[GitHub] [arrow] pitrou commented on a change in pull request #8632: ARROW-10426: [C++] Allow writing large strings to Parquet

[GitBox <gi...@apache.org>]

pitrou commented on a change in pull request #8632:
URL: https://github.com/apache/arrow/pull/8632#discussion_r524188718



##########
File path: cpp/src/parquet/arrow/arrow_reader_writer_test.cc
##########
@@ -1135,14 +1172,50 @@ TEST_F(TestStringParquetIO, EmptyStringColumnRequiredWrite) {
   ASSERT_NO_FATAL_FAILURE(this->ReaderFromSink(&reader));
   ASSERT_NO_FATAL_FAILURE(this->ReadTableFromFile(std::move(reader), &out));
   ASSERT_EQ(1, out->num_columns());
-  ASSERT_EQ(100, out->num_rows());
+  ASSERT_EQ(table->num_rows(), out->num_rows());
 
   std::shared_ptr<ChunkedArray> chunked_array = out->column(0);
   ASSERT_EQ(1, chunked_array->num_chunks());
 
   AssertArraysEqual(*values, *chunked_array->chunk(0));
 }
 
+using TestLargeBinaryParquetIO = TestParquetIO<::arrow::LargeBinaryType>;
+
+TEST_F(TestLargeBinaryParquetIO, Basics) {
+  const char* json = "[\"foo\", \"\", null, \"\xff\"]";
+
+  const auto large_type = ::arrow::large_binary();
+  const auto narrow_type = ::arrow::binary();
+  const auto large_array = ::arrow::ArrayFromJSON(large_type, json);
+  const auto narrow_array = ::arrow::ArrayFromJSON(narrow_type, json);
+
+  this->RoundTripSingleColumn(large_array, narrow_array,
+                              default_arrow_writer_properties());
+  const auto arrow_properties =
+      ::parquet::ArrowWriterProperties::Builder().store_schema()->build();
+
+  this->RoundTripSingleColumn(large_array, large_array, arrow_properties);
+}
+
+using TestLargeStringParquetIO = TestParquetIO<::arrow::LargeStringType>;
+
+TEST_F(TestLargeStringParquetIO, Basics) {
+  const char* json = R"(["foo", "", null, "bar"])";
+
+  const auto large_type = ::arrow::large_utf8();
+  const auto narrow_type = ::arrow::utf8();
+  const auto large_array = ::arrow::ArrayFromJSON(large_type, json);
+  const auto narrow_array = ::arrow::ArrayFromJSON(narrow_type, json);
+
+  this->RoundTripSingleColumn(large_array, narrow_array,

Review comment:
       I'll add a comment indeed.




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org