#!/usr/bin/env python

# Canonicalizes a spreadsheet column to a vocabulary.

# Unrecognized names are left untouched, permitting successive runs on different

# vocabularies.

# Case- and punctuation-insensitive.

    dict_ = {}

    stream = open(vocab_path, 'rb')

    reader = csv.reader(stream)

    for row in reader: dict_[simplify(row[0])] = row[0]

    stream.close()

    # Canonicalize input

    reader = csv.reader(sys.stdin)

    writer = csv.writer(sys.stdout)

    for row in reader:

        term = simplify(row[col_num])

        try: row[col_num] = dict_[term]