ARROW-7762: [Python] Do not ignore exception for invalid version in P…

…arquetWriter
DataDog · Feb 4, 2020 · 9353658 · 9353658
1 parent 0326ea3
commit 9353658
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 2 deletions.
diff --git a/python/pyarrow/_parquet.pyx b/python/pyarrow/_parquet.pyx
@@ -1304,14 +1304,15 @@ cdef class ParquetWriter:
         else:
             props.disallow_truncated_timestamps()
 
-    cdef void _set_version(self, WriterProperties.Builder* props):
+    cdef int _set_version(self, WriterProperties.Builder* props) except -1:
         if self.version is not None:
             if self.version == "1.0":
                 props.version(ParquetVersion_V1)
             elif self.version == "2.0":
                 props.version(ParquetVersion_V2)
             else:
-                raise ArrowException("Unsupported Parquet format version")
+                raise ValueError("Unsupported Parquet format version: {0}"
+                                 .format(self.version))
 
     cdef void _set_compression_props(self, WriterProperties.Builder* props):
         if isinstance(self.compression, basestring):

diff --git a/python/pyarrow/tests/test_parquet.py b/python/pyarrow/tests/test_parquet.py
@@ -177,6 +177,12 @@ def test_pandas_parquet_2_0_roundtrip(tempdir, chunk_size):
     tm.assert_frame_equal(df, df_read)
 
 
+def test_parquet_invalid_version(tempdir):
+    table = pa.table({'a': [1, 2, 3]})
+    with pytest.raises(ValueError, match="Unsupported Parquet format version"):
+        _write_table(table, tempdir / 'test_version.parquet', version="2.2")
+
+
 def test_set_data_page_size():
     arr = pa.array([1, 2, 3] * 100000)
     t = pa.Table.from_arrays([arr], names=['f0'])