def main():
fw = open('58.txt', 'w')
sys.stdout = fw
document = exp50.read('50.txt.xml')
collapsed_dependencies = exp57.make_collapsed_dependencies(document)
flag = 0
for line in collapsed_dependencies:
nsubj_pairs = []
dobj_pairs = []
for item in line:
search_nsubj = re.search('<dep type="nsubj">', item)
search_dobj = re.search('<dep type="dobj">', item)
#print item
if search_nsubj:
flag = 1
nsubj_pair = []
if search_dobj:
flag = 2
dobj_pair = []
if item == '</dep>':
flag = 0
if flag == 1:
governor = exp57.search_governor(item)
dependent = exp57.search_dependent(item)
if governor != None:
nsubj_pair.append(governor)
if dependent != None:
nsubj_pair.append(dependent)
if len(nsubj_pair) == 2:
nsubj_pairs.append(nsubj_pair)
if flag == 2:
governor = exp57.search_governor(item)
dependent = exp57.search_dependent(item)
if governor != None:
dobj_pair.append(governor)
if dependent != None:
dobj_pair.append(dependent)
if len(dobj_pair) == 2:
dobj_pairs.append(dobj_pair)
sentences = make_sentence(nsubj_pairs, dobj_pairs)
#print sentences
for sentence in sentences:
if len(sentence) == 2:
print sentence[1][1], sentence[1][0], sentence[0]
def main():
fw = open('52.txt', 'w')
sys.stdout = fw
stemmer = nltk.PorterStemmer()
document = exp50.read('51.txt')
for line in document:
print line, '\t', stemmer.stem(line)
fw.close()
def main():
fw = open('53.txt', 'w')
sys.stdout = fw
document = exp50.read('50.txt.xml')
for line in document:
search = re.search('<word>(.+)</word>', line)
if search:
print search.group(1)
fw.close()
def main():
fw = open('53.txt', 'w')
sys.stdout = fw
document = exp50.read('50.txt.xml')
for line in document:
search = re.search('<word>(.+)</word>', line)
if search:
print search.group(1)
fw.close()
def main():
fw = open('51.txt', 'w')
sys.stdout = fw
document = exp50.read('50.txt')
for line in document:
string = re.sub('\s', '\n', line)
search = re.search('(\w+\.|\w+\?|\w+!|\w+\:|\w+\;)', string)
if search:
print string
print '\n'.strip()
else:
print string
fw.close()
def main():
fw = open('54.txt', 'w')
sys.stdout = fw
document = exp50.read('50.txt.xml')
for line in document:
search1 = re.search('<word>(\w+)</word>', line)
search2 = re.search('<lemma>(\w+)</lemma>', line)
search3 = re.search('<POS>(\w+)</POS>', line)
if search1:
print search1.group(1), '\t',
if search2:
print search2.group(1), '\t',
if search3:
print search3.group(1)
fw.close()
def main():
fw = open('54.txt', 'w')
sys.stdout = fw
document = exp50.read('50.txt.xml')
for line in document:
search1 = re.search('<word>(\w+)</word>', line)
search2 = re.search('<lemma>(\w+)</lemma>', line)
search3 = re.search('<POS>(\w+)</POS>', line)
if search1:
print search1.group(1), '\t',
if search2:
print search2.group(1), '\t',
if search3:
print search3.group(1)
fw.close()
def main():
fw = open('copy.txt', 'w')
sys.stdout = fw
document = exp50.read('50.txt.xml')
parse_trees = s_list(document)
for parse_tree in parse_trees[1]:
add_space_list = add_space(parse_tree)
s = make_parse_list(add_space_list)
np = make_np_list(s)
for item in np:
#print item
np_word = extract_np(item)
print ' '.join(np_word)
#print np_word
fw.close()
def main():
fw = open('copy.txt', 'w')
sys.stdout = fw
document = exp50.read('50.txt.xml')
parse_trees = s_list(document)
for parse_tree in parse_trees[1]:
add_space_list = add_space(parse_tree)
s = make_parse_list(add_space_list)
np = make_np_list(s)
for item in np:
#print item
np_word = extract_np(item)
print ' '.join(np_word)
#print np_word
fw.close()
def main():
fw = open('57.dot', 'w')
sys.stdout = fw
document = exp50.read('50.txt.xml')
collapsed_dependencies = make_collapsed_dependencies(document)
print 'digraph sample{'
print '', 'graph [rankdir = LR];'
for line in collapsed_dependencies[2]:
governor = search_governor(line)
dependent = search_dependent(line)
if governor != None:
print governor, '->',
if dependent != None:
print dependent
print '}'
fw.close()
# !/usr/bin/python
# coding:UTF-8
# 6-(55):固有表現抽出
#入力文中の人名をすべて抜き出せ．
import re
import sys
import exp50
if __name__ == "__main__":
fw = open('55.txt', 'w')
sys.stdout = fw
document = exp50.read('50.txt.xml')
sentence = []
flag = 0
for line in document:
search1 = re.search('<token id=".+">', line)
search2 = re.search('</token>', line)
if search1:
word = []
flag = 1
if search2:
sentence.append(word)
flag = 0
if flag == 1:
word.append(line)
for word in sentence:
if '<NER>PERSON</NER>' in word:
# !/usr/bin/python
# coding:UTF-8
# 6-(55):固有表現抽出
#入力文中の人名をすべて抜き出せ．
import re
import sys
import exp50
if __name__ == "__main__":
fw = open('55.txt', 'w')
sys.stdout = fw
document = exp50.read('50.txt.xml')
sentence = []
flag = 0
for line in document:
search1 = re.search('<token id=".+">', line)
search2 = re.search('</token>', line)
if search1:
word = []
flag = 1
if search2:
sentence.append(word)
flag = 0
if flag == 1:
word.append(line)
for word in sentence:
if '<NER>PERSON</NER>' in word: