lz_string 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/README.md +2 -0
- data/lib/lz_string/base.rb +397 -0
- data/lib/lz_string/base64.rb +51 -0
- data/lib/lz_string/utf16.rb +24 -0
- data/lib/lz_string/version.rb +4 -0
- data/lib/lz_string.rb +23 -0
- metadata +49 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 536eca3d25c94ce1558bd881c8f09dfa5dab331a7d3c3da19a5166681ad2ac41
|
4
|
+
data.tar.gz: 86d3a24237c3e1654b9b3c29bf7978435e68cf4caa6a22a66b04472ac222b3df
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 311b8e802592b7c364c43f031c89b6fa104b76637c2679d6a0d7f8955ffd40e63e55d48543e9f371f64a38e23e6bdce9d1a7b3985057b10a8717ca699b89cdcb
|
7
|
+
data.tar.gz: d1e2f28b4c9ed85483254ed7d7f8f90cdb438f112b115e0f893be9a91986714990805acd1ba0a2126bf92e79a60b19660ac98c5e953903cd3c678d6511e822a6
|
data/README.md
ADDED
@@ -0,0 +1,397 @@
|
|
1
|
+
module LZString
|
2
|
+
# Base compression class.
|
3
|
+
class Base
|
4
|
+
# @param uncompressed [String]
|
5
|
+
# @param bits_per_char [Integer]
|
6
|
+
# @param get_char_from_int [Integer]
|
7
|
+
def self.compress(uncompressed, bits_per_char, get_char_from_int)
|
8
|
+
return "" if uncompressed.nil?
|
9
|
+
|
10
|
+
i, value, ii = nil
|
11
|
+
context_dictionary = {}
|
12
|
+
context_dictionary_to_create = {}
|
13
|
+
context_c = ""
|
14
|
+
context_wc = ""
|
15
|
+
context_w = ""
|
16
|
+
# Compensate for the first entry which should not count
|
17
|
+
context_enlarge_in = 2
|
18
|
+
context_dict_size = 3
|
19
|
+
context_num_bits = 2
|
20
|
+
context_data = []
|
21
|
+
context_data_val = 0
|
22
|
+
context_data_position = 0
|
23
|
+
|
24
|
+
for ii in 0...uncompressed.length do
|
25
|
+
context_c = uncompressed[ii]
|
26
|
+
|
27
|
+
if (!context_dictionary.has_key?(context_c))
|
28
|
+
context_dictionary[context_c] = context_dict_size
|
29
|
+
context_dictionary_to_create[context_c] = true
|
30
|
+
context_dict_size += 1
|
31
|
+
end
|
32
|
+
|
33
|
+
context_wc = context_w + context_c
|
34
|
+
if (context_dictionary.has_key?(context_wc))
|
35
|
+
context_w = context_wc
|
36
|
+
else
|
37
|
+
if (context_dictionary_to_create.has_key?(context_w))
|
38
|
+
if (context_w[0].ord < 256)
|
39
|
+
for i in 0...context_num_bits do
|
40
|
+
context_data_val = (context_data_val << 1)
|
41
|
+
if (context_data_position == bits_per_char - 1)
|
42
|
+
context_data_position = 0
|
43
|
+
context_data.push(get_char_from_int[context_data_val])
|
44
|
+
context_data_val = 0
|
45
|
+
else
|
46
|
+
context_data_position += 1
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
value = context_w[0].ord
|
51
|
+
for i in 0...8 do
|
52
|
+
context_data_val = (context_data_val << 1) | (value & 1)
|
53
|
+
if (context_data_position == bits_per_char - 1)
|
54
|
+
context_data_position = 0
|
55
