From fd036451bf0e0ade8783e21df801abf7be96d020 Mon Sep 17 00:00:00 2001 From: Antoine Pitrou Date: Tue, 19 Aug 2008 17:56:33 +0000 Subject: [PATCH] #2834: Change re module semantics, so that str and bytes mixing is forbidden, and str (unicode) patterns get full unicode matching by default. The re.ASCII flag is also introduced to ask for ASCII matching instead. --- Doc/library/re.rst | 127 ++++++++++++++++++------------ Lib/_strptime.py | 4 +- Lib/base64.py | 14 ++-- Lib/decimal.py | 2 +- Lib/distutils/cygwinccompiler.py | 6 +- Lib/distutils/emxccompiler.py | 2 +- Lib/distutils/sysconfig.py | 2 +- Lib/distutils/util.py | 2 +- Lib/distutils/version.py | 2 +- Lib/distutils/versionpredicate.py | 6 +- Lib/email/quoprimime.py | 12 +-- Lib/email/utils.py | 17 ++-- Lib/encodings/idna.py | 8 +- Lib/ftplib.py | 5 +- Lib/html/parser.py | 2 +- Lib/http/cookiejar.py | 22 +++--- Lib/http/cookies.py | 2 +- Lib/imaplib.py | 9 ++- Lib/json/decoder.py | 2 +- Lib/logging/handlers.py | 2 +- Lib/platform.py | 16 ++-- Lib/plistlib.py | 2 +- Lib/posixpath.py | 2 +- Lib/py_compile.py | 2 +- Lib/re.py | 31 ++++++-- Lib/sre_constants.py | 3 +- Lib/sre_parse.py | 14 ++++ Lib/tarfile.py | 2 +- Lib/test/re_tests.py | 2 +- Lib/test/test_bytes.py | 2 +- Lib/test/test_mmap.py | 2 +- Lib/test/test_re.py | 65 ++++++++++----- Lib/tokenize.py | 14 ++-- Lib/urllib/request.py | 2 +- Misc/NEWS | 8 ++ Modules/_sre.c | 27 ++++++- Modules/sre.h | 1 + 37 files changed, 280 insertions(+), 163 deletions(-) diff --git a/Doc/library/re.rst b/Doc/library/re.rst index a6ebc22eb12..f6f0d893163 100644 --- a/Doc/library/re.rst +++ b/Doc/library/re.rst @@ -11,9 +11,13 @@ This module provides regular expression matching operations similar to -those found in Perl. Both patterns and strings to be searched can be -Unicode strings as well as 8-bit strings. The :mod:`re` module is -always available. +those found in Perl. The :mod:`re` module is always available. + +Both patterns and strings to be searched can be Unicode strings as well as +8-bit strings. However, Unicode strings and 8-bit strings cannot be mixed: +that is, you cannot match an Unicode string with a byte pattern or +vice-versa; similarly, when asking for a substition, the replacement +string must be of the same type as both the pattern and the search string. Regular expressions use the backslash character (``'\'``) to indicate special forms or to allow special characters to be used without invoking @@ -212,12 +216,12 @@ The special characters are: group; ``(?P...)`` is the only exception to this rule. Following are the currently supported extensions. -``(?iLmsux)`` - (One or more letters from the set ``'i'``, ``'L'``, ``'m'``, ``'s'``, - ``'u'``, ``'x'``.) The group matches the empty string; the letters - set the corresponding flags: :const:`re.I` (ignore case), - :const:`re.L` (locale dependent), :const:`re.M` (multi-line), - :const:`re.S` (dot matches all), :const:`re.U` (Unicode dependent), +``(?aiLmsux)`` + (One or more letters from the set ``'a'``, ``'i'``, ``'L'``, ``'m'``, + ``'s'``, ``'u'``, ``'x'``.) The group matches the empty string; the + letters set the corresponding flags: :const:`re.a` (ASCII-only matching), + :const:`re.I` (ignore case), :const:`re.L` (locale dependent), + :const:`re.M` (multi-line), :const:`re.S` (dot matches all), and :const:`re.X` (verbose), for the entire regular expression. (The flags are described in :ref:`contents-of-module-re`.) This is useful if you wish to include the flags as part of the regular @@ -324,56 +328,62 @@ the second character. For example, ``\$`` matches the character ``'$'``. word is indicated by whitespace or a non-alphanumeric, non-underscore character. Note that ``\b`` is defined as the boundary between ``\w`` and ``\ W``, so the precise set of characters deemed to be alphanumeric depends on the values of the - ``UNICODE`` and ``LOCALE`` flags. Inside a character range, ``\b`` represents + ``ASCII`` and ``LOCALE`` flags. Inside a character range, ``\b`` represents the backspace character, for compatibility with Python's string literals. ``\B`` Matches the empty string, but only when it is *not* at the beginning or end of a word. This is just the opposite of ``\b``, so is also subject to the settings - of ``LOCALE`` and ``UNICODE``. + of ``ASCII`` and ``LOCALE`` . ``\d`` - When the :const:`UNICODE` flag is not specified, matches any decimal digit; this - is equivalent to the set ``[0-9]``. With :const:`UNICODE`, it will match - whatever is classified as a digit in the Unicode character properties database. + For Unicode (str) patterns: + When the :const:`ASCII` flag is specified, matches any decimal digit; this + is equivalent to the set ``[0-9]``. Otherwise, it will match whatever + is classified as a digit in the Unicode character properties database + (but this does include the standard ASCII digits and is thus a superset + of [0-9]). + For 8-bit (bytes) patterns: + Matches any decimal digit; this is equivalent to the set ``[0-9]``. ``\D`` - When the :const:`UNICODE` flag is not specified, matches any non-digit - character; this is equivalent to the set ``[^0-9]``. With :const:`UNICODE`, it - will match anything other than character marked as digits in the Unicode - character properties database. + Matches any character which is not a decimal digit. This is the + opposite of ``\d`` and is therefore similarly subject to the settings of + ``ASCII`` and ``LOCALE``. ``\s`` - When the :const:`LOCALE` and :const:`UNICODE` flags are not specified, matches - any whitespace character; this is equivalent to the set ``[ \t\n\r\f\v]``. With - :const:`LOCALE`, it will match this set plus whatever characters are defined as - space for the current locale. If :const:`UNICODE` is set, this will match the - characters ``[ \t\n\r\f\v]`` plus whatever is classified as space in the Unicode - character properties database. + For Unicode (str) patterns: + When the :const:`ASCII` flag is specified, matches only ASCII whitespace + characters; this is equivalent to the set ``[ \t\n\r\f\v]``. Otherwise, + it will match this set whatever is classified as space in the Unicode + character properties database (including for example the non-breaking + spaces mandated by typography rules in many languages). + For 8-bit (bytes) patterns: + Matches characters considered whitespace in the ASCII character set; + this is equivalent to the set ``[ \t\n\r\f\v]``. ``\S`` - When the :const:`LOCALE` and :const:`UNICODE` flags are not specified, matches - any non-whitespace character; this is equivalent to the set ``[^ \t\n\r\f\v]`` - With :const:`LOCALE`, it will match any character not in this set, and not - defined as space in the current locale. If :const:`UNICODE` is set, this will - match anything other than ``[ \t\n\r\f\v]`` and characters marked as space in - the Unicode character properties database. + Matches any character which is not a whitespace character. This is the + opposite of ``\s`` and is therefore similarly subject to the settings of + ``ASCII`` and ``LOCALE``. ``\w`` - When the :const:`LOCALE` and :const:`UNICODE` flags are not specified, matches - any alphanumeric character and the underscore; this is equivalent to the set - ``[a-zA-Z0-9_]``. With :const:`LOCALE`, it will match the set ``[0-9_]`` plus - whatever characters are defined as alphanumeric for the current locale. If - :const:`UNICODE` is set, this will match the characters ``[0-9_]`` plus whatever - is classified as alphanumeric in the Unicode character properties database. + For Unicode (str) patterns: + When the :const:`ASCII` flag is specified, this is equivalent to the set + ``[a-zA-Z0-9_]``. Otherwise, it will match whatever is classified as + alphanumeric in the Unicode character properties database (it will + include most characters that can be part of a word in whatever