mailops 0.2.4__tar.gz → 0.2.5__tar.gz

{mailops-0.2.4 → mailops-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mailops
-Version: 0.2.4
+Version: 0.2.5
 Summary: 邮件操作工具箱 — 下载、统计、搜索、转发、附件管理、发送
 Author: Song Wupei
 License-Expression: MIT
@@ -186,7 +186,8 @@ accounts:
 |--------|--------|
 | `maildl.py` | `mailops download-docs` |
 | `mailfwd.py` | `mailops forward` |
-| `sync163.py` | `mailops fetch` (IMAP → Maildir) + `mailops organize` (分类) |
+| `sync163.py` | `sync_account.py 163` (IMAP → Maildir，索引去重) + `mailops organize` |
+| `mbsync` | `sync_account.py QQ` (IMAP → Maildir，索引去重，本地删除不重下) |
 | `sync163.py` | `mailops fetch -m 163` |
 | `run-wf.py` | `mailops workflow` |
 | `mailx` (系统命令) | `mailops send` |

{mailops-0.2.4 → mailops-0.2.5}/README.md

@@ -165,7 +165,8 @@ accounts:
 |--------|--------|
 | `maildl.py` | `mailops download-docs` |
 | `mailfwd.py` | `mailops forward` |
-| `sync163.py` | `mailops fetch` (IMAP → Maildir) + `mailops organize` (分类) |
+| `sync163.py` | `sync_account.py 163` (IMAP → Maildir，索引去重) + `mailops organize` |
+| `mbsync` | `sync_account.py QQ` (IMAP → Maildir，索引去重，本地删除不重下) |
 | `sync163.py` | `mailops fetch -m 163` |
 | `run-wf.py` | `mailops workflow` |
 | `mailx` (系统命令) | `mailops send` |

{mailops-0.2.4 → mailops-0.2.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "mailops"
-version = "0.2.4"
+version = "0.2.5"
 description = "邮件操作工具箱 — 下载、统计、搜索、转发、附件管理、发送"
 readme = "README.md"
 license = "MIT"

{mailops-0.2.4 → mailops-0.2.5}/src/mailops.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mailops
-Version: 0.2.4
+Version: 0.2.5
 Summary: 邮件操作工具箱 — 下载、统计、搜索、转发、附件管理、发送
 Author: Song Wupei
 License-Expression: MIT
@@ -186,7 +186,8 @@ accounts:
 |--------|--------|
 | `maildl.py` | `mailops download-docs` |
 | `mailfwd.py` | `mailops forward` |
-| `sync163.py` | `mailops fetch` (IMAP → Maildir) + `mailops organize` (分类) |
+| `sync163.py` | `sync_account.py 163` (IMAP → Maildir，索引去重) + `mailops organize` |
+| `mbsync` | `sync_account.py QQ` (IMAP → Maildir，索引去重，本地删除不重下) |
 | `sync163.py` | `mailops fetch -m 163` |
 | `run-wf.py` | `mailops workflow` |
 | `mailx` (系统命令) | `mailops send` |

{mailops-0.2.4 → mailops-0.2.5}/src/mailops.egg-info/SOURCES.txt

@@ -3,6 +3,7 @@ pyproject.toml
 src/maildl.py
 src/mailfwd.py
 src/sync163.py
+src/sync_account.py
 src/mailops/__init__.py
 src/mailops/cli.py
 src/mailops/config.py

{mailops-0.2.4 → mailops-0.2.5}/src/mailops.egg-info/top_level.txt

@@ -2,3 +2,4 @@ maildl
 mailfwd
 mailops
 sync163
+sync_account

{mailops-0.2.4 → mailops-0.2.5}/src/sync163.py

@@ -22,19 +22,23 @@ PASS_ENV = "MAIL163_SMTP_PASS_AERC"
 
 
 def load_index():
-    """加载已知 Message-ID → 文件名 的索引。"""
+    """加载已知 Message-ID 集合。"""
     if INDEX_FILE.exists():
         try:
-            return json.loads(INDEX_FILE.read_text())
+            data = json.loads(INDEX_FILE.read_text())
+            # 兼容旧格式（dict → 取 keys；新格式是 list）
+            if isinstance(data, dict):
+                return set(data.keys())
+            return set(data)
         except (json.JSONDecodeError, OSError):
             pass
-    return {}
+    return set()
 
