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
|
#!/usr/bin/env python3
import re
import sys
import os
import codecs
canonical_url = 'https://slurm.schedmd.com/'
include_pat = r'(<!--\s*#include\s*virtual\s*=\s*"([^"]+)"\s*-->)'
include_regex = re.compile(include_pat)
canonical_pat = r'(<!--\s*#canonical\s*-->)'
canonical_regex = re.compile(canonical_pat)
page_title_pat = r'(<!--\s*#pagetitle\s*-->)'
page_title_regex = re.compile(page_title_pat)
url_pat = r'(\s+href\s*=\s*")([^"#]+)(#[^"]+)?(")'
url_regex = re.compile(url_pat)
first_header_pat = r'(<[h|H]1>\s*([a-zA-Z0-9_ ()\'/-\\.]+)\s*</[h|H]1>)'
first_header_regex = re.compile(first_header_pat)
version_pat = r'(@SLURM_VERSION@)'
version_regex = re.compile(version_pat)
ids = {}
title = ''
dirname = ''
# Insert tags for options
# Two styles are processed.
# <DT><B>pppppp</B><DD>
# has tag <a id="OPT_pppppp"></a>
# <DT><B>--pppppp</B> or <DT><B>-P</B>, <B>--pppppp</B>
# has tag <a id="OPT_pppppp"></a>
# <H2>hhhh</h2> also has tag has tag <a id="SECTION_hhhh"></a> inserted
def insert_tag(lineIn):
lineOt = ""
if lineIn[0:2] == "<H" and lineIn[3] == ">":
header_num = lineIn[2]
# Don't make links to h1 tags - no need, since already at top of page
if header_num == "1":
return lineIn;
posEnd = lineIn.find("</H%s>" % header_num)
if posEnd == -1:
return lineIn;
contents = lineIn[4:posEnd]
id_name = contents.replace(' ','-')
if id_name in ids:
ids[id_name] += 1
id_name += "_" + str(ids[id_name])
else:
ids[id_name] = 0
id_name = "SECTION_%s" % (id_name)
lineOt = '<h%s>%s<a class="slurm_link" id="%s" href="#%s"></a></h%s>' % (header_num, contents, id_name, id_name, header_num)
return lineOt
if lineIn[0:4] != "<DT>":
return lineIn
if lineIn[4:7] == "<B>":
bold_tag = True
elif lineIn[4:7] == "<I>":
bold_tag = False
else:
return lineIn
contentsBgn = 4
contentsEnd = lineIn.find("<DD>")
contents = lineIn[contentsBgn:contentsEnd]
posBgn = lineIn.find("--")
if posBgn == -1:
# 1st form
posBgn = 7
else:
posBgn += 2
if bold_tag:
posEnd = lineIn.find("</B>",posBgn)
else:
posEnd = lineIn.find("</I>",posBgn)
if posEnd == -1:
# poorly constructed
return lineIn
id_name = lineIn[posBgn:posEnd]
id_name = id_name.replace(' ','-')
if id_name in ids:
ids[id_name] += 1
id_name += "_" + str(ids[id_name])
else:
ids[id_name] = 0
id_name = "OPT_%s" % (id_name)
link_and_contents = '%s<a class="slurm_link" id="%s" href="#%s"></a>' % (contents, id_name, id_name)
lineOt = "<dt>" + link_and_contents + "</dt><dd>"
return lineOt
def llnl_references(line):
manStr = "Refer to mc_support.html"
htmlStr = 'Refer to <a href="mc_support.html">mc_support</a>'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '<A HREF="https://slurm.schedmd.com/mc_support.html">https://slurm.schedmd.com/mc_support.html</A>'
htmlStr = 'the <a href="mc_support.html">mc_support</a> document'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '<A HREF="https://slurm.schedmd.com/dist_plane.html.">https://slurm.schedmd.com/dist_plane.html.</A>'
htmlStr = 'the <a href="dist_plane.html">dist_plane</a> document'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '<<A HREF="https://slurm.schedmd.com/mpi_guide.html">https://slurm.schedmd.com/mpi_guide.html</A>>'
htmlStr = '<a href="mpi_guide.html">mpi_guide</a>'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '(<A HREF="https://slurm.schedmd.com/power_save.html).">https://slurm.schedmd.com/power_save.html).</A>'
htmlStr = '<a href="power_save.html">power_save</a>'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '<A HREF="https://slurm.schedmd.com/cons_tres.html">https://slurm.schedmd.com/cons_tres.html</A>'
htmlStr = '<a href="cons_tres.html">cons_tres</a>'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '<A HREF="https://slurm.schedmd.com/cons_tres_share.html">https://slurm.schedmd.com/cons_tres_share.html</A>'
htmlStr = '<a href="cons_tres_share.html">cons_tres_share</a>'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '<A HREF="https://slurm.schedmd.com/gang_scheduling.html">https://slurm.schedmd.com/gang_scheduling.html</A>'
htmlStr = '<a href="gang_scheduling.html">gang_scheduling</a>'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '<A HREF="https://slurm.schedmd.com/preempt.html">https://slurm.schedmd.com/preempt.html</A>'
