Module: Addressable::IDNA

Defined in:
lib/addressable/idna/pure.rb,
lib/addressable/idna/native.rb

Defined Under Namespace

Classes: PunycodeBadInput, PunycodeBigOutput, PunycodeOverflow

Constant Summary collapse

UNICODE_TABLE = 
File.expand_path(
  File.join(File.dirname(__FILE__), '../../..', 'data/unicode.data')
)
ACE_PREFIX = 
"xn--"
UTF8_REGEX = 
/\A(?:
[\x09\x0A\x0D\x20-\x7E]               # ASCII
| [\xC2-\xDF][\x80-\xBF]              # non-overlong 2-byte
| \xE0[\xA0-\xBF][\x80-\xBF]          # excluding overlongs
| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}   # straight 3-byte
| \xED[\x80-\x9F][\x80-\xBF]          # excluding surrogates
| \xF0[\x90-\xBF][\x80-\xBF]{2}       # planes 1-3
| [\xF1-\xF3][\x80-\xBF]{3}           # planes 4nil5
| \xF4[\x80-\x8F][\x80-\xBF]{2}       # plane 16
)*\z/mnx
UTF8_REGEX_MULTIBYTE = 
/(?:
[\xC2-\xDF][\x80-\xBF]                # non-overlong 2-byte
| \xE0[\xA0-\xBF][\x80-\xBF]          # excluding overlongs
| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}   # straight 3-byte
| \xED[\x80-\x9F][\x80-\xBF]          # excluding surrogates
| \xF0[\x90-\xBF][\x80-\xBF]{2}       # planes 1-3
| [\xF1-\xF3][\x80-\xBF]{3}           # planes 4nil5
| \xF4[\x80-\x8F][\x80-\xBF]{2}       # plane 16
)/mnx
HANGUL_SBASE = 
0xac00
HANGUL_LBASE = 
0x1100
HANGUL_LCOUNT = 
19
HANGUL_VBASE = 
0x1161
HANGUL_VCOUNT = 
21
HANGUL_TBASE = 
0x11a7
HANGUL_TCOUNT = 
28
HANGUL_NCOUNT =

588

HANGUL_VCOUNT * HANGUL_TCOUNT
HANGUL_SCOUNT =

11172

HANGUL_LCOUNT * HANGUL_NCOUNT
UNICODE_DATA_COMBINING_CLASS = 
0
UNICODE_DATA_EXCLUSION = 
1
UNICODE_DATA_CANONICAL = 
2
UNICODE_DATA_COMPATIBILITY = 
3
UNICODE_DATA_UPPERCASE = 
4
UNICODE_DATA_LOWERCASE = 
5
UNICODE_DATA_TITLECASE = 
6
UNICODE_DATA =

This is a sparse Unicode table. Codepoints without entries are assumed to have the value: [0, 0, nil, nil, nil, nil, nil]

File.open(UNICODE_TABLE, "rb") do |file|
  Marshal.load(file.read)
end
COMPOSITION_TABLE = 
{}
UNICODE_MAX_LENGTH = 
256
ACE_MAX_LENGTH = 
256
PUNYCODE_BASE = 
36
PUNYCODE_TMIN = 
1
PUNYCODE_TMAX = 
26
PUNYCODE_SKEW = 
38
PUNYCODE_DAMP = 
700
PUNYCODE_INITIAL_BIAS = 
72
PUNYCODE_INITIAL_N = 
0x80
PUNYCODE_DELIMITER = 
0x2D
PUNYCODE_MAXINT = 
1 << 64
PUNYCODE_PRINT_ASCII = 
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n" +
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n" +
" !\"\#$%&'()*+,-./" +
"0123456789:;<=>?" +
"@ABCDEFGHIJKLMNO" +
"PQRSTUVWXYZ[\\]^_" +
"`abcdefghijklmno" +
"pqrstuvwxyz{|}~\n"

Class Method Summary collapse

Class Method Details

.lookup_unicode_combining_class(codepoint) ⇒ Object 



274
275
276
277
278
279
 
# File 'lib/addressable/idna/pure.rb', line 274

def self.lookup_unicode_combining_class(codepoint)
  codepoint_data = UNICODE_DATA[codepoint]
  (codepoint_data ?
    (codepoint_data[UNICODE_DATA_COMBINING_CLASS] || 0) :
    0)
end

