weflow-cli 1.17.0 → 1.19.0

package/scripts/network.py

@@ -1,206 +1,206 @@
-"""人脉图谱：谁和你在同一个群、谁适合做引荐人。
-
-数据全在 `contact.db`（联系人 + 群 + 群成员），不碰消息库，也就没有"读聊天内容"这件事：
-     contact(id, username, nick_name, remark)      4192 人
-     chat_room(id, username, owner)                80 个群
-     chatroom_member(room_id, member_id)           4305 条关系（member_id 是 contact.id）
-
-用法：
-    python scripts/network.py --groups              群概览（成员数，按大小排）
-    python scripts/network.py --with 张三           我和他共同在哪些群
-    python scripts/network.py --intro 张三           谁最适合把我介绍给他
-    python scripts/network.py --intro 张三 --json
-"""
-from __future__ import annotations
-
-import argparse
-import json
-import pathlib
-import sys
-from collections import defaultdict
-
-SCRIPT_DIR = pathlib.Path(__file__).resolve().parent
-sys.path.insert(0, str(SCRIPT_DIR))
-
-from _utils import load_config, decrypt_lock  # noqa: E402
-from nt_common import derive_database_key  # noqa: E402
-from export_chat_html import connect  # noqa: E402
-
-
-def _open_contact(cfg):
-    path = cfg.get('contactDbPath') or ''
-    if not path:
-        raise SystemExit('配置里没有 contactDbPath，先跑 weflow-cli init')
-    key = decrypt_lock(cfg.get('contactKey', '') or cfg.get('ntKey', '') or '')
-    salt = decrypt_lock(cfg.get('contactSalt', '') or cfg.get('ntSalt', '') or '')
-    pw = decrypt_lock(cfg.get('favPassphrase', '') or cfg.get('decryptKey', '') or '')
-    k, s = derive_database_key(path, key, salt, pw)
-    return connect(path, k, s)
-
-
-def load_graph(cfg):
-    """(people, rooms, members) —— people: id->名字; rooms: id->群名; members: room->{id}"""
-    conn, cur = _open_contact(cfg)
-    try:
-        people = {}
-        for pid, username, nick, remark in cur.execute(
-                'SELECT id, username, COALESCE(nick_name,""), COALESCE(remark,"") FROM contact'):
-            name = remark or nick or username
-            people[int(pid)] = {'name': name, 'username': username, 'nick': nick, 'remark': remark}
-
-        rooms = {}
-        # 群昵称在 `contact` 里（`@chatroom` 那条的 remark/nick_name），`chat_room.username`
-        # 只是 id —— 不查这一步，输出里 80 个群全叫 `47966561144@chatroom`。
-        by_username = {p['username']: p for p in people.values()}
-        for rid, username, owner in cur.execute('SELECT id, username, COALESCE(owner,"") FROM chat_room'):
-            info = by_username.get(username) or {}
-            name = info.get('remark') or info.get('nick') or username
-            rooms[int(rid)] = {'name': name, 'username': username, 'owner': owner}
-
-        members = defaultdict(set)
-        for rid, mid in cur.execute('SELECT room_id, member_id FROM chatroom_member'):
-            members[int(rid)].add(int(mid))
-        return people, rooms, members
-    finally:
-        conn.close()
-
-
-def resolve(people, needle):
-    """按 wxid / 昵称 / 备注找一个人；返回 (id, 记录) 或 None。
-
-    **排除群**：`contact` 表里 `@chatroom` 也在，用 `--with 老表` 会先命中「老表亲戚群」
-    这个群而不是人（第一版就这么错），所以匹配人时跳过它们。
-    """
-    needle = (needle or '').strip()
-    if not needle:
-        return None
-    exact, fuzzy = [], []
-    for pid, p in people.items():
-        if p['username'].endswith('@chatroom'):
-            continue
-        fields = (p['name'], p['username'], p['nick'], p['remark'])
-        if needle == p['username']:
-            return pid, p
-        if any(needle == f for f in fields if f):
-            exact.append((pid, p))
-        elif any(needle in f for f in fields if f):
-            fuzzy.append((pid, p))
-    pool = exact or fuzzy
-    return pool[0] if pool else None
-
-
-def find_me(people, members, cfg):
-    """自己的 contact.id。
-
-    先按配置里的 wxid 找；**找不到就用"出现在最多群里的人"** —— 你在自己所有群里，
-    而 `contact` 表不一定收录自己（实测这里就没有），少了这个兜底，
