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
|
#!/usr/bin/env python3
import re
import sys
import os
import codecs
try:
import pypandoc
no_pandoc = 0
except ImportError:
print("WARNING: pypandoc not found, will wrap markdown in <pre> tags instead")
no_pandoc = 1
canonical_url = "https://slurm.schedmd.com/"
include_pat = r'(<!--\s*#include\s*virtual\s*=\s*"([^"]+)"\s*-->)'
include_regex = re.compile(include_pat)
markdown_pat = r'(<!--\s*#include\s*markdown\s*=\s*"([^"]+)"\s*-->)'
markdown_regex = re.compile(markdown_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'<[hH]1>\s*(<a name="top">)?\s*(?P<title>[a-zA-Z0-9_ ()\'/-]+)[:]*.*\s*[</a>]?\s*</[hH]1>'
first_header_regex = re.compile(first_header_pat)
version_pat = r"(@SLURM_VERSION@)"
version_regex = re.compile(version_pat)
title = ""
dirname = ""
newfilename = ""
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):
# print('Including file', filename)
lines = open(filename, "r").read()
return lines
else:
return matchobj.group(0)
def include_markdown(matchobj):
global dirname
if dirname:
filename = dirname + "/" + matchobj.group(2)
else:
filename = matchobj.group(2)
if os.access(filename, os.F_OK):
if no_pandoc:
lines = open(filename, "r").read()
return "<pre>\n" + lines + "</pre>"
else:
lines = pypandoc.convert_file(filename, "html", format="md")
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)
# print('Rewriting', location, 'to', newname)
return matchobj.group(1) + newname + matchobj.group(4)
else:
return matchobj.group(0)
def version_rewrite(matchobj):
global version
return version
# Make sure all of the files on the command line have the .shtml extension.
version = sys.argv[1]
files = []
for f in sys.argv[2:]:
if f[-6:] == ".shtml":
files.append(f)
else:
# print('Skipping file ', f, ' (extension is not .shtml)')
pass
for filename in files:
dirname, basefilename = os.path.split(filename)
newfilename = basefilename[:-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("title")
break
shtml.seek(0)
for line in shtml.readlines():
line = include_regex.sub(include_virtual, line)
line = markdown_regex.sub(include_markdown, line)
line = page_title_regex.sub(page_title_rewrite, line)
line = version_regex.sub(version_rewrite, line)
line = canonical_regex.sub(canonical_rewrite, line)
line = url_regex.sub(url_rewrite, line)
html.write(line)
html.close()
shtml.close()
|
