Class: Reline::Unicode

Inherits:
Object
  • Object
show all
Defined in:
lib/reline/unicode.rb

Defined Under Namespace

Classes: EastAsianWidth

Constant Summary collapse

EscapedPairs = 
{
  0x00 => '^@',
  0x01 => '^A', # C-a
  0x02 => '^B',
  0x03 => '^C',
  0x04 => '^D',
  0x05 => '^E',
  0x06 => '^F',
  0x07 => '^G',
  0x08 => '^H', # Backspace
  0x09 => '^I',
  0x0A => '^J',
  0x0B => '^K',
  0x0C => '^L',
  0x0D => '^M', # Enter
  0x0E => '^N',
  0x0F => '^O',
  0x10 => '^P',
  0x11 => '^Q',
  0x12 => '^R',
  0x13 => '^S',
  0x14 => '^T',
  0x15 => '^U',
  0x16 => '^V',
  0x17 => '^W',
  0x18 => '^X',
  0x19 => '^Y',
  0x1A => '^Z', # C-z
  0x1B => '^[', # C-[ C-3
  0x1D => '^]', # C-]
  0x1E => '^^', # C-~ C-6
  0x1F => '^_', # C-_ C-7
  0x7F => '^?', # C-? C-8
}
EscapedChars =

C-? C-8

EscapedPairs.keys.map(&:chr)
CSI_REGEXP = 
/\e\[[\d;]*[ABCDEFGHJKSTfminsuhl]/
OSC_REGEXP = 
/\e\]\d+(?:;[^;]+)*\a/
NON_PRINTING_START = 
"\1"
NON_PRINTING_END = 
"\2"
WIDTH_SCANNER = 
/\G(?:#{NON_PRINTING_START}|#{NON_PRINTING_END}|#{CSI_REGEXP}|#{OSC_REGEXP}|\X)/
MBCharWidthRE = 
/
  (?<width_2_1>
    [#{ EscapedChars.map {|c| "\\x%02x" % c.ord }.join }] (?# ^ + char, such as ^M, ^H, ^[, ...)
  )
| (?<width_3>^\u{2E3B}) (?# THREE-EM DASH)
| (?<width_0>^\p{M})
| (?<width_2_2>
    #{ EastAsianWidth::TYPE_F }
  | #{ EastAsianWidth::TYPE_W }
  )
| (?<width_1>
    #{ EastAsianWidth::TYPE_H }
  | #{ EastAsianWidth::TYPE_NA }
  | #{ EastAsianWidth::TYPE_N }
  )
/x

Class Method Summary collapse

Class Method Details

.calculate_width(str, allow_escape_code = false) ⇒ Object 



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
 
# File 'lib/reline/unicode.rb', line 106

def self.calculate_width(str, allow_escape_code = false)
  if allow_escape_code
    width = 0
    rest = str.encode(Encoding::UTF_8)
    in_zero_width = false
    rest.scan(WIDTH_SCANNER) do |gc|
      case gc
      when NON_PRINTING_START
        in_zero_width = true
      when NON_PRINTING_END
        in_zero_width = false
      when CSI_REGEXP, OSC_REGEXP
      else
        unless in_zero_width
          width += get_mbchar_width(gc)
        end
      end
    end
    width
  else
    str.encode(Encoding::UTF_8).grapheme_clusters.inject(0) { |w, gc|
      w + get_mbchar_width(gc)
    }
  end
end

