Add abbreviations support to regex patterns

README.rst

@@ -124,6 +124,15 @@ If `regex module`_ is available, it automatically supports repeated captures.
     >>> matches[0].children
     [<01:(0, 2)>, <04:(9, 11)>]
 
+- ``abbreviations``
+
+  Defined as a list of 2-tuple, each tuple is an abbreviation.
+
+  >>> Rebulk().regex(r'Custom-separators', abbreviations=[("-", "[\W_]+")])\
+  ...         .matches("Custom_separators using-abbreviations")
+  [<Custom_separators:(0, 17)>]
+
+
 Functional Patterns
 -------------------
 Functional Patterns are based on the evaluation of a function.

rebulk/pattern.py

@@ -152,14 +152,21 @@ def __init__(self, *patterns, **kwargs):
             self.repeated_captures = kwargs.get('repeated_captures')
         if self.repeated_captures and not REGEX_AVAILABLE:  # pragma: no cover
             raise NotImplementedError("repeated_capture is available only with regex module.")
+        self.abbreviations = kwargs.get('abbreviations', [])
         self._kwargs = kwargs
         self._match_kwargs = _filter_match_kwargs(kwargs)
         self._children_match_kwargs = _filter_match_kwargs(kwargs, children=True)
         self._patterns = []
         for pattern in patterns:
             if isinstance(pattern, six.string_types):
+                if self.abbreviations and pattern:
+                    for key, replacement in self.abbreviations:
+                        pattern = pattern.replace(key, replacement)
                 pattern = call(re.compile, pattern, **self._kwargs)
             elif isinstance(pattern, dict):
+                if self.abbreviations and 'pattern' in pattern:
+                    for key, replacement in self.abbreviations:
+                        pattern['pattern'] = pattern['pattern'].replace(key, replacement)
                 pattern = re.compile(**pattern)
             elif hasattr(pattern, '__iter__'):
                 pattern = re.compile(*pattern)

rebulk/test/test_pattern.py

@@ -122,6 +122,17 @@ def test_no_match(self):
         matches = list(pattern.matches(self.input_string))
         assert len(matches) == 0
 
+    def test_shortcuts(self):
+        pattern = RePattern("Celtic-violin", abbreviations=[("-", r"[\W_]+")])
+
+        matches = list(pattern.matches(self.input_string))
+        assert len(matches) == 1
+
+        pattern = RePattern({"pattern": "celtic-violin", "flags": re.IGNORECASE}, abbreviations=[("-", r"[\W_]+")])
+
+        matches = list(pattern.matches(self.input_string))
+        assert len(matches) == 1
+
     def test_multiple_patterns(self):
         pattern = RePattern("pla.?ing", "ann.?yed", "Heb.?ew")