def delay(framework, projects, githubtoken):
print("Computing delay to update")
path_dos_repositorios = 'repositories'
measure = "delay"
output_write(framework, measure, measure, "framework,path,current_version,next_version,framework_release_date (YYYY-DD-MM),sample_update_date (YYYY-DD-MM) ,delay_in_days", True)
framework_release_data = buscar_dados_de_lancamento_de_versoes(framework, githubtoken)
configuration_file = define_arquivo_de_configuracao(framework)
samples = get_samples(projects)
for index, sample in enumerate(samples):
print_status_samples(index+1, len(samples))
sample_path = path_dos_repositorios + "/" + sample
paths_configuration_file = find_paths(configuration_file, sample_path)
repository = Repo(sample_path)
reversed_commits = get_commits(repository)
for path in paths_configuration_file:
current_version, reversed_commits = get_first_version(framework, path, repository, reversed_commits)
if current_version == {}:
continue
for commit in reversed_commits:
repository.git.checkout(commit, '-f')
next_version = buscar_versao_do_framework(framework, path)
if current_version != next_version and next_version != '' and current_version != '' and current_version != None and next_version != None:
sample_update_date = get_commit_date(commit)
framework_release_date = framework_release_data[next_version]
delay_in_days = calculate_delay(framework_release_date, sample_update_date)
output_write(framework, measure, measure, create_output(current_version, delay_in_days, framework, framework_release_date, next_version, path, sample_update_date), False)
current_version = next_version
repository.git.checkout('master', '-f')
def githubmetadata(framework, projects, githubtoken):
print("Computing github metadata")
measure = "githubmetadata"
output_write(framework, measure, measure, "framework,repository,forks,stargazers,watchers,openedIssues,closedIssues,commits,openedPullRequests,closedPullRequests,updatedAt,projects,lifetime,lifetime per commit", True)
g = Github(githubtoken)
samples = get_samples(projects)
for index, sample in enumerate(samples):
print_status_samples(index+1, len(samples))
repo = g.get_repo(sample)
output = create_output(framework, repo, sample)
output_write(framework, measure, measure, output, False)
def forksahead(framework, projects, githubtoken):
print("Computing forks ahead data")
g = Github(githubtoken)
output_write(framework, "forksahead", "forks_ahead_by_projects", "framework,path,number_of_forks,forks_ahead,ratio", True)
output_write(framework, "forksahead", "forks_ahead", "framework,path,number_of_forks,forks_ahead,ratio", True)
samples = get_samples(projects)
for index, sample in enumerate(samples):
manage_limit_rate(len(samples))
print_status_samples(index+1, len(samples))
repository = g.get_repo(sample)
forks = repository.get_forks()
forks_ahead = count_forks_ahead(framework, forks, repository)
number_of_forks = repository.forks_count
ratio_forks_ahead = forks_ahead / number_of_forks
output = create_output(sample, framework, number_of_forks, forks_ahead, ratio_forks_ahead)
output_write(framework, "forksahead", "forks_ahead_by_projects", output, False)
def importcount(framework, projects):
print("Computing imports")
measure = "importcount"
output_write(framework, measure, measure,
"framework,path,imports,javaFiles,imports/java_files", True)
samples = get_samples(projects)
for index, sample in enumerate(samples):
print_status_samples(index + 1, len(samples))
deal_with_empty_repo(sample)
java_files_path = find_paths("*.java", "repositories/" + sample)
imports = get_imports(framework, java_files_path)
relative = calculate_relative(imports, java_files_path)
output_write(
framework, measure, measure,
create_output(framework, imports, java_files_path, relative,
sample), False)
def numberofextensionfile(framework, projects):
print("Computing extension files")
extensions = create_extension_files()
measure = "numberofextensionfile"
output_write(
framework, measure, measure,
'framework,project,java,properties,jar,build.gradle,pom.xml,manifest.xml,xml,bat,md,adoc,README,yaml,txt,sh,travis.yml,yml,cmd,kt,json,numberOfFiles,others',
True)
samples = get_samples(projects)
for index, sample in enumerate(samples):
print_status_samples(index + 1, len(samples))
deal_with_empty_repo(sample)
count_extension_files(extensions, sample)
others = count_others(extensions)
output = concat_output(extensions) + str(others)
output_write(framework, measure, measure,
framework + "," + sample + "," + output, False)
def currentframeworkversion(framework, projects):
print("Computing current framework version")
configuration_file = find_config_file(framework)
configuration_file_key_words = get_key_words(framework)
write_output_header(configuration_file_key_words, framework)
samples = get_samples(projects)
for index, sample in enumerate(samples):
print_status_samples(index+1, len(samples))
checkout_default_branch_repository(sample)
deal_with_empty_repo(sample)
configuration_files_paths = find_paths(configuration_file, "repositories/" + sample)
for path in configuration_files_paths:
output = framework + "," + path
for key, value in configuration_file_key_words.items():
version = get_framework_version(framework, path, key)
output = output + "," + version
if ",,," not in output and (framework != "spring" or "RELEASE" in output):
output_write(framework, "currentframeworkversion", "currentframeworkversion", output, False)
def maintainers(framework, projects, githubtoken):
print("Computing maintainers data")
output_write(
framework, "maintainers", "maintainers",
"framework,path,framework_contributors,sample_contributors,commom_contributors,commom/framework,commom/sample",
True)
framework_repository = get_repository_name(framework)
framework_contributors = get_contributors(framework_repository,
githubtoken)
framework_contributors.totalCount
samples = get_samples(projects)
for index, sample in enumerate(samples):
print_status_samples(index + 1, len(samples))
sample_contributors = get_contributors(sample, githubtoken)
commmom_contributors = get_commom_contributors(framework_contributors,
sample_contributors)
output_write(
framework, "maintainers", "maintainers",
create_output(framework, sample, framework_contributors,
sample_contributors, commmom_contributors), False)
def metrics_by_commits(framework, projects):
samples = get_samples(projects)
for index, sample in enumerate(samples):
print_status_samples(index+1, len(samples))
owner = sample.split("/")[0]
create_output_directory("metricsbycommits", owner)
output_write(sample, "metricsbycommits", "", "framework,path,commits,date,numberOfJavaFiles,countLineCode/numberOfJavaFiles,SumCyclomaticStrict/CountDeclMethod,readability",True)
repositories_path = "/home/gabriel/Documentos/gabrielsmenezes/pesquisamestrado/repositories/"
sample_path = repositories_path + sample
udb_path = "metricsbycommits/" + sample
commits = get_commits_from(sample)
commits.reverse()
########## é so rodar, esta com a hash certa para o proximo
# for index, commit in enumerate(commits):
# if commit.hexsha == "dfe62cb3e72c7a9cfd759dc7411197d9a629f813":
# position = index
# commits = commits[position+1:]
for index, commit in enumerate(commits):
checkout_to(sample, commit.hexsha)
print("commit ======= " + commit.hexsha)
metrics = get_metrics(commit, framework, sample, sample_path, udb_path)
output_write(sample, "metricsbycommits", "", create_output(metrics), False)
delete_unused_files(sample)
print("{0}% of commits completed from sample {1}".format((index/len(commits) * 100), sample))