fix(image): scope local_id lookup by chat_id + use real column name (#82)
* fix(image): scope local_id lookup by chat_id + use real column name `ImageResolver.get_image_md5` made two wrong assumptions about the production `MessageResourceInfo` schema, which made the decode_image MCP tool always fail with "无法找到 local_id=X 的图片信息": 1. The column is `message_local_id`, not `local_id`. The current query throws `sqlite3.OperationalError: no such column: local_id`, but the exception is swallowed by `except Exception: pass`, masking the real failure as a silent miss. 2. `message_local_id` is not globally unique. In production it repeats across chats, and within an active chat the same local_id can recur up to 7 times (observed on a real DB). The production schema scopes by `chat_id`, resolved from `ChatName2Id.rowid WHERE user_name = ?`. Fix: `get_image_md5` now takes `(username, local_id)`: - Resolve `username -> chat_id` via `ChatName2Id`. - Query `MessageResourceInfo` filtered by `chat_id + message_local_id + message_local_type == 3` (image type; high bits are session flags, so use `% 2^32`), ordered by `message_create_time DESC LIMIT 1`. External callers (`mcp_server.decode_image_tool` / `list_chat_images_tool`) already pass `username` through `ImageResolver.decode_image()` / `list_chat_images()`, so the public API is unchanged. Only the internal helper signature shifts. The existing test fixture in `test_decode_image_v2` used the same wrong schema as the buggy code (`CREATE TABLE MessageResourceInfo (local_id INTEGER PRIMARY KEY, packed_info BLOB)`), so the tests passed against a self-consistent fiction. The fixture is rebuilt to match real columns plus `ChatName2Id`, and three regression tests are added: - cross-chat collision (same local_id in 3 chats; must pick the right one and not the type=43 video row) - same-chat reuse (same local_id, two timestamps; must pick the newer) - unknown chat (username not in ChatName2Id; structured error, no crash) All 154 tests pass locally (151 baseline + 3 new). * fix(image): surface get_image_md5 errors and use read-only DB open Two follow-ups on top of the chat_id scoping fix: 1. The bare `except Exception: pass` was the original failure mode: it silently swallowed `OperationalError: no such column: local_id` when the production schema diverged from the old `local_id` column name, masking the bug this PR fixes. Print the exception to stderr so future schema drift surfaces immediately instead of returning a misleading "image not found" error. 2. Open message_resource.db with `file:...?mode=ro` URI to match the rest of the project (monitor_web.py uses this idiom in 9 places). The DB is read-only for our purposes and a running WeChat may still hold it; using URI ro avoids any chance of lock contention. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Belugary
@@ -335,22 +335,42 @@ class ImageResolver:
|
||||
self.aes_key = aes_key
|
||||
self.xor_key = xor_key
|
||||
|
||||
def get_image_md5(self, local_id):
|
||||
