bpo-38043: Move unicodedata.normalize tests into test_unicodedata. (p…

…ythonGH-15712)

Having these in a separate file from the one that's named after the
module in the usual way makes it very easy to miss them when looking
for tests for these two functions.

(In fact when working recently on is_normalized, I'd been surprised to
see no tests for it here and concluded the function had evaded being
tested at all.  I'd gone as far as to write up some tests myself
before I spotted this other file.)

Mostly this just means moving all the one file's code into the other,
and moving code from the module toplevel to inside the test class to
keep it tidily separate from the rest of the file's code.

There's one substantive change, which reduces by a bit the amount of
code to be moved: we drop the `x > sys.maxunicode` conditional and all
the `RangeError` logic behind it.  Now if that condition ever occurs
it will cause an error at `chr(x)`, and a test failure.  That's the
right result because, since PEP 393 in Python 3.3, there is no longer
such a thing as an "unsupported character".

Lib/test/test_ucn.py

@@ -12,7 +12,6 @@
 
 from test import support
 from http.client import HTTPException
-from test.test_normalization import check_version
 
 try:
     from _testcapi import INT_MAX, PY_SSIZE_T_MAX, UINT_MAX
@@ -172,6 +171,9 @@ def test_named_sequences_sample(self):
 
     def test_named_sequences_full(self):
         # Check all the named sequences
+        def check_version(testfile):
+            hdr = testfile.readline()
+            return unicodedata.unidata_version in hdr
         url = ("http://www.pythontest.net/unicode/%s/NamedSequences.txt" %
                unicodedata.unidata_version)
         try:

Lib/test/test_unicodedata.py

@@ -7,10 +7,11 @@
 """
 
 import hashlib
+from http.client import HTTPException
 import sys
 import unicodedata
 import unittest
-from test.support import script_helper
+from test.support import open_urlresource, script_helper
 
 
 class UnicodeMethodsTest(unittest.TestCase):
@@ -171,13 +172,6 @@ def test_combining(self):
         self.assertRaises(TypeError, self.db.combining)
         self.assertRaises(TypeError, self.db.combining, 'xx')
 
-    def test_normalize(self):
-        self.assertRaises(TypeError, self.db.normalize)
-        self.assertRaises(ValueError, self.db.normalize, 'unknown', 'xx')
-        self.assertEqual(self.db.normalize('NFKC', ''), '')
-        # The rest can be found in test_normalization.py
-        # which requires an external file.
-
     def test_pr29(self):
         # http://www.unicode.org/review/pr-29.html
         # See issues #1054943 and #10254.
@@ -208,9 +202,6 @@ def test_issue29456(self):
         self.assertEqual(self.db.normalize('NFC', u11a7_str_a), u11a7_str_b)
         self.assertEqual(self.db.normalize('NFC', u11c3_str_a), u11c3_str_b)
 
-    # For tests of unicodedata.is_normalized / self.db.is_normalized ,
-    # see test_normalization.py .
-
     def test_east_asian_width(self):
         eaw = self.db.east_asian_width
         self.assertRaises(TypeError, eaw, b'a')
@@ -315,5 +306,102 @@ def test_linebreak_7643(self):
                 self.assertEqual(len(lines), 1,
                                  r"\u%.4x should not be a linebreak" % i)
 
+class NormalizationTest(unittest.TestCase):
+    @staticmethod
+    def check_version(testfile):
+        hdr = testfile.readline()
+        return unicodedata.unidata_version in hdr
+
+    @staticmethod
+    def unistr(data):
+        data = [int(x, 16) for x in data.split(" ")]
+        return "".join([chr(x) for x in data])
+
+    def test_normalization(self):
+        TESTDATAFILE = "NormalizationTest.txt"
+        TESTDATAURL = f"http://www.pythontest.net/unicode/{unicodedata.unidata_version}/{TESTDATAFILE}"
+
+        # Hit the exception early
+        try:
+            testdata = open_urlresource(TESTDATAURL, encoding="utf-8",
+                                        check=self.check_version)
+        except PermissionError:
+            self.skipTest(f"Permission error when downloading {TESTDATAURL} "
+                          f"into the test data directory")
+        except (OSError, HTTPException):
+            self.fail(f"Could not retrieve {TESTDATAURL}")
+
+        with testdata:
+            self.run_normalization_tests(testdata)
+
+    def run_normalization_tests(self, testdata):
+        part = None
+        part1_data = {}
+
+        def NFC(str):
+            return unicodedata.normalize("NFC", str)
+
+        def NFKC(str):
+            return unicodedata.normalize("NFKC", str)
+
+        def NFD(str):
+            return unicodedata.normalize("NFD", str)
+
+        def NFKD(str):
+            return unicodedata.normalize("NFKD", str)
+
+        for line in testdata:
+            if '#' in line:
+                line = line.split('#')[0]
+            line = line.strip()
+            if not line:
+                continue
+            if line.startswith("@Part"):
+                part = line.split()[0]
+                continue
+            c1,c2,c3,c4,c5 = [self.unistr(x) for x in line.split(';')[:-1]]
+
+            # Perform tests
+            self.assertTrue(c2 ==  NFC(c1) ==  NFC(c2) ==  NFC(c3), line)
+            self.assertTrue(c4 ==  NFC(c4) ==  NFC(c5), line)
+            self.assertTrue(c3 ==  NFD(c1) ==  NFD(c2) ==  NFD(c3), line)
+            self.assertTrue(c5 ==  NFD(c4) ==  NFD(c5), line)
+            self.assertTrue(c4 == NFKC(c1) == NFKC(c2) == \
+                            NFKC(c3) == NFKC(c4) == NFKC(c5),
+                            line)
+            self.assertTrue(c5 == NFKD(c1) == NFKD(c2) == \
+                            NFKD(c3) == NFKD(c4) == NFKD(c5),
+                            line)
+
+            self.assertTrue(unicodedata.is_normalized("NFC", c2))
+            self.assertTrue(unicodedata.is_normalized("NFC", c4))
+
+            self.assertTrue(unicodedata.is_normalized("NFD", c3))
+            self.assertTrue(unicodedata.is_normalized("NFD", c5))
+
+            self.assertTrue(unicodedata.is_normalized("NFKC", c4))
+            self.assertTrue(unicodedata.is_normalized("NFKD", c5))
+
+            # Record part 1 data
+            if part == "@Part1":
+                part1_data[c1] = 1
+
+        # Perform tests for all other data
+        for c in range(sys.maxunicode+1):
+            X = chr(c)
+            if X in part1_data:
+                continue
+            self.assertTrue(X == NFC(X) == NFD(X) == NFKC(X) == NFKD(X), c)
+
+    def test_edge_cases(self):
+        self.assertRaises(TypeError, unicodedata.normalize)
+        self.assertRaises(ValueError, unicodedata.normalize, 'unknown', 'xx')
+        self.assertEqual(unicodedata.normalize('NFKC', ''), '')
+
+    def test_bug_834676(self):
+        # Check for bug 834676
+        unicodedata.normalize('NFC', '\ud55c\uae00')
+
+
 if __name__ == "__main__":
     unittest.main()

PCbuild/lib.pyproj

@@ -1191,7 +1191,6 @@
     <Compile Include="test\test_netrc.py" />
     <Compile Include="test\test_nis.py" />
     <Compile Include="test\test_nntplib.py" />
-    <Compile Include="test\test_normalization.py" />
     <Compile Include="test\test_ntpath.py" />
     <Compile Include="test\test_numeric_tower.py" />
     <Compile Include="test\test_opcodes.py" />