def main(clean_text):
global TAGGER
TAGGER = postagger.get_tagger()
passive_sentences = findpassives(clean_text)
# all_sentences = sentence_count(clean_text)
# if len(sys.argv) > 1:
# for fn in sys.argv[1:]:
# print "------------------------------------"
# passive_sentences = findpassives(fn)
# print type(passive_sentences)
# print len(passive_sentences)
# for sentence in passive_sentences:
# print sentence
#sentences = fn
#sentences = sentences.replace("\n", "").replace("\r", "")
#sentences = nltk.sent_tokenize(sentences)
# all_sentences = sentence_count(fn)
#sentence_count = len(sentences)
#else:
# repl()
# for report
#fn = sys.argv[1]
#fh = open("results.txt", "r")
#passive_sentences = fh.readlines()
#fh.close
#report(fn, len(passive_sentences), float(all_sentences), passive_sentences)
return passive_sentences
print len(passive_sentences)
print type(passive_sentences)
for sentence in passive_sentences:
print sentence
def main():
global TAGGER
TAGGER = postagger.get_tagger()
if len(sys.argv) > 1:
for fn in sys.argv[1:]:
findpassives(fn)
else:
repl()
def main():
global TAGGER
TAGGER = postagger.get_tagger()
if len(sys.argv) > 1:
for fn in sys.argv[1:]:
findpassives(fn)
else:
repl()
# -*- coding: utf-8 -*-
from __future__ import print_function
import os
import sys
import nltk
import re
from nltk import pos_tag, word_tokenize
from itertools import dropwhile
import postagger
global TAGGER
TAGGER = postagger.get_tagger()
# The code for the detection of passive voice has been done with help from https://github.com/j-c-h-e-n-g/nltk-passive-voice
def tag_sentence(sent):
"""Take a sentence as a string and return a list of (word, tag) tuples."""
assert isinstance(sent, basestring)
tokens = word_tokenize(sent)
return TAGGER.tag(tokens)
def passivep(tags):
postToBe = list(dropwhile(lambda(tag): not tag.startswith("BE"), tags))
nongerund = lambda(tag): tag.startswith("V") and not tag.startswith("VBG")
filtered = filter(nongerund, postToBe)