add scripts for apisan

icy17 · icy17 · commit 6e50f98c43ce · 2023-08-04T08:11:16.000+04:00
diff --git a/apisan/auto_apisan.py b/apisan/auto_apisan.py
@@ -0,0 +1,117 @@
+import os
+import sys
+import subprocess
+import json
+import time
+
+# return a dict list. dict: {name: file_name, path: full_path}
+def get_all_file_path(in_dir):
+    res = []
+    out_list = list()
+    for path in os.listdir(in_dir):
+        # print(in_dir)
+    # check if current path is a file
+        orig_path = os.path.join(in_dir, path)
+        # print(orig_path)
+        # if not os.path.isfile(orig_path):
+            # print('in')
+        out_dict = dict()
+        out_dict['name'] = path
+        out_dict['path'] = orig_path
+        res.append(out_dict)
+    return res
+
+def read_json(in_path):
+    # in_list = list()
+    out_list = list()
+    with open(in_path, 'r') as f:
+        tmp_list = f.readlines()
+    for line in tmp_list:
+        line = line.strip('\n')
+        line_json = json.loads(line)
+        out_list.append(line_json)
+    return out_list
+
+def get_repo_name(link):
+    link = link.replace('.git', '')
+    name = link.strip('/').split('/')[-1]
+    return name
+
+if __name__ == '__main__':
+    if len(sys.argv) != 3:
+        print("wrong input")
+        print('Usage: python3 ./auto_apisan.py <in_software_dir> <out_dir>')
+        exit(1)
+    
+    # TODO check if more?
+    apisan_cmd = ['apisan check --checker=rvchk', 'apisan check --checker=cpair', 'apisan check --checker=args', 'apisan check --checker=intovfl', 'apisan check --checker=cond', 'apisan check --checker=fsb']
+    
+    in_dir = sys.argv[1]
+    out_dir = sys.argv[2]
+    out_log = out_dir + '/apisan-log'
+    faild_log = out_dir + '/apisan-faild-log'
+    success_log = out_dir + '/apisan-success-log'
+    software_path = in_dir + '/apisan-in'
+    software_list = list()
+
+    if not os.path.exists(out_dir):
+        os.mkdir(out_dir)
+    
+    with open(software_path, 'r') as f:
+        tmp = f.read().strip('\n')
+        software_list = tmp.split('\n')
+    for software in software_list:
+        out_dict = dict()
+        out_dict['repo'] = software
+        out_dict['status'] = 'begin'
+        out_dict['faild_stage'] = ''
+        software_dir = in_dir + '/' + software
+        out_software_dir = out_dir + '/' + software
+        if not os.path.exists(out_software_dir):
+            os.mkdir(out_software_dir)
+        
+        os.chdir(software_dir)
+        with open(out_log, 'a') as f:
+            f.write('Parse' + software + '\n')
+        for cmd in apisan_cmd:
+            start = time.time()
+            check_name = cmd.strip(' ').split('=')[-1]
+            out_path = out_software_dir + '/' + check_name
+            all_cmd = cmd + ' > ' + out_path
+            out_dict['status'] = all_cmd
+            with open(out_log, 'a') as f:
+                f.write('Exec' + all_cmd + '\n')
+            return_info = subprocess.Popen(all_cmd, shell=True, stderr=subprocess.PIPE)
+            try:
+                out, err = return_info.communicate(timeout=18000)
+            except:
+
+                with open(faild_log, 'a') as f:
+                    out_dict['faild_stage'] = 'timeout'
+                    f.write(json.dumps(out_dict))
+                    f.write('\n')
+                with open(out_log, 'a') as f:
+                    f.write('Cost too much time. Break!\n\n')
+                # os.remove(ql_path)
+                continue
+            end = time.time()
+            info = err.decode("utf-8","ignore")
+            if return_info.returncode != 0:
+                with open(faild_log, 'a') as f:
+                    out_dict['faild_stage'] = 'run wrong'
+                    f.write(json.dumps(out_dict))
+                    f.write('\n')
+                with open(out_log, 'a') as f:
+                    f.write('Error: ' + info + '\n\n')
+                    continue
