[-] Remove commented code

python/commitCollector.py

@@ -31,57 +31,10 @@ def getCommitFromRepo(f: PathLike, gitrepo: str, branch: str):
     shellCallTemplate(f"git -C {f} log --no-merges --pretty=format:'{form}' > {file}", enc='latin1')
 
     # Collect commits
-    commits = json.loads(f'[{Path(file).read_text()}]')
+    content = Path(file).read_text().replace("\n", ",")
+    commits = json.loads(f'[{content}]')
 
     # Convert to DataFrame
     ds = pd.DataFrame.from_dict(commits)
     ds['commitDate'] = pd.to_datetime(ds['commitDate'])
     return ds
-
-
-def caseCollect(subject):
-    if not os.path.exists(COMMIT_FOLDER):
-        os.mkdir(COMMIT_FOLDER)
-    if not os.path.exists(COMMIT_DFS):
-        os.mkdir(COMMIT_DFS)
-
-    subjects = pd.read_csv(join(DATA_PATH, 'subjects.csv'))
-    if subject == 'ALL':
-        tuples = subjects[['Repo', 'Branch']].values.tolist()
-    else:
-        # repos = subjects.query("Subject == '{0}'".format(subject)).Repo.tolist()
-        tuples = subjects.query("Subject == '{0}'".format(subject))[
-            ['Repo', 'Branch']].values.tolist()
-
-    for t in tuples:
-        repo, branch = t
-        logging.info(repo)
-        getCommitFromRepo(join(REPO_PATH, repo), join(COMMIT_FOLDER, repo), branch)
-
-    if subject == 'ALL':
-        commits = listdir(COMMIT_FOLDER)
-    else:
-        commits = [i for i in listdir(COMMIT_FOLDER) if i.startswith(repo)]
-
-    for commit in commits:
-        logging.info(commit)
-        rDF = makeDF(join(COMMIT_FOLDER, commit))
-        repoName = commit.split('.')[0]
-        save_zipped_pickle(rDF, join(COMMIT_DFS, repoName + ".pickle"))
-        # p.dump(rDF, open(join(COMMIT_DFS, repoName + ".pickle"), "wb"))
-
-
-def caseClone(subject):
-    if not os.path.exists(REPO_PATH):
-        os.mkdir(REPO_PATH)
-
-    subjects = pd.read_csv(join(DATA_PATH, 'subjects.csv'))
-    if subject == 'ALL':
-        gitrepos = subjects.GitRepo.tolist()
-    else:
-        gitrepos = subjects.query("Subject == '{0}'".format(subject)).GitRepo.tolist()
-    os.getcwd()
-    os.chdir(REPO_PATH)
-    for gitrepo in gitrepos:
-        cmd = 'git clone ' + gitrepo
-        out = shellCallTemplate(cmd)

python/javaDS.py

@@ -89,71 +89,3 @@ def createDS(project_list: str = PROJECT_LIST):
         print(len(commits))
         # for s in a.commit.values.tolist():
         parallelRun(prepareFiles, commits[['commit', 'files']].values.tolist(), repo)
-
-    # # if job == 'clone':
-    # for repo,src in subjects[['Repo','GitRepo']].values.tolist():
-    #     if(pjList != ['ALL']):
-    #         if repo in pjList:
-    #             print(repo)
-    #             cmd = 'git -C ' + DATASET_PATH + ' clone ' + src
-    #             shellCallTemplate(cmd)
-    #             logging.info(repo)
-
-    # caseClone(subject)
-
-    # caseCollect(subject)
-    # # elif job == 'fix':
-    # from filterBugFixingCommits import caseFix
-    #
-    # caseFix(subject)
-    # #
-    # # # elif job =='brDownload':
-    # from bugReportDownloader import caseBRDownload
-    #
-    # caseBRDownload(subject)
-    # # # elif job =='brParser':
-    # from bugReportParser import step1
-    #
-    # step1(subject)
-    #
-    # # elif job =='dataset':
-    #
-    # if not isfile(join(DATA_PATH, 'singleBR.pickle')):
-    #
-    #     brs = load_zipped_pickle(join(DATA_PATH, subject + "bugReportsComplete.pickle"))
-    #
-    #     subjects = pd.read_csv(join(DATA_PATH, 'subjects.csv'))
-    #
-    #
-    #     def getCommit(x):
-    #         bid, project = x
-    #
-    #         subjects = pd.read_csv(join(DATA_PATH, 'subjects.csv'))
-    #         repo = subjects.query("Subject == '{0}'".format(project)).Repo.tolist()[0]
-    #         commits = load_zipped_pickle(join(DATA_PATH, COMMIT_DFS, repo + '.pickle'))
-    #         correspondingCommit = commits.query("fix =='{0}'".format(bid)).commit.tolist()
-    #         if len(correspondingCommit) == 1:
-    #             return [bid, correspondingCommit[0], project]
-    #         else:
-    #             return None
-    #             print('error')
-    #
-    #
-    #     wl = brs[['bid', 'project']].values.tolist()
-    #     dataL = parallelRunMerge(getCommit, wl)
-    #
-    #     commits = pd.DataFrame(
-    #         columns=['bid', 'commit', 'project'],
-    #         data=list(filter(None.__ne__, dataL)))
-    #
-    #     save_zipped_pickle(commits, join(DATA_PATH, 'singleBR.pickle'))
-    # else:
-    #     commits = load_zipped_pickle(join(DATA_PATH, 'singleBR.pickle'))
-    #     subjects = pd.read_csv(join(DATA_PATH, 'subjects.csv'))
-    # logging.info('done matching commits')
-    # commits['repo'] = commits.project.apply(lambda x: subjects.query("Subject == '{0}'".format(x)).Repo.tolist()[0])
-    #
-    # workList = commits[['commit', 'repo']].values.tolist()
-    # from dataset import prepareFiles
-    #
-    # parallelRun(prepareFiles, workList)