weflow-cli 1.15.1 → 1.17.0

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_decrypt.py

@@ -1275,6 +1275,120 @@ def get_messages(conns, talker, limit=100, offset=0, name_map=None, own_wxid=Non
     return {"messages": collected}
 
 
+def cursor_probe(db_path, key_hex, salt_hex, passphrase='',
+                 tables_per_shard=5, rows_per_table=500):
+    """Measure what a stable incremental cursor would need on this database.
+
+    D-027 keeps `stableCursor: false` until every message backend can honour
+    the same semantics. This probe answers the NT backend's **data-side** half:
+    whether every message table carries the anchor columns, and whether sampled
+    rows actually hold a nonzero `server_id` (the reader's identity falls back
+    to localId+createTime without one, and `local_id` is per-shard, so those
+    rows cannot be resumed across shards). Duplicate server ids are collected
+    across the sample too - an id that appears in two places cannot key a
+    cursor, whatever the column definition says.
+
+    Sampling is bounded and says so (`exhaustive: false`): `tables_per_shard`
+    tables per shard (sorted names, deterministic) read at both rowid ends,
+    `rows_per_table` rows each. A full scan of every shard would cost minutes
+    on a real account; the schema check IS exhaustive - `PRAGMA table_info` is
+    cheap, so every Msg_* table's anchor columns are checked, not sampled.
+
+    Read-only: no write, no network, nothing leaves stdout.
+    """
+    pairs, failures = connect_message_shards_detailed(
+        db_path, key_hex, salt_hex, passphrase)
+    shard_items = []
+    totals = {'tables': 0, 'tablesSampled': 0, 'rowsSampled': 0,
+              'serverIdMissing': 0}
+    anchor_missing_total = 0
+    # server_id(str) -> {(shard, table)} it was sampled in. A set per id keeps
+    # the two rowid ends of one small table from double-counting the same row
+    # as a "duplicate" - both ends see it, but it is one location.
+    id_locations = {}
+
+    for failure in failures:
+        shard_items.append({
+            'name': failure['name'], 'opened': False, 'reason': failure['reason'],
+            'tables': None,
+        })
+
+    for path, conn in pairs:
+        item = {'name': os.path.basename(path), 'opened': True, 'reason': None}
+        try:
+            tables = sorted(msg_tables(conn))
+            item['tables'] = len(tables)
+            totals['tables'] += len(tables)
+
+            # Schema half: exhaustive over every message table.
+            anchor_missing = []
+            for table in tables:
+                cols = table_columns(conn.cursor(), table)
+                missing = [c for c in MESSAGE_ANCHOR_COLUMNS if c not in cols]
+                if missing and missing not in anchor_missing:
+                    anchor_missing.append(missing)
+            anchor_missing_total += len(anchor_missing)
+            item['anchorColumnsMissing'] = anchor_missing
+
+            # Data half: bounded sample, both rowid ends per table. A table
+            # shorter than the bound hands the same rows to both ends - they
+            # are one sample, not two, so rowids are deduplicated per table
+            # (and the same id read at both ends must not look "duplicated").
+            sample_targets = tables[:tables_per_shard]
+            item['tablesSampled'] = len(sample_targets)
+            totals['tablesSampled'] += len(sample_targets)
+            sampled = 0
+            missing_ids = 0
+            for table in sample_targets:
+                c = conn.cursor()
+                seen_rowids = set()
+                table_ids = set()
+                for order in ('ASC', 'DESC'):
+                    c.execute(
+                        'SELECT rowid, server_id FROM "%s" ORDER BY rowid %s LIMIT ?'
+                        % (table, order), (rows_per_table,))
+                    for rowid, server_id in c.fetchall():
+                        if rowid in seen_rowids:
+                            continue
+                        seen_rowids.add(rowid)
+                        sampled += 1
+                        if server_id is None or server_id == 0:
+                            missing_ids += 1
+                        else:
+                            table_ids.add(str(int(server_id)))
+                for sid in table_ids:
+                    id_locations.setdefault(sid, set()).add((item['name'], table))
+            item['rowsSampled'] = sampled
+            item['serverIdMissing'] = missing_ids
+            totals['rowsSampled'] += sampled
+            totals['serverIdMissing'] += missing_ids
+        except Exception as exc:
+            item['reason'] = 'READ_FAILED: %s' % str(exc).split('\n')[0][:120]
+        finally:
+            shard_items.append(item)
+            conn.close()
+
+    duplicates = {sid: locs for sid, locs in id_locations.items() if len(locs) > 1}
+    return {
+        'shards': shard_items,
+        'schemaAnchorMissingTables': anchor_missing_total,
+        'sample': {
+            'tablesPerShard': tables_per_shard,
+            'rowsPerTable': rows_per_table,
+            'exhaustive': False,
+            'tablesTotal': totals['tables'],
+            'tablesSampled': totals['tablesSampled'],
+            'rowsSampled': totals['rowsSampled'],
+            'serverIdMissing': totals['serverIdMissing'],
+            'duplicateServerIds': len(duplicates),
+            'duplicateServerIdSamples': [
+                {'serverId': sid, 'locations': sorted('%s/%s' % loc for loc in locs)}
+                for sid, locs in sorted(duplicates.items())[:20]
+            ],
+        },
+    }
+
+
 def get_contacts(conns, limit=200, keyword=None):
     """Get contacts from NT database, merged across every shard.
 
