vendor/golang.org/x/text/encoding/unicode/utf32/utf32_test.go

   1 // Copyright 2016 The Go Authors. All rights reserved.
   2 // Use of this source code is governed by a BSD-style
   3 // license that can be found in the LICENSE file.
   4
   5 package utf32
   6
   7 import (
   8         "testing"
   9
  10         "golang.org/x/text/encoding"
  11         "golang.org/x/text/encoding/internal/enctest"
  12         "golang.org/x/text/transform"
  13 )
  14
  15 var (
  16         utf32LEIB = UTF32(LittleEndian, IgnoreBOM) // UTF-32LE (atypical interpretation)
  17         utf32LEUB = UTF32(LittleEndian, UseBOM)    // UTF-32, LE
  18         //      utf32LEEB = UTF32(LittleEndian, ExpectBOM) // UTF-32, LE, Expect - covered in encoding_test.go
  19         utf32BEIB = UTF32(BigEndian, IgnoreBOM) // UTF-32BE (atypical interpretation)
  20         utf32BEUB = UTF32(BigEndian, UseBOM)    // UTF-32 default
  21         utf32BEEB = UTF32(BigEndian, ExpectBOM) // UTF-32 Expect
  22 )
  23
  24 func TestBasics(t *testing.T) {
  25         testCases := []struct {
  26                 e         encoding.Encoding
  27                 encPrefix string
  28                 encSuffix string
  29                 encoded   string
  30                 utf8      string
  31         }{{
  32                 e:       utf32BEIB,
  33                 encoded: "\x00\x00\x00\x57\x00\x00\x00\xe4\x00\x01\xd5\x65",
  34                 utf8:    "\x57\u00e4\U0001d565",
  35         }, {
  36                 e:         UTF32(BigEndian, ExpectBOM),
  37                 encPrefix: "\x00\x00\xfe\xff",
  38                 encoded:   "\x00\x00\x00\x57\x00\x00\x00\xe4\x00\x01\xd5\x65",
  39                 utf8:      "\x57\u00e4\U0001d565",
  40         }, {
  41                 e:       UTF32(LittleEndian, IgnoreBOM),
  42                 encoded: "\x57\x00\x00\x00\xe4\x00\x00\x00\x65\xd5\x01\x00",
  43                 utf8:    "\x57\u00e4\U0001d565",
  44         }, {
  45                 e:         UTF32(LittleEndian, ExpectBOM),
  46                 encPrefix: "\xff\xfe\x00\x00",
  47                 encoded:   "\x57\x00\x00\x00\xe4\x00\x00\x00\x65\xd5\x01\x00",
  48                 utf8:      "\x57\u00e4\U0001d565",
  49         }}
  50
  51         for _, tc := range testCases {
  52                 enctest.TestEncoding(t, tc.e, tc.encoded, tc.utf8, tc.encPrefix, tc.encSuffix)
  53         }
  54 }
  55
  56 func TestFiles(t *testing.T) { enctest.TestFile(t, utf32BEIB) }
  57
  58 func BenchmarkEncoding(b *testing.B) { enctest.Benchmark(b, utf32BEIB) }
  59
  60 func TestUTF32(t *testing.T) {
  61         testCases := []struct {
  62                 desc    string
  63                 src     string
  64                 notEOF  bool // the inverse of atEOF
  65                 sizeDst int
  66                 want    string
  67                 nSrc    int
  68                 err     error
  69                 t       transform.Transformer
  70         }{{
  71                 desc: "utf-32 IgnoreBOM dec: empty string",
  72                 t:    utf32BEIB.NewDecoder(),
  73         }, {
  74                 desc: "utf-32 UseBOM dec: empty string",
  75                 t:    utf32BEUB.NewDecoder(),
  76         }, {
  77                 desc: "utf-32 ExpectBOM dec: empty string",
  78                 err:  ErrMissingBOM,
  79                 t:    utf32BEEB.NewDecoder(),
  80         }, {
  81                 desc:    "utf-32be dec: Doesn't interpret U+FEFF as BOM",
  82                 src:     "\x00\x00\xFE\xFF\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
  83                 sizeDst: 100,
  84                 want:    "\uFEFF\U00012345=Ra",
  85                 nSrc:    20,
  86                 t:       utf32BEIB.NewDecoder(),
  87         }, {
  88                 desc:    "utf-32be dec: Interprets little endian U+FEFF as invalid",
  89                 src:     "\xFF\xFE\x00\x00\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
