Upgrade to SQLAlchemy 2.0 (synchronous) (#803)

SQLAlchemy 1.3 has been end-of-life since 2021, and alembic was held at 1.10
because newer releases need SQLAlchemy 2.  This is a mechanical port; the code
stays synchronous.

- SQLAlchemy[asyncio]==2.0.54, alembic==1.20.0.
- Model annotations use Mapped[...] (2.0 rejects bare annotations on mapped
  attributes); declarative_base moves to sqlalchemy.orm.
- Plain SQL strings go through text() or exec_driver_sql; schema_ddl.execute_sql
  accepts a SQLAlchemy Connection or a raw sqlite3 connection, so rebuild_fts
  works from the baseline migration again.
- Session.get replaces Query.get; session.in_transaction() replaces
  session.transaction; cache_ok on MediaPathType and FancyJSON.
- The tag-directory sync query joins through TagFile's relationships instead of
  the legacy two-entity outerjoin.
- Section-hint rows use attribute access (2.0 rows are tuples).
- Migrations run on an AUTOCOMMIT connection, matching 1.3, where each
  statement committed on its own.  2.0 autobegins, so the unique-stem
  migration's read snapshot could not become a writer after its helpers wrote
  on another connection ("database is locked").  The begin listener emits no
  BEGIN for AUTOCOMMIT connections.
- Newer alembic compares column types: WrolpiKV now describes the TEXT table
  its migration created.
- The test database installs its DDL inside engine.begin(); 2.0 connections
  no longer autocommit, so the FTS tables were rolled back.
- Dependabot now holds SQLAlchemy at 2.0 instead of 1.3.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

modules/archive/__init__.py

@@ -6,6 +6,7 @@ from abc import ABC
 from dataclasses import dataclass
 from typing import Callable, List, Optional, Tuple
 
+from sqlalchemy import text
 from sqlalchemy.orm import Session
 
 from wrolpi.cmd import SINGLE_FILE_BIN, CHROMIUM, FIREFOX, DENO_BIN, SINGLE_FILE_DENO_SCRIPT
@@ -405,7 +406,7 @@ def archive_cleanup():
     with get_db_session(commit=True) as session:
         # Remove any domain Collections without any Archives.
         # Get all collection_ids that have archives
-        collection_ids = [i[0] for i in session.execute('SELECT DISTINCT collection_id FROM archive') if i[0]]
+        collection_ids = [i[0] for i in session.execute(text('SELECT DISTINCT collection_id FROM archive')) if i[0]]
         # Find domain collections that have no archives
         for collection in session.query(Collection).filter_by(kind='domain'):
             if collection.id not in collection_ids:

modules/archive/models.py

@@ -5,7 +5,7 @@ from typing import Iterable, List, Optional
 
 import pytz
 from sqlalchemy import Column, Integer, ForeignKey, BigInteger, Index
-from sqlalchemy.orm import relationship, Session, joinedload
+from sqlalchemy.orm import Mapped, relationship, Session, joinedload
 
 from wrolpi import dates
 from wrolpi.collections import Collection
@@ -36,9 +36,9 @@ class Archive(Base, ModelHelper):
     id = Column(Integer, primary_key=True)
 
     collection_id = Column(Integer, ForeignKey('collection.id', ondelete='CASCADE'))
-    collection: Collection = relationship('Collection', primaryjoin='Archive.collection_id==Collection.id')
+    collection: Mapped[Collection] = relationship('Collection', primaryjoin='Archive.collection_id==Collection.id')
     file_group_id = Column(BigInteger, ForeignKey('file_group.id', ondelete='CASCADE'), unique=True, nullable=False)
-    file_group: FileGroup = relationship('FileGroup')
+    file_group: Mapped[FileGroup] = relationship('FileGroup')
 
     @staticmethod
     def json_options() -> tuple:

modules/archive/test/test_collection_id_bug.py

@@ -135,7 +135,7 @@ async def test_model_archive_extracts_url_from_singlefile(async_client, test_ses
         "collection_id should be set after URL extraction"
 