.ed_transpose_words(line, byte_pointer) ⇒ Object 



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
 
# File 'lib/reline/unicode.rb', line 271

def self.ed_transpose_words(line, byte_pointer)
  right_word_start = nil
  size = get_next_mbchar_size(line, byte_pointer)
  mbchar = line.byteslice(byte_pointer, size)
  if size.zero?
    # ' aaa bbb [cursor]'
    byte_size = 0
    while 0 < (byte_pointer + byte_size)
      size = get_prev_mbchar_size(line, byte_pointer + byte_size)
      mbchar = line.byteslice(byte_pointer + byte_size - size, size)
      break if mbchar.encode(Encoding::UTF_8) =~ /\p{Word}/
      byte_size -= size
    end
    while 0 < (byte_pointer + byte_size)
      size = get_prev_mbchar_size(line, byte_pointer + byte_size)
      mbchar = line.byteslice(byte_pointer + byte_size - size, size)
      break if mbchar.encode(Encoding::UTF_8) =~ /\P{Word}/
      byte_size -= size
    end
    right_word_start = byte_pointer + byte_size
    byte_size = 0
    while line.bytesize > (byte_pointer + byte_size)
      size = get_next_mbchar_size(line, byte_pointer + byte_size)
      mbchar = line.byteslice(byte_pointer + byte_size, size)
      break if mbchar.encode(Encoding::UTF_8) =~ /\P{Word}/
      byte_size += size
    end
    after_start = byte_pointer + byte_size
  elsif mbchar.encode(Encoding::UTF_8) =~ /\p{Word}/
    # ' aaa bb[cursor]b'
    byte_size = 0
    while 0 < (byte_pointer + byte_size)
      size = get_prev_mbchar_size(line, byte_pointer + byte_size)
      mbchar = line.byteslice(byte_pointer + byte_size - size, size)
      break if mbchar.encode(Encoding::UTF_8) =~ /\P{Word}/
      byte_size -= size
    end
    right_word_start = byte_pointer + byte_size
    byte_size = 0
    while line.bytesize > (byte_pointer + byte_size)
      size = get_next_mbchar_size(line, byte_pointer + byte_size)
      mbchar = line.byteslice(byte_pointer + byte_size, size)
      break if mbchar.encode(Encoding::UTF_8) =~ /\P{Word}/
      byte_size += size
    end
    after_start = byte_pointer + byte_size
  else
    byte_size = 0
    while (line.bytesize - 1) > (byte_pointer + byte_size)
      size = get_next_mbchar_size(line, byte_pointer + byte_size)
      mbchar = line.byteslice(byte_pointer + byte_size, size)
      break if mbchar.encode(Encoding::UTF_8) =~ /\p{Word}/
      byte_size += size
    end
    if (byte_pointer + byte_size) == (line.bytesize - 1)
      # ' aaa bbb [cursor] '
      after_start = line.bytesize
      while 0 < (byte_pointer + byte_size)
        size = get_prev_mbchar_size(line, byte_pointer + byte_size)
        mbchar = line.byteslice(byte_pointer + byte_size - size, size)
        break if mbchar.encode(Encoding::UTF_8) =~ /\p{Word}/
        byte_size -= size
      end
      while 0 < (byte_pointer + byte_size)
        size = get_prev_mbchar_size(line, byte_pointer + byte_size)
        mbchar = line.byteslice(byte_pointer + byte_size - size, size)
        break if mbchar.encode(Encoding::UTF_8) =~ /\P{Word}/
        byte_size -= size
      end
      right_word_start = byte_pointer + byte_size
    else
      # ' aaa [cursor] bbb '
      right_word_start = byte_pointer + byte_size
      while line.bytesize > (byte_pointer + byte_size)
        size = get_next_mbchar_size(line, byte_pointer + byte_size)
        mbchar = line.byteslice(byte_pointer + byte_size, size)
        break if mbchar.encode(Encoding::UTF_8) =~ /\P{Word}/
        byte_size += size
      end
      after_start = byte_pointer + byte_size
    end
  end
  byte_size = right_word_start - byte_pointer
  while 0 < (byte_pointer + byte_size)
    size = get_prev_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size - size, size)
    break if mbchar.encode(Encoding::UTF_8) =~ /\p{Word}/
    byte_size -= size
  end
  middle_start = byte_pointer + byte_size
  byte_size = middle_start - byte_pointer
  while 0 < (byte_pointer + byte_size)
    size = get_prev_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size - size, size)
    break if mbchar.encode(Encoding::UTF_8) =~ /\P{Word}/
    byte_size -= size
  end
  left_word_start = byte_pointer + byte_size
  [left_word_start, middle_start, right_word_start, after_start]
end

