#!/usr/bin/env python
# -*- coding: utf-8 -*-
#   

import fileinput
import re
import sys
"""
Given a file with a name like:

    ENGLISH

Which contains the appropriate text from this Wikipedia page (see the bottom
of this file for sample file content):

    http://en.wikipedia.org/wiki/Scrabble_letter_distributions

For the corresponding language, generate code containing a Python 
dictionary representing the Scrabble "language model" of the language.

(To compile several files into a single models.py, see buildmodels.sh)
"""

scores = {}

def extracttiles(seq):
    """
        >>> extracttiles(u'B ×2, C ×2, M ×2, P ×2')
        [u'B', u'C', u'M', u'P']
    """
    timessymbol = u'×'    
    parts = seq.split()
    tiles = [part for part in parts if timessymbol not in part]
    return tiles
    
for line in fileinput.input():
    line = unicode(line)
    valRE = re.compile('[0-9]+')
    if 'point' in line and 'blank' not in line:
        val, letters = line.split(':')
        val = int(valRE.findall(val)[0])
        letters = extracttiles(letters)
        for letter in letters: 
            scores[letter] = val

lgname = sys.argv[2]
print '\n%s = {' % lgname
for letter,value  in scores.items():
    print "\tu'%s': %s, " % (letter, value)
print '}'




"""
# 2 blanks (zero points)
# 1 point: E ×12, A ×9, I ×9, O ×8, R ×6, N ×6, T ×6, L ×4, S ×4 U ×4
# 2 points: D ×4, G ×3
# 3 points: B ×2, C ×2, M ×2, P ×2
# 4 points: F ×2, H ×2, V ×2, W ×2, Y ×2
# 5 points: K ×1
# 8 points: J ×1, X ×1
# 10 points: Q ×1, Z ×1

"""