"""通过 local_id 查 message_resource.db 获取图片文件 MD5"""
|
||||
def get_image_md5(self, username, local_id):
|
||||
"""通过 (username, local_id) 查 message_resource.db 获取图片 MD5
|
||||
|
||||
message_local_id 在 MessageResourceInfo 中跨 chat 重复 (不全局唯一),
|
||||
必须用 chat_id 缩小范围;同一 chat 内活跃聊天也会复用 local_id
|
||||
(实测最高同 chat 7 条同 local_id 的记录), 默认取最新一条。
|
||||
|
||||
message_local_type 上 32 bit 是版本/会话 flag, 用 % 2^32 取低位匹配
|
||||
图片类型 3, 同 monitor_web.py 里 push 路径的写法。
|
||||
"""
|
||||
path = self.cache.get("message/message_resource.db")
|
||||
if not path:
|
||||
return None
|
||||
|
||||
conn = sqlite3.connect(path)
|
||||
conn = sqlite3.connect(f"file:{path}?mode=ro", uri=True)
|
||||
try:
|
||||
chat_row = conn.execute(
|
||||
"SELECT rowid FROM ChatName2Id WHERE user_name = ?",
|
||||
(username,)
|
||||
).fetchone()
|
||||
if not chat_row:
|
||||
return None
|
||||
chat_id = chat_row[0]
|
||||
|
||||
row = conn.execute(
|
||||
"SELECT packed_info FROM MessageResourceInfo WHERE local_id = ?",
|
||||
(local_id,)
|
||||
"SELECT packed_info FROM MessageResourceInfo "
|
||||
"WHERE chat_id = ? AND message_local_id = ? "
|
||||
"AND (message_local_type = 3 OR message_local_type % 4294967296 = 3) "
|
||||
"ORDER BY message_create_time DESC LIMIT 1",
|
||||
(chat_id, local_id)
|
||||
).fetchone()
|
||||
if row and row[0]:
|
||||
return extract_md5_from_packed_info(row[0])
|
||||
except Exception:
|
||||
pass
|
||||
except Exception as e:
|
||||
print(f"[get_image_md5] {type(e).__name__}: {e}",
|
||||
file=sys.stderr, flush=True)
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
@@ -381,10 +401,10 @@ class ImageResolver:
|
||||
Returns:
|
||||
dict with keys: success, path, format, md5, error
|
||||
"""
|
||||
# 1. 获取 MD5
|
||||
file_md5 = self.get_image_md5(local_id)
|
||||
# 1. 获取 MD5 (chat-scoped: 同 local_id 跨 chat 重复)
|
||||
file_md5 = self.get_image_md5(username, local_id)
|
||||
if not file_md5:
|
||||
return {'success': False, 'error': f'无法从 message_resource.db 找到 local_id={local_id} 的图片信息'}
|
||||
return {'success': False, 'error': f'无法从 message_resource.db 找到 {username} local_id={local_id} 的图片信息'}
|
||||
|
||||
# 2. 找 .dat 文件
|
||||
dat_files = self.find_dat_files(username, file_md5)
|
||||
@@ -448,7 +468,7 @@ class ImageResolver:
|
||||
|
||||
results = []
|
||||
for local_id, create_time in rows:
|
||||
file_md5 = self.get_image_md5(local_id)
|
||||
file_md5 = self.get_image_md5(username, local_id)
|
||||
info = {
|
||||
'local_id': local_id,
|
||||
'create_time': create_time,
|
||||
|
||||
@@ -70,23 +70,68 @@ class _FakeCache:
|
||||
return self._mapping.get(rel_key)
|
||||
|
||||
|
||||
def _make_resource_db(path, local_id, file_md5):
|
||||
"""构造最小 message_resource.db,只含一条 packed_info 记录。
|
||||
def _make_resource_db(path, local_id, file_md5, username="wxid_test123",
|
||||
chat_id=1, message_create_time=1700000000,
|
||||
message_local_type=3, extra_rows=()):
|
||||
"""构造最小 message_resource.db, 表 schema 对齐真实微信结构。
|
||||
|
||||
