#22650: test suite: load Unicode test data files from www.pythontest.net

Lib/test/test_codecmaps_cn.py

@@ -10,19 +10,17 @@ import unittest
 class TestGB2312Map(multibytecodec_support.TestBase_Mapping,
                    unittest.TestCase):
     encoding = 'gb2312'
-    mapfileurl = 'http://people.freebsd.org/~perky/i18n/EUC-CN.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/EUC-CN.TXT'
 
 class TestGBKMap(multibytecodec_support.TestBase_Mapping,
                    unittest.TestCase):
     encoding = 'gbk'
-    mapfileurl = 'http://www.unicode.org/Public/MAPPINGS/VENDORS/' \
-                 'MICSFT/WINDOWS/CP936.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/CP936.TXT'
 
 class TestGB18030Map(multibytecodec_support.TestBase_Mapping,
                      unittest.TestCase):
     encoding = 'gb18030'
-    mapfileurl = 'http://source.icu-project.org/repos/icu/data/' \
-                 'trunk/charset/data/xml/gb-18030-2000.xml'
+    mapfileurl = 'http://www.pythontest.net/unicode/gb-18030-2000.xml'
 
 
 if __name__ == "__main__":

Lib/test/test_codecmaps_hk.py

@@ -10,7 +10,7 @@ import unittest
 class TestBig5HKSCSMap(multibytecodec_support.TestBase_Mapping,
                        unittest.TestCase):
     encoding = 'big5hkscs'
-    mapfileurl = 'http://people.freebsd.org/~perky/i18n/BIG5HKSCS-2004.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/BIG5HKSCS-2004.TXT'
 
 if __name__ == "__main__":
     unittest.main()

Lib/test/test_codecmaps_jp.py

@@ -10,8 +10,7 @@ import unittest
 class TestCP932Map(multibytecodec_support.TestBase_Mapping,
                    unittest.TestCase):
     encoding = 'cp932'
-    mapfileurl = 'http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/' \
-                 'WINDOWS/CP932.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/CP932.TXT'
     supmaps = [
         (b'\x80', '\u0080'),
         (b'\xa0', '\uf8f0'),
@@ -27,15 +26,14 @@ class TestEUCJPCOMPATMap(multibytecodec_support.TestBase_Mapping,
                          unittest.TestCase):
     encoding = 'euc_jp'
     mapfilename = 'EUC-JP.TXT'
-    mapfileurl = 'http://people.freebsd.org/~perky/i18n/EUC-JP.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/EUC-JP.TXT'
 
 
 class TestSJISCOMPATMap(multibytecodec_support.TestBase_Mapping,
                         unittest.TestCase):
     encoding = 'shift_jis'
     mapfilename = 'SHIFTJIS.TXT'
-    mapfileurl = 'http://www.unicode.org/Public/MAPPINGS/OBSOLETE' \
-                 '/EASTASIA/JIS/SHIFTJIS.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/SHIFTJIS.TXT'
     pass_enctest = [
         (b'\x81_', '\\'),
     ]
@@ -49,14 +47,14 @@ class TestEUCJISX0213Map(multibytecodec_support.TestBase_Mapping,
                          unittest.TestCase):
     encoding = 'euc_jisx0213'
     mapfilename = 'EUC-JISX0213.TXT'
-    mapfileurl = 'http://people.freebsd.org/~perky/i18n/EUC-JISX0213.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/EUC-JISX0213.TXT'
 
 
 class TestSJISX0213Map(multibytecodec_support.TestBase_Mapping,
                        unittest.TestCase):
     encoding = 'shift_jisx0213'
     mapfilename = 'SHIFT_JISX0213.TXT'
-    mapfileurl = 'http://people.freebsd.org/~perky/i18n/SHIFT_JISX0213.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/SHIFT_JISX0213.TXT'
 
 
 if __name__ == "__main__":

Lib/test/test_codecmaps_kr.py

@@ -10,14 +10,13 @@ import unittest
 class TestCP949Map(multibytecodec_support.TestBase_Mapping,
                    unittest.TestCase):
     encoding = 'cp949'
-    mapfileurl = 'http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT' \
-                 '/WINDOWS/CP949.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/CP949.TXT'
 
 
 class TestEUCKRMap(multibytecodec_support.TestBase_Mapping,
                    unittest.TestCase):
     encoding = 'euc_kr'
-    mapfileurl = 'http://people.freebsd.org/~perky/i18n/EUC-KR.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/EUC-KR.TXT'
 
     # A4D4 HANGUL FILLER indicates the begin of 8-bytes make-up sequence.
     pass_enctest = [(b'\xa4\xd4', '\u3164')]
@@ -27,8 +26,7 @@ class TestEUCKRMap(multibytecodec_support.TestBase_Mapping,
 class TestJOHABMap(multibytecodec_support.TestBase_Mapping,
                    unittest.TestCase):
     encoding = 'johab'
-    mapfileurl = 'http://www.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/' \
-                 'KSC/JOHAB.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/JOHAB.TXT'
     # KS X 1001 standard assigned 0x5c as WON SIGN.
     # but, in early 90s that is the only era used johab widely,
     # the most softwares implements it as REVERSE SOLIDUS.

Lib/test/test_codecmaps_tw.py

@@ -10,14 +10,12 @@ import unittest
 class TestBIG5Map(multibytecodec_support.TestBase_Mapping,
                   unittest.TestCase):
     encoding = 'big5'
-    mapfileurl = 'http://www.unicode.org/Public/MAPPINGS/OBSOLETE/' \
-                 'EASTASIA/OTHER/BIG5.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/BIG5.TXT'
 
 class TestCP950Map(multibytecodec_support.TestBase_Mapping,
                    unittest.TestCase):
     encoding = 'cp950'
-    mapfileurl = 'http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/' \
-                 'WINDOWS/CP950.TXT'
+    mapfileurl = 'http://www.pythontest.net/unicode/CP950.TXT'
     pass_enctest = [
         (b'\xa2\xcc', '\u5341'),
         (b'\xa2\xce', '\u5345'),

Lib/test/test_normalization.py

@@ -7,7 +7,7 @@ import os
 from unicodedata import normalize, unidata_version
 
 TESTDATAFILE = "NormalizationTest.txt"
-TESTDATAURL = "http://www.unicode.org/Public/" + unidata_version + "/ucd/" + TESTDATAFILE
+TESTDATAURL = "http://www.pythontest.net/unicode/" + unidata_version + "/" + TESTDATAFILE
 
 def check_version(testfile):
     hdr = testfile.readline()

Lib/test/test_ucn.py

@@ -172,7 +172,7 @@ class UnicodeNamesTest(unittest.TestCase):
 
     def test_named_sequences_full(self):
         # Check all the named sequences
-        url = ("http://www.unicode.org/Public/%s/ucd/NamedSequences.txt" %
+        url = ("http://www.pythontest.net/unicode/%s/NamedSequences.txt" %
                unicodedata.unidata_version)
         try:
             testdata = support.open_urlresource(url, encoding="utf-8",