diff --git a/sql/swh-data.sql b/sql/swh-data.sql index 63606c6f3..263dc161f 100644 --- a/sql/swh-data.sql +++ b/sql/swh-data.sql @@ -1,880 +1,877 @@ insert into entity_history (uuid, parent, name, type, description, homepage, active, generated, validity) values ('5f4d4c51-498a-4e28-88b3-b3e4e8396cba', NULL, 'softwareheritage', 'organization', 'Software Heritage', 'http://www.softwareheritage.org/', true, false, ARRAY[now()]), ('6577984d-64c8-4fab-b3ea-3cf63ebb8589', NULL, 'gnu', 'organization', 'GNU is not UNIX', 'https://gnu.org/', true, false, ARRAY[now()]), ('7c33636b-8f11-4bda-89d9-ba8b76a42cec', '6577984d-64c8-4fab-b3ea-3cf63ebb8589', 'GNU Hosting', 'group_of_entities', 'GNU Hosting facilities', NULL, true, false, ARRAY[now()]), ('4706c92a-8173-45d9-93d7-06523f249398', '6577984d-64c8-4fab-b3ea-3cf63ebb8589', 'GNU rsync mirror', 'hosting', 'GNU rsync mirror', 'rsync://mirror.gnu.org/', true, false, ARRAY[now()]), ('5cb20137-c052-4097-b7e9-e1020172c48e', '6577984d-64c8-4fab-b3ea-3cf63ebb8589', 'GNU Projects', 'group_of_entities', 'GNU Projects', 'https://gnu.org/software/', true, false, ARRAY[now()]), ('4bfb38f6-f8cd-4bc2-b256-5db689bb8da4', NULL, 'GitHub', 'organization', 'GitHub', 'https://github.org/', true, false, ARRAY[now()]), ('aee991a0-f8d7-4295-a201-d1ce2efc9fb2', '4bfb38f6-f8cd-4bc2-b256-5db689bb8da4', 'GitHub Hosting', 'group_of_entities', 'GitHub Hosting facilities', 'https://github.org/', true, false, ARRAY[now()]), ('34bd6b1b-463f-43e5-a697-785107f598e4', 'aee991a0-f8d7-4295-a201-d1ce2efc9fb2', 'GitHub git hosting', 'hosting', 'GitHub git hosting', 'https://github.org/', true, false, ARRAY[now()]), ('e8c3fc2e-a932-4fd7-8f8e-c40645eb35a7', 'aee991a0-f8d7-4295-a201-d1ce2efc9fb2', 'GitHub asset hosting', 'hosting', 'GitHub asset hosting', 'https://github.org/', true, false, ARRAY[now()]), ('9f7b34d9-aa98-44d4-8907-b332c1036bc3', '4bfb38f6-f8cd-4bc2-b256-5db689bb8da4', 'GitHub Organizations', 'group_of_entities', 'GitHub Organizations', 'https://github.org/', true, false, ARRAY[now()]), ('ad6df473-c1d2-4f40-bc58-2b091d4a750e', '4bfb38f6-f8cd-4bc2-b256-5db689bb8da4', 'GitHub Users', 'group_of_entities', 'GitHub Users', 'https://github.org/', true, false, ARRAY[now()]); insert into listable_entity (uuid, list_engine) values ('34bd6b1b-463f-43e5-a697-785107f598e4', 'swh.lister.github'); insert into fossology_license (name) values ('3DFX'), ('3DFX-PL'), ('AAL'), ('ACAA'), ('ACDL'), ('ACE'), ('Adaptec-GPL'), ('Adaptec.RESTRICTED'), ('Adobe'), ('Adobe-AFM'), ('Adobe-EULA'), ('Adobe-SCLA'), ('AFL'), ('AFL-1.0'), ('AFL-1.1'), ('AFL-1.2'), ('AFL-2.0'), ('AFL-2.1'), ('AFL-3.0'), ('AFPL-Ghostscript'), ('AgainstDRM'), ('AGE-Logic'), ('Agere-EULA'), ('AGFA-EULA'), ('AGFA(RESTRICTED)'), ('AGPL'), ('AGPL-1.0'), ('AGPL-1.0+'), ('AGPL-3.0'), ('AGPL-3.0+'), ('AGFA.RESTRICTED'), ('Aladdin'), ('Alfresco'), ('Alfresco-FLOSS'), ('Algorithmics'), ('AMD'), ('AMD-EULA'), ('AML'), ('AndroidFraunhofer.Commercial'), ('AndroidSDK.Commercial'), ('ANTLR-PD'), ('AOL-EULA'), ('Apache'), ('Apache-1.0'), ('Apache-1.1'), ('Apache-2.0'), ('Apache-style'), ('Apache-v1.0'), ('APL'), ('APL-1.0'), ('Apple'), ('Apple-EULA'), ('Apple.FontForge'), ('Apple.Sample'), ('APSL'), ('APSL-1.0'), ('APSL-1.1'), ('APSL-1.2'), ('APSL-2.0'), ('APSL-style'), ('Aptana'), ('Aptana-1.0'), ('ARJ'), ('Arphic-Font-PL'), ('Arphic-style'), ('Artifex'), ('Artistic-1.0'), ('Artistic-1.0-cl8'), ('Artistic-1.0-Perl'), ('Artistic-2.0'), ('Ascender-EULA'), ('ATI-EULA'), ('ATMEL-FW'), ('ATT'), ('ATT.Non-commercial'), ('ATT-Source'), ('ATT-Source-1.0'), ('ATT-Source-1.2d'), ('ATT-style'), ('AVM'), ('Baekmuk-Font'), ('Baekmuk.Hwan'), ('BancTec'), ('BEA'), ('Beerware'), ('Bellcore'), ('Bellcore-style'), ('BH-Font'), ('BH-Font-style'), ('BISON'), ('Bitstream'), ('BitTorrent'), ('BitTorrent-1.0'), ('BitTorrent-1.1'), ('BIZNET'), ('BIZNET-style'), ('BrainStorm-EULA'), ('Broadcom.Commercial'), ('Broadcom-EULA'), ('BSD'), ('BSD-2-Clause'), ('BSD-2-Clause-FreeBSD'), ('BSD-2-Clause-NetBSD'), ('BSD-3-Clause'), ('BSD-3-Clause-Clear'), ('BSD-3-Clause-Severability'), ('BSD-4-Clause'), ('BSD-4-Clause-UC'), ('BSD.non-commercial'), ('BSD-style'), ('BSL-1.0'), ('BSL-style'), ('CA'), ('Cadence'), ('Catharon'), ('CATOSL'), ('CATOSL-1.1'), ('CC0-1.0'), ('CC-BY'), ('CC-BY-1.0'), ('CC-BY-2.0'), ('CC-BY-2.5'), ('CC-BY-3.0'), ('CC-BY-4.0'), ('CC-BY-NC-1.0'), ('CC-BY-NC-2.0'), ('CC-BY-NC-2.5'), ('CC-BY-NC-3.0'), ('CC-BY-NC-4.0'), ('CC-BY-NC-ND-1.0'), ('CC-BY-NC-ND-2.0'), ('CC-BY-NC-ND-2.5'), ('CC-BY-NC-ND-3.0'), ('CC-BY-NC-ND-4.0'), ('CC-BY-NC-SA-1.0'), ('CC-BY-NC-SA-2.0'), ('CC-BY-NC-SA-2.5'), ('CC-BY-NC-SA-3.0'), ('CC-BY-NC-SA-4.0'), ('CC-BY-ND-1.0'), ('CC-BY-ND-2.0'), ('CC-BY-ND-2.5'), ('CC-BY-ND-3.0'), ('CC-BY-ND-4.0'), ('CC-BY-SA'), ('CC-BY-SA-1.0'), ('CC-BY-SA-2.0'), ('CC-BY-SA-2.5'), ('CC-BY-SA-3.0'), ('CC-BY-SA-4.0'), ('CC-LGPL'), ('CC-LGPL-2.1'), ('CCLRC'), ('CCPL'), ('CDDL'), ('CDDL-1.0'), ('CDDL-1.1'), ('CECILL'), ('CECILL-1.0'), ('CECILL-1.1'), ('CECILL-2.0'), ('CECILL-B'), ('CECILL-C'), ('CECILL(dual)'), ('Cisco'), ('Cisco-style'), ('Citrix'), ('ClArtistic'), ('ClearSilver'), ('CMake'), ('CMU'), ('CMU-style'), ('CNRI-Python'), ('CNRI-Python-GPL-Compatible'), ('Combined_OpenSSL+SSLeay'), ('COMMERCIAL'), ('CompuServe'), ('Comtrol'), ('Condor-1.0'), ('Condor-1.1'), ('CopyLeft[1]'), ('CopyLeft[2]'), ('CPAL'), ('CPAL-1.0'), ('CPL'), ('CPL-0.5'), ('CPL-1.0'), ('CPOL'), ('CPOL-1.02'), ('Cryptogams'), ('CUA-OPL-1.0'), ('CUPS'), ('CUPS-EULA'), ('Cygnus-eCos-1.0'), ('Cylink-ISC'), ('Cypress-FW'), ('DARPA'), ('DARPA-Cougaar'), ('Debian-social-DFSG'), ('Debian-SPI'), ('Debian-SPI-style'), ('D.E.Knuth'), ('D-FSL-1.0'), ('DMTF'), ('DOCBOOK'), ('DOCBOOK-style'), ('DPTC'), ('DSCT'), ('DSL'), ('Dual-license'), ('Dyade'), ('EBT-style'), ('ECL-1.0'), ('ECL-2.0'), ('eCos-2.0'), ('EDL-1.0'), ('EFL'), ('EFL-1.0'), ('EFL-2.0'), ('eGenix'), ('Entessa'), ('Epinions'), ('EPL'), ('EPL-1.0'), ('Epson-EULA'), ('Epson-PL'), ('ErlPL-1.1'), ('EUDatagrid'), ('EUPL-1.0'), ('EUPL-1.1'), ('FaCE'), ('Fair'), ('Fair-style'), ('FAL-1.0'), ('FAL-1.3'), ('Fedora'), ('FedoraCLA'), ('Flash2xml-1.0'), ('Flora'), ('Flora-1.0'), ('Flora-1.1'), ('Frameworx'), ('Frameworx-1.0'), ('FreeBSD-Doc'), ('Free-PL'), ('Free-SW'), ('Free-SW.run-COMMAND'), ('FSF'), ('FTL'), ('FTL-style'), ('Fujitsu'), ('Garmin-EULA'), ('GFDL'), ('GFDL-1.1'), ('GFDL-1.1+'), ('GFDL-1.2'), ('GFDL-1.2+'), ('GFDL-1.3'), ('GFDL-v1.2'), ('Genivia.Commercial'), ('Ghostscript-GPL'), ('Ghostscript-GPL-1.1'), ('Giftware'), ('GNU-copyleft'), ('GNU-Ghostscript'), ('GNU-javamail-exception'), ('GNU-Manpages'), ('GNU-style.EXECUTE'), ('GNU-style.interactive'), ('Google'), ('Google-BSD'), ('Govt-restrict'), ('Govt-rights'), ('Govt-work'), ('GPDL'), ('GPL'), ('GPL-1.0'), ('GPL-1.0+'), ('GPL-2.0'), ('GPL-2.0+'), ('GPL-2.0-with-autoconf-exception'), ('GPL-2.0-with-bison-exception'), ('GPL-2.0+-with-bison-exception'), ('GPL-2.0-with-classpath-exception'), ('GPL-2.0+-with-classpath-exception'), ('GPL-2.0-with-font-exception'), ('GPL-2.0-with-GCC-exception'), ('GPL-2.0-with-trolltech-exception'), ('GPL-2.0+-with-UPX-exception'), ('GPL-3.0'), ('GPL-3.0+'), ('GPL-3.0-with-autoconf-exception'), ('GPL-3.0+-with-autoconf-exception'), ('GPL-3.0-with-bison-exception'), ('GPL-3.0+-with-bison-exception'), ('GPL-3.0-with-classpath-exception'), ('GPL-3.0+-with-classpath-exception'), ('GPL-3.0-with-GCC-exception'), ('GPL-3.0+-with-GCC-exception'), ('GPL-exception'), ('GPL-or-LGPL'), ('GPL(rms)'), ('GPL-with-autoconf-exception'), ('gSOAP'), ('gSOAP-1.3b'), ('H2'), ('H2-1.0'), ('Hacktivismo'), ('Hauppauge'), ('Helix.RealNetworks-EULA'), ('HP'), ('HP-Compaq'), ('HP-DEC'), ('HP-DEC-style'), ('HP-EULA'), ('HP+IBM'), ('HPND'), ('HP-Proprietary'), ('HP-style'), ('HSQLDB'), ('IBM'), ('IBM-Courier'), ('IBM-EULA'), ('IBM-JCL'), ('IBM-pibs'), ('IBM-reciprocal'), ('ICU'), ('ID-EULA'), ('IDPL'), ('IDPL-1.0'), ('IEEE-Doc'), ('IETF'), ('IETF-style'), ('IJG'), ('ImageMagick'), ('ImageMagick-style'), ('Imlib2'), ('InfoSeek'), ('info-zip'), ('InnerNet'), ('InnerNet-2.00'), ('InnerNet-style'), ('Intel'), ('Intel.Commercial'), ('Intel-EULA'), ('Intel-other'), ('Intel.RESTRICTED'), ('Intel-WLAN'), ('Interbase-1.0'), ('Interbase-PL'), ('Interlink-EULA'), ('Intranet-only'), ('IOS'), ('IoSoft.COMMERCIAL'), ('IPA'), ('IPA-Font-EULA'), ('IP-claim'), ('IPL'), ('IPL-1.0'), ('IPL-2.0'), ('IPTC'), ('IronDoc'), ('ISC'), ('Jabber'), ('Jabber-1.0'), ('Java-Multi-Corp'), ('Java-WSDL4J'), ('Java-WSDL-Policy'), ('Java-WSDL-Schema'), ('Java-WSDL-Spec'), ('JISP'), ('JPEG.netpbm'), ('JPNIC'), ('JSON'), ('KDE'), ('KD-Tools-EULA'), ('Keyspan-FW'), ('KnowledgeTree-1.1'), ('Knuth-style'), ('Lachman-Proprietary'), ('Larabie-EULA'), ('LDP'), ('LDP-1A'), ('LDP-2.0'), ('Legato'), ('Leptonica'), ('LGPL'), ('LGPL-1.0'), ('LGPL-1.0+'), ('LGPL-2.0'), ('LGPL-2.0+'), ('LGPL-2.1'), ('LGPL-2.1+'), ('LGPL-3.0'), ('LGPL-3.0+'), ('LIBGCJ'), ('Libpng'), ('Link-exception'), ('LinuxDoc'), ('Linux-HOWTO'), ('Logica-OSL-1.0'), ('LPL-1.0'), ('LPL-1.02'), ('LPPL'), ('LPPL-1.0'), ('LPPL-1.0+'), ('LPPL-1.1'), ('LPPL-1.1+'), ('LPPL-1.2'), ('LPPL-1.2+'), ('LPPL-1.3'), ('LPPL-1.3+'), ('LPPL-1.3a'), ('LPPL-1.3a+'), ('LPPL-1.3b'), ('LPPL-1.3b+'), ('LPPL-1.3c'), ('LPPL-1.3c+'), ('MacroMedia-RPSL'), ('Macrovision'), ('Macrovision-EULA'), ('Majordomo'), ('Majordomo-1.1'), ('Mandriva'), ('Mellanox'), ('MetroLink'), ('MetroLink-nonfree'), ('Mibble'), ('Mibble-2.8'), ('Microsoft'), ('Migemo'), ('MindTerm'), ('MirOS'), ('MIT'), ('MIT.BSD'), ('MIT&BSD'), ('MITEM'), ('Mitre'), ('MitreCVW'), ('MitreCVW-style'), ('MIT-style'), ('Motorola'), ('Motosoto'), ('MPEG3-decoder'), ('MPL'), ('MPL-1.0'), ('MPL-1.1'), ('MPL-1.1+'), ('MPL-1.1-style'), ('MPL-2.0'), ('MPL-2.0-no-copyleft-exception'), ('MPL-EULA-1.1'), ('MPL-EULA-2.0'), ('MPL-EULA-3.0'), ('MPL-style'), ('MPL.TPL'), ('MPL.TPL-1.0'), ('M-Plus-Project'), ('MRL'), ('MS-EULA'), ('MS-indemnity'), ('MS-IP'), ('MS-LPL'), ('MS-LRL'), ('MS-PL'), ('MS-RL'), ('MS-SSL'), ('Multics'), ('MX4J'), ('MX4J-1.0'), ('MySQL-0.3'), ('MySQL.FLOSS'), ('MySQL-style'), ('NASA'), ('NASA-1.3'), ('Naumen'), ('NBPL-1.0'), ('nCipher'), ('NCSA'), ('NESSUS-EULA'), ('NGPL'), ('Nokia'), ('No_license_found'), ('non-ATT-BSD'), ('Non-commercial'), ('Non-profit'), ('NOSL'), ('NOSL-1.0'), ('Not-for-sale'), ('Not-Free'), ('Not-Internet'), ('Not-OpenSource'), ('NOT-Open-Source'), ('NotreDame'), ('NotreDame-style'), ('Novell'), ('Novell-EULA'), ('Novell-IP'), ('NPL'), ('NPL-1.0'), ('NPL-1.1'), ('NPL-1.1+'), ('NPL-EULA'), ('NPOSL-3.0'), ('NRL'), ('NTP'), ('Nvidia'), ('Nvidia-EULA'), ('OASIS'), ('OCL'), ('OCL-1.0'), ('OCLC'), ('OCLC-1.0'), ('OCLC-2.0'), ('OCL-style'), ('ODbL-1.0'), ('ODL'), ('OFL-1.0'), ('OFL-1.1'), ('OGTSL'), ('OLDAP'), ('OLDAP-1.1'), ('OLDAP-1.2'), ('OLDAP-1.3'), ('OLDAP-1.4'), ('OLDAP-2.0'), ('OLDAP-2.0.1'), ('OLDAP-2.1'), ('OLDAP-2.2'), ('OLDAP-2.2.1'), ('OLDAP-2.2.2'), ('OLDAP-2.3'), ('OLDAP-2.4'), ('OLDAP-2.5'), ('OLDAP-2.6'), ('OLDAP-2.7'), ('OLDAP-2.8'), ('OLDAP-style'), ('OMF'), ('OMRON'), ('Ontopia'), ('OpenCASCADE-PL'), ('OpenGroup'), ('OpenGroup-Proprietary'), ('OpenGroup-style'), ('OpenMap'), ('OpenMarket'), ('Open-PL'), ('Open-PL-0.4'), ('Open-PL-1.0'), ('Open-PL-style'), ('OpenSSL'), ('OpenSSL-exception'), ('OPL-1.0'), ('OPL-style'), ('Oracle-Berkeley-DB'), ('Oracle-Dev'), ('Oracle-EULA'), ('OReilly'), ('OReilly-style'), ('OSD'), ('OSF'), ('OSF-style'), ('OSL'), ('OSL-1.0'), ('OSL-1.1'), ('OSL-2.0'), ('OSL-2.1'), ('OSL-3.0'), ('Paradigm'), ('Patent-ref'), ('PDDL-1.0'), ('Phorum'), ('PHP'), ('PHP-2.0'), ('PHP-2.0.2'), ('PHP-3.0'), ('PHP-3.01'), ('PHP-style'), ('Piriform'), ('Pixware-EULA'), ('Platform-Computing(RESTRICTED)'), ('Polyserve-CONFIDENTIAL'), ('Postfix'), ('PostgreSQL'), ('Powder-Proprietary'), ('Princeton'), ('Princeton-style'), ('Proprietary'), ('Public-domain'), ('Public-domain(C)'), ('Public-domain-ref'), ('Public-Use'), ('Public-Use-1.0'), ('Python'), ('Python-2.0'), ('Python-2.0.1'), ('Python-2.0.2'), ('Python-2.1.1'), ('Python-2.1.3'), ('Python-2.2'), ('Python-2.2.3'), ('Python-2.2.7'), ('Python-2.3'), ('Python-2.3.7'), ('Python-2.4.4'), ('Python-style'), ('Qmail'), ('QPL'), ('QPL-1.0'), ('QT.Commercial'), ('QuarterDeck'), ('Quest-EULA'), ('RCSL'), ('RCSL-1.0'), ('RCSL-2.0'), ('RCSL-3.0'), ('RealNetworks-EULA'), ('RedHat'), ('RedHat-EULA'), ('RedHat.Non-commercial'), ('RedHat-specific'), ('Redland'), ('Restricted-rights'), ('RHeCos-1.1'), ('Riverbank-EULA'), ('RPL'), ('RPL-1.0'), ('RPL-1.1'), ('RPL-1.5'), ('RPSL'), ('RPSL-1.0'), ('RPSL-2.0'), ('RPSL-3.0'), ('RSA-DNS'), ('RSA-Security'), ('RSCPL'), ('Ruby'), ('Same-license-as'), ('SAX-PD'), ('SciTech'), ('SCO.commercial'), ('SCSL'), ('SCSL-2.3'), ('SCSL-3.0'), ('SCSL-TSA'), ('SCSL-TSA-1.0'), ('See-doc.OTHER'), ('See-file'), ('See-file.COPYING'), ('See-file.LICENSE'), ('See-file.README'), ('See-URL'), ('Sendmail'), ('SGI'), ('SGI-B-1.0'), ('SGI-B-1.1'), ('SGI-B-2.0'), ('SGI-Freeware'), ('SGI_GLX'), ('SGI_GLX-1.0'), ('SGI-Proprietary'), ('SGI-style'), ('SGML'), ('SimPL-2.0'), ('SISSL'), ('SISSL-1.1'), ('SISSL-1.2'), ('Skype-EULA'), ('Sleepycat'), ('Sleepycat.Non-commercial'), ('SMLNJ'), ('SNIA'), ('SNIA-1.0'), ('SNIA-1.1'), ('SpikeSource'), ('SPL'), ('SPL-1.0'), ('Stanford'), ('Stanford-style'), ('SugarCRM-1.1.3'), ('Sun'), ('SUN'), ('Sun-BCLA'), ('Sun-BCLA-1.5.0'), ('Sun-EULA'), ('Sun-IP'), ('Sun-Java'), ('Sun.Non-commercial'), ('SunPro'), ('Sun-Proprietary'), ('Sun.RESTRICTED'), ('Sun-RPC'), ('Sun-SCA'), ('Sun(tm)'), ('SW-Research'), ('Tapjoy'), ('TCL'), ('Tektronix'), ('Tektronix-style'), ('TeX-exception'), ('Trident-EULA'), ('Trolltech'), ('TrueCrypt-3.0'), ('U-BC'), ('U-Cambridge'), ('U-Cambridge-style'), ('UCAR'), ('UCAR-style'), ('U-Chicago'), ('U-Columbia'), ('UCWare-EULA'), ('U-Del'), ('U-Del-style'), ('U-Edinburgh'), ('U-Edinburgh-style'), ('U-Michigan'), ('U-Mich-style'), ('U-Monash'), ('Unicode'), ('Unidex'), ('UnitedLinux-EULA'), ('Unix-Intl'), ('Unlicense'), ('unRAR restriction'), ('URA.govt'), ('USC'), ('USC.Non-commercial'), ('USC-style'), ('US-Export-restrict'), ('USL-Europe'), ('U-Utah'), ('U-Wash.Free-Fork'), ('U-Washington'), ('U-Wash-style'), ('VIM'), ('Vixie'), ('Vixie-license'), ('VMware-EULA'), ('VSL-1.0'), ('W3C'), ('W3C-IP'), ('W3C-style'), ('Wash-U-StLouis'), ('Wash-U-style'), ('Watcom'), ('Watcom-1.0'), ('WebM'), ('Wintertree'), ('WordNet-3.0'), ('WTFPL'), ('WTI.Not-free'), ('WXwindows'), ('X11'), ('X11-style'), ('Xerox'), ('Xerox-style'), ('XFree86'), ('XFree86-1.0'), ('XFree86-1.1'), ('Ximian'), ('Ximian-1.0'), ('XMLDB-1.0'), ('Xnet'), ('X/Open'), ('XOPEN-EULA'), ('X/Open-style'), ('Yahoo-EULA'), ('YaST.SuSE'), ('YPL'), ('YPL-1.0'), ('YPL-1.1'), ('Zend-1.0'), ('Zend-2.0'), ('Zeus'), ('Zimbra'), ('Zimbra-1.2'), ('Zimbra-1.3'), ('Zlib'), ('Zlib-possibility'), ('ZoneAlarm-EULA'), ('ZPL'), ('ZPL-1.0'), ('ZPL-1.1'), ('ZPL-2.0'), ('ZPL-2.1'), ('Zveno'), ('Affero-possibility'), ('Apache-possibility'), ('Apache_v2-possibility'), ('Artistic-possibility'), ('BSD-possibility'), ('CMU-possibility'), ('CPL-possibility'), ('Freeware'), ('FSF-possibility'), ('GPL-2.0+:3.0'), ('GPL-2.0+&GPL-3.0+'), ('GPL-2.1[sic]'), ('GPL-2.1+[sic]'), ('GPL-possibility'), ('HP-possibility'), ('IBM-possibility'), ('ISC-possibility'), ('LGPL-possibility'), ('LGPL_v3-possibility'), ('Microsoft-possibility'), ('MIT-possibility'), ('NOT-public-domain'), ('Perl-possibility'), ('PHP-possibility'), ('RSA-possibility'), ('Sun-possibility'), ('Trademark-ref'), ('UnclassifiedLicense'), ('W3C-possibility'), ('X11-possibility'); insert into indexer_configuration(tool_name, tool_version, tool_configuration) values ('nomos', '3.1.0rc2-31-ga2cbb8c', '{"command_line": "nomossa "}'); insert into indexer_configuration(tool_name, tool_version, tool_configuration) values ('file', '5.22', '{"command_line": "file --mime "}'); insert into indexer_configuration(tool_name, tool_version, tool_configuration) values ('universal-ctags', '~git7859817b', '{"command_line": "ctags --fields=+lnz --sort=no --links=no --output-format=json "}'); insert into indexer_configuration(tool_name, tool_version, tool_configuration) values ('pygments', '2.0.1+dfsg-1.1+deb8u1', '{"type": "library", "debian-package": "python3-pygments"}'); insert into indexer_configuration(tool_name, tool_version, tool_configuration) values ('pygments', '2.0.1+dfsg-1.1+deb8u1', '{"type": "library", "debian-package": "python3-pygments", "max_content_size": 10240}'); insert into indexer_configuration(tool_name, tool_version, tool_configuration) values ('swh-metadata-translator', '0.0.1', '{"type": "local", "context": "npm"}'); - --- insert into indexer_configuration(tool_name, tool_version, tool_configuration) --- values ('swh-metadata-translator', '0.0.1', '{"type": "local", "context": "maven"}'); diff --git a/sql/swh-schema.sql b/sql/swh-schema.sql index f9c0869f7..baa414fc1 100644 --- a/sql/swh-schema.sql +++ b/sql/swh-schema.sql @@ -1,516 +1,479 @@ --- --- Software Heritage Data Model --- -- drop schema if exists swh cascade; -- create schema swh; -- set search_path to swh; create table dbversion ( version int primary key, release timestamptz, description text ); insert into dbversion(version, release, description) values(107, now(), 'Work In Progress'); -- a SHA1 checksum (not necessarily originating from Git) create domain sha1 as bytea check (length(value) = 20); -- a Git object ID, i.e., a SHA1 checksum create domain sha1_git as bytea check (length(value) = 20); -- a SHA256 checksum create domain sha256 as bytea check (length(value) = 32); -- a blake2 checksum create domain blake2s256 as bytea check (length(value) = 32); -- UNIX path (absolute, relative, individual path component, etc.) create domain unix_path as bytea; -- a set of UNIX-like access permissions, as manipulated by, e.g., chmod create domain file_perms as int; -- Checksums about actual file content. Note that the content itself is not -- stored in the DB, but on external (key-value) storage. A single checksum is -- used as key there, but the other can be used to verify that we do not inject -- content collisions not knowingly. create table content ( sha1 sha1 not null, sha1_git sha1_git not null, sha256 sha256 not null, blake2s256 blake2s256, length bigint not null, ctime timestamptz not null default now(), -- creation time, i.e. time of (first) injection into the storage status content_status not null default 'visible', object_id bigserial ); -- Entities constitute a typed