.lookup_unicode_compatibility(codepoint) ⇒ Object 



282
283
284
285
286
 
# File 'lib/addressable/idna/pure.rb', line 282

def self.lookup_unicode_compatibility(codepoint)
  codepoint_data = UNICODE_DATA[codepoint]
  (codepoint_data ?
    codepoint_data[UNICODE_DATA_COMPATIBILITY] : nil)
end

.lookup_unicode_composition(unpacked) ⇒ Object 



297
298
299
 
# File 'lib/addressable/idna/pure.rb', line 297

def self.lookup_unicode_composition(unpacked)
  return COMPOSITION_TABLE[unpacked]
end

.lookup_unicode_lowercase(codepoint) ⇒ Object 



289
290
291
292
293
294
 
# File 'lib/addressable/idna/pure.rb', line 289

def self.lookup_unicode_lowercase(codepoint)
  codepoint_data = UNICODE_DATA[codepoint]
  (codepoint_data ?
    (codepoint_data[UNICODE_DATA_LOWERCASE] || codepoint) :
    codepoint)
end

.punycode_adapt(delta, numpoints, firsttime) ⇒ Object

Bias adaptation method



641
642
643
644
645
646
647
648
649
650
651
652
653
654
 
# File 'lib/addressable/idna/pure.rb', line 641

def self.punycode_adapt(delta, numpoints, firsttime)
  delta = firsttime ? delta / PUNYCODE_DAMP : delta >> 1
  # delta >> 1 is a faster way of doing delta / 2
  delta += delta / numpoints
  difference = PUNYCODE_BASE - PUNYCODE_TMIN

  k = 0
  while delta > (difference * PUNYCODE_TMAX) / 2
    delta /= difference
    k += PUNYCODE_BASE
  end

  k + (difference + 1) * delta / (delta + PUNYCODE_SKEW)
end

.punycode_basic?(codepoint) ⇒ Boolean

Returns:

  • (Boolean) 


609
610
611
 
# File 'lib/addressable/idna/pure.rb', line 609

def self.punycode_basic?(codepoint)
  codepoint < 0x80
end

.punycode_decode(value) ⇒ Object 



487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
 
# File 'lib/addressable/idna/pure.rb', line 487

def self.punycode_decode(punycode)
  input = []
  output = []

  if ACE_MAX_LENGTH * 2 < punycode.size
    raise PunycodeBigOutput, "Output would exceed the space provided."
  end
  punycode.each_byte do |c|
    unless c >= 0 && c <= 127
      raise PunycodeBadInput, "Input is invalid."
    end
    input.push(c)
  end

  input_length = input.length
  output_length = [UNICODE_MAX_LENGTH]

  # Initialize the state
  n = PUNYCODE_INITIAL_N

  out = i = 0
  max_out = output_length[0]
  bias = PUNYCODE_INITIAL_BIAS

  # Handle the basic code points:  Let b be the number of input code
  # points before the last delimiter, or 0 if there is none, then
  # copy the first b code points to the output.

  b = 0
  input_length.times do |j|
    b = j if punycode_delimiter?(input[j])
  end
  if b > max_out
    raise PunycodeBigOutput, "Output would exceed the space provided."
  end

  b.times do |j|
    unless punycode_basic?(input[j])
      raise PunycodeBadInput, "Input is invalid."
    end
    output[out] = input[j]
    out+=1
  end

  # Main decoding loop:  Start just after the last delimiter if any
  # basic code points were copied; start at the beginning otherwise.

  in_ = b > 0 ? b + 1 : 0
  while in_ < input_length

    # in_ is the index of the next character to be consumed, and
    # out is the number of code points in the output array.

    # Decode a generalized variable-length integer into delta,
    # which gets added to i.  The overflow checking is easier
    # if we increase i as we go, then subtract off its starting
    # value at the end to obtain delta.

    oldi = i; w = 1; k = PUNYCODE_BASE
    while true
      if in_ >= input_length
        raise PunycodeBadInput, "Input is invalid."
      end
      digit = punycode_decode_digit(input[in_])
      in_+=1
      if digit >= PUNYCODE_BASE
        raise PunycodeBadInput, "Input is invalid."
      end
      if digit > (PUNYCODE_MAXINT - i) / w
        raise PunycodeOverflow, "Input needs wider integers to process."
      end
      i += digit * w
      t = (
        if k <= bias
          PUNYCODE_TMIN
        elsif k >= bias + PUNYCODE_TMAX
          PUNYCODE_TMAX
        else
          k - bias
        end
      )
      break if digit < t
      if w > PUNYCODE_MAXINT / (PUNYCODE_BASE - t)
        raise PunycodeOverflow, "Input needs wider integers to process."
      end
      w *= PUNYCODE_BASE - t
      k += PUNYCODE_BASE
    end

    bias = punycode_adapt(i - oldi, out + 1, oldi == 0)

