def static_analysis_by_folder(folders: list, date: str) -> dict:
"""return the statistic analysis result for target folders in one day
Arguments:
folders {str} -- the target folders to be analysed
date {str}
Returns:
dict -- the analysis result
"""
dataFile1 = 'files_detail_' + date + '.csv'
dataFile2 = 'methods_detail_' + date + '.csv'
total_complex_ave = 0
total_complex_max = 0
total_lines = 0
total_files = 0
total_range = {'1~10': 0, '11~20': 0, '21~50': 0, '>50': 0}
for idx in range(len(folders)):
folders[idx] = folders[idx].replace('/', '\\')
with open(dataFile1, 'r') as fin:
with open(dataFile2, 'r') as fin2:
with open('config.json', 'r') as config_file:
config = json.loads(config_file.read())
data = csv.DictReader(fin)
data2 = csv.DictReader(fin2)
for i in data:
flag = False
for folder in folders:
if i['File Name'].startswith(folder):
flag = True
break
flag = flag and is_keep(
'Source/media/media_driver/' + i['File Name'], config)
if flag:
total_files += 1
lines_i = int(i['Lines'])
total_lines += lines_i
complex_ave_i = float(i['Average Complexity*'])
complex_max_i = int(i['Maximum Complexity*'])
total_complex_ave += complex_ave_i
if complex_max_i > total_complex_max:
total_complex_max = complex_max_i
for i in data2:
flag = False
for folder in folders:
if i['File Name'].startswith(folder):
flag = True
break
flag = flag and is_keep(
'Source/media/media_driver/' + i['File Name'], config)
if flag:
complex_i = int(i['Complexity'])
if complex_i > 50:
total_range['>50'] += 1
elif complex_i > 20:
total_range['21~50'] += 1
elif complex_i > 10:
total_range['11~20'] += 1
else:
total_range['1~10'] += 1
result = {
'LOC': total_lines,
'Average Complexity': round(total_complex_ave / total_files, 2),
'Max Complexity': total_complex_max,
'1~10': total_range['1~10'],
'11~20': total_range['11~20'],
'21~50': total_range['21~50'],
'>50': total_range['>50']
}
return result
def analyze_code_churn_by_period(self, period: str, date_range: list,
category_list: list, classify_func,
tmp_folders: list) -> dict:
"""return code churn analysis by period, in date_range, classfied by category_list
Args:
period (str): 'daily','weekly','monthly'
date_range (list): [start,end] yyyy-MM-DD, yyyy-WW, yyyy-MM for daily,weekly,monthly respectively
category_list (list): all the components in the category
classify_func ([function]): the function to classify each component
Returns:
dict: {component1:{date:{add,delete,files},...},
component2:{date:{add,delete,files},...},...}
"""
after, before = get_start_end(period, date_range)
total_file_set = FileSet() # record all files latest name
dict_fileset = {} # {date:set(file1,file2),...}
d = {} # return result
config = self.get_tmp_config(tmp_folders)
is_classify = True
is_subfolder = False
if classify_func == 'subfolder':
is_subfolder = True
else:
if len(category_list) == 0:
category_list = ['All']
is_classify = False
for category in category_list:
d[category] = {}
commits = self.commit.find({
"commitDate": {
"$gte": after
},
}, {
'_id': False,
'files': True,
'regressions': True,
'commitDate': True
}).sort('commitDate', DESCENDING)
for commit in commits:
commit_date = commit['commitDate']
files = commit['files']
if commit_date > before:
for f in files:
filename = f['filename']
self.update_fileset(total_file_set, filename)
continue
commit_comps = set()
date_param = get_date_param(period, commit_date)
if date_param not in dict_fileset:
dict_fileset[date_param] = set()
if not is_subfolder:
for category in category_list:
if date_param not in d[category]:
d[category][date_param] = {
'loc': 0,
'files': 0,
'commit': 0,
'regression': 0
}
for f in files:
filename = f['filename']
add = f['add']
delete = f['delete']
filename = self.update_fileset(total_file_set, filename)
# filename not satisfy config whitelist or not changed
if not is_keep(filename, config) or (add == 0 and delete == 0):
continue
is_add_regression = 0
if is_subfolder:
comp = get_folder(filename)
if comp not in d:
d[comp] = {}
if date_param not in d[comp]:
d[comp][date_param] = {
'loc': 0,
'files': 0,
'commit': 0,
'regression': 0
}
elif is_classify:
comp = classify_func(filename)
else:
comp = 'All'
if filename in dict_fileset[date_param]:
is_add_file = 0
else:
dict_fileset[date_param].add(filename)
is_add_file = 1
if comp in commit_comps:
is_add_comp = 0
else:
commit_comps.add(comp)
is_add_comp = 1
if 'regressions' in commit:
is_add_regression = 1
d[comp][date_param]['loc'] += add + delete
d[comp][date_param]['files'] += is_add_file
d[comp][date_param]['commit'] += is_add_comp
d[comp][date_param]['regression'] += is_add_regression
return d
def analyze_group_total_code_churn(self, date_range: list,
groups: list) -> dict:
"""return group code churn analysis in date_range, classfied by category_list from give groups
Args:
date_range (list): [dayStart, dayEnd] yyyy-MM-DD inclusive
groups (list): nested arrays indicating groups [[folder1,folder2],[folder3],[folder4,folder5]...]
