E578 Don't prettify HTML in PEP pages · python/pythondotorg@cbb14fc · GitHub
[go: up one dir, main page]
Skip to content

Commit cbb14fc

Browse files
berkerpeksagberkerpeksag
committed
Don't prettify HTML in PEP pages
Fixes #825
1 parent de4e5d3 commit cbb14fc
< E880 /div>

File tree

4 files changed

+85
-21
lines changed

4 files changed

+85
-21
lines changed

‎peps/converters.py‎

Lines changed: 22 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,4 @@
1+
import functools
12
import re
23
import os
34

@@ -13,22 +14,24 @@
1314
pep_url = lambda num: 'dev/peps/pep-{}/'.format(num)
1415

1516

16-
def check_paths():
17-
""" Checks to ensure our PEP_REPO_PATH is setup correctly """
18-
if not hasattr(settings, 'PEP_REPO_PATH'):
19-
raise ImproperlyConfigured("No PEP_REPO_PATH in settings")
20-
21-
if not os.path.exists(settings.PEP_REPO_PATH):
22-
raise ImproperlyConfigured("PEP_REPO_PATH in settings does not exist")
17+
def check_paths(func):
18+
"""Ensure that our PEP_REPO_PATH is setup correctly."""
19+
@functools.wraps(func)
20+
def wrapped(*args, **kwargs):
21+
if not hasattr(settings, 'PEP_REPO_PATH'):
22+
raise ImproperlyConfigured('No PEP_REPO_PATH in settings')
23+
if not os.path.exists(settings.PEP_REPO_PATH):
24+
raise ImproperlyConfigured('Path set as PEP_REPO_PATH does not exist')
25+
return func(*args, **kwargs)
26+
return wrapped
2327

2428

29+
@check_paths
2530
def convert_pep0():
2631
"""
2732
Take existing generated pep-0000.html and convert to something suitable
2833
for a Python.org Page returns the core body HTML necessary only
2934
"""
30-
check_paths()
31-
3235
pep0_path = os.path.join(settings.PEP_REPO_PATH, 'pep-0000.html')
3336
pep0_content = open(pep0_path).read()
3437

@@ -60,7 +63,7 @@ def convert_pep0():
6063
if 'Version:' in t.text and 'N/A' in t.next_sibling.text:
6164
t.parent.extract()
6265

63-
return ''.join([header.prettify(), pep_content.prettify()])
66+
return ''.join([str(header), str(pep_content)])
6467

6568

6669
def get_pep0_page(commit=True):
@@ -109,11 +112,11 @@ def fix_headers(soup, data):
109112
return soup, data
110113

111114

115+
@check_paths
112116
def convert_pep_page(pep_number, content):
113117
"""
114118
Handle different formats that pep2html.py outputs
115119
"""
116-
check_paths()
117120
data = {
118121
'title': None,
119122
}
@@ -132,11 +135,11 @@ def convert_pep_page(pep_number, content):
132135

133136
header = soup.body.find('div', class_="header")
134137
header, data = fix_headers(header, data)
135-
data['header'] = header.prettify()
138+
data['header'] = str(header)
136139

137140
main_content = soup.body.find('div', class_="content")
138141

139-
data['main_content'] = main_content.prettify()
142+
data['main_content'] = str(main_content)
140143
data['content'] = ''.join([
141144
data['header'],
142145
data['main_content']
@@ -155,7 +158,7 @@ def convert_pep_page(pep_number, content):
155158
data['title'],
156159
)
157160

158-
data['content'] = soup.prettify()
161+
data['content'] = str(soup)
159162

160163
# Fix PEP links
161164
pep_content = BeautifulSoup(data['content'])
@@ -172,7 +175,7 @@ def convert_pep_page(pep_number, content):
172175

173176
b.attrs['href'] = '/dev/peps/pep-{}/'.format(m.group(1))
174177

175-
data['content'] = pep_content.prettify()
178+
data['content'] = str(pep_content)
176179

177180
source_link = "https://github.com/python/peps/blob/master/pep-{0}.txt".format(pep_number)
178181
data['content'] += """Source: <a href="{0}">{0}</a>""".format(source_link)
@@ -187,6 +190,7 @@ def get_pep_page(pep_number, commit=True):
187190
pep_path = os.path.join(settings.PEP_REPO_PATH, 'pep-{}.html'.format(pep_number))
188191
if not os.path.exists(pep_path):
189192
print("PEP Path '{}' does not exist, skipping".format(pep_path))
193+
return
190194

191195
pep_content = convert_pep_page(pep_number, open(pep_path).read())
192196

@@ -208,6 +212,7 @@ def add_pep_image(pep_number, path):
208212
image_path = os.path.join(settings.PEP_REPO_PATH, path)
209213
if not os.path.exists(image_path):
210214
print("Image Path '{}' does not exist, skipping".format(image_path))
215+
return
211216

