Initial upload for secondary development

chatlog_fastAPI/services/media_resolver.py

@@ -0,0 +1,174 @@
+from __future__ import annotations
+
+import logging
+import sqlite3
+from dataclasses import dataclass
+from pathlib import Path
+
+import httpx
+from fastapi import HTTPException
+
+from config import settings
+from services.chatlog_context import get_chatlog_context
+
+log = logging.getLogger(__name__)
+
+
+@dataclass
+class ResolvedMedia:
+    bytes: bytes
+    content_type: str
+    url: str
+
+
+def _media_url(kind: str, key: str, thumb: bool = False) -> str:
+    url = f"{settings.chatlog_base_url}/{kind}/{key}"
+    if thumb:
+        url += "?thumb=1"
+    return url
+
+
+def _read_voice_resource_status(key: str) -> dict:
+    ctx = get_chatlog_context()
+    work_dir = ctx.get("work_dir") or ""
+    if not work_dir:
+        return {"checked": False, "reason": "missing_work_dir"}
+
+    db_path = Path(work_dir) / "db_storage" / "message" / "message_resource.db"
+    if not db_path.exists():
+        return {"checked": False, "reason": "message_resource_db_missing", "path": str(db_path)}
+
+    try:
+        conn = sqlite3.connect(f"file:{db_path.as_posix()}?mode=ro", uri=True)
+        conn.row_factory = sqlite3.Row
+        try:
+            info = conn.execute(
+                "SELECT * FROM MessageResourceInfo WHERE message_svr_id=?",
+                (int(key),),
+            ).fetchone()
+            if not info:
+                return {
+                    "checked": True,
+                    "found": False,
+                    "path": str(db_path),
+                    "message": "当前已解密资源库里没有这条语音的媒体资源记录",
+                }
+            details = conn.execute(
+                "SELECT type,size,status,data_index FROM MessageResourceDetail WHERE message_id=?",
+                (info["message_id"],),
+            ).fetchall()
+            return {
+                "checked": True,
+                "found": True,
+                "path": str(db_path),
+                "message_id": info["message_id"],
+                "resources": [dict(row) for row in details],
+            }
+        finally:
+            conn.close()
+    except Exception as exc:
+        return {"checked": False, "reason": "resource_db_read_failed", "error": str(exc), "path": str(db_path)}
+
+
+def _download_failure_message(kind: str, key: str, status_code: int | None, body: str = "") -> str:
+    if kind == "voice":
+        base = "底层语音文件未读取成功"
+        if status_code:
+            base += f"（chatlog /voice 返回 HTTP {status_code}）"
+        return (
+            f"{base}。请先确认已安装新版程序并重新识别当前微信账号；"
+            "如果仍失败，说明当前 chatlog 版本还不能解析该 WeChat 4.x 语音资源。"
+        )
+    if status_code:
+        return f"从 chatlog 下载媒体失败: HTTP {status_code}"
+    return f"从 chatlog 下载媒体失败: {body or 'unknown error'}"
+
+
+async def diagnose_media(kind: str, key: str) -> dict:
+    if kind not in {"voice", "image", "video"}:
+        raise HTTPException(400, "不支持的媒体类型")
+    if not key:
+        raise HTTPException(400, "媒体 key 不能为空")
+
+    url = _media_url(kind, key, thumb=kind in {"image", "video"})
+    result = {
+        "ok": False,
+        "kind": kind,
+        "key": key,
+        "url": url,
+        "chatlog_base_url": settings.chatlog_base_url,
+        "chatlog_context": get_chatlog_context(),
+    }
+
+    async with httpx.AsyncClient(timeout=20, trust_env=False, follow_redirects=True) as client:
+        try:
+            resp = await client.get(url)
+            content_type = resp.headers.get("content-type", "")
+            result.update(
+                {
+                    "status_code": resp.status_code,
+                    "content_type": content_type,
+                    "content_length": len(resp.content or b""),
+                    "ok": resp.status_code < 400 and bool(resp.content),
+                }
+            )
+            if resp.status_code >= 400:
+                result["error"] = _download_failure_message(kind, key, resp.status_code, resp.text[:500])
+                result["response_preview"] = resp.text[:500]
+            elif not resp.content:
+                result["error"] = "chatlog 返回了空媒体文件"
+        except Exception as exc:
+            result.update({"error": f"无法连接 chatlog 媒体接口: {exc}", "exception": str(exc)})
+
+    if kind == "voice":
+        result["resource_db"] = _read_voice_resource_status(key)
+    return result
+
+
+async def resolve_media(kind: str, key: str) -> ResolvedMedia:
+    if kind not in {"voice", "image", "video"}:
+        raise HTTPException(400, "不支持的媒体类型")
+    if not key:
+        raise HTTPException(400, "媒体 key 不能为空")
+
+    url = _media_url(kind, key, thumb=kind in {"image", "video"})
+    async with httpx.AsyncClient(timeout=60, trust_env=False, follow_redirects=True) as client:
+        try:
+            resp = await client.get(url)
+            resp.raise_for_status()
+        except httpx.HTTPStatusError as exc:
+            diagnostics = await diagnose_media(kind, key)
+            log.warning("[media_resolver] media download failed: %s", diagnostics)
+            raise HTTPException(
+                502,
+                {
+                    "message": _download_failure_message(kind, key, exc.response.status_code, exc.response.text[:500]),
+                    "diagnostics": diagnostics,
+                },
+            )
+        except Exception as exc:
+            diagnostics = await diagnose_media(kind, key)
+            log.warning("[media_resolver] media download exception: %s", diagnostics)
+            raise HTTPException(
+                502,
+                {
+                    "message": _download_failure_message(kind, key, None, str(exc)),
+                    "diagnostics": diagnostics,
+                },
+            )
+
+    if not resp.content:
+        diagnostics = await diagnose_media(kind, key)
+        raise HTTPException(
+            502,
+            {
+                "message": "chatlog 返回了空媒体文件",
+                "diagnostics": diagnostics,
+            },
+        )
+
+    return ResolvedMedia(
+        bytes=resp.content,
+        content_type=resp.headers.get("content-type", "application/octet-stream"),
+        url=url,
+    )