/
string19.rb
751 lines (633 loc) · 22.2 KB
/
string19.rb
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
464
465
466
467
468
469
470
471
472
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
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
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
640
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
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
class String
def self.try_convert(obj)
Rubinius::Type.try_convert obj, String, :to_str
end
def initialize(arg = undefined)
Rubinius.check_frozen
replace StringValue(arg) unless arg.equal?(undefined)
self
end
private :initialize
def encode(to=undefined, from=undefined, options=nil)
# TODO
self
end
def hex
return 0 if self.chars.first == "_"
to_inum(16, false)
end
def partition(pattern)
unless pattern.is_a? Regexp
pattern = Rubinius::Type.coerce_to(pattern, String, :to_str)
end
i = index(pattern)
return [self, "", ""] unless i
if pattern.is_a? Regexp
match = Regexp.last_match
[match.pre_match, match[0], match.post_match]
else
last = i+pattern.length
[self[0...i], self[i...last], self[last...length]]
end
end
def upto(stop, exclusive=false)
return to_enum :upto, stop, exclusive unless block_given?
stop = StringValue(stop)
return self if self > stop
if stop.size == 1 && size == 1
after_stop = stop.getbyte(0) + (exclusive ? 0 : 1)
current = getbyte(0)
until current == after_stop
yield current.chr
current += 1
end
else
unless stop.size < size
after_stop = exclusive ? stop : stop.succ
current = self
until current == after_stop
yield current
current = StringValue(current.succ)
break if current.size > stop.size || current.size == 0
end
end
end
self
end
def ord
raise ArgumentError, 'empty string' if empty?
@data[0]
end
def encoding
# TODO: temporary until encoding is set on create.
@encoding ||= Encoding.find("us-ascii")
end
def force_encoding(name)
self
end
# Reverses <i>self</i> in place.
def reverse!
Rubinius.check_frozen
return self if @num_bytes <= 1
self.modify!
@data.reverse(0, @num_bytes)
self
end
# Squeezes <i>self</i> in place, returning either <i>self</i>, or
# <code>nil</code> if no changes were made.
def squeeze!(*strings)
if strings.first =~ /.+\-.+/
range = strings.first.gsub(/-/, '').split('')
raise ArgumentError, "invalid range #{strings} in string transliteration" unless range == range.sort
end
return if @num_bytes == 0
self.modify!
table = count_table(*strings).__data__
i, j, last = 1, 0, @data[0]
while i < @num_bytes
c = @data[i]
unless c == last and table[c] == 1
@data[j+=1] = last = c
end
i += 1
end
if (j += 1) < @num_bytes
@num_bytes = j
self
else
nil
end
end
# Performs the substitutions of <code>String#sub</code> in place,
# returning <i>self</i>, or <code>nil</code> if no substitutions were
# performed.
#
def sub!(pattern, replacement=undefined)
# Copied mostly from sub to keep Regexp.last_match= working right.
if replacement.equal?(undefined) and !block_given?
raise ArgumentError, "wrong number of arguments (1 for 2)"
end
unless pattern
raise ArgumentError, "wrong number of arguments (0 for 2)"
end
Rubinius.check_frozen
if match = get_pattern(pattern, true).match_from(self, 0)
out = match.pre_match
Regexp.last_match = match
if replacement.equal?(undefined)
replacement = yield(match[0].dup).to_s
out.taint if replacement.tainted?
out.append(replacement).append(match.post_match)
else
out.taint if replacement.tainted?
replacement = StringValue(replacement).to_sub_replacement(out, match)
out.append(match.post_match)
end
# We have to reset it again to match the specs
Regexp.last_match = match
out.taint if self.tainted?
