def decode(self, img, first_strip=False):
softstrip_matrix = SoftstripMatrix(img, self.gray_img)
header_extractor = HeaderExtractor(softstrip_matrix)
header_extractor.parse_header()
vertical_sync_start = header_extractor.vertical_sync_start
self.bits_count = header_extractor.get_bits_per_row()
if self.config['row_extractor'] == CNN_ROW_EXTRACTOR:
row_extractor = CnnRowExtractor(softstrip_matrix.grayscale_matrix, softstrip_matrix.binary_matrix, self.bits_count)
gray_grouped_matrix, grouped_matrix = row_extractor.extract_rows()
else:
row_extractor = AlgorithmicRowExtractor(softstrip_matrix, self.bits_count)
grouped_matrix, gray_grouped_matrix = row_extractor.extract_rows()
if self.config['row_decoder'] == CNN_ROW_DECODER:
row_decoder = CnnRowDecoder(gray_grouped_matrix, self.start_time, self.bits_count, self.config['timeout'], vertical_sync_start)
reduced_pixel_matrix = row_decoder.decode_rows()
else:
row_decoder = AlgorithmicRowDecoder(grouped_matrix, self.bits_count, self.start_time, self.config['timeout'])
reduced_pixel_matrix = row_decoder.decode_rows()
if len(reduced_pixel_matrix) == 0:
print('[ERROR] ' + self.path + ' is invalid!')
else:
data_extractor = DataExtractor(self.config['timeout'])
data_extractor.extract_data(reduced_pixel_matrix, first_strip, self.start_time)
self.data += data_extractor.data
if data_extractor.valid:
print('Checksum valid!')
if first_strip:
self.strip_meta_info = data_extractor.file_header
print(self.strip_meta_info)
else:
print('Checksum invalid!')
def get_arguments(argument_list):
short_options = "d:"
long_options = ["document="]
try:
document_file = ''
arguments, values = getopt.getopt(argument_list, short_options,
long_options)
print(arguments)
if len(arguments) < 1:
print("Invalid arguments")
sys.exit(2)
for t in arguments:
if t[0] in ("-d", "--document"):
document_file = t[1]
print(document_file)
return document_file
except getopt.error as err:
print(str(err))
sys.exit(2)
if __name__ == '__main__':
wiki_10_file = get_arguments(sys.argv[1:])
inverted_index = InvertedIndex()
data_extractor = DataExtractor()
structure_file_name = data_extractor.extract_data(wiki_10_file)
index_file, vector_file = inverted_index.build_term_index(
structure_file_name, wiki_10_file)
print("Index file name: ", index_file)
print("Vector file name: ", vector_file)
