From 9c41fab95c37b4bcedef7e1f80b0ceffe9f89f98 Mon Sep 17 00:00:00 2001
From: liuyebo <1515783401@qq.com>
Date: Thu, 17 Oct 2024 12:58:23 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BC=98=E5=8C=96=E5=90=ABpdf=E6=97=B6?=
 =?UTF-8?q?=E5=87=BA=E9=99=A2=E8=AE=B0=E5=BD=95=E7=9A=84=E5=A4=84=E7=90=86?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 photo_review/auto_photo_review.py | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/photo_review/auto_photo_review.py b/photo_review/auto_photo_review.py
index 4ed9d17..b357f0d 100644
--- a/photo_review/auto_photo_review.py
+++ b/photo_review/auto_photo_review.py
@@ -473,6 +473,7 @@ def photo_review(pk_phhd, name):
     better_settlement_path = None
     better_cost_path = None
     settlement_text = ''
+    qrcode_img_id = None
     for phrec in phrecs:
         original_img_path = common_util.get_img_path(phrec.cfjaddress)
         if not original_img_path:
@@ -486,31 +487,29 @@ def photo_review(pk_phhd, name):
         better_settlement_path, settlement_text, better_cost_path = parse_qrcode(img_path, phrec.cfjaddress)
         if better_settlement_path:
             has_pdf = True
+            qrcode_img_id = phrec.cfjaddress
             break
 
     discharge_text = ''
     if has_pdf:
         settlement_result, discharge_result, cost_result = parse_pdf_text(settlement_text)
-        discharge_result = defaultdict(list, discharge_result)
+        discharge_ie_result = defaultdict(list)
 
-        is_settlement_updated = False
         is_cost_updated = False
         for phrec in phrecs:
             if phrec.cRectype == '1':
-                if not is_settlement_updated:
+                if phrec.cfjaddress == qrcode_img_id:
                     try:
                         ufile.copy_file(BUCKET, phrec.cfjaddress, "drg2015", phrec.cfjaddress)
                         ufile.upload_file(phrec.cfjaddress, better_settlement_path)
                     except Exception as e:
                         logging.error("更新结算单pdf图片出错", exc_info=e)
-                    finally:
-                        is_settlement_updated = True
             elif phrec.cRectype == '3':
                 rec_type, ie_result, ocr_text = information_extraction(phrec, pk_phhd)
                 if rec_type == '出院记录':
                     discharge_text += ocr_text
                     for key, value in ie_result.items():
-                        discharge_result[key].append(value)
+                        discharge_ie_result[key].append(value)
             elif phrec.cRectype == '4':
                 if not is_cost_updated:
                     try:
@@ -520,6 +519,14 @@ def photo_review(pk_phhd, name):
                         logging.error("更新费用清单pdf图片出错", exc_info=e)
                     finally:
                         is_cost_updated = True
+
+        # 合并出院记录
+        for key, value in discharge_ie_result.items():
+            ie_value = get_best_value_of_key(discharge_ie_result, key)
+            pdf_value = discharge_result.get(key)[0][0]['text']
+            similarity_ratio = fuzz.ratio(ie_value, pdf_value)
+            if similarity_ratio < 60:
+                discharge_result[key] = [[{'text': ie_value, 'probability': 1}]]
     else:
         for phrec in phrecs:
             rec_type, ie_result, ocr_text = information_extraction(phrec, pk_phhd)