diff --git a/codemeta.json b/codemeta.json index 28306be..8eaf5cc 100644 --- a/codemeta.json +++ b/codemeta.json @@ -1,39 +1,39 @@ { "@context": "https://raw.githubusercontent.com/codemeta/codemeta/2.0/codemeta.jsonld", "@type": "SoftwareSourceCode", "identifier": "5682a72dc61f86ae69f2841c2184d6159c0b6d5d", "description": "Software Heritage Indexer for revisions and contents", "name": "swh-indexer", "isPartOf": { "@type": "SoftwareSourceCode", "name": "swh-environment", "identifier": "83e766feafde91242883be1bf369ed3e6865824f" }, "codeRepository": "https://forge.softwareheritage.org/diffusion/78/", "issueTracker": "https://forge.softwareheritage.org/maniphest/", "license": "https://spdx.org/licenses/GPL-3.0.html", "version": "0.0.35", "author": [ { "@type": "Organization", "name": "Software Heritage", "url": "https://www.softwareheritage.org", "email": "swh-devel@inria.fr" - }, + } ], "developmentStatus": "active", "keywords": [ "indexer", "software", "mimetype", "ctags", "language", "fossology-license", "metadata", "metadata-detector", "metadata-translator" ], "dateCreated":"2017-06-12", "datePublished":"2017-06-12", - "programmingLanguage": "Python", + "programmingLanguage": "Python" } diff --git a/docs/images/tasks-metadata-indexers.uml b/docs/images/tasks-metadata-indexers.uml index 9bb04a7..954e079 100644 --- a/docs/images/tasks-metadata-indexers.uml +++ b/docs/images/tasks-metadata-indexers.uml @@ -1,84 +1,84 @@ @startuml participant LOADERS as "Loaders" participant JOURNAL as "Journal" participant SCHEDULER as "Scheduler" participant IDX_ORIG_HEAD as "Origin-Head Indexer" participant IDX_REV_META as "Revision Metadata Indexer" participant IDX_CONT_META as "Content Metadata Indexer" participant IDX_ORIG_META as "Origin Metadata Indexer" participant IDX_STORAGE as "Indexer Storage" participant STORAGE as "Graph Storage" participant OBJ_STORAGE as "Object Storage" activate OBJ_STORAGE activate IDX_STORAGE activate STORAGE activate JOURNAL activate SCHEDULER activate LOADERS LOADERS->>JOURNAL: Origin 42 was added/revisited deactivate LOADERS JOURNAL->>SCHEDULER: run indexers on origin 42 SCHEDULER->>IDX_ORIG_HEAD: Find HEAD revision of 42 activate IDX_ORIG_HEAD IDX_ORIG_HEAD->>STORAGE: snapshot_get_latest(origin=42) STORAGE->>IDX_ORIG_HEAD: branches IDX_ORIG_HEAD->>SCHEDULER: run Revision Metadata Indexer\non revision 42abcdef\n(head of origin 42) deactivate IDX_ORIG_HEAD SCHEDULER->>IDX_REV_META: Index revision 42abcdef\n(head of origin 42) activate IDX_REV_META IDX_REV_META->>STORAGE: revision_get(sha1=42abcdef) STORAGE->>IDX_REV_META: {id: 42abcdef, message: "Commit message", directory: 456789ab, ...} IDX_REV_META->>STORAGE: directory_ls(sha1=456789ab) STORAGE->>IDX_REV_META: [{id: 1234cafe, name: "package.json", type: file, ...}, {id: cafe4321, name: "README", type: file, ...}, ...] IDX_REV_META->>IDX_REV_META: package.json is a metadata file IDX_REV_META->>IDX_STORAGE: content_metadata_get(sha1=1234cafe) IDX_STORAGE->>IDX_REV_META: none / {author: "Jane Doe", ...} alt If the storage answered "none" IDX_REV_META->>IDX_CONT_META: Index file 1234cafe as an NPM metadata file activate IDX_CONT_META IDX_CONT_META->>OBJ_STORAGE: content_get 1234cafe OBJ_STORAGE->>IDX_CONT_META: raw content is: '{"name": "FooPackage", "author": "Jane Doe"...' IDX_CONT_META->>IDX_CONT_META: "Jane Doe" is the author IDX_CONT_META->>IDX_STORAGE: content_metadata_add(sha1=1234cafe, {author: "Jane Doe", ...}) IDX_STORAGE->>IDX_CONT_META: ok IDX_CONT_META->>IDX_REV_META: extracted: {author: "Jane Doe", ...} deactivate IDX_CONT_META end IDX_REV_META->>IDX_STORAGE: revision_metadata_add(sha1=42abcdef, {author: "Jane Doe", ...}) IDX_STORAGE->>IDX_REV_META: ok IDX_REV_META->>SCHEDULER: run Origin Metadata Indexer\non origin 42; the head is 42abcdef deactivate IDX_REV_META SCHEDULER->>IDX_ORIG_META: Index origin 42; the head is 42abcdef activate IDX_ORIG_META IDX_ORIG_META->>IDX_STORAGE: revision_metadata_get(sha1=42abcdef) IDX_STORAGE->>IDX_ORIG_META: {author: "Jane Doe", ...} IDX_ORIG_META->>IDX_STORAGE: origin_metadata_add(id=42, {author: "Jane Doe", ...}) IDX_STORAGE->>IDX_ORIG_META: ok deactivate IDX_ORIG_META - + @enduml diff --git a/sql/json/revision_metadata.translated_metadata.json b/sql/json/revision_metadata.translated_metadata.json index 4b6814d..4041b2c 100644 --- a/sql/json/revision_metadata.translated_metadata.json +++ b/sql/json/revision_metadata.translated_metadata.json @@ -1,56 +1,56 @@ { "$schema": "http://json-schema.org/schema#", "id": "http://softwareheritage.org/schemas/revision_metadata.translated_metadata.schema.json", "type": "object", "properties": { "developmentStatus": { "type": "list" }, "version": { "type": "list" }, "operatingSystem": { "type": "list" }, "description": { "type": "list" }, "keywords": { "type": "list" }, "issueTracker": { "type": "list" }, "name": { "type": "list" }, "author": { "type": "list" }, "relatedLink": { "type": "list" }, "url": { "type": "list" }, "license": { "type": "list" }, "maintainer": { "type": "list" }, "email": { "type": "list" }, "softwareRequirements": { "type": "list" }, "identifier": { "type": "list" }, "codeRepository": { "type": "list" - }, + } } } diff --git a/swh/indexer/data/codemeta/codemeta.jsonld b/swh/indexer/data/codemeta/codemeta.jsonld index ecba88b..5e19122 100644 --- a/swh/indexer/data/codemeta/codemeta.jsonld +++ b/swh/indexer/data/codemeta/codemeta.jsonld @@ -1,80 +1,80 @@ { "@context": { "type": "@type", "id": "@id", "schema":"http://schema.org/", "codemeta": "https://codemeta.github.io/terms/", "Organization": {"@id": "schema:Organization"}, "Person": {"@id": "schema:Person"}, "SoftwareSourceCode": {"@id": "schema:SoftwareSourceCode"}, "SoftwareApplication": {"@id": "schema:SoftwareApplication"}, "Text": {"@id": "schema:Text"}, "URL": {"@id": "schema:URL"}, "address": { "@id": "schema:address"}, "affiliation": { "@id": "schema:affiliation"}, "applicationCategory": { "@id": "schema:applicationCategory", "@type": "@id"}, "applicationSubCategory": { "@id": "schema:applicationSubCategory", "@type": "@id"}, "citation": { "@id": "schema:citation"}, "codeRepository": { "@id": "schema:codeRepository", "@type": "@id"}, "contributor": { "@id": "schema:contributor"}, "copyrightHolder": { "@id": "schema:copyrightHolder"}, "copyrightYear": { "@id": "schema:copyrightYear"}, "creator": { "@id": "schema:creator"}, "dateCreated": {"@id": "schema:dateCreated", "@type": "schema:Date" }, "dateModified": {"@id": "schema:dateModified", "@type": "schema:Date" }, "datePublished": {"@id": "schema:datePublished", "@type": "schema:Date" }, "description": { "@id": "schema:description"}, "downloadUrl": { "@id": "schema:downloadUrl", "@type": "@id"}, "email": { "@id": "schema:email"}, "editor": { "@id": "schema:editor"}, "encoding": { "@id": "schema:encoding"}, "familyName": { "@id": "schema:familyName"}, "fileFormat": { "@id": "schema:fileFormat", "@type": "@id"}, "fileSize": { "@id": "schema:fileSize"}, "funder": { "@id": "schema:funder"}, "givenName": { "@id": "schema:givenName"}, "hasPart": { "@id": "schema:hasPart" }, "identifier": { "@id": "schema:identifier", "@type": "@id"}, "installUrl": { "@id": "schema:installUrl", "@type": "@id"}, "isAccessibleForFree": { "@id": "schema:isAccessibleForFree"}, "isPartOf": { "@id": "schema:isPartOf"}, "keywords": { "@id": "schema:keywords"}, "license": { "@id": "schema:license", "@type": "@id"}, "memoryRequirements": { "@id": "schema:memoryRequirements", "@type": "@id"}, "name": { "@id": "schema:name"}, "operatingSystem": { "@id": "schema:operatingSystem"}, "permissions": { "@id": "schema:permissions"}, "position": { "@id": "schema:position"}, "processorRequirements": { "@id": "schema:processorRequirements"}, "producer": { "@id": "schema:producer"}, "programmingLanguage": { "@id": "schema:programmingLanguage"}, "provider": { "@id": "schema:provider"}, "publisher": { "@id": "schema:publisher"}, "relatedLink": { "@id": "schema:relatedLink", "@type": "@id"}, "releaseNotes": { "@id": "schema:releaseNotes", "@type": "@id"}, "runtimePlatform": { "@id": "schema:runtimePlatform"}, "sameAs": { "@id": "schema:sameAs", "@type": "@id"}, "softwareHelp": { "@id": "schema:softwareHelp"}, "softwareRequirements": { "@id": "schema:softwareRequirements", "@type": "@id"}, "softwareVersion": { "@id": "schema:softwareVersion"}, "sponsor": { "@id": "schema:sponsor"}, "storageRequirements": { "@id": "schema:storageRequirements", "@type": "@id"}, "supportingData": { "@id": "schema:supportingData"}, "targetProduct": { "@id": "schema:targetProduct"}, "url": { "@id": "schema:url", "@type": "@id"}, "version": { "@id": "schema:version"}, - + "author": { "@id": "schema:author", "@container": "@list" }, - + "softwareSuggestions": { "@id": "codemeta:softwareSuggestions", "@type": "@id"}, "contIntegration": { "@id": "codemeta:contIntegration", "@type": "@id"}, "buildInstructions": { "@id": "codemeta:buildInstructions", "@type": "@id"}, "developmentStatus": { "@id": "codemeta:developmentStatus", "@type": "@id"}, "embargoDate": { "@id":"codemeta:embargoDate", "@type": "schema:Date" }, "funding": { "@id": "codemeta:funding" }, "readme": { "@id":"codemeta:readme", "@type": "@id" }, "issueTracker": { "@id":"codemeta:issueTracker", "@type": "@id" }, "referencePublication": { "@id": "codemeta:referencePublication", "@type": "@id"}, "maintainer": { "@id": "codemeta:maintainer" } } } diff --git a/swh/indexer/sql/40-swh-func.sql b/swh/indexer/sql/40-swh-func.sql index 31ab57c..d2c62b7 100644 --- a/swh/indexer/sql/40-swh-func.sql +++ b/swh/indexer/sql/40-swh-func.sql @@ -1,454 +1,454 @@ -- Postgresql index helper function create or replace function hash_sha1(text) returns text language sql strict immutable as $$ select encode(public.digest($1, 'sha1'), 'hex') $$; comment on function hash_sha1(text) is 'Compute sha1 hash as text'; -- create a temporary table called tmp_TBLNAME, mimicking existing table -- TBLNAME -- -- Args: --- tblname: name of the table to mimick +-- tblname: name of the table to mimic create or replace function swh_mktemp(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table tmp_%1$I (like %1$I including defaults) on commit drop; alter table tmp_%1$I drop column if exists object_id; ', tblname); return; end $$; -- create a temporary table for content_mimetype tmp_content_mimetype, create or replace function swh_mktemp_content_mimetype() returns void language sql as $$ create temporary table tmp_content_mimetype ( like content_mimetype including defaults ) on commit drop; $$; comment on function swh_mktemp_content_mimetype() IS 'Helper table to add mimetype information'; -- add tmp_content_mimetype entries to content_mimetype, overwriting -- duplicates if conflict_update is true, skipping duplicates otherwise. -- -- If filtering duplicates is in order, the call to -- swh_content_mimetype_missing must take place before calling this -- function. -- -- -- operates in bulk: 0. swh_mktemp(content_mimetype), 1. COPY to tmp_content_mimetype, -- 2. call this function create or replace function swh_content_mimetype_add(conflict_update boolean) returns void language plpgsql as $$ begin if conflict_update then insert into content_mimetype (id, mimetype, encoding, indexer_configuration_id) select id, mimetype, encoding, indexer_configuration_id from tmp_content_mimetype tcm on conflict(id, indexer_configuration_id) do update set mimetype = excluded.mimetype, encoding = excluded.encoding; else insert into content_mimetype (id, mimetype, encoding, indexer_configuration_id) select id, mimetype, encoding, indexer_configuration_id from tmp_content_mimetype tcm on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; comment on function swh_content_mimetype_add(boolean) IS 'Add new content mimetypes'; -- add tmp_content_language entries to content_language, overwriting -- duplicates if conflict_update