indexOf.js 14.6 KB
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463
'use strict'

var tape       = require('tape')
  , BufferList = require('../')
  , Buffer     = require('safe-buffer').Buffer

tape('indexOf single byte needle', t => {
  const bl = new BufferList(['abcdefg', 'abcdefg', '12345'])
  t.equal(bl.indexOf('e'), 4)
  t.equal(bl.indexOf('e', 5), 11)
  t.equal(bl.indexOf('e', 12), -1)
  t.equal(bl.indexOf('5'), 18)
  t.end()
})

tape('indexOf multiple byte needle', t => {
  const bl = new BufferList(['abcdefg', 'abcdefg'])
  t.equal(bl.indexOf('ef'), 4)
  t.equal(bl.indexOf('ef', 5), 11)
  t.end()
})

tape('indexOf multiple byte needles across buffer boundaries', t => {
  const bl = new BufferList(['abcdefg', 'abcdefg'])
  t.equal(bl.indexOf('fgabc'), 5)
  t.end()
})

tape('indexOf takes a buffer list search', t => {
  const bl = new BufferList(['abcdefg', 'abcdefg'])
  const search = new BufferList('fgabc')
  t.equal(bl.indexOf(search), 5)
  t.end()
})

tape('indexOf a zero byte needle', t => {
  const b = new BufferList('abcdef')
  const buf_empty = Buffer.from('')
  t.equal(b.indexOf(''), 0)
  t.equal(b.indexOf('', 1), 1)
  t.equal(b.indexOf('', b.length + 1), b.length)
  t.equal(b.indexOf('', Infinity), b.length)
  t.equal(b.indexOf(buf_empty), 0)
  t.equal(b.indexOf(buf_empty, 1), 1)
  t.equal(b.indexOf(buf_empty, b.length + 1), b.length)
  t.equal(b.indexOf(buf_empty, Infinity), b.length)
  t.end()
})

tape('indexOf buffers smaller and larger than the needle', t => {
  const bl = new BufferList(['abcdefg', 'a', 'bcdefg', 'a', 'bcfgab'])
  t.equal(bl.indexOf('fgabc'), 5)
  t.equal(bl.indexOf('fgabc', 6), 12)
  t.equal(bl.indexOf('fgabc', 13), -1)
  t.end()
})

// only present in node 6+
;(process.version.substr(1).split('.')[0] >= 6) && tape('indexOf latin1 and binary encoding', t => {
  const b = new BufferList('abcdef')

  // test latin1 encoding
  t.equal(
    new BufferList(Buffer.from(b.toString('latin1'), 'latin1'))
      .indexOf('d', 0, 'latin1'),
    3
  )
  t.equal(
    new BufferList(Buffer.from(b.toString('latin1'), 'latin1'))
      .indexOf(Buffer.from('d', 'latin1'), 0, 'latin1'),
    3
  )
  t.equal(
    new BufferList(Buffer.from('aa\u00e8aa', 'latin1'))
      .indexOf('\u00e8', 'latin1'),
    2
  )
  t.equal(
    new BufferList(Buffer.from('\u00e8', 'latin1'))
      .indexOf('\u00e8', 'latin1'),
    0
  )
  t.equal(
    new BufferList(Buffer.from('\u00e8', 'latin1'))
      .indexOf(Buffer.from('\u00e8', 'latin1'), 'latin1'),
    0
  )

  // test binary encoding
  t.equal(
    new BufferList(Buffer.from(b.toString('binary'), 'binary'))
      .indexOf('d', 0, 'binary'),
    3
  )
  t.equal(
    new BufferList(Buffer.from(b.toString('binary'), 'binary'))
      .indexOf(Buffer.from('d', 'binary'), 0, 'binary'),
    3
  )
  t.equal(
    new BufferList(Buffer.from('aa\u00e8aa', 'binary'))
      .indexOf('\u00e8', 'binary'),
    2
  )
  t.equal(
    new BufferList(Buffer.from('\u00e8', 'binary'))
      .indexOf('\u00e8', 'binary'),
    0
  )
  t.equal(
    new BufferList(Buffer.from('\u00e8', 'binary'))
      .indexOf(Buffer.from('\u00e8', 'binary'), 'binary'),
    0
  )
  t.end()
})

