def __init__(self, docs, gram):
self.index = {}
self.docs = docs
self.gram = gram
if self.gram == 2:
all_words = unique([inner
for outer in docs
for inner in docs[outer].words])
new_docs = {}
for i in range(len(all_words)):
word = "#"+all_words[i]+"#"
id = i
words = [word[j:j+2] for j in range(len(word) - 1)]
doc = Doc(id, ' '.join(words))
doc.words = words
new_docs[id] = doc
self.docs = new_docs
self.create_index()
preprocessor = EnglishPreprocessor(docs)
else:
docs = read_docs('../data/Persian.xml')
preprocessor = PersianPreprocessor(docs)
for doc in docs.values():
doc.words = preprocessor.preprocess(doc.text)
print("Preprocess is done!")
index = PositionalIndexer(docs, 1).index
print("Index Created Successfully!")
query = input("Enter Query: ")
q_doc = Doc(0, query)
q_doc.words = preprocessor.preprocess(q_doc.text)
query_tag = input("Enter Tag (1, 2, 3, 4, None): ")
tag = None
if query_tag in ["1", "2", "3", "4"]:
tag = int(query_tag)
if tag is not None:
classify(docs)
results = search(q_doc, docs, index, 10, query_tag)
for result in results:
print(result[1])
print(result[0].text)
print()