is true, skipping duplicates otherwise. -- -- If filtering duplicates is in order, the call to -- swh_content_language_missing must take place before calling this -- function. -- -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to -- tmp_content_language, 2. call this function create or replace function swh_content_language_add(conflict_update boolean) returns void language plpgsql as $$ begin if conflict_update then insert into content_language (id, lang, indexer_configuration_id) select id, lang, indexer_configuration_id from tmp_content_language tcl on conflict(id, indexer_configuration_id) do update set lang = excluded.lang; else insert into content_language (id, lang, indexer_configuration_id) select id, lang, indexer_configuration_id from tmp_content_language tcl on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; comment on function swh_content_language_add(boolean) IS 'Add new content languages'; -- create a temporary table for retrieving content_language create or replace function swh_mktemp_content_language() returns void language sql as $$ create temporary table tmp_content_language ( like content_language including defaults ) on commit drop; $$; comment on function swh_mktemp_content_language() is 'Helper table to add content language'; -- create a temporary table for content_ctags tmp_content_ctags, create or replace function swh_mktemp_content_ctags() returns void language sql as $$ create temporary table tmp_content_ctags ( like content_ctags including defaults ) on commit drop; $$; comment on function swh_mktemp_content_ctags() is 'Helper table to add content ctags'; -- add tmp_content_ctags entries to content_ctags, overwriting -- duplicates if conflict_update is true, skipping duplicates otherwise. -- -- operates in bulk: 0. swh_mktemp(content_ctags), 1. COPY to tmp_content_ctags, -- 2. call this function create or replace function swh_content_ctags_add(conflict_update boolean) returns void language plpgsql as $$ begin if conflict_update then delete from content_ctags where id in (select tmp.id from tmp_content_ctags tmp inner join indexer_configuration i on i.id=tmp.indexer_configuration_id); end if; insert into content_ctags (id, name, kind, line, lang, indexer_configuration_id) select id, name, kind, line, lang, indexer_configuration_id from tmp_content_ctags tct on conflict(id, hash_sha1(name), kind, line, lang, indexer_configuration_id) do nothing; return; end $$; comment on function swh_content_ctags_add(boolean) IS 'Add new ctags symbols per content'; create type content_ctags_signature as ( id sha1, name text, kind text, line bigint, lang ctags_languages, tool_id integer, tool_name text, tool_version text, tool_configuration jsonb ); -- Search within ctags content. -- create or replace function swh_content_ctags_search( expression text, l integer default 10, last_sha1 sha1 default '\x0000000000000000000000000000000000000000') returns setof content_ctags_signature language sql as $$ select c.id, name, kind, line, lang, i.id as tool_id, tool_name, tool_version, tool_configuration from content_ctags c inner join indexer_configuration i on i.id = c.indexer_configuration_id where hash_sha1(name) = hash_sha1(expression) and c.id > last_sha1 order by id limit l; $$; comment on function swh_content_ctags_search(text, integer, sha1) IS 'Equality search through ctags'' symbols'; -- create a temporary table for content_fossology_license tmp_content_fossology_license, create or replace function swh_mktemp_content_fossology_license() returns void language sql as $$ create temporary table tmp_content_fossology_license ( id sha1, license text, indexer_configuration_id integer ) on commit drop; $$; comment on function swh_mktemp_content_fossology_license() is 'Helper table to add content license'; -- add tmp_content_fossology_license entries to content_fossology_license, overwriting -- duplicates if conflict_update is true, skipping duplicates otherwise. -- -- operates in bulk: 0. swh_mktemp(content_fossology_license), 1. COPY to -- tmp_content_fossology_license, 2. call this function create or replace function swh_content_fossology_license_add(conflict_update boolean) returns void language plpgsql as $$ begin -- insert unknown licenses first insert into fossology_license (name) select distinct license from tmp_content_fossology_license tmp where not exists (select 1 from fossology_license where name=tmp.license) on conflict(name) do nothing; if conflict_update then -- delete from content_fossology_license c -- using tmp_content_fossology_license tmp, indexer_configuration i -- where c.id = tmp.id and i.id=tmp.indexer_configuration_id delete from content_fossology_license where id in (select tmp.id from tmp_content_fossology_license tmp inner join indexer_configuration i on i.id=tmp.indexer_configuration_id); end if; insert into content_fossology_license (id, license_id, indexer_configuration_id) select tcl.id, (select id from fossology_license where name = tcl.license) as license, indexer_configuration_id from tmp_content_fossology_license tcl on conflict(id, license_id, indexer_configuration_id) do nothing; return; end $$; comment on function swh_content_fossology_license_add(boolean) IS 'Add new content licenses'; -- content_metadata functions -- add tmp_content_metadata entries to content_metadata, overwriting -- duplicates if conflict_update is true, skipping duplicates otherwise. -- -- If filtering duplicates is in order, the call to -- swh_content_metadata_missing must take place before calling this -- function. -- -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to -- tmp_content_metadata, 2. call this function create or replace function swh_content_metadata_add(conflict_update boolean) returns void language plpgsql as $$ begin if conflict_update then insert into content_metadata (id, metadata, indexer_configuration_id) select id, metadata, indexer_configuration_id from tmp_content_metadata tcm on conflict(id, indexer_configuration_id) do update set metadata = excluded.metadata; else insert into content_metadata (id, metadata, indexer_configuration_id) select id, metadata, indexer_configuration_id from tmp_content_metadata tcm on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; comment on function swh_content_metadata_add(boolean) IS 'Add new content metadata'; -- create a temporary table for retrieving content_metadata create or replace function swh_mktemp_content_metadata() returns void language sql as $$ create temporary table tmp_content_metadata ( like content_metadata including defaults ) on commit drop; $$; comment on function swh_mktemp_content_metadata() is 'Helper table to add content metadata'; -- end content_metadata functions -- add tmp_revision_intrinsic_metadata entries to revision_intrinsic_metadata, -- overwriting duplicates if conflict_update is true, skipping duplicates -- otherwise. -- -- If filtering duplicates is in order, the call to -- swh_revision_intrinsic_metadata_missing must take place before calling this -- function. -- -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to -- tmp_revision_intrinsic_metadata, 2. call this function create or replace function swh_revision_intrinsic_metadata_add(conflict_update boolean) returns void language plpgsql as $$ begin if conflict_update then insert into revision_intrinsic_metadata (id, metadata, mappings, indexer_configuration_id) select id, metadata, mappings, indexer_configuration_id from tmp_revision_intrinsic_metadata tcm on conflict(id, indexer_configuration_id) do update set metadata = excluded.metadata, mappings = excluded.mappings; else insert into revision_intrinsic_metadata (id, metadata, mappings, indexer_configuration_id) select id, metadata, mappings, indexer_configuration_id from tmp_revision_intrinsic_metadata tcm on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; comment on function swh_revision_intrinsic_metadata_add(boolean) IS 'Add new revision intrinsic metadata'; -- create a temporary table for retrieving revision_intrinsic_metadata create or replace function swh_mktemp_revision_intrinsic_metadata() returns void language sql as $$ create temporary table tmp_revision_intrinsic_metadata ( like revision_intrinsic_metadata including defaults ) on commit drop; $$; comment on function swh_mktemp_revision_intrinsic_metadata() is 'Helper table to add revision intrinsic metadata'; -- create a temporary table for retrieving origin_intrinsic_metadata create or replace function swh_mktemp_origin_intrinsic_metadata() returns void language sql as $$ create temporary table tmp_origin_intrinsic_metadata ( like origin_intrinsic_metadata including defaults ) on commit drop; $$; comment on function swh_mktemp_origin_intrinsic_metadata() is 'Helper table to add origin intrinsic metadata'; create or replace function swh_mktemp_indexer_configuration() returns void language sql as $$ create temporary table tmp_indexer_configuration ( like indexer_configuration including defaults ) on commit drop; alter table tmp_indexer_configuration drop column id; $$; -- add tmp_indexer_configuration entries to indexer_configuration, -- skipping duplicates if any. -- -- operates in bulk: 0. create temporary tmp_indexer_configuration, 1. COPY to -- it, 2. call this function to insert and filtering out duplicates create or replace function swh_indexer_configuration_add() returns setof indexer_configuration language plpgsql as $$ begin insert into indexer_configuration(tool_name, tool_version, tool_configuration) select tool_name, tool_version, tool_configuration from tmp_indexer_configuration tmp on conflict(tool_name, tool_version, tool_configuration) do nothing; return query select id, tool_name, tool_version, tool_configuration from tmp_indexer_configuration join indexer_configuration using(tool_name, tool_version, tool_configuration); return; end $$; -- add tmp_origin_intrinsic_metadata entries to origin_intrinsic_metadata, -- overwriting duplicates if conflict_update is true, skipping duplicates -- otherwise. -- -- If filtering duplicates is in order, the call to -- swh_origin_intrinsic_metadata_missing must take place before calling this -- function. -- -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to -- tmp_origin_intrinsic_metadata, 2. call this function create or replace function swh_origin_intrinsic_metadata_add( conflict_update boolean) returns void language plpgsql as $$ begin perform swh_origin_intrinsic_metadata_compute_tsvector(); if conflict_update then insert into origin_intrinsic_metadata (id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) select id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings from tmp_origin_intrinsic_metadata on conflict(id, indexer_configuration_id) do update set metadata = excluded.metadata, metadata_tsvector = excluded.metadata_tsvector, mappings = excluded.mappings, from_revision = excluded.from_revision; else insert into origin_intrinsic_metadata (id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) select id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings from tmp_origin_intrinsic_metadata on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; comment on function swh_origin_intrinsic_metadata_add(boolean) IS 'Add new origin intrinsic metadata'; -- Compute the metadata_tsvector column in tmp_origin_intrinsic_metadata. -- -- It uses the "pg_catalog.simple" dictionary, as it has no stopword, -- so it should be suitable for proper names and non-English text. create or replace function swh_origin_intrinsic_metadata_compute_tsvector() returns void language plpgsql as $$ begin update tmp_origin_intrinsic_metadata set metadata_tsvector = to_tsvector('pg_catalog.simple', metadata); end $$; diff --git a/swh/indexer/storage/__init__.py b/swh/indexer/storage/__init__.py index a8d557f..c76af20 100644 --- a/swh/indexer/storage/__init__.py +++ b/swh/indexer/storage/__init__.py @@ -1,936 +1,936 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import json import psycopg2 from collections import defaultdict from swh.core.api import remote_api_endpoint from swh.storage.common import db_transaction_generator, db_transaction from swh.storage.exc import StorageDBError from .db import Db from . import converters INDEXER_CFG_KEY = 'indexer_storage' MAPPING_NAMES = ['codemeta', 'gemspec', 'maven', 'npm', 'pkg-info'] def get_indexer_storage(cls, args): """Get an indexer storage object of class `storage_class` with arguments `storage_args`. Args: cls (str): storage's class, either 'local' or 'remote' args (dict): dictionary of arguments passed to the storage class constructor Returns: an instance of swh.indexer's storage (either local or remote) Raises: ValueError if passed an unknown storage class. """ if cls == 'remote': from .api.client import RemoteStorage as IndexerStorage elif cls == 'local': from . import IndexerStorage elif cls == 'memory': from .in_memory import IndexerStorage else: raise ValueError('Unknown indexer storage class `%s`' % cls) return IndexerStorage(**args) def _check_id_duplicates(data): """ If any two dictionaries in `data` have the same id, raises a `ValueError`. Values associated to the key must be hashable. Args: data (List[dict]): List of dictionaries to be inserted >>> _check_id_duplicates([ ... {'id': 'foo', 'data': 'spam'}, ... {'id': 'bar', 'data': 'egg'}, ... ]) >>> _check_id_duplicates([ ... {'id': 'foo', 'data': 'spam'}, ... {'id': 'foo', 'data': 'egg'}, ... ]) Traceback (most recent call last): ... ValueError: The same id is present more than once. """ if len({item['id'] for item in data}) < len(data): raise ValueError('The same id is present more than once.') class IndexerStorage: """SWH Indexer Storage """ def __init__(self, db, min_pool_conns=1, max_pool_conns=10): """ Args: db_conn: either a libpq connection string, or a psycopg2 connection """ 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) def get_db(self): if self._db: return self._db return Db.from_pool(self._pool) def put_db(self, db): if db is not self._db: db.put_conn() @remote_api_endpoint('check_config') @db_transaction() def check_config(self, *, check_write, db=None, cur=None): """Check that the storage is configured and ready to go.""" # Check permissions on one of the tables if check_write: check = 'INSERT' else: check = 'SELECT' cur.execute( "select has_table_privilege(current_user, 'content_mimetype', %s)", # noqa (check,) ) return cur.fetchone()[0] @remote_api_endpoint('content_mimetype/missing') @db_transaction_generator() def content_mimetype_missing(self, mimetypes, db=None, cur=None): """Generate mimetypes missing from storage. Args: mimetypes (iterable): iterable of dict with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: tuple (id, indexer_configuration_id): missing id """ for obj in db.content_mimetype_missing_from_list(mimetypes, cur): yield obj[0] def _content_get_range(self, content_type, start, end, indexer_configuration_id, limit=1000, with_textual_data=False, db=None, cur=None): """Retrieve ids of type content_type within range [start, end] bound by limit. Args: **content_type** (str): content's type (mimetype, language, etc...) **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) **with_textual_data** (bool): Deal with only textual content (True) or all content (all contents by defaults, False) Raises: ValueError for; - limit to None - wrong content_type provided Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ if limit is None: raise ValueError('Development error: limit should not be None') if content_type not in db.content_indexer_names: err = 'Development error: Wrong type. Should be one of [%s]' % ( ','.join(db.content_indexer_names)) raise ValueError(err) ids = [] next_id = None for counter, obj in enumerate(db.content_get_range( content_type, start, end, indexer_configuration_id, limit=limit+1, with_textual_data=with_textual_data, cur=cur)): _id = obj[0] if counter >= limit: next_id = _id break ids.append(_id) return { 'ids': ids, 'next': next_id } @remote_api_endpoint('content_mimetype/range') @db_transaction() def content_mimetype_get_range(self, start, end, indexer_configuration_id, limit=1000, db=None, cur=None): """Retrieve mimetypes within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ return self._content_get_range('mimetype', start, end, indexer_configuration_id, limit=limit, db=db, cur=cur) @remote_api_endpoint('content_mimetype/add') @db_transaction() def content_mimetype_add(self, mimetypes, conflict_update=False, db=None, cur=None): """Add mimetypes not present in storage. Args: mimetypes (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **mimetype** (bytes): raw content's mimetype - **encoding** (bytes): raw content's encoding - **indexer_configuration_id** (int): tool's id used to compute the results - **conflict_update** (bool): Flag to determine if we want to overwrite (``True``) or skip duplicates (``False``, the default) """ _check_id_duplicates(mimetypes) mimetypes.sort(key=lambda m: m['id']) db.mktemp_content_mimetype(cur) db.copy_to(mimetypes, 'tmp_content_mimetype', ['id', 'mimetype', 'encoding', 'indexer_configuration_id'], cur) db.content_mimetype_add_from_temp(conflict_update, cur) @remote_api_endpoint('content_mimetype') @db_transaction_generator() def content_mimetype_get(self, ids, db=None, cur=None): """Retrieve full content mimetype per ids. Args: ids (iterable): sha1 identifier Yields: mimetypes (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **mimetype** (bytes): raw content's mimetype - **encoding** (bytes): raw content's encoding - **tool** (dict): Tool used to compute the language """ for c in db.content_mimetype_get_from_list(ids, cur): yield converters.db_to_mimetype( dict(zip(db.content_mimetype_cols, c))) @remote_api_endpoint('content_language/missing') @db_transaction_generator() def content_language_missing(self, languages, db=None, cur=None): """List languages missing from storage. Args: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: an iterable of missing id for the tuple (id, indexer_configuration_id) """ for obj in db.content_language_missing_from_list(languages, cur): yield obj[0] @remote_api_endpoint('content_language') @db_transaction_generator() def content_language_get(self, ids, db=None, cur=None): """Retrieve full content language per ids. Args: ids (iterable): sha1 identifier Yields: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **lang** (bytes): raw content's language - **tool** (dict): Tool used to compute the language """ for c in db.content_language_get_from_list(ids, cur): yield converters.db_to_language( dict(zip(db.content_language_cols, c))) @remote_api_endpoint('content_language/add') @db_transaction() def content_language_add(self, languages, conflict_update=False, db=None, cur=None): """Add languages not present in storage. Args: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 - **lang** (bytes): language detected conflict_update (bool): Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ _check_id_duplicates(languages) languages.sort(key=lambda m: m['id']) db.mktemp_content_language(cur) # empty language is mapped to 'unknown' db.copy_to( ({ 'id': l['id'], 'lang': 'unknown' if not l['lang'] else l['lang'], 'indexer_configuration_id': l['indexer_configuration_id'], } for l in languages), 'tmp_content_language', ['id', 'lang', 'indexer_configuration_id'], cur) db.content_language_add_from_temp(conflict_update, cur) @remote_api_endpoint('content/ctags/missing') @db_transaction_generator() def content_ctags_missing(self, ctags, db=None, cur=None): """List ctags missing from storage. Args: ctags (iterable): dicts with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: an iterable of missing id for the tuple (id, indexer_configuration_id) """ for obj in db.content_ctags_missing_from_list(ctags, cur): yield obj[0] @remote_api_endpoint('content/ctags') @db_transaction_generator() def content_ctags_get(self, ids, db=None, cur=None): """Retrieve ctags per id. Args: ids (iterable): sha1 checksums Yields: Dictionaries with keys: - **id** (bytes): content's identifier - **name** (str): symbol's name - **kind** (str): symbol's kind - **lang** (str): language for that content - **tool** (dict): tool used to compute the ctags' info """ for c in db.content_ctags_get_from_list(ids, cur): yield converters.db_to_ctags(dict(zip(db.content_ctags_cols, c))) @remote_api_endpoint('content/ctags/add') @db_transaction() def content_ctags_add(self, ctags, conflict_update=False, db=None, cur=None): """Add ctags not present in storage Args: ctags (iterable): dictionaries with keys: - **id** (bytes): sha1 - **ctags** ([list): List of dictionary with keys: name, kind, line, lang """ _check_id_duplicates(ctags) ctags.sort(key=lambda m: m['id']) def _convert_ctags(__ctags): """Convert ctags dict to list of ctags. """ for ctags in __ctags: yield from converters.ctags_to_db(ctags) db.mktemp_content_ctags(cur) db.copy_to(list(_convert_ctags(ctags)), tblname='tmp_content_ctags', columns=['id', 'name', 'kind', 'line', 'lang', 'indexer_configuration_id'], cur=cur) db.content_ctags_add_from_temp(conflict_update, cur) @remote_api_endpoint('content/ctags/search') @db_transaction_generator() def content_ctags_search(self, expression, limit=10, last_sha1=None, db=None, cur=None): """Search through content's raw ctags symbols. Args: expression (str): Expression to search for limit (int): Number of rows to return (default to 10). last_sha1 (str): Offset from which retrieving data (default to ''). Yields: rows of ctags including id, name, lang, kind, line, etc... """ for obj in db.content_ctags_search(expression, last_sha1, limit, cur=cur): yield converters.db_to_ctags(dict(zip(db.content_ctags_cols, obj))) @remote_api_endpoint('content/fossology_license') @db_transaction_generator() def content_fossology_license_get(self, ids, db=None, cur=None): """Retrieve licenses per id. Args: ids (iterable): sha1 checksums Yields: dict: ``{id: facts}`` where ``facts`` is a dict with the following keys: - **licenses** ([str]): associated licenses for that content - **tool** (dict): Tool used to compute the license """ d = defaultdict(list) for c in db.content_fossology_license_get_from_list(ids, cur): license = dict(zip(db.content_fossology_license_cols, c)) id_ = license['id'] d[id_].append(converters.db_to_fossology_license(license)) for id_, facts in d.items(): yield {id_: facts} @remote_api_endpoint('content/fossology_license/add') @db_transaction() def content_fossology_license_add(self, licenses, conflict_update=False, db=None, cur=None): """Add licenses not present in storage. Args: licenses (iterable): dictionaries with keys: - **id**: sha1 - **licenses** ([bytes]): List of licenses associated to sha1 - **tool** (str): nomossa conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) Returns: list: content_license entries which failed due to unknown licenses """ _check_id_duplicates(licenses) licenses.sort(key=lambda m: m['id']) db.mktemp_content_fossology_license(cur) db.copy_to( ({ 'id': sha1['id'], 'indexer_configuration_id': sha1['indexer_configuration_id'], 'license': license, } for sha1 in licenses for license in sha1['licenses']), tblname='tmp_content_fossology_license', columns=['id', 'license', 'indexer_configuration_id'], cur=cur) db.content_fossology_license_add_from_temp(conflict_update, cur) @remote_api_endpoint('content/fossology_license/range') @db_transaction() def content_fossology_license_get_range( self, start, end, indexer_configuration_id, limit=1000, db=None, cur=None): """Retrieve licenses within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ return self._content_get_range('fossology_license', start, end, indexer_configuration_id, limit=limit, with_textual_data=True, db=db, cur=cur) @remote_api_endpoint('content_metadata/missing') @db_transaction_generator() def