Add structured parsing for transfer messages so they no longer fall through to the generic `[链接/文件]` fallback in chat history exports. Mirrors the dispatch + helper pattern PR #65 (merged-forward type=19) established for `base_type=49` appmsg sub-types. ## What is added **Helpers (mcp_server.py):** - `_TRANSFER_PAYSUBTYPE_LABEL` — maps the 6 community-consensus paysubtypes (1 发起 / 3 已收款 / 4 已退还 / 5 过期已退还 / 7 待领取 / 8 已领取); unknown values degrade to `未知(paysubtype=N)` so a new variant in a future WeChat build is visible rather than silently dropped. - `_extract_transfer_info(appmsg)` — pulls fields out of `<wcpayinfo>`, with snake/camelCase fallback (`feedesc`/`feeDesc`, `pay_memo`/`paymemo`) observed across WeChat versions. - `_format_transfer_message_text(appmsg, title)` — one-line render for chat history: `[转账·已收款] ¥100.00 备注: lunch`. **Dispatch (mcp_server.py):** - `_format_app_message_text` gains an `app_type == 2000` branch that routes to `_format_transfer_message_text`. `get_chat_history`, `export_chat`, `export_all_chats` and `monitor_web` all inherit automatically. **New MCP tool (mcp_server.py):** - `decode_transfer(chat_name, local_id, create_time=0)` — full structured view: direction, amount, memo, payer/receiver wxid, transfer id, transcation id, begin/invalid timestamps. Uses the same multi-shard scan + ambiguity-by-create_time pattern as `decode_file_message` / `decode_record_item`. **CLI wrapper:** - `decode_transfer.py` at the repo root — argparse wrapper that prints the same text as the MCP tool, returning non-zero exit when the message can't be decoded (script-friendly). **JSON export (chat_export_helpers.py + export_chat.py + export_all_chats.py):** - `_extract_content` now returns `(rendered, extras)`. `extras` carries structured fields when a message type has more signal than the human-readable string (currently: transfers → `type:"transfer" + transfer:{direction, fee_desc, pay_memo, ...}`). The channel is forward-compatible — future additions (video号 metadata, expanded merged-forward, etc.) flow through the same shape without changing the caller signature. JSON consumers that only read `content` are unaffected; the change is additive. **monitor_web (monitor_web.py):** - Backend dispatch branch + orange-yellow `.msg-transfer` card CSS + `renderRich` JS handler. ## Tests 12 new cases in `tests/test_record_decoders.py`: - `TransferPaysubTypeLabelTests` — locks the 6-value label table. - `ExtractTransferInfoTests` (6 cases) — full field round-trip, missing `<wcpayinfo>` fallback, snake/camelCase variants, unknown paysubtype degradation, empty paysubtype handling. - `FormatTransferMessageTextTests` (4 cases) — initiate / received-with-memo / missing-wcpayinfo / missing-fee-desc. - `AppMessageDispatchTransferTests` — `_format_app_message_text` routes type=2000 correctly so `get_chat_history` / `export_chat` both pick it up. All fixtures use synthetic placeholder values (`wxid_payer_synth`, `¥100.00`, `1` + 27×`0`); no real PII or transaction IDs. ## Scope 7 files, +546 / -15 (additions only — no behavior change for existing message types). All 180 tests pass locally (168 baseline + 12 new).
191 lines
6.2 KiB
Python
191 lines
6.2 KiB
Python
"""聊天导出共享工具函数。
|
|
|
|
本模块包含 export_chat.py 和 export_all_chats.py 共用的消息格式化函数。
|
|
统一维护,避免两处代码漂移。
|
|
"""
|
|
|
|
import base64
|
|
|
|
import mcp_server
|
|
|
|
|
|
MSG_TYPE_MAP = {
|
|
1: "text",
|
|
3: "image",
|
|
34: "voice",
|
|
42: "contact_card",
|
|
43: "video",
|
|
47: "sticker",
|
|
48: "location",
|
|
49: "link_or_file",
|
|
50: "call",
|
|
10000: "system",
|
|
10002: "recall",
|
|
}
|
|
|
|
|
|
def _msg_type_str(local_type):
|
|
base, _ = mcp_server._split_msg_type(local_type)
|
|
return MSG_TYPE_MAP.get(base, f"type_{local_type}")
|
|
|
|
|
|
def _resolve_sender(row, ctx, names, id_to_username):
|
|
"""Resolve the sender of a message.
|
|
|
|
Returns "me" for the logged-in user, or the sender's display name otherwise
|
|
(the contact's name in 1-on-1 chats, the member's name in groups). Empty
|
|
string for unattributable messages (e.g. system notifications).
|
|
"""
|
|
local_id, local_type, create_time, real_sender_id, content, ct = row
|
|
decoded = mcp_server._decompress_content(content, ct)
|
|
sender_from_content, _ = mcp_server._format_message_text(
|
|
local_id, local_type, decoded, ctx["is_group"], ctx["username"], ctx["display_name"], names
|
|
)
|
|
label = mcp_server._resolve_sender_label(
|
|
real_sender_id,
|
|
sender_from_content,
|
|
ctx["is_group"],
|
|
ctx["username"],
|
|
ctx["display_name"],
|
|
names,
|
|
id_to_username,
|
|
)
|
|
return label or ""
|
|
|
|
|
|
def _decode_sticker_desc(b64_desc):
|
|
"""WeChat encodes sticker labels as base64 protobuf: repeated (lang, text) pairs.
