summaryrefslogtreecommitdiff
path: root/vendor/golang.org/x/text/encoding/unicode/utf32/utf32_test.go
blob: cd6158e5ead6d71d21da5478b77a7842eefd1251 (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
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
// Copyright 2016 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package utf32

import (
	"testing"

	"golang.org/x/text/encoding"
	"golang.org/x/text/encoding/internal/enctest"
	"golang.org/x/text/transform"
)

var (
	utf32LEIB = UTF32(LittleEndian, IgnoreBOM) // UTF-32LE (atypical interpretation)
	utf32LEUB = UTF32(LittleEndian, UseBOM)    // UTF-32, LE
	//	utf32LEEB = UTF32(LittleEndian, ExpectBOM) // UTF-32, LE, Expect - covered in encoding_test.go
	utf32BEIB = UTF32(BigEndian, IgnoreBOM) // UTF-32BE (atypical interpretation)
	utf32BEUB = UTF32(BigEndian, UseBOM)    // UTF-32 default
	utf32BEEB = UTF32(BigEndian, ExpectBOM) // UTF-32 Expect
)

func TestBasics(t *testing.T) {
	testCases := []struct {
		e         encoding.Encoding
		encPrefix string
		encSuffix string
		encoded   string
		utf8      string
	}{{
		e:       utf32BEIB,
		encoded: "\x00\x00\x00\x57\x00\x00\x00\xe4\x00\x01\xd5\x65",
		utf8:    "\x57\u00e4\U0001d565",
	}, {
		e:         UTF32(BigEndian, ExpectBOM),
		encPrefix: "\x00\x00\xfe\xff",
		encoded:   "\x00\x00\x00\x57\x00\x00\x00\xe4\x00\x01\xd5\x65",
		utf8:      "\x57\u00e4\U0001d565",
	}, {
		e:       UTF32(LittleEndian, IgnoreBOM),
		encoded: "\x57\x00\x00\x00\xe4\x00\x00\x00\x65\xd5\x01\x00",
		utf8:    "\x57\u00e4\U0001d565",
	}, {
		e:         UTF32(LittleEndian, ExpectBOM),
		encPrefix: "\xff\xfe\x00\x00",
		encoded:   "\x57\x00\x00\x00\xe4\x00\x00\x00\x65\xd5\x01\x00",
		utf8:      "\x57\u00e4\U0001d565",
	}}

	for _, tc := range testCases {
		enctest.TestEncoding(t, tc.e, tc.encoded, tc.utf8, tc.encPrefix, tc.encSuffix)
	}
}

