You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by ma...@apache.org on 2022/11/28 17:26:47 UTC
[spark] branch master updated: [SPARK-41180][SQL] Reuse `INVALID_SCHEMA` instead of `_LEGACY_ERROR_TEMP_1227`
This is an automated email from the ASF dual-hosted git repository.
maxgekk pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new bdb4d5e4da5 [SPARK-41180][SQL] Reuse `INVALID_SCHEMA` instead of `_LEGACY_ERROR_TEMP_1227`
bdb4d5e4da5 is described below
commit bdb4d5e4da558775df2be712dd8760d5f5f14747
Author: yangjie01 <ya...@baidu.com>
AuthorDate: Mon Nov 28 20:26:27 2022 +0300
[SPARK-41180][SQL] Reuse `INVALID_SCHEMA` instead of `_LEGACY_ERROR_TEMP_1227`
### What changes were proposed in this pull request?
This pr aims rename `_LEGACY_ERROR_TEMP_1227` to `INVALID_SCHEMA`
### Why are the changes needed?
Proper names of error classes to improve user experience with Spark SQL.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Pass GitHub Actions
Closes #38754 from LuciferYang/SPARK-41180.
Lead-authored-by: yangjie01 <ya...@baidu.com>
Co-authored-by: YangJie <ya...@baidu.com>
Signed-off-by: Max Gekk <ma...@gmail.com>
---
core/src/main/resources/error/error-classes.json | 23 ++++---
project/MimaExcludes.scala | 5 +-
.../spark/sql/catalyst/expressions/ExprUtils.scala | 2 +-
.../spark/sql/errors/QueryCompilationErrors.scala | 23 ++++---
.../apache/spark/sql/errors/QueryErrorsBase.scala | 4 ++
.../org/apache/spark/sql/types/DataType.scala | 13 ++--
.../scala/org/apache/spark/sql/functions.scala | 1 -
.../sql-tests/results/csv-functions.sql.out | 12 ++--
.../sql-tests/results/json-functions.sql.out | 12 ++--
.../org/apache/spark/sql/CsvFunctionsSuite.scala | 4 +-
.../apache/spark/sql/DataFrameFunctionsSuite.scala | 4 +-
.../org/apache/spark/sql/JsonFunctionsSuite.scala | 73 ++++++++++++++++------
12 files changed, 115 insertions(+), 61 deletions(-)
diff --git a/core/src/main/resources/error/error-classes.json b/core/src/main/resources/error/error-classes.json
index 9f4337d0618..89728777201 100644
--- a/core/src/main/resources/error/error-classes.json
+++ b/core/src/main/resources/error/error-classes.json
@@ -780,8 +780,21 @@
},
"INVALID_SCHEMA" : {
"message" : [
- "The expression <expr> is not a valid schema string."
- ]
+ "The input schema <inputSchema> is not a valid schema string."
+ ],
+ "subClass" : {
+ "NON_STRING_LITERAL" : {
+ "message" : [
+ "The input expression must be string literal and not null."
+ ]
+ },
+ "PARSE_ERROR" : {
+ "message" : [
+ "Cannot parse the schema:",
+ "<reason>"
+ ]
+ }
+ }
},
"INVALID_SQL_SYNTAX" : {
"message" : [
@@ -2844,12 +2857,6 @@
"The SQL config '<configName>' was removed in the version <version>. <comment>"
]
},
- "_LEGACY_ERROR_TEMP_1227" : {
- "message" : [
- "<msg><e1>",
- "Failed fallback parsing: <e2>"
- ]
- },
"_LEGACY_ERROR_TEMP_1228" : {
"message" : [
"Decimal scale (<scale>) cannot be greater than precision (<precision>)."
