weflow-cli 1.16.0 → 1.19.0

package/scripts/on_this_day.py

@@ -1,178 +1,178 @@
-"""「那年今日」：把几年前的今天你在聊什么捞出来。
-
-为什么只有本地全量数据能做到：微信的搜索只覆盖当前会话、而且历史一长就翻不动；
-这里直接按 `create_time` 扫所有分片里的每一张会话表，所以"五年前的今天"是能查的。
-
-用法：
-    python scripts/on_this_day.py                     # 1 / 3 / 5 年前的今天
-    python scripts/on_this_day.py --years 2,4,6
-    python scripts/on_this_day.py --talker 老表亲戚群   # 只看某个会话
-    python scripts/on_this_day.py --json
-"""
-from __future__ import annotations
-
-import argparse
-import re
-import json
-import pathlib
-import sys
-import time
-from collections import Counter, defaultdict
-from datetime import datetime, timezone, timedelta
-
-SCRIPT_DIR = pathlib.Path(__file__).resolve().parent
-sys.path.insert(0, str(SCRIPT_DIR))
-
-from _utils import load_config, decrypt_lock  # noqa: E402
-import nt_decrypt as nd  # noqa: E402
-
-TZ = timezone(timedelta(hours=8))
-DEFAULT_YEARS = (1, 3, 5)
-
-
-def _keys(cfg):
-    key = decrypt_lock(cfg.get('ntKey', '') or '')
-    salt = decrypt_lock(cfg.get('ntSalt', '') or '')
-    pw = decrypt_lock(cfg.get('favPassphrase', '') or cfg.get('decryptKey', '') or '')
-    return key, salt, pw
-
-
-def _text_of(content, local_type=0):
-    """消息正文 → 一行字。
-
-    **不能只看 `message_content` 是不是以 `<` 开头**：appmsg 那一族（链接/文件/小程序）
-    的内容是 zstd 压缩的二进制，原样打出来就是 `(/`$` 这种碎片（第一版就是这么翻车的）。
-    这里直接复用 `nt_decrypt` 里那套已经处理过压缩、类型标签与引用消息的显示层。
-    """
-    lt = int(local_type or 0)
-    base = lt & 0xFFFFFFFF
-    if base == 1:                      # 纯文本
-        text = nd._decode_content(content)
-        text = ' '.join(str(text).split())[:120]
-        # 群消息的 `message_content` 自带 `wxid_xxx: ` 前缀，而发言人已经在左边显示了一次
-        return re.sub(r'^[A-Za-z0-9_\-]+@?(chatroom|openim)?\s*:\s*', '', text)[:120]
-    try:
-        out = nd.non_text_display(lt, content)[:120]
-        return re.sub(r'^[A-Za-z0-9_\-]+:\s*', '', out)[:120]
-    except Exception:
-        return ''
-
-
-def day_bounds(dt):
-    start = datetime(dt.year, dt.month, dt.day, tzinfo=TZ)
-    return int(start.timestamp()), int((start + timedelta(days=1)).timestamp())
-
-
-def collect_for_day(conns, name_map, target_day, talker_filter=''):
-    """{talker: [(ts, sender, text), ...]} for one calendar day."""
