Python sre_constants.error方法代码示例

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def test_sre_character_class_literals(self):
        for i in [0, 8, 16, 32, 64, 127, 128, 255, 256, 0xFFFF, 0x10000, 0x10FFFF]:
            if i < 256:
                self.assertIsNotNone(re.match(r"[\%o]" % i, chr(i)))
                self.assertIsNotNone(re.match(r"[\%o8]" % i, chr(i)))
                self.assertIsNotNone(re.match(r"[\%03o]" % i, chr(i)))
                self.assertIsNotNone(re.match(r"[\%03o0]" % i, chr(i)))
                self.assertIsNotNone(re.match(r"[\%03o8]" % i, chr(i)))
                self.assertIsNotNone(re.match(r"[\x%02x]" % i, chr(i)))
                self.assertIsNotNone(re.match(r"[\x%02x0]" % i, chr(i)))
                self.assertIsNotNone(re.match(r"[\x%02xz]" % i, chr(i)))
            if i < 0x10000:
                self.assertIsNotNone(re.match(r"[\u%04x]" % i, chr(i)))
                self.assertIsNotNone(re.match(r"[\u%04x0]" % i, chr(i)))
                self.assertIsNotNone(re.match(r"[\u%04xz]" % i, chr(i)))
            self.assertIsNotNone(re.match(r"[\U%08x]" % i, chr(i)))
            self.assertIsNotNone(re.match(r"[\U%08x0]" % i, chr(i)+"0"))
            self.assertIsNotNone(re.match(r"[\U%08xz]" % i, chr(i)+"z"))
        self.assertIsNotNone(re.match(r"[\U0001d49c-\U0001d4b5]", "\U0001d49e"))
        self.assertRaises(re.error, re.match, r"[\911]", "")
        self.assertRaises(re.error, re.match, r"[\x1z]", "")
        self.assertRaises(re.error, re.match, r"[\u123z]", "")
        self.assertRaises(re.error, re.match, r"[\U0001234z]", "")
        self.assertRaises(re.error, re.match, r"[\U00110000]", "") 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def test_symbolic_groups(self):
        re.compile('(?P<a>x)(?P=a)(?(a)y)')
        re.compile('(?P<a1>x)(?P=a1)(?(a1)y)')
        self.assertRaises(re.error, re.compile, '(?P<a>)(?P<a>)')
        self.assertRaises(re.error, re.compile, '(?Px)')
        self.assertRaises(re.error, re.compile, '(?P=)')
        self.assertRaises(re.error, re.compile, '(?P=1)')
        self.assertRaises(re.error, re.compile, '(?P=a)')
        self.assertRaises(re.error, re.compile, '(?P=a1)')
        self.assertRaises(re.error, re.compile, '(?P=a.)')
        self.assertRaises(re.error, re.compile, '(?P<)')
        self.assertRaises(re.error, re.compile, '(?P<>)')
        self.assertRaises(re.error, re.compile, '(?P<1>)')
        self.assertRaises(re.error, re.compile, '(?P<a.>)')
        self.assertRaises(re.error, re.compile, '(?())')
        self.assertRaises(re.error, re.compile, '(?(a))')
        self.assertRaises(re.error, re.compile, '(?(1a))')
        self.assertRaises(re.error, re.compile, '(?(a.))') 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def test_other_escapes(self):
        self.assertRaises(re.error, re.compile, "\\")
        self.assertEqual(re.match(r"\(", '(').group(), '(')
        self.assertIsNone(re.match(r"\(", ')'))
        self.assertEqual(re.match(r"\\", '\\').group(), '\\')
        self.assertEqual(re.match(r"[\]]", ']').group(), ']')
        self.assertIsNone(re.match(r"[\]]", '['))
        self.assertEqual(re.match(r"[a\-c]", '-').group(), '-')
        self.assertIsNone(re.match(r"[a\-c]", 'b'))
        self.assertEqual(re.match(r"[\^a]+", 'a^').group(), 'a^')
        self.assertIsNone(re.match(r"[\^a]+", 'b'))
        re.purge()  # for warnings
        for c in 'ceghijklmopquyzCEFGHIJKLMNOPQRTUVXY':
            warn = FutureWarning if c in 'Uu' else DeprecationWarning
            with check_py3k_warnings(('', warn)):
                self.assertEqual(re.match('\\%c$' % c, c).group(), c)
                self.assertIsNone(re.match('\\%c' % c, 'a'))
        for c in 'ceghijklmopquyzABCEFGHIJKLMNOPQRTUVXYZ':
            warn = FutureWarning if c in 'Uu' else DeprecationWarning
            with check_py3k_warnings(('', warn)):
                self.assertEqual(re.match('[\\%c]$' % c, c).group(), c)
                self.assertIsNone(re.match('[\\%c]' % c, 'a')) 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def rm(self, target):

