summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_normalization.py
blob: 664155473464e89b4e50e1a3e052cdaab4cd2f89 (plain)
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
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
from test.support import run_unittest, open_urlresource
import unittest

import sys
import os
from unicodedata import normalize, unidata_version

TESTDATAFILE = "NormalizationTest.txt"
TESTDATAURL = "http://www.unicode.org/Public/" + unidata_version + "/ucd/" + TESTDATAFILE

# Verify we have the correct version of the test data file.
TESTDATAPATH = os.path.join(os.path.dirname(__file__), "data", TESTDATAFILE)
if os.path.exists(TESTDATAPATH):
    f = open(TESTDATAPATH, encoding='utf-8')
    l = f.readline()
    f.close()
    if not unidata_version in l:
        os.unlink(testdatafile)

class RangeError(Exception):
    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 "".join([chr(x) for x in data])

class NormalizationTest(unittest.TestCase):
    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_bug_834676(self):
        # Check for bug 834676
        normalize('NFC', '\ud55c\uae00')


def test_main():
    run_unittest(NormalizationTest)

if __name__ == "__main__":
    test_main()