From 199d2f79972431e1d47eaaea8cdb6cab78669d14 Mon Sep 17 00:00:00 2001 From: Raymond Hettinger Date: Fri, 9 Sep 2005 22:27:13 +0000 Subject: SF #1285086: urllib.quote is too slow Simplify and speed-up quote() function. --- Lib/urllib.py | 36 ++++++++++++------------------------ 1 file changed, 12 insertions(+), 24 deletions(-) diff --git a/Lib/urllib.py b/Lib/urllib.py index 1daa49d..b8ba454 100644 --- a/Lib/urllib.py +++ b/Lib/urllib.py @@ -1076,22 +1076,7 @@ def unquote_plus(s): always_safe = ('ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' '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 c in _fast_safe: - res[i] = '%%%02X' % ord(c) - return ''.join(res) +_safemaps = {} def quote(s, safe = '/'): """quote('abc def') -> 'abc%20def' @@ -1114,14 +1099,17 @@ def quote(s, safe = '/'): called on a path where the existing slash characters are used as reserved characters. """ - safe = always_safe + safe - if _fast_safe_test == safe: - return _fast_quote(s) - res = list(s) - for i in range(len(res)): - c = res[i] - if c not in safe: - res[i] = '%%%02X' % ord(c) + cachekey = (safe, always_safe) + try: + safe_map = _safemaps[cachekey] + except KeyError: + safe += always_safe + safe_map = {} + for i in range(256): + c = chr(i) + safe_map[c] = (c in safe) and c or ('%%%02X' % i) + _safemaps[cachekey] = safe_map + res = map(safe_map.__getitem__, s) return ''.join(res) def quote_plus(s, safe = ''): -- cgit v0.12