diff -r 6a997c2b8eb6 Lib/_strptime.py --- a/Lib/_strptime.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/_strptime.py Sat Jul 05 23:02:45 2008 +0200 @@ -14,7 +14,7 @@ import locale import locale import calendar from re import compile as re_compile -from re import IGNORECASE +from re import IGNORECASE, ASCII from re import escape as re_escape from datetime import date as datetime_date try: @@ -262,7 +262,7 @@ class TimeRE(dict): def compile(self, format): """Return a compiled re object for the format string.""" - return re_compile(self.pattern(format), IGNORECASE) + return re_compile(self.pattern(format), IGNORECASE | ASCII) _cache_lock = _thread_allocate_lock() # DO NOT modify _TimeRE_cache or _regex_cache without acquiring the cache lock diff -r 6a997c2b8eb6 Lib/base64.py --- a/Lib/base64.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/base64.py Sat Jul 05 23:02:45 2008 +0200 @@ -39,7 +39,7 @@ def _translate(s, altchars): return s.translate(translation) - + # Base64 encoding/decoding uses binascii def b64encode(s, altchars=None): @@ -126,7 +126,7 @@ def urlsafe_b64decode(s): return b64decode(s, b'-_') - + # Base32 encoding/decoding must be done in Python _b32alphabet = { 0: b'A', 9: b'J', 18: b'S', 27: b'3', @@ -225,7 +225,7 @@ def b32decode(s, casefold=False, map01=N # characters because this will tell us how many null bytes to remove from # the end of the decoded string. padchars = 0 - mo = re.search('(?P[=]*)$', s) + mo = re.search(b'(?P[=]*)$', s) if mo: padchars = len(mo.group('pad')) if padchars > 0: @@ -262,7 +262,7 @@ def b32decode(s, casefold=False, map01=N return b''.join(parts) - + # RFC 3548, Base 16 Alphabet specifies uppercase, but hexlify() returns # lowercase. The RFC also recommends against accepting input case # insensitively. @@ -291,12 +291,12 @@ def b16decode(s, casefold=False): raise TypeError("expected bytes, not %s" % s.__class__.__name__) if casefold: s = s.upper() - if re.search('[^0-9A-F]', s): + if re.search(b'[^0-9A-F]', s): raise binascii.Error('Non-base16 digit found') return binascii.unhexlify(s) - + # Legacy interface. This code could be cleaned up since I don't believe # binascii has any line length limitations. It just doesn't seem worth it # though. The files should be opened in binary mode. @@ -353,7 +353,7 @@ def decodestring(s): return binascii.a2b_base64(s) - + # Usable as a script... def main(): """Small main program""" diff -r 6a997c2b8eb6 Lib/decimal.py --- a/Lib/decimal.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/decimal.py Sat Jul 05 23:02:45 2008 +0200 @@ -5417,7 +5417,7 @@ ExtendedContext = Context( # 2. For finite numbers (not infinities and NaNs) the body of the # number between the optional sign and the optional exponent must have # at least one decimal digit, possibly after the decimal point. The -# lookahead expression '(?=\d|\.\d)' checks this. +# lookahead expression '(?=[0-9]|\.[0-9])' checks this. # # As the flag UNICODE is not enabled here, we're explicitly avoiding any # other meaning for \d than the numbers [0-9]. diff -r 6a997c2b8eb6 Lib/distutils/cygwinccompiler.py --- a/Lib/distutils/cygwinccompiler.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/distutils/cygwinccompiler.py Sat Jul 05 23:02:45 2008 +0200 @@ -409,7 +409,7 @@ def get_versions(): out = os.popen(gcc_exe + ' -dumpversion','r') out_string = out.read() out.close() - result = re.search('(\d+\.\d+(\.\d+)*)',out_string) + result = re.search('(\d+\.\d+(\.\d+)*)', out_string, re.ASCII) if result: gcc_version = StrictVersion(result.group(1)) else: @@ -421,7 +421,7 @@ def get_versions(): out = os.popen(ld_exe + ' -v','r') out_string = out.read() out.close() - result = re.search('(\d+\.\d+(\.\d+)*)',out_string) + result = re.search('(\d+\.\d+(\.\d+)*)', out_string, re.ASCII) if result: ld_version = StrictVersion(result.group(1)) else: @@ -433,7 +433,7 @@ def get_versions(): out = os.popen(dllwrap_exe + ' --version','r') out_string = out.read() out.close() - result = re.search(' (\d+\.\d+(\.\d+)*)',out_string) + result = re.search(' (\d+\.\d+(\.\d+)*)', out_string, re.ASCII) if result: dllwrap_version = StrictVersion(result.group(1)) else: diff -r 6a997c2b8eb6 Lib/distutils/emxccompiler.py --- a/Lib/distutils/emxccompiler.