No OneTemporary
Actions

Size

115 KB

Subscribers

None

View Options

	diff --git a/sql/swh-func.sql b/sql/swh-func.sql
	index 584fb8d38..568028d61 100644
	--- a/sql/swh-func.sql
	+++ b/sql/swh-func.sql
	@@ -1,858 +1,885 @@
	-- 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_<foo> 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 $$
	create temporary table tmp_release (
	like release including defaults,
	author_name bytea not null default '',
	author_email bytea not null default ''
	) on commit drop;
	alter table tmp_release drop column author;
	$$;

	+-- create a temporary table for entity_history, sans id
	+create or replace function swh_mktemp_entity_history()
	+ returns void
	+ language sql
	+as $$
	+ create temporary table tmp_entity_history (
	+ like entity_history including defaults);
	+ alter table tmp_entity_history drop column id;
	+$$;
	+

	-- 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 tmp_directory as d
	set %1$s_entries = new_entries.entries
	from new_entries
	where d.id = new_entries.dir_id
	', typ);

	return;
	end
	$$;

	-- Insert the data from tmp_directory, tmp_directory_entry_file,
	-- tmp_directory_entry_dir, tmp_directory_entry_rev into their final
	-- tables.
	--
	-- Prerequisites:
	-- directory ids in tmp_directory
	-- entries in tmp_directory_entry_{file,dir,rev}
	--
	create or replace function swh_directory_add()
	returns void
	language plpgsql
	as $$
	begin
	perform swh_directory_entry_add('file');
	perform swh_directory_entry_add('dir');
	perform swh_directory_entry_add('rev');

	insert into directory
	select * from tmp_directory t
	where not exists (
	select 1 from directory d
	where d.id = t.id);

	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,
	metadata jsonb,
	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 $$
	select revision.id, date, date_offset,
	committer_date, committer_date_offset,
	type, directory, message,
	author.name as author_name, author.email as author_email,
	committer.name as committer_name, committer.email as committer_email,
	revision.metadata, revision.synthetic
	from swh_revision_list(root_revision) as rev_list
	join revision on revision.id = rev_list
	join person as author on revision.author = author.id
	join person as committer on revision.committer = committer.id;
	$$;

	-- 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,
	metadata jsonb,
	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 $$
	begin
	return query
	select t.id, r.date, r.date_offset,
	r.committer_date, r.committer_date_offset,
	r.type, r.directory, r.message,
	a.name, a.email, c.name, c.email, r.metadata, r.synthetic,
	array_agg(rh.parent_id::bytea order by rh.parent_rank)
	as parents
	from tmp_revision t
	left join revision r on t.id = r.id
	left join person a on a.id = r.author
	left join person c on c.id = r.committer
	left join revision_history rh on rh.id = r.id
	group by t.id, a.name, a.email, r.date, r.date_offset,
	c.name, c.email, r.committer_date, r.committer_date_offset,
	r.type, r.directory, r.message, r.metadata, r.synthetic;
	return;
	end
	$$;

	-- 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, metadata, 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.metadata, 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 entries in entity_history from tmp_entity_history
	+--
	+-- TODO: do something smarter to compress the entries if the data
	+-- didn't change.
	+create or replace function swh_entity_history_add()
	+ returns void
	+ language plpgsql
	+as $$
	+begin
	+ insert into entity_history (
	+ uuid, parent, name, type, description, homepage, active, generated,
	+ lister, lister_metadata, doap, validity
	+ ) select * from tmp_entity_history;
	+ return;
	+end
	+$$;
	+

	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 $$
	select relname::text as label, reltuples::bigint as value
	from pg_class
	where oid in (
	'public.content'::regclass,
	'public.directory'::regclass,
	'public.directory_entry_dir'::regclass,
	'public.directory_entry_file'::regclass,
	'public.directory_entry_rev'::regclass,
	'public.occurrence'::regclass,
	'public.occurrence_history'::regclass,
	'public.origin'::regclass,
	'public.person'::regclass,
	'public.entity'::regclass,
	'public.entity_history'::regclass,
	'public.release'::regclass,
	'public.revision'::regclass,
	'public.revision_history'::regclass,
	'public.skipped_content'::regclass
	);
	$$;
	diff --git a/sql/swh-schema.sql b/sql/swh-schema.sql
	index 2bd13c164..a550a4939 100644
	--- a/sql/swh-schema.sql
	+++ b/sql/swh-schema.sql
	@@ -1,411 +1,411 @@
	---
	--- 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(29, now(), 'Work In Progress');
	+ values(30, 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');

