Python re.X Examples

The following are 30 code examples of re.X(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module re , or try the search function .
Example #1
Source File: tools.py    From hadrian with Apache License 2.0 6 votes vote down vote up
def getmatch(self, haystack):
        if not isinstance(haystack, basestring):
            return None
        flags = 0
        if self.flags is not None:
            if "i" in self.flags or "I" in self.flags:
                flags |= re.I
            if "l" in self.flags or "L" in self.flags:
                flags |= re.L
            if "m" in self.flags or "M" in self.flags:
                flags |= re.M
            if "s" in self.flags or "S" in self.flags:
                flags |= re.S
            if "u" in self.flags or "U" in self.flags:
                flags |= re.U
            if "x" in self.flags or "X" in self.flags:
                flags |= re.X
        if re.match(self.pattern, haystack, flags=flags) is None:
            return None
        elif self.to is None:
            return Match(haystack, haystack)
        else:
            return Match(haystack, re.sub(self.pattern, self.to, haystack, flags=flags)) 
Example #2
Source File: utils.py    From schemathesis with MIT License 6 votes vote down vote up
def make_loader(*tags_to_remove: str) -> Type[yaml.SafeLoader]:
    """Create a YAML loader, that doesn't parse specific tokens into Python objects."""
    cls: Type[yaml.SafeLoader] = type("YAMLLoader", (SafeLoader,), {})
    cls.yaml_implicit_resolvers = {
        key: [(tag, regexp) for tag, regexp in mapping if tag not in tags_to_remove]
        for key, mapping in cls.yaml_implicit_resolvers.copy().items()
    }

    # Fix pyyaml scientific notation parse bug
    # See PR: https://github.com/yaml/pyyaml/pull/174 for upstream fix
    cls.add_implicit_resolver(  # type: ignore
        "tag:yaml.org,2002:float",
        re.compile(
            r"""^(?:[-+]?(?:[0-9][0-9_]*)\.[0-9_]*(?:[eE][-+]?[0-9]+)?
                       |[-+]?(?:[0-9][0-9_]*)(?:[eE][-+]?[0-9]+)
                       |\.[0-9_]+(?:[eE][-+]?[0-9]+)?
                       |[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\.[0-9_]*
                       |[-+]?\.(?:inf|Inf|INF)
                       |\.(?:nan|NaN|NAN))$""",
            re.X,
        ),
        list("-+0123456789."),
    )

    return cls 
Example #3
Source File: lexer.py    From jbox with MIT License 6 votes vote down vote up
def match_text(self):
        match = self.match(r"""
                (.*?)         # anything, followed by:
                (
                 (?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
                                             # comment preceded by a
                                             # consumed newline and whitespace
                 |
                 (?=\${)      # an expression
                 |
                 (?=</?[%&])  # a substitution or block or call start or end
                              # - don't consume
                 |
                 (\\\r?\n)    # an escaped newline  - throw away
                 |
                 \Z           # end of string
                )""", re.X | re.S)

