meetjunsu commented on a change in pull request #17542:
URL: https://github.com/apache/flink/pull/17542#discussion_r761628631
##########
File path:
flink-formats/flink-parquet/src/test/java/org/apache/flink/formats/parquet/row/ParquetRowDataWriterTest.java
##########
@@ -158,6 +190,65 @@ private void innerTest(Configuration conf, boolean
utcTimestamp) throws IOExcept
Assert.assertEquals(number, cnt);
}
+ public void complexTypeTest(Configuration conf, boolean utcTimestamp)
throws Exception {
+ Path path = new Path(TEMPORARY_FOLDER.newFolder().getPath(),
UUID.randomUUID().toString());
+ int number = 1000;
+ List<Row> rows = new ArrayList<>(number);
+ Map<String, String> mapData = new HashMap<>();
+ mapData.put("k1", "v1");
+ mapData.put(null, "v2");
+ mapData.put("k2", null);
+
+ for (int i = 0; i < number; i++) {
+ Integer v = i;
+ rows.add(Row.of(new Integer[] {v}, mapData,
Row.of(String.valueOf(v), v)));
+ }
+
+ ParquetWriterFactory<RowData> factory =
+ ParquetRowDataBuilder.createWriterFactory(ROW_TYPE_COMPLEX,
conf, utcTimestamp);
+ BulkWriter<RowData> writer =
+ factory.create(path.getFileSystem().create(path,
FileSystem.WriteMode.OVERWRITE));
+ for (int i = 0; i < number; i++) {
+ writer.addElement(CONVERTER_COMPLEX.toInternal(rows.get(i)));
+ }
+ writer.flush();
+ writer.finish();
+
+ File file = new File(path.getPath());
+ final List<Row> fileContent = readParquetFile(file);
+ assertEquals(rows, fileContent);
+ }
+
+ private static List<Row> readParquetFile(File file) throws IOException {
+ InputFile inFile =
+ HadoopInputFile.fromPath(
+ new org.apache.hadoop.fs.Path(file.toURI()), new
Configuration());
+
+ ArrayList<Row> results = new ArrayList<>();
+ try (ParquetReader<GenericRecord> reader =
+ AvroParquetReader.<GenericRecord>builder(inFile).build()) {
+ GenericRecord next;
+ while ((next = reader.read()) != null) {
+ Integer c0 = (Integer) ((ArrayList<GenericData.Record>)
next.get(0)).get(0).get(0);
+ HashMap<Utf8, Utf8> map = ((HashMap<Utf8, Utf8>) next.get(1));
+ String c21 = ((GenericData.Record)
next.get(2)).get(0).toString();
+ Integer c22 = (Integer) ((GenericData.Record)
next.get(2)).get(1);
+
+ Map<String, String> c1 = new HashMap<>();
+ for (Utf8 key : map.keySet()) {
+ String k = Strings.isEmpty(key) ? null : key.toString();
Review comment:
key is nullable, avro GenericRecord will auto convert null to empty
string.
--
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.
To unsubscribe, e-mail: issues-unsubscr...@flink.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
