""" We wish to extract a list of translated sentences from two Wikipedia articles. 1. Spider the articles 2. Extract sentences 3. Extract links 4. Represent the sentences as sets of bilingual links 5. Return pairs of sentences ordered by rank intersection """ def spider_article(language_code, title): pass def split_into_sentences(markup): sentences = markup.split('.') # @@TODO haha return sentences def extract_wikitext_links(sentence): """ >>> s = ""[[Rennes|The city of Rennes]] is in [[France]]."" """ pass def bilingualize_link(link): pass def number_of_links_in_common(source, target): return len(source.links.intersect(target.links)) def extract_links(sentence): pass def enrich_links(links): pass def compare_sentences(source, target): pass