        try:
            # 1st try to delete it as a file
            self.eval("uos.remove('%s')" % (self._fqn(target)))
        except PyboardError:
            try:
                # 2nd see if it is empty dir
                self.eval("uos.rmdir('%s')" % (self._fqn(target)))
            except PyboardError as e:
                # 3rd report error if nor successful
                if _was_file_not_existing(e):
                    if self.sysname == "WiPy":
                        raise RemoteIOError(
                            "No such file or directory or directory not empty: %s"
                            % target
                        )
                    else:
                        raise RemoteIOError("No such file or directory: %s" % target)
                elif "EACCES" in str(e):
                    raise RemoteIOError("Directory not empty: %s" % target)
                else:
                    raise e 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def mput(self, src_dir, pat, verbose=False):

        try:

            find = re.compile(pat)
            files = os.listdir(src_dir)

            for f in files:
                if os.path.isfile(f) and find.match(f):
                    if verbose:
                        print(" * put %s" % f)

                    self.put(posixpath.join(src_dir, f), f)

        except sre_constants.error as e:
            raise RemoteIOError("Error in regular expression: %s" % e) 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def mget(self, dst_dir, pat, verbose=False):

        try:

            files = self.ls(add_dirs=False)
            find = re.compile(pat)

            for f in files:
                if find.match(f):
                    if verbose:
                        print(" * get %s" % f)

                    self.get(f, dst=posixpath.join(dst_dir, f))

        except sre_constants.error as e:
            raise RemoteIOError("Error in regular expression: %s" % e) 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def match_examples(self, parse_fn, examples):
        """ Given a parser instance and a dictionary mapping some label with
            some malformed syntax examples, it'll return the label for the
            example that bests matches the current error.
        """
        assert self.state is not None, "Not supported for this exception"

        candidate = None
        for label, example in examples.items():
            assert not isinstance(example, STRING_TYPE)

            for malformed in example:
                try:
                    parse_fn(malformed)
                except UnexpectedInput as ut:
                    if ut.state == self.state:
                        try:
                            if ut.token == self.token:  # Try exact match first
                                return label
                        except AttributeError:
                            pass
                        if not candidate:
                            candidate = label

        return candidate 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def __init__(self, terminals, ignore=(), user_callbacks={}):
        assert all(isinstance(t, TerminalDef) for t in terminals), terminals

        terminals = list(terminals)

        # Sanitization
        for t in terminals:
            try:
                re.compile(t.pattern.to_regexp())
            except re.error:
                raise LexError("Cannot compile token %s: %s" % (t.name, t.pattern))

            if t.pattern.min_width == 0:
                raise LexError("Lexer does not allow zero-width terminals. (%s: %s)" % (t.name, t.pattern))

        assert set(ignore) <= {t.name for t in terminals}

        # Init
        self.newline_types = [t.name for t in terminals if _regexp_has_newline(t.pattern.to_regexp())]
        self.ignore_types = list(ignore)

