def test_analyze_repository(self):
"""Test whether lizard returns the expected fields data for repository"""
lizard = Lizard()
kwargs = {
'repository_path': self.tmp_data_path,
'repository_level': True,
'files_affected': [],
'details': False
}
result = lizard.analyze(**kwargs)
result = result[0]
self.assertIn('ccn', result)
self.assertTrue(type(result['ccn']), int)
self.assertIn('num_funs', result)
self.assertTrue(type(result['num_funs']), int)
self.assertIn('loc', result)
self.assertTrue(type(result['loc']), int)
self.assertIn('tokens', result)
self.assertTrue(type(result['tokens']), int)
self.assertIn('in_commit', result)
self.assertTrue(type(result['in_commit']), bool)
self.assertIn('blanks', result)
self.assertTrue(type(result['blanks']), int)
self.assertIn('comments', result)
self.assertTrue(type(result['comments']), int)
def test_analyze_no_details(self):
"""Test whether lizard returns the expected fields data"""
lizard = Lizard()
kwargs = {
'file_path': os.path.join(self.tmp_data_path, ANALYZER_TEST_FILE),
'details': False
}
result = lizard.analyze(**kwargs)
self.assertNotIn('funs', result)
self.assertIn('ccn', result)
self.assertTrue(type(result['ccn']), int)
self.assertIn('avg_ccn', result)
self.assertTrue(type(result['avg_ccn']), float)
self.assertIn('avg_loc', result)
self.assertTrue(type(result['avg_loc']), float)
self.assertIn('avg_tokens', result)
self.assertTrue(type(result['avg_tokens']), float)
self.assertIn('num_funs', result)
self.assertTrue(type(result['num_funs']), int)
self.assertIn('loc', result)
self.assertTrue(type(result['loc']), int)
self.assertIn('tokens', result)
self.assertTrue(type(result['tokens']), int)
def __init__(self, details=False, kind=LIZARD_FILE):
self.details = details
self.kind = kind
if self.kind == LIZARD_FILE:
self.cloc = Cloc()
self.lizard = Lizard()
else:
self.scc = SCC()
class RepositoryAnalyzer:
"""Class to analyse the content of a repository"""
def __init__(self, details=False):
self.details = details
self.lizard = Lizard()
def analyze(self, repository_path, files_affected):
"""Analyze the content of a repository using CLOC and Lizard.
:param repository_path: repository path
:returns a list containing the results of the analysis
[ {
'loc': ..,
'ccn': ..,
'tokens': ..,
'num_funs': ..,
'file_path': ..,
'in_commit': ..,
'blanks': ..,
'comments': ..,
},
...
]
"""
kwargs = {
'repository_path': repository_path,
'repository_level': True,
'files_affected': files_affected,
'details': self.details
}
lizard_analysis = self.lizard.analyze(**kwargs)
return lizard_analysis
def __init__(self, details=False, kind=LIZARD_REPOSITORY):
self.details = details
self.kind = kind
if kind == LIZARD_REPOSITORY:
self.analyzer = Lizard()
else:
self.analyzer = SCC()
def test_analyze_details(self):
"""Test whether lizard returns the expected fields data"""
lizard = Lizard()
kwargs = {
'file_path': os.path.join(self.tmp_data_path, ANALYZER_TEST_FILE),
'details': True
}
result = lizard.analyze(**kwargs)
self.assertIn('ccn', result)
self.assertTrue(type(result['ccn']), int)
self.assertIn('avg_ccn', result)
self.assertTrue(type(result['avg_ccn']), float)
self.assertIn('avg_loc', result)
self.assertTrue(type(result['avg_loc']), float)
self.assertIn('avg_tokens', result)
self.assertTrue(type(result['avg_tokens']), float)
self.assertIn('num_funs', result)
self.assertTrue(type(result['num_funs']), int)
self.assertIn('loc', result)
self.assertTrue(type(result['loc']), int)
self.assertIn('tokens', result)
self.assertTrue(type(result['tokens']), int)
self.assertIn('funs', result)
self.assertTrue(type(result['funs']), dict)
for fd in result['funs']:
self.assertIn('ccn', fd)
self.assertTrue(type(fd['ccn']), int)
self.assertIn('tokens', fd)
self.assertTrue(type(fd['tokens']), int)
self.assertIn('loc', fd)
self.assertTrue(type(fd['loc']), int)
self.assertIn('lines', fd)
self.assertTrue(type(fd['lines']), int)
self.assertIn('name', fd)
self.assertTrue(type(fd['name']), str)
self.assertIn('args', fd)
self.assertTrue(type(fd['args']), int)
self.assertIn('start', fd)
self.assertTrue(type(fd['start']), int)
self.assertIn('end', fd)
self.assertTrue(type(fd['end']), int)
class FileAnalyzer:
"""Class to analyse the content of files"""
ALLOWED_EXTENSIONS = ['java', 'py', 'php', 'scala', 'js', 'rb', 'cs', 'cpp', 'c', 'lua', 'go', 'swift']
FORBIDDEN_EXTENSIONS = ['tar', 'bz2', "gz", "lz", "apk", "tbz2",
"lzma", "tlz", "war", "xar", "zip", "zipx"]
def __init__(self, details=False, kind=LIZARD_FILE):
self.details = details
self.kind = kind
if self.kind == LIZARD_FILE:
self.cloc = Cloc()
self.lizard = Lizard()
else:
self.scc = SCC()
def analyze(self, file_path):
"""Analyze the content of a file using CLOC, Lizard and SCC
:param file_path: file path
:returns a dict containing the results of the analysis, like the one below
{
'blanks': ..,
'comments': ..,
'loc': ..,
'ccn': ..,
'avg_ccn': ..,
'avg_loc': ..,
'avg_tokens': ..,
'num_funs': ..,
'tokens': ..,
'funs': [..]
}
"""
kwargs = {'file_path': file_path}
if self.kind == LIZARD_FILE:
cloc_analysis = self.cloc.analyze(**kwargs)
if GraalRepository.extension(file_path) not in self.ALLOWED_EXTENSIONS:
return cloc_analysis
kwargs['details'] = self.details
file_analysis = self.lizard.analyze(**kwargs)
# the LOC returned by CLOC is replaced by the one obtained with Lizard
# for consistency purposes
file_analysis['blanks'] = cloc_analysis['blanks']
file_analysis['comments'] = cloc_analysis['comments']
else:
file_analysis = self.scc.analyze(**kwargs)
return file_analysis
