def run_engine(corpus_path='', output_path='', stemming=False):
"""
:return:
"""
# Create PostingFile directory if it doesn't exist
number_of_documents = 0
config = ConfigClass()
r = ReadFile(corpus_path=corpus_path)
p = Parse(stemming)
indexer = Indexer(config, output_path)
# Get all parquet files from corpus path
parquets = []
for root, dirs, files in os.walk(corpus_path):
for name in files:
if name.endswith((".parquet", ".htm")):
parquets.append((root, name))
for index in range(len(parquets)):
r.corpus_path = parquets[index][0]
documents_list = r.read_file(file_name=parquets[index][1])
# Create a new process for each document
with Pool(CPUCOUNT) as _p:
for parsed_doc in _p.imap_unordered(p.parse_doc, documents_list):
number_of_documents += 1
indexer.add_new_doc(parsed_doc)
_p.close()
_p.join()
p.entities.clear()
indexer.finish_index()
save_obj(indexer.term_dict, output_path + '/' + "inverted_idx")
save_obj(indexer.document_dict, output_path + '/' + "doc_dictionary")
indexer.document_dict.clear()
indexer.term_dict.clear()
