def parse(name, content, doc_path=""):
word_list = []
for line in content.split("\n"):
for word in line.split():
word_list.append(word)
term_list = tokenize(word_list)
doc = Document(name, term_list)
if doc_path != "":
create_document(doc, doc_path)
return doc
def parse(name, content, doc_path = ""):
word_list = []
for line in content.split("\n"):
for word in line.split():
word_list.append(word)
term_list = tokenize(word_list)
doc = Document(name, term_list)
if doc_path != "":
create_document(doc, doc_path)
return doc
def query(self, search_text):
word_list = search_text.split()
term_list = tk.tokenize(word_list)
term_set = set(term_list)
score_dict = {}
for doc_id, doc_term_dict in self.docSpace.vector_dict.items():
doc_term_set = set(list(doc_term_dict.keys()))
termInt = len (term_set & doc_term_set)
termUni = len (term_set | doc_term_set)
if termUni == 0:
ji = 0
else :
ji = float(termInt) / float(termUni)
score_dict[doc_id] = ji
return score_dict
def query(self, search_text):
word_list = search_text.split()
term_list = tk.tokenize(word_list)
term_set = set(term_list)
score_dict = {}
for doc_id, doc_term_dict in self.docSpace.vector_dict.items():
doc_term_set = set(list(doc_term_dict.keys()))
termInt = len(term_set & doc_term_set)
termUni = len(term_set | doc_term_set)
if termUni == 0:
ji = 0
else:
ji = float(termInt) / float(termUni)
score_dict[doc_id] = ji
return score_dict
def get_term_list(self, phrase):
word_list = phrase.split()
term_list = tk.tokenize(word_list)
return term_list