(iceberg-python) branch main updated: Set the ManifestEntryStatus (#2408)

[fokko]

This is an automated email from the ASF dual-hosted git repository.

fokko pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg-python.git


The following commit(s) were added to refs/heads/main by this push:
     new 7acdb12f Set the ManifestEntryStatus (#2408)
7acdb12f is described below

commit 7acdb12f5239594e593f2822de75c7a4c669f52f
Author: Fokko Driesprong <fo...@apache.org>
AuthorDate: Tue Sep 2 10:22:13 2025 +0200

    Set the ManifestEntryStatus (#2408)
    
    A faulty refactor:
    
    
    
https://github.com/apache/iceberg-python/commit/59742e01e8d190aa759e0154b03300bd81a28d02#diff-e9df836e263024ba54e2706853fb25c00269fbfe3726b440ba57f4a929c995dcR927
    
    This produces incorrect metadata, but was hidden by the writer.
    
    <!--
    Thanks for opening a pull request!
    -->
    
    <!-- In the case this PR will resolve an issue, please replace
    ${GITHUB_ISSUE_ID} below with the actual Github issue id. -->
    <!-- Closes #${GITHUB_ISSUE_ID} -->
    
    # Rationale for this change
    
    ## Are these changes tested?
    
    ## Are there any user-facing changes?
    
    <!-- In the case of user-facing changes, please add the changelog label.
    -->
    
    ---------
    
    Co-authored-by: Kevin Liu <kevinjq...@users.noreply.github.com>
---
 pyiceberg/manifest.py     | 19 ++++++++-----------
 tests/catalog/test_sql.py |  4 ++++
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/pyiceberg/manifest.py b/pyiceberg/manifest.py
index a92d9448..470c99d6 100644
--- a/pyiceberg/manifest.py
+++ b/pyiceberg/manifest.py
@@ -1087,18 +1087,15 @@ class ManifestWriter(ABC):
         return self
 
     def add(self, entry: ManifestEntry) -> ManifestWriter:
-        if entry.sequence_number is not None and entry.sequence_number >= 0:
-            self.add_entry(
-                ManifestEntry.from_args(
-                    snapshot_id=self._snapshot_id, 
sequence_number=entry.sequence_number, data_file=entry.data_file
-                )
-            )
-        else:
-            self.add_entry(
-                ManifestEntry.from_args(
-                    status=ManifestEntryStatus.ADDED, 
snapshot_id=self._snapshot_id, data_file=entry.data_file
-                )
+        self.add_entry(
+            ManifestEntry.from_args(
+                status=ManifestEntryStatus.ADDED,
+                snapshot_id=self._snapshot_id,
+                sequence_number=entry.sequence_number if entry.sequence_number 
!= UNASSIGNED_SEQ else None,
+                data_file=entry.data_file,
             )
+        )
+
         return self
 
     def delete(self, entry: ManifestEntry) -> ManifestWriter:
diff --git a/tests/catalog/test_sql.py b/tests/catalog/test_sql.py
index 27105e80..00868a57 100644
--- a/tests/catalog/test_sql.py
+++ b/tests/catalog/test_sql.py
@@ -1657,6 +1657,10 @@ def test_merge_manifests_local_file_system(catalog: 
SqlCatalog, arrow_table_with
         tbl.append(arrow_table_with_null)
 
     assert len(tbl.scan().to_arrow()) == 5 * len(arrow_table_with_null)
+    current_snapshot = tbl.current_snapshot()
+    assert current_snapshot
+    manifests = current_snapshot.manifests(tbl.io)
+    assert len(manifests) == 1
 
 
 @pytest.mark.parametrize(