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/distutils/emxccompiler.py Sat Jul 05 23:02:45 2008 +0200 @@ -300,7 +300,7 @@ def get_versions(): out = os.popen(gcc_exe + ' -dumpversion','r') out_string = out.read() out.close() - result = re.search('(\d+\.\d+\.\d+)',out_string) + result = re.search('(\d+\.\d+\.\d+)', out_string, re.ASCII) if result: gcc_version = StrictVersion(result.group(1)) else: diff -r 6a997c2b8eb6 Lib/distutils/sysconfig.py --- a/Lib/distutils/sysconfig.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/distutils/sysconfig.py Sat Jul 05 23:02:45 2008 +0200 @@ -512,7 +512,7 @@ def get_config_vars(*args): # patched up as well. 'CFLAGS', 'PY_CFLAGS', 'BLDSHARED'): flags = _config_vars[key] - flags = re.sub('-arch\s+\w+\s', ' ', flags) + flags = re.sub('-arch\s+\w+\s', ' ', flags, re.ASCII) flags = re.sub('-isysroot [^ \t]*', ' ', flags) _config_vars[key] = flags diff -r 6a997c2b8eb6 Lib/distutils/util.py --- a/Lib/distutils/util.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/distutils/util.py Sat Jul 05 23:02:45 2008 +0200 @@ -81,7 +81,7 @@ def get_platform (): return "%s-%s.%s" % (osname, version, release) elif osname[:6] == "cygwin": osname = "cygwin" - rel_re = re.compile (r'[\d.]+') + rel_re = re.compile (r'[\d.]+', re.ASCII) m = rel_re.match(release) if m: release = m.group() diff -r 6a997c2b8eb6 Lib/distutils/version.py --- a/Lib/distutils/version.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/distutils/version.py Sat Jul 05 23:02:45 2008 +0200 @@ -134,7 +134,7 @@ class StrictVersion (Version): """ version_re = re.compile(r'^(\d+) \. (\d+) (\. (\d+))? ([ab](\d+))?$', - re.VERBOSE) + re.VERBOSE | re.ASCII) def parse (self, vstring): diff -r 6a997c2b8eb6 Lib/distutils/versionpredicate.py --- a/Lib/distutils/versionpredicate.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/distutils/versionpredicate.py Sat Jul 05 23:02:45 2008 +0200 @@ -5,7 +5,8 @@ import operator import operator -re_validPackage = re.compile(r"(?i)^\s*([a-z_]\w*(?:\.[a-z_]\w*)*)(.*)") +re_validPackage = re.compile(r"(?i)^\s*([a-z_]\w*(?:\.[a-z_]\w*)*)(.*)", + re.ASCII) # (package) (rest) re_paren = re.compile(r"^\s*\((.*)\)\s*$") # (list) inside of parentheses @@ -153,7 +154,8 @@ def split_provision(value): global _provision_rx if _provision_rx is None: _provision_rx = re.compile( - "([a-zA-Z_]\w*(?:\.[a-zA-Z_]\w*)*)(?:\s*\(\s*([^)\s]+)\s*\))?$") + "([a-zA-Z_]\w*(?:\.[a-zA-Z_]\w*)*)(?:\s*\(\s*([^)\s]+)\s*\))?$", + re.ASCII) value = value.strip() m = _provision_rx.match(value) if not m: diff -r 6a997c2b8eb6 Lib/email/quoprimime.py --- a/Lib/email/quoprimime.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/email/quoprimime.py Sat Jul 05 23:02:45 2008 +0200 @@ -70,7 +70,7 @@ for c in (b' !"#$%&\'()*+,-./0123456789: _QUOPRI_BODY_MAP[c] = chr(c) - + # Helpers def header_check(octet): """Return True if the octet should be escaped with header quopri.""" @@ -125,7 +125,7 @@ def quote(c): return '=%02X' % ord(c) - + def header_encode(header_bytes, charset='iso-8859-1'): """Encode a single header line with quoted-printable (like) encoding. @@ -149,7 +149,7 @@ def header_encode(header_bytes, charset= return '=?%s?q?%s?=' % (charset, EMPTYSTRING.join(encoded)) - + def body_encode(body, maxlinelen=76, eol=NL): """Encode with quoted-printable, wrapping at maxlinelen characters. @@ -225,7 +225,7 @@ def body_encode(body, maxlinelen=76, eol return encoded_body - + # BAW: I'm not sure if the intent was for the signature of this function to be # the same as base64MIME.decode() or not... def decode(encoded, eol=NL): @@ -280,7 +280,7 @@ decodestring = decode decodestring = decode - + def _unquote_match(match): """Turn a match in the form =AB to the ASCII character with value 0xab""" s = match.group(0) @@ -296,4 +296,4 @@ def header_decode(s): the high level email.Header class for that functionality. """ s = s.replace('_', ' ') - return re.sub(r'=\w{2}', _unquote_match, s) + return re.sub(r'=\w{2}', _unquote_match, s, re.ASCII) diff -r 6a997c2b8eb6 Lib/email/utils.py --- a/Lib/email/utils.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/email/utils.py Sat Jul 05 23:02:45 2008 +0200 @@ -52,7 +52,7 @@ escapesre = re.compile(r'[][\\()"]') escapesre = re.compile(r'[][\\()"]') - + # Helpers def formataddr(pair): @@ -73,7 +73,7 @@ def formataddr(pair): return address - + def getaddresses(fieldvalues): """Return a list of (REALNAME, EMAIL) for each fieldvalue.""" all = COMMASPACE.join(fieldvalues) @@ -81,7 +81,7 @@ def getaddresses(fieldvalues): return a.addresslist - + ecre = re.compile(r''' =\? # literal =? (?P[^?]