else
out = self
Regexp.last_match = nil
return nil
end
replace(out)
return self
end
# Deletes the specified portion from <i>self</i>, and returns the portion
# deleted. The forms that take a <code>Fixnum</code> will raise an
# <code>IndexError</code> if the value is out of range; the <code>Range</code>
# form will raise a <code>RangeError</code>, and the <code>Regexp</code> and
# <code>String</code> forms will silently ignore the assignment.
#
# string = "this is a string"
# string.slice!(2) #=> 105
# string.slice!(3..6) #=> " is "
# string.slice!(/s.*t/) #=> "sa st"
# string.slice!("r") #=> "r"
# string #=> "thing"
def slice!(one, two=undefined)
Rubinius.check_frozen
# This is un-DRY, but it's a simple manual argument splitting. Keeps
# the code fast and clean since the sequence are pretty short.
#
if two.equal?(undefined)
result = slice(one)
if one.kind_of? Regexp
lm = Regexp.last_match
self[one] = '' if result
Regexp.last_match = lm
else
self[one] = '' if result
end
else
result = slice(one, two)
if one.kind_of? Regexp
lm = Regexp.last_match
self[one, two] = '' if result
Regexp.last_match = lm
else
self[one, two] = '' if result
end
end
result
end
# Equivalent to <code>String#succ</code>, but modifies the receiver in
# place.
#
# TODO: make encoding aware.
def succ!
self.modify!
return self if @num_bytes == 0
carry = nil
last_alnum = 0
start = @num_bytes - 1
ctype = Rubinius::CType
while start >= 0
s = @data[start]
if ctype.isalnum(s)
carry = 0
if (48 <= s && s < 57) ||
(97 <= s && s < 122) ||
(65 <= s && s < 90)
@data[start] += 1
elsif s == 57
@data[start] = 48
carry = 49
elsif s == 122
@data[start] = carry = 97
elsif s == 90
@data[start] = carry = 65
end
break if carry == 0
last_alnum = start
end
start -= 1
end
if carry.nil?
start = length - 1
carry = 1
while start >= 0
if @data[start] >= 255
@data[start] = 0
else
@data[start] += 1
break
end
start -= 1
end
end
if start < 0
splice! last_alnum, 1, carry.chr + @data[last_alnum].chr
end
return self
end
alias_method :next, :succ
alias_method :next!, :succ!
def to_r
return Rational(0,1) if empty?
clean = strip
numerator = clean.gsub(".", "").to_i
denominator = 1
if clean.match(/\d\.\d/)
denominator = 10**clean.split(".")[1].to_i.to_s.length
end
if clean.match(/\d\/\d/)
denominator *= clean.split("/")[1].to_i
end
return Rational(numerator, denominator)
