def _code_jam():
"""
Run coverage for codejam
:return:
"""
codejam_format = r'Y\d+rUtils\d+P\d+'
total_coverage_percentages = []
reports = []
for project_name in sorted(cache.list_dir(properties.META_RESULTS_FOLDER, is_absolute=False)):
if re.match(codejam_format, project_name):
LOGGER.info("For project %s" % project_name)
project_path = "%s/%s" % (properties.META_RESULTS_FOLDER, project_name)
coverage_percentages = []
for user in cache.list_dir(project_path, is_absolute=False):
project_folder = os.path.join(project_name, user)
metrics = coverage(project_folder)
coverage_percentages.append(metrics['code_coverage'])
reports.append("\n### Project: %s" % project_name)
reports.append(stat.Stat(coverage_percentages).report())
total_coverage_percentages += coverage_percentages
LOGGER.info("Aggregating ...")
reports.append("\n### Total Coverage")
reports.append(stat.Stat(total_coverage_percentages).report())
report = "\n".join(reports)
cache.write_file(os.path.join(properties.RESULTS_FOLDER, "codejam", "coverage.md"), report)
return report
def save_only_mixed_clusters(dataset, mixed_file_base_name):
"""
Save only mixed functions
:param dataset: Name of dataset
:param mixed_file_base_name: Type of language eg. java_python
:return:
"""
clusters_base_folder = os.path.join(lib.get_clusters_folder(dataset), "cluster_testing")
for folder in sorted(cache.list_dir(clusters_base_folder, is_absolute=False)):
LOGGER.info("Processing '%s' ..." % folder)
folder_path = os.path.join(clusters_base_folder, folder)
base_clusters_file = os.path.join(folder_path, "%s.pkl" % mixed_file_base_name)
base_clusters = cache.load_pickle(base_clusters_file)
mixed_clusters = {}
for label, functions in base_clusters.items():
if label == -1 or len(functions) == 1: continue
sources = set()
for func in functions:
sources.add(func.source)
if len(sources) > 1:
mixed_clusters[label] = functions
LOGGER.info("For folder = %s, # of mixed clusters = %d" % (folder, len(mixed_clusters)))
file_path = os.path.join(folder_path, "only_mixed.txt")
pkl_path = os.path.join(folder_path, "only_mixed.pkl")
file_contents = []
for label, functions in mixed_clusters.items():
file_contents.append("\n\n****** Cluster %d ******" % label)
for func in functions:
file_contents.append(func.body)
cache.write_file(file_path, "\n".join(file_contents))
cache.save_pickle(pkl_path, mixed_clusters)
def save_only_target_functions(dataset, mixed_file_base_name, target_language):
"""
Save only java functions from a mixture of java and python clusters
:param dataset: Name of dataset
:param mixed_file_base_name: Type of language eg. java_python
:param target_language: Target Language
:return:
"""
clusters_base_folder = os.path.join(lib.get_clusters_folder(dataset),
"cluster_testing")
for folder in sorted(
cache.list_dir(clusters_base_folder, is_absolute=False)):
LOGGER.info("Processing '%s' ..." % folder)
folder_path = os.path.join(clusters_base_folder, folder)
cache.mkdir(folder_path)
base_clusters_file = os.path.join(folder_path,
"%s.pkl" % mixed_file_base_name)
base_clusters = cache.load_pickle(base_clusters_file)
target_clusters = {}
for label, functions in base_clusters.items():
if label == -1 or len(functions) == 1: continue
contains_target = False
contains_other = False
for func in functions:
if func.source == target_language:
contains_target = True
else:
contains_other = True
if contains_target and not contains_other:
target_clusters[label] = functions
LOGGER.info("For folder = %s, # of '%s' clusters = %d" %
(folder, target_language, len(target_clusters)))
file_path = os.path.join(folder_path, "only_%s.txt" % target_language)
pkl_path = os.path.join(folder_path, "only_%s.pkl" % target_language)
file_contents = []
for label, functions in target_clusters.items():
file_contents.append("\n\n****** Cluster %d ******" % label)
for func in functions:
file_contents.append(func.body)
cache.write_file(file_path, "\n".join(file_contents))
cache.save_pickle(pkl_path, target_clusters)