From c7b8e8682e9dc8d4a5050c511a3e5f70a098553e Mon Sep 17 00:00:00 2001 From: Florent Xicluna Date: Mon, 17 May 2010 17:33:07 +0000 Subject: [PATCH] Issue #1285086: Speed up urllib.parse functions: quote, quote_from_bytes, unquote, unquote_to_bytes. Recorded merge of revisions 81265 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r81265 | florent.xicluna | 2010-05-17 15:35:09 +0200 (lun, 17 mai 2010) | 2 lines Issue #1285086: Speed up urllib.quote and urllib.unquote for simple cases. ........ --- Lib/urllib/parse.py | 93 ++++++++++++++++++++++++++------------------- Misc/NEWS | 3 ++ 2 files changed, 56 insertions(+), 40 deletions(-) diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index a391face7c3..33790da3f99 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -41,7 +41,7 @@ uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'imap', uses_netloc = ['ftp', 'http', 'gopher', 'nntp', 'telnet', 'imap', 'wais', 'file', 'mms', 'https', 'shttp', 'snews', 'prospero', 'rtsp', 'rtspu', 'rsync', '', - 'svn', 'svn+ssh', 'sftp', 'nfs',' git', 'git+ssh'] + 'svn', 'svn+ssh', 'sftp', 'nfs', 'git', 'git+ssh'] non_hierarchical = ['gopher', 'hdl', 'mailto', 'news', 'telnet', 'wais', 'imap', 'snews', 'sip', 'sips'] uses_params = ['ftp', 'hdl', 'prospero', 'http', 'imap', @@ -307,17 +307,20 @@ def unquote_to_bytes(string): """unquote_to_bytes('abc%20def') -> b'abc def'.""" # Note: strings are encoded as UTF-8. This is only an issue if it contains # unescaped non-ASCII characters, which URIs should not. + if not string: + return b'' if isinstance(string, str): string = string.encode('utf-8') res = string.split(b'%') - res[0] = res[0] - for i in range(1, len(res)): - item = res[i] + if len(res) == 1: + return string + string = res[0] + for item in res[1:]: try: - res[i] = bytes([int(item[:2], 16)]) + item[2:] + string += bytes([int(item[:2], 16)]) + item[2:] except ValueError: - res[i] = b'%' + item - return b''.join(res) + string += b'%' + item + return string def unquote(string, encoding='utf-8', errors='replace'): """Replace %xx escapes by their single-character equivalent. The optional @@ -329,36 +332,39 @@ def unquote(string, encoding='utf-8', errors='replace'): unquote('abc%20def') -> 'abc def'. """ - if encoding is None: encoding = 'utf-8' - if errors is None: errors = 'replace' - # pct_sequence: contiguous sequence of percent-encoded bytes, decoded - # (list of single-byte bytes objects) - pct_sequence = [] + if not string: + return string res = string.split('%') - for i in range(1, len(res)): - item = res[i] + if len(res) == 1: + return string + if encoding is None: + encoding = 'utf-8' + if errors is None: + errors = 'replace' + # pct_sequence: contiguous sequence of percent-encoded bytes + pct_sequence = b'' + string = res[0] + for item in res[1:]: try: - if not item: raise ValueError - pct_sequence.append(bytes.fromhex(item[:2])) + if not item: + raise ValueError + pct_sequence += bytes.fromhex(item[:2]) rest = item[2:] + if not rest: + # This segment was just a single percent-encoded character. + # May be part of a sequence of code units, so delay decoding. + # (Stored in pct_sequence). + continue except ValueError: rest = '%' + item - if not rest: - # This segment was just a single percent-encoded character. - # May be part of a sequence of code units, so delay decoding. - # (Stored in pct_sequence). - res[i] = '' - else: - # Encountered non-percent-encoded characters. Flush