end
##
# call-seq:
# str.unpack(format) => anArray
#
# Decodes <i>str</i> (which may contain binary data) according to
# the format string, returning an array of each value
# extracted. The format string consists of a sequence of
# single-character directives, summarized in the table at the end
# of this entry.
#
# Each directive may be followed by a number, indicating the number
# of times to repeat with this directive. An asterisk
# (``<code>*</code>'') will use up all remaining elements. The
# directives <code>sSiIlL</code> may each be followed by an
# underscore (``<code>_</code>'') to use the underlying platform's
# native size for the specified type; otherwise, it uses a
# platform-independent consistent size. Spaces are ignored in the
# format string. See also <code>Array#pack</code>.
#
# "abc \0\0abc \0\0".unpack('A6Z6') #=> ["abc", "abc "]
# "abc \0\0".unpack('a3a3') #=> ["abc", " \000\000"]
# "abc \0abc \0".unpack('Z*Z*') #=> ["abc ", "abc "]
# "aa".unpack('b8B8') #=> ["10000110", "01100001"]
# "aaa".unpack('h2H2c') #=> ["16", "61", 97]
# "\xfe\xff\xfe\xff".unpack('sS') #=> [-2, 65534]
# "now=20is".unpack('M*') #=> ["now is"]
# "whole".unpack('xax2aX2aX1aX2a') #=> ["h", "e", "l", "l", "o"]
#
# This table summarizes the various formats and the Ruby classes
# returned by each.
#
# Format | Returns | Function
# -------+---------+-----------------------------------------
# A | String | with trailing nulls and spaces removed
# -------+---------+-----------------------------------------
# a | String | string
# -------+---------+-----------------------------------------
# B | String | extract bits from each character (msb first)
# -------+---------+-----------------------------------------
# b | String | extract bits from each character (lsb first)
# -------+---------+-----------------------------------------
# C | Fixnum | extract a character as an unsigned integer
# -------+---------+-----------------------------------------
# c | Fixnum | extract a character as an integer
# -------+---------+-----------------------------------------
# d,D | Float | treat sizeof(double) characters as
# | | a native double
# -------+---------+-----------------------------------------
# E | Float | treat sizeof(double) characters as
# | | a double in little-endian byte order
# -------+---------+-----------------------------------------
# e | Float | treat sizeof(float) characters as
# | | a float in little-endian byte order
# -------+---------+-----------------------------------------
# f,F | Float | treat sizeof(float) characters as
# | | a native float
# -------+---------+-----------------------------------------
# G | Float | treat sizeof(double) characters as
# | | a double in network byte order
# -------+---------+-----------------------------------------
# g | Float | treat sizeof(float) characters as a
# | | float in network byte order
# -------+---------+-----------------------------------------
# H | String | extract hex nibbles from each character
# | | (most significant first)
# -------+---------+-----------------------------------------
# h | String | extract hex nibbles from each character
# | | (least significant first)
# -------+---------+-----------------------------------------
# I | Integer | treat sizeof(int) (modified by _)
# | | successive characters as an unsigned
# | | native integer
# -------+---------+-----------------------------------------
# i | Integer | treat sizeof(int) (modified by _)
# | | successive characters as a signed
# | | native integer
# -------+---------+-----------------------------------------
# L | Integer | treat four (modified by _) successive
# | | characters as an unsigned native
# | | long integer
# -------+---------+-----------------------------------------
# l | Integer | treat four (modified by _) successive
# | | characters as a signed native
# | | long integer
# -------+---------+-----------------------------------------
# M | String | quoted-printable
# -------+---------+-----------------------------------------
# m | String | base64-encoded
# -------+---------+-----------------------------------------
# N | Integer | treat four characters as an unsigned
# | | long in network byte order
# -------+---------+-----------------------------------------
# n | Fixnum | treat two characters as an unsigned
# | | short in network byte order
# -------+---------+-----------------------------------------
# P | String | treat sizeof(char *) characters as a
# | | pointer, and return \emph{len} characters
# | | from the referenced location
# -------+---------+-----------------------------------------
# p | String | treat sizeof(char *) characters as a
# | | pointer to a null-terminated string
# -------+---------+-----------------------------------------
# Q | Integer | treat 8 characters as an unsigned
# | | quad word (64 bits)
# -------+---------+-----------------------------------------
# q | Integer | treat 8 characters as a signed
# | | quad word (64 bits)
# -------+---------+-----------------------------------------
# S | Fixnum | treat two (different if _ used)
# | | successive characters as an unsigned
# | | short in native byte order
# -------+---------+-----------------------------------------
# s | Fixnum | Treat two (different if _ used)
# | | successive characters as a signed short
# | | in native byte order
# -------+---------+-----------------------------------------
# U | Integer | UTF-8 characters as unsigned integers
# -------+---------+-----------------------------------------
# u | String | UU-encoded
# -------+---------+-----------------------------------------
# V | Fixnum | treat four characters as an unsigned
# | | long in little-endian byte order
# -------+---------+-----------------------------------------
# v | Fixnum | treat two characters as an unsigned
# | | short in little-endian byte order
# -------+---------+-----------------------------------------
# w | Integer | BER-compressed integer (see Array.pack)
# -------+---------+-----------------------------------------
# X | --- | skip backward one character
# -------+---------+-----------------------------------------
# x | --- | skip forward one character
# -------+---------+-----------------------------------------
# Z | String | with trailing nulls removed
# | | upto first null with *
# -------+---------+-----------------------------------------
# @ | --- | skip to the offset given by the
# | | length argument
# -------+---------+-----------------------------------------
def unpack(directives)
Rubinius.primitive :string_unpack19
unless directives.kind_of? String
return unpack(StringValue(directives))
end
raise ArgumentError, "invalid directives string: #{directives}"
