Hopiu/linkchecker
1
0
Fork 0
mirror of https://github.com/Hopiu/linkchecker.git synced 2026-05-12 16:43:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

test for hierarchical URLs, and retain non-numeric port parts

Browse source 
git-svn-id: https://linkchecker.svn.sourceforge.net/svnroot/linkchecker/trunk/linkchecker@2739 e7d03fd6-7b0d-0410-9947-9c21f3af8025
This commit is contained in:
calvin 2005-07-12 07:18:13 +00:00
parent 907facaf16
commit b559c4f82e
1 changed files with 17 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
linkcheck/url.py
View file

@ -23,6 +23,8 @@ import os
import urlparse
import urllib
urlparse.uses_netloc.append('ldap')
# constants defining url part indexes
SCHEME = 0
HOSTNAME = DOMAIN = 1
@ -229,7 +231,9 @@ def url_fix_host (urlparts):
userpass += "@"
else:
userpass = ""
host, port = urllib.splitnport(host)
newhost, port = urllib.splitnport(host)
if port is not None:
host = newhost
# remove trailing dot
if host.endswith("."):
host = host[:-1]
@ -301,18 +305,18 @@ def url_norm (url):
is_idn = url_fix_host(urlparts)
# query
urlparts[3] = url_parse_query(urlparts[3])
if not urlparts[2]:
# empty path is allowed if url is non-hierarchical, or if both
# query and fragment are also empty
# note that in relative links, urlparts[0] might be empty
# in this case, do not make any assumptions
if urlparts[0] and \
urlparts[0] not in urlparse.non_hierarchical and \
(urlparts[3] or urlparts[4]):
urlparts[2] = '/'
else:
# fix redundant path parts
urlparts[2] = collapse_segments(urlparts[2])
is_hierarchical = urlparts[0] not in urlparse.non_hierarchical
if is_hierarchical:
# URL has a hierarchical path we should norm
if not urlparts[2]:
# Empty path is allowed if both query and fragment are also empty.
# Note that in relative links, urlparts[0] might be empty.
# In this case, do not make any assumptions.
if urlparts[0] and (urlparts[3] or urlparts[4]):
urlparts[2] = '/'
else:
# fix redundant path parts
urlparts[2] = collapse_segments(urlparts[2])
# quote parts again
urlparts[0] = urllib.quote(urlparts[0]) # scheme
urlparts[1] = urllib.quote(urlparts[1], '@:') # host