	-- 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);


	-- 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 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),
	metadata jsonb, -- extra metadata (tarball checksums, extra commit information, etc...)
	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 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::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/api/client.py b/swh/storage/api/client.py
	index 5d9e3e676..e2ba78655 100644
	--- a/swh/storage/api/client.py
	+++ b/swh/storage/api/client.py
	@@ -1,135 +1,138 @@
	# 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 pickle

	import requests

	from swh.core.serializers import msgpack_dumps, msgpack_loads, SWHJSONDecoder


	def encode_data(data):
	return msgpack_dumps(data)


	def decode_response(response):
	content_type = response.headers['content-type']

	if content_type.startswith('application/x-msgpack'):
	r = msgpack_loads(response.content)
	elif content_type.startswith('application/json'):
	r = response.json(cls=SWHJSONDecoder)
	else:
	raise ValueError('Wrong content type `%s` for API response'
	% content_type)

	return r


	class RemoteStorage():
	"""Proxy to a remote storage API"""
	def __init__(self, base_url):
	self.base_url = base_url
	self.session = requests.Session()

	def url(self, endpoint):
	return '%s%s' % (self.base_url, endpoint)

	def post(self, endpoint, data):
	response = self.session.post(
	self.url(endpoint),
	data=encode_data(data),
	headers={'content-type': 'application/x-msgpack'},
	)

	# XXX: this breaks language-independence and should be
	# replaced by proper unserialization
	if response.status_code == 400:
	raise pickle.loads(decode_response(response))

	return decode_response(response)

	def get(self, endpoint, data=None):
	response = self.session.get(
	self.url(endpoint),
	params=data,
	)

	if response.status_code == 404:
	return None

	# XXX: this breaks language-independence and should be
	# replaced by proper unserialization
	if response.status_code == 400:
	raise pickle.loads(decode_response(response))

	else:
	return decode_response(response)

	def content_add(self, content):
	return self.post('content/add', {'content': content})

	def content_missing(self, content, key_hash='sha1'):
	return self.post('content/missing', {'content': content,
	'key_hash': key_hash})

	def content_exist(self, content):
	return self.post('content/present', {'content': content})

	def content_find_occurrence(self, content):
	return self.post('content/occurrence', {'content': content})

	def directory_add(self, directories):
	return self.post('directory/add', {'directories': directories})

	def directory_missing(self, directories):
	return self.post('directory/missing', {'directories': directories})

	def directory_get(self, directory):
	return [tuple(entry)
	for entry in self.get('directory', {'directory': directory})]

	def revision_get(self, revisions):
	return self.post('revision', {'revisions': revisions})

	def revision_add(self, revisions):
	return self.post('revision/add', {'revisions': revisions})

	def revision_missing(self, revisions):
	return self.post('revision/missing', {'revisions': revisions})

	def release_add(self, releases):
	return self.post('release/add', {'releases': releases})

	def release_missing(self, releases):
	return self.post('release/missing', {'releases': releases})

	def occurrence_add(self, occurrences):
	return self.post('occurrence/add', {'occurrences': occurrences})

	def origin_get(self, origin):
	origin = self.get('origin', origin)

	if not origin:
	return None
	else:
	return origin['id']

	def origin_add_one(self, origin):
	return self.post('origin', {'origin': origin})

	def fetch_history_start(self, origin_id):
	return self.post('fetch_history/start', {'origin_id': origin_id})

	def fetch_history_end(self, fetch_history_id, data):
	return self.post('fetch_history/end',
	{'fetch_history_id': fetch_history_id,
	'data': data})

	def fetch_history_get(self, fetch_history_id):
	return self.get('fetch_history', {'id': fetch_history_id})