212217
try:
213218
page = Page.objects.get(path=pep_url(pep_number))
@@ -250,12 +255,13 @@ def add_pep_image(pep_number, path):
250255
if img_tag['src'] == path:
251256
img_tag['src'] = os.path.join(settings.MEDIA_URL, page.path, path)
252257

253-
page.content.raw = soup.prettify()
258+
page.content.raw = str(soup)
254259
page.save()
255260

256261
return image
257262

258263

264+
@check_paths
259265
def get_peps_rss():
260266
rss_feed = os.path.join(settings.PEP_REPO_PATH, 'peps.rss')
261267
if not os.path.exists(rss_feed):

‎peps/tests/test_commands.py‎

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,12 @@ class PEPManagementCommandTests(TestCase):
1515

1616
@override_settings(PEP_REPO_PATH='/path/that/does/not/exist')
1717
def test_generate_pep_pages(self):
18+
with self.assertRaises(ImproperlyConfigured):
19+
call_command('generate_pep_pages')
1820

21+
@override_settings()
22+
def test_generate_pep_pages_without_setting(self):
23+
del settings.PEP_REPO_PATH
1924
with self.assertRaises(ImproperlyConfigured):
2025
call_command('generate_pep_pages')
2126

‎peps/tests/test_converters.py‎

Lines changed: 34 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,8 @@
22
from django.core.exceptions import ImproperlyConfigured
33
from django.test.utils import override_settings
44

5-
from peps.converters import check_paths, get_pep0_page, get_pep_page
5+
from peps.converters import get_pep0_page, get_pep_page, add_pep_image
6+
from pydotorg.test_utils import captured_stdout
67

78
from . import FAKE_PEP_REPO
89

@@ -11,10 +12,6 @@ class PEPConverterTests(TestCase):
1112

1213
@override_settings(PEP_REPO_PATH='/path/that/does/not/exist')
1314
def test_converter_path_checks(self):
14-
15-
with self.assertRaises(ImproperlyConfigured):
16-
check_paths()
17-
1815
with self.assertRaises(ImproperlyConfigured):
1916
get_pep0_page()
2017

@@ -27,3 +24,35 @@ def test_source_link(self):
2724
'pep-0525.txt">https://github.com/python/peps/blob/master/pep-0525.txt</a>',
2825
pep.content.rendered
2926
)
27+
28+
@override_settings(PEP_REPO_PATH=FAKE_PEP_REPO)
29+
def test_invalid_pep_number(self):
30+
with captured_stdout() as stdout:
31+
get_pep_page('9999999')
32+
self.assertRegex(
33+
stdout.getvalue(),
34+
r"PEP Path '(.*)9999999(.*)' does not exist, skipping"
35+
)
36+
37+
@override_settings(PEP_REPO_PATH=FAKE_PEP_REPO)
38+
def test_add_image_not_found(self):
39+
with captured_stdout() as stdout:
40+
add_pep_image('0525', '/path/that/does/not/exist')
41+
self.assertRegex(
42+
stdout.getvalue(),
43+
r"Image Path '(.*)/path/that/does/not/exist(.*)' does not exist, skipping"
44+
)
45+
46+
@override_settings(PEP_REPO_PATH=FAKE_PEP_REPO)
47+
def test_html_do_not_prettify(self):
48+
pep = get_pep_page('3001')
49+
self.assertEqual(
50+
pep.title,
51+
'PEP 3001 -- Procedure for reviewing and improving standard library modules'
52+
)
53+
self.assertIn(
54+
'<tr class="field"><th class="field-name">Title:</th>'
55+
'<td class="field-body">Procedure for reviewing and improving '
56+
'standard library modules</td>\n</tr>',
57+
pep.content.rendered
58+
)

‎pydotorg/test_utils.py‎

Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
# TODO: Remove this when we switched to Django 1.8
2+
3+
import contextlib
4+
import sys
5+
6+
from django.utils import six
7+
8+
9+
@contextlib.contextmanager
10+
def captured_output(stream_name):
11+
"""Return a context manager used by captured_stdout/stdin/stderr
12+
that temporarily replaces the sys stream *stream_name* with a StringIO.
13+
Note: This function and the following ``captured_std*`` are copied
14+
from CPython's ``test.support`` module."""
15+
orig_stdout = getattr(sys, stream_name)
16+
setattr(sys, stream_name, six.StringIO())
17+
try:
18+
yield getattr(sys, stream_name)
19+
finally:
20+
setattr(sys, stream_name, orig_stdout)
21+
22+
23+
def captured_stdout():
24+
return captured_output("stdout")

0 commit comments

Comments
 (0)
0