Merge pull request #342 from cockroacher/i331

pylint of issue #331

tests/w3c_base.py

@@ -14,6 +14,25 @@
 
 
 def get_errors(test_type, params):
+    """
+    This function takes a test type and parameters as input and
+    returns any errors found during the test.
+
+    The function checks if the test type is 'css' or 'html' and
+    sets the test arguments accordingly.
+    It then checks if a document URL is provided in the parameters.
+    If the URL does not start with 'https://' or 'http://', it raises a ValueError.
+    It then checks if the file is cached and if not, it caches the file.
+    It then runs a command using the vnu.jar validator and returns any errors found.
+
+    Parameters:
+    test_type (str): The type of the test to be run. It can be 'css' or 'html'.
+    params (dict): A dictionary containing the parameters for the test.
+    It should contain a 'doc' key with the URL of the document to be tested.
+
+    Returns:
+    list: A list of dictionaries where each dictionary represents an error message.
+    """
 
     url = ''
     arg = ''
@@ -31,20 +50,20 @@ def get_errors(test_type, params):
         url = params['doc']
 
         if 'https://' not in url and 'http://' not in url:
-            raise Exception(
-                'Tested url must start with \'https://\' or \'http://\': {0}'.format(url))
+            raise ValueError(
+                f'Tested url must start with \'https://\' or \'http://\': {url}')
 
         file_path = get_cache_path(url, True)
         if is_html:
             html_file_ending_fix = file_path.replace('.cache', '.cache.html')
-            if has_cache_file(url, True, CACHE_TIME_DELTA) and not os.path.exists(html_file_ending_fix):
+            if has_cache_file(url, True, CACHE_TIME_DELTA) \
+                    and not os.path.exists(html_file_ending_fix):
                 os.rename(file_path, html_file_ending_fix)
             file_path = html_file_ending_fix
 
-        arg = '--exit-zero-always{1} --stdout --format json --errors-only {0}'.format(
-            file_path, test_arg)
+        arg = f'--exit-zero-always{test_arg} --stdout --format json --errors-only {file_path}'
 
-    command = "java -jar vnu.jar {0}".format(arg)
+    command = f'java -jar vnu.jar {arg}'
     process = subprocess.Popen(command.split(), stdout=subprocess.PIPE)
     output, _ = process.communicate(timeout=REQUEST_TIMEOUT * 10)
 
@@ -55,14 +74,34 @@ def get_errors(test_type, params):
     return errors
 
 def identify_files(filename):
+    """
+    This function takes a filename as input and identifies different types of files in the HAR data.
+
+    The function reads the HAR data from the file, iterates over the entries,
+    and categorizes them into HTML and CSS files.
+    It also checks if the file is already cached and if not, it caches the file.
+
+    Parameters:
+    filename (str): The name of the file containing the HAR data.
+
+    Returns:
+    dict: A dictionary containing categorized file data.
+    The dictionary has four keys - 'htmls', 'elements', 'attributes', and 'resources'.
+    Each key maps to a list of dictionaries where each dictionary contains:
+    - 'url',
+    - 'content'
+    - 'index'
+    of the file.
+    """
+
     data = {
         'htmls': [],
         'elements': [],
         'attributes': [],
         'resources': []
     }
 
-    with open(filename) as json_input_file:
+    with open(filename, encoding='utf-8') as json_input_file:
         har_data = json.load(json_input_file)
 
         if 'log' in har_data: