Raise an error for invalid repetition levels when delimiting records

apache · Jan 7, 2025 · be347da · be347da
1 parent f41f590
commit be347da
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 1 deletion.
diff --git a/cpp/src/parquet/arrow/arrow_reader_writer_test.cc b/cpp/src/parquet/arrow/arrow_reader_writer_test.cc
@@ -3990,6 +3990,12 @@ TEST(TestArrowReaderAdHoc, CorruptedSchema) {
   TryReadDataFile(path, ::arrow::StatusCode::IOError);
 }
 
+TEST(TestArrowReaderAdHoc, InvalidRepetitionLevels) {
+  // GH-45185 - Repetition levels start with 1 instead of 0
+  auto path = test::get_data_file("ARROW-GH-45185.parquet", /*is_good=*/false);
+  TryReadDataFile(path, ::arrow::StatusCode::IOError);
+}
+
 TEST(TestArrowReaderAdHoc, LARGE_MEMORY_TEST(LargeStringColumn)) {
   // ARROW-3762
   ::arrow::StringBuilder builder;

diff --git a/cpp/src/parquet/column_reader.cc b/cpp/src/parquet/column_reader.cc
@@ -1603,7 +1603,12 @@ class TypedRecordReader : public TypedColumnReaderImpl<DType>,
     // another record start or exhausting the ColumnChunk
     int64_t level = levels_position_;
     if (at_record_start_) {
-      ARROW_DCHECK_EQ(0, rep_levels[levels_position_]);
+      if (rep_levels[levels_position_] != 0) {
+        std::stringstream ss;
+        ss << "The repetition level at the start of a record must be 0 but got "
+           << rep_levels[levels_position_];
+        throw ParquetException(ss.str());
+      }
       ++levels_position_;
       // We have decided to consume the level at this position; therefore we
       // must advance until we find another record boundary