def load_parameters(json_parameters): parameters = Parameters() parameters.clustering_threshold = json_parameters['clustering_threshold'] parameters.size_threshold = json_parameters['size_threshold'] parameters.distance_threshold = json_parameters['distance_threshold'] parameters.hashing_depth = json_parameters['hashing_depth'] parameters.clusterize_using_dcup = json_parameters['clusterize_using_dcup'] parameters.clusterize_using_hash = json_parameters['clusterize_using_hash'] parameters.report_unifiers = json_parameters['report_unifiers'] parameters.force = json_parameters['force'] parameters.use_diff = json_parameters['use_diff']
def scan(language, file_manifest, source_file_names):
# Determine the files to scan. If no files are given, use a default manifest.
if len(source_file_names) == 0 and file_manifest is None:
file_manifest = manifest.default_manifest(language)
source_file_names = set(source_file_names)
if file_manifest is not None:
source_file_names.update(set(manifest.contents(file_manifest)))
supplier = ast_suppliers.abstract_syntax_tree_suppliers[language]
# TODO: Configuration files!
parameters = Parameters()
parameters.distance_threshold = supplier.distance_threshold
parameters.size_threshold = supplier.size_threshold
source_files = []
report = Report(parameters)
def parse_file(file_name):
try:
logging.info('Parsing ' + file_name + '...')
source_file = supplier(file_name, parameters)
source_file.getTree().propagateCoveredLineNumbers()
source_file.getTree().propagateHeight()
source_files.append(source_file)
report.addFileName(file_name)
logging.info('done')
except:
logging.warn('Can\'t parse "%s" \n: ' % (file_name,) + traceback.format_exc())
for file_name in source_file_names:
parse_file(file_name)
duplicates = clone_detection_algorithm.findDuplicateCode(source_files, report)
n = 1
for duplicate in duplicates:
distance = duplicate.calcDistance()
summary = CloneSummary(
"Clone #"+str(n),
[ # TODO: This is a mess! Most of this info should be assembled on the fly and in member functions.
Snippet(
duplicate[i].getSourceFile()._file_name,
duplicate[i].getCoveredLineNumbers(),
'\n'.join([line for line in duplicate[i].getSourceLines()])
) for i in [0, 1]], distance)
report.addClone(summary)
n += 1
report.sortByCloneSize()
save_report(".orphanblack", report)