|
+
context_data.push(get_char_from_int[context_data_val])
|
56
|
+
context_data_val = 0
|
57
|
+
else
|
58
|
+
context_data_position += 1
|
59
|
+
end
|
60
|
+
value = value >> 1
|
61
|
+
end
|
62
|
+
else
|
63
|
+
value = 1
|
64
|
+
for i in 0...context_num_bits do
|
65
|
+
context_data_val = (context_data_val << 1) | value
|
66
|
+
if (context_data_position == bits_per_char-1)
|
67
|
+
context_data_position = 0
|
68
|
+
context_data.push(get_char_from_int[context_data_val])
|
69
|
+
context_data_val = 0
|
70
|
+
else
|
71
|
+
context_data_position += 1
|
72
|
+
end
|
73
|
+
value = 0
|
74
|
+
end
|
75
|
+
value = context_w[0].ord
|
76
|
+
for i in 0...16 do
|
77
|
+
context_data_val = (context_data_val << 1) | (value & 1)
|
78
|
+
if (context_data_position == bits_per_char - 1)
|
79
|
+
context_data_position = 0
|
80
|
+
context_data.push(get_char_from_int[context_data_val])
|
81
|
+
context_data_val = 0
|
82
|
+
else
|
83
|
+
context_data_position += 1
|
84
|
+
end
|
85
|
+
value = value >> 1
|
86
|
+
end
|
87
|
+
end
|
88
|
+
context_enlarge_in -= 1
|
89
|
+
if (context_enlarge_in == 0)
|
90
|
+
context_enlarge_in = 2**context_num_bits
|
91
|
+
context_num_bits += 1
|
92
|
+
end
|
93
|
+
context_dictionary_to_create.delete(context_w)
|
94
|
+
else
|
95
|
+
value = context_dictionary[context_w]
|
96
|
+
for i in 0...context_num_bits do
|
97
|
+
context_data_val = (context_data_val << 1) | (value & 1)
|
98
|
+
if (context_data_position == bits_per_char - 1)
|
99
|
+
context_data_position = 0
|
100
|
+
context_data.push(get_char_from_int[context_data_val])
|
101
|
+
context_data_val = 0
|
102
|
+
else
|
103
|
+
context_data_position += 1
|
104
|
+
end
|
105
|
+
value = value >> 1
|
106
|
+
end
|
107
|
+
end
|
108
|
+
|
109
|
+
context_enlarge_in -= 1
|
110
|
+
|
111
|
+
if (context_enlarge_in == 0)
|
112
|
+
context_enlarge_in = 2**context_num_bits
|
113
|
+
context_num_bits += 1
|
114
|
+
end
|
115
|
+
|
116
|
+
# Add wc to the dictionary.
|
117
|
+
context_dictionary[context_wc] = context_dict_size
|
118
|
+
context_dict_size += 1
|
119
|
+
context_w = context_c.to_s
|
120
|
+
end
|
121
|
+
end
|
122
|
+
|
123
|
+
# Output the code for w.
|
124
|
+
if (context_w != "")
|
125
|
+
if (context_dictionary_to_create.has_key?(context_w))
|
126
|
+
if (context_w[0].ord < 256)
|
127
|
+
for i in 0...context_num_bits do
|
128
|
+
context_data_val = (context_data_val << 1)
|
129
|
+
if (context_data_position == bits_per_char-1)
|
130
|
+
context_data_position = 0
|
131
|
+
context_data.push(get_char_from_int[context_data_val])
|
132
|
+
context_data_val = 0
|
133
|
+
else
|
134
|
+
context_data_position += 1
|
135
|
+
end
|
136
|
+
end
|
137
|
+
value = context_w[0].ord
|
138
|
+
for i in 0...8 do
|
139
|
+