tape('indexOf the entire nodejs10 buffer test suite', t => {
  const b = new BufferList('abcdef')
  const buf_a = Buffer.from('a')
  const buf_bc = Buffer.from('bc')
  const buf_f = Buffer.from('f')
  const buf_z = Buffer.from('z')

  const stringComparison = 'abcdef'

  t.equal(b.indexOf('a'), 0)
  t.equal(b.indexOf('a', 1), -1)
  t.equal(b.indexOf('a', -1), -1)
  t.equal(b.indexOf('a', -4), -1)
  t.equal(b.indexOf('a', -b.length), 0)
  t.equal(b.indexOf('a', NaN), 0)
  t.equal(b.indexOf('a', -Infinity), 0)
  t.equal(b.indexOf('a', Infinity), -1)
  t.equal(b.indexOf('bc'), 1)
  t.equal(b.indexOf('bc', 2), -1)
  t.equal(b.indexOf('bc', -1), -1)
  t.equal(b.indexOf('bc', -3), -1)
  t.equal(b.indexOf('bc', -5), 1)
  t.equal(b.indexOf('bc', NaN), 1)
  t.equal(b.indexOf('bc', -Infinity), 1)
  t.equal(b.indexOf('bc', Infinity), -1)
  t.equal(b.indexOf('f'), b.length - 1)
  t.equal(b.indexOf('z'), -1)
  // empty search tests
  t.equal(b.indexOf(buf_a), 0)
  t.equal(b.indexOf(buf_a, 1), -1)
  t.equal(b.indexOf(buf_a, -1), -1)
  t.equal(b.indexOf(buf_a, -4), -1)
  t.equal(b.indexOf(buf_a, -b.length), 0)
  t.equal(b.indexOf(buf_a, NaN), 0)
  t.equal(b.indexOf(buf_a, -Infinity), 0)
  t.equal(b.indexOf(buf_a, Infinity), -1)
  t.equal(b.indexOf(buf_bc), 1)
  t.equal(b.indexOf(buf_bc, 2), -1)
  t.equal(b.indexOf(buf_bc, -1), -1)
  t.equal(b.indexOf(buf_bc, -3), -1)
  t.equal(b.indexOf(buf_bc, -5), 1)
  t.equal(b.indexOf(buf_bc, NaN), 1)
  t.equal(b.indexOf(buf_bc, -Infinity), 1)
  t.equal(b.indexOf(buf_bc, Infinity), -1)
  t.equal(b.indexOf(buf_f), b.length - 1)
  t.equal(b.indexOf(buf_z), -1)
  t.equal(b.indexOf(0x61), 0)
  t.equal(b.indexOf(0x61, 1), -1)
  t.equal(b.indexOf(0x61, -1), -1)
  t.equal(b.indexOf(0x61, -4), -1)
  t.equal(b.indexOf(0x61, -b.length), 0)
  t.equal(b.indexOf(0x61, NaN), 0)
  t.equal(b.indexOf(0x61, -Infinity), 0)
  t.equal(b.indexOf(0x61, Infinity), -1)
  t.equal(b.indexOf(0x0), -1)

  // test offsets
  t.equal(b.indexOf('d', 2), 3)
  t.equal(b.indexOf('f', 5), 5)
  t.equal(b.indexOf('f', -1), 5)
  t.equal(b.indexOf('f', 6), -1)

  t.equal(b.indexOf(Buffer.from('d'), 2), 3)
  t.equal(b.indexOf(Buffer.from('f'), 5), 5)
  t.equal(b.indexOf(Buffer.from('f'), -1), 5)
  t.equal(b.indexOf(Buffer.from('f'), 6), -1)

  t.equal(Buffer.from('ff').indexOf(Buffer.from('f'), 1, 'ucs2'), -1)

