def testMakeobjectsfromxml(self):
reader = Reader()
soup = reader.readfile()
threads = reader.makeobjectsfromxml(soup)
for thread in threads:
for document in thread._documents:
print(document.text)
def testtokenizerfromfile(self):
reader = Reader()
soup = reader.readfile()
threads = reader.makeobjectsfromxml(soup)
tokenizer = Tokenizer(threads)
threads_tokenized = tokenizer.tokenize()
for thread in threads_tokenized:
print(thread._query._body)
for document in thread._documents:
print(document._text)
def test_final(self):
reader = Reader()
soup = reader.readfile()
threads = reader.makeobjectsfromxml(soup)
tokenizer = Tokenizer(threads)
collection_tokenized = tokenizer.tokenize()
coll_model = CollectionModel(collection_tokenized)
doc_model = DocumentModel(collection_tokenized)
ret_model = RetrievalModel(collection_tokenized, doc_model, coll_model)
ret_model.calculate_relevance()
def testdocumentmodel(self):
reader = Reader()
soup = reader.readfile()
threads = reader.makeobjectsfromxml(soup)
tokenizer = Tokenizer(threads)
threads_tokenized = tokenizer.tokenize()
collection_model = CollectionModel(threads_tokenized)
freq_collection = collection_model.calculate_frequency()
print(freq_collection)
document_model = DocumentModel(threads_tokenized)
freq_document = document_model.calculate_frequency()
print(freq_document)