mirror of https://github.com/jackwener/wx-cli.git
review: tighten attachment extraction scope
jackwener
parent
7feacc6371
commit
b63589b368
|
|
@ -211,14 +211,14 @@ wx biz-articles --json | jq '.[].url' # 下游消费 URL
|
|||
|
||||
每条返回：`account` / `account_username` / `title` / `url` / `digest` / `cover_url` / `time` / `timestamp` / `recv_time_str`。多图文推送会展开成多行。
|
||||
|
||||
### 附件提取（图片 / 视频 / 文件 / 语音）
|
||||
### 附件提取（图片）
|
||||
|
||||
聊天里的附件本体存在 `xwechat_files/<wxid>/msg/attach/...` 下的 `.dat` 文件，需要按消息所在 `message_resource.db` 的 md5 + 平台相关 image key 解码才能拿到原图。
|
||||
|
||||
```bash
|
||||
# 1) 列出会话里的附件，先拿到不透明的 attachment_id（默认 image，可多选）
|
||||
# 1) 列出会话里的图片附件，先拿到不透明的 attachment_id
|
||||
wx attachments "张三"
|
||||
wx attachments "AI群" --kind image --kind video -n 100
|
||||
wx attachments "AI群" --kind image -n 100
|
||||
wx attachments "AI群" --since 2026-04-01 --until 2026-04-15
|
||||
|
||||
# 2) 把单个 attachment_id 解密写出去（扩展名建议保留 .jpg / .mp4 等）
|
||||
|
|
@ -226,7 +226,7 @@ wx extract <attachment_id> -o ~/Desktop/photo.jpg
|
|||
wx extract <attachment_id> -o /tmp/x.jpg --overwrite
|
||||
```
|
||||
|
||||
`attachments` 输出每条带：`attachment_id` / `kind` / `type` / `local_id` / `timestamp` / `time`，群聊里还有 `sender`。
|
||||
`attachments` 输出每条带：`attachment_id` / `kind` / `type` / `local_id` / `timestamp` / `time`，群聊里还有 `sender`。当前 `kind` 固定为 `image`；命令名保留成 `attachments` 是为了后续扩到其他附件类型时不 break CLI。
|
||||
|
||||
`extract` 输出报告里带：`md5` / `dat_path` / `dat_size` / `output` / `output_size` / `format`（实际识别出的图片格式：jpg / png / gif / webp / hevc 等）/ `decoder`（实际选用的解码器：`legacy_xor` / `v1_aes` / `v2`）。
|
||||
|
||||
|
|
|
|||
10
SKILL.md
10
SKILL.md
|
|
@ -242,14 +242,14 @@ wx biz-articles --since 2026-05-10 --json | jq '.[].url'
|
|||
|
||||
每条返回的字段：`account` / `account_username`（`gh_*`）/ `title` / `url`（`mp.weixin.qq.com` 链接）/ `digest` / `cover_url` / `time` + `timestamp`（文章发布时间）/ `recv_time_str` + `recv_time`（微信接收推送的时间）。多图文推送会展开为多行。
|
||||
|
||||
### 附件提取（图片 / 视频 / 文件 / 语音）
|
||||
### 附件提取（图片）
|
||||
|
||||
聊天里的图片/视频/文件本体在 `xwechat_files/<wxid>/msg/attach/...` 下加密存储（`.dat`），需要按消息所在 `message_resource.db` 的 md5 + 平台相关 image key 才能解码。两步走：
|
||||
聊天里的图片本体在 `xwechat_files/<wxid>/msg/attach/...` 下加密存储（`.dat`），需要按消息所在 `message_resource.db` 的 md5 + 平台相关 image key 才能解码。两步走：
|
||||
|
||||
```bash
|
||||
# 1) 先列出附件，拿到不透明的 attachment_id（默认 image，可多选）
|
||||
# 1) 先列出图片附件，拿到不透明的 attachment_id
|
||||
wx attachments "张三"
|
||||
wx attachments "AI群" --kind image --kind video -n 100
|
||||
wx attachments "AI群" --kind image -n 100
|
||||
wx attachments "AI群" --since 2026-04-01 --until 2026-04-15
|
||||
|
||||
# 2) 用 attachment_id 把单个资源解密写到指定路径
|