.em_backward_word(line, byte_pointer) ⇒ Object 



231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
 
# File 'lib/reline/unicode.rb', line 231

def self.em_backward_word(line, byte_pointer)
  width = 0
  byte_size = 0
  while 0 < (byte_pointer - byte_size)
    size = get_prev_mbchar_size(line, byte_pointer - byte_size)
    mbchar = line.byteslice(byte_pointer - byte_size - size, size)
    break if mbchar.encode(Encoding::UTF_8) =~ /\p{Word}/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  while 0 < (byte_pointer - byte_size)
    size = get_prev_mbchar_size(line, byte_pointer - byte_size)
    mbchar = line.byteslice(byte_pointer - byte_size - size, size)
    break if mbchar.encode(Encoding::UTF_8) =~ /\P{Word}/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [byte_size, width]
end

.em_big_backward_word(line, byte_pointer) ⇒ Object 



251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
 
# File 'lib/reline/unicode.rb', line 251

def self.em_big_backward_word(line, byte_pointer)
  width = 0
  byte_size = 0
  while 0 < (byte_pointer - byte_size)
    size = get_prev_mbchar_size(line, byte_pointer - byte_size)
    mbchar = line.byteslice(byte_pointer - byte_size - size, size)
    break if mbchar =~ /\S/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  while 0 < (byte_pointer - byte_size)
    size = get_prev_mbchar_size(line, byte_pointer - byte_size)
    mbchar = line.byteslice(byte_pointer - byte_size - size, size)
    break if mbchar =~ /\s/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [byte_size, width]
end

.em_forward_word(line, byte_pointer) ⇒ Object 



182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
 
# File 'lib/reline/unicode.rb', line 182

def self.em_forward_word(line, byte_pointer)
  width = 0
  byte_size = 0
  while line.bytesize > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    break if mbchar.encode(Encoding::UTF_8) =~ /\p{Word}/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  while line.bytesize > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    break if mbchar.encode(Encoding::UTF_8) =~ /\P{Word}/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [byte_size, width]
end

.em_forward_word_with_capitalization(line, byte_pointer) ⇒ Object 



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
 
# File 'lib/reline/unicode.rb', line 202

def self.em_forward_word_with_capitalization(line, byte_pointer)
  width = 0
  byte_size = 0
  new_str = String.new
  while line.bytesize > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    break if mbchar.encode(Encoding::UTF_8) =~ /\p{Word}/
    new_str += mbchar
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  first = true
  while line.bytesize > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    break if mbchar.encode(Encoding::UTF_8) =~ /\P{Word}/
    if first
      new_str += mbchar.upcase
      first = false
    else
      new_str += mbchar.downcase
    end
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [byte_size, width, new_str]
end

.escape_for_print(str) ⇒ Object 



64
65
66
67
68
69
70
71
72
73
 
# File 'lib/reline/unicode.rb', line 64

def self.escape_for_print(str)
  str.chars.map! { |gr|
    escaped = EscapedPairs[gr.ord]
    if escaped && gr != -"\n" && gr != -"\t"
      escaped
    else
      gr
    end
  }.join
end

.get_mbchar_byte_size_by_first_char(c) ⇒ Object 



44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
 
# File 'lib/reline/unicode.rb', line 44

def self.get_mbchar_byte_size_by_first_char(c)
  # Checks UTF-8 character byte size
  case c.ord
  # 0b0xxxxxxx
  when ->(code) { (code ^ 0b10000000).allbits?(0b10000000) } then 1
  # 0b110xxxxx
  when ->(code) { (code ^ 0b00100000).allbits?(0b11100000) } then 2
  # 0b1110xxxx
  when ->(code) { (code ^ 0b00010000).allbits?(0b11110000) } then 3
  # 0b11110xxx
  when ->(code) { (code ^ 0b00001000).allbits?(0b11111000) } then 4
  # 0b111110xx
  when ->(code) { (code ^ 0b00000100).allbits?(0b11111100) } then 5
  # 0b1111110x
  when ->(code) { (code ^ 0b00000010).allbits?(0b11111110) } then 6
  # successor of mbchar
  else 0
  end
end

.get_mbchar_width(mbchar) ⇒ Object 



94
95
96
97
98
99
100
101
102
103
104
 
# File 'lib/reline/unicode.rb', line 94

def self.get_mbchar_width(mbchar)
  m = mbchar.encode(Encoding::UTF_8).match(MBCharWidthRE)
  case
  when m[:width_2_1], m[:width_2_2] then 2
  when m[:width_3] then 3
  when m[:width_0] then 0
  when m[:width_1] then 1
  else
    nil
  end
end

