Merge pull request #8879 from rapidsai/branch-21.08

[gpuCI] Forward-merge branch-21.08 to branch-21.10 [skip ci]
rapidsai · Jul 28, 2021 · 5d7c172 · 5d7c172
2 parents 279f9a4 + 452743f
commit 5d7c172
Show file tree

Hide file tree

Showing 3 changed files with 21 additions and 2 deletions.
diff --git a/cpp/src/io/orc/writer_impl.cu b/cpp/src/io/orc/writer_impl.cu
@@ -575,8 +575,8 @@ orc_streams writer::impl::create_streams(host_span<orc_column_view> columns,
         break;
       }
       case TypeKind::TIMESTAMP:
-        add_RLE_stream(gpu::CI_DATA, DATA, TypeKind::INT);
-        add_RLE_stream(gpu::CI_DATA2, SECONDARY, TypeKind::INT);
+        add_RLE_stream(gpu::CI_DATA, DATA, TypeKind::LONG);
+        add_RLE_stream(gpu::CI_DATA2, SECONDARY, TypeKind::LONG);
         column.set_orc_encoding(DIRECT_V2);
         break;
       case TypeKind::DECIMAL:

diff --git a/python/cudf/cudf/tests/data/orc/TestOrcFile.largeTimestamps.orc b/python/cudf/cudf/tests/data/orc/TestOrcFile.largeTimestamps.orc
diff --git a/python/cudf/cudf/tests/test_orc.py b/python/cudf/cudf/tests/test_orc.py
@@ -1152,3 +1152,22 @@ def test_chunked_orc_writer_lists():
 
     got = pa.orc.ORCFile(buffer).read().to_pandas()
     assert_eq(expect, got)
+
+
+def test_writer_timestamp_stream_size(datadir, tmpdir):
+    pdf_fname = datadir / "TestOrcFile.largeTimestamps.orc"
+    gdf_fname = tmpdir.join("gdf.orc")
+
+    try:
+        orcfile = pa.orc.ORCFile(pdf_fname)
+    except Exception as excpr:
+        if type(excpr).__name__ == "ArrowIOError":
+            pytest.skip(".orc file is not found")
+        else:
+            print(type(excpr).__name__)
+
+    expect = orcfile.read().to_pandas()
+    cudf.from_pandas(expect).to_orc(gdf_fname.strpath)
+    got = pa.orc.ORCFile(gdf_fname).read().to_pandas()
+
+    assert_eq(expect, got)