_storage, sample_data): swh_storage.directory_add([sample_data.directory2]) cont = SkippedContent( sha1_git=sample_data.directory2.entries[0].target, sha1=b"c" * 20, sha256=None, blake2s256=None, length=42, status="absent", reason="You need a premium subscription to access this content", ) swh_storage.skipped_content_add([cont]) assert list(swh_storage.directory_ls(sample_data.directory2.id)) == [ { "dir_id": sample_data.directory2.id, "length": 42, "name": b"oof", "perms": 33188, "sha1": b"c" * 20, "sha1_git": sample_data.directory2.entries[0].target, "sha256": None, "status": "absent", "target": sample_data.directory2.entries[0].target, "type": "file", }, ] def test_directory_entry_get_by_path(self, swh_storage, sample_data): cont, content2 = sample_data.contents[:2] dir1, dir2, dir3, dir4, dir5 = sample_data.directories[:5] # given dir_ids = [d.id for d in [dir1, dir2, dir3, dir4, dir5]] init_missing = list(swh_storage.directory_missing(dir_ids)) assert init_missing == dir_ids actual_result = swh_storage.directory_add([dir3, dir4]) assert actual_result == {"directory:add": 2} expected_entries = [ { "dir_id": dir3.id, "name": b"foo", "type": "file", "target": cont.sha1_git, "sha1": None, "sha1_git": None, "sha256": None, "status": None, "perms": from_disk.DentryPerms.content, "length": None, }, { "dir_id": dir3.id, "name": b"subdir", "type": "dir", "target": dir2.id, "sha1": None, "sha1_git": None, "sha256": None, "status": None, "perms": from_disk.DentryPerms.directory, "length": None, }, { "dir_id": dir3.id, "name": b"hello", "type": "file", "target": content2.sha1_git, "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(dir3.entries, expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( dir3.id, [entry.name] ) assert actual_entry == expected_entry # same, but deeper for entry, expected_entry in zip(dir3.entries, expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( dir4.id, [b"subdir1", entry.name] ) expected_entry = expected_entry.copy() expected_entry["name"] = b"subdir1/" + expected_entry["name"] assert actual_entry == expected_entry # when (nothing should be found here since `dir` is not persisted.) for entry in dir2.entries: actual_entry = swh_storage.directory_entry_get_by_path( dir2.id, [entry.name] ) assert actual_entry is None def test_directory_get_random(self, swh_storage, sample_data): dir1, dir2, dir3 = sample_data.directories[:3] swh_storage.directory_add([dir1, dir2, dir3]) assert swh_storage.directory_get_random() in { dir1.id, dir2.id, dir3.id, } def test_revision_add(self, swh_storage, sample_data): revision = sample_data.revision init_missing = swh_storage.revision_missing([revision.id]) assert list(init_missing) == [revision.id] actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} end_missing = swh_storage.revision_missing([revision.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision) ] # already there so nothing added actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["revision"] == 1 def test_revision_add_twice(self, swh_storage, sample_data): revision, revision2 = sample_data.revisions[:2] actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision) ] actual_result = swh_storage.revision_add([revision, revision2]) assert actual_result == {"revision:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision), ("revision", revision2), ] def test_revision_add_name_clash(self, swh_storage, sample_data): revision, revision2 = sample_data.revisions[:2] revision1 = attr.evolve( revision, author=Person( fullname=b"John Doe ", name=b"John Doe", email=b"john.doe@example.com", ), ) revision2 = attr.evolve( revision2, author=Person( fullname=b"John Doe ", name=b"John Doe ", email=b"john.doe@example.com ", ), ) actual_result = swh_storage.revision_add([revision1, revision2]) assert actual_result == {"revision:add": 2} def test_revision_get_order(self, swh_storage, sample_data): revision, revision2 = sample_data.revisions[:2] add_result = swh_storage.revision_add([revision, revision2]) assert add_result == {"revision:add": 2} # order 1 actual_revisions = swh_storage.revision_get([revision.id, revision2.id]) assert actual_revisions == [revision, revision2] # order 2 actual_revisions2 = swh_storage.revision_get([revision2.id, revision.id]) assert actual_revisions2 == [revision2, revision] def test_revision_log(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # rev4 -is-child-of-> rev3 -> rev1, (rev2 -> rev1) swh_storage.revision_add([revision1, revision2, revision3, revision4]) # when results = list(swh_storage.revision_log([revision4.id])) # for comparison purposes actual_results = [Revision.from_dict(r) for r in results] assert len(actual_results) == 4 # rev4 -child-> rev3 -> rev1, (rev2 -> rev1) assert actual_results == [revision4, revision3, revision1, revision2] def test_revision_log_with_limit(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # revision4 -is-child-of-> revision3 swh_storage.revision_add([revision3, revision4]) results = list(swh_storage.revision_log([revision4.id], 1)) actual_results = [Revision.from_dict(r) for r in results] assert len(actual_results) == 1 assert actual_results[0] == revision4 def test_revision_log_unknown_revision(self, swh_storage, sample_data): revision = sample_data.revision rev_log = list(swh_storage.revision_log([revision.id])) assert rev_log == [] def test_revision_shortlog(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # rev4 -is-child-of-> rev3 -> (rev1, rev2); rev2 -> rev1 swh_storage.revision_add([revision1, revision2, revision3, revision4]) results = list(swh_storage.revision_shortlog([revision4.id])) actual_results = [[id, tuple(parents)] for (id, parents) in results] assert len(actual_results) == 4 assert actual_results == [ [revision4.id, revision4.parents], [revision3.id, revision3.parents], [revision1.id, revision1.parents], [revision2.id, revision2.parents], ] def test_revision_shortlog_with_limit(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # revision4 -is-child-of-> revision3 swh_storage.revision_add([revision1, revision2, revision3, revision4]) results = list(swh_storage.revision_shortlog([revision4.id], 1)) actual_results = [[id, tuple(parents)] for (id, parents) in results] assert len(actual_results) == 1 assert list(actual_results[0]) == [revision4.id, revision4.parents] def test_revision_get(self, swh_storage, sample_data): revision, revision2 = sample_data.revisions[:2] swh_storage.revision_add([revision]) actual_revisions = swh_storage.revision_get([revision.id, revision2.id]) assert len(actual_revisions) == 2 assert actual_revisions == [revision, None] def test_revision_get_no_parents(self, swh_storage, sample_data): revision = sample_data.revision swh_storage.revision_add([revision]) actual_revision = swh_storage.revision_get([revision.id])[0] assert revision.parents == () assert actual_revision.parents == () # no parents on this one def test_revision_get_random(self, swh_storage, sample_data): revision1, revision2, revision3 = sample_data.revisions[:3] swh_storage.revision_add([revision1, revision2, revision3]) assert swh_storage.revision_get_random() in { revision1.id, revision2.id, revision3.id, } def test_extid_add_git(self, swh_storage, sample_data): gitids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=gitid, extid_type="git", target=CoreSWHID(object_id=gitid, object_type=ObjectType.REVISION,), ) for gitid in gitids ] assert swh_storage.extid_get_from_extid("git", gitids) == [] assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == [] summary = swh_storage.extid_add(extids) assert summary == {"extid:add": len(gitids)} assert swh_storage.extid_get_from_extid("git", gitids) == extids assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == extids assert swh_storage.extid_get_from_extid("hg", gitids) == [] assert swh_storage.extid_get_from_target(ObjectType.RELEASE, gitids) == [] + # check ExtIDs have been added to the journal + extids_in_journal = [ + obj + for (obj_type, obj) in swh_storage.journal_writer.journal.objects + if obj_type == "extid" + ] + assert extids == extids_in_journal + def test_extid_add_hg(self, swh_storage, sample_data): def get_node(revision): node = None if revision.extra_headers: node = dict(revision.extra_headers).get(b"node") if node is None and revision.metadata: node = hash_to_bytes(revision.metadata.get("node")) return node swhids = [ revision.id for revision in sample_data.revisions if revision.type.value == "hg" ] extids = [ get_node(revision) for revision in sample_data.revisions if revision.type.value == "hg" ] assert swh_storage.extid_get_from_extid("hg", extids) == [] assert swh_storage.extid_get_from_target(ObjectType.REVISION, swhids) == [] extid_objs = [ ExtID( extid=hgid, extid_type="hg", target=CoreSWHID(object_id=swhid, object_type=ObjectType.REVISION,), ) for hgid, swhid in zip(extids, swhids) ] summary = swh_storage.extid_add(extid_objs) assert summary == {"extid:add": len(swhids)} assert swh_storage.extid_get_from_extid("hg", extids) == extid_objs assert ( swh_storage.extid_get_from_target(ObjectType.REVISION, swhids) == extid_objs ) assert swh_storage.extid_get_from_extid("git", extids) == [] assert swh_storage.extid_get_from_target(ObjectType.RELEASE, swhids) == [] + # check ExtIDs have been added to the journal + extids_in_journal = [ + obj + for (obj_type, obj) in swh_storage.journal_writer.journal.objects + if obj_type == "extid" + ] + assert extid_objs == extids_in_journal + def test_extid_add_twice(self, swh_storage, sample_data): gitids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=gitid, extid_type="git", target=CoreSWHID(object_id=gitid, object_type=ObjectType.REVISION,), ) for gitid in gitids ] summary = swh_storage.extid_add(extids) assert summary == {"extid:add": len(gitids)} # add them again, should be noop summary = swh_storage.extid_add(extids) # assert summary == {"extid:add": 0} assert swh_storage.extid_get_from_extid("git", gitids) == extids assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == extids def test_extid_add_extid_multicity(self, swh_storage, sample_data): ids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=extid, extid_type="git", target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,), ) for extid in ids ] swh_storage.extid_add(extids) # try to add "modified-extid" versions, should be added extids2 = [ ExtID( extid=extid, extid_type="hg", target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,), ) for extid in ids ] swh_storage.extid_add(extids2) assert swh_storage.extid_get_from_extid("git", ids) == extids assert swh_storage.extid_get_from_extid("hg", ids) == extids2 assert set(swh_storage.extid_get_from_target(ObjectType.REVISION, ids)) == { *extids, *extids2, } def test_extid_add_target_multicity(self, swh_storage, sample_data): ids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=extid, extid_type="git", target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,), ) for extid in ids ] swh_storage.extid_add(extids) # try to add "modified" versions, should be added extids2 = [ ExtID( extid=extid, extid_type="git", target=CoreSWHID(object_id=extid, object_type=ObjectType.RELEASE,), ) for extid in ids ] swh_storage.extid_add(extids2) assert set(swh_storage.extid_get_from_extid("git", ids)) == {*extids, *extids2} assert swh_storage.extid_get_from_target(ObjectType.REVISION, ids) == extids assert swh_storage.extid_get_from_target(ObjectType.RELEASE, ids) == extids2 def test_release_add(self, swh_storage, sample_data): release, release2 = sample_data.releases[:2] init_missing = swh_storage.release_missing([release.id, release2.id]) assert list(init_missing) == [release.id, release2.id] actual_result = swh_storage.release_add([release, release2]) assert actual_result == {"release:add": 2} end_missing = swh_storage.release_missing([release.id, release2.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("release", release), ("release", release2), ] # already present so nothing added actual_result = swh_storage.release_add([release, release2]) assert actual_result == {"release:add": 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["release"] == 2 def test_release_add_no_author_date(self, swh_storage, sample_data): full_release = sample_data.release release = attr.evolve(full_release, author=None, date=None) actual_result = swh_storage.release_add([release]) assert actual_result == {"release:add": 1} end_missing = swh_storage.release_missing([release.