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
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
|
#!/usr/bin/env python3
# This script takes a manpage written in markdown and turns it into an html web
# page and a nroff man page. The input file must have the name of the program
# and the section in this format: NAME.NUM.md. The output files are written
# into the current directory named NAME.NUM.html and NAME.NUM. The input
# format has one extra extension: if a numbered list starts at 0, it is turned
# into a description list. The dl's dt tag is taken from the contents of the
# first tag inside the li, which is usually a p, code, or strong tag. The
# cmarkgfm or commonmark lib is used to transforms the input file into html.
# The html.parser is used as a state machine that both tweaks the html and
# outputs the nroff data based on the html tags.
#
# We normally grab the prefix from the generated Makefile, which is then used
# in the various other grabbed values (see the Makefile for its ${prefix}
# paths). However, the maintainer can choose to override this prefix by
# exporting RSYNC_OVERRIDE_PREFIX=/usr. This allows the man pages to refer to
# /usr paths (and are thus compatible with the release-rsync script) while
# still having the built rsync get installed into /usr/local for local testing.
#
# Copyright (C) 2020 Wayne Davison
#
# This program is freely redistributable.
import sys, os, re, argparse, subprocess, time
from html.parser import HTMLParser
CONSUMES_TXT = set('h1 h2 p li pre'.split())
HTML_START = """\
<html><head>
<title>%s</title>
<link href="https://fonts.googleapis.com/css2?family=Roboto&family=Roboto+Mono&display=swap" rel="stylesheet">
<style>
body {
max-width: 50em;
margin: auto;
}
body, b, strong, u {
font-family: 'Roboto', sans-serif;
}
code {
font-family: 'Roboto Mono', monospace;
font-weight: bold;
white-space: pre;
}
pre code {
display: block;
font-weight: normal;
}
blockquote pre code {
background: #f1f1f1;
}
dd p:first-of-type {
margin-block-start: 0em;
}
</style>
</head><body>
"""
HTML_END = """\
<div style="float: right"><p><i>%s</i></p></div>
</body></html>
"""
MAN_START = r"""
.TH "%s" "%s" "%s" "%s" "User Commands"
.\" prefix=%s
""".lstrip()
MAN_END = """\
"""
NORM_FONT = ('\1', r"\fP")
BOLD_FONT = ('\2', r"\fB")
UNDR_FONT = ('\3', r"\fI")
NBR_DASH = ('\4', r"\-")
NBR_SPACE = ('\xa0', r"\ ")
md_parser = None
def main():
fi = re.match(r'^(?P<fn>(?P<srcdir>.+/)?(?P<name>(?P<prog>[^/]+)\.(?P<sect>\d+))\.md)$', args.mdfile)
if not fi:
die('Failed to parse NAME.NUM.md out of input file:', args.mdfile)
fi = argparse.Namespace(**fi.groupdict())
if args.srcdir:
fi.srcdir = args.srcdir + '/'
elif not fi.srcdir:
fi.srcdir = './'
fi.title = fi.prog + '(' + fi.sect + ') man page'
fi.mtime = 0
git_dir = fi.srcdir + '.git'
if os.path.lexists(git_dir):
fi.mtime = int(subprocess.check_output(['git', '--git-dir', git_dir, 'log', '-1', '--format=%at']))
env_subs = { 'prefix': os.environ.get('RSYNC_OVERRIDE_PREFIX', None) }
if args.test:
env_subs['VERSION'] = '1.0.0'
env_subs['bindir'] = '/usr/bin'
env_subs['libdir'] = '/usr/lib/rsync'
else:
for fn in (fi.srcdir + 'version.h', 'Makefile'):
try:
st = os.lstat(fn)
except OSError:
die('Failed to find', fi.srcdir + fn)
if not fi.mtime:
fi.mtime = st.st_mtime
with open(fi.srcdir + 'version.h', 'r', encoding='utf-8') as fh:
txt = fh.read()
m = re.search(r'"(.+?)"', txt)
env_subs['VERSION'] = m.group(1)
with open('Makefile', 'r', encoding='utf-8') as fh:
for line in fh:
m = re.match(r'^(\w+)=(.+)', line)
if not m:
continue
var, val = (m.group(1), m.group(2))
if var == 'prefix' and env_subs[var] is not None:
continue
while re.search(r'\$\{', val):
val = re.sub(r'\$\{(\w+)\}', lambda m: env_subs[m.group(1)], val)
env_subs[var] = val
if var == 'srcdir':
break
fi.prog_ver = 'rsync ' + env_subs['VERSION']
if fi.prog != 'rsync':
fi.prog_ver = fi.prog + ' from ' + fi.prog_ver
with open(fi.fn, 'r', encoding='utf-8') as fh:
txt = fh.read()
txt = re.sub(r'@VERSION@', env_subs['VERSION'], txt)
txt = re.sub(r'@BINDIR@', env_subs['bindir'], txt)
txt = re.sub(r'@LIBDIR@', env_subs['libdir'], txt)
fi.html_in = md_parser(txt)
txt = None
fi.date = time.strftime('%d %b %Y', time.localtime(fi.mtime))
fi.man_headings = (fi.prog, fi.sect, fi.date, fi.prog_ver, env_subs['prefix'])
HtmlToManPage(fi)
if args.test:
print("The test was successful.")