hierarchy of organization, hosting -- facilities, groups, people and software projects. -- -- Examples of entities: Software Heritage, Debian, GNU, GitHub, -- Apache, The Linux Foundation, the Debian Python Modules Team, the -- torvalds GitHub user, the torvalds/linux GitHub project. -- -- The data model is hierarchical (via the parent attribute) and might -- store sub-branches of existing entities. The key feature of an -- entity is might be *listed* (if it is available in listable_entity) -- to retrieve information about its content, i.e: sub-entities, -- projects, origins. -- The history of entities. Allows us to keep historical metadata -- about entities. The temporal invariant is the uuid. Root -- organization uuids are manually generated (and available in -- swh-data.sql). -- -- For generated entities (generated = true), we can provide -- generation_metadata to allow listers to retrieve the uuids of previous -- iterations of the entity. -- -- Inactive entities that have been active in the past (active = -- false) should register the timestamp at which we saw them -- deactivate, in a new entry of entity_history. create table entity_history ( id bigserial not null, uuid uuid, parent uuid, -- should reference entity_history(uuid) name text not null, type entity_type not null, description text, homepage text, active boolean not null, -- whether the entity was seen on the last listing generated boolean not null, -- whether this entity has been generated by a lister lister_metadata jsonb, -- lister-specific metadata, used for queries metadata jsonb, validity timestamptz[] -- timestamps at which we have seen this entity ); -- The entity table provides a view of the latest information on a -- given entity. It is updated via a trigger on entity_history. create table entity ( uuid uuid not null, parent uuid, name text not null, type entity_type not null, description text, homepage text, active boolean not null, -- whether the entity was seen on the last listing generated boolean not null, -- whether this entity has been generated by a lister lister_metadata jsonb, -- lister-specific metadata, used for queries metadata jsonb, last_seen timestamptz, -- last listing time or disappearance time for active=false last_id bigint -- last listing id ); -- Register the equivalence between two entities. Allows sideways -- navigation in the entity table create table entity_equivalence ( entity1 uuid, entity2 uuid ); -- Register a lister for a specific entity. create table listable_entity ( uuid uuid, enabled boolean not null default true, -- do we list this entity automatically? list_engine text, -- crawler to be used to list entity's content list_url text, -- root URL to start the listing list_params jsonb, -- org-specific listing parameter latest_list timestamptz -- last time the entity's content has been listed ); -- Log of all entity listings (i.e., entity crawling) that have been -- done in the past, or are still ongoing. create table list_history ( id bigserial not null, date timestamptz not null, status boolean, -- true if and only if the listing has been successful result jsonb, -- more detailed return value, depending on status stdout text, stderr text, duration interval, -- fetch duration of NULL if still ongoing entity uuid ); -- An origin is a place, identified by an URL, where software can be found. We -- support different kinds of origins, e.g., git and other VCS repositories, -- web pages that list tarballs URLs (e.g., http://www.kernel.org), indirect -- tarball URLs (e.g., http://www.example.org/latest.tar.gz), etc. The key -- feature of an origin is that it can be *fetched* (wget, git clone, svn -- checkout, etc.) to retrieve all the contained software. create table origin ( id bigserial not null, type text, -- TODO use an enum here (?) url text not null, lister uuid, project uuid ); -- Content we have seen but skipped for some reason. This table is -- separate from the content table as we might not have the sha1 -- checksum of that data (for instance when we inject git -- repositories, objects that are too big will be skipped here, and we -- will only know their sha1_git). 'reason' contains the reason the -- content was skipped. origin is a nullable column allowing to find -- out which origin contains that skipped content. create table skipped_content ( sha1 sha1, sha1_git sha1_git, sha256 sha256, blake2s256 blake2s256, length bigint not null, ctime timestamptz not null default now(), status content_status not null default 'absent', reason text not null, origin bigint, object_id bigserial ); -- Log of all origin fetches (i.e., origin crawling) that have been done in the -- past, or are still ongoing. Similar to list_history, but for origins. create table fetch_history ( id bigserial, origin bigint, date timestamptz not null, status boolean, -- true if and only if the fetch has been successful result jsonb, -- more detailed returned values, times, etc... stdout text, stderr text, -- null when status is true, filled otherwise duration interval -- fetch duration of NULL if still ongoing ); -- A file-system directory. A directory is a list of directory entries (see -- tables: directory_entry_{dir,file}). -- -- To list the contents of a directory: -- 1. list the contained directory_entry_dir using array dir_entries -- 2. list the contained directory_entry_file using array file_entries -- 3. list the contained directory_entry_rev using array rev_entries -- 4. UNION -- -- Synonyms/mappings: -- * git: tree create table directory ( id sha1_git, dir_entries bigint[], -- sub-directories, reference directory_entry_dir file_entries bigint[], -- contained files, reference directory_entry_file rev_entries bigint[], -- mounted revisions, reference directory_entry_rev object_id bigserial -- short object identifier ); -- A directory entry pointing to a sub-directory. create table directory_entry_dir ( id bigserial, target sha1_git, -- id of target directory name unix_path, -- path name, relative to containing dir perms file_perms -- unix-like permissions ); -- A directory entry pointing to a file. create table directory_entry_file ( id bigserial, target sha1_git, -- id of target file name unix_path, -- path name, relative to containing dir perms file_perms -- unix-like permissions ); -- A directory entry pointing to a revision. create table directory_entry_rev ( id bigserial, target sha1_git, -- id of target revision name unix_path, -- path name, relative to containing dir perms file_perms -- unix-like permissions ); create table person ( id bigserial, name bytea, -- advisory: not null if we managed to parse a name email bytea, -- advisory: not null if we managed to parse an email fullname bytea not null -- freeform specification; what is actually used in the checksums -- will usually be of the form 'name ' ); -- A snapshot of a software project at a specific point in time. -- -- Synonyms/mappings: -- * git / subversion / etc: commit -- * tarball: a specific tarball -- -- Revisions are organized as DAGs. Each revision points to 0, 1, or more (in -- case of merges) parent revisions. Each revision points to a directory, i.e., -- a file-system tree containing files and directories. create table revision ( id sha1_git, date timestamptz, date_offset smallint, committer_date timestamptz, committer_date_offset smallint, type revision_type not null, directory sha1_git, -- file-system tree message bytea, author bigint, committer bigint, synthetic boolean not null default false, -- true if synthetic (cf. swh-loader-tar) metadata jsonb, -- extra metadata (tarball checksums, extra commit information, etc...) object_id bigserial, date_neg_utc_offset boolean, committer_date_neg_utc_offset boolean ); -- either this table or the sha1_git[] column on the revision table create table revision_history ( id sha1_git, parent_id sha1_git, parent_rank int not null default 0 -- parent position in merge commits, 0-based ); -- The timestamps at which Software Heritage has made a visit of the given origin. create table origin_visit ( origin bigint not null, visit bigint not null, date timestamptz not null, status origin_visit_status not null, metadata jsonb ); comment on column origin_visit.origin is 'Visited origin'; comment on column origin_visit.visit is 'Visit number the visit occurred for that origin'; comment on column origin_visit.date is 'Visit date for that origin'; comment on column origin_visit.status is 'Visit status for that origin'; comment on column origin_visit.metadata is 'Metadata associated with the visit'; -- The content of software origins is indexed starting from top-level pointers -- called "branches". Every time we fetch some origin we store in this table -- where the branches pointed to at fetch time. -- -- Synonyms/mappings: -- * git: ref (in the "git update-ref" sense) create table occurrence_history ( origin bigint not null, branch bytea not null, -- e.g., b"master" (for VCS), or b"sid" (for Debian) target sha1_git not null, -- ref target, e.g., commit id target_type object_type not null, -- ref target type visits bigint[] not null, -- the visits where that occurrence was valid. References -- origin_visit(visit), where o_h.origin = origin_visit.origin. object_id bigserial not null -- short object identifier ); -- Materialized view of occurrence_history, storing the *current* value of each -- branch, as last seen by SWH. create table occurrence ( origin bigint, branch bytea not null, target sha1_git not null, target_type object_type not null ); -- A "memorable" point in the development history of a project. -- -- Synonyms/mappings: -- * git: tag (of the annotated kind, otherwise they are just references) -- * tarball: the release version number create table release ( id sha1_git not null, target sha1_git, date timestamptz, date_offset smallint, name bytea, comment bytea, author bigint, synthetic boolean not null default false, -- true if synthetic (cf. swh-loader-tar) object_id bigserial, target_type object_type not null, date_neg_utc_offset boolean ); -- Content provenance information caches -- https://forge.softwareheritage.org/T547 -- -- Those tables aren't expected to be exhaustive, and get filled on a case by -- case basis: absence of data doesn't mean the data is not there -- content <-> revision mapping cache -- -- semantics: "we have seen the content with given id in the given path inside -- the given revision" create table cache_content_revision ( content sha1_git not null, blacklisted boolean default false, revision_paths bytea[][] ); create table cache_content_revision_processed ( revision sha1_git not null ); -- revision <-> origin_visit mapping cache -- -- semantics: "we have seen the given revision in the given origin during the -- given visit" create table cache_revision_origin ( revision sha1_git not null, origin bigint not null, visit bigint not null ); -- Computing metadata on sha1's contents create table indexer_configuration ( id serial not null, tool_name text not null, tool_version text not null, tool_configuration jsonb ); comment on table indexer_configuration is 'Indexer''s configuration version'; comment on column indexer_configuration.id is 'Tool identifier'; comment on column indexer_configuration.tool_version is 'Tool name'; comment on column indexer_configuration.tool_version is 'Tool version'; comment on column indexer_configuration.tool_configuration is 'Tool configuration: command line, flags, etc...'; -- Properties (mimetype, encoding, etc...) create table content_mimetype ( id sha1 not null, mimetype bytea not null, encoding bytea not null, indexer_configuration_id bigint not null ); comment on table content_mimetype is 'Metadata associated to a raw content'; comment on column content_mimetype.mimetype is 'Raw content Mimetype'; comment on column content_mimetype.encoding is 'Raw content encoding'; comment on column content_mimetype.indexer_configuration_id is 'Tool used to compute the information'; -- Language metadata create table content_language ( id sha1 not null, lang languages not null, indexer_configuration_id bigint not null ); comment on table content_language is 'Language information on a raw content'; comment on column content_language.lang is 'Language information'; comment on column content_language.indexer_configuration_id is 'Tool used to compute the information'; -- ctags information per content create table content_ctags ( id sha1 not null, name text not null, kind text not null, line bigint not null, lang ctags_languages not null, indexer_configuration_id bigint not null ); comment on table content_ctags is 'Ctags information on a raw content'; comment on column content_ctags.id is 'Content identifier'; comment on column content_ctags.name is 'Symbol name'; comment on column content_ctags.kind is 'Symbol kind (function, class, variable, const...)'; comment on column content_ctags.line is 'Symbol line'; comment on column content_ctags.lang is 'Language information for that content'; comment on column content_ctags.indexer_configuration_id is 'Tool used to compute the information'; create table fossology_license( id smallserial, name text not null ); comment on table fossology_license is 'Possible license recognized by license indexer'; comment on column fossology_license.id is 'License identifier'; comment on column fossology_license.name is 'License name'; create table content_fossology_license ( id sha1 not null, license_id smallserial not null, indexer_configuration_id bigint not null ); comment on table content_fossology_license is 'license associated to a raw content'; comment on column content_fossology_license.id is 'Raw content identifier'; comment on column content_fossology_license.license_id is 'One of the content''s license identifier'; comment on column content_fossology_license.indexer_configuration_id is 'Tool used to compute the information'; -- The table content_metadata provides a translation to files -- identified as potentially containning metadata with a translation tool (indexer_configuration_id) create table content_metadata( id sha1 not null, translated_metadata jsonb not null, indexer_configuration_id bigint not null ); comment on table content_metadata is 'metadata semantically translated from a content file'; comment on column content_metadata.id is 'sha1 of content file'; comment on column content_metadata.translated_metadata is 'result of translation with defined format'; comment on column content_metadata.indexer_configuration_id is 'tool used for translation'; - - --- Discovery of metadata during a listing or a deposit of an origin --- also provides a translation to a defined json schema using a translation tool (indexer_configuration_id) -create table origin_metadata_history( - origin_id bigint not null, - discovery_date timestamptz not null, - translation_date timestamptz, - provenance_type text not null, -- TODO use an enum (?) - raw_metadata jsonb not null, - translated_metadata jsonb, - indexer_configuration_id bigint, - object_id bigserial -- short object identifier -); - - -comment on table origin_metadata_history is 'keeps latest metadata concerning an origin'; -comment on column origin_metadata_history.origin_id is 'the origin id for which the metadata was found'; -comment on column origin_metadata_history.discovery_date is 'the date of retrieval'; -comment on column origin_metadata_history.translation_date is 'the date of translation'; -comment on column origin_metadata_history.provenance_type is 'lister, publisher, etc'; -comment on column origin_metadata_history.raw_metadata is 'metadata in json format but with original terms'; -comment on column origin_metadata_history.translated_metadata is 'metadata in defined terms in json schema'; -comment on column origin_metadata_history.indexer_configuration_id is 'tool used for translation'; - - --- Materialized view of origin_metadata_history, storing the *current* value of --- metadata, as last seen by SWH. -create table origin_metadata( - origin_id bigint not null, - discovery_date timestamptz not null, - translation_date timestamptz, - provenance_type text not null, -- TODO use an enum (?) - raw_metadata jsonb not null, - translated_metadata jsonb, - indexer_configuration_id bigint -); diff --git a/swh/storage/storage.py b/swh/storage/storage.py index 5328e36f6..92afe4d32 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,1627 +1,1622 @@ # Copyright (C) 2015-2017 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from collections import defaultdict import datetime import itertools import json import dateutil.parser import psycopg2 from . import converters from .common import db_transaction_generator, db_transaction from .db import Db from .exc import StorageDBError from swh.model.hashutil import ALGORITHMS from swh.objstorage import get_objstorage from swh.objstorage.exc import ObjNotFoundError # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 CONTENT_HASH_KEYS = ['sha1', 'sha1_git', 'sha256', 'blake2s256'] class Storage(): """SWH storage proxy, encompassing DB and object storage """ def __init__(self, db, objstorage): """ Args: db_conn: either a libpq connection string, or a psycopg2 connection obj_root: path to the root of the object storage """ try: if isinstance(db, psycopg2.extensions.connection): self.db = Db(db) else: self.db = Db.connect(db) except psycopg2.OperationalError as e: raise StorageDBError(e) self.objstorage = get_objstorage(**objstorage) def check_config(self, *, check_write): """Check that the storage is configured and ready to go.""" if not self.objstorage.check_config(check_write=check_write): return False # Check permissions on one of the tables with self.db.transaction() as cur: if check_write: check = 'INSERT' else: check = 'SELECT' cur.execute( "select has_table_privilege(current_user, 'content', %s)", (check,) ) return cur.fetchone()[0] return True def content_add(self, content): """Add content blobs to the storage Note: in case of DB errors, objects might have already been added to the object storage and will not be removed. Since addition to the object storage is idempotent, that should not be a problem. Args: content: iterable of dictionaries representing individual pieces of content to add. Each dictionary has the following keys: - data (bytes): the actual content - length (int): content length (default: -1) - one key for each checksum algorithm in