[SPARK-39212][SQL] Use double quotes for values of SQL configs/DS options in error messages

core/src/main/resources/error/error-classes.json

@@ -4,15 +4,15 @@
     "sqlState" : "42000"
   },
   "ARITHMETIC_OVERFLOW" : {
-    "message" : [ "<message>.<alternative> If necessary set <config> to false (except for ANSI interval type) to bypass this error.<context>" ],
+    "message" : [ "<message>.<alternative> If necessary set <config> to \"false\" (except for ANSI interval type) to bypass this error.<context>" ],
     "sqlState" : "22003"
   },
   "CANNOT_CAST_DATATYPE" : {
     "message" : [ "Cannot cast <sourceType> to <targetType>." ],
     "sqlState" : "22005"
   },
   "CANNOT_CHANGE_DECIMAL_PRECISION" : {
-    "message" : [ "<value> cannot be represented as Decimal(<precision>, <scale>). If necessary set <config> to false to bypass this error.<details>" ],
+    "message" : [ "<value> cannot be represented as Decimal(<precision>, <scale>). If necessary set <config> to \"false\" to bypass this error.<details>" ],
     "sqlState" : "22005"
   },
   "CANNOT_PARSE_DECIMAL" : {
@@ -23,11 +23,11 @@
     "message" : [ "Cannot up cast <value> from <sourceType> to <targetType>.\n<details>" ]
   },
   "CAST_INVALID_INPUT" : {
-    "message" : [ "The value <value> of the type <sourceType> cannot be cast to <targetType> because it is malformed. To return NULL instead, use `try_cast`. If necessary set <config> to false to bypass this error.<details>" ],
+    "message" : [ "The value <value> of the type <sourceType> cannot be cast to <targetType> because it is malformed. To return NULL instead, use `try_cast`. If necessary set <config> to \"false\" to bypass this error.<details>" ],
     "sqlState" : "42000"
   },
   "CAST_OVERFLOW" : {
-    "message" : [ "The value <value> of the type <sourceType> cannot be cast to <targetType> due to an overflow. To return NULL instead, use `try_cast`. If necessary set <config> to false to bypass this error." ],
+    "message" : [ "The value <value> of the type <sourceType> cannot be cast to <targetType> due to an overflow. To return NULL instead, use `try_cast`. If necessary set <config> to \"false\" to bypass this error." ],
     "sqlState" : "22005"
   },
   "CONCURRENT_QUERY" : {
@@ -38,7 +38,7 @@
     "sqlState" : "22008"
   },
   "DIVIDE_BY_ZERO" : {
-    "message" : [ "Division by zero. To return NULL instead, use `try_divide`. If necessary set <config> to false (except for ANSI interval type) to bypass this error.<details>" ],
+    "message" : [ "Division by zero. To return NULL instead, use `try_divide`. If necessary set <config> to \"false\" (except for ANSI interval type) to bypass this error.<details>" ],
     "sqlState" : "22012"
   },
   "DUPLICATE_KEY" : {
@@ -86,19 +86,19 @@
     "message" : [ "You may get a different result due to the upgrading to" ],
     "subClass" : {
       "DATETIME_PATTERN_RECOGNITION" : {
-        "message" : [ " Spark >= 3.0: \nFail to recognize <pattern> pattern in the DateTimeFormatter. 1) You can set <config> to 'LEGACY' to restore the behavior before Spark 3.0. 2) You can form a valid datetime pattern with the guide from https://spark.apache.org/docs/latest/sql-ref-datetime-pattern.html" ]
+        "message" : [ " Spark >= 3.0: \nFail to recognize <pattern> pattern in the DateTimeFormatter. 1) You can set <config> to \"LEGACY\" to restore the behavior before Spark 3.0. 2) You can form a valid datetime pattern with the guide from https://spark.apache.org/docs/latest/sql-ref-datetime-pattern.html" ]
       },
       "FORMAT_DATETIME_BY_NEW_PARSER" : {
-        "message" : [ " Spark >= 3.0: \nFail to format it to <resultCandidate> in the new formatter. You can set\n<config> to 'LEGACY' to restore the behavior before\nSpark 3.0, or set to 'CORRECTED' and treat it as an invalid datetime string.\n" ]
+        "message" : [ " Spark >= 3.0: \nFail to format it to <resultCandidate> in the new formatter. You can set\n<config> to \"LEGACY\" to restore the behavior before\nSpark 3.0, or set to \"CORRECTED\" and treat it as an invalid datetime string.\n" ]
       },
       "PARSE_DATETIME_BY_NEW_PARSER" : {
-        "message" : [ " Spark >= 3.0: \nFail to parse <datetime> in the new parser. You can set <config> to 'LEGACY' to restore the behavior before Spark 3.0, or set to 'CORRECTED' and treat it as an invalid datetime string." ]
+        "message" : [ " Spark >= 3.0: \nFail to parse <datetime> in the new parser. You can set <config> to \"LEGACY\" to restore the behavior before Spark 3.0, or set to \"CORRECTED\" and treat it as an invalid datetime string." ]
       },
       "READ_ANCIENT_DATETIME" : {
-        "message" : [ " Spark >= 3.0: \nreading dates before 1582-10-15 or timestamps before 1900-01-01T00:00:00Z\nfrom <format> files can be ambiguous, as the files may be written by\nSpark 2.x or legacy versions of Hive, which uses a legacy hybrid calendar\nthat is different from Spark 3.0+'s Proleptic Gregorian calendar.\nSee more details in SPARK-31404. You can set the SQL config <config> or\nthe datasource option '<option>' to 'LEGACY' to rebase the datetime values\nw.r.t. the calendar difference during reading. To read the datetime values\nas it is, set the SQL config <config> or the datasource option '<option>'\nto 'CORRECTED'.\n" ]
+        "message" : [ " Spark >= 3.0: \nreading dates before 1582-10-15 or timestamps before 1900-01-01T00:00:00Z\nfrom <format> files can be ambiguous, as the files may be written by\nSpark 2.x or legacy versions of Hive, which uses a legacy hybrid calendar\nthat is different from Spark 3.0+'s Proleptic Gregorian calendar.\nSee more details in SPARK-31404. You can set the SQL config <config> or\nthe datasource option <option> to \"LEGACY\" to rebase the datetime values\nw.r.t. the calendar difference during reading. To read the datetime values\nas it is, set the SQL config <config> or the datasource option <option>\nto \"CORRECTED\".\n" ]
       },
       "WRITE_ANCIENT_DATETIME" : {
-        "message" : [ " Spark >= 3.0: \nwriting dates before 1582-10-15 or timestamps before 1900-01-01T00:00:00Z\ninto <format> files can be dangerous, as the files may be read by Spark 2.x\nor legacy versions of Hive later, which uses a legacy hybrid calendar that\nis different from Spark 3.0+'s Proleptic Gregorian calendar. See more\ndetails in SPARK-31404. You can set <config> to 'LEGACY' to rebase the\ndatetime values w.r.t. the calendar difference during writing, to get maximum\ninteroperability. Or set <config> to 'CORRECTED' to write the datetime\nvalues as it is, if you are sure that the written files will only be read by\nSpark 3.0+ or other systems that use Proleptic Gregorian calendar.\n" ]
+        "message" : [ " Spark >= 3.0: \nwriting dates before 1582-10-15 or timestamps before 1900-01-01T00:00:00Z\ninto <format> files can be dangerous, as the files may be read by Spark 2.x\nor legacy versions of Hive later, which uses a legacy hybrid calendar that\nis different from Spark 3.0+'s Proleptic Gregorian calendar. See more\ndetails in SPARK-31404. You can set <config> to \"LEGACY\" to rebase the\ndatetime values w.r.t. the calendar difference during writing, to get maximum\ninteroperability. Or set <config> to \"CORRECTED\" to write the datetime\nvalues as it is, if you are sure that the written files will only be read by\nSpark 3.0+ or other systems that use Proleptic Gregorian calendar.\n" ]
       }
     }
   },
@@ -110,17 +110,17 @@
     "message" : [ "<message>" ]
   },
   "INVALID_ARRAY_INDEX" : {
-    "message" : [ "The index <indexValue> is out of bounds. The array has <arraySize> elements. If necessary set <config> to false to bypass this error." ]
+    "message" : [ "The index <indexValue> is out of bounds. The array has <arraySize> elements. If necessary set <config> to \"false\" to bypass this error." ]
   },
   "INVALID_ARRAY_INDEX_IN_ELEMENT_AT" : {
-    "message" : [ "The index <indexValue> is out of bounds. The array has <arraySize> elements. To return NULL instead, use `try_element_at`. If necessary set <config> to false to bypass this error." ]
+    "message" : [ "The index <indexValue> is out of bounds. The array has <arraySize> elements. To return NULL instead, use `try_element_at`. If necessary set <config> to \"false\" to bypass this error." ]
   },
   "INVALID_FIELD_NAME" : {
     "message" : [ "Field name <fieldName> is invalid: <path> is not a struct." ],
     "sqlState" : "42000"
   },
   "INVALID_FRACTION_OF_SECOND" : {
-    "message" : [ "The fraction of sec must be zero. Valid range is [0, 60]. If necessary set <config> to false to bypass this error. " ],
+    "message" : [ "The fraction of sec must be zero. Valid range is [0, 60]. If necessary set <config> to \"false\" to bypass this error. " ],
     "sqlState" : "22023"
   },
   "INVALID_JSON_SCHEMA_MAP_TYPE" : {
@@ -138,7 +138,7 @@
     "sqlState" : "42000"
   },
   "MAP_KEY_DOES_NOT_EXIST" : {
-    "message" : [ "Key <keyValue> does not exist. To return NULL instead, use 'try_element_at'. If necessary set <config> to false to bypass this error.<details>" ]
+    "message" : [ "Key <keyValue> does not exist. To return NULL instead, use `try_element_at`. If necessary set <config> to \"false\" to bypass this error.<details>" ]
   },
   "MISSING_COLUMN" : {
     "message" : [ "Column '<columnName>' does not exist. Did you mean one of the following? [<proposal>]" ],
@@ -289,7 +289,7 @@
     }
   },
   "UNTYPED_SCALA_UDF" : {
-    "message" : [ "You're using untyped Scala UDF, which does not have the input type information. Spark may blindly pass null to the Scala closure with primitive-type argument, and the closure will see the default value of the Java type for the null argument, e.g. `udf((x: Int) => x, IntegerType)`, the result is 0 for null input. To get rid of this error, you could:\n1. use typed Scala UDF APIs(without return type parameter), e.g. `udf((x: Int) => x)`\n2. use Java UDF APIs, e.g. `udf(new UDF1[String, Integer] { override def call(s: String): Integer = s.length() }, IntegerType)`, if input types are all non primitive\n3. set \"spark.sql.legacy.allowUntypedScalaUDF\" to true and use this API with caution" ]
+    "message" : [ "You're using untyped Scala UDF, which does not have the input type information. Spark may blindly pass null to the Scala closure with primitive-type argument, and the closure will see the default value of the Java type for the null argument, e.g. `udf((x: Int) => x, IntegerType)`, the result is 0 for null input. To get rid of this error, you could:\n1. use typed Scala UDF APIs(without return type parameter), e.g. `udf((x: Int) => x)`\n2. use Java UDF APIs, e.g. `udf(new UDF1[String, Integer] { override def call(s: String): Integer = s.length() }, IntegerType)`, if input types are all non primitive\n3. set \"spark.sql.legacy.allowUntypedScalaUDF\" to \"true\" and use this API with caution" ]
   },
   "WRITING_JOB_ABORTED" : {
     "message" : [ "Writing job aborted" ],

core/src/test/scala/org/apache/spark/SparkThrowableSuite.scala

@@ -126,7 +126,7 @@ class SparkThrowableSuite extends SparkFunSuite {
     // Does not fail with too many args (expects 0 args)
     assert(getMessage("DIVIDE_BY_ZERO", Array("foo", "bar", "baz")) ==
       "[DIVIDE_BY_ZERO] Division by zero. " +
-      "To return NULL instead, use `try_divide`. If necessary set foo to false " +
+      "To return NULL instead, use `try_divide`. If necessary set foo to \"false\" " +
         "(except for ANSI interval type) to bypass this error.bar")
   }
 

sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryErrorsBase.scala

@@ -67,4 +67,8 @@ trait QueryErrorsBase {
   def toSQLConf(conf: String): String = {
     quoteByDefault(conf)
   }
+
+  def toDSOption(option: String): String = {
+    quoteByDefault(option)
+  }
 }

sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala

@@ -214,8 +214,12 @@ object QueryExecutionErrors extends QueryErrorsBase {
   }
 
   def mapKeyNotExistError(key: Any, dataType: DataType, context: String): NoSuchElementException = {
-    new SparkNoSuchElementException(errorClass = "MAP_KEY_DOES_NOT_EXIST",
-      messageParameters = Array(toSQLValue(key, dataType), SQLConf.ANSI_ENABLED.key, context))
+    new SparkNoSuchElementException(
+      errorClass = "MAP_KEY_DOES_NOT_EXIST",
+      messageParameters = Array(
+        toSQLValue(key, dataType),
+        toSQLConf(SQLConf.ANSI_ENABLED.key),
+        context))
   }
 
   def invalidFractionOfSecondError(): DateTimeException = {
@@ -557,9 +561,9 @@ object QueryExecutionErrors extends QueryErrorsBase {
         "READ_ANCIENT_DATETIME",
         format,
         toSQLConf(config),
-        option,
+        toDSOption(option),
         toSQLConf(config),
-        option),
+        toDSOption(option)),
       cause = null
     )
   }

sql/core/src/test/resources/sql-tests/results/ansi/array.sql.out

@@ -168,7 +168,7 @@ select element_at(array(1, 2, 3), 5)
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX_IN_ELEMENT_AT] The index 5 is out of bounds. The array has 3 elements. To return NULL instead, use `try_element_at`. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX_IN_ELEMENT_AT] The index 5 is out of bounds. The array has 3 elements. To return NULL instead, use `try_element_at`. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
 
 
 -- !query
@@ -177,7 +177,7 @@ select element_at(array(1, 2, 3), -5)
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX_IN_ELEMENT_AT] The index -5 is out of bounds. The array has 3 elements. To return NULL instead, use `try_element_at`. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX_IN_ELEMENT_AT] The index -5 is out of bounds. The array has 3 elements. To return NULL instead, use `try_element_at`. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
 
 
 -- !query
@@ -195,7 +195,7 @@ select elt(4, '123', '456')
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX] The index 4 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX] The index 4 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
 
 
 -- !query
@@ -204,7 +204,7 @@ select elt(0, '123', '456')
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX] The index 0 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX] The index 0 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
 
 
 -- !query
@@ -213,7 +213,7 @@ select elt(-1, '123', '456')
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX] The index -1 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX] The index -1 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
 
 
 -- !query
@@ -254,7 +254,7 @@ select array(1, 2, 3)[5]
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX] The index 5 is out of bounds. The array has 3 elements. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX] The index 5 is out of bounds. The array has 3 elements. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
 
 
 -- !query
@@ -263,7 +263,7 @@ select array(1, 2, 3)[-1]
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX] The index -1 is out of bounds. The array has 3 elements. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX] The index -1 is out of bounds. The array has 3 elements. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
 
 
 -- !query
@@ -337,7 +337,7 @@ select element_at(array(1, 2, 3), 5)
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX_IN_ELEMENT_AT] The index 5 is out of bounds. The array has 3 elements. To return NULL instead, use `try_element_at`. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX_IN_ELEMENT_AT] The index 5 is out of bounds. The array has 3 elements. To return NULL instead, use `try_element_at`. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
 
 
 -- !query
@@ -346,7 +346,7 @@ select element_at(array(1, 2, 3), -5)
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX_IN_ELEMENT_AT] The index -5 is out of bounds. The array has 3 elements. To return NULL instead, use `try_element_at`. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX_IN_ELEMENT_AT] The index -5 is out of bounds. The array has 3 elements. To return NULL instead, use `try_element_at`. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
 
 
 -- !query
@@ -364,7 +364,7 @@ select elt(4, '123', '456')
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX] The index 4 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX] The index 4 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
 
 
 -- !query
@@ -373,7 +373,7 @@ select elt(0, '123', '456')
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX] The index 0 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX] The index 0 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
 
 
 -- !query
@@ -382,4 +382,4 @@ select elt(-1, '123', '456')
 struct<>
 -- !query output
 org.apache.spark.SparkArrayIndexOutOfBoundsException
-[INVALID_ARRAY_INDEX] The index -1 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to false to bypass this error.
+[INVALID_ARRAY_INDEX] The index -1 is out of bounds. The array has 2 elements. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.