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
|
# This Source Code Form is subject to the terms of the Mozilla Public
# License, v. 2.0. If a copy of the MPL was not distributed with this
# file, You can obtain one at http://mozilla.org/MPL/2.0/.
import os
import shutil
import unittest
import StringIO
import tarfile
import HTMLParser
import urlparse
import urllib
from cuddlefish.docs import generate
from cuddlefish.tests import env_root
INITIAL_FILESET = [ ["static-files", "base.html"], \
["dev-guide", "index.html"], \
["modules", "sdk", "aardvark-feeder.html"], \
["modules", "sdk", "anteater", "anteater.html"]]
EXTENDED_FILESET = [ ["static-files", "base.html"], \
["dev-guide", "extra.html"], \
["dev-guide", "index.html"], \
["modules", "sdk", "aardvark-feeder.html"], \
["modules", "sdk", "anteater", "anteater.html"]]
EXTRAFILE = ["dev-guide", "extra.html"]
def get_test_root():
return os.path.join(env_root, "python-lib", "cuddlefish", "tests", "static-files")
def get_sdk_docs_root():
return os.path.join(get_test_root(), "sdk-docs")
def get_base_url_path():
return os.path.join(get_sdk_docs_root(), "doc")
def url_from_path(path):
path = path.lstrip("/")
return "file://"+"/"+"/".join(path.split(os.sep))+"/"
def get_base_url():
return url_from_path(get_base_url_path())
class Link_Checker(HTMLParser.HTMLParser):
def __init__(self, tester, filename, base_url):
HTMLParser.HTMLParser.__init__(self)
self.tester = tester
self.filename = filename
self.base_url = base_url
self.errors = []
def handle_starttag(self, tag, attrs):
link = self.find_link(attrs)
if link:
self.validate_link(link)
def handle_startendtag(self, tag, attrs):
link = self.find_link(attrs)
if link:
self.validate_link(link)
def find_link(self, attrs):
attrs = dict(attrs)
href = attrs.get('href', '')
if href:
parsed = urlparse.urlparse(href)
if not parsed.scheme:
return href
src = attrs.get('src', '')
if src:
parsed = urlparse.urlparse(src)
if not parsed.scheme:
return src
def validate_link(self, link):
parsed = urlparse.urlparse(link)
# there should not be any file:// URLs
self.tester.assertNotEqual(parsed.scheme, "file")
# any other absolute URLs will not be checked
if parsed.scheme:
return
current_path_as_url = url_from_path(os.path.dirname(self.filename))
# otherwise try to open the file at: baseurl + path
absolute_url = current_path_as_url + parsed.path
try:
urllib.urlopen(absolute_url)
except IOError:
self.errors.append(self.filename + "\n " + absolute_url)
class Generate_Docs_Tests(unittest.TestCase):
def test_generate_static_docs(self):
def cleanup():
shutil.rmtree(get_base_url_path())
tgz.close()
os.remove(tar_filename)
generate.clean_generated_docs(os.path.join(env_root, "doc"))
# make sure we start clean
if os.path.exists(get_base_url_path()):
shutil.rmtree(get_base_url_path())
# generate a doc tarball, and extract it
base_url = get_base_url()
tar_filename = generate.generate_static_docs(env_root)
tgz = tarfile.open(tar_filename)
tgz.extractall(get_sdk_docs_root())
broken_links = []
# get each HTML file...
for root, subFolders, filenames in os.walk(get_sdk_docs_root()):
for filename in filenames:
if not filename.endswith(".html"):
continue
if root.endswith("static-files"):
continue
filename = os.path.join(root, filename)
# ...and feed it to the link checker
linkChecker = Link_Checker(self, filename, base_url)
linkChecker.feed(open(filename, "r").read())
broken_links.extend(linkChecker.errors)
if broken_links:
print
print "The following links are broken:"
for broken_link in sorted(broken_links):
print " "+ broken_link
cleanup()
self.fail("%d links are broken" % len(broken_links))
cleanup()
def test_generate_docs(self):
test_root = get_test_root()
docs_root = os.path.join(test_root, "doc")
generate.clean_generated_docs(docs_root)
new_digest = self.check_generate_regenerate_cycle(test_root, INITIAL_FILESET)
# touching an MD file under sdk **does** cause a regenerate
os.utime(os.path.join(test_root, "doc", "module-source", "sdk", "aardvark-feeder.md"), None)
new_digest = self.check_generate_regenerate_cycle(test_root, INITIAL_FILESET, new_digest)
# touching a non MD file under sdk **does not** cause a regenerate
os.utime(os.path.join(test_root, "doc", "module-source", "sdk", "not_a_doc.js"), None)
self.check_generate_is_skipped(test_root, INITIAL_FILESET, new_digest)
# touching a non MD file under static-files **does not** cause a regenerate
os.utime(os.path.join(docs_root, "static-files", "another.html"), None)
new_digest = self.check_generate_is_skipped(test_root, INITIAL_FILESET, new_digest)
# touching an MD file under dev-guide **does** cause a regenerate
os.utime(os.path.join(docs_root, "dev-guide-source", "index.md"), None)
new_digest = self.check_generate_regenerate_cycle(test_root, INITIAL_FILESET, new_digest)
# adding a file **does** cause a regenerate
open(os.path.join(docs_root, "dev-guide-source", "extra.md"), "w").write("some content")
new_digest = self.check_generate_regenerate_cycle(test_root, EXTENDED_FILESET, new_digest)
# deleting a file **does** cause a regenerate
os.remove(os.path.join(docs_root, "dev-guide-source", "extra.md"))
new_digest = self.check_generate_regenerate_cycle(test_root, INITIAL_FILESET, new_digest)
# remove the files
generate.clean_generated_docs(docs_root)
def check_generate_is_skipped(self, test_root, files_to_expect, initial_digest):
generate.generate_docs(test_root, stdout=StringIO.StringIO())
docs_root = os.path.join(test_root, "doc")
for file_to_expect in files_to_expect:
self.assertTrue(os.path.exists(os.path.join(docs_root, *file_to_expect)))
self.assertTrue(initial_digest == open(os.path.join(docs_root, "status.md5"), "r").read())
def check_generate_regenerate_cycle(self, test_root, files_to_expect, initial_digest = None):
# test that if we generate, files are getting generated
generate.generate_docs(test_root, stdout=StringIO.StringIO())
docs_root = os.path.join(test_root, "doc")
for file_to_expect in files_to_expect:
self.assertTrue(os.path.exists(os.path.join(docs_root, *file_to_expect)), os.path.join(docs_root, *file_to_expect) + "not found")
if initial_digest:
self.assertTrue(initial_digest != open(os.path.join(docs_root, "status.md5"), "r").read())
# and that if we regenerate, nothing changes...
new_digest = open(os.path.join(docs_root, "status.md5"), "r").read()
self.check_generate_is_skipped(test_root, files_to_expect, new_digest)
return new_digest
if __name__ == '__main__':
unittest.main()
|