context_data_val = (context_data_val << 1) | (value & 1)
|
140
|
+
if (context_data_position == bits_per_char-1)
|
141
|
+
context_data_position = 0
|
142
|
+
context_data.push(get_char_from_int[context_data_val])
|
143
|
+
context_data_val = 0
|
144
|
+
else
|
145
|
+
context_data_position += 1
|
146
|
+
end
|
147
|
+
value = value >> 1
|
148
|
+
end
|
149
|
+
else
|
150
|
+
value = 1
|
151
|
+
for i in 0...context_num_bits do
|
152
|
+
context_data_val = (context_data_val << 1) | value
|
153
|
+
if (context_data_position == bits_per_char-1)
|
154
|
+
context_data_position = 0
|
155
|
+
context_data.push(get_char_from_int[context_data_val])
|
156
|
+
context_data_val = 0
|
157
|
+
else
|
158
|
+
context_data_position += 1
|
159
|
+
end
|
160
|
+
value = 0
|
161
|
+
end
|
162
|
+
value = context_w[0].ord
|
163
|
+
for i in 0...16 do
|
164
|
+
context_data_val = (context_data_val << 1) | (value & 1)
|
165
|
+
if (context_data_position == bits_per_char-1)
|
166
|
+
context_data_position = 0
|
167
|
+
context_data.push(get_char_from_int[context_data_val])
|
168
|
+
context_data_val = 0
|
169
|
+
else
|
170
|
+
context_data_position += 1
|
171
|
+
end
|
172
|
+
value = value >> 1
|
173
|
+
end
|
174
|
+
end
|
175
|
+
context_enlarge_in -= 1
|
176
|
+
if (context_enlarge_in == 0)
|
177
|
+
context_enlarge_in = 2**context_num_bits
|
178
|
+
context_num_bits += 1
|
179
|
+
end
|
180
|
+
context_dictionary_to_create.delete(context_w)
|
181
|
+
else
|
182
|
+
value = context_dictionary[context_w]
|
183
|
+
for i in 0...context_num_bits
|
184
|
+
context_data_val = (context_data_val << 1) | (value & 1)
|
185
|
+
if (context_data_position == bits_per_char-1)
|
186
|
+
context_data_position = 0
|
187
|
+
context_data.push(get_char_from_int[context_data_val])
|
188
|
+
context_data_val = 0
|
189
|
+
else
|
190
|
+
context_data_position += 1
|
191
|
+
end
|
192
|
+
value = value >> 1
|
193
|
+
end
|
194
|
+
end
|
195
|
+
|
196
|
+
context_enlarge_in -= 1
|
197
|
+
if (context_enlarge_in == 0)
|
198
|
+
context_enlarge_in = 2**context_num_bits
|
199
|
+
context_num_bits += 1
|
200
|
+
end
|
201
|
+
end
|
202
|
+
|
203
|
+
# Mark the end of the stream
|
204
|
+
value = 2
|
205
|
+
for i in 0...context_num_bits do
|
206
|
+
context_data_val = (context_data_val << 1) | (value & 1)
|
207
|
+
if (context_data_position == bits_per_char - 1)
|
208
|
+
context_data_position = 0
|
209
|
+
context_data.push(get_char_from_int[context_data_val])
|
210
|
+
context_data_val = 0
|
211
|
+
else
|
212
|
+
context_data_position += 1
|
213
|
+
end
|
214
|
+
value = value >> 1
|
215
|
+
end
|
216
|
+
|
217
|
+
# Flush the last char
|
218
|
+
while (true)
|
219
|
+
context_data_val = (context_data_val << 1)
|
220
|
+
if (context_data_position == bits_per_char-1)
|
221
|
+