        if match:
            text = match.group(1)
            if text:
                self.append_node(parsetree.Text, text)
            return True
        else:
            return False 
Example #4
Source File: config.py    From Pixel2MeshPlusPlus with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up
def parse_args(parser):
    args = parser.parse_args()
    if args.config_file:
        loader = yaml.SafeLoader
        loader.add_implicit_resolver(
            u'tag:yaml.org,2002:float',
            re.compile(u'''^(?:
        [-+]?(?:[0-9][0-9_]*)\\.[0-9_]*(?:[eE][-+]?[0-9]+)?
        |[-+]?(?:[0-9][0-9_]*)(?:[eE][-+]?[0-9]+)
        |\\.[0-9_]+(?:[eE][-+][0-9]+)?
        |[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\\.[0-9_]*
        |[-+]?\\.(?:inf|Inf|INF)
        |\\.(?:nan|NaN|NAN))$''', re.X),
            list(u'-+0123456789.'))
        data = yaml.load(args.config_file, Loader=loader)
        delattr(args, 'config_file')
        arg_dict = args.__dict__
        # print(len(list(arg_dict.keys())))
        # print(len(list(data.keys())))
        for key, value in arg_dict.items():
            default_arg = parser.get_default(key)
            if arg_dict[key] == default_arg and key in data:
                arg_dict[key] = data[key]
    return args 
Example #5
Source File: markdown2.py    From dl with Apache License 2.0 6 votes vote down vote up
def _do_code_blocks(self, text):
        """Process Markdown `<pre><code>` blocks."""
        code_block_re = re.compile(r'''
            (?:\n\n|\A\n?)
            (               # $1 = the code block -- one or more lines, starting with a space/tab
              (?:
                (?:[ ]{%d} | \t)  # Lines must start with a tab or a tab-width of spaces
                .*\n+
              )+
            )
            ((?=^[ ]{0,%d}\S)|\Z)   # Lookahead for non-space at line-start, or end of doc
            # Lookahead to make sure this block isn't already in a code block.
            # Needed when syntax highlighting is being used.
            (?![^<]*\</code\>)
            ''' % (self.tab_width, self.tab_width),
            re.M | re.X)
        return code_block_re.sub(self._code_block_sub, text) 
Example #6
Source File: markdown2.py    From dl with Apache License 2.0 6 votes vote down vote up
def _xml_oneliner_re_from_tab_width(tab_width):
    """Standalone XML processing instruction regex."""
    return re.compile(r"""
        (?:
            (?<=\n\n)       # Starting after a blank line
            |               # or
            \A\n?           # the beginning of the doc
        )
        (                           # save in $1
            [ ]{0,%d}
            (?:
                <\?\w+\b\s+.*?\?>   # XML processing instruction
                |
                <\w+:\w+\b\s+.*?/>  # namespaced single tag
            )
            [ \t]*
            (?=\n{2,}|\Z)       # followed by a blank line or end of document
        )
        """ % (tab_width - 1), re.X) 
Example #7
Source File: markdown2.py    From dl with Apache License 2.0 6 votes vote down vote up
def _hr_tag_re_from_tab_width(tab_width):
    return re.compile(r"""
        (?:
            (?<=\n\n)       # Starting after a blank line
            |               # or
            \A\n?           # the beginning of the doc
        )
        (                       # save in \1
            [ ]{0,%d}
            <(hr)               # start tag = \2
            \b                  # word break
            ([^<>])*?           #
            /?>                 # the matching end tag
            [ \t]*
            (?=\n{2,}|\Z)       # followed by a blank line or end of document
        )
        """ % (tab_width - 1), re.X) 
Example #8
Source File: markdown2.py    From dl with Apache License 2.0 6 votes vote down vote up
def _do_code_blocks(self, text):
        """Process Markdown `<pre><code>` blocks."""
        code_block_re = re.compile(r'''
            (?:\n\n|\A\n?)
            (               # $1 = the code block -- one or more lines, starting with a space/tab
              (?:
                (?:[ ]{%d} | \t)  # Lines must start with a tab or a tab-width of spaces
                .*\n+
              )+
            )
            ((?=^[ ]{0,%d}\S)|\Z)   # Lookahead for non-space at line-start, or end of doc
            # Lookahead to make sure this block isn't already in a code block.
            # Needed when syntax highlighting is being used.
            (?![^<]*\</code\>)
            ''' % (self.tab_width, self.tab_width),
            re.M | re.X)
        return code_block_re.sub(self._code_block_sub, text) 
Example #9
Source File: markdown2.py    From dl with Apache License 2.0 6 votes vote down vote up
def _xml_oneliner_re_from_tab_width(tab_width):
    """Standalone XML processing instruction regex."""
    return re.compile(r"""
        (?:
            (?<=\n\n)       # Starting after a blank line
            |               # or
            \A\n?           # the beginning of the doc
        )
        (                           # save in $1
            [ ]{0,%d}
            (?:
                <\?\w+\b\s+.*?\?>   # XML processing instruction
                |
                <\w+:\w+\b\s+.*?/>  # namespaced single tag
            )
            [ \t]*
            (?=\n{2,}|\Z)       # followed by a blank line or end of document
        )
        """ % (tab_width - 1), re.X) 
Example #10
Source File: markdown2.py    From python-webapp-blog with GNU General Public License v3.0 6 votes vote down vote up
def _xml_oneliner_re_from_tab_width(tab_width):
    """Standalone XML processing instruction regex."""
    return re.compile(r"""
        (?:
            (?<=\n\n)       # Starting after a blank line
            |               # or
            \A\n?           # the beginning of the doc
        )
        (                           # save in $1
            [ ]{0,%d}
            (?:
                <\?\w+\b\s+.*?\?>   # XML processing instruction
                |
                <\w+:\w+\b\s+.*?/>  # namespaced single tag
            )
            [ \t]*
            (?=\n{2,}|\Z)       # followed by a blank line or end of document
        )
        """ % (tab_width - 1), re.X) 
Example #11
Source File: markdown2.py    From python-webapp-blog with GNU General Public License v3.0 6 votes vote down vote up
def _hr_tag_re_from_tab_width(tab_width):
    return re.compile(r"""
        (?:
            (?<=\n\n)       # Starting after a blank line
            |               # or
            \A\n?           # the beginning of the doc
        )
        (                       # save in \1
            [ ]{0,%d}
            <(hr)               # start tag = \2
            \b                  # word break
            ([^<>])*?           #
            /?>                 # the matching end tag
            [ \t]*
            (?=\n{2,}|\Z)       # followed by a blank line or end of document
        )
        """ % (tab_width - 1), re.X) 
Example #12
Source File: lexer.py    From teleport with Apache License 2.0 6 votes vote down vote up
def match_text(self):
        match = self.match(r"""
                (.*?)         # anything, followed by:
                (
                 (?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
                                             # comment preceded by a
                                             # consumed newline and whitespace
                 |
                 (?=\${)      # an expression
                 |
                 (?=</?[%&])  # a substitution or block or call start or end
                              # - don't consume
                 |
                 (\\\r?\n)    # an escaped newline  - throw away
                 |
                 \Z           # end of string
                )""", re.X | re.S)