 
 def save_index(idx):
-    """保存索引到磁盘。"""
+    """保存索引到磁盘（Message-ID 集合）。"""
     INDEX_FILE.parent.mkdir(parents=True, exist_ok=True)
-    INDEX_FILE.write_text(json.dumps(idx))
+    INDEX_FILE.write_text(json.dumps(sorted(idx)))
 
 
 def extract_message_id(msg_bytes):
@@ -55,23 +59,30 @@ def extract_message_id(msg_bytes):
 
 
 def backfill_index(known):
-    """首次运行：从已有 Maildir 文件重建索引，避免重复下载。"""
+    """首次运行：从已有 Maildir 文件重建索引（递归扫描所有子文件夹）。
+
+    不仅扫描 INBOX，也扫描 organize 移入的 GitHub/、Archive/ 等子文件夹。
+    """
     existing = 0
-    for sub in ["cur", "new"]:
-        folder = MAILDIR / sub
-        if not folder.exists():
-            continue
-        for fpath in folder.iterdir():
-            if not fpath.is_file():
+    maildir_root = MAILDIR.parent  # ~/Mail/163/
+    for maildir_root, dirs, files in os.walk(maildir_root):
+        # 跳过 tmp/ 目录
+        dirs[:] = [d for d in dirs if d != "tmp"]
+        for sub in ["cur", "new"]:
+            folder = Path(maildir_root) / sub
+            if not folder.is_dir():
                 continue
-            try:
-                # 只读前 8KB 足以包含所有头部
-                mid = extract_message_id(fpath.read_bytes()[:8192])
-                if mid and mid not in known:
-                    known[mid] = fpath.name
-                    existing += 1
-            except OSError:
-                pass
+            for fpath in folder.iterdir():
+                if not fpath.is_file() or fpath.name.startswith("."):
+                    continue
+                try:
+                    # 只读前 8KB 足以包含所有头部
+                    mid = extract_message_id(fpath.read_bytes()[:8192])
+                    if mid and mid not in known:
+                        known.add(mid)
+                        existing += 1
+                except OSError:
+                    pass
     if existing:
         print(f"从本地 Maildir 重建索引: +{existing} 封")
     return known
@@ -130,9 +141,9 @@ def sync(limit=None):
 
         # ---- 先通过只下载 HEADER 来获取 Message-ID（轻量级） ----
         # 批量获取所有邮件的 Message-ID，用于判断哪些是新的
-        ids = list(reversed(all_ids))
+        ids = all_ids  # 保持原始顺序（升序）
         if limit:
-            ids = ids[-limit:]
+            ids = ids[-limit:]  # 取最后 N 封（最新）
 
         # 分批处理，每批 200 封
         BATCH = 200
@@ -141,7 +152,9 @@ def sync(limit=None):
 
         for i in range(0, len(ids), BATCH):
             batch = ids[i : i + BATCH]
-            id_range = f"{batch[0].decode()}:{batch[-1].decode()}"
+            # 确保范围升序（min:max），修复倒序范围导致 163 返回异常
+            nums = sorted(int(x) for x in batch)
+            id_range = f"{nums[0]}:{nums[-1]}"
             status, hdr_data = conn.fetch(
                 id_range, "(BODY.PEEK[HEADER.FIELDS (MESSAGE-ID)])"
             )
@@ -190,7 +203,7 @@ def sync(limit=None):
             fpath.write_bytes(msg_bytes)
 
             # 更新索引
-            known[msg_id] = fname
+            known.add(msg_id)
 
             new_count += 1
             # 快速预览主题
@@ -208,14 +221,6 @@ def sync(limit=None):
     # ---- 保存索引 ----
     save_index(known)
 