return
for fn, txt in ((fi.name + '.html', fi.html_out), (fi.name, fi.man_out)):
print("Wrote:", fn)
with open(fn, 'w', encoding='utf-8') as fh:
fh.write(txt)
def html_via_commonmark(txt):
return commonmark.HtmlRenderer().render(commonmark.Parser().parse(txt))
class HtmlToManPage(HTMLParser):
def __init__(self, fi):
HTMLParser.__init__(self, convert_charrefs=True)
st = self.state = argparse.Namespace(
list_state = [ ],
p_macro = ".P\n",
at_first_tag_in_li = False,
at_first_tag_in_dd = False,
dt_from = None,
in_pre = False,
in_code = False,
html_out = [ HTML_START % fi.title ],
man_out = [ MAN_START % fi.man_headings ],
txt = '',
)
self.feed(fi.html_in)
fi.html_in = None
st.html_out.append(HTML_END % fi.date)
st.man_out.append(MAN_END)
fi.html_out = ''.join(st.html_out)
st.html_out = None
fi.man_out = ''.join(st.man_out)
st.man_out = None
def handle_starttag(self, tag, attrs_list):
st = self.state
if args.debug:
self.output_debug('START', (tag, attrs_list))
if st.at_first_tag_in_li:
if st.list_state[-1] == 'dl':
st.dt_from = tag
if tag == 'p':
tag = 'dt'
else:
st.html_out.append('<dt>')
elif tag == 'p':
st.at_first_tag_in_dd = True # Kluge to suppress a .P at the start of an li.
st.at_first_tag_in_li = False
if tag == 'p':
if not st.at_first_tag_in_dd:
st.man_out.append(st.p_macro)
elif tag == 'li':
st.at_first_tag_in_li = True
lstate = st.list_state[-1]
if lstate == 'dl':
return
if lstate == 'o':
st.man_out.append(".IP o\n")
else:
st.man_out.append(".IP " + str(lstate) + ".\n")
st.list_state[-1] += 1
elif tag == 'blockquote':
st.man_out.append(".RS 4\n")
elif tag == 'pre':
st.in_pre = True
st.man_out.append(st.p_macro + ".nf\n")
elif tag == 'code' and not st.in_pre:
st.in_code = True
st.txt += BOLD_FONT[0]
elif tag == 'strong' or tag == 'b':
st.txt += BOLD_FONT[0]
elif tag == 'em' or tag == 'i':
tag = 'u' # Change it into underline to be more like the man page
st.txt += UNDR_FONT[0]
elif tag == 'ol':
start = 1
for var, val in attrs_list:
if var == 'start':
start = int(val) # We only support integers.