language, + as well as numbers and the underscore sign). + For 8-bit (bytes) patterns: + Matches characters considered alphanumeric in the ASCII character set; + this is equivalent to the set ``[a-zA-Z0-9_]``. With :const:`LOCALE`, + it will additionally match whatever characters are defined as + alphanumeric for the current locale. ``\W`` - When the :const:`LOCALE` and :const:`UNICODE` flags are not specified, matches - any non-alphanumeric character; this is equivalent to the set ``[^a-zA-Z0-9_]``. - With :const:`LOCALE`, it will match any character not in the set ``[0-9_]``, and - not defined as alphanumeric for the current locale. If :const:`UNICODE` is set, - this will match anything other than ``[0-9_]`` and characters marked as - alphanumeric in the Unicode character properties database. + Matches any character which is not an alphanumeric character. This is the + opposite of ``\w`` and is therefore similarly subject to the settings of + ``ASCII`` and ``LOCALE``. ``\Z`` Matches only at the end of the string. @@ -454,6 +464,25 @@ form. expression at a time needn't worry about compiling regular expressions.) +.. data:: A + ASCII + + Make ``\w``, ``\W``, ``\b``, ``\B``, ``\s`` and ``\S`` perform ASCII-only + matching instead of full Unicode matching. This is only meaningful for + Unicode patterns, and is ignored for byte patterns. + + Note that the :const:`re.U` flag still exists (as well as its synonym + :const:`re.UNICODE` and its embedded counterpart ``(?u)``), but it has + become useless in Python 3.0. + In previous Python versions, it was used to specify that + matching had to be Unicode dependent (the default was ASCII matching in + all circumstances). Starting from Python 3.0, the default is Unicode + matching for Unicode strings (which can be changed by specifying the + ``'a'`` flag), and ASCII matching for 8-bit strings. Further, Unicode + dependent matching for 8-bit strings isn't allowed anymore and results + in a ValueError. + + .. data:: I IGNORECASE @@ -465,7 +494,10 @@ form. LOCALE Make ``\w``, ``\W``, ``\b``, ``\B``, ``\s`` and ``\S`` dependent on the - current locale. + current locale. The use of this flag is discouraged as the locale mechanism + is very unreliable, and it only handles one "culture" at a time anyway; + you should use Unicode matching instead, which is the default in Python 3.0 + for Unicode (str) patterns. .. data:: M @@ -486,13 +518,6 @@ form. newline; without this flag, ``'.'`` will match anything *except* a newline. -.. data:: U - UNICODE - - Make ``\w``, ``\W``, ``\b``, ``\B``, ``\d``, ``\D``, ``\s`` and ``\S`` dependent - on the Unicode character properties database. - - .. data:: X VERBOSE @@ -511,6 +536,8 @@ form. b = re.compile(r"\d+\.\d*") + + .. function:: search(pattern, string[, flags]) Scan through *string* looking for a location where the regular expression diff --git a/Lib/_strptime.py b/Lib/_strptime.py index c3568b0d1d4..896c7986c4e 100644 --- a/Lib/_strptime.py +++ b/Lib/_strptime.py @@ -14,7 +14,7 @@ import time 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 --git a/Lib/base64.py b/Lib/base64.py index fc80835add0..4308fb489db 100755 --- a/Lib/base64.py +++ b/Lib/base64.py @@ -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=None): # 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=None): 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 --git a/Lib/decimal.py b/Lib/decimal.py index 2c02f112134..88cc5cd5ccd 100644 --- a/Lib/decimal.py +++ b/Lib/decimal.py @@ -5415,7 +5415,7 @@ 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 --git a/Lib/distutils/cygwinccompiler.py b/Lib/distutils/cygwinccompiler.py index 488752300b9..da2c74a2b1a 100644 --- a/Lib/distutils/cygwinccompiler.py +++ b/Lib/distutils/cygwinccompiler.py @@ -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 --git a/Lib/distutils/emxccompiler.py b/Lib/distutils/emxccompiler.py index d9ee82d58a0..62a4c5b4e8a 