swh.model.hashutil.ALGORITHMS, mapped to the corresponding checksum - status (str): one of visible, hidden, absent - reason (str): if status = absent, the reason why - origin (int): if status = absent, the origin we saw the content in """ db = self.db def _unique_key(hash, keys=CONTENT_HASH_KEYS): """Given a hash (tuple or dict), return a unique key from the aggregation of keys. """ if isinstance(hash, tuple): return hash return tuple([hash[k] for k in keys]) content_by_status = defaultdict(list) for d in content: if 'status' not in d: d['status'] = 'visible' if 'length' not in d: d['length'] = -1 content_by_status[d['status']].append(d) content_with_data = content_by_status['visible'] content_without_data = content_by_status['absent'] missing_content = set(self.content_missing(content_with_data)) missing_skipped = set(_unique_key(hashes) for hashes in self.skipped_content_missing( content_without_data)) with db.transaction() as cur: if missing_content: # create temporary table for metadata injection db.mktemp('content', cur) def add_to_objstorage(cont): self.objstorage.add(cont['data'], obj_id=cont['sha1']) content_filtered = (cont for cont in content_with_data if cont['sha1'] in missing_content) db.copy_to(content_filtered, 'tmp_content', db.content_get_metadata_keys, cur, item_cb=add_to_objstorage) # move metadata in place db.content_add_from_temp(cur) if missing_skipped: missing_filtered = (cont for cont in content_without_data if _unique_key(cont) in missing_skipped) db.mktemp('skipped_content', cur) db.copy_to(missing_filtered, 'tmp_skipped_content', db.skipped_content_keys, cur) # move metadata in place db.skipped_content_add_from_temp(cur) @db_transaction def content_update(self, content, keys=[], cur=None): """Update content blobs to the storage. Does nothing for unknown contents or skipped ones. Args: content: iterable of dictionaries representing individual pieces of content to update. Each dictionary has the following keys: - data (bytes): the actual content - length (int): content length (default: -1) - one key for each checksum algorithm in swh.model.hashutil.ALGORITHMS, mapped to the corresponding checksum - status (str): one of visible, hidden, absent keys ([str]): List of keys whose values needs an update ( e.g. new hash column) """ db = self.db # TODO: Add a check on input keys. How to properly implement # this? We don't know yet the new columns. db.mktemp('content') select_keys = list(set(db.content_get_metadata_keys).union(set(keys))) db.copy_to(content, 'tmp_content', select_keys, cur) db.content_update_from_temp(keys_to_update=keys, cur=cur) def content_get(self, content): """Retrieve in bulk contents and their data. Args: content: iterables of sha1 Returns: Generates streams of contents as dict with their raw data: - sha1: sha1's content - data: bytes data of the content Raises: ValueError in case of too much contents are required. cf. BULK_BLOCK_CONTENT_LEN_MAX """ # FIXME: Improve on server module to slice the result if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise ValueError( "Send at maximum %s contents." % BULK_BLOCK_CONTENT_LEN_MAX) for obj_id in content: try: data = self.objstorage.get(obj_id) except ObjNotFoundError: yield None continue yield {'sha1': obj_id, 'data': data} @db_transaction_generator def content_get_metadata(self, content, cur=None): """Retrieve content metadata in bulk Args: content: iterable of content identifiers (sha1) Returns: an iterable with content metadata corresponding to the given ids """ db = self.db db.store_tmp_bytea(content, cur) for content_metadata in db.content_get_metadata_from_temp(cur): yield dict(zip(db.content_get_metadata_keys, content_metadata)) @db_transaction_generator def content_missing(self, content, key_hash='sha1', cur=None): """List content missing from storage Args: content: iterable of dictionaries containing one key for each checksum algorithm in swh.model.hashutil.ALGORITHMS, mapped to the corresponding checksum, and a length key mapped to the content length. key_hash: the name of the hash used as key (default: 'sha1') Returns: an iterable of `key_hash`es missing from the storage Raises: TODO: an exception when we get a hash collision. """ db = self.db keys = CONTENT_HASH_KEYS if key_hash not in CONTENT_HASH_KEYS: raise ValueError("key_hash should be one of %s" % keys) key_hash_idx = keys.index(key_hash) # Create temporary table for metadata injection db.mktemp('content', cur) db.copy_to(content, 'tmp_content', keys + ['length'], cur) for obj in db.content_missing_from_temp(cur): yield obj[key_hash_idx] @db_transaction_generator def content_missing_per_sha1(self, contents, cur=None): """List content missing from storage based only on sha1. Args: contents: Iterable of sha1 to check for absence. Returns: an iterable of `sha1`s missing from the storage. Raises: TODO: an exception when we get a hash collision. """ db = self.db db.store_tmp_bytea(contents, cur) for obj in db.content_missing_per_sha1_from_temp(cur): yield obj[0] @db_transaction_generator def skipped_content_missing(self, content, cur=None): """List skipped_content missing from storage Args: content: iterable of dictionaries containing the data for each checksum algorithm. Returns: an iterable of signatures missing from the storage """ keys = CONTENT_HASH_KEYS db = self.db db.mktemp('skipped_content', cur) db.copy_to(content, 'tmp_skipped_content', keys + ['length', 'reason'], cur) yield from db.skipped_content_missing_from_temp(cur) @db_transaction def content_find(self, content, cur=None): """Find a content hash in db. Args: content: a dictionary representing one content hash, mapping checksum algorithm names (see swh.model.hashutil.ALGORITHMS) to checksum values Returns: a triplet (sha1, sha1_git, sha256) if the content exist or None otherwise. Raises: ValueError in case the key of the dictionary is not sha1, sha1_git nor sha256. """ db = self.db if not set(content).intersection(ALGORITHMS): raise ValueError('content keys must contain at least one of: ' 'sha1, sha1_git, sha256, blake2s256') c = db.content_find(sha1=content.get('sha1'), sha1_git=content.get('sha1_git'), sha256=content.get('sha256'), blake2s256=content.get('blake2s256'), cur=cur) if c: return dict(zip(db.content_find_cols, c)) return None @db_transaction_generator def content_find_provenance(self, content, cur=None): """Find content's provenance information. Args: content: a dictionary entry representing one content hash. The dictionary key is one of swh.model.hashutil.ALGORITHMS. The value mapped to the corresponding checksum. Yields: The provenance information on content. """ db = self.db c = self.content_find(content) if not c: return [] sha1_git = c['sha1_git'] for provenance in db.content_find_provenance(sha1_git, cur=cur): yield dict(zip(db.provenance_cols, provenance)) def directory_add(self, directories): """Add directories to the storage Args: directories: iterable of dictionaries representing the individual directories to add. Each dict has the following keys: - id (sha1_git): the id of the directory to add - entries (list): list of dicts for each entry in the directory. Each dict has the following keys: - name (bytes) - type (one of 'file', 'dir', 'rev'): type of the directory entry (file, directory, revision) - target (sha1_git): id of the object pointed at by the directory entry - perms (int): entry permissions """ dirs = set() dir_entries = { 'file': defaultdict(list), 'dir': defaultdict(list), 'rev': defaultdict(list), } for cur_dir in directories: dir_id = cur_dir['id'] dirs.add(dir_id) for src_entry in cur_dir['entries']: entry = src_entry.copy() entry['dir_id'] = dir_id dir_entries[entry['type']][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs)) if not dirs_missing: return db = self.db with db.transaction() as cur: # Copy directory ids dirs_missing_dict = ({'id': dir} for dir in dirs_missing) db.mktemp('directory', cur) db.copy_to(dirs_missing_dict, 'tmp_directory', ['id'], cur) # Copy entries for entry_type, entry_list in dir_entries.items(): entries = itertools.chain.from_iterable( entries_for_dir for dir_id, entries_for_dir in entry_list.items() if dir_id in dirs_missing) db.mktemp_dir_entry(entry_type) db.copy_to( entries, 'tmp_directory_entry_%s' % entry_type, ['target', 'name', 'perms', 'dir_id'], cur, ) # Do the final copy db.directory_add_from_temp(cur) @db_transaction_generator def directory_missing(self, directories, cur): """List directories missing from storage Args: an iterable of directory ids Returns: a list of missing directory ids """ db = self.db # Create temporary table for metadata injection db.mktemp('directory', cur) directories_dicts = ({'id': dir} for dir in directories) db.copy_to(directories_dicts, 'tmp_directory', ['id'], cur) for obj in db.directory_missing_from_temp(cur): yield obj[0] @db_transaction_generator def directory_get(self, directories, cur=None): """Get information on directories. Args: - directories: an iterable of directory ids Returns: List of directories as dict with keys and associated values. """ db = self.db keys = ('id', 'dir_entries', 'file_entries', 'rev_entries') db.mktemp('directory', cur) db.copy_to(({'id': dir_id} for dir_id in directories), 'tmp_directory', ['id'], cur) dirs = db.directory_get_from_temp(cur) for line in dirs: yield dict(zip(keys, line)) @db_transaction_generator def directory_ls(self, directory, recursive=False, cur=None): """Get entries for one directory. Args: - directory: the directory to list entries from. - recursive: if flag on, this list recursively from this directory. Returns: List of entries for such directory. """ db = self.db if recursive: res_gen = db.directory_walk(directory, cur=cur) else: res_gen = db.directory_walk_one(directory, cur=cur) for line in res_gen: yield dict(zip(db.directory_ls_cols, line)) @db_transaction def directory_entry_get_by_path(self, directory, paths, cur=None): """Get the directory entry (either file or dir) from directory with path. Args: - directory: sha1 of the top level directory - paths: path to lookup from the top level directory. From left (top) to right (bottom). Returns: The corresponding directory entry if found, None otherwise. """ db = self.db res = db.directory_entry_get_by_path(directory, paths, cur) if res: return dict(zip(db.directory_ls_cols, res)) @db_transaction def cache_content_revision_add(self, revisions, cur=None): """Cache the current revision's current targeted arborescence directory. If the revision has already been cached, it just does nothing. Args: - revisions: the revisions to cache Returns: None """ db = self.db db.store_tmp_bytea(revisions, cur) db.cache_content_revision_add() @db_transaction_generator def cache_content_get_all(self, cur=None): """Read the distinct contents in the cache table. Yields: contents from cache """ for content in self.db.cache_content_get_all(cur): yield dict(zip(self.db.cache_content_get_cols, content)) @db_transaction def cache_content_get(self, content, cur=None): """Retrieve information on content. Args: content (dict): content with checkums Returns: Its properties (sha1, sha1_git, sha256, revision_paths) """ if 'sha1_git' in content: sha1_git = content['sha1_git'] else: c = self.content_find(content) if not c: return None sha1_git = c['sha1_git'] c = self.db.cache_content_get(sha1_git, cur=cur) if not c: return None return dict(zip(self.db.cache_content_get_cols, c)) @db_transaction_generator def cache_revision_origin_add(self, origin, visit, cur=None): """Cache the list of revisions the given visit added to the origin. Args: - origin: the id of the origin - visit: the id of the visit Returns: The list of new revisions """ for (revision,) in self.db.cache_revision_origin_add(origin, visit): yield revision def revision_add(self, revisions): """Add revisions to the storage Args: revisions: iterable of dictionaries representing the individual revisions to add. Each dict has the following keys: - id (sha1_git): id of the revision to add - date (datetime.DateTime): date the revision was written - date_offset (int): offset from UTC in minutes the revision was written - date_neg_utc_offset (boolean): whether a null date_offset represents a negative UTC offset - committer_date (datetime.DateTime): date the revision got added to the origin - committer_date_offset (int): offset from UTC in minutes the revision was added to the origin - committer_date_neg_utc_offset (boolean): whether a null committer_date_offset represents a negative UTC offset - type (one of 'git', 'tar'): type of the revision added - directory (sha1_git): the directory the revision points at - message (bytes): the message associated with the revision - author_name (bytes): the name of the revision author - author_email (bytes): the email of the revision author - committer_name (bytes): the name of the revision committer - committer_email (bytes): the email of the revision committer - metadata (jsonb): extra information as dictionary - synthetic (bool): revision's nature (tarball, directory creates synthetic revision) - parents (list of sha1_git): the parents of this revision """ db = self.db revisions_missing = set(self.revision_missing( set(revision['id'] for revision in revisions))) if not revisions_missing: return with db.transaction() as cur: db.mktemp_revision(cur) revisions_filtered = ( converters.revision_to_db(revision) for revision in revisions if revision['id'] in revisions_missing) parents_filtered = [] db.copy_to( revisions_filtered, 'tmp_revision', db.revision_add_cols, cur, lambda rev: parents_filtered.extend(rev['parents'])) db.revision_add_from_temp(cur) db.copy_to(parents_filtered, 'revision_history', ['id', 'parent_id', 'parent_rank'], cur) @db_transaction_generator def revision_missing(self, revisions, cur=None): """List revisions missing from storage Args: an iterable of revision ids Returns: a list of missing revision ids """ db = self.db db.store_tmp_bytea(revisions, cur) for obj in db.revision_missing_from_temp(cur): yield obj[0] @db_transaction_generator def revision_get(self, revisions, cur): """Get all revisions from storage Args: an iterable of revision ids Returns: an iterable of revisions as dictionaries (or None if the revision doesn't exist) """ db = self.db db.store_tmp_bytea(revisions, cur) for line in self.db.revision_get_from_temp(cur): data = converters.db_to_revision( dict(zip(db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data @db_transaction_generator def revision_log(self, revisions, limit=None, cur=None): """Fetch revision entry from the given root revisions. Args: - revisions: array of root revision to lookup - limit: limitation on the output result. Default to null. Yields: List of revision log from such revisions root. """ db = self.db for line in db.revision_log(revisions, limit, cur): data = converters.db_to_revision( dict(zip(db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data @db_transaction_generator def revision_shortlog(self, revisions, limit=None, cur=None): """Fetch the shortlog for the given revisions Args: revisions: list of root revisions to lookup limit: depth limitation for the output Yields: a list of (id, parents) tuples. """ db = self.db yield from db.revision_shortlog(revisions, limit, cur) @db_transaction_generator def revision_log_by(self, origin_id, branch_name=None, timestamp=None, limit=None, cur=None): """Fetch revision entry from the actual origin_id's latest revision. Args: - origin_id: the origin id from which deriving the revision - branch_name: (optional) occurrence's branch name - timestamp: (optional) occurrence's time - limit: (optional) depth limitation for the output. Default to None. Yields: The revision log starting from the revision derived from the (origin, branch_name, timestamp) combination if any. Returns the [] if no revision matching this combination is found. """ db = self.db # Retrieve the revision by criterion revisions = list(db.revision_get_by( origin_id, branch_name, timestamp, limit=1)) if not revisions: return None revision_id = revisions[0][0] # otherwise, retrieve the revision log from that revision yield from self.revision_log([revision_id], limit) def release_add(self, releases): """Add releases to the storage Args: releases: iterable of dictionaries representing the individual releases to add. Each dict has the following keys: - id (sha1_git): id of the release to add - revision (sha1_git): id of the revision the release points to - date (datetime.DateTime): the date the release was made - date_offset (int): offset from UTC in minutes the release was made - date_neg_utc_offset (boolean): whether a null date_offset represents a negative UTC offset - name (bytes): the name of the release - comment (bytes): the comment associated with the release - author_name (bytes): the name of the release author - author_email (bytes): the email of the release author """ db = self.db release_ids = set(release['id'] for release in releases) releases_missing = set(self.release_missing(release_ids)) if not releases_missing: return with db.transaction() as cur: db.mktemp_release(cur) releases_filtered = ( converters.release_to_db(release) for release in releases if release['id'] in releases_missing ) db.copy_to(releases_filtered, 'tmp_release', db.release_add_cols, cur) db.release_add_from_temp(cur) @db_transaction_generator def release_missing(self, releases, cur=None): """List releases missing from storage Args: an iterable of release ids Returns: a list of missing release ids """ db = self.db # Create temporary table for metadata injection db.store_tmp_bytea(releases, cur) for obj in db.release_missing_from_temp(cur): yield obj[0] @db_transaction_generator def release_get(self, releases, cur=None): """Given a list of sha1, return the releases's information Args: releases: list of sha1s Returns: Generates the list of releases dict with the following keys: - id: origin's id - revision: origin's type - url: origin's url - lister: lister's uuid - project: project's uuid (FIXME, retrieve this information) Raises: ValueError if the keys does not match (url and type) nor id. """ db = self.db # Create temporary table for metadata injection db.store_tmp_bytea(releases, cur) for release in db.release_get_from_temp(cur): yield converters.db_to_release( dict(zip(db.release_get_cols, release)) ) @db_transaction def occurrence_add(self, occurrences, cur=None): """Add