Hopiu/linkchecker
1
0
Fork 0
mirror of https://github.com/Hopiu/linkchecker.git synced 2026-04-07 16:10:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #440 from cjmayo/misc

Browse source 
Assorted review comments and use python3 for setup.py
This commit is contained in:
Chris Mayo 2020-06-09 19:53:58 +01:00 committed by GitHub
commit 26525a332f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
12 changed files with 37 additions and 36 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
linkcheck/checker/fileurl.py
View file

@ -71,7 +71,7 @@ def get_os_filename(path):
path = prepare_urlpath_for_nt(path)
res = urllib.request.url2pathname(fileutil.path_safe(path))
if os.name == 'nt' and res.endswith(':') and len(res) == 2:
# Work around http://bugs.python.org/issue11474
# Work around https://bugs.python.org/issue11474
res += os.sep
return res

14
linkcheck/checker/mailtourl.py
View file

@ -137,20 +137,20 @@ class MailtoUrl(urlbase.UrlBase):
def check_email_syntax(self, mail):
"""Check email syntax. The relevant RFCs:
- How to check names (memo):
http://tools.ietf.org/html/rfc3696
https://tools.ietf.org/html/rfc3696
- Email address syntax
http://tools.ietf.org/html/rfc2822
https://tools.ietf.org/html/rfc2822
- SMTP protocol
http://tools.ietf.org/html/rfc5321#section-4.1.3
https://tools.ietf.org/html/rfc5321#section-4.1.3
- IPv6
http://tools.ietf.org/html/rfc4291#section-2.2
https://tools.ietf.org/html/rfc4291#section-2.2
- Host syntax
http://tools.ietf.org/html/rfc1123#section-2
https://tools.ietf.org/html/rfc1123#section-2
"""
# length checks
# restrict email length to 256 characters
# http://www.rfc-editor.org/errata_search.php?eid=1003
# https://www.rfc-editor.org/errata_search.php?eid=1003
if len(mail) > 256:
self.set_result(
_(
@ -210,7 +210,7 @@ class MailtoUrl(urlbase.UrlBase):
# local part syntax check
# Rules taken from http://tools.ietf.org/html/rfc3696#section-3
# Rules taken from https://tools.ietf.org/html/rfc3696#section-3
if is_quoted(local):
if is_missing_quote(local):
self.set_result(

13
linkcheck/configuration/confparse.py
View file

@ -233,9 +233,11 @@ class LCConfigParser(RawConfigParser):
if fileutil.is_accessable_by_others(fn):
log.warn(
LOG_CHECK,
"The configuration file %s contains password information (in"
" section [%s] and options %s) and the file is readable by"
" others. Please make the file only readable by you.",
_(
"The configuration file %s contains password information (in"
" section [%s] and options %s) and the file is readable by"
" others. Please make the file only readable by you."
),
fn,
section,
fields,
@ -246,9 +248,8 @@ class LCConfigParser(RawConfigParser):
log.warn(
LOG_CHECK,
_(
"See http://support.microsoft.com/kb/308419 for"
" more info on setting file permissions."
),
"See %(url)s for more info on setting file permissions."
) % {"url": "https://support.microsoft.com/kb/308419"}
)
def read_filtering_config(self):

7
linkcheck/logger/blacklist.py
View file

@ -18,7 +18,7 @@ A blacklist logger.
"""
import os
import codecs
from linkcheck.configuration import get_user_data
from . import _Logger
@ -76,9 +76,8 @@ class BlacklistLogger(_Logger):
"""
Read a previously stored blacklist from file fd.
"""
with codecs.open(
self.filename, 'r', self.output_encoding, self.codec_errors
) as fd:
with open(self.filename, 'r', encoding=self.output_encoding,
errors=self.codec_errors) as fd:
for line in fd:
line = line.rstrip()
if line.startswith('#') or not line:

2
linkcheck/logger/dot.py
View file

@ -15,7 +15,7 @@
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
"""
A DOT graph format logger. The specification has been taken from
http://www.graphviz.org/doc/info/lang.html
https://www.graphviz.org/doc/info/lang.html
"""
from .graph import _GraphLogger

8
linkcheck/logger/html.py
View file

@ -26,10 +26,10 @@ from .. import strformat, configuration
# ss=1 enables show source
validate_html = "http://validator.w3.org/check?ss=1&uri=%(uri)s"
validate_html = "https://validator.w3.org/check?ss=1&uri=%(uri)s"
# options are the default
validate_css = (
"http://jigsaw.w3.org/css-validator/validator?"
"https://jigsaw.w3.org/css-validator/validator?"
"uri=%(uri)s&warning=1&profile=css2&usermedium=all"
)
@ -194,7 +194,7 @@ class HtmlLogger(_Logger):
"<tr><td>"
+ self.part("parenturl")
+ '</td><td><a target="top" href="'
+ url_data.parent_url
+ html.escape(url_data.parent_url)
+ '">'
+ html.escape(url_data.parent_url)
+ "</a>"
@ -231,7 +231,7 @@ class HtmlLogger(_Logger):
+ self.part("realurl")
+ "</td><td>"
+ '<a target="top" href="'
+ url_data.url
+ html.escape(url_data.url)
+ '">'
+ html.escape(url_data.url)
+ "</a></td></tr>"

