Fixes for common json errors, cleanup json_parser file.

scripts/json_utils.py

@@ -0,0 +1,127 @@
+import re
+import json
+from config import Config
+
+cfg = Config()
+
+
+def extract_char_position(error_message: str) -> int:
+    """Extract the character position from the JSONDecodeError message.
+
+    Args:
+        error_message (str): The error message from the JSONDecodeError
+          exception.
+
+    Returns:
+        int: The character position.
+    """
+    import re
+
+    char_pattern = re.compile(r'\(char (\d+)\)')
+    if match := char_pattern.search(error_message):
+        return int(match[1])
+    else:
+        raise ValueError("Character position not found in the error message.")
+
+
+def add_quotes_to_property_names(json_string: str) -> str:
+    """
+    Add quotes to property names in a JSON string.
+
+    Args:
+        json_string (str): The JSON string.
+
+    Returns:
+        str: The JSON string with quotes added to property names.
+    """
+
+    def replace_func(match):
+        return f'"{match.group(1)}":'
+
+    property_name_pattern = re.compile(r'(\w+):')
+    corrected_json_string = property_name_pattern.sub(
+        replace_func,
+        json_string)
+
+    try:
+        json.loads(corrected_json_string)
+        return corrected_json_string
+    except json.JSONDecodeError as e:
+        raise e
+
+
+def balance_braces(json_string: str) -> str:
+    """
+    Balance the braces in a JSON string.
+
+    Args:
+        json_string (str): The JSON string.
+
+    Returns:
+        str: The JSON string with braces balanced.
+    """
+
+    open_braces_count = json_string.count('{')
+    close_braces_count = json_string.count('}')
+
+    while open_braces_count > close_braces_count:
+        json_string += '}'
+        close_braces_count += 1
+
+    while close_braces_count > open_braces_count:
+        json_string = json_string.rstrip('}')
+        close_braces_count -= 1
+
+    try:
+        json.loads(json_string)
+        return json_string
+    except json.JSONDecodeError as e:
+        raise e
+
+
+def fix_invalid_escape(json_str: str, error_message: str) -> str:
+    while error_message.startswith('Invalid \\escape'):
+        bad_escape_location = extract_char_position(error_message)
+        json_str = json_str[:bad_escape_location] + \
+            json_str[bad_escape_location + 1:]
+        try:
+            json.loads(json_str)
+            return json_str
+        except json.JSONDecodeError as e:
+            if cfg.debug:
+                print('json loads error - fix invalid escape', e)
+            error_message = str(e)
+    return json_str
+
+
+def correct_json(json_str: str) -> str:
+    """
+    Correct common JSON errors.
+
+    Args:
+        json_str (str): The JSON string.
+    """
+
+    try:
+        if cfg.debug:
+            print("json", json_str)
+        json.loads(json_str)
+        return json_str
+    except json.JSONDecodeError as e:
+        if cfg.debug:
+            print('json loads error', e)
+        error_message = str(e)
+        if error_message.startswith('Invalid \\escape'):
+            json_str = fix_invalid_escape(json_str, error_message)
+        if error_message.startswith('Expecting property name enclosed in double quotes'):
+            json_str = add_quotes_to_property_names(json_str)
+            try:
+                json.loads(json_str)
+                return json_str
+            except json.JSONDecodeError as e:
+                if cfg.debug:
+                    print('json loads error - add quotes', e)
+                error_message = str(e)
+        if balanced_str := balance_braces(json_str):
+            return balanced_str
+    return json_str