diff --git a/sql/swh-func.sql b/sql/swh-func.sql index 1ff02edd..65ff6983 100644 --- a/sql/swh-func.sql +++ b/sql/swh-func.sql @@ -1,383 +1,397 @@ -- create a temporary table called tmp_TBLNAME, mimicking existing table -- TBLNAME -- -- Args: -- tblname: name of the table to mimick create or replace function swh_mktemp(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table tmp_%I (like %I including defaults) on commit drop ', tblname, tblname); return; end $$; -- create a temporary table for directory entries called tmp_TBLNAME, -- mimicking existing table TBLNAME with an extra dir_id (sha1_git) -- column, and dropping the id column. -- -- This is used to create the tmp_directory_entry_ tables. -- -- Args: -- tblname: name of the table to mimick create or replace function swh_mktemp_dir_entry(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table tmp_%I (like %I including defaults, dir_id sha1_git) on commit drop; alter table tmp_%I drop column id; ', tblname, tblname, tblname, tblname); return; end $$; -- create a temporary table for revisions called tmp_revisions, -- mimicking existing table revision, replacing the foreign keys to -- people with an email and name field -- create or replace function swh_mktemp_revision() returns void language plpgsql as $$ begin create temporary table tmp_revision ( like revision including defaults, author_name text not null default '', author_email text not null default '', committer_name text not null default '', committer_email text not null default '' ) on commit drop; alter table tmp_revision drop column author; alter table tmp_revision drop column committer; return; end $$; -- 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 plpgsql as $$ begin create temporary table tmp_release ( like release including defaults, author_name text not null default '', author_email text not null default '' ) on commit drop; alter table tmp_release drop column author; return; end $$; -- 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 $$ begin return query select sha1, sha1_git, sha256 from tmp_content except select sha1, sha1_git, sha256 from content; return; end $$; -- 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 $$ declare rows bigint; begin insert into content (sha1, sha1_git, sha256, length, status) select distinct sha1, sha1_git, sha256, length, status from tmp_content where (sha1, sha1_git, sha256) in (select * from swh_content_missing()); -- TODO XXX use postgres 9.5 "UPSERT" support here, when available. -- Specifically, using "INSERT .. ON CONFLICT IGNORE" we can avoid -- the extra swh_content_missing() query here. return; end $$; -- 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 directory language plpgsql as $$ begin return query select id from tmp_directory except select id from directory; return; end $$; -- Add tmp_directory_entry_dir entries to directory_entry_dir and -- directory_list_dir, skipping duplicates in directory_entry_dir. -- -- operates in bulk: 0. swh_mktemp_dir_entry('directory_entry_dir'), 1 COPY to -- tmp_directory_entry_dir, 2. call this function create or replace function swh_directory_entry_dir_add() returns void language plpgsql as $$ begin insert into directory_entry_dir (target, name, perms, atime, mtime, ctime) select distinct t.target, t.name, t.perms, t.atime, t.mtime, t.ctime from tmp_directory_entry_dir t where not exists ( select 1 from directory_entry_dir i where t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime); insert into directory_list_dir (entry_id, dir_id) select i.id, t.dir_id from tmp_directory_entry_dir t inner join directory_entry_dir i on t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime; return; end $$; -- Add tmp_directory_entry_file entries to directory_entry_file and -- directory_list_file, skipping duplicates in directory_entry_file. -- -- operates in bulk: 0. swh_mktemp_dir_entry('directory_entry_file'), 1 COPY to -- tmp_directory_entry_file, 2. call this function create or replace function swh_directory_entry_file_add() returns void language plpgsql as $$ begin insert into directory_entry_file (target, name, perms, atime, mtime, ctime) select distinct t.target, t.name, t.perms, t.atime, t.mtime, t.ctime from tmp_directory_entry_file t where not exists ( select 1 from directory_entry_file i where t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime); insert into directory_list_file (entry_id, dir_id) select i.id, t.dir_id from tmp_directory_entry_file t inner join directory_entry_file i on t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime; return; end $$; -- Add tmp_directory_entry_rev entries to directory_entry_rev and -- directory_list_rev, skipping duplicates in directory_entry_rev. -- -- operates in bulk: 0. swh_mktemp_dir_entry('directory_entry_rev'), 1 COPY to -- tmp_directory_entry_rev, 2. call this function create or replace function swh_directory_entry_rev_add() returns void language plpgsql as $$ begin insert into directory_entry_rev (target, name, perms, atime, mtime, ctime) select