func TestFiles(t *testing.T) { enctest.TestFile(t, utf32BEIB) }

func BenchmarkEncoding(b *testing.B) { enctest.Benchmark(b, utf32BEIB) }

func TestUTF32(t *testing.T) {
	testCases := []struct {
		desc    string
		src     string
		notEOF  bool // the inverse of atEOF
		sizeDst int
		want    string
		nSrc    int
		err     error
		t       transform.Transformer
	}{{
		desc: "utf-32 IgnoreBOM dec: empty string",
		t:    utf32BEIB.NewDecoder(),
	}, {
		desc: "utf-32 UseBOM dec: empty string",
		t:    utf32BEUB.NewDecoder(),
	}, {
		desc: "utf-32 ExpectBOM dec: empty string",
		err:  ErrMissingBOM,
		t:    utf32BEEB.NewDecoder(),
	}, {
		desc:    "utf-32be dec: Doesn't interpret U+FEFF as BOM",
		src:     "\x00\x00\xFE\xFF\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
		sizeDst: 100,
		want:    "\uFEFF\U00012345=Ra",
		nSrc:    20,
		t:       utf32BEIB.NewDecoder(),
	}, {
		desc:    "utf-32be dec: Interprets little endian U+FEFF as invalid",
		src:     "\xFF\xFE\x00\x00\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
		sizeDst: 100,
		want:    "\uFFFD\U00012345=Ra",
		nSrc:    20,
		t:       utf32BEIB.NewDecoder(),
	}, {
		desc:    "utf-32le dec: Doesn't interpret U+FEFF as BOM",
		src:     "\xFF\xFE\x00\x00\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
		sizeDst: 100,
		want:    "\uFEFF\U00012345=Ra",
		nSrc:    20,
		t:       utf32LEIB.NewDecoder(),
	}, {
		desc:    "utf-32le dec: Interprets big endian U+FEFF as invalid",
		src:     "\x00\x00\xFE\xFF\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
		sizeDst: 100,
		want:    "\uFFFD\U00012345=Ra",
		nSrc:    20,
		t:       utf32LEIB.NewDecoder(),
	}, {
		desc:    "utf-32 enc: Writes big-endian BOM",
		src:     "\U00012345=Ra",
		sizeDst: 100,
		want:    "\x00\x00\xFE\xFF\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
		nSrc:    7,
		t:       utf32BEUB.NewEncoder(),
	}, {
		desc:    "utf-32 enc: Writes little-endian BOM",
		src:     "\U00012345=Ra",
		sizeDst: 100,
		want:    "\xFF\xFE\x00\x00\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
		nSrc:    7,
		t:       utf32LEUB.NewEncoder(),
	}, {
		desc:    "utf-32 dec: Interprets text using big-endian default when BOM not present",
		src:     "\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
		sizeDst: 100,
		want:    "\U00012345=Ra",
		nSrc:    16,
		t:       utf32BEUB.NewDecoder(),
	}, {
		desc:    "utf-32 dec: Interprets text using little-endian default when BOM not present",
		src:     "\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
		sizeDst: 100,
		want:    "\U00012345=Ra",
		nSrc:    16,
		t:       utf32LEUB.NewDecoder(),
	}, {
		desc:    "utf-32 dec: BOM determines encoding BE",
		src:     "\x00\x00\xFE\xFF\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
		sizeDst: 100,
		want:    "\U00012345=Ra",
		nSrc:    20,
		t:       utf32BEUB.NewDecoder(),
	}, {
		desc:    "utf-32 dec: BOM determines encoding LE",
		src:     "\xFF\xFE\x00\x00\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
		sizeDst: 100,
		want:    "\U00012345=Ra",
		nSrc:    20,
		t:       utf32LEUB.NewDecoder(),
	}, {
		desc:    "utf-32 dec: BOM determines encoding LE, change default",
		src:     "\xFF\xFE\x00\x00\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
		sizeDst: 100,
		want:    "\U00012345=Ra",
		nSrc:    20,
		t:       utf32BEUB.NewDecoder(),
	}, {
		desc:    "utf-32 dec: BOM determines encoding BE, change default",
		src:     "\x00\x00\xFE\xFF\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
		sizeDst: 100,
		want:    "\U00012345=Ra",
		nSrc:    20,
		t:       utf32LEUB.NewDecoder(),
	}, {
		desc:    "utf-32 dec: Don't change big-endian byte order mid-stream",
		src:     "\x00\x01\x23\x45\x00\x00\x00\x3D\xFF\xFE\x00\x00\x00\x00\xFE\xFF\x00\x00\x00\x52\x00\x00\x00\x61",
		sizeDst: 100,
		want:    "\U00012345=\uFFFD\uFEFFRa",
		nSrc:    24,
		t:       utf32BEUB.NewDecoder(),
	}, {
		desc:    "utf-32 dec: Don't change little-endian byte order mid-stream",
		src:     "\x45\x23\x01\x00\x3D\x00\x00\x00\x00\x00\xFE\xFF\xFF\xFE\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
		sizeDst: 100,
		want:    "\U00012345=\uFFFD\uFEFFRa",
		nSrc:    24,
		t:       utf32LEUB.NewDecoder(),
	}, {
		desc:    "utf-32 dec: Fail on missing BOM when required",
		src:     "\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
		sizeDst: 100,
		want:    "",
		nSrc:    0,
		err:     ErrMissingBOM,
		t:       utf32BEEB.NewDecoder(),
	}, {
		desc:    "utf-32 enc: Short dst",
		src:     "\U00012345=Ra",
		sizeDst: 15,
		want:    "\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52",
		nSrc:    6,
		err:     transform.ErrShortDst,
		t:       utf32BEIB.NewEncoder(),
	}, {
		desc:    "utf-32 enc: Short src",
		src:     "\U00012345=Ra\xC2",
		notEOF:  true,
		sizeDst: 100,
		want:    "\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
		nSrc:    7,
		err:     transform.ErrShortSrc,
		t:       utf32BEIB.NewEncoder(),
	}, {
		desc:    "utf-32 enc: Invalid input",
		src:     "\x80\xC1\xC2\x7F\xC2",
		sizeDst: 100,
		want:    "\x00\x00\xFF\xFD\x00\x00\xFF\xFD\x00\x00\xFF\xFD\x00\x00\x00\x7F\x00\x00\xFF\xFD",
		nSrc:    5,
		t:       utf32BEIB.NewEncoder(),
	}, {
		desc:    "utf-32 dec: Short dst",
		src:     "\x00\x00\x00\x41",
		sizeDst: 0,
		want:    "",
		nSrc:    0,
		err:     transform.ErrShortDst,
		t:       utf32BEIB.NewDecoder(),
	}, {
		desc:    "utf-32 dec: Short src",
		src:     "\x00\x00\x00",
		notEOF:  true,
		sizeDst: 4,
		want:    "",
		nSrc:    0,
		err:     transform.ErrShortSrc,
		t:       utf32BEIB.NewDecoder(),
	}, {
		desc:    "utf-32 dec: Invalid input",
		src:     "\x00\x00\xD8\x00\x00\x00\xDF\xFF\x00\x11\x00\x00\x00\x00\x00",
		sizeDst: 100,
		want:    "\uFFFD\uFFFD\uFFFD\uFFFD",
		nSrc:    15,
		t:       utf32BEIB.NewDecoder(),
	}}
	for i, tc := range testCases {
		b := make([]byte, tc.sizeDst)
		nDst, nSrc, err := tc.t.Transform(b, []byte(tc.src), !tc.notEOF)
		if err != tc.err {
			t.Errorf("%d:%s: error was %v; want %v", i, tc.desc, err, tc.err)
		}
		if got := string(b[:nDst]); got != tc.want {
			t.Errorf("%d:%s: result was %q: want %q", i, tc.desc, got, tc.want)
		}
		if nSrc != tc.nSrc {
			t.Errorf("%d:%s: nSrc was %d; want %d", i, tc.desc, nSrc, tc.nSrc)
		}
	}
}