*?) # non-greedy up to the next ? is the charset @@ -93,7 +93,7 @@ ecre = re.compile(r''' ''', re.VERBOSE | re.IGNORECASE) - + def formatdate(timeval=None, localtime=False, usegmt=False): """Returns a date string as specified by RFC 2822, e.g.: @@ -146,7 +146,7 @@ def formatdate(timeval=None, localtime=F zone) - + def make_msgid(idstring=None): """Returns a string suitable for RFC 2822 compliant Message-ID, e.g: @@ -168,7 +168,7 @@ def make_msgid(idstring=None): return msgid - + # These functions are in the standalone mimelib version only because they've # subsequently been fixed in the latest Python versions. We use this to worm # around broken older Pythons. @@ -202,7 +202,7 @@ def unquote(str): return str - + # RFC2231-related functions - parameter encoding and decoding def decode_rfc2231(s): """Decode string according to RFC 2231""" @@ -227,7 +227,8 @@ def encode_rfc2231(s, charset=None, lang return "%s'%s'%s" % (charset, language, s) -rfc2231_continuation = re.compile(r'^(?P\w+)\*((?P[0-9]+)\*?)?$') +rfc2231_continuation = re.compile(r'^(?P\w+)\*((?P[0-9]+)\*?)?$', + re.ASCII) def decode_params(params): """Decode parameters list according to RFC 2231. diff -r 6a997c2b8eb6 Lib/encodings/idna.py --- a/Lib/encodings/idna.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/encodings/idna.py Sat Jul 05 23:02:45 2008 +0200 @@ -176,12 +176,10 @@ class Codec(codecs.Codec): return "", 0 # IDNA allows decoding to operate on Unicode strings, too. - if isinstance(input, bytes): - labels = dots.split(input) - else: - # Force to bytes + if not isinstance(input, bytes): + # XXX obviously wrong, see #3232 input = bytes(input) - labels = input.split(b".") + labels = input.split(b".") if labels and len(labels[-1]) == 0: trailing_dot = '.' diff -r 6a997c2b8eb6 Lib/ftplib.py --- a/Lib/ftplib.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/ftplib.py Sat Jul 05 23:02:45 2008 +0200 @@ -590,7 +590,8 @@ def parse150(resp): global _150_re if _150_re is None: import re - _150_re = re.compile("150 .* \((\d+) bytes\)", re.IGNORECASE) + _150_re = re.compile( + "150 .* \((\d+) bytes\)", re.IGNORECASE | re.ASCII) m = _150_re.match(resp) if not m: return None @@ -613,7 +614,7 @@ def parse227(resp): global _227_re if _227_re is None: import re - _227_re = re.compile(r'(\d+),(\d+),(\d+),(\d+),(\d+),(\d+)') + _227_re = re.compile(r'(\d+),(\d+),(\d+),(\d+),(\d+),(\d+)', re.ASCII) m = _227_re.search(resp) if not m: raise error_proto(resp) diff -r 6a997c2b8eb6 Lib/html/parser.py --- a/Lib/html/parser.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/html/parser.py Sat Jul 05 23:02:45 2008 +0200 @@ -385,4 +385,4 @@ class HTMLParser(_markupbase.ParserBase) return '&'+s+';' return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", - replaceEntities, s) + replaceEntities, s, re.ASCII) diff -r 6a997c2b8eb6 Lib/http/cookiejar.py --- a/Lib/http/cookiejar.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/http/cookiejar.py Sat Jul 05 23:02:45 2008 +0200 @@ -121,7 +121,7 @@ def time2netscape(t=None): UTC_ZONES = {"GMT": None, "UTC": None, "UT": None, "Z": None} -TIMEZONE_RE = re.compile(r"^([-+])?(\d\d?):?(\d\d)?$") +TIMEZONE_RE = re.compile(r"^([-+])?(\d\d?):?(\d\d)?$", re.ASCII) def offset_from_tz_string(tz): offset = None if tz in UTC_ZONES: @@ -191,9 +191,9 @@ def _str2time(day, mon, yr, hr, min, sec STRICT_DATE_RE = re.compile( r"^[SMTWF][a-z][a-z], (\d\d) ([JFMASOND][a-z][a-z]) " - "(\d\d\d\d) (\d\d):(\d\d):(\d\d) GMT$") + "(\d\d\d\d) (\d\d):(\d\d):(\d\d) GMT$", re.ASCII) WEEKDAY_RE = re.compile( - r"^(?:Sun|Mon|Tue|Wed|Thu|Fri|Sat)[a-z]*,?\s*", re.I) + r"^(?:Sun|Mon|Tue|Wed|Thu|Fri|Sat)[a-z]*,?\s*", re.I | re.ASCII) LOOSE_HTTP_DATE_RE = re.compile( r"""^ (\d\d?) # day @@ -210,7 +210,7 @@ LOOSE_HTTP_DATE_RE = re.compile( ([-+]?\d{2,4}|(?![APap][Mm]\b)[A-Za-z]+)? # timezone \s* (?:\(\w+\))? # ASCII representation of timezone in parens. - \s*$""", re.X) + \s*$""", re.X | re.ASCII) def http2time(text): """Returns time in seconds since epoch of time represented by a string. @@ -282,7 +282,7 @@ ISO_DATE_RE = re.compile( \s* ([-+]?