Mirror
/
cpython
mirror of https://github.com/python/cpython
4
1
Fork 0
Code Issues Releases Wiki Activity

Use sys.exc_info() where needed. 

Use "re" module, making it threadsafe.
This commit is contained in:
Guido van Rossum 1997-09-29 23:23:46 +00:00
parent f15d15964b
commit 332e14437c
1 changed files with 106 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

150
Lib/urllib.py
View File

@ -23,12 +23,11 @@
import string import string
import socket import socket
import regex
import os import os
import sys import sys
__version__ = '1.7' __version__ = '1.8'
MAXFTPCACHE = 10 # Trim the ftp cache beyond this size MAXFTPCACHE = 10 # Trim the ftp cache beyond this size
@ -140,8 +139,8 @@ class URLopener:
url = (host, fullurl) # Signal special case to open_*() url = (host, fullurl) # Signal special case to open_*()
name = 'open_' + type name = 'open_' + type
if '-' in name: if '-' in name:
import regsub # replace - with _
name = regsub.gsub('-', '_', name) name = string.join(string.split(name, '-'), '_')
if not hasattr(self, name): if not hasattr(self, name):
if data is None: if data is None:
return self.open_unknown(fullurl) return self.open_unknown(fullurl)
@ -153,7 +152,7 @@ class URLopener:
else: else:
return getattr(self, name)(url, data) return getattr(self, name)(url, data)
except socket.error, msg: except socket.error, msg:
raise IOError, ('socket error', msg), sys.exc_traceback raise IOError, ('socket error', msg), sys.exc_info()[2]
# Overridable interface to open unknown URL type # Overridable interface to open unknown URL type
def open_unknown(self, fullurl, data=None): def open_unknown(self, fullurl, data=None):
@ -347,7 +346,7 @@ class URLopener:
self.ftpcache[key].retrfile(file, type), self.ftpcache[key].retrfile(file, type),
noheaders(), self.openedurl) noheaders(), self.openedurl)
except ftperrors(), msg: except ftperrors(), msg:
raise IOError, ('ftp error', msg), sys.exc_traceback raise IOError, ('ftp error', msg), sys.exc_info()[2]
# Derived class with handlers for errors we can handle (perhaps) # Derived class with handlers for errors we can handle (perhaps)
@ -383,10 +382,11 @@ class FancyURLopener(URLopener):
def http_error_401(self, url, fp, errcode, errmsg, headers): def http_error_401(self, url, fp, errcode, errmsg, headers):
if headers.has_key('www-authenticate'): if headers.has_key('www-authenticate'):
stuff = headers['www-authenticate'] stuff = headers['www-authenticate']
p = regex.compile( import re
'[ \t]*\([^ \t]+\)[ \t]+realm="\([^"]*\)"') match = re.match(
if p.match(stuff) >= 0: '[ \t]*([^ \t]+)[ \t]+realm="([^"]*)"', stuff)
scheme, realm = p.group(1, 2) if match:
scheme, realm = match.group()
if string.lower(scheme) == 'basic': if string.lower(scheme) == 'basic':
return self.retry_http_basic_auth( return self.retry_http_basic_auth(
url, realm) url, realm)
@ -514,7 +514,7 @@ class ftpwrapper:
except ftplib.error_perm, reason: except ftplib.error_perm, reason:
if reason[:3] != '550': if reason[:3] != '550':
raise IOError, ('ftp error', reason), \ raise IOError, ('ftp error', reason), \
sys.exc_traceback sys.exc_info()[2]
if not conn: if not conn:
# Try a directory listing # Try a directory listing
if file: cmd = 'LIST ' + file if file: cmd = 'LIST ' + file
@ -664,41 +664,77 @@ def unwrap(url):
if url[:4] == 'URL:': url = string.strip(url[4:]) if url[:4] == 'URL:': url = string.strip(url[4:])
return url return url