100644 --- a/Lib/distutils/emxccompiler.py +++ b/Lib/distutils/emxccompiler.py @@ -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 --git a/Lib/distutils/sysconfig.py b/Lib/distutils/sysconfig.py index 3a120dd5845..b17743a8651 100644 --- a/Lib/distutils/sysconfig.py +++ b/Lib/distutils/sysconfig.py @@ -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 --git a/Lib/distutils/util.py b/Lib/distutils/util.py index 76798b95062..b87dfbe0658 100644 --- a/Lib/distutils/util.py +++ b/Lib/distutils/util.py @@ -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 --git a/Lib/distutils/version.py b/Lib/distutils/version.py index f71b2f6ce38..907f71c3135 100644 --- a/Lib/distutils/version.py +++ b/Lib/distutils/version.py @@ -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 --git a/Lib/distutils/versionpredicate.py b/Lib/distutils/versionpredicate.py index 434b34f184e..b0dd9f45bff 100644 --- a/Lib/distutils/versionpredicate.py +++ b/Lib/distutils/versionpredicate.py @@ -5,7 +5,8 @@ import distutils.version 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*\(\s*([^)\s]+)\s*\))?$", + re.ASCII) value = value.strip() m = _provision_rx.match(value) if not m: diff --git a/Lib/email/quoprimime.py b/Lib/email/quoprimime.py index 68dc11c695e..ca916316958 100644 --- a/Lib/email/quoprimime.py +++ b/Lib/email/quoprimime.py @@ -70,7 +70,7 @@ for c in (b' !"#$%&\'()*+,-./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='iso-8859-1'): 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=NL): 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 @@ body_decode = 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 --git a/Lib/email/utils.py b/Lib/email/utils.py index 35275f6a42b..465903f88d3 100644 --- a/Lib/email/utils.py +++ b/Lib/email/utils.py @@ -52,7 +52,7 @@ specialsre = 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=False, usegmt=False): 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, language=None): 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 --git a/Lib/encodings/idna.py b/Lib/encodings/idna.py index c2ba1da3db8..583bdf130a5 100644 --- a/Lib/encodings/idna.py +++ b/Lib/encodings/idna.py @@ -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 --git a/Lib/ftplib.py b/Lib/ftplib.py index 49557271477..b64e45ec4b8 100644 --- a/Lib/ftplib.py +++ b/Lib/ftplib.py @@ -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 --git a/Lib/html/parser.py b/Lib/html/parser.py index 828eece4efb..83a58258c7a 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -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 --git a/Lib/http/cookiejar.py b/Lib/http/cookiejar.py index afd5f20d195..e9efab88df7 100644 --- a/Lib/http/cookiejar.py +++ b/Lib/http/cookiejar.py @@ -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, tz): 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 --git a/Lib/http/cookies.py b/Lib/http/cookies.py index 344bedeccdc..3242d8374ad 100644 --- a/Lib/http/cookies.py +++ b/Lib/http/cookies.py @@ -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 --git a/Lib/imaplib.py b/Lib/imaplib.py index 0d9704e9d72..156b15db3d1 100644 --- a/Lib/imaplib.py +++ b/Lib/imaplib.py @@ -88,11 +88,12 @@ InternalDate = re.compile(r'.*INTERNALDATE "' 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 --git a/Lib/json/decoder.py b/Lib/json/decoder.py index 5283eaeccfc..f0bc245645f 100644 --- a/Lib/json/decoder.py +++ b/Lib/json/decoder.py @@ -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 --git a/Lib/logging/handlers.py b/Lib/logging/handlers.py index 1e69120b8f4..19fb959fb26 100644 --- a/Lib/logging/handlers.py +++ b/Lib/logging/handlers.py @@ -199,7 +199,7 @@ class TimedRotatingFileHandler(BaseRotatingHandler): 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 --git a/Lib/platform.py b/Lib/platform.py index ff81d281965..01821803535 100755 --- a/Lib/platform.py +++ b/Lib/platform.py @@ -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 @@ def processor(): _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 --git a/Lib/plistlib.py b/Lib/plistlib.py index b7753246a5b..83e5d04a034 100644 --- a/Lib/plistlib.py +++ b/Lib/plistlib.py @@ -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 --git a/Lib/posixpath.py b/Lib/posixpath.py index dc0aa108f0f..575492f92b3 100644 --- a/Lib/posixpath.py +++ b/Lib/posixpath.py @@ -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 --git a/Lib/py_compile.py b/Lib/py_compile.py index 8ef36627074..cce5ac145ac 100644 --- a/Lib/py_compile.py +++ b/Lib/py_compile.py @@ -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 --git a/Lib/re.py b/Lib/re.py index 951f239c9f0..63a95fd7e01 100644 --- a/Lib/re.py +++ b/Lib/re.py @@ -44,7 +44,7 @@ The special characters are: "|" A|B, creates an RE that will match either A or B. (...) Matches the RE inside the parentheses. The contents can be retrieved or matched later in the string. - (?iLmsux) Set the I, L, M, S, U, or X flag for the RE (see below). + (?aiLmsux) Set the A, I, L, M, S, U, or X flag for the RE (see below). (?:...) Non-grouping version of regular parentheses. (?P...) The substring matched by the group is accessible by name. (?P=name) Matches the text matched earlier by the group named name. @@ -64,11 +64,18 @@ resulting RE will match the second character. \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 functions: 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 takes flags as optional parameters: 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 --git a/Lib/sre_constants.py b/Lib/sre_constants.py index 94962cbc39b..6cf69c321b8 100644 --- a/Lib/sre_constants.py +++ b/Lib/sre_constants.py @@ -207,9 +207,10 @@ SRE_FLAG_IGNORECASE = 2 # case insensitive 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 --git a/Lib/sre_parse.py b/Lib/sre_parse.py index ffa8902b7b4..9d6e631ef1f 100644 --- a/Lib/sre_parse.py +++ b/Lib/sre_parse.py @@ -64,6 +64,7 @@ FLAGS = { "s": SRE_FLAG_DOTALL, "x": SRE_FLAG_VERBOSE, # extensions + "a": SRE_FLAG_ASCII, "t": SRE_FLAG_TEMPLATE, "u": SRE_FLAG_UNICODE, } @@ -672,6 +673,18 @@ 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 +696,7 @@ 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 --git a/Lib/tarfile.py b/Lib/tarfile.py index ecb32f6d031..222b4337198 100644 --- a/Lib/tarfile.py +++ b/Lib/tarfile.py @@ -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 --git a/Lib/test/re_tests.py b/Lib/test/re_tests.py index 220301ad294..d314e200bbc 100755 --- a/Lib/test/re_tests.py +++ b/Lib/test/re_tests.py @@ -667,4 +667,4 @@ tests.extend([ (r'\b.\b', 'a', SUCCEED, 'found', 'a'), (r'(?u)\b.\b', u, SUCCEED, 'found', u), (r'(?u)\w', u, SUCCEED, 'found', u), - ]) +]) diff --git a/Lib/test/test_bytes.py b/Lib/test/test_bytes.py index c64ac192e5d..630f862a151 100644 --- a/Lib/test/test_bytes.py +++ b/Lib/test/test_bytes.py @@ -506,7 +506,7 @@ class ByteArrayTest(BaseBytesTest): def by(s): return bytearray(map(ord, s)) b = by("Hello, world") - self.assertEqual(re.findall(r"\w+", b), [by("Hello"), by("world")]) + self.assertEqual(re.findall(br"\w+", b), [by("Hello"), by("world")]) def test_setitem(self): b = bytearray([1, 2, 3]) diff --git a/Lib/test/test_mmap.py b/Lib/test/test_mmap.py index 0b5202a4a34..9fe044fac85 100644 --- a/Lib/test/test_mmap.py +++ b/Lib/test/test_mmap.py @@ -54,7 +54,7 @@ class MmapTests(unittest.TestCase): m.flush() # Test doing a regular expression match in an mmap'ed file - match = re.search('[A-Za-z]+', m) + match = re.search(b'[A-Za-z]+', m) if match is None: self.fail('regex match on mmap failed!') else: diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py index 60b816ee2ca..755cb00ae45 100644 --- a/Lib/test/test_re.py +++ b/Lib/test/test_re.py @@ -83,23 +83,6 @@ class ReTests(unittest.TestCase): self.assertEqual(re.sub('\r\n', '\n', 'abc\r\ndef\r\n'), 'abc\ndef\n') - def