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("release", release) ] def test_release_add_twice(self, swh_storage, sample_data): release, release2 = sample_data.releases[:2] actual_result = swh_storage.release_add([release]) assert actual_result == {"release:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("release", release) ] actual_result = swh_storage.release_add([release, release2, release, release2]) assert actual_result == {"release:add": 1} assert set(swh_storage.journal_writer.journal.objects) == set( [("release", release), ("release", release2),] ) def test_release_add_name_clash(self, swh_storage, sample_data): release, release2 = [ attr.evolve( c, author=Person( fullname=b"John Doe ", name=b"John Doe", email=b"john.doe@example.com", ), ) for c in sample_data.releases[:2] ] actual_result = swh_storage.release_add([release, release2]) assert actual_result == {"release:add": 2} def test_release_get(self, swh_storage, sample_data): release, release2, release3 = sample_data.releases[:3] # given swh_storage.release_add([release, release2]) # when actual_releases = swh_storage.release_get([release.id, release2.id]) # then assert actual_releases == [release, release2] unknown_releases = swh_storage.release_get([release3.id]) assert unknown_releases[0] is None def test_release_get_order(self, swh_storage, sample_data): release, release2 = sample_data.releases[:2] add_result = swh_storage.release_add([release, release2]) assert add_result == {"release:add": 2} # order 1 actual_releases = swh_storage.release_get([release.id, release2.id]) assert actual_releases == [release, release2] # order 2 actual_releases2 = swh_storage.release_get([release2.id, release.id]) assert actual_releases2 == [release2, release] def test_release_get_random(self, swh_storage, sample_data): release, release2, release3 = sample_data.releases[:3] swh_storage.release_add([release, release2, release3]) assert swh_storage.release_get_random() in { release.id, release2.id, release3.id, } def test_origin_add(self, swh_storage, sample_data): origins = list(sample_data.origins[:2]) origin_urls = [o.url for o in origins] assert swh_storage.origin_get(origin_urls) == [None, None] stats = swh_storage.origin_add(origins) assert stats == {"origin:add": 2} actual_origins = swh_storage.origin_get(origin_urls) assert actual_origins == origins assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origins[0]), ("origin", origins[1]),] ) swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["origin"] == 2 def test_origin_add_twice(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] add1 = swh_storage.origin_add([origin, origin2]) assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origin), ("origin", origin2),] ) assert add1 == {"origin:add": 2} add2 = swh_storage.origin_add([origin, origin2]) assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origin), ("origin", origin2),] ) assert add2 == {"origin:add": 0} def test_origin_add_twice_at_once(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] add1 = swh_storage.origin_add([origin, origin2, origin, origin2]) assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origin), ("origin", origin2),] ) assert add1 == {"origin:add": 2} add2 = swh_storage.origin_add([origin, origin2, origin, origin2]) assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origin), ("origin", origin2),] ) assert add2 == {"origin:add": 0} def test_origin_get(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] assert swh_storage.origin_get([origin.url]) == [None] swh_storage.origin_add([origin]) actual_origins = swh_storage.origin_get([origin.url]) assert actual_origins == [origin] actual_origins = swh_storage.origin_get([origin.url, "not://exists"]) assert actual_origins == [origin, None] def _generate_random_visits(self, nb_visits=100, start=0, end=7): """Generate random visits within the last 2 months (to avoid computations) """ visits = [] today = now() for weeks in range(nb_visits, 0, -1): hours = random.randint(0, 24) minutes = random.randint(0, 60) seconds = random.randint(0, 60) days = random.randint(0, 28) weeks = random.randint(start, end) date_visit = today - timedelta( weeks=weeks, hours=hours, minutes=minutes, seconds=seconds, days=days ) visits.append(date_visit) return visits def test_origin_visit_get__unknown_origin(self, swh_storage): actual_page = swh_storage.origin_visit_get("foo") assert actual_page.next_page_token is None assert actual_page.results == [] assert actual_page == PagedResult() def test_origin_visit_get__validation_failure(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) with pytest.raises( StorageArgumentException, match="page_token must be a string" ): swh_storage.origin_visit_get(origin.url, page_token=10) # not bytes with pytest.raises( StorageArgumentException, match="order must be a ListOrder value" ): swh_storage.origin_visit_get(origin.url, order="foobar") # wrong order def test_origin_visit_get_all(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) ov1, ov2, ov3 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), ] ) # order asc, no token, no limit actual_page = swh_storage.origin_visit_get(origin.url) assert actual_page.next_page_token is None assert actual_page.results == [ov1, ov2, ov3] # order asc, no token, limit actual_page = swh_storage.origin_visit_get(origin.url, limit=2) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov1, ov2] # order asc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ov3] # order asc, no token, limit actual_page = swh_storage.origin_visit_get(origin.url, limit=1) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov1] # order asc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ov2, ov3] # order asc, token, limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, limit=2 ) assert actual_page.next_page_token is None assert actual_page.results == [ov2, ov3] actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov2] actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, limit=1 ) assert actual_page.next_page_token is None assert actual_page.results == [ov3] # order desc, no token, no limit actual_page = swh_storage.origin_visit_get(origin.url, order=ListOrder.DESC) assert actual_page.next_page_token is None assert actual_page.results == [ov3, ov2, ov1] # order desc, no token, limit actual_page = swh_storage.origin_visit_get( origin.url, limit=2, order=ListOrder.DESC ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov3, ov2] # order desc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ov1] # order desc, no token, limit actual_page = swh_storage.origin_visit_get( origin.url, limit=1, order=ListOrder.DESC ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov3] # order desc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ov2, ov1] # order desc, token, limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov2] actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ov1] def test_origin_visit_status_get__unknown_cases(self, swh_storage, sample_data): origin = sample_data.origin actual_page = swh_storage.origin_visit_status_get("foobar", 1) assert actual_page.next_page_token is None assert actual_page.results == [] actual_page = swh_storage.origin_visit_status_get(origin.url, 1) assert actual_page.next_page_token is None assert actual_page.results == [] origin = sample_data.origin swh_storage.origin_add([origin]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), ] )[0] actual_page = swh_storage.origin_visit_status_get(origin.url, ov1.visit + 10) assert actual_page.next_page_token is None assert actual_page.results == [] def test_origin_visit_status_add_unknown_type(self, swh_storage, sample_data): ov = OriginVisit( origin=sample_data.origin.url, date=now(), type=sample_data.type_visit1, visit=42, ) ovs = OriginVisitStatus( origin=ov.origin, visit=ov.visit, date=now(), status="created", snapshot=None, ) with pytest.raises(StorageArgumentException): swh_storage.origin_visit_status_add([ovs]) swh_storage.origin_add([sample_data.origin]) with pytest.raises(StorageArgumentException): swh_storage.origin_visit_status_add([ovs]) swh_storage.origin_visit_add([ov]) swh_storage.origin_visit_status_add([ovs]) def test_origin_visit_status_get_all(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) date_visit3 = round_to_milliseconds(now()) date_visit1 = date_visit3 - datetime.timedelta(hours=2) date_visit2 = date_visit3 - datetime.timedelta(hours=1) assert date_visit1 < date_visit2 < date_visit3 ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=date_visit1, type=sample_data.type_visit1, ), ] )[0] ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit1, type=ov1.type, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit2, type=ov1.type, status="partial", snapshot=None, ) ovs3 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit3, type=ov1.type, status="full", snapshot=sample_data.snapshot.id, metadata={}, ) swh_storage.origin_visit_status_add([ovs2, ovs3]) # order asc, no token, no limit actual_page = swh_storage.origin_visit_status_get(origin.url, ov1.visit) assert actual_page.next_page_token is None assert actual_page.results == [ovs1, ovs2, ovs3] # order asc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=2 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs1, ovs2] # order asc, token, no limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ovs3] # order asc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs1] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ovs2, ovs3] # order asc, token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, limit=2 ) assert actual_page.next_page_token is None assert actual_page.results == [ovs2, ovs3] # order asc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=2 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs1, ovs2] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, limit=1 ) assert actual_page.next_page_token is None assert actual_page.results == [ovs3] # order desc, no token, no limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs3, ovs2, ovs1] # order desc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=2, order=ListOrder.DESC ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs3, ovs2] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs1] # order desc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, order=ListOrder.DESC, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs3] # order desc, token, no limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs2, ovs1] # order desc, token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC, limit=1, ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs2] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs1] def test_origin_visit_status_get_random(self, swh_storage, sample_data): origins = sample_data.origins[:2] swh_storage.origin_add(origins) # Add some random visits within the selection range visits = self._generate_random_visits() visit_type = "git" # Add visits to those origins for origin in origins: for date_visit in visits: visit = swh_storage.origin_visit_add( [OriginVisit(origin=origin.url, date=date_visit, type=visit_type,)] )[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=visit.visit, date=now(), status="full", snapshot=None, ) ] ) swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() assert stats["origin"] == len(origins) assert stats["origin_visit"] == len(origins) * len(visits) random_ovs = swh_storage.origin_visit_status_get_random(visit_type) assert random_ovs assert random_ovs.origin is not None assert random_ovs.origin in [o.url for o in origins] assert random_ovs.type is not None def test_origin_visit_status_get_random_nothing_found( self, swh_storage, sample_data ): origins = sample_data.origins swh_storage.origin_add(origins) visit_type = "hg" # Add some visits outside of the random generation selection so nothing # will be found by the random selection visits = self._generate_random_visits(nb_visits=3, start=13, end=24) for origin in origins: for date_visit in visits: visit = swh_storage.origin_visit_add( [OriginVisit(origin=origin.url, date=date_visit, type=visit_type,)] )[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=visit.visit, date=now(), status="full", snapshot=None, ) ] ) random_origin_visit = swh_storage.origin_visit_status_get_random(visit_type) assert random_origin_visit is None def test_origin_get_by_sha1(self, swh_storage, sample_data): origin = sample_data.origin assert swh_storage.origin_get([origin.url])[0] is None swh_storage.origin_add([origin]) origins = list(swh_storage.origin_get_by_sha1([sha1(origin.url)])) assert len(origins) == 1 assert origins[0]["url"] == origin.url def test_origin_get_by_sha1_not_found(self, swh_storage, sample_data): unknown_origin = sample_data.origin assert swh_storage.origin_get([unknown_origin.url])[0] is None origins = list(swh_storage.origin_get_by_sha1([sha1(unknown_origin.url)])) assert len(origins) == 1 assert origins[0] is None def test_origin_search_single_result(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] actual_page = swh_storage.origin_search(origin.url) assert actual_page.next_page_token is None assert actual_page.results == [] actual_page = swh_storage.origin_search(origin.url, regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [] swh_storage.origin_add([origin]) actual_page = swh_storage.origin_search(origin.url) assert actual_page.next_page_token is None assert actual_page.results == [origin] actual_page = swh_storage.origin_search(f".