_typeprog = regex.compile('^\([^/:]+\):') _typeprog = None
def splittype(url): def splittype(url):
if _typeprog.match(url) >= 0: global _typeprog
scheme = _typeprog.group(1) if _typeprog is None:
import re
_typeprog = re.compile('^([^/:]+):')
match = _typeprog.match(url)
if match:
scheme = match.group(1)
return scheme, url[len(scheme) + 1:] return scheme, url[len(scheme) + 1:]
return None, url return None, url
_hostprog = regex.compile('^//\([^/]+\)\(.*\)$') _hostprog = None
def splithost(url): def splithost(url):
if _hostprog.match(url) >= 0: return _hostprog.group(1, 2) global _hostprog
if _hostprog is None:
import re
_hostprog = re.compile('^//([^/]+)(.*)$')
match = _hostprog.match(url)
if match: return match.group(1, 2)
return None, url return None, url
_userprog = regex.compile('^\([^@]*\)@\(.*\)$') _userprog = None
def splituser(host): def splituser(host):
if _userprog.match(host) >= 0: return _userprog.group(1, 2) global _userprog
if _userprog is None:
import re
_userprog = re.compile('^([^@]*)@(.*)$')
match = _userprog.match(host)
if match: return match.group(1, 2)
return None, host return None, host
_passwdprog = regex.compile('^\([^:]*\):\(.*\)$') _passwdprog = None
def splitpasswd(user): def splitpasswd(user):
if _passwdprog.match(user) >= 0: return _passwdprog.group(1, 2) global _passwdprog
if _passwdprog is None:
import re
_passwdprog = re.compile('^([^:]*):(.*)$')
match = _passwdprog.match(host)
if match: return match.group(1, 2)
return user, None return user, None
_portprog = regex.compile('^\(.*\):\([0-9]+\)$') _portprog = None
def splitport(host): def splitport(host):
if _portprog.match(host) >= 0: return _portprog.group(1, 2) global _portprog
if _portprog is None:
import re
_portprog = re.compile('^(.*):([0-9]+)$')
match = _portprog.match(host)
if match: return match.group(1, 2)
return host, None return host, None
# Split host and port, returning numeric port. # Split host and port, returning numeric port.
# Return given default port if no ':' found; defaults to -1. # Return given default port if no ':' found; defaults to -1.
# Return numerical port if a valid number are found after ':'. # Return numerical port if a valid number are found after ':'.
# Return None if ':' but not a valid number. # Return None if ':' but not a valid number.
_nportprog = regex.compile('^\(.*\):\(.*\)$') _nportprog = None
def splitnport(host, defport=-1): def splitnport(host, defport=-1):
if _nportprog.match(host) >= 0: global _nportprog
host, port = _nportprog.group(1, 2) if _nportprog is None:
import re
_nportprog = re.compile('^(.*):(.*)$')
match = _nportprog.match(host)
if match:
host, port = match.group(1, 2)
try: try:
if not port: raise string.atoi_error, "no digits" if not port: raise string.atoi_error, "no digits"
nport = string.atoi(port) nport = string.atoi(port)
@ -707,23 +743,41 @@ def splitnport(host, defport=-1):
return host, nport return host, nport
return host, defport return host, defport
_queryprog = regex.compile('^\(.*\)\?\([^?]*\)$') _queryprog = None
def splitquery(url): def splitquery(url):
if _queryprog.match(url) >= 0: return _queryprog.group(1, 2) global _queryprog
if _queryprog is None:
import re
_queryprog = re.compile('^(.*)\?([^?]*)$')
match = _queryprog.match(url)
if match: return match.group(1, 2)
return url, None return url, None
_tagprog = regex.compile('^\(.*\)#\([^#]*\)$') _tagprog = None
def splittag(url): def splittag(url):
