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
|
# -*- coding: utf-8 -*-
#
# Copyright (C) 2011 Tiger Soldier
#
# This file is part of OSD Lyrics.
#
# OSD Lyrics is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# OSD Lyrics is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with OSD Lyrics. If not, see <https://www.gnu.org/licenses/>.
#
import re
import dbus.types
__all__ = (
'AttrToken',
'TimeToken',
'StringToken',
'tokenize',
'parse_lrc',
)
LINE_PATTERN = re.compile(r'(\[[^\[]*?\])')
TIMESTAMP_PATTERN = re.compile(r'^\[(\d+(:\d+){0,2}(\.\d+)?)\]$')
ATTR_PATTERN = re.compile(r'^\[([\w\d]+):(.*)\]$')
class AttrToken:
"""
Represents tags with the form of ``[key:value]``
"""
def __init__(self, key, value):
self.key = key
self.value = value
def __repr__(self):
return '{%s: %s}' % (self.key, self.value)
class StringToken(object):
"""
Represents a line of lyric text
"""
def __init__(self, text):
self.text = text
def __repr__(self):
return '"%s"\n' % self.text
class TimeToken(object):
"""
Represents tags with the form of ``[h:m:s.ms]``
The time attribute is the timestamp in milliseconds
"""
def __init__(self, string):
parts = string.split(':')
parts.reverse()
factor = 1000
ms = int(float(parts[0]) * factor)
for s in parts[1:]:
factor = factor * 60
ms = ms + factor * int(s)
self.time = ms
def __repr__(self):
return '[%s]' % self.time
def tokenize(content):
""" Split the content of LRC file into tokens
Returns a list of tokens
Arguments:
- `content`: UTF8 string, the content to be tokenized
"""
def parse_tag(tag):
m = TIMESTAMP_PATTERN.match(tag)
if m:
return TimeToken(m.group(1))
m = ATTR_PATTERN.match(tag)
if m:
return AttrToken(m.group(1), m.group(2))
return None
def tokenize_line(line):
pos = 0
tokens = []
while pos < len(line) and line[pos] == '[':
has_tag = False
m = LINE_PATTERN.search(line, pos)
if m and m.start() == pos:
tag = m.group()
token = parse_tag(tag)
if token:
tokens.append(token)
has_tag = True
pos = m.end()
if not has_tag:
break
tokens.append(StringToken(line[pos:]))
return tokens
lines = content.splitlines()
tokens = []
for line in lines:
tokens.extend(tokenize_line(line))
return tokens
def parse_lrc(content):
"""
Parse an lrc file
Arguments:
- `content`: LRC file content encoded in UTF8
Return values: attr, lyrics
- `attr`: A dict represents attributes in LRC file
- `lyrics`: A list of dict with 3 keys: id, timestamp and text.
The list is sorted in ascending order by timestamp. Id increases from 0.
"""
tokens = tokenize(content)
attrs = {}
lyrics = []
timetags = []
for token in tokens:
if isinstance(token, AttrToken):
attrs[token.key] = token.value
elif isinstance(token, TimeToken):
timetags.append(token.time)
else:
for timestamp in timetags:
lyrics.append({'timestamp': dbus.types.Int64(timestamp),
'text': token.text})
timetags = []
lyrics.sort(key=lambda a: a['timestamp'])
i = 0
for lyric in lyrics:
lyric['id'] = dbus.types.UInt32(i)
i = i + 1
return attrs, lyrics
def test():
TEST_CASE1 = \
"""[ti:焔の扉~hearty edition][ar:FictionJunction YUUKA]
[al:焔の扉]
[02:45.59]その日まで
[52.78]
[03:48][35]焔の扉へ
[1:03:56.66][03:14.77]
おわり
"""
def test_tokenizer():
tokens = tokenize(TEST_CASE1)
print(tokens)
def test_parser():
attr, lyrics = parse_lrc(TEST_CASE1)
print(attr)
for line in lyrics:
print('%s: %s -> %s' % (line['id'], line['timestamp'], line['text']))
test_tokenizer()
test_parser()
if __name__ == '__main__':
test()
|