        if match:
            text = match.group(1)
            if text:
                self.append_node(parsetree.Text, text)
            return True
        else:
            return False 
Example #13
Source File: core.py    From teleport with Apache License 2.0 6 votes vote down vote up
def __bytes__(self):
        """
        :return:
            A byte string
        """

        if self.contents is None:
            return b''
        if self._bytes is None:
            if not self._indefinite:
                self._bytes, self._unused_bits = self._as_chunk()[0]
            else:
                chunks = self._merge_chunks()
                self._unused_bits = ()
                for chunk in chunks:
                    if self._unused_bits:
                        # Disallowed by X.690 §8.6.4
                        raise ValueError('Only last chunk in a bit string may have unused bits')
                    self._unused_bits = chunk[1]
                self._bytes = b''.join(chunk[0] for chunk in chunks)

        return self._bytes 
Example #14
Source File: test_re.py    From jawfish with MIT License 5 votes vote down vote up
def test_basic_re_sub(self):
        self.assertEqual(re.sub("(?i)b+", "x", "bbbb BBBB"), 'x x')
        self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y'),
                         '9.3 -3 24x100y')
        self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', 3),
                         '9.3 -3 23x99y')

        self.assertEqual(re.sub('.', lambda m: r"\n", 'x'), '\\n')
        self.assertEqual(re.sub('.', r"\n", 'x'), '\n')

        s = r"\1\1"
        self.assertEqual(re.sub('(.)', s, 'x'), 'xx')
        self.assertEqual(re.sub('(.)', re.escape(s), 'x'), s)
        self.assertEqual(re.sub('(.)', lambda m: s, 'x'), s)

        self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<a>', 'xx'), 'xxxx')
        self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<1>', 'xx'), 'xxxx')
        self.assertEqual(re.sub('(?P<unk>x)', '\g<unk>\g<unk>', 'xx'), 'xxxx')
        self.assertEqual(re.sub('(?P<unk>x)', '\g<1>\g<1>', 'xx'), 'xxxx')

        self.assertEqual(re.sub('a',r'\t\n\v\r\f\a\b\B\Z\a\A\w\W\s\S\d\D','a'),
                         '\t\n\v\r\f\a\b\\B\\Z\a\\A\\w\\W\\s\\S\\d\\D')
        self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'), '\t\n\v\r\f\a')
        self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'),
                         (chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7)))

        self.assertEqual(re.sub('^\s*', 'X', 'test'), 'Xtest') 
Example #15
Source File: test_re.py    From jawfish with MIT License 5 votes vote down vote up
def test_constants(self):
        self.assertEqual(re.I, re.IGNORECASE)
        self.assertEqual(re.L, re.LOCALE)
        self.assertEqual(re.M, re.MULTILINE)
        self.assertEqual(re.S, re.DOTALL)
        self.assertEqual(re.X, re.VERBOSE) 
Example #16
Source File: test_re.py    From jawfish with MIT License 5 votes vote down vote up
def test_flags(self):
        for flag in [re.I, re.M, re.X, re.S, re.L]:
            self.assertNotEqual(re.compile('^pattern$', flag), None) 
Example #17
Source File: filters.py    From misp42splunk with GNU Lesser General Public License v3.0 5 votes vote down vote up
def __escape(self, m):
        codepoint = ord(m.group())
        try:
            return self.codepoint2entity[codepoint]
        except (KeyError, IndexError):
            return "&#x%X;" % codepoint 
Example #18
Source File: lexer.py    From misp42splunk with GNU Lesser General Public License v3.0 5 votes vote down vote up
def match_text(self):
        match = self.match(
            r"""
                (.*?)         # anything, followed by:
                (
                 (?<=\n)(?=[ \t]*(?=%|\#\#)) # an eval or line-based
                                             # comment preceded by a
                                             # consumed newline and whitespace
                 |
                 (?=\${)      # an expression
                 |
                 (?=</?[%&])  # a substitution or block or call start or end
                              # - don't consume
                 |
                 (\\\r?\n)    # an escaped newline  - throw away
                 |
                 \Z           # end of string
                )""",
            re.X | re.S,
        )