||||
|
|
@ -257,7 +257,7 @@ wx extract <attachment_id> -o ~/Desktop/photo.jpg
|
|||
wx extract <attachment_id> -o /tmp/x.jpg --overwrite
|
||||
```
|
||||
|
||||
`attachments` 输出每条带：`attachment_id` / `kind`（image/voice/video/file）/ `type` / `local_id` / `timestamp` / `time`，群聊里另带 `sender`。
|
||||
`attachments` 输出每条带：`attachment_id` / `kind`（当前固定 `image`）/ `type` / `local_id` / `timestamp` / `time`，群聊里另带 `sender`。命令名保留成 `attachments` 是为了后续扩到其他附件类型时不 break CLI。
|
||||
|
||||
`extract` 报告里带：`md5` / `dat_path` / `dat_size` / `output` / `output_size` / `format`（实际识别出的图片格式：jpg / png / gif / webp / hevc 等）/ `decoder`（实际选用的解码器：`legacy_xor` / `v1_aes` / `v2`）。
|
||||
|
||||
|
|
|
|||
|
|
@ -48,6 +48,7 @@ pub fn lookup_md5_blocking(
|
|||
resource_db_path: &Path,
|
||||
chat: &str,
|
||||
local_id: i64,
|
||||
create_time: i64,
|
||||
msg_local_type_lo32: i64,
|
||||
) -> Result<Option<AttachmentMetadata>> {
|
||||
let conn = Connection::open_with_flags(
|
||||
|
|
@ -68,9 +69,25 @@ pub fn lookup_md5_blocking(
|
|||
return Ok(None);
|
||||
};
|
||||
|
||||
// 2) MessageResourceInfo: 同 chat 内 local_id 也会复用，按 create_time DESC 取最新
|
||||
// 2) MessageResourceInfo:
|
||||
// 同 chat 内 local_id 会复用，所以先用 create_time 精确命中；
|
||||
// 若资源库里的时间戳跟 message_N.db 不完全对齐，再 fallback 到“同 local_id/type 取最新”
|
||||
// message_local_type 高 32 bit 是版本/会话 flag，低 32 bit 才是真实类型
|
||||
let packed: Option<Vec<u8>> = conn
|
||||
let packed_exact: Option<Vec<u8>> = conn
|
||||
.query_row(
|
||||
"SELECT packed_info FROM MessageResourceInfo
|
||||
WHERE chat_id = ?1
|
||||
AND message_local_id = ?2
|
||||
AND (message_local_type = ?3 OR message_local_type % 4294967296 = ?3)
|
||||
AND message_create_time = ?4
|
||||
ORDER BY rowid DESC
|
||||
LIMIT 1",
|
||||
rusqlite::params![chat_id, local_id, msg_local_type_lo32, create_time],
|
||||
|row| row.get(0),
|
||||
)
|
||||
.ok();
|
||||
|
||||
let packed: Option<Vec<u8>> = packed_exact.or_else(|| conn
|
||||
.query_row(
|
||||
"SELECT packed_info FROM MessageResourceInfo
|
||||
WHERE chat_id = ?1
|
||||
|
|
@ -81,7 +98,7 @@ pub fn lookup_md5_blocking(
|
|||
rusqlite::params![chat_id, local_id, msg_local_type_lo32],
|
||||
|row| row.get(0),
|
||||
)
|
||||
.ok();
|
||||
.ok());
|
||||
|
||||
let Some(blob) = packed else {
|
||||
return Ok(None);
|
||||
|
|
@ -235,7 +252,13 @@ pub fn resolve_blocking(
|
|||
super::AttachmentKind::File => 49,
|
||||
};
|
||||
|
||||
let meta = lookup_md5_blocking(resource_db_path, &id.chat, id.local_id, lo32_type)?
|
||||
let meta = lookup_md5_blocking(
|
||||
resource_db_path,
|
||||
&id.chat,
|
||||
id.local_id,
|
||||
id.create_time,
|
||||
lo32_type,
|
||||
)?
