github-backup 0.52.0__py3-none-any.whl → 0.54.0__py3-none-any.whl

github_backup/__init__.py

@@ -1 +1 @@
-__version__ = "0.52.0"
+__version__ = "0.54.0"

github_backup/github_backup.py

@@ -1587,7 +1587,9 @@ def filter_repositories(args, unfiltered_repositories):
     repositories = []
     for r in unfiltered_repositories:
         # gists can be anonymous, so need to safely check owner
-        if r.get("owner", {}).get("login") == args.user or r.get("is_starred"):
+        # Use case-insensitive comparison to match GitHub's case-insensitive username behavior
+        owner_login = r.get("owner", {}).get("login", "")
+        if owner_login.lower() == args.user.lower() or r.get("is_starred"):
             repositories.append(r)
 
     name_regex = None
@@ -1898,11 +1900,21 @@ def backup_milestones(args, repo_cwd, repository, repos_template):
     for milestone in _milestones:
         milestones[milestone["number"]] = milestone
 
-    logger.info("Saving {0} milestones to disk".format(len(list(milestones.keys()))))
+    written_count = 0
     for number, milestone in list(milestones.items()):
         milestone_file = "{0}/{1}.json".format(milestone_cwd, number)
-        with codecs.open(milestone_file, "w", encoding="utf-8") as f:
-            json_dump(milestone, f)
+        if json_dump_if_changed(milestone, milestone_file):
+            written_count += 1
+
+    total = len(milestones)
+    if written_count == total:
+        logger.info("Saved {0} milestones to disk".format(total))
+    elif written_count == 0:
+        logger.info("{0} milestones unchanged, skipped write".format(total))
+    else:
+        logger.info("Saved {0} of {1} milestones to disk ({2} unchanged)".format(
+            written_count, total, total - written_count
+        ))
 
 
 def backup_labels(args, repo_cwd, repository, repos_template):
@@ -1955,19 +1967,17 @@ def backup_releases(args, repo_cwd, repository, repos_template, include_assets=F
             reverse=True,
         )
         releases = releases[: args.number_of_latest_releases]
-        logger.info("Saving the latest {0} releases to disk".format(len(releases)))
-    else:
-        logger.info("Saving {0} releases to disk".format(len(releases)))
 
     # for each release, store it
+    written_count = 0
     for release in releases:
         release_name = release["tag_name"]
         release_name_safe = release_name.replace("/", "__")
         output_filepath = os.path.join(
             release_cwd, "{0}.json".format(release_name_safe)
         )
-        with codecs.open(output_filepath, "w+", encoding="utf-8") as f:
-            json_dump(release, f)
+        if json_dump_if_changed(release, output_filepath):
+            written_count += 1
 
         if include_assets:
             assets = retrieve_data(args, release["assets_url"])
@@ -1984,6 +1994,17 @@ def backup_releases(args, repo_cwd, repository, repos_template, include_assets=F
                         fine=True if args.token_fine is not None else False,
                     )
 
+    # Log the results
+    total = len(releases)
+    if written_count == total:
+        logger.info("Saved {0} releases to disk".format(total))
+    elif written_count == 0:
+        logger.info("{0} releases unchanged, skipped write".format(total))
+    else:
+        logger.info("Saved {0} of {1} releases to disk ({2} unchanged)".format(
+            written_count, total, total - written_count
+        ))
+
 
 def fetch_repository(
     name,
@@ -2108,9 +2129,10 @@ def _backup_data(args, name, template, output_file, output_directory):
         mkdir_p(output_directory)
         data = retrieve_data(args, template)
 
-        logger.info("Writing {0} {1} to disk".format(len(data), name))
-        with codecs.open(output_file, "w", encoding="utf-8") as f:
-            json_dump(data, f)
+        if json_dump_if_changed(data, output_file):
+            logger.info("Saved {0} {1} to disk".format(len(data), name))
+        else:
+            logger.info("{0} {1} unchanged, skipped write".format(len(data), name))
 
 
 def json_dump(data, output_file):
@@ -2122,3 +2144,57 @@ def json_dump(data, output_file):
         indent=4,
         separators=(",", ": "),
     )
+
+
+def json_dump_if_changed(data, output_file_path):
+    """
+    Write JSON data to file only if content has changed.
+
+    Compares the serialized JSON data with the existing file content
+    and only writes if different. This prevents unnecessary file
+    modification timestamp updates and disk writes.
+
+    Uses atomic writes (temp file + rename) to prevent corruption
+    if the process is interrupted during the write.
+
+    Args:
+        data: The data to serialize as JSON
+        output_file_path: The path to the output file
+
+    Returns:
+        True if file was written (content changed or new file)
+        False if write was skipped (content unchanged)
+    """
+    # Serialize new data with consistent formatting matching json_dump()
+    new_content = json.dumps(
+        data,
+        ensure_ascii=False,
+        sort_keys=True,
+        indent=4,
+        separators=(",", ": "),
+    )
+
+    # Check if file exists and compare content
+    if os.path.exists(output_file_path):
+        try:
+            with codecs.open(output_file_path, "r", encoding="utf-8") as f:
+                existing_content = f.read()
+            if existing_content == new_content:
+                logger.debug(
+                    "Content unchanged, skipping write: {0}".format(output_file_path)
+                )
+                return False
+        except (OSError, UnicodeDecodeError) as e:
+            # If we can't read the existing file, write the new one
+            logger.debug(
+                "Error reading existing file {0}, will overwrite: {1}".format(
+                    output_file_path, e
+                )
+            )
+
+    # Write the file atomically using temp file + rename
+    temp_file = output_file_path + ".temp"
+    with codecs.open(temp_file, "w", encoding="utf-8") as f:
+        f.write(new_content)
+    os.rename(temp_file, output_file_path)  # Atomic on POSIX systems
+    return True

