GH-16161 Fix parquet export NPE

h2oai · Apr 23, 2024 · 6879ffd · 6879ffd
1 parent adeebb5
commit 6879ffd
Show file tree

Hide file tree

Showing 2 changed files with 26 additions and 1 deletion.
diff --git a/h2o-parsers/h2o-parquet-parser/src/main/java/water/parser/parquet/FrameParquetExporter.java b/h2o-parsers/h2o-parquet-parser/src/main/java/water/parser/parquet/FrameParquetExporter.java
@@ -112,7 +112,11 @@ public void map(Chunk[] cs) {
                                 group = group.append(currColName, cs[j].at8(i));
                                 break;
                             case (T_STR):
-                                group = group.append(currColName, cs[j].atStr(new BufferedString(), i).toString());
+                                if (cs[j].isNA(i)) {
+                                    group = group.append(currColName, "");
+                                } else {
+                                    group = group.append(currColName, cs[j].atStr(new BufferedString(), i).toString());
+                                } 
                                 break;
                             case (T_CAT):
                                 if (cs[j].isNA(i)) {

diff --git a/h2o-py/tests/testdir_misc/pyunit_export_parquet_npe.py b/h2o-py/tests/testdir_misc/pyunit_export_parquet_npe.py
@@ -0,0 +1,21 @@
+import sys
+import tempfile
+
+sys.path.insert(1, "../../../")
+import h2o
+from tests import pyunit_utils
+
+
+def test_export_file_npe_gh_16161():
+    with tempfile.TemporaryDirectory() as dir:
+        df = h2o.create_frame(rows=100, cols=10, string_fraction=0.1, seed=5, seed_for_column_types=25)
+        h2o.export_file(df, path=dir, format="parquet", write_checksum=False)
+
+
+if __name__ == "__main__":
+    pyunit_utils.standalone_test(test_export_file_npe_gh_16161)
+else:
+    test_export_file_npe_gh_16161()
+
+
+