|
||||
.ok_or_else(|| {
|
||||
anyhow!(
|
||||
"message_resource.db 中找不到 chat={} local_id={} type={} 的资源行（可能是非附件消息或资源库未同步）",
|
||||
|
|
@ -306,6 +329,69 @@ mod tests {
|
|||
assert!(extract_md5_from_packed_info(&blob).is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lookup_md5_prefers_exact_create_time_over_latest_reuse() {
|
||||
let dir = tempdir_for_test();
|
||||
let db_path = dir.join("message_resource.db");
|
||||
let conn = Connection::open(&db_path).unwrap();
|
||||
conn.execute(
|
||||
"CREATE TABLE ChatName2Id (user_name TEXT)",
|
||||
[],
|
||||
)
|
||||
.unwrap();
|
||||
conn.execute(
|
||||
"INSERT INTO ChatName2Id (rowid, user_name) VALUES (1, 'room@chatroom')",
|
||||
[],
|
||||
)
|
||||
.unwrap();
|
||||
conn.execute(
|
||||
"CREATE TABLE MessageResourceInfo (
|
||||
chat_id INTEGER,
|
||||
message_local_id INTEGER,
|
||||
message_local_type INTEGER,
|
||||
message_create_time INTEGER,
|
||||
packed_info BLOB
|
||||
)",
|
||||
[],
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let old_blob = {
|
||||
let mut blob = vec![0x12, 0x22, 0x0A, 0x20];
|
||||
blob.extend_from_slice(b"11111111111111111111111111111111");
|
||||
blob
|
||||
};
|
||||
let new_blob = {
|
||||
let mut blob = vec![0x12, 0x22, 0x0A, 0x20];
|
||||
blob.extend_from_slice(b"22222222222222222222222222222222");
|
||||
blob
|
||||
};
|
||||
|
||||
conn.execute(
|
||||
"INSERT INTO MessageResourceInfo
|
||||
(chat_id, message_local_id, message_local_type, message_create_time, packed_info)
|
||||
VALUES (?1, ?2, ?3, ?4, ?5)",
|
||||
rusqlite::params![1i64, 7i64, 3i64, 1000i64, old_blob],
|
||||
)
|
||||
.unwrap();
|
||||
conn.execute(
|
||||
"INSERT INTO MessageResourceInfo
|
||||
(chat_id, message_local_id, message_local_type, message_create_time, packed_info)
|
||||
VALUES (?1, ?2, ?3, ?4, ?5)",
|
||||
rusqlite::params![1i64, 7i64, 3i64, 2000i64, new_blob],
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let old = lookup_md5_blocking(&db_path, "room@chatroom", 7, 1000, 3)
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
let new = lookup_md5_blocking(&db_path, "room@chatroom", 7, 2000, 3)
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
assert_eq!(old.md5, "11111111111111111111111111111111");
|
||||
assert_eq!(new.md5, "22222222222222222222222222222222");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn three_month_candidates_includes_prev_curr_next() {
|
||||
// 2025-08-15 (mid-month) → 2025-07, 2025-08, 2025-09
|
||||
|
|
|
|||
|
|
@ -264,13 +264,13 @@ enum Commands {
|
|||
#[arg(long)]
|
||||
json: bool,
|
||||
},
|
||||
/// 列出某会话的附件（图片 / 视频 / 文件 / 语音），返回不透明 attachment_id
|
||||
/// 列出某会话的图片附件，返回不透明 attachment_id
|
||||
Attachments {
|
||||
/// 会话名称（联系人显示名 / wxid / @chatroom username 都可以）
|
||||
chat: String,
|
||||
/// 类型（多选，默认 image）。可选：image / voice / video / file
|
||||
/// 类型（当前仅支持 image）
|
||||
#[arg(long = "kind", value_name = "KIND",
|
||||
value_parser = ["image", "voice", "video", "file", "audio", "img"])]
|
||||
value_parser = ["image", "img"])]
|
||||
kinds: Vec<String>,
|
||||
/// 显示数量
|