	+ def entity_add(self, entities):
	+ return self.post('entity/add', {'entities': entities})
	+
	def stat_counters(self):
	return self.get('stat/counters')
	diff --git a/swh/storage/api/server.py b/swh/storage/api/server.py
	index 12b7962fc..d69d2f512 100644
	--- a/swh/storage/api/server.py
	+++ b/swh/storage/api/server.py
	@@ -1,202 +1,208 @@
	# 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 json
	import logging
	import pickle

	from flask import Flask, Request, Response, abort, g, request

	from swh.core import config
	from swh.core.serializers import msgpack_dumps, msgpack_loads, SWHJSONDecoder
	from swh.storage import Storage

	DEFAULT_CONFIG = {
	'db': ('str', 'dbname=softwareheritage-dev'),
	'storage_base': ('str', '/tmp/swh-storage/test'),
	}


	class BytesRequest(Request):
	"""Request with proper escaping of arbitrary byte sequences."""
	encoding = 'utf-8'
	encoding_errors = 'surrogateescape'


	app = Flask(__name__)
	app.request_class = BytesRequest


	def encode_data(data):
	return Response(
	msgpack_dumps(data),
	mimetype='application/x-msgpack',
	)


	def decode_request(request):
	content_type = request.mimetype
	data = request.get_data()

	if content_type == 'application/x-msgpack':
	r = msgpack_loads(data)
	elif content_type == 'application/json':
	r = json.loads(data, cls=SWHJSONDecoder)
	else:
	raise ValueError('Wrong content type `%s` for API request'
	% content_type)

	return r


	@app.errorhandler(Exception)
	def error_handler(exception):
	# XXX: this breaks language-independence and should be
	# replaced by proper serialization of errors
	response = encode_data(pickle.dumps(exception))
	response.status_code = 400
	return response


	@app.before_request
	def before_request():
	g.storage = Storage(app.config['db'], app.config['storage_base'])


	@app.route('/')
	def index():
	return 'Hello'


	@app.route('/content/missing', methods=['POST'])
	def content_missing():
	return encode_data(g.storage.content_missing(**decode_request(request)))


	@app.route('/content/present', methods=['POST'])
	def content_exist():
	return encode_data(g.storage.content_exist(**decode_request(request)))


	@app.route('/content/occurrence', methods=['POST'])
	def content_find_occurrence():
	res = g.storage.content_find_occurrence(**decode_request(request))
	return encode_data(res)


	@app.route('/content/add', methods=['POST'])
	def content_add():
	return encode_data(g.storage.content_add(**decode_request(request)))


	@app.route('/directory/missing', methods=['POST'])
	def directory_missing():
	return encode_data(g.storage.directory_missing(**decode_request(request)))


	@app.route('/directory/add', methods=['POST'])
	def directory_add():
	return encode_data(g.storage.directory_add(**decode_request(request)))


	@app.route('/directory', methods=['GET'])
	def directory_get():
	dir = request.args['directory'].encode('utf-8', 'surrogateescape')
	return encode_data(g.storage.directory_get(dir))


	@app.route('/revision/add', methods=['POST'])
	def revision_add():
	return encode_data(g.storage.revision_add(**decode_request(request)))


	@app.route('/revision', methods=['POST'])
	def revision_get():
	return encode_data(g.storage.revision_get(**decode_request(request)))


	@app.route('/revision/missing', methods=['POST'])
	def revision_missing():
	return encode_data(g.storage.revision_missing(**decode_request(request)))


	@app.route('/release/add', methods=['POST'])
	def release_add():
	return encode_data(g.storage.release_add(**decode_request(request)))


	@app.route('/release/missing', methods=['POST'])
	def release_missing():
	return encode_data(g.storage.release_missing(**decode_request(request)))


	@app.route('/occurrence/add', methods=['POST'])
	def occurrence_add():
	return encode_data(g.storage.occurrence_add(**decode_request(request)))