  90                 sizeDst: 100,
  91                 want:    "\uFFFD\U00012345=Ra",
  92                 nSrc:    20,
  93                 t:       utf32BEIB.NewDecoder(),
  94         }, {
  95                 desc:    "utf-32le dec: Doesn't interpret U+FEFF as BOM",
  96                 src:     "\xFF\xFE\x00\x00\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
  97                 sizeDst: 100,
  98                 want:    "\uFEFF\U00012345=Ra",
  99                 nSrc:    20,
 100                 t:       utf32LEIB.NewDecoder(),
 101         }, {
 102                 desc:    "utf-32le dec: Interprets big endian U+FEFF as invalid",
 103                 src:     "\x00\x00\xFE\xFF\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
 104                 sizeDst: 100,
 105                 want:    "\uFFFD\U00012345=Ra",
 106                 nSrc:    20,
 107                 t:       utf32LEIB.NewDecoder(),
 108         }, {
 109                 desc:    "utf-32 enc: Writes big-endian BOM",
 110                 src:     "\U00012345=Ra",
 111                 sizeDst: 100,
 112                 want:    "\x00\x00\xFE\xFF\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
 113                 nSrc:    7,
 114                 t:       utf32BEUB.NewEncoder(),
 115         }, {
 116                 desc:    "utf-32 enc: Writes little-endian BOM",
 117                 src:     "\U00012345=Ra",
 118                 sizeDst: 100,
 119                 want:    "\xFF\xFE\x00\x00\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
 120                 nSrc:    7,
 121                 t:       utf32LEUB.NewEncoder(),
 122         }, {
 123                 desc:    "utf-32 dec: Interprets text using big-endian default when BOM not present",
 124                 src:     "\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
 125                 sizeDst: 100,
 126                 want:    "\U00012345=Ra",
 127                 nSrc:    16,
 128                 t:       utf32BEUB.NewDecoder(),
 129         }, {
 130                 desc:    "utf-32 dec: Interprets text using little-endian default when BOM not present",
 131                 src:     "\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
 132                 sizeDst: 100,
 133                 want:    "\U00012345=Ra",
 134                 nSrc:    16,
 135                 t:       utf32LEUB.NewDecoder(),
 136         }, {
 137                 desc:    "utf-32 dec: BOM determines encoding BE",
 138                 src:     "\x00\x00\xFE\xFF\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
 139                 sizeDst: 100,
 140                 want:    "\U00012345=Ra",
 141                 nSrc:    20,
 142                 t:       utf32BEUB.NewDecoder(),
 143         }, {
 144                 desc:    "utf-32 dec: BOM determines encoding LE",
 145                 src:     "\xFF\xFE\x00\x00\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
 146                 sizeDst: 100,
 147                 want:    "\U00012345=Ra",
 148                 nSrc:    20,
 149                 t:       utf32LEUB.NewDecoder(),
 150         }, {
 151                 desc:    "utf-32 dec: BOM determines encoding LE, change default",
 152                 src:     "\xFF\xFE\x00\x00\x45\x23\x01\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61\x00\x00\x00",
 153                 sizeDst: 100,
 154                 want:    "\U00012345=Ra",
 155                 nSrc:    20,
 156                 t:       utf32BEUB.NewDecoder(),
 157         }, {
 158                 desc:    "utf-32 dec: BOM determines encoding BE, change default",
 159                 src:     "\x00\x00\xFE\xFF\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
 160                 sizeDst: 100,
 161                 want:    "\U00012345=Ra",
 162                 nSrc:    20,
 163                 t:       utf32LEUB.NewDecoder(),
 164         }, {
 165                 desc:    "utf-32 dec: Don't change big-endian byte order mid-stream",