the current - # pct_sequence. - res[i] = b''.join(pct_sequence).decode(encoding, errors) + rest - pct_sequence = [] + # Encountered non-percent-encoded characters. Flush the current + # pct_sequence. + string += pct_sequence.decode(encoding, errors) + rest + pct_sequence = b'' if pct_sequence: # Flush the final pct_sequence - # res[-1] will always be empty if pct_sequence != [] - assert not res[-1], "string=%r, res=%r" % (string, res) - res[-1] = b''.join(pct_sequence).decode(encoding, errors) - return ''.join(res) + string += pct_sequence.decode(encoding, errors) + return string def parse_qs(qs, keep_blank_values=False, strict_parsing=False): """Parse a query given as a string argument. @@ -439,7 +445,8 @@ _ALWAYS_SAFE = frozenset(b'ABCDEFGHIJKLMNOPQRSTUVWXYZ' b'abcdefghijklmnopqrstuvwxyz' b'0123456789' b'_.-') -_safe_quoters= {} +_ALWAYS_SAFE_BYTES = bytes(_ALWAYS_SAFE) +_safe_quoters = {} class Quoter(collections.defaultdict): """A mapping from bytes (in range(0,256)) to strings. @@ -451,7 +458,7 @@ class Quoter(collections.defaultdict): # of cached keys don't call Python code at all). def __init__(self, safe): """safe: bytes object.""" - self.safe = _ALWAYS_SAFE.union(c for c in safe if c < 128) + self.safe = _ALWAYS_SAFE.union(safe) def __repr__(self): # Without this, will just display as a defaultdict @@ -459,7 +466,7 @@ class Quoter(collections.defaultdict): def __missing__(self, b): # Handle a cache miss. Store quoted string in cache and return. - res = b in self.safe and chr(b) or ('%%%02X' % b) + res = chr(b) if b in self.safe else '%{:02X}'.format(b) self[b] = res return res @@ -493,6 +500,8 @@ def quote(string, safe='/', encoding=None, errors=None): errors='strict' (unsupported characters raise a UnicodeEncodeError). """ if isinstance(string, str): + if not string: + return string if encoding is None: encoding = 'utf-8' if errors is None: @@ -527,18 +536,22 @@ def quote_from_bytes(bs, safe='/'): not perform string-to-bytes encoding. It always returns an ASCII string. quote_from_bytes(b'abc def\xab') -> 'abc%20def%AB' """ + if not isinstance(bs, (bytes, bytearray)): + raise TypeError("quote_from_bytes() expected bytes") + if not bs: + return '' if isinstance(safe, str): # Normalize 'safe' by converting to bytes and removing non-ASCII chars safe = safe.encode('ascii', 'ignore') - cachekey = bytes(safe) # In case it was a bytearray - if not (isinstance(bs, bytes) or isinstance(bs, bytearray)): - raise TypeError("quote_from_bytes() expected a bytes") + else: + safe = bytes([c for c in safe if c < 128]) + if not bs.rstrip(_ALWAYS_SAFE_BYTES + safe): + return bs.decode() try: - quoter = _safe_quoters[cachekey] + quoter = _safe_quoters[safe] except KeyError: - quoter = Quoter(safe) - _safe_quoters[cachekey] = quoter - return ''.join([quoter[char] for char in bs]) + _safe_quoters[safe] = quoter = Quoter(safe).__getitem__ + return ''.join([quoter(char) for char in bs]) def urlencode(query, doseq=False): """Encode a sequence of two-element tuples or dictionary into a URL query string. diff --git a/Misc/NEWS b/Misc/NEWS index 4f7ee6c7075..1df122b0aa1 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -366,6 +366,9 @@ C-API Library ------- +- Issue #1285086: Speed up urllib.parse functions: quote, quote_from_bytes, + unquote, unquote_to_bytes. + - Issue #8688: Distutils now recalculates MANIFEST everytime. - Issue #8477: ssl.RAND_egd() and ssl._test_decode_cert() support str with