\d\d?:?(:?\d\d)? |Z|z)? # timezone (Z is "zero meridian", i.e. GMT) - \s*$""", re.X) + \s*$""", re.X | re. ASCII) def iso2time(text): """ As for http2time, but parses the ISO 8601 formats: @@ -489,7 +489,7 @@ def parse_ns_headers(ns_headers): return result -IPV4_RE = re.compile(r"\.\d+$") +IPV4_RE = re.compile(r"\.\d+$", re.ASCII) def is_HDN(text): """Return True if text is a host domain name.""" # XXX @@ -574,7 +574,7 @@ def user_domain_match(A, B): return True return False -cut_port_re = re.compile(r":\d+$") +cut_port_re = re.compile(r":\d+$", re.ASCII) def request_host(request): """Return request-host, as defined by RFC 2965. @@ -1207,7 +1207,7 @@ class CookieJar: domain_re = re.compile(r"[^.]*") dots_re = re.compile(r"^\.+") - magic_re = r"^\#LWP-Cookies-(\d+\.\d+)" + magic_re = re.compile(r"^\#LWP-Cookies-(\d+\.\d+)", re.ASCII) def __init__(self, policy=None): if policy is None: @@ -1856,7 +1856,7 @@ class LWPCookieJar(FileCookieJar): def _really_load(self, f, filename, ignore_discard, ignore_expires): magic = f.readline() - if not re.search(self.magic_re, magic): + if not self.magic_re.search(magic): msg = ("%r does not look like a Set-Cookie3 (LWP) format " "file" % filename) raise LoadError(msg) @@ -1965,7 +1965,7 @@ class MozillaCookieJar(FileCookieJar): header by default (Mozilla can cope with that). """ - magic_re = "#( Netscape)? HTTP Cookie File" + magic_re = re.compile("#( Netscape)? HTTP Cookie File") header = """\ # Netscape HTTP Cookie File # http://www.netscape.com/newsref/std/cookie_spec.html @@ -1977,7 +1977,7 @@ class MozillaCookieJar(FileCookieJar): now = time.time() magic = f.readline() - if not re.search(self.magic_re, magic): + if not self.magic_re.search(magic): f.close() raise LoadError( "%r does not look like a Netscape format cookies file" % diff -r 6a997c2b8eb6 Lib/http/cookies.py --- a/Lib/http/cookies.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/http/cookies.py Sat Jul 05 23:02:45 2008 +0200 @@ -445,7 +445,7 @@ _CookiePattern = re.compile( ""+ _LegalCharsPatt +"*" # Any word or empty string r")" # End of group 'val' r"\s*;?" # Probably ending in a semi-colon - ) + , re.ASCII) # May be removed if safe. # At long last, here is the cookie class. diff -r 6a997c2b8eb6 Lib/imaplib.py --- a/Lib/imaplib.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/imaplib.py Sat Jul 05 23:02:45 2008 +0200 @@ -88,11 +88,12 @@ InternalDate = re.compile(r'.*INTERNALDA r' (?P[0-9][0-9]):(?P[0-9][0-9]):(?P[0-9][0-9])' r' (?P[-+])(?P[0-9][0-9])(?P[0-9][0-9])' r'"') -Literal = re.compile(r'.*{(?P\d+)}$') +Literal = re.compile(r'.*{(?P\d+)}$', re.ASCII) MapCRLF = re.compile(r'\r\n|\r|\n') Response_code = re.compile(r'\[(?P[A-Z-]+)( (?P[^\]]*))?\]') Untagged_response = re.compile(r'\* (?P[A-Z-]+)( (?P.*))?') -Untagged_status = re.compile(r'\* (?P\d+) (?P[A-Z-]+)( (?P.*))?') +Untagged_status = re.compile( + r'\* (?P\d+) (?P[A-Z-]+)( (?P.*))?', re.ASCII) @@ -146,7 +147,7 @@ class IMAP4: class abort(error): pass # Service errors - close and retry class readonly(abort): pass # Mailbox status changed to READ-ONLY - mustquote = re.compile(r"[^\w!#$%&'*+,.:;<=>?^`|~-]") + mustquote = re.compile(r"[^\w!#$%&'*+,.:;<=>?^`|~-]", re.ASCII) def __init__(self, host = '', port = IMAP4_PORT): self.debug = Debug @@ -168,7 +169,7 @@ class IMAP4: self.tagpre = Int2AP(random.randint(4096, 65535)) self.tagre = re.compile(r'(?P' + self.tagpre - + r'\d+) (?P[A-Z]+) (?P.*)') + + r'\d+) (?P[A-Z]+) (?P.*)', re.ASCII) # Get server welcome message, # request and store CAPABILITY response. diff -r 6a997c2b8eb6 Lib/json/decoder.py --- a/Lib/json/decoder.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/json/decoder.py Sat Jul 05 23:02:45 2008 +0200 @@ -67,7 +67,7 @@ def JSONNumber(match, context): fn = getattr(context, 'parse_int', None) or int res = fn(integer) return res, None -pattern(r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?')(JSONNumber) +pattern(r'(-?(?:0|[1-9][0-9]*))(\.[0-9]+)?([eE][-+]?[0-9]+)?')(JSONNumber) STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS) diff -r 6a997c2b8eb6 Lib/logging/handlers.py --- a/Lib/logging/handlers.