	@app.route('/origin', methods=['GET'])
	def origin_get():
	origin = {
	'type': request.args['type'],
	'url': request.args['url'],
	}

	id = g.storage.origin_get(origin)

	if not id:
	abort(404)
	else:
	origin['id'] = id
	return encode_data(origin)


	@app.route('/origin', methods=['POST'])
	def origin_add_one():
	return encode_data(g.storage.origin_add_one(**decode_request(request)))


	@app.route('/fetch_history', methods=['GET'])
	def fetch_history_get():
	return encode_data(g.storage.fetch_history_get(request.args['id']))


	@app.route('/fetch_history/start', methods=['POST'])
	def fetch_history_start():
	return encode_data(
	g.storage.fetch_history_start(**decode_request(request)))


	@app.route('/fetch_history/end', methods=['POST'])
	def fetch_history_end():
	return encode_data(
	g.storage.fetch_history_end(**decode_request(request)))


	+@app.route('/entity/add', methods=['POST'])
	+def entity_add():
	+ return encode_data(
	+ g.storage.entity_add(**decode_request(request)))
	+
	+
	@app.route('/stat/counters', methods=['GET'])
	def stat_counters():
	return encode_data(g.storage.stat_counters())


	def run_from_webserver(environ, start_response):
	"""Run the WSGI app from the webserver, loading the configuration."""

	config_path = '/etc/softwareheritage/storage/storage.ini'

	app.config.update(config.read(config_path, DEFAULT_CONFIG))

	handler = logging.StreamHandler()
	app.logger.addHandler(handler)

	return app(environ, start_response)


	if __name__ == '__main__':
	import sys

	app.config.update(config.read(sys.argv[1], DEFAULT_CONFIG))

	host = sys.argv[2] if len(sys.argv) >= 3 else '127.0.0.1'
	app.run(host, debug=True)
	diff --git a/swh/storage/db.py b/swh/storage/db.py
	index c30ee4e27..63eb50e11 100644
	--- a/swh/storage/db.py
	+++ b/swh/storage/db.py
	@@ -1,327 +1,341 @@
	# 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 binascii
	import datetime
	import functools
	import json
	import psycopg2
	import tempfile

	from contextlib import contextmanager

	TMP_CONTENT_TABLE = 'tmp_content'


	def stored_procedure(stored_proc):
	"""decorator to execute remote stored procedure, specified as argument

	Generally, the body of the decorated function should be empty. If it is
	not, the stored procedure will be executed first; the function body then.

	"""
	def wrap(meth):
	@functools.wraps(meth)
	def _meth(self, args, *kwargs):
	cur = kwargs.get('cur', None)
	self._cursor(cur).execute('SELECT %s()' % stored_proc)
	meth(self, args, *kwargs)
	return _meth
	return wrap


	def jsonize(value):
	"""Convert a value to a psycopg2 JSON object if necessary"""
	if isinstance(value, dict):
	return psycopg2.extras.Json(value)

	return value


	def entry_to_bytes(entry):
	"""Convert an entry coming from the database to bytes"""
	if isinstance(entry, memoryview):
	return entry.tobytes()
	if isinstance(entry, list):
	return [entry_to_bytes(value) for value in entry]
	return entry


	def line_to_bytes(line):
	"""Convert a line coming from the database to bytes"""
	return line.__class__(entry_to_bytes(entry) for entry in line)


	def cursor_to_bytes(cursor):
	"""Yield all the data from a cursor as bytes"""
	yield from (line_to_bytes(line) for line in cursor)


	class Db:
	"""Proxy to the SWH DB, with wrappers around stored procedures

	"""

	@classmethod
	def connect(cls, args, *kwargs):
	"""factory method to create a DB proxy

	Accepts all arguments of psycopg2.connect; only some specific
	possibilities are reported below.

