Python code coverage for Lib/test/test_ucn.py

#	count	content
1	n/a	""" Test script for the Unicode implementation.
2	n/a
3	n/a	Written by Bill Tutt.
4	n/a	Modified for Python 2.0 by Fredrik Lundh (fredrik@pythonware.com)
5	n/a
6	n/a	(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
7	n/a
8	n/a	"""#"
9	n/a
10	n/a	import unittest
11	n/a	import unicodedata
12	n/a
13	n/a	from test import support
14	n/a	from http.client import HTTPException
15	n/a	from test.test_normalization import check_version
16	n/a
17	n/a	try:
18	n/a	from _testcapi import INT_MAX, PY_SSIZE_T_MAX, UINT_MAX
19	n/a	except ImportError:
20	n/a	INT_MAX = PY_SSIZE_T_MAX = UINT_MAX = 2**64 - 1
21	n/a
22	n/a	class UnicodeNamesTest(unittest.TestCase):
23	n/a
24	n/a	def checkletter(self, name, code):
25	n/a	# Helper that put all \N escapes inside eval'd raw strings,
26	n/a	# to make sure this script runs even if the compiler
27	n/a	# chokes on \N escapes
28	n/a	res = eval(r'"\N{%s}"' % name)
29	n/a	self.assertEqual(res, code)
30	n/a	return res
31	n/a
32	n/a	def test_general(self):
33	n/a	# General and case insensitivity test:
34	n/a	chars = [
35	n/a	"LATIN CAPITAL LETTER T",
36	n/a	"LATIN SMALL LETTER H",
37	n/a	"LATIN SMALL LETTER E",
38	n/a	"SPACE",
39	n/a	"LATIN SMALL LETTER R",
40	n/a	"LATIN CAPITAL LETTER E",
41	n/a	"LATIN SMALL LETTER D",
42	n/a	"SPACE",
43	n/a	"LATIN SMALL LETTER f",
44	n/a	"LATIN CAPITAL LeTtEr o",
45	n/a	"LATIN SMaLl LETTER x",
46	n/a	"SPACE",
47	n/a	"LATIN SMALL LETTER A",
48	n/a	"LATIN SMALL LETTER T",
49	n/a	"LATIN SMALL LETTER E",
50	n/a	"SPACE",
51	n/a	"LATIN SMALL LETTER T",
52	n/a	"LATIN SMALL LETTER H",
53	n/a	"LATIN SMALL LETTER E",
54	n/a	"SpAcE",
55	n/a	"LATIN SMALL LETTER S",
56	n/a	"LATIN SMALL LETTER H",
57	n/a	"LATIN small LETTER e",
58	n/a	"LATIN small LETTER e",
59	n/a	"LATIN SMALL LETTER P",
60	n/a	"FULL STOP"
61	n/a	]
62	n/a	string = "The rEd fOx ate the sheep."
63	n/a
64	n/a	self.assertEqual(
65	n/a	"".join([self.checkletter(*args) for args in zip(chars, string)]),
66	n/a	string
67	n/a	)
68	n/a
69	n/a	def test_ascii_letters(self):
70	n/a	for char in "".join(map(chr, range(ord("a"), ord("z")))):
71	n/a	name = "LATIN SMALL LETTER %s" % char.upper()
72	n/a	code = unicodedata.lookup(name)
73	n/a	self.assertEqual(unicodedata.name(code), name)
74	n/a
75	n/a	def test_hangul_syllables(self):
76	n/a	self.checkletter("HANGUL SYLLABLE GA", "\uac00")
77	n/a	self.checkletter("HANGUL SYLLABLE GGWEOSS", "\uafe8")
78	n/a	self.checkletter("HANGUL SYLLABLE DOLS", "\ub3d0")
79	n/a	self.checkletter("HANGUL SYLLABLE RYAN", "\ub7b8")
80	n/a	self.checkletter("HANGUL SYLLABLE MWIK", "\ubba0")
81	n/a	self.checkletter("HANGUL SYLLABLE BBWAEM", "\ubf88")
82	n/a	self.checkletter("HANGUL SYLLABLE SSEOL", "\uc370")
83	n/a	self.checkletter("HANGUL SYLLABLE YI", "\uc758")
84	n/a	self.checkletter("HANGUL SYLLABLE JJYOSS", "\ucb40")
85	n/a	self.checkletter("HANGUL SYLLABLE KYEOLS", "\ucf28")
86	n/a	self.checkletter("HANGUL SYLLABLE PAN", "\ud310")
87	n/a	self.checkletter("HANGUL SYLLABLE HWEOK", "\ud6f8")
88	n/a	self.checkletter("HANGUL SYLLABLE HIH", "\ud7a3")
89	n/a
90	n/a	self.assertRaises(ValueError, unicodedata.name, "\ud7a4")
91	n/a