     # Verify collection was created with correct domain
-    collection = test_session.query(Collection).get(archive.collection_id)
+    collection = test_session.get(Collection, archive.collection_id)
     assert collection.name == domain
     assert collection.kind == 'domain'
 

modules/docs/lib.py

@@ -404,8 +404,7 @@ def _search_docs(session: Session, search_str=None, author=None, subject=None, l
         from wrolpi.tags import Tag, TagFile
         tagged_fg_ids = session.query(TagFile.file_group_id) \
             .join(Tag, Tag.id == TagFile.tag_id) \
-            .filter(Tag.name.in_(tag_names)) \
-            .subquery()
+            .filter(Tag.name.in_(tag_names))
         query = query.filter(FileGroup.id.in_(tagged_fg_ids))
 
     unfiltered = not (search_str or author or subject or language or mimetype or tag_names)
@@ -497,10 +496,10 @@ def _fetch_section_hints(session, file_group_ids, search_str):
     rows = session.execute(sql, {'q': match, 'ids': list(file_group_ids)}).fetchall()
     hints = {}
     for row in rows:
-        hints[row['fg_id']] = {
-            'kind': row['kind'],
-            'ordinal': row['ordinal'],
-            'label': row['label'],
-            'snippet': row['snippet'],
+        hints[row.fg_id] = {
+            'kind': row.kind,
+            'ordinal': row.ordinal,
+            'label': row.label,
+            'snippet': row.snippet,
         }
     return hints

modules/docs/models.py

@@ -2,7 +2,7 @@ import pathlib
 from typing import Optional
 
 from sqlalchemy import Column, Integer, BigInteger, ForeignKey, String, Text, Index, or_
-from sqlalchemy.orm import relationship, Session, joinedload
+from sqlalchemy.orm import Mapped, relationship, Session, joinedload
 
 from wrolpi.common import ModelHelper, Base
 from wrolpi.db import get_db_session, serializer
@@ -56,7 +56,7 @@ class Doc(ModelHelper, Base):
     description = Column(Text)
 
     file_group_id = Column(BigInteger, ForeignKey('file_group.id', ondelete='CASCADE'), nullable=False, unique=True)
-    file_group: FileGroup = relationship('FileGroup')
+    file_group: Mapped[FileGroup] = relationship('FileGroup')
     sections = relationship('DocSection', back_populates='doc',
                             cascade='all, delete-orphan',
                             passive_deletes=True)

modules/videos/downloader.py

@@ -1259,7 +1259,7 @@ class VideoDownloader(Downloader, ABC):
         # Update channel's collection's file_format to track the format used.
         if executed.channel_id:
             from modules.videos.lib import save_channels_config
-            channel_obj = session.query(Channel).get(executed.channel_id)
+            channel_obj = session.get(Channel, executed.channel_id)
             if channel_obj and channel_obj.collection and not channel_obj.collection.file_format:
                 video_config = get_videos_downloader_config()
                 channel_obj.collection.file_format = video_config.file_name_format

modules/videos/models.py

@@ -3,8 +3,7 @@ import pathlib
 from typing import Optional, Dict, List
 
 from sqlalchemy import Column, Integer, String, Boolean, Date, ForeignKey, BigInteger, Index, text, JSON
-from sqlalchemy.orm import relationship, Session, deferred, undefer, joinedload, selectinload
-from sqlalchemy.orm.collections import InstrumentedList
+from sqlalchemy.orm import Mapped, relationship, Session, deferred, undefer, joinedload, selectinload
 
 from modules.videos.errors import UnknownVideo, UnknownChannel
 from wrolpi.captions import read_captions, read_captions_with_timestamps
@@ -49,7 +48,7 @@ class Video(ModelHelper, Base):
     channel_id = Column(Integer, ForeignKey('channel.id'))
     channel = relationship('Channel', primaryjoin='Video.channel_id==Channel.id', back_populates='videos')
     file_group_id = Column(BigInteger, ForeignKey('file_group.id', ondelete='CASCADE'), unique=True, nullable=False)
-    file_group: FileGroup = relationship('FileGroup')
+    file_group: Mapped[FileGroup] = relationship('FileGroup')
 
     def __repr__(self):
         v = None
@@ -628,7 +627,7 @@ class Channel(ModelHelper, Base):
     info_json = deferred(Column(JSON))
     info_date = Column(Date)
 