{origin.url[1:-1]}.", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin] swh_storage.origin_add([origin2]) actual_page = swh_storage.origin_search(origin2.url) assert actual_page.next_page_token is None assert actual_page.results == [origin2] actual_page = swh_storage.origin_search(f".{origin2.url[1:-1]}.", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_no_regexp(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) # no pagination actual_page = swh_storage.origin_search("/") assert actual_page.next_page_token is None assert actual_page.results == [origin, origin2] # offset=0 actual_page = swh_storage.origin_search("/", page_token=None, limit=1) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [origin] # offset=1 actual_page = swh_storage.origin_search( "/", page_token=next_page_token, limit=1 ) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_regexp_substring(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) # no pagination actual_page = swh_storage.origin_search("/", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin, origin2] # offset=0 actual_page = swh_storage.origin_search( "/", page_token=None, limit=1, regexp=True ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [origin] # offset=1 actual_page = swh_storage.origin_search( "/", page_token=next_page_token, limit=1, regexp=True ) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_regexp_fullstring(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) # no pagination actual_page = swh_storage.origin_search(".*/.*", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin, origin2] # offset=0 actual_page = swh_storage.origin_search( ".*/.*", page_token=None, limit=1, regexp=True ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [origin] # offset=1 actual_page = swh_storage.origin_search( ".*/.*", page_token=next_page_token, limit=1, regexp=True ) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_no_visit_types(self, swh_storage, sample_data): origin = sample_data.origins[0] swh_storage.origin_add([origin]) actual_page = swh_storage.origin_search(origin.url, visit_types=["git"]) assert actual_page.next_page_token is None assert actual_page.results == [] def test_origin_search_with_visit_types(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) swh_storage.origin_visit_add( [ OriginVisit(origin=origin.url, date=now(), type="git"), OriginVisit(origin=origin2.url, date=now(), type="svn"), ] ) actual_page = swh_storage.origin_search(origin.url, visit_types=["git"]) assert actual_page.next_page_token is None assert actual_page.results == [origin] actual_page = swh_storage.origin_search(origin2.url, visit_types=["svn"]) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_multiple_visit_types(self, swh_storage, sample_data): origin = sample_data.origins[0] swh_storage.origin_add([origin]) def _add_visit_type(visit_type): swh_storage.origin_visit_add( [OriginVisit(origin=origin.url, date=now(), type=visit_type)] ) def _check_visit_types(visit_types): actual_page = swh_storage.origin_search(origin.url, visit_types=visit_types) assert actual_page.next_page_token is None assert actual_page.results == [origin] _add_visit_type("git") _check_visit_types(["git"]) _check_visit_types(["git", "hg"]) _add_visit_type("hg") _check_visit_types(["hg"]) _check_visit_types(["git", "hg"]) def test_origin_visit_add(self, swh_storage, sample_data): origin1 = sample_data.origins[1] swh_storage.origin_add([origin1]) date_visit = now() date_visit2 = date_visit + datetime.timedelta(minutes=1) date_visit = round_to_milliseconds(date_visit) date_visit2 = round_to_milliseconds(date_visit2) visit1 = OriginVisit( origin=origin1.url, date=date_visit, type=sample_data.type_visit1, ) visit2 = OriginVisit( origin=origin1.url, date=date_visit2, type=sample_data.type_visit2, ) # add once ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2]) # then again (will be ignored as they already exist) origin_visit1, origin_visit2 = swh_storage.origin_visit_add([ov1, ov2]) assert ov1 == origin_visit1 assert ov2 == origin_visit2 ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit, type=ov1.type, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=date_visit2, type=ov2.type, status="created", snapshot=None, ) actual_visits = swh_storage.origin_visit_get(origin1.url).results expected_visits = [ov1, ov2] assert len(expected_visits) == len(actual_visits) for visit in expected_visits: assert visit in actual_visits actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = list( [("origin", origin1)] + [("origin_visit", visit) for visit in expected_visits] * 2 + [("origin_visit_status", ovs) for ovs in [ovs1, ovs2]] ) for obj in expected_objects: assert obj in actual_objects def test_origin_visit_add_validation(self, swh_storage, sample_data): """Unknown origin when adding visits should raise""" visit = attr.evolve(sample_data.origin_visit, origin="something-unknonw") with pytest.raises(StorageArgumentException, match="Unknown origin"): swh_storage.origin_visit_add([visit]) objects = list(swh_storage.journal_writer.journal.objects) assert not objects def test_origin_visit_status_add_validation(self, swh_storage): """Wrong origin_visit_status input should raise storage argument error""" date_visit = now() visit_status1 = OriginVisitStatus( origin="unknown-origin-url", visit=10, date=date_visit, status="full", snapshot=None, ) with pytest.raises(StorageArgumentException, match="Unknown origin"): swh_storage.origin_visit_status_add([visit_status1]) objects = list(swh_storage.journal_writer.journal.objects) assert not objects def test_origin_visit_status_add(self, swh_storage, sample_data): """Correct origin visit statuses should add a new visit status """ snapshot = sample_data.snapshot origin1 = sample_data.origins[1] origin2 = Origin(url="new-origin") swh_storage.origin_add([origin1, origin2]) ov1, ov2 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), OriginVisit( origin=origin2.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), ] ) ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit1, type=ov1.type, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=sample_data.date_visit2, type=ov2.type, status="created", snapshot=None, ) date_visit_now = round_to_milliseconds(now()) visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, type=ov1.type, status="full", snapshot=snapshot.id, ) date_visit_now = round_to_milliseconds(now()) visit_status2 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=date_visit_now, type=ov2.type, status="ongoing", snapshot=None, metadata={"intrinsic": "something"}, ) swh_storage.origin_visit_status_add([visit_status1, visit_status2]) visit = swh_storage.origin_visit_get_latest(origin1.url, require_snapshot=True) visit_status = swh_storage.origin_visit_status_get_latest( origin1.url, visit.visit, require_snapshot=True ) assert visit_status == visit_status1 visit = swh_storage.origin_visit_get_latest(origin2.url, require_snapshot=False) visit_status = swh_storage.origin_visit_status_get_latest( origin2.url, visit.visit, require_snapshot=False ) assert origin2.url != origin1.url assert visit_status == visit_status2 actual_objects = list(swh_storage.journal_writer.journal.objects) expected_origins = [origin1, origin2] expected_visits = [ov1, ov2] expected_visit_statuses = [ovs1, ovs2, visit_status1, visit_status2] expected_objects = ( [("origin", o) for o in expected_origins] + [("origin_visit", v) for v in expected_visits] + [("origin_visit_status", ovs) for ovs in expected_visit_statuses] ) for obj in expected_objects: assert obj in actual_objects def test_origin_visit_status_add_twice(self, swh_storage, sample_data): """Correct origin visit statuses should add a new visit status """ snapshot = sample_data.snapshot origin1 = sample_data.origins[1] swh_storage.origin_add([origin1]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), ] )[0] ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit1, type=ov1.type, status="created", snapshot=None, ) date_visit_now = round_to_milliseconds(now()) visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, type=ov1.type, status="full", snapshot=snapshot.id, ) swh_storage.origin_visit_status_add([visit_status1]) # second call will ignore existing entries (will send to storage though) swh_storage.origin_visit_status_add([visit_status1]) visit_status = swh_storage.origin_visit_status_get_latest(ov1.origin, ov1.visit) assert visit_status == visit_status1 actual_objects = list(swh_storage.journal_writer.journal.objects) expected_origins = [origin1] expected_visits = [ov1] expected_visit_statuses = [ovs1, visit_status1, visit_status1] # write twice in the journal expected_objects = ( [("origin", o) for o in expected_origins] + [("origin_visit", v) for v in expected_visits] + [("origin_visit_status", ovs) for ovs in expected_visit_statuses] ) for obj in expected_objects: assert obj in actual_objects def test_origin_visit_find_by_date(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit1, ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit3, type=sample_data.type_visit2, ) visit3 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit3, ) ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) ovs1 = OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=sample_data.date_visit2, status="ongoing", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin.url, visit=ov2.visit, date=sample_data.date_visit3, status="ongoing", snapshot=None, ) ovs3 = OriginVisitStatus( origin=origin.url, visit=ov3.visit, date=sample_data.date_visit2, status="ongoing", snapshot=None, ) swh_storage.origin_visit_status_add([ovs1, ovs2, ovs3]) # Simple case actual_visit = swh_storage.origin_visit_find_by_date( origin.url, sample_data.date_visit3 ) assert actual_visit == ov2 # There are two visits at the same date, the latest must be returned actual_visit = swh_storage.origin_visit_find_by_date( origin.url, sample_data.date_visit2 ) assert actual_visit == ov3 def test_origin_visit_find_by_date__unknown_origin(self, swh_storage, sample_data): actual_visit = swh_storage.origin_visit_find_by_date( "foo", sample_data.date_visit2 ) assert actual_visit is None def test_origin_visit_get_by(self, swh_storage, sample_data): snapshot = sample_data.snapshot origins = sample_data.origins[:2] swh_storage.origin_add(origins) origin_url, origin_url2 = [o.url for o in origins] visit = OriginVisit( origin=origin_url, date=sample_data.date_visit2, type=sample_data.type_visit2, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin_url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=snapshot.id, ) ] ) # Add some other {origin, visit} entries visit2 = OriginVisit( origin=origin_url, date=sample_data.date_visit3, type=sample_data.type_visit3, ) visit3 = OriginVisit( origin=origin_url2, date=sample_data.date_visit3, type=sample_data.type_visit3, ) swh_storage.origin_visit_add([visit2, visit3]) # when visit1_metadata = { "contents": 42, "directories": 22, } swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin_url, visit=origin_visit1.visit, date=now(), status="full", snapshot=snapshot.id, metadata=visit1_metadata, ) ] ) actual_visit = swh_storage.origin_visit_get_by(origin_url, origin_visit1.visit) assert actual_visit == origin_visit1 def test_origin_visit_get_by__no_result(self, swh_storage, sample_data): actual_visit = swh_storage.origin_visit_get_by("unknown", 10) # unknown origin assert actual_visit is None origin = sample_data.origin swh_storage.origin_add([origin]) actual_visit = swh_storage.origin_visit_get_by(origin.url, 999) # unknown visit assert actual_visit is None def test_origin_visit_get_latest_edge_cases(self, swh_storage, sample_data): # unknown origin so no result assert swh_storage.origin_visit_get_latest("unknown-origin") is None # unknown type so no result origin = sample_data.origin swh_storage.origin_add([origin]) assert swh_storage.origin_visit_get_latest(origin.url, type="unknown") is None # unknown allowed statuses should raise with pytest.raises(StorageArgumentException, match="Unknown allowed statuses"): swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["unknown"] ) def test_origin_visit_get_latest_filter_type(self, swh_storage, sample_data): """Filtering origin visit get latest with filter type should be ok """ origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type="hg", ) date_now = round_to_milliseconds(now()) visit3 = OriginVisit(origin=origin.url, date=date_now, type="hg",) assert sample_data.date_visit1 < sample_data.date_visit2 assert sample_data.date_visit2 < date_now ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) # Check type filter is ok actual_visit = swh_storage.origin_visit_get_latest(origin.url, type="git") assert actual_visit == ov1 actual_visit = swh_storage.origin_visit_get_latest(origin.url, type="hg") assert actual_visit == ov3 actual_visit_unknown_type = swh_storage.origin_visit_get_latest( origin.url, type="npm", # no visit matching that type ) assert