        terminals.sort(key=lambda x:(-x.priority, -x.pattern.max_width, -len(x.pattern.value), x.name))
        self.terminals = terminals
        self.user_callbacks = user_callbacks
        self.build() 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def lex(self, stream, get_parser_state):
        parser_state = get_parser_state()
        l = _Lex(self.lexers[parser_state], parser_state)
        try:
            for x in l.lex(stream, self.root_lexer.newline_types, self.root_lexer.ignore_types):
                yield x
                parser_state = get_parser_state()
                l.lexer = self.lexers[parser_state]
                l.state = parser_state # For debug only, no need to worry about multithreading
        except UnexpectedCharacters as e:
            # In the contextual lexer, UnexpectedCharacters can mean that the terminal is defined,
            # but not in the current context.
            # This tests the input against the global context, to provide a nicer error.
            root_match = self.root_lexer.match(stream, e.pos_in_stream)
            if not root_match:
                raise

            value, type_ = root_match
            t = Token(type_, value, e.pos_in_stream, e.line, e.column)
            raise UnexpectedToken(t, e.allowed, state=e.state) 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def get_regexp_width(expr):
    if regex:
        # Since `sre_parse` cannot deal with Unicode categories of the form `\p{Mn}`, we replace these with
        # a simple letter, which makes no difference as we are only trying to get the possible lengths of the regex
        # match here below.
        regexp_final = re.sub(categ_pattern, 'A', expr)
    else:
        if re.search(categ_pattern, expr):
            raise ImportError('`regex` module must be installed in order to use Unicode categories.', expr)
        regexp_final = expr
    try:
        return [int(x) for x in sre_parse.parse(regexp_final).getwidth()]
    except sre_constants.error:
        raise ValueError(expr)

###} 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def read_clues_from_file(filename):
        logging.info("Reading clues file %s", filename)
        try:
            json_data = open(filename)
        except IOError as e:
            logging.error("Error while opening clues file, terminating: %s", tools.error_to_str(e))
            raise

        try:
            if six.PY2:
                clues = json.load(json_data, encoding='utf-8')
            else:
                clues = json.load(json_data)
        except ValueError as e:
            logging.error("Error while reading JSON file, terminating: %s", tools.error_to_str(e))
            raise

        json_data.close()
        categories = dict((k, v['name']) for k, v in six.iteritems(clues['categories']))
        apps = clues['apps']
        return apps, categories 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def compile_clues(self):
        # compiling regular expressions
        for app in self.apps:
            regexps = {}
            for key in list(self.apps[app]):
                if key in ['script', 'html', 'url']:
                    try:
                        regexps[key + "_re"] = list(six.moves.map(self.compile_clue, self.apps[app][key]))
                    except sre_constants.error:
                        del self.apps[app][key]
                if key in ['meta', 'headers', 'js', 'cookies']:
                    try:
                        regexps[key + "_re"] = dict((entry, self.compile_clue(self.apps[app][key][entry]))
                                                    for entry in self.apps[app][key])
                    except sre_constants.error:
                        del self.apps[app][key]
            self.apps[app].update(regexps) 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def regex_validator(args, state):
    with open(args.checks, "r") as fd:
        for line in fd.read().splitlines():
            if line.startswith("#") or len(line) == 0:
                continue
            try:
                re.subn(line, r'\1', "Expression test")
            except sre_constants.error as e:
                print(bcolors.FAIL + "Invalid Regular expression:\n\t" + line)
                if "group" in str(e):
                    print(
                        "Ensure expression contains"
                        "a capture group for matches:\n\t" + str(e))
                sys.exit(-1)
            state.checks.append(line)

    split = []
    if not (state.query[0] == "\"" and state.query[-1] == "\""):
        split = re.split(GITHUB_WHITESPACE, state.query)

    for part in [state.query] + split:
        if part:
            escaped_query = re.escape(part) if split else \
                part.replace("\"", "")
            state.checks.append("(?i)(" + escaped_query + ")")
    return state 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def test_sub_template_numeric_escape(self):
        # bug 776311 and friends
        self.assertEqual(re.sub('x', r'\0', 'x'), '\0')
        self.assertEqual(re.sub('x', r'\000', 'x'), '\000')
        self.assertEqual(re.sub('x', r'\001', 'x'), '\001')
        self.assertEqual(re.sub('x', r'\008', 'x'), '\0' + '8')
        self.assertEqual(re.sub('x', r'\009', 'x'), '\0' + '9')
        self.assertEqual(re.sub('x', r'\111', 'x'), '\111')
        self.assertEqual(re.sub('x', r'\117', 'x'), '\117')