Returns:
dict: {group1:count1, group1:count2, ...}
"""
after, before = date_range
total_file_set = FileSet() # record all files latest name
file_sets = []
d = {}
configs = []
for group in groups:
configs.append(self.get_tmp_config(group))
file_sets.append(set())
for index in range(len(groups)):
d['Group' + str(index + 1)] = {
'loc': 0,
'files': 0,
'commit': 0,
'regression': 0
}
commits = self.commit.find({
"commitDate": {
"$gte": after
},
}, {
'_id': False,
'files': True,
'regressions': True,
'commitDate': True
}).sort('commitDate', DESCENDING)
for commit in commits:
commit_date = commit['commitDate']
files = commit['files']
if commit_date > before:
for f in files:
filename = f['filename']
self.update_fileset(total_file_set, filename)
continue
commit_comps = set() # indicates all the compoents in this commit
for f in files:
filename = f['filename']
add = f['add']
delete = f['delete']
filename = self.update_fileset(total_file_set, filename)
if add == 0 and delete == 0: # this file is not changed at all
continue
for (index, config) in enumerate(configs):
file_set = file_sets[index]
if is_keep(filename, config):
is_add_regression = 0
comp = 'Group' + str(index + 1)
if filename in file_set:
is_add_file = 0
else:
file_set.add(filename)
is_add_file = 1
if comp in commit_comps:
is_add_comp = 0
else:
commit_comps.add(comp)
is_add_comp = 1
if 'regressions' in commit:
is_add_regression = 1
d[comp]['loc'] += add + delete
d[comp]['files'] += is_add_file
d[comp]['commit'] += is_add_comp
d[comp]['regression'] += is_add_regression
return d
def analyze_total_code_churn(self, date_range: list, category_list: list,
classify_func, tmp_folders: list) -> dict:
"""return code churn analysis in date_range, classfied by category_list
Args:
commits (list): output of `logfile_to_list`
date_range (list): [dayStart, dayEnd] yyyy-MM-DD inclusive
category_list (list): all the components in the category
classify_func ([type]): the function to classify each component
Returns:
dict: {component1:count1, component2:count2, ...}
"""
after, before = date_range
total_file_set = FileSet() # record all files latest name
file_set = set() # record files satisfy the result
d = {}
config = self.get_tmp_config(tmp_folders)
for category in category_list:
d[category] = {'loc': 0, 'files': 0, 'commit': 0, 'regression': 0}
commits = self.commit.find({
"commitDate": {
"$gte": after
},
}, {
'_id': False,
'files': True,
'commitDate': True,
'regressions': True
}).sort('commitDate', DESCENDING)
for commit in commits:
commit_date = commit['commitDate']
files = commit['files']
if commit_date > before:
for f in files:
filename = f['filename']
self.update_fileset(total_file_set, filename)
continue
commit_comps = set() # indicates all the compoents in this commit
for f in files:
filename = f['filename']
add = f['add']
delete = f['delete']
filename = self.update_fileset(total_file_set, filename)
if not is_keep(filename, config) or (add == 0 and delete == 0):
continue
is_add_regression = 0
comp = classify_func(filename)
if filename in file_set:
is_add_file = 0
else:
file_set.add(filename)
is_add_file = 1
if comp in commit_comps:
is_add_comp = 0
else:
commit_comps.add(comp)
is_add_comp = 1
if 'regressions' in commit:
is_add_regression = 1
d[comp]['loc'] += add + delete
d[comp]['files'] += is_add_file
d[comp]['commit'] += is_add_comp
d[comp]['regression'] += is_add_regression
return d