-    start, end = day_bounds(target_day)
-    out = defaultdict(list)
-    for conn in conns:
-        c = conn.cursor()
-        try:
-            c.execute('SELECT user_name FROM Name2Id WHERE is_session = 1')
-            sessions = [r[0] for r in c.fetchall() if r[0]]
-        except Exception:
-            continue
-        # `real_sender_id` 是 **Name2Id 的 rowid**，不是 wxid —— 少这一步映射，
-        # 输出里发言人就全是 `65`、`4`、`8` 这样的数字（第一版就是这样）。
-        try:
-            c.execute('SELECT rowid, user_name FROM Name2Id')
-            sender_map = {r[0]: r[1] for r in c.fetchall()}
-        except Exception:
-            sender_map = {}
-        for talker in sessions:
-            if talker_filter and talker_filter not in (talker, name_map.get(talker, talker)):
-                continue
-            tbl = f'Msg_{__import__("hashlib").md5(talker.encode()).hexdigest()}'
-            try:
-                c.execute('SELECT COUNT(*) FROM sqlite_master WHERE name=?', (tbl,))
-                if c.fetchone()[0] == 0:
-                    continue
-                c.execute(f'SELECT create_time, real_sender_id, local_type, message_content '
-                          'FROM "{0}" WHERE create_time >= ? AND create_time < ? ORDER BY create_time'.format(tbl),
-                          (start, end))
-                for ts, sender, ltype, content in c.fetchall():
-                    text = _text_of(content, ltype)
-                    if text:
-                        who = sender_map.get(sender, '')
-                        out[name_map.get(talker, talker)].append(
-                            (int(ts), name_map.get(who, who), text))
-            except Exception:
-                continue
-    return out
-
-
-def main():
-    ap = argparse.ArgumentParser(description='那几年的今天你在聊什么')
-    ap.add_argument('--years', default=','.join(str(y) for y in DEFAULT_YEARS),
-                    help='往前看几年，逗号分隔（默认 1,3,5）')
-    ap.add_argument('--talker', default='', help='只看某个会话（wxid 或昵称）')
-    ap.add_argument('--limit', type=int, default=6, help='每天最多列几条（默认 6）')
-    ap.add_argument('--json', action='store_true')
-    args = ap.parse_args()
-
-    cfg = load_config()
-    db = cfg.get('ntDbPath') or ''
-    if not db:
-        raise SystemExit('配置里没有 ntDbPath，先跑 weflow-cli init')
-    key, salt, pw = _keys(cfg)
-    conns = nd.connect_message_shards(db, key, salt, pw)
-    if not conns:
-        raise SystemExit('打不开任何消息分片')
-
-    try:
-        # 联系人在 **contact.db**，不在消息库里 —— 从消息库找 `contact` 表一定落空，
-        # 输出里就只剩 `47966561144@chatroom` 和 `wxid_xxx`（第一版就是这样）。
-        name_map = {}
-        try:
-            from network import load_graph
-            people, _rooms, _members = load_graph(cfg)
-            name_map = {p['username']: (p['remark'] or p['nick'] or p['username'])
-                        for p in people.values()}
-        except Exception as exc:
-            print(f'[WARN] 读联系人失败（{type(exc).__name__}: {exc}），下面显示 id',
-                  file=sys.stderr)
-
-        today = datetime.now(TZ)
-        years = [int(y) for y in args.years.split(',') if y.strip().isdigit()]
-        result = []
-        for y in years:
-            try:
-                day = today.replace(year=today.year - y)
-            except ValueError:      # 2 月 29 日
-                day = today.replace(year=today.year - y, day=28)
-            by_talker = collect_for_day(conns, name_map, day, args.talker)
-            total = sum(len(v) for v in by_talker.values())