.get_next_mbchar_size(line, byte_pointer) ⇒ Object 



168
169
170
171
 
# File 'lib/reline/unicode.rb', line 168

def self.get_next_mbchar_size(line, byte_pointer)
  grapheme = line.byteslice(byte_pointer..-1).grapheme_clusters.first
  grapheme ? grapheme.bytesize : 0
end

.get_prev_mbchar_size(line, byte_pointer) ⇒ Object 



173
174
175
176
177
178
179
180
 
# File 'lib/reline/unicode.rb', line 173

def self.get_prev_mbchar_size(line, byte_pointer)
  if byte_pointer.zero?
    0
  else
    grapheme = line.byteslice(0..(byte_pointer - 1)).grapheme_clusters.last
    grapheme ? grapheme.bytesize : 0
  end
end

.split_by_width(str, max_width, encoding = str.encoding) ⇒ Object 



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
 
# File 'lib/reline/unicode.rb', line 132

def self.split_by_width(str, max_width, encoding = str.encoding)
  lines = [String.new(encoding: encoding)]
  height = 1
  width = 0
  rest = str.encode(Encoding::UTF_8)
  in_zero_width = false
  rest.scan(WIDTH_SCANNER) do |gc|
    case gc
    when NON_PRINTING_START
      in_zero_width = true
    when NON_PRINTING_END
      in_zero_width = false
    when CSI_REGEXP, OSC_REGEXP
      lines.last << gc
    else
      unless in_zero_width
        mbchar_width = get_mbchar_width(gc)
        if (width += mbchar_width) > max_width
          width = mbchar_width
          lines << nil
          lines << String.new(encoding: encoding)
          height += 1
        end
      end
      lines.last << gc
    end
  end
  # The cursor moves to next line in first
  if width == max_width
    lines << nil
    lines << String.new(encoding: encoding)
    height += 1
  end
  [lines, height]
end

.vi_backward_word(line, byte_pointer) ⇒ Object 



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
 
# File 'lib/reline/unicode.rb', line 559

def self.vi_backward_word(line, byte_pointer)
  width = 0
  byte_size = 0
  while 0 < (byte_pointer - byte_size)
    size = get_prev_mbchar_size(line, byte_pointer - byte_size)
    mbchar = line.byteslice(byte_pointer - byte_size - size, size)
    if mbchar =~ /\S/
      if mbchar =~ /\w/
        started_by = :word
      else
        started_by = :non_word_printable
      end
      break
    end
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  while 0 < (byte_pointer - byte_size)
    size = get_prev_mbchar_size(line, byte_pointer - byte_size)
    mbchar = line.byteslice(byte_pointer - byte_size - size, size)
    case started_by
    when :word
      break if mbchar =~ /\W/
    when :non_word_printable
      break if mbchar =~ /[\w\s]/
    end
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [byte_size, width]
end

.vi_big_backward_word(line, byte_pointer) ⇒ Object 



422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
 
# File 'lib/reline/unicode.rb', line 422

def self.vi_big_backward_word(line, byte_pointer)
  width = 0
  byte_size = 0
  while 0 < (byte_pointer - byte_size)
    size = get_prev_mbchar_size(line, byte_pointer - byte_size)
    mbchar = line.byteslice(byte_pointer - byte_size - size, size)
    break if mbchar =~ /\S/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  while 0 < (byte_pointer - byte_size)
    size = get_prev_mbchar_size(line, byte_pointer - byte_size)
    mbchar = line.byteslice(byte_pointer - byte_size - size, size)
    break if mbchar =~ /\s/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [byte_size, width]
end

.vi_big_forward_end_word(line, byte_pointer) ⇒ Object 



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
 
# File 'lib/reline/unicode.rb', line 392

def self.vi_big_forward_end_word(line, byte_pointer)
  if (line.bytesize - 1) > byte_pointer
    size = get_next_mbchar_size(line, byte_pointer)
    mbchar = line.byteslice(byte_pointer, size)
    width = get_mbchar_width(mbchar)
    byte_size = size
  else
    return [0, 0]
  end
  while (line.bytesize - 1) > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    break if mbchar =~ /\S/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  prev_width = width
  prev_byte_size = byte_size
  while line.bytesize > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    break if mbchar =~ /\s/
    prev_width = width
    prev_byte_size = byte_size
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [prev_byte_size, prev_width]
end