occurrences to the storage Args: occurrences: iterable of dictionaries representing the individual occurrences to add. Each dict has the following keys: - origin (int): id of the origin corresponding to the occurrence - branch (str): the reference name of the occurrence - target (sha1_git): the id of the object pointed to by the occurrence - target_type (str): the type of object pointed to by the occurrence """ db = self.db db.mktemp_occurrence_history(cur) db.copy_to(occurrences, 'tmp_occurrence_history', ['origin', 'branch', 'target', 'target_type', 'visit'], cur) db.occurrence_history_add_from_temp(cur) @db_transaction_generator def occurrence_get(self, origin_id, cur=None): """Retrieve occurrence information per origin_id. Args: origin_id: The occurrence's origin. Yields: List of occurrences matching criterion. """ db = self.db for line in db.occurrence_get(origin_id, cur): yield { 'origin': line[0], 'branch': line[1], 'target': line[2], 'target_type': line[3], } @db_transaction def origin_visit_add(self, origin, ts, cur=None): """Add an origin_visit for the origin at ts with status 'ongoing'. Args: origin: Visited Origin id ts: timestamp of such visit Returns: Dict with keys origin and visit where: - origin: origin identifier - visit: the visit identifier for the new visit occurrence - ts (datetime.DateTime): the visit date """ if isinstance(ts, str): ts = dateutil.parser.parse(ts) return { 'origin': origin, 'visit': self.db.origin_visit_add(origin, ts, cur) } @db_transaction def origin_visit_update(self, origin, visit_id, status, metadata=None, cur=None): """Update an origin_visit's status. Args: origin: Visited Origin id visit_id: Visit's id status: Visit's new status metadata: Data associated to the visit Returns: None """ return self.db.origin_visit_update(origin, visit_id, status, metadata, cur) @db_transaction_generator def origin_visit_get(self, origin, last_visit=None, limit=None, cur=None): """Retrieve all the origin's visit's information. Args: origin (int): The occurrence's origin (identifier). last_visit (int): Starting point from which listing the next visits Default to None limit (int): Number of results to return from the last visit. Default to None Yields: List of visits. """ db = self.db for line in db.origin_visit_get_all( origin, last_visit=last_visit, limit=limit, cur=cur): data = dict(zip(self.db.origin_visit_get_cols, line)) yield data @db_transaction def origin_visit_get_by(self, origin, visit, cur=None): """Retrieve origin visit's information. Args: origin: The occurrence's origin (identifier). Returns: The information on that particular (origin, visit) """ db = self.db ori_visit = db.origin_visit_get(origin, visit, cur) if not ori_visit: return None ori_visit = dict(zip(self.db.origin_visit_get_cols, ori_visit)) occs = {} for occ in db.occurrence_by_origin_visit(origin, visit): _, branch_name, target, target_type = occ occs[branch_name] = { 'target': target, 'target_type': target_type } ori_visit.update({ 'occurrences': occs }) return ori_visit @db_transaction_generator def revision_get_by(self, origin_id, branch_name=None, timestamp=None, limit=None, cur=None): """Given an origin_id, retrieve occurrences' list per given criterions. Args: origin_id: The origin to filter on. branch_name: (optional) branch name. timestamp: (optional) time. limit: (optional) limit Yields: List of occurrences matching the criterions or None if nothing is found. """ for line in self.db.revision_get_by(origin_id, branch_name, timestamp, limit=limit, cur=cur): data = converters.db_to_revision( dict(zip(self.db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data def release_get_by(self, origin_id, limit=None): """Given an origin id, return all the tag objects pointing to heads of origin_id. Args: origin_id: the origin to filter on. limit: None by default Yields: List of releases matching the criterions or None if nothing is found. """ for line in self.db.release_get_by(origin_id, limit=limit): data = converters.db_to_release( dict(zip(self.db.release_get_cols, line)) ) yield data @db_transaction def object_find_by_sha1_git(self, ids, cur=None): """Return the objects found with the given ids. Args: ids: a generator of sha1_gits Returns: a dict mapping the id to the list of objects found. Each object found is itself a dict with keys: sha1_git: the input id type: the type of object found id: the id of the object found object_id: the numeric id of the object found. """ db = self.db ret = {id: [] for id in ids} for retval in db.object_find_by_sha1_git(ids): if retval[1]: ret[retval[0]].append(dict(zip(db.object_find_by_sha1_git_cols, retval))) return ret @db_transaction def origin_get(self, origin, cur=None): """Return the origin either identified by its id or its tuple (type, url). Args: origin: dictionary representing the individual origin to find. This dict has either the keys type and url: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to either the id: - id: the origin id Returns: the origin dict with the keys: - id: origin's id - type: origin's type - url: origin's url - lister: lister's uuid - project: project's uuid (FIXME, retrieve this information) Raises: ValueError if the keys does not match (url and type) nor id. """ db = self.db keys = ['id', 'type', 'url', 'lister', 'project'] origin_id = origin.get('id') if origin_id: # check lookup per id first ori = db.origin_get(origin_id, cur) elif 'type' in origin and 'url' in origin: # or lookup per type, url ori = db.origin_get_with(origin['type'], origin['url'], cur) else: # unsupported lookup raise ValueError('Origin must have either id or (type and url).') if ori: return dict(zip(keys, ori)) return None @db_transaction def _person_add(self, person, cur=None): """Add a person in storage. BEWARE: Internal function for now. Do not do anything fancy in case a person already exists. Please adapt code if more checks are needed. Args: person dictionary with keys name and email. Returns: Id of the new person. """ db = self.db return db.person_add(person) @db_transaction_generator def person_get(self, person, cur=None): """Return the persons identified by their ids. Args: person: array of ids. Returns: The array of persons corresponding of the ids. """ db = self.db for person in db.person_get(person): yield dict(zip(db.person_get_cols, person)) @db_transaction def origin_add(self, origins, cur=None): """Add origins to the storage Args: origins: list of dictionaries representing the individual origins, with the following keys: type: the origin type ('git', 'svn', 'deb', ...) url (bytes): the url the origin points to Returns: The array of ids corresponding to the given origins """ ret = [] for origin in origins: ret.append(self.origin_add_one(origin, cur=cur)) return ret @db_transaction def origin_add_one(self, origin, cur=None): """Add origin to the storage Args: origin: dictionary representing the individual origin to add. This dict has the following keys: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to Returns: the id of the added origin, or of the identical one that already exists. """ db = self.db data = db.origin_get_with(origin['type'], origin['url'], cur) if data: return data[0] return db.origin_add(origin['type'], origin['url'], cur) @db_transaction def fetch_history_start(self, origin_id, cur=None): """Add an entry for origin origin_id in fetch_history. Returns the id of the added fetch_history entry """ fetch_history = { 'origin': origin_id, 'date': datetime.datetime.now(tz=datetime.timezone.utc), } return self.db.create_fetch_history(fetch_history, cur) @db_transaction def fetch_history_end(self, fetch_history_id, data, cur=None): """Close the fetch_history entry with id `fetch_history_id`, replacing its data with `data`. """ now = datetime.datetime.now(tz=datetime.timezone.utc) fetch_history = self.db.get_fetch_history(fetch_history_id, cur) if not fetch_history: raise ValueError('No fetch_history with id %d' % fetch_history_id) fetch_history['duration'] = now - fetch_history['date'] fetch_history.update(data) self.db.update_fetch_history(fetch_history, cur) @db_transaction def fetch_history_get(self, fetch_history_id, cur=None): """Get the fetch_history entry with id `fetch_history_id`. """ return self.db.get_fetch_history(fetch_history_id, cur) @db_transaction def entity_add(self, entities, cur=None): """Add the given entitites to the database (in entity_history). Args: - entities: iterable of dictionaries containing the following keys: - uuid (uuid): id of the entity - parent (uuid): id of the parent entity - name (str): name of the entity - type (str): type of entity (one of 'organization', 'group_of_entities', 'hosting', 'group_of_persons', 'person', 'project') - description (str, optional): description of the entity - homepage (str): url of the entity's homepage - active (bool): whether the entity is active - generated (bool): whether the entity was generated - lister_metadata (dict): lister-specific entity metadata - metadata (dict): other metadata for the entity - validity (datetime.DateTime array): timestamps at which we listed the entity. """ db = self.db cols = list(db.entity_history_cols) cols.remove('id') db.mktemp_entity_history() db.copy_to(entities, 'tmp_entity_history', cols, cur) db.entity_history_add_from_temp() @db_transaction_generator def entity_get_from_lister_metadata(self, entities, cur=None): """Fetch entities from the database, matching with the lister and associated metadata. Args: entities: iterable of dictionaries containing the lister metadata to look for. Useful keys are 'lister', 'type', 'id', ... Returns: A generator of fetched entities with all their attributes. If no match was found, the returned entity is None. """ db = self.db db.mktemp_entity_lister(cur) mapped_entities = [] for i, entity in enumerate(entities): mapped_entity = { 'id': i, 'lister_metadata': entity, } mapped_entities.append(mapped_entity) db.copy_to(mapped_entities, 'tmp_entity_lister', ['id', 'lister_metadata'], cur) cur.execute('''select id, %s from swh_entity_from_tmp_entity_lister() order by id''' % ','.join(db.entity_cols)) for id, *entity_vals in cur: fetched_entity = dict(zip(db.entity_cols, entity_vals)) if fetched_entity['uuid']: yield fetched_entity else: yield { 'uuid': None, 'lister_metadata': entities[i], } @db_transaction_generator def entity_get(self, uuid, cur=None): """Returns the list of entity per its uuid identifier and also its parent hierarchy. Args: uuid: entity's identifier Returns: List of entities starting with entity with uuid and the parent hierarchy from such entity. """ db = self.db for entity in db.entity_get(uuid, cur): yield dict(zip(db.entity_cols, entity)) @db_transaction def entity_get_one(self, uuid, cur=None): """Returns one entity using its uuid identifier. Args: uuid: entity's identifier Returns: the object corresponding to the given entity """ db = self.db entity = db.entity_get_one(uuid, cur) if entity: return dict(zip(db.entity_cols, entity)) else: return None @db_transaction def stat_counters(self, cur=None): """compute statistics about the number of tuples in various tables Returns: a dictionary mapping textual labels (e.g., content) to integer values (e.g., the number of tuples in table content) """ return {k: v for (k, v) in self.db.stat_counters()} @db_transaction_generator def content_mimetype_missing(self, mimetypes, cur=None): """List mimetypes missing from storage. Args: mimetypes: iterable of dict with keys: - id (bytes): sha1 identifier - tool_name (str): tool used to compute the results - tool_version (str): associated tool's version Returns: an iterable of missing id for the triplets id, tool_name, tool_version """ db = self.db db.mktemp_content_mimetype_missing(cur) db.copy_to(mimetypes, 'tmp_content_mimetype_missing', ['id', 'indexer_configuration_id'], cur) for obj in db.content_mimetype_missing_from_temp(cur): yield obj[0] @db_transaction def content_mimetype_add(self, mimetypes, conflict_update=False, cur=None): """Add mimetypes not present in storage. Args: mimetypes: iterable of dictionary 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: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ db = self.db 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) @db_transaction_generator def content_mimetype_get(self, ids, cur=None): db = self.db db.store_tmp_bytea(ids, cur) for c in db.content_mimetype_get_from_temp(): yield converters.db_to_mimetype( dict(zip(db.content_mimetype_cols, c))) @db_transaction_generator def content_language_missing(self, languages, cur=None): """List languages missing from storage. Args: languages: iterable of dict with keys: - id (bytes): sha1 identifier - tool_name (str): tool used to compute the results - tool_version (str): associated tool's version Returns: an iterable of missing id """ db = self.db db.mktemp_content_language_missing(cur) db.copy_to(languages, 'tmp_content_language_missing', ['id', 'indexer_configuration_id'], cur) for obj in db.content_language_missing_from_temp(cur): yield obj[0] @db_transaction_generator def content_language_get(self, ids, cur=None): db = self.db db.store_tmp_bytea(ids, cur) for c in db.content_language_get_from_temp(): yield converters.db_to_language( dict(zip(db.content_language_cols, c))) @db_transaction def content_language_add(self, languages, conflict_update=False, cur=None): """Add languages not present in storage. Args: languages: iterable of dictionary with keys: - id: sha1 - lang: bytes conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ db = self.db 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) @db_transaction_generator def content_ctags_missing(self, ctags, cur=None): """List ctags missing from storage. Args: ctags: iterable of dict with keys: - id (bytes): sha1 identifier - tool_name (str): tool name used - tool_version (str): associated version Returns: an iterable of missing id """ db = self.db db.mktemp_content_ctags_missing(cur) db.copy_to(ctags, tblname='tmp_content_ctags_missing', columns=['id', 'indexer_configuration_id'], cur=cur) for obj in db.content_ctags_missing_from_temp(cur): yield obj[0] @db_transaction_generator def content_ctags_get(self, ids, cur=None): """Retrieve ctags per id. Args: ids ([sha1]): Iterable of sha1 """ db = self.db db.store_tmp_bytea(ids, cur) for c in db.content_ctags_get_from_temp(): yield converters.db_to_ctags(dict(zip(db.content_ctags_cols, c))) @db_transaction def content_ctags_add(self, ctags, conflict_update=False, cur=None): """Add ctags not present in storage Args: ctags: iterable of dictionaries with keys: - id (bytes): sha1 - ctags ([dict]): List of dictionary with keys (name, kind, line, language) """ db = self.db 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) @db_transaction_generator def content_ctags_search(self, expression, limit=10, last_sha1=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... """ db = self.db 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))) @db_transaction_generator def content_fossology_license_get(self, ids, cur=None): """Retrieve licenses per id. Args: ids ([sha1]): Iterable of sha1 Yields: List of dict with the following keys: - id (bytes) - licenses ([str]): associated licenses for that content """ db = self.db db.store_tmp_bytea(ids, cur) for c in db.content_fossology_license_get_from_temp(): license = dict(zip(db.content_fossology_license_cols, c)) yield converters.db_to_fossology_license(license) @db_transaction def content_fossology_license_add(self, licenses, conflict_update=False, cur=None): """Add licenses not present in storage. Args: licenses ([dict]): iterable of dict with keys: - id: sha1 - license ([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 of content_license entries which failed due to unknown licenses """ db = self.db # Then, we add the correct ones 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) @db_transaction_generator def content_metadata_missing(self, metadatas, cur=None): """List metadatas missing from storage. Args: metadatas: iterable of dict with keys: - id (bytes): sha1 identifier - tool_name (str): tool used to compute the results - tool_version (str): associated tool's version Returns: an iterable of missing id """ db = self.db db.mktemp_content_metadata_missing(cur) db.copy_to(metadatas, 'tmp_content_metadata_missing', ['id', 'indexer_configuration_id'], cur) for obj in db.content_metadata_missing_from_temp(cur): yield obj[0] @db_transaction_generator def content_metadata_get(self, ids, cur=None): db = self.db db.store_tmp_bytea(ids, cur) for c in db.content_metadata_get_from_temp(): yield converters.db_to_metadata( dict(zip(db.content_metadata_cols, c))) @db_transaction def content_metadata_add(self, metadatas, conflict_update=False, cur=None): """Add metadatas not present in storage. Args: metadatas: iterable of dictionary with keys: - id: sha1 - translated_metadata: bytes / jsonb ? conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ db = self.db db.mktemp_content_metadata(cur) # empty metadata is mapped to 'unknown' - db.copy_to( - ({ - 'id': m['id'], - 'translated_metadata': m['translated_metadata'], - 'indexer_configuration_id': m['indexer_configuration_id'], - } for m in metadatas), - 'tmp_content_metadata', - ['id', 'translated_metadata', 'indexer_configuration_id'], cur) + db.copy_to(metadatas, 'tmp_content_metadata', + ['id', 'translated_metadata', 'indexer_configuration_id'], + cur) db.content_metadata_add_from_temp(conflict_update, cur) @db_transaction def indexer_configuration_get(self, tool, cur=None): db = self.db 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(self.db.indexer_configuration_cols, idx)) diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index d8a86c8ad..06f6148a3 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,3344 +1,3344 @@ # Copyright (C) 2015-2017 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import copy import datetime from operator import itemgetter import os import psycopg2 import shutil import tempfile import unittest from uuid import UUID from unittest.mock import patch from nose.tools import istest from nose.plugins.attrib import attr from swh.core.tests.db_testing import DbTestFixture from swh.model import identifiers from swh.model.hashutil import hash_to_bytes from swh.storage import get_storage from swh.storage.db import cursor_to_bytes TEST_DIR = os.path.dirname(os.path.abspath(__file__)) TEST_DATA_DIR = os.path.join(TEST_DIR, '../../../../swh-storage-testdata') @attr('db') class BaseTestStorage(DbTestFixture): TEST_DB_DUMP = os.path.join(TEST_DATA_DIR, 'dumps/swh.dump') def setUp(self): super().setUp() self.maxDiff = None self.objroot = tempfile.mkdtemp() storage_conf = { 'cls': 'local', 'args': { 'db': self.conn, 'objstorage': { 'cls': 'pathslicing', 'args': { 'root': self.objroot, 'slicing': '0:2/2:4/4:6', }, }, }, } self.storage = get_storage(**storage_conf) self.cont = { 'data': b'42\n', 'length': 3, 'sha1': hash_to_bytes( '34973274ccef6ab4dfaaf86599792fa9c3fe4689'), 'sha1_git': hash_to_bytes( 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), 'sha256': hash_to_bytes( '673650f936cb3b0a2f93ce09d81be107' '48b1b203c19e8176b4eefc1964a0cf3a'), 'blake2s256': hash_to_bytes('d5fe1939576527e42cfd76a9455a2' '432fe7f56669564577dd93c4280e76d661d'), 'status': 'visible', } self.cont2 = { 'data': b'4242\n', 'length': 5, 'sha1': hash_to_bytes( '61c2b3a30496d329e21af70dd2d7e097046d07b7'), 'sha1_git': hash_to_bytes( '36fade77193cb6d2bd826161a0979d64c28ab4fa'), 'sha256': hash_to_bytes( '859f0b154fdb2d630f45e1ecae4a8629' '15435e663248bb8461d914696fc047cd'), 'blake2s256': hash_to_bytes('849c20fad132b7c2d62c15de310adfe87be' '94a379941bed295e8141c6219810d'), 'status': 'visible', } self.cont3 = { 'data': b'424242\n', 'length': 7, 'sha1': hash_to_bytes( '3e21cc4942a4234c9e5edd8a9cacd1670fe59f13'), 'sha1_git': hash_to_bytes( 'c932c7649c6dfa4b82327d121215116909eb3bea'), 'sha256': hash_to_bytes( '92fb72daf8c6818288a35137b72155f5' '07e5de8d892712ab96277aaed8cf8a36'), 'blake2s256': hash_to_bytes('76d0346f44e5a27f6bafdd9c2befd304af' 'f83780f93121d801ab6a1d4769db11'), 'status': 'visible', } self.missing_cont = { 'data': b'missing\n', 'length': 8, 'sha1': hash_to_bytes( 'f9c24e2abb82063a3ba2c44efd2d3c797f28ac90'), 'sha1_git': hash_to_bytes( '33e45d56f88993aae6a0198013efa80716fd8919'), 'sha256': hash_to_bytes( '6bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes('306856b8fd879edb7b6f1aeaaf8db9bbecc9' '93cd7f776c333ac3a782fa5c6eba'), 'status': 'absent', } self.skipped_cont = { 'length': 1024 * 1024 * 200, 'sha1_git': hash_to_bytes( '33e45d56f88993aae6a0198013efa80716fd8920'), 'sha1': hash_to_bytes( '43e45d56f88993aae6a0198013efa80716fd8920'), 'sha256': hash_to_bytes( '7bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes( 'ade18b1adecb33f891ca36664da676e1' '2c772cc193778aac9a137b8dc5834b9b'), 'reason': 'Content too long', 'status': 'absent', } self.skipped_cont2 = { 'length': 1024 * 1024 * 300, 'sha1_git': hash_to_bytes( '44e45d56f88993aae6a0198013efa80716fd8921'), 'sha1': hash_to_bytes( '54e45d56f88993aae6a0198013efa80716fd8920'), 'sha256': hash_to_bytes( '8cbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes( '9ce18b1adecb33f891ca36664da676e1' '2c772cc193778aac9a137b8dc5834b9b'), 'reason': 'Content too long', 'status': 'absent', } self.dir = { 'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa90', 'entries': [ { 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': 0o644, }, { 'name': b'bar\xc3', 'type': 'dir', 'target': b'12345678901234567890', 'perms': 0o2000, }, ], } self.dir2 = { 'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa95', 'entries': [ { 'name': b'oof', 'type': 'file', 'target': self.cont2['sha1_git'], 'perms': 0o644, } ], } self.dir3 = { 'id': hash_to_bytes('33e45d56f88993aae6a0198013efa80716fd8921'), 'entries': [ { 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': 0o644, }, { 'name': b'bar', 'type': 'dir', 'target': b'12345678901234560000', 'perms': 0o2000, }, { 'name': b'hello', 'type': 'file', 'target': b'12345678901234567890', 'perms': 0o644, }, ], } self.minus_offset = datetime.timezone(datetime.timedelta(minutes=-120)) self.plus_offset = datetime.timezone(datetime.timedelta(minutes=120)) self.revision = { 'id': b'56789012345678901234', 'message': b'hello', 'author': { 'name': b'Nicolas Dandrimont', 'email': b'nicolas@example.com', 'fullname': b'Nicolas Dandrimont ', }, 'date': { 'timestamp': 1234567890, 'offset': 120, 'negative_utc': None, }, 'committer': { 'name': b'St\xc3fano Zacchiroli', 'email': b'stefano@example.com', 'fullname': b'St\xc3fano Zacchiroli ' }, 'committer_date': { 'timestamp': 1123456789, 'offset': 0, 'negative_utc': True, }, 'parents': [b'01234567890123456789', b'23434512345123456789'], 'type': 'git', 'directory': self.dir['id'], 'metadata': { 'checksums': { 'sha1': 'tarball-sha1', 'sha256': 'tarball-sha256', }, 'signed-off-by': 'some-dude', 'extra_headers': [ ['gpgsig', b'test123'], ['mergetags', [b'foo\\bar', b'\x22\xaf\x89\x80\x01\x00']], ], }, 'synthetic': True } self.revision2 = { 'id': b'87659012345678904321', 'message': b'hello again', 'author': { 'name': b'Roberto Dicosmo', 'email': b'roberto@example.com', 'fullname': b'Roberto Dicosmo ', }, 'date': { 'timestamp': { 'seconds': 1234567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'committer_date': { 'timestamp': 1123456789, 'offset': 0, 'negative_utc': False, }, 'parents': [b'01234567890123456789'], 'type': 'git', 'directory': self.dir2['id'], 'metadata': None, 'synthetic': False } self.revision3 = { 'id': hash_to_bytes('7026b7c1a2af56521e951c01ed20f255fa054238'), 'message': b'a simple revision with no parents this time', 'author': { 'name': b'Roberto Dicosmo', 'email': b'roberto@example.com', 'fullname': b'Roberto Dicosmo ', }, 'date': { 'timestamp': { 'seconds': 1234567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'committer_date': { 'timestamp': 1127351742, 'offset': 0, 'negative_utc': False, }, 'parents': [], 'type': 'git', 'directory': self.dir2['id'], 'metadata': None, 'synthetic': True } self.revision4 = { 'id': hash_to_bytes('368a48fe15b7db2383775f97c6b247011b3f14f4'), 'message': b'parent of self.revision2', 'author': { 'name': b'me', 'email': b'me@soft.heri', 'fullname': b'me ', }, 'date': { 'timestamp': { 'seconds': 1244567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'committer-dude', 'email': b'committer@dude.com', 'fullname': b'committer-dude ', }, 'committer_date': { 'timestamp': { 'seconds': 1244567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'parents': [self.revision3['id']], 'type': 'git', 'directory': self.dir['id'], 'metadata': None, 'synthetic': False } self.origin = { 'url': 'file:///dev/null', 'type': 'git', } self.origin2 = { 'url': 'file:///dev/zero', 'type': 'git', } self.date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.occurrence = { 'branch': b'master', 'target': b'67890123456789012345', 'target_type': 'revision', } self.date_visit2 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.occurrence2 = { 'branch': b'master', 'target': self.revision2['id'], 'target_type': 'revision', } self.date_visit3 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) # template occurrence to be filled in test (cf. revision_log_by) self.occurrence3 = { 'branch': b'master', 'target_type': 'revision', } self.release = { 'id': b'87659012345678901234', 'name': b'v0.0.1', 'author': { 'name': b'olasd', 'email': b'nic@olasd.fr', 'fullname': b'olasd ', }, 'date': { 'timestamp': 1234567890, 'offset': 42, 'negative_utc': None, }, 'target': b'43210987654321098765', 'target_type': 'revision', 'message': b'synthetic release', 'synthetic': True, } self.release2 = { 'id': b'56789012348765901234', 'name': b'v0.0.2', 'author': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'date': { 'timestamp': 1634366813, 'offset': -120, 'negative_utc': None, }, 'target': b'432109\xa9765432\xc309\x00765', 'target_type': 'revision', 'message': b'v0.0.2\nMisc performance improvments + bug fixes', 'synthetic': False } self.release3 = { 'id': b'87659012345678904321', 'name': b'v0.0.2', 'author': { 'name': b'tony', 'email': b'tony@ardumont.fr', 'fullname': b'tony ', }, 'date': { 'timestamp': 1634336813, 'offset': 0, 'negative_utc': False, }, 'target': self.revision2['id'], 'target_type': 'revision', 'message': b'yet another synthetic release', 'synthetic': True, } self.fetch_history_date = datetime.datetime( 2015, 1, 2, 21, 0, 0, tzinfo=datetime.timezone.utc) self.fetch_history_end = datetime.datetime( 2015, 1, 2, 23, 0, 0, tzinfo=datetime.timezone.utc) self.fetch_history_duration = (self.fetch_history_end - self.fetch_history_date) self.fetch_history_data = { 'status': True, 'result': {'foo': 'bar'}, 'stdout': 'blabla', 'stderr': 'blablabla', } self.entity1 = { 'uuid': UUID('f96a7ec1-0058-4920-90cc-7327e4b5a4bf'), # GitHub users 'parent': UUID('ad6df473-c1d2-4f40-bc58-2b091d4a750e'), 'name': 'github:user:olasd', 'type': 'person', 'description': 'Nicolas Dandrimont', 'homepage': 'http://example.com', 'active': True, 'generated': True, 'lister_metadata': { # swh.lister.github 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 12877, 'type': 'user', 'last_activity': '2015-11-03', }, 'metadata': None, 'validity': [ datetime.datetime(2015, 11, 3, 11, 0, 0, tzinfo=datetime.timezone.utc), ] } self.entity1_query = { 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 12877, 'type': 'user', } self.entity2 = { 'uuid': UUID('3903d075-32d6-46d4-9e29-0aef3612c4eb'), # GitHub users 'parent': UUID('ad6df473-c1d2-4f40-bc58-2b091d4a750e'), 'name': 'github:user:zacchiro', 'type': 'person', 'description': 'Stefano Zacchiroli', 'homepage': 'http://example.com', 'active': True, 'generated': True, 'lister_metadata': { # swh.lister.github 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 216766, 'type': 'user', 'last_activity': '2015-11-03', }, 'metadata': None, 'validity': [ datetime.datetime(2015, 11, 3, 11, 0, 0, tzinfo=datetime.timezone.utc), ] } self.entity3 = { 'uuid': UUID('111df473-c1d2-4f40-bc58-2b091d4a7111'), # GitHub users 'parent': UUID('222df473-c1d2-4f40-bc58-2b091d4a7222'), 'name': 'github:user:ardumont', 'type': 'person', 'description': 'Antoine R. Dumont a.k.a tony', 'homepage': 'https://ardumont.github.io', 'active': True, 'generated': True, 'lister_metadata': { 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 666, 'type': 'user', 'last_activity': '2016-01-15', }, 'metadata': None, 'validity': [ datetime.datetime(2015, 11, 3, 11, 0, 0, tzinfo=datetime.timezone.utc), ] } self.entity4 = { 'uuid': UUID('222df473-c1d2-4f40-bc58-2b091d4a7222'), # GitHub users 'parent': None, 'name': 'github:user:ToNyX', 'type': 'person', 'description': 'ToNyX', 'homepage': 'https://ToNyX.github.io', 'active': True, 'generated': True, 'lister_metadata': { 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 999, 'type': 'user', 'last_activity': '2015-12-24', }, 'metadata': None, 'validity': [ datetime.datetime(2015, 11, 3, 11, 0, 0, tzinfo=datetime.timezone.utc), ] } self.entity2_query = { 'lister_metadata': { 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 216766, 'type': 'user', }, } def tearDown(self): shutil.rmtree(self.objroot) self.cursor.execute("""SELECT table_name FROM information_schema.tables WHERE table_schema = %s""", ('public',)) tables = set(table for (table,) in self.cursor.fetchall()) tables -= {'dbversion', 'entity', 'entity_history', 'listable_entity', 'fossology_license', 'indexer_configuration'} for table in tables: self.cursor.execute('truncate table %s cascade' % table) self.cursor.execute('delete from entity where generated=true') self.cursor.execute('delete from entity_history where generated=true') self.conn.commit() super().tearDown() def fetch_tools(self): tools = {} self.cursor.execute('''select tool_name, id, tool_version, tool_configuration from indexer_configuration''') for row in self.cursor.fetchall(): tools[row[0]] = { 'id': row[1], 'name': row[0], 'version': row[2], 'configuration': row[3] } return tools class CommonTestStorage(BaseTestStorage): """Base class for Storage testing. This class is used as-is to test local storage (see TestStorage below) and remote storage (see TestRemoteStorage in test_remote_storage.py. We need to have the two classes inherit from this base class separately to avoid nosetests running the tests from the base class twice. """ @staticmethod def normalize_entity(entity): entity = copy.deepcopy(entity) for key in ('date', 'committer_date'): if key in entity: entity[key] = identifiers.normalize_timestamp(entity[key]) return entity @istest def check_config(self): self.assertTrue(self.storage.check_config(check_write=True)) self.assertTrue(self.storage.check_config(check_write=False)) @istest def content_add(self): cont = self.cont self.storage.content_add([cont]) if hasattr(self.storage, 'objstorage'): self.assertIn(cont['sha1'], self.storage.objstorage) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = self.cursor.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) @istest def content_add_collision(self): cont1 = self.cont # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() sha256_array = bytearray(cont1b['sha256']) sha256_array[0] += 1 cont1b['sha256'] = bytes(sha256_array) with self.assertRaises(psycopg2.IntegrityError): self.storage.content_add([cont1, cont1b]) @istest def skipped_content_add(self): cont = self.skipped_cont.copy() cont2 = self.skipped_cont2.copy() cont2['blake2s256'] = None self.storage.content_add([cont, cont, cont2]) self.cursor.execute('SELECT sha1, sha1_git, sha256, blake2s256, ' 'length, status, reason ' 'FROM skipped_content ORDER BY sha1_git') datums = self.cursor.fetchall() self.assertEquals(2, len(datums)) datum = datums[0] self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3].tobytes(), datum[4], datum[5], datum[6]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['blake2s256'], cont['length'], 'absent', 'Content too long') ) datum2 = datums[1] self.assertEqual( (datum2[0].tobytes(), datum2[1].tobytes(), datum2[2].tobytes(), datum2[3], datum2[4], datum2[5], datum2[6]), (cont2['sha1'], cont2['sha1_git'], cont2['sha256'], cont2['blake2s256'], cont2['length'], 'absent', 'Content too long') ) @istest def content_missing(self): cont2 = self.cont2 missing_cont = self.missing_cont self.storage.content_add([cont2]) gen = self.storage.content_missing([cont2, missing_cont]) self.assertEqual(list(gen), [missing_cont['sha1']]) @istest def content_missing_per_sha1(self): # given cont2 = self.cont2 missing_cont = self.missing_cont self.storage.content_add([cont2]) # when gen = self.storage.content_missing_per_sha1([cont2['sha1'], missing_cont['sha1']]) # then self.assertEqual(list(gen), [missing_cont['sha1']]) @istest def content_get_metadata(self): cont1 = self.cont.copy() cont2 = self.cont2.copy() self.storage.content_add([cont1, cont2]) gen = self.storage.content_get_metadata([cont1['sha1'], cont2['sha1']]) # we only retrieve the metadata cont1.pop('data') cont2.pop('data') self.assertEqual(list(gen), [cont1, cont2]) @istest def content_get_metadata_missing_sha1(self): cont1 = self.cont.copy() cont2 = self.cont2.copy() missing_cont = self.missing_cont.copy() self.storage.content_add([cont1, cont2]) gen = self.storage.content_get_metadata([missing_cont['sha1']]) # All the metadata keys are None missing_cont.pop('data') for key in list(missing_cont): if key != 'sha1': missing_cont[key] = None self.assertEqual(list(gen), [missing_cont]) @istest def directory_get(self): # given init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) self.storage.directory_add([self.dir]) # when actual_dirs = list(self.storage.directory_get([self.dir['id']])) self.assertEqual(len(actual_dirs), 1) dir0 = actual_dirs[0] self.assertEqual(dir0['id'], self.dir['id']) # ids are generated so non deterministic value self.assertEqual(len(dir0['file_entries']), 1) self.assertEqual(len(dir0['dir_entries']), 1) self.assertIsNone(dir0['rev_entries']) after_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([], after_missing) @istest def directory_add(self): init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) self.storage.directory_add([self.dir]) stored_data = list(self.storage.directory_ls(self.dir['id'])) data_to_store = [] for ent in sorted(self.dir['entries'], key=itemgetter('name')): data_to_store.append({ 'dir_id': self.dir['id'], 'type': ent['type'], 'target': ent['target'], 'name': ent['name'], 'perms': ent['perms'], 'status': None, 'sha1': None, 'sha1_git': None, 'sha256': None, 'length': None, }) self.assertEqual(data_to_store, stored_data) after_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([], after_missing) @istest def directory_entry_get_by_path(self): # given init_missing = list(self.storage.directory_missing([self.dir3['id']])) self.assertEqual([self.dir3['id']], init_missing) self.storage.directory_add([self.dir3]) expected_entries = [ { 'dir_id': self.dir3['id'], 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': 0o644, 'length': None, }, { 'dir_id': self.dir3['id'], 'name': b'bar', 'type': 'dir', 'target': b'12345678901234560000', 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': 0o2000, 'length': None, }, { 'dir_id': self.dir3['id'], 'name': b'hello', 'type': 'file', 'target': b'12345678901234567890', 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': 0o644, 'length': None, }, ] # when (all must be found here) for entry, expected_entry in zip(self.dir3['entries'], expected_entries): actual_entry = self.storage.directory_entry_get_by_path( self.dir3['id'], [entry['name']]) self.assertEqual(actual_entry, expected_entry) # when (nothing should be found here since self.dir is not persisted.) for entry in self.dir['entries']: actual_entry = self.storage.directory_entry_get_by_path( self.dir['id'], [entry['name']]) self.assertIsNone(actual_entry) @istest def revision_add(self): init_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([self.revision['id']], list(init_missing)) self.storage.revision_add([self.revision]) end_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([], list(end_missing)) def cache_content_revision_objects(self): self.storage.content_add([self.cont, self.cont2, self.cont3]) directory = { 'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa90', 'entries': [ { 'name': b'bar', 'type': 'file', 'target': self.cont2['sha1_git'], 'perms': 0o644, }, { 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': 0o644, }, { 'name': b'bar\xc3', 'type': 'dir', 'target': b'12345678901234567890', 'perms': 0o2000, }, ], } directory2 = copy.deepcopy(directory) directory2['id'] = (directory2['id'][:-1] + bytes([(directory2['id'][-1] + 1) % 256])) directory2['entries'][1] = { 'name': b'foo', 'type': 'file', 