Add support for dynamic overwrite of pyparsing's use of stdlib re module with regex or other RE-compatible module

2 files changed, 54 insertions, 8 deletions

diff --git a/CHANGES b/CHANGES
index e0ae174..162f96e 100644
--- a/CHANGES
+++ b/CHANGES
@@ -73,13 +73,41 @@ Version 3.0.0a1
 
         pp.__diag__.enable_all_warnings()
 
-- New namespace, assert methods and classes added to support writing unit tests.
+- New namespace, assert methods and classes added to support writing
+  unit tests.
   - assertParseResultsEquals
   - assertParseAndCheckList
   - assertParseAndCheckDict
   - assertRunTestResults
   - assertRaisesParseException
-  - reset_pyparsing_context context manager, to restore pyparsing config settings
+  - reset_pyparsing_context context manager, to restore pyparsing
+    config settings
+
+- Enhanced the Regex class to be compatible with re's compiled with the
+  re-equivalent regex module. Individual expressions can be built with
+  regex compiled expressions using:
+
+    import pyparsing as pp
+    import regex
+
+    # would use regex for this expression
+    integer_parser = pp.Regex(regex.compile(r'\d+'))
+
+  You can also replace the use of the re module as it is used internally
+  by pyparsing in a number of classes by overwriting pyparsing's imported
+  re symbol:
+
+    import pyparsing as pp
+    import regex
+    pp.re = regex  # redirects all internal re usage in pyparsing to regex
+
+    # would now use regex instead of re to compile this string
+    integer_parser = pp.Regex(r'\d+')
+
+    # would also now use regex internally instead of re
+    integer_parser = pp.Word(pp.nums)
+
+  Inspired by PR submitted by bjrnfrdnnd on GitHub, very nice!
 
 - Fixed handling of ParseSyntaxExceptions raised as part of Each
   expressions, when sub-expressions contain '-' backtrack
diff --git a/pyparsing.py b/pyparsing.py
index 6c3c7ec..48720f0 100644
--- a/pyparsing.py
+++ b/pyparsing.py
@@ -96,7 +96,7 @@ classes inherit from. Use the docstrings for examples of how to:
 """
 
 __version__ = "3.0.0a1"
-__versionTime__ = "13 Oct 2019 05:28 UTC"
+__versionTime__ = "13 Oct 2019 05:49 UTC"
 __author__ = "Paul McGuire <ptmcg@users.sourceforge.net>"
 
 import string
@@ -219,7 +219,7 @@ __all__ = ['__version__', '__versionTime__', '__author__', '__compat__', '__diag
            'stringStart', 'traceParseAction', 'unicodeString', 'withAttribute',
            'indentedBlock', 'originalTextFor', 'ungroup', 'infixNotation', 'locatedExpr', 'withClass',
            'CloseMatch', 'tokenMap', 'pyparsing_common', 'pyparsing_unicode', 'unicode_set',
-           'conditionAsParseAction', 'pyparsing_test',
+           'conditionAsParseAction', 'pyparsing_test', 're',
            ]
 
 system_version = tuple(sys.version_info)[:3]
@@ -3065,14 +3065,32 @@ class Regex(Token):
     If the given regex contains named groups (defined using ``(?P<name>...)``),
     these will be preserved as named parse results.
 
+    If instead of the Python stdlib re module you wish to use a different RE module
+    (such as the `regex` module), you can replace it by either building your
+    Regex object with a compiled RE that was compiled using regex, or by replacing
+    the imported `re` module in pyparsing with the `regex` module:
+
+
     Example::
 
         realnum = Regex(r"[+-]?\d+\.\d*")
         date = Regex(r'(?P<year>\d{4})-(?P<month>\d\d?)-(?P<day>\d\d?)')
         # ref: https://stackoverflow.com/questions/267399/how-do-you-match-only-valid-roman-numerals-with-a-regular-expression
         roman = Regex(r"M{0,4}(CM|CD|D?{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})")
+
+        import regex
+        parser = pp.Regex(regex.compile(r'[0-9]'))
+
+        # or
+
+        import pyparsing
+        pyparsing.re = regex
+
+        # both of these will use the regex module to compile their internal re's
+        parser = pp.Regex(r'[0-9]')
+        parser = pp.Word(pp.nums)
+
     """
-    compiledREtype = type(re.compile("[A-Z]"))
     def __init__(self, pattern, flags=0, asGroupList=False, asMatch=False):
         """The parameters ``pattern`` and ``flags`` are passed
         to the ``re.compile()`` function as-is. See the Python
@@ -3097,13 +3115,13 @@ class Regex(Token):
                               SyntaxWarning, stacklevel=2)
                 raise
 
-        elif isinstance(pattern, Regex.compiledREtype):
+        elif hasattr(pattern, 'pattern') and hasattr(pattern, 'match'):
             self.re = pattern
-            self.pattern = self.reString = str(pattern)
+            self.pattern = self.reString = pattern.pattern
             self.flags = flags
 
         else:
-            raise ValueError("Regex may only be constructed with a string or a compiled RE object")
+            raise TypeError("Regex may only be constructed with a string or a compiled RE object")
 
         self.re_match = self.re.match