comparison g_read_sents.py @ 1:fb617586f4b2 draft

planemo upload commit a81826fe44f09a3710a35c183aa88b745aeec064-dirty

0:e991d4e60c17

    args = the_parser.parse_args()
    return args

def print_out(outp, text, sentences):
    o = open(outp, 'w')
    curr = 0
    for sent in sentences:
        times = count_occurences(sent, sent[-1])
        curr = text.find(sent[0], curr)
        end = find_nth(text, sent[-1], times, curr) + len(sent[-1])
        o.write(text[curr:end] + '\n')
        curr = end
    o.close()

def find_nth(string, sub, n, offset):
    start = string.find(sub, offset)
    while start >= 0 and n > 1:
        start = string.find(sub, start + len(sub))

        if string in item:
            count += 1
    return count

def read_sents(inp, outp):
    i = open(inp, 'r').read()
    corpus = PlaintextCorpusReader(os.path.dirname(inp), os.path.basename(inp))
    sents = corpus.sents()
    print_out(outp, i, sents)

if __name__ == '__main__':

1:fb617586f4b2

    args = the_parser.parse_args()
    return args

def print_out(outp, text, sentences):
    with open(outp, 'w') as output:
        curr = 0
        for sent in sentences:
            times = count_occurences(sent, sent[-1])
            curr = text.find(sent[0], curr)
            end = find_nth(text, sent[-1], times, curr) + len(sent[-1])
            output.write(text[curr:end] + '\n')
            curr = end

def find_nth(string, sub, n, offset):
    start = string.find(sub, offset)
    while start >= 0 and n > 1:
        start = string.find(sub, start + len(sub))

        if string in item:
            count += 1
    return count

def read_sents(inp, outp):
    with open(inp, 'r') as fd:
        i = fd.read()
    corpus = PlaintextCorpusReader(os.path.dirname(inp), os.path.basename(inp))
    sents = corpus.sents()
    print_out(outp, i, sents)

if __name__ == '__main__':