if _tagprog.match(url) >= 0: return _tagprog.group(1, 2) global _tagprog
if _tagprog is None:
import re
_tagprog = re.compile('^(.*)#([^#]*)$')
match = _tagprog.match(url)
if match: return match.group(1, 2)
return url, None return url, None
def splitattr(url): def splitattr(url):
words = string.splitfields(url, ';') words = string.splitfields(url, ';')
return words[0], words[1:] return words[0], words[1:]
_valueprog = regex.compile('^\([^=]*\)=\(.*\)$') _valueprog = None
def splitvalue(attr): def splitvalue(attr):
if _valueprog.match(attr) >= 0: return _valueprog.group(1, 2) global _valueprog
if _valueprog is None:
import re
_valueprog = re.compile('^([^=]*)=(.*)$')
match = _valueprog.match(attr)
if match: return match.group(1, 2)
return attr, None return attr, None
def splitgophertype(selector): def splitgophertype(selector):
@ -731,24 +785,30 @@ def splitgophertype(selector):
return selector[1], selector[2:] return selector[1], selector[2:]
return None, selector return None, selector
_quoteprog = regex.compile('%[0-9a-fA-F][0-9a-fA-F]') _quoteprog = None
def unquote(s): def unquote(s):
global _quoteprog
if _quoteprog is None:
import re
_quoteprog = re.compile('%[0-9a-fA-F][0-9a-fA-F]')
i = 0 i = 0
n = len(s) n = len(s)
res = [] res = []
while 0 <= i < n: while 0 <= i < n:
j = _quoteprog.search(s, i) match = _quoteprog.search(s, i)
if j < 0: if not match:
res.append(s[i:]) res.append(s[i:])
break break
j = match.start(0)
res.append(s[i:j] + chr(string.atoi(s[j+1:j+3], 16))) res.append(s[i:j] + chr(string.atoi(s[j+1:j+3], 16)))
i = j+3 i = j+3
return string.joinfields(res, '') return string.joinfields(res, '')
def unquote_plus(s): def unquote_plus(s):
if '+' in s: if '+' in s:
import regsub # replace '+' with ' '
s = regsub.gsub('+', ' ', s) s = string.join(string.split(s, '+'), ' ')
return unquote(s) return unquote(s)
always_safe = string.letters + string.digits + '_,.-' always_safe = string.letters + string.digits + '_,.-'
@ -764,8 +824,8 @@ def quote(s, safe = '/'):
def quote_plus(s, safe = '/'): def quote_plus(s, safe = '/'):
if ' ' in s: if ' ' in s:
import regsub # replace ' ' with '+'
s = regsub.gsub(' ', '+', s) s = string.join(string.split(s, ' '), '+')
return quote(s, safe + '+') return quote(s, safe + '+')
else: else:
return quote(s, safe) return quote(s, safe)
@ -810,16 +870,15 @@ def test1():
# Test program # Test program
def test(): def test():
import sys import sys
import regsub
args = sys.argv[1:] args = sys.argv[1:]
if not args: if not args:
args = [ args = [
'/etc/passwd', '/etc/passwd',
'file:/etc/passwd', 'file:/etc/passwd',
'file://localhost/etc/passwd', 'file://localhost/etc/passwd',
'ftp://ftp.cwi.nl/etc/passwd', 'ftp://ftp.python.org/etc/passwd',
'gopher://gopher.cwi.nl/11/', 'gopher://gopher.micro.umn.edu/1/',
'http://www.cwi.nl/index.html', 'http://www.python.org/index.html',
] ]
try: try:
for url in args: for url in args:
@ -833,7 +892,10 @@ def test():
fp = open(fn, 'rb') fp = open(fn, 'rb')
data = fp.read() data = fp.read()
del fp del fp
print regsub.gsub('\r', '', data) if '\r' in data:
table = string.maketrans("", "")
data = string.translate(data, table, "\r")
print data
fn, h = None, None fn, h = None, None
print '-'*40 print '-'*40
finally: finally:
@ -841,5 +903,5 @@ def test():
# Run test program when run as a script # Run test program when run as a script
if __name__ == '__main__': if __name__ == '__main__':
## test1() test1()
test() test()