def getques():
try:
ques=sys.argv[1]
worder=Worder()
stems=[]
named_ent=worder.named_entities(ques)
print named_ent
entities=re.findall(r'\s(.*?)/NN',str(named_ent)) #regex spliting about NN
entities+=re.findall(r'\s(.*?)/VB',str(named_ent))
print "entities are : "
print(entities)
for entity in entities: # for loop for finding the stems
stems.append(worder.stemmer(entity))
print "stems are :"
print stems
descriptives= ','.join(re.findall(r'\s(.*?)/WP',str(named_ent)))
print "descriptive or type of question is : %s" %(descriptives)
print "searching using stems........"
search=''.join(entities).strip()
print search
def keyword():
return search
subprocess_cmd('python src/main.py'+ " " +search+',')
print 'python src/main.py'+ " " +search+','
except Exception ,e:
print(str(e))
print "traceback: error in getques() of question.py"
def split_by_lines():
subprocess_cmd("cat output/extract.txt | tr -d ',' |tr '\n' ' ' | tr '.?!' '\n' > output/lines.txt")
line=file("output/lines.txt","rb").read()
lines=re.findall(r'(.*?)\n',line)
keywords=re.findall(r'(.*?),',keyword)
answer=[]
# for l in range(2,len(lines)):
# for keyword in keywords:
# if keyword.isdigit():
# breakpoint=l;
# else if
for l in range(1,len(lines)):
for keyword in keywords:
if keyword in lines[l]:
# print "success"
answer.append(lines[l])
for i in range(1,9):
if l+i < len(lines):
answer.append(lines[l+i])
else:
pass
if not answer:
for l in range(1,len(lines)):
answer.append(lines[l])
print '.\n'.join(answer)
def split_by_lines(keywords):
print "in"
subprocess_cmd("cat extract.txt | tr -d ',' |tr '\n' ' ' | tr '.?!' '\n' > lines.txt")
line=file("lines.txt","rb").read()
lines=re.findall(r'(.*?)\n',line)
keys=re.findall(r'(.*?),',keywords)
answer=[]
for l in range(1,len(lines)):
for key in keys:
if key in lines[l]:
answer.append(lines[l])
for i in range(1,9):
if l+i < len(lines):
answer.append(lines[l+i])
else:
pass
if not answer:
for l in range(1,len(lines)):
answer.append(lines[l])
print '.\n'.join(answer)