  // test invalid and uppercase encoding
  t.equal(b.indexOf('b', 'utf8'), 1)
  t.equal(b.indexOf('b', 'UTF8'), 1)
  t.equal(b.indexOf('62', 'HEX'), 1)
  t.throws(() => b.indexOf('bad', 'enc'), TypeError)

  // test hex encoding
  t.equal(
    Buffer.from(b.toString('hex'), 'hex')
      .indexOf('64', 0, 'hex'),
    3
  )
  t.equal(
    Buffer.from(b.toString('hex'), 'hex')
      .indexOf(Buffer.from('64', 'hex'), 0, 'hex'),
    3
  )

  // test base64 encoding
  t.equal(
    Buffer.from(b.toString('base64'), 'base64')
      .indexOf('ZA==', 0, 'base64'),
    3
  )
  t.equal(
    Buffer.from(b.toString('base64'), 'base64')
      .indexOf(Buffer.from('ZA==', 'base64'), 0, 'base64'),
    3
  )

  // test ascii encoding
  t.equal(
    Buffer.from(b.toString('ascii'), 'ascii')
      .indexOf('d', 0, 'ascii'),
    3
  )
  t.equal(
    Buffer.from(b.toString('ascii'), 'ascii')
      .indexOf(Buffer.from('d', 'ascii'), 0, 'ascii'),
    3
  )

  // test optional offset with passed encoding
  t.equal(Buffer.from('aaaa0').indexOf('30', 'hex'), 4)
  t.equal(Buffer.from('aaaa00a').indexOf('3030', 'hex'), 4)

  {
    // test usc2 encoding
    const twoByteString = Buffer.from('\u039a\u0391\u03a3\u03a3\u0395', 'ucs2')

    t.equal(8, twoByteString.indexOf('\u0395', 4, 'ucs2'))
    t.equal(6, twoByteString.indexOf('\u03a3', -4, 'ucs2'))
    t.equal(4, twoByteString.indexOf('\u03a3', -6, 'ucs2'))
    t.equal(4, twoByteString.indexOf(
      Buffer.from('\u03a3', 'ucs2'), -6, 'ucs2'))
    t.equal(-1, twoByteString.indexOf('\u03a3', -2, 'ucs2'))
  }

  const mixedByteStringUcs2 =
      Buffer.from('\u039a\u0391abc\u03a3\u03a3\u0395', 'ucs2')
  t.equal(6, mixedByteStringUcs2.indexOf('bc', 0, 'ucs2'))
  t.equal(10, mixedByteStringUcs2.indexOf('\u03a3', 0, 'ucs2'))
  t.equal(-1, mixedByteStringUcs2.indexOf('\u0396', 0, 'ucs2'))

  t.equal(
    6, mixedByteStringUcs2.indexOf(Buffer.from('bc', 'ucs2'), 0, 'ucs2'))
  t.equal(
    10, mixedByteStringUcs2.indexOf(Buffer.from('\u03a3', 'ucs2'), 0, 'ucs2'))
  t.equal(
    -1, mixedByteStringUcs2.indexOf(Buffer.from('\u0396', 'ucs2'), 0, 'ucs2'))

  {
    const twoByteString = Buffer.from('\u039a\u0391\u03a3\u03a3\u0395', 'ucs2')

    // Test single char pattern
    t.equal(0, twoByteString.indexOf('\u039a', 0, 'ucs2'))
    let index = twoByteString.indexOf('\u0391', 0, 'ucs2')
    t.equal(2, index, `Alpha - at index ${index}`)
    index = twoByteString.indexOf('\u03a3', 0, 'ucs2')
    t.equal(4, index, `First Sigma - at index ${index}`)
    index = twoByteString.indexOf('\u03a3', 6, 'ucs2')
    t.equal(6, index, `Second Sigma - at index ${index}`)
    index = twoByteString.indexOf('\u0395', 0, 'ucs2')
    t.equal(8, index, `Epsilon - at index ${index}`)
    index = twoByteString.indexOf('\u0392', 0, 'ucs2')
    t.equal(-1, index, `Not beta - at index ${index}`)

