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
|
# -*- coding: utf-8 -*-
# Copyright © 2012-2014 Roberto Alsina and others.
# Permission is hereby granted, free of charge, to any
# person obtaining a copy of this software and associated
# documentation files (the "Software"), to deal in the
# Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish,
# distribute, sublicense, and/or sell copies of the
# Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice
# shall be included in all copies or substantial portions of
# the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
# KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
# WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
# PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS
# OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
from __future__ import print_function
import os
import re
import sys
try:
from urllib import unquote
from urlparse import urlparse, urljoin, urldefrag
except ImportError:
from urllib.parse import unquote, urlparse, urljoin, urldefrag # NOQA
import lxml.html
from nikola.plugin_categories import Command
from nikola.utils import get_logger
def real_scan_files(site):
task_fnames = set([])
real_fnames = set([])
output_folder = site.config['OUTPUT_FOLDER']
# First check that all targets are generated in the right places
for task in os.popen('nikola list --all', 'r').readlines():
task = task.strip()
if output_folder in task and ':' in task:
fname = task.split(':', 1)[-1]
task_fnames.add(fname)
# And now check that there are no non-target files
for root, dirs, files in os.walk(output_folder, followlinks=True):
for src_name in files:
fname = os.path.join(root, src_name)
real_fnames.add(fname)
only_on_output = list(real_fnames - task_fnames)
only_on_input = list(task_fnames - real_fnames)
return (only_on_output, only_on_input)
def fs_relpath_from_url_path(url_path):
"""Expects as input an urlparse(s).path"""
url_path = unquote(url_path)
# in windows relative paths don't begin with os.sep
if sys.platform == 'win32' and len(url_path):
url_path = url_path[1:].replace('/', '\\')
return url_path
class CommandCheck(Command):
"""Check the generated site."""
name = "check"
logger = None
doc_usage = "-l [--find-sources] | -f"
doc_purpose = "check links and files in the generated site"
cmd_options = [
{
'name': 'links',
'short': 'l',
'long': 'check-links',
'type': bool,
'default': False,
'help': 'Check for dangling links',
},
{
'name': 'files',
'short': 'f',
'long': 'check-files',
'type': bool,
'default': False,
'help': 'Check for unknown (orphaned and not generated) files',
},
{
'name': 'clean',
'long': 'clean-files',
'type': bool,
'default': False,
'help': 'Remove all unknown files, use with caution',
},
{
'name': 'find_sources',
'long': 'find-sources',
'type': bool,
'default': False,
'help': 'List possible source files for files with broken links.',
},
{
'name': 'verbose',
'long': 'verbose',
'short': 'v',
'type': bool,
'default': False,
'help': 'Be more verbose.',
},
]
def _execute(self, options, args):
"""Check the generated site."""
self.logger = get_logger('check', self.site.loghandlers)
if not options['links'] and not options['files'] and not options['clean']:
print(self.help())
return False
if options['verbose']:
self.logger.level = 1
else:
self.logger.level = 4
if options['links']:
failure = self.scan_links(options['find_sources'])
if options['files']:
failure = self.scan_files()
if options['clean']:
failure = self.clean_files()
if failure:
sys.exit(1)
existing_targets = set([])
def analyze(self, task, find_sources=False):
rv = False
self.whitelist = [re.compile(x) for x in self.site.config['LINK_CHECK_WHITELIST']]
base_url = urlparse(self.site.config['BASE_URL'])
self.existing_targets.add(self.site.config['SITE_URL'])
self.existing_targets.add(self.site.config['BASE_URL'])
url_type = self.site.config['URL_TYPE']
if url_type == 'absolute':
url_netloc_to_root = urlparse(self.site.config['SITE_URL']).path
try:
filename = task.split(":")[-1]
d = lxml.html.fromstring(open(filename).read())
for l in d.iterlinks():
target = l[0].attrib[l[1]]
if target == "#":
continue
target, _ = urldefrag(target)
parsed = urlparse(target)
# Absolute links when using only paths, skip.
if (parsed.scheme or target.startswith('//')) and url_type in ('rel_path', 'full_path'):
continue
# Absolute links to other domains, skip
if (parsed.scheme or target.startswith('//')) and parsed.netloc != base_url.netloc:
continue
if url_type == 'rel_path':
target_filename = os.path.abspath(
os.path.join(os.path.dirname(filename), unquote(target)))
elif url_type in ('full_path', 'absolute'):
if url_type == 'absolute':
# convert to 'full_path' case, ie url relative to root
url_rel_path = target.path[len(url_netloc_to_root):]
else:
url_rel_path = target.path
if url_rel_path == '' or url_rel_path.endswith('/'):
url_rel_path = urljoin(url_rel_path, self.site.config['INDEX_FILE'])
fs_rel_path = fs_relpath_from_url_path(url_rel_path)
target_filename = os.path.join(self.site.config['OUTPUT_FOLDER'], fs_rel_path)
if any(re.match(x, target_filename) for x in self.whitelist):
continue
elif target_filename not in self.existing_targets:
if os.path.exists(target_filename):
self.logger.notice("Good link {0} => {1}".format(target, target_filename))
self.existing_targets.add(target_filename)
else:
rv = True
self.logger.warn("Broken link in {0}: {1}".format(filename, target))
if find_sources:
self.logger.warn("Possible sources:")
self.logger.warn(os.popen('nikola list --deps ' + task, 'r').read())
self.logger.warn("===============================\n")
except Exception as exc:
self.logger.error("Error with: {0} {1}".format(filename, exc))
return rv
def scan_links(self, find_sources=False):
self.logger.info("Checking Links:")
self.logger.info("===============\n")
self.logger.notice("{0} mode".format(self.site.config['URL_TYPE']))
failure = False
for task in os.popen('nikola list --all', 'r').readlines():
task = task.strip()
if task.split(':')[0] in (
'render_tags', 'render_archive',
'render_galleries', 'render_indexes',
'render_pages'
'render_site') and '.html' in task:
if self.analyze(task, find_sources):
failure = True
if not failure:
self.logger.info("All links checked.")
return failure
def scan_files(self):
failure = False
self.logger.info("Checking Files:")
self.logger.info("===============\n")
only_on_output, only_on_input = real_scan_files(self.site)
# Ignore folders
only_on_output = [p for p in only_on_output if not os.path.isdir(p)]
only_on_input = [p for p in only_on_input if not os.path.isdir(p)]
if only_on_output:
only_on_output.sort()
self.logger.warn("Files from unknown origins (orphans):")
for f in only_on_output:
self.logger.warn(f)
failure = True
if only_on_input:
only_on_input.sort()
self.logger.warn("Files not generated:")
for f in only_on_input:
self.logger.warn(f)
if not failure:
self.logger.info("All files checked.")
return failure
def clean_files(self):
only_on_output, _ = real_scan_files(self.site)
for f in only_on_output:
os.unlink(f)
return True
|
