Merge branch 'main' of github.com:apache/iceberg-python into fd-rust

Author: Fokko

pyiceberg/expressions/parser.py

@@ -82,7 +82,7 @@
 BETWEEN = CaselessKeyword("between")
 
 unquoted_identifier = Word(alphas + "_", alphanums + "_$")
-quoted_identifier = QuotedString('"', escChar="\\", unquoteResults=True)
+quoted_identifier = QuotedString('"', esc_quote="\\", unquote_results=True)
 
 
 @quoted_identifier.set_parse_action

pyiceberg/io/pyarrow.py

@@ -2681,7 +2681,7 @@ def bin_pack_arrow_table(tbl: pa.Table, target_file_size: int) -> Iterator[list[
     from pyiceberg.utils.bin_packing import PackingIterator
 
     avg_row_size_bytes = tbl.nbytes / tbl.num_rows
-    target_rows_per_file = target_file_size // avg_row_size_bytes
+    target_rows_per_file = max(1, int(target_file_size / avg_row_size_bytes))
     batches = tbl.to_batches(max_chunksize=target_rows_per_file)
     bin_packed_record_batches = PackingIterator(
         items=batches,

tests/integration/test_writes/test_writes.py

@@ -1650,18 +1650,18 @@ def test_merge_manifests_file_content(session_catalog: Catalog, arrow_table_with
     for i in range(3):
         tbl_a_data_file = tbl_a_entries["data_file"][i]
         assert tbl_a_data_file["column_sizes"] == [
-            (1, 49),
-            (2, 78),
-            (3, 128),
-            (4, 94),
-            (5, 118),
-            (6, 94),
-            (7, 118),
-            (8, 118),
-            (9, 118),
-            (10, 94),
-            (11, 78),
-            (12, 109),
+            (1, 51),
+            (2, 80),
+            (3, 130),
+            (4, 96),
+            (5, 120),
+            (6, 96),
+            (7, 120),
+            (8, 120),
+            (9, 120),
+            (10, 96),
+            (11, 80),
+            (12, 111),
         ]
         assert tbl_a_data_file["content"] == 0
         assert tbl_a_data_file["equality_ids"] is None

tests/io/test_pyarrow.py

@@ -2248,6 +2248,12 @@ def test_bin_pack_arrow_table(arrow_table_with_null: pa.Table) -> None:
     assert len(list(bin_packed)) == 5
 
 
+def test_bin_pack_arrow_table_target_size_smaller_than_row(arrow_table_with_null: pa.Table) -> None:
+    bin_packed = list(bin_pack_arrow_table(arrow_table_with_null, target_file_size=1))
+    assert len(bin_packed) == arrow_table_with_null.num_rows
+    assert sum(batch.num_rows for bin_ in bin_packed for batch in bin_) == arrow_table_with_null.num_rows
+
+
 def test_schema_mismatch_type(table_schema_simple: Schema) -> None:
     other_schema = pa.schema(
         (