def churn_info_in_commit(xml_commit, debug=False):
# Process the stat-tag
xml_stat = xml_commit.find('stat')
# Debug-info
if debug:
logger.debug('Getting the churn from commit: %s', xml_commit.get('revision'))
logger.debug('Stat-content: \n%s', etree.tostring(xml_stat))
if xml_stat.text is None or xml_stat.text.strip() == '':
#error_msg = 'Error while running churn-info-in-commit. '+
# 'Commit-content:\n%s.'%etree.tostring(xml_commit, pretty_print=True)
#logger.debug(error_msg)
#raise Exception(error_msg)
logger.warn('Commit %s has an empty stat-tag.', xml_commit.get('revision') )
return dict_to_class({'num_files':0,
'insertions':0,
'deletions': 0,
'churn': 0})
stat_data = xml_stat.text.strip()
summary_line = stat_data.splitlines()[-1] # which is the last-line
# Debug-info
if debug:
logger.debug('Summary-line: %s', summary_line)
# Get the num-files and churn
summary_as_list = summary_line.split(',')
if len(summary_as_list) == 3:
raw_num_files, raw_insertions, raw_deletions = summary_as_list
elif len(summary_as_list) == 2:
raw_num_files, raw_ins_or_dels = summary_as_list
if '+' in raw_ins_or_dels:
raw_insertions = raw_ins_or_dels
raw_deletions = ' 0 deletions(-)'
else:
raw_insertions = ' 0 insertions(+)'
raw_deletions = raw_ins_or_dels
else:
error_msg = "Error while getting the churn in commit:\n%s"%etree.tostring(xml_commit)
logger.debug(error_msg)
raise Exception(error_msg)
num_files = raw_num_files.strip().split()[0]
insertions = raw_insertions.strip().split()[0]
deletions = raw_deletions.strip().split()[0]
num_files = int(num_files)
insertions = int(insertions)
deletions = int(deletions)
churn = insertions + deletions
# Debug-info
if debug:
logger.debug('files: %s - inserts: %s - deletes: %s - churn: %s',
num_files, insertions, deletions, churn)
# Return as an object
return dict_to_class({'num_files':num_files,
'insertions':insertions,
'deletions': deletions,
'churn': churn})
def get_churn_info_commits_per_bug(xml_root):
logger.info('Getting the churn of the commits per bug')
hash_bugs = dict()
for xml_commit in xml_root:
xml_identified_bugs = xml_commit.find('identified_bugs')
churn_info = churn_info_in_commit(xml_commit, debug=False)
if churn_info.num_files == 0:
logger.warn('Skipping this commit')
continue
for xml_bug in xml_identified_bugs:
bug_id = xml_bug.get('bug_id')
clazz = xml_bug.get('clazz')
if clazz == 'none':
continue
if bug_id not in hash_bugs:
bug = {'bug_id': bug_id, 'clazz': clazz, 'num_commits': 0, 'num_files': 0, 'churn': 0}
bug_obj = dict_to_class(bug)
hash_bugs[bug_id] = bug_obj
bug_obj = hash_bugs[bug_id]
bug_obj.num_commits += 1
bug_obj.num_files += churn_info.num_files
bug_obj.churn += churn_info.churn
# Save it as a csv
list_bugs = list()
for bug_obj in hash_bugs.values():
list_bugs.append([bug_obj.bug_id, bug_obj.clazz, bug_obj.churn,
bug_obj.num_files, bug_obj.num_commits])
list_bugs = sorted(list_bugs, key=operator.itemgetter(2), reverse=True)
header = ['bug_id', 'clazz', 'churn', 'num_files', 'num_commits']
if len(list_bugs) == 0 :
list_bugs = [['--', '0', -1, -1, -1]]
bugs_churn_as_array = tabular2array(list_bugs, header)
return bugs_churn_as_array
def main(args):
"""
Plot job execution times.
"""
with open(args.fconfig, 'rb') as fp:
args_fconfig = utils.dict_to_class(json.load(fp))
utils.plot(args_fconfig)
return None
def main(args):
"""
Plot job execution times.
"""
with open(args.fconfig, 'rb') as fp:
args_fconfig = utils.dict_to_class(json.load(fp))
utils.plot(args_fconfig)
return None