docling-studio/document-parser/persistence/database.py
Pier-Jean Malandrino ff0b795b6d feat(#202): introduce Document lifecycle state machine
Adds a first-class lifecycle state to every document, distinct from
AnalysisJob.status. The lifecycle describes the document as a whole and
is the foundation for the doc-centric pivot in 0.6.0.

Domain
- DocumentLifecycleState enum (Uploaded/Parsed/Chunked/Ingested/Stale/Failed)
- Document.lifecycle_state and lifecycle_state_at fields
- Document.transition_to() validates against a transition table
  (domain/lifecycle.py) and returns a DocumentLifecycleChanged event
- InvalidLifecycleTransitionError on disallowed transitions

Persistence
- ALTER TABLE documents to add the two columns (default 'Uploaded')
- New index idx_documents_lifecycle_state for filter perf
- _COLUMN_MIGRATIONS refactored to support multiple tables
- _POST_MIGRATION_DDL list for indexes on freshly-added columns
- SqliteDocumentRepository.update_lifecycle()

Services
- AnalysisService drives transitions on parse / chunk / re-chunk / fail
  via _transition_document(); idempotent and resilient (logs WARN and
  continues if a stale state is somehow encountered)

API
- DocumentResponse exposes lifecycleState + lifecycleStateAt
  (additive — existing 'status' field kept for backwards compat)

Frontend
- Document type extended with lifecycleState and lifecycleStateAt
- DocumentLifecycleState union literal mirroring the backend enum

Tests
- 24 new tests in test_lifecycle.py covering transitions, idempotency,
  invariant preservation, and event emission
- test_repos.py: round-trip + every-enum-value check + update_lifecycle
- test_chunking.py: rechunk path now mocks document_repo correctly

Refs #202
2026-05-05 09:38:39 +02:00

129 lines
4.4 KiB
Python

"""SQLite database management — async via aiosqlite."""
from __future__ import annotations
import logging
import os
from collections.abc import AsyncIterator
from contextlib import asynccontextmanager
import aiosqlite
logger = logging.getLogger(__name__)
DB_PATH = os.environ.get("DB_PATH", "./data/docling_studio.db")
_SCHEMA = """
CREATE TABLE IF NOT EXISTS documents (
id TEXT PRIMARY KEY,
filename TEXT NOT NULL,
content_type TEXT,
file_size INTEGER,
page_count INTEGER,
storage_path TEXT NOT NULL,
created_at TEXT NOT NULL DEFAULT (datetime('now'))
);
CREATE TABLE IF NOT EXISTS analysis_jobs (
id TEXT PRIMARY KEY,
document_id TEXT NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
status TEXT NOT NULL DEFAULT 'PENDING',
content_markdown TEXT,
content_html TEXT,
pages_json TEXT,
document_json TEXT,
chunks_json TEXT,
error_message TEXT,
started_at TEXT,
completed_at TEXT,
created_at TEXT NOT NULL DEFAULT (datetime('now'))
);
CREATE INDEX IF NOT EXISTS idx_analysis_jobs_status ON analysis_jobs(status);
CREATE INDEX IF NOT EXISTS idx_analysis_jobs_created_at ON analysis_jobs(created_at);
CREATE INDEX IF NOT EXISTS idx_documents_created_at ON documents(created_at);
"""
# Column migrations: (table, column_name, ddl). Idempotent — applied only
# when the column is missing from the live schema. Order matters when a
# later migration depends on an earlier one (none today).
_COLUMN_MIGRATIONS: list[tuple[str, str, str]] = [
("analysis_jobs", "document_json", "ALTER TABLE analysis_jobs ADD COLUMN document_json TEXT"),
("analysis_jobs", "chunks_json", "ALTER TABLE analysis_jobs ADD COLUMN chunks_json TEXT"),
(
"analysis_jobs",
"progress_current",
"ALTER TABLE analysis_jobs ADD COLUMN progress_current INTEGER",
),
(
"analysis_jobs",
"progress_total",
"ALTER TABLE analysis_jobs ADD COLUMN progress_total INTEGER",
),
# 0.6.0 — Document lifecycle state machine (#202).
(
"documents",
"lifecycle_state",
"ALTER TABLE documents ADD COLUMN lifecycle_state TEXT NOT NULL DEFAULT 'Uploaded'",
),
(
"documents",
"lifecycle_state_at",
"ALTER TABLE documents ADD COLUMN lifecycle_state_at TEXT",
),
]
# DDL statements run after column migrations — typically CREATE INDEX
# IF NOT EXISTS for indexes on freshly-added columns.
_POST_MIGRATION_DDL: list[str] = [
"CREATE INDEX IF NOT EXISTS idx_documents_lifecycle_state ON documents(lifecycle_state)",
]
async def _run_migrations(db: aiosqlite.Connection) -> None:
"""Apply additive column migrations, then any post-migration DDL.
Existing columns are detected via PRAGMA `table_info`, so re-running
the migration on an already-up-to-date DB is a no-op.
"""
columns_by_table: dict[str, set[str]] = {}
for table, col_name, ddl in _COLUMN_MIGRATIONS:
if table not in columns_by_table:
cursor = await db.execute(f"PRAGMA table_info({table})")
columns_by_table[table] = {row[1] for row in await cursor.fetchall()}
if col_name not in columns_by_table[table]:
await db.execute(ddl)
columns_by_table[table].add(col_name)
logger.info("Migration: added column %s to %s", col_name, table)
for ddl in _POST_MIGRATION_DDL:
await db.execute(ddl)
await db.commit()
async def init_db() -> None:
"""Create database file and tables if they don't exist."""
os.makedirs(os.path.dirname(DB_PATH) or ".", exist_ok=True)
async with aiosqlite.connect(DB_PATH) as db:
await db.executescript(_SCHEMA)
await _run_migrations(db)
await db.commit()
logger.info("Database initialized at %s", DB_PATH)
async def get_db() -> aiosqlite.Connection:
"""Open a new database connection with row factory and FK enforcement."""
db = await aiosqlite.connect(DB_PATH)
db.row_factory = aiosqlite.Row
await db.execute("PRAGMA foreign_keys = ON")
return db
@asynccontextmanager
async def get_connection() -> AsyncIterator[aiosqlite.Connection]:
"""Context manager that opens and auto-closes a database connection."""
db = await get_db()
try:
yield db
finally:
await db.close()