真实表里 message_local_id 不全局唯一 (跨 chat 重复, 活跃 chat 内也会复用),
|
||||
解析必须用 ChatName2Id.rowid -> chat_id 限定 + message_local_type=3 过滤图片。
|
||||
|
||||
packed_info 里嵌入 extract_md5_from_packed_info 期望的 protobuf marker
|
||||
(\\x12\\x22\\x0a\\x20) 加 32 字节 ASCII hex MD5。
|
||||
|
||||
Args:
|
||||
extra_rows: 额外 (chat_id, message_local_id, message_local_type,
|
||||
message_create_time, file_md5) 元组列表, 用于构造同 local_id
|
||||
跨 chat / 同 chat 多版本的歧义场景。
|
||||
"""
|
||||
marker = b'\x12\x22\x0a\x20'
|
||||
packed = b'\x00' * 8 + marker + file_md5.encode('ascii') + b'\x00' * 4
|
||||
def _packed(md5_hex):
|
||||
return b'\x00' * 8 + marker + md5_hex.encode('ascii') + b'\x00' * 4
|
||||
|
||||
conn = sqlite3.connect(path)
|
||||
try:
|
||||
conn.execute("""
|
||||
CREATE TABLE MessageResourceInfo (
|
||||
message_id INTEGER PRIMARY KEY,
|
||||
chat_id INTEGER,
|
||||
sender_id INTEGER,
|
||||
message_local_type INTEGER,
|
||||
message_create_time INTEGER,
|
||||
message_local_id INTEGER,
|
||||
message_svr_id INTEGER,
|
||||
message_origin_source INTEGER,
|
||||
packed_info BLOB
|
||||
)
|
||||
""")
|
||||
conn.execute(
|
||||
"CREATE TABLE MessageResourceInfo (local_id INTEGER PRIMARY KEY, packed_info BLOB)"
|
||||
"CREATE TABLE ChatName2Id (user_name TEXT PRIMARY KEY, update_time INTEGER)"
|
||||
)
|
||||
conn.execute(
|
||||
"INSERT INTO MessageResourceInfo VALUES (?, ?)",
|
||||
(local_id, packed),
|
||||
"INSERT INTO ChatName2Id (rowid, user_name, update_time) VALUES (?, ?, ?)",
|
||||
(chat_id, username, message_create_time),
|
||||
)
|
||||
next_msg_id = 1
|
||||
conn.execute(
|
||||
"INSERT INTO MessageResourceInfo "
|
||||
"(message_id, chat_id, sender_id, message_local_type, message_create_time, "
|
||||
" message_local_id, message_svr_id, message_origin_source, packed_info) "
|
||||
"VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)",
|
||||
(next_msg_id, chat_id, 0, message_local_type, message_create_time,
|
||||
local_id, 0, 0, _packed(file_md5)),
|
||||
)
|
||||
next_msg_id += 1
|
||||
for extra in extra_rows:
|
||||
ex_chat_id, ex_local_id, ex_type, ex_ctime, ex_md5 = extra
|
||||
conn.execute(
|
||||
"INSERT INTO MessageResourceInfo "
|
||||
"(message_id, chat_id, sender_id, message_local_type, message_create_time, "
|
||||
" message_local_id, message_svr_id, message_origin_source, packed_info) "
|
||||
"VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)",
|
||||
(next_msg_id, ex_chat_id, 0, ex_type, ex_ctime, ex_local_id, 0, 0, _packed(ex_md5)),
|
||||
)
|
||||
next_msg_id += 1
|
||||
conn.commit()
|
||||
finally:
|
||||
conn.close()
|
||||
@@ -335,6 +380,81 @@ class TestImageResolverV2(unittest.TestCase):
|
||||
self.assertTrue(result['success'], msg=result)
|
||||
self.assertEqual(result['format'], 'png')
|
||||
|
||||
def test_decode_image_disambiguates_local_id_across_chats(self):
|
||||
"""同 local_id 跨 chat 重复时, 必须按 username -> chat_id 选对; 否则会拿到
|
||||
别的 chat 的 MD5 (或视频 type=43 的 packed_info), 解出错图。
|
||||
|
||||
生产 DB 上同一个 message_local_id 实测会出现在 5+ 个不同 chat 里,
