comparison g_stemmer.py @ 2:a47980ef2b96 draft

planemo upload for repository https://github.com/Alveo/alveo-galaxy-tools commit b5b26e9118f2ad8af109d606746b39a5588f0511-dirty

1:fb617586f4b2

import sys
import os
import nltk
from nltk.stem import *
import argparse


def arguments():
    parser = argparse.ArgumentParser(description="Segments the text input into separate sentences")
    parser.add_argument('--input', required=True, action="store", type=str, help="input text file")
    parser.add_argument('--output', required=True, action="store", type=str, help="output file path")
    parser.add_argument('--stemmer', required=False, action="store", type=str, help="output file path")
    args = parser.parse_args()
    return args

def stem_file(in_file, out_file, stemmer_type):
    with open(in_file, 'r') as fd:
        unsegmented = fd.read()

            for word in words:
                stemmed_word = stemmer.stem(word)
                output.write(stemmed_word)
                output.write('\n')

def get_stemmer(stemmer_type):
    if stemmer_type == 'lancaster':
        stemmer = LancasterStemmer()
    elif stemmer_type == 'porter':
        stemmer = PorterStemmer()
    else:
        stemmer = snowball.EnglishStemmer()
    return stemmer

if __name__ == '__main__':
    args = arguments()
    stem_file(args.input, args.output, args.stemmer)

2:a47980ef2b96

import nltk
from nltk.stem import PorterStemmer, LancasterStemmer, snowball
import argparse


def arguments():
    parser = argparse.ArgumentParser(description="Segments the text input into separate sentences")
    parser.add_argument('--input', required=True, action="store", type=str, help="input text file")
    parser.add_argument('--output', required=True, action="store", type=str, help="output file path")
    parser.add_argument('--stemmer', required=False, action="store", type=str, help="output file path")
    args = parser.parse_args()
    return args


def stem_file(in_file, out_file, stemmer_type):
    with open(in_file, 'r') as fd:
        unsegmented = fd.read()

            for word in words:
                stemmed_word = stemmer.stem(word)
                output.write(stemmed_word)
                output.write('\n')


def get_stemmer(stemmer_type):
    if stemmer_type == 'lancaster':
        stemmer = LancasterStemmer()
    elif stemmer_type == 'porter':
        stemmer = PorterStemmer()
    else:
        stemmer = snowball.EnglishStemmer()
    return stemmer


if __name__ == '__main__':
    args = arguments()
    stem_file(args.input, args.output, args.stemmer)