Hopiu/linkchecker
1
0
Fork 0
mirror of https://github.com/Hopiu/linkchecker.git synced 2026-03-16 22:10:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove unused linkcheck.htmlutil.linkname module

Browse source 
Unused since:
d6d48b48 ("html parser: use name instead of peeking", 2019-07-22)
This commit is contained in:
Chris Mayo 2020-03-30 19:31:11 +01:00
parent 78530956a1
commit 2c000683e1
3 changed files with 0 additions and 135 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

71
linkcheck/htmlutil/linkname.py
View file

@ -1,71 +0,0 @@
# -*- coding: iso-8859-1 -*-
# Copyright (C) 2001-2014 Bastian Kleineidam
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program 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 General Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
"""
Parse names of title tags and link types.
"""
import re
from .. import HtmlParser, strformat
imgtag_re = re.compile(r"(?i)\s+alt\s*=\s*"+\
r"""(?P<name>("[^"\n]*"|'[^'\n]*'|[^\s>]+))""")
img_re = re.compile(r"""(?i)<\s*img\s+("[^"\n]*"|'[^'\n]*'|[^>])+>""")
def endtag_re (tag):
"""Return matcher for given end tag"""
return re.compile(r"(?i)</%s\s*>" % tag)
a_end_search = endtag_re("a").search
title_end_search = endtag_re("title").search
def _unquote (txt):
"""Resolve entities and remove markup from txt."""
return HtmlParser.resolve_entities(strformat.remove_markup(txt))
def image_name (txt):
"""Return the alt part of the first <img alt=""> tag in txt."""
mo = imgtag_re.search(txt)
if mo:
name = strformat.unquote(mo.group('name').strip())
return _unquote(name)
return u''
def href_name (txt):
"""Return the name part of the first <a href="">name</a> link in txt."""
name = u""
endtag = a_end_search(txt)
if not endtag:
return name
name = txt[:endtag.start()]
if img_re.search(name):
return image_name(name)
return _unquote(name)
def title_name (txt):
"""Return the part of the first <title>name</title> in txt."""
name = u""
endtag = title_end_search(txt)
if not endtag:
return name
name = txt[:endtag.start()]
return _unquote(name)

1
linkcheck/htmlutil/linkparse.py
View file

@ -20,7 +20,6 @@ Find link tags in HTML text.
import re
from .. import strformat, log, LOG_CHECK, url as urlutil
from . import linkname
from builtins import str as str_text
unquote = strformat.unquote

63
tests/test_linkname.py
View file

@ -1,63 +0,0 @@
# -*- coding: iso-8859-1 -*-
# Copyright (C) 2004-2009 Bastian Kleineidam
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program 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 General Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
"""
Test linkname routines.
"""
import unittest
from linkcheck.htmlutil import linkname
class TestLinkname (unittest.TestCase):
"""
Test href and image name parsing.
"""
def image_name_test (self, txt, expected):
"""
Helper function calling linkname.image_name().
"""
self.assertEqual(linkname.image_name(txt), expected)
def href_name_test (self, txt, expected):
"""
Helper function calling linkname.href_name().
"""
self.assertEqual(linkname.href_name(txt), expected)
def test_image_name (self):
"""
Test image name parsing.
"""
self.image_name_test("<img src='' alt=''></a>", '')
self.image_name_test("<img src alt=abc></a>", 'abc')
def test_href_name (self):
"""
Test href name parsing.
"""
self.href_name_test("<b>guru guru</a>", 'guru guru')
self.href_name_test("a\njo</a>", "a\njo")
self.href_name_test("test<</a>", "test<")
self.href_name_test("test</</a>", "test</")
self.href_name_test("test</a</a>", "test</a")
self.href_name_test("test", "")
self.href_name_test("\n", "")
self.href_name_test("", "")
self.href_name_test('"</a>"foo', '"')
self.href_name_test("<img src='' alt=''></a>", '')
self.href_name_test("<img src alt=abc></a>", 'abc')