'target': self.cont3['sha1_git'], 'perms': 0o644, } self.storage.directory_add([directory, directory2]) revision = self.revision.copy() revision['directory'] = directory['id'] revision2 = copy.deepcopy(revision) revision2['parents'] = [revision['id']] revision2['directory'] = directory2['id'] revision2['id'] = (revision2['id'][:-1] + bytes([(revision2['id'][-1] + 1) % 256])) self.storage.revision_add([revision, revision2]) return (directory, directory2, revision, revision2) @istest def cache_content_revision_add(self): # Create a real arborescence tree (contents + directory) and a # revision targeting that directory. # Assert the cache is empty for that revision # Then create that revision # Trigger the cache population for that revision # Assert the cache now contains information for that revision # Trigger again the cache population for that revision # Assert the cache is not modified # given () (directory, directory2, revision, revision2) = self.cache_content_revision_objects() # assert nothing in cache yet count_query = '''select count(*) from cache_content_revision''' self.cursor.execute(count_query) ret = self.cursor.fetchone() self.assertEqual(ret, (0, )) # when, triggered the first time, we cache the revision self.storage.cache_content_revision_add([revision['id']]) # the second time, we do nothing as this is already done self.storage.cache_content_revision_add([revision['id']]) # then self.cursor.execute(count_query) ret = self.cursor.fetchone() # only 2 contents exists for that revision (the second call to # revision_cache discards as the revision is already cached) self.assertEqual(ret, (2, )) self.cursor.execute('select * from cache_content_revision') ret = self.cursor.fetchall() expected_cache_entries = [ (directory['entries'][0]['target'], False, [[revision['id'], directory['entries'][0]['name']]]), (directory['entries'][1]['target'], False, [[revision['id'], directory['entries'][1]['name']]]) ] for i, expected_entry in enumerate(expected_cache_entries): ret_entry = (ret[i][0].tobytes(), ret[i][1], [[ret[i][2][0][0].tobytes(), ret[i][2][0][1].tobytes()]]) self.assertEquals(ret_entry, expected_entry) @istest def cache_content_revision_add_twice(self): # given () (directory, directory2, revision, revision2) = self.cache_content_revision_objects() # assert nothing in cache yet count_query = '''select count(*) from cache_content_revision''' self.cursor.execute(count_query) ret = self.cursor.fetchone() self.assertEqual(ret, (0, )) # when, triggered the first time, we cache the revision self.storage.cache_content_revision_add([revision['id']]) # the second time, we do nothing as this is already done self.storage.cache_content_revision_add([revision2['id']]) # then self.cursor.execute('select * from cache_content_revision') cache_entries = { content.tobytes(): [[rev.tobytes(), path.tobytes()] for rev, path in rev_paths] for content, blacklisted, rev_paths in self.cursor.fetchall() } self.assertEquals(len(cache_entries), 3) self.assertEquals(len(cache_entries[self.cont['sha1_git']]), 1) self.assertEquals(len(cache_entries[self.cont2['sha1_git']]), 2) self.assertEquals(len(cache_entries[self.cont3['sha1_git']]), 1) @istest def cache_content_get_all(self): # given (directory, directory2, revision, revision2) = self.cache_content_revision_objects() # assert nothing in cache yet test_query = '''select sha1, sha1_git, sha256, ccr.revision_paths from cache_content_revision ccr inner join content c on c.sha1_git=ccr.content''' self.storage.cache_content_revision_add([revision['id']]) self.cursor.execute(test_query, (revision['id'],)) ret = list(cursor_to_bytes(self.cursor)) self.assertEqual(len(ret), 2) expected_contents = [] for entry in ret: expected_contents.append(dict( zip(['sha1', 'sha1_git', 'sha256', 'revision_paths'], entry))) # 1. default filters gives everything actual_cache_contents = list(self.storage.cache_content_get_all()) self.assertEquals(actual_cache_contents, expected_contents) @istest def cache_content_get(self): # given (directory, directory2, revision, revision2) = self.cache_content_revision_objects() # assert nothing in cache yet test_query = '''select c.sha1, c.sha1_git, c.sha256, ccr.revision_paths from cache_content_revision ccr inner join content c on c.sha1_git=ccr.content where ccr.content=%s''' self.storage.cache_content_revision_add([revision['id']]) self.cursor.execute(test_query, (self.cont2['sha1_git'],)) ret = list(cursor_to_bytes(self.cursor))[0] self.assertIsNotNone(ret) expected_content = dict( zip(['sha1', 'sha1_git', 'sha256', 'revision_paths'], ret)) # when actual_cache_content = self.storage.cache_content_get(self.cont2) # then self.assertEquals(actual_cache_content, expected_content) @istest def revision_log(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) # when actual_results = list(self.storage.revision_log( [self.revision4['id']])) # hack: ids generated for actual_result in actual_results: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3 self.assertEquals(actual_results[0], self.normalize_entity(self.revision4)) self.assertEquals(actual_results[1], self.normalize_entity(self.revision3)) @istest def revision_log_with_limit(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) actual_results = list(self.storage.revision_log( [self.revision4['id']], 1)) # hack: ids generated for actual_result in actual_results: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEqual(len(actual_results), 1) self.assertEquals(actual_results[0], self.revision4) @istest def revision_log_by(self): # given origin_id = self.storage.origin_add_one(self.origin2) self.storage.revision_add([self.revision3, self.revision4]) # occurrence3 targets 'revision4' # with branch 'master' and origin origin_id occurrence3 = self.occurrence3.copy() date_visit1 = self.date_visit3 origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1) occurrence3.update({ 'origin': origin_id, 'target': self.revision4['id'], 'visit': origin_visit1['visit'], }) self.storage.occurrence_add([occurrence3]) # self.revision4 -is-child-of-> self.revision3 # when actual_results = list(self.storage.revision_log_by( origin_id, branch_name=occurrence3['branch'], timestamp=date_visit1)) # hack: ids generated for actual_result in actual_results: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEqual(len(actual_results), 2) self.assertEquals(actual_results[0], self.normalize_entity(self.revision4)) self.assertEquals(actual_results[1], self.normalize_entity(self.revision3)) # when - 2 actual_results = list(self.storage.revision_log_by( origin_id, branch_name=None, timestamp=None, limit=1)) # then for actual_result in actual_results: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEqual(len(actual_results), 1) self.assertEquals(actual_results[0], self.revision4) # when - 3 (revision not found) actual_res = list(self.storage.revision_log_by( origin_id, branch_name='inexistant-branch', timestamp=None)) self.assertEquals(actual_res, []) @staticmethod def _short_revision(revision): return [revision['id'], revision['parents']] @istest def revision_shortlog(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) # when actual_results = list(self.storage.revision_shortlog( [self.revision4['id']])) self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3 self.assertEquals(list(actual_results[0]), self._short_revision(self.revision4)) self.assertEquals(list(actual_results[1]), self._short_revision(self.revision3)) @istest def revision_shortlog_with_limit(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) actual_results = list(self.storage.revision_shortlog( [self.revision4['id']], 1)) self.assertEqual(len(actual_results), 1) self.assertEquals(list(actual_results[0]), self._short_revision(self.revision4)) @istest def revision_get(self): self.storage.revision_add([self.revision]) actual_revisions = list(self.storage.revision_get( [self.revision['id'], self.revision2['id']])) # when del actual_revisions[0]['author']['id'] # hack: ids are generated del actual_revisions[0]['committer']['id'] self.assertEqual(len(actual_revisions), 2) self.assertEqual(actual_revisions[0], self.normalize_entity(self.revision)) self.assertIsNone(actual_revisions[1]) @istest def revision_get_no_parents(self): self.storage.revision_add([self.revision3]) get = list(self.storage.revision_get([self.revision3['id']])) self.assertEqual(len(get), 1) self.assertEqual(get[0]['parents'], []) # no parents on this one @istest def revision_get_by(self): # given self.storage.content_add([self.cont2]) self.storage.directory_add([self.dir2]) # point to self.cont self.storage.revision_add([self.revision2]) # points to self.dir origin_id = self.storage.origin_add_one(self.origin2) # occurrence2 points to 'revision2' with branch 'master', we # need to point to the right origin occurrence2 = self.occurrence2.copy() date_visit1 = self.date_visit2 origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1) occurrence2.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], }) self.storage.occurrence_add([occurrence2]) # we want only revision 2 expected_revisions = list(self.storage.revision_get( [self.revision2['id']])) # when actual_results = list(self.storage.revision_get_by( origin_id, occurrence2['branch'], None)) self.assertEqual(actual_results[0], expected_revisions[0]) # when (with no branch filtering, it's still ok) actual_results = list(self.storage.revision_get_by( origin_id, None, None)) self.assertEqual(actual_results[0], expected_revisions[0]) @istest def revision_get_by_multiple_occurrence(self): # 2 occurrences pointing to 2 different revisions # each occurence have 1 day delta # the api must return the revision whose occurrence is the nearest. # given self.storage.content_add([self.cont2]) self.storage.directory_add([self.dir2]) self.storage.revision_add([self.revision2, self.revision3]) origin_id = self.storage.origin_add_one(self.origin2) # occurrence2 points to 'revision2' with branch 'master', we # need to point to the right origin date_visit1 = self.date_visit2 origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1) occurrence2 = self.occurrence2.copy() occurrence2.update({ 'origin': origin_id, 'visit': origin_visit1['visit'] }) dt = datetime.timedelta(days=1) date_visit2 = date_visit1 + dt origin_visit2 = self.storage.origin_visit_add(origin_id, date_visit2) occurrence3 = self.occurrence2.copy() occurrence3.update({ 'origin': origin_id, 'visit': origin_visit2['visit'], 'target': self.revision3['id'], }) # 2 occurrences on same revision with lower validity date with 1 day # delta self.storage.occurrence_add([occurrence2]) self.storage.occurrence_add([occurrence3]) # when actual_results0 = list(self.storage.revision_get_by( origin_id, occurrence2['branch'], date_visit1)) # hack: ids are generated del actual_results0[0]['author']['id'] del actual_results0[0]['committer']['id'] self.assertEquals(len(actual_results0), 1) self.assertEqual(actual_results0, [self.normalize_entity(self.revision2)]) # when actual_results1 = list(self.storage.revision_get_by( origin_id, occurrence2['branch'], date_visit1 + dt/3)) # closer to first visit # hack: ids are generated del actual_results1[0]['author']['id'] del actual_results1[0]['committer']['id'] self.assertEquals(len(actual_results1), 1) self.assertEqual(actual_results1, [self.normalize_entity(self.revision2)]) # when actual_results2 = list(self.storage.revision_get_by( origin_id, occurrence2['branch'], date_visit1 + 2*dt/3)) # closer to second visit del actual_results2[0]['author']['id'] del actual_results2[0]['committer']['id'] self.assertEquals(len(actual_results2), 1) self.assertEqual(actual_results2, [self.normalize_entity(self.revision3)]) # when actual_results3 = list(self.storage.revision_get_by( origin_id, occurrence3['branch'], date_visit2)) # hack: ids are generated del actual_results3[0]['author']['id'] del actual_results3[0]['committer']['id'] self.assertEquals(len(actual_results3), 1) self.assertEqual(actual_results3, [self.normalize_entity(self.revision3)]) # when actual_results4 = list(self.storage.revision_get_by( origin_id, None, None)) for actual_result in actual_results4: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEquals(len(actual_results4), 1) self.assertCountEqual(actual_results4, [self.normalize_entity(self.revision3)]) @istest def release_add(self): init_missing = self.storage.release_missing([self.release['id'], self.release2['id']]) self.assertEqual([self.release['id'], self.release2['id']], list(init_missing)) self.storage.release_add([self.release, self.release2]) end_missing = self.storage.release_missing([self.release['id'], self.release2['id']]) self.assertEqual([], list(end_missing)) @istest def release_get(self): # given self.storage.release_add([self.release, self.release2]) # when actual_releases = list(self.storage.release_get([self.release['id'], self.release2['id']])) # then for actual_release in actual_releases: del actual_release['author']['id'] # hack: ids are generated self.assertEquals([self.normalize_entity(self.release), self.normalize_entity(self.release2)], [actual_releases[0], actual_releases[1]]) @istest def release_get_by(self): # given self.storage.revision_add([self.revision2]) # points to self.dir self.storage.release_add([self.release3]) origin_id = self.storage.origin_add_one(self.origin2) # occurrence2 points to 'revision2' with branch 'master', we # need to point to the right origin origin_visit = self.storage.origin_visit_add(origin_id, self.date_visit2) occurrence2 = self.occurrence2.copy() occurrence2.update({ 'origin': origin_id, 'visit': origin_visit['visit'], }) self.storage.occurrence_add([occurrence2]) # we want only revision 2 expected_releases = list(self.storage.release_get( [self.release3['id']])) # when actual_results = list(self.storage.release_get_by( occurrence2['origin'])) # then self.assertEqual(actual_results[0], expected_releases[0]) @istest def origin_add_one(self): origin0 = self.storage.origin_get(self.origin) self.assertIsNone(origin0) id = self.storage.origin_add_one(self.origin) actual_origin = self.storage.origin_get({'url': self.origin['url'], 'type': self.origin['type']}) self.assertEqual(actual_origin['id'], id) id2 = self.storage.origin_add_one(self.origin) self.assertEqual(id, id2) @istest def origin_add(self): origin0 = self.storage.origin_get(self.origin) self.assertIsNone(origin0) id1, id2 = self.storage.origin_add([self.origin, self.origin2]) actual_origin = self.storage.origin_get({ 'url': self.origin['url'], 'type': self.origin['type'], }) self.assertEqual(actual_origin['id'], id1) actual_origin2 = self.storage.origin_get({ 'url': self.origin2['url'], 'type': self.origin2['type'], }) self.assertEqual(actual_origin2['id'], id2) @istest def origin_add_twice(self): add1 = self.storage.origin_add([self.origin, self.origin2]) add2 = self.storage.origin_add([self.origin, self.origin2]) self.assertEqual(add1, add2) @istest def origin_get(self): self.assertIsNone(self.storage.origin_get(self.origin)) id = self.storage.origin_add_one(self.origin) # lookup per type and url (returns id) actual_origin0 = self.storage.origin_get({'url': self.origin['url'], 'type': self.origin['type']}) self.assertEqual(actual_origin0['id'], id) # lookup per id (returns dict) actual_origin1 = self.storage.origin_get({'id': id}) self.assertEqual(actual_origin1, {'id': id, 'type': self.origin['type'], 'url': self.origin['url'], 'lister': None, 'project': None}) @istest def origin_visit_add(self): # given self.assertIsNone(self.storage.origin_get(self.origin2)) origin_id = self.storage.origin_add_one(self.origin2) self.assertIsNotNone(origin_id) # when origin_visit1 = self.storage.origin_visit_add( origin_id, ts=self.date_visit2) # then self.assertEquals(origin_visit1['origin'], origin_id) self.assertIsNotNone(origin_visit1['visit']) self.assertTrue(origin_visit1['visit'] > 0) actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEquals(actual_origin_visits, [{ 'origin': origin_id, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'ongoing', 'metadata': None, }]) @istest def origin_visit_update(self): # given origin_id = self.storage.origin_add_one(self.origin2) origin_id2 = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add( origin_id, ts=self.date_visit2) origin_visit2 = self.storage.origin_visit_add( origin_id, ts=self.date_visit3) origin_visit3 = self.storage.origin_visit_add( origin_id2, ts=self.date_visit3) # when visit1_metadata = { 'contents': 42, 'directories': 22, } self.storage.origin_visit_update( origin_id, origin_visit1['visit'], status='full', metadata=visit1_metadata) self.storage.origin_visit_update(origin_id2, origin_visit3['visit'], status='partial') # then actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEquals(actual_origin_visits, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'full', 'metadata': visit1_metadata, }, { 'origin': origin_visit2['origin'], 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'status': 'ongoing', 'metadata': None, }]) actual_origin_visits_bis = list(self.storage.origin_visit_get( origin_id, limit=1)) self.assertEquals(actual_origin_visits_bis, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'full', 'metadata': visit1_metadata, }]) actual_origin_visits_ter = list(self.storage.origin_visit_get( origin_id, last_visit=origin_visit1['visit'])) self.assertEquals(actual_origin_visits_ter, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'status': 'ongoing', 'metadata': None, }]) actual_origin_visits2 = list(self.storage.origin_visit_get(origin_id2)) self.assertEquals(actual_origin_visits2, [{ 'origin': origin_visit3['origin'], 'date': self.date_visit3, 'visit': origin_visit3['visit'], 'status': 'partial', 'metadata': None, }]) @istest def origin_visit_get_by(self): origin_id = self.storage.origin_add_one(self.origin2) origin_id2 = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add( origin_id, ts=self.date_visit2) occurrence2 = self.occurrence2.copy() occurrence2.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], }) self.storage.occurrence_add([occurrence2]) # Add some other {origin, visit} entries self.storage.origin_visit_add(origin_id, ts=self.date_visit3) self.storage.origin_visit_add(origin_id2, ts=self.date_visit3) # when visit1_metadata = { 'contents': 42, 'directories': 22, } self.storage.origin_visit_update( origin_id, origin_visit1['visit'], status='full', metadata=visit1_metadata) expected_origin_visit = origin_visit1.copy() expected_origin_visit.