-    「共同群」这类功能会直接退化成一列群名。
-    """
-    wxid = cfg.get('wxid') or ''
-    if wxid:
-        for pid, p in people.items():
-            if p['username'] == wxid:
-                return pid
-    counts = defaultdict(int)
-    for ids in members.values():
-        for pid in ids:
-            counts[pid] += 1
-    if counts:
-        pid, n = max(counts.items(), key=lambda kv: kv[1])
-        if n >= 3:
-            return pid
-    return None
-
-
-def rooms_of(members, pid):
-    return {rid for rid, ids in members.items() if pid in ids}
-
-
-def cmd_groups(people, rooms, members):
-    rows = []
-    for rid, info in rooms.items():
-        ids = members.get(rid, set())
-        rows.append({'room': info['name'], 'members': len(ids)})
-    rows.sort(key=lambda r: -r['members'])
-    print(f'共 {len(rows)} 个群\n')
-    for r in rows[:30]:
-        print(f"  {r['members']:>4} 人  {r['room']}")
-    if len(rows) > 30:
-        print(f'  …还有 {len(rows)-30} 个')
-
-
-def cmd_with(people, rooms, members, needle, cfg):
-    me_id = find_me(people, members, cfg)
-    me = (me_id, people.get(me_id, {})) if me_id else None
-    target = resolve(people, needle)
-    if not target:
-        raise SystemExit(f'没找到「{needle}」')
-    tid, tinfo = target
-    t_rooms = rooms_of(members, tid)
-    print(f"目标：{tinfo['name']}（{tinfo['username']}）在 {len(t_rooms)} 个群")
-    if not me:
-        print('（配置里没有自己的 wxid，跳过共同群计算）')
-        for rid in sorted(t_rooms):
-            print(f"  · {rooms[rid]['name']}")
-        return
-    my_rooms = rooms_of(members, me[0])
-    common = t_rooms & my_rooms
-    print(f"你们共同在 {len(common)} 个群：")
-    for rid in sorted(common):
-        print(f"  · {rooms[rid]['name']}（{len(members.get(rid, []))} 人）")
-    if not common:
-        print('  （没有共同群）')
-
-
-def cmd_intro(people, rooms, members, needle, cfg, top=8):
-    me_id = find_me(people, members, cfg)
-    me = (me_id, people.get(me_id, {})) if me_id else None
-    target = resolve(people, needle)
-    if not target:
-        raise SystemExit(f'没找到「{needle}」')
-    tid, tinfo = target
-    if not me:
-        raise SystemExit('配置里没有自己的 wxid，算不了引荐路径')
-    my_rooms = rooms_of(members, me[0])
-    t_rooms = rooms_of(members, tid)
-
-    # 候选人 = 同时在我和目标的群里的人；分数 = 交集群数，其次是他和目标最近的共同群大小
-    scores = defaultdict(lambda: {'rooms': set()})
-    for rid in my_rooms & t_rooms:
-        for pid in members.get(rid, set()):
-            if pid in (me[0], tid):
-                continue
-            scores[pid]['rooms'].add(rid)
-    if not scores:
-        print(f'你和「{tinfo["name"]}」不在同一个群，也没有共同的联系人可引荐')
-        return
-    ranked = sorted(scores.items(), key=lambda kv: -len(kv[1]['rooms']))
-    print(f"想认识「{tinfo['name']}」，这些人同时和你们在一个群：\n")
-    for pid, info in ranked[:top]:
-        p = people.get(pid, {})
-        shared = '、'.join(rooms[r]['name'] for r in list(info['rooms'])[:3])
-        print(f"  {p.get('name') or p.get('username')}  共同群 {len(info['rooms'])} 个：{shared}")
-
-
-def main():
-    ap = argparse.ArgumentParser(description='人脉图谱：共同群与引荐路径')
-    ap.add_argument('--groups', action='store_true', help='群概览')
-    ap.add_argument('--with', dest='with_who', default='', help='我和他共同在哪些群')
-    ap.add_argument('--intro', default='', help='谁能把我介绍给他')
-    ap.add_argument('--json', action='store_true')
-    args = ap.parse_args()
-
-    cfg = load_config()
-    people, rooms, members = load_graph(cfg)
-    if args.groups:
-        cmd_groups(people, rooms, members)
-    elif args.with_who:
-        cmd_with(people, rooms, members, args.with_who, cfg)
-    elif args.intro:
-        cmd_intro(people, rooms, members, args.intro, cfg)
-    else:
-        ap.print_help()
-
-
