def run_engine(corpus_path_, output_path_, stemming_):
"""
:return:
"""
number_of_documents = 0
config = ConfigClass(corpuspath=corpus_path_,outputpath=output_path_,stemming=stemming_)
config.corpusPath = corpus_path_
config.savedFileMainFolder=output_path_
r = ReadFile(corpus_path=config.get__corpusPath())
p = Parse()
indexer = Indexer(config)
pathes = r.get_all_path_of_parquet()
length_of_array = len(pathes)
iteration = 0
is_stemmer = config.toStem
parsed_doc_list = list()
for i in range(0, length_of_array):
documents_list = r.get_documents(pathes[i][0], pathes[i][0])
for doc, j in zip(documents_list, range(len(documents_list))):
parsed_document = p.parse_doc(doc, stemmer=is_stemmer)
if parsed_document == None:
continue
parsed_doc_list.append(parsed_document)
number_of_documents += 1
if number_of_documents % 200000 == 0:
for doc in parsed_doc_list:
indexer.add_new_doc(doc)
indexer.write_posting_to_txt_file_lower_upper(iteration)
iteration += 1
parsed_doc_list.clear()
parsed_doc_list = list()
elif j == len(documents_list) - 1 and i == length_of_array - 1:
for doc in parsed_doc_list:
indexer.add_new_doc(doc)
indexer.write_posting_to_txt_file_lower_upper(iteration)
parsed_doc_list.clear()
parsed_doc_list = list()
indexer.merge_posting_file()
indexer.merge_two_last_posting_file()
indexer.split_posting_file_and_create_inverted_index()
indexer.write_inverted_index_to_txt_file()
number_of_documents = 0
def main(corpus_path, output_path, stemming, queries, num_doc_to_retrieve):
config = ConfigClass()
config.corpusPath = corpus_path
config.savedFileMainFolder = output_path
config.toStem = stemming
run_engine(config)
inverted_index = load_index()
queries_file = open(queries, encoding="utf8")
tuple_answers = []
query_num = 1
for query in queries_file:
for doc_tuple in search_and_rank_query(query[:-1], inverted_index, num_doc_to_retrieve, config):
print('tweet id: {} Score: {}'.format(doc_tuple[0], doc_tuple[1]))
doc_tuple = doc_tuple + (query_num,)
tuple_answers.append(doc_tuple)
query_num += 1
queries_file.close()
def run_engine(corpus_path=None,
output_path=None,
stemming=False,
lemma=False,
queries=None,
num_docs_to_retrieve=None):
"""
:return:
"""
global config, number_of_documents
number_of_documents = 0
config = ConfigClass()
config.corpusPath = corpus_path
config.set_output_path(output_path)
config.toStem = stemming
config.toLemm = lemma
if os.path.exists(config.get_output_path()):
shutil.rmtree(config.get_output_path())
r = ReadFile(corpus_path=config.get__corpusPath())
p = Parse(config.toStem, config.toLemm)
indexer = Indexer(config)
documents_list = []
for root, dirs, files in os.walk(corpus_path):
r.set_corpus_path(root)
for file in files:
if file.endswith(".parquet"):
documents_list += r.read_file(file)
# Iterate over every document in the file
for idx, document in enumerate(documents_list):
# parse the document
parsed_document = p.parse_doc(document)
number_of_documents += 1
# index the document data
indexer.add_new_doc(parsed_document)
documents_list.clear(
) # Finished parsing and indexing all files - need to clean all the used memory
indexer.cleanup(number_of_documents)