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/logging/handlers.py Sat Jul 05 23:02:45 2008 +0200 @@ -199,7 +199,7 @@ class TimedRotatingFileHandler(BaseRotat else: raise ValueError("Invalid rollover interval specified: %s" % self.when) - self.extMatch = re.compile(self.extMatch) + self.extMatch = re.compile(self.extMatch, re.ASCII) self.interval = self.interval * interval # multiply by units requested self.rolloverAt = currentTime + self.interval diff -r 6a997c2b8eb6 Lib/platform.py --- a/Lib/platform.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/platform.py Sat Jul 05 23:02:45 2008 +0200 @@ -118,7 +118,7 @@ _libc_search = re.compile(r'(__libc_init '|' '(GLIBC_([0-9.]+))' '|' - '(libc(_\w+)?\.so(?:\.(\d[0-9.]*))?)') + '(libc(_\w+)?\.so(?:\.(\d[0-9.]*))?)', re.ASCII) def libc_ver(executable=sys.executable,lib='',version='', @@ -223,15 +223,15 @@ def _dist_try_harder(distname,version,id return distname,version,id -_release_filename = re.compile(r'(\w+)[-_](release|version)') +_release_filename = re.compile(r'(\w+)[-_](release|version)', re.ASCII) _lsb_release_version = re.compile(r'(.+)' ' release ' '([\d.]+)' - '[^(]*(?:\((.+)\))?') + '[^(]*(?:\((.+)\))?', re.ASCII) _release_version = re.compile(r'([^0-9]+)' '(?: release )?' '([\d.]+)' - '[^(]*(?:\((.+)\))?') + '[^(]*(?:\((.+)\))?', re.ASCII) # See also http://www.novell.com/coolsolutions/feature/11251.html # and http://linuxmafia.com/faq/Admin/release-files.html @@ -464,7 +464,7 @@ def _norm_version(version, build=''): _ver_output = re.compile(r'(?:([\w ]+) ([\w.]+) ' '.*' - 'Version ([\d.]+))') + 'Version ([\d.]+))', re.ASCII) def _syscmd_ver(system='', release='', version='', @@ -1253,16 +1253,16 @@ _sys_version_parser = re.compile( _sys_version_parser = re.compile( r'([\w.+]+)\s*' '\(#?([^,]+),\s*([\w ]+),\s*([\w :]+)\)\s*' - '\[([^\]]+)\]?') + '\[([^\]]+)\]?', re.ASCII) _jython_sys_version_parser = re.compile( - r'([\d\.]+)') + r'([\d\.]+)', re.ASCII) _ironpython_sys_version_parser = re.compile( r'IronPython\s*' '([\d\.]+)' '(?: \(([\d\.]+)\))?' - ' on (.NET [\d\.]+)') + ' on (.NET [\d\.]+)', re.ASCII) _sys_version_cache = {} diff -r 6a997c2b8eb6 Lib/plistlib.py --- a/Lib/plistlib.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/plistlib.py Sat Jul 05 23:02:45 2008 +0200 @@ -147,7 +147,7 @@ class DumbXMLWriter: # Contents should conform to a subset of ISO 8601 # (in particular, YYYY '-' MM '-' DD 'T' HH ':' MM ':' SS 'Z'. Smaller units may be omitted with # a loss of precision) -_dateParser = re.compile(r"(?P\d\d\d\d)(?:-(?P\d\d)(?:-(?P\d\d)(?:T(?P\d\d)(?::(?P\d\d)(?::(?P\d\d))?)?)?)?)?Z") +_dateParser = re.compile(r"(?P\d\d\d\d)(?:-(?P\d\d)(?:-(?P\d\d)(?:T(?P\d\d)(?::(?P\d\d)(?::(?P\d\d))?)?)?)?)?Z", re.ASCII) def _dateFromString(s): order = ('year', 'month', 'day', 'hour', 'minute', 'second') diff -r 6a997c2b8eb6 Lib/posixpath.py --- a/Lib/posixpath.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/posixpath.py Sat Jul 05 23:02:45 2008 +0200 @@ -241,7 +241,7 @@ def expandvars(path): return path if not _varprog: import re - _varprog = re.compile(r'\$(\w+|\{[^}]*\})') + _varprog = re.compile(r'\$(\w+|\{[^}]*\})', re.ASCII) i = 0 while True: m = _varprog.search(path, i) diff -r 6a997c2b8eb6 Lib/py_compile.py --- a/Lib/py_compile.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/py_compile.py Sat Jul 05 23:02:45 2008 +0200 @@ -86,7 +86,7 @@ def read_encoding(file, default): line = f.readline() if not line: break - m = re.match(r".*\bcoding:\s*(\S+)\b", line) + m = re.match(br".*\bcoding:\s*(\S+)\b", line) if m: return m.group(1).decode("ascii") return default diff -r 6a997c2b8eb6 Lib/re.py --- a/Lib/re.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/re.py Sat Jul 05 23:02:45 2008 +0200 @@ -64,11 +64,18 @@ resulting RE will match the second chara \Z Matches only at the end of the string. \b Matches the empty string, but only at the start or end of a word. \B Matches the empty string, but not at the start or end of a word. - \d Matches any decimal digit; equivalent to the set [0-9]. - \D Matches any non-digit character; equivalent to the set [^0-9]. + \d Matches any decimal digit; equivalent to the set [0-9] in + bytes patterns or string patterns with the ASCII flag. + In string patterns without the ASCII flag, it will match the whole + range of Unicode digits. + \D Matches any non-digit character; equivalent to [^\d]. \s Matches any whitespace character; equivalent to [ \t\n\r\f\v]. \S Matches any non-whitespace character; equiv. to [^ \t\n\r\f\v]. - \w Matches any alphanumeric character; equivalent to [a-zA-Z0-9_]. + \w Matches any alphanumeric character; equivalent to [a-zA-Z0-9_] + in bytes patterns or string patterns with the ASCII flag. + In string patterns without the ASCII flag, it will match the + range of Unicode alphanumeric characters (letters plus digits + plus underscore). With LOCALE, it will match the set [0-9_] plus characters defined as letters for the current locale. \W Matches the complement of \w. @@ -87,6 +94,12 @@ This module exports the following functi escape Backslash all non-alphanumerics in a string. Some of the functions in this module takes flags as optional parameters: + A ASCII For string patterns, make \w, \W, \b, \B, \d, \D + match the corresponding ASCII character categories + (rather than the whole Unicode categories, which is the + default). + For bytes patterns, this flag is the only available + behaviour and needn't be specified. I IGNORECASE Perform case-insensitive matching. L LOCALE Make \w, \W, \b, \B, dependent on the current locale. M MULTILINE "^" matches the beginning of lines (after a newline) @@ -95,7 +108,8 @@ Some of the functions in this module tak as the end of the string. S DOTALL "." matches any character at all, including the newline. X VERBOSE Ignore whitespace and comments for nicer looking RE's. - U UNICODE Make \w, \W, \b, \B, dependent on the Unicode locale. + U UNICODE For compatibility only. Ignored for string patterns (it + is the default), and forbidden for bytes patterns. This module also defines an exception 'error'. @@ -107,16 +121,17 @@ import sre_parse # public symbols __all__ = [ "match", "search", "sub", "subn", "split", "findall", - "compile", "purge", "template", "escape", "I", "L", "M", "S", "X", - "U", "IGNORECASE", "LOCALE", "MULTILINE", "DOTALL", "VERBOSE", + "compile", "purge", "template", "escape", "A", "I", "L", "M", "S", "X", + "U", "ASCII", "IGNORECASE", "LOCALE", "MULTILINE", "DOTALL", "VERBOSE", "UNICODE", "error" ] __version__ = "2.2.1" # flags +A = ASCII = sre_compile.SRE_FLAG_ASCII # assume ascii "locale" I = IGNORECASE = sre_compile.SRE_FLAG_IGNORECASE # ignore case L = LOCALE = sre_compile.SRE_FLAG_LOCALE # assume current 8-bit locale -U = UNICODE = sre_compile.SRE_FLAG_UNICODE # assume unicode locale +U = UNICODE = sre_compile.SRE_FLAG_UNICODE # assume unicode "locale" M = MULTILINE = sre_compile.SRE_FLAG_MULTILINE # make anchors look for newline S = DOTALL = sre_compile.SRE_FLAG_DOTALL # make dot match newline X = VERBOSE = sre_compile.SRE_FLAG_VERBOSE # ignore whitespace and comments diff -r 6a997c2b8eb6 Lib/sre_constants.py --- a/Lib/sre_constants.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/sre_constants.py Sat Jul 05 23:02:45 2008 +0200 @@ -207,9 +207,10 @@ SRE_FLAG_LOCALE = 4 # honour system loca SRE_FLAG_LOCALE = 4 # honour system locale SRE_FLAG_MULTILINE = 8 # treat target as multiline string SRE_FLAG_DOTALL = 16 # treat target as a single string -SRE_FLAG_UNICODE = 32 # use unicode locale +SRE_FLAG_UNICODE = 32 # use unicode "locale" SRE_FLAG_VERBOSE = 64 # ignore whitespace and comments SRE_FLAG_DEBUG = 128 # debugging +SRE_FLAG_ASCII = 256 # use ascii "locale" # flags for INFO primitive SRE_INFO_PREFIX = 1 # has prefix diff -r 6a997c2b8eb6 Lib/sre_parse.py --- a/Lib/sre_parse.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/sre_parse.py Sat Jul 05 23:02:45 2008 +0200 @@ -200,7 +200,7 @@ class Tokenizer: except IndexError: raise error("bogus escape (end of line)") if isinstance(self.string, bytes): - char = chr(c) + c = chr(c) char = char + c self.index = self.index + len(char) self.next = char @@ -672,6 +672,18 @@ def _parse(source, state): return subpattern +def fix_flags(src, flags): + # Check and fix flags according to the type of pattern (str or bytes) + if isinstance(src, str): + if not flags & SRE_FLAG_ASCII: + flags |= SRE_FLAG_UNICODE + elif flags & SRE_FLAG_UNICODE: + raise ValueError("ASCII and UNICODE flags are incompatible") + else: + if flags & SRE_FLAG_UNICODE: + raise ValueError("can't use UNICODE flag with a bytes pattern") + return flags + def parse(str, flags=0, pattern=None): # parse 're' pattern into list of (opcode, argument) tuples @@ -683,6 +695,7 @@ def parse(str, flags=0, pattern=None): pattern.str = str p = _parse_sub(source, pattern, 0) + p.pattern.flags = fix_flags(str, p.pattern.flags) tail = source.get() if tail == ")": diff -r 6a997c2b8eb6 Lib/tarfile.py --- a/Lib/tarfile.