github-backup 0.51.3__tar.gz → 0.53.0__tar.gz

{github_backup-0.51.3 → github_backup-0.53.0}/CHANGES.rst

@@ -1,9 +1,125 @@
 Changelog
 =========
 
-0.51.3 (2025-11-18)
+0.53.0 (2025-11-30)
 -------------------
 ------------------------
+
+Fix
+~~~
+- Case-sensitive username filtering causing silent backup failures.
+  [Rodos]
+
+  GitHub's API accepts usernames in any case but returns canonical case.
+  The case-sensitive comparison in filter_repositories() filtered out all
+  repositories when user-provided case didn't match GitHub's canonical case.
+
+  Changed to case-insensitive comparison.
+
+  Fixes #198
+
+Other
+~~~~~
+- Avoid rewriting unchanged JSON files for labels, milestones, releases,
+  hooks, followers, and following. [Rodos]
+
+  This change reduces unnecessary writes when backing up metadata that changes
+  infrequently. The implementation compares existing file content before writing
+  and skips the write if the content is identical, preserving file timestamps.
+
+  Key changes:
+  - Added json_dump_if_changed() helper that compares content before writing
+  - Uses atomic writes (temp file + rename) for all metadata files
+  - NOT applied to issues/pulls (they use incremental_by_files logic)
+  - Made log messages consistent and past tense ("Saved" instead of "Saving")
+  - Added informative logging showing skip counts
+
+  Fixes #133
+
+
+0.52.0 (2025-11-28)
+-------------------
+- Skip DMCA'd repos which return a 451 response. [Rodos]
+
+  Log a warning and the link to the DMCA notice. Continue backing up
+  other repositories instead of crashing.
+
+  Closes #163
+- Chore(deps): bump restructuredtext-lint in the python-packages group.
+  [dependabot[bot]]
+
+  Bumps the python-packages group with 1 update: [restructuredtext-lint](https://github.com/twolfson/restructuredtext-lint).
+
+
+  Updates `restructuredtext-lint` from 1.4.0 to 2.0.2
+  - [Changelog](https://github.com/twolfson/restructuredtext-lint/blob/master/CHANGELOG.rst)
+  - [Commits](https://github.com/twolfson/restructuredtext-lint/compare/1.4.0...2.0.2)
+
+  ---
+  updated-dependencies:
+  - dependency-name: restructuredtext-lint
+    dependency-version: 2.0.2
+    dependency-type: direct:production
+    update-type: version-update:semver-major
+    dependency-group: python-packages
+  ...
+- Chore(deps): bump actions/checkout from 5 to 6. [dependabot[bot]]
+
+  Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6.
+  - [Release notes](https://github.com/actions/checkout/releases)
+  - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md)
+  - [Commits](https://github.com/actions/checkout/compare/v5...v6)
+
+  ---
+  updated-dependencies:
+  - dependency-name: actions/checkout
+    dependency-version: '6'
+    dependency-type: direct:production
+    update-type: version-update:semver-major
+  ...
+- Chore(deps): bump the python-packages group with 3 updates.
+  [dependabot[bot]]
+
+  Bumps the python-packages group with 3 updates: [click](https://github.com/pallets/click), [pytest](https://github.com/pytest-dev/pytest) and [keyring](https://github.com/jaraco/keyring).
+
+
+  Updates `click` from 8.3.0 to 8.3.1
+  - [Release notes](https://github.com/pallets/click/releases)
+  - [Changelog](https://github.com/pallets/click/blob/main/CHANGES.rst)
+  - [Commits](https://github.com/pallets/click/compare/8.3.0...8.3.1)
+
+  Updates `pytest` from 8.3.3 to 9.0.1
+  - [Release notes](https://github.com/pytest-dev/pytest/releases)
+  - [Changelog](https://github.com/pytest-dev/pytest/blob/main/CHANGELOG.rst)
+  - [Commits](https://github.com/pytest-dev/pytest/compare/8.3.3...9.0.1)
+
+  Updates `keyring` from 25.6.0 to 25.7.0
+  - [Release notes](https://github.com/jaraco/keyring/releases)
+  - [Changelog](https://github.com/jaraco/keyring/blob/main/NEWS.rst)
+  - [Commits](https://github.com/jaraco/keyring/compare/v25.6.0...v25.7.0)
+
+  ---
+  updated-dependencies:
+  - dependency-name: click
+    dependency-version: 8.3.1
+    dependency-type: direct:production
+    update-type: version-update:semver-patch
+    dependency-group: python-packages
+  - dependency-name: pytest
+    dependency-version: 9.0.1
+    dependency-type: direct:production
+    update-type: version-update:semver-major
+    dependency-group: python-packages
+  - dependency-name: keyring
+    dependency-version: 25.7.0
+    dependency-type: direct:production
+    update-type: version-update:semver-minor
+    dependency-group: python-packages
+  ...
+
+
+0.51.3 (2025-11-18)
+-------------------
 - Test: Add pagination tests for cursor and page-based Link headers.
   [Rodos]
 - Use cursor based pagination. [Helio Machado]

