Refactored replacement elements into base

ezregex/base/__init__.py

@@ -1,9 +1,32 @@
+from types import EllipsisType
+from typing import Callable
 from ..EZRegex import EZRegex
 from .elements import base
+from string import Formatter
 
 
-def load_base(dialect, exclude=[]) -> dict:
+def load_base(dialect, rgroup_func: Callable[[int|str, EllipsisType], str], replace_entire_func=...) -> dict:
     rtn = {}
     for name, kwargs in base.items():
         rtn[name] = EZRegex(**kwargs, dialect=dialect)
+
+    # I'm creating this here, so we don't have to reimplement both of them every time
+    def replace(string, rtn_str=True):
+        class CustomFormatter(Formatter):
+            def get_value(self, key, args, kwargs):
+                return rgroup_func(key, '')
+
+        string = CustomFormatter().format(string)
+
+        return string if rtn_str else EZRegex(string, dialect, sanatize=False, replacement=True)
+
+
+    rtn['replace'] = replace
+    rtn['rgroup'] = EZRegex(rgroup_func, dialect, replacement=True)
+    rtn['replace_entire'] = EZRegex(
+        lambda cur=...: rgroup_func(0, cur=cur) if replace_entire_func is Ellipsis else replace_entire_func,
+        dialect,
+        replacement=True
+    )
+
     return rtn

ezregex/javascript/__init__.py

@@ -1,5 +1,5 @@
 """ Support for the JavaScript dialect of regular expressions"""
-__version__ = '1.1.1'
+__version__ = '0.0.1'
 
 from .elements import *
 from .psuedonymns import *

ezregex/javascript/elements.py

@@ -1,30 +1,6 @@
 # pyright: reportArgumentType = false
-import re
-from json import load
-
+# pyright: reportUndefinedVariable = false
 from ..base import load_base
 from ..EZRegex import EZRegex
 
-globals().update(load_base('javascript'))
-
-# TODO: Use https://docs.python.org/3/library/string.html#string.Formatter instead
-def replace(string, rtn_str=True):
-    # Made with ezregex.org
-    # Previous method
-    # '{' + optional(anyCharExcept('{'), greedy=False) + group(+alphaNum) + '}' + optional(anyCharExcept('}'), greedy=False)
-    # Current method
-    # '{' + group(+alphaNum) + '}'
-    r = r'\{((?:[A-Za-z0-9_])+)\}'
-    # Convert them to something unique, then back, so we won't pick up things like {{this}}
-    # {{this}} -> \0(this\0) -> {this}
-    # instead of
-    # {{this}} -> {this} -> \g<this>
-    string = re.sub('{{', '\0\0(', string)
-    string = re.sub('}}', '\0\0)', string)
-    string = re.sub(r, r'\\g<\g<1>>', string)
-    string = re.sub(r'\0\0\(', '{', string)
-    string = re.sub(r'\0\0\)', '}', string)
-    return string if rtn_str else EZRegex(string, 'javascript', sanatize=False, replacement=True)
-
-rgroup = EZRegex(lambda num_or_name, cur=...: fr'{cur}\g<{num_or_name}>', 'javascript', replacement=True)
-replace_entire = EZRegex(lambda cur=...: cur + r'\g<0>', 'javascript', replacement=True)
+globals().update(load_base('javascript', lambda num_or_name, cur=...: fr'{cur}\g<{num_or_name}>'))

ezregex/perl/__init__.py

@@ -1,5 +1,5 @@
 """ Support for the Perl dialect of regular expressions"""
-__version__ = '1.1.1'
+__version__ = '0.0.1'
 
 from .elements import *
 from .psuedonymns import *

ezregex/perl/elements.py

@@ -1,32 +1,6 @@
 # pyright: reportArgumentType = false
-import re
-from json import load
-
+# pyright: reportUndefinedVariable = false
 from ..base import load_base
 from ..EZRegex import EZRegex
 