        if match:
            text = match.group(1)
            if text:
                self.append_node(parsetree.Text, text)
            return True
        else:
            return False 
Example #19
Source File: filters.py    From misp42splunk with GNU Lesser General Public License v3.0 5 votes vote down vote up
def __escape(self, m):
        codepoint = ord(m.group())
        try:
            return self.codepoint2entity[codepoint]
        except (KeyError, IndexError):
            return "&#x%X;" % codepoint 
Example #20
Source File: url.py    From jbox with MIT License 5 votes vote down vote up
def _rfc_1738_quote(text):
    return re.sub(r'[:@/]', lambda m: "%%%X" % ord(m.group(0)), text) 
Example #21
Source File: filters.py    From jbox with MIT License 5 votes vote down vote up
def __escape(self, m):
        codepoint = ord(m.group())
        try:
            return self.codepoint2entity[codepoint]
        except (KeyError, IndexError):
            return '&#x%X;' % codepoint 
Example #22
Source File: test_re.py    From ironpython2 with Apache License 2.0 5 votes vote down vote up
def test_basic_re_sub(self):
        self.assertEqual(re.sub("(?i)b+", "x", "bbbb BBBB"), 'x x')
        self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y'),
                         '9.3 -3 24x100y')
        self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', 3),
                         '9.3 -3 23x99y')

        self.assertEqual(re.sub('.', lambda m: r"\n", 'x'), '\\n')
        self.assertEqual(re.sub('.', r"\n", 'x'), '\n')

        s = r"\1\1"
        self.assertEqual(re.sub('(.)', s, 'x'), 'xx')
        self.assertEqual(re.sub('(.)', s.replace('\\', r'\\'), 'x'), s)
        self.assertEqual(re.sub('(.)', lambda m: s, 'x'), s)

        self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<a>', 'xx'), 'xxxx')
        self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<1>', 'xx'), 'xxxx')
        self.assertEqual(re.sub('(?P<unk>x)', '\g<unk>\g<unk>', 'xx'), 'xxxx')
        self.assertEqual(re.sub('(?P<unk>x)', '\g<1>\g<1>', 'xx'), 'xxxx')

        self.assertEqual(re.sub('a', r'\t\n\v\r\f\a\b', 'a'), '\t\n\v\r\f\a\b')
        self.assertEqual(re.sub('a', '\t\n\v\r\f\a\b', 'a'), '\t\n\v\r\f\a\b')
        self.assertEqual(re.sub('a', '\t\n\v\r\f\a\b', 'a'),
                         (chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7)+chr(8)))
        for c in 'cdehijklmopqsuwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ':
            with check_py3k_warnings():
                self.assertEqual(re.sub('a', '\\' + c, 'a'), '\\' + c)

        self.assertEqual(re.sub('^\s*', 'X', 'test'), 'Xtest') 
Example #23
Source File: test_re.py    From ironpython2 with Apache License 2.0 5 votes vote down vote up
def test_constants(self):
        self.assertEqual(re.I, re.IGNORECASE)
        self.assertEqual(re.L, re.LOCALE)
        self.assertEqual(re.M, re.MULTILINE)
        self.assertEqual(re.S, re.DOTALL)
        self.assertEqual(re.X, re.VERBOSE) 
Example #24
Source File: test_re.py    From ironpython2 with Apache License 2.0 5 votes vote down vote up
def test_flags(self):
        for flag in [re.I, re.M, re.X, re.S, re.L]:
            self.assertTrue(re.compile('^pattern$', flag)) 
Example #25
Source File: test_re.py    From ironpython2 with Apache License 2.0 5 votes vote down vote up
def test_optional_paren(self):
        pattern = r"""\(?\w+\)?"""
        c = re.compile(pattern, re.X)
        self.assertEqual(c.findall('abc'), ['abc']) 
Example #26
Source File: test_re.py    From ironpython2 with Apache License 2.0 5 votes vote down vote up
def test_bug858(self):
        pattern = r"""\(? #optional paren
        \)? #optional paren
        \d+ """
        c = re.compile(pattern, re.X)
        l = c.findall("989")
        self.assertTrue(l == ['989']) 
Example #27
Source File: markdown2.py    From dl with Apache License 2.0 5 votes vote down vote up
def _strip_link_definitions(self, text):
        # Strips link definitions from text, stores the URLs and titles in
        # hash references.
        less_than_tab = self.tab_width - 1

