5 examples of 'python split regex' in Python

73
def make_regex_split(pattern):
74
    try:
75
        regex = re.compile(pattern)
76
77
    except Exception as e:
78
        raise argparse.ArgumentTypeError(
79
            "Invalid regular expression '%s'" % (pattern)
80
        )
81
        
82
    # This separates regex parsing from application and provides
83
    # a nice type factory for argparse
84
    def split(line):
85
        return regex.split(line)
86
87
    return split

89
def token_split(text, pattern, advanced=False):
90
        """
91
        @return: An iterator that generates tokens and the gaps between them
92
        """
93
94
        if advanced:
95
            regexp = _compile(pattern)   # pattern contains ()
96
        else:
97
            regexp = re.compile(pattern)
98
99
        # If it's a single string, then convert it to a tuple
100
        # (which we can iterate over, just like an iterator.)
101
        if type(text) is str: text = (text,)
102
103
        # Process each substring returned by the iterator, in turn.
104
        # "leftover" is used to record any leftover material when we
105
        # move on to a new substring.
106
        leftover = ''
107
        offset = 0
108
        for substring in text:
109
            position = 0  # The position within the substring
110
            
111
            # Skip any matching material in the substring:
112
            match = regexp.match(substring)
113
            if match:
114
                yield leftover+substring[position:match.start()]
115
                yield substring[match.start():match.end()]
116
                position = match.end()
117
                leftover = ''
118
119
            # Walk through the substring, looking for matches.
120
            while position < len(substring):
121
                match = regexp.search(substring, position)
122
                if match:
123
                    yield leftover+substring[position:match.start()]
124
                    yield substring[match.start():match.end()]
125
                    position = match.end()
126
                    leftover = ''
127
                else:
128
                    leftover = substring[position:]
129
                    break
130
131
            # Update the offset
132
            offset += position
133
134
        # If the last string had leftover, then return it.
135
        if leftover:
136
            yield leftover

312
def split(pattern, string, maxsplit=0, flags=0, concurrent=None, **kwargs):
313
    """Split the source string by the occurrences of the pattern, returning a
314
    list containing the resulting substrings.  If capturing parentheses are used
315
    in pattern, then the text of all groups in the pattern are also returned as
316
    part of the resulting list.  If maxsplit is nonzero, at most maxsplit splits
317
    occur, and the remainder of the string is returned as the final element of
318
    the list."""
319
    return _compile(pattern, flags, kwargs).split(string, maxsplit, concurrent)

896
def _splitShellPattern(value):
897
    return value.split(',') if '{' not in value else [value]

63
def _tokenize(s):
64
    token_spec = [
65
        ('HYPHEN', r'-'),
66
        ('COORD',  r'[0-9,]+(\.[0-9]*)?(?:[a-z]+)?'),
67
        ('OTHER',  r'.+')
68
    ]
69
    tok_regex = r'\s*' + r'|\s*'.join(
70
        r'(?P<%s>%s)' % pair for pair in token_spec)
71
    tok_regex = re.compile(tok_regex, re.IGNORECASE)
72
    for match in tok_regex.finditer(s):
73
        typ = match.lastgroup
74
        yield typ, match.group(typ)