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], 'date': self.date_visit2, 'metadata': visit1_metadata, 'status': 'full', 'occurrences': { occurrence2['branch']: { 'target': occurrence2['target'], 'target_type': occurrence2['target_type'], } } }) # when actual_origin_visit1 = self.storage.origin_visit_get_by( origin_visit1['origin'], origin_visit1['visit']) # then self.assertEquals(actual_origin_visit1, expected_origin_visit) @istest def origin_visit_get_by_no_result(self): # No result actual_origin_visit = self.storage.origin_visit_get_by( 10, 999) self.assertIsNone(actual_origin_visit) @istest def occurrence_add(self): occur = self.occurrence.copy() origin_id = self.storage.origin_add_one(self.origin2) date_visit1 = self.date_visit1 origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1) revision = self.revision.copy() revision['id'] = occur['target'] self.storage.revision_add([revision]) occur.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], }) self.storage.occurrence_add([occur]) test_query = ''' with indiv_occurrences as ( select origin, branch, target, target_type, unnest(visits) as visit from occurrence_history ) select origin, branch, target, target_type, date from indiv_occurrences left join origin_visit using(origin, visit) order by origin, date''' self.cursor.execute(test_query) ret = self.cursor.fetchall() self.assertEqual(len(ret), 1) self.assertEqual( (ret[0][0], ret[0][1].tobytes(), ret[0][2].tobytes(), ret[0][3], ret[0][4]), (occur['origin'], occur['branch'], occur['target'], occur['target_type'], self.date_visit1)) date_visit2 = date_visit1 + datetime.timedelta(hours=10) origin_visit2 = self.storage.origin_visit_add(origin_id, date_visit2) occur2 = occur.copy() occur2.update({ 'visit': origin_visit2['visit'], }) self.storage.occurrence_add([occur2]) self.cursor.execute(test_query) ret = self.cursor.fetchall() self.assertEqual(len(ret), 2) self.assertEqual( (ret[0][0], ret[0][1].tobytes(), ret[0][2].tobytes(), ret[0][3], ret[0][4]), (occur['origin'], occur['branch'], occur['target'], occur['target_type'], date_visit1)) self.assertEqual( (ret[1][0], ret[1][1].tobytes(), ret[1][2].tobytes(), ret[1][3], ret[1][4]), (occur2['origin'], occur2['branch'], occur2['target'], occur2['target_type'], date_visit2)) @istest def occurrence_get(self): # given occur = self.occurrence.copy() origin_id = self.storage.origin_add_one(self.origin2) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) revision = self.revision.copy() revision['id'] = occur['target'] self.storage.revision_add([revision]) occur.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], }) self.storage.occurrence_add([occur]) self.storage.occurrence_add([occur]) # when actual_occurrence = list(self.storage.occurrence_get(origin_id)) # then expected_occurrence = self.occurrence.copy() expected_occurrence.update({ 'origin': origin_id }) self.assertEquals(len(actual_occurrence), 1) self.assertEquals(actual_occurrence[0], expected_occurrence) def _trigger_cache_provenance(self, origin_visit): """Trigger cache population for cache_content_revision. """ ret = list(self.storage.cache_revision_origin_add( origin_visit['origin'], origin_visit['visit'], )) for revision_id in ret: self.storage.cache_content_revision_add([revision_id]) return ret @istest def content_find_provenance_with_present_content(self): # 1. with something to find # given origin_id = self.storage.origin_add_one(self.origin2) self.storage.content_add([self.cont2]) self.storage.directory_add([self.dir2]) # point to self.cont self.storage.revision_add([self.revision3]) # points to self.dir occurrence = self.occurrence3.copy() occurrence['target'] = self.revision3['id'] origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit2) occurrence.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], }) self.storage.occurrence_add([occurrence]) # Trigger cache population for cache_content_revision cached_revisions = self._trigger_cache_provenance(origin_visit1) self.assertIn(self.revision3['id'], cached_revisions) # when occs = list(self.storage.content_find_provenance( {'sha1': self.cont2['sha1']})) # then self.assertEquals(len(occs), 1) self.assertEquals(occs[0]['origin'], origin_visit1['origin']) self.assertEquals(occs[0]['visit'], origin_visit1['visit']) self.assertEquals(occs[0]['revision'], self.revision3['id']) self.assertEquals(occs[0]['path'], self.dir2['entries'][0]['name']) occs2 = list(self.storage.content_find_provenance( {'sha1_git': self.cont2['sha1_git']})) self.assertEquals(len(occs2), 1) self.assertEquals(occs2[0]['origin'], origin_visit1['origin']) self.assertEquals(occs2[0]['visit'], origin_visit1['visit']) self.assertEquals(occs2[0]['revision'], self.revision3['id']) self.assertEquals(occs2[0]['path'], self.dir2['entries'][0]['name']) occs3 = list(self.storage.content_find_provenance( {'sha256': self.cont2['sha256']})) self.assertEquals(len(occs3), 1) self.assertEquals(occs3[0]['origin'], origin_visit1['origin']) self.assertEquals(occs3[0]['visit'], origin_visit1['visit']) self.assertEquals(occs3[0]['revision'], self.revision3['id']) self.assertEquals(occs3[0]['path'], self.dir2['entries'][0]['name']) @istest def content_find_provenance_with_non_present_content(self): # 1. with something that does not exist missing_cont = self.missing_cont occ = list(self.storage.content_find_provenance( {'sha1': missing_cont['sha1']})) self.assertEquals(occ, [], "Content does not exist so no occurrence") # 2. with something that does not exist occ = list(self.storage.content_find_provenance( {'sha1_git': missing_cont['sha1_git']})) self.assertEquals(occ, [], "Content does not exist so no occurrence") # 3. with something that does not exist occ = list(self.storage.content_find_provenance( {'sha256': missing_cont['sha256']})) self.assertEquals(occ, [], "Content does not exist so no occurrence") @istest def content_find_occurrence_bad_input(self): # 1. with bad input with self.assertRaises(ValueError) as cm: list(self.storage.content_find_provenance({})) # empty is bad self.assertIn('content keys', cm.exception.args[0]) # 2. with bad input with self.assertRaises(ValueError) as cm: list(self.storage.content_find_provenance( {'unknown-sha1': 'something'})) # not the right key self.assertIn('content keys', cm.exception.args[0]) @istest def entity_get_from_lister_metadata(self): self.storage.entity_add([self.entity1]) fetched_entities = list( self.storage.entity_get_from_lister_metadata( [self.entity1_query, self.entity2_query])) # Entity 1 should have full metadata, with last_seen/last_id instead # of validity entity1 = self.entity1.copy() entity1['last_seen'] = entity1['validity'][0] del fetched_entities[0]['last_id'] del entity1['validity'] # Entity 2 should have no metadata entity2 = { 'uuid': None, 'lister_metadata': self.entity2_query.copy(), } self.assertEquals(fetched_entities, [entity1, entity2]) @istest def entity_get_from_lister_metadata_twice(self): self.storage.entity_add([self.entity1]) fetched_entities1 = list( self.storage.entity_get_from_lister_metadata( [self.entity1_query])) fetched_entities2 = list( self.storage.entity_get_from_lister_metadata( [self.entity1_query])) self.assertEquals(fetched_entities1, fetched_entities2) @istest def entity_get(self): # given self.storage.entity_add([self.entity4]) self.storage.entity_add([self.entity3]) # when: entity3 -child-of-> entity4 actual_entity3 = list(self.storage.entity_get(self.entity3['uuid'])) self.assertEquals(len(actual_entity3), 2) # remove dynamic data (modified by db) entity3 = self.entity3.copy() entity4 = self.entity4.copy() del entity3['validity'] del entity4['validity'] del actual_entity3[0]['last_seen'] del actual_entity3[0]['last_id'] del actual_entity3[1]['last_seen'] del actual_entity3[1]['last_id'] self.assertEquals(actual_entity3, [entity3, entity4]) # when: entity4 only child actual_entity4 = list(self.storage.entity_get(self.entity4['uuid'])) self.assertEquals(len(actual_entity4), 1) # remove dynamic data (modified by db) entity4 = self.entity4.copy() del entity4['validity'] del actual_entity4[0]['last_id'] del actual_entity4[0]['last_seen'] self.assertEquals(actual_entity4, [entity4]) @istest def entity_get_one(self): # given self.storage.entity_add([self.entity3, self.entity4]) # when: entity3 -child-of-> entity4 actual_entity3 = self.storage.entity_get_one(self.entity3['uuid']) # remove dynamic data (modified by db) entity3 = self.entity3.copy() del entity3['validity'] del actual_entity3['last_seen'] del actual_entity3['last_id'] self.assertEquals(actual_entity3, entity3) @istest def stat_counters(self): expected_keys = ['content', 'directory', 'directory_entry_dir', 'occurrence', 'origin', 'person', 'revision'] counters = self.storage.stat_counters() self.assertTrue(set(expected_keys) <= set(counters)) self.assertIsInstance(counters[expected_keys[0]], int) @istest def content_find_with_present_content(self): # 1. with something to find cont = self.cont self.storage.content_add([cont]) actually_present = self.storage.content_find({'sha1': cont['sha1']}) actually_present.pop('ctime') self.assertEqual(actually_present, { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' }) # 2. with something to find actually_present = self.storage.content_find( {'sha1_git': cont['sha1_git']}) actually_present.pop('ctime') self.assertEqual(actually_present, { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' }) # 3. with something to find actually_present = self.storage.content_find( {'sha256': cont['sha256']}) actually_present.pop('ctime') self.assertEqual(actually_present, { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' }) # 4. with something to find actually_present = self.storage.content_find({ 'sha1': cont['sha1'], 'sha1_git': cont['sha1_git'], 'sha256': cont['sha256'], 'blake2s256': cont['blake2s256'], }) actually_present.pop('ctime') self.assertEqual(actually_present, { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' }) @istest def content_find_with_non_present_content(self): # 1. with something that does not exist missing_cont = self.missing_cont actually_present = self.storage.content_find( {'sha1': missing_cont['sha1']}) self.assertIsNone(actually_present) # 2. with something that does not exist actually_present = self.storage.content_find( {'sha1_git': missing_cont['sha1_git']}) self.assertIsNone(actually_present) # 3. with something that does not exist actually_present = self.storage.content_find( {'sha256': missing_cont['sha256']}) self.assertIsNone(actually_present) @istest def content_find_bad_input(self): # 1. with bad input with self.assertRaises(ValueError): self.storage.content_find({}) # empty is bad # 2. with bad input with self.assertRaises(ValueError): self.storage.content_find( {'unknown-sha1': 'something'}) # not the right key @istest def object_find_by_sha1_git(self): sha1_gits = [b'00000000000000000000'] expected = { b'00000000000000000000': [], } self.storage.content_add([self.cont]) sha1_gits.append(self.cont['sha1_git']) expected[self.cont['sha1_git']] = [{ 'sha1_git': self.cont['sha1_git'], 'type': 'content', 'id': self.cont['sha1'], }] self.storage.directory_add([self.dir]) sha1_gits.append(self.dir['id']) expected[self.dir['id']] = [{ 'sha1_git': self.dir['id'], 'type': 'directory', 'id': self.dir['id'], }] self.storage.revision_add([self.revision]) sha1_gits.append(self.revision['id']) expected[self.revision['id']] = [{ 'sha1_git': self.revision['id'], 'type': 'revision', 'id': self.revision['id'], }] self.storage.release_add([self.release]) sha1_gits.append(self.release['id']) expected[self.release['id']] = [{ 'sha1_git': self.release['id'], 'type': 'release', 'id': self.release['id'], }] ret = self.storage.object_find_by_sha1_git(sha1_gits) for val in ret.values(): for obj in val: del obj['object_id'] self.assertEqual(expected, ret) @istest def content_mimetype_missing(self): # given tools = self.fetch_tools() tool_id = tools['file']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) mimetypes = [ { 'id': self.cont2['sha1'], 'indexer_configuration_id': tool_id, }, { 'id': self.missing_cont['sha1'], 'indexer_configuration_id': tool_id, }] # when actual_missing = self.storage.content_mimetype_missing(mimetypes) # then self.assertEqual(list(actual_missing), [ self.cont2['sha1'], self.missing_cont['sha1'] ]) # given self.storage.content_mimetype_add([{ 'id': self.cont2['sha1'], 'mimetype': b'text/plain', 'encoding': b'utf-8', 'indexer_configuration_id': tool_id, }]) # when actual_missing = self.storage.content_mimetype_missing(mimetypes) # then self.assertEqual(list(actual_missing), [self.missing_cont['sha1']]) @istest def content_mimetype_add__drop_duplicate(self): # given tools = self.fetch_tools() tool_id = tools['file']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) mimetype_v1 = { 'id': self.cont2['sha1'], 'mimetype': b'text/plain', 'encoding': b'utf-8', 'indexer_configuration_id': tool_id, } # given self.storage.content_mimetype_add([mimetype_v1]) # when actual_mimetypes = list(self.storage.content_mimetype_get( [self.cont2['sha1']])) # then expected_mimetypes_v1 = [{ 'id': self.cont2['sha1'], 'mimetype': b'text/plain', 'encoding': b'utf-8', 'tool': tools['file'], }] self.assertEqual(actual_mimetypes, expected_mimetypes_v1) # given mimetype_v2 = mimetype_v1.copy() mimetype_v2.update({ 'mimetype': b'text/html', 'encoding': b'us-ascii', }) self.storage.content_mimetype_add([mimetype_v2]) actual_mimetypes = list(self.storage.content_mimetype_get( [self.cont2['sha1']])) # mimetype did not change as the v2 was dropped. self.assertEqual(actual_mimetypes, expected_mimetypes_v1) @istest def content_mimetype_add__update_in_place_duplicate(self): # given tools = self.fetch_tools() tool_id = tools['file']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) mimetype_v1 = { 'id': self.cont2['sha1'], 'mimetype': b'text/plain', 'encoding': b'utf-8', 'indexer_configuration_id': tool_id, } # given self.storage.content_mimetype_add([mimetype_v1]) # when actual_mimetypes = list(self.storage.content_mimetype_get( [self.cont2['sha1']])) expected_mimetypes_v1 = [{ 'id': self.cont2['sha1'], 'mimetype': b'text/plain', 'encoding': b'utf-8', 'tool': tools['file'], }] # then self.assertEqual(actual_mimetypes, expected_mimetypes_v1) # given mimetype_v2 = mimetype_v1.copy() mimetype_v2.update({ 'mimetype': b'text/html', 'encoding': b'us-ascii', }) self.storage.content_mimetype_add([mimetype_v2], conflict_update=True) actual_mimetypes = list(self.storage.content_mimetype_get( [self.cont2['sha1']])) expected_mimetypes_v2 = [{ 'id': self.cont2['sha1'], 'mimetype': b'text/html', 'encoding': b'us-ascii', 'tool': { 'id': 2, 'name': 'file', 'version': '5.22', 'configuration': {'command_line': 'file --mime '} } }] # mimetype did change as the v2 was used to overwrite v1 self.assertEqual(actual_mimetypes, expected_mimetypes_v2) @istest def content_mimetype_get(self): # given tools = self.fetch_tools() tool_id = tools['file']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) mimetypes = [self.cont2['sha1'], self.missing_cont['sha1']] mimetype1 = { 'id': self.cont2['sha1'], 'mimetype': b'text/plain', 'encoding': b'utf-8', 'indexer_configuration_id': tool_id, } # when self.storage.content_mimetype_add([mimetype1]) # then actual_mimetypes = list(self.storage.content_mimetype_get(mimetypes)) # then expected_mimetypes = [{ 'id': self.cont2['sha1'], 'mimetype': b'text/plain', 'encoding': b'utf-8', 'tool': tools['file'] }] self.assertEqual(actual_mimetypes, expected_mimetypes) @istest def content_language_missing(self): # given tools = self.fetch_tools() tool_id = tools['pygments']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) languages = [ { 'id': self.cont2['sha1'], 'indexer_configuration_id': tool_id, }, { 'id': self.missing_cont['sha1'], 'indexer_configuration_id': tool_id, } ] # when actual_missing = list(self.storage.content_language_missing(languages)) # then self.assertEqual(list(actual_missing), [ self.cont2['sha1'], self.missing_cont['sha1'], ]) # given self.storage.content_language_add([{ 'id': self.cont2['sha1'], 'lang': 'haskell', 'indexer_configuration_id': tool_id, }]) # when actual_missing = list(self.storage.content_language_missing(languages)) # then self.assertEqual(actual_missing, [self.missing_cont['sha1']]) @istest def content_language_get(self): # given tools = self.fetch_tools() tool_id = tools['pygments']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) language1 = { 'id': self.cont2['sha1'], 'lang': 'common-lisp', 'indexer_configuration_id': tool_id, } # when self.storage.content_language_add([language1]) # then actual_languages = list(self.storage.content_language_get( [self.cont2['sha1'], self.missing_cont['sha1']])) # then expected_languages = [{ 'id': self.cont2['sha1'], 'lang': 'common-lisp', 'tool': tools['pygments'] }] self.assertEqual(actual_languages, expected_languages) @istest def content_language_add__drop_duplicate(self): # given tools = self.fetch_tools() tool_id = tools['pygments']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) language_v1 = { 'id': self.cont2['sha1'], 'lang': 'emacslisp', 'indexer_configuration_id': tool_id, } # given self.storage.content_language_add([language_v1]) # when actual_languages = list(self.storage.content_language_get( [self.cont2['sha1']])) # then expected_languages_v1 = [{ 'id': self.cont2['sha1'], 'lang': 'emacslisp', 'tool': tools['pygments'] }] self.assertEqual(actual_languages, expected_languages_v1) # given language_v2 = language_v1.copy() language_v2.update({ 'lang': 'common-lisp', }) self.storage.content_language_add([language_v2]) actual_languages = list(self.storage.content_language_get( [self.cont2['sha1']])) # language did not change as the v2 was dropped. self.assertEqual(actual_languages, expected_languages_v1) @istest def content_language_add__update_in_place_duplicate(self): # given tools = self.fetch_tools() tool_id = tools['pygments']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) language_v1 = { 'id': self.cont2['sha1'], 'lang': 'common-lisp', 'indexer_configuration_id': tool_id, } # given self.storage.content_language_add([language_v1]) # when actual_languages = list(self.storage.content_language_get( [self.cont2['sha1']])) # then expected_languages_v1 = [{ 'id': self.cont2['sha1'], 