-if __name__ == '__main__':
-    main()
+"""人脉图谱：谁和你在同一个群、谁适合做引荐人。
+
+数据全在 `contact.db`（联系人 + 群 + 群成员），不碰消息库，也就没有"读聊天内容"这件事：
+     contact(id, username, nick_name, remark)      4192 人
+     chat_room(id, username, owner)                80 个群
+     chatroom_member(room_id, member_id)           4305 条关系（member_id 是 contact.id）
+
+用法：
+    python scripts/network.py --groups              群概览（成员数，按大小排）
+    python scripts/network.py --with 张三           我和他共同在哪些群
+    python scripts/network.py --intro 张三           谁最适合把我介绍给他
+    python scripts/network.py --intro 张三 --json
+"""
+from __future__ import annotations
+
+import argparse
+import json
+import pathlib
+import sys
+from collections import defaultdict
+
+SCRIPT_DIR = pathlib.Path(__file__).resolve().parent
+sys.path.insert(0, str(SCRIPT_DIR))
+
+from _utils import load_config, decrypt_lock  # noqa: E402
+from nt_common import derive_database_key  # noqa: E402
+from export_chat_html import connect  # noqa: E402
+
+
+def _open_contact(cfg):
+    path = cfg.get('contactDbPath') or ''
+    if not path:
+        raise SystemExit('配置里没有 contactDbPath，先跑 weflow-cli init')
+    key = decrypt_lock(cfg.get('contactKey', '') or cfg.get('ntKey', '') or '')
+    salt = decrypt_lock(cfg.get('contactSalt', '') or cfg.get('ntSalt', '') or '')
+    pw = decrypt_lock(cfg.get('favPassphrase', '') or cfg.get('decryptKey', '') or '')
+    k, s = derive_database_key(path, key, salt, pw)
+    return connect(path, k, s)
+
+
+def load_graph(cfg):
+    """(people, rooms, members) —— people: id->名字; rooms: id->群名; members: room->{id}"""
+    conn, cur = _open_contact(cfg)
+    try:
+        people = {}
+        for pid, username, nick, remark in cur.execute(
+                'SELECT id, username, COALESCE(nick_name,""), COALESCE(remark,"") FROM contact'):
+            name = remark or nick or username
+            people[int(pid)] = {'name': name, 'username': username, 'nick': nick, 'remark': remark}
+
+        rooms = {}
+        # 群昵称在 `contact` 里（`@chatroom` 那条的 remark/nick_name），`chat_room.username`
+        # 只是 id —— 不查这一步，输出里 80 个群全叫 `47966561144@chatroom`。
+        by_username = {p['username']: p for p in people.values()}
+        for rid, username, owner in cur.execute('SELECT id, username, COALESCE(owner,"") FROM chat_room'):
+            info = by_username.get(username) or {}
+            name = info.get('remark') or info.get('nick') or username
+            rooms[int(rid)] = {'name': name, 'username': username, 'owner': owner}
+
+        members = defaultdict(set)
+        for rid, mid in cur.execute('SELECT room_id, member_id FROM chatroom_member'):
+            members[int(rid)].add(int(mid))
+        return people, rooms, members
+    finally:
+        conn.close()
+
+
+def resolve(people, needle):
+    """按 wxid / 昵称 / 备注找一个人；返回 (id, 记录) 或 None。
+
+    **排除群**：`contact` 表里 `@chatroom` 也在，用 `--with 老表` 会先命中「老表亲戚群」
+    这个群而不是人（第一版就这么错），所以匹配人时跳过它们。
+    """
+    needle = (needle or '').strip()
+    if not needle:
+        return None
+    exact, fuzzy = [], []
+    for pid, p in people.items():
+        if p['username'].endswith('@chatroom'):
+            continue
+        fields = (p['name'], p['username'], p['nick'], p['remark'])
+        if needle == p['username']:
+            return pid, p
+        if any(needle == f for f in fields if f):
+            exact.append((pid, p))
+        elif any(needle in f for f in fields if f):
+            fuzzy.append((pid, p))
+    pool = exact or fuzzy
+    return pool[0] if pool else None
+
+
+def find_me(people, members, cfg):
+    """自己的 contact.id。
+
+    先按配置里的 wxid 找；**找不到就用"出现在最多群里的人"** —— 你在自己所有群里，
+    而 `contact` 表不一定收录自己（实测这里就没有），少了这个兜底，
+    「共同群」这类功能会直接退化成一列群名。