actual_visit_unknown_type is None def test_origin_visit_get_latest(self, swh_storage, sample_data): empty_snapshot, complete_snapshot = sample_data.snapshots[1:3] origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type="hg", ) date_now = round_to_milliseconds(now()) visit3 = OriginVisit(origin=origin.url, date=date_now, type="hg",) assert visit1.date < visit2.date assert visit2.date < visit3.date ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) # no filters, latest visit is the last one (whose date is most recent) actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # 3 visits, none has snapshot so nothing is returned actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) assert actual_visit is None # visit are created with "created" status, so nothing will get returned actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["partial"] ) assert actual_visit is None # visit are created with "created" status, so most recent again actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["created"] ) assert actual_visit == ov3 # Add snapshot to visit1; require_snapshot=True makes it return first visit swh_storage.snapshot_add([complete_snapshot]) visit_status_with_snapshot = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=round_to_milliseconds(now()), type=ov1.type, status="ongoing", snapshot=complete_snapshot.id, ) swh_storage.origin_visit_status_add([visit_status_with_snapshot]) # only the first visit has a snapshot now actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) assert actual_visit == ov1 # only the first visit has a status ongoing now actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["ongoing"] ) assert actual_visit == ov1 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov1.visit, require_snapshot=True ) assert actual_visit_status == visit_status_with_snapshot # ... and require_snapshot=False (defaults) still returns latest visit (3rd) actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=False ) assert actual_visit == ov3 # no specific filter, this returns as before the latest visit actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # Status filter: all three visits are status=ongoing, so no visit # returned actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"] ) assert actual_visit is None visit_status1_full = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=round_to_milliseconds(now()), type=ov1.type, status="full", snapshot=complete_snapshot.id, ) # Mark the first visit as completed and check status filter again swh_storage.origin_visit_status_add([visit_status1_full]) # only the first visit has the full status actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"] ) assert actual_visit == ov1 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov1.visit, allowed_statuses=["full"] ) assert actual_visit_status == visit_status1_full # no specific filter, this returns as before the latest visit actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([empty_snapshot]) visit_status2_full = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=round_to_milliseconds(now()), type=ov2.type, status="ongoing", snapshot=empty_snapshot.id, ) swh_storage.origin_visit_status_add([visit_status2_full]) actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) # 2nd visit is most recent with a snapshot assert actual_visit == ov2 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov2.visit, require_snapshot=True ) assert actual_visit_status == visit_status2_full # no specific filter, this returns as before the latest visit, 3rd one actual_origin = swh_storage.origin_visit_get_latest(origin.url) assert actual_origin == ov3 # full status is still the first visit actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"] ) assert actual_visit == ov1 # Add snapshot to visit3 (same date as visit2) visit_status3_with_snapshot = OriginVisitStatus( origin=ov3.origin, visit=ov3.visit, date=round_to_milliseconds(now()), type=ov3.type, status="ongoing", snapshot=complete_snapshot.id, ) swh_storage.origin_visit_status_add([visit_status3_with_snapshot]) # full status is still the first visit actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"], require_snapshot=True, ) assert actual_visit == ov1 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, visit=actual_visit.visit, allowed_statuses=["full"], require_snapshot=True, ) assert actual_visit_status == visit_status1_full # most recent is still the 3rd visit actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # 3rd visit has a snapshot now, so it's elected actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) assert actual_visit == ov3 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov3.visit, require_snapshot=True ) assert actual_visit_status == visit_status3_with_snapshot def test_origin_visit_get_latest__same_date(self, swh_storage, sample_data): empty_snapshot, complete_snapshot = sample_data.snapshots[1:3] origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="hg", ) ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2]) # ties should be broken by using the visit id actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov2 def test_origin_visit_get_latest__not_last(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) visit1, visit2 = sample_data.origin_visits[:2] assert visit1.origin == origin.url swh_storage.origin_visit_add([visit1]) ov1 = swh_storage.origin_visit_get_latest(origin.url) # Add snapshot to visit1, latest snapshot = visit 1 snapshot complete_snapshot = sample_data.snapshots[2] swh_storage.snapshot_add([complete_snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=visit2.date, status="partial", snapshot=None, ) ] ) assert visit1.date < visit2.date # no snapshot associated to the visit, so None visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["partial"], require_snapshot=True, ) assert visit is None date_now = now() assert visit2.date < date_now swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=date_now, status="full", snapshot=complete_snapshot.id, ) ] ) swh_storage.origin_visit_add( [OriginVisit(origin=origin.url, date=now(), type=visit1.type,)] ) visit = swh_storage.origin_visit_get_latest(origin.url, require_snapshot=True) assert visit is not None def test_origin_visit_status_get_latest__validation(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) # unknown allowed statuses should raise with pytest.raises(StorageArgumentException, match="Unknown allowed statuses"): swh_storage.origin_visit_status_get_latest( origin.url, visit1.visit, allowed_statuses=["unknown"] ) def test_origin_visit_status_get_latest(self, swh_storage, sample_data): snapshot = sample_data.snapshots[2] origin1 = sample_data.origin swh_storage.origin_add([origin1]) # to have some reference visits ov1, ov2 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), OriginVisit( origin=origin1.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), ] ) swh_storage.snapshot_add([snapshot]) date_now = round_to_milliseconds(now()) assert sample_data.date_visit1 < sample_data.date_visit2 assert sample_data.date_visit2 < date_now ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit1, type=ov1.type, status="partial", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit2, type=ov1.type, status="ongoing", snapshot=None, ) ovs3 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=sample_data.date_visit2 + datetime.timedelta(minutes=1), # to not be ignored type=ov2.type, status="ongoing", snapshot=None, ) ovs4 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=date_now, type=ov2.type, status="full", snapshot=snapshot.id, metadata={"something": "wicked"}, ) swh_storage.origin_visit_status_add([ovs1, ovs2, ovs3, ovs4]) # unknown origin so no result actual_origin_visit = swh_storage.origin_visit_status_get_latest( "unknown-origin", ov1.visit ) assert actual_origin_visit is None # unknown visit so no result actual_origin_visit = swh_storage.origin_visit_status_get_latest( ov1.origin, ov1.visit + 10 ) assert actual_origin_visit is None # Two visits, both with no snapshot, take the most recent actual_origin_visit2 = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit ) assert isinstance(actual_origin_visit2, OriginVisitStatus) assert actual_origin_visit2 == ovs2 assert ovs2.origin == origin1.url assert ovs2.visit == ov1.visit actual_origin_visit = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit, require_snapshot=True ) # there is no visit with snapshot yet for that visit assert actual_origin_visit is None actual_origin_visit2 = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit, allowed_statuses=["partial", "ongoing"] ) # visit status with partial status visit elected assert actual_origin_visit2 == ovs2 assert actual_origin_visit2.status == "ongoing" actual_origin_visit4 = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, require_snapshot=True ) assert actual_origin_visit4 == ovs4 assert actual_origin_visit4.snapshot == snapshot.id actual_origin_visit = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, require_snapshot=True, allowed_statuses=["ongoing"] ) # nothing matches so nothing assert actual_origin_visit is None # there is no visit with status full actual_origin_visit3 = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, allowed_statuses=["ongoing"] ) assert actual_origin_visit3 == ovs3 def test_person_fullname_unicity(self, swh_storage, sample_data): revision, rev2 = sample_data.revisions[0:2] # create a revision with same committer fullname but wo name and email revision2 = attr.evolve( rev2, committer=Person( fullname=revision.committer.fullname, name=None, email=None ), ) swh_storage.revision_add([revision, revision2]) # when getting added revisions revisions = swh_storage.revision_get([revision.id, revision2.id]) # then check committers are the same assert revisions[0].committer == revisions[1].committer def test_snapshot_add_get_empty(self, swh_storage, sample_data): empty_snapshot = sample_data.snapshots[1] empty_snapshot_dict = empty_snapshot.to_dict() origin = sample_data.origin swh_storage.origin_add([origin]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ) ] )[0] actual_result = swh_storage.snapshot_add([empty_snapshot]) assert actual_result == {"snapshot:add": 1} date_now = now() swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_now, type=ov1.type, status="full", snapshot=empty_snapshot.id, ) ] ) by_id = swh_storage.snapshot_get(empty_snapshot.id) assert by_id == {**empty_snapshot_dict, "next_branch": None} ovs1 = OriginVisitStatus.from_dict( { "origin": ov1.origin, "date": sample_data.date_visit1, "type": ov1.type, "visit": ov1.visit, "status": "created", "snapshot": None, "metadata": None, } ) ovs2 = OriginVisitStatus.from_dict( { "origin": ov1.origin, "date": date_now, "type": ov1.type, "visit": ov1.visit, "status": "full", "metadata": None, "snapshot": empty_snapshot.id, } ) actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("origin", origin), ("origin_visit", ov1), ("origin_visit_status", ovs1,), ("snapshot", empty_snapshot), ("origin_visit_status", ovs2,), ] for obj in expected_objects: assert obj in actual_objects def test_snapshot_add_get_complete(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] complete_snapshot_dict = complete_snapshot.to_dict() origin = sample_data.origin swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] actual_result = swh_storage.snapshot_add([complete_snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=complete_snapshot.id, ) ] ) assert actual_result == {"snapshot:add": 1} by_id = swh_storage.snapshot_get(complete_snapshot.id) assert by_id == {**complete_snapshot_dict, "next_branch": None} def test_snapshot_add_many(self, swh_storage, sample_data): snapshot, _, complete_snapshot = sample_data.snapshots[:3] actual_result = swh_storage.snapshot_add([snapshot, complete_snapshot]) assert actual_result == {"snapshot:add": 2} assert swh_storage.snapshot_get(complete_snapshot.id) == { **complete_snapshot.to_dict(), "next_branch": None, } assert swh_storage.snapshot_get(snapshot.id) == { **snapshot.to_dict(), "next_branch": None, } swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["snapshot"] == 2 def test_snapshot_add_many_incremental(self, swh_storage, sample_data): snapshot, _, complete_snapshot = sample_data.snapshots[:3] actual_result = swh_storage.snapshot_add([complete_snapshot]) assert actual_result == {"snapshot:add": 1} actual_result2 = swh_storage.snapshot_add([snapshot, complete_snapshot]) assert actual_result2 == {"snapshot:add": 1} assert swh_storage.snapshot_get(complete_snapshot.id) == { **complete_snapshot.to_dict(), "next_branch": None, } assert swh_storage.snapshot_get(snapshot.id) == { **snapshot.to_dict(), "next_branch": None, } def test_snapshot_add_twice(self, swh_storage, sample_data): snapshot, empty_snapshot = sample_data.snapshots[:2] actual_result = swh_storage.snapshot_add([empty_snapshot]) assert actual_result == {"snapshot:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("snapshot", empty_snapshot) ] actual_result = swh_storage.snapshot_add([snapshot]) assert actual_result == {"snapshot:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("snapshot", empty_snapshot), ("snapshot", snapshot), ] def test_snapshot_add_count_branches(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] actual_result = swh_storage.snapshot_add([complete_snapshot]) assert actual_result == {"snapshot:add": 1} snp_size = swh_storage.snapshot_count_branches(complete_snapshot.id) expected_snp_size = { "alias": 1, "content": 1, "directory": 2, "release": 1, "revision": 1, "snapshot": 1, None: 1, } assert snp_size == expected_snp_size def test_snapshot_add_count_branches_with_filtering(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] actual_result = swh_storage.snapshot_add([complete_snapshot]) assert actual_result == {"snapshot:add": 1} snp_size = swh_storage.snapshot_count_branches( complete_snapshot.id, branch_name_exclude_prefix=b"release" ) expected_snp_size = { "alias": 1, "content": 1, "directory": 2, "revision": 1, "snapshot": 1, None: 1, } assert snp_size == expected_snp_size def test_snapshot_add_count_branches_with_filtering_edge_cases( self, swh_storage, sample_data ): snapshot = Snapshot( branches={ b"\xaa\xff": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xaa\xff\x00": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xff\xff": SnapshotBranch( target=sample_data.release.id, target_type=TargetType.RELEASE, ), b"\xff\xff\x00": SnapshotBranch( target=sample_data.release.id, target_type=TargetType.RELEASE, ), b"dangling": None, }, ) swh_storage.snapshot_add([snapshot]) assert swh_storage.snapshot_count_branches( snapshot.id, branch_name_exclude_prefix=b"\xaa\xff" ) == {None: 1, "release": 2} assert swh_storage.snapshot_count_branches( snapshot.id, branch_name_exclude_prefix=b"\xff\xff" ) == {None: 1, "revision": 2} def test_snapshot_add_get_paginated(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] swh_storage.snapshot_add([complete_snapshot]) snp_id = complete_snapshot.id branches = complete_snapshot.branches branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches(snp_id, branches_from=b"release") 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, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches(snp_id, branches_count=1) expected_snapshot = { "id": snp_id, "branches": {branch_names[0]: branches[branch_names[0]],}, "next_branch": b"content", } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, branches_from=b"directory", branches_count=3 ) 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], } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered(self, swh_storage, sample_data): origin = sample_data.origin complete_snapshot = sample_data.snapshots[2] swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([complete_snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=complete_snapshot.id, ) ] ) snp_id = complete_snapshot.id branches = complete_snapshot.branches snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["release", "revision"] ) expected_snapshot = { "id": snp_id, "branches": { name: tgt for name, tgt in branches.items() if tgt and tgt.target_type in [TargetType.RELEASE, TargetType.REVISION] }, "next_branch": None, } assert snapshot == expected_snapshot snapshot = swh_storage.snapshot_get_branches(snp_id, target_types=["alias"]) expected_snapshot = { "id": snp_id, "branches": { name: tgt for name, tgt in branches.items() if tgt and tgt.target_type == TargetType.ALIAS }, "next_branch": None, } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered_and_paginated(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] swh_storage.snapshot_add([complete_snapshot]) snp_id = complete_snapshot.id branches = complete_snapshot.branches branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_from=b"directory2" ) expected_snapshot = { "id": snp_id, "branches": {name: branches[name] for name in (b"directory2", b"release")}, "next_branch": None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_count=1 ) expected_snapshot = { "id": snp_id, "branches": {b"directory": branches[b"directory"]}, "next_branch": b"directory2", } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_count=2 ) expected_snapshot = { "id": snp_id, "branches": { name: branches[name] for name in (b"directory", b"directory2") }, "next_branch": b"release", } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_from=b"directory2", branches_count=1, ) dir_idx = branch_names.index(b"directory2") expected_snapshot = { "id": snp_id, "branches": {branch_names[dir_idx]: branches[branch_names[dir_idx]],}, "next_branch": b"release", } assert snapshot == expected_snapshot def test_snapshot_add_get_branch_by_type(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] snapshot = complete_snapshot.to_dict() alias1 = b"alias1" alias2 = b"alias2" target1 = random.choice(list(snapshot["branches"].keys())) target2 = random.choice(list(snapshot["branches"].keys())) snapshot["branches"][alias2] = { "target": target2, "target_type": "alias", } snapshot["branches"][alias1] = { "target": target1, "target_type": "alias", } new_snapshot = Snapshot.from_dict(snapshot) swh_storage.snapshot_add([new_snapshot]) branches = swh_storage.snapshot_get_branches( new_snapshot.id, target_types=["alias"], branches_from=alias1, branches_count=1, )["branches"] assert len(branches) == 1 assert alias1 in branches def test_snapshot_add_get_by_branches_name_pattern(self, swh_storage, sample_data): snapshot = Snapshot( branches={ b"refs/heads/master": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"refs/heads/incoming": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"refs/pull/1": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"refs/pull/2": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"dangling": None, b"\xaa\xff": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xaa\xff\x00": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xff\xff": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xff\xff\x00": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), }, ) swh_storage.snapshot_add([snapshot]) for include_pattern, exclude_prefix, nb_results in ( (b"pull", None, 2), (b"incoming", None, 1), (b"dangling", None, 1), (None, b"refs/heads/", 7), (b"refs", b"refs/heads/master", 3), (b"refs", b"refs/heads/master", 3), (None, b"\xaa\xff", 7), (None, b"\xff\xff", 7), ): branches = swh_storage.snapshot_get_branches( snapshot.id, branch_name_include_substring=include_pattern, branch_name_exclude_prefix=exclude_prefix, )["branches"] expected_branches = [ branch_name for branch_name in snapshot.branches if (include_pattern is None or include_pattern in branch_name) and ( exclude_prefix is None or not branch_name.startswith(exclude_prefix) ) ] assert sorted(branches) == sorted(expected_branches) assert len(branches) == nb_results def test_snapshot_add_get_by_branches_name_pattern_filtered_paginated( self, swh_storage, sample_data ): pattern = b"foo" nb_branches_by_target_type = 10 branches = {} for i in range(nb_branches_by_target_type): branches[f"branch/directory/bar{i}".encode()] = SnapshotBranch( target=sample_data.directory.id, target_type=TargetType.DIRECTORY, ) branches[f"branch/revision/bar{i}".encode()] = SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ) branches[f"branch/directory/{pattern}{i}".encode()] = SnapshotBranch( target=sample_data.directory.id, target_type=TargetType.DIRECTORY, ) branches[f"branch/revision/{pattern}{i}".encode()] = SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ) snapshot = Snapshot(branches=branches) swh_storage.snapshot_add([snapshot]) branches_count = nb_branches_by_target_type // 2 for target_type in ( TargetType.DIRECTORY, TargetType.REVISION, ): target_type_str = target_type.value partial_branches = swh_storage.snapshot_get_branches( snapshot.id, branch_name_include_substring=pattern, target_types=[target_type_str], branches_count=branches_count, ) branches = partial_branches["branches"] expected_branches = [ branch_name for branch_name, branch_data in snapshot.branches.items() if pattern in branch_name and branch_data.target_type == target_type ][:branches_count] assert sorted(branches) == sorted(expected_branches) assert ( partial_branches["next_branch"] == f"branch/{target_type_str}/{pattern}{branches_count}".encode() ) partial_branches = swh_storage.snapshot_get_branches( snapshot.id, branch_name_include_substring=pattern, target_types=[target_type_str], branches_from=partial_branches["next_branch"], ) branches = partial_branches["branches"] expected_branches = [ branch_name for branch_name, branch_data in snapshot.branches.items() if pattern in branch_name and branch_data.target_type == target_type ][branches_count:] assert sorted(branches) == sorted(expected_branches) assert partial_branches["next_branch"] is None def test_snapshot_add_get(self, swh_storage, sample_data): snapshot = sample_data.snapshot origin = sample_data.origin swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ) ov1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=now(), status="ongoing", snapshot=snapshot.id, ) ] ) expected_snapshot = {**snapshot.to_dict(), "next_branch": None} by_id = swh_storage.snapshot_get(snapshot.id) assert by_id == expected_snapshot actual_visit = swh_storage.origin_visit_get_by(origin.url, ov1.visit) assert actual_visit == ov1 visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov1.visit, require_snapshot=True ) assert visit_status.snapshot == snapshot.id def test_snapshot_get_random(self, swh_storage, sample_data): snapshot, empty_snapshot, complete_snapshot = sample_data.snapshots[:3] swh_storage.snapshot_add([snapshot, empty_snapshot, complete_snapshot]) assert swh_storage.snapshot_get_random() in { snapshot.id, empty_snapshot.id, complete_snapshot.id, } def test_snapshot_missing(self, swh_storage, sample_data): snapshot, missing_snapshot = sample_data.snapshots[:2] snapshots = [snapshot.id, missing_snapshot.id] swh_storage.snapshot_add([snapshot]) missing_snapshots = swh_storage.snapshot_missing(snapshots) assert list(missing_snapshots) == [missing_snapshot.id] def test_stat_counters(self, swh_storage, sample_data): origin = sample_data.origin snapshot = sample_data.snapshot revision = sample_data.revision release = sample_data.release directory = sample_data.directory content = sample_data.content expected_keys = ["content", "directory", "origin", "revision"] # Initially, all counters are 0 swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: assert counters[key] == 0 # Add a content. Only the content counter should increase. swh_storage.content_add([content]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: if key != "content": assert counters[key] == 0 assert counters["content"] == 1 # Add other objects. Check their counter increased as well. swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=snapshot.id, ) ] ) swh_storage.directory_add([directory]) swh_storage.revision_add([revision]) swh_storage.release_add([release]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert counters["content"] == 1 assert counters["directory"] == 1 assert counters["snapshot"] == 1 assert counters["origin"] == 1 assert counters["origin_visit"] == 1 assert counters["revision"] == 1 assert counters["release"] == 1 assert counters["snapshot"] == 1 if "person" in counters: assert counters["person"] == 3 def test_content_find_ctime(self, swh_storage, sample_data): origin_content = sample_data.content ctime = round_to_milliseconds(now()) content = attr.evolve(origin_content, data=None, ctime=ctime) swh_storage.content_add_metadata([content]) actually_present = swh_storage.content_find({"sha1": content.sha1}) assert actually_present[0] == content assert actually_present[0].ctime is not None assert actually_present[0].ctime.tzinfo is not None def test_content_find_with_present_content(self, swh_storage, sample_data): content = sample_data.content expected_content = attr.evolve(content, data=None) # 1. with something to find swh_storage.content_add([content]) actually_present = swh_storage.content_find({"sha1": content.sha1}) assert 1 == len(actually_present) assert actually_present[0] == expected_content # 2. with something to find actually_present = swh_storage.content_find({"sha1_git": content.sha1_git}) assert 1 == len(actually_present) assert actually_present[0] == expected_content # 3. with something to find actually_present = swh_storage.content_find({"sha256": content.sha256}) assert 1 == len(actually_present) assert actually_present[0] == expected_content # 4. with something to find actually_present = swh_storage.content_find(content.hashes()) assert 1 == len(actually_present) assert actually_present[0] == expected_content def test_content_find_with_non_present_content(self, swh_storage, sample_data): missing_content = sample_data.skipped_content # 1. with something that does not exist actually_present = swh_storage.content_find({"sha1": missing_content.sha1}) assert actually_present == [] # 2. with something that does not exist actually_present = swh_storage.content_find( {"sha1_git": missing_content.sha1_git} ) assert actually_present == [] # 3. with something that does not exist actually_present = swh_storage.content_find({"sha256": missing_content.sha256}) assert actually_present == [] def test_content_find_with_duplicate_input(self, swh_storage, sample_data): content = sample_data.content # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(content.sha1) sha1_array[0] += 1 sha1git_array = bytearray(content.sha1_git) sha1git_array[0] += 1 duplicated_content = attr.evolve( content, sha1=bytes(sha1_array), sha1_git=bytes(sha1git_array) ) # Inject the data swh_storage.content_add([content, duplicated_content]) actual_result = swh_storage.content_find( { "blake2s256": duplicated_content.blake2s256, "sha256": duplicated_content.sha256, } ) expected_content = attr.evolve(content, data=None) expected_duplicated_content = attr.evolve(duplicated_content, data=None) for result in actual_result: assert result in [expected_content, expected_duplicated_content] def test_content_find_with_duplicate_sha256(self, swh_storage, sample_data): content = sample_data.content hashes = {} # Create fake data with colliding sha256 for hashalgo in ("sha1", "sha1_git", "blake2s256"): value = bytearray(getattr(content, hashalgo)) value[0] += 1 hashes[hashalgo] = bytes(value) duplicated_content = attr.evolve( content, sha1=hashes["sha1"], sha1_git=hashes["sha1_git"], blake2s256=hashes["blake2s256"], ) swh_storage.content_add([content, duplicated_content]) actual_result = swh_storage.content_find({"sha256": duplicated_content.sha256}) assert len(actual_result) == 2 expected_content = attr.evolve(content, data=None) expected_duplicated_content = attr.evolve(duplicated_content, data=None) for result in actual_result: assert result in [expected_content, expected_duplicated_content] # Find with both sha256 and blake2s256 actual_result = swh_storage.content_find( { "sha256": duplicated_content.sha256, "blake2s256": duplicated_content.blake2s256, } ) assert len(actual_result) == 1 assert actual_result == [expected_duplicated_content] def test_content_find_with_duplicate_blake2s256(self, swh_storage, sample_data): content = sample_data.content # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(content.sha1) sha1_array[0] += 1 sha1git_array = bytearray(content.sha1_git) sha1git_array[0] += 1 sha256_array = bytearray(content.sha256) sha256_array[0] += 1 duplicated_content = attr.evolve( content, sha1=bytes(sha1_array), sha1_git=bytes(sha1git_array), sha256=bytes(sha256_array), ) swh_storage.content_add([content, duplicated_content]) actual_result = swh_storage.content_find( {"blake2s256": duplicated_content.blake2s256} ) expected_content = attr.evolve(content, data=None) expected_duplicated_content = attr.evolve(duplicated_content, data=None) for result in actual_result: assert result in [expected_content, expected_duplicated_content] # Find with both sha256 and blake2s256 actual_result = swh_storage.content_find( { "sha256": duplicated_content.sha256, "blake2s256": duplicated_content.blake2s256, } ) assert actual_result == [expected_duplicated_content] def test_content_find_bad_input(self, swh_storage): # 1. with no hash to lookup with pytest.raises(StorageArgumentException): swh_storage.content_find({}) # need at least one hash # 2. with bad hash with pytest.raises(StorageArgumentException): swh_storage.content_find({"unknown-sha1": "something"}) # not the right key def test_object_find_by_sha1_git(self, swh_storage, sample_data): content = sample_data.content directory = sample_data.directory revision = sample_data.revision release = sample_data.release sha1_gits = [b"00000000000000000000"] expected = { b"00000000000000000000": [], } swh_storage.content_add([content]) sha1_gits.append(content.sha1_git) expected[content.sha1_git] = [ {"sha1_git": content.sha1_git, "type": "content",} ] swh_storage.directory_add([directory]) sha1_gits.append(directory.id) expected[directory.id] = [{"sha1_git": directory.id, "type": "directory",}] swh_storage.revision_add([revision]) sha1_gits.append(revision.id) expected[revision.id] = [{"sha1_git": revision.id, "type": "revision",}] swh_storage.release_add([release]) sha1_gits.append(release.id) expected[release.id] = [{"sha1_git": release.id, "type": "release",}] ret = swh_storage.object_find_by_sha1_git(sha1_gits) assert expected == ret def test_metadata_fetcher_add_get(self, swh_storage, sample_data): fetcher = sample_data.metadata_fetcher actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert actual_fetcher is None # does not exist swh_storage.metadata_fetcher_add([fetcher]) res = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert res == fetcher actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_fetcher", fetcher), ] for obj in expected_objects: assert obj in actual_objects def test_metadata_fetcher_add_zero(self, swh_storage, sample_data): fetcher = sample_data.metadata_fetcher actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert actual_fetcher is None # does not exist swh_storage.metadata_fetcher_add([]) def test_metadata_authority_add_get(self, swh_storage, sample_data): authority = sample_data.metadata_authority actual_authority = swh_storage.metadata_authority_get( authority.type, authority.url ) assert actual_authority is None # does not exist swh_storage.metadata_authority_add([authority]) res = swh_storage.metadata_authority_get(authority.type, authority.url) assert res == authority actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_authority", authority), ] for obj in expected_objects: assert obj in actual_objects def test_metadata_authority_add_zero(self, swh_storage, sample_data): authority = sample_data.metadata_authority actual_authority = swh_storage.metadata_authority_get( authority.type, authority.url ) assert actual_authority is None # does not exist swh_storage.metadata_authority_add([]) def test_content_metadata_add(self, swh_storage, sample_data): content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add(content_metadata) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority ) assert result.next_page_token is None assert list(sorted(result.results, key=lambda x: x.discovery_date,)) == list( content_metadata ) actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_authority", authority), ("metadata_fetcher", fetcher), ] + [("raw_extrinsic_metadata", item) for item in content_metadata] for obj in expected_objects: assert obj in actual_objects def test_content_metadata_add_duplicate(self, swh_storage, sample_data): """Duplicates should be silently ignored.""" content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) swh_storage.raw_extrinsic_metadata_add([content_metadata2, content_metadata]) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority ) assert result.next_page_token is None expected_results = (content_metadata, content_metadata2) assert ( tuple(sorted(result.results, key=lambda x: x.discovery_date,)) == expected_results ) def test_content_metadata_get(self, swh_storage, sample_data): content, content2 = sample_data.contents[:2] fetcher, fetcher2 = sample_data.fetchers[:2] authority, authority2 = sample_data.authorities[:2] ( content1_metadata1, content1_metadata2, content1_metadata3, ) = sample_data.content_metadata[:3] content2_metadata = RawExtrinsicMetadata.from_dict( { **remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id "target": str(content2.swhid()), } ) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.raw_extrinsic_metadata_add( [ content1_metadata1, content1_metadata2, content1_metadata3, content2_metadata, ] ) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority ) assert result.next_page_token is None assert [content1_metadata1, content1_metadata2] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority2 ) assert result.next_page_token is None assert [content1_metadata3] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( content2.swhid().to_extended(), authority ) assert result.next_page_token is None assert [content2_metadata] == list(result.results,) def test_content_metadata_get_after(self, swh_storage, sample_data): content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, after=content_metadata.discovery_date - timedelta(seconds=1), ) assert result.next_page_token is None assert [content_metadata, content_metadata2] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, after=content_metadata.discovery_date, ) assert result.next_page_token is None assert result.results == [content_metadata2] result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, after=content_metadata2.discovery_date, ) assert result.next_page_token is None assert result.results == [] def test_content_metadata_get_paginate(self, swh_storage, sample_data): content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) swh_storage.raw_extrinsic_metadata_get(content.swhid().to_extended(), authority) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [content_metadata] result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results == [content_metadata2] def test_content_metadata_get_paginate_same_date(self, swh_storage, sample_data): content = sample_data.content fetcher1, fetcher2 = sample_data.fetchers[:2] authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher1, fetcher2]) swh_storage.metadata_authority_add([authority]) new_content_metadata2 = RawExtrinsicMetadata.from_dict( { **remove_keys(content_metadata2.to_dict(), ("id",)), # recompute id "discovery_date": content_metadata2.discovery_date, "fetcher": attr.evolve(fetcher2, metadata=None).to_dict(), } ) swh_storage.raw_extrinsic_metadata_add( [content_metadata, new_content_metadata2] ) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [content_metadata] result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results[0].to_dict() == new_content_metadata2.to_dict() assert result.results == [new_content_metadata2] def test_origin_metadata_add(self, swh_storage, sample_data): origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority ) assert result.next_page_token is None assert list(sorted(result.results, key=lambda x: x.discovery_date)) == [ origin_metadata, origin_metadata2, ] actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_authority", authority), ("metadata_fetcher", fetcher), ("raw_extrinsic_metadata", origin_metadata), ("raw_extrinsic_metadata", origin_metadata2), ] for obj in expected_objects: assert obj in actual_objects def test_origin_metadata_add_duplicate(self, swh_storage, sample_data): """Duplicates should be silently updated.""" origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) swh_storage.raw_extrinsic_metadata_add([origin_metadata2, origin_metadata]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority ) assert result.next_page_token is None # which of the two behavior happens is backend-specific. expected_results = (origin_metadata, origin_metadata2) assert ( tuple(sorted(result.results, key=lambda x: x.discovery_date,)) == expected_results ) def test_origin_metadata_get(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] fetcher, fetcher2 = sample_data.fetchers[:2] authority, authority2 = sample_data.authorities[:2] ( origin1_metadata1, origin1_metadata2, origin1_metadata3, ) = sample_data.origin_metadata[:3] assert swh_storage.origin_add([origin, origin2]) == {"origin:add": 2} origin2_metadata = RawExtrinsicMetadata.from_dict( { **remove_keys(origin1_metadata2.to_dict(), ("id",)), # recompute id "target": str(Origin(origin2.url).swhid()), } ) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.raw_extrinsic_metadata_add( [origin1_metadata1, origin1_metadata2, origin1_metadata3, origin2_metadata] ) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority ) assert result.next_page_token is None assert [origin1_metadata1, origin1_metadata2] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority2 ) assert result.next_page_token is None assert [origin1_metadata3] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin2.url).swhid(), authority ) assert result.next_page_token is None assert [origin2_metadata] == list(result.results,) def test_origin_metadata_get_after(self, swh_storage, sample_data): origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, after=origin_metadata.discovery_date - timedelta(seconds=1), ) assert result.next_page_token is None assert list(sorted(result.results, key=lambda x: x.discovery_date,)) == [ origin_metadata, origin_metadata2, ] result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, after=origin_metadata.discovery_date, ) assert result.next_page_token is None assert result.results == [origin_metadata2] result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, after=origin_metadata2.discovery_date, ) assert result.next_page_token is None assert result.results == [] def