{github_backup-0.51.3/github_backup.egg-info → github_backup-0.53.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: github-backup
-Version: 0.51.3
+Version: 0.53.0
 Summary: backup a github user or organization
 Home-page: http://github.com/josegonzalez/python-github-backup
 Author: Jose Diaz-Gonzalez

github_backup-0.53.0/github_backup/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.53.0"

{github_backup-0.51.3 → github_backup-0.53.0}/github_backup/github_backup.py

@@ -37,6 +37,15 @@ FNULL = open(os.devnull, "w")
 FILE_URI_PREFIX = "file://"
 logger = logging.getLogger(__name__)
 
+
+class RepositoryUnavailableError(Exception):
+    """Raised when a repository is unavailable due to legal reasons (e.g., DMCA takedown)."""
+
+    def __init__(self, message, dmca_url=None):
+        super().__init__(message)
+        self.dmca_url = dmca_url
+
+
 # Setup SSL context with fallback chain
 https_ctx = ssl.create_default_context()
 if https_ctx.get_ca_certs():
@@ -612,6 +621,19 @@ def retrieve_data_gen(args, template, query_args=None, single_request=False):
 
         status_code = int(r.getcode())
 
+        # Handle DMCA takedown (HTTP 451) - raise exception to skip entire repository
+        if status_code == 451:
+            dmca_url = None
+            try:
+                response_data = json.loads(r.read().decode("utf-8"))
+                dmca_url = response_data.get("block", {}).get("html_url")
+            except Exception:
+                pass
+            raise RepositoryUnavailableError(
+                "Repository unavailable due to legal reasons (HTTP 451)",
+                dmca_url=dmca_url
+            )
+
         # Check if we got correct data
         try:
             response = json.loads(r.read().decode("utf-8"))
@@ -1565,7 +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
@@ -1668,40 +1692,47 @@ def backup_repositories(args, output_directory, repositories):
 
                 continue  # don't try to back anything else for a gist; it doesn't exist
 
-        download_wiki = args.include_wiki or args.include_everything
-        if repository["has_wiki"] and download_wiki:
-            fetch_repository(
-                repository["name"],
-                repo_url.replace(".git", ".wiki.git"),
-                os.path.join(repo_cwd, "wiki"),
-                skip_existing=args.skip_existing,
-                bare_clone=args.bare_clone,
-                lfs_clone=args.lfs_clone,
-                no_prune=args.no_prune,
-            )
-        if args.include_issues or args.include_everything:
-            backup_issues(args, repo_cwd, repository, repos_template)
+        try:
+            download_wiki = args.include_wiki or args.include_everything
+            if repository["has_wiki"] and download_wiki:
+                fetch_repository(
+                    repository["name"],
+                    repo_url.replace(".git", ".wiki.git"),
+                    os.path.join(repo_cwd, "wiki"),
+                    skip_existing=args.skip_existing,
+                    bare_clone=args.bare_clone,
+                    lfs_clone=args.lfs_clone,
+                    no_prune=args.no_prune,
+                )
+            if args.include_issues or args.include_everything:
+                backup_issues(args, repo_cwd, repository, repos_template)
 