    # I was supposed to wrap around from out + 1 to 0,
    # incrementing n each time, so we'll fix that now:

    if i / (out + 1) > PUNYCODE_MAXINT - n
      raise PunycodeOverflow, "Input needs wider integers to process."
    end
    n += i / (out + 1)
    i %= out + 1

    # Insert n at position i of the output:

    # not needed for Punycode:
    # raise PUNYCODE_INVALID_INPUT if decode_digit(n) <= base
    if out >= max_out
      raise PunycodeBigOutput, "Output would exceed the space provided."
    end

    #memmove(output + i + 1, output + i, (out - i) * sizeof *output)
    output[i + 1, out - i] = output[i, out - i]
    output[i] = n
    i += 1

    out += 1
  end

  output_length[0] = out

  output.pack("U*")
end

.punycode_decode_digit(codepoint) ⇒ Object

Returns the numeric value of a basic codepoint (for use in representing integers) in the range 0 to base - 1, or PUNYCODE_BASE if codepoint does not represent a value.



627
628
629
630
631
632
633
634
635
636
637
 
# File 'lib/addressable/idna/pure.rb', line 627

def self.punycode_decode_digit(codepoint)
  if codepoint - 48 < 10
    codepoint - 22
  elsif codepoint - 65 < 26
    codepoint - 65
  elsif codepoint - 97 < 26
    codepoint - 97
  else
    PUNYCODE_BASE
  end
end

.punycode_delimiter?(codepoint) ⇒ Boolean

Returns:

  • (Boolean) 


614
615
616
 
# File 'lib/addressable/idna/pure.rb', line 614

def self.punycode_delimiter?(codepoint)
  codepoint == PUNYCODE_DELIMITER
end

.punycode_encode(value) ⇒ Object 



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
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
 
# File 'lib/addressable/idna/pure.rb', line 367

def self.punycode_encode(unicode)
  input = unicode.unpack("U*")
  output = [0] * (ACE_MAX_LENGTH + 1)
  input_length = input.size
  output_length = [ACE_MAX_LENGTH]

  # Initialize the state
  n = PUNYCODE_INITIAL_N
  delta = out = 0
  max_out = output_length[0]
  bias = PUNYCODE_INITIAL_BIAS

  # Handle the basic code points:
  input_length.times do |j|
    if punycode_basic?(input[j])
      if max_out - out < 2
        raise PunycodeBigOutput,
          "Output would exceed the space provided."
      end
      output[out] = input[j]
      out += 1
    end
  end

  h = b = out

  # h is the number of code points that have been handled, b is the
  # number of basic code points, and out is the number of characters
  # that have been output.

  if b > 0
    output[out] = PUNYCODE_DELIMITER
    out += 1
  end

  # Main encoding loop:

  while h < input_length
    # All non-basic code points < n have been
    # handled already.  Find the next larger one:

    m = PUNYCODE_MAXINT
    input_length.times do |j|
      m = input[j] if (n...m) === input[j]
    end

    # Increase delta enough to advance the decoder's
    # <n,i> state to <m,0>, but guard against overflow:

    if m - n > (PUNYCODE_MAXINT - delta) / (h + 1)
      raise PunycodeOverflow, "Input needs wider integers to process."
    end
    delta += (m - n) * (h + 1)
    n = m

    input_length.times do |j|
      # Punycode does not need to check whether input[j] is basic:
      if input[j] < n
        delta += 1
        if delta == 0
          raise PunycodeOverflow,
            "Input needs wider integers to process."
        end
      end

      if input[j] == n
        # Represent delta as a generalized variable-length integer:

        q = delta; k = PUNYCODE_BASE
        while true
          if out >= max_out
            raise PunycodeBigOutput,
              "Output would exceed the space provided."
          end
          t = (
            if k <= bias
              PUNYCODE_TMIN
            elsif k >= bias + PUNYCODE_TMAX
              PUNYCODE_TMAX
            else
              k - bias
            end
          )
          break if q < t
          output[out] =
            punycode_encode_digit(t + (q - t) % (PUNYCODE_BASE - t))
          out += 1
          q = (q - t) / (PUNYCODE_BASE - t)
          k += PUNYCODE_BASE
        end

