|
1
|
|
|
# -*- coding: utf-8 -*- |
|
2
|
|
|
|
|
3
|
|
|
# Copyright 2014-2018 by Christopher C. Little. |
|
4
|
|
|
# This file is part of Abydos. |
|
5
|
|
|
# |
|
6
|
|
|
# Abydos is free software: you can redistribute it and/or modify |
|
7
|
|
|
# it under the terms of the GNU General Public License as published by |
|
8
|
|
|
# the Free Software Foundation, either version 3 of the License, or |
|
9
|
|
|
# (at your option) any later version. |
|
10
|
|
|
# |
|
11
|
|
|
# Abydos is distributed in the hope that it will be useful, |
|
12
|
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
13
|
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
14
|
|
|
# GNU General Public License for more details. |
|
15
|
|
|
# |
|
16
|
|
|
# You should have received a copy of the GNU General Public License |
|
17
|
|
|
# along with Abydos. If not, see <http://www.gnu.org/licenses/>. |
|
18
|
|
|
|
|
19
|
1 |
|
"""abydos.compression._rle. |
|
20
|
|
|
|
|
21
|
|
|
Run-Length Encoding encoder/decoder (rle_encoder & rle_decoder) |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import unicode_literals |
|
25
|
|
|
|
|
26
|
1 |
|
from itertools import groupby |
|
27
|
|
|
|
|
28
|
1 |
|
from ._bwt import bwt_decode, bwt_encode |
|
29
|
|
|
|
|
30
|
|
|
|
|
31
|
1 |
|
__all__ = ['rle_decode', 'rle_encode'] |
|
32
|
|
|
|
|
33
|
|
|
|
|
34
|
1 |
|
def rle_encode(text, use_bwt=True): |
|
35
|
|
|
r"""Perform encoding of run-length-encoding (RLE). |
|
36
|
|
|
|
|
37
|
|
|
Cf. :cite:`Robinson:1967`. |
|
38
|
|
|
|
|
39
|
|
|
Based on http://rosettacode.org/wiki/Run-length_encoding#Python |
|
40
|
|
|
:cite:`rosettacode:2018`. This is licensed GFDL 1.2. |
|
41
|
|
|
|
|
42
|
|
|
Digits 0-9 cannot be in text. |
|
43
|
|
|
|
|
44
|
|
|
:param str text: a text string to encode |
|
45
|
|
|
:param bool use_bwt: boolean indicating whether to perform BWT encoding |
|
46
|
|
|
before RLE encoding |
|
47
|
|
|
:returns: word decoded by BWT |
|
48
|
|
|
:rtype: str |
|
49
|
|
|
|
|
50
|
|
|
>>> rle_encode('align') |
|
51
|
|
|
'n\x00ilag' |
|
52
|
|
|
>>> rle_encode('align', use_bwt=False) |
|
53
|
|
|
'align' |
|
54
|
|
|
|
|
55
|
|
|
>>> rle_encode('banana') |
|
56
|
|
|
'annb\x00aa' |
|
57
|
|
|
>>> rle_encode('banana', use_bwt=False) |
|
58
|
|
|
'banana' |
|
59
|
|
|
|
|
60
|
|
|
>>> rle_encode('aaabaabababa') |
|
61
|
|
|
'ab\x00abbab5a' |
|
62
|
|
|
>>> rle_encode('aaabaabababa', False) |
|
63
|
|
|
'3abaabababa' |
|
64
|
|
|
""" |
|
65
|
1 |
|
if use_bwt: |
|
66
|
1 |
|
text = bwt_encode(text) |
|
67
|
1 |
|
if text: |
|
68
|
1 |
|
text = ((len(list(g)), k) for k, g in groupby(text)) |
|
|
|
|
|
|
69
|
1 |
|
text = ( |
|
70
|
|
|
(str(n) + k if n > 2 else (k if n == 1 else 2 * k)) |
|
|
|
|
|
|
71
|
|
|
for n, k in text |
|
72
|
|
|
) |
|
73
|
1 |
|
return ''.join(text) |
|
74
|
|
|
|
|
75
|
|
|
|
|
76
|
1 |
|
def rle_decode(text, use_bwt=True): |
|
77
|
|
|
r"""Perform decoding of run-length-encoding (RLE). |
|
78
|
|
|
|
|
79
|
|
|
Cf. :cite:`Robinson:1967`. |
|
80
|
|
|
|
|
81
|
|
|
Based on http://rosettacode.org/wiki/Run-length_encoding#Python |
|
82
|
|
|
:cite:`rosettacode:2018`. This is licensed GFDL 1.2. |
|
83
|
|
|
|
|
84
|
|
|
Digits 0-9 cannot have been in the original text. |
|
85
|
|
|
|
|
86
|
|
|
:param str text: a text string to decode |
|
87
|
|
|
:param bool use_bwt: boolean indicating whether to perform BWT decoding |
|
88
|
|
|
after RLE decoding |
|
89
|
|
|
:returns: word decoded by BWT |
|
90
|
|
|
:rtype: str |
|
91
|
|
|
|
|
92
|
|
|
>>> rle_decode('n\x00ilag') |
|
93
|
|
|
'align' |
|
94
|
|
|
>>> rle_decode('align', use_bwt=False) |
|
95
|
|
|
'align' |
|
96
|
|
|
|
|
97
|
|
|
>>> rle_decode('annb\x00aa') |
|
98
|
|
|
'banana' |
|
99
|
|
|
>>> rle_decode('banana', use_bwt=False) |
|
100
|
|
|
'banana' |
|
101
|
|
|
|
|
102
|
|
|
>>> rle_decode('ab\x00abbab5a') |
|
103
|
|
|
'aaabaabababa' |
|
104
|
|
|
>>> rle_decode('3abaabababa', False) |
|
105
|
|
|
'aaabaabababa' |
|
106
|
|
|
""" |
|
107
|
1 |
|
mult = '' |
|
108
|
1 |
|
decoded = [] |
|
109
|
1 |
|
for letter in list(text): |
|
110
|
1 |
|
if not letter.isdigit(): |
|
111
|
1 |
|
if mult: |
|
112
|
1 |
|
decoded.append(int(mult) * letter) |
|
113
|
1 |
|
mult = '' |
|
114
|
|
|
else: |
|
115
|
1 |
|
decoded.append(letter) |
|
116
|
|
|
else: |
|
117
|
1 |
|
mult += letter |
|
118
|
|
|
|
|
119
|
1 |
|
text = ''.join(decoded) |
|
120
|
1 |
|
if use_bwt: |
|
121
|
1 |
|
text = bwt_decode(text) |
|
122
|
1 |
|
return text |
|
123
|
|
|
|
|
124
|
|
|
|
|
125
|
|
|
if __name__ == '__main__': |
|
126
|
|
|
import doctest |
|
127
|
|
|
|
|
128
|
|
|
doctest.testmod() |
|
129
|
|
|
|
chrislit /
abydos
Loading history...