-globals().update(load_base('perl'))
-
-del UNICODE # type: ignore
-
-# TODO: Use https://docs.python.org/3/library/string.html#string.Formatter instead
-def replace(string, rtn_str=True):
-    # Made with ezregex.org
-    # Previous method
-    # '{' + optional(anyCharExcept('{'), greedy=False) + group(+alphaNum) + '}' + optional(anyCharExcept('}'), greedy=False)
-    # Current method
-    # '{' + group(+alphaNum) + '}'
-    r = r'\{((?:[A-Za-z0-9_])+)\}'
-    # Convert them to something unique, then back, so we won't pick up things like {{this}}
-    # {{this}} -> \0(this\0) -> {this}
-    # instead of
-    # {{this}} -> {this} -> \g<this>
-    string = re.sub('{{', '\0\0(', string)
-    string = re.sub('}}', '\0\0)', string)
-    string = re.sub(r, r'\\g<\g<1>>', string)
-    string = re.sub(r'\0\0\(', '{', string)
-    string = re.sub(r'\0\0\)', '}', string)
-    return string if rtn_str else EZRegex(string, 'perl', sanatize=False, replacement=True)
-
-rgroup = EZRegex(lambda num_or_name, cur=...: fr'{cur}\g<{num_or_name}>', 'perl', replacement=True)
-replace_entire = EZRegex(lambda cur=...: cur + r'\g<0>', 'perl', replacement=True)
+globals().update(load_base('perl', lambda num_or_name, cur=...: fr'{cur}\g<{num_or_name}>'))

ezregex/python/__init__.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """ Support for the Python dialect of regular expressions"""
-__version__ = '0.1.0'
+__version__ = '1.1.0'
 
 from .elements import *
 from .psuedonymns import *

ezregex/python/elements.py

@@ -1,35 +1,11 @@
 # pyright: reportArgumentType = false
-import re
-from json import load
-
+# pyright: reportUndefinedVariable = false
 from ..base import load_base
 from ..EZRegex import EZRegex
 
-globals().update(load_base('python'))
-
-del UNICODE # type: ignore
-
-# TODO: Use https://docs.python.org/3/library/string.html#string.Formatter instead
-def replace(string, rtn_str=True):
-    # Made with ezregex.org
-    # Previous method
-    # '{' + optional(anyCharExcept('{'), greedy=False) + group(+alphaNum) + '}' + optional(anyCharExcept('}'), greedy=False)
-    # Current method
-    # '{' + group(+alphaNum) + '}'
-    r = r'\{((?:[A-Za-z0-9_])+)\}'
-    # Convert them to something unique, then back, so we won't pick up things like {{this}}
-    # {{this}} -> \0(this\0) -> {this}
-    # instead of
-    # {{this}} -> {this} -> \g<this>
-    string = re.sub('{{', '\0\0(', string)
-    string = re.sub('}}', '\0\0)', string)
-    string = re.sub(r, r'\\g<\g<1>>', string)
-    string = re.sub(r'\0\0\(', '{', string)
-    string = re.sub(r'\0\0\)', '}', string)
-    return string if rtn_str else EZRegex(string, 'python', sanatize=False, replacement=True)
+globals().update(load_base('python', lambda num_or_name, cur=...: fr'{cur}\g<{num_or_name}>'))
 
-rgroup = EZRegex(lambda num_or_name, cur=...: fr'{cur}\g<{num_or_name}>', 'python', replacement=True)
-replace_entire = EZRegex(lambda cur=...: cur + r'\g<0>', 'python', replacement=True)
+del UNICODE
 
 # Source: http://stackoverflow.com/questions/201323/ddg#201378
 email = raw(r"(?:[a-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[a-z0-9!#$%&'*+/=?^_`{|}~-]+)*|\"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])*\")@(?:(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?|\[(?:(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9]))\.){3}(?:(2(5[0-5]|[0-4][0-9])|1[0-9][0-9]|[1-9]?[0-9])|[a-z0-9-]*[a-z0-9]:(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21-\x5a\x53-\x7f]|\\[\x01-\x09\x0b\x0c\x0e-\x7f])+)\])")

tests/data/python_regexs.jsonc

@@ -0,0 +1,9 @@
+// This goes ["regex", [things it should match], [things it shouldnt match]]
+[
+    [
+
+    ],
+    [
+
+    ]
+]

tests/data/regexs.jsonc

@@ -1,4 +1,4 @@
-// This goes [regex, [things it should match], [things it shouldnt match]]
+// This goes ["regex", [things it should match], [things it shouldnt match]]
 // IMPORTANT NOTE: Because this is a JSON file, and the the regexs get compiled, escaped characters like \n and \t need to
 // be double escaped in the regex patterns (i.e. \\n, \\t), but NOT in the strings they should and shouldn't match
 [

tests/test_python.py

@@ -1,4 +1,3 @@
-# import jsonc
 from ezregex import python
 import jstyleson
 import ezregex as er