#!/usr/bin/env python

# Finds spreadsheet rows where a column is not in a vocabulary.

# The vocabulary should not have a header. CSVs without a header are supported.

# Case- and punctuation-insensitive.

import csv

import re

import sys

def simplify(str_): return re.sub(r'[\W_]+', r'', str_.lower())

def main():

    try: _prog_name, col_num, vocab_path = sys.argv

    except ValueError: raise SystemExit('Usage: '+sys.argv[0]

        +' <in col# vocab [| '+sys.argv[0]+' col# vocab_2]... >out')

    col_num = int(col_num)

    # Get vocab

    vocab = set()

    stream = open(vocab_path, 'rb')

    reader = csv.reader(stream)

    for row in reader: vocab.add(simplify(row[0]))

    stream.close()

    # Filter input

    reader = csv.reader(sys.stdin)

    writer = csv.writer(sys.stdout)

    for row in reader:

        term = simplify(row[col_num])

        if term not in vocab: writer.writerow(row)

main()