    // Test multi-char pattern
    index = twoByteString.indexOf('\u039a\u0391', 0, 'ucs2')
    t.equal(0, index, `Lambda Alpha - at index ${index}`)
    index = twoByteString.indexOf('\u0391\u03a3', 0, 'ucs2')
    t.equal(2, index, `Alpha Sigma - at index ${index}`)
    index = twoByteString.indexOf('\u03a3\u03a3', 0, 'ucs2')
    t.equal(4, index, `Sigma Sigma - at index ${index}`)
    index = twoByteString.indexOf('\u03a3\u0395', 0, 'ucs2')
    t.equal(6, index, `Sigma Epsilon - at index ${index}`)
  }

  const mixedByteStringUtf8 = Buffer.from('\u039a\u0391abc\u03a3\u03a3\u0395')
  t.equal(5, mixedByteStringUtf8.indexOf('bc'))
  t.equal(5, mixedByteStringUtf8.indexOf('bc', 5))
  t.equal(5, mixedByteStringUtf8.indexOf('bc', -8))
  t.equal(7, mixedByteStringUtf8.indexOf('\u03a3'))
  t.equal(-1, mixedByteStringUtf8.indexOf('\u0396'))


  // Test complex string indexOf algorithms. Only trigger for long strings.
  // Long string that isn't a simple repeat of a shorter string.
  let longString = 'A'
  for (let i = 66; i < 76; i++) {  // from 'B' to 'K'
    longString = longString + String.fromCharCode(i) + longString
  }

  const longBufferString = Buffer.from(longString)

  // pattern of 15 chars, repeated every 16 chars in long
  let pattern = 'ABACABADABACABA'
  for (let i = 0; i < longBufferString.length - pattern.length; i += 7) {
    const index = longBufferString.indexOf(pattern, i)
    t.equal((i + 15) & ~0xf, index,
                      `Long ABACABA...-string at index ${i}`)
  }

  let index = longBufferString.indexOf('AJABACA')
  t.equal(510, index, `Long AJABACA, First J - at index ${index}`)
  index = longBufferString.indexOf('AJABACA', 511)
  t.equal(1534, index, `Long AJABACA, Second J - at index ${index}`)

  pattern = 'JABACABADABACABA'
  index = longBufferString.indexOf(pattern)
  t.equal(511, index, `Long JABACABA..., First J - at index ${index}`)
  index = longBufferString.indexOf(pattern, 512)
  t.equal(
    1535, index, `Long JABACABA..., Second J - at index ${index}`)

  // Search for a non-ASCII string in a pure ASCII string.
  const asciiString = Buffer.from(
    'arglebargleglopglyfarglebargleglopglyfarglebargleglopglyf')
  t.equal(-1, asciiString.indexOf('\x2061'))
  t.equal(3, asciiString.indexOf('leb', 0))

  // Search in string containing many non-ASCII chars.
  const allCodePoints = []
  for (let i = 0; i < 65536; i++) allCodePoints[i] = i
  const allCharsString = String.fromCharCode.apply(String, allCodePoints)
  const allCharsBufferUtf8 = Buffer.from(allCharsString)
  const allCharsBufferUcs2 = Buffer.from(allCharsString, 'ucs2')

  // Search for string long enough to trigger complex search with ASCII pattern
  // and UC16 subject.
  t.equal(-1, allCharsBufferUtf8.indexOf('notfound'))
  t.equal(-1, allCharsBufferUcs2.indexOf('notfound'))

  // Needle is longer than haystack, but only because it's encoded as UTF-16
  t.equal(Buffer.from('aaaa').indexOf('a'.repeat(4), 'ucs2'), -1)

  t.equal(Buffer.from('aaaa').indexOf('a'.repeat(4), 'utf8'), 0)
  t.equal(Buffer.from('aaaa').indexOf('你好', 'ucs2'), -1)

  // Haystack has odd length, but the needle is UCS2.
  t.equal(Buffer.from('aaaaa').indexOf('b', 'ucs2'), -1)

