add 接口测试 保存json 规范化文件名

TestAllOcr/config.py

@@ -0,0 +1,39 @@
+import base64
+import requests
+
+# 测试url
+test_url = 'http://aihub-test.digitalyili.com/aiSquare/openApi/reasoning-services/rlocrxm'
+sb_url = 'http://aihub.digitalyili.com/aiSquare/openApi/reasoning-services/rlocrxm'
+idc_url = 'http://aihubpre-idc.digitalyili.com/aiSquare/openApi/reasoning-services/hrocr'
+
+URL = {
+    'test': test_url,
+    'sb': sb_url,
+    'idc': idc_url
+}
+
+# 测试token
+test_header = {
+    'Content-Type': 'application/json',
+    'Authorization': 'Bearer 9679c2b3-b90b-4029-a3c7-f347b4d242f7'
+}
+sb_header = {
+    'Content-Type': 'application/json',
+    'Authorization': 'Bearer dcae8cc6-0e49-4db8-a2d2-94ef84da3636'
+}
+idc_header = {
+    'Content-Type': 'application/json',
+    'Authorization': 'Bearer 4e00c444-620b-4d3c-85f4-777e64276f0e'
+}
+
+TOKEN = {
+    'test': test_header,
+    'sb': sb_header,
+    'idc': idc_header
+}
+
+def send_request(image_path, suffix, URL, TOKEN):
+    with open(image_path, 'rb') as f:
+        img_str: str = base64.encodebytes(f.read()).decode('utf-8')
+        r = requests.post(f'{URL}{suffix}', json={'image': img_str, 'image_type': '0'}, headers=TOKEN)
+        return r.json()

TestAllOcr/image/bankcard.json

@@ -0,0 +1 @@
+"101"

TestAllOcr/image/cet.json

@@ -0,0 +1,9 @@
+{
+    "orientation": 0,
+    "name": "鉴康",
+    "id": "152801200003178527",
+    "language": "英语",
+    "level": "CET4",
+    "exam_time": "2021年6月",
+    "score": "451"
+}

TestAllOcr/image/idcard.json

@@ -0,0 +1 @@
+"101"

TestAllOcr/image/regbook.json

@@ -0,0 +1 @@
+"101"

TestAllOcr/image/schoolcert.json

@@ -0,0 +1 @@
+"101"

TestAllOcr/test_interface.py

@@ -0,0 +1,44 @@
+import base64
+from pathlib import Path
+import unittest
+import config
+from config import send_request
+
+image_path = 'image'
+
+# test, sb ,idc
+url = config.URL['idc']
+token = config.TOKEN['idc']
+
+class TestOcr(unittest.TestCase):
+
+    def _helper(self, image_path, suffix):
+        root = Path(__file__).parent
+        image_path = str(root / image_path)
+        r = send_request(image_path, suffix, url, token)
+        self.assertIn('result', r, f'{suffix} test error')
+
+    def test_bank(self):
+        image_path = './image/bankcard.jpg'
+        suffix = '/yhksb/bankcard'
+        self._helper(image_path, suffix)
+
+    def test_idcard(self):
+        image_path = './image/idcard.jpg'
+        suffix = '/sfzsb/idcard'
+        self._helper(image_path, suffix)
+
+    def test_regbook(self):
+        image_path = './image/regbook.jpg'
+        suffix = '/hkbsb/regbook'
+        self._helper(image_path, suffix)
+
+    def test_schoolcert(self):
+        image_path = './image/schoolcert.jpg'
+        suffix = '/xxw/schoolcert'
+        self._helper(image_path, suffix)
+
+    def test_cet(self):
+        image_path = './image/cet.jpg'
+        suffix = '/cet/cet'
+        self._helper(image_path, suffix)

convert_json.py

@@ -0,0 +1,54 @@
+from pathlib import Path
+
+import requests
+import json
+import base64
+from itertools import chain
+
+url = 'http://192.168.199.27:18040'
+imgs_path = '户口本/首页'
+
+def send_request(img_path, image_type = 1):
+    with open(img_path, 'rb') as f:
+        img_str: str = base64.encodebytes(f.read()).decode('utf-8')
+        data = {
+            'image': img_str,
+            'image_type': image_type
+        }
+        # idc_header = {
+        #     'Content-Type': 'application/json',
+        #     'Authorization': 'Bearer 4e00c444-620b-4d3c-85f4-777e64276f0e'
+        # }
+        r = requests.post(f'{url}/ocr_system/regbook', json=data)
+        print(r.json())
+        return r.json()
+
+
+def _parse_result(r):
+    if r['status'] == '000':
+        r = r['result']
+        if r:
+            del r['confidence']
+        return {k: v['text'] if isinstance(v, dict) else v for k, v in r.items()}
+    elif r['status'] == '101':
+        return "101"
+
+
+if __name__ == '__main__':
+
+    # 0
+    root = Path(__file__).parent
+    print(root)
+    # img_paths = chain(*[Path(root / imgs_path).rglob(f'*.{ext}') for ext in ['jpeg', 'jpg', 'png', 'JPG', 'PNG']])
+    img_paths = chain(*[Path(root / imgs_path).rglob(f'*.{ext}') for ext in ['jpg']])
+    for img_path in img_paths:
+        print(img_path)
+        r = send_request(img_path)
+        res = _parse_result(r)
+        print(res)
+        img_path: Path = img_path
+        d = img_path.parent
+        fn = f'{img_path.stem}.json'
+
+        with (d / fn).open('w', encoding='utf-8') as f:
+            json.dump(res, f, ensure_ascii=False, indent=4)

