mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-09-27 02:39:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

Some cleanup -- don't use splitfields/joinfields, standardize

Browse source 
indentation (tabs only), rationalize some code in urljoin...
This commit is contained in:
Guido van Rossum 2000-04-10 17:02:46 +00:00
parent 3bb1edb328
commit a25d7ddbf0
1 changed files with 16 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

34
Lib/urlparse.py
View file

@ -6,7 +6,7 @@ UC Irvine, June 1995.
# Standard/builtin Python modules # Standard/builtin Python modules
import string import string
from string import joinfields, splitfields, rfind from string import join, split, rfind
# A classification of schemes ('' means apply by default) # A classification of schemes ('' means apply by default)
uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'wais', 'file', uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'wais', 'file',
@ -37,9 +37,9 @@ MAX_CACHE_SIZE = 20
_parse_cache = {} _parse_cache = {}
def clear_cache(): def clear_cache():
"""Clear the parse cache.""" """Clear the parse cache."""
global _parse_cache global _parse_cache
_parse_cache = {} _parse_cache = {}
def urlparse(url, scheme = '', allow_fragments = 1): def urlparse(url, scheme = '', allow_fragments = 1):
@ -53,7 +53,7 @@ def urlparse(url, scheme = '', allow_fragments = 1):
if cached: if cached:
return cached return cached
if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth
clear_cache() clear_cache()
find = string.find find = string.find
netloc = path = params = query = fragment = '' netloc = path = params = query = fragment = ''
i = find(url, ':') i = find(url, ':')
@ -151,10 +151,8 @@ def urljoin(base, url, allow_fragments = 1):
if not path: if not path:
return urlunparse((scheme, netloc, bpath, return urlunparse((scheme, netloc, bpath,
params, query or bquery, fragment)) params, query or bquery, fragment))
i = rfind(bpath, '/') segments = split(bpath, '/')[:-1] + split(path, '/')
if i >= 0: # XXX The stuff below is bogus in various ways...
path = bpath[:i] + '/' + path
segments = splitfields(path, '/')
if segments[-1] == '.': if segments[-1] == '.':
segments[-1] = '' segments[-1] = ''
while '.' in segments: while '.' in segments:
@ -173,19 +171,19 @@ def urljoin(base, url, allow_fragments = 1):
segments[-1] = '' segments[-1] = ''
elif len(segments) >= 2 and segments[-1] == '..': elif len(segments) >= 2 and segments[-1] == '..':
segments[-2:] = [''] segments[-2:] = ['']
return urlunparse((scheme, netloc, joinfields(segments, '/'), return urlunparse((scheme, netloc, join(segments, '/'),
params, query, fragment)) params, query, fragment))
def urldefrag(url): def urldefrag(url):
"""Removes any existing fragment from URL. """Removes any existing fragment from URL.
Returns a tuple of the defragmented URL and the fragment. If Returns a tuple of the defragmented URL and the fragment. If
the URL contained no fragments, the second element is the the URL contained no fragments, the second element is the
empty string. empty string.
""" """
s, n, p, a, q, frag = urlparse(url) s, n, p, a, q, frag = urlparse(url)
defrag = urlunparse((s, n, p, a, q, '')) defrag = urlunparse((s, n, p, a, q, ''))
return defrag, frag return defrag, frag
test_input = """ test_input = """