2
linkcheck/logger/sitemapxml.py
View file

@ -34,7 +34,7 @@ HTML_TYPES = ('text/html', "application/xhtml+xml")
class SitemapXmlLogger(xmllog._XMLLogger):
"""Sitemap XML output according to http://www.sitemaps.org/protocol.html
"""Sitemap XML output according to https://www.sitemaps.org/protocol.html
"""
LoggerName = 'sitemap'

2
linkcheck/plugins/locationinfo.py
View file

@ -91,7 +91,7 @@ if geoip_dat:
else:
def get_geoip_record(host):
return {
'country_name': geoip.country_name_by_name(host)
'country_name': geoip.country_name_by_name(host),
}

8
linkcheck/plugins/syntaxchecks.py
View file

@ -45,7 +45,7 @@ class W3Timer:
class HtmlSyntaxCheck(_ContentPlugin):
"""Check the syntax of HTML pages with the online W3C HTML validator.
See http://validator.w3.org/docs/api.html.
See https://validator.w3.org/docs/api.html.
"""
def __init__(self, config):
@ -63,7 +63,7 @@ class HtmlSyntaxCheck(_ContentPlugin):
session = url_data.session
try:
body = {'uri': url_data.url, 'output': 'soap12'}
response = session.post('http://validator.w3.org/check', data=body)
response = session.post('https://validator.w3.org/check', data=body)
response.raise_for_status()
if response.headers.get('x-w3c-validator-status', 'Invalid') == 'Valid':
url_data.add_info("W3C Validator: %s" % _("valid HTML syntax"))
@ -79,7 +79,7 @@ class HtmlSyntaxCheck(_ContentPlugin):
class CssSyntaxCheck(_ContentPlugin):
"""Check the syntax of HTML pages with the online W3C CSS validator.
See http://jigsaw.w3.org/css-validator/manual.html#expert.
See https://jigsaw.w3.org/css-validator/manual.html#expert.
"""
def __init__(self, config):
@ -96,7 +96,7 @@ class CssSyntaxCheck(_ContentPlugin):
self.timer.check_w3_time()
session = url_data.session
try:
url = 'http://jigsaw.w3.org/css-validator/validator'
url = 'https://jigsaw.w3.org/css-validator/validator'
params = {
'uri': url_data.url,
'warning': '2',

2
setup.py
View file

@ -1,4 +1,4 @@
#!/usr/bin/env python
#!/usr/bin/python3
# Copyright (C) 2000-2014 Bastian Kleineidam
#
# This program is free software; you can redistribute it and/or modify

3
tests/checker/__init__.py
View file

@ -18,7 +18,6 @@ Define standard test support classes funtional for LinkChecker tests.
"""
import os
import re
import codecs
import difflib
import unittest
import linkcheck.checker
@ -235,7 +234,7 @@ class LinkCheckTest(unittest.TestCase):
if hasattr(self, "port"):
d["port"] = self.port
# all result files are encoded in utf-8
with codecs.open(resultfile, "r", "utf-8") as f:
with open(resultfile, "r", encoding="utf-8") as f:
return [
line.rstrip("\r\n") % d
for line in f

10
tests/test_po.py
View file

@ -34,6 +34,8 @@ def get_pofiles():
pofiles = []
pofiles.extend(glob.glob("po/*.po"))
pofiles.extend(glob.glob("doc/*.po"))
if not pofiles:
raise Exception("No .po files found")
return pofiles
@ -56,15 +58,15 @@ class TestGTranslator(unittest.TestCase):
def test_gtranslator(self):
"""Test all pofiles for GTranslator brokenness."""
for f in get_pofiles():
with open(f, "rb") as fd:
with open(f, encoding="UTF-8") as fd:
self.check_file(fd, f)
def check_file(self, fd, f):
"""Test for GTranslator broken syntax."""
for line in fd:
if line.strip().startswith(b"#"):
if line.strip().startswith("#"):
continue
self.assertFalse(
b"\xc2\xb7" in line,
"Broken GTranslator copy/paste in %r:\n%r" % (f, line),
"·" in line,
"Broken GTranslator copy/paste in %r:\n%s" % (f, line),
)