content_metadata_missing(self, metadata, db=None, cur=None): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing sha1s """ for obj in db.content_metadata_missing_from_list(metadata, cur): yield obj[0] @remote_api_endpoint('content_metadata') @db_transaction_generator() def content_metadata_get(self, ids, db=None, cur=None): """Retrieve metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: id (bytes) metadata (str): associated metadata tool (dict): tool used to compute metadata """ for c in db.content_metadata_get_from_list(ids, cur): yield converters.db_to_metadata( dict(zip(db.content_metadata_cols, c))) @remote_api_endpoint('content_metadata/add') @db_transaction() def content_metadata_add(self, metadata, conflict_update=False, db=None, cur=None): """Add metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: sha1 - **metadata**: arbitrary dict conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ _check_id_duplicates(metadata) metadata.sort(key=lambda m: m['id']) db.mktemp_content_metadata(cur) db.copy_to(metadata, 'tmp_content_metadata', ['id', 'metadata', 'indexer_configuration_id'], cur) db.content_metadata_add_from_temp(conflict_update, cur) @remote_api_endpoint('revision_intrinsic_metadata/missing') @db_transaction_generator() def revision_intrinsic_metadata_missing(self, metadata, db=None, cur=None): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1_git revision identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing ids """ for obj in db.revision_intrinsic_metadata_missing_from_list( metadata, cur): yield obj[0] @remote_api_endpoint('revision_intrinsic_metadata') @db_transaction_generator() def revision_intrinsic_metadata_get(self, ids, db=None, cur=None): """Retrieve revision metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: - **id** (bytes) - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ for c in db.revision_intrinsic_metadata_get_from_list(ids, cur): yield converters.db_to_metadata( dict(zip(db.revision_intrinsic_metadata_cols, c))) @remote_api_endpoint('revision_intrinsic_metadata/add') @db_transaction() def revision_intrinsic_metadata_add(self, metadata, conflict_update=False, db=None, cur=None): """Add metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: sha1_git of revision - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ _check_id_duplicates(metadata) metadata.sort(key=lambda m: m['id']) db.mktemp_revision_intrinsic_metadata(cur) db.copy_to(metadata, 'tmp_revision_intrinsic_metadata', ['id', 'metadata', 'mappings', 'indexer_configuration_id'], cur) db.revision_intrinsic_metadata_add_from_temp(conflict_update, cur) @remote_api_endpoint('revision_intrinsic_metadata/delete') @db_transaction() def revision_intrinsic_metadata_delete(self, entries, db=None, cur=None): """Remove revision metadata from the storage. Args: entries (dict): dictionaries with the following keys: - **id** (bytes): revision identifier - **indexer_configuration_id** (int): tool used to compute metadata """ db.revision_intrinsic_metadata_delete(entries, cur) @remote_api_endpoint('origin_intrinsic_metadata') @db_transaction_generator() def origin_intrinsic_metadata_get(self, ids, db=None, cur=None): """Retrieve origin metadata per id. Args: ids (iterable): origin identifiers Yields: list: dictionaries with the following keys: - **id** (str): origin url - **from_revision** (bytes): which revision this metadata was extracted from - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ for c in db.origin_intrinsic_metadata_get_from_list(ids, cur): yield converters.db_to_metadata( dict(zip(db.origin_intrinsic_metadata_cols, c))) @remote_api_endpoint('origin_intrinsic_metadata/add') @db_transaction() def origin_intrinsic_metadata_add(self, metadata, conflict_update=False, db=None, cur=None): """Add origin metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: origin urls - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ _check_id_duplicates(metadata) metadata.sort(key=lambda m: m['id']) db.mktemp_origin_intrinsic_metadata(cur) db.copy_to(metadata, 'tmp_origin_intrinsic_metadata', ['id', 'metadata', 'indexer_configuration_id', 'from_revision', 'mappings'], cur) db.origin_intrinsic_metadata_add_from_temp(conflict_update, cur) @remote_api_endpoint('origin_intrinsic_metadata/delete') @db_transaction() def origin_intrinsic_metadata_delete( self, entries, db=None, cur=None): """Remove origin metadata from the storage. Args: entries (dict): dictionaries with the following keys: - **id** (str): origin urls - **indexer_configuration_id** (int): tool used to compute metadata """ db.origin_intrinsic_metadata_delete(entries, cur) @remote_api_endpoint('origin_intrinsic_metadata/search/fulltext') @db_transaction_generator() def origin_intrinsic_metadata_search_fulltext( self, conjunction, limit=100, db=None, cur=None): """Returns the list of origins whose metadata contain all the terms. Args: conjunction (List[str]): List of terms to be searched for. limit (int): The maximum number of results to return Yields: list: dictionaries with the following keys: - **id** (str): origin urls - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ for c in db.origin_intrinsic_metadata_search_fulltext( conjunction, limit=limit, cur=cur): yield converters.db_to_metadata( dict(zip(db.origin_intrinsic_metadata_cols, c))) @remote_api_endpoint('origin_intrinsic_metadata/search/by_producer') @db_transaction() def origin_intrinsic_metadata_search_by_producer( self, page_token='', limit=100, ids_only=False, mappings=None, tool_ids=None, db=None, cur=None): """Returns the list of origins whose metadata contain all the terms. Args: page_token (str): Opaque token used for pagination. limit (int): The maximum number of results to return ids_only (bool): Determines whether only origin urls are returned or the content as well mappings (List[str]): Returns origins whose intrinsic metadata were generated using at least one of these mappings. Returns: dict: dict with the following keys: - **next_page_token** (str, optional): opaque token to be used as `page_token` for retrieving the next page. If absent, there is no more pages to gather. - **origins** (list): list of origin url (str) if `ids_only=True` else dictionaries with the following keys: - **id** (str): origin urls - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ assert isinstance(page_token, str) - # we go to limit+1 to check wether we should add next_page_token in + # we go to limit+1 to check whether we should add next_page_token in # the response res = db.origin_intrinsic_metadata_search_by_producer( page_token, limit + 1, ids_only, mappings, tool_ids, cur) result = {} if ids_only: result['origins'] = [origin for (origin,) in res] if len(result['origins']) > limit: result['origins'][limit:] = [] result['next_page_token'] = result['origins'][-1] else: result['origins'] = [converters.db_to_metadata( dict(zip(db.origin_intrinsic_metadata_cols, c)))for c in res] if len(result['origins']) > limit: result['origins'][limit:] = [] result['next_page_token'] = result['origins'][-1]['id'] return result @remote_api_endpoint('origin_intrinsic_metadata/stats') @db_transaction() def origin_intrinsic_metadata_stats( self, db=None, cur=None): """Returns counts of indexed metadata per origins, broken down into metadata types. Returns: dict: dictionary with keys: - total (int): total number of origins that were indexed (possibly yielding an empty metadata dictionary) - non_empty (int): total number of origins that we extracted a non-empty metadata dictionary from - per_mapping (dict): a dictionary with mapping names as keys and number of origins whose indexing used this mapping. Note that indexing a given origin may use 0, 1, or many mappings. """ mapping_names = [m for m in MAPPING_NAMES] select_parts = [] # Count rows for each mapping for mapping_name in mapping_names: select_parts.append(( "sum(case when (mappings @> ARRAY['%s']) " " then 1 else 0 end)" ) % mapping_name) # Total select_parts.append("sum(1)") # Rows whose metadata has at least one key that is not '@context' select_parts.append( "sum(case when ('{}'::jsonb @> (metadata - '@context')) " " then 0 else 1 end)") cur.execute('select ' + ', '.join(select_parts) + ' from origin_intrinsic_metadata') results = dict(zip(mapping_names + ['total', 'non_empty'], cur.fetchone())) return { 'total': results.pop('total'), 'non_empty': results.pop('non_empty'), 'per_mapping': results, } @remote_api_endpoint('indexer_configuration/add') @db_transaction_generator() def indexer_configuration_add(self, tools, db=None, cur=None): """Add new tools to the storage. Args: tools ([dict]): List of dictionary representing tool to insert in the db. Dictionary with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: List of dict inserted in the db (holding the id key as well). The order of the list is not guaranteed to match the order of the initial list. """ db.mktemp_indexer_configuration(cur) db.copy_to(tools, 'tmp_indexer_configuration', ['tool_name', 'tool_version', 'tool_configuration'], cur) tools = db.indexer_configuration_add_from_temp(cur) for line in tools: yield dict(zip(db.indexer_configuration_cols, line)) @remote_api_endpoint('indexer_configuration/data') @db_transaction() def indexer_configuration_get(self, tool, db=None, cur=None): """Retrieve tool information. Args: tool (dict): Dictionary representing a tool with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: The same dictionary with an `id` key, None otherwise. """ tool_conf = tool['tool_configuration'] if isinstance(tool_conf, dict): tool_conf = json.dumps(tool_conf) idx = db.indexer_configuration_get(tool['tool_name'], tool['tool_version'], tool_conf) if not idx: return None return dict(zip(db.indexer_configuration_cols, idx)) diff --git a/swh/indexer/storage/in_memory.py b/swh/indexer/storage/in_memory.py index 0aed233..9a589d4 100644 --- a/swh/indexer/storage/in_memory.py +++ b/swh/indexer/storage/in_memory.py @@ -1,848 +1,848 @@ # Copyright (C) 2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import bisect from collections import defaultdict, Counter import itertools import json import operator import math import re from . import MAPPING_NAMES SHA1_DIGEST_SIZE = 160 def _transform_tool(tool): return { 'id': tool['id'], 'name': tool['tool_name'], 'version': tool['tool_version'], 'configuration': tool['tool_configuration'], } class SubStorage: """Implements common missing/get/add logic for each indexer type.""" def __init__(self, tools): self._tools = tools self._sorted_ids = [] self._data = {} # map (id_, tool_id) -> metadata_dict self._tools_per_id = defaultdict(set) # map id_ -> Set[tool_id] def missing(self, ids): """List data missing from storage. Args: data (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing sha1s """ for id_ in ids: tool_id = id_['indexer_configuration_id'] id_ = id_['id'] if tool_id not in self._tools_per_id.get(id_, set()): yield id_ def get(self, ids): """Retrieve data per id. Args: ids (iterable): sha1 checksums Yields: dict: dictionaries with the following keys: - **id** (bytes) - **tool** (dict): tool used to compute metadata - arbitrary data (as provided to `add`) """ for id_ in ids: for tool_id in self._tools_per_id.get(id_, set()): key = (id_, tool_id) yield { 'id': id_, 'tool': _transform_tool(self._tools[tool_id]), **self._data[key], } def get_all(self): yield from self.get(self._sorted_ids) def get_range(self, start, end, indexer_configuration_id, limit): """Retrieve data within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ if limit is None: raise ValueError('Development error: limit should not be None') from_index = bisect.bisect_left(self._sorted_ids, start) to_index = bisect.bisect_right(self._sorted_ids, end, lo=from_index) if to_index - from_index >= limit: return { 'ids': self._sorted_ids[from_index:from_index+limit], 'next': self._sorted_ids[from_index+limit], } else: return { 'ids': self._sorted_ids[from_index:to_index], 'next': None, } def add(self, data, conflict_update): """Add data not present in storage. Args: data (iterable): dictionaries with keys: - **id**: sha1 - **indexer_configuration_id**: tool used to compute the results - arbitrary data conflict_update (bool): Flag to determine if we want to overwrite (true) or skip duplicates (false) """ data = list(data) if len({x['id'] for x in data}) < len(data): # For "exception-compatibility" with the pgsql backend raise ValueError('The same id is present more than once.') for item in data: item = item.copy() tool_id = item.pop('indexer_configuration_id') id_ = item.pop('id') data = item if not conflict_update and \ tool_id in self._tools_per_id.get(id_, set()): # Duplicate, should not be updated continue key = (id_, tool_id) self._data[key] = data self._tools_per_id[id_].add(tool_id) if id_ not in self._sorted_ids: bisect.insort(self._sorted_ids, id_) def add_merge(self, new_data, conflict_update, merged_key): for new_item in new_data: id_ = new_item['id'] tool_id = new_item['indexer_configuration_id'] if conflict_update: all_subitems = [] else: existing = list(self.get([id_])) all_subitems = [ old_subitem for existing_item in existing if existing_item['tool']['id'] == tool_id for old_subitem in existing_item[merged_key] ] for new_subitem in new_item[merged_key]: if new_subitem not in all_subitems: all_subitems.append(new_subitem) self.add([ { 'id': id_, 'indexer_configuration_id': tool_id, merged_key: all_subitems, } ], conflict_update=True) if id_ not in self._sorted_ids: bisect.insort(self._sorted_ids, id_) def delete(self, entries): for entry in entries: (id_, tool_id) = (entry['id'], entry['indexer_configuration_id']) key = (id_, tool_id) if tool_id in self._tools_per_id[id_]: self._tools_per_id[id_].remove(tool_id) if key in self._data: del self._data[key] class IndexerStorage: """In-memory SWH indexer storage.""" def __init__(self): self._tools = {} self._mimetypes = SubStorage(self._tools) self._languages = SubStorage(self._tools) self._content_ctags = SubStorage(self._tools) self._licenses = SubStorage(self._tools) self._content_metadata = SubStorage(self._tools) self._revision_intrinsic_metadata = SubStorage(self._tools) self._origin_intrinsic_metadata = SubStorage(self._tools) def check_config(self, *, check_write): return True def content_mimetype_missing(self, mimetypes): """Generate mimetypes missing from storage. Args: mimetypes (iterable): iterable of dict with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: tuple (id, indexer_configuration_id): missing id """ yield from self._mimetypes.missing(mimetypes) def content_mimetype_get_range( self, start, end, indexer_configuration_id, limit=1000): """Retrieve mimetypes within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ return self._mimetypes.get_range( start, end, indexer_configuration_id, limit) def content_mimetype_add(self, mimetypes, conflict_update=False): """Add mimetypes not present in storage. Args: mimetypes (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **mimetype** (bytes): raw content's mimetype - **encoding** (bytes): raw content's encoding - **indexer_configuration_id** (int): tool's id used to compute the results - **conflict_update** (bool): Flag to determine if we want to overwrite (``True``) or skip duplicates (``False``, the default) """ if not all(isinstance(x['id'], bytes) for x in mimetypes): raise TypeError('identifiers must be bytes.') self._mimetypes.add(mimetypes, conflict_update) def content_mimetype_get(self, ids, db=None, cur=None): """Retrieve full content mimetype per ids. Args: ids (iterable): sha1 identifier Yields: mimetypes (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **mimetype** (bytes): raw content's mimetype - **encoding** (bytes): raw content's encoding - **tool** (dict): Tool used to compute the language """ yield from self._mimetypes.get(ids) def content_language_missing(self, languages): """List languages missing from storage. Args: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: an iterable of missing id for the tuple (id, indexer_configuration_id) """ yield from self._languages.missing(languages) def content_language_get(self, ids): """Retrieve full content language per ids. Args: ids (iterable): sha1 identifier Yields: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **lang** (bytes): raw content's language - **tool** (dict): Tool used to compute the language """ yield from self._languages.get(ids) def content_language_add(self, languages, conflict_update=False): """Add languages not present in storage. Args: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 - **lang** (bytes): language detected conflict_update (bool): Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ if not all(isinstance(x['id'], bytes) for x in languages): raise TypeError('identifiers must be bytes.') self._languages.add(languages, conflict_update) def content_ctags_missing(self, ctags): """List ctags missing from storage. Args: ctags (iterable): dicts with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: an iterable of missing id for the tuple (id, indexer_configuration_id) """ yield from self._content_ctags.missing(ctags) def content_ctags_get(self, ids): """Retrieve ctags per id. Args: ids (iterable): sha1 checksums Yields: Dictionaries with keys: - **id** (bytes): content's identifier - **name** (str): symbol's name - **kind** (str): symbol's kind - **lang** (str): language for that content - **tool** (dict): tool used to compute the ctags' info """ for item in self._content_ctags.get(ids): for item_ctags_item in item['ctags']: yield { 'id': item['id'], 'tool': item['tool'], **item_ctags_item } def content_ctags_add(self, ctags, conflict_update=False): """Add ctags not present in storage Args: ctags (iterable): dictionaries with keys: - **id** (bytes): sha1 - **ctags** ([list): List of dictionary with keys: name, kind, line, lang - **indexer_configuration_id**: tool used to compute the results """ if not all(isinstance(x['id'], bytes) for x in ctags): raise TypeError('identifiers must be bytes.') self._content_ctags.add_merge(ctags, conflict_update, 'ctags') def content_ctags_search(self, expression, limit=10, last_sha1=None, db=None, cur=None): """Search through content's raw ctags symbols. Args: expression (str): Expression to search for limit (int): Number of rows to return (default to 10). last_sha1 (str): Offset from which retrieving data (default to ''). Yields: rows of ctags including id, name, lang, kind, line, etc... """ nb_matches = 0 for ((id_, tool_id), item) in \ sorted(self._content_ctags._data.items()): if id_ <= (last_sha1 or bytes(0 for _ in range(SHA1_DIGEST_SIZE))): continue for ctags_item in item['ctags']: if ctags_item['name'] != expression: continue nb_matches += 1 yield { 'id': id_, 'tool': _transform_tool(self._tools[tool_id]), **ctags_item } if nb_matches >= limit: return def content_fossology_license_get(self, ids): """Retrieve licenses per id. Args: ids (iterable): sha1 checksums Yields: dict: ``{id: facts}`` where ``facts`` is a dict with the following keys: - **licenses** ([str]): associated licenses for that content - **tool** (dict): Tool used to compute the license """ # Rewrites the output of SubStorage.get from the old format to # the new one. SubStorage.get should be updated once all other # *_get methods use the new format. # See: https://forge.softwareheritage.org/T1433 res = {} for d in self._licenses.get(ids): res.setdefault(d.pop('id'), []).append(d) for (id_, facts) in res.items(): yield {id_: facts} def content_fossology_license_add(self, licenses, conflict_update=False): """Add licenses not present in storage. Args: licenses (iterable): dictionaries with keys: - **id**: sha1 - **licenses** ([bytes]): List of licenses associated to sha1 - **tool** (str): nomossa conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) Returns: list: content_license entries which failed due to unknown licenses """ if not all(isinstance(x['id'], bytes) for x in licenses): raise TypeError('identifiers must be bytes.') self._licenses.add_merge(licenses, conflict_update, 'licenses') def content_fossology_license_get_range( self, start, end, indexer_configuration_id, limit=1000): """Retrieve licenses within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ return self._licenses.get_range( start, end, indexer_configuration_id, limit) def content_metadata_missing(self, metadata): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing sha1s """ yield from self._content_metadata.missing(metadata) def content_metadata_get(self, ids): """Retrieve metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: - **id** (bytes) - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata """ yield from self._content_metadata.get(ids) def content_metadata_add(self, metadata, conflict_update=False): """Add metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: sha1 - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute the results conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ if not all(isinstance(x['id'], bytes) for x in metadata): raise TypeError('identifiers must be bytes.') self._content_metadata.add(metadata, conflict_update) def revision_intrinsic_metadata_missing(self, metadata): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1_git revision identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing ids """ yield from self._revision_intrinsic_metadata.missing(metadata) def revision_intrinsic_metadata_get(self, ids): """Retrieve revision metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: - **id** (bytes) - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ yield from self._revision_intrinsic_metadata.get(ids) def revision_intrinsic_metadata_add(self, metadata, conflict_update=False): """Add metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: sha1_git of revision - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ if not all(isinstance(x['id'], bytes) for x in metadata): raise TypeError('identifiers must be bytes.') self._revision_intrinsic_metadata.add(metadata, conflict_update) def revision_intrinsic_metadata_delete(self, entries): """Remove revision metadata from the storage. Args: entries (dict): dictionaries with the following keys: - **revision** (int): origin identifier - **id** (int): tool used to compute metadata """ self._revision_intrinsic_metadata.delete(entries) def origin_intrinsic_metadata_get(self, ids): """Retrieve origin metadata per id. Args: ids (iterable): origin identifiers Yields: list: dictionaries with the following keys: - **id** (str): origin url - **from_revision** (bytes): which revision this metadata was extracted from - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ yield from self._origin_intrinsic_metadata.get(ids) def origin_intrinsic_metadata_add(self, metadata, conflict_update=False): """Add origin metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: origin url - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ self._origin_intrinsic_metadata.add(metadata, conflict_update) def origin_intrinsic_metadata_delete(self, entries): """Remove origin metadata from the storage. Args: entries (dict): dictionaries with the following keys: - **id** (str): origin url - **indexer_configuration_id** (int): tool used to compute metadata """ self._origin_intrinsic_metadata.delete(entries) def origin_intrinsic_metadata_search_fulltext( self, conjunction, limit=100): """Returns the list of origins whose metadata contain all the terms. Args: conjunction (List[str]): List of terms to be searched for. limit (int): The maximum number of results to return Yields: list: dictionaries with the following keys: - **id** (str): origin url - **from_revision** (bytes): which revision this metadata was extracted from - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ # A very crude fulltext search implementation, but that's enough # to work on English metadata tokens_re = re.compile('[a-zA-Z0-9]+') search_tokens = list(itertools.chain( *map(tokens_re.findall, conjunction))) def rank(data): # Tokenize the metadata text = json.dumps(data['metadata']) text_tokens = tokens_re.findall(text) text_token_occurences = Counter(text_tokens) # Count the number of occurrences of search tokens in the text score = 0 for search_token in search_tokens: if text_token_occurences[search_token] == 0: # Search token is not in the text. return 0 score += text_token_occurences[search_token] # Normalize according to the text's length return score / math.log(len(text_tokens)) results = [(rank(data), data) for data in self._origin_intrinsic_metadata.get_all()] results = [(rank_, data) for (rank_, data) in results if rank_ > 0] results.sort(key=operator.itemgetter(0), # Don't try to order 'data' reverse=True) for (rank_, result) in results[:limit]: yield result def origin_intrinsic_metadata_search_by_producer( self, page_token='', limit=100, ids_only=False, mappings=None, tool_ids=None, db=None, cur=None): """Returns the list of origins whose metadata contain all the terms. Args: page_token (str): Opaque token used for pagination. limit (int): The maximum number of results to return ids_only (bool): Determines whether only origin ids are returned or the content as well mappings (List[str]): Returns origins whose intrinsic metadata were generated using at least one of these mappings. Returns: dict: dict with the following keys: - **next_page_token** (str, optional): opaque token to be used as `page_token` for retrieveing the next page. - **origins** (list): list of origin url (str) if `ids_only=True` else dictionaries with the following keys: - **id** (str): origin urls - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ assert isinstance(page_token, str) nb_results = 0 if mappings is not None: mappings = frozenset(mappings) if tool_ids is not None: tool_ids = frozenset(tool_ids) origins = [] - # we go to limit+1 to check wether we should add next_page_token in + # we go to limit+1 to check whether we should add next_page_token in # the response for entry in self._origin_intrinsic_metadata.get_all(): if entry['id'] <= page_token: continue if nb_results >= (limit + 1): break if mappings is not None and mappings.isdisjoint(entry['mappings']): continue if tool_ids is not None and entry['tool']['id'] not in tool_ids: continue origins.append(entry) nb_results += 1 result = {} if len(origins) > limit: origins = origins[:limit] result['next_page_token'] = origins[-1]['id'] if ids_only: origins = [origin['id'] for origin in origins] result['origins'] = origins return result def origin_intrinsic_metadata_stats(self): """Returns statistics on stored intrinsic metadata. Returns: dict: dictionary with keys: - total (int): total number of origins that were indexed (possibly yielding an empty metadata dictionary) - non_empty (int): total number of origins that we extracted a non-empty metadata dictionary from - per_mapping (dict): a dictionary with mapping names as keys and number of origins whose indexing used this mapping. Note that indexing a given origin may use 0, 1, or many mappings. """ mapping_count = {m: 0 for m in MAPPING_NAMES} total = non_empty = 0 for data in self._origin_intrinsic_metadata.get_all(): total += 1 if set(data['metadata']) - {'@context'}: non_empty += 1 for mapping in data['mappings']: mapping_count[mapping] += 1 return { 'per_mapping': mapping_count, 'total': total, 'non_empty': non_empty } def indexer_configuration_add(self, tools): """Add new tools to the storage. Args: tools ([dict]): List of dictionary representing tool to insert in the db. Dictionary with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: list: List of dict inserted in the db (holding the id key as well). The order of the list is not guaranteed to match the order of the initial list. """ inserted = [] for tool in tools: tool = tool.copy() id_ = self._tool_key(tool) tool['id'] = id_ self._tools[id_] = tool inserted.append(tool) return inserted def indexer_configuration_get(self, tool): """Retrieve tool information. Args: tool (dict): Dictionary representing a tool with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: The same dictionary with an `id` key, None otherwise. """ return self._tools.get(self._tool_key(tool)) def _tool_key(self, tool): return hash((tool['tool_name'], tool['tool_version'], json.dumps(tool['tool_configuration'], sort_keys=True))) diff --git a/swh/indexer/tests/storage/test_server.py b/swh/indexer/tests/storage/test_server.py index f4055bb..9130e1f 100644 --- a/swh/indexer/tests/storage/test_server.py +++ b/swh/indexer/tests/storage/test_server.py @@ -1,123 +1,123 @@ # 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 pytest import yaml from swh.indexer.storage.api.server import load_and_check_config def prepare_config_file(tmpdir, content, name='config.yml'): """Prepare configuration file in `$tmpdir/name` with content `content`. Args: tmpdir (LocalPath): root directory content (str/dict): Content of the file either as string or as a dict. If a dict, converts the dict into a yaml string. name (str): configuration filename Returns path (str) of the configuration file prepared. """ config_path = tmpdir / name if isinstance(content, dict): # convert if needed content = yaml.dump(content) config_path.write_text(content, encoding='utf-8') # pytest on python3.5 does not support LocalPath manipulation, so # convert path to string return str(config_path) def test_load_and_check_config_no_configuration(): - """Inexistant configuration files raises""" + """Inexistent configuration files raises""" with pytest.raises(EnvironmentError) as e: load_and_check_config(None) assert e.value.args[0] == 'Configuration file must be defined' - config_path = '/indexer/inexistant/config.yml' + config_path = '/indexer/inexistent/config.yml' with pytest.raises(FileNotFoundError) as e: load_and_check_config(config_path) assert e.value.args[0] == 'Configuration file %s does not exist' % ( config_path, ) def test_load_and_check_config_wrong_configuration(tmpdir): """Wrong configuration raises""" config_path = prepare_config_file(tmpdir, 'something: useless') with pytest.raises(KeyError) as e: load_and_check_config(config_path) assert e.value.args[0] == 'Missing \'%indexer_storage\' configuration' def test_load_and_check_config_remote_config_local_type_raise(tmpdir): """'local' configuration without 'local' storage raises""" config = { 'indexer_storage': { 'cls': 'remote', 'args': {} } } config_path = prepare_config_file(tmpdir, config) with pytest.raises(ValueError) as e: load_and_check_config(config_path, type='local') assert ( e.value.args[0] == "The indexer_storage backend can only be started with a 'local' " "configuration" ) def test_load_and_check_config_local_incomplete_configuration(tmpdir): """Incomplete 'local' configuration should raise""" config = { 'indexer_storage': { 'cls': 'local', 'args': { } } } config_path = prepare_config_file(tmpdir, config) with pytest.raises(ValueError) as e: load_and_check_config(config_path) assert ( e.value.args[0] == "Invalid configuration; missing 'db' config entry" ) def test_load_and_check_config_local_config_fine(tmpdir): """'Remote configuration is fine""" config = { 'indexer_storage': { 'cls': 'local', 'args': { 'db': 'db', } } } config_path = prepare_config_file(tmpdir, config) cfg = load_and_check_config(config_path, type='local') assert cfg == config def test_load_and_check_config_remote_config_fine(tmpdir): """'Remote configuration is fine""" config = { 'indexer_storage': { 'cls': 'remote', 'args': {} } } config_path = prepare_config_file(tmpdir, config) cfg = load_and_check_config(config_path, type='any') assert cfg == config diff --git a/swh/indexer/tests/test_ctags.py b/swh/indexer/tests/test_ctags.py index c0dff65..6ce1627 100644 --- a/swh/indexer/tests/test_ctags.py +++ b/swh/indexer/tests/test_ctags.py @@ -1,184 +1,184 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import json import unittest from unittest.mock import patch import pytest import swh.indexer.ctags from swh.indexer.ctags import ( CtagsIndexer, run_ctags ) from swh.indexer.tests.utils import ( CommonContentIndexerTest, SHA1_TO_CTAGS, BASE_TEST_CONFIG, OBJ_STORAGE_DATA, fill_storage, fill_obj_storage, filter_dict, ) class BasicTest(unittest.TestCase): - @patch('swh.indexer.ctags.subprocess') + @patch("swh.indexer.ctags.subprocess") def test_run_ctags(self, mock_subprocess): """Computing licenses from a raw content should return results """ output0 = """ {"name":"defun","kind":"function","line":1,"language":"scheme"} {"name":"name","kind":"symbol","line":5,"language":"else"}""" output1 = """ {"name":"let","kind":"var","line":10,"language":"something"}""" expected_result0 = [ { 'name': 'defun', 'kind': 'function', 'line': 1, 'lang': 'scheme' }, { 'name': 'name', 'kind': 'symbol', 'line': 5, 'lang': 'else' } ] expected_result1 = [ { 'name': 'let', 'kind': 'var', 'line': 10, 'lang': 'something' } ] for path, lang, intermediary_result, expected_result in [ (b'some/path', 'lisp', output0, expected_result0), (b'some/path/2', 'markdown', output1, expected_result1) ]: mock_subprocess.check_output.return_value = intermediary_result actual_result = list(run_ctags(path, lang=lang)) self.assertEqual(actual_result, expected_result) class InjectCtagsIndexer: """Override ctags computations. """ def compute_ctags(self, path, lang): """Inject fake ctags given path (sha1 identifier). """ return { 'lang': lang, **SHA1_TO_CTAGS.get(path) } CONFIG = { **BASE_TEST_CONFIG, 'tools': { 'name': 'universal-ctags', 'version': '~git7859817b', 'configuration': { 'command_line': '''ctags --fields=+lnz --sort=no ''' ''' --links=no ''', 'max_content_size': 1000, }, }, 'languages': { 'python': 'python', 'haskell': 'haskell', 'bar': 'bar', }, 'workdir': '/tmp', } class TestCtagsIndexer(CommonContentIndexerTest, unittest.TestCase): """Ctags indexer test scenarios: - Known sha1s in the input list have their data indexed - Unknown sha1 in the input list are not indexed """ legacy_get_format = True def get_indexer_results(self, ids): yield from self.idx_storage.content_ctags_get(ids) def setUp(self): super().setUp() self.indexer = CtagsIndexer(config=CONFIG) self.indexer.catch_exceptions = False self.idx_storage = self.indexer.idx_storage fill_storage(self.indexer.storage) fill_obj_storage(self.indexer.objstorage) # Prepare test input self.id0 = '01c9379dfc33803963d07c1ccc748d3fe4c96bb5' self.id1 = 'd4c647f0fc257591cc9ba1722484229780d1c607' self.id2 = '688a5ef812c53907562fe379d4b3851e69c7cb15' tool = {k.replace('tool_', ''): v for (k, v) in self.indexer.tool.items()} self.expected_results = { self.id0: { 'id': self.id0, 'tool': tool, **SHA1_TO_CTAGS[self.id0][0], }, self.id1: { 'id': self.id1, 'tool': tool, **SHA1_TO_CTAGS[self.id1][0], }, self.id2: { 'id': self.id2, 'tool': tool, **SHA1_TO_CTAGS[self.id2][0], } } self._set_mocks() def _set_mocks(self): def find_ctags_for_content(raw_content): for (sha1, ctags) in SHA1_TO_CTAGS.items(): if OBJ_STORAGE_DATA[sha1] == raw_content: return ctags else: raise ValueError(('%r not found in objstorage, can\'t mock ' 'its ctags.') % raw_content) def fake_language(raw_content, *args, **kwargs): ctags = find_ctags_for_content(raw_content) return {'lang': ctags[0]['lang']} self._real_compute_language = swh.indexer.ctags.compute_language swh.indexer.ctags.compute_language = fake_language def fake_check_output(cmd, *args, **kwargs): print(cmd) id_ = cmd[-1].split('/')[-1] return '\n'.join( json.dumps({'language': ctag['lang'], **ctag}) for ctag in