-            top = Counter({k: len(v) for k, v in by_talker.items()}).most_common(3)
-            picks = []
-            for talker, msgs in sorted(by_talker.items(), key=lambda kv: -len(kv[1]))[:3]:
-                for ts, sender, text in msgs[:max(1, args.limit // 3)]:
-                    picks.append({'talker': talker, 'time': datetime.fromtimestamp(ts, tz=TZ).strftime('%H:%M'),
-                                  'sender': sender, 'text': text})
-            result.append({'date': day.strftime('%Y-%m-%d'), 'yearsAgo': y,
-                           'total': total, 'threads': top, 'samples': picks[:args.limit]})
-    finally:
-        for conn in conns:
-            try:
-                conn.close()
-            except Exception:
-                pass
-
-    if args.json:
-        print(json.dumps({'success': True, 'days': result}, ensure_ascii=False, indent=2))
-        return
-
-    for item in result:
-        head = f"{item['date']}（{item['yearsAgo']} 年前的今天）"
-        if not item['total']:
-            print(f'\n{head}\n  那天没有聊天记录')
-            continue
-        threads = '、'.join(f'{n}({c})' for n, c in item['threads'])
-        print(f"\n{head}  {item['total']} 条  {threads}")
-        for s in item['samples']:
-            print(f"  {s['time']}  {s['talker']} · {s['sender'] or '?'}：{s['text']}")
-
-
-if __name__ == '__main__':
-    main()
+"""「那年今日」：把几年前的今天你在聊什么捞出来。
+
+为什么只有本地全量数据能做到：微信的搜索只覆盖当前会话、而且历史一长就翻不动；
+这里直接按 `create_time` 扫所有分片里的每一张会话表，所以"五年前的今天"是能查的。
+
+用法：
+    python scripts/on_this_day.py                     # 1 / 3 / 5 年前的今天
+    python scripts/on_this_day.py --years 2,4,6
+    python scripts/on_this_day.py --talker 老表亲戚群   # 只看某个会话
+    python scripts/on_this_day.py --json
+"""
+from __future__ import annotations
+
+import argparse
+import re
+import json
+import pathlib
+import sys
+import time
+from collections import Counter, defaultdict
+from datetime import datetime, timezone, timedelta
+
+SCRIPT_DIR = pathlib.Path(__file__).resolve().parent
+sys.path.insert(0, str(SCRIPT_DIR))
+
+from _utils import load_config, decrypt_lock  # noqa: E402
+import nt_decrypt as nd  # noqa: E402
+
+TZ = timezone(timedelta(hours=8))
+DEFAULT_YEARS = (1, 3, 5)
+
+
+def _keys(cfg):
+    key = decrypt_lock(cfg.get('ntKey', '') or '')
+    salt = decrypt_lock(cfg.get('ntSalt', '') or '')
+    pw = decrypt_lock(cfg.get('favPassphrase', '') or cfg.get('decryptKey', '') or '')
+    return key, salt, pw
+
+
+def _text_of(content, local_type=0):
+    """消息正文 → 一行字。
+
+    **不能只看 `message_content` 是不是以 `<` 开头**：appmsg 那一族（链接/文件/小程序）
+    的内容是 zstd 压缩的二进制，原样打出来就是 `(/`$` 这种碎片（第一版就是这么翻车的）。
+    这里直接复用 `nt_decrypt` 里那套已经处理过压缩、类型标签与引用消息的显示层。
+    """
+    lt = int(local_type or 0)
+    base = lt & 0xFFFFFFFF
+    if base == 1:                      # 纯文本
+        text = nd._decode_content(content)
+        text = ' '.join(str(text).split())[:120]
+        # 群消息的 `message_content` 自带 `wxid_xxx: ` 前缀，而发言人已经在左边显示了一次
+        return re.sub(r'^[A-Za-z0-9_\-]+@?(chatroom|openim)?\s*:\s*', '', text)[:120]
+    try:
+        out = nd.non_text_display(lt, content)[:120]
+        return re.sub(r'^[A-Za-z0-9_\-]+:\s*', '', out)[:120]
+    except Exception:
+        return ''
+
+
+def day_bounds(dt):
+    start = datetime(dt.year, dt.month, dt.day, tzinfo=TZ)
+    return int(start.timestamp()), int((start + timedelta(days=1)).timestamp())
+
+
+def collect_for_day(conns, name_map, target_day, talker_filter=''):
+    """{talker: [(ts, sender, text), ...]} for one calendar day."""
