fix: split message type into normalized label + raw code

The scraper was writing a normalized type label ("text"/"unknown"/...) into
Message.type, but the column was Integer, so the storage layer coerced it to
NULL and the raw code was only recoverable from raw_json. Align with design
§4.3, which specifies two fields: `type` (normalized enum) and `type_raw`
(original code).

- Model (Message): type -> String(32) normalized label; add type_raw Integer
  for the raw upstream type code.
- Scraper: _normalize_message sets both `type` (label) and `type_raw`
  (coerced int from messageType/type); _is_divider now checks raw -2.
- Repos: type_raw joins _INT_FIELDS; Message.type stored as-is (string).
- Migration 96975050fa79: add type_raw + alter type Integer->String(32),
  wrapped in batch_alter_table so it runs on SQLite and MySQL.
- env.py: enable render_as_batch on SQLite (dev/test) for portable batch
  migrations; MySQL still uses direct ALTER.
- Tests updated end-to-end (scraper, repos, models).

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
浅念
2026-08-01 12:04:08 +08:00
parent 854efd3119
commit 5a2ff58af3
8 changed files with 176 additions and 29 deletions
+9 -9
View File
@@ -23,9 +23,9 @@ dict (see :func:`_coerce_bool`, :func:`_coerce_int`):
``1`` / ``"1"`` / ``True`` -> ``True``; ``0`` / ``"0"`` / ``False`` ->
``False``; ``None`` preserved.
* ``gender``: ``"0"`` / ``"1"`` / ``"2"`` (str) -> ``int`` when not ``None``.
* ``type`` (Message): coerced to ``int``; a non-numeric string (e.g. a
normalized type label like ``"text"``) collapses to ``None`` — the raw code
is still recoverable from ``raw_json``.
* ``type_raw`` (Message): the raw upstream type code, coerced to
``int | None``. ``Message.type`` is a normalized label string and is
stored as-is (no int coercion).
* Timestamps (``last_chat_time`` / ``timestamp`` / ``last_update`` / ...):
passed through as-is (ms-epoch ``int`` or ``None``).
* ``raw_json``: the original record dict, preserved verbatim. When the input
@@ -72,7 +72,7 @@ _BOOL_FIELDS: frozenset[str] = frozenset(
_INT_FIELDS: frozenset[str] = frozenset(
{
"gender",
"type",
"type_raw",
"pic_type",
"friend_state",
"delete_flag",
@@ -118,8 +118,7 @@ def _coerce_int(value: Any) -> int | None:
``"2"`` -> ``2``; ``2`` -> ``2``; ``0``/``"0"`` -> ``0``; ``None`` ->
``None``. A non-numeric string (e.g. ``"text"``) returns ``None`` — the
caller (Message.type) treats that as "no value", and the raw code is still
recoverable from ``raw_json``.
caller (e.g. Message.type_raw) treats that as "no value".
"""
if value is None:
return None
@@ -287,9 +286,10 @@ async def upsert_customers(session: AsyncSession, recs: list[dict[str, Any]]) ->
async def upsert_messages(session: AsyncSession, recs: list[dict[str, Any]]) -> int:
"""Batch idempotent upsert for :class:`Message` (PK = ``msg_id``).
Applies the documented coercions (``is_send``/``is_del`` -> bool, ``type``
-> int). Returns the number of records processed (input length); the DB
collapses duplicate ``msg_id`` values to one row.
Applies the documented coercions (``is_send``/``is_del`` -> bool,
``type_raw`` -> int). ``Message.type`` is the normalized label string and
is stored as-is. Returns the number of records processed (input length);
the DB collapses duplicate ``msg_id`` values to one row.
.. note::
For M1 the ``Message`` model maps to a single physical ``message``