rdblue commented on code in PR #6506:
URL: https://github.com/apache/iceberg/pull/6506#discussion_r1060141470


##########
python/pyiceberg/manifest.py:
##########
@@ -104,29 +104,100 @@ class ManifestEntry(IcebergBaseModel):
     data_file: DataFile = Field()
 
 
+PARTITION_FIELD_SUMMARY_TYPE = StructType(
+    NestedField(509, "contains_null", BooleanType(), required=True),
+    NestedField(518, "contains_nan", BooleanType(), required=False),
+    NestedField(510, "lower_bound", BinaryType(), required=False),
+    NestedField(511, "upper_bound", BinaryType(), required=False)
+)
+
+
 class PartitionFieldSummary(IcebergBaseModel):
     contains_null: bool = Field()
     contains_nan: Optional[bool] = Field()
     lower_bound: Optional[bytes] = Field()
     upper_bound: Optional[bytes] = Field()
 
 
-class ManifestFile(IcebergBaseModel):
-    manifest_path: str = Field()
-    manifest_length: int = Field()
-    partition_spec_id: int = Field()
-    content: ManifestContent = Field(default=ManifestContent.DATA)
-    sequence_number: int = Field(default=0)
-    min_sequence_number: int = Field(default=0)
-    added_snapshot_id: Optional[int] = Field()
-    added_data_files_count: Optional[int] = Field()
-    existing_data_files_count: Optional[int] = Field()
-    deleted_data_files_count: Optional[int] = Field()
-    added_rows_count: Optional[int] = Field()
-    existing_rows_counts: Optional[int] = Field()
-    deleted_rows_count: Optional[int] = Field()
-    partitions: Optional[List[PartitionFieldSummary]] = Field()
-    key_metadata: Optional[bytes] = Field()
+MANIFEST_FILE_SCHEMA: Schema = Schema(
+    NestedField(500, "manifest_path", StringType(), required=True, 
doc="Location URI with FS scheme"),
+    NestedField(501, "manifest_length", LongType(), required=True),
+    NestedField(502, "partition_spec_id", IntegerType(), required=True),
+    NestedField(517, "content", IntegerType(), required=False),
+    NestedField(515, "sequence_number", LongType(), required=False),
+    NestedField(516, "min_sequence_number", LongType(), required=False),
+    NestedField(503, "added_snapshot_id", LongType(), required=False),
+    NestedField(504, "added_data_files_count", IntegerType(), required=False),
+    NestedField(505, "existing_data_files_count", IntegerType(), 
required=False),
+    NestedField(506, "deleted_data_files_count", IntegerType(), 
required=False),
+    NestedField(512, "added_rows_count", LongType(), required=False),
+    NestedField(513, "existing_rows_count", LongType(), required=False),
+    NestedField(514, "deleted_rows_count", LongType(), required=False),
+    NestedField(507, "partitions", ListType(508, PARTITION_FIELD_SUMMARY_TYPE, 
element_required=True), required=False),
+    NestedField(519, "key_metadata", BinaryType(), required=False),
+)
+
+MANIFEST_FILE_FIELD_NAMES: Dict[int, str] = {pos: field.name for pos, field in 
MANIFEST_FILE_SCHEMA.fields}
+IN_TRANSFORMS: Dict[int, Callable[[Any], Any]] = {
+    3: lambda id: ManifestContent.DATA if id == 0 else ManifestContent.DELETES

Review Comment:
   We should replace this with a method that decodes the id.



-- 
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

Reply via email to