diff --git a/project/MimaExcludes.scala b/project/MimaExcludes.scala
index d8f87a504fa..eed79d1f204 100644
--- a/project/MimaExcludes.scala
+++ b/project/MimaExcludes.scala
@@ -120,7 +120,10 @@ object MimaExcludes {
ProblemFilters.exclude[IncompatibleMethTypeProblem]("org.apache.spark.storage.ShuffleBlockFetcherIterator#FetchRequest.apply"),
// [SPARK-41072][SS] Add the error class STREAM_FAILED to StreamingQueryException
- ProblemFilters.exclude[DirectMissingMethodProblem]("org.apache.spark.sql.streaming.StreamingQueryException.this")
+ ProblemFilters.exclude[DirectMissingMethodProblem]("org.apache.spark.sql.streaming.StreamingQueryException.this"),
+
+ // [SPARK-41180][SQL] Reuse INVALID_SCHEMA instead of _LEGACY_ERROR_TEMP_1227
+ ProblemFilters.exclude[DirectMissingMethodProblem]("org.apache.spark.sql.types.DataType.parseTypeWithFallback")
)
// Defulat exclude rules
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExprUtils.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExprUtils.scala
index 3e10b820aa6..e9084442b22 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExprUtils.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExprUtils.scala
@@ -35,7 +35,7 @@ object ExprUtils extends QueryErrorsBase {
case s: UTF8String if s != null =>
val dataType = DataType.fromDDL(s.toString)
CharVarcharUtils.failIfHasCharVarchar(dataType)
- case _ => throw QueryCompilationErrors.invalidSchemaStringError(exp)
+ case _ => throw QueryCompilationErrors.unexpectedSchemaTypeError(exp)
}
} else {
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
index 486bd21b844..ce99bf4aa47 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
@@ -993,10 +993,20 @@ private[sql] object QueryCompilationErrors extends QueryErrorsBase {
messageParameters = Map("key" -> key, "details" -> details))
}
- def invalidSchemaStringError(exp: Expression): Throwable = {
+ def schemaFailToParseError(schema: String, e: Throwable): Throwable = {
new AnalysisException(
- errorClass = "INVALID_SCHEMA",
- messageParameters = Map("expr" -> toSQLExpr(exp)))
+ errorClass = "INVALID_SCHEMA.PARSE_ERROR",
+ messageParameters = Map(
+ "inputSchema" -> toSQLSchema(schema),
+ "reason" -> e.getMessage
+ ),
+ cause = Some(e))
+ }
+
+ def unexpectedSchemaTypeError(exp: Expression): Throwable = {
+ new AnalysisException(
+ errorClass = "INVALID_SCHEMA.NON_STRING_LITERAL",
+ messageParameters = Map("inputSchema" -> toSQLExpr(exp)))
}
def schemaNotFoldableError(exp: Expression): Throwable = {
@@ -2229,13 +2239,6 @@ private[sql] object QueryCompilationErrors extends QueryErrorsBase {
"comment" -> comment))
}
- def failedFallbackParsingError(msg: String, e1: Throwable, e2: Throwable): Throwable = {
- new AnalysisException(
- errorClass = "_LEGACY_ERROR_TEMP_1227",
- messageParameters = Map("msg" -> msg, "e1" -> e1.getMessage, "e2" -> e2.getMessage),
- cause = Some(e1.getCause))
- }
-
def decimalCannotGreaterThanPrecisionError(scale: Int, precision: Int): Throwable = {
new AnalysisException(
errorClass = "_LEGACY_ERROR_TEMP_1228",
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryErrorsBase.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryErrorsBase.scala
index 560c7d9beb9..5460de77a14 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryErrorsBase.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryErrorsBase.scala
@@ -104,6 +104,10 @@ private[sql] trait QueryErrorsBase {
quoteByDefault(toPrettySQL(e))
}
+ def toSQLSchema(schema: String): String = {
+ quoteByDefault(schema)
+ }
+
def getSummary(sqlContext: SQLQueryContext): String = {
if (sqlContext == null) "" else sqlContext.summary
}
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/types/DataType.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/types/DataType.scala
index ef7f1553be9..ecd1cc77515 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/types/DataType.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/types/DataType.scala
@@ -27,6 +27,7 @@ import org.json4s.JsonAST.JValue
import org.json4s.JsonDSL._
import org.json4s.jackson.JsonMethods._
+import org.apache.spark.SparkThrowable
import org.apache.spark.annotation.Stable
import org.apache.spark.sql.catalyst.analysis.Resolver
import org.apache.spark.sql.catalyst.expressions.{Cast, Expression}
@@ -133,7 +134,6 @@ object DataType {
parseTypeWithFallback(
ddl,
CatalystSqlParser.parseDataType,
- "Cannot parse the data type: ",
fallbackParser = str => CatalystSqlParser.parseTableSchema(str))
}
@@ -144,24 +144,25 @@ object DataType {
*
* @param schema The schema string to parse by `parser` or `fallbackParser`.
* @param parser The function that should be invoke firstly.
- * @param errorMsg The error message for `parser`.
* @param fallbackParser The function that is called when `parser` fails.
* @return The data type parsed from the `schema` schema.
*/
def parseTypeWithFallback(
schema: String,
parser: String => DataType,
- errorMsg: String,
fallbackParser: String => DataType): DataType = {
try {
parser(schema)
} catch {
- case NonFatal(e1) =>
+ case NonFatal(e) =>
try {
fallbackParser(schema)
} catch {
- case NonFatal(e2) =>
- throw QueryCompilationErrors.failedFallbackParsingError(errorMsg, e1, e2)
+ case NonFatal(_) =>
+ if (e.isInstanceOf[SparkThrowable]) {
+ throw e
+ }
+ throw QueryCompilationErrors.schemaFailToParseError(schema, e)
}
}
}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
index f38f24920fa..dc47e358341 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
@@ -4563,7 +4563,6 @@ object functions {
val dataType = parseTypeWithFallback(
schema,
DataType.fromJson,
- "Cannot parse the schema in JSON format: ",
fallbackParser = DataType.fromDDL)
from_json(e, dataType, options)
}
diff --git a/sql/core/src/test/resources/sql-tests/results/csv-functions.sql.out b/sql/core/src/test/resources/sql-tests/results/csv-functions.sql.out
index 200ddd837e1..bddd8ccc37c 100644
--- a/sql/core/src/test/resources/sql-tests/results/csv-functions.sql.out
+++ b/sql/core/src/test/resources/sql-tests/results/csv-functions.sql.out
@@ -22,9 +22,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "INVALID_SCHEMA",
+ "errorClass" : "INVALID_SCHEMA.NON_STRING_LITERAL",
"messageParameters" : {
- "expr" : "\"1\""
+ "inputSchema" : "\"1\""
},
"queryContext" : [ {
"objectType" : "",
@@ -43,11 +43,11 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_1227",
+ "errorClass" : "PARSE_SYNTAX_ERROR",
+ "sqlState" : "42000",
"messageParameters" : {
- "e1" : "\n[PARSE_SYNTAX_ERROR] Syntax error at or near 'InvalidType': extra input 'InvalidType'(line 1, pos 2)\n\n== SQL ==\na InvalidType\n--^^^\n",
- "e2" : "\nDataType invalidtype is not supported.(line 1, pos 2)\n\n== SQL ==\na InvalidType\n--^^^\n",
- "msg" : "Cannot parse the data type: "
+ "error" : "'InvalidType'",
+ "hint" : ": extra input 'InvalidType'"
},
"queryContext" : [ {
"objectType" : "",
diff --git a/sql/core/src/test/resources/sql-tests/results/json-functions.sql.out b/sql/core/src/test/resources/sql-tests/results/json-functions.sql.out
index a9c4dd0b9fd..c8c8bee3925 100644
--- a/sql/core/src/test/resources/sql-tests/results/json-functions.sql.out
+++ b/sql/core/src/test/resources/sql-tests/results/json-functions.sql.out
@@ -148,9 +148,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "INVALID_SCHEMA",
+ "errorClass" : "INVALID_SCHEMA.NON_STRING_LITERAL",
"messageParameters" : {
- "expr" : "\"1\""
+ "inputSchema" : "\"1\""
},
"queryContext" : [ {
"objectType" : "",
@@ -169,11 +169,11 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_1227",
+ "errorClass" : "PARSE_SYNTAX_ERROR",
+ "sqlState" : "42000",
"messageParameters" : {
- "e1" : "\n[PARSE_SYNTAX_ERROR] Syntax error at or near 'InvalidType': extra input 'InvalidType'(line 1, pos 2)\n\n== SQL ==\na InvalidType\n--^^^\n",
- "e2" : "\nDataType invalidtype is not supported.(line 1, pos 2)\n\n== SQL ==\na InvalidType\n--^^^\n",
- "msg" : "Cannot parse the data type: "
+ "error" : "'InvalidType'",
+ "hint" : ": extra input 'InvalidType'"
},
"queryContext" : [ {
"objectType" : "",
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/CsvFunctionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/CsvFunctionsSuite.scala
index 2a3058d9395..940eaaed6ac 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/CsvFunctionsSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/CsvFunctionsSuite.scala
@@ -367,8 +367,8 @@ class CsvFunctionsSuite extends QueryTest with SharedSparkSession {
exception = intercept[AnalysisException] {
Seq("1").toDF("csv").select(from_csv($"csv", lit(1), options)).collect()
},
- errorClass = "INVALID_SCHEMA",
- parameters = Map("expr" -> "\"1\"")
+ errorClass = "INVALID_SCHEMA.NON_STRING_LITERAL",
+ parameters = Map("inputSchema" -> "\"1\"")
)
}
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala
index e9455ea51c1..2b747735f18 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala
@@ -5226,9 +5226,9 @@ class DataFrameFunctionsSuite extends QueryTest with SharedSparkSession {
exception = intercept[AnalysisException] {
sql("select from_json('{\"a\":1}', 1)")