92	n/a	def test_cjk_unified_ideographs(self):
93	n/a	self.checkletter("CJK UNIFIED IDEOGRAPH-3400", "\u3400")
94	n/a	self.checkletter("CJK UNIFIED IDEOGRAPH-4DB5", "\u4db5")
95	n/a	self.checkletter("CJK UNIFIED IDEOGRAPH-4E00", "\u4e00")
96	n/a	self.checkletter("CJK UNIFIED IDEOGRAPH-9FCB", "\u9fCB")
97	n/a	self.checkletter("CJK UNIFIED IDEOGRAPH-20000", "\U00020000")
98	n/a	self.checkletter("CJK UNIFIED IDEOGRAPH-2A6D6", "\U0002a6d6")
99	n/a	self.checkletter("CJK UNIFIED IDEOGRAPH-2A700", "\U0002A700")
100	n/a	self.checkletter("CJK UNIFIED IDEOGRAPH-2B734", "\U0002B734")
101	n/a	self.checkletter("CJK UNIFIED IDEOGRAPH-2B740", "\U0002B740")
102	n/a	self.checkletter("CJK UNIFIED IDEOGRAPH-2B81D", "\U0002B81D")
103	n/a
104	n/a	def test_bmp_characters(self):
105	n/a	for code in range(0x10000):
106	n/a	char = chr(code)
107	n/a	name = unicodedata.name(char, None)
108	n/a	if name is not None:
109	n/a	self.assertEqual(unicodedata.lookup(name), char)
110	n/a
111	n/a	def test_misc_symbols(self):
112	n/a	self.checkletter("PILCROW SIGN", "\u00b6")
113	n/a	self.checkletter("REPLACEMENT CHARACTER", "\uFFFD")
114	n/a	self.checkletter("HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK", "\uFF9F")
115	n/a	self.checkletter("FULLWIDTH LATIN SMALL LETTER A", "\uFF41")
116	n/a
117	n/a	def test_aliases(self):
118	n/a	# Check that the aliases defined in the NameAliases.txt file work.
119	n/a	# This should be updated when new aliases are added or the file
120	n/a	# should be downloaded and parsed instead. See #12753.
121	n/a	aliases = [
122	n/a	('LATIN CAPITAL LETTER GHA', 0x01A2),
123	n/a	('LATIN SMALL LETTER GHA', 0x01A3),
124	n/a	('KANNADA LETTER LLLA', 0x0CDE),
125	n/a	('LAO LETTER FO FON', 0x0E9D),
126	n/a	('LAO LETTER FO FAY', 0x0E9F),
127	n/a	('LAO LETTER RO', 0x0EA3),
128	n/a	('LAO LETTER LO', 0x0EA5),
129	n/a	('TIBETAN MARK BKA- SHOG GI MGO RGYAN', 0x0FD0),
130	n/a	('YI SYLLABLE ITERATION MARK', 0xA015),
131	n/a	('PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRACKET', 0xFE18),
132	n/a	('BYZANTINE MUSICAL SYMBOL FTHORA SKLIRON CHROMA VASIS', 0x1D0C5)
133	n/a	]
134	n/a	for alias, codepoint in aliases:
135	n/a	self.checkletter(alias, chr(codepoint))
136	n/a	name = unicodedata.name(chr(codepoint))
137	n/a	self.assertNotEqual(name, alias)
138	n/a	self.assertEqual(unicodedata.lookup(alias),
139	n/a	unicodedata.lookup(name))
140	n/a	with self.assertRaises(KeyError):
141	n/a	unicodedata.ucd_3_2_0.lookup(alias)
142	n/a
143	n/a	def test_aliases_names_in_pua_range(self):
144	n/a	# We are storing aliases in the PUA 15, but their names shouldn't leak
145	n/a	for cp in range(0xf0000, 0xf0100):
146	n/a	with self.assertRaises(ValueError) as cm:
147	n/a	unicodedata.name(chr(cp))
148	n/a	self.assertEqual(str(cm.exception), 'no such name')
149	n/a
150	n/a	def test_named_sequences_names_in_pua_range(self):
151	n/a	# We are storing named seq in the PUA 15, but their names shouldn't leak
152	n/a	for cp in range(0xf0100, 0xf0fff):
153	n/a	with self.assertRaises(ValueError) as cm:
154	n/a	unicodedata.name(chr(cp))
155	n/a	self.assertEqual(str(cm.exception), 'no such name')
156	n/a
157	n/a	def test_named_sequences_sample(self):
158	n/a	# Check a few named sequences. See #12753.
159	n/a	sequences = [
160	n/a	('LATIN SMALL LETTER R WITH TILDE', '\u0072\u0303'),
161	n/a	('TAMIL SYLLABLE SAI', '\u0BB8\u0BC8'),
162	n/a	('TAMIL SYLLABLE MOO', '\u0BAE\u0BCB'),
163	n/a	('TAMIL SYLLABLE NNOO', '\u0BA3\u0BCB'),
164	n/a	('TAMIL CONSONANT KSS', '\u0B95\u0BCD\u0BB7\u0BCD'),
165	n/a	]
166	n/a	for seqname, codepoints in sequences:
167	n/a	self.assertEqual(unicodedata.lookup(seqname), codepoints)
168	n/a	with self.assertRaises(SyntaxError):
169	n/a	self.checkletter(seqname, None)
170	n/a	with self.assertRaises(KeyError):
171	n/a	unicodedata.ucd_3_2_0.lookup(seqname)
172	n/a
173	n/a	def test_named_sequences_full(self):
174	n/a	# Check all the named sequences
175	n/a	url = ("http://www.pythontest.net/unicode/%s/NamedSequences.txt" %
176	n/a	unicodedata.unidata_version)
177	n/a	try:
178	n/a	testdata = support.open_urlresource(url, encoding="utf-8",
179	n/a	check=check_version)
180	n/a	except (OSError, HTTPException):
181	n/a	self.skipTest("Could not retrieve " + url)
182	n/a	self.addCleanup(testdata.close)
183	n/a	for line in testdata:
184	n/a	line = line.strip()
185	n/a	if not line or line.startswith('#'):
186	n/a	continue
187	n/a	seqname, codepoints = line.split(';')
188	n/a	codepoints = ''.join(chr(int(cp, 16)) for cp in codepoints.split())
189	n/a	self.assertEqual(unicodedata.lookup(seqname), codepoints)
190	n/a	with self.assertRaises(SyntaxError):
191	n/a	self.checkletter(seqname, None)
192	n/a	with self.assertRaises(KeyError):
193	n/a	unicodedata.ucd_3_2_0.lookup(seqname)
194	n/a
195	n/a	def test_errors(self):
196	n/a	self.assertRaises(TypeError, unicodedata.name)
197	n/a	self.assertRaises(TypeError, unicodedata.name, 'xx')
198	n/a	self.assertRaises(TypeError, unicodedata.lookup)
199	n/a	self.assertRaises(KeyError, unicodedata.lookup, 'unknown')
200	n/a
201	n/a	def test_strict_error_handling(self):
202	n/a	# bogus character name
203	n/a	self.assertRaises(
204	n/a	UnicodeError,
205	n/a	str, b"\\N{blah}", 'unicode-escape', 'strict'
206	n/a	)
207	n/a	# long bogus character name
208	n/a	self.assertRaises(
209	n/a	UnicodeError,
210	n/a	str, bytes("\\N{%s}" % ("x" * 100000), "ascii"), 'unicode-escape', 'strict'
211	n/a	)
212	n/a	# missing closing brace
213	n/a	self.assertRaises(
214	n/a	UnicodeError,
215	n/a	str, b"\\N{SPACE", 'unicode-escape', 'strict'
216	n/a	)
217	n/a	# missing opening brace
218	n/a	self.assertRaises(
219	n/a	UnicodeError,
220	n/a	str, b"\\NSPACE", 'unicode-escape', 'strict'
221	n/a	)
222	n/a
223	n/a	@support.cpython_only
224	n/a	@unittest.skipUnless(INT_MAX < PY_SSIZE_T_MAX, "needs UINT_MAX < SIZE_MAX")
225	n/a	@support.bigmemtest(size=UINT_MAX + 1, memuse=2 + 1, dry_run=False)
226	n/a	def test_issue16335(self, size):
227	n/a	# very very long bogus character name
228	n/a	x = b'\\N{SPACE' + b'x' * (UINT_MAX + 1) + b'}'
229	n/a	self.assertEqual(len(x), len(b'\\N{SPACE}') + (UINT_MAX + 1))
230	n/a	self.assertRaisesRegex(UnicodeError,
231	n/a	'unknown Unicode character name',
232	n/a	x.decode, 'unicode-escape'
233	n/a	)
234	n/a
235	n/a
236	n/a	if __name__ == "__main__":
237	n/a	unittest.main()