	Args:
	connstring: libpq2 connection string

	"""
	conn = psycopg2.connect(args, *kwargs)
	return cls(conn)

	def _cursor(self, cur_arg):
	"""get a cursor: from cur_arg if given, or a fresh one otherwise

	meant to avoid boilerplate if/then/else in methods that proxy stored
	procedures

	"""
	if cur_arg is not None:
	return cur_arg
	# elif self.cur is not None:
	# return self.cur
	else:
	return self.conn.cursor()

	def __init__(self, conn):
	"""create a DB proxy

	Args:
	conn: psycopg2 connection to the SWH DB

	"""
	self.conn = conn

	@contextmanager
	def transaction(self):
	"""context manager to execute within a DB transaction

	Yields:
	a psycopg2 cursor

	"""
	with self.conn.cursor() as cur:
	try:
	yield cur
	self.conn.commit()
	except:
	if not self.conn.closed:
	self.conn.rollback()
	raise

	def mktemp(self, tblname, cur=None):
	self._cursor(cur).execute('SELECT swh_mktemp(%s)', (tblname,))

	def mktemp_dir_entry(self, entry_type, cur=None):
	self._cursor(cur).execute('SELECT swh_mktemp_dir_entry(%s)',
	(('directory_entry_%s' % entry_type),))

	@stored_procedure('swh_mktemp_revision')
	def mktemp_revision(self, cur=None): pass

	@stored_procedure('swh_mktemp_release')
	def mktemp_release(self, cur=None): pass

	+ @stored_procedure('swh_mktemp_entity_history')
	+ def mktemp_entity_history(self, cur=None): pass
	+
	def copy_to(self, items, tblname, columns, cur=None, item_cb=None):
	def escape(data):
	if data is None:
	return ''
	if isinstance(data, bytes):
	return '\\x%s' % binascii.hexlify(data).decode('ascii')
	elif isinstance(data, str):
	return '"%s"' % data.replace('"', '""')
	elif isinstance(data, datetime.datetime):
	# We escape twice to make sure the string generated by
	# isoformat gets escaped
	return escape(data.isoformat())
	elif isinstance(data, dict):
	return escape(json.dumps(data))
	elif isinstance(data, list):
	return escape("{%s}" % ','.join(escape(d) for d in data))
	elif isinstance(data, psycopg2.extras.Range):
	# We escape twice here too, so that we make sure
	# everything gets passed to copy properly
	return escape(
	'%s%s,%s%s' % (
	'[' if data.lower_inc else '(',
	'-infinity' if data.lower_inf else escape(data.lower),
	'infinity' if data.upper_inf else escape(data.upper),
	']' if data.upper_inc else ')',
	)
	)
	else:
	# We don't escape here to make sure we pass literals properly
	return str(data)
	with tempfile.TemporaryFile('w+') as f:
	for d in items:
	if item_cb is not None:
	item_cb(d)
	line = [escape(d.get(k)) for k in columns]
	f.write(','.join(line))
	f.write('\n')
	f.seek(0)
	self._cursor(cur).copy_expert('COPY %s (%s) FROM STDIN CSV' % (
	tblname, ', '.join(columns)), f)

	@stored_procedure('swh_content_add')
	def content_add_from_temp(self, cur=None): pass

	@stored_procedure('swh_directory_add')
	def directory_add_from_temp(self, cur=None): pass

	@stored_procedure('swh_skipped_content_add')
	def skipped_content_add_from_temp(self, cur=None): pass

	@stored_procedure('swh_revision_add')
	def revision_add_from_temp(self, cur=None): pass

	@stored_procedure('swh_release_add')
	def release_add_from_temp(self, cur=None): pass

	@stored_procedure('swh_occurrence_history_add')
	def occurrence_history_add_from_temp(self, cur=None): pass

	+ @stored_procedure('swh_entity_history_add')
	+ def entity_history_add_from_temp(self, cur=None): pass
	+
	def content_missing_from_temp(self, cur=None):
	cur = self._cursor(cur)

	cur.execute("""SELECT sha1, sha1_git, sha256
	FROM swh_content_missing()""")

	yield from cursor_to_bytes(cur)

	def skipped_content_missing_from_temp(self, cur=None):
	cur = self._cursor(cur)

	cur.execute("""SELECT sha1, sha1_git, sha256
	FROM swh_skipped_content_missing()""")

	yield from cursor_to_bytes(cur)

	def content_find(self, sha1=None, sha1_git=None, sha256=None, cur=None):
	"""Find the content optionally on a combination of the following
	checksums sha1, sha1_git or sha256.