-    videos: InstrumentedList = relationship('Video', primaryjoin='Channel.id==Video.channel_id')
+    videos: Mapped[List['Video']] = relationship('Video', primaryjoin='Channel.id==Video.channel_id')
     collection_id = Column(Integer, ForeignKey('collection.id', ondelete='CASCADE'))
     # Joined: a Channel's name, directory and Tag live on its Collection.
     collection = relationship('Collection', foreign_keys=[collection_id], lazy='joined')

modules/zim/models.py

@@ -7,7 +7,7 @@ from typing import List, Tuple, OrderedDict as OrderedDictType, Dict, Optional,
 
 from libzim import Archive, Searcher, Query, Entry, SuggestionSearcher
 from sqlalchemy import Column, Integer, BigInteger, ForeignKey, Text, tuple_, Boolean, UniqueConstraint
-from sqlalchemy.orm import relationship, Session, joinedload
+from sqlalchemy.orm import Mapped, relationship, Session, joinedload
 from sqlalchemy.orm.exc import NoResultFound  # noqa
 
 from modules.zim.errors import UnknownZimEntry, UnknownZimTagEntry, UnknownZim
@@ -71,10 +71,10 @@ class Zim(Base, ModelHelper):
         UniqueConstraint('path', name='zim_path_key'),
     )
     id = Column(Integer, primary_key=True)
-    path: pathlib.Path = Column(MediaPathType, nullable=False)
+    path: Mapped[pathlib.Path] = Column(MediaPathType, nullable=False)
 
     file_group_id = Column(BigInteger, ForeignKey('file_group.id', ondelete='CASCADE'), nullable=False)
-    file_group: FileGroup = relationship('FileGroup')
+    file_group: Mapped[FileGroup] = relationship('FileGroup')
     auto_search = Column(Boolean, default=True)
 
     def __repr__(self):
@@ -359,11 +359,11 @@ class TagZimEntry(Base):
     )
 
     tag_id = Column(Integer, ForeignKey('tag.id'), primary_key=True)
-    tag: Tag = relationship('Tag')
+    tag: Mapped[Tag] = relationship('Tag')
     zim_id = Column(Integer, ForeignKey('zim.id', ondelete='CASCADE'), primary_key=True)
-    zim: Zim = relationship('Zim')
-    zim_entry: str = Column(Text, nullable=False, primary_key=True)
-    created_at: datetime = Column(TZDateTime, default=dates.now)
+    zim: Mapped[Zim] = relationship('Zim')
+    zim_entry: Mapped[str] = Column(Text, nullable=False, primary_key=True)
+    created_at: Mapped[datetime] = Column(TZDateTime, default=dates.now)
 
     def __repr__(self):
         tag = self.tag_id
@@ -384,11 +384,11 @@ class TagZimEntry(Base):
 class ZimSubscription(Base):
     __tablename__ = 'zim_subscription'
 
-    id: int = Column(Integer, primary_key=True)
-    name: str = Column(Text, unique=True, nullable=False)
-    language: str = Column(Text, nullable=False)
-    download_id: int = Column(Integer, ForeignKey('download.id', ondelete='CASCADE'), nullable=False)
-    download: Download = relationship('Download', primaryjoin='ZimSubscription.download_id==Download.id')
+    id: Mapped[int] = Column(Integer, primary_key=True)
+    name: Mapped[str] = Column(Text, unique=True, nullable=False)
+    language: Mapped[str] = Column(Text, nullable=False)
+    download_id: Mapped[int] = Column(Integer, ForeignKey('download.id', ondelete='CASCADE'), nullable=False)
+    download: Mapped[Download] = relationship('Download', primaryjoin='ZimSubscription.download_id==Download.id')
 
     def __repr__(self):
         name = self.name