Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/20937#discussion_r184851348
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/json/JsonSuite.scala
---
@@ -2167,4 +2167,259 @@ class JsonSuite extends QueryTest with
SharedSQLContext with TestJsonData {
val sampled = spark.read.option("samplingRatio", 1.0).json(ds)
assert(sampled.count() == ds.count())
}
+
+ def testFile(fileName: String): String = {
+
Thread.currentThread().getContextClassLoader.getResource(fileName).toString
+ }
+
+ test("SPARK-23723: json in UTF-16 with BOM") {
+ val fileName = "json-tests/utf16WithBOM.json"
+ val schema = new StructType().add("firstName",
StringType).add("lastName", StringType)
+ val jsonDF = spark.read.schema(schema)
+ .option("multiline", "true")
+ .option("encoding", "UTF-16")
+ .json(testFile(fileName))
+
+ checkAnswer(jsonDF, Seq(Row("Chris", "Baird"), Row("Doug", "Rood")))
+ }
+
+ test("SPARK-23723: multi-line json in UTF-32BE with BOM") {
+ val fileName = "json-tests/utf32BEWithBOM.json"
+ val schema = new StructType().add("firstName",
StringType).add("lastName", StringType)
+ val jsonDF = spark.read.schema(schema)
+ .option("multiline", "true")
+ .json(testFile(fileName))
+
+ checkAnswer(jsonDF, Seq(Row("Chris", "Baird")))
+ }
+
+ test("SPARK-23723: Use user's encoding in reading of multi-line json in
UTF-16LE") {
+ val fileName = "json-tests/utf16LE.json"
+ val schema = new StructType().add("firstName",
StringType).add("lastName", StringType)
+ val jsonDF = spark.read.schema(schema)
+ .option("multiline", "true")
+ .options(Map("encoding" -> "UTF-16LE"))
+ .json(testFile(fileName))
+
+ checkAnswer(jsonDF, Seq(Row("Chris", "Baird")))
+ }
+
+ test("SPARK-23723: Unsupported encoding name") {
+ val invalidCharset = "UTF-128"
+ val exception = intercept[UnsupportedCharsetException] {
+ spark.read
+ .options(Map("encoding" -> invalidCharset, "lineSep" -> "\n"))
+ .json(testFile("json-tests/utf16LE.json"))
+ .count()
+ }
+
+ assert(exception.getMessage.contains(invalidCharset))
+ }
+
+ test("SPARK-23723: checking that the encoding option is case agnostic") {
+ val fileName = "json-tests/utf16LE.json"
+ val schema = new StructType().add("firstName",
StringType).add("lastName", StringType)
+ val jsonDF = spark.read.schema(schema)
+ .option("multiline", "true")
+ .options(Map("encoding" -> "uTf-16lE"))
+ .json(testFile(fileName))
+
+ checkAnswer(jsonDF, Seq(Row("Chris", "Baird")))
+ }
+
+
+ test("SPARK-23723: specified encoding is not matched to actual
encoding") {
+ val fileName = "json-tests/utf16LE.json"
+ val schema = new StructType().add("firstName",
StringType).add("lastName", StringType)
+ val exception = intercept[SparkException] {
+ spark.read.schema(schema)
+ .option("mode", "FAILFAST")
+ .option("multiline", "true")
+ .options(Map("encoding" -> "UTF-16BE"))
+ .json(testFile(fileName))
+ .count()
+ }
+ val errMsg = exception.getMessage
+
+ assert(errMsg.contains("Malformed records are detected in record
parsing"))
+ }
+
+ def checkEncoding(
+ expectedEncoding: String,
+ pathToJsonFiles: String,
+ expectedContent: String): Unit = {
+ val jsonFiles = new File(pathToJsonFiles)
+ .listFiles()
+ .filter(_.isFile)
+ .filter(_.getName.endsWith("json"))
+ val actualContent = jsonFiles.map { file =>
+ new String(Files.readAllBytes(file.toPath), expectedEncoding)
+ }.mkString.trim.replaceAll(" ", "")
+
+ assert(actualContent == expectedContent)
+ }
+
+ test("SPARK-23723: save json in UTF-32BE") {
+ val encoding = "UTF-32BE"
+ withTempPath { path =>
+ val df = spark.createDataset(Seq(("Dog", 42)))
+ df.write
+ .options(Map("encoding" -> encoding, "lineSep" -> "\n"))
+ .format("json").mode("overwrite")
--- End diff --
I think `.mode("overwrite")` is not needed.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
