1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
|
from test.test_support import verbose, TestFailed, TestSkipped, verify
import sys
from unicodedata import normalize
try:
data = open("NormalizationTest.txt","r").readlines()
except IOError:
raise TestSkipped("NormalizationTest.txt not found, download from http://www.unicode.org/Public/UNIDATA/NormalizationTest.txt")
class RangeError:
pass
def NFC(str):
return normalize("NFC", str)
def NFKC(str):
return normalize("NFKC", str)
def NFD(str):
return normalize("NFD", str)
def NFKD(str):
return normalize("NFKD", str)
def unistr(data):
data = [int(x, 16) for x in data.split(" ")]
for x in data:
if x > sys.maxunicode:
raise RangeError
return u"".join([unichr(x) for x in data])
part1_data = {}
for line in data:
if '#' in line:
line = line.split('#')[0]
line = line.strip()
if not line:
continue
if line.startswith("@Part"):
part = line
continue
try:
c1,c2,c3,c4,c5 = [unistr(x) for x in line.split(';')[:-1]]
except RangeError:
# Skip unsupported characters
continue
if verbose:
print line
# Perform tests
verify(c2 == NFC(c1) == NFC(c2) == NFC(c3), line)
verify(c4 == NFC(c4) == NFC(c5), line)
verify(c3 == NFD(c1) == NFD(c2) == NFD(c3), line)
verify(c5 == NFD(c4) == NFD(c5), line)
verify(c4 == NFKC(c1) == NFKC(c2) == NFKC(c3) == NFKC(c4) == NFKC(c5), line)
verify(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 = unichr(c)
if X in part1_data:
continue
assert X == NFC(X) == NFD(X) == NFKC(X) == NFKD(X), c
|