-        if args.include_pulls or args.include_everything:
-            backup_pulls(args, repo_cwd, repository, repos_template)
+            if args.include_pulls or args.include_everything:
+                backup_pulls(args, repo_cwd, repository, repos_template)
 
-        if args.include_milestones or args.include_everything:
-            backup_milestones(args, repo_cwd, repository, repos_template)
+            if args.include_milestones or args.include_everything:
+                backup_milestones(args, repo_cwd, repository, repos_template)
 
-        if args.include_labels or args.include_everything:
-            backup_labels(args, repo_cwd, repository, repos_template)
+            if args.include_labels or args.include_everything:
+                backup_labels(args, repo_cwd, repository, repos_template)
 
-        if args.include_hooks or args.include_everything:
-            backup_hooks(args, repo_cwd, repository, repos_template)
+            if args.include_hooks or args.include_everything:
+                backup_hooks(args, repo_cwd, repository, repos_template)
 
-        if args.include_releases or args.include_everything:
-            backup_releases(
-                args,
-                repo_cwd,
-                repository,
-                repos_template,
-                include_assets=args.include_assets or args.include_everything,
-            )
+            if args.include_releases or args.include_everything:
+                backup_releases(
+                    args,
+                    repo_cwd,
+                    repository,
+                    repos_template,
+                    include_assets=args.include_assets or args.include_everything,
+                )
+        except RepositoryUnavailableError as e:
+            logger.warning(f"Repository {repository['full_name']} is unavailable (HTTP 451)")
+            if e.dmca_url:
+                logger.warning(f"DMCA notice: {e.dmca_url}")
+            logger.info(f"Skipping remaining resources for {repository['full_name']}")
+            continue
 
     if args.incremental:
         if last_update == "0000-00-00T00:00:00Z":
@@ -1869,11 +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):
@@ -1926,19 +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"])
@@ -1955,6 +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,
@@ -2079,9 +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):
@@ -2093,3 +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-0.51.3 → github_backup-0.53.0/github_backup.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: github-backup
-Version: 0.51.3
+Version: 0.53.0
 Summary: backup a github user or organization
 Home-page: http://github.com/josegonzalez/python-github-backup
 Author: Jose Diaz-Gonzalez

{github_backup-0.51.3 → github_backup-0.53.0}/github_backup.egg-info/SOURCES.txt

@@ -15,4 +15,6 @@ github_backup.egg-info/dependency_links.txt
 github_backup.egg-info/top_level.txt
 github_backup.egg-info/zip-safe
 tests/test_attachments.py
+tests/test_http_451.py
+tests/test_json_dump_if_changed.py
 tests/test_pagination.py

{github_backup-0.51.3 → github_backup-0.53.0}/release-requirements.txt

@@ -3,16 +3,16 @@ black==25.11.0
 bleach==6.3.0
 certifi==2025.11.12
 charset-normalizer==3.4.4
-click==8.3.0
+click==8.3.1
 colorama==0.4.6
 docutils==0.22.3
 flake8==7.3.0
 gitchangelog==3.0.4
-pytest==8.3.3
+pytest==9.0.1
 idna==3.11
 importlib-metadata==8.7.0
 jaraco.classes==3.4.0
-keyring==25.6.0
+keyring==25.7.0
 markdown-it-py==4.0.0
 mccabe==0.7.0
 mdurl==0.1.2
@@ -28,7 +28,7 @@ Pygments==2.19.2
 readme-renderer==44.0
 requests==2.32.5
 requests-toolbelt==1.0.0
-restructuredtext-lint==1.4.0
+restructuredtext-lint==2.0.2
 rfc3986==2.0.0
 rich==14.2.0
 setuptools==80.9.0

