def descript(query_decp, source_category, except_files=None,extend=False, pool_size=32):
"""
生成描述文件
~1分钟得出结果
:param query_decp: 描述文件矩阵
example line: xml_file_name, class_name, element_name
:param except_files: 排除文件关键词，接受字符串或字符串数组
:param pool_size: 并行池大小
:return: a tuple. 得到src app与 数据库每个app的总相似度，按照相似度降序排列. 用作 搜索 app
"""
query_decp = nlp_util.process_xsv(query_decp)
if extend :
src_dir = work_path.in_project('./model/data/description_extend_all')
else:
src_dir = work_path.in_project('./model/data/description')
print("PATH!!!! {}".format(src_dir))
logger = logging.getLogger("StreamLogger")
file_list = os.listdir(src_dir)
file_list = [os.path.join(src_dir, f) for f in file_list]
if except_files is not None:
tmp = []
rms = []
if type(except_files) == str:
for i in file_list:
if except_files not in i:
tmp.append(i)
else:
rms.append(i)
elif type(except_files) == list or type(except_files) == set:
except_files = set(except_files)
for i in file_list:
flag = False
for j in except_files:
if j in i:
flag = True
break
if not flag:
tmp.append(i)
else:
rms.append(i)
logger.debug(pp.pformat(rms))
file_list = tmp
logger.debug(pp.pformat(file_list))
scan_output = _scan_match(source_category, query_decp, file_list, match_name.ngram_compare, [1, 0.5, 0.5],
threshold=0.7,
pool_size=pool_size)
# 得到src app与 数据库每个app的总相似度，按照相似度降序排列。
# tuple(
# str "参考APP描述文件名",
# float "APP相似度",
# list "参考APP的组件相似度" [(请求app组件, 参考app组件，组件相似度)]
# )
logger.debug(pp.pformat(util.get_col(scan_output, [0, 1])))
return scan_output
def _single_scan_helper(arg):
index, file_path, sample_ui_list, comp_func, weight_list, threshold = arg
logger = logging.getLogger("StreamLogger")
logger.debug(file_path)
tmp_out = util.read_csv(file_path)
tmp_out = nlp_util.process_xsv(tmp_out)
if len(tmp_out) == 0:
logger.debug(f"EMPTY {file_path}")
score_distribution_list = []
else:
score_distribution_list = match_name.weight_compare_list(sample_ui_list, tmp_out, comp_func,
weight_list)
# score_distribution_list = util.get_col(score_distribution_list, 2)
score = match_name.similar_index(score_distribution_list, threshold, col_index=2, rate=True)
rt = (file_path, score, score_distribution_list)
logger.debug(f"ADD {index} {file_path}")
return rt