context_data.push(get_char_from_int[context_data_val])
|
222
|
+
break
|
223
|
+
else
|
224
|
+
context_data_position += 1
|
225
|
+
end
|
226
|
+
end
|
227
|
+
|
228
|
+
return context_data.join("")
|
229
|
+
end
|
230
|
+
|
231
|
+
# @param length [Integer]
|
232
|
+
# @param reset_value [Integer]
|
233
|
+
# @param get_next_value [Proc]
|
234
|
+
def self.decompress(length, reset_value, get_next_value, encoding = "ASCII-8BIT")
|
235
|
+
dictionary = [0, 1, 2]
|
236
|
+
enlarge_in = 4
|
237
|
+
dict_size = 4
|
238
|
+
num_bits = 3
|
239
|
+
entry = ""
|
240
|
+
result = []
|
241
|
+
data = {
|
242
|
+
val: get_next_value[(0)],
|
243
|
+
position: reset_value,
|
244
|
+
index: 1
|
245
|
+
}
|
246
|
+
bits = 0
|
247
|
+
maxpower = 2**2
|
248
|
+
power = 1
|
249
|
+
i, w, resb, c = nil
|
250
|
+
|
251
|
+
while (power != maxpower)
|
252
|
+
resb = data[:val] & data[:position]
|
253
|
+
data[:position] >>= 1
|
254
|
+
if (data[:position] == 0)
|
255
|
+
data[:position] = reset_value
|
256
|
+
data[:val] = get_next_value[data[:index]]
|
257
|
+
data[:index] += 1
|
258
|
+
end
|
259
|
+
bits |= (resb > 0 ? 1 : 0) * power
|
260
|
+
power <<= 1
|
261
|
+
end
|
262
|
+
|
263
|
+
case(n = bits)
|
264
|
+
when 0
|
265
|
+
bits = 0
|
266
|
+
maxpower = 2**8
|
267
|
+
power = 1
|
268
|
+
while power != maxpower
|
269
|
+
resb = data[:val] & data[:position]
|
270
|
+
data[:position] >>= 1
|
271
|
+
if (data[:position] == 0)
|
272
|
+
data[:position] = reset_value
|
273
|
+
data[:val] = get_next_value[data[:index]]
|
274
|
+
data[:index] += 1
|
275
|
+
end
|
276
|
+
bits |= (resb > 0 ? 1 : 0) * power
|
277
|
+
power <<= 1
|
278
|
+
end
|
279
|
+
c = bits.chr(encoding)
|
280
|
+
when 1
|
281
|
+
bits = 0
|
282
|
+
maxpower = 2*16
|
283
|
+
power = 1
|
284
|
+
while (power != maxpower)
|
285
|
+
resb = data[:val] & data[:position]
|
286
|
+
data[:position] >>= 1
|
287
|
+
if (data[:position] == 0)
|
288
|
+
data[:position] = reset_value
|
289
|
+
data[:val] = get_next_value[data[:index]]
|
290
|
+
data[:index] += 1
|
291
|
+
end
|
292
|
+
bits |= (resb > 0 ? 1 : 0) * power
|
293
|
+
power <<= 1
|
294
|
+
end
|
295
|
+
c = bits.chr(encoding)
|
296
|
+
when 2
|
297
|
+
""
|
298
|
+
end
|
299
|
+
|
300
|
+
dictionary[3] = c
|
301
|
+
w = c
|
302
|
+
result << c
|
303
|
+
|
304
|
+
while(true)
|
305
|
+
return "" if (data[:index] > length)
|
306
|
+
|
307
|
+
bits = 0
|
308
|
+
maxpower = 2**num_bits
|
309
|
+
power = 1
|
310
|
+
while (power != maxpower)
|
311
|
+
resb = data[:val] & data[:position]
|
312
|
+
data[:position] >>= 1
|
313
|
+
if (data[:position] == 0)
|
314
|
+
data[:position] = reset_value
|
315
|
+
data[:val] = get_next_value[data[:index]]
|
316
|
+
data[:index] += 1
|
317
|
+
end
|
318
|
+
bits |= (resb > 0 ? 1 : 0) * power
|
319
|
+
