Merge pull request josegonzalez#474 from mwtzzz/retry_logic

update retry logic and logging

Author: josegonzalez

README.rst

@@ -152,7 +152,8 @@ CLI Help output::
                             --throttle-limit to be set)
       --exclude [EXCLUDE ...]
                             names of repositories to exclude
-
+      --retries MAX_RETRIES
+                            maximum number of retries for API calls (default: 5)
 
 Usage Details
 =============

github_backup/github_backup.py

@@ -74,9 +74,6 @@ def __init__(self, message, dmca_url=None):
                 "  3. Debian/Ubuntu: apt-get install ca-certificates\n\n"
             )
 
-# Retry configuration
-MAX_RETRIES = 5
-
 
 def logging_subprocess(
     popenargs, stdout_log_level=logging.DEBUG, stderr_log_level=logging.ERROR, **kwargs
@@ -144,6 +141,17 @@ def mask_password(url, secret="*****"):
     return url.replace(parsed.password, secret)
 
 
+def non_negative_int(value):
+    """Argparse type validator for non-negative integers."""
+    try:
+        ivalue = int(value)
+    except ValueError:
+        raise argparse.ArgumentTypeError(f"'{value}' is not a valid integer")
+    if ivalue < 0:
+        raise argparse.ArgumentTypeError(f"{value} must be 0 or greater")
+    return ivalue
+
+
 def parse_args(args=None):
     parser = argparse.ArgumentParser(description="Backup a github account")
     parser.add_argument("user", metavar="USER", type=str, help="github username")
@@ -468,6 +476,13 @@ def parse_args(args=None):
     parser.add_argument(
         "--exclude", dest="exclude", help="names of repositories to exclude", nargs="*"
     )
+    parser.add_argument(
+        "--retries",
+        dest="max_retries",
+        type=non_negative_int,
+        default=5,
+        help="maximum number of retries for API calls (default: 5)",
+    )
     return parser.parse_args(args)
 
 
@@ -622,7 +637,7 @@ def retrieve_data(args, template, query_args=None, paginated=True):
     def _extract_next_page_url(link_header):
         for link in link_header.split(","):
             if 'rel="next"' in link:
-                return link[link.find("<") + 1:link.find(">")]
+                return link[link.find("<") + 1 : link.find(">")]
         return None
 
     def fetch_all() -> Generator[dict, None, None]:
@@ -631,7 +646,7 @@ def fetch_all() -> Generator[dict, None, None]:
         while True:
             # FIRST: Fetch response
 
-            for attempt in range(MAX_RETRIES):
+            for attempt in range(args.max_retries + 1):
                 request = _construct_request(
                     per_page=per_page if paginated else None,
                     query_args=query_args,
@@ -640,7 +655,7 @@ def fetch_all() -> Generator[dict, None, None]:
                     as_app=args.as_app,
                     fine=args.token_fine is not None,
                 )
-                http_response = make_request_with_retry(request, auth)
+                http_response = make_request_with_retry(request, auth, args.max_retries)
 
                 match http_response.getcode():
                     case 200:
@@ -654,10 +669,10 @@ def fetch_all() -> Generator[dict, None, None]:
                             TimeoutError,
                         ) as e:
                             logger.warning(f"{type(e).__name__} reading response")
-                            if attempt < MAX_RETRIES - 1:
+                            if attempt < args.max_retries:
                                 delay = calculate_retry_delay(attempt, {})
                                 logger.warning(
-                                    f"Retrying in {delay:.1f}s (attempt {attempt + 1}/{MAX_RETRIES})"
+                                    f"Retrying read in {delay:.1f}s (attempt {attempt + 1}/{args.max_retries + 1})"
                                 )
                                 time.sleep(delay)
                             continue  # Next retry attempt
@@ -683,10 +698,10 @@ def fetch_all() -> Generator[dict, None, None]:
                         )
             else:
                 logger.error(
-                    f"Failed to read response after {MAX_RETRIES} attempts for {next_url or template}"
+                    f"Failed to read response after {args.max_retries + 1} attempts for {next_url or template}"
                 )
                 raise Exception(
-                    f"Failed to read response after {MAX_RETRIES} attempts for {next_url or template}"
+                    f"Failed to read response after {args.max_retries + 1} attempts for {next_url or template}"
                 )
 
             # SECOND: Process and paginate
@@ -718,7 +733,7 @@ def fetch_all() -> Generator[dict, None, None]:
     return list(fetch_all())
 
 
-def make_request_with_retry(request, auth):
+def make_request_with_retry(request, auth, max_retries=5):
     """Make HTTP request with automatic retry for transient errors."""
 
     def is_retryable_status(status_code, headers):
@@ -730,40 +745,49 @@ def is_retryable_status(status_code, headers):
             return int(headers.get("x-ratelimit-remaining", 1)) < 1
         return False
 
-    for attempt in range(MAX_RETRIES):
+    for attempt in range(max_retries + 1):
         try:
             return urlopen(request, context=https_ctx)
 
         except HTTPError as exc:
             # HTTPError can be used as a response-like object
             if not is_retryable_status(exc.code, exc.headers):
+                logger.error(
+                    f"API Error: {exc.code} {exc.reason} for {request.full_url}"
+                )
                 raise  # Non-retryable error
 