||||
#[arg(short = 'n', long, default_value = "50")]
|
||||
|
|
|
|||
|
|
@ -3285,7 +3285,7 @@ pub async fn q_biz_articles(
|
|||
Ok(json!({ "count": results.len(), "articles": results }))
|
||||
}
|
||||
|
||||
// ─── 附件（图片 / 视频 / 文件 / 语音）查询与提取 ─────────────────────────────────
|
||||
// ─── 附件（当前先支持图片）查询与提取 ─────────────────────────────────
|
||||
//
|
||||
// 设计要点：
|
||||
// - `q_attachments` 只走 `Msg_<chat_md5>` 表，按 `local_type & 0xFFFFFFFF IN (...)` 过滤
|
||||
|
|
@ -3296,7 +3296,7 @@ pub async fn q_biz_articles(
|
|||
// - V2 image AES key 通过 `image_key::default_provider()` 拿（codex 后续填实现）。
|
||||
// 缺 key 时 V2 解码会返回明确错误，CLI 直接抛给用户。
|
||||
|
||||
/// 列出某会话内的附件消息（默认 image，可多选）。返回每条的 `attachment_id`，
|
||||
/// 列出某会话内的附件消息（当前仅 image）。返回每条的 `attachment_id`，
|
||||
/// 后续传给 `Extract` 才真正读 message_resource.db + 解密 .dat。
|
||||
pub async fn q_attachments(
|
||||
db: &DbCache,
|
||||
|
|
@ -3319,7 +3319,7 @@ pub async fn q_attachments(
|
|||
// 解析 kinds → 低 32 bit local_type 集合
|
||||
let kind_filters: Vec<(AttachmentKind, i64)> = parse_attachment_kinds(kinds.as_deref())?;
|
||||
if kind_filters.is_empty() {
|
||||
anyhow::bail!("kinds 为空 — 至少传一种 image/video/file/voice");
|
||||
anyhow::bail!("kinds 为空 — 当前至少传一种 image");
|
||||
}
|
||||
let lo32_types: Vec<i64> = kind_filters.iter().map(|(_, t)| *t).collect();
|
||||
// local_type → AttachmentKind 反查（mask 完后定 kind）
|
||||
|
|
@ -3569,7 +3569,7 @@ pub async fn q_extract(
|
|||
}
|
||||
|
||||
/// 解析 `kinds` 参数到 `(AttachmentKind, lo32_local_type)` 列表。
|
||||
/// 缺省（None / 空）按 image 处理。
|
||||
/// 当前只支持 image；命令名保留成 `attachments` 是为了后续扩到其他附件类型时不 break CLI。
|
||||
fn parse_attachment_kinds(
|
||||
kinds: Option<&[String]>,
|
||||
) -> Result<Vec<(crate::attachment::AttachmentKind, i64)>> {
|
||||
|
|
@ -3583,10 +3583,10 @@ fn parse_attachment_kinds(
|
|||
for k in raw {
|
||||
let (kind, t): (AttachmentKind, i64) = match k.to_ascii_lowercase().as_str() {
|
||||
"image" | "img" => (AttachmentKind::Image, 3),
|
||||
"voice" | "audio" => (AttachmentKind::Voice, 34),
|
||||
"video" => (AttachmentKind::Video, 43),
|
||||
"file" => (AttachmentKind::File, 49),
|
||||
other => anyhow::bail!("未知附件类型：{}（支持 image/voice/video/file）", other),
|
||||
"voice" | "audio" | "video" | "file" => {
|
||||
anyhow::bail!("当前只支持 image 提取；video/file/voice 的资源路径与 decoder 还没接通")
|
||||
}
|
||||
other => anyhow::bail!("未知附件类型：{}（当前仅支持 image）", other),
|
||||
};
|
||||
if seen.insert(kind.as_str()) {
|
||||
out.push((kind, t));
|
||||
|
|
|
|||
|
|
@ -131,11 +131,11 @@ pub enum Request {
|
|||
},
|
||||
/// 重新加载配置和密钥（init --force 后 daemon 不会自动重读）
|
||||
ReloadConfig,
|
||||
/// 列出某个会话里的附件（图片 / 视频 / 文件 / 语音）
|
||||
/// 列出某个会话里的图片附件
|
||||
/// 输出每条带 `attachment_id`（不透明 base64url 句柄），传给 `Extract` 时取回本体
|
||||
Attachments {
|
||||
chat: String,
|
||||
/// 类型过滤：image / video / file / voice，多选；缺省返回 image
|
||||
/// 类型过滤：当前仅支持 image
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
kinds: Option<Vec<String>>,
|
||||
#[serde(default = "default_limit_50")]
|
||||
|
|
|
|||
Loading…
Reference in New Issue