htmlStr = '<a href="preempt.html">preempt</a>'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '<A HREF="/cgi-bin/man/man2html?8+logrotate">logrotate</A>'
htmlStr = 'logrotate'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '<A HREF="/man/man2html?8+logrotate">logrotate</A>'
htmlStr = 'logrotate'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '<A HREF="/cgi-bin/man/man2html?7+path_resolution">path_resolution</A>'
htmlStr = 'path_resolution'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
manStr = '<A HREF="/man/man2html?7+path_resolution">path_resolution</A>'
htmlStr = 'path_resolution'
lineFix = line.replace(manStr,htmlStr)
if lineFix != line:
return lineFix
return line
def relative_reference(lineIn):
lineOt = ""
refAnchor="<A HREF=";
lenRefAnchor = len(refAnchor)
for fullRef in ["/cgi-bin/man/man2html", "/man/man2html"]:
lenRef = len(fullRef)
lineOt = ""
cursor = 0
posHREF = lineIn.find(fullRef,cursor)
if posHREF == -1:
continue
if lineIn[posHREF+lenRef] != "?":
pos = lineIn.find("Return to Main Contents",cursor)
if pos != -1:
return ""
return "<i>man2html</i> "
while posHREF != -1:
posRefAnchor = lineIn.find(refAnchor,cursor)
lineOt = lineOt + lineIn[cursor:posRefAnchor+lenRefAnchor]
cursor = posHREF + lenRef + 3
lineOt = lineOt + '"'
posQuote = lineIn.find('"',cursor)
lineOt = lineOt + lineIn[cursor:posQuote] + ".html"
cursor = posQuote
posHREF = lineIn.find(fullRef,cursor)
lineOt = lineOt + lineIn[cursor:]
if lineOt != lineIn:
break;
if lineOt == "":
return lineIn
return lineOt
def include_virtual(matchobj):
global dirname
if dirname:
filename = dirname + '/' + matchobj.group(2)
else:
filename = matchobj.group(2)
if os.access(filename, os.F_OK):
lines = open(filename, 'r').read()
return lines
else:
return matchobj.group(0)
def canonical_rewrite(matchobj):
global newfilename
return '<link rel="canonical" href="' + canonical_url + newfilename + '" />'
def page_title_rewrite(matchobj):
global title
return '<title>Slurm Workload Manager - ' + title + '</title>'
def url_rewrite(matchobj):
global dirname
if dirname:
localpath = dirname + '/' + matchobj.group(2)
else:
localpath = matchobj.group(2)
if matchobj.group(2)[-6:] == '.shtml' and os.access(localpath, os.F_OK):
location = matchobj.group(2)
if matchobj.group(3) is None:
newname = location[:-6] + '.html'
else:
newname = location[:-6] + '.html' + matchobj.group(3)
return matchobj.group(1) + newname + matchobj.group(4)
else:
return matchobj.group(0)
def version_rewrite(matchobj):
global version
return version
files = []
version = sys.argv[1]
for f in sys.argv[4:]:
dirname, basefilename = os.path.split(f)
posLastDot = basefilename.rfind(".")
mhtmlname = basefilename[:posLastDot] + ".mhtml"
cmd = "man2html < " + f + "> " + mhtmlname
os.system(cmd)
print(">>>>>>> " + mhtmlname)
files.append(mhtmlname)
for filename in files:
newfilename = filename[:-6] + '.html'
print('Converting', filename, '->', newfilename)
shtml = codecs.open(filename, 'r', encoding='utf-8')
html = codecs.open(newfilename, 'w', encoding='utf-8')
for line in shtml.readlines():
result = first_header_regex.match(line)
if result:
title = result.group(2)
break
shtml.seek(0)
lines = open(sys.argv[2], 'r').read()
lines = lines.replace(".shtml",".html")
lines = version_regex.sub(version_rewrite, lines)
lines = page_title_regex.sub(page_title_rewrite, lines)
lines = canonical_regex.sub(canonical_rewrite, lines)
html.write(lines)
# html.write(<!--#include virtual="header.txt"-->)
for line in shtml.readlines():
# Remove html header/footer created by man2html
if line == "Content-type: text/html\n":
continue
if line == "Content-type: text/html; charset=UTF-8\n":
continue
if line[:6] == "<HTML>":
continue
if line[:7] == "</HEAD>":
continue
if line[:7] == "</HTML>":
continue
if line[:7] == "</BODY>":
continue
line = include_regex.sub(include_virtual, line)
# Special case some html references
line = llnl_references(line)
#insert tags for some options
line = insert_tag(line)
# Make man2html links relative ones
line = relative_reference(line)
line = url_regex.sub(url_rewrite, line)
html.write(line)
lines = open(sys.argv[3], 'r').read()
lines = lines.replace(".shtml",".html")
lines = version_regex.sub(version_rewrite, lines)
html.write(lines)
# html.write(<!--#include virtual="footer.txt"-->)
html.close()
shtml.close()
os.remove(filename)
|
