String number matching magic for scene releases

number_clustering.py

import regex
test_release = 'Release.Name.v1.3.0.DISC.1.Other.Tags.x.264.<RESOLUTION>.WMV'
 
memory = []
main = []
split_release = test_release.split('.')
split_release.reverse()
split_release_copy = split_release[:]

# Tags that I want to know about
number_reg = regex.compile('(?:(?P<disc>DISC)|(?P<update>UPDATE)|(?P<build>BUILD)|(?P<version>v\d+)|'
                           '(?P<codec>\Ax|h))\Z', 258)
# Special functions for those found tags
extra_modifiers = {'codec': lambda memory_list: ''.join(memory),
                   'disc': lambda memory_list: disc_join_plus(memory)}


def disc_join_plus(memory_list):
    print 'DISC: {}'.format(memory[1:])
    return '<DISC>'


def is_numberlike(string):
    try:
        float(string)
        return True
    except ValueError:
        if string[0].isdigit() and string[-1].isalpha() and (len(filter(str.isdigit, string))/len(string) >= 0.5):
            return True
        return False

for k, v in enumerate(split_release):
    try:
        # prints out what item your on nicely
        nice = ''
        marker = ''
        for i in split_release:
            nice += i + '\t'
        for i in range(0, k):
            marker += '\t'
        print nice
        print marker + '^'

        # item always put into memory
        memory.append(split_release_copy.pop(0))
        print('Main string is {} | Current memory: {}'.format(main, memory))
        do_special_work = number_reg.search(v)
        # item always put in tracked

        # if it's a special known tag type change it + the memory items to whatever
        if do_special_work and len(memory) > 1:

            # reverse the memory to original state
            memory.reverse()

            # see what regex group matched
            tag_info = list(next((group_name, group_value) for group_name, group_value in
                            do_special_work.groupdict().iteritems() if group_value))

            # do a regular do join on the numbers or something special if specified
            main.append( extra_modifiers[tag_info[0]](memory) if tag_info[0] in extra_modifiers else '.'.join(memory))

            # clear the memory
            memory = []

        elif is_numberlike(v) and k < len(split_release):
            # This item is a number (and not first item in original string) so it must belong to the upcoming item
            continue
        else:
            memory.reverse()
            # I might want to skip the join and directly add all items to memory 'as is' or something different,
            # i.e. this item (main.append(memory.pop())) >> main, then join rest of memory to main, however it seems
            # that numbers and number-like items should always belong to an item
            main.append('.'.join(memory))

            # clear the memory
            memory = []

    except IndexError as e:
        print e
split_release.reverse()
print '{} became:'.format(split_release)
main.reverse()
print main
---------------
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
^
Main string is [] | Current memory: ['WMV']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
	^
Main string is ['WMV'] | Current memory: ['<RESOLUTION>']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
		^
Main string is ['WMV', '<RESOLUTION>'] | Current memory: ['264']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
			^
Main string is ['WMV', '<RESOLUTION>'] | Current memory: ['264', 'x']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
				^
Main string is ['WMV', '<RESOLUTION>', 'x264'] | Current memory: ['Tags']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
					^
Main string is ['WMV', '<RESOLUTION>', 'x264', 'Tags'] | Current memory: ['Other']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
						^
Main string is ['WMV', '<RESOLUTION>', 'x264', 'Tags', 'Other'] | Current memory: ['1']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
							^
Main string is ['WMV', '<RESOLUTION>', 'x264', 'Tags', 'Other'] | Current memory: ['1', 'DISC']
DISC: ['1']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
								^
Main string is ['WMV', '<RESOLUTION>', 'x264', 'Tags', 'Other', '<DISC>'] | Current memory: ['0']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
									^
Main string is ['WMV', '<RESOLUTION>', 'x264', 'Tags', 'Other', '<DISC>'] | Current memory: ['0', '3']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
										^
Main string is ['WMV', '<RESOLUTION>', 'x264', 'Tags', 'Other', '<DISC>'] | Current memory: ['0', '3', 'v1']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
											^
Main string is ['WMV', '<RESOLUTION>', 'x264', 'Tags', 'Other', '<DISC>', 'v1.3.0'] | Current memory: ['Name']
WMV	<RESOLUTION>	264	x	Tags	Other	1	DISC	0	3	v1	Name	Release	
												^
Main string is ['WMV', '<RESOLUTION>', 'x264', 'Tags', 'Other', '<DISC>', 'v1.3.0', 'Name'] | Current memory: ['Release']
['Release', 'Name', 'v1', '3', '0', 'DISC', '1', 'Other', 'Tags', 'x', '264', '<RESOLUTION>', 'WMV'] became:
['Release', 'Name', 'v1.3.0', '<DISC>', 'Other', 'Tags', 'x264', '<RESOLUTION>', 'WMV']