- update to srange to accept unicode literals in the input StringEnd

- enhanced version of replaceWith

3 files changed, 26 insertions, 10 deletions

diff --git a/src/CHANGES b/src/CHANGES
index 2fe5905..f1d1130 100644
--- a/src/CHANGES
+++ b/src/CHANGES
@@ -2,6 +2,15 @@
 Change Log

 ==========

 

+Version 2.0.4 -

+---------------------------

+- Slight mod to srange to accept unicode literals for the input string,

+  such as "[а-яА-Я]" instead of "[\u0430-\u044f\u0410-\u042f]". Thanks 

+  to Alexandr Suchkov for the patch!

+

+- Enhanced implementation of replaceWith

+

+

 Version 2.0.3 - 

 ---------------------------

 - Fixed escaping behavior in QuotedString. Formerly, only quotation

@@ -719,7 +728,7 @@ Version 1.4.8 - October, 2007
   the new features.

 

 - Added performance speedup to grammars using operatorPrecedence,

-  instigated by Stefan Reich�r - thanks for the feedback, Stefan!

+  instigated by Stefan Reichör - thanks for the feedback, Stefan!

 

 - Fixed bug/typo when deleting an element from a ParseResults by

   using the element's results name.

@@ -1414,7 +1423,7 @@ Version 1.3 - March, 2005
   (Big thanks to Gavin Panella!)

 

 - Added constant alphas8bit to include the following 8-bit characters:

-    �������������������������������������������������������������

+    ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþ

 

 - Added srange() function to simplify definition of Word elements, using

   regexp-like '[A-Za-z0-9]' syntax.  This also simplifies referencing

diff --git a/src/pyparsing.py b/src/pyparsing.py
index 7b82f71..ff1ff60 100644
--- a/src/pyparsing.py
+++ b/src/pyparsing.py
@@ -70,6 +70,9 @@ import re
 import sre_constants

 import collections

 import pprint

+import functools

+import itertools

+

 #~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) )

 

 __all__ = [

@@ -3352,7 +3355,7 @@ stringEnd   = StringEnd().setName("stringEnd")
 _escapedPunc = Word( _bslash, r"\[]-*.$+^?()~ ", exact=2 ).setParseAction(lambda s,l,t:t[0][1])

 _escapedHexChar = Regex(r"\\0?[xX][0-9a-fA-F]+").setParseAction(lambda s,l,t:unichr(int(t[0].lstrip(r'\0x'),16)))

 _escapedOctChar = Regex(r"\\0[0-7]+").setParseAction(lambda s,l,t:unichr(int(t[0][1:],8)))

-_singleChar = _escapedPunc | _escapedHexChar | _escapedOctChar | Word(printables, excludeChars=r'\]', exact=1)

+_singleChar = _escapedPunc | _escapedHexChar | _escapedOctChar | Word(printables, excludeChars=r'\]', exact=1) | Regex(r"\w", re.UNICODE)

 _charRange = Group(_singleChar + Suppress("-") + _singleChar)

 _reBracketExpr = Literal("[") + Optional("^").setResultsName("negate") + Group( OneOrMore( _charRange | _singleChar ) ).setResultsName("body") + "]"

 

@@ -3392,9 +3395,10 @@ def replaceWith(replStr):
     """Helper method for common parse actions that simply return a literal value.  Especially

        useful when used with C{L{transformString<ParserElement.transformString>}()}.

     """

-    def _replFunc(*args):

-        return [replStr]

-    return _replFunc

+    #def _replFunc(*args):

+    #    return [replStr]

+    #return _replFunc

+    return functools.partial(next, itertools.repeat([replStr]))

 

 def removeQuotes(s,l,t):

     """Helper parse action for removing quotation marks from parsed quoted strings.

diff --git a/src/unitTests.py b/src/unitTests.py
index cefd763..84fe9c9 100644
--- a/src/unitTests.py
+++ b/src/unitTests.py
@@ -854,6 +854,8 @@ class ReStringRangeTest(ParseTestCase):
             (r"[A-]"),

             (r"[-A]"),

             (r"[\x21]"),

+            #(r"[а-яА-ЯёЁA-Z$_\041α-ω]".decode('utf-8')),

+            (u'[\u0430-\u044f\u0410-\u042f\u0451\u0401ABCDEFGHIJKLMNOPQRSTUVWXYZ$_\041\u03b1-\u03c9]'),

             )

         expectedResults = (

             "ABCDEFGHIJKLMNOPQRSTUVWXYZ",

@@ -877,12 +879,13 @@ class ReStringRangeTest(ParseTestCase):
             "A-",

             "-A",

             "!",

+            u"абвгдежзийклмнопрстуфхцчшщъыьэюяАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯёЁABCDEFGHIJKLMNOPQRSTUVWXYZ$_!αβγδεζηθικλμνξοπρςστυφχψω",

             )

         for test in zip( testCases, expectedResults ):

             t,exp = test

             res = pyparsing.srange(t)

-            #~ print t,"->",res

-            assert res == exp, "srange error, srange(%s)->'%r', expected '%r'" % (t, res, exp)

+            #print_(t,"->",res)

+            assert res == exp, "srange error, srange(%r)->'%r', expected '%r'" % (t, res, exp)

 

 class SkipToParserTests(ParseTestCase):

     def runTest(self):

@@ -1376,8 +1379,8 @@ class UpcaseDowncaseUnicode(ParseTestCase):
             from __builtin__ import unichr

 

         a = '\u00bfC\u00f3mo esta usted?'

-        ualphas = "".join( [ unichr(i) for i in range(sys.maxunicode)

-                            if unichr(i).isalpha() ] )

+        ualphas = "".join( unichr(i) for i in range(sys.maxunicode)

+                            if unichr(i).isalpha() )

         uword = pp.Word(ualphas).setParseAction(pp.upcaseTokens)

 

         print_ = lambda *args: None