diff --git a/sql/clusters.dot b/sql/clusters.dot index 5580f9d0..7217f7ae 100644 --- a/sql/clusters.dot +++ b/sql/clusters.dot @@ -1,81 +1,80 @@ subgraph "logical_grouping" { style = rounded; bgcolor = gray95; color = gray; subgraph cluster_meta { label = <meta
version: @@VERSION@@>; dbversion; } subgraph cluster_content { label = <content>; content; skipped_content; } subgraph cluster_directory { label = <directories>; directory; directory_entry_dir; directory_entry_file; directory_entry_rev; } subgraph cluster_revision { label = <revisions>; revision; revision_history; person; } subgraph cluster_release { label = <releases>; release; } subgraph cluster_occurrences { label = <occurrences>; occurrence; occurrence_history; } subgraph cluster_origins { label = <origins>; origin; fetch_history; } - subgraph cluster_projects { - label = <projects>; - project; - project_history; - } - - subgraph cluster_organization { - label = <organizations>; - organization; + subgraph cluster_entity { + label = <entities>; + entity; + entity_history; + entity_equivalence; + listable_entity; list_history; } { edge [style = dashed]; # "rtcolN" identifies the N-th row in a table, as a source # "ltcolN" identifies the N-th row in a table, as a destination "directory_entry_dir":rtcol2 -> "directory":ltcol1; "directory_entry_file":rtcol2 -> "content":ltcol2; "directory_entry_file":rtcol2 -> "skipped_content":ltcol2; "directory_entry_rev":rtcol2 -> "revision":ltcol1; "directory":rtcol2 -> "directory_entry_dir":ltcol1; "directory":rtcol3 -> "directory_entry_file":ltcol1; "directory":rtcol4 -> "directory_entry_rev":ltcol1; "occurrence":rtcol3 -> "revision":ltcol1; "occurrence_history":rtcol3 -> "revision":ltcol1; "release":rtcol2 -> "revision":ltcol1; "revision":rtcol7 -> "directory":ltcol1; "revision_history":rtcol2 -> "revision":ltcol1; + "entity_history":rtcol3 -> "entity_history":ltcol2; + "entity_history":rtcol10 -> "listable_entity":ltcol1; } } diff --git a/sql/swh-data.sql b/sql/swh-data.sql index ff035bf1..313e13e1 100644 --- a/sql/swh-data.sql +++ b/sql/swh-data.sql @@ -1,9 +1,39 @@ -insert into organization(name, description, homepage) - values('softwareheritage', - 'Software Heritage', - 'http://www.softwareheritage.org'); +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 organization(name, description, homepage) - values('gnu', - 'GNU is not Unix!', - 'https://gnu.org/'); +insert into listable_entity + (uuid, list_engine) +values + ('34bd6b1b-463f-43e5-a697-785107f598e4', 'swh.lister.github'); diff --git a/sql/swh-func.sql b/sql/swh-func.sql index 53c1ed5a..905052f0 100644 --- a/sql/swh-func.sql +++ b/sql/swh-func.sql @@ -1,782 +1,831 @@ -- create a temporary table called tmp_TBLNAME, mimicking existing table -- TBLNAME -- -- Args: -- tblname: name of the table to mimick create or replace function swh_mktemp(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table tmp_%I (like %I including defaults) on commit drop ', tblname, tblname); return; end $$; -- create a temporary table for directory entries called tmp_TBLNAME, -- mimicking existing table TBLNAME with an extra dir_id (sha1_git) -- column, and dropping the id column. -- -- This is used to create the tmp_directory_entry_ tables. -- -- Args: -- tblname: name of the table to mimick create or replace function swh_mktemp_dir_entry(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table tmp_%I (like %I including defaults, dir_id sha1_git) on commit drop; alter table tmp_%I drop column id; ', tblname, tblname, tblname, tblname); return; end $$; -- create a temporary table for revisions called tmp_revisions, -- mimicking existing table revision, replacing the foreign keys to -- people with an email and name field -- create or replace function swh_mktemp_revision() returns void language sql as $$ create temporary table tmp_revision ( like revision including defaults, author_name bytea not null default '', author_email bytea not null default '', committer_name bytea not null default '', committer_email bytea not null default '' ) on commit drop; alter table tmp_revision drop column author; alter table tmp_revision drop column committer; $$; -- create a temporary table for releases called tmp_release, -- mimicking existing table release, replacing the foreign keys to -- people with an email and name field -- create or replace function swh_mktemp_release() returns void language sql as $$ create temporary table tmp_release ( like release including defaults, author_name bytea not null default '', author_email bytea not null default '' ) on commit drop; alter table tmp_release drop column author; $$; -- a content signature is a set of cryptographic checksums that we use to -- uniquely identify content, for the purpose of verifying if we already have -- some content or not during content injection create type content_signature as ( sha1 sha1, sha1_git sha1_git, sha256 sha256 ); -- check which entries of tmp_content are missing from content -- -- operates in bulk: 0. swh_mktemp(content), 1. COPY to tmp_content, -- 2. call this function create or replace function swh_content_missing() returns setof content_signature language plpgsql as $$ begin -- This query is critical for (single-algorithm) hash collision detection, -- so we cannot rely only on the fact that a single hash (e.g., sha1) is -- missing from the table content to conclude that a given content is -- missing. Ideally, we would want to (try to) add to content all entries -- in tmp_content that, when considering all columns together, are missing -- from content. -- -- But doing that naively would require a *compound* index on all checksum -- columns; that index would not be significantly smaller than the content -- table itself, and therefore won't be used. Therefore we union together -- all contents that differ on at least one column from what is already -- available. If there is a collision on some (but not all) columns, the -- relevant tmp_content entry will be included in the set of content to be -- added, causing a downstream violation of unicity constraint. return query (select sha1, sha1_git, sha256 from tmp_content as tmp where not exists (select 1 from content as c where c.sha1 = tmp.sha1)) union (select sha1, sha1_git, sha256 from tmp_content as tmp where not exists (select 1 from content as c where c.sha1_git = tmp.sha1_git)) union (select sha1, sha1_git, sha256 from tmp_content as tmp where not exists (select 1 from content as c where c.sha256 = tmp.sha256)); return; end $$; -- check which entries of tmp_skipped_content are missing from skipped_content -- -- operates in bulk: 0. swh_mktemp(skipped_content), 1. COPY to tmp_skipped_content, -- 2. call this function create or replace function swh_skipped_content_missing() returns setof content_signature language plpgsql as $$ begin return query select sha1, sha1_git, sha256 from tmp_skipped_content t where not exists (select 1 from skipped_content s where s.sha1 is not distinct from t.sha1 and s.sha1_git is not distinct from t.sha1_git and s.sha256 is not distinct from t.sha256); return; end $$; -- Look up content based on one or several different checksums. Return all -- content information if the content is found; a NULL row otherwise. -- -- At least one checksum should be not NULL. If several are not NULL, they will -- be AND-ed together in the lookup query. -- -- Note: this function is meant to be used to look up individual contents -- (e.g., for the web app), for batch lookup of missing content (e.g., to be -- added) see swh_content_missing create or replace function swh_content_find( sha1 sha1 default NULL, sha1_git sha1_git default NULL, sha256 sha256 default NULL ) returns content language plpgsql as $$ declare con content; filters text[] := array[] :: text[]; -- AND-clauses used to filter content q text; begin if sha1 is not null then filters := filters || format('sha1 = %L', sha1); end if; if sha1_git is not null then filters := filters || format('sha1_git = %L', sha1_git); end if; if sha256 is not null then filters := filters || format('sha256 = %L', sha256); end if; if cardinality(filters) = 0 then return null; else q = format('select * from content where %s', array_to_string(filters, ' and ')); execute q into con; return con; end if; end $$; -- add tmp_content entries to content, skipping duplicates -- -- operates in bulk: 0. swh_mktemp(content), 1. COPY to tmp_content, -- 2. call this function create or replace function swh_content_add() returns void language plpgsql as $$ begin insert into content (sha1, sha1_git, sha256, length, status) select distinct sha1, sha1_git, sha256, length, status from tmp_content where (sha1, sha1_git, sha256) in (select * from swh_content_missing()); -- TODO XXX use postgres 9.5 "UPSERT" support here, when available. -- Specifically, using "INSERT .. ON CONFLICT IGNORE" we can avoid -- the extra swh_content_missing() query here. return; end $$; -- add tmp_skipped_content entries to skipped_content, skipping duplicates -- -- operates in bulk: 0. swh_mktemp(skipped_content), 1. COPY to tmp_skipped_content, -- 2. call this function create or replace function swh_skipped_content_add() returns void language plpgsql as $$ begin insert into skipped_content (sha1, sha1_git, sha256, length, status, reason, origin) select distinct sha1, sha1_git, sha256, length, status, reason, origin from tmp_skipped_content where (coalesce(sha1, ''), coalesce(sha1_git, ''), coalesce(sha256, '')) in (select coalesce(sha1, ''), coalesce(sha1_git, ''), coalesce(sha256, '') from swh_skipped_content_missing()); -- TODO XXX use postgres 9.5 "UPSERT" support here, when available. -- Specifically, using "INSERT .. ON CONFLICT IGNORE" we can avoid -- the extra swh_content_missing() query here. return; end $$; -- check which entries of tmp_directory are missing from directory -- -- operates in bulk: 0. swh_mktemp(directory), 1. COPY to tmp_directory, -- 2. call this function create or replace function swh_directory_missing() returns setof sha1_git language plpgsql as $$ begin return query select id from tmp_directory t where not exists ( select 1 from directory d where d.id = t.id); return; end $$; create type directory_entry_type as enum('file', 'dir', 'rev'); -- Add tmp_directory_entry_* entries to directory_entry_* and directory, -- skipping duplicates in directory_entry_*. This is a generic function that -- works on all kind of directory entries. -- -- operates in bulk: 0. swh_mktemp_dir_entry('directory_entry_*'), 1 COPY to -- tmp_directory_entry_*, 2. call this function -- -- Assumption: this function is used in the same transaction that inserts the -- context directory in table "directory". create or replace function swh_directory_entry_add(typ directory_entry_type) returns void language plpgsql as $$ begin execute format(' insert into directory_entry_%1$s (target, name, perms) select distinct t.target, t.name, t.perms from tmp_directory_entry_%1$s t where not exists ( select 1 from directory_entry_%1$s i where t.target = i.target and t.name = i.name and t.perms = i.perms) ', typ); execute format(' with new_entries as ( select t.dir_id, array_agg(i.id) as entries from tmp_directory_entry_%1$s t inner join directory_entry_%1$s i using (target, name, perms) group by t.dir_id ) update directory as d set %1$s_entries = new_entries.entries from new_entries where d.id = new_entries.dir_id ', typ); return; end $$; -- a directory listing entry with all the metadata -- -- can be used to list a directory, and retrieve all the data in one go. create type directory_entry as ( dir_id sha1_git, -- id of the parent directory type directory_entry_type, -- type of entry target sha1_git, -- id of target name unix_path, -- path name, relative to containing dir perms file_perms -- unix-like permissions ); -- List a single level of directory walked_dir_id -- FIXME: order by name is not correct. For git, we need to order by -- lexicographic order but as if a trailing / is present in directory -- name create or replace function swh_directory_walk_one(walked_dir_id sha1_git) returns setof directory_entry language sql stable as $$ with dir as ( select id as dir_id, dir_entries, file_entries, rev_entries from directory where id = walked_dir_id), ls_d as (select dir_id, unnest(dir_entries) as entry_id from dir), ls_f as (select dir_id, unnest(file_entries) as entry_id from dir), ls_r as (select dir_id, unnest(rev_entries) as entry_id from dir) (select dir_id, 'dir'::directory_entry_type as type, target, name, perms from ls_d left join directory_entry_dir d on ls_d.entry_id = d.id) union (select dir_id, 'file'::directory_entry_type as type, target, name, perms from ls_f left join directory_entry_file d on ls_f.entry_id = d.id) union (select dir_id, 'rev'::directory_entry_type as type, target, name, perms from ls_r left join directory_entry_rev d on ls_r.entry_id = d.id) order by name; $$; -- List recursively the content of a directory create or replace function swh_directory_walk(walked_dir_id sha1_git) returns setof directory_entry language sql stable as $$ with recursive entries as ( select dir_id, type, target, name, perms from swh_directory_walk_one(walked_dir_id) union all select dir_id, type, target, (dirname || '/' || name)::unix_path as name, perms from (select (swh_directory_walk_one(dirs.target)).*, dirs.name as dirname from (select target, name from entries where type = 'dir') as dirs) as with_parent ) select dir_id, type, target, name, perms from entries $$; -- List all revision IDs starting from a given revision, going back in time -- -- TODO ordering: should be breadth-first right now (what do we want?) -- TODO ordering: ORDER BY parent_rank somewhere? create or replace function swh_revision_list(root_revision sha1_git) returns setof sha1_git language sql stable as $$ with recursive rev_list(id) as ( (select id from revision where id = root_revision) union (select parent_id from revision_history as h join rev_list on h.id = rev_list.id) ) select * from rev_list; $$; -- List all the children of a given revision create or replace function swh_revision_list_children(root_revision sha1_git) returns setof sha1_git language sql stable as $$ with recursive rev_list(id) as ( (select id from revision where id = root_revision) union (select h.id from revision_history as h join rev_list on h.parent_id = rev_list.id) ) select * from rev_list; $$; -- Detailed entry in a revision log create type revision_log_entry as ( id sha1_git, date timestamptz, date_offset smallint, committer_date timestamptz, committer_date_offset smallint, type revision_type, directory sha1_git, message bytea, author_name bytea, author_email bytea, committer_name bytea, committer_email bytea, synthetic boolean ); -- "git style" revision log. Similar to swh_revision_list(), but returning all -- information associated to each revision, and expanding authors/committers create or replace function swh_revision_log(root_revision sha1_git) returns setof revision_log_entry language sql stable as $$ select revision.id, date, date_offset, committer_date, committer_date_offset, type, directory, message, author.name as author_name, author.email as author_email, committer.name as committer_name, committer.email as committer_email, revision.synthetic from swh_revision_list(root_revision) as rev_list join revision on revision.id = rev_list join person as author on revision.author = author.id join person as committer on revision.committer = committer.id; $$; -- Detailed entry for a revision create type revision_entry as ( id sha1_git, date timestamptz, date_offset smallint, committer_date timestamptz, committer_date_offset smallint, type revision_type, directory sha1_git, message bytea, author_name bytea, author_email bytea, committer_name bytea, committer_email bytea, synthetic boolean, parents bytea[] ); -- Retrieve revisions from tmp_revision in bulk create or replace function swh_revision_get() returns