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
|
#!/usr/bin/env python3
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library. If not, see
# <http://www.gnu.org/licenses/>.
#
# Check that external references between documentation HTML files are not broken.
import sys
import os
import argparse
import re
import xml.etree.ElementTree as ET
ns = {'html': 'http://www.w3.org/1999/xhtml'}
externallinks = []
def get_file_list(prefix):
filelist = []
for root, dir, files in os.walk(prefix):
prefixbase = os.path.dirname(prefix)
if root.startswith(prefixbase):
relroot = root[len(prefixbase):]
else:
relroot = root
for file in files:
if not re.search('\\.html$', file):
continue
# the 404 page doesn't play well
if '404.html' in file:
continue
fullfilename = os.path.join(root, file)
relfilename = os.path.join(relroot, file)
filelist.append((fullfilename, relfilename))
return filelist
# loads an XHTML and extracts all anchors, local and remote links for the one file
def process_file(filetuple):
filename, relfilename = filetuple
tree = ET.parse(filename)
root = tree.getroot()
anchors = [relfilename]
targets = []
for elem in root.findall('.//html:a', ns):
target = elem.get('href')
an = elem.get('id')
if an:
anchors.append(relfilename + '#' + an)
if target:
if re.search('://', target):
externallinks.append(target)
elif target[0] != '#' and 'mailto:' not in target:
dirname = os.path.dirname(relfilename)
targetname = os.path.normpath(os.path.join(dirname, target))
targets.append((targetname, filename, target))
# older docutils generate "<div class='section'"
for elem in root.findall('.//html:div/[@class=\'section\']', ns):
an = elem.get('id')
if an:
anchors.append(relfilename + '#' + an)
# modern docutils generate a <section element
for elem in root.findall('.//html:section', ns):
an = elem.get('id')
if an:
anchors.append(relfilename + '#' + an)
return (anchors, targets)
def process_all(filelist):
anchors = []
targets = []
for filetuple in filelist:
anchor, target = process_file(filetuple)
targets = targets + target
anchors = anchors + anchor
return (targets, anchors)
def check_targets(targets, anchors):
errors = []
for target, targetfrom, targetorig in targets:
if target not in anchors:
errors.append((targetfrom, targetorig))
if errors:
errors.sort()
print('broken link targets:')
for file, target in errors:
print(file + " broken link: " + target)
return True
return False
parser = argparse.ArgumentParser(description='HTML reference checker')
parser.add_argument('--prefix', default='.',
help='build tree prefix')
parser.add_argument('--external', action="store_true",
help='print external references instead')
args = parser.parse_args()
files = get_file_list(args.prefix)
targets, anchors = process_all(files)
if args.external:
prev = None
externallinks.sort()
for ext in externallinks:
if ext != prev:
print(ext)
prev = ext
else:
if check_targets(targets, anchors):
sys.exit(1)
sys.exit(0)
|