distinct t.target, t.name, t.perms, t.atime, t.mtime, t.ctime from tmp_directory_entry_rev t where not exists ( select 1 from directory_entry_rev i where t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime); insert into directory_list_rev (entry_id, dir_id) select i.id, t.dir_id from tmp_directory_entry_rev t inner join directory_entry_rev i on t.target = i.target and t.name = i.name and t.perms = i.perms and t.atime is not distinct from i.atime and t.mtime is not distinct from i.mtime and t.ctime is not distinct from i.ctime; return; end $$; -- 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 text, -- type of entry (one of 'dir', 'file', 'rev') target sha1_git, -- id of target name unix_path, -- path name, relative to containing dir perms file_perms, -- unix-like permissions atime timestamptz, -- time of last access mtime timestamptz, -- time of last modification ctime timestamptz -- time of last status change ); -- List a single level of directory walked_dir_id create or replace function swh_directory_walk_one(walked_dir_id sha1_git) returns setof directory_entry language plpgsql as $$ begin return query ( select dir_id, 'dir' as type, target, name, perms, atime, mtime, ctime from directory_list_dir l left join directory_entry_dir d on l.entry_id = d.id where l.dir_id = walked_dir_id union select dir_id, 'file' as type, target, name, perms, atime, mtime, ctime from directory_list_file l left join directory_entry_file d on l.entry_id = d.id where l.dir_id = walked_dir_id union select dir_id, 'rev' as type, target, name, perms, atime, mtime, ctime from directory_list_rev l left join directory_entry_rev d on l.entry_id = d.id where l.dir_id = walked_dir_id ) order by name; return; end $$; -- List missing revisions from tmp_revision create or replace function swh_revision_missing() returns setof sha1_git language plpgsql as $$ begin return query select id from tmp_revision except select id from revision; return; end $$; -- 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 $$ begin perform swh_person_add_from_revision(); insert into revision (id, date, date_offset, committer_date, committer_date_offset, type, directory, message, author, committer) select t.id, t.date, t.date_offset, t.committer_date, t.committer_date_offset, t.type, t.directory, t.message, a.id, c.id from tmp_revision t left join person a on a.name = t.author_name and a.email = t.author_email left join person c on c.name = t.committer_name and c.email = t.committer_email; return; end $$; +-- List missing releases from tmp_release +create or replace function swh_release_missing() + returns setof sha1_git + language plpgsql +as $$ +begin + return query + select id from tmp_release + except + select id from release; + return; +end +$$; + -- 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 $$ begin perform swh_person_add_from_release(); insert into release (id, revision, date, date_offset, name, comment, author) select t.id, t.revision, t.date, t.date_offset, t.name, t.comment, a.id from tmp_release t left join person a on a.name = t.author_name and a.email = t.author_email; return; end $$; diff --git a/swh/storage/db.py b/swh/storage/db.py index 513b701e..abee735a 100644 --- a/swh/storage/db.py +++ b/swh/storage/db.py @@ -1,179 +1,186 @@ # 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 csv import functools 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 entry_to_bytes(entry): """Convert an entry coming from the database to bytes""" if isinstance(entry, memoryview): return entry.tobytes() 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 def copy_to(self, items, tblname, columns, cur=None, item_cb=None): def escape(data): if data is None: return None if isinstance(data, bytes): return '\\x%s' % binascii.hexlify(data).decode('ascii') else: return str(data) with tempfile.TemporaryFile('w+', newline='') as f: writer = csv.writer(f, delimiter=',', quotechar='"', quoting=csv.QUOTE_ALL) for d in items: if item_cb is not None: item_cb(d) line = [escape(d.get(k)) for k in columns] writer.writerow(line) 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_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 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 directory_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute("SELECT id 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 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) diff --git a/swh/storage/storage.py b/swh/storage/storage.py index a9d41ae5..4dadf133 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,339 +1,351 @@ # 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 functools import itertools import psycopg2 from collections import defaultdict from .db import Db from .objstorage import ObjStorage 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) @db_transaction def content_add(self, content, cur): """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 - one key for each checksum algorithm in swh.core.hashutil.ALGORITHMS, mapped to the corresponding checksum """ db = self.db # 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']) db.copy_to(content, 'tmp_content', ['sha1', 'sha1_git', 'sha256', 'length'], cur, item_cb=add_to_objstorage) # move metadata in place db.content_add_from_temp(cur) db.conn.commit() @db_transaction_generator def content_missing(self, content, cur): """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. Returns: an iterable of sha1s missing from the storage Raises: TODO: an exception when we get a hash collision. """ db = self.db # Create temporary table for metadata injection db.mktemp('content', cur) db.copy_to(content, 'tmp_content', ['sha1', 'sha1_git', 'sha256', 'length'], cur) for obj in db.content_missing_from_temp(cur): yield obj[0] 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 - atime (datetime.DateTime): entry access time - ctime (datetime.DateTime): entry creation time - mtime (datetime.DateTime): entry modification time """ dirs = set() dir_entries = { 'file': defaultdict(list), 'dir': defaultdict(list), 'rev': defaultdict(list), } for cur_dir in directories: dir_id = cur_dir['id'] dirs.add(dir_id) for entry in cur_dir['entries']: entry['dir_id'] = dir_id dir_entries[entry['type']][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs)) if not dirs_missing: return db = self.db with db.transaction() as cur: dirs_missing_dict = ({'id': dir} for dir in dirs_missing) db.copy_to(dirs_missing_dict, 'directory', ['id'], cur) for entry_type, entry_list in dir_entries.items(): entries = itertools.chain.from_iterable( entries_for_dir for dir_id, entries_for_dir in entry_list.items() if dir_id in dirs_missing) db.mktemp_dir_entry(entry_type) db.copy_to( entries, 'tmp_directory_entry_%s' % entry_type, ['target', 'name', 'perms', 'atime', 'mtime', 'ctime', 'dir_id'], cur, ) cur.execute('SELECT swh_directory_entry_%s_add()' % entry_type) @db_transaction_generator def directory_missing(self, directories, cur): """List directories missing from storage Args: an iterable of directory ids Returns: a list of missing directory ids """ db = self.db # Create temporary table for metadata injection db.mktemp('directory', cur) directories_dicts = ({'id': dir} for dir in directories) db.copy_to(directories_dicts, 'tmp_directory', ['id'], cur) for obj in db.directory_missing_from_temp(cur): yield obj[0] def directory_get(self, directory): """Get the entries for one directory""" yield from self.db.directory_walk_one(directory) def revision_add(self, revisions): """Add revisions to the storage Args: revisions: iterable of dictionaries representing the individual revisions to add. Each dict has the following keys: - id (sha1_git): id of the revision to add - date (datetime.DateTime): date the revision was written - date_offset (int): offset from UTC in minutes the revision was written - committer_date (datetime.DateTime): date the revision got added to the origin - committer_date_offset (int): offset from UTC in minutes the revision was added to the origin - type (one of 'git', 'tar'): type of the revision added - directory (sha1_git): the directory the revision points at - message (bytes): the message associated with the revision - author_name (bytes): the name of the revision author - author_email (bytes): the email of the revision author - committer_name (bytes): the name of the revision committer - committer_email (bytes): the email of the revision committer - parents (list of sha1_git): the parents of this revision """ db = self.db parents = {} for revision in revisions: id = revision['id'] cur_parents = enumerate(revision.get('parents', [])) parents[id] = [{ 'id': id, 'parent_id': parent, 'parent_rank': i } for i, parent in cur_parents] revisions_missing = list(self.revision_missing(parents.keys())) if not revisions_missing: return with db.transaction() as cur: db.mktemp_revision(cur) revisions_filtered = (revision for revision in revisions if revision['id'] in revisions_missing) db.copy_to(revisions_filtered, 'tmp_revision', ['id', 'date', 'date_offset', 'committer_date', 'committer_date_offset', 'type', 'directory', 'message', 'author_name', 'author_email', 'committer_name', 'committer_email'], 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] 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 - 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 """ pass - def release_missing(self, releases): + @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 """ - pass + 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] + def occurrence_add(self, occurrences): """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 - reference (bytes): the reference name of the occurrence - revision (sha1_git): the id of the revision pointed to by the occurrence - date (datetime.DateTime): the validity date for the given occurrence """ pass def origin_add(self, origins): """Add origins to the storage Args: origins: iterable of dictionaries representing the individual origins to add. Each dict has the following keys: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to """ pass