Upload 2 files

prepare_fulltext_index.py

@@ -3,7 +3,6 @@
 
 from __future__ import annotations
 
-import hashlib
 import json
 import os
 import sqlite3
@@ -17,14 +16,6 @@ TOKENIZER_VERSION = "cjk-bigram-boundary-fts5-v5"
 SOURCES = ("CCRD", "CW")
 
 
-def sha256(path: Path) -> str:
-    digest = hashlib.sha256()
-    with path.open("rb") as handle:
-        for chunk in iter(lambda: handle.read(1024 * 1024), b""):
-            digest.update(chunk)
-    return digest.hexdigest()
-
-
 def validated_database(bucket: Path, source: str, details: object) -> Path:
     if not isinstance(details, dict):
         raise ValueError(f"{source}: missing manifest details")
@@ -42,16 +33,13 @@ def validated_database(bucket: Path, source: str, details: object) -> Path:
     path = (bucket / relative_path).resolve()
     if bucket not in path.parents or not path.is_file():
         raise ValueError(f"{source}: database is outside the bucket or missing")
-    if sha256(path) != expected_hash:
-        raise ValueError(f"{source}: database hash mismatch")
     with sqlite3.connect(f"file:{path}?mode=ro&immutable=1", uri=True) as connection:
         tokenizer = connection.execute("SELECT value FROM metadata WHERE key = 'tokenizer_version'").fetchone()
         documents = int(connection.execute("SELECT COUNT(*) FROM documents").fetchone()[0])
         fts_rows = int(connection.execute("SELECT COUNT(*) FROM content_fts").fetchone()[0])
-        integrity = connection.execute("PRAGMA integrity_check").fetchone()[0]
     if not tokenizer or tokenizer[0] != TOKENIZER_VERSION:
         raise ValueError(f"{source}: tokenizer version mismatch")
-    if documents != expected_documents or fts_rows != expected_fts_rows or integrity != "ok":
+    if documents != expected_documents or fts_rows != expected_fts_rows:
         raise ValueError(f"{source}: database structure mismatch")
     return path
 

start.sh

@@ -2,8 +2,10 @@
 set -eu
 
 mkdir -p /app/data/fulltext
-if ! python /app/prepare_fulltext_index.py; then
-  python /app/build_fulltext_db.py &
-fi
+(
+  if ! python /app/prepare_fulltext_index.py; then
+    python /app/build_fulltext_db.py
+  fi
+) &
 
 exec uvicorn app:app --host 0.0.0.0 --port 7860 --log-level info