feat: add database schema and migration runner

app/config.py

@@ -0,0 +1,32 @@
+"""Configuration from environment variables — no file parsing required for basic use."""
+
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+DATA_DIR = Path(os.environ.get("PAGEPIPER_DATA_DIR", "data"))
+DB_PATH = str(DATA_DIR / "pagepiper.db")
+VEC_DB_PATH = str(DATA_DIR / "pagepiper_vecs.db")
+WATCH_DIR = Path(os.environ.get("PAGEPIPER_WATCH_DIR", "books"))
+
+
+def get_llm_config() -> dict | None:
+    """Build LLMRouter config from env vars. Returns None if PAGEPIPER_OLLAMA_URL is unset."""
+    url = os.environ.get("PAGEPIPER_OLLAMA_URL", "").strip()
+    if not url:
+        return None
+    return {
+        "fallback_order": ["ollama"],
+        "backends": {
+            "ollama": {
+                "type": "openai_compat",
+                "base_url": url.rstrip("/") + "/v1",
+                "model": os.environ.get("PAGEPIPER_CHAT_MODEL", "mistral:7b"),
+                "embedding_model": os.environ.get(
+                    "PAGEPIPER_EMBED_MODEL", "nomic-embed-text"
+                ),
+                "supports_images": False,
+            }
+        },
+    }

migrations/001_initial_schema.sql

@@ -0,0 +1,29 @@
+-- pagepiper initial schema
+-- Run via: conda run -n cf python scripts/db_migrate.py
+
+CREATE TABLE IF NOT EXISTS documents (
+    id          TEXT PRIMARY KEY DEFAULT (lower(hex(randomblob(16)))),
+    title       TEXT NOT NULL,
+    file_path   TEXT NOT NULL UNIQUE,
+    status      TEXT NOT NULL DEFAULT 'pending',
+    -- status: pending | processing | ready | error
+    task_id     TEXT,
+    page_count  INTEGER,
+    error_msg   TEXT,
+    created_at  TEXT NOT NULL DEFAULT (datetime('now')),
+    updated_at  TEXT NOT NULL DEFAULT (datetime('now'))
+);
+
+CREATE TABLE IF NOT EXISTS page_chunks (
+    id          TEXT PRIMARY KEY DEFAULT (lower(hex(randomblob(16)))),
+    doc_id      TEXT NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
+    page_number INTEGER NOT NULL,
+    text        TEXT NOT NULL DEFAULT '',
+    source      TEXT NOT NULL,
+    -- source: text_layer | ocr
+    word_count  INTEGER NOT NULL DEFAULT 0,
+    created_at  TEXT NOT NULL DEFAULT (datetime('now'))
+);
+
+CREATE INDEX IF NOT EXISTS idx_page_chunks_doc_id ON page_chunks(doc_id);
+CREATE INDEX IF NOT EXISTS idx_page_chunks_doc_page ON page_chunks(doc_id, page_number);

scripts/db_migrate.py

@@ -0,0 +1,30 @@
+"""Apply all pending migrations to the pagepiper SQLite database."""
+
+from __future__ import annotations
+
+import sqlite3
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from app.config import DB_PATH
+
+
+def migrate(db_path: str = DB_PATH) -> None:
+    migrations_dir = Path(__file__).parent.parent / "migrations"
+    conn = sqlite3.connect(db_path)
+    conn.execute("PRAGMA foreign_keys = ON")
+    conn.execute("PRAGMA journal_mode = WAL")
+
+    for sql_file in sorted(migrations_dir.glob("*.sql")):
+        print(f"Applying {sql_file.name}...")
+        conn.executescript(sql_file.read_text())
+
+    conn.commit()
+    conn.close()
+    print(f"Migrations applied to {db_path}")
+
+
+if __name__ == "__main__":
+    migrate()

tests/test_db_migrate.py

@@ -0,0 +1,70 @@
+"""Tests for migrations/001_initial_schema.sql via scripts/db_migrate.py."""
+
+from __future__ import annotations
+
+import sqlite3
+from pathlib import Path
+
+import pytest
+
+
+def test_migration_creates_documents_table(tmp_path):
+    db_path = str(tmp_path / "test.db")
+    schema = Path("migrations/001_initial_schema.sql").read_text()
+
+    conn = sqlite3.connect(db_path)
+    conn.executescript(schema)
+    conn.commit()
+
+    tables = {
+        r[0]
+        for r in conn.execute(
+            "SELECT name FROM sqlite_master WHERE type='table'"
+        ).fetchall()
+    }
+    assert "documents" in tables
+    assert "page_chunks" in tables
+
+
+def test_documents_table_has_required_columns(tmp_path):
+    db_path = str(tmp_path / "test.db")
+    schema = Path("migrations/001_initial_schema.sql").read_text()
+
+    conn = sqlite3.connect(db_path)
+    conn.executescript(schema)
+
+    cols = {r[1] for r in conn.execute("PRAGMA table_info(documents)").fetchall()}
+    assert {
+        "id",
+        "title",
+        "file_path",
+        "status",
+        "task_id",
+        "page_count",
+        "created_at",
+    } <= cols
+
+
+def test_page_chunks_foreign_key_cascades(tmp_path):
+    db_path = str(tmp_path / "test.db")
+    schema = Path("migrations/001_initial_schema.sql").read_text()
+
+    conn = sqlite3.connect(db_path)
+    conn.executescript(schema)
+    conn.execute("PRAGMA foreign_keys = ON")
+
+    conn.execute(
+        "INSERT INTO documents(id, title, file_path, status) VALUES ('d1','Book','path.pdf','ready')"
+    )
+    conn.execute(
+        "INSERT INTO page_chunks(doc_id, page_number, text, source, word_count) VALUES ('d1',1,'text','text_layer',1)"
+    )
+    conn.commit()
+
+    conn.execute("DELETE FROM documents WHERE id='d1'")
+    conn.commit()
+
+    count = conn.execute(
+        "SELECT COUNT(*) FROM page_chunks WHERE doc_id='d1'"
+    ).fetchone()[0]
+    assert count == 0