setof revision_entry language plpgsql as $$ begin return query select t.id, r.date, r.date_offset, r.committer_date, r.committer_date_offset, r.type, r.directory, r.message, a.name, a.email, c.name, c.email, r.synthetic, array_agg(rh.parent_id::bytea order by rh.parent_rank) as parents from tmp_revision t left join revision r on t.id = r.id left join person a on a.id = r.author left join person c on c.id = r.committer left join revision_history rh on rh.id = r.id group by t.id, a.name, a.email, r.date, r.date_offset, c.name, c.email, r.committer_date, r.committer_date_offset, r.type, r.directory, r.message, r.synthetic; return; end $$; -- List missing revisions from tmp_revision create or replace function swh_revision_missing() returns setof sha1_git language plpgsql as $$ begin return query select id from tmp_revision t where not exists ( select 1 from revision r where r.id = t.id); return; end $$; -- Create entries in person from tmp_revision create or replace function swh_person_add_from_revision() returns void language plpgsql as $$ begin with t as ( select author_name as name, author_email as email from tmp_revision union select committer_name as name, committer_email as email from tmp_revision ) insert into person (name, email) select distinct name, email from t where not exists ( select 1 from person p where t.name = p.name and t.email = p.email ); return; end $$; -- Create entries in revision from tmp_revision create or replace function swh_revision_add() returns void language plpgsql as $$ begin perform swh_person_add_from_revision(); insert into revision (id, date, date_offset, committer_date, committer_date_offset, type, directory, message, author, committer, synthetic) select t.id, t.date, t.date_offset, t.committer_date, t.committer_date_offset, t.type, t.directory, t.message, a.id, c.id, t.synthetic from tmp_revision t left join person a on a.name = t.author_name and a.email = t.author_email left join person c on c.name = t.committer_name and c.email = t.committer_email; return; end $$; -- List missing releases from tmp_release create or replace function swh_release_missing() returns setof sha1_git language plpgsql as $$ begin return query select id from tmp_release t where not exists ( select 1 from release r where r.id = t.id); return; end $$; -- Create entries in person from tmp_release create or replace function swh_person_add_from_release() returns void language plpgsql as $$ begin with t as ( select distinct author_name as name, author_email as email from tmp_release ) insert into person (name, email) select name, email from t where not exists ( select 1 from person p where t.name = p.name and t.email = p.email ); return; end $$; -- Create entries in release from tmp_release create or replace function swh_release_add() returns void language plpgsql as $$ begin perform swh_person_add_from_release(); insert into release (id, revision, date, date_offset, name, comment, author, synthetic) select t.id, t.revision, t.date, t.date_offset, t.name, t.comment, a.id, t.synthetic from tmp_release t left join person a on a.name = t.author_name and a.email = t.author_email; return; end $$; -- add tmp_occurrence_history entries to occurrence_history -- -- operates in bulk: 0. swh_mktemp(occurrence_history), 1. COPY to tmp_occurrence_history, -- 2. call this function create or replace function swh_occurrence_history_add() returns void language plpgsql as $$ begin -- Update intervals we have the data to update with new_intervals as ( select t.origin, t.branch, t.authority, t.validity, o.validity - t.validity as new_validity from tmp_occurrence_history t left join occurrence_history o using (origin, branch, authority) where o.origin is not null), -- do not update intervals if they would become empty (perfect overlap) to_update as ( select * from new_intervals where not isempty(new_validity)) update occurrence_history o set validity = t.new_validity from to_update t where o.origin = t.origin and o.branch = t.branch and o.authority = t.authority; -- Now only insert intervals that aren't already present insert into occurrence_history (origin, branch, revision, authority, validity) select distinct origin, branch, revision, authority, validity from tmp_occurrence_history t where not exists ( select 1 from occurrence_history o where o.origin = t.origin and o.branch = t.branch and o.authority = t.authority and o.revision = t.revision and o.validity = t.validity); return; end $$; -- Absolute path: directory reference + complete path relative to it create type content_dir as ( directory sha1_git, path unix_path ); -- Find the containing directory of a given content, specified by sha1 -- (note: *not* sha1_git). -- -- Return a pair (dir_it, path) where path is a UNIX path that, from the -- directory root, reach down to a file with the desired content. Return NULL -- if no match is found. -- -- In case of multiple paths (i.e., pretty much always), an arbitrary one is -- chosen. create or replace function swh_content_find_directory(content_id sha1) returns content_dir language sql stable as $$ with recursive path as ( -- Recursively build a path from the requested content to a root -- directory. Each iteration returns a pair (dir_id, filename) where -- filename is relative to dir_id. Stops when no parent directory can -- be found. (select dir.id as dir_id, dir_entry_f.name as name, 0 as depth from directory_entry_file as dir_entry_f join content on content.sha1_git = dir_entry_f.target join directory as dir on dir.file_entries @> array[dir_entry_f.id] where content.sha1 = content_id limit 1) union all (select dir.id as dir_id, (dir_entry_d.name || '/' || path.name)::unix_path as name, path.depth + 1 from path join directory_entry_dir as dir_entry_d on dir_entry_d.target = path.dir_id join directory as dir on dir.dir_entries @> array[dir_entry_d.id] limit 1) ) select dir_id, name from path order by depth desc limit 1; $$; -- Walk the revision history starting from a given revision, until a matching -- occurrence is found. Return all occurrence information if one is found, NULL -- otherwise. create or replace function swh_revision_find_occurrence(revision_id sha1_git) returns occurrence language sql stable as $$ select origin, branch, revision from swh_revision_list_children(revision_id) as rev_list(sha1_git) left join occurrence_history occ_hist on rev_list.sha1_git = occ_hist.revision where occ_hist.origin is not null order by upper(occ_hist.validity) -- TODO filter by authority? limit 1; $$; -- Occurrence of some content in a given context create type content_occurrence as ( origin_type text, origin_url text, branch text, revision_id sha1_git, path unix_path ); -- Given the sha1 of some content, look up an occurrence that points to a -- revision, which in turns reference (transitively) a tree containing the -- content. Answer the question: "where/when did SWH see a given content"? -- Return information about an arbitrary occurrence/revision/tree if one is -- found, NULL otherwise. create or replace function swh_content_find_occurrence(content_id sha1) returns content_occurrence language plpgsql as $$ declare dir content_dir; rev sha1_git; occ occurrence%ROWTYPE; coc content_occurrence; begin -- each step could fail if no results are found, and that's OK select * from swh_content_find_directory(content_id) -- look up directory into dir; if not found then return null; end if; select id from revision where directory = dir.directory -- look up revision limit 1 into rev; if not found then return null; end if; select * from swh_revision_find_occurrence(rev) -- look up occurrence into occ; if not found then return null; end if; select origin.type, origin.url, occ.branch, rev, dir.path from origin where origin.id = occ.origin into coc; return coc; -- might be NULL end $$; + +create or replace function swh_update_entity_from_entity_history() + returns trigger + language plpgsql +as $$ +begin + with all_entities as ( + select