},
- errorClass = "INVALID_SCHEMA",
+ errorClass = "INVALID_SCHEMA.NON_STRING_LITERAL",
parameters = Map(
- "expr" -> "\"1\""
+ "inputSchema" -> "\"1\""
),
context = ExpectedContext(
fragment = "from_json('{\"a\":1}', 1)",
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala
index 56bdefc98ba..800a602425b 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala
@@ -443,8 +443,8 @@ class JsonFunctionsSuite extends QueryTest with SharedSparkSession {
exception = intercept[AnalysisException] {
df3.selectExpr("from_json(value, 1)")
},
- errorClass = "INVALID_SCHEMA",
- parameters = Map("expr" -> "\"1\""),
+ errorClass = "INVALID_SCHEMA.NON_STRING_LITERAL",
+ parameters = Map("inputSchema" -> "\"1\""),
context = ExpectedContext(
fragment = "from_json(value, 1)",
start = 0,
@@ -452,10 +452,22 @@ class JsonFunctionsSuite extends QueryTest with SharedSparkSession {
)
)
- val errMsg2 = intercept[AnalysisException] {
- df3.selectExpr("""from_json(value, 'time InvalidType')""")
- }
- assert(errMsg2.getMessage.contains("DataType invalidtype is not supported"))
+ checkError(
+ exception = intercept[AnalysisException] {
+ df3.selectExpr("""from_json(value, 'time InvalidType')""")
+ },
+ errorClass = "PARSE_SYNTAX_ERROR",
+ sqlState = "42000",
+ parameters = Map(
+ "error" -> "'InvalidType'",
+ "hint" -> ": extra input 'InvalidType'"
+ ),
+ context = ExpectedContext(
+ fragment = "from_json(value, 'time InvalidType')",
+ start = 0,
+ stop = 35
+ )
+ )
checkError(
exception = intercept[AnalysisException] {
df3.selectExpr("from_json(value, 'time Timestamp', named_struct('a', 1))")
@@ -991,22 +1003,47 @@ class JsonFunctionsSuite extends QueryTest with SharedSparkSession {
test("SPARK-33286: from_json - combined error messages") {
val df = Seq("""{"a":1}""").toDF("json")
val invalidJsonSchema = """{"fields": [{"a":123}], "type": "struct"}"""
- val errMsg1 = intercept[AnalysisException] {
- df.select(from_json($"json", invalidJsonSchema, Map.empty[String, String])).collect()
- }.getMessage
- assert(errMsg1.contains("""Failed to convert the JSON string '{"a":123}' to a field"""))
+ val invalidJsonSchemaReason = "Failed to convert the JSON string '{\"a\":123}' to a field."
+ checkError(
+ exception = intercept[AnalysisException] {
+ df.select(from_json($"json", invalidJsonSchema, Map.empty[String, String])).collect()
+ },
+ errorClass = "INVALID_SCHEMA.PARSE_ERROR",
+ parameters = Map(
+ "inputSchema" -> "\"{\"fields\": [{\"a\":123}], \"type\": \"struct\"}\"",
+ "reason" -> invalidJsonSchemaReason
+ )
+ )
val invalidDataType = "MAP<INT, cow>"
- val errMsg2 = intercept[AnalysisException] {
- df.select(from_json($"json", invalidDataType, Map.empty[String, String])).collect()
- }.getMessage
- assert(errMsg2.contains("DataType cow is not supported"))
+ val invalidDataTypeReason = "Unrecognized token 'MAP': " +
+ "was expecting (JSON String, Number, Array, Object or token 'null', 'true' or 'false')\n " +
+ "at [Source: (String)\"MAP<INT, cow>\"; line: 1, column: 4]"
+ checkError(
+ exception = intercept[AnalysisException] {
+ df.select(from_json($"json", invalidDataType, Map.empty[String, String])).collect()
+ },
+ errorClass = "INVALID_SCHEMA.PARSE_ERROR",
+ parameters = Map(
+ "inputSchema" -> "\"MAP<INT, cow>\"",
+ "reason" -> invalidDataTypeReason
+ )
+ )
val invalidTableSchema = "x INT, a cow"
- val errMsg3 = intercept[AnalysisException] {
- df.select(from_json($"json", invalidTableSchema, Map.empty[String, String])).collect()
- }.getMessage
- assert(errMsg3.contains("DataType cow is not supported"))
+ val invalidTableSchemaReason = "Unrecognized token 'x': " +
+ "was expecting (JSON String, Number, Array, Object or token 'null', 'true' or 'false')\n" +
+ " at [Source: (String)\"x INT, a cow\"; line: 1, column: 2]"
+ checkError(
+ exception = intercept[AnalysisException] {
+ df.select(from_json($"json", invalidTableSchema, Map.empty[String, String])).collect()
+ },
+ errorClass = "INVALID_SCHEMA.PARSE_ERROR",
+ parameters = Map(
+ "inputSchema" -> "\"x INT, a cow\"",
+ "reason" -> invalidTableSchemaReason
+ )
+ )
}
test("SPARK-33907: bad json input with json pruning optimization: GetStructField") {
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org