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/tarfile.py Sat Jul 05 23:02:45 2008 +0200 @@ -1368,7 +1368,7 @@ class TarInfo(object): # "%d %s=%s\n" % (length, keyword, value). length is the size # of the complete record including the length field itself and # the newline. keyword and value are both UTF-8 encoded strings. - regex = re.compile(r"(\d+) ([^=]+)=", re.U) + regex = re.compile(br"(\d+) ([^=]+)=") pos = 0 while True: match = regex.match(buf, pos) diff -r 6a997c2b8eb6 Lib/test/re_tests.py --- a/Lib/test/re_tests.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/test/re_tests.py Sat Jul 05 23:02:45 2008 +0200 @@ -661,14 +661,10 @@ 123""", SUCCEED, 'found', 'abc'), ('^([ab]*?)(?a)(?Pb)").groupindex, @@ -614,8 +597,8 @@ class ReTests(unittest.TestCase): import array for typecode in 'bBuhHiIlLfd': a = array.array(typecode) - self.assertEqual(re.compile("bla").match(a), None) - self.assertEqual(re.compile("").match(a).groups(), ()) + self.assertEqual(re.compile(b"bla").match(a), None) + self.assertEqual(re.compile(b"").match(a).groups(), ()) def test_inline_flags(self): # Bug #1700 @@ -657,6 +640,43 @@ class ReTests(unittest.TestCase): self.assertEqual(pattern.sub('#', 'a\nb\n' ), 'a#\nb#\n#' ) self.assertEqual(pattern.sub('#', 'a\nb\nc'), 'a#\nb#\nc#') self.assertEqual(pattern.sub('#', '\n'), '#\n#') + + def test_bytes_str_mixing(self): + # Mixing str and bytes is disallowed + pat = re.compile('.') + bpat = re.compile(b'.') + self.assertRaises(TypeError, pat.match, b'b') + self.assertRaises(TypeError, bpat.match, 'b') + self.assertRaises(TypeError, pat.sub, b'b', 'c') + self.assertRaises(TypeError, pat.sub, 'b', b'c') + self.assertRaises(TypeError, pat.sub, b'b', b'c') + self.assertRaises(TypeError, bpat.sub, b'b', 'c') + self.assertRaises(TypeError, bpat.sub, 'b', b'c') + self.assertRaises(TypeError, bpat.sub, 'b', 'c') + + def test_unicode_flag(self): + # String patterns + for flags in (0, re.UNICODE): + pat = re.compile('\xc0', flags | re.IGNORECASE) + self.assertNotEqual(pat.match('\xe0'), None) + pat = re.compile('\w', flags) + self.assertNotEqual(pat.match('\xe0'), None) + pat = re.compile('\xc0', re.ASCII | re.IGNORECASE) + self.assertEqual(pat.match('\xe0'), None) + pat = re.compile('\w', re.ASCII) + self.assertEqual(pat.match('\xe0'), None) + # Bytes patterns + for flags in (0, re.ASCII): + pat = re.compile(b'\xc0', re.IGNORECASE) + self.assertEqual(pat.match(b'\xe0'), None) + pat = re.compile(b'\w') + self.assertEqual(pat.match(b'\xe0'), None) + # Incompatibilities + self.assertRaises(ValueError, re.compile, b'\w', re.UNICODE) + self.assertRaises(ValueError, re.compile, b'(?u)\w') + self.assertRaises(ValueError, re.compile, '\w', + re.UNICODE | re.ASCII) + self.assertRaises(ValueError, re.compile, '(?u)\w', re.ASCII) def run_re_tests(): @@ -732,23 +752,25 @@ def run_re_tests(): else: print('=== Failed incorrectly', t) - # Try the match on a unicode string, and check that it - # still succeeds. + # Try the match with both pattern and string converted to + # bytes, and check that it still succeeds. try: - result = obj.search(str(s, "latin-1")) - if result is None: - print('=== Fails on unicode match', t) - except NameError: - continue # 1.5.2 - except TypeError: - continue # unicode test case - - # Try the match on a unicode pattern, and check that it - # still succeeds. - obj=re.compile(str(pattern, "latin-1")) - result = obj.search(s) - if result is None: - print('=== Fails on unicode pattern match', t) + bpat = bytes(pattern, "ascii") + bs = bytes(s, "ascii") + except UnicodeEncodeError: + # skip non-ascii tests + pass + else: + try: + bpat = re.compile(bpat) + except Exception: + print('=== Fails on bytes pattern compile', t) + if verbose: + traceback.print_exc(file=sys.stdout) + else: + bytes_result = bpat.search(bs) + if bytes_result is None: + print('=== Fails on bytes pattern match', t) # Try the match with the search area limited to the extent # of the match and see if it still succeeds. \B will @@ -771,10 +793,11 @@ def run_re_tests(): # Try the match with LOCALE enabled, and check that it # still succeeds. - obj = re.compile(pattern, re.LOCALE) - result = obj.search(s) - if result is None: - print('=== Fails on locale-sensitive match', t) + if '(?u)' not in pattern: + obj = re.compile(pattern, re.LOCALE) + result = obj.search(s) + if result is None: + print('=== Fails on locale-sensitive match', t) # Try the match with UNICODE locale enabled, and check # that it still succeeds. diff -r 6a997c2b8eb6 Lib/tokenize.py --- a/Lib/tokenize.