break
if st.list_state:
st.man_out.append(".RS\n")
if start == 0:
tag = 'dl'
attrs_list = [ ]
st.list_state.append('dl')
else:
st.list_state.append(start)
st.man_out.append(st.p_macro)
st.p_macro = ".IP\n"
elif tag == 'ul':
st.man_out.append(st.p_macro)
if st.list_state:
st.man_out.append(".RS\n")
st.p_macro = ".IP\n"
st.list_state.append('o')
st.html_out.append('<' + tag + ''.join(' ' + var + '="' + htmlify(val) + '"' for var, val in attrs_list) + '>')
st.at_first_tag_in_dd = False
def handle_endtag(self, tag):
st = self.state
if args.debug:
self.output_debug('END', (tag,))
if tag in CONSUMES_TXT or st.dt_from == tag:
txt = st.txt.strip()
st.txt = ''
else:
txt = None
add_to_txt = None
if tag == 'h1':
st.man_out.append(st.p_macro + '.SH "' + manify(txt) + '"\n')
elif tag == 'h2':
st.man_out.append(st.p_macro + '.SS "' + manify(txt) + '"\n')
elif tag == 'p':
if st.dt_from == 'p':
tag = 'dt'
st.man_out.append('.IP "' + manify(txt) + '"\n')
st.dt_from = None
elif txt != '':
st.man_out.append(manify(txt) + "\n")
elif tag == 'li':
if st.list_state[-1] == 'dl':
if st.at_first_tag_in_li:
die("Invalid 0. -> td translation")
tag = 'dd'
if txt != '':
st.man_out.append(manify(txt) + "\n")
st.at_first_tag_in_li = False
elif tag == 'blockquote':
st.man_out.append(".RE\n")
elif tag == 'pre':
st.in_pre = False
st.man_out.append(manify(txt) + "\n.fi\n")
elif (tag == 'code' and not st.in_pre):
st.in_code = False
add_to_txt = NORM_FONT[0]
elif tag == 'strong' or tag == 'b':
add_to_txt = NORM_FONT[0]
elif tag == 'em' or tag == 'i':
tag = 'u' # Change it into underline to be more like the man page
add_to_txt = NORM_FONT[0]
elif tag == 'ol' or tag == 'ul':
if st.list_state.pop() == 'dl':
tag = 'dl'
if st.list_state:
st.man_out.append(".RE\n")
else:
st.p_macro = ".P\n"
st.at_first_tag_in_dd = False
st.html_out.append('</' + tag + '>')
if add_to_txt:
if txt is None:
st.txt += add_to_txt
else:
txt += add_to_txt
if st.dt_from == tag:
st.man_out.append('.IP "' + manify(txt) + '"\n')
st.html_out.append('</dt><dd>')
st.at_first_tag_in_dd = True
st.dt_from = None
elif tag == 'dt':
st.html_out.append('<dd>')
st.at_first_tag_in_dd = True
def handle_data(self, txt):
st = self.state
if args.debug:
self.output_debug('DATA', (txt,))
if st.in_pre:
html = htmlify(txt)
else:
txt = re.sub(r'\s--(\s)', NBR_SPACE[0] + r'--\1', txt).replace('--', NBR_DASH[0]*2)
txt = re.sub(r'(^|\W)-', r'\1' + NBR_DASH[0], txt)
html = htmlify(txt)
if st.in_code:
txt = re.sub(r'\s', NBR_SPACE[0], txt)
html = html.replace(NBR_DASH[0], '-').replace(NBR_SPACE[0], ' ') # <code> is non-breaking in CSS
st.html_out.append(html.replace(NBR_SPACE[0], ' ').replace(NBR_DASH[0], '-⁠'))
st.txt += txt
def output_debug(self, event, extra):
import pprint
st = self.state
if args.debug < 2:
st = argparse.Namespace(**vars(st))
if len(st.html_out) > 2:
st.html_out = ['...'] + st.html_out[-2:]
if len(st.man_out) > 2:
st.man_out = ['...'] + st.man_out[-2:]
print(event, extra)
pprint.PrettyPrinter(indent=2).pprint(vars(st))
def manify(txt):
return re.sub(r"^(['.])", r'\&\1', txt.replace('\\', '\\\\')
.replace(NBR_SPACE[0], NBR_SPACE[1])
.replace(NBR_DASH[0], NBR_DASH[1])
.replace(NORM_FONT[0], NORM_FONT[1])
.replace(BOLD_FONT[0], BOLD_FONT[1])
.replace(UNDR_FONT[0], UNDR_FONT[1]), flags=re.M)
def htmlify(txt):
return txt.replace('&', '&').replace('<', '<').replace('>', '>').replace('"', '"')
def warn(*msg):
print(*msg, file=sys.stderr)
def die(*msg):
warn(*msg)
sys.exit(1)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Transform a NAME.NUM.md markdown file into a NAME.NUM.html web page & a NAME.NUM man page.', add_help=False)
parser.add_argument('--srcdir', '-s', help='Specify the source dir if the input file is not in it.')
parser.add_argument('--test', action='store_true', help='Test if we can parse the input w/o updating any files.')
parser.add_argument('--debug', '-D', action='count', default=0, help='Output copious info on the html parsing. Repeat for even more.')
parser.add_argument("--help", "-h", action="help", help="Output this help message and exit.")
parser.add_argument('mdfile', help="The NAME.NUM.md file to parse.")
args = parser.parse_args()
try:
import cmarkgfm
md_parser = cmarkgfm.markdown_to_html
except:
try:
import commonmark
md_parser = html_via_commonmark
except:
die("Failed to find cmarkgfm or commonmark for python3.")
main()
|
