add tests for wikipedia, malformed xml, bzip2, correct bz2 bug in wikiq.

2018-07-04 15:08:30 -07:00
parent d2746879d0
commit e925ac9da1
5 changed files with 27892 additions and 11 deletions
--- a/2
+++ b/2
@@ -277,7 +277,7 @@ def open_input_file(input_filename):
    elif re.match(r'.*\.gz$', input_filename):
        cmd = ["zcat", input_filename] 
    elif re.match(r'.*\.bz2$', input_filename):
-        cmd = ["zcat", input_filename] 
+        cmd = ["bzcat", "-dk", input_filename] 

    try:
        input_file = Popen(cmd, stdout=PIPE).stdout