        output[out] = punycode_encode_digit(q)
        out += 1
        bias = punycode_adapt(delta, h + 1, h == b)
        delta = 0
        h += 1
      end
    end

    delta += 1
    n += 1
  end

  output_length[0] = out

  outlen = out
  outlen.times do |j|
    c = output[j]
    unless c >= 0 && c <= 127
      raise Exception, "Invalid output char."
    end
    unless PUNYCODE_PRINT_ASCII[c]
      raise PunycodeBadInput, "Input is invalid."
    end
  end

  output[0..outlen].map { |x| x.chr }.join("").sub(/\0+\z/, "")
end

.punycode_encode_digit(d) ⇒ Object 



619
620
621
 
# File 'lib/addressable/idna/pure.rb', line 619

def self.punycode_encode_digit(d)
  d + 22 + 75 * ((d < 26) ? 1 : 0)
end

.to_ascii(value) ⇒ Object

Converts from a Unicode internationalized domain name to an ASCII domain name as described in RFC 3490.



66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
 
# File 'lib/addressable/idna/pure.rb', line 66

def self.to_ascii(input)
  input = input.dup
  if input.respond_to?(:force_encoding)
    input.force_encoding(Encoding::ASCII_8BIT)
  end
  if input =~ UTF8_REGEX && input =~ UTF8_REGEX_MULTIBYTE
    parts = unicode_downcase(input).split('.')
    parts.map! do |part|
      if part.respond_to?(:force_encoding)
        part.force_encoding(Encoding::ASCII_8BIT)
      end
      if part =~ UTF8_REGEX && part =~ UTF8_REGEX_MULTIBYTE
        ACE_PREFIX + punycode_encode(unicode_normalize_kc(part))
      else
        part
      end
    end
    parts.join('.')
  else
    input
  end
end

.to_unicode(value) ⇒ Object

Converts from an ASCII domain name to a Unicode internationalized domain name as described in RFC 3490.



91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
 
# File 'lib/addressable/idna/pure.rb', line 91

def self.to_unicode(input)
  parts = input.split('.')
  parts.map! do |part|
    if part =~ /^#{ACE_PREFIX}/
      punycode_decode(part[/^#{ACE_PREFIX}(.+)/, 1])
    else
      part
    end
  end
  output = parts.join('.')
  if output.respond_to?(:force_encoding)
    output.force_encoding(Encoding::UTF_8)
  end
  output
end

.unicode_compose(unpacked) ⇒ Object 



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
 
# File 'lib/addressable/idna/pure.rb', line 129

def self.unicode_compose(unpacked)
  unpacked_result = []
  length = unpacked.length

  return unpacked if length == 0

  starter = unpacked[0]
  starter_cc = lookup_unicode_combining_class(starter)
  starter_cc = 256 if starter_cc != 0
  for i in 1...length
    ch = unpacked[i]
    cc = lookup_unicode_combining_class(ch)

    if (starter_cc == 0 &&
        (composite = unicode_compose_pair(starter, ch)) != nil)
      starter = composite
      startercc = lookup_unicode_combining_class(composite)
    else
      unpacked_result << starter
      starter = ch
      startercc = cc
    end
  end
  unpacked_result << starter
  return unpacked_result
end

.unicode_compose_pair(ch_one, ch_two) ⇒ Object 



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
 
# File 'lib/addressable/idna/pure.rb', line 157

def self.unicode_compose_pair(ch_one, ch_two)
  if ch_one >= HANGUL_LBASE && ch_one < HANGUL_LBASE + HANGUL_LCOUNT &&
      ch_two >= HANGUL_VBASE && ch_two < HANGUL_VBASE + HANGUL_VCOUNT
    # Hangul L + V
    return HANGUL_SBASE + (
      (ch_one - HANGUL_LBASE) * HANGUL_VCOUNT + (ch_two - HANGUL_VBASE)
    ) * HANGUL_TCOUNT
  elsif ch_one >= HANGUL_SBASE &&
      ch_one < HANGUL_SBASE + HANGUL_SCOUNT &&
      (ch_one - HANGUL_SBASE) % HANGUL_TCOUNT == 0 &&
      ch_two >= HANGUL_TBASE && ch_two < HANGUL_TBASE + HANGUL_TCOUNT
       # Hangul LV + T
    return ch_one + (ch_two - HANGUL_TBASE)
  end

