Commit c5b377e3 authored Nov 17, 2017 by root

fixed encoding issues

parent e5635f35

dblp/dblp_to_bracket.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -32,7 +32,7 @@ dblp_data_tree = etree.parse('dblp-2017-11-01.xml', dblp_parser)
		root = dblp_data_tree.getroot()

		# Output files.
		dblp_bracket = open('dblp.bracket', 'w')
		dblp_bracket = open('dblp.bracket', mode='w', encoding="utf8")

		print("--- Processing each child of DBLP's root.")

dblp/random_lines.py

+2 −2

Original line number	Diff line number	Diff line
		@@ -4,10 +4,10 @@ import random
		number = int(sys.argv[1])
		filename = sys.argv[2]

		with open(filename) as f:
		with open(filename, encoding='utf-8') as f:
		lines = f.readlines()

		linestoprint = random.sample(range(len(lines)), number)

		for ln in linestoprint:
		print(lines[ln], end='')
		print(lines[ln].encode('utf8'), end='')