add encoding for open (#10769)

ppocr/data/imaug/label_ops.py

@@ -118,7 +118,7 @@ class BaseRecLabelEncode(object):
             self.lower = True
         else:
             self.character_str = []
-            with open(character_dict_path, "rb") as fin:
+            with open(character_dict_path, "rb", encoding="utf-8") as fin:
                 lines = fin.readlines()
                 for line in lines:
                     line = line.decode('utf-8').strip("\n").strip("\r\n")
@@ -278,7 +278,7 @@ class KieLabelEncode(object):
                 char = line.strip()
                 self.dict[char] = idx
                 idx += 1
-        with open(class_path, "r") as fin:
+        with open(class_path, "r", encoding="utf-8") as fin:
             lines = fin.readlines()
             for idx, line in enumerate(lines):
                 line = line.strip("\n")
@@ -640,7 +640,7 @@ class TableLabelEncode(AttnLabelEncode):
         self.replace_empty_cell_token = replace_empty_cell_token
 
         dict_character = []
-        with open(character_dict_path, "rb") as fin:
+        with open(character_dict_path, "rb", encoding="utf-8") as fin:
             lines = fin.readlines()
             for line in lines:
                 line = line.decode('utf-8').strip("\n").strip("\r\n")
@@ -1380,7 +1380,7 @@ class SRLabelEncode(BaseRecLabelEncode):
         super(SRLabelEncode, self).__init__(max_text_length,
                                             character_dict_path, use_space_char)
         self.dic = {}
-        with open(character_dict_path, 'r') as fin:
+        with open(character_dict_path, 'r', encoding="utf-8") as fin:
             for line in fin.readlines():
                 line = line.strip()
                 character, sequence = line.split()

ppocr/data/pubtab_dataset.py

@@ -59,7 +59,7 @@ class PubTabDataSet(Dataset):
             file_list = [file_list]
         data_lines = []
         for idx, file in enumerate(file_list):
-            with open(file, "rb") as f:
+            with open(file, "rb", encoding="utf-8") as f:
                 lines = f.readlines()
                 if self.mode == "train" or ratio_list[idx] < 1.0:
                     random.seed(self.seed)
@@ -112,7 +112,7 @@ class PubTabDataSet(Dataset):
                 'file_name': file_name
             }
 
-            with open(data['img_path'], 'rb') as f:
+            with open(data['img_path'], 'rb', encoding="utf-8") as f:
                 img = f.read()
                 data['image'] = img
             outs = transform(data, self.ops)

ppocr/data/simple_dataset.py

@@ -74,7 +74,7 @@ class SimpleDataSet(Dataset):
             file_list = [file_list]
         data_lines = []
         for idx, file in enumerate(file_list):
-            with open(file, "rb") as f:
+            with open(file, "rb", encoding="utf-8") as f:
                 lines = f.readlines()
                 if self.mode == "train" or ratio_list[idx] < 1.0:
                     random.seed(self.seed)
@@ -120,7 +120,7 @@ class SimpleDataSet(Dataset):
             data = {'img_path': img_path, 'label': label}
             if not os.path.exists(img_path):
                 continue
-            with open(data['img_path'], 'rb') as f:
+            with open(data['img_path'], 'rb', encoding="utf-8") as f:
                 img = f.read()
                 data['image'] = img
             data = transform(data, load_data_ops)
@@ -146,7 +146,7 @@ class SimpleDataSet(Dataset):
             data = {'img_path': img_path, 'label': label}
             if not os.path.exists(img_path):
                 raise Exception("{} does not exist!".format(img_path))
-            with open(data['img_path'], 'rb') as f:
+            with open(data['img_path'], 'rb', encoding="utf-8") as f:
                 img = f.read()
                 data['image'] = img
             data['ext_data'] = self.get_ext_data()
@@ -240,7 +240,7 @@ class MultiScaleDataSet(SimpleDataSet):
             data = {'img_path': img_path, 'label': label}
             if not os.path.exists(img_path):
                 raise Exception("{} does not exist!".format(img_path))
-            with open(data['img_path'], 'rb') as f:
+            with open(data['img_path'], 'rb', encoding="utf-8") as f:
                 img = f.read()
                 data['image'] = img
             data['ext_data'] = self.get_ext_data()

ppocr/postprocess/rec_postprocess.py

@@ -31,7 +31,7 @@ class BaseRecLabelDecode(object):
             self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
             dict_character = list(self.character_str)
         else:
-            with open(character_dict_path, "rb") as fin:
+            with open(character_dict_path, "rb", encoding="utf-8") as fin:
                 lines = fin.readlines()
                 for line in lines:
                     line = line.decode('utf-8').strip("\n").strip("\r\n")

ppocr/postprocess/table_postprocess.py

@@ -26,7 +26,7 @@ class TableLabelDecode(AttnLabelDecode):
                  merge_no_span_structure=False,
                  **kwargs):
         dict_character = []
-        with open(character_dict_path, "rb") as fin:
+        with open(character_dict_path, "rb", encoding="utf-8") as fin:
             lines = fin.readlines()
             for line in lines:
                 line = line.decode('utf-8').strip("\n").strip("\r\n")