end
# Removes trailing whitespace from <i>self</i>, returning <code>nil</code> if
# no change was made. See also <code>String#lstrip!</code> and
# <code>String#strip!</code>.
#
# " hello ".rstrip #=> " hello"
# "hello".rstrip! #=> nil
def rstrip!
Rubinius.check_frozen
return if @num_bytes == 0
stop = @num_bytes - 1
ctype = Rubinius::CType
while stop >= 0 && (@data[stop] == 0 || ctype.isspace(@data[stop]))
stop -= 1
end
return if (stop += 1) == @num_bytes
modify!
@num_bytes = stop
self
end
# Removes leading whitespace from <i>self</i>, returning <code>nil</code> if no
# change was made. See also <code>String#rstrip!</code> and
# <code>String#strip!</code>.
#
# " hello ".lstrip #=> "hello "
# "hello".lstrip! #=> nil
def lstrip!
Rubinius.check_frozen
return if @num_bytes == 0
start = 0
ctype = Rubinius::CType
while start < @num_bytes && ctype.isspace(@data[start])
start += 1
end
return if start == 0
modify!
@num_bytes = @num_bytes - start
@data.move_bytes start, @num_bytes, 0
self
end
# Processes <i>self</i> as for <code>String#chop</code>, returning <i>self</i>,
# or <code>nil</code> if <i>self</i> is the empty string. See also
# <code>String#chomp!</code>.
def chop!
Rubinius.check_frozen
return if @num_bytes == 0
self.modify!
if @num_bytes > 1 and
@data[@num_bytes-1] == 10 and @data[@num_bytes-2] == 13
@num_bytes = @num_bytes - 2
else
@num_bytes = @num_bytes - 1
end
self
end
# Modifies <i>self</i> in place as described for <code>String#chomp</code>,
# returning <i>self</i>, or <code>nil</code> if no modifications were made.
#---
# NOTE: TypeError is raised in String#replace and not in String#chomp! when
# self is frozen. This is intended behaviour.
#+++
def chomp!(sep=undefined)
Rubinius.check_frozen
# special case for performance. No seperator is by far the most common usage.
if sep.equal?(undefined)
return if @num_bytes == 0
c = @data[@num_bytes-1]
if c == 10 # ?\n
@num_bytes -= 1 if @num_bytes > 1 && @data[@num_bytes-2] == 13 # ?\r
elsif c != 13 # ?\r
return
end
# don't use modify! because it will dup the data when we don't need to.
@hash_value = nil
@num_bytes = @num_bytes - 1
return self
end
return if sep.nil? || @num_bytes == 0
sep = StringValue sep
if (sep == $/ && sep == DEFAULT_RECORD_SEPARATOR) || sep == "\n"
c = @data[@num_bytes-1]
if c == 10 # ?\n
@num_bytes -= 1 if @num_bytes > 1 && @data[@num_bytes-2] == 13 # ?\r
elsif c != 13 # ?\r
return
end
# don't use modify! because it will dup the data when we don't need to.
@hash_value = nil
@num_bytes = @num_bytes - 1
elsif sep.size == 0
size = @num_bytes
while size > 0 && @data[size-1] == 10 # ?\n
if size > 1 && @data[size-2] == 13 # ?\r
size -= 2
else
size -= 1
end
end
return if size == @num_bytes
# don't use modify! because it will dup the data when we don't need to.
@hash_value = nil
@num_bytes = size
else
size = sep.size
return if size > @num_bytes || sep.compare_substring(self, -size, size) != 0
# don't use modify! because it will dup the data when we don't need to.
@hash_value = nil
@num_bytes = @num_bytes - size
end
return self
end
# Replaces the contents and taintedness of <i>string</i> with the corresponding
# values in <i>other</i>.
#
# s = "hello" #=> "hello"
# s.replace "world" #=> "world"
def replace(other)
Rubinius.check_frozen
# If we're replacing with ourselves, then we have nothing to do
return self if equal?(other)
other = StringValue(other)
@shared = true
other.shared!
