diff --git a/rq2/README.md b/rq2/README.md index 18d918e..29f09d3 100644 --- a/rq2/README.md +++ b/rq2/README.md @@ -28,7 +28,7 @@ Printing details: + data[n].raw_dockerfile + data[n].clean_stdout_log + Example of pre-processed data we used for clustering: - ['the command / bin / sh c go wrapper download returned a non zero code : 1'] + ['add failed : failed to get http : / / repo1 . maven . org / maven2 / org / codehaus / cargo / cargo jetty 7 and onwards deployer / 1 . 4 . 4 / cargo jetty 7 and onwards deployer 1 . 4 . 4 . war with status 501 https required : 501 https required . ', 'use https : / / repo1 . maven . org / maven2 / ', 'more information at https : / / links . sonatype . com / central / 501 https required'] ``` ## Details diff --git a/rq2/clustering.py b/rq2/clustering.py index ffdd3d1..d2f6c3a 100755 --- a/rq2/clustering.py +++ b/rq2/clustering.py @@ -21,6 +21,8 @@ data.append(json.loads(fin.read().decode('utf-8'))) print(' + Done!') +data = sorted(data, key=lambda x: x['clean_stderr_log']) + print('Printing details:') print(' + Number of records: {}'.format(len(data))) print(' + Available fields:')