uuid, parent, name, type, description, homepage, active, + generated, lister, lister_metadata, doap, last_seen, last_id + from ( + select row_number() over (partition by uuid order by unnest(validity) desc) as row, + id as last_id, uuid, parent, name, type, description, homepage, active, + generated, lister, lister_metadata, doap, + unnest(validity) as last_seen + from entity_history + ) as latest_entities + where latest_entities.row = 1 + ), + updated_uuids as ( + update entity set + parent = all_entities.parent, + name = all_entities.name, + type = all_entities.type, + description = all_entities.description, + homepage = all_entities.homepage, + active = all_entities.active, + generated = all_entities.generated, + lister = all_entities.lister, + lister_metadata = all_entities.lister_metadata, + doap = all_entities.doap, + last_seen = all_entities.last_seen, + last_id = all_entities.last_id + from all_entities + where entity.uuid = all_entities.uuid + returning entity.uuid + ) + insert into entity + (select * from all_entities + where uuid not in (select uuid from updated_uuids)); + return null; +end +$$; + +create trigger update_entity + after insert or update or delete or truncate + on entity_history + for each statement + execute procedure swh_update_entity_from_entity_history(); + -- simple counter mapping a textual label to an integer value create type counter as ( label text, value bigint ); -- return statistics about the number of tuples in various SWH tables -- -- Note: the returned values are based on postgres internal statistics -- (pg_class table), which are only updated daily (by autovacuum) or so create or replace function swh_stat_counters() returns setof counter language sql stable as $$ select relname::text as label, reltuples::bigint as value from pg_class where oid in ( 'public.content'::regclass, 'public.directory'::regclass, 'public.directory_entry_dir'::regclass, 'public.directory_entry_file'::regclass, 'public.directory_entry_rev'::regclass, 'public.occurrence'::regclass, 'public.occurrence_history'::regclass, 'public.origin'::regclass, 'public.person'::regclass, - 'public.project'::regclass, - 'public.project_history'::regclass, + 'public.entity'::regclass, + 'public.entity_history'::regclass, 'public.release'::regclass, 'public.revision'::regclass, 'public.revision_history'::regclass, 'public.skipped_content'::regclass ); $$; diff --git a/sql/swh-schema.sql b/sql/swh-schema.sql index 36c027b1..850e425b 100644 --- a/sql/swh-schema.sql +++ b/sql/swh-schema.sql @@ -1,335 +1,410 @@ --- --- 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(26, now(), 'Work In Progress'); + values(27, 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); -- 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; create type content_status as enum ('absent', 'visible', 'hidden'); --- 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 primary key, - type text, -- TODO use an enum here (?) - url text not null -); - -- 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 primary key, sha1_git sha1_git not null, sha256 sha256 not null, 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' ); create unique index on content(sha1_git); create unique index on content(sha256); create index on content(ctime); -- TODO use a BRIN index here (postgres >= 9.5) +-- 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. + +-- Types of entities. +-- +-- - organization: a root entity, usually backed by a non-profit, a +-- company, or another kind of "association". (examples: Software +-- Heritage, Debian, GNU, GitHub) +-- +-- - group_of_entities: used for hierarchies, doesn't need to have a +-- concrete existence. (examples: GNU hosting facilities, Debian +-- hosting facilities, GitHub users, ...) +-- +-- - hosting: a hosting facility, can usually be listed to generate +-- other data. (examples: GitHub git hosting, alioth.debian.org, +-- snapshot.debian.org) +-- +-- - group_of_persons: an entity representing a group of +-- persons. (examples: a GitHub organization, a Debian team) +-- +-- - person: an entity representing a person. (examples: +-- a GitHub user, a Debian developer) +-- +-- - project: an entity representing a software project. (examples: a +-- GitHub project, Apache httpd, a Debian source package, ...) +create type entity_type as enum ( + 'organization', + 'group_of_entities', + 'hosting', + 'group_of_persons', + 'person', + 'project' +); + +-- 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 primary key, + 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 uuid, -- should reference entity_history(uuid) + lister_metadata jsonb, -- lister-specific metadata + doap jsonb, -- metadata in doap format + validity timestamptz[] -- timestamps at which we have seen this entity +); + +create index on entity_history(uuid); +create index on entity_history(name); + +-- 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 primary key, + parent uuid references entity(uuid) deferrable initially deferred, + 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 uuid, -- the entity that created this entity. + -- References listable_entity(uuid) later on. + lister_metadata jsonb, -- lister-specific metadata + doap jsonb, -- metadata in doap format + last_seen timestamptz, -- last listing time or disappearance time for active=false + last_id bigint references entity_history(id) -- last listing id +); + +create index on entity(name); + +-- Register the equivalence between two entities. Allows sideways +-- navigation in the entity table +create table entity_equivalence +( + entity1 uuid references entity(uuid), + entity2 uuid references entity(uuid), + primary key (entity1, entity2), + constraint order_entities check (entity1 < entity2) +); + +-- Register a lister for a specific entity. +create table listable_entity +( + uuid uuid references entity(uuid) primary key, + 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 json, -- org-specific listing parameter + latest_list timestamptz -- last time the entity's content has been listed +); + +-- Add the circular foreign key on entity(lister) -> listable_entity(uuid) +alter table entity add foreign key (lister) references listable_entity(uuid); + +-- 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 primary key, + entity uuid references listable_entity(uuid), + date timestamptz not null, + status boolean, -- true if and only if the listing has been successful + result json, -- more detailed return value, depending on status + stdout text, + stderr text, + duration interval -- fetch duration of NULL if still ongoing +); + + +-- 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 primary key, + type text, -- TODO use an enum here (?) + url text not null, + lister uuid references listable_entity(uuid), + project uuid references entity(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, length bigint not null, ctime timestamptz not null default now(), status content_status not null default 'absent', reason text not null, origin bigint references origin(id), unique (sha1, sha1_git, sha256) ); -- those indexes support multiple NULL values. create unique index on skipped_content(sha1); create unique index on skipped_content(sha1_git); create unique index on skipped_content(sha256); --- An organization (or part thereof) that might be in charge of running --- software projects. Examples: Debian, GNU, GitHub, Apache, The Linux --- Foundation. The data model is hierarchical (via parent_id) and might store --- sub-branches of existing organizations. The key feature of an organization --- is that it can be *listed* to retrieve information about its content, i.e: --- sub-organizations, projects, origins. -create table organization -( - id bigserial primary key, - parent_id bigint references organization(id), - name text not null, - description text, - homepage text, - list_engine text, -- crawler to be used to org's content - list_url text, -- root URL to start the listing - list_params json, -- org-specific listing parameter - latest_list timestamptz -- last time the org's content has been listed -); - --- Log of all organization listings (i.e., organization crawling) that have --- been done in the past, or are still ongoing. Similar to fetch_history, but --- for organizations. -create table list_history -( - id bigserial primary key, - organization bigint references organization(id), - date timestamptz not null, - status boolean, -- true if and only if the listing has been successful - result json, -- more detailed return value, depending on status - stdout text, - stderr text, - duration interval -- fetch duration of NULL if still ongoing -); -- 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 primary key, origin bigint references origin(id), date timestamptz not null, status boolean, -- true if and only if the fetch has been successful result json, -- 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 specific software project, e.g., the Linux kernel, Apache httpd. A --- software project is version-less at this level, but is associated to several --- metadata. Metadata can evolve over time, this table only contains the most --- recent version of them; for old versions of project see table --- project_history. -create table project -( - id bigserial primary key, - organization bigint references organization(id), -- the "owning" organization - origin bigint references origin(id), -- where to find project releases - name text, - description text, - homepage text, - doap jsonb - -- other kinds of metadata/software project description ontologies can be - -- added here, in addition to DOAP -); - --- History of project metadata. Time-sensitive version of the table project. -create table project_history -( - id bigserial primary key, - project bigint references project(id), - validity tstzrange, - organization bigint references organization(id), - origin bigint references origin(id), - name text, - description text, - homepage text, - doap jsonb -); -- 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 primary key, 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 ); create index on directory using gin (dir_entries); create index on directory using gin (file_entries); create index on directory using gin (rev_entries); -- A directory entry pointing to a sub-directory. create table directory_entry_dir ( id bigserial primary key, target sha1_git, -- id of target directory name unix_path, -- path name, relative to containing dir perms file_perms -- unix-like permissions ); create unique index on directory_entry_dir(target, name, perms); -- A directory entry pointing to a file. create table directory_entry_file ( id bigserial primary key, target sha1_git, -- id of target file name unix_path, -- path name, relative to containing dir perms file_perms -- unix-like permissions ); create unique index on directory_entry_file(target, name, perms); -- A directory entry pointing to a revision. create table directory_entry_rev ( id bigserial primary key, target sha1_git, -- id of target revision name unix_path, -- path name, relative to containing dir perms file_perms -- unix-like permissions ); create unique index on directory_entry_rev(target, name, perms); create table person ( id bigserial primary key, name bytea not null default '', email bytea not null default '' ); create unique index on person(name, email); create type revision_type as enum ('git', 'tar', 'dsc'); -- 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 primary key, 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 references person(id), committer bigint references person(id), synthetic boolean not null default false -- true if synthetic (cf. swh-loader-tar) ); create index on revision(directory); -- either this table or the sha1_git[] column on the revision table create table revision_history ( id sha1_git references revision(id), parent_id sha1_git, parent_rank int not null default 0, -- parent position in merge commits, 0-based primary key (id, parent_rank) ); create index on revision_history(parent_id); -- 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 references origin(id), branch text, -- e.g., "master" (for VCS), or "sid" (for Debian) revision sha1_git, -- ref target, e.g., commit id - authority bigint references organization(id) not null, + authority uuid references entity(uuid), -- who is claiming to have seen the occurrence. -- Note: SWH is such an authority, and has an entry in -- the organization table. validity tstzrange, -- The time validity of this table entry. If the upper -- bound is missing, the entry is still valid. exclude using gist (origin with =, branch with =, revision with =, - authority with =, + (authority::text) with =, validity with &&), -- unicity exclusion constraint on lines where the same value is found for -- `origin`, `reference`, `revision`, `authority` and overlapping values for -- `validity`. primary key (origin, branch, revision, authority, validity) ); create index on occurrence_history(revision); -- Materialized view of occurrence_history, storing the *current* value of each -- branch, as last seen by SWH. create table occurrence ( origin bigint references origin(id), branch text, revision sha1_git, primary key(origin, branch, revision) ); -- 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 primary key, revision sha1_git, date timestamptz, date_offset smallint, name text, comment bytea, author bigint references person(id), synthetic boolean not null default false -- true if synthetic (cf. swh-loader-tar) ); create index on release(revision); diff --git a/swh/storage/storage.py b/swh/storage/storage.py index b94c5792..6ba2a83c 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,661 +1,661 @@ # Copyright (C) 2015 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from collections import defaultdict import datetime import functools import itertools import dateutil.parser import psycopg2 from psycopg2.extras import DateTimeTZRange from .db import Db from .objstorage import ObjStorage from swh.core.hashutil import ALGORITHMS def db_transaction(meth): """decorator to execute Storage methods within DB transactions The decorated method must accept a `cur` keyword argument """ @functools.wraps(meth) def _meth(self, *args, **kwargs): with self.db.transaction() as cur: return meth(self, *args, cur=cur, **kwargs) return _meth def db_transaction_generator(meth): """decorator to execute Storage methods within DB transactions, while returning a generator The decorated method must accept a `cur` keyword argument """ @functools.wraps(meth) def _meth(self, *args, **kwargs): with self.db.transaction() as cur: yield from meth(self, *args, cur=cur, **kwargs) return _meth class Storage(): """SWH storage proxy, encompassing DB and object storage """ def __init__(self, db_conn, obj_root): """ Args: db_conn: either a libpq connection string, or a psycopg2 connection obj_root: path to the root of the object storage """ if isinstance(db_conn, psycopg2.extensions.connection): self.db = Db(db_conn) else: self.db = Db.connect(db_conn) self.objstorage = ObjStorage(obj_root) def content_add(self, content): """Add content blobs to the storage Note: in case of DB errors, objects might have already been added to the object storage and will not be removed. Since addition to the object storage is idempotent, that should not be a problem. Args: content: iterable of dictionaries representing individual pieces of content to add. Each dictionary has the following keys: - data (bytes): the actual content - length (int): content length (default: -1) - one key for each checksum algorithm in swh.core.