+    start, end = day_bounds(target_day)
+    out = defaultdict(list)
+    for conn in conns:
+        c = conn.cursor()
+        try:
+            c.execute('SELECT user_name FROM Name2Id WHERE is_session = 1')
+            sessions = [r[0] for r in c.fetchall() if r[0]]
+        except Exception:
+            continue
+        # `real_sender_id` 是 **Name2Id 的 rowid**，不是 wxid —— 少这一步映射，
+        # 输出里发言人就全是 `65`、`4`、`8` 这样的数字（第一版就是这样）。
+        try:
+            c.execute('SELECT rowid, user_name FROM Name2Id')
+            sender_map = {r[0]: r[1] for r in c.fetchall()}
+        except Exception:
+            sender_map = {}
+        for talker in sessions:
+            if talker_filter and talker_filter not in (talker, name_map.get(talker, talker)):
+                continue
+            tbl = f'Msg_{__import__("hashlib").md5(talker.encode()).hexdigest()}'
+            try:
+                c.execute('SELECT COUNT(*) FROM sqlite_master WHERE name=?', (tbl,))
+                if c.fetchone()[0] == 0:
+                    continue
+                c.execute(f'SELECT create_time, real_sender_id, local_type, message_content '
+                          'FROM "{0}" WHERE create_time >= ? AND create_time < ? ORDER BY create_time'.format(tbl),
+                          (start, end))
+                for ts, sender, ltype, content in c.fetchall():
+                    text = _text_of(content, ltype)
+                    if text:
+                        who = sender_map.get(sender, '')
+                        out[name_map.get(talker, talker)].append(
+                            (int(ts), name_map.get(who, who), text))
+            except Exception:
+                continue
+    return out
+
+
+def main():
+    ap = argparse.ArgumentParser(description='那几年的今天你在聊什么')
+    ap.add_argument('--years', default=','.join(str(y) for y in DEFAULT_YEARS),
+                    help='往前看几年，逗号分隔（默认 1,3,5）')
+    ap.add_argument('--talker', default=os.environ.get('WEFLOW_TALKER', ''), help='只看某个会话（wxid 或昵称）')
+    ap.add_argument('--limit', type=int, default=6, help='每天最多列几条（默认 6）')
+    ap.add_argument('--json', action='store_true')
+    args = ap.parse_args()
+
+    cfg = load_config()
+    db = cfg.get('ntDbPath') or ''
+    if not db:
+        raise SystemExit('配置里没有 ntDbPath，先跑 weflow-cli init')
+    key, salt, pw = _keys(cfg)
+    conns = nd.connect_message_shards(db, key, salt, pw)
+    if not conns:
+        raise SystemExit('打不开任何消息分片')
+
+    try:
+        # 联系人在 **contact.db**，不在消息库里 —— 从消息库找 `contact` 表一定落空，
+        # 输出里就只剩 `47966561144@chatroom` 和 `wxid_xxx`（第一版就是这样）。
+        name_map = {}
+        try:
+            from network import load_graph
+            people, _rooms, _members = load_graph(cfg)
+            name_map = {p['username']: (p['remark'] or p['nick'] or p['username'])
+                        for p in people.values()}
+        except Exception as exc:
+            print(f'[WARN] 读联系人失败（{type(exc).__name__}: {exc}），下面显示 id',
+                  file=sys.stderr)
+
+        today = datetime.now(TZ)
+        years = [int(y) for y in args.years.split(',') if y.strip().isdigit()]
+        result = []
+        for y in years:
+            try:
+                day = today.replace(year=today.year - y)
+            except ValueError:      # 2 月 29 日
+                day = today.replace(year=today.year - y, day=28)
+            by_talker = collect_for_day(conns, name_map, day, args.talker)
+            total = sum(len(v) for v in by_talker.values())
+            top = Counter({k: len(v) for k, v in by_talker.items()}).most_common(3)
+            picks = []
+            for talker, msgs in sorted(by_talker.items(), key=lambda kv: -len(kv[1]))[:3]:
+                for ts, sender, text in msgs[:max(1, args.limit // 3)]:
+                    picks.append({'talker': talker, 'time': datetime.fromtimestamp(ts, tz=TZ).strftime('%H:%M'),
+                                  'sender': sender, 'text': text})
+            result.append({'date': day.strftime('%Y-%m-%d'), 'yearsAgo': y,
+                           'total': total, 'threads': top, 'samples': picks[:args.limit]})
+    finally:
+        for conn in conns:
+            try:
+                conn.close()
+            except Exception:
+                pass
+
+    if args.json:
+        print(json.dumps({'success': True, 'days': result}, ensure_ascii=False, indent=2))
+        return
+
+    for item in result:
+        head = f"{item['date']}（{item['yearsAgo']} 年前的今天）"
+        if not item['total']:
+            print(f'\n{head}\n  那天没有聊天记录')
+            continue
+        threads = '、'.join(f'{n}({c})' for n, c in item['threads'])
+        print(f"\n{head}  {item['total']} 条  {threads}")
+        for s in item['samples']:
+            print(f"  {s['time']}  {s['talker']} · {s['sender'] or '?'}：{s['text']}")
+
+
+if __name__ == '__main__':
+    main()