Fokko commented on code in PR #650:
URL: https://github.com/apache/iceberg-python/pull/650#discussion_r1669195441
##########
pyiceberg/manifest.py:
##########
@@ -770,6 +818,81 @@ def add_entry(self, entry: ManifestEntry) ->
ManifestWriter:
self._writer.write_block([self.prepare_entry(entry)])
return self
+ def __len__(self) -> int:
+ """Return the total number number of bytes written."""
+ return len(self._writer)
+
+
+class RollingManifestWriter:
+ closed: bool
+ _supplier: Generator[ManifestWriter, None, None]
+ _manifest_files: list[ManifestFile]
+ _target_file_size_in_bytes: int
+ _target_number_of_rows: int
+ _current_writer: Optional[ManifestWriter]
+ _current_file_rows: int
+
+ def __init__(
+ self, supplier: Generator[ManifestWriter, None, None],
target_file_size_in_bytes, target_number_of_rows
+ ) -> None:
+ self._closed = False
+ self._manifest_files = []
+ self._supplier = supplier
+ self._target_file_size_in_bytes = target_file_size_in_bytes
+ self._target_number_of_rows = target_number_of_rows
+ self._current_writer = None
+ self._current_file_rows = 0
+
+ def __enter__(self) -> RollingManifestWriter:
+ self._get_current_writer().__enter__()
+ return self
+
+ def __exit__(
+ self,
+ exc_type: Optional[Type[BaseException]],
+ exc_value: Optional[BaseException],
+ traceback: Optional[TracebackType],
+ ) -> None:
+ self.closed = True
+ if self._current_writer:
+ self._current_writer.__exit__(exc_type, exc_value, traceback)
+
+ def _get_current_writer(self) -> ManifestWriter:
+ if self._should_roll_to_new_file():
+ self._close_current_writer()
+ if not self._current_writer:
+ self._current_writer = next(self._supplier)
+ self._current_writer.__enter__()
+ return self._current_writer
+ return self._current_writer
+
+ def _should_roll_to_new_file(self) -> bool:
+ if not self._current_writer:
+ return False
+ return (
+ self._current_file_rows >= self._target_number_of_rows or
len(self._current_writer) >= self._target_file_size_in_bytes
+ )
+
+ def _close_current_writer(self):
+ if self._current_writer:
+ self._current_writer.__exit__(None, None, None)
+ current_file = self._current_writer.to_manifest_file()
+ self._manifest_files.append(current_file)
+ self._current_writer = None
+ self._current_file_rows = 0
+
+ def to_manifest_files(self) -> list[ManifestFile]:
+ self._close_current_writer()
Review Comment:
I like the same pattern as in Java, where the `to_manifest_files` call
expects the writer to be closed.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