  p = []
  ucs4_to_utf8 = lambda do |ch|
    # For some reason, rcov likes to drop BUS errors here.
    if ch < 128
      p << ch
    elsif ch < 2048
      p << (ch >> 6 | 192)
      p << (ch & 63 | 128)
    elsif ch < 0x10000
      p << (ch >> 12 | 224)
      p << (ch >> 6 & 63 | 128)
      p << (ch & 63 | 128)
    elsif ch < 0x200000
      p << (ch >> 18 | 240)
      p << (ch >> 12 & 63 | 128)
      p << (ch >> 6 & 63 | 128)
      p << (ch & 63 | 128)
    elsif ch < 0x4000000
      p << (ch >> 24 | 248)
      p << (ch >> 18 & 63 | 128)
      p << (ch >> 12 & 63 | 128)
      p << (ch >> 6 & 63 | 128)
      p << (ch & 63 | 128)
    elsif ch < 0x80000000
      p << (ch >> 30 | 252)
      p << (ch >> 24 & 63 | 128)
      p << (ch >> 18 & 63 | 128)
      p << (ch >> 12 & 63 | 128)
      p << (ch >> 6 & 63 | 128)
      p << (ch & 63 | 128)
    end
  end

  ucs4_to_utf8.call(ch_one)
  ucs4_to_utf8.call(ch_two)

  return lookup_unicode_composition(p)
end

.unicode_decompose(unpacked) ⇒ Object 



236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
 
# File 'lib/addressable/idna/pure.rb', line 236

def self.unicode_decompose(unpacked)
  unpacked_result = []
  for cp in unpacked
    if cp >= HANGUL_SBASE && cp < HANGUL_SBASE + HANGUL_SCOUNT
      l, v, t = unicode_decompose_hangul(cp)
      unpacked_result << l
      unpacked_result << v if v
      unpacked_result << t if t
    else
      dc = lookup_unicode_compatibility(cp)
      unless dc
        unpacked_result << cp
      else
        unpacked_result.concat(unicode_decompose(dc.unpack("U*")))
      end
    end
  end
  return unpacked_result
end

.unicode_decompose_hangul(codepoint) ⇒ Object 



257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
 
# File 'lib/addressable/idna/pure.rb', line 257

def self.unicode_decompose_hangul(codepoint)
  sindex = codepoint - HANGUL_SBASE;
  if sindex < 0 || sindex >= HANGUL_SCOUNT
    l = codepoint
    v = t = nil
    return l, v, t
  end
  l = HANGUL_LBASE + sindex / HANGUL_NCOUNT
  v = HANGUL_VBASE + (sindex % HANGUL_NCOUNT) / HANGUL_TCOUNT
  t = HANGUL_TBASE + sindex % HANGUL_TCOUNT
  if t == HANGUL_TBASE
    t = nil
  end
  return l, v, t
end

.unicode_downcase(input) ⇒ String

This method is part of a private API. You should avoid using this method if possible, as it may be removed or be changed in the future.

Unicode aware downcase method.

Parameters:

  • input (String) —

    The input string.

Returns:

  • (String) —

    The downcased result.



122
123
124
125
126
 
# File 'lib/addressable/idna/pure.rb', line 122

def self.unicode_downcase(input)
  unpacked = input.unpack("U*")
  unpacked.map! { |codepoint| lookup_unicode_lowercase(codepoint) }
  return unpacked.pack("U*")
end

.unicode_normalize_kc(value) ⇒ Object

Unicode normalization form KC.



108
109
110
111
112
113
 
# File 'lib/addressable/idna/pure.rb', line 108

def self.unicode_normalize_kc(input)
  unpacked = input.unpack("U*")
  unpacked =
    unicode_compose(unicode_sort_canonical(unicode_decompose(unpacked)))
  return unpacked.pack("U*")
end

.unicode_sort_canonical(unpacked) ⇒ Object 



212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
 
# File 'lib/addressable/idna/pure.rb', line 212

def self.unicode_sort_canonical(unpacked)
  unpacked = unpacked.dup
  i = 1
  length = unpacked.length

  return unpacked if length < 2

  while i < length
    last = unpacked[i-1]
    ch = unpacked[i]
    last_cc = lookup_unicode_combining_class(last)
    cc = lookup_unicode_combining_class(ch)
    if cc != 0 && last_cc != 0 && last_cc > cc
      unpacked[i] = last
      unpacked[i-1] = ch
      i -= 1 if i > 1
    else
      i += 1
    end
  end
  return unpacked
end