  {
    // Find substrings in Utf8.
    const lengths = [1, 3, 15];  // Single char, simple and complex.
    const indices = [0x5, 0x60, 0x400, 0x680, 0x7ee, 0xFF02, 0x16610, 0x2f77b]
    for (let lengthIndex = 0; lengthIndex < lengths.length; lengthIndex++) {
      for (let i = 0; i < indices.length; i++) {
        const index = indices[i]
        let length = lengths[lengthIndex]

        if (index + length > 0x7F) {
          length = 2 * length
        }

        if (index + length > 0x7FF) {
          length = 3 * length
        }

        if (index + length > 0xFFFF) {
          length = 4 * length
        }

        const patternBufferUtf8 = allCharsBufferUtf8.slice(index, index + length)
        t.equal(index, allCharsBufferUtf8.indexOf(patternBufferUtf8))

        const patternStringUtf8 = patternBufferUtf8.toString()
        t.equal(index, allCharsBufferUtf8.indexOf(patternStringUtf8))
      }
    }
  }

  {
    // Find substrings in Usc2.
    const lengths = [2, 4, 16];  // Single char, simple and complex.
    const indices = [0x5, 0x65, 0x105, 0x205, 0x285, 0x2005, 0x2085, 0xfff0]
    for (let lengthIndex = 0; lengthIndex < lengths.length; lengthIndex++) {
      for (let i = 0; i < indices.length; i++) {
        const index = indices[i] * 2
        const length = lengths[lengthIndex]

        const patternBufferUcs2 =
            allCharsBufferUcs2.slice(index, index + length)
        t.equal(
          index, allCharsBufferUcs2.indexOf(patternBufferUcs2, 0, 'ucs2'))

        const patternStringUcs2 = patternBufferUcs2.toString('ucs2')
        t.equal(
          index, allCharsBufferUcs2.indexOf(patternStringUcs2, 0, 'ucs2'))
      }
    }
  }

  [
    () => {},
    {},
    []
  ].forEach(val => {
    debugger
    t.throws(() => b.indexOf(val), TypeError, `"${JSON.stringify(val)}" should throw`)
  })

  // Test weird offset arguments.
  // The following offsets coerce to NaN or 0, searching the whole Buffer
  t.equal(b.indexOf('b', undefined), 1)
  t.equal(b.indexOf('b', {}), 1)
  t.equal(b.indexOf('b', 0), 1)
  t.equal(b.indexOf('b', null), 1)
  t.equal(b.indexOf('b', []), 1)

  // The following offset coerces to 2, in other words +[2] === 2
  t.equal(b.indexOf('b', [2]), -1)

  // Behavior should match String.indexOf()
  t.equal(
    b.indexOf('b', undefined),
    stringComparison.indexOf('b', undefined))
  t.equal(
    b.indexOf('b', {}),
    stringComparison.indexOf('b', {}))
  t.equal(
    b.indexOf('b', 0),
    stringComparison.indexOf('b', 0))
  t.equal(
    b.indexOf('b', null),
    stringComparison.indexOf('b', null))
  t.equal(
    b.indexOf('b', []),
    stringComparison.indexOf('b', []))
  t.equal(
    b.indexOf('b', [2]),
    stringComparison.indexOf('b', [2]))

  // test truncation of Number arguments to uint8
  {
    const buf = Buffer.from('this is a test')
    t.equal(buf.indexOf(0x6973), 3)
    t.equal(buf.indexOf(0x697320), 4)
    t.equal(buf.indexOf(0x69732069), 2)
    t.equal(buf.indexOf(0x697374657374), 0)
    t.equal(buf.indexOf(0x69737374), 0)
    t.equal(buf.indexOf(0x69737465), 11)
    t.equal(buf.indexOf(0x69737465), 11)
    t.equal(buf.indexOf(-140), 0)
    t.equal(buf.indexOf(-152), 1)
    t.equal(buf.indexOf(0xff), -1)
    t.equal(buf.indexOf(0xffff), -1)
  }

  // Test that Uint8Array arguments are okay.
  {
    const needle = new Uint8Array([ 0x66, 0x6f, 0x6f ])
    const haystack = new BufferList(Buffer.from('a foo b foo'))
    t.equal(haystack.indexOf(needle), 2)
  }
  t.end()
})