	Args:
	sha1: sha1 content
	git_sha1: the sha1 computed `a la git` sha1 of the content
	sha256: sha256 content

	Returns:
	The triplet (sha1, sha1_git, sha256) if found or None.

	"""
	cur = self._cursor(cur)

	cur.execute("""SELECT sha1, sha1_git, sha256
	FROM swh_content_find(%s, %s, %s)
	LIMIT 1""", (sha1, sha1_git, sha256))

	content = line_to_bytes(cur.fetchone())
	return None if content == (None, None, None) else content

	def content_find_occurrence(self, sha1, cur=None):
	"""Find one content's occurrence.

	Args:
	sha1: sha1 content
	cur: cursor to use

	Returns:
	One occurrence for that particular sha1

	"""
	cur = self._cursor(cur)

	cur.execute("""SELECT *
	FROM swh_content_find_occurrence(%s)
	LIMIT 1""",
	(sha1, ))

	return line_to_bytes(cur.fetchone())

	def directory_missing_from_temp(self, cur=None):
	cur = self._cursor(cur)
	cur.execute('SELECT * FROM swh_directory_missing()')
	yield from cursor_to_bytes(cur)

	def directory_walk_one(self, directory, cur=None):
	cur = self._cursor(cur)
	cur.execute('SELECT * FROM swh_directory_walk_one(%s)', (directory,))
	yield from cursor_to_bytes(cur)

	def revision_missing_from_temp(self, cur=None):
	cur = self._cursor(cur)

	cur.execute('SELECT id FROM swh_revision_missing() as r(id)')

	yield from cursor_to_bytes(cur)

	def revision_get_from_temp(self, cur=None):
	cur = self._cursor(cur)
	cur.execute('SELECT * FROM swh_revision_get()')
	yield from cursor_to_bytes(cur)

	def release_missing_from_temp(self, cur=None):
	cur = self._cursor(cur)
	cur.execute('SELECT id FROM swh_release_missing() as r(id)')
	yield from cursor_to_bytes(cur)

	def stat_counters(self, cur=None):
	cur = self._cursor(cur)
	cur.execute('SELECT * FROM swh_stat_counters()')
	yield from cur

	fetch_history_cols = ['origin', 'date', 'status', 'result', 'stdout',
	'stderr', 'duration']

	def create_fetch_history(self, fetch_history, cur=None):
	"""Create a fetch_history entry with the data in fetch_history"""
	cur = self._cursor(cur)
	query = '''INSERT INTO fetch_history (%s)
	VALUES (%s) RETURNING id''' % (
	','.join(self.fetch_history_cols),
	','.join(['%s'] * len(self.fetch_history_cols))
	)
	cur.execute(query, [fetch_history.get(col) for col in
	self.fetch_history_cols])

	return cur.fetchone()[0]

	def get_fetch_history(self, fetch_history_id, cur=None):
	"""Get a fetch_history entry with the given id"""
	cur = self._cursor(cur)
	query = '''SELECT %s FROM fetch_history WHERE id=%%s''' % (
	', '.join(self.fetch_history_cols),
	)
	cur.execute(query, (fetch_history_id,))

	data = cur.fetchone()

	if not data:
	return None

	ret = {'id': fetch_history_id}
	for i, col in enumerate(self.fetch_history_cols):
	ret[col] = data[i]

