#!/usr/bin/env python
# coding: utf-8
import sys, os
sys.path.append(os.environ['HOME'])
sys.path.append(os.environ['HOME']+os.sep+'.pylib')
import codecs
from glob import glob
from collections import defaultdict
from textual import freq
from string import Template
"""
This program generates a bunch of .html files in the current directory which are graded to learn an alphabet.

It's a mess.
"""

lexicon = [line.lower().strip().split('\t') for line in open('en2ru.matches').read().decode('utf-8').splitlines() if len(line.strip().split('\t')) == 2]

en2ru = dict(lexicon)
ru2en = dict([(r,e) for e,r in en2ru.items() )
targetfreq = dict(freq(''.join(ru2en.keys())))
byfreq = sorted(targetfreq, key=lambda letter:targetfreq[letter], reverse=True)

prefixes = []
for i in range(1,len(''.join(byfreq))): 
	prefixes.append(tuple(sorted(byfreq[:i])))

levels = defaultdict(list)
for word in ru2en.keys():
 for prefix in prefixes:
  if set(word) < set(prefix):
   levels[prefix].append(word)
   break

def makepage(pattern, words):
 words = sorted(words, key=len)
 template = open('russian.html').read().decode('utf-8')
 content = u"<h1>%s</h1>\n<dl>" % pattern
 for word in words:
  content += u"""<dt lang="ru">%s</dt><dd lang="en">%s</dd>\n""" % (word, ru2en[word])
 content += "</dl>"
 page = Template(template)
 return page.substitute({'title':pattern, 'css':'style.css','content':content})

def make_link(url, anchor): 
  return """<a href="%s">%s</a>""" % (url, anchor)

for i, (pattern, words) in enumerate(sorted(levels.items(), key=lambda x: len(x[0]))):
 print ''.join(pattern)
 outfilename = str(i+1) + ".html"
 outfile = codecs.open( outfilename, mode='w', encoding='utf-8')
 sortedpattern = u''.join(sorted(pattern, key=lambda letter:byfreq.index(letter)))
 outfile.write( makepage(sortedpattern, words ) )
 outfile.close()