github_backup-0.53.0/tests/test_http_451.py

@@ -0,0 +1,143 @@
+"""Tests for HTTP 451 (DMCA takedown) handling."""
+
+import json
+from unittest.mock import Mock, patch
+
+import pytest
+
+from github_backup import github_backup
+
+
+class TestHTTP451Exception:
+    """Test suite for HTTP 451 DMCA takedown exception handling."""
+
+    def test_repository_unavailable_error_raised(self):
+        """HTTP 451 should raise RepositoryUnavailableError with DMCA URL."""
+        # Create mock args
+        args = Mock()
+        args.as_app = False
+        args.token_fine = None
+        args.token_classic = None
+        args.username = None
+        args.password = None
+        args.osx_keychain_item_name = None
+        args.osx_keychain_item_account = None
+        args.throttle_limit = None
+        args.throttle_pause = 0
+
+        # Mock HTTPError 451 response
+        mock_response = Mock()
+        mock_response.getcode.return_value = 451
+
+        dmca_data = {
+            "message": "Repository access blocked",
+            "block": {
+                "reason": "dmca",
+                "created_at": "2024-11-12T14:38:04Z",
+                "html_url": "https://github.com/github/dmca/blob/master/2024/11/2024-11-04-source-code.md"
+            }
+        }
+        mock_response.read.return_value = json.dumps(dmca_data).encode("utf-8")
+        mock_response.headers = {"x-ratelimit-remaining": "5000"}
+        mock_response.reason = "Unavailable For Legal Reasons"
+
+        def mock_get_response(request, auth, template):
+            return mock_response, []
+
+        with patch("github_backup.github_backup._get_response", side_effect=mock_get_response):
+            with pytest.raises(github_backup.RepositoryUnavailableError) as exc_info:
+                list(github_backup.retrieve_data_gen(args, "https://api.github.com/repos/test/dmca/issues"))
+
+            # Check exception has DMCA URL
+            assert exc_info.value.dmca_url == "https://github.com/github/dmca/blob/master/2024/11/2024-11-04-source-code.md"
+            assert "451" in str(exc_info.value)
+
+    def test_repository_unavailable_error_without_dmca_url(self):
+        """HTTP 451 without DMCA details should still raise exception."""
+        args = Mock()
+        args.as_app = False
+        args.token_fine = None
+        args.token_classic = None
+        args.username = None
+        args.password = None
+        args.osx_keychain_item_name = None
+        args.osx_keychain_item_account = None
+        args.throttle_limit = None
+        args.throttle_pause = 0
+
+        mock_response = Mock()
+        mock_response.getcode.return_value = 451
+        mock_response.read.return_value = b'{"message": "Blocked"}'
+        mock_response.headers = {"x-ratelimit-remaining": "5000"}
+        mock_response.reason = "Unavailable For Legal Reasons"
+
+        def mock_get_response(request, auth, template):
+            return mock_response, []
+
+        with patch("github_backup.github_backup._get_response", side_effect=mock_get_response):
+            with pytest.raises(github_backup.RepositoryUnavailableError) as exc_info:
+                list(github_backup.retrieve_data_gen(args, "https://api.github.com/repos/test/dmca/issues"))
+
+            # Exception raised even without DMCA URL
+            assert exc_info.value.dmca_url is None
+            assert "451" in str(exc_info.value)
+
+    def test_repository_unavailable_error_with_malformed_json(self):
+        """HTTP 451 with malformed JSON should still raise exception."""
+        args = Mock()
+        args.as_app = False
+        args.token_fine = None
+        args.token_classic = None
+        args.username = None
+        args.password = None
+        args.osx_keychain_item_name = None
+        args.osx_keychain_item_account = None
+        args.throttle_limit = None
+        args.throttle_pause = 0
+
+        mock_response = Mock()
+        mock_response.getcode.return_value = 451
+        mock_response.read.return_value = b"invalid json {"
+        mock_response.headers = {"x-ratelimit-remaining": "5000"}
+        mock_response.reason = "Unavailable For Legal Reasons"
+
+        def mock_get_response(request, auth, template):
+            return mock_response, []
+
+        with patch("github_backup.github_backup._get_response", side_effect=mock_get_response):
+            with pytest.raises(github_backup.RepositoryUnavailableError):
+                list(github_backup.retrieve_data_gen(args, "https://api.github.com/repos/test/dmca/issues"))
+
+    def test_other_http_errors_unchanged(self):
+        """Other HTTP errors should still raise generic Exception."""
+        args = Mock()
+        args.as_app = False
+        args.token_fine = None
+        args.token_classic = None
+        args.username = None
+        args.password = None
+        args.osx_keychain_item_name = None
+        args.osx_keychain_item_account = None
+        args.throttle_limit = None
+        args.throttle_pause = 0
+
+        mock_response = Mock()
+        mock_response.getcode.return_value = 404
+        mock_response.read.return_value = b'{"message": "Not Found"}'
+        mock_response.headers = {"x-ratelimit-remaining": "5000"}
+        mock_response.reason = "Not Found"
+
+        def mock_get_response(request, auth, template):
+            return mock_response, []
+
+        with patch("github_backup.github_backup._get_response", side_effect=mock_get_response):
+            # Should raise generic Exception, not RepositoryUnavailableError
+            with pytest.raises(Exception) as exc_info:
+                list(github_backup.retrieve_data_gen(args, "https://api.github.com/repos/test/notfound/issues"))
+
+            assert not isinstance(exc_info.value, github_backup.RepositoryUnavailableError)
+            assert "404" in str(exc_info.value)
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"])