|
||||
其中混有图片 (type=3) / 视频 (type=43) / 群聊 / 私聊, 必须 chat-scoped
|
||||
+ type 过滤才能定位。
|
||||
"""
|
||||
os.unlink(self.db_path)
|
||||
other_md5 = "f" * 32
|
||||
video_md5 = "a" * 32
|
||||
_make_resource_db(
|
||||
self.db_path, self.local_id, self.file_md5,
|
||||
username=self.username, chat_id=7,
|
||||
message_create_time=1778487726,
|
||||
extra_rows=[
|
||||
# 另一个 chat 同 local_id 同图片类型, MD5 不同 —— 选错就拿这个
|
||||
(5, self.local_id, 3, 1700000000, other_md5),
|
||||
# 又一个 chat 同 local_id 但是视频 (type=43), 应被 type 过滤
|
||||
(132, self.local_id, 43, 1750000000, video_md5),
|
||||
],
|
||||
)
|
||||
# 给冲突 chat 也注册 user_name, 否则 chat-scope 等价
|
||||
conn = sqlite3.connect(self.db_path)
|
||||
conn.execute(
|
||||
"INSERT INTO ChatName2Id (rowid, user_name, update_time) VALUES (5, ?, 0), (132, ?, 0)",
|
||||
("other_chat_wxid", "video_chat_wxid"),
|
||||
)
|
||||
conn.commit()
|
||||
conn.close()
|
||||
|
||||
resolver = ImageResolver(
|
||||
self.wechat_base, self.out_dir, self.cache,
|
||||
aes_key=TEST_AES_KEY, xor_key=TEST_XOR_KEY,
|
||||
)
|
||||
result = resolver.decode_image(self.username, self.local_id)
|
||||
self.assertTrue(result['success'], msg=result)
|
||||
# 必须拿目标 chat 的 MD5, 不是 other_chat 也不是视频
|
||||
self.assertEqual(result['md5'], self.file_md5)
|
||||
|
||||
def test_decode_image_picks_latest_when_same_chat_local_id_reused(self):
|
||||
"""活跃 chat 里 local_id 会被复用 (实测同 chat 同 local_id 最多 7 条);
|
||||
默认应返回 message_create_time 最新的那张, 对应用户最近一次 reference。
|
||||
"""
|
||||
os.unlink(self.db_path)
|
||||
old_md5 = "c" * 32
|
||||
# self.file_md5 / self.local_id 在 _make_resource_db 默认插入为 "latest" 那条
|
||||
_make_resource_db(
|
||||
self.db_path, self.local_id, self.file_md5,
|
||||
username=self.username, chat_id=1,
|
||||
message_create_time=1778487726,
|
||||
extra_rows=[
|
||||
# 同 chat 同 local_id 但更早, 不应该被选中
|
||||
(1, self.local_id, 3, 1700000000, old_md5),
|
||||
],
|
||||
)
|
||||
|
||||
resolver = ImageResolver(
|
||||
self.wechat_base, self.out_dir, self.cache,
|
||||
aes_key=TEST_AES_KEY, xor_key=TEST_XOR_KEY,
|
||||
)
|
||||
result = resolver.decode_image(self.username, self.local_id)
|
||||
self.assertTrue(result['success'], msg=result)
|
||||
self.assertEqual(result['md5'], self.file_md5)
|
||||
|
||||
def test_decode_image_unknown_chat_returns_error(self):
|
||||
"""username 在 ChatName2Id 里找不到时, 应返回结构化错误而不是 crash 或乱选 row。"""
|
||||
resolver = ImageResolver(
|
||||
self.wechat_base, self.out_dir, self.cache,
|
||||
aes_key=TEST_AES_KEY, xor_key=TEST_XOR_KEY,
|
||||
)
|
||||
result = resolver.decode_image("wxid_does_not_exist", self.local_id)
|
||||
self.assertFalse(result['success'])
|
||||
self.assertIn('wxid_does_not_exist', result['error'])
|
||||
|
||||
def test_decode_image_v1_no_aes_key_uses_fixed_key(self):
|
||||
# V1 magic 不会被 is_v2_format guard 拦截 (V1 magic 是 \x07\x08V1, V2 是 \x07\x08V2);
|
||||
# 即便 ImageResolver(aes_key=None), V1 文件也应通过 decrypt_dat_file 内置固定 key 解密
|
||||
|
||||
Reference in New Issue
Block a user