        # Link defs are in the form:
        #   [id]: url "optional title"
        _link_def_re = re.compile(r"""
            ^[ ]{0,%d}\[(.+)\]: # id = \1
              [ \t]*
              \n?               # maybe *one* newline
              [ \t]*
            <?(.+?)>?           # url = \2
              [ \t]*
            (?:
                \n?             # maybe one newline
                [ \t]*
                (?<=\s)         # lookbehind for whitespace
                ['"(]
                ([^\n]*)        # title = \3
                ['")]
                [ \t]*
            )?  # title is optional
            (?:\n+|\Z)
            """ % less_than_tab, re.X | re.M | re.U)
        return _link_def_re.sub(self._extract_link_def_sub, text) 
Example #28
Source File: markdown2.py    From dl with Apache License 2.0 5 votes vote down vote up
def _strip_footnote_definitions(self, text):
        """A footnote definition looks like this:

            [^note-id]: Text of the note.

                May include one or more indented paragraphs.

        Where,
        - The 'note-id' can be pretty much anything, though typically it
          is the number of the footnote.
        - The first paragraph may start on the next line, like so:

            [^note-id]:
                Text of the note.
        """
        less_than_tab = self.tab_width - 1
        footnote_def_re = re.compile(r'''
            ^[ ]{0,%d}\[\^(.+)\]:   # id = \1
            [ \t]*
            (                       # footnote text = \2
              # First line need not start with the spaces.
              (?:\s*.*\n+)
              (?:
                (?:[ ]{%d} | \t)  # Subsequent lines must be indented.
                .*\n+
              )*
            )
            # Lookahead for non-space at line-start, or end of doc.
            (?:(?=^[ ]{0,%d}\S)|\Z)
            ''' % (less_than_tab, self.tab_width, self.tab_width),
            re.X | re.M)
        return footnote_def_re.sub(self._extract_footnote_def_sub, text) 
Example #29
Source File: markdown2.py    From dl with Apache License 2.0 5 votes vote down vote up
def _prepare_pyshell_blocks(self, text):
        """Ensure that Python interactive shell sessions are put in
        code blocks -- even if not properly indented.
        """
        if ">>>" not in text:
            return text

        less_than_tab = self.tab_width - 1
        _pyshell_block_re = re.compile(r"""
            ^([ ]{0,%d})>>>[ ].*\n   # first line
            ^(\1.*\S+.*\n)*         # any number of subsequent lines
            ^\n                     # ends with a blank line
            """ % less_than_tab, re.M | re.X)

        return _pyshell_block_re.sub(self._pyshell_block_sub, text) 
Example #30
Source File: markdown2.py    From dl with Apache License 2.0 5 votes vote down vote up
def _do_tables(self, text):
        """Copying PHP-Markdown and GFM table syntax. Some regex borrowed from
        https://github.com/michelf/php-markdown/blob/lib/Michelf/Markdown.php#L2538
        """
        less_than_tab = self.tab_width - 1
        table_re = re.compile(r'''
                (?:(?<=\n\n)|\A\n?)             # leading blank line

                ^[ ]{0,%d}                      # allowed whitespace
                (.*[|].*)  \n                   # $1: header row (at least one pipe)

                ^[ ]{0,%d}                      # allowed whitespace
                (                               # $2: underline row
                    # underline row with leading bar
                    (?:  \|\ *:?-+:?\ *  )+  \|?  \n
                    |
                    # or, underline row without leading bar
                    (?:  \ *:?-+:?\ *\|  )+  (?:  \ *:?-+:?\ *  )?  \n
                )

                (                               # $3: data rows
                    (?:
                        ^[ ]{0,%d}(?!\ )         # ensure line begins with 0 to less_than_tab spaces
                        .*\|.*  \n
                    )+
                )
            ''' % (less_than_tab, less_than_tab, less_than_tab), re.M | re.X)
        return table_re.sub(self._table_sub, text)