'lang': 'common-lisp', 'tool': tools['pygments'] }] self.assertEqual(actual_languages, expected_languages_v1) # given language_v2 = language_v1.copy() language_v2.update({ 'lang': 'emacslisp', }) self.storage.content_language_add([language_v2], conflict_update=True) actual_languages = list(self.storage.content_language_get( [self.cont2['sha1']])) # language did not change as the v2 was dropped. expected_languages_v2 = [{ 'id': self.cont2['sha1'], 'lang': 'emacslisp', 'tool': tools['pygments'] }] # language did change as the v2 was used to overwrite v1 self.assertEqual(actual_languages, expected_languages_v2) @istest def content_ctags_missing(self): # given tools = self.fetch_tools() tool_id = tools['universal-ctags']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) ctags = [ { 'id': self.cont2['sha1'], 'indexer_configuration_id': tool_id, }, { 'id': self.missing_cont['sha1'], 'indexer_configuration_id': tool_id, } ] # when actual_missing = self.storage.content_ctags_missing(ctags) # then self.assertEqual(list(actual_missing), [ self.cont2['sha1'], self.missing_cont['sha1'] ]) # given self.storage.content_ctags_add([ { 'id': self.cont2['sha1'], 'indexer_configuration_id': tool_id, 'ctags': [{ 'name': 'done', 'kind': 'variable', 'line': 119, 'lang': 'OCaml', }] }, ]) # when actual_missing = self.storage.content_ctags_missing(ctags) # then self.assertEqual(list(actual_missing), [self.missing_cont['sha1']]) @istest def content_ctags_get(self): # given tools = self.fetch_tools() tool_id = tools['universal-ctags']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) ctags = [self.cont2['sha1'], self.missing_cont['sha1']] ctag1 = { 'id': self.cont2['sha1'], 'indexer_configuration_id': tool_id, 'ctags': [ { 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Python', }, { 'name': 'main', 'kind': 'function', 'line': 119, 'lang': 'Python', }] } # when self.storage.content_ctags_add([ctag1]) # then actual_ctags = list(self.storage.content_ctags_get(ctags)) # then expected_ctags = [ { 'id': self.cont2['sha1'], 'tool': tools['universal-ctags'], 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Python', }, { 'id': self.cont2['sha1'], 'tool': tools['universal-ctags'], 'name': 'main', 'kind': 'function', 'line': 119, 'lang': 'Python', } ] self.assertEqual(actual_ctags, expected_ctags) @istest def content_ctags_search(self): # 1. given tools = self.fetch_tools() tool = tools['universal-ctags'] tool_id = tool['id'] cont = self.cont cont2 = self.cont2 self.storage.content_add([cont, cont2]) ctag1 = { 'id': cont['sha1'], 'indexer_configuration_id': tool_id, 'ctags': [ { 'name': 'hello', 'kind': 'function', 'line': 133, 'lang': 'Python', }, { 'name': 'counter', 'kind': 'variable', 'line': 119, 'lang': 'Python', }, ] } ctag2 = { 'id': cont2['sha1'], 'indexer_configuration_id': tool_id, 'ctags': [ { 'name': 'hello', 'kind': 'variable', 'line': 100, 'lang': 'C', }, ] } self.storage.content_ctags_add([ctag1, ctag2]) # 1. when actual_ctags = list(self.storage.content_ctags_search('hello', limit=1)) # 1. then self.assertEqual(actual_ctags, [ { 'id': ctag1['id'], 'tool': tool, 'name': 'hello', 'kind': 'function', 'line': 133, 'lang': 'Python', } ]) # 2. when actual_ctags = list(self.storage.content_ctags_search( 'hello', limit=1, last_sha1=ctag1['id'])) # 2. then self.assertEqual(actual_ctags, [ { 'id': ctag2['id'], 'tool': tool, 'name': 'hello', 'kind': 'variable', 'line': 100, 'lang': 'C', } ]) # 3. when actual_ctags = list(self.storage.content_ctags_search('hello')) # 3. then self.assertEqual(actual_ctags, [ { 'id': ctag1['id'], 'tool': tool, 'name': 'hello', 'kind': 'function', 'line': 133, 'lang': 'Python', }, { 'id': ctag2['id'], 'tool': tool, 'name': 'hello', 'kind': 'variable', 'line': 100, 'lang': 'C', }, ]) # 4. when actual_ctags = list(self.storage.content_ctags_search('counter')) # then self.assertEqual(actual_ctags, [{ 'id': ctag1['id'], 'tool': tool, 'name': 'counter', 'kind': 'variable', 'line': 119, 'lang': 'Python', }]) @istest def content_ctags_search_no_result(self): actual_ctags = list(self.storage.content_ctags_search('counter')) self.assertEquals(actual_ctags, []) @istest def content_ctags_add__add_new_ctags_added(self): # given tools = self.fetch_tools() tool = tools['universal-ctags'] tool_id = tool['id'] cont2 = self.cont2 self.storage.content_add([cont2]) ctag_v1 = { 'id': self.cont2['sha1'], 'indexer_configuration_id': tool_id, 'ctags': [{ 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', }] } # given self.storage.content_ctags_add([ctag_v1]) self.storage.content_ctags_add([ctag_v1]) # conflict does nothing # when actual_ctags = list(self.storage.content_ctags_get( [self.cont2['sha1']])) # then expected_ctags = [{ 'id': self.cont2['sha1'], 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool, }] self.assertEqual(actual_ctags, expected_ctags) # given ctag_v2 = ctag_v1.copy() ctag_v2.update({ 'ctags': [ { 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', } ] }) self.storage.content_ctags_add([ctag_v2]) expected_ctags = [ { 'id': self.cont2['sha1'], 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool, }, { 'id': self.cont2['sha1'], 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', 'tool': tool, } ] actual_ctags = list(self.storage.content_ctags_get( [self.cont2['sha1']])) self.assertEqual(actual_ctags, expected_ctags) @istest def content_ctags_add__update_in_place(self): # given tools = self.fetch_tools() tool = tools['universal-ctags'] tool_id = tool['id'] cont2 = self.cont2 self.storage.content_add([cont2]) ctag_v1 = { 'id': self.cont2['sha1'], 'indexer_configuration_id': tool_id, 'ctags': [{ 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', }] } # given self.storage.content_ctags_add([ctag_v1]) # when actual_ctags = list(self.storage.content_ctags_get( [self.cont2['sha1']])) # then expected_ctags = [ { 'id': self.cont2['sha1'], 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool } ] self.assertEqual(actual_ctags, expected_ctags) # given ctag_v2 = ctag_v1.copy() ctag_v2.update({ 'ctags': [ { 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', }, { 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', } ] }) self.storage.content_ctags_add([ctag_v2], conflict_update=True) actual_ctags = list(self.storage.content_ctags_get( [self.cont2['sha1']])) # ctag did change as the v2 was used to overwrite v1 expected_ctags = [ { 'id': self.cont2['sha1'], 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool, }, { 'id': self.cont2['sha1'], 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', 'tool': tool, } ] self.assertEqual(actual_ctags, expected_ctags) @istest def content_fossology_license_get(self): # given tools = self.fetch_tools() tool = tools['nomos'] tool_id = tool['id'] cont = self.cont self.storage.content_add([cont]) license1 = { 'id': cont['sha1'], 'licenses': ['GPL-2.0+'], 'indexer_configuration_id': tool_id, } # when self.storage.content_fossology_license_add([license1]) # then actual_licenses = list(self.storage.content_fossology_license_get( [cont['sha1'], self.missing_cont['sha1']])) expected_license = { 'id': cont['sha1'], 'licenses': ['GPL-2.0+'], 'tool': tool, } # then self.assertEqual(actual_licenses, [expected_license]) @istest def content_fossology_license_add__new_license_added(self): # given tools = self.fetch_tools() tool = tools['nomos'] tool_id = tool['id'] cont = self.cont self.storage.content_add([cont]) license_v1 = { 'id': cont['sha1'], 'licenses': ['Apache-2.0'], 'indexer_configuration_id': tool_id, } # given self.storage.content_fossology_license_add([license_v1]) # conflict does nothing self.storage.content_fossology_license_add([license_v1]) # when actual_licenses = list(self.storage.content_fossology_license_get( [cont['sha1']])) # then expected_license = { 'id': cont['sha1'], 'licenses': ['Apache-2.0'], 'tool': tool, } self.assertEqual(actual_licenses, [expected_license]) # given license_v2 = license_v1.copy() license_v2.update({ 'licenses': ['BSD-2-Clause'], }) self.storage.content_fossology_license_add([license_v2]) actual_licenses = list(self.storage.content_fossology_license_get( [cont['sha1']])) expected_license.update({ 'licenses': ['Apache-2.0', 'BSD-2-Clause'], }) # license did not change as the v2 was dropped. self.assertEqual(actual_licenses, [expected_license]) @istest def content_fossology_license_add__update_in_place_duplicate(self): # given tools = self.fetch_tools() tool = tools['nomos'] tool_id = tool['id'] cont = self.cont self.storage.content_add([cont]) license_v1 = { 'id': cont['sha1'], 'licenses': ['CECILL'], 'indexer_configuration_id': tool_id, } # given self.storage.content_fossology_license_add([license_v1]) # conflict does nothing self.storage.content_fossology_license_add([license_v1]) # when actual_licenses = list(self.storage.content_fossology_license_get( [cont['sha1']])) # then expected_license = { 'id': cont['sha1'], 'licenses': ['CECILL'], 'tool': tool, } self.assertEqual(actual_licenses, [expected_license]) # given license_v2 = license_v1.copy() license_v2.update({ 'licenses': ['CECILL-2.0'] }) self.storage.content_fossology_license_add([license_v2], conflict_update=True) actual_licenses = list(self.storage.content_fossology_license_get( [cont['sha1']])) # license did change as the v2 was used to overwrite v1 expected_license.update({ 'licenses': ['CECILL-2.0'] }) self.assertEqual(actual_licenses, [expected_license]) @istest def content_metadata_missing(self): # given tools = self.fetch_tools() tool_id = tools['swh-metadata-translator']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) metadatas = [ { 'id': self.cont2['sha1'], 'indexer_configuration_id': tool_id, }, { 'id': self.missing_cont['sha1'], 'indexer_configuration_id': tool_id, } ] # when actual_missing = list(self.storage.content_metadata_missing(metadatas)) # then self.assertEqual(list(actual_missing), [ self.cont2['sha1'], self.missing_cont['sha1'], ]) # given self.storage.content_metadata_add([{ 'id': self.cont2['sha1'], 'translated_metadata': { 'other': {}, 'codeRepository': { 'type': 'git', 'url': 'https://github.com/moranegg/metadata_test' }, 'description': 'Simple package.json test for indexer', 'name': 'test_metadata', 'version': '0.0.1' }, 'indexer_configuration_id': tool_id }]) # when actual_missing = list(self.storage.content_metadata_missing(metadatas)) # then self.assertEqual(actual_missing, [self.missing_cont['sha1']]) @istest def content_metadata_get(self): # given tools = self.fetch_tools() tool_id = tools['swh-metadata-translator']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) metadata1 = { 'id': self.cont2['sha1'], 'translated_metadata': { 'other': {}, 'codeRepository': { 'type': 'git', 'url': 'https://github.com/moranegg/metadata_test' }, 'description': 'Simple package.json test for indexer', 'name': 'test_metadata', 'version': '0.0.1' }, 'indexer_configuration_id': tool_id, } # when self.storage.content_metadata_add([metadata1]) # then actual_metadatas = list(self.storage.content_metadata_get( [self.cont2['sha1'], self.missing_cont['sha1']])) expected_metadatas = [{ 'id': self.cont2['sha1'], 'translated_metadata': { 'other': {}, 'codeRepository': { 'type': 'git', 'url': 'https://github.com/moranegg/metadata_test' }, 'description': 'Simple package.json test for indexer', 'name': 'test_metadata', 'version': '0.0.1' }, 'tool': tools['swh-metadata-translator'] }] self.assertEqual(actual_metadatas, expected_metadatas) @istest def content_metadata_add_drop_duplicate(self): # given tools = self.fetch_tools() tool_id = tools['swh-metadata-translator']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) metadata_v1 = { 'id': self.cont2['sha1'], 'translated_metadata': { 'other': {}, 'name': 'test_metadata', 'version': '0.0.1' }, 'indexer_configuration_id': tool_id, } # given self.storage.content_metadata_add([metadata_v1]) # when actual_metadatas = list(self.storage.content_metadata_get( [self.cont2['sha1']])) expected_metadatas_v1 = [{ 'id': self.cont2['sha1'], 'translated_metadata': { 'other': {}, 'name': 'test_metadata', 'version': '0.0.1' }, 'tool': tools['swh-metadata-translator'] }] self.assertEqual(actual_metadatas, expected_metadatas_v1) # given metadata_v2 = metadata_v1.copy() metadata_v2.update({ 'translated_metadata': { 'other': {}, 'name': 'test_drop_duplicated_metadata', 'version': '0.0.1' }, }) self.storage.content_metadata_add([metadata_v2]) # then actual_metadatas = list(self.storage.content_metadata_get( [self.cont2['sha1']])) # metadata did not change as the v2 was dropped. self.assertEqual(actual_metadatas, expected_metadatas_v1) @istest def content_metadata_add_update_in_place_duplicate(self): # given tools = self.fetch_tools() tool_id = tools['swh-metadata-translator']['id'] cont2 = self.cont2 self.storage.content_add([cont2]) metadata_v1 = { 'id': self.cont2['sha1'], 'translated_metadata': { 'other': {}, 'name': 'test_metadata', 'version': '0.0.1' }, 'indexer_configuration_id': tool_id, } # given self.storage.content_metadata_add([metadata_v1]) # when actual_metadatas = list(self.storage.content_metadata_get( [self.cont2['sha1']])) # then expected_metadatas_v1 = [{ 'id': self.cont2['sha1'], 'translated_metadata': { 'other': {}, 'name': 'test_metadata', 'version': '0.0.1' }, 'tool': tools['swh-metadata-translator'] }] self.assertEqual(actual_metadatas, expected_metadatas_v1) # given metadata_v2 = metadata_v1.copy() metadata_v2.update({ 'translated_metadata': { 'other': {}, 'name': 'test_update_duplicated_metadata', 'version': '0.0.1' }, }) self.storage.content_metadata_add([metadata_v2], conflict_update=True) actual_metadatas = list(self.storage.content_metadata_get( [self.cont2['sha1']])) # language did not change as the v2 was dropped. expected_metadatas_v2 = [{ 'id': self.cont2['sha1'], 'translated_metadata': { 'other': {}, 'name': 'test_update_duplicated_metadata', 'version': '0.0.1' }, 'tool': tools['swh-metadata-translator'] }] - # language did change as the v2 was used to overwrite v1 + # metadata did change as the v2 was used to overwrite v1 self.assertEqual(actual_metadatas, expected_metadatas_v2) class TestLocalStorage(CommonTestStorage, unittest.TestCase): """Test the local storage""" # Can only be tested with local storage as you can't mock # datetimes for the remote server @istest def fetch_history(self): origin = self.storage.origin_add_one(self.origin) with patch('datetime.datetime'): datetime.datetime.now.return_value = self.fetch_history_date fetch_history_id = self.storage.fetch_history_start(origin) datetime.datetime.now.assert_called_with(tz=datetime.timezone.utc) with patch('datetime.datetime'): datetime.datetime.now.return_value = self.fetch_history_end self.storage.fetch_history_end(fetch_history_id, self.fetch_history_data) fetch_history = self.storage.fetch_history_get(fetch_history_id) expected_fetch_history = self.fetch_history_data.copy() expected_fetch_history['id'] = fetch_history_id expected_fetch_history['origin'] = origin expected_fetch_history['date'] = self.fetch_history_date expected_fetch_history['duration'] = self.fetch_history_duration self.assertEqual(expected_fetch_history, fetch_history) @istest def person_get(self): # given person0 = { 'fullname': b'bob ', 'name': b'bob', 'email': b'alice@bob', } id0 = self.storage._person_add(person0) person1 = { 'fullname': b'tony ', 'name': b'tony', 'email': b'tony@bob', } id1 = self.storage._person_add(person1) # when actual_persons = self.storage.person_get([id0, id1]) # given (person injection through release for example) self.assertEqual( list(actual_persons), [ { 'id': id0, 'fullname': person0['fullname'], 'name': person0['name'], 'email': person0['email'], }, { 'id': id1, 'fullname': person1['fullname'], 'name': person1['name'], 'email': person1['email'], }, ]) @istest def indexer_configuration_get_missing(self): tool = { 'tool_name': 'unknown-tool', 'tool_version': '3.1.0rc2-31-ga2cbb8c', 'tool_configuration': {"command_line": "nomossa "}, } actual_tool = self.storage.indexer_configuration_get(tool) self.assertIsNone(actual_tool) @istest def indexer_configuration_get(self): tool = { 'tool_name': 'nomos', 'tool_version': '3.1.0rc2-31-ga2cbb8c', 'tool_configuration': {"command_line": "nomossa "}, } actual_tool = self.storage.indexer_configuration_get(tool) expected_tool = tool.copy() expected_tool['id'] = 1 self.assertEqual(expected_tool, actual_tool) @istest def indexer_configuration_metadata_get_missing_context(self): tool = { 'tool_name': 'swh-metadata-translator', 'tool_version': '0.0.1', 'tool_configuration': {"context": "unknown-context"}, } actual_tool = self.storage.indexer_configuration_get(tool) self.assertIsNone(actual_tool) @istest def indexer_configuration_metadata_get(self): tool = { 'tool_name': 'swh-metadata-translator', 'tool_version': '0.0.1', 'tool_configuration': {"type": "local", "context": "npm"}, } actual_tool = self.storage.indexer_configuration_get(tool) expected_tool = tool.copy() expected_tool['id'] = actual_tool['id'] self.assertEqual(expected_tool, actual_tool) class AlteringSchemaTest(BaseTestStorage, unittest.TestCase): """This class is dedicated for the rare case where the schema needs to be altered dynamically. Otherwise, the tests could be blocking when ran altogether. """ @istest def content_update(self): cont = copy.deepcopy(self.cont) self.storage.content_add([cont]) # alter the sha1_git for example cont['sha1_git'] = hash_to_bytes( '3a60a5275d0333bf13468e8b3dcab90f4046e654') self.storage.content_update([cont], keys=['sha1_git']) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = self.cursor.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) @istest def content_update_with_new_cols(self): self.cursor.execute("""alter table content add column test text default null, add column test2 text default null""") cont = copy.deepcopy(self.cont2) self.storage.content_add([cont]) cont['test'] = 'value-1' cont['test2'] = 'value-2' self.storage.content_update([cont], keys=['test', 'test2']) self.cursor.execute( 'SELECT sha1, sha1_git, sha256, length, status, test, test2' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = self.cursor.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4], datum[5], datum[6]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible', cont['test'], cont['test2'])) self.cursor.execute("""alter table content drop column test, drop column test2""")