Add Cloud Tour Libo knowledge graph platform

app/api/ocr.py

@@ -0,0 +1,57 @@
+"""OCR 相关接口——目前供旅行社"名单"模块识别护照使用。"""
+from __future__ import annotations
+
+from typing import Any
+
+from fastapi import APIRouter, File, Form, HTTPException, UploadFile
+
+from app.aliyun_ocr import OcrCallError, OcrConfigError, recognize_passport
+
+router = APIRouter()
+
+MAX_IMAGE_BYTES = 10 * 1024 * 1024  # 阿里云接口单图上限按 10MB 兜底
+
+
+@router.post("/ocr/passport")
+async def ocr_passport(
+    file: UploadFile | None = File(default=None),
+    url: str | None = Form(default=None),
+) -> dict[str, Any]:
+    """护照识别。任选其一：
+    - multipart 上传 `file`（图片二进制）
+    - 表单字段 `url`（图片可公网访问的 URL，如阿里云 OSS）
+
+    成功返回 OCR 解析后的字段 dict，失败按错误类型映射到不同 HTTP 状态：
+    - 400：参数缺失/图片过大
+    - 503：AK/SK 未配置（运维介入）
+    - 502：阿里云返回错误或网络故障
+    """
+    if file is None and not (url and url.strip()):
+        raise HTTPException(status_code=400, detail="请上传图片文件或提供图片 URL")
+
+    image_bytes: bytes | None = None
+    if file is not None:
+        image_bytes = await file.read()
+        if not image_bytes:
+            raise HTTPException(status_code=400, detail="上传的图片为空")
+        if len(image_bytes) > MAX_IMAGE_BYTES:
+            raise HTTPException(
+                status_code=400,
+                detail=f"图片过大（{len(image_bytes)} 字节），请压缩到 10MB 以内",
+            )
+
+    try:
+        data = recognize_passport(
+            image_bytes=image_bytes,
+            image_url=url.strip() if url else None,
+        )
+    except OcrConfigError as exc:
+        raise HTTPException(status_code=503, detail=str(exc)) from exc
+    except OcrCallError as exc:
+        raise HTTPException(status_code=502, detail=str(exc)) from exc
+
+    return {
+        "ok": True,
+        "filename": file.filename if file else None,
+        "data": data,
+    }