SHA1_TO_CTAGS[id_]) self._real_check_output = swh.indexer.ctags.subprocess.check_output swh.indexer.ctags.subprocess.check_output = fake_check_output def tearDown(self): swh.indexer.ctags.compute_language = self._real_compute_language swh.indexer.ctags.subprocess.check_output = self._real_check_output super().tearDown() def test_ctags_w_no_tool(): with pytest.raises(ValueError): CtagsIndexer(config=filter_dict(CONFIG, 'tools')) diff --git a/swh/indexer/tests/test_fossology_license.py b/swh/indexer/tests/test_fossology_license.py index cd6030b..8b15b90 100644 --- a/swh/indexer/tests/test_fossology_license.py +++ b/swh/indexer/tests/test_fossology_license.py @@ -1,181 +1,181 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import unittest import pytest from unittest.mock import patch from typing import Any, Dict from swh.indexer import fossology_license from swh.indexer.fossology_license import ( FossologyLicenseIndexer, FossologyLicenseRangeIndexer, compute_license ) from swh.indexer.tests.utils import ( SHA1_TO_LICENSES, CommonContentIndexerTest, CommonContentIndexerRangeTest, BASE_TEST_CONFIG, fill_storage, fill_obj_storage, filter_dict, ) class BasicTest(unittest.TestCase): - @patch('swh.indexer.fossology_license.subprocess') + @patch("swh.indexer.fossology_license.subprocess") def test_compute_license(self, mock_subprocess): """Computing licenses from a raw content should return results """ for path, intermediary_result, output in [ (b'some/path', None, []), (b'some/path/2', [], []), (b'other/path', ' contains license(s) GPL,AGPL', ['GPL', 'AGPL'])]: mock_subprocess.check_output.return_value = intermediary_result actual_result = compute_license(path, log=None) self.assertEqual(actual_result, { 'licenses': output, 'path': path, }) def mock_compute_license(path, log=None): """path is the content identifier """ if isinstance(id, bytes): path = path.decode('utf-8') # path is something like /tmp/tmpXXX/ so we keep only the sha1 part path = path.split('/')[-1] return { 'licenses': SHA1_TO_LICENSES.get(path) } CONFIG = { **BASE_TEST_CONFIG, 'workdir': '/tmp', 'tools': { 'name': 'nomos', 'version': '3.1.0rc2-31-ga2cbb8c', 'configuration': { 'command_line': 'nomossa ', }, }, } # type: Dict[str, Any] RANGE_CONFIG = dict(list(CONFIG.items()) + [('write_batch_size', 100)]) class TestFossologyLicenseIndexer(CommonContentIndexerTest, unittest.TestCase): """Language indexer test scenarios: - Known sha1s in the input list have their data indexed - Unknown sha1 in the input list are not indexed """ def get_indexer_results(self, ids): yield from self.idx_storage.content_fossology_license_get(ids) def setUp(self): super().setUp() # replace actual license computation with a mock self.orig_compute_license = fossology_license.compute_license fossology_license.compute_license = mock_compute_license self.indexer = FossologyLicenseIndexer(CONFIG) self.indexer.catch_exceptions = False self.idx_storage = self.indexer.idx_storage fill_storage(self.indexer.storage) fill_obj_storage(self.indexer.objstorage) self.id0 = '01c9379dfc33803963d07c1ccc748d3fe4c96bb5' self.id1 = '688a5ef812c53907562fe379d4b3851e69c7cb15' self.id2 = 'da39a3ee5e6b4b0d3255bfef95601890afd80709' # empty content tool = {k.replace('tool_', ''): v for (k, v) in self.indexer.tool.items()} # then self.expected_results = { self.id0: { 'tool': tool, 'licenses': SHA1_TO_LICENSES[self.id0], }, self.id1: { 'tool': tool, 'licenses': SHA1_TO_LICENSES[self.id1], }, self.id2: { 'tool': tool, 'licenses': SHA1_TO_LICENSES[self.id2], } } def tearDown(self): super().tearDown() fossology_license.compute_license = self.orig_compute_license class TestFossologyLicenseRangeIndexer( CommonContentIndexerRangeTest, unittest.TestCase): """Range Fossology License Indexer tests. - new data within range are indexed - no data outside a range are indexed - with filtering existing indexed data prior to compute new index - without filtering existing indexed data prior to compute new index """ def setUp(self): super().setUp() # replace actual license computation with a mock self.orig_compute_license = fossology_license.compute_license fossology_license.compute_license = mock_compute_license self.indexer = FossologyLicenseRangeIndexer(config=RANGE_CONFIG) self.indexer.catch_exceptions = False fill_storage(self.indexer.storage) fill_obj_storage(self.indexer.objstorage) self.id0 = '01c9379dfc33803963d07c1ccc748d3fe4c96bb5' self.id1 = '02fb2c89e14f7fab46701478c83779c7beb7b069' self.id2 = '103bc087db1d26afc3a0283f38663d081e9b01e6' tool_id = self.indexer.tool['id'] self.expected_results = { self.id0: { 'id': self.id0, 'indexer_configuration_id': tool_id, 'licenses': SHA1_TO_LICENSES[self.id0] }, self.id1: { 'id': self.id1, 'indexer_configuration_id': tool_id, 'licenses': SHA1_TO_LICENSES[self.id1] }, self.id2: { 'id': self.id2, 'indexer_configuration_id': tool_id, 'licenses': SHA1_TO_LICENSES[self.id2] } } def tearDown(self): super().tearDown() fossology_license.compute_license = self.orig_compute_license def test_fossology_w_no_tool(): with pytest.raises(ValueError): FossologyLicenseIndexer(config=filter_dict(CONFIG, 'tools')) def test_fossology_range_w_no_tool(): with pytest.raises(ValueError): FossologyLicenseRangeIndexer(config=filter_dict(RANGE_CONFIG, 'tools')) diff --git a/swh/indexer/tests/utils.py b/swh/indexer/tests/utils.py index 7d8d0c6..0472e99 100644 --- a/swh/indexer/tests/utils.py +++ b/swh/indexer/tests/utils.py @@ -1,760 +1,760 @@ # Copyright (C) 2017-2019 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 abc import datetime import functools import random import unittest from hypothesis import strategies from swh.model import hashutil from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.indexer.storage import INDEXER_CFG_KEY BASE_TEST_CONFIG = { 'storage': { 'cls': 'memory', 'args': { }, }, 'objstorage': { 'cls': 'memory', 'args': { }, }, INDEXER_CFG_KEY: { 'cls': 'memory', 'args': { }, }, } ORIGIN_VISITS = [ { 'type': 'git', 'url': 'https://github.com/SoftwareHeritage/swh-storage'}, { 'type': 'ftp', 'url': 'rsync://ftp.gnu.org/gnu/3dldf'}, { 'type': 'deposit', 'url': 'https://forge.softwareheritage.org/source/jesuisgpl/'}, { 'type': 'pypi', 'url': 'https://pypi.org/project/limnoria/'}, { 'type': 'svn', 'url': 'http://0-512-md.googlecode.com/svn/'}, { 'type': 'git', 'url': 'https://github.com/librariesio/yarn-parser'}, { 'type': 'git', 'url': 'https://github.com/librariesio/yarn-parser.git'}, ] SNAPSHOTS = [ { 'origin': 'https://github.com/SoftwareHeritage/swh-storage', 'branches': { b'refs/heads/add-revision-origin-cache': { 'target': b'L[\xce\x1c\x88\x8eF\t\xf1"\x19\x1e\xfb\xc0' b's\xe7/\xe9l\x1e', 'target_type': 'revision'}, b'HEAD': { 'target': b'8K\x12\x00d\x03\xcc\xe4]bS\xe3\x8f{\xd7}' b'\xac\xefrm', 'target_type': 'revision'}, b'refs/tags/v0.0.103': { 'target': b'\xb6"Im{\xfdLb\xb0\x94N\xea\x96m\x13x\x88+' b'\x0f\xdd', 'target_type': 'release'}, }}, { 'origin': 'rsync://ftp.gnu.org/gnu/3dldf', 'branches': { b'3DLDF-1.1.4.tar.gz': { 'target': b'dJ\xfb\x1c\x91\xf4\x82B%]6\xa2\x90|\xd3\xfc' b'"G\x99\x11', 'target_type': 'revision'}, b'3DLDF-2.0.2.tar.gz': { 'target': b'\xb6\x0e\xe7\x9e9\xac\xaa\x19\x9e=' b'\xd1\xc5\x00\\\xc6\xfc\xe0\xa6\xb4V', 'target_type': 'revision'}, b'3DLDF-2.0.3-examples.tar.gz': { 'target': b'!H\x19\xc0\xee\x82-\x12F1\xbd\x97' b'\xfe\xadZ\x80\x80\xc1\x83\xff', 'target_type': 'revision'}, b'3DLDF-2.0.3.tar.gz': { 'target': b'\x8e\xa9\x8e/\xea}\x9feF\xf4\x9f\xfd\xee' b'\xcc\x1a\xb4`\x8c\x8by', 'target_type': 'revision'}, b'3DLDF-2.0.tar.gz': { 'target': b'F6*\xff(?\x19a\xef\xb6\xc2\x1fv$S\xe3G' b'\xd3\xd1m', 'target_type': 'revision'} }}, { 'origin': 'https://forge.softwareheritage.org/source/jesuisgpl/', 'branches': { b'master': { 'target': b'\xe7n\xa4\x9c\x9f\xfb\xb7\xf76\x11\x08{' b'\xa6\xe9\x99\xb1\x9e]q\xeb', 'target_type': 'revision'} }, 'id': b"h\xc0\xd2a\x04\xd4~'\x8d\xd6\xbe\x07\xeda\xfa\xfbV" b"\x1d\r "}, { 'origin': 'https://pypi.org/project/limnoria/', 'branches': { b'HEAD': { 'target': b'releases/2018.09.09', 'target_type': 'alias'}, b'releases/2018.09.01': { 'target': b'<\xee1(\xe8\x8d_\xc1\xc9\xa6rT\xf1\x1d' b'\xbb\xdfF\xfdw\xcf', 'target_type': 'revision'}, b'releases/2018.09.09': { 'target': b'\x83\xb9\xb6\xc7\x05\xb1%\xd0\xfem\xd8k' b'A\x10\x9d\xc5\xfa2\xf8t', 'target_type': 'revision'}}, 'id': b'{\xda\x8e\x84\x7fX\xff\x92\x80^\x93V\x18\xa3\xfay' b'\x12\x9e\xd6\xb3'}, { 'origin': 'http://0-512-md.googlecode.com/svn/', 'branches': { b'master': { 'target': b'\xe4?r\xe1,\x88\xab\xec\xe7\x9a\x87\xb8' b'\xc9\xad#.\x1bw=\x18', 'target_type': 'revision'}}, 'id': b'\xa1\xa2\x8c\n\xb3\x87\xa8\xf9\xe0a\x8c\xb7' b'\x05\xea\xb8\x1f\xc4H\xf4s'}, { 'origin': 'https://github.com/librariesio/yarn-parser', 'branches': { b'HEAD': { 'target': hash_to_bytes( '8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'target_type': 'revision'}}}, { 'origin': 'https://github.com/librariesio/yarn-parser.git', 'branches': { b'HEAD': { 'target': hash_to_bytes( '8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'target_type': 'revision'}}}, ] REVISIONS = [{ 'id': hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'message': 'Improve search functionality', 'author': { 'name': b'Andrew Nesbitt', 'fullname': b'Andrew Nesbitt ', 'email': b'andrewnez@gmail.com' }, 'committer': { 'name': b'Andrew Nesbitt', 'fullname': b'Andrew Nesbitt ', 'email': b'andrewnez@gmail.com' }, 'committer_date': { 'negative_utc': None, 'offset': 120, 'timestamp': { 'microseconds': 0, 'seconds': 1380883849 } }, 'type': 'git', 'synthetic': False, 'date': { 'negative_utc': False, 'timestamp': { 'seconds': 1487596456, 'microseconds': 0 }, 'offset': 0 }, 'directory': b'10' }] DIRECTORY_ID = b'10' DIRECTORY_ENTRIES = [{ 'name': b'index.js', 'type': 'file', 'target': b'abc', 'perms': 33188, }, { 'name': b'package.json', 'type': 'file', 'target': b'cde', 'perms': 33188, }, { 'name': b'.github', 'type': 'dir', 'target': b'11', 'perms': 16384, } ] SHA1_TO_LICENSES = { '01c9379dfc33803963d07c1ccc748d3fe4c96bb5': ['GPL'], '02fb2c89e14f7fab46701478c83779c7beb7b069': ['Apache2.0'], '103bc087db1d26afc3a0283f38663d081e9b01e6': ['MIT'], '688a5ef812c53907562fe379d4b3851e69c7cb15': ['AGPL'], 'da39a3ee5e6b4b0d3255bfef95601890afd80709': [], } SHA1_TO_CTAGS = { '01c9379dfc33803963d07c1ccc748d3fe4c96bb5': [{ 'name': 'foo', 'kind': 'str', 'line': 10, 'lang': 'bar', }], 'd4c647f0fc257591cc9ba1722484229780d1c607': [{ 'name': 'let', 'kind': 'int', 'line': 100, 'lang': 'haskell', }], '688a5ef812c53907562fe379d4b3851e69c7cb15': [{ 'name': 'symbol', 'kind': 'float', 'line': 99, 'lang': 'python', }], } OBJ_STORAGE_DATA = { '01c9379dfc33803963d07c1ccc748d3fe4c96bb5': b'this is some text', '688a5ef812c53907562fe379d4b3851e69c7cb15': b'another text', '8986af901dd2043044ce8f0d8fc039153641cf17': b'yet another text', '02fb2c89e14f7fab46701478c83779c7beb7b069': b""" import unittest import logging from swh.indexer.mimetype import MimetypeIndexer from swh.indexer.tests.test_utils import MockObjStorage class MockStorage(): def content_mimetype_add(self, mimetypes): self.state = mimetypes self.conflict_update = conflict_update def indexer_configuration_add(self, tools): return [{ 'id': 10, }] """, '103bc087db1d26afc3a0283f38663d081e9b01e6': b""" #ifndef __AVL__ #define __AVL__ typedef struct _avl_tree avl_tree; typedef struct _data_t { int content; } data_t; """, '93666f74f1cf635c8c8ac118879da6ec5623c410': b""" (should 'pygments (recognize 'lisp 'easily)) """, '26a9f72a7c87cc9205725cfd879f514ff4f3d8d5': b""" { "name": "test_metadata", "version": "0.0.1", "description": "Simple package.json test for indexer", "repository": { "type": "git", "url": "https://github.com/moranegg/metadata_test" } } """, 'd4c647f0fc257591cc9ba1722484229780d1c607': b""" { "version": "5.0.3", "name": "npm", "description": "a package manager for JavaScript", "keywords": [ "install", "modules", "package manager", "package.json" ], "preferGlobal": true, "config": { "publishtest": false }, "homepage": "https://docs.npmjs.com/", "author": "Isaac Z. Schlueter (http://blog.izs.me)", "repository": { "type": "git", "url": "https://github.com/npm/npm" }, "bugs": { "url": "https://github.com/npm/npm/issues" }, "dependencies": { "JSONStream": "~1.3.1", "abbrev": "~1.1.0", "ansi-regex": "~2.1.1", "ansicolors": "~0.3.2", "ansistyles": "~0.1.3" }, "devDependencies": { "tacks": "~1.2.6", "tap": "~10.3.2" }, "license": "Artistic-2.0" } """, 'a7ab314d8a11d2c93e3dcf528ca294e7b431c449': b""" """, 'da39a3ee5e6b4b0d3255bfef95601890afd80709': b'', # 626364 hash_to_hex(b'bcd'): b'unimportant content for bcd', # 636465 hash_to_hex(b'cde'): b""" { "name": "yarn-parser", "version": "1.0.0", "description": "Tiny web service for parsing yarn.lock files", "main": "index.js", "scripts": { "start": "node index.js", "test": "mocha" }, "engines": { "node": "9.8.0" }, "repository": { "type": "git", "url": "git+https://github.com/librariesio/yarn-parser.git" }, "keywords": [ "yarn", "parse", "lock", "dependencies" ], "author": "Andrew Nesbitt", "license": "AGPL-3.0", "bugs": { "url": "https://github.com/librariesio/yarn-parser/issues" }, "homepage": "https://github.com/librariesio/yarn-parser#readme", "dependencies": { "@yarnpkg/lockfile": "^1.0.0", "body-parser": "^1.15.2", "express": "^4.14.0" }, "devDependencies": { "chai": "^4.1.2", "mocha": "^5.2.0", "request": "^2.87.0", "test": "^0.6.0" } } """ } YARN_PARSER_METADATA = { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'url': 'https://github.com/librariesio/yarn-parser#readme', 'codeRepository': 'git+git+https://github.com/librariesio/yarn-parser.git', 'author': [{ 'type': 'Person', 'name': 'Andrew Nesbitt' }], 'license': 'https://spdx.org/licenses/AGPL-3.0', 'version': '1.0.0', 'description': - 'Tiny web service for parsing yarn.lock files', + 'Tiny web service for parsing yarn.lock files.', 'issueTracker': 'https://github.com/librariesio/yarn-parser/issues', 'name': 'yarn-parser', 'keywords': ['yarn', 'parse', 'lock', 'dependencies'], 'type': 'SoftwareSourceCode', } json_dict_keys = strategies.one_of( strategies.characters(), strategies.just('type'), strategies.just('url'), strategies.just('name'), strategies.just('email'), strategies.just('@id'), strategies.just('@context'), strategies.just('repository'), strategies.just('license'), strategies.just('repositories'), strategies.just('licenses'), ) """Hypothesis strategy that generates strings, with an emphasis on those that are often used as dictionary keys in metadata files.""" generic_json_document = strategies.recursive( strategies.none() | strategies.booleans() | strategies.floats() | strategies.characters(), lambda children: ( strategies.lists(children, 1) | strategies.dictionaries(json_dict_keys, children, min_size=1) ) ) """Hypothesis strategy that generates possible values for values of JSON metadata files.""" def json_document_strategy(keys=None): """Generates an hypothesis strategy that generates metadata files for a JSON-based format that uses the given keys.""" if keys is None: keys = strategies.characters() else: keys = strategies.one_of(map(strategies.just, keys)) return strategies.dictionaries(keys, generic_json_document, min_size=1) def _tree_to_xml(root, xmlns, data): def encode(s): "Skips unpaired surrogates generated by json_document_strategy" return s.encode('utf8', 'replace') def to_xml(data, indent=b' '): if data is None: return b'' elif isinstance(data, (bool, str, int, float)): return indent + encode(str(data)) elif isinstance(data, list): return b'\n'.join(to_xml(v, indent=indent) for v in data) elif isinstance(data, dict): lines = [] for (key, value) in data.items(): lines.append(indent + encode('<{}>'.format(key))) lines.append(to_xml(value, indent=indent+b' ')) lines.append(indent + encode(''.format(key))) return b'\n'.join(lines) else: raise TypeError(data) return b'\n'.join([ '<{} xmlns="{}">'.format(root, xmlns).encode(), to_xml(data), ''.format(root).encode(), ]) class TreeToXmlTest(unittest.TestCase): def test_leaves(self): self.assertEqual( _tree_to_xml('root', 'http://example.com', None), b'\n\n' ) self.assertEqual( _tree_to_xml('root', 'http://example.com', True), b'\n True\n' ) self.assertEqual( _tree_to_xml('root', 'http://example.com', 'abc'), b'\n abc\n' ) self.assertEqual( _tree_to_xml('root', 'http://example.com', 42), b'\n 42\n' ) self.assertEqual( _tree_to_xml('root', 'http://example.com', 3.14), b'\n 3.14\n' ) def test_dict(self): self.assertIn( _tree_to_xml('root', 'http://example.com', { 'foo': 'bar', 'baz': 'qux' }), [ b'\n' b' \n bar\n \n' b' \n qux\n \n' b'', b'\n' b' \n qux\n \n' b' \n bar\n \n' b'' ] ) def test_list(self): self.assertEqual( _tree_to_xml('root', 'http://example.com', [ {'foo': 'bar'}, {'foo': 'baz'}, ]), b'\n' b' \n bar\n \n' b' \n baz\n \n' b'' ) def xml_document_strategy(keys, root, xmlns): """Generates an hypothesis strategy that generates metadata files for an XML format that uses the given keys.""" return strategies.builds( functools.partial(_tree_to_xml, root, xmlns), json_document_strategy(keys)) def filter_dict(d, keys): 'return a copy of the dict with keys deleted' if not isinstance(keys, (list, tuple)): keys = (keys, ) return dict((k, v) for (k, v) in d.items() if k not in keys) def fill_obj_storage(obj_storage): """Add some content in an object storage.""" for (obj_id, content) in OBJ_STORAGE_DATA.items(): obj_storage.add(content, obj_id=hash_to_bytes(obj_id)) def fill_storage(storage): visit_types = {} for visit in ORIGIN_VISITS: storage.origin_add_one({'url': visit['url']}) visit_types[visit['url']] = visit['type'] for snap in SNAPSHOTS: origin_url = snap['origin'] visit = storage.origin_visit_add( origin=origin_url, date=datetime.datetime.now(), type=visit_types[origin_url]) snap_id = snap.get('id') or \ bytes([random.randint(0, 255) for _ in range(32)]) storage.snapshot_add([{ 'id': snap_id, 'branches': snap['branches'] }]) storage.origin_visit_update( origin_url, visit['visit'], status='full', snapshot=snap_id) storage.revision_add(REVISIONS) contents = [] for (obj_id, content) in OBJ_STORAGE_DATA.items(): content_hashes = hashutil.MultiHash.from_data(content).digest() contents.append({ 'data': content, 'length': len(content), 'status': 'visible', 'sha1': hash_to_bytes(obj_id), 'sha1_git': hash_to_bytes(obj_id), 'sha256': content_hashes['sha256'], 'blake2s256': content_hashes['blake2s256'] }) storage.content_add(contents) storage.directory_add([{ 'id': DIRECTORY_ID, 'entries': DIRECTORY_ENTRIES, }]) class CommonContentIndexerTest(metaclass=abc.ABCMeta): legacy_get_format = False """True if and only if the tested indexer uses the legacy format. see: https://forge.softwareheritage.org/T1433 """ def get_indexer_results(self, ids): """Override this for indexers that don't have a mock storage.""" return self.indexer.idx_storage.state def assert_legacy_results_ok(self, sha1s, expected_results=None): # XXX old format, remove this when all endpoints are # updated to the new one # see: https://forge.softwareheritage.org/T1433 sha1s = [sha1 if isinstance(sha1, bytes) else hash_to_bytes(sha1) for sha1 in sha1s] actual_results = list(self.get_indexer_results(sha1s)) if expected_results is None: expected_results = self.expected_results self.assertEqual(len(expected_results), len(actual_results), (expected_results, actual_results)) for indexed_data in actual_results: _id = indexed_data['id'] expected_data = expected_results[hashutil.hash_to_hex(_id)].copy() expected_data['id'] = _id self.assertEqual(indexed_data, expected_data) def assert_results_ok(self, sha1s, expected_results=None): if self.legacy_get_format: self.assert_legacy_results_ok(sha1s, expected_results) return sha1s = [sha1 if isinstance(sha1, bytes) else hash_to_bytes(sha1) for sha1 in sha1s] actual_results = list(self.get_indexer_results(sha1s)) if expected_results is None: expected_results = self.expected_results self.assertEqual(len(expected_results), len(actual_results), (expected_results, actual_results)) for indexed_data in actual_results: (_id, indexed_data) = list(indexed_data.items())[0] expected_data = expected_results[hashutil.hash_to_hex(_id)].copy() expected_data = [expected_data] self.assertEqual(indexed_data, expected_data) def test_index(self): """Known sha1 have their data indexed """ sha1s = [self.id0, self.id1, self.id2] # when self.indexer.run(sha1s, policy_update='update-dups') self.assert_results_ok(sha1s) # 2nd pass self.indexer.run(sha1s, policy_update='ignore-dups') self.assert_results_ok(sha1s) def test_index_one_unknown_sha1(self): """Unknown sha1 are not indexed""" sha1s = [self.id1, '799a5ef812c53907562fe379d4b3851e69c7cb15', # unknown '800a5ef812c53907562fe379d4b3851e69c7cb15'] # unknown # when self.indexer.run(sha1s, policy_update='update-dups') # then expected_results = { k: v for k, v in self.expected_results.items() if k in sha1s } self.assert_results_ok(sha1s, expected_results) class CommonContentIndexerRangeTest: """Allows to factorize tests on range indexer. """ def setUp(self): self.contents = sorted(OBJ_STORAGE_DATA) def assert_results_ok(self, start, end, actual_results, expected_results=None): if expected_results is None: expected_results = self.expected_results actual_results = list(actual_results) for indexed_data in actual_results: _id = indexed_data['id'] assert isinstance(_id, bytes) indexed_data = indexed_data.copy() indexed_data['id'] = hash_to_hex(indexed_data['id']) self.assertEqual(indexed_data, expected_results[hash_to_hex(_id)]) self.assertTrue(start <= _id <= end) _tool_id = indexed_data['indexer_configuration_id'] self.assertEqual(_tool_id, self.indexer.tool['id']) def test__index_contents(self): """Indexing contents without existing data results in indexed data """ _start, _end = [self.contents[0], self.contents[2]] # output hex ids start, end = map(hashutil.hash_to_bytes, (_start, _end)) # given actual_results = list(self.indexer._index_contents( start, end, indexed={})) self.assert_results_ok(start, end, actual_results) def test__index_contents_with_indexed_data(self): """Indexing contents with existing data results in less indexed data """ _start, _end = [self.contents[0], self.contents[2]] # output hex ids start, end = map(hashutil.hash_to_bytes, (_start, _end)) data_indexed = [self.id0, self.id2] # given actual_results = self.indexer._index_contents( start, end, indexed=set(map(hash_to_bytes, data_indexed))) # craft the expected results expected_results = self.expected_results.copy() for already_indexed_key in data_indexed: expected_results.pop(already_indexed_key) self.assert_results_ok( start, end, actual_results, expected_results) def test_generate_content_get(self): """Optimal indexing should result in indexed data """ _start, _end = [self.contents[0], self.contents[2]] # output hex ids start, end = map(hashutil.hash_to_bytes, (_start, _end)) # given actual_results = self.indexer.run(start, end) # then self.assertTrue(actual_results) def test_generate_content_get_input_as_bytes(self): """Optimal indexing should result in indexed data Input are in bytes here. """ _start, _end = [self.contents[0], self.contents[2]] # output hex ids start, end = map(hashutil.hash_to_bytes, (_start, _end)) # given actual_results = self.indexer.run( # checks the bytes input this time start, end, skip_existing=False) # no already indexed data so same result as prior test # then self.assertTrue(actual_results) def test_generate_content_get_no_result(self): """No result indexed returns False""" _start, _end = ['0000000000000000000000000000000000000000', '0000000000000000000000000000000000000001'] start, end = map(hashutil.hash_to_bytes, (_start, _end)) # given actual_results = self.indexer.run( start, end, incremental=False) # then self.assertFalse(actual_results)