Define a Python class and methods for locating diminutive nouns in a Russian text.

DimFinderClass.py

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

import nltk
from nltk.stem import SnowballStemmer
from nltk import FreqDist
import codecs

def print_list(mylist):
    '''Print a list containing unicode characters.'''
    print '[' + ', '.join(
        "" + word.encode('utf8') + "" for word in mylist) + ']'

class DiminutiveFinder(object):

    def __init__(self, text):
        self.text = text
        self.verified_diminutives = []
        self.diminutives = []
        self.stemlist = []
        self.tokens = []
        # possible endings of diminutive stems
        self.diminutive_endings = (
            # first degree of expressiveness
            #u"к", 
            u"ик",
            u"чик",
            u"ок", #u"ек",
            u"ец", u"иц",
            u"енок", u"онок", u"еныш",
            u"инк", u"инок",
            u"ыш",
            #u"ц",
            # second degree of expressiveness
            u"еньк",
            u"оньк",
            u"ушк", u"юшк", u"ушек", u"юшек",
            u"уш", u"юш",
            u"ышк", u"ышек",
            u"ишк", u"ишек",
            u"ашк", u"ашек",
            u"онка", u"енка", u"онок", u"енок",
            # third degree of expressiveness
            u"очк", u"ечк", u"очок", u"ечок",
            u"ичк", u"ичок",
            u"очек", u"ечек",
            u"оночек", u"еночек", u"оночк", u"еночк",
            u"иночк", u"иночек", u"иночок",
            u"ишечк", u"ишечек", u"ишечок", u"ушечк", u"ушечек", u"ушечок",
            u"юшечк", u"юшечек", u"юшечшк",
            # diminutive adjectives
            u"еньк", u"оньк",
            u"ехоньк", u"охоньк", u"ешеньк", u"ошеньк",
            u"юсеньк", u"усеньк",
            u"оват", u"еват",
            u"оватеньк", u"еватеньк"
            )
        
    def find_diminutives(self, text):
        # data = codecs.open(text_file, encoding="utf8")
        # text = data.read()
        self.tokens = nltk.word_tokenize(text)
        stemmer = SnowballStemmer("russian")

        for item in self.tokens:
            barestem = stemmer.stem(unicode(item))
            self.stemlist.append(barestem)

        for word in self.stemlist:
            if word.endswith(self.diminutive_endings):
                self.diminutives.append(word)

        self.dim_fd = FreqDist(self.diminutives)

    def find_verified_diminutives(self, text):
	self.tokens = nltk.word_tokenize(text)
	stemmer = SnowballStemmer("russian")

	for item in self.tokens:
	    barestem = stemmer.stem(unicode(item))
	    self.stemlist.append(barestem)

	for word in self.stemlist:
	    if word in self.verified_dims:
	        self.verified_diminutives.append(word)

	self.ver_dim_fd = FreqDist(self.verified_diminutives)