How do you translate this regular-expression idiom from Perl into Python?

Question

I switched from Perl to Python about a year ago and haven\'t looked back. There is only one idiom that I\'ve ever found I can do more easily in Perl than in Python:<

Answer 1

r"""
This is an extension of the re module. It stores the last successful
match object and lets you access it's methods and attributes via
this module.

This module exports the following additional functions:
    expand  Return the string obtained by doing backslash substitution on a
            template string.
    group   Returns one or more subgroups of the match.
    groups  Return a tuple containing all the subgroups of the match.
    start   Return the indices of the start of the substring matched by
            group.
    end     Return the indices of the end of the substring matched by group.
    span    Returns a 2-tuple of (start(), end()) of the substring matched
            by group.

This module defines the following additional public attributes:
    pos         The value of pos which was passed to the search() or match()
                method.
    endpos      The value of endpos which was passed to the search() or
                match() method.
    lastindex   The integer index of the last matched capturing group.
    lastgroup   The name of the last matched capturing group.
    re          The regular expression object which as passed to search() or
                match().
    string      The string passed to match() or search().
"""

import re as re_

from re import *
from functools import wraps

__all__ = re_.__all__ + [ "expand", "group", "groups", "start", "end", "span",
        "last_match", "pos", "endpos", "lastindex", "lastgroup", "re", "string" ]

last_match = pos = endpos = lastindex = lastgroup = re = string = None

def _set_match(match=None):
    global last_match, pos, endpos, lastindex, lastgroup, re, string
    if match is not None:
        last_match = match
        pos = match.pos
        endpos = match.endpos
        lastindex = match.lastindex
        lastgroup = match.lastgroup
        re = match.re
        string = match.string
    return match

@wraps(re_.match)
def match(pattern, string, flags=0):
    return _set_match(re_.match(pattern, string, flags))


@wraps(re_.search)
def search(pattern, string, flags=0):
    return _set_match(re_.search(pattern, string, flags))

@wraps(re_.findall)
def findall(pattern, string, flags=0):
    matches = re_.findall(pattern, string, flags)
    if matches:
        _set_match(matches[-1])
    return matches

@wraps(re_.finditer)
def finditer(pattern, string, flags=0):
    for match in re_.finditer(pattern, string, flags):
        yield _set_match(match)

def expand(template):
    if last_match is None:
        raise TypeError, "No successful match yet."
    return last_match.expand(template)

def group(*indices):
    if last_match is None:
        raise TypeError, "No successful match yet."
    return last_match.group(*indices)

def groups(default=None):
    if last_match is None:
        raise TypeError, "No successful match yet."
    return last_match.groups(default)

def groupdict(default=None):
    if last_match is None:
        raise TypeError, "No successful match yet."
    return last_match.groupdict(default)

def start(group=0):
    if last_match is None:
        raise TypeError, "No successful match yet."
    return last_match.start(group)

def end(group=0):
    if last_match is None:
        raise TypeError, "No successful match yet."
    return last_match.end(group)

def span(group=0):
    if last_match is None:
        raise TypeError, "No successful match yet."
    return last_match.span(group)

del wraps  # Not needed past module compilation

For example:

if gre.match("foo(.+)", var):
  # do something with gre.group(1)
elif gre.match("bar(.+)", var):
  # do something with gre.group(1)
elif gre.match("baz(.+)", var):
  # do something with gre.group(1)

Answer 2

how about using a dictionary?

match_objects = {}

if match_objects.setdefault( 'mo_foo', re_foo.search( text ) ):
  # do something with match_objects[ 'mo_foo' ]

elif match_objects.setdefault( 'mo_bar', re_bar.search( text ) ):
  # do something with match_objects[ 'mo_bar' ]

elif match_objects.setdefault( 'mo_baz', re_baz.search( text ) ):
  # do something with match_objects[ 'mo_baz' ]

...

however, you must ensure there are no duplicate match_objects dictionary keys ( mo_foo, mo_bar, ... ), best by giving each regular expression its own name and naming the match_objects keys accordingly, otherwise match_objects.setdefault() method would return existing match object instead of creating new match object by running re_xxx.search( text ).

Answer 3

Alternatively, something not using regular expressions at all:

prefix, data = var[:3], var[3:]
if prefix == 'foo':
    # do something with data
elif prefix == 'bar':
    # do something with data
elif prefix == 'baz':
    # do something with data
else:
    # do something with var

Whether that is suitable depends on your actual problem. Don't forget, regular expressions aren't the swiss army knife that they are in Perl; Python has different constructs for doing string manipulation.

Answer 4

def find_first_match(string, *regexes):
    for regex, handler in regexes:
        m = re.search(regex, string):
        if m:
            handler(m)
            return
    else:
        raise ValueError

find_first_match(
    foo, 
    (r'foo(.+)', handle_foo), 
    (r'bar(.+)', handle_bar), 
    (r'baz(.+)', handle_baz))

To speed it up, one could turn all regexes into one internally and create the dispatcher on the fly. Ideally, this would be turned into a class then.

Answer 5

My solution would be:

import re

class Found(Exception): pass

try:        
    for m in re.finditer('bar(.+)', var):
        # Do something
        raise Found

    for m in re.finditer('foo(.+)', var):
        # Do something else
        raise Found

except Found: pass

Answer 6

A minimalist DataHolder:

class Holder(object):
    def __call__(self, *x):
        if x:
            self.x = x[0]
        return self.x

data = Holder()

if data(re.search('foo (\d+)', string)):
    print data().group(1)

or as a singleton function:

def data(*x):
    if x:
        data.x = x[0]
    return data.x