Remove "," from the list of always_safe characters. It is a reserved

character according to RFC 2396. Add some text to quote doc string
that explains the quoting rules better.

This closes SF Bug #114427.

Add _fast_quote operation that uses a dictionary instead of a list
when the standard set of safe characters is used.
This commit is contained in:
Jeremy Hylton 2000-09-14 16:59:07 +00:00
parent d94f70716e
commit 7ae51bf82d
2 changed files with 62 additions and 8 deletions

View File

@ -12,3 +12,21 @@
test = urllib.quote(chars) test = urllib.quote(chars)
assert test == expected, "urllib.quote problem" assert test == expected, "urllib.quote problem"
test2 = urllib.unquote(expected)
assert test2 == chars
in1 = "abc/def"
out1_1 = "abc/def"
out1_2 = "abc%2fdef"
assert urllib.quote(in1) == out1_1, "urllib.quote problem"
assert urllib.quote(in1, '') == out1_2, "urllib.quote problem"
in2 = "abc?def"
out2_1 = "abc%3fdef"
out2_2 = "abc?def"
assert urllib.quote(in2) == out2_1, "urllib.quote problem"
assert urllib.quote(in2, '?') == out2_2, "urllib.quote problem"

View File

@ -426,7 +426,7 @@ def open_ftp(self, url):
dirs, file = dirs[:-1], dirs[-1] dirs, file = dirs[:-1], dirs[-1]
if dirs and not dirs[0]: dirs = dirs[1:] if dirs and not dirs[0]: dirs = dirs[1:]
if dirs and not dirs[0]: dirs[0] = '/' if dirs and not dirs[0]: dirs[0] = '/'
key = (user, host, port, string.joinfields(dirs, '/')) key = user, host, port, string.join(dirs, '/')
# XXX thread unsafe! # XXX thread unsafe!
if len(self.ftpcache) > MAXFTPCACHE: if len(self.ftpcache) > MAXFTPCACHE:
# Prune the cache, rather arbitrarily # Prune the cache, rather arbitrarily
@ -1013,22 +1013,58 @@ def unquote_plus(s):
always_safe = ('ABCDEFGHIJKLMNOPQRSTUVWXYZ' always_safe = ('ABCDEFGHIJKLMNOPQRSTUVWXYZ'
'abcdefghijklmnopqrstuvwxyz' 'abcdefghijklmnopqrstuvwxyz'
'0123456789' '_,.-') '0123456789' '_.-')
_fast_safe_test = always_safe + '/'
_fast_safe = None
def _fast_quote(s):
global _fast_safe
if _fast_safe is None:
_fast_safe = {}
for c in _fast_safe_test:
_fast_safe[c] = c
res = list(s)
for i in range(len(res)):
c = res[i]
if not _fast_safe.has_key(c):
res[i] = '%%%02x' % ord(c)
return string.join(res, '')
def quote(s, safe = '/'): def quote(s, safe = '/'):
"""quote('abc def') -> 'abc%20def'.""" """quote('abc def') -> 'abc%20def'
# XXX Can speed this up an order of magnitude
Each part of a URL, e.g. the path info, the query, etc., has a
different set of reserved characters that must be quoted.
RFC 2396 Uniform Resource Identifiers (URI): Generic Syntax lists
the following reserved characters.
reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
"$" | ","
Each of these characters is reserved in some component of a URL,
but not necessarily in all of them.
By default, the quote function is intended for quoting the path
section of a URL. Thus, it will not encode '/'. This character
is reserved, but in typical usage the quote function is being
called on a path where the existing slash characters are used as
reserved characters.
"""
safe = always_safe + safe safe = always_safe + safe
if _fast_safe_test == safe:
return _fast_quote(s)
res = list(s) res = list(s)
for i in range(len(res)): for i in range(len(res)):
c = res[i] c = res[i]
if c not in safe: if c not in safe:
res[i] = '%%%02x' % ord(c) res[i] = '%%%02x' % ord(c)
return string.joinfields(res, '') return string.join(res, '')
def quote_plus(s, safe = '/'): def quote_plus(s, safe = ''):
# XXX Can speed this up an order of magnitude """Quote the query fragment of a URL; replacing ' ' with '+'"""
if ' ' in s: if ' ' in s:
# replace ' ' with '+'
l = string.split(s, ' ') l = string.split(s, ' ')
for i in range(len(l)): for i in range(len(l)):
l[i] = quote(l[i], safe) l[i] = quote(l[i], safe)