power <<= 1
|
320
|
+
end
|
321
|
+
|
322
|
+
case(c = bits)
|
323
|
+
when 0
|
324
|
+
bits = 0
|
325
|
+
maxpower = 2**8
|
326
|
+
power = 1
|
327
|
+
while (power != maxpower)
|
328
|
+
resb = data[:val] & data[:position]
|
329
|
+
data[:position] >>= 1
|
330
|
+
if (data[:position] == 0)
|
331
|
+
data[:position] = reset_value
|
332
|
+
data[:val] = get_next_value[data[:index]]
|
333
|
+
data[:index] += 1
|
334
|
+
end
|
335
|
+
bits |= (resb > 0 ? 1 : 0) * power
|
336
|
+
power <<= 1
|
337
|
+
end
|
338
|
+
|
339
|
+
dictionary[dict_size] = bits.chr(encoding)
|
340
|
+
dict_size += 1
|
341
|
+
c = dict_size - 1
|
342
|
+
enlarge_in -= 1
|
343
|
+
when 1
|
344
|
+
bits = 0
|
345
|
+
maxpower = 2**16
|
346
|
+
power = 1
|
347
|
+
while (power != maxpower)
|
348
|
+
resb = data[:val] & data[:position]
|
349
|
+
data[:position] >>= 1
|
350
|
+
if (data[:position] == 0)
|
351
|
+
data[:position] = reset_value
|
352
|
+
data[:val] = get_next_value[data[:index]]
|
353
|
+
data[:index] += 1
|
354
|
+
end
|
355
|
+
bits |= (resb > 0 ? 1 : 0) * power
|
356
|
+
power <<= 1
|
357
|
+
end
|
358
|
+
dictionary[dict_size] = bits.chr(encoding)
|
359
|
+
dict_size += 1
|
360
|
+
c = dict_size - 1
|
361
|
+
enlarge_in -= 1
|
362
|
+
when 2
|
363
|
+
return result.join("")
|
364
|
+
end
|
365
|
+
|
366
|
+
if (enlarge_in == 0)
|
367
|
+
enlarge_in = 2**num_bits
|
368
|
+
num_bits += 1
|
369
|
+
end
|
370
|
+
|
371
|
+
if (dictionary[c])
|
372
|
+
entry = dictionary[c]
|
373
|
+
else
|
374
|
+
if (c === dict_size)
|
375
|
+
entry = w + w[0]
|
376
|
+
else
|
377
|
+
return nil
|
378
|
+
end
|
379
|
+
end
|
380
|
+
|
381
|
+
result << entry
|
382
|
+
|
383
|
+
# Add w+entry[0] to the dictionary.
|
384
|
+
dictionary[dict_size] = w + entry[0]
|
385
|
+
dict_size += 1
|
386
|
+
enlarge_in -= 1
|
387
|
+
|
388
|
+
w = entry
|
389
|
+
|
390
|
+
if (enlarge_in == 0)
|
391
|
+
enlarge_in = 2**num_bits
|
392
|
+
num_bits += 1
|
393
|
+
end
|
394
|
+
end
|
395
|
+
end
|
396
|
+
end
|
397
|
+
end
|
@@ -0,0 +1,51 @@
|
|
1
|
+
module LZString
|
2
|
+
# Base64 compressing algorithm.
|
3
|
+
class Base64
|
4
|
+
# Base64 alphabet.
|
5
|
+
KEY_STR_BASE64 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/="
|
6
|
+
|
7
|
+
# @param input [String]
|
8
|
+
def self.compress(input)
|
9
|
+
return "" if input.nil?
|
10
|
+
|
11
|
+
res = LZString::Base.compress(input, 6, lambda { |a| KEY_STR_BASE64[a] })
|
12
|
+
|
13
|
+
# To produce valid Base64
|
14
|
+
case (res.length % 4)
|
15
|
+
when 0 then res
|
16
|
+
when 1 then res + "==="
|
17
|
+
when 2 then res + "=="
|
18
|
+
when 3 then res + "="
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
# @param compressed [String]
|
23
|
+
def self.decompress(compressed)
|
24
|
+
return "" if compressed.nil?