	return ret

	def update_fetch_history(self, fetch_history, cur=None):
	"""Update the fetch_history entry from the data in fetch_history"""
	cur = self._cursor(cur)
	query = '''UPDATE fetch_history
	SET %s
	WHERE id=%%s''' % (
	','.join('%s=%%s' % col for col in self.fetch_history_cols)
	)
	cur.execute(query, [jsonize(fetch_history.get(col)) for col in
	self.fetch_history_cols + ['id']])
	+
	+ base_entity_cols = ['uuid', 'parent', 'name', 'type',
	+ 'description', 'homepage', 'active',
	+ 'generated', 'lister', 'lister_metadata',
	+ 'doap']
	+
	+ entity_cols = base_entity_cols + ['last_seen', 'last_id']
	+ entity_history_cols = base_entity_cols + ['id', 'validity']
	diff --git a/swh/storage/storage.py b/swh/storage/storage.py
	index 2af0a4248..aa5e65554 100644
	--- a/swh/storage/storage.py
	+++ b/swh/storage/storage.py
	@@ -1,669 +1,700 @@
	# 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:
	# 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]

	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
	- 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

	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', 'metadata',
	'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', 'metadata',
	'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 (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 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 (uuid): the uuid of the generating entity
	+ - lister_metadata (dict): lister-specific entity metadata
	+ - doap (dict): DOAP data 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
	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 312ed0450..e9caee3e4 100644
	--- a/swh/storage/tests/test_storage.py
	+++ b/swh/storage/tests/test_storage.py
	@@ -1,600 +1,671 @@
	# 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.maxDiff = None
	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'],
	'metadata': {'checksums': {'sha1': 'tarball-sha1',
	'sha256': 'tarball-sha256'},
	'signed-off-by': 'some-dude'},
	'synthetic': True
	}

	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'],
	'metadata': None,
	'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': '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': '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',
	}

	+ self.entity1 = {
	+ 'uuid': 'f96a7ec1-0058-4920-90cc-7327e4b5a4bf',
	+ # GitHub users
	+ 'parent': 'ad6df473-c1d2-4f40-bc58-2b091d4a750e',
	+ 'name': 'github:user:olasd',
	+ 'type': 'person',
	+ 'description': 'Nicolas Dandrimont',
	+ 'homepage': 'http://example.com',
	+ 'active': True,
	+ 'generated': True,
	+ # swh.lister.github
	+ 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
	+ 'lister_metadata': {
	+ 'id': 12877,
	+ 'type': 'user',
	+ 'last_activity': '2015-11-03',
	+ },
	+ 'doap': None,
	+ 'validity': [
	+ datetime.datetime(2015, 11, 3, 11, 0, 0,
	+ tzinfo=datetime.timezone.utc),
	+ ]
	+ }
	+
	+ self.entity1_query = {
	+ 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
	+ 'lister_metadata': {
	+ 'id': 12877,
	+ 'type': 'user',
	+ },
	+ }
	+
	+ self.entity2 = {
	+ 'uuid': '3903d075-32d6-46d4-9e29-0aef3612c4eb',
	+ # GitHub users
	+ 'parent': 'ad6df473-c1d2-4f40-bc58-2b091d4a750e',
	+ 'name': 'github:user:zacchiro',
	+ 'type': 'person',
	+ 'description': 'Stefano Zacchiroli',
	+ 'homepage': 'http://example.com',
	+ 'active': True,
	+ 'generated': True,
	+ # swh.lister.github
	+ 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
	+ 'lister_metadata': {
	+ 'id': 216766,
	+ 'type': 'user',
	+ 'last_activity': '2015-11-03',
	+ },
	+ 'doap': None,
	+ 'validity': [
	+ datetime.datetime(2015, 11, 3, 11, 0, 0,
	+ tzinfo=datetime.timezone.utc),
	+ ]
	+ }
	+
	+ self.entity2_query = {
	+ 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
	+ 'lister_metadata': {
	+ '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'}

	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()

	@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(get[0], self.revision)
	self.assertEqual(get[1], None)

	@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 entity_get_from_lister_metadata(self):
	+ self.storage.entity_add([self.entity1])
	+
	@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)

File Metadata

Mime Type: text/x-diff
Expires: Fri, Jul 4, 11:25 AM (3 w, 2 d ago)
Storage Engine: blob
Storage Format: Raw Data
Storage Handle: 3452539

No OneTemporaryActions

View Options

File Metadata

Event Timeline

No OneTemporary
Actions