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
|
#!/usr/bin/env python3
"""Convert usfm line-by-line into gemtext"""
__author__ = "Zach DeCook"
__email__ = "zachdecook@librem.one"
__copyright__ = "Copyright (C) 2021 Zach DeCook"
__license__ = "AGPL"
__version__ = "3"
import fileinput
def printf(string):
print(string,end='')
def smallcaps(word):
sc = 'ᴀʙᴄᴅᴇғɢʜɪᴊᴋʟᴍɴᴏᴘǫʀsᴛᴜᴠᴡxʏᴢ'
new = ''
for c in word:
if c >= 'a' and c <= 'z':
# I like C programming.
new += sc[ord(c)-ord('a')]
else:
new += c
return new
def superscript(word):
#TODO: also superscript lowercase letters
ss='⁰¹²³⁴⁵⁶⁷⁸⁹:;<=>?@ᴬᴮCᴰᴱFᴳᴴᶦᴶᴷᴸᴹᴺᴼᴾQᴿSᵀᵁⱽᵂ'
new = ''
for c in word:
if c >= '0' and c <= 'W':
new += ss[ord(c)-ord('0')]
else:
new += c
return new
def convert(line, printStrongs=False):
"""Convert a string to a list of tuples, each a token"""
# TODO: preserve the lack of whitespace before a backslash.
split = line.replace('\\', ' \\').replace('\\nd*','\\nd* ').replace('\\+nd*','\\+nd* ').replace('\\f*','\\f* ').replace('\\wj*','\\wj* ').replace('\\w*',' \\w* ').replace('\\+w*', '\\+w* ').replace('\\ref*', '\\ref* ').replace('\\+w', ' \\+w').replace('\\+wa*', '\\+wa* ').replace('\\+wg*', '\\+wg* ').replace('\\+wh*', '\\+wh* ').split()
out = ''
nd = False
superS = False
ref = False
yesprint = True
if len(split) == 0:
return out
elif split[0] in ['\\mt1','\\mt','\\ms','\\h']:
return '\n# ' + convert(' '.join(split[1:]))
# TODO: parse as word for title tags in title line
elif split[0] in ['\\mt2','\\s','\\s1']:
return '\n## ' + convert(' '.join(split[1:]))
elif split[0] in ['\\mt3','\\d', '\\sp']:
return '\n### ' + convert(' '.join(split[1:]))
elif split[0] == '\\b':
return '\n'
elif split[0] == '\\rem':
return out
skip = 0
for word in split:
if skip > 0:
skip = skip - 1
elif word in ['\\id','\\ide']:
skip = 1
elif word in ['\\v','\\c']:
skip = 1
elif word in ['\\p','\\m']:
out += '\n'
elif word in ['\\pi','\\pi1','\\mi']:
out += '\n\t'
elif word in ['\\li1']:
out += '\n* '
elif word in ['\\q', '\\q1']:
out += '\n> '
elif word in ['\\q2', '\\q22']: # \q22 is bad input
out += '\n>\t'
elif word in ['\\q3']:
out += '\n>\t\t'
elif word in ['\\qs']:
out += '\t'
elif word in ['\\qs*']:
continue
elif word in ['\\r']:
out += '\n> '
elif word in ['\\+wa', '\\+wa*', '\\wa', '\\wa*']: # https://docs.usfm.bible/usfm/3.1/char/features/wa.html
continue
elif word in ['\\+wg', '\\+wg*', '\\wg', '\\wg*']: # https://docs.usfm.bible/usfm/3.1/char/features/wg.html
continue
elif word in ['\\+wh', '\\+wh*', '\\wh', '\\wh*']: # https://docs.usfm.bible/usfm/3.1/char/features/wh.html
continue
elif word in ['\\wj','\\wj*']:
continue
elif word in ['\\em','\\it']:
out += '*'
elif word in ['\\em*', '\\it*']:
out = out.rstrip() + '*'
elif word in ['\\nd','\\+nd']:
nd = True
elif word in ['\\nd*','\\+nd*']:
nd = False
# Footnotes (https://ubsicap.github.io/usfm/notes_basic/fnotes.html)
elif word == '\\f':
out += '['
skip = 1 # the next character is the footnote caller
elif word == '\\fr':
skip = 1 # verse reference not necessary for inline fn
elif word == '\\fqa':
pass # indicates that the following part of the footnote is an alternate translation
elif word == '\\f*':
out += ']'
# Cross-references (https://ubsicap.github.io/usfm/notes_basic/xrefs.html)
elif word == '\\x':
out += '('
skip = 1 # next character is xref caller
elif word == '\\xo':
skip = 1 # verse reference not necessary for inline xref
elif word in ['\\xt']:
continue
elif word == '\\x*':
out += ')'
# https://docs.usfm.bible/usfm/3.1.1/char/features/ref.html
elif word == '\\ref':
ref = True
elif word == '\\ref*':
ref = False
yesprint = True
elif ref and '|' in word:
spl = word.split('|')
out += spl[0]
# Everything after the pipe is the link
yesprint = False
# TODO: support Endnotes (\fe and \fe*)
elif word in ['\\ft']:
continue # TODO: fancy formatting of more types
# Words which appear in the glossary.
elif word in ['\\w','\\w*', '\\+w', '\\+w*']:
continue
elif word in ['\\nb']:
continue
elif word == '\\+sup':
superS = True
elif word == '\\+sup*':
superS = False
elif '|strong="' in word:
spl = word.split('|')
out += spl[0]
if printStrongs:
out += superscript(spl[1][8:-1])
out += ' '
elif 'x-morph="' in word:
continue
# Remove those extra spaces that sneak in.
elif word in [',', '.', ';', '”', ',”', '.”', '?”', ')', ':', '!', '?', '.’', '.’”', '?’”', '?’', ';”', '!”', ');', '),', '’s', '.)', '’t']:
if out[-1] == ' ':
out = out[:-1] + word + ' '
else:
out += word + ' '
elif word in ['“', '(', '‘']:
out += word
else:
if nd:
out += smallcaps(word) + ' '
if superS:
out += superscript(word) + ' '
elif yesprint:
out += word + ' '
return out
def main():
"""Read usfm from stdin, output gemtext to stdout
./usfm2gmi <in.usfm >out.md
"""
for line in fileinput.input():
gmi = convert(line)
printf(gmi)
if __name__ == '__main__':
main()
|
