Wavyzz/python-github-backup
2
0
Fork 0
mirror of https://github.com/josegonzalez/python-github-backup.git synced 2025-12-05 16:18:02 +01:00
Code Issues Packages Projects Releases Wiki Activity

Implementing incremental by files, safer version of incremental backup.

Browse Source
This commit is contained in:
Honza Maly
2025-01-16 21:00:02 +00:00
parent 332c9b586a
commit a49322cf7d
2 changed files with 30 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
github_backup/github_backup.py
View File

@@ -181,6 +181,12 @@ def parse_args(args=None):
dest="incremental",
help="incremental backup",
)
parser.add_argument(
"--incremental-by-files",
action="store_true",
dest="incremental_by_files",
help="incremental backup based on modification date of files",
)
parser.add_argument(
"--starred",
action="store_true",
@@ -1114,6 +1120,13 @@ def backup_issues(args, repo_cwd, repository, repos_template):
comments_template = _issue_template + "/{0}/comments"
events_template = _issue_template + "/{0}/events"
for number, issue in list(issues.items()):
issue_file = "{0}/{1}.json".format(issue_cwd, number)
if args.incremental_by_files and os.path.isfile(issue_file):
modified = os.path.getmtime(issue_file)
if modified > issue["updated_at"]
logger.info("Skipping issue {0} because it wasn't modified since last backup".format(number))
continue
if args.include_issue_comments or args.include_everything:
template = comments_template.format(number)
issues[number]["comment_data"] = retrieve_data(args, template)
@@ -1121,9 +1134,9 @@ def backup_issues(args, repo_cwd, repository, repos_template):
template = events_template.format(number)
issues[number]["event_data"] = retrieve_data(args, template)
issue_file = "{0}/{1}.json".format(issue_cwd, number)
with codecs.open(issue_file, "w", encoding="utf-8") as f:
with codecs.open(issue_file + ".temp", "w", encoding="utf-8") as f:
json_dump(issue, f)
os.rename(issue_file + ".temp", issue_file) # Unlike json_dump, this is atomic
def backup_pulls(args, repo_cwd, repository, repos_template):
@@ -1176,6 +1189,12 @@ def backup_pulls(args, repo_cwd, repository, repos_template):
comments_template = _pulls_template + "/{0}/comments"
commits_template = _pulls_template + "/{0}/commits"
for number, pull in list(pulls.items()):
pull_file = "{0}/{1}.json".format(pulls_cwd, number)
if args.incremental_by_files and os.path.isfile(pull_file):
modified = os.path.getmtime(pull_file)
if modified > pull["updated_at"]
logger.info("Skipping pull request {0} because it wasn't modified since last backup".format(number))
continue
if args.include_pull_comments or args.include_everything:
template = comments_regular_template.format(number)
pulls[number]["comment_regular_data"] = retrieve_data(args, template)
@@ -1185,9 +1204,9 @@ def backup_pulls(args, repo_cwd, repository, repos_template):
template = commits_template.format(number)
pulls[number]["commit_data"] = retrieve_data(args, template)
pull_file = "{0}/{1}.json".format(pulls_cwd, number)
with codecs.open(pull_file, "w", encoding="utf-8") as f:
with codecs.open(pull_file + ".temp", "w", encoding="utf-8") as f:
json_dump(pull, f)
os.rename(pull_file + ".temp", pull_file) # Unlike json_dump, this is atomic
def backup_milestones(args, repo_cwd, repository, repos_template):