Refactor CharClass and BackReference to improve type hints and clarity; update version to 0.9.5

Author: Buba98

regex_enumerator/regex_parser.py

@@ -93,7 +93,7 @@ def _parseRegex(self, to_close: bool) -> RegexTree:
                         chars = self._parseEscapeChar()
                         min_len, max_len = self._parseQuantifier()
                         elements.append(
-                            CharClass(chars, min_len, max_len, self.precompute))
+                            CharClass([chars], min_len, max_len, self.precompute))
                         continue
                     if isinstance(reference, str):
                         if reference not in named_groups:
@@ -257,7 +257,7 @@ def _parseCharClass(self) -> list[str]:
 
         return chars_list
 
-    def _parseQuantifier(self) -> tuple[int, int]:
+    def _parseQuantifier(self) -> tuple[int, int | None]:
 
         if len(self.regex) <= self.index:
             return 1, 1

regex_enumerator/regex_tree.py

@@ -3,7 +3,7 @@ class RegexTree:
 
 
 class CharClass:
-    def __init__(self, chars_list: list[str], min_len: int, max_len: int, precompute: bool):
+    def __init__(self, chars_list: list[str], min_len: int, max_len: int | None, precompute: bool):
         self._index = 0
         self._precompute = precompute and max_len is not None
         self._chars: str = ''.join(sorted(set(''.join(chars_list))))
@@ -33,7 +33,7 @@ def _compute_all(self) -> list[str]:
         result = []
         for i in range(self._min_len, self._max_len + 1):
             temp = ['']
-            for j in range(i):
+            for _ in range(i):
                 temp = [pfx + sfx for pfx in self._chars for sfx in temp]
             result.extend(temp)
         return result
@@ -96,8 +96,7 @@ def __init__(self, reference: RegexTree, min_len: int, max_len: int | None, prec
         self.reference: RegexTree = reference
         self.done = max_len == 0 or (
             reference.done and len(reference.current) == 0)
-        self.current: dict[str, list[str]
-                           ] = self._calculate() if not self.done else {}
+        self.current: dict[str, list[str]] = self._calculate() if not self.done else {}
 
     def update_reference(self, new_strings: set[str]) -> None:
         if self._max_len is not None and self._min_len + self._index >= self._max_len and self.reference.done:
@@ -108,7 +107,7 @@ def update_reference(self, new_strings: set[str]) -> None:
             self.current[string] = [
                 string * i for i in range(self._min_len, self._min_len + self._index + 1)]
 
-    def _calculate(self) -> dict[str, set[str]]:
+    def _calculate(self) -> dict[str, list[str]]:
         current_ref = self.reference.current
         if self._max_len is not None and self._min_len + self._index >= self._max_len:
             self.done = True
@@ -121,7 +120,7 @@ def _calculate(self) -> dict[str, set[str]]:
 
         return result
 
-    def next(self) -> dict[str, set[str]]:
+    def next(self) -> dict[str, list[str]]:
         assert not self.done
         self._index += 1
         if self._max_len is not None and self._min_len + self._index >= self._max_len:
@@ -270,7 +269,7 @@ def _calculate_first(self) -> set[str]:
 
         return result
 
-    def add_reference(self, reference: BackReference):
+    def add_reference(self, reference: BackReference) -> None:
         if reference.done and len(reference.current) == 0:
             return
         self.references.append(reference)

setup.py

@@ -5,7 +5,7 @@
 
 setup(
     name='regex_enumerator',
-    version='0.9.4',
+    version='0.9.5',
     packages=find_packages(include=['regex_enumerator', 'regex_enumerator.*']),
     description='Enumerate all strings that match a given regex',
     author='Vincenzo Greco',

tests/test_mixed.py

@@ -31,6 +31,7 @@ def test_done():
 
     f_finite(regex, possibilities)
 
+
 def test_empty_additional_charset():
     regexEnumerator = RegexEnumerator(r'')
     assert regexEnumerator.next() == ''
@@ -63,3 +64,16 @@ def test_weak_password():
                                         l_char + o + v + e + y + year + special_1 + special_2)
 
     f_finite(regex, possibilities)
+
+
+def test_complete_regex():
+    regex = r'[Ll]([Uu])?\1{0,2}(0|1){0,3}[!1.]'
+    possibilities = []
+
+    for l_char in 'Ll':
+        for u in ['U', 'UU', 'UUU', 'u', 'uu', 'uuu', '']:
+            for num in ['0', '1', '00', '01', '10', '11', '000', '001', '010', '011', '100', '101', '110', '111', '']:
+                for special in ['!', '1', '.']:
+                    possibilities.append(l_char + u + num + special)
+
+    f_finite(regex, possibilities)