github_backup-0.53.0/tests/test_json_dump_if_changed.py

@@ -0,0 +1,198 @@
+"""Tests for json_dump_if_changed functionality."""
+
+import codecs
+import json
+import os
+import tempfile
+
+import pytest
+
+from github_backup import github_backup
+
+
+class TestJsonDumpIfChanged:
+    """Test suite for json_dump_if_changed function."""
+
+    def test_writes_new_file(self):
+        """Should write file when it doesn't exist."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            output_file = os.path.join(tmpdir, "test.json")
+            test_data = {"key": "value", "number": 42}
+
+            result = github_backup.json_dump_if_changed(test_data, output_file)
+
+            assert result is True
+            assert os.path.exists(output_file)
+
+            # Verify content matches expected format
+            with codecs.open(output_file, "r", encoding="utf-8") as f:
+                content = f.read()
+                loaded = json.loads(content)
+                assert loaded == test_data
+
+    def test_skips_unchanged_file(self):
+        """Should skip write when content is identical."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            output_file = os.path.join(tmpdir, "test.json")
+            test_data = {"key": "value", "number": 42}
+
+            # First write
+            result1 = github_backup.json_dump_if_changed(test_data, output_file)
+            assert result1 is True
+
+            # Get the initial mtime
+            mtime1 = os.path.getmtime(output_file)
+
+            # Second write with same data
+            result2 = github_backup.json_dump_if_changed(test_data, output_file)
+            assert result2 is False
+
+            # File should not have been modified
+            mtime2 = os.path.getmtime(output_file)
+            assert mtime1 == mtime2
+
+    def test_writes_when_content_changed(self):
+        """Should write file when content has changed."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            output_file = os.path.join(tmpdir, "test.json")
+            test_data1 = {"key": "value1"}
+            test_data2 = {"key": "value2"}
+
+            # First write
+            result1 = github_backup.json_dump_if_changed(test_data1, output_file)
+            assert result1 is True
+
+            # Second write with different data
+            result2 = github_backup.json_dump_if_changed(test_data2, output_file)
+            assert result2 is True
+
+            # Verify new content
+            with codecs.open(output_file, "r", encoding="utf-8") as f:
+                loaded = json.load(f)
+                assert loaded == test_data2
+
+    def test_uses_consistent_formatting(self):
+        """Should use same JSON formatting as json_dump."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            output_file = os.path.join(tmpdir, "test.json")
+            test_data = {"z": "last", "a": "first", "m": "middle"}
+
+            github_backup.json_dump_if_changed(test_data, output_file)
+
+            with codecs.open(output_file, "r", encoding="utf-8") as f:
+                content = f.read()
+
+            # Check for consistent formatting:
+            # - sorted keys
+            # - 4-space indent
+            # - comma-colon-space separator
+            expected = json.dumps(
+                test_data,
+                ensure_ascii=False,
+                sort_keys=True,
+                indent=4,
+                separators=(",", ": "),
+            )
+            assert content == expected
+
+    def test_atomic_write_always_used(self):
+        """Should always use temp file and rename for atomic writes."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            output_file = os.path.join(tmpdir, "test.json")
+            test_data = {"key": "value"}
+
