Thee, Aggrandizer

aggrandizer.py

import nltk
import nltk.data
import string
import sys

from nltk.corpus import wordnet

def wordnet_pos(treebank_tag):
    if treebank_tag.startswith('J'):
        return wordnet.ADJ
    elif treebank_tag.startswith('V'):
        return wordnet.VERB
    elif treebank_tag.startswith('N'):
        return wordnet.NOUN
    elif treebank_tag.startswith('R'):
        return wordnet.ADV
    else:
        return ''

def aggrandize(text):
    exclude = set(string.punctuation)
    tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')

    # use wordnet to aggrandise text
    aggrandised_content = []

    sentences = nltk.sent_tokenize(text)
    for sentence in sentences:
        words =  nltk.word_tokenize(sentence)
        for i, (word, pos) in enumerate(nltk.pos_tag(words)):
            if len(word) > 1:
                synonyms = wordnet.synsets(word, pos=wordnet_pos(pos))
                for synonym in synonyms:
                    for lemma in synonym.lemma_names():
                        if lemma > word:
                            word = lemma
            if i == 0:
                word = word.capitalize()

            aggrandised_content.append(word)

    return "".join([" "+i if not i.startswith("'")
                          and i not in string.punctuation else i
                          for i in aggrandised_content]).strip()

if __name__ == '__main__':
    try:
        nltk.data.load('tokenizers/punkt/english.pickle')
        word_pos = nltk.pos_tag('foo bar quux xyzzy')
        word, pos = word_pos[0]
        wordnet.synsets(word, pos=wordnet_pos(pos))
    except Exception as e:
        print("downloading nltk requirements...")
        nltk.download('punkt')
        nltk.download('averaged_perceptron_tagger')
        nltk.download('wordnet')
    print(aggrandize(' '.join(sys.argv[1:])))