-    # ---- 清理索引中已经不存在的文件 ----
-    stale = [mid for mid, fname in known.items() if not (MAILDIR / "new" / fname).exists() and not (MAILDIR / "cur" / fname).exists()]
-    if stale:
-        for mid in stale:
-            del known[mid]
-        save_index(known)
-        print(f"  (清理了 {len(stale)} 条过期索引记录)")
-
     print(f"\n同步完成，新增 {new_count} 封 → {MAILDIR}")
 
 

mailops-0.2.5/src/sync_account.py

@@ -0,0 +1,240 @@
+#!/usr/bin/env python3
+"""IMAP → Maildir 同步（通用版，索引去重，支持 163/QQ 等）。
+
+用法: python3 sync_account.py 163
+      python3 sync_account.py QQ --limit 50
+      python3 sync_account.py 163 --limit 10
+"""
+
+import imaplib
+import json
+import os
+import re
+import ssl
+import sys
+import time
+from pathlib import Path
+
+# ---- 账号配置 ----
+ACCOUNTS = {
+    "163": {
+        "host": "imap.163.com",
+        "user": "songwupei@163.com",
+        "pass_file": Path.home() / ".config" / "aerc" / "163-pass",
+        "maildir": Path.home() / "Mail" / "163" / "INBOX",
+        "need_id": True,   # 163 需要 IMAP ID 命令
+    },
+    "QQ": {
+        "host": "imap.qq.com",
+        "user": "songwupei@qq.com",
+        "pass_file": Path.home() / ".config" / "aerc" / "qq-pass",
+        "maildir": Path.home() / "Mail" / "QQ" / "INBOX",
+        "need_id": False,
+    },
+}
+
+CACHE_DIR = Path.home() / ".cache" / "aerc"
+
+
+def index_path(account: str) -> Path:
+    return CACHE_DIR / f"sync-{account}-index.json"
+
+
+def load_index(account: str) -> set:
+    path = index_path(account)
+    if path.exists():
+        try:
+            data = json.loads(path.read_text())
+            if isinstance(data, dict):
+                return set(data.keys())
+            return set(data)
+        except (json.JSONDecodeError, OSError):
+            pass
+    return set()
+
+
+def save_index(account: str, idx: set):
+    path = index_path(account)
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(json.dumps(sorted(idx)))
+
+
+def extract_message_id(msg_bytes):
+    """从邮件字节中快速提取 Message-ID。"""
+    header_end = msg_bytes.find(b"\r\n\r\n")
+    if header_end == -1:
+        header_end = msg_bytes.find(b"\n\n")
+    if header_end == -1:
+        header_end = len(msg_bytes)
+    header = msg_bytes[:header_end].decode("utf-8", errors="replace")
+    m = re.search(r"(?im)^Message-ID:\s*(.+)", header)
+    if m:
+        return m.group(1).strip().strip("<>")
+    return None
+
+
+def backfill_index(maildir: Path, known: set) -> set:
+    """从已有 Maildir 递归重建索引。"""
+    existing = 0
+    root = maildir.parent  # ~/Mail/<account>/
+    if not root.is_dir():
+        return known
+    for walk_root, dirs, files in os.walk(root):
+        dirs[:] = [d for d in dirs if d != "tmp"]
+        for sub in ["cur", "new"]:
+            folder = Path(walk_root) / sub
+            if not folder.is_dir():
+                continue
+            for fpath in folder.iterdir():
+                if not fpath.is_file() or fpath.name.startswith("."):
+                    continue
+                try:
+                    mid = extract_message_id(fpath.read_bytes()[:8192])
+                    if mid and mid not in known:
+                        known.add(mid)
+                        existing += 1
+                except OSError:
+                    pass
+    if existing:
+        print(f"  从本地 Maildir 重建索引: +{existing} 封")
+    return known
+
+
+def sync(account: str, limit: int = None):
+    cfg = ACCOUNTS.get(account)
+    if not cfg:
+        print(f"错误: 未知账号 '{account}'，可用: {', '.join(ACCOUNTS)}")
+        sys.exit(1)
+
+    host = cfg["host"]
+    user = cfg["user"]
+    maildir = cfg["maildir"]
+    pass_file = cfg["pass_file"]
+    need_id = cfg.get("need_id", False)
+
+    # ---- 密码 ----
+    if pass_file.exists():
+        password = pass_file.read_text().strip()
+    else:
+        print(f"错误: 密码文件不存在: {pass_file}")