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 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( sha1_git for sha1, sha1_git, sha256 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_bytes(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', ['sha1', 'sha1_git', 'sha256', 'length', 'status'], 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 cont['sha1_git'] in missing_skipped) db.mktemp('skipped_content', cur) db.copy_to(missing_filtered, 'tmp_skipped_content', ['sha1', 'sha1_git', 'sha256', 'length', 'reason', 'status', 'origin'], cur) # move metadata in place db.skipped_content_add_from_temp(cur) @db_transaction_generator def content_missing(self, content, key_hash='sha1', cur=None): """List content missing from storage Args: content: iterable of dictionaries containing one key for each checksum algorithm in swh.core.hashutil.ALGORITHMS, mapped to the corresponding checksum, and a length key mapped to the content length. key_hash: the name of the hash used as key (default: 'sha1') Returns: an iterable of `key_hash`es missing from the storage Raises: TODO: an exception when we get a hash collision. """ db = self.db keys = ['sha1', 'sha1_git', 'sha256'] if key_hash not in keys: raise ValueError("key_hash should be one of %s" % keys) key_hash_idx = keys.index(key_hash) # Create temporary table for metadata injection db.mktemp('content', cur) db.copy_to(content, 'tmp_content', keys + ['length'], cur) for obj in db.content_missing_from_temp(cur): yield obj[key_hash_idx] @db_transaction_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 = ['sha1', 'sha1_git', 'sha256'] 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.core.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') # format the output found_hash = db.content_find(sha1=content.get('sha1'), sha1_git=content.get('sha1_git'), sha256=content.get('sha256'), cur=cur) return found_hash @db_transaction def content_exist(self, content, cur=None): """Predicate to check the presence of a content's hashes. Args: content: a dictionary entry representing one content hash. The dictionary key is one of swh.core.hashutil.ALGORITHMS. The value mapped to the corresponding checksum. Returns: a boolean indicator of presence Raises: ValueError in case the key of the dictionary is not sha1, sha1_git nor sha256. """ return self.content_find(content) is not None @db_transaction def content_find_occurrence(self, content, cur=None): """Find the content's occurrence. Args: content: a dictionary entry representing one content hash. The dictionary key is one of swh.core.hashutil.ALGORITHMS. The value mapped to the corresponding checksum. Returns: The occurrence of the content. Raises: ValueError in case the key of the dictionary is not sha1, sha1_git nor sha256. """ db = self.db c = self.content_find(content) if c is None: return None sha1, _, _ = c found_occ = db.content_find_occurrence(sha1, cur=cur) if found_occ is None: return None return {'origin_type': found_occ[0], 'origin_url': found_occ[1], 'branch': found_occ[2], 'revision': found_occ[3], 'path': found_occ[4]} 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 entry in cur_dir['entries']: entry['dir_id'] = dir_id dir_entries[entry['type']][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs)) if not dirs_missing: return db = self.db with db.transaction() as cur: dirs_missing_dict = ({'id': dir} for dir in dirs_missing) db.copy_to(dirs_missing_dict, 'directory', ['id'], cur) for entry_type, entry_list in dir_entries.items(): entries = itertools.chain.from_iterable( entries_for_dir for dir_id, entries_for_dir in entry_list.items() if dir_id in dirs_missing) db.mktemp_dir_entry(entry_type) db.copy_to( entries, 'tmp_directory_entry_%s' % entry_type, ['target', 'name', 'perms', 'dir_id'], cur, ) cur.execute('SELECT swh_directory_entry_add(%s)', (entry_type,)) @db_transaction_generator def directory_missing(self, directories, cur): """List directories missing from storage Args: an iterable of directory ids Returns: a list of missing directory ids """ db = self.db # Create temporary table for metadata injection db.mktemp('directory', cur) directories_dicts = ({'id': dir} for dir in directories) db.copy_to(directories_dicts, 'tmp_directory', ['id'], cur) for obj in db.directory_missing_from_temp(cur): yield obj[0] def directory_get(self, directory): """Get the entries for one directory""" yield from self.db.directory_walk_one(directory) def revision_add(self, revisions): """Add revisions to the storage Args: revisions: iterable of dictionaries representing the individual revisions to add. Each dict has the following keys: - id (sha1_git): id of the revision to add - date (datetime.DateTime): date the revision was written - date_offset (int): offset from UTC in minutes the revision was written - committer_date (datetime.DateTime): date the revision got added to the origin - committer_date_offset (int): offset from UTC in minutes the revision was added to the origin - type (one of 'git', 'tar'): type of the revision added - directory (sha1_git): the directory the revision points at - message (bytes): the message associated with the revision - author_name (bytes): the name of the revision author - author_email (bytes): the email of the revision author - committer_name (bytes): the name of the revision committer - committer_email (bytes): the email of the revision committer - parents (list of sha1_git): the parents of this revision """ db = self.db parents = {} for revision in revisions: id = revision['id'] cur_parents = enumerate(revision.get('parents', [])) parents[id] = [{ 'id': id, 'parent_id': parent, 'parent_rank': i } for i, parent in cur_parents] revisions_missing = list(self.revision_missing(parents.keys())) if not revisions_missing: return with db.transaction() as cur: db.mktemp_revision(cur) revisions_filtered = (revision for revision in revisions if revision['id'] in revisions_missing) db.copy_to(revisions_filtered, 'tmp_revision', ['id', 'date', 'date_offset', 'committer_date', 'committer_date_offset', 'type', 'directory', 'message', 'author_name', 'author_email', 'committer_name', 'committer_email', 'synthetic'], cur) db.revision_add_from_temp(cur) parents_filtered = itertools.chain.from_iterable( parents[id] for id in revisions_missing) db.copy_to(parents_filtered, 'revision_history', ['id', 'parent_id', 'parent_rank'], cur) @db_transaction_generator def revision_missing(self, revisions, cur): """List revisions missing from storage Args: an iterable of revision ids Returns: a list of missing revision ids """ db = self.db # Create temporary table for metadata injection db.mktemp('revision', cur) revisions_dicts = ({'id': dir, 'type': 'git'} for dir in revisions) db.copy_to(revisions_dicts, 'tmp_revision', ['id', 'type'], cur) for obj in db.revision_missing_from_temp(cur): yield obj[0] @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) """ keys = ('id', 'date', 'date_offset', 'committer_date', 'committer_date_offset', 'type', 'directory', 'message', 'author_name', 'author_email', 'committer_name', 'committer_email', 'synthetic', 'parents') db = self.db # Create temporary table for metadata injection db.mktemp('revision', cur) revisions_dicts = ({'id': rev, 'type': 'git'} for rev in revisions) db.copy_to(revisions_dicts, 'tmp_revision', ['id', 'type'], cur) for line in self.db.revision_get_from_temp(cur): data = dict(zip(keys, line)) if not data['type']: yield None continue yield data def release_add(self, releases): """Add releases to the storage Args: releases: iterable of dictionaries representing the individual releases to add. Each dict has the following keys: - id (sha1_git): id of the release to add - revision (sha1_git): id of the revision the release points to - date (datetime.DateTime): the date the release was made - date_offset (int): offset from UTC in minutes the release was made - name (bytes): the name of the release - comment (bytes): the comment associated with the release - author_name (bytes): the name of the release author - author_email (bytes): the email of the release author """ db = self.db release_ids = set(release['id'] for release in releases) releases_missing = list(self.release_missing(release_ids)) if not releases_missing: return with