-            if attempt >= MAX_RETRIES - 1:
-                logger.error(f"HTTP {exc.code} failed after {MAX_RETRIES} attempts")
+            if attempt >= max_retries:
+                logger.error(
+                    f"HTTP {exc.code} failed after {max_retries + 1} attempts for {request.full_url}"
+                )
                 raise
 
             delay = calculate_retry_delay(attempt, exc.headers)
             logger.warning(
-                f"HTTP {exc.code}, retrying in {delay:.1f}s "
-                f"(attempt {attempt + 1}/{MAX_RETRIES})"
+                f"HTTP {exc.code} ({exc.reason}), retrying in {delay:.1f}s "
+                f"(attempt {attempt + 1}/{max_retries + 1}) for {request.full_url}"
             )
             if auth is None and exc.code in (403, 429):
                 logger.info("Hint: Authenticate to raise your GitHub rate limit")
             time.sleep(delay)
 
         except (URLError, socket.error) as e:
-            if attempt >= MAX_RETRIES - 1:
-                logger.error(f"Connection error failed after {MAX_RETRIES} attempts: {e}")
+            if attempt >= max_retries:
+                logger.error(
+                    f"Connection error failed after {max_retries + 1} attempts: {e} for {request.full_url}"
+                )
                 raise
             delay = calculate_retry_delay(attempt, {})
             logger.warning(
                 f"Connection error: {e}, retrying in {delay:.1f}s "
-                f"(attempt {attempt + 1}/{MAX_RETRIES})"
+                f"(attempt {attempt + 1}/{max_retries + 1}) for {request.full_url}"
             )
             time.sleep(delay)
 
-    raise Exception(f"Request failed after {MAX_RETRIES} attempts")  # pragma: no cover
+    raise Exception(
+        f"Request failed after {max_retries + 1} attempts"
+    )  # pragma: no cover
 
 
 def _construct_request(per_page, query_args, template, auth, as_app=None, fine=False):
@@ -1579,9 +1603,7 @@ def filter_repositories(args, unfiltered_repositories):
         repositories = [r for r in repositories if not r.get("archived")]
     if args.starred_skip_size_over is not None:
         if args.starred_skip_size_over <= 0:
-            logger.warning(
-                "--starred-skip-size-over must be greater than 0, ignoring"
-            )
+            logger.warning("--starred-skip-size-over must be greater than 0, ignoring")
         else:
             size_limit_kb = args.starred_skip_size_over * 1024
             filtered = []
@@ -1590,7 +1612,9 @@ def filter_repositories(args, unfiltered_repositories):
                     size_mb = r.get("size", 0) / 1024
                     logger.info(
                         "Skipping starred repo {0} ({1:.0f} MB) due to --starred-skip-size-over {2}".format(
-                            r.get("full_name", r.get("name")), size_mb, args.starred_skip_size_over
+                            r.get("full_name", r.get("name")),
+                            size_mb,
+                            args.starred_skip_size_over,
                         )
                     )
                 else:

tests/test_http_451.py

@@ -21,6 +21,7 @@ def test_repository_unavailable_error_raised(self):
         args.osx_keychain_item_account = None
         args.throttle_limit = None
         args.throttle_pause = 0
+        args.max_retries = 5
 
         mock_response = Mock()
         mock_response.getcode.return_value = 451
@@ -30,18 +31,26 @@ def test_repository_unavailable_error_raised(self):
             "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"
-            }
+                "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"
 
-        with patch("github_backup.github_backup.make_request_with_retry", return_value=mock_response):
+        with patch(
+            "github_backup.github_backup.make_request_with_retry",
+            return_value=mock_response,
+        ):
             with pytest.raises(github_backup.RepositoryUnavailableError) as exc_info:
-                github_backup.retrieve_data(args, "https://api.github.com/repos/test/dmca/issues")
-
-            assert exc_info.value.dmca_url == "https://github.com/github/dmca/blob/master/2024/11/2024-11-04-source-code.md"
+                github_backup.retrieve_data(
+                    args, "https://api.github.com/repos/test/dmca/issues"
+                )
+
+            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):
@@ -54,16 +63,22 @@ def test_repository_unavailable_error_without_dmca_url(self):
         args.osx_keychain_item_account = None
         args.throttle_limit = None
         args.throttle_pause = 0
+        args.max_retries = 5
 
         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"
 
-        with patch("github_backup.github_backup.make_request_with_retry", return_value=mock_response):
+        with patch(
+            "github_backup.github_backup.make_request_with_retry",
+            return_value=mock_response,
+        ):
             with pytest.raises(github_backup.RepositoryUnavailableError) as exc_info:
-                github_backup.retrieve_data(args, "https://api.github.com/repos/test/dmca/issues")
+                github_backup.retrieve_data(
+                    args, "https://api.github.com/repos/test/dmca/issues"
+                )
 
             assert exc_info.value.dmca_url is None
             assert "451" in str(exc_info.value)
@@ -78,16 +93,22 @@ def test_repository_unavailable_error_with_malformed_json(self):
         args.osx_keychain_item_account = None
         args.throttle_limit = None
         args.throttle_pause = 0
+        args.max_retries = 5
 
         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"
 
-        with patch("github_backup.github_backup.make_request_with_retry", return_value=mock_response):
+        with patch(
+            "github_backup.github_backup.make_request_with_retry",
+            return_value=mock_response,
+        ):
             with pytest.raises(github_backup.RepositoryUnavailableError):
-                github_backup.retrieve_data(args, "https://api.github.com/repos/test/dmca/issues")
+                github_backup.retrieve_data(
+                    args, "https://api.github.com/repos/test/dmca/issues"
+                )
 
 
 if __name__ == "__main__":

tests/test_pagination.py

@@ -49,6 +49,7 @@ def mock_args():
     args.osx_keychain_item_account = None
     args.throttle_limit = None
     args.throttle_pause = 0
+    args.max_retries = 5
     return args