summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_multibytecodec_support.py
blob: 45a63e7af81e02163b16df5099cf45a4014a9c4a (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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
#!/usr/bin/env python
#
# test_multibytecodec_support.py
#   Common Unittest Routines for CJK codecs
#
# $CJKCodecs: test_multibytecodec_support.py,v 1.6 2004/06/19 06:09:55 perky Exp $

import sys, codecs, os.path
import unittest
from test import test_support
from StringIO import StringIO

__cjkcodecs__ = 0 # define this as 0 for python

class TestBase:
    encoding        = ''   # codec name
    codec           = None # codec tuple (with 4 elements)
    tstring         = ''   # string to test StreamReader

    codectests      = None # must set. codec test tuple
    roundtriptest   = 1    # set if roundtrip is possible with unicode
    has_iso10646    = 0    # set if this encoding contains whole iso10646 map
    xmlcharnametest = None # string to test xmlcharrefreplace

    def setUp(self):
        if self.codec is None:
            self.codec = codecs.lookup(self.encoding)
        self.encode, self.decode, self.reader, self.writer = self.codec

    def test_chunkcoding(self):
        for native, utf8 in zip(*[StringIO(f).readlines()
                                  for f in self.tstring]):
            u = self.decode(native)[0]
            self.assertEqual(u, utf8.decode('utf-8'))
            if self.roundtriptest:
                self.assertEqual(native, self.encode(u)[0])

    def test_errorhandle(self):
        for source, scheme, expected in self.codectests:
            if type(source) == type(''):
                func = self.decode
            else:
                func = self.encode
            if expected:
                result = func(source, scheme)[0]
                self.assertEqual(result, expected)
            else:
                self.assertRaises(UnicodeError, func, source, scheme)

    if sys.hexversion >= 0x02030000:
        def test_xmlcharrefreplace(self):
            if self.has_iso10646:
                return

            s = u"\u0b13\u0b23\u0b60 nd eggs"
            self.assertEqual(
                self.encode(s, "xmlcharrefreplace")[0],
                "ଓଣୠ nd eggs"
            )

        def test_customreplace(self):
            if self.has_iso10646:
                return

            import htmlentitydefs

            names = {}
            for (key, value) in htmlentitydefs.entitydefs.items():
                if len(value)==1:
                    names[value.decode('latin-1')] = self.decode(key)[0]
                else:
                    names[unichr(int(value[2:-1]))] = self.decode(key)[0]

            def xmlcharnamereplace(exc):
                if not isinstance(exc, UnicodeEncodeError):
                    raise TypeError("don't know how to handle %r" % exc)
                l = []
                for c in exc.object[exc.start:exc.end]:
                    try:
                        l.append(u"&%s;" % names[c])
                    except KeyError:
                        l.append(u"&#%d;" % ord(c))
                return (u"".join(l), exc.end)

            codecs.register_error(
                "test.xmlcharnamereplace", xmlcharnamereplace)

            if self.xmlcharnametest:
                sin, sout = self.xmlcharnametest
            else:
                sin = u"\xab\u211c\xbb = \u2329\u1234\u232a"
                sout = "«ℜ» = ⟨ሴ⟩"
            self.assertEqual(self.encode(sin,
                                        "test.xmlcharnamereplace")[0], sout)

    def test_streamreader(self):
        UTF8Writer = codecs.getwriter('utf-8')
        for name in ["read", "readline", "readlines"]:
            for sizehint in [None, -1] + range(1, 33) + \
                            [64, 128, 256, 512, 1024]:
                istream = self.reader(StringIO(self.tstring[0]))
                ostream = UTF8Writer(StringIO())
                func = getattr(istream, name)
                while 1:
                    data = func(sizehint)
                    if not data:
                        break
                    if name == "readlines":
                        ostream.writelines(data)
                    else:
                        ostream.write(data)

                self.assertEqual(ostream.getvalue(), self.tstring[1])

    def test_streamwriter(self):
        if __cjkcodecs__:
            readfuncs = ('read', 'readline', 'readlines')
        else:
            # standard utf8 codec has broken readline and readlines.
            readfuncs = ('read',)
        UTF8Reader = codecs.getreader('utf-8')
        for name in readfuncs:
            for sizehint in [None] + range(1, 33) + \
                            [64, 128, 256, 512, 1024]:
                istream = UTF8Reader(StringIO(self.tstring[1]))
                ostream = self.writer(StringIO())
                func = getattr(istream, name)
                while 1:
                    if sizehint is not None:
                        data = func(sizehint)
                    else:
                        data = func()

                    if not data:
                        break
                    if name == "readlines":
                        ostream.writelines(data)
                    else:
                        ostream.write(data)

                self.assertEqual(ostream.getvalue(), self.tstring[0])

if len(u'\U00012345') == 2: # ucs2 build
    _unichr = unichr
    def unichr(v):
        if v >= 0x10000:
            return _unichr(0xd800 + ((v - 0x10000) >> 10)) + \
                   _unichr(0xdc00 + ((v - 0x10000) & 0x3ff))
        else:
            return _unichr(v)
    _ord = ord
    def ord(c):
        if len(c) == 2:
            return 0x10000 + ((_ord(c[0]) - 0xd800) << 10) + \
                          (ord(c[1]) - 0xdc00)
        else:
            return _ord(c)

class TestBase_Mapping(unittest.TestCase):
    pass_enctest = []
    pass_dectest = []
    supmaps = []

    def __init__(self, *args, **kw):
        unittest.TestCase.__init__(self, *args, **kw)
        self.open_mapping_file() # test it to report the error early

    def open_mapping_file(self):
        return test_support.open_urlresource(self.mapfileurl)

    def test_mapping_file(self):
        unichrs = lambda s: u''.join(map(unichr, map(eval, s.split('+'))))
        urt_wa = {}

        for line in self.open_mapping_file():
            if not line:
                break
            data = line.split('#')[0].strip().split()
            if len(data) != 2:
                continue

            csetval = eval(data[0])
            if csetval <= 0x7F:
                csetch = chr(csetval & 0xff)
            elif csetval >= 0x1000000:
                csetch = chr(csetval >> 24) + chr((csetval >> 16) & 0xff) + \
                         chr((csetval >> 8) & 0xff) + chr(csetval & 0xff)
            elif csetval >= 0x10000:
                csetch = chr(csetval >> 16) + \
                         chr((csetval >> 8) & 0xff) + chr(csetval & 0xff)
            elif csetval >= 0x100:
                csetch = chr(csetval >> 8) + chr(csetval & 0xff)
            else:
                continue

            unich = unichrs(data[1])
            if ord(unich) == 0xfffd or urt_wa.has_key(unich):
                continue
            urt_wa[unich] = csetch

            self._testpoint(csetch, unich)

    def test_mapping_supplemental(self):
        for mapping in self.supmaps:
            self._testpoint(*mapping)

    def _testpoint(self, csetch, unich):
        if (csetch, unich) not in self.pass_enctest:
            self.assertEqual(unich.encode(self.encoding), csetch)
        if (csetch, unich) not in self.pass_dectest:
            self.assertEqual(unicode(csetch, self.encoding), unich)

def load_teststring(encoding):
    if __cjkcodecs__:
        etxt = open(os.path.join('sampletexts', encoding) + '.txt').read()
        utxt = open(os.path.join('sampletexts', encoding) + '.utf8').read()
        return (etxt, utxt)
    else:
        from test import cjkencodings_test
        return cjkencodings_test.teststring[encoding]