+            result = github_backup.json_dump_if_changed(test_data, output_file)
+
+            assert result is True
+            assert os.path.exists(output_file)
+
+            # Temp file should not exist after atomic write
+            temp_file = output_file + ".temp"
+            assert not os.path.exists(temp_file)
+
+            # Verify content
+            with codecs.open(output_file, "r", encoding="utf-8") as f:
+                loaded = json.load(f)
+                assert loaded == test_data
+
+    def test_handles_unicode_content(self):
+        """Should correctly handle Unicode content."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            output_file = os.path.join(tmpdir, "test.json")
+            test_data = {
+                "emoji": "🚀",
+                "chinese": "你好",
+                "arabic": "مرحبا",
+                "cyrillic": "Привет",
+            }
+
+            result = github_backup.json_dump_if_changed(test_data, output_file)
+            assert result is True
+
+            # Verify Unicode is preserved
+            with codecs.open(output_file, "r", encoding="utf-8") as f:
+                loaded = json.load(f)
+                assert loaded == test_data
+
+            # Second write should skip
+            result2 = github_backup.json_dump_if_changed(test_data, output_file)
+            assert result2 is False
+
+    def test_handles_complex_nested_data(self):
+        """Should handle complex nested data structures."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            output_file = os.path.join(tmpdir, "test.json")
+            test_data = {
+                "users": [
+                    {"id": 1, "name": "Alice", "tags": ["admin", "user"]},
+                    {"id": 2, "name": "Bob", "tags": ["user"]},
+                ],
+                "metadata": {"version": "1.0", "nested": {"deep": {"value": 42}}},
+            }
+
+            result = github_backup.json_dump_if_changed(test_data, output_file)
+            assert result is True
+
+            # Verify structure is preserved
+            with codecs.open(output_file, "r", encoding="utf-8") as f:
+                loaded = json.load(f)
+                assert loaded == test_data
+
+    def test_overwrites_on_unicode_decode_error(self):
+        """Should overwrite if existing file has invalid UTF-8."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            output_file = os.path.join(tmpdir, "test.json")
+            test_data = {"key": "value"}
+
+            # Write invalid UTF-8 bytes
+            with open(output_file, "wb") as f:
+                f.write(b"\xff\xfe invalid utf-8")
+
+            # Should catch UnicodeDecodeError and overwrite
+            result = github_backup.json_dump_if_changed(test_data, output_file)
+            assert result is True
+
+            # Verify new content was written
+            with codecs.open(output_file, "r", encoding="utf-8") as f:
+                loaded = json.load(f)
+                assert loaded == test_data
+
+    def test_key_order_independence(self):
+        """Should treat differently-ordered dicts as same if keys/values match."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            output_file = os.path.join(tmpdir, "test.json")
+
+            # Write first dict
+            data1 = {"z": 1, "a": 2, "m": 3}
+            github_backup.json_dump_if_changed(data1, output_file)
+
+            # Try to write same data but different order
+            data2 = {"a": 2, "m": 3, "z": 1}
+            result = github_backup.json_dump_if_changed(data2, output_file)
+
+            # Should skip because content is the same (keys are sorted)
+            assert result is False
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"])

github_backup-0.51.3/github_backup/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.51.3"