Convert, or unformat, a string to variables (like format(), but in reverse) in Python

Question

I have strings of the form Version 1.4.0\\n and Version 1.15.6\\n, and I\'d like a simple way of extracting the three numbers from them. I know I

Answer 1

Some time ago I made the code below that does the reverse of format but limited to the cases I needed.

And, I never tried it, but I think this is also the purpose of the parse library

My code:

import string
import re

_def_re   = '.+'
_int_re   = '[0-9]+'
_float_re = '[-+]?[0-9]*\.?[0-9]+([eE][-+]?[0-9]+)?'

_spec_char = '[\^$.|?*+()'

def format_parse(text, pattern):
    """
    Scan `text` using the string.format-type `pattern`

    If `text` is not a string but iterable return a list of parsed elements

    All format-like pattern cannot be process:
      - variable name cannot repeat (even unspecified ones s.t. '{}_{0}')
      - alignment is not taken into account
      - only the following variable types are recognized:
           'd' look for and returns an integer
           'f' look for and returns a  float

    Examples::

        res = format_parse('the depth is -42.13', 'the {name} is {value:f}')
        print res
        print type(res['value'])
        # {'name': 'depth', 'value': -42.13}
        # 

        print 'the {name} is {value:f}'.format(**res)
        # 'the depth is -42.130000'

        # Ex2: without given variable name and and invalid item (2nd)
        versions = ['Version 1.4.0', 'Version 3,1,6', 'Version 0.1.0']
        v = format_parse(versions, 'Version {:d}.{:d}.{:d}')
        # v=[{0: 1, 1: 4, 2: 0}, None, {0: 0, 1: 1, 2: 0}]

    """
    # convert pattern to suitable regular expression & variable name
    v_int = 0   # available integer variable name for unnamed variable 
    cur_g = 0   # indices of current regexp group name 
    n_map = {}  # map variable name (keys) to regexp group name (values)
    v_cvt = {}  # (optional) type conversion function attached to variable name
    rpattern = '^'    # stores to regexp pattern related to format pattern        

    for txt,vname, spec, conv in string.Formatter().parse(pattern):
        # process variable name
        if len(vname)==0:
            vname = v_int
            v_int += 1
        if vname not in n_map:
            gname = '_'+str(cur_g)
            n_map[vname] = gname
            cur_g += 1                   
        else:    
            gname = n_map[vname]

        # process type of required variables 
        if   'd' in spec: vtype = _int_re;   v_cvt[vname] = int
        elif 'f' in spec: vtype = _float_re; v_cvt[vname] = float
        else:             vtype = _def_re;

        # check for regexp special characters in txt (add '\' before)
        txt = ''.join(map(lambda c: '\\'+c if c in _spec_char else c, txt))

        rpattern += txt + '(?P<'+gname+'>' + vtype +')'

    rpattern += '$'

    # replace dictionary key from regexp group-name to the variable-name 
    def map_result(match):
        if match is None: return None
        match = match.groupdict()
        match = dict((vname, match[gname]) for vname,gname in n_map.iteritems())
        for vname, value in match.iteritems():
            if vname in v_cvt:
                match[vname] = v_cvt[vname](value)
        return match

    # parse pattern
    if isinstance(text,basestring):
        match = re.search(rpattern, text)
        match = map_result(match)
    else:
        comp  = re.compile(rpattern)
        match = map(comp.search, text)
        match = map(map_result, match)

    return match

for your case, here is a use example:

versions = ['Version 1.4.0', 'Version 3.1.6', 'Version 0.1.0']
v = format_parse(versions, 'Version {:d}.{:d}.{:d}')
# v=[{0: 1, 1: 4, 2: 0}, {0: 3, 1: 1, 2: 6}, {0: 0, 1: 1, 2: 0}]

# to get the versions as a list of integer list, you can use:
v = [[vi[i] for i in range(3)] for vi in filter(None,v)]

Note the filter(None,v) to remove unparsable versions (which return None). Here it is not necessary.