 166                 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",
 167                 sizeDst: 100,
 168                 want:    "\U00012345=\uFFFD\uFEFFRa",
 169                 nSrc:    24,
 170                 t:       utf32BEUB.NewDecoder(),
 171         }, {
 172                 desc:    "utf-32 dec: Don't change little-endian byte order mid-stream",
 173                 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",
 174                 sizeDst: 100,
 175                 want:    "\U00012345=\uFFFD\uFEFFRa",
 176                 nSrc:    24,
 177                 t:       utf32LEUB.NewDecoder(),
 178         }, {
 179                 desc:    "utf-32 dec: Fail on missing BOM when required",
 180                 src:     "\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
 181                 sizeDst: 100,
 182                 want:    "",
 183                 nSrc:    0,
 184                 err:     ErrMissingBOM,
 185                 t:       utf32BEEB.NewDecoder(),
 186         }, {
 187                 desc:    "utf-32 enc: Short dst",
 188                 src:     "\U00012345=Ra",
 189                 sizeDst: 15,
 190                 want:    "\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52",
 191                 nSrc:    6,
 192                 err:     transform.ErrShortDst,
 193                 t:       utf32BEIB.NewEncoder(),
 194         }, {
 195                 desc:    "utf-32 enc: Short src",
 196                 src:     "\U00012345=Ra\xC2",
 197                 notEOF:  true,
 198                 sizeDst: 100,
 199                 want:    "\x00\x01\x23\x45\x00\x00\x00\x3D\x00\x00\x00\x52\x00\x00\x00\x61",
 200                 nSrc:    7,
 201                 err:     transform.ErrShortSrc,
 202                 t:       utf32BEIB.NewEncoder(),
 203         }, {
 204                 desc:    "utf-32 enc: Invalid input",
 205                 src:     "\x80\xC1\xC2\x7F\xC2",
 206                 sizeDst: 100,
 207                 want:    "\x00\x00\xFF\xFD\x00\x00\xFF\xFD\x00\x00\xFF\xFD\x00\x00\x00\x7F\x00\x00\xFF\xFD",
 208                 nSrc:    5,
 209                 t:       utf32BEIB.NewEncoder(),
 210         }, {
 211                 desc:    "utf-32 dec: Short dst",
 212                 src:     "\x00\x00\x00\x41",
 213                 sizeDst: 0,
 214                 want:    "",
 215                 nSrc:    0,
 216                 err:     transform.ErrShortDst,
 217                 t:       utf32BEIB.NewDecoder(),
 218         }, {
 219                 desc:    "utf-32 dec: Short src",
 220                 src:     "\x00\x00\x00",
 221                 notEOF:  true,
 222                 sizeDst: 4,
 223                 want:    "",
 224                 nSrc:    0,
 225                 err:     transform.ErrShortSrc,
 226                 t:       utf32BEIB.NewDecoder(),
 227         }, {
 228                 desc:    "utf-32 dec: Invalid input",
 229                 src:     "\x00\x00\xD8\x00\x00\x00\xDF\xFF\x00\x11\x00\x00\x00\x00\x00",
 230                 sizeDst: 100,
 231                 want:    "\uFFFD\uFFFD\uFFFD\uFFFD",
 232                 nSrc:    15,
 233                 t:       utf32BEIB.NewDecoder(),
 234         }}
 235         for i, tc := range testCases {
 236                 b := make([]byte, tc.sizeDst)
 237                 nDst, nSrc, err := tc.t.Transform(b, []byte(tc.src), !tc.notEOF)
 238                 if err != tc.err {
 239                         t.Errorf("%d:%s: error was %v; want %v", i, tc.desc, err, tc.err)
 240                 }
 241                 if got := string(b[:nDst]); got != tc.want {
 242                         t.Errorf("%d:%s: result was %q: want %q", i, tc.desc, got, tc.want)
 243                 }
 244                 if nSrc != tc.nSrc {
 245                         t.Errorf("%d:%s: nSrc was %d; want %d", i, tc.desc, nSrc, tc.nSrc)
 246                 }
 247         }
 248 }