Fokko commented on code in PR #61: URL: https://github.com/apache/iceberg-python/pull/61#discussion_r1372139436
########## pyiceberg/table/snapshots.py: ########## @@ -116,3 +144,199 @@ class MetadataLogEntry(IcebergBaseModel): class SnapshotLogEntry(IcebergBaseModel): snapshot_id: int = Field(alias="snapshot-id") timestamp_ms: int = Field(alias="timestamp-ms") + + +class SnapshotSummaryCollector: + added_size: int + removed_size: int + added_files: int + removed_files: int + added_eq_delete_files: int + removed_eq_delete_files: int + added_pos_delete_files: int + removed_pos_delete_files: int + added_delete_files: int + removed_delete_files: int + added_records: int + deleted_records: int + added_pos_deletes: int + removed_pos_deletes: int + added_eq_deletes: int + removed_eq_deletes: int + + def __init__(self) -> None: + self.added_size = 0 + self.removed_size = 0 + self.added_files = 0 + self.removed_files = 0 + self.added_eq_delete_files = 0 + self.removed_eq_delete_files = 0 + self.added_pos_delete_files = 0 + self.removed_pos_delete_files = 0 + self.added_delete_files = 0 + self.removed_delete_files = 0 + self.added_records = 0 + self.deleted_records = 0 + self.added_pos_deletes = 0 + self.removed_pos_deletes = 0 + self.added_eq_deletes = 0 + self.removed_eq_deletes = 0 + + def add_file(self, data_file: DataFile) -> None: + if data_file.content == DataFileContent.DATA: + self.added_files += 1 + self.added_records += data_file.record_count + self.added_size += data_file.file_size_in_bytes + elif data_file.content == DataFileContent.POSITION_DELETES: + self.added_delete_files += 1 + self.added_pos_delete_files += 1 + self.added_pos_deletes += data_file.record_count + elif data_file.content == DataFileContent.EQUALITY_DELETES: + self.added_delete_files += 1 + self.added_eq_delete_files += 1 + self.added_eq_deletes += data_file.record_count + else: + raise ValueError(f"Unknown data file content: {data_file.content}") + + def removed_file(self, data_file: DataFile) -> None: + if data_file.content == DataFileContent.DATA: Review Comment: Great suggestion, missed that one ref: https://github.com/apache/iceberg/blob/aa891acf20040d15e7ca59dc503adb3c1e4325b8/core/src/main/java/org/apache/iceberg/SnapshotSummary.java#L301 ########## pyiceberg/table/snapshots.py: ########## @@ -116,3 +144,199 @@ class MetadataLogEntry(IcebergBaseModel): class SnapshotLogEntry(IcebergBaseModel): snapshot_id: int = Field(alias="snapshot-id") timestamp_ms: int = Field(alias="timestamp-ms") + + +class SnapshotSummaryCollector: + added_size: int + removed_size: int + added_files: int + removed_files: int + added_eq_delete_files: int + removed_eq_delete_files: int + added_pos_delete_files: int + removed_pos_delete_files: int + added_delete_files: int + removed_delete_files: int + added_records: int + deleted_records: int + added_pos_deletes: int + removed_pos_deletes: int + added_eq_deletes: int + removed_eq_deletes: int + + def __init__(self) -> None: + self.added_size = 0 + self.removed_size = 0 + self.added_files = 0 + self.removed_files = 0 + self.added_eq_delete_files = 0 + self.removed_eq_delete_files = 0 + self.added_pos_delete_files = 0 + self.removed_pos_delete_files = 0 + self.added_delete_files = 0 + self.removed_delete_files = 0 + self.added_records = 0 + self.deleted_records = 0 + self.added_pos_deletes = 0 + self.removed_pos_deletes = 0 + self.added_eq_deletes = 0 + self.removed_eq_deletes = 0 + + def add_file(self, data_file: DataFile) -> None: + if data_file.content == DataFileContent.DATA: + self.added_files += 1 + self.added_records += data_file.record_count + self.added_size += data_file.file_size_in_bytes Review Comment: Yes, great catch! 👍 ref: https://github.com/apache/iceberg/blob/aa891acf20040d15e7ca59dc503adb3c1e4325b8/core/src/main/java/org/apache/iceberg/SnapshotSummary.java#L278 -- 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