+    """
+    wxid = cfg.get('wxid') or ''
+    if wxid:
+        for pid, p in people.items():
+            if p['username'] == wxid:
+                return pid
+    counts = defaultdict(int)
+    for ids in members.values():
+        for pid in ids:
+            counts[pid] += 1
+    if counts:
+        pid, n = max(counts.items(), key=lambda kv: kv[1])
+        if n >= 3:
+            return pid
+    return None
+
+
+def rooms_of(members, pid):
+    return {rid for rid, ids in members.items() if pid in ids}
+
+
+def cmd_groups(people, rooms, members):
+    rows = []
+    for rid, info in rooms.items():
+        ids = members.get(rid, set())
+        rows.append({'room': info['name'], 'members': len(ids)})
+    rows.sort(key=lambda r: -r['members'])
+    print(f'共 {len(rows)} 个群\n')
+    for r in rows[:30]:
+        print(f"  {r['members']:>4} 人  {r['room']}")
+    if len(rows) > 30:
+        print(f'  …还有 {len(rows)-30} 个')
+
+
+def cmd_with(people, rooms, members, needle, cfg):
+    me_id = find_me(people, members, cfg)
+    me = (me_id, people.get(me_id, {})) if me_id else None
+    target = resolve(people, needle)
+    if not target:
+        raise SystemExit(f'没找到「{needle}」')
+    tid, tinfo = target
+    t_rooms = rooms_of(members, tid)
+    print(f"目标：{tinfo['name']}（{tinfo['username']}）在 {len(t_rooms)} 个群")
+    if not me:
+        print('（配置里没有自己的 wxid，跳过共同群计算）')
+        for rid in sorted(t_rooms):
+            print(f"  · {rooms[rid]['name']}")
+        return
+    my_rooms = rooms_of(members, me[0])
+    common = t_rooms & my_rooms
+    print(f"你们共同在 {len(common)} 个群：")
+    for rid in sorted(common):
+        print(f"  · {rooms[rid]['name']}（{len(members.get(rid, []))} 人）")
+    if not common:
+        print('  （没有共同群）')
+
+
+def cmd_intro(people, rooms, members, needle, cfg, top=8):
+    me_id = find_me(people, members, cfg)
+    me = (me_id, people.get(me_id, {})) if me_id else None
+    target = resolve(people, needle)
+    if not target:
+        raise SystemExit(f'没找到「{needle}」')
+    tid, tinfo = target
+    if not me:
+        raise SystemExit('配置里没有自己的 wxid，算不了引荐路径')
+    my_rooms = rooms_of(members, me[0])
+    t_rooms = rooms_of(members, tid)
+
+    # 候选人 = 同时在我和目标的群里的人；分数 = 交集群数，其次是他和目标最近的共同群大小
+    scores = defaultdict(lambda: {'rooms': set()})
+    for rid in my_rooms & t_rooms:
+        for pid in members.get(rid, set()):
+            if pid in (me[0], tid):
+                continue
+            scores[pid]['rooms'].add(rid)
+    if not scores:
+        print(f'你和「{tinfo["name"]}」不在同一个群，也没有共同的联系人可引荐')
+        return
+    ranked = sorted(scores.items(), key=lambda kv: -len(kv[1]['rooms']))
+    print(f"想认识「{tinfo['name']}」，这些人同时和你们在一个群：\n")
+    for pid, info in ranked[:top]:
+        p = people.get(pid, {})
+        shared = '、'.join(rooms[r]['name'] for r in list(info['rooms'])[:3])
+        print(f"  {p.get('name') or p.get('username')}  共同群 {len(info['rooms'])} 个：{shared}")
+
+
+def main():
+    ap = argparse.ArgumentParser(description='人脉图谱：共同群与引荐路径')
+    ap.add_argument('--groups', action='store_true', help='群概览')
+    ap.add_argument('--with', dest='with_who', default='', help='我和他共同在哪些群')
+    ap.add_argument('--intro', default='', help='谁能把我介绍给他')
+    ap.add_argument('--json', action='store_true')
+    args = ap.parse_args()
+
+    cfg = load_config()
+    people, rooms, members = load_graph(cfg)
+    if args.groups:
+        cmd_groups(people, rooms, members)
+    elif args.with_who:
+        cmd_with(people, rooms, members, args.with_who, cfg)
+    elif args.intro:
+        cmd_intro(people, rooms, members, args.intro, cfg)
+    else:
+        ap.print_help()
+
+
+if __name__ == '__main__':
+    main()

