add new regex based searching

README.MD

@@ -107,6 +107,37 @@
         # keylevel11.keylevel23.[{name=Awesome}]
         # return {name: Awesome}
         ```
+
+    - #### [{key~regex}]
+        - When you have a unordered list of object and you want extract a specific object from the list based on the key and a regex of value inside the object
+        - For extraction from beyond first level, append keys with a separator and provide `key_delimiter` for the program to recognize the start of next level.
+        - The regex search is case sensitive. You do not need to add `//` or `r''` to write your regex.
+        - Example: 
+        ```
+        """
+        {
+            keylevel11: {
+                keylevel21: [
+                    1, 2, 3
+                ],
+                keylevel22: {
+                    keylevel31: value
+                },
+                keylevel23: [
+                    {
+                        name: Awesome123,
+                    },
+                    {
+                        name: Package
+                    }
+                ]
+            }
+        }
+        """
+        # key to extract second level, and from that extarct the object with name matching Awesome
+        # keylevel11.keylevel23.[{name~Awesome}]
+        # return {name: Awesome}
+        ```
 
 ### Available Methods
 

WPTParser/Constants/RegexConstants.py

@@ -1,4 +1,5 @@
 class RegexConstants:
     INDEXED_ARRAY = r'\[(\d+)\]'
     DICT_ARRAY_SEARCH = r'\[\{(.+\=.+)\}\]'
-    RANGE_INDEXED_ARRAY = r'\[(\d+)\:(\d+)\]'
+    RANGE_INDEXED_ARRAY = r'\[(\d+)\:(\d+)\]'
+    DICT_ARRAY_REGEX_SEARCH = r'\[\{(.+\~.+)\}\]'

WPTParser/JSONParser/ObjectListDataRegexExtracter.py

@@ -0,0 +1,30 @@
+import re
+
+from WPTParser.JSONParser.DataExtracter import DataExtracter
+
+class ObjectListDataRegexExtracter(DataExtracter):
+
+    def __init__(self):
+        super().__init__()
+
+    def extract(self, obj_list: list, key: str):
+        """extract the keys of format [{key~value}]
+
+        Keyword Arguments:
+            obj_list {list} -- list of objects received from the previous key
+            key {str} -- key that needs to be processed
+
+        Returns:
+            {} -- The found dict
+        """
+        try:
+            key = key.replace(' ', '')
+            dict_key, dict_value = key.split('~')
+            for obj in obj_list:
+
+                regex_dict_value = re.compile(dict_value)
+                if dict_key in obj and re.search(regex_dict_value, obj[dict_key]):
+                    return obj
+            return None
+        except Exception as ex:
+            return None

WPTParser/JSONParser/__init__.py

@@ -1,11 +1,13 @@
 # TODO: ADD support for array type fields while parsing eg: data.Median.[0].value
 import re
+import logging
 
 from WPTParser.Constants import RegexConstants
 from WPTParser.JSONParser.KeyDataExtracter import KeyDataExtracter
 from WPTParser.JSONParser.ListDataExtracter import ListDataExtracter
 from WPTParser.JSONParser.ObjectListDataExtracter import ObjectListDataExtracter
 from WPTParser.JSONParser.ListRangeDataExtractor import ListRangeDataExtractor
+from WPTParser.JSONParser.ObjectListDataRegexExtracter import ObjectListDataRegexExtracter
 
 class JSONParser():
 
@@ -55,7 +57,7 @@ def _recursive_find(self, obj: dict = {}, level_list: list = [], index: int = 0)
                 else:
                     return None
         except Exception as ex:
-            print('error:', ex)
+            logging.error(ex)
             return None
 
     def _process_key(self, key: str):
@@ -74,6 +76,9 @@ def _process_key(self, key: str):
         elif re.match(RegexConstants.DICT_ARRAY_SEARCH, key):
             key = re.findall(RegexConstants.DICT_ARRAY_SEARCH, key)[0]
             extracter = ObjectListDataExtracter()
+        elif re.match(RegexConstants.DICT_ARRAY_REGEX_SEARCH, key):
+            key = re.findall(RegexConstants.DICT_ARRAY_REGEX_SEARCH, key)[0]
+            extracter = ObjectListDataRegexExtracter()
         # TODO: add support for range of array index
         # elif re.match(RegexConstants.RANGE_INDEXED_ARRAY, key):
         #     key = re.findall(RegexConstants.RANGE_INDEXED_ARRAY, key)[0]

setup.py

@@ -16,7 +16,7 @@ def read(fname):
 setuptools.setup(
     name="wpt-parser",
     package=['wpt-parser'],
-    version="0.0.4",
+    version="0.0.5",
     author="Bharat Sinha",
     author_email="bharat.sinha.2307@gmail.com",
     description=description,