db.transaction() as cur: db.mktemp_release(cur) releases_filtered = (release for release in releases if release['id'] in releases_missing) db.copy_to(releases_filtered, 'tmp_release', ['id', 'revision', 'date', 'date_offset', 'name', 'comment', 'author_name', 'author_email', 'synthetic'], cur) db.release_add_from_temp(cur) @db_transaction_generator def release_missing(self, releases, cur=None): """List releases missing from storage Args: an iterable of release ids Returns: a list of missing release ids """ db = self.db # Create temporary table for metadata injection db.mktemp('release', cur) releases_dicts = ({'id': rel} for rel in releases) db.copy_to(releases_dicts, 'tmp_release', ['id'], cur) for obj in db.release_missing_from_temp(cur): yield obj[0] @db_transaction def occurrence_add(self, occurrences, cur=None): """Add occurrences to the storage Args: occurrences: iterable of dictionaries representing the individual occurrences to add. Each dict has the following keys: - origin (int): id of the origin corresponding to the occurrence - branch (str): the reference name of the occurrence - revision (sha1_git): the id of the revision pointed to by the occurrence - - authority (int): id of the authority giving the validity + - authority (uuid): id of the authority giving the validity - validity (datetime.DateTime): the validity date for the given occurrence """ db = self.db processed = [] for occurrence in occurrences: validity = occurrence['validity'] if isinstance(validity, str): validity = dateutil.parser.parse(validity) if isinstance(validity, datetime.datetime): occurrence = occurrence.copy() occurrence['validity'] = DateTimeTZRange(lower=validity) processed.append(occurrence) db.mktemp('occurrence_history', cur) db.copy_to(processed, 'tmp_occurrence_history', ['origin', 'branch', 'revision', 'authority', 'validity'], cur) db.occurrence_history_add_from_temp(cur) @db_transaction def origin_get(self, origin, cur=None): """Return the id of the given origin Args: origin: dictionary representing the individual origin to find. This dict has the following keys: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to Returns: the id of the queried origin """ query = "select id from origin where type=%s and url=%s" cur.execute(query, (origin['type'], origin['url'])) data = cur.fetchone() if not data: return None else: return data[0] @db_transaction def origin_add_one(self, origin, cur=None): """Add origin to the storage Args: origin: dictionary representing the individual origin to add. This dict has the following keys: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to Returns: the id of the added origin, or of the identical one that already exists. """ query = "select id from origin where type=%s and url=%s" cur.execute(query, (origin['type'], origin['url'])) data = cur.fetchone() if data: return data[0] insert = """insert into origin (type, url) values (%s, %s) returning id""" cur.execute(insert, (origin['type'], origin['url'])) return cur.fetchone()[0] @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 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()} diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index 6728caeb..7f4a1a5f 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,594 +1,594 @@ # Copyright (C) 2015 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import os import psycopg2 import shutil import tempfile import unittest 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.core.hashutil import hex_to_hash from swh.storage import Storage TEST_DIR = os.path.dirname(os.path.abspath(__file__)) TEST_DATA_DIR = os.path.join(TEST_DIR, '../../../../swh-storage-testdata') @attr('db') class AbstractTestStorage(DbTestFixture): """Base class for Storage testing. This class is used as-is to test local storage (see TestStorage below) and remote storage (see TestRemoteStorage in test_remote_storage.py. We need to have the two classes inherit from this base class separately to avoid nosetests running the tests from the base class twice. """ TEST_DB_DUMP = os.path.join(TEST_DATA_DIR, 'dumps/swh.dump') def setUp(self): super().setUp() self.objroot = tempfile.mkdtemp() self.storage = Storage(self.conn, self.objroot) self.cont = { 'data': b'42\n', 'length': 3, 'sha1': hex_to_hash( '34973274ccef6ab4dfaaf86599792fa9c3fe4689'), 'sha1_git': hex_to_hash( 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), 'sha256': hex_to_hash( '673650f936cb3b0a2f93ce09d81be107' '48b1b203c19e8176b4eefc1964a0cf3a'), } self.cont2 = { 'data': b'4242\n', 'length': 5, 'sha1': hex_to_hash( '61c2b3a30496d329e21af70dd2d7e097046d07b7'), 'sha1_git': hex_to_hash( '36fade77193cb6d2bd826161a0979d64c28ab4fa'), 'sha256': hex_to_hash( '859f0b154fdb2d630f45e1ecae4a8629' '15435e663248bb8461d914696fc047cd'), } self.missing_cont = { 'data': b'missing\n', 'length': 8, 'sha1': hex_to_hash( 'f9c24e2abb82063a3ba2c44efd2d3c797f28ac90'), 'sha1_git': hex_to_hash( '33e45d56f88993aae6a0198013efa80716fd8919'), 'sha256': hex_to_hash( '6bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), } self.skipped_cont = { 'length': 1024 * 1024 * 200, 'sha1_git': hex_to_hash( '33e45d56f88993aae6a0198013efa80716fd8920'), 'reason': 'Content too long', 'status': 'absent', } self.skipped_cont2 = { 'length': 1024 * 1024 * 300, 'sha1_git': hex_to_hash( '33e45d56f88993aae6a0198013efa80716fd8921'), '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.revision = { 'id': b'56789012345678901234', 'message': b'hello', 'author_name': b'Nicolas Dandrimont', 'author_email': b'nicolas@example.com', 'committer_name': b'St\xc3fano Zacchiroli', 'committer_email': b'stefano@example.com', 'parents': [b'01234567890123456789', b'23434512345123456789'], 'date': datetime.datetime(2015, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc), 'date_offset': 120, 'committer_date': datetime.datetime(2015, 1, 2, 22, 0, 0, tzinfo=datetime.timezone.utc), 'committer_date_offset': -120, 'type': 'git', 'directory': self.dir['id'], 'synthetic': False } self.revision2 = { 'id': b'87659012345678904321', 'message': b'hello again', 'author_name': 'Roberto Dicosmo', 'author_email': 'roberto@example.com', 'committer_name': 'tony', 'committer_email': 'ar@dumont.fr', 'parents': [b'01234567890123456789'], 'date': datetime.datetime(2015, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc), 'date_offset': 120, 'committer_date': datetime.datetime(2015, 1, 2, 22, 0, 0, tzinfo=datetime.timezone.utc), 'committer_date_offset': -120, 'type': 'git', 'directory': self.dir2['id'], 'synthetic': False } self.origin = { 'url': 'file:///dev/null', 'type': 'git', } self.origin2 = { 'url': 'file:///dev/zero', 'type': 'git', } self.occurrence = { 'branch': 'master', 'revision': b'67890123456789012345', - 'authority': 1, + 'authority': '5f4d4c51-498a-4e28-88b3-b3e4e8396cba', 'validity': datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc), } self.occurrence2 = { 'branch': 'master', 'revision': self.revision2['id'], - 'authority': 1, + 'authority': '5f4d4c51-498a-4e28-88b3-b3e4e8396cba', 'validity': datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc), } self.release = { 'id': b'87659012345678901234', 'name': 'v0.0.1', 'date': datetime.datetime(2015, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc), 'offset': 120, 'author_name': 'olasd', 'author_email': 'nic@olasd.fr', 'comment': 'synthetic release', 'synthetic': True } self.release2 = { 'id': b'56789012348765901234', 'name': 'v0.0.2', 'date': datetime.datetime(2015, 1, 2, 23, 0, 0, tzinfo=datetime.timezone.utc), 'offset': 120, 'author_name': 'tony', 'author_email': 'ar@dumont.fr', 'comment': 'v0.0.2\nMisc performance improvments + bug fixes', 'synthetic': False } 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', } 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', 'organization'} + tables -= {'dbversion', 'entity', 'entity_history', 'listable_entity'} for table in tables: self.cursor.execute('truncate table %s cascade' % table) self.conn.commit() super().tearDown() @istest def content_add(self): cont = self.cont self.storage.content_add([cont]) if hasattr(self.storage, 'objstorage'): self.assertIn(cont['sha1'], self.storage.objstorage) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = self.cursor.