A naive script to construct an inverted index

construct_inverted_index.py

def construct_index(docs):
    term_dict = {}
    postings = {}
    for id, doc in docs.items():

        terms = list(set(doc.lower().split()))
        for term in terms:
            term_count = term_dict.get(term, 0)
            term_posting = postings.get(term, None)

            # update the dictionary
            if term_count == 0:
                term_dict.setdefault(term, 1)
            else:
                term_dict[term] += 1

            # update the postings
            if term_posting is None:
                postings[term] = [id]
            else:
                term_posting.append(id)
                postings[term] = term_posting

    return term_dict, postings

def main():

    # from IR book Ch. 1-2 Exercise 1.1
    test_docs = {
        1:"new home sales top forecasts",
        2:"home sales rise in july",
        3:"increase in home sales in july",
        4:"july new home sales rise"
    }

    term_dict, postings = construct_index(test_docs)
    print(term_dict)
    print(postings)

if __name__ == '__main__':
    main()