.vi_big_forward_word(line, byte_pointer) ⇒ Object 



372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
 
# File 'lib/reline/unicode.rb', line 372

def self.vi_big_forward_word(line, byte_pointer)
  width = 0
  byte_size = 0
  while (line.bytesize - 1) > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    break if mbchar =~ /\s/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  while (line.bytesize - 1) > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    break if mbchar =~ /\S/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [byte_size, width]
end

.vi_first_print(line) ⇒ Object 



591
592
593
594
595
596
597
598
599
600
601
602
603
604
 
# File 'lib/reline/unicode.rb', line 591

def self.vi_first_print(line)
  width = 0
  byte_size = 0
  while (line.bytesize - 1) > byte_size
    size = get_next_mbchar_size(line, byte_size)
    mbchar = line.byteslice(byte_size, size)
    if mbchar =~ /\S/
      break
    end
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [byte_size, width]
end

.vi_forward_end_word(line, byte_pointer) ⇒ Object 



482
483
484
485
486
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
 
# File 'lib/reline/unicode.rb', line 482

def self.vi_forward_end_word(line, byte_pointer)
  if (line.bytesize - 1) > byte_pointer
    size = get_next_mbchar_size(line, byte_pointer)
    mbchar = line.byteslice(byte_pointer, size)
    if mbchar =~ /\w/
      started_by = :word
    elsif mbchar =~ /\s/
      started_by = :space
    else
      started_by = :non_word_printable
    end
    width = get_mbchar_width(mbchar)
    byte_size = size
  else
    return [0, 0]
  end
  if (line.bytesize - 1) > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    if mbchar =~ /\w/
      second = :word
    elsif mbchar =~ /\s/
      second = :space
    else
      second = :non_word_printable
    end
    second_width = get_mbchar_width(mbchar)
    second_byte_size = size
  else
    return [byte_size, width]
  end
  if second == :space
    width += second_width
    byte_size += second_byte_size
    while (line.bytesize - 1) > (byte_pointer + byte_size)
      size = get_next_mbchar_size(line, byte_pointer + byte_size)
      mbchar = line.byteslice(byte_pointer + byte_size, size)
      if mbchar =~ /\S/
        if mbchar =~ /\w/
          started_by = :word
        else
          started_by = :non_word_printable
        end
        break
      end
      width += get_mbchar_width(mbchar)
      byte_size += size
    end
  else
    case [started_by, second]
    when [:word, :non_word_printable], [:non_word_printable, :word]
      started_by = second
    else
      width += second_width
      byte_size += second_byte_size
      started_by = second
    end
  end
  prev_width = width
  prev_byte_size = byte_size
  while line.bytesize > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    case started_by
    when :word
      break if mbchar =~ /\W/
    when :non_word_printable
      break if mbchar =~ /[\w\s]/
    end
    prev_width = width
    prev_byte_size = byte_size
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [prev_byte_size, prev_width]
end

.vi_forward_word(line, byte_pointer) ⇒ Object 



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
 
# File 'lib/reline/unicode.rb', line 442

def self.vi_forward_word(line, byte_pointer)
  if (line.bytesize - 1) > byte_pointer
    size = get_next_mbchar_size(line, byte_pointer)
    mbchar = line.byteslice(byte_pointer, size)
    if mbchar =~ /\w/
      started_by = :word
    elsif mbchar =~ /\s/
      started_by = :space
    else
      started_by = :non_word_printable
    end
    width = get_mbchar_width(mbchar)
    byte_size = size
  else
    return [0, 0]
  end
  while (line.bytesize - 1) > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    case started_by
    when :word
      break if mbchar =~ /\W/
    when :space
      break if mbchar =~ /\S/
    when :non_word_printable
      break if mbchar =~ /\w|\s/
    end
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  while (line.bytesize - 1) > (byte_pointer + byte_size)
    size = get_next_mbchar_size(line, byte_pointer + byte_size)
    mbchar = line.byteslice(byte_pointer + byte_size, size)
    break if mbchar =~ /\S/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [byte_size, width]
end