Added unicode sets for LatinA and LatinB ranges

3 files changed, 33 insertions, 5 deletions

diff --git a/CHANGES b/CHANGES
index e96fee0..b9ae519 100644
--- a/CHANGES
+++ b/CHANGES
@@ -2,6 +2,11 @@
 Change Log

 ==========

 

+Version 2.3.1 -

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

+- Added unicode sets to pyparsing_unicode for Latin-A and Latin-B ranges.

+

+

 Version 2.3.0 - October, 2018

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

 - NEW SUPPORT FOR UNICODE CHARACTER RANGES

diff --git a/pyparsing.py b/pyparsing.py
index 5006e4e..19b0141 100644
--- a/pyparsing.py
+++ b/pyparsing.py
@@ -75,8 +75,8 @@ classes inherit from. Use the docstrings for examples of how to:
  - find more useful common expressions in the L{pyparsing_common} namespace class

 """

 

-__version__ = "2.3.0"

-__versionTime__ = "28 Oct 2018 01:57 UTC"

+__version__ = "2.3.1"

+__versionTime__ = "10 Nov 2018 04:38 UTC"

 __author__ = "Paul McGuire <ptmcg@users.sourceforge.net>"

 

 import string

@@ -5865,9 +5865,13 @@ class pyparsing_unicode(unicode_set):
     _ranges = [(32, sys.maxunicode)]

 

     class Latin1(unicode_set):

-        _ranges = [

-            (0x0020, 0x007e), (0x00a0, 0x00ff),

-        ]

+        _ranges = [(0x0020, 0x007e), (0x00a0, 0x00ff),]

+

+    class LatinA(unicode_set):

+        _ranges = [(0x0100, 0x017f),]

+

+    class LatinB(unicode_set):

+        _ranges = [(0x0180, 0x024f),]

 

     class Greek(unicode_set):

         _ranges = [

diff --git a/unitTests.py b/unitTests.py
index e54d68b..e4f2c63 100644
--- a/unitTests.py
+++ b/unitTests.py
@@ -3632,6 +3632,24 @@ class UnicodeTests(ParseTestCase):
         self.assertTrue(result.asList() == [u'Καλημέρα', ',', u'κόσμε', '!'],

                         "Failed to parse Greek 'Hello, World!' using pyparsing_unicode.Greek.alphas")

 

+        class Turkish_set(pp.unicode_set):

+            _ranges = pp.pyparsing_unicode.Latin1._ranges + pp.pyparsing_unicode.LatinA._ranges

+

+        key = pp.Word(Turkish_set.alphas)

+        value = pp.pyparsing_common.integer | pp.Word(Turkish_set.alphas, Turkish_set.alphanums)

+        EQ = pp.Suppress('=')

+        key_value = key + EQ + value

+

+        sample = """\

+            şehir=İzmir

+            ülke=Türkiye

+            nüfus=4279677"""

+        result = pp.Dict(pp.OneOrMore(pp.Group(key_value))).parseString(sample)

+

+        print(result.asDict())

+        self.assertEqual(result.asDict(), {'şehir': 'İzmir', 'ülke': 'Türkiye', 'nüfus': 4279677},

+                         "Failed to parse Turkish key-value pairs")

+

 class IndentedBlockTest(ParseTestCase):

     # parse pseudo-yaml indented text

     def runTest(self):

@@ -3914,6 +3932,7 @@ if __name__ == '__main__':
     # run specific tests by including them in this list, otherwise

     # all tests will be run

     testclasses = [

+        UnicodeTests

         ]

 

     if not testclasses: