HyukjinKwon commented on code in PR #46408: URL: https://github.com/apache/spark/pull/46408#discussion_r1594851880
########## sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/json/JsonSuite.scala: ########## @@ -3865,6 +3865,65 @@ abstract class JsonSuite } } } + + test("SPARK-48148: values are unchanged when read as string") { + withTempPath { path => + def extractData( + jsonString: String, + expectedInexactData: Seq[String], + expectedExactData: Seq[String], + multiLine: Boolean = false): Unit = { + Seq(jsonString).toDF() + .repartition(1) + .write + .mode("overwrite") + .text(path.getAbsolutePath) + + withClue("Exact string parsing") { + withSQLConf(SQLConf.JSON_EXACT_STRING_PARSING.key -> "true") { + val df = spark.read + .schema("data STRING") + .option("multiLine", multiLine.toString) + .json(path.getAbsolutePath) + checkAnswer(df, expectedExactData.map(d => Row(d))) + } + } + + withClue("Inexact string parsing") { + withSQLConf(SQLConf.JSON_EXACT_STRING_PARSING.key -> "false") { + val df = spark.read + .schema("data STRING") + .option("multiLine", multiLine.toString) + .json(path.getAbsolutePath) + checkAnswer(df, expectedInexactData.map(d => Row(d))) + } + } + } + extractData( + s"""{"data": {"white": "space"}}""", + expectedInexactData = Seq(s"""{"white":"space"}"""), + expectedExactData = Seq(s"""{"white": "space"}""") Review Comment: ```suggestion expectedExactData = Seq("""{"white": "space"}""") ``` ########## sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/json/JsonSuite.scala: ########## @@ -3865,6 +3865,65 @@ abstract class JsonSuite } } } + + test("SPARK-48148: values are unchanged when read as string") { + withTempPath { path => + def extractData( + jsonString: String, + expectedInexactData: Seq[String], + expectedExactData: Seq[String], + multiLine: Boolean = false): Unit = { + Seq(jsonString).toDF() + .repartition(1) + .write + .mode("overwrite") + .text(path.getAbsolutePath) + + withClue("Exact string parsing") { + withSQLConf(SQLConf.JSON_EXACT_STRING_PARSING.key -> "true") { + val df = spark.read + .schema("data STRING") + .option("multiLine", multiLine.toString) + .json(path.getAbsolutePath) + checkAnswer(df, expectedExactData.map(d => Row(d))) + } + } + + withClue("Inexact string parsing") { + withSQLConf(SQLConf.JSON_EXACT_STRING_PARSING.key -> "false") { + val df = spark.read + .schema("data STRING") + .option("multiLine", multiLine.toString) + .json(path.getAbsolutePath) + checkAnswer(df, expectedInexactData.map(d => Row(d))) + } + } + } + extractData( + s"""{"data": {"white": "space"}}""", + expectedInexactData = Seq(s"""{"white":"space"}"""), Review Comment: ```suggestion expectedInexactData = Seq("""{"white":"space"}"""), ``` ########## sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/json/JsonSuite.scala: ########## @@ -3865,6 +3865,65 @@ abstract class JsonSuite } } } + + test("SPARK-48148: values are unchanged when read as string") { + withTempPath { path => + def extractData( + jsonString: String, + expectedInexactData: Seq[String], + expectedExactData: Seq[String], + multiLine: Boolean = false): Unit = { + Seq(jsonString).toDF() + .repartition(1) + .write + .mode("overwrite") + .text(path.getAbsolutePath) + + withClue("Exact string parsing") { + withSQLConf(SQLConf.JSON_EXACT_STRING_PARSING.key -> "true") { + val df = spark.read + .schema("data STRING") + .option("multiLine", multiLine.toString) + .json(path.getAbsolutePath) + checkAnswer(df, expectedExactData.map(d => Row(d))) + } + } + + withClue("Inexact string parsing") { + withSQLConf(SQLConf.JSON_EXACT_STRING_PARSING.key -> "false") { + val df = spark.read + .schema("data STRING") + .option("multiLine", multiLine.toString) + .json(path.getAbsolutePath) + checkAnswer(df, expectedInexactData.map(d => Row(d))) + } + } + } + extractData( + s"""{"data": {"white": "space"}}""", Review Comment: ```suggestion """{"data": {"white": "space"}}""", ``` -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org