def test_main(self):
part1_data = {}
# Hit the exception early
try:
open_urlresource(TESTDATAURL, encoding="utf-8")
except IOError:
self.skipTest("Could not retrieve " + TESTDATAURL)
for line in open_urlresource(TESTDATAURL, encoding="utf-8"):
if '#' in line:
line = line.split('#')[0]
line = line.strip()
if not line:
continue
if line.startswith("@Part"):
part = line.split()[0]
continue
if part == "@Part3":
# XXX we don't support PRI #29 yet, so skip these tests for now
continue
try:
c1, c2, c3, c4, c5 = [unistr(x) for x in line.split(';')[:-1]]
except RangeError:
# Skip unsupported characters;
# try atleast adding c1 if we are in part1
if part == "@Part1":
try:
c1 = unistr(line.split(';')[0])
except RangeError:
pass
else:
part1_data[c1] = 1
continue
# 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)
# 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_main(self):
part1_data = {}
# Hit the exception early
try:
open_urlresource(TESTDATAURL, encoding="utf-8")
except IOError:
self.skipTest("Could not retrieve " + TESTDATAURL)
for line in open_urlresource(TESTDATAURL, encoding="utf-8"):
if '#' in line:
line = line.split('#')[0]
line = line.strip()
if not line:
continue
if line.startswith("@Part"):
part = line.split()[0]
continue
if part == "@Part3":
# XXX we don't support PRI #29 yet, so skip these tests for now
continue
try:
c1,c2,c3,c4,c5 = [unistr(x) for x in line.split(';')[:-1]]
except RangeError:
# Skip unsupported characters;
# try atleast adding c1 if we are in part1
if part == "@Part1":
try:
c1 = unistr(line.split(';')[0])
except RangeError:
pass
else:
part1_data[c1] = 1
continue
# 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)
# 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_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:
testdata = support.open_urlresource(url,
encoding="utf-8",
check=check_version)
except (OSError, HTTPException):
self.skipTest("Could not retrieve " + url)
self.addCleanup(testdata.close)
for line in testdata:
line = line.strip()
if not line or line.startswith('#'):
continue
seqname, codepoints = line.split(';')
codepoints = ''.join(chr(int(cp, 16)) for cp in codepoints.split())
self.assertEqual(unicodedata.lookup(seqname), codepoints)
with self.assertRaises(SyntaxError):
self.checkletter(seqname, None)
with self.assertRaises(KeyError):
unicodedata.ucd_3_2_0.lookup(seqname)
def read_vectors(hash_name):
with support.open_urlresource(URL.format(hash_name)) as f:
for line in f:
line = line.strip()
if line.startswith('#') or not line:
continue
parts = line.split(',')
parts[0] = bytes.fromhex(parts[0])
yield parts
def test_main(self):
# Hit the exception early
try:
testdata = open_urlresource(TESTDATAURL, encoding="utf-8",
check=check_version)
except (OSError, HTTPException):
self.fail(f"Could not retrieve {TESTDATAURL}")
with testdata:
self.run_normalization_tests(testdata)
def test_main(self):
# Hit the exception early
try:
testdata = open_urlresource(TESTDATAURL,
encoding="utf-8",
check=check_version)
except (OSError, HTTPException):
self.fail(f"Could not retrieve {TESTDATAURL}")
with testdata:
self.run_normalization_tests(testdata)
def test_main(self):
# Hit the exception early
try:
testdata = open_urlresource(TESTDATAURL, encoding="utf-8",
check=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 read_vectors(hash_name):
url = URL.format(hash_name)
try:
testdata = support.open_urlresource(url, encoding="utf-8")
except (OSError, HTTPException):
raise unittest.SkipTest("Could not retrieve {}".format(url))
with testdata:
for line in testdata:
line = line.strip()
if line.startswith('#') or not line:
continue
parts = line.split(',')
parts[0] = bytes.fromhex(parts[0])
yield parts
def read_vectors(hash_name):
url = URL.format(hash_name)
try:
testdata = support.open_urlresource(url)
except (OSError, HTTPException):
raise unittest.SkipTest("Could not retrieve {}".format(url))
with testdata:
for line in testdata:
line = line.strip()
if line.startswith('#') or not line:
continue
parts = line.split(',')
parts[0] = bytes.fromhex(parts[0])
yield parts
def test_main(self):
# Hit the exception early
try:
testdata = open_urlresource(TESTDATAURL,
encoding="utf-8",
check=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 test_main(self):
part = None
part1_data = {}
# Hit the exception early
try:
testdata = open_urlresource(TESTDATAURL, encoding="utf-8", check=check_version)
except (OSError, HTTPException):
self.skipTest("Could not retrieve " + TESTDATAURL)
self.addCleanup(testdata.close)
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
try:
c1, c2, c3, c4, c5 = [unistr(x) for x in line.split(";")[:-1]]
except RangeError:
# Skip unsupported characters;
# try at least adding c1 if we are in part1
if part == "@Part1":
try:
c1 = unistr(line.split(";")[0])
except RangeError:
pass
else:
part1_data[c1] = 1
continue
# 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)
# 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_main(self):
part = None
part1_data = {}
try:
testdata = open_urlresource(TESTDATAURL,
encoding='utf-8',
check=check_version)
except (OSError, HTTPException):
self.skipTest('Could not retrieve ' + TESTDATAURL)
self.addCleanup(testdata.close)
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
try:
c1, c2, c3, c4, c5 = [unistr(x) for x in line.split(';')[:-1]]
except RangeError:
if part == '@Part1':
try:
c1 = unistr(line.split(';')[0])
except RangeError:
pass
else:
part1_data[c1] = 1
continue
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)
if part == '@Part1':
part1_data[c1] = 1
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_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 test_named_sequences_full(self):
# Check all the named sequences
url = ("http://www.unicode.org/Public/%s/ucd/NamedSequences.txt" %
unicodedata.unidata_version)
try:
testdata = support.open_urlresource(url, encoding="utf-8",
check=check_version)
except (IOError, HTTPException):
self.skipTest("Could not retrieve " + url)
self.addCleanup(testdata.close)
for line in testdata:
line = line.strip()
if not line or line.startswith('#'):
continue
seqname, codepoints = line.split(';')
codepoints = ''.join(chr(int(cp, 16)) for cp in codepoints.split())
self.assertEqual(unicodedata.lookup(seqname), codepoints)
with self.assertRaises(SyntaxError):
self.checkletter(seqname, None)
with self.assertRaises(KeyError):
unicodedata.ucd_3_2_0.lookup(seqname)
def open_mapping_file(self):
return support.open_urlresource(self.mapfileurl)
def open_mapping_file(self):
return support.open_urlresource(self.mapfileurl)
def test_main():
# Hit the exception early
open_urlresource(TESTDATAURL)
run_unittest(NormalizationTest)
def test_main():
# Hit the exception early
open_urlresource(TESTDATAURL)
run_unittest(NormalizationTest)
def open_mapping_file(self):
return support.open_urlresource(self.mapfileurl, encoding="utf-8")
