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)
NON_PRINTING_START = 
"\1"
NON_PRINTING_END = 
"\2"
CSI_REGEXP = 
/\e\[[\d;]*[ABCDEFGHJKSTfminsuhl]/
OSC_REGEXP = 
/\e\]\d+(?:;[^;\a\e]+)*(?:\a|\e\\)/
WIDTH_SCANNER = 
/\G(?:(#{NON_PRINTING_START})|(#{NON_PRINTING_END})|(#{CSI_REGEXP})|(#{OSC_REGEXP})|(\X))/o

Class Method Summary collapse

Class Method Details

.calculate_width(str, allow_escape_code = false) ⇒ Object 



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
 
# File 'lib/reline/unicode.rb', line 98

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 |non_printing_start, non_printing_end, csi, osc, gc|
      case
      when non_printing_start
        in_zero_width = true
      when non_printing_end
        in_zero_width = false
      when csi, osc
      when gc
        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 



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
 
# File 'lib/reline/unicode.rb', line 352

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 



312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
 
# File 'lib/reline/unicode.rb', line 312

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 



332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
 
# File 'lib/reline/unicode.rb', line 332

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 



263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
 
# File 'lib/reline/unicode.rb', line 263

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 



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
 
# File 'lib/reline/unicode.rb', line 283

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 



44
45
46
47
48
49
50
51
52
53
54
55
 
# File 'lib/reline/unicode.rb', line 44

def self.escape_for_print(str)
  str.chars.map! { |gr|
    case gr
    when -"\n"
      gr
    when -"\t"
      -'  '
    else
      EscapedPairs[gr.ord] || gr
    end
  }.join
end

.get_mbchar_width(mbchar) ⇒ Object 



75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
 
# File 'lib/reline/unicode.rb', line 75

def self.get_mbchar_width(mbchar)
  ord = mbchar.ord
  if ord <= 0x1F # in EscapedPairs
    return 2
  elsif ord <= 0x7E # printable ASCII chars
    return 1
  end
  utf8_mbchar = mbchar.encode(Encoding::UTF_8)
  ord = utf8_mbchar.ord
  chunk_index = EastAsianWidth::CHUNK_LAST.bsearch_index { |o| ord <= o }
  size = EastAsianWidth::CHUNK_WIDTH[chunk_index]
  if size == -1
    Reline.ambiguous_width
  elsif size == 1 && utf8_mbchar.size >= 2
    second_char_ord = utf8_mbchar[1].ord
    # Halfwidth Dakuten Handakuten
    # Only these two character has Letter Modifier category and can be combined in a single grapheme cluster
    (second_char_ord == 0xFF9E || second_char_ord == 0xFF9F) ? 2 : 1
  else
    size
  end
end

.get_next_mbchar_size(line, byte_pointer) ⇒ Object 



249
250
251
252
 
# File 'lib/reline/unicode.rb', line 249

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 



254
255
256
257
258
259
260
261
 
# File 'lib/reline/unicode.rb', line 254

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

.safe_encode(str, encoding) ⇒ Object 



57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
 
# File 'lib/reline/unicode.rb', line 57

def self.safe_encode(str, encoding)
  # Reline only supports utf-8 convertible string.
  converted = str.encode(encoding, invalid: :replace, undef: :replace)
  return converted if str.encoding == Encoding::UTF_8 || converted.encoding == Encoding::UTF_8 || converted.ascii_only?

  # This code is essentially doing the same thing as
  # `str.encode(utf8, **replace_options).encode(encoding, **replace_options)`
  # but also avoids unneccesary irreversible encoding conversion.
  converted.gsub(/\X/) do |c|
    c.encode(Encoding::UTF_8)
    c
  rescue Encoding::UndefinedConversionError
    '?'
  end
end

.split_by_width(str, max_width, encoding = str.encoding, offset: 0) ⇒ Object 



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
 
# File 'lib/reline/unicode.rb', line 124

def self.split_by_width(str, max_width, encoding = str.encoding, offset: 0)
  lines = [String.new(encoding: encoding)]
  height = 1
  width = offset
  rest = str.encode(Encoding::UTF_8)
  in_zero_width = false
  seq = String.new(encoding: encoding)
  rest.scan(WIDTH_SCANNER) do |non_printing_start, non_printing_end, csi, osc, gc|
    case
    when non_printing_start
      in_zero_width = true
    when non_printing_end
      in_zero_width = false
    when csi
      lines.last << csi
      unless in_zero_width
        if csi == -"\e[m" || csi == -"\e[0m"
          seq.clear
        else
          seq << csi
        end
      end
    when osc
      lines.last << osc
      seq << osc unless in_zero_width
    when gc
      unless in_zero_width
        mbchar_width = get_mbchar_width(gc)
        if (width += mbchar_width) > max_width
          width = mbchar_width
          lines << nil
          lines << seq.dup
          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

