zzhyyyyy
45 lines
1.5 KiB
Python
45 lines
1.5 KiB
Python
"""POST /api/v1/parse-ocr —— OCR 文本识别接口(占坑期 mock 实现)。
|
|
|
|
application/json:
|
|
{"ocr_text": "...", "clusters": [{"id":"<uuid|long-str>","title":"..."}, ...]}
|
|
|
|
客户端在本地 OCR(或截图)后把整段文本发来,后端从文本里抠出
|
|
title/price/source_app + 归簇 + 估常见价。占坑期接 mock_extractor;
|
|
接真模型时改这里调真实 extractor_ocr。
|
|
|
|
注:此前 main.py 引用了本 router 但文件缺失,会在启动时 ImportError —— 本文件补齐。
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
|
|
from fastapi import APIRouter, HTTPException
|
|
|
|
from app.mock_extractor import mock_extract_ocr
|
|
from app.schemas import ParseOcrRequest, ParseStrResponse
|
|
|
|
logger = logging.getLogger("app.parse_ocr")
|
|
|
|
router = APIRouter(prefix="/api/v1")
|
|
|
|
|
|
@router.post("/parse-ocr", response_model=ParseStrResponse)
|
|
async def parse_ocr(req: ParseOcrRequest) -> ParseStrResponse:
|
|
text = req.ocr_text.strip()
|
|
if not text:
|
|
raise HTTPException(status_code=422, detail="empty_ocr_text")
|
|
|
|
logger.info("parse_ocr request chars=%d clusters=%d", len(text), len(req.clusters))
|
|
|
|
result = await mock_extract_ocr(text, req.clusters)
|
|
if not result.get("success"):
|
|
raise HTTPException(status_code=422, detail=result.get("reason", "extract_failed"))
|
|
|
|
return ParseStrResponse(
|
|
title=result["title"],
|
|
price=result["price"],
|
|
source_app=result["source_app"],
|
|
cluster_id=result.get("cluster_id"),
|
|
typical_price=result["typical_price"],
|
|
)
|