@data = other.__data__
@num_bytes = other.num_bytes
@hash_value = nil
taint if other.tainted?
self
end
alias_method :initialize_copy, :replace
# private :initialize_copy
# Returns a new string with the characters from <i>self</i> in reverse order.
#
# "stressed".reverse #=> "desserts"
# Append --- Concatenates the given object to <i>self</i>. If the object is a
# <code>Fixnum</code> between 0 and 255, it is converted to a character before
# concatenation.
#
# a = "hello "
# a << "world" #=> "hello world"
# a.concat(33) #=> "hello world!"
def <<(other)
modify!
unless other.kind_of? String
if other.kind_of?(Integer) && other >= 0 && other <= 255
other = other.chr
elsif other.kind_of?(Integer) && other < 0
raise RangeError, "negative argument"
else
other = StringValue(other)
end
end
taint if other.tainted?
append(other)
end
alias_method :concat, :<<
# Returns a one-character string at the beginning of the string.
#
# a = "abcde"
# a.chr #=> "a"
def chr
if empty?
self
else
self[0]
end
end
# Splits <i>self</i> using the supplied parameter as the record separator
# (<code>$/</code> by default), passing each substring in turn to the supplied
# block. If a zero-length record separator is supplied, the string is split on
# <code>\n</code> characters, except that multiple successive newlines are
# appended together.
#
# print "Example one\n"
# "hello\nworld".each { |s| p s }
# print "Example two\n"
# "hello\nworld".each('l') { |s| p s }
# print "Example three\n"
# "hello\n\n\nworld".each('') { |s| p s }
#
# <em>produces:</em>
#
# Example one
# "hello\n"
# "world"
# Example two
# "hel"
# "l"
# "o\nworl"
# "d"
# Example three
# "hello\n\n\n"
# "world"
def each_line(sep=$/)
return to_enum(:each_line, sep) unless block_given?
# weird edge case.
if sep.nil?
yield self
return self
end
sep = StringValue(sep)
pos = 0
size = @num_bytes
orig_data = @data
# If the separator is empty, we're actually in paragraph mode. This
# is used so infrequently, we'll handle it completely separately from
# normal line breaking.
if sep.empty?
sep = "\n\n"
pat_size = 2
while pos < size
nxt = find_string(sep, pos)
break unless nxt
while @data[nxt] == 10 and nxt < @num_bytes
nxt += 1
end
match_size = nxt - pos
# string ends with \n's
break if pos == @num_bytes
str = substring(pos, match_size)
yield str unless str.empty?
# detect mutation within the block
if !@data.equal?(orig_data) or @num_bytes != size
raise RuntimeError, "string modified while iterating"
end
pos = nxt
end
# No more separates, but we need to grab the last part still.
fin = substring(pos, @num_bytes - pos)
yield fin if fin and !fin.empty?
else
# This is the normal case.
pat_size = sep.size
unmodified_self = clone
while pos < size
nxt = unmodified_self.find_string(sep, pos)
break unless nxt
match_size = nxt - pos
str = unmodified_self.substring(pos, match_size + pat_size)
yield str unless str.empty?
pos = nxt + pat_size
end
# No more separates, but we need to grab the last part still.
fin = unmodified_self.substring(pos, @num_bytes - pos)
yield fin unless fin.empty?
end
self
end
alias_method :lines, :each_line
end