From 33add0a95aa6c5ba5dbb8cae7b51a253209ecd6f Mon Sep 17 00:00:00 2001
From: Guido van Rossum <guido@python.org>
Date: Fri, 18 Dec 1998 15:25:22 +0000
Subject: [PATCH] Sjoerd Mullender:

File names with "funny" characters get translated wrong by
pathname2url (any variety).  E.g. the (Unix) file "/ufs/sjoerd/#tmp"
gets translated into "/ufs/sjoerd/#tmp" which, when interpreted as a
URL is file "/ufs/sjoerd/" with fragment ID "tmp".

Here's an easy fix.  (An alternative fix would be to change the
various implementations of pathname2url and url2pathname to include
calls to quote and unquote.

[The main problem is with the normal use of URLs:
	url = url2pathname(file)
	transmit url
	url, tag = splittag(url)
	urlopen(url)
]

In addition, this patch fixes some uses of unquote:
- the host part of URLs should be unquoted
- the file path in the FTP URL should be unquoted before it is split
  into components.
- because of the latter, I removed all unquoting from ftpwrapper,
  and moved it to the caller, but that is not essential
---
 Lib/urllib.py | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/Lib/urllib.py b/Lib/urllib.py
index 62e5c7f5298..d175eef91bd 100644
--- a/Lib/urllib.py
+++ b/Lib/urllib.py
@@ -42,6 +42,13 @@ else:
 	def pathname2url(pathname):
 		return pathname
 
+_url2pathname = url2pathname
+def url2pathname(url):
+	return _url2pathname(unquote(url))
+_pathname2url = pathname2url
+def pathname2url(p):
+	return quote(_pathname2url(p))
+
 # This really consists of two pieces:
 # (1) a class which handles opening of all sorts of URLs
 #     (plus assorted utilities etc.)
@@ -228,6 +235,7 @@ class URLopener:
 			host, selector = splithost(url)
 			if host:
 				user_passwd, host = splituser(host)
+				host = unquote(host)
 			realhost = host
 		else:
 			host, selector = url
@@ -298,6 +306,7 @@ class URLopener:
 		import gopherlib
 		host, selector = splithost(url)
 		if not host: raise IOError, ('gopher error', 'no host given')
+		host = unquote(host)
 		type, selector = splitgophertype(selector)
 		selector, query = splitquery(selector)
 		selector = unquote(selector)
@@ -329,7 +338,6 @@ class URLopener:
 		host, port = splitport(host)
 		if not port and socket.gethostbyname(host) in (
 			  localhost(), thishost()):
-			file = unquote(file)
 			return addinfourl(
 				open(url2pathname(file), 'rb'),
 				headers, 'file:'+file)
@@ -343,6 +351,9 @@ class URLopener:
 		user, host = splituser(host)
 		if user: user, passwd = splitpasswd(user)
 		else: passwd = None
+		host = unquote(host)
+		user = unquote(user or '')
+		passwd = unquote(passwd or '')
 		host = socket.gethostbyname(host)
 		if not port:
 			import ftplib
@@ -350,6 +361,7 @@ class URLopener:
 		else:
 			port = int(port)
 		path, attrs = splitattr(path)
+		path = unquote(path)
 		dirs = string.splitfields(path, '/')
 		dirs, file = dirs[:-1], dirs[-1]
 		if dirs and not dirs[0]: dirs = dirs[1:]
@@ -548,13 +560,11 @@ def noheaders():
 # Class used by open_ftp() for cache of open FTP connections
 class ftpwrapper:
 	def __init__(self, user, passwd, host, port, dirs):
-		self.user = unquote(user or '')
-		self.passwd = unquote(passwd or '')
+		self.user = user
+		self.passwd = passwd
 		self.host = host
 		self.port = port
-		self.dirs = []
-		for dir in dirs:
-			self.dirs.append(unquote(dir))
+		self.dirs = dirs
 		self.init()
 	def init(self):
 		import ftplib