example/08-23_CET-tem_R.md

@@ -1,35 +0,0 @@
-
-
-
-
-# 08-23_CET-tem_R.md测试报告
-
-
-92.86%
-|字段|正确率|
-| :---: | :---: |
-|orientation|100.00%|
-|name|50.00%|
-|id|100.00%|
-|language|100.00%|
-|level|100.00%|
-|exam_time|100.00%|
-|score|100.00%|
-
-# True
-
-|图片|识别结果|
-| :---: | :---: |
-|![](img/20.jpg)|{'orientation': 0, 'name': '于海龙', 'id': '150424199401132415', 'language': '英语', 'level': 'CET4', 'exam_time': '2013年6月', 'score': '438'}|
-|![](.ro_dst/20-1.jpg)|{'orientation': 1, 'name': '于海龙', 'id': '150424199401132415', 'language': '英语', 'level': 'CET4', 'exam_time': '2013年6月', 'score': '438'}|
-|![](.ro_dst/20-2.jpg)|{'orientation': 2, 'name': '于海龙', 'id': '150424199401132415', 'language': '英语', 'level': 'CET4', 'exam_time': '2013年6月', 'score': '438'}|
-|![](.ro_dst/20-3.jpg)|{'orientation': 3, 'name': '于海龙', 'id': '150424199401132415', 'language': '英语', 'level': 'CET4', 'exam_time': '2013年6月', 'score': '438'}|
-
-# False
-
-|图片|识别结果|
-| :---: | :---: |
-|![](img/25_img.jpg)|正确:徐潇然<br>返回:徐然<br>|
-|![](.ro_dst/25_img-1.jpg)|正确:徐潇然<br>返回:徐然<br>|
-|![](.ro_dst/25_img-2.jpg)|正确:徐潇然<br>返回:徐然<br>|
-|![](.ro_dst/25_img-3.jpg)|正确:徐潇然<br>返回:徐然<br>|

example/img/20.json

@@ -1,9 +0,0 @@
-{
-    "orientation": 0,
-    "name": "于海龙",
-    "id": "150424199401132415",
-    "language": "英语",
-    "level": "CET4",
-    "exam_time": "2013年6月",
-    "score": "438"
-}

example/img/25_img.json

@@ -1,9 +0,0 @@
-{
-    "orientation": 0,
-    "name": "徐潇然",
-    "id": "210404199610292117",
-    "language": "英语",
-    "level": "CET6",
-    "exam_time": "2018年06月",
-    "score": "435"
-}

ocr_config.py

@@ -20,7 +20,7 @@ class Configs:
 
 
 # cet
-cet_local_config = RequestConfig(url='http://192.168.199.249:18050/ocr_system/cet', token='')
+cet_local_config = RequestConfig(url='http://192.168.199.27:18050/ocr_system/cet', token='')
 cet_test_config = RequestConfig(
     url='http://aihub-test.digitalyili.com/aiSquare/openApi/reasoning-services/rlocrxm/cettest/cet',
     token='9679c2b3-b90b-4029-a3c7-f347b4d242f7')
@@ -35,7 +35,7 @@ CET_CONFIGS = {
 }
 
 # regbook
-regbook_local_config = RequestConfig(url='http://192.168.199.249:18040/ocr_system/regbook', token='')
+regbook_local_config = RequestConfig(url='http://192.168.199.27:18040/ocr_system/regbook', token='')
 regbook_test_config = RequestConfig(
     url='http://aihub-test.digitalyili.com/aiSquare/openApi/reasoning-services/rlocrxm/hkbsb/regbook',
     token='9679c2b3-b90b-4029-a3c7-f347b4d242f7')

suffix.py

@@ -0,0 +1,27 @@
+import os
+from pathlib import Path
+from itertools import chain
+import sys
+
+# conf
+target_path = '户口本'
+#suffix = sys.argv[2]
+suffix = 'jpg' if len(sys.argv) != 3 else sys.argv[2]
+
+def get_range(n):
+    len_n = len(str(n))
+    for num in range(1, n + 1):
+        output = str(num)
+        while len(output) < len_n:
+            output = f'0{output}'
+        yield output
+
+
+file_paths = list(chain(*[Path(target_path).rglob(f'*.{ext}') for ext in ['jpeg', 'jpg', 'png', 'JPG', 'PNG']]))
+num = len(file_paths)
+file_name_list = list(get_range(num))
+for i in range(num):
+    file = file_paths[i]
+    print(file)
+    new = file.parent / f'{file_name_list[i]}_img.{suffix}'
+    file.rename(new)

use.py

@@ -5,14 +5,14 @@ from new import MD, Image, Dataset, parser_path
 
 # config
 # 图片路径
-image_path = Path('/Users/zeke/Downloads/9.1/专四/img')
-image_type = 0
+image_path = Path('/Users/sxkj/Desktop/测试文档/四六级/9.8/身份证/img')
+image_type = 1
 # 是否旋转
-image_rotate = False
+image_rotate = True
 ocr_address = 'local'  # 'local' 'test' 'sb'
-ocr_name = 'cet'  # 'cet' 'idcard' 'bankcard' 'regbook' 'schoolcert'
-md_name = 'CET'
-filed = 'cet'
+ocr_name = 'regbook'  # 'cet' 'idcard' 'bankcard' 'regbook' 'schoolcert'
+md_name = 'RegBook'
+filed = 'regbook'
 # 若md_path为None 则默认使用图片父路径为markdown保存路径
 # md_path = '/Users/zeke/work/sx/OCR/HROCR/to_md/example' or image_path.parent
 md_path = None or image_path.parent