+        sys.exit(1)
+    if not password:
+        print(f"错误: 密码为空: {pass_file}")
+        sys.exit(1)
+
+    # ---- 初始化 Maildir ----
+    for sub in ["cur", "new", "tmp"]:
+        (maildir / sub).mkdir(parents=True, exist_ok=True)
+
+    # ---- 加载/重建索引 ----
+    known = load_index(account)
+    if not known:
+        known = backfill_index(maildir, known)
+        save_index(account, known)
+
+    print(f"[{account}] 服务器连接中...")
+
+    # ---- 连接 ----
+    ctx = ssl.create_default_context()
+    with imaplib.IMAP4_SSL(host, 993, ssl_context=ctx) as conn:
+        conn.login(user, password)
+
+        # 163.com 必须的 ID 命令
+        if need_id:
+            try:
+                conn.socket().send(
+                    b'a001 ID ("name" "mail-dl" "version" "1.0")\r\n'
+                )
+                conn.socket().recv(1024)
+            except Exception:
+                pass
+
+        conn.select("INBOX")
+        status, data = conn.search(None, "ALL")
+        if status != "OK":
+            print("  搜索失败")
+            return
+
+        all_ids = data[0].split()
+        if not all_ids:
+            print("  收件箱为空")
+            return
+
+        total = len(all_ids)
+        print(f"  服务器 {total} 封，索引 {len(known)} 封")
+
+        ids = all_ids
+        if limit:
+            ids = ids[-limit:]
+
+        BATCH = 200
+        to_fetch = []
+        seen_msgids = set()
+
+        for i in range(0, len(ids), BATCH):
+            batch = ids[i : i + BATCH]
+            nums = sorted(int(x) for x in batch)
+            id_range = f"{nums[0]}:{nums[-1]}"
+            status, hdr_data = conn.fetch(
+                id_range, "(BODY.PEEK[HEADER.FIELDS (MESSAGE-ID)])"
+            )
+            if status != "OK":
+                continue
+
+            for item in hdr_data:
+                if isinstance(item, tuple):
+                    header_bytes = item[1]
+                    if header_bytes:
+                        msg_id = extract_message_id(header_bytes)
+                        if msg_id and msg_id not in known and msg_id not in seen_msgids:
+                            marker = item[0].decode() if isinstance(
+                                item[0], bytes
+                            ) else str(item[0])
+                            m = re.match(r"(\d+)", marker)
+                            if m:
+                                to_fetch.append((m.group(1).encode(), msg_id))
+                                seen_msgids.add(msg_id)
+
+        new_count = 0
+        for num_bytes, msg_id in to_fetch:
+            status, msg_data = conn.fetch(num_bytes, "(RFC822)")
+            if status != "OK":
+                continue
+
+            msg_bytes = msg_data[0][1]
+            if msg_bytes is None:
+                continue
+
+            ts = int(time.time())
+            fname = f"{ts}.{num_bytes.decode()}.{new_count}.{os.uname().nodename}"
+            fpath = maildir / "new" / fname
+            fpath.write_bytes(msg_bytes)
+
+            known.add(msg_id)
+            new_count += 1
+
+            subject = "(无主题)"
+            try:
+                s = re.search(rb"(?im)^Subject:\s*(.+)", msg_bytes[:4096])
+                if s:
+                    subject = s.group(1).decode("utf-8", errors="replace").strip()
+            except Exception:
+                pass
+            print(f"  [{new_count}] {subject}")
+
+    save_index(account, known)
+    print(f"  完成，新增 {new_count} 封\n")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print(f"用法: python3 sync_account.py <163|QQ> [--limit N]")
+        print(f"可用账号: {', '.join(ACCOUNTS)}")
+        sys.exit(1)
+
+    account = sys.argv[1]
+    limit = None
+    if len(sys.argv) > 2 and sys.argv[2] == "--limit":
+        limit = int(sys.argv[3]) if len(sys.argv) > 3 else 50
+
+    sync(account, limit)