.strip_non_printing_start_end(prompt) ⇒ Object 



171
172
173
 
# File 'lib/reline/unicode.rb', line 171

def self.strip_non_printing_start_end(prompt)
  prompt.gsub(/\x01([^\x02]*)(?:\x02|\z)/) { $1 }
end

.take_mbchar_range(str, start_col, width, cover_begin: false, cover_end: false, padding: false) ⇒ Object 



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
 
# File 'lib/reline/unicode.rb', line 180

def self.take_mbchar_range(str, start_col, width, cover_begin: false, cover_end: false, padding: false)
  chunk = String.new(encoding: str.encoding)

  end_col = start_col + width
  total_width = 0
  rest = str.encode(Encoding::UTF_8)
  in_zero_width = false
  chunk_start_col = nil
  chunk_end_col = nil
  has_csi = false
  rest.scan(WIDTH_SCANNER) do |non_printing_start, non_printing_end, csi, osc, gc|
    case
    when non_printing_start
      in_zero_width = true
    when non_printing_end
      in_zero_width = false
    when csi
      has_csi = true
      chunk << csi
    when osc
      chunk << osc
    when gc
      if in_zero_width
        chunk << gc
        next
      end

      mbchar_width = get_mbchar_width(gc)
      prev_width = total_width
      total_width += mbchar_width

      if (cover_begin || padding ? total_width <= start_col : prev_width < start_col)
        # Current character haven't reached start_col yet
        next
      elsif padding && !cover_begin && prev_width < start_col && start_col < total_width
        # Add preceding padding. This padding might have background color.
        chunk << ' '
        chunk_start_col ||= start_col
        chunk_end_col = total_width
        next
      elsif (cover_end ? prev_width < end_col : total_width <= end_col)
        # Current character is in the range
        chunk << gc
        chunk_start_col ||= prev_width
        chunk_end_col = total_width
        break if total_width >= end_col
      else
        # Current character exceeds end_col
        if padding && end_col < total_width
          # Add succeeding padding. This padding might have background color.
          chunk << ' '
          chunk_start_col ||= prev_width
          chunk_end_col = end_col
        end
        break
      end
    end
  end
  chunk_start_col ||= start_col
  chunk_end_col ||= start_col
  if padding && chunk_end_col < end_col
    # Append padding. This padding should not include background color.
    chunk << "\e[0m" if has_csi
    chunk << ' ' * (end_col - chunk_end_col)
    chunk_end_col = end_col
  end
  [chunk, chunk_start_col, chunk_end_col - chunk_start_col]
end

.take_range(str, start_col, max_width) ⇒ Object

Take a chunk of a String cut by width with escape sequences.



176
177
178
 
# File 'lib/reline/unicode.rb', line 176

def self.take_range(str, start_col, max_width)
  take_mbchar_range(str, start_col, max_width).first
end

.vi_backward_word(line, byte_pointer) ⇒ Object 



641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
 
# File 'lib/reline/unicode.rb', line 641

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 



503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
 
# File 'lib/reline/unicode.rb', line 503

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 



473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
 
# File 'lib/reline/unicode.rb', line 473

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 



453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
 
# File 'lib/reline/unicode.rb', line 453

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 



673
674
675
676
677
678
679
680
681
682
683
684
685
686
 
# File 'lib/reline/unicode.rb', line 673

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 



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
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
 
# File 'lib/reline/unicode.rb', line 564

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, drop_terminate_spaces = false) ⇒ Object 



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
 
# File 'lib/reline/unicode.rb', line 523

def self.vi_forward_word(line, byte_pointer, drop_terminate_spaces = false)
  if line.bytesize > 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 > (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
  return [byte_size, width] if drop_terminate_spaces
  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/
    width += get_mbchar_width(mbchar)
    byte_size += size
  end
  [byte_size, width]
end