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/tokenize.py Sat Jul 05 23:02:45 2008 +0200 @@ -47,21 +47,23 @@ def any(*choices): return group(*choices def any(*choices): return group(*choices) + '*' def maybe(*choices): return group(*choices) + '?' +# Note: we use unicode matching for names ("\w") but ascii matching for +# number literals. Whitespace = r'[ \f\t]*' Comment = r'#[^\r\n]*' Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment) Name = r'[a-zA-Z_]\w*' -Hexnumber = r'0[xX][\da-fA-F]+' +Hexnumber = r'0[xX][0-9a-fA-F]+' Binnumber = r'0[bB][01]+' Octnumber = r'0[oO][0-7]+' -Decnumber = r'(?:0+|[1-9]\d*)' +Decnumber = r'(?:0+|[1-9][0-9]*)' Intnumber = group(Hexnumber, Binnumber, Octnumber, Decnumber) -Exponent = r'[eE][-+]?\d+' -Pointfloat = group(r'\d+\.\d*', r'\.\d+') + maybe(Exponent) -Expfloat = r'\d+' + Exponent +Exponent = r'[eE][-+]?[0-9]+' +Pointfloat = group(r'[0-9]+\.[0-9]*', r'\.[0-9]+') + maybe(Exponent) +Expfloat = r'[0-9]+' + Exponent Floatnumber = group(Pointfloat, Expfloat) -Imagnumber = group(r'\d+[jJ]', Floatnumber + r'[jJ]') +Imagnumber = group(r'[0-9]+[jJ]', Floatnumber + r'[jJ]') Number = group(Imagnumber, Floatnumber, Intnumber) # Tail end of ' string. diff -r 6a997c2b8eb6 Lib/urllib/request.py --- a/Lib/urllib/request.py Sat Jul 05 17:55:00 2008 +0200 +++ b/Lib/urllib/request.py Sat Jul 05 23:02:45 2008 +0200 @@ -141,7 +141,7 @@ def urlcleanup(): _opener = None # copied from cookielib.py -_cut_port_re = re.compile(r":\d+$") +_cut_port_re = re.compile(r":\d+$", re.ASCII) def request_host(request): """Return request-host, as defined by RFC 2965. diff -r 6a997c2b8eb6 Modules/_sre.c --- a/Modules/_sre.c Sat Jul 05 17:55:00 2008 +0200 +++ b/Modules/_sre.c Sat Jul 05 23:02:45 2008 +0200 @@ -1691,7 +1691,7 @@ getstring(PyObject* string, Py_ssize_t* /* get pointer to string buffer */ view.len = -1; buffer = Py_TYPE(string)->tp_as_buffer; - if (!buffer || !buffer->bf_getbuffer || + if (!buffer || !buffer->bf_getbuffer || (*buffer->bf_getbuffer)(string, &view, PyBUF_SIMPLE) < 0) { PyErr_SetString(PyExc_TypeError, "expected string or buffer"); return NULL; @@ -1717,7 +1717,7 @@ getstring(PyObject* string, Py_ssize_t* if (PyBytes_Check(string) || bytes == size) charsize = 1; #if defined(HAVE_UNICODE) - else if (bytes == (Py_ssize_t) (size * sizeof(Py_UNICODE))) + else if (bytes == (Py_ssize_t) (size * sizeof(Py_UNICODE))) charsize = sizeof(Py_UNICODE); #endif else { @@ -1729,7 +1729,7 @@ getstring(PyObject* string, Py_ssize_t* *p_charsize = charsize; if (ptr == NULL) { - PyErr_SetString(PyExc_ValueError, + PyErr_SetString(PyExc_ValueError, "Buffer is NULL"); } return ptr; @@ -1753,6 +1753,17 @@ state_init(SRE_STATE* state, PatternObje ptr = getstring(string, &length, &charsize); if (!ptr) return NULL; + + if (charsize == 1 && pattern->charsize > 1) { + PyErr_SetString(PyExc_TypeError, + "can't use a string pattern on a bytes-like object"); + return NULL; + } + if (charsize > 1 && pattern->charsize == 1) { + PyErr_SetString(PyExc_TypeError, + "can't use a bytes pattern on a string-like object"); + return NULL; + } /* adjust boundaries */ if (start < 0) @@ -2680,6 +2691,16 @@ _compile(PyObject* self_, PyObject* args return NULL; } + if (pattern == Py_None) + self->charsize = -1; + else { + Py_ssize_t p_length; + if (!getstring(pattern, &p_length, &self->charsize)) { + PyObject_DEL(self); + return NULL; + } + } + Py_INCREF(pattern); self->pattern = pattern; diff -r 6a997c2b8eb6 Modules/sre.h --- a/Modules/sre.h Sat Jul 05 17:55:00 2008 +0200 +++ b/Modules/sre.h Sat Jul 05 23:02:45 2008 +0200 @@ -30,6 +30,7 @@ typedef struct { PyObject* pattern; /* pattern source (or None) */ int flags; /* flags used when compiling pattern source */ PyObject *weakreflist; /* List of weak references */ + int charsize; /* pattern charsize (or -1) */ /* pattern code */ Py_ssize_t codesize; SRE_CODE code[1];