test fix

Author: rambleraptor

pyiceberg/table/puffin.py

@@ -219,14 +219,16 @@ def finish(self) -> bytes:
             for blob_payload in self._blob_payloads:
                 payload_buffer.write(blob_payload)
 
-            # Set offsets and lengths in metadata
-            current_offset = 4  # Start after file magic
+            updated_blobs_metadata: List[PuffinBlobMetadata] = []
+            current_offset = 4  # Start after file magic (4 bytes)
             for i, blob_payload in enumerate(self._blob_payloads):
-                self._blobs[i].offset = current_offset
-                self._blobs[i].length = len(blob_payload)
+                original_metadata_dict = self._blobs[i].model_dump(by_alias=True, exclude_none=True)
+                original_metadata_dict["offset"] = current_offset
+                original_metadata_dict["length"] = len(blob_payload)
+                updated_blobs_metadata.append(PuffinBlobMetadata(**original_metadata_dict))
                 current_offset += len(blob_payload)
 
-            footer = Footer(blobs=self._blobs)
+            footer = Footer(blobs=updated_blobs_metadata)
             footer_payload_bytes = footer.model_dump_json(by_alias=True, exclude_none=True).encode("utf-8")
 
             # Final assembly

tests/table/test_puffin.py

@@ -19,7 +19,7 @@
 import pytest
 from pyroaring import BitMap
 
-from pyiceberg.table.puffin import _deserialize_bitmap, PuffinFile, PuffinWriter
+from pyiceberg.table.puffin import _deserialize_bitmap, PuffinFile, PuffinWriter, PROPERTY_REFERENCED_DATA_FILE
 
 
 def _open_file(file: str) -> bytes:
@@ -94,11 +94,11 @@ def test_puffin_round_trip():
     assert len(reader.footer.blobs) == 2
 
     blob1_meta = reader.footer.blobs[0]
-    assert blob1_meta.properties[PuffinFile.PROPERTY_REFERENCED_DATA_FILE] == file1_path
+    assert blob1_meta.properties[PROPERTY_REFERENCED_DATA_FILE] == file1_path
     assert blob1_meta.properties["cardinality"] == str(len(deletions1))
 
     blob2_meta = reader.footer.blobs[1]
-    assert blob2_meta.properties[PuffinFile.PROPERTY_REFERENCED_DATA_FILE] == file2_path
+    assert blob2_meta.properties[PROPERTY_REFERENCED_DATA_FILE] == file2_path
     assert blob2_meta.properties["cardinality"] == str(len(deletions2))
 
     # Assert the content of deletion vectors