test_bug_1140(self): - # re.sub(x, y, b'') should return b'', not '', and - # re.sub(x, y, '') should return '', not b''. - # Also: - # re.sub(x, y, str(x)) should return str(y), and - # re.sub(x, y, bytes(x)) should return - # str(y) if isinstance(y, str) else unicode(y). - for x in 'x', b'x': - for y in 'y', b'y': - z = re.sub(x, y, b'') - self.assertEqual(z, b'') - self.assertEqual(type(z), bytes) - # - z = re.sub(x, y, '') - self.assertEqual(z, '') - self.assertEqual(type(z), str) - def test_bug_1661(self): # Verify that flags do not get silently ignored with compiled patterns pattern = re.compile('.') @@ -327,7 +310,7 @@ class ReTests(unittest.TestCase): def test_getattr(self): self.assertEqual(re.compile("(?i)(a)(b)").pattern, "(?i)(a)(b)") - self.assertEqual(re.compile("(?i)(a)(b)").flags, re.I) + self.assertEqual(re.compile("(?i)(a)(b)").flags, re.I | re.U) self.assertEqual(re.compile("(?i)(a)(b)").groups, 2) self.assertEqual(re.compile("(?i)(a)(b)").groupindex, {}) self.assertEqual(re.compile("(?i)(?Pa)(?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 @@ -658,6 +641,48 @@ class ReTests(unittest.TestCase): 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_ascii_and_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('(?a)\xc0', re.IGNORECASE) + self.assertEqual(pat.match('\xe0'), None) + pat = re.compile('\w', re.ASCII) + self.assertEqual(pat.match('\xe0'), None) + pat = re.compile('(?a)\w') + 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) + self.assertRaises(ValueError, re.compile, '(?a)\w', re.UNICODE) + self.assertRaises(ValueError, re.compile, '(?au)\w') + def run_re_tests(): from test.re_tests import benchmarks, tests, SUCCEED, FAIL, SYNTAX_ERROR diff --git a/Lib/tokenize.py b/Lib/tokenize.py index 31366deb1f5..ec5a79a6453 100644 --- a/Lib/tokenize.py +++ b/Lib/tokenize.py @@ -47,21 +47,23 @@ def group(*choices): return '(' + '|'.join(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 --git a/Lib/urllib/request.py b/Lib/urllib/request.py index 889d9642092..aaab059300b 100644 --- a/Lib/urllib/request.py +++ b/Lib/urllib/request.py @@ -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 --git a/Misc/NEWS b/Misc/NEWS index 38237722025..e8fa5f5ac50 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -30,6 +30,14 @@ Core and Builtins Library ------- +- Issue #2834: update the regular expression library to match the unicode + standards of py3k. In other words, mixing bytes and unicode strings + (be it as pattern, search string or replacement string) raises a TypeError. + Moreover, the re.UNICODE flag is enabled automatically for unicode patterns, + and can be disabled by specifying a new re.ASCII flag; as for bytes + patterns, ASCII matching is the only option and trying to specify re.UNICODE + for such patterns raises a ValueError. + - Issue #3300: make urllib.parse.[un]quote() default to UTF-8. Code contributed by Matt Giuca. quote() now encodes the input before quoting, unquote() decodes after unquoting. There are diff --git a/Modules/_sre.c b/Modules/_sre.c index 64fc5132c82..2a54d8e603f 100644 --- a/Modules/_sre.c +++ b/Modules/_sre.c @@ -1691,7 +1691,7 @@ getstring(PyObject* string, Py_ssize_t* p_length, int* p_charsize) /* 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* p_length, int* p_charsize) 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_length, int* p_charsize) *p_charsize = charsize; if (ptr == NULL) { - PyErr_SetString(PyExc_ValueError, + PyErr_SetString(PyExc_ValueError, "Buffer is NULL"); } return ptr; @@ -1754,6 +1754,17 @@ state_init(SRE_STATE* state, PatternObject* pattern, PyObject* string, 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) start = 0; @@ -2682,6 +2693,16 @@ _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 --git a/Modules/sre.h b/Modules/sre.h index d4af05c045e..518c11db309 100644 --- a/Modules/sre.h +++ b/Modules/sre.h @@ -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];