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) @istest def content_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 cont2 = self.skipped_cont2 self.storage.content_add([cont]) self.storage.content_add([cont2]) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status,' 'reason FROM skipped_content ORDER BY sha1_git') datum = self.cursor.fetchone() self.assertEqual( (datum[0], datum[1].tobytes(), datum[2], datum[3], datum[4], datum[5]), (None, cont['sha1_git'], None, cont['length'], 'absent', 'Content too long')) datum2 = self.cursor.fetchone() self.assertEqual( (datum2[0], datum2[1].tobytes(), datum2[2], datum2[3], datum2[4], datum2[5]), (None, cont2['sha1_git'], None, 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_exist_with_present_content(self): # 1. with something to find cont = self.cont self.storage.content_add([cont]) actually_present = self.storage.content_exist({'sha1': cont['sha1']}) self.assertEquals(actually_present, True, "Should be present") # 2. with something to find actually_present = self.storage.content_exist( {'sha1_git': cont['sha1_git']}) self.assertEquals(actually_present, True, "Should be present") # 3. with something to find actually_present = self.storage.content_exist( {'sha256': cont['sha256']}) self.assertEquals(actually_present, True, "Should be present") # 4. with something to find actually_present = self.storage.content_exist( {'sha1': cont['sha1'], 'sha1_git': cont['sha1_git'], 'sha256': cont['sha256']}) self.assertEquals(actually_present, True, "Should be present") @istest def content_exist_with_non_present_content(self): # 1. with something that does not exist missing_cont = self.missing_cont actually_present = self.storage.content_exist( {'sha1': missing_cont['sha1']}) self.assertEquals(actually_present, False, "Should be missing") # 2. with something that does not exist actually_present = self.storage.content_exist( {'sha1_git': missing_cont['sha1_git']}) self.assertEquals(actually_present, False, "Should be missing") # 3. with something that does not exist actually_present = self.storage.content_exist( {'sha256': missing_cont['sha256']}) self.assertEquals(actually_present, False, "Should be missing") @istest def content_exist_bad_input(self): # 1. with bad input with self.assertRaises(ValueError): self.storage.content_exist({}) # empty is bad # 2. with bad input with self.assertRaises(ValueError): self.storage.content_exist( {'unknown-sha1': 'something'}) # not the right key @istest def directory_add(self): init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) self.storage.directory_add([self.dir]) stored_data = list(self.storage.directory_get(self.dir['id'])) data_to_store = [ (self.dir['id'], ent['type'], ent['target'], ent['name'], ent['perms']) for ent in sorted(self.dir['entries'], key=lambda ent: ent['name']) ] self.assertEqual(data_to_store, stored_data) after_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([], after_missing) @istest def revision_add(self): init_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([self.revision['id']], list(init_missing)) self.storage.revision_add([self.revision]) end_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([], list(end_missing)) @istest def revision_get(self): self.storage.revision_add([self.revision]) get = list(self.storage.revision_get([self.revision['id'], self.revision2['id']])) self.assertEqual(len(get), 2) self.assertEqual(self.revision, get[0]) self.assertEqual(None, get[1]) @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 origin_add(self): self.assertIsNone(self.storage.origin_get(self.origin)) id = self.storage.origin_add_one(self.origin) self.assertEqual(self.storage.origin_get(self.origin), id) @istest def occurrence_add(self): origin_id = self.storage.origin_add_one(self.origin2) revision = self.revision.copy() revision['id'] = self.occurrence['revision'] self.storage.revision_add([revision]) occur = self.occurrence occur['origin'] = origin_id self.storage.occurrence_add([occur]) self.storage.occurrence_add([occur]) test_query = '''select origin, branch, revision, authority, validity from occurrence_history order by origin, validity''' self.cursor.execute(test_query) ret = self.cursor.fetchall() self.assertEqual(len(ret), 1) self.assertEqual((ret[0][0], ret[0][1], ret[0][2].tobytes(), ret[0][3]), (occur['origin'], occur['branch'], occur['revision'], occur['authority'])) self.assertEqual(ret[0][4].lower, occur['validity']) self.assertEqual(ret[0][4].lower_inc, True) self.assertEqual(ret[0][4].upper, datetime.datetime.max) orig_validity = occur['validity'] occur['validity'] += datetime.timedelta(hours=10) self.storage.occurrence_add([occur]) self.cursor.execute(test_query) ret = self.cursor.fetchall() self.assertEqual(len(ret), 2) self.assertEqual(ret[0][4].lower, orig_validity) self.assertEqual(ret[0][4].lower_inc, True) self.assertEqual(ret[0][4].upper, occur['validity']) self.assertEqual(ret[0][4].upper_inc, False) self.assertEqual(ret[1][4].lower, occur['validity']) self.assertEqual(ret[1][4].lower_inc, True) self.assertEqual(ret[1][4].upper, datetime.datetime.max) @istest def content_find_occurrence_with_present_content(self): # 1. with something to find # 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) occurrence = self.occurrence2 occurrence.update({'origin': origin_id}) self.storage.occurrence_add([occurrence]) # when occ = self.storage.content_find_occurrence( {'sha1': self.cont2['sha1']}) # then self.assertEquals(occ['origin_type'], self.origin2['type']) self.assertEquals(occ['origin_url'], self.origin2['url']) self.assertEquals(occ['branch'], self.occurrence2['branch']) self.assertEquals(occ['revision'], self.revision2['id']) self.assertEquals(occ['path'], self.dir2['entries'][0]['name']) occ2 = self.storage.content_find_occurrence( {'sha1_git': self.cont2['sha1_git']}) self.assertEquals(occ2['origin_type'], self.origin2['type']) self.assertEquals(occ2['origin_url'], self.origin2['url']) self.assertEquals(occ2['branch'], self.occurrence2['branch']) self.assertEquals(occ2['revision'], self.revision2['id']) self.assertEquals(occ2['path'], self.dir2['entries'][0]['name']) occ3 = self.storage.content_find_occurrence( {'sha256': self.cont2['sha256']}) self.assertEquals(occ3['origin_type'], self.origin2['type']) self.assertEquals(occ3['origin_url'], self.origin2['url']) self.assertEquals(occ3['branch'], self.occurrence2['branch']) self.assertEquals(occ3['revision'], self.revision2['id']) self.assertEquals(occ3['path'], self.dir2['entries'][0]['name']) @istest def content_find_occurrence_with_non_present_content(self): # 1. with something that does not exist missing_cont = self.missing_cont occ = self.storage.content_find_occurrence( {'sha1': missing_cont['sha1']}) self.assertEquals(occ, None, "Content does not exist so no occurrence") # 2. with something that does not exist occ = self.storage.content_find_occurrence( {'sha1_git': missing_cont['sha1_git']}) self.assertEquals(occ, None, "Content does not exist so no occurrence") # 3. with something that does not exist occ = self.storage.content_find_occurrence( {'sha256': missing_cont['sha256']}) self.assertEquals(occ, None, "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: self.storage.content_find_occurrence({}) # empty is bad self.assertIn('content keys', cm.exception.args[0]) # 2. with bad input with self.assertRaises(ValueError) as cm: self.storage.content_find_occurrence( {'unknown-sha1': 'something'}) # not the right key self.assertIn('content keys', cm.exception.args[0]) @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) class TestStorage(AbstractTestStorage, 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)