sunchao commented on pull request #34308:
URL: https://github.com/apache/spark/pull/34308#issuecomment-962137740
Oops sorry @AngersZhuuuu . Maybe we can try the following then:
```scala
test("XXX") {
val data = (0 to 10).flatMap(n => Seq.fill(10)(n)).map(i => (i,
i.toString))
withParquetFile(data) { dir =>
val file = SpecificParquetRecordReaderBase.listDirectory(new
File(dir)).get(0)
val filePath = new Path(file)
val reader = ParquetFileReader.open(HadoopInputFile.fromPath(filePath,
new Configuration))
try {
val descriptor = reader.getFileMetaData.getSchema.getColumns.get(0)
val pages = reader.readNextRowGroup().getPageReader(descriptor)
val dictionaryPage = pages.readDictionaryPage()
assert(dictionaryPage != null, "dictionaryPage shouldn't be null")
val dictionary =
dictionaryPage.getEncoding.initDictionary(descriptor, dictionaryPage)
val parquetDictionary = new ParquetDictionary(dictionary, file, true)
val msg = intercept[UnsupportedOperationException] {
parquetDictionary.decodeToInt(0)
}.getMessage
assert(msg.contains("Decoding to Int is not supported"))
} finally {
reader.close()
}
}
}
```
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
