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
|
import sys
import abc
import dataclasses
import enum
import typing
from bs4 import BeautifulSoup
from bs4.element import Tag
class ParseError(Exception):
pass
class Token(abc.ABC):
def to_latex(self) -> str:
raise NotImplementedError
class TextToken(Token):
def __init__(self, text: str):
self.text = text
def to_latex(self) -> str:
return self.text
class NotatedToken(Token):
def __init__(self, text: str, notation: str):
self.text = text
self.notation = notation
def to_latex(self) -> str:
if len(self.text) == 1:
return r'\ruby{%s}{%s}' % (self.text, self.notation)
else:
# TODO tokenize hiragana to make the annotation more accurate and beautiful
return r'\ruby[g]{%s}{%s}' % (self.text, self.notation)
class NewLineToken(Token):
def __init__(self):
pass
def to_latex(self) -> str:
return '\n\n'
@dataclasses.dataclass
class LatexDocInjectionInfo:
packages: list[str]
header: list[str]
footer: list[str]
class CJKProvider(enum.Enum):
CJK = LatexDocInjectionInfo([r'\usepackage{CJKutf8}'], [r'\begin{CJK}{UTF8}{min}'], [r'\end{CJK}'])
xeCJK = LatexDocInjectionInfo([r'\usepackage{xeCJK}'], [], [])
def process_notated(ele: Tag):
ch = list(ele.children)
if (ln := len(ch)) != 2:
# Expecting a (kanji block, hiragana block)
raise ParseError(f'Invalid notated node length: {ln} != 2')
yield NotatedToken(*(x.text.strip() for x in ch))
def tokenize(lyric: Tag) -> typing.Iterator[Token]:
newline = NewLineToken()
for i, ele in enumerate(lyric):
if ele.name == 'span':
yield from process_notated(ele)
elif ele.name is None:
# text
t = ele.text.strip()
if not t:
continue
yield TextToken(t)
elif ele.name == 'br':
# newline
yield newline
else:
print(f'<unknown block {ele.name}>')
class LatexGenerator:
centering: bool
cjk: CJKProvider
def __init__(self):
pass
def generate_lyric(self, lyric_tokens: typing.Iterator[Token]) -> str:
injectors = []
injectors.append(LatexDocInjectionInfo([], [r'\usepackage{pxrubrica}'], []))
injectors.append(LatexDocInjectionInfo([], [r'\usepackage{setspace}', r'\doublespacing'], []))
injectors.append(LatexDocInjectionInfo([], [
r'\setCJKmainfont{Noto Serif CJK TC}',
r'\setCJKsansfont{Noto Sans CJK TC}',
r'\setCJKmonofont{Noto Sans Mono CJK TC}',
], []))
injectors.append(LatexDocInjectionInfo([], [r'\begin{document}'], [r'\end{document}']))
if self.centering:
injectors.append(LatexDocInjectionInfo([], [r'\begin{center}'], [r'\end{center}']))
injectors.append(self.cjk.value)
def _inject(injectors, getter) -> str:
doc = ''
for i in injectors:
for s in getter(i):
doc += s
doc += '\n'
return doc
doc = r'\documentclass{article}' + '\n'
doc += _inject(injectors, lambda _i: _i.packages)
doc += _inject(injectors, lambda _i: _i.header)
for t in lyric_tokens:
doc += t.to_latex()
doc += _inject(injectors[::-1], lambda _i: _i.footer)
return doc
def main():
if len(sys.argv) > 2:
print(f'Usage: <{sys.argv[0]}> [path_to_html_file]')
exit(0)
if len(sys.argv) == 2:
file_name = sys.argv[1]
try:
with open(file_name, 'r', encoding='utf-8') as f:
html = f.read()
except FileNotFoundError:
print(f'File does not exist: {file_name}')
exit(1)
else:
# read html from STDIN
html = sys.stdin.read()
p = BeautifulSoup(html, "html5lib")
lyric = p.select_one('.hiragana')
tokens = tokenize(lyric)
gen = LatexGenerator()
gen.centering = True
gen.cjk = CJKProvider.xeCJK
print(gen.generate_lyric(tokens))
if __name__ == '__main__':
main()
|