test_origin_metadata_get_paginate(self, swh_storage, sample_data): origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) swh_storage.raw_extrinsic_metadata_get(Origin(origin.url).swhid(), authority) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [origin_metadata] result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results == [origin_metadata2] def test_origin_metadata_get_paginate_same_date(self, swh_storage, sample_data): origin = sample_data.origin fetcher1, fetcher2 = sample_data.fetchers[:2] authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher1, fetcher2]) swh_storage.metadata_authority_add([authority]) new_origin_metadata2 = RawExtrinsicMetadata.from_dict( { **remove_keys(origin_metadata2.to_dict(), ("id",)), # recompute id "discovery_date": origin_metadata2.discovery_date, "fetcher": attr.evolve(fetcher2, metadata=None).to_dict(), } ) swh_storage.raw_extrinsic_metadata_add([origin_metadata, new_origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [origin_metadata] result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results == [new_origin_metadata2] def test_origin_metadata_add_missing_authority(self, swh_storage, sample_data): origin = sample_data.origin fetcher = sample_data.metadata_fetcher origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) with pytest.raises(StorageArgumentException, match="authority"): swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) def test_origin_metadata_add_missing_fetcher(self, swh_storage, sample_data): origin = sample_data.origin authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_authority_add([authority]) with pytest.raises(StorageArgumentException, match="fetcher"): swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) class TestStorageGeneratedData: def test_generate_content_get_data(self, swh_storage, swh_contents): contents_with_data = [c for c in swh_contents if c.status != "absent"] # retrieve contents for content in contents_with_data: actual_content_data = swh_storage.content_get_data(content.sha1) assert actual_content_data is not None assert actual_content_data == content.data def test_generate_content_get(self, swh_storage, swh_contents): expected_contents = [ attr.evolve(c, data=None) for c in swh_contents if c.status != "absent" ] actual_contents = swh_storage.content_get([c.sha1 for c in expected_contents]) assert len(actual_contents) == len(expected_contents) assert actual_contents == expected_contents @pytest.mark.parametrize("limit", [1, 7, 10, 100, 1000]) def test_origin_list(self, swh_storage, swh_origins, limit): returned_origins = [] page_token = None i = 0 while True: actual_page = swh_storage.origin_list(page_token=page_token, limit=limit) assert len(actual_page.results) <= limit returned_origins.extend(actual_page.results) i += 1 page_token = actual_page.next_page_token if page_token is None: assert i * limit >= len(swh_origins) break else: assert len(actual_page.results) == limit assert sorted(returned_origins) == sorted(swh_origins) def test_origin_count(self, swh_storage, sample_data): swh_storage.origin_add(sample_data.origins) assert swh_storage.origin_count("github") == 3 assert swh_storage.origin_count("gitlab") == 2 assert swh_storage.origin_count(".*user.*", regexp=True) == 5 assert swh_storage.origin_count(".*user.*", regexp=False) == 0 assert swh_storage.origin_count(".*user1.*", regexp=True) == 2 assert swh_storage.origin_count(".*user1.*", regexp=False) == 0 def test_origin_count_with_visit_no_visits(self, swh_storage, sample_data): swh_storage.origin_add(sample_data.origins) # none of them have visits, so with_visit=True => 0 assert swh_storage.origin_count("github", with_visit=True) == 0 assert swh_storage.origin_count("gitlab", with_visit=True) == 0 assert swh_storage.origin_count(".*user.*", regexp=True, with_visit=True) == 0 assert swh_storage.origin_count(".*user.*", regexp=False, with_visit=True) == 0 assert swh_storage.origin_count(".*user1.*", regexp=True, with_visit=True) == 0 assert swh_storage.origin_count(".*user1.*", regexp=False, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_no_snapshot( self, swh_storage, sample_data ): swh_storage.origin_add(sample_data.origins) origin_url = "https://github.com/user1/repo1" visit = OriginVisit(origin=origin_url, date=now(), type="git",) swh_storage.origin_visit_add([visit]) assert swh_storage.origin_count("github", with_visit=False) == 3 # it has a visit, but no snapshot, so with_visit=True => 0 assert swh_storage.origin_count("github", with_visit=True) == 0 assert swh_storage.origin_count("gitlab", with_visit=False) == 2 # these gitlab origins have no visit assert swh_storage.origin_count("gitlab", with_visit=True) == 0 assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=False) == 1 ) assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=True) == 0 ) assert swh_storage.origin_count("github", regexp=True, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_and_snapshot( self, swh_storage, sample_data ): snapshot = sample_data.snapshot swh_storage.origin_add(sample_data.origins) swh_storage.snapshot_add([snapshot]) origin_url = "https://github.com/user1/repo1" visit = OriginVisit(origin=origin_url, date=now(), type="git",) visit = swh_storage.origin_visit_add([visit])[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin_url, visit=visit.visit, date=now(), status="ongoing", snapshot=snapshot.id, ) ] ) assert swh_storage.origin_count("github", with_visit=False) == 3 # github/user1 has a visit and a snapshot, so with_visit=True => 1 assert swh_storage.origin_count("github", with_visit=True) == 1 assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=False) == 1 ) assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=True) == 1 ) assert swh_storage.origin_count("github", regexp=True, with_visit=True) == 1 @settings( suppress_health_check=[HealthCheck.too_slow] + function_scoped_fixture_check, ) @given(strategies.lists(objects(split_content=True), max_size=2)) def test_add_arbitrary(self, swh_storage, objects): for (obj_type, obj) in objects: if obj.object_type == "origin_visit": swh_storage.origin_add([Origin(url=obj.origin)]) visit = OriginVisit(origin=obj.origin, date=obj.date, type=obj.type,) swh_storage.origin_visit_add([visit]) else: method = getattr(swh_storage, obj_type + "_add") try: method([obj]) except HashCollision: pass diff --git a/swh/storage/tests/test_backfill.py b/swh/storage/tests/test_backfill.py index d228ca8d..6865aa6c 100644 --- a/swh/storage/tests/test_backfill.py +++ b/swh/storage/tests/test_backfill.py @@ -1,295 +1,298 @@ # Copyright (C) 2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import functools import logging from unittest.mock import patch import pytest from swh.journal.client import JournalClient from swh.model.tests.swh_model_data import TEST_OBJECTS from swh.storage import get_storage from swh.storage.backfill import ( PARTITION_KEY, JournalBackfiller, byte_ranges, compute_query, raw_extrinsic_metadata_target_ranges, ) +from swh.storage.in_memory import InMemoryStorage from swh.storage.replay import process_replay_objects from swh.storage.tests.test_replay import check_replayed TEST_CONFIG = { "journal_writer": { "brokers": ["localhost"], "prefix": "swh.tmp_journal.new", "client_id": "swh.journal.client.test", }, "storage": {"cls": "local", "db": "service=swh-dev"}, } def test_config_ko_missing_mandatory_key(): """Missing configuration key will make the initialization fail """ for key in TEST_CONFIG.keys(): config = TEST_CONFIG.copy() config.pop(key) with pytest.raises(ValueError) as e: JournalBackfiller(config) error = "Configuration error: The following keys must be provided: %s" % ( ",".join([key]), ) assert e.value.args[0] == error def test_config_ko_unknown_object_type(): """Parse arguments will fail if the object type is unknown """ backfiller = JournalBackfiller(TEST_CONFIG) with pytest.raises(ValueError) as e: backfiller.parse_arguments("unknown-object-type", 1, 2) error = ( "Object type unknown-object-type is not supported. " "The only possible values are %s" % (", ".join(sorted(PARTITION_KEY))) ) assert e.value.args[0] == error def test_compute_query_content(): query, where_args, column_aliases = compute_query("content", "\x000000", "\x000001") assert where_args == ["\x000000", "\x000001"] assert column_aliases == [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "status", "ctime", ] assert ( query == """ select sha1,sha1_git,sha256,blake2s256,length,status,ctime from content where (sha1) >= %s and (sha1) < %s """ ) def test_compute_query_skipped_content(): query, where_args, column_aliases = compute_query("skipped_content", None, None) assert where_args == [] assert column_aliases == [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "ctime", "status", "reason", ] assert ( query == """ select sha1,sha1_git,sha256,blake2s256,length,ctime,status,reason from skipped_content """ ) def test_compute_query_origin_visit(): query, where_args, column_aliases = compute_query("origin_visit", 1, 10) assert where_args == [1, 10] assert column_aliases == [ "visit", "type", "origin", "date", ] assert ( query == """ select visit,type,origin.url as origin,date from origin_visit left join origin on origin_visit.origin=origin.id where (origin_visit.origin) >= %s and (origin_visit.origin) < %s """ ) def test_compute_query_release(): query, where_args, column_aliases = compute_query("release", "\x000002", "\x000003") assert where_args == ["\x000002", "\x000003"] assert column_aliases == [ "id", "date", "date_offset", "date_neg_utc_offset", "comment", "name", "synthetic", "target", "target_type", "author_id", "author_name", "author_email", "author_fullname", ] assert ( query == """ select release.id as id,date,date_offset,date_neg_utc_offset,comment,release.name as name,synthetic,target,target_type,a.id as author_id,a.name as author_name,a.email as author_email,a.fullname as author_fullname from release left join person a on release.author=a.id where (release.id) >= %s and (release.id) < %s """ # noqa ) @pytest.mark.parametrize("numbits", [2, 3, 8, 16]) def test_byte_ranges(numbits): ranges = list(byte_ranges(numbits)) assert len(ranges) == 2 ** numbits assert ranges[0][0] is None assert ranges[-1][1] is None bounds = [] for i, (left, right) in enumerate(zip(ranges[:-1], ranges[1:])): assert left[1] == right[0], f"Mismatched bounds in {i}th range" bounds.append(left[1]) assert bounds == sorted(bounds) def test_raw_extrinsic_metadata_target_ranges(): ranges = list(raw_extrinsic_metadata_target_ranges()) assert ranges[0][0] == "" assert ranges[-1][1] is None bounds = [] for i, (left, right) in enumerate(zip(ranges[:-1], ranges[1:])): assert left[1] == right[0], f"Mismatched bounds in {i}th range" bounds.append(left[1]) assert bounds == sorted(bounds) RANGE_GENERATORS = { "content": lambda start, end: [(None, None)], "skipped_content": lambda start, end: [(None, None)], "directory": lambda start, end: [(None, None)], "extid": lambda start, end: [(None, None)], "metadata_authority": lambda start, end: [(None, None)], "metadata_fetcher": lambda start, end: [(None, None)], "revision": lambda start, end: [(None, None)], "release": lambda start, end: [(None, None)], "snapshot": lambda start, end: [(None, None)], "origin": lambda start, end: [(None, 10000)], "origin_visit": lambda start, end: [(None, 10000)], "origin_visit_status": lambda start, end: [(None, 10000)], "raw_extrinsic_metadata": lambda start, end: [(None, None)], } @patch("swh.storage.backfill.RANGE_GENERATORS", RANGE_GENERATORS) def test_backfiller( swh_storage_backend_config, kafka_prefix: str, kafka_consumer_group: str, kafka_server: str, caplog, ): prefix1 = f"{kafka_prefix}-1" prefix2 = f"{kafka_prefix}-2" journal1 = { "cls": "kafka", "brokers": [kafka_server], "client_id": "kafka_writer-1", "prefix": prefix1, } swh_storage_backend_config["journal_writer"] = journal1 storage = get_storage(**swh_storage_backend_config) # fill the storage and the journal (under prefix1) for object_type, objects in TEST_OBJECTS.items(): method = getattr(storage, object_type + "_add") method(objects) # now apply the backfiller on the storage to fill the journal under prefix2 backfiller_config = { "journal_writer": { "brokers": [kafka_server], "client_id": "kafka_writer-2", "prefix": prefix2, }, "storage": swh_storage_backend_config, } # Backfilling backfiller = JournalBackfiller(backfiller_config) for object_type in TEST_OBJECTS: backfiller.run(object_type, None, None) # Trace log messages for unhandled object types in the replayer caplog.set_level(logging.DEBUG, "swh.storage.replay") # now check journal content are the same under both topics # use the replayer scaffolding to fill storages to make is a bit easier # Replaying #1 sto1 = get_storage(cls="memory") replayer1 = JournalClient( brokers=kafka_server, group_id=f"{kafka_consumer_group}-1", prefix=prefix1, stop_on_eof=True, ) worker_fn1 = functools.partial(process_replay_objects, storage=sto1) replayer1.process(worker_fn1) # Replaying #2 sto2 = get_storage(cls="memory") replayer2 = JournalClient( brokers=kafka_server, group_id=f"{kafka_consumer_group}-2", prefix=prefix2, stop_on_eof=True, ) worker_fn2 = functools.partial(process_replay_objects, storage=sto2) replayer2.process(worker_fn2) # Compare storages + assert isinstance(sto1, InMemoryStorage) # needed to help mypy + assert isinstance(sto2, InMemoryStorage) check_replayed(sto1, sto2) for record in caplog.records: assert ( "this should not happen" not in record.message ), "Replayer ignored some message types, see captured logging" diff --git a/swh/storage/tests/test_replay.py b/swh/storage/tests/test_replay.py index a01589b2..6562f2aa 100644 --- a/swh/storage/tests/test_replay.py +++ b/swh/storage/tests/test_replay.py @@ -1,366 +1,375 @@ # Copyright (C) 2019-2020 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 dataclasses import datetime import functools import logging from typing import Any, Container, Dict, Optional import attr import pytest from swh.journal.client import JournalClient from swh.journal.serializers import key_to_kafka, value_to_kafka -from swh.model.hashutil import DEFAULT_ALGORITHMS, MultiHash, hash_to_hex -from swh.model.tests.swh_model_data import DUPLICATE_CONTENTS, TEST_OBJECTS +from swh.model.hashutil import DEFAULT_ALGORITHMS, MultiHash, hash_to_bytes, hash_to_hex +from swh.model.model import Revision, RevisionType +from swh.model.tests.swh_model_data import ( + COMMITTERS, + DATES, + DUPLICATE_CONTENTS, + REVISIONS, +) +from swh.model.tests.swh_model_data import TEST_OBJECTS as _TEST_OBJECTS from swh.storage import get_storage from swh.storage.cassandra.model import ContentRow, SkippedContentRow from swh.storage.in_memory import InMemoryStorage from swh.storage.replay import process_replay_objects UTC = datetime.timezone.utc +TEST_OBJECTS = _TEST_OBJECTS.copy() +TEST_OBJECTS["revision"] = list(_TEST_OBJECTS["revision"]) + [ + Revision( + id=hash_to_bytes("a569b03ebe6e5f9f2f6077355c40d89bd6986d0c"), + message=b"hello again", + date=DATES[1], + committer=COMMITTERS[1], + author=COMMITTERS[0], + committer_date=DATES[0], + type=RevisionType.GIT, + directory=b"\x03" * 20, + synthetic=False, + metadata={"something": "interesting"}, + parents=(REVISIONS[0].id,), + ), +] + def nullify_ctime(obj): if isinstance(obj, (ContentRow, SkippedContentRow)): return dataclasses.replace(obj, ctime=None) else: return obj @pytest.fixture() def replayer_storage_and_client( kafka_prefix: str, kafka_consumer_group: str, kafka_server: str ): journal_writer_config = { "cls": "kafka", "brokers": [kafka_server], "client_id": "kafka_writer", "prefix": kafka_prefix, } storage_config: Dict[str, Any] = { "cls": "memory", "journal_writer": journal_writer_config, } storage = get_storage(**storage_config) replayer = JournalClient( brokers=kafka_server, group_id=kafka_consumer_group, prefix=kafka_prefix, stop_on_eof=True, ) yield storage, replayer def test_storage_replayer(replayer_storage_and_client, caplog): """Optimal replayer scenario. This: - writes objects to a source storage - replayer consumes objects from the topic and replays them - a destination storage is filled from this In the end, both storages should have the same content. """ src, replayer = replayer_storage_and_client # Fill Kafka using a source storage nb_sent = 0 for object_type, objects in TEST_OBJECTS.items(): method = getattr(src, object_type + "_add") method(objects) if object_type == "origin_visit": nb_sent += len(objects) # origin-visit-add adds origin-visit-status as well nb_sent += len(objects) caplog.set_level(logging.ERROR, "swh.journal.replay") # Fill the destination storage from Kafka dst = get_storage(cls="memory") worker_fn = functools.partial(process_replay_objects, storage=dst) nb_inserted = replayer.process(worker_fn) assert nb_sent == nb_inserted - _check_replayed(src, dst) + assert isinstance(src, InMemoryStorage) # needed to help mypy + assert isinstance(dst, InMemoryStorage) + check_replayed(src, dst) collision = 0 for record in caplog.records: logtext = record.getMessage() if "Colliding contents:" in logtext: collision += 1 assert collision == 0, "No collision should be detected" def test_storage_play_with_collision(replayer_storage_and_client, caplog): """Another replayer scenario with collisions. This: - writes objects to the topic, including colliding contents - replayer consumes objects from the topic and replay them - This drops the colliding contents from the replay when detected """ src, replayer = replayer_storage_and_client # Fill Kafka using a source storage nb_sent = 0 for object_type, objects in TEST_OBJECTS.items(): method = getattr(src, object_type + "_add") method(objects) if object_type == "origin_visit": nb_sent += len(objects) # origin-visit-add adds origin-visit-status as well nb_sent += len(objects) # Create collision in input data # These should not be written in the destination producer = src.journal_writer.journal.producer prefix = src.journal_writer.journal._prefix for content in DUPLICATE_CONTENTS: topic = f"{prefix}.content" key = content.sha1 now = datetime.datetime.now(tz=UTC) content = attr.evolve(content, ctime=now) producer.produce( topic=topic, key=key_to_kafka(key), value=value_to_kafka(content.to_dict()), ) nb_sent += 1 producer.flush() caplog.set_level(logging.ERROR, "swh.journal.replay") # Fill the destination storage from Kafka dst = get_storage(cls="memory") worker_fn = functools.partial(process_replay_objects, storage=dst) nb_inserted = replayer.process(worker_fn) assert nb_sent == nb_inserted # check the logs for the collision being properly detected nb_collisions = 0 actual_collision: Dict for record in caplog.records: logtext = record.getMessage() if "Collision detected:" in logtext: nb_collisions += 1 actual_collision = record.args["collision"] assert nb_collisions == 1, "1 collision should be detected" algo = "sha1" assert actual_collision["algo"] == algo expected_colliding_hash = hash_to_hex(DUPLICATE_CONTENTS[0].get_hash(algo)) assert actual_collision["hash"] == expected_colliding_hash actual_colliding_hashes = actual_collision["objects"] assert len(actual_colliding_hashes) == len(DUPLICATE_CONTENTS) for content in DUPLICATE_CONTENTS: expected_content_hashes = { k: hash_to_hex(v) for k, v in content.hashes().items() } assert expected_content_hashes in actual_colliding_hashes # all objects from the src should exists in the dst storage - _check_replayed(src, dst, exclude=["contents"]) + assert isinstance(src, InMemoryStorage) # needed to help mypy + assert isinstance(dst, InMemoryStorage) # needed to help mypy + check_replayed(src, dst, exclude=["contents"]) # but the dst has one content more (one of the 2 colliding ones) assert ( len(list(src._cql_runner._contents.iter_all())) == len(list(dst._cql_runner._contents.iter_all())) - 1 ) def test_replay_skipped_content(replayer_storage_and_client): """Test the 'skipped_content' topic is properly replayed.""" src, replayer = replayer_storage_and_client _check_replay_skipped_content(src, replayer, "skipped_content") def test_replay_skipped_content_bwcompat(replayer_storage_and_client): """Test the 'content' topic can be used to replay SkippedContent objects.""" src, replayer = replayer_storage_and_client _check_replay_skipped_content(src, replayer, "content") # utility functions -def _check_replayed( - src: InMemoryStorage, dst: InMemoryStorage, exclude: Optional[Container] = None +def check_replayed( + src: InMemoryStorage, + dst: InMemoryStorage, + exclude: Optional[Container] = None, + expected_anonymized=False, ): - """Simple utility function to compare the content of 2 in_memory storages + """Simple utility function to compare the content of 2 in_memory storages""" + + def fix_expected(attr, row): + if expected_anonymized: + if attr == "releases": + row = dataclasses.replace( + row, author=row.author and row.author.anonymize() + ) + elif attr == "revisions": + row = dataclasses.replace( + row, + author=row.author.anonymize(), + committer=row.committer.anonymize(), + ) + if attr == "revisions": + # the replayer should now drop the metadata attribute; see + # swh/storgae/replay.py:_insert_objects() + row.metadata = "null" + + return row - """ for attr_ in ( "contents", "skipped_contents", "directories", "extid", "revisions", "releases", "snapshots", "origins", "origin_visits", "origin_visit_statuses", "raw_extrinsic_metadata", ): if exclude and attr_ in exclude: continue expected_objects = [ - (id, nullify_ctime(obj)) + (id, nullify_ctime(fix_expected(attr_, obj))) for id, obj in sorted(getattr(src._cql_runner, f"_{attr_}").iter_all()) ] got_objects = [ (id, nullify_ctime(obj)) for id, obj in sorted(getattr(dst._cql_runner, f"_{attr_}").iter_all()) ] assert got_objects == expected_objects, f"Mismatch object list for {attr_}" def _check_replay_skipped_content(storage, replayer, topic): skipped_contents = _gen_skipped_contents(100) nb_sent = len(skipped_contents) producer = storage.journal_writer.journal.producer prefix = storage.journal_writer.journal._prefix for i, obj in enumerate(skipped_contents): producer.produce( topic=f"{prefix}.{topic}", key=key_to_kafka({"sha1": obj["sha1"]}), value=value_to_kafka(obj), ) producer.flush() dst_storage = get_storage(cls="memory") worker_fn = functools.partial(process_replay_objects, storage=dst_storage) nb_inserted = replayer.process(worker_fn) assert nb_sent == nb_inserted for content in skipped_contents: assert not storage.content_find({"sha1": content["sha1"]}) # no skipped_content_find API endpoint, so use this instead assert not list(dst_storage.skipped_content_missing(skipped_contents)) def _updated(d1, d2): d1.update(d2) d1.pop("data", None) return d1 def _gen_skipped_contents(n=10): # we do not use the hypothesis strategy here because this does not play well with # pytest fixtures, and it makes test execution very slow algos = DEFAULT_ALGORITHMS | {"length"} now = datetime.datetime.now(tz=UTC) return [ _updated( MultiHash.from_data(data=f"foo{i}".encode(), hash_names=algos).digest(), { "status": "absent", "reason": "why not", "origin": f"https://somewhere/{i}", "ctime": now, }, ) for i in range(n) ] @pytest.mark.parametrize("privileged", [True, False]) def test_storage_play_anonymized( kafka_prefix: str, kafka_consumer_group: str, kafka_server: str, privileged: bool, ): """Optimal replayer scenario. This: - writes objects to the topic - replayer consumes objects from the topic and replay them This tests the behavior with both a privileged and non-privileged replayer """ writer_config = { "cls": "kafka", "brokers": [kafka_server], "client_id": "kafka_writer", "prefix": kafka_prefix, "anonymize": True, } src_config: Dict[str, Any] = {"cls": "memory", "journal_writer": writer_config} storage = get_storage(**src_config) # Fill the src storage nb_sent = 0 for obj_type, objs in TEST_OBJECTS.items(): if obj_type in ("origin_visit", "origin_visit_status"): # these are unrelated with what we want to test here continue method = getattr(storage, obj_type + "_add") method(objs) nb_sent += len(objs) # Fill a destination storage from Kafka, potentially using privileged topics dst_storage = get_storage(cls="memory") replayer = JournalClient( brokers=kafka_server, group_id=kafka_consumer_group, prefix=kafka_prefix, stop_after_objects=nb_sent, privileged=privileged, ) worker_fn = functools.partial(process_replay_objects, storage=dst_storage) nb_inserted = replayer.process(worker_fn) replayer.consumer.commit() assert nb_sent == nb_inserted # Check the contents of the destination storage, and whether the anonymization was # properly used + assert isinstance(storage, InMemoryStorage) # needed to help mypy + assert isinstance(dst_storage, InMemoryStorage) check_replayed(storage, dst_storage, expected_anonymized=not privileged) - - -def check_replayed(src, dst, expected_anonymized=False): - """Simple utility function to compare the content of 2 in_memory storages - - If expected_anonymized is True, objects from the source storage are anonymized - before comparing with the destination storage. - - """ - - def maybe_anonymize(attr_, row): - if expected_anonymized: - if attr_ == "releases": - row = dataclasses.replace(row, author=row.author.anonymize()) - elif attr_ == "revisions": - row = dataclasses.replace( - row, - author=row.author.anonymize(), - committer=row.committer.anonymize(), - ) - return row - - for attr_ in ( - "contents", - "skipped_contents", - "directories", - "revisions", - "releases", - "snapshots", - "origins", - "origin_visit_statuses", - "raw_extrinsic_metadata", - ): - expected_objects = [ - (id, nullify_ctime(maybe_anonymize(attr_, obj))) - for id, obj in sorted(getattr(src._cql_runner, f"_{attr_}").iter_all()) - ] - got_objects = [ - (id, nullify_ctime(obj)) - for id, obj in sorted(getattr(dst._cql_runner, f"_{attr_}").iter_all()) - ] - assert got_objects == expected_objects, f"Mismatch object list for {attr_}"