def __init__(self, path, tokenizer, search, write):
start = time.time()
cr = CorpusReader(path, tokenizer)
cr.processFile()
#performance metrics
print("Index time: {:.2f} seconds".format(time.time() - start))
size = os.stat(path + '.bin').st_size
print("Index Size on disk :", sizeof_fmt(size))
words = cr.index.keys()
metrics(cr.indexer)
print(
f"Vocabulary: {len(words)} words, size: {sizeof_fmt(len(''.join(words)))}"
)
if search != '':
print(cr.indexer.search(search))
if write:
cr.indexer.writeIndexToFile(f"{path}_indexer.txt")