|
25
|
+
return nil if compressed == ""
|
26
|
+
|
27
|
+
LZString::Base.decompress(
|
28
|
+
compressed.length,
|
29
|
+
32,
|
30
|
+
lambda { |index| get_base_value(KEY_STR_BASE64, compressed[index]) }
|
31
|
+
)
|
32
|
+
end
|
33
|
+
|
34
|
+
# @param alphabet [String]
|
35
|
+
# @param character [String]
|
36
|
+
def self.get_base_value(alphabet, character)
|
37
|
+
base_reverse_dic = {}
|
38
|
+
|
39
|
+
if (!base_reverse_dic[alphabet])
|
40
|
+
base_reverse_dic[alphabet] = {}
|
41
|
+
for i in 0...alphabet.length do
|
42
|
+
base_reverse_dic[alphabet][alphabet[i]] = i
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
base_reverse_dic[alphabet][character]
|
47
|
+
end
|
48
|
+
|
49
|
+
private_class_method :get_base_value
|
50
|
+
end
|
51
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
module LZString
|
2
|
+
# UTF16 compressing algorithm.
|
3
|
+
class UTF16
|
4
|
+
# @param input [String]
|
5
|
+
def self.compress(input)
|
6
|
+
return "" if (input == nil)
|
7
|
+
|
8
|
+
LZString::Base.compress(input, 15, lambda { |a| (a + 32).chr("UTF-8") }) + " "
|
9
|
+
end
|
10
|
+
|
11
|
+
# @param compressed [String]
|
12
|
+
def self.decompress(compressed)
|
13
|
+
return "" if (compressed == nil)
|
14
|
+
return nil if (compressed == "")
|
15
|
+
|
16
|
+
LZString::Base.decompress(
|
17
|
+
compressed.length,
|
18
|
+
16384,
|
19
|
+
lambda { |index| compressed[index].ord - 32 },
|
20
|
+
"UTF-8"
|
21
|
+
)
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
data/lib/lz_string.rb
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
require "pry"
|
2
|
+
require "lz_string/base"
|
3
|
+
require "lz_string/base64"
|
4
|
+
require "lz_string/utf16"
|
5
|
+
require "lz_string/version"
|
6
|
+
|
7
|
+
# LZ-based compression algorithm.
|
8
|
+
module LZString
|
9
|
+
# @param input [String]
|
10
|
+
def self.compress(input)
|
11
|
+
return "" if input.nil?
|
12
|
+
|
13
|
+
LZString::Base.compress(input, 16, lambda { |a| a.chr("UTF-8") })
|
14
|
+
end
|
15
|
+
|
16
|
+
# @param compressed [String]
|
17
|
+
def self.decompress(compressed)
|
18
|
+
return "" if compressed.nil?
|
19
|
+
return nil if compressed == ""
|
20
|
+
|
21
|
+
LZString::Base.decompress(compressed.length, 32768, lambda { |index| compressed[index].ord })
|
22
|
+
end
|
23
|
+
end
|
metadata
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: lz_string
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Altivi
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2019-12-05 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: Ruby implementation of LZ-String compression algorithm
|
14
|
+
email:
|
15
|
+
- altivi.prog@gmail.com
|
16
|
+
executables: []
|
17
|
+
extensions: []
|
18
|
+
extra_rdoc_files: []
|
19
|
+
files:
|
20
|
+
- README.md
|
21
|
+
- lib/lz_string.rb
|
22
|
+
- lib/lz_string/base.rb
|
23
|
+
- lib/lz_string/base64.rb
|
24
|
+
- lib/lz_string/utf16.rb
|
25
|
+
- lib/lz_string/version.rb
|
26
|
+
homepage: https://github.com/Altivi/lz-string
|
27
|
+
licenses: []
|
28
|
+
metadata: {}
|
29
|
+
post_install_message:
|
30
|
+
rdoc_options: []
|
31
|
+
require_paths:
|
32
|
+
- lib
|
33
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
34
|
+
requirements:
|
35
|
+
- - ">="
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
39
|
+
requirements:
|
40
|
+
- - ">="
|
41
|
+
- !ruby/object:Gem::Version
|
42
|
+
version: '0'
|
43
|
+
requirements: []
|
44
|
+
rubyforge_project:
|
45
|
+
rubygems_version: 2.7.6
|
46
|
+
signing_key:
|
47
|
+
specification_version: 4
|
48
|
+
summary: Ruby implementation of LZ-String compression algorithm
|
49
|
+
test_files: []
|