package/scripts/nt_common.py

@@ -80,3 +80,35 @@ def table_columns(cursor, table):
     except Exception:
         return set()
     return {row[1] for row in rows}
+
+
+#: zstd frame magic。`message_content` 在 4.x 里**可能被压缩**（issue #12）。
+ZSTD_MAGIC = bytes([0x28, 0xB5, 0x2F, 0xFD])
+
+
+def decode_content(value):
+    """`message_content` → 文本。**所有读消息的脚本都该走这里。**
+
+    三种形态都要接：`str`（老格式，直接返回）、zstd frame（4.x 压缩后存的）、
+    以及普通 bytes。解不出就回空串——调用方拿到的永远是字符串，不需要自己判断类型。
+
+    为什么要一个公共函数：这条规则以前散在五个脚本里，其中四个写的是
+    `if not isinstance(content, str): continue`，于是**压缩正文被整条跳过**——
+    消息不进索引、不进待办、不进年度统计，而且不报错（issue #12 同源）。
+    """
+    if isinstance(value, str):
+        return value
+    if not value:
+        return ''
+    try:
+        data = bytes(value)
+    except Exception:
+        return ''
+    if data[:4] == ZSTD_MAGIC:
+        try:
+            import zstandard
+            return zstandard.ZstdDecompressor().decompress(data).decode('utf-8', 'ignore')
+        except Exception:
+            # 声称是 zstd 但内容坏了：回退成按字节解码，不抛也不丢整条消息。
+            return data.decode('utf-8', 'ignore')
+    return data.decode('utf-8', 'ignore')

package/scripts/nt_decrypt.py

@@ -989,19 +989,13 @@ QUOTE_CLIP = 120
 
 ZSTD_MAGIC = bytes([0x28, 0xB5, 0x2F, 0xFD])
 def _decode_content(raw):
-    """消息内容 → 文本。BLOB 先按 zstd 解压（公众号消息同一套机制）。解不出回空串。"""
-    if isinstance(raw, str):
-        return raw
-    if not raw:
-        return ''
-    data = bytes(raw)
-    if data[:4] == ZSTD_MAGIC:        # zstd frame header
-        try:
-            import zstandard
-            return zstandard.ZstdDecompressor().decompress(data).decode('utf-8', 'ignore')
-        except Exception:
-            return ''
-    return data.decode('utf-8', 'ignore')
+    """消息内容 → 文本。实现在 `nt_common.decode_content`（各脚本共用一份）。
+
+    保留这个名字是为了不动 `non_text_display` 等既有调用点；行为与公共函数一致：
+    str 原样、zstd frame 解压、其它 bytes 按 UTF-8 解码，解不出回空串。
+    """
+    from nt_common import decode_content
+    return decode_content(raw)
 
 
 def _xml_block(xml, tag):
@@ -1117,7 +1111,15 @@ def _message_dict(row, sender_id_map, name_map, own_wxid, is_group=False):
 
     # Parse message_content - TEXT column
     raw_content = row.get('message_content')
-    content = raw_content if isinstance(raw_content, str) else ""
+    # **普通文本也可能是 zstd 压缩的 BLOB**（issue #12）。这里原来只认 `str`，
+    # 于是 `local_type == 1` 的压缩正文被置空、再交给 `non_text_display()`，
+    # 最终输出 `[未识别的消息类型 1]` —— 消息还在，正文没了，下游按
+    # `parsedContent` 做的关键词 / @所有人 筛选就漏掉这些通知。
+    # `_decode_content()` 已经处理三种形态（str / zstd frame / 普通 bytes），复用它即可。
+    if local_type == 1:
+        content = _decode_content(raw_content)
+    else:
+        content = raw_content if isinstance(raw_content, str) else ""
 
     # `content`/`rawContent` stay exactly as stored; only `parsedContent` - the
     # field every consumer reads first - gets the display-ready form.
@@ -1140,7 +1142,9 @@ def _message_dict(row, sender_id_map, name_map, own_wxid, is_group=False):
         "senderDisplay": sender_display,
         "content": content,
         "rawContent": content,
-        "parsedContent": display[:200] if local_type == 1 else display[:200],
+        # 文本不截断：末尾的 `@所有人` 一类关键词正是下游筛选要用的，截掉等于静默漏消息
+        # （issue #12）。非文本仍保留 200 字的展示上限——它们是标签和标题，不是正文。
+        "parsedContent": display if local_type == 1 else display[:200],
     }