[CodeStyle] use built-in `open` instead of `io.open` (#46751)

* [CodeStyle] use built-in `open` instead of `io.open`

* revert flake8 config changes

python/paddle/fluid/tests/unittests/tokenizer/tokenizer_utils.py

@@ -15,7 +15,6 @@
 # limitations under the License.
 
 import copy
-import io
 import json
 import os
 import unicodedata
@@ -464,7 +463,7 @@ class PretrainedTokenizer(object):
         tokenizer_config_file = resolved_vocab_files.pop(
             "tokenizer_config_file", None)
         if tokenizer_config_file is not None:
-            with io.open(tokenizer_config_file, encoding="utf-8") as f:
+            with open(tokenizer_config_file, 'r', encoding="utf-8") as f:
                 init_kwargs = json.load(f)
         else:
             init_kwargs = init_configuration
@@ -527,7 +526,7 @@ class PretrainedTokenizer(object):
                                              self.tokenizer_config_file)
         # init_config is set in metaclass created `__init__`,
         tokenizer_config = self.init_config
-        with io.open(tokenizer_config_file, "w", encoding="utf-8") as f:
+        with open(tokenizer_config_file, "w", encoding="utf-8") as f:
             f.write(json.dumps(tokenizer_config, ensure_ascii=False))
 
         self.save_resources(save_directory)
@@ -571,7 +570,7 @@ class PretrainedTokenizer(object):
             Vocab: An instance of `Vocab`.
         """
         token_to_idx = {}
-        with io.open(filepath, 'r', encoding='utf-8') as f:
+        with open(filepath, 'r', encoding='utf-8') as f:
             for index, line in enumerate(f):
                 token = line.rstrip('\n')
                 token_to_idx[token] = int(index)

tools/codestyle/copyright.hook

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 import argparse
-import io
 import re
 import sys
 import os
@@ -67,7 +66,7 @@ RE_SHEBANG = re.compile(r"^[ \t\v]*#[ \t]?\!")
 def _check_copyright(path):
     head=[]
     try:
-        with open(path) as f:
+        with open(path, 'r', encoding='utf-8') as f:
             head = [next(f) for x in range(4)]
     except StopIteration:
         pass
@@ -79,7 +78,7 @@ def _check_copyright(path):
     return False
 
 def generate_copyright(path, comment_mark):
-    original_contents = io.open(path, encoding="utf-8").readlines()
+    original_contents = open(path, 'r', encoding="utf-8").readlines()
     head = original_contents[0:4]
 
     insert_line_no=0
@@ -102,7 +101,7 @@ def generate_copyright(path, comment_mark):
         new_contents.extend(original_contents[insert_line_no:])
     new_contents="".join(new_contents)
 
-    with io.open(path, 'w') as output_file:
+    with open(path, 'w', encoding='utf-8') as output_file:
         output_file.write(new_contents)
 
 

tools/prune_for_jetson.py

@@ -20,7 +20,6 @@ import os
 import sys
 import re
 import glob
-import io
 
 
 def find_type_files(cur_dir, file_type, file_list=[]):
@@ -77,7 +76,7 @@ def prune_phi_kernels():
 
         op_name = os.path.split(op_file)[1]
         all_matches = []
-        with io.open(op_file, 'r', encoding='utf-8') as f:
+        with open(op_file, 'r', encoding='utf-8') as f:
             content = ''.join(f.readlines())
             op_pattern = 'PD_REGISTER_KERNEL\(.*?\).*?\{.*?\}'
             op, op_count = find_kernel(content, op_pattern)
@@ -87,7 +86,7 @@ def prune_phi_kernels():
         for p in all_matches:
             content = content.replace(p, '')
 
-        with io.open(op_file, 'w', encoding='utf-8') as f:
+        with open(op_file, 'w', encoding='utf-8') as f:
             f.write(u'{}'.format(content))
 
     print('We erase all grad op and kernel for Paddle-Inference lib.')
@@ -115,7 +114,7 @@ def append_fluid_kernels():
     for op in op_white_list:
         append_str = append_str + "file(APPEND ${pybind_file} \"USE_OP__(%s);\\n\")\n" % op
 
-    with io.open(file_name, 'r', encoding='utf-8') as f:
+    with open(file_name, 'r', encoding='utf-8') as f:
         content = ''.join(f.readlines())
 
     location_str = "nv_library(\n  tensorrt_op_teller\n  SRCS op_teller.cc\n  DEPS framework_proto device_context)"
@@ -126,7 +125,7 @@ def append_fluid_kernels():
               (location_str, file_name))
         return False
 
-    with io.open(file_name, 'w', encoding='utf-8') as f:
+    with open(file_name, 'w', encoding='utf-8') as f:
         f.write(u'{}'.format(new_content))
 
     #2. add op and kernel register
@@ -140,7 +139,7 @@ def append_fluid_kernels():
                         recursive=True)
 
     for op_file in all_op:
-        with io.open(op_file, 'r', encoding='utf-8') as f:
+        with open(op_file, 'r', encoding='utf-8') as f:
             content = ''.join(f.readlines())
 
         for op in op_white_list:
@@ -156,7 +155,7 @@ def append_fluid_kernels():
                 if len(matches) > 0:
                     content = content.replace(matches[0],
                                               matches[0].replace(k, k + "__"))
-                    with io.open(op_file, 'w', encoding='utf-8') as f:
+                    with open(op_file, 'w', encoding='utf-8') as f:
                         f.write(u'{}'.format(content))
 
     return True

tools/remove_grad_op_and_kernel.py

@@ -20,7 +20,6 @@ import os
 import sys
 import re
 import glob
-import io
 
 
 def find_type_files(cur_dir, file_type, file_list=[]):
@@ -120,7 +119,7 @@ if __name__ == '__main__':
             custom_pattern2 = custom_pattern2[:-1]
 
         all_matches = []
-        with io.open(op_file, 'r', encoding='utf-8') as f:
+        with open(op_file, 'r', encoding='utf-8') as f:
             content = ''.join(f.readlines())
 
             op, op_count = remove_grad_op_and_kernel(content, op_pattern1,
@@ -153,7 +152,7 @@ if __name__ == '__main__':
         for i in all_matches:
             content = content.replace(i, '')
 
-        with io.open(op_file, 'w', encoding='utf-8') as f:
+        with open(op_file, 'w', encoding='utf-8') as f:
             f.write(u'{}'.format(content))
 
     # 2. update operators/CMakeLists.txt