+            
+            else:
+                out_dict['status'] = 'finish'
+                with open(success_log, 'a') as f:
+                    f.write(json.dumps(out_dict))
+                    f.write('\n')
+                with open(out_log, 'a') as f:
+                    f.write('Success! Time: ' + str(end-start) + 's\n\n')
+                
+
+    
diff --git a/auto_clone.py b/auto_clone.py
@@ -0,0 +1,64 @@
+import os
+import sys
+import json
+
+def read_json(in_path):
+    # in_list = list()
+    out_list = list()
+    with open(in_path, 'r') as f:
+        tmp_list = f.readlines()
+    for line in tmp_list:
+        line = line.strip('\n')
+        line_json = json.loads(line)
+        out_list.append(line_json)
+    return out_list
+
+def get_repo_name(link):
+    link = link.replace('.git', '')
+    name = link.strip('/').split('/')[-1]
+    return name
+
+if __name__ == '__main__':
+    if len(sys.argv) != 3:
+        print("wrong input")
+        print('Usage: python3 ./auto_clone.py <https_link_path> <out_dir>')
+        exit(1)
+    
+    in_path = sys.argv[1]
+    out_dir = sys.argv[2]
+    out_log = out_dir + '/clone-log'
+    faild_log = out_dir + '/clong-faild-log'
+    
+    in_list = read_json(in_path)
+    os.chdir(out_dir)
+    for item in in_list: 
+        os.chdir(out_dir)
+        repo_link = item['github link']
+        commit_id = item['commit id']
+        repo_name = get_repo_name(repo_link)
+        cmd = 'git clone --recursive ' + repo_link
+        with open(out_log, 'a') as f:
+            f.write('Exec: ' + cmd + '\n')
+        re = os.system(cmd)
+        if not re:
+            with open(out_log, 'a') as f:
+                f.write('Success\n')
+        else:
+            item['faild_stage'] = 'clone'
+            with open(faild_log, 'a') as f:
+                f.write(item + '\n')
+        
+        os.chdir(out_dir + '/' + repo_name)
+        cmd = 'git checkout ' + str(commit_id)
+        with open(out_log, 'a') as f:
+            f.write('Exec: ' + cmd + '\n')
+        re = os.system(cmd)
+        if not re:
+            with open(out_log, 'a') as f:
+                f.write('Success\n')
+        else:
+            item['faild_stage'] = 'checkout'
+            with open(faild_log, 'a') as f:
+                f.write(item + '\n')
+        
+        
diff --git a/parse_csv.py b/parse_csv.py
@@ -0,0 +1,54 @@
+import csv
+import sys
+import json
+# from  openpyxl import  Workbook 
+# from openpyxl  import load_workbook
+# import openpyxl
+
+def get_data_excel(in_path):
+    wb= openpyxl.load_workbook(in_path)
+# 第二步选取表单
+    sheet = wb.active
+# 按行获取数据转换成列表
+    rows_data = list(sheet.rows)
+# 获取表单的表头信息(第一行)，也就是列表的第一个元素
+    titles = [title.value for title in rows_data.pop(0)]
+    # print(titles)
+
+# 整个表格最终转换出来的字典数据列表
+    all_row_dict = []
+    # 遍历出除了第一行的其他行
+    for a_row in rows_data:
+        the_row_data = [cell.value for cell in a_row]
+        # 将表头和该条数据内容，打包成一个字典
+        row_dict = dict(zip(titles, the_row_data))
+        # print(row_dict)
+        all_row_dict.append(row_dict)
+    return all_row_dict
+
+def get_data_csv(in_path):
+    out_list = list()
+    with open(in_path, 'r') as file_csv:
+        # fieldnames = ("field1","field2")
+        reader = csv.DictReader(file_csv)
+        for info in reader:
+            # print(info)
+            out_list.append(info)
+
+    return out_list
+
+if __name__ == '__main__':
+    if len(sys.argv) != 2:
+        print('python3 ./parse_csv.py in_path')
+        exit(1)
+    in_path = sys.argv[1]
+    out_path = in_path.split('.')[0]
+    # in_path = '/home/jhliu/data/GT-no-keyword.csv'
+    # out_path = '/home/jhliu//data/GT-no-keyword'
+    json_list = get_data_csv(in_path)
+    # print(json_list)
+    for info in json_list:
+        # print(info)
+        with open(out_path, 'a') as f:
+            f.write(json.dumps(info))
+            f.write('\n')