{github_backup-0.52.0.data → github_backup-0.54.0.data}/scripts/github-backup

@@ -16,12 +16,23 @@ from github_backup.github_backup import (
     retrieve_repositories,
 )
 
-logging.basicConfig(
-    format="%(asctime)s.%(msecs)03d: %(message)s",
+# INFO and DEBUG go to stdout, WARNING and above go to stderr
+log_format = logging.Formatter(
+    fmt="%(asctime)s.%(msecs)03d: %(message)s",
     datefmt="%Y-%m-%dT%H:%M:%S",
-    level=logging.INFO,
 )
 
+stdout_handler = logging.StreamHandler(sys.stdout)
+stdout_handler.setLevel(logging.DEBUG)
+stdout_handler.addFilter(lambda r: r.levelno < logging.WARNING)
+stdout_handler.setFormatter(log_format)
+
+stderr_handler = logging.StreamHandler(sys.stderr)
+stderr_handler.setLevel(logging.WARNING)
+stderr_handler.setFormatter(log_format)
+
+logging.basicConfig(level=logging.INFO, handlers=[stdout_handler, stderr_handler])
+
 
 def main():
     args = parse_args()

{github_backup-0.52.0.dist-info → github_backup-0.54.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: github-backup
-Version: 0.52.0
+Version: 0.54.0
 Summary: backup a github user or organization
 Home-page: http://github.com/josegonzalez/python-github-backup
 Author: Jose Diaz-Gonzalez
@@ -338,6 +338,25 @@ Skip existing on incomplete backups
 The ``--skip-existing`` argument will skip a backup if the directory already exists, even if the backup in that directory failed (perhaps due to a blocking error). This may result in unexpected missing data in a regular backup.
 
 
+Updates use fetch, not pull
+---------------------------
+
+When updating an existing repository backup, ``github-backup`` uses ``git fetch`` rather than ``git pull``. This is intentional - a backup tool should reliably download data without risk of failure. Using ``git pull`` would require handling merge conflicts, which adds complexity and could cause backups to fail unexpectedly.
+
+With fetch, **all branches and commits are downloaded** safely into remote-tracking branches. The working directory files won't change, but your backup is complete.
+
+If you look at files directly (e.g., ``cat README.md``), you'll see the old content. The new data is in the remote-tracking branches (confusingly named "remote" but stored locally). To view or use the latest files::
+
+    git show origin/main:README.md           # view a file
+    git merge origin/main                    # update working directory
+
+All branches are backed up as remote refs (``origin/main``, ``origin/feature-branch``, etc.).
+
+If you want to browse files directly without merging, consider using ``--bare`` which skips the working directory entirely - the backup is just the git data.
+
+See `#269 <https://github.com/josegonzalez/python-github-backup/issues/269>`_ for more discussion.
+
+
 Github Backup Examples
 ======================
 
@@ -387,7 +406,12 @@ A huge thanks to all the contibuters!
 Testing
 -------
 
-This project currently contains no unit tests.  To run linting::
+To run the test suite::
+
+    pip install pytest
+    pytest
+
+To run linting::
 
     pip install flake8
     flake8 --ignore=E501

github_backup-0.54.0.dist-info/RECORD

@@ -0,0 +1,9 @@
+github_backup/__init__.py,sha256=GL361gEztfNayz_pZjsGe3Es4PhpuAOve1lCqPCbSZs,23
+github_backup/github_backup.py,sha256=-7oiAGDfavMxSiqWgaiyS5vYq31kFxOXgEH0Vw5MTIo,80149
+github_backup-0.54.0.data/scripts/github-backup,sha256=hC59RgEKx2RbHKC-eQkKfB3JXfiNIvIO4VAXiodSkLw,2004
+github_backup-0.54.0.dist-info/licenses/LICENSE.txt,sha256=ML-pLyn1qtAKo_DHMcQ8-p7k3f8cp-IR-mf5B49R2rk,1085
+github_backup-0.54.0.dist-info/METADATA,sha256=CJyhg2JeoygmRFtyGbyjs0PLOoy04IkdC4mLnu1WOnM,22810
+github_backup-0.54.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+github_backup-0.54.0.dist-info/top_level.txt,sha256=Za6fKRAlxZ0b3ZBH_osPqklLe14LetdNAkvAQANT2AA,14
+github_backup-0.54.0.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+github_backup-0.54.0.dist-info/RECORD,,

github_backup-0.52.0.dist-info/RECORD

@@ -1,9 +0,0 @@
-github_backup/__init__.py,sha256=uXy9jtvBCb6cwZyNng8d7tehPtkx2Xcdr7Lm3SEzEF8,23
-github_backup/github_backup.py,sha256=eo8P69vIgeP_ntzY4DdGrzFnEKPIoqBrgBX3Dw_2lIo,77487
-github_backup-0.52.0.data/scripts/github-backup,sha256=I79TNA67phytRmI9nm_LlD9h2zauXFOsOn9tYyAy9pU,1546
-github_backup-0.52.0.dist-info/licenses/LICENSE.txt,sha256=ML-pLyn1qtAKo_DHMcQ8-p7k3f8cp-IR-mf5B49R2rk,1085
-github_backup-0.52.0.dist-info/METADATA,sha256=92rNj52N87cGNzBGRJYCyaotJIEgZ5ZgZ-DUugpuvlI,21544
-github_backup-0.52.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-github_backup-0.52.0.dist-info/top_level.txt,sha256=Za6fKRAlxZ0b3ZBH_osPqklLe14LetdNAkvAQANT2AA,14
-github_backup-0.52.0.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-github_backup-0.52.0.dist-info/RECORD,,