|
|
Returns the 'default' language label (usually Chinese), or None.
|
|
|
|
Limitation: treats the length byte as a single octet rather than a real protobuf
|
|
varint — labels >127 bytes would be misread. In practice sticker descriptions are
|
|
short (<30 chars), so this is adequate. Also sensitive to the bytes b"default"
|
|
appearing inside a preceding value; no such cases observed.
|
|
"""
|
|
try:
|
|
raw = base64.b64decode(b64_desc)
|
|
except Exception:
|
|
return None
|
|
# Find the 'default' marker; text follows as: \x12 <varint len> <utf-8>
|
|
i = raw.find(b"default")
|
|
if i < 0 or i + 7 >= len(raw) or raw[i + 7] != 0x12:
|
|
return None
|
|
try:
|
|
text_len = raw[i + 8]
|
|
text_bytes = raw[i + 9 : i + 9 + text_len]
|
|
return text_bytes.decode("utf-8") or None
|
|
except (IndexError, UnicodeDecodeError):
|
|
return None
|
|
|
|
|
|
def _format_sticker_message(content):
|
|
root = mcp_server._parse_xml_root(content) if content else None
|
|
if root is None:
|
|
return "[表情]"
|
|
emoji = root.find(".//emoji")
|
|
if emoji is None:
|
|
return "[表情]"
|
|
desc = emoji.get("desc") or ""
|
|
label = _decode_sticker_desc(desc) if desc else None
|
|
return f"[表情] {label}" if label else "[表情]"
|
|
|
|
|
|
def _format_system_message(content):
|
|
if not content:
|
|
return "[系统消息]"
|
|
if "<sysmsg" not in content:
|
|
return content
|
|
root = mcp_server._parse_xml_root(content)
|
|
if root is None:
|
|
return content
|
|
inner = root.findtext(".//content")
|
|
return inner.strip() if inner else content
|
|
|
|
|
|
def _format_video_message(content):
|
|
root = mcp_server._parse_xml_root(content) if content else None
|
|
if root is None:
|
|
return "[视频]"
|
|
video = root.find(".//videomsg")
|
|
if video is None:
|
|
return "[视频]"
|
|
playlength = video.get("playlength")
|
|
return f"[视频] {playlength}秒" if playlength else "[视频]"
|
|
|
|
|
|
def _extract_transfer_extras(content):
|
|
"""Detect appmsg type=2000 and return structured transfer fields, else None.
|
|
|
|
Reuses mcp_server._extract_transfer_info so the schema/version-quirks logic
|
|
lives in one place. Empty values are dropped to keep the export compact.
|
|
Numeric timestamps are returned as ints (consistent with the top-level
|
|
`timestamp` field), not iso strings — downstream consumers can format.
|
|
"""
|
|
if not content or '<appmsg' not in content:
|
|
return None
|
|
root = mcp_server._parse_app_message_outer(content)
|
|
if root is None:
|
|
return None
|
|
appmsg = root.find('.//appmsg')
|
|
if appmsg is None:
|
|
return None
|
|
app_type = mcp_server._parse_int(
|
|
mcp_server._collapse_text(appmsg.findtext('type') or ''), 0
|
|
)
|
|
if app_type != 2000:
|
|
return None
|
|
|
|
info = mcp_server._extract_transfer_info(appmsg)
|
|
if not info:
|
|
return None
|
|
|
|
out = {}
|
|
if info['paysubtype_label']:
|
|
out['direction'] = info['paysubtype_label']
|
|
for k in ('paysubtype', 'fee_desc', 'pay_memo',
|
|
'payer_username', 'receiver_username',
|
|
'transfer_id', 'transcation_id', 'pay_msg_id'):
|
|
v = info.get(k)
|
|
if v:
|
|
out[k] = v
|
|
for k in ('begin_transfer_time', 'invalid_time'):
|
|
v = mcp_server._parse_int(info.get(k) or '', 0)
|
|
if v:
|
|
out[k] = v
|
|
return out or None
|
|
|
|
|
|
def _extract_content(local_id, local_type, content, ct, chat_username, chat_display_name):
|
|
"""Return (rendered_text, extras_dict). Either may be None.
|
|
|
|
extras carries structured fields for non-text message types where caller
|
|
wants more than the human-readable string (currently: transfer). Future
|
|
additions (video号 metadata, merged-forward expansion, …) can flow through
|
|
the same channel without changing the caller signature.
|
|
"""
|
|
content = mcp_server._decompress_content(content, ct)
|
|
if content is None:
|
|
return None, None
|
|
|
|
base, _ = mcp_server._split_msg_type(local_type)
|
|
if base == 1:
|
|
return (content or ""), None
|
|
if base == 43:
|
|
return _format_video_message(content), None
|
|
if base == 47:
|
|
return _format_sticker_message(content), None
|
|
if base == 49:
|
|
rendered = mcp_server._format_app_message_text(
|
|
content, local_type, False, chat_username, chat_display_name, {}
|
|
)
|
|
transfer = _extract_transfer_extras(content)
|
|
extras = {'type': 'transfer', 'transfer': transfer} if transfer else None
|
|
return rendered, extras
|
|
if base == 50:
|
|
return mcp_server._format_voip_message_text(content), None
|
|
if base == 10000:
|
|
return _format_system_message(content), None
|
|
if base == 10002:
|
|
return "[撤回消息]", None
|
|
return None, None
|