@@ -1627,10 +1741,23 @@ def main():
     fav_list_parser.add_argument('--key', default=os.environ.get('WEFLOW_NT_KEY'), required=not os.environ.get('WEFLOW_NT_KEY'), help='Key hex (64 chars)')
     fav_list_parser.add_argument('--limit', type=int, default=100)
     fav_list_parser.add_argument('--offset', type=int, default=0)
-    fav_list_parser.add_argument('--keyword', default=os.environ.get('WEFLOW_QUERY_KEYWORD'), help='Search keyword')
+    fav_list_parser.add_argument('--keyword', default=os.environ.get('WEFLOW_QUERY_KEYWORD'), help='Filter by keyword')
     fav_list_parser.add_argument('--type', type=int, dest='fav_type',
                                  help='Filter by type: 1=text 2=image 4=video 5=article 14=chatrecord')
 
+    # cursor-probe command: the data-side half of D-027's stable-cursor answer.
+    cursor_parser = sub.add_parser(
+        'cursor-probe',
+        help='Probe what a stable incremental cursor would need here (read-only, bounded sample)')
+    cursor_parser.add_argument('--db', default=os.environ.get('WEFLOW_DB_PATH'), required=not os.environ.get('WEFLOW_DB_PATH'), help='Path to NT database')
+    cursor_parser.add_argument('--key', default=os.environ.get('WEFLOW_NT_KEY'), required=not os.environ.get('WEFLOW_NT_KEY'), help='Key hex (64 chars)')
+    cursor_parser.add_argument('--salt', default=os.environ.get('WEFLOW_NT_SALT'), required=not os.environ.get('WEFLOW_NT_SALT'), help='Salt hex (32 chars)')
+    cursor_parser.add_argument('--passphrase', default=os.environ.get('WEFLOW_NT_PASSPHRASE'), help='Shared passphrase for deriving per-shard keys')
+    cursor_parser.add_argument('--tables-per-shard', type=int, default=5,
+                               help='Message tables sampled per shard for the identity half (schema half is exhaustive)')
+    cursor_parser.add_argument('--rows-per-table', type=int, default=500,
+                               help='Rows read at each rowid end per sampled table')
+
     args = parser.parse_args()
 
     if args.command == 'scan':
@@ -1812,6 +1939,13 @@ def main():
                                args.keyword, getattr(args, 'fav_type', None))
         print(json.dumps(result, ensure_ascii=True, default=str))
 
+    elif args.command == 'cursor-probe':
+        result = cursor_probe(args.db, args.key, args.salt,
+                              getattr(args, 'passphrase', '') or '',
+                              tables_per_shard=args.tables_per_shard,
+                              rows_per_table=args.rows_per_table)
+        print(json.dumps(result, ensure_ascii=True))
+
     else:
         parser.print_help()