        self.assertEqual(re.sub('x', r'\1111', 'x'), '\1111')
        self.assertEqual(re.sub('x', r'\1111', 'x'), '\111' + '1')

        self.assertEqual(re.sub('x', r'\00', 'x'), '\x00')
        self.assertEqual(re.sub('x', r'\07', 'x'), '\x07')
        self.assertEqual(re.sub('x', r'\08', 'x'), '\0' + '8')
        self.assertEqual(re.sub('x', r'\09', 'x'), '\0' + '9')
        self.assertEqual(re.sub('x', r'\0a', 'x'), '\0' + 'a')

        self.assertEqual(re.sub('x', r'\400', 'x'), '\0')
        self.assertEqual(re.sub('x', r'\777', 'x'), '\377')

        self.assertRaises(re.error, re.sub, 'x', r'\1', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\8', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\9', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\11', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\18', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\1a', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\90', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\99', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\118', 'x') # r'\11' + '8'
        self.assertRaises(re.error, re.sub, 'x', r'\11a', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\181', 'x') # r'\18' + '1'
        self.assertRaises(re.error, re.sub, 'x', r'\800', 'x') # r'\80' + '0'

        # in python2.3 (etc), these loop endlessly in sre_parser.py
        self.assertEqual(re.sub('(((((((((((x)))))))))))', r'\11', 'x'), 'x')
        self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\118', 'xyz'),
                         'xz8')
        self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\11a', 'xyz'),
                         'xza') 

# 需要导入模块: import sre_constants [as 别名]
# 或者: from sre_constants import error [as 别名]
def test_sre_character_literals(self):
        for i in [0, 8, 16, 32, 64, 127, 128, 255, 256, 0xFFFF, 0x10000, 0x10FFFF]:
            if i < 256:
                self.assertIsNotNone(re.match(r"\%03o" % i, chr(i)))
                self.assertIsNotNone(re.match(r"\%03o0" % i, chr(i)+"0"))
                self.assertIsNotNone(re.match(r"\%03o8" % i, chr(i)+"8"))
                self.assertIsNotNone(re.match(r"\x%02x" % i, chr(i)))
                self.assertIsNotNone(re.match(r"\x%02x0" % i, chr(i)+"0"))
                self.assertIsNotNone(re.match(r"\x%02xz" % i, chr(i)+"z"))
            if i < 0x10000:
                self.assertIsNotNone(re.match(r"\u%04x" % i, chr(i)))
                self.assertIsNotNone(re.match(r"\u%04x0" % i, chr(i)+"0"))
                self.assertIsNotNone(re.match(r"\u%04xz" % i, chr(i)+"z"))
            self.assertIsNotNone(re.match(r"\U%08x" % i, chr(i)))
            self.assertIsNotNone(re.match(r"\U%08x0" % i, chr(i)+"0"))
            self.assertIsNotNone(re.match(r"\U%08xz" % i, chr(i)+"z"))
        self.assertIsNotNone(re.match(r"\0", "\000"))
        self.assertIsNotNone(re.match(r"\08", "\0008"))
        self.assertIsNotNone(re.match(r"\01", "\001"))
        self.assertIsNotNone(re.match(r"\018", "\0018"))
        self.assertIsNotNone(re.match(r"\567", chr(0o167)))
        self.assertRaises(re.error, re.match, r"\911", "")
        self.assertRaises(re.error, re.match, r"\x1", "")
        self.assertRaises(re.error, re.match, r"\x1z", "")
        self.assertRaises(re.error, re.match, r"\u123", "")
        self.assertRaises(re.error, re.match, r"\u123z", "")
        self.assertRaises(re.error, re.match, r"\U0001234", "")
        self.assertRaises(re.error, re.match, r"\U0001234z", "")
        self.assertRaises(re.error, re.match, r"\U00110000", "")