This is an automated email from the ASF dual-hosted git repository.
wenchen 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 43e610333fb [SPARK-38972][SQL] Support <param> in error-class messages
43e610333fb is described below
commit 43e610333fb78834a09cd82f3da32bad262564f3
Author: Serge Rielau <[email protected]>
AuthorDate: Thu Apr 21 21:53:28 2022 +0800
[SPARK-38972][SQL] Support <param> in error-class messages
### What changes were proposed in this pull request?
Use symbolic names for parameters in error messages which are substituted
with %s before formatting the string.
### Why are the changes needed?
Increase readability of error message docs (TBD)
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
SQL Project.
Closes #36289 from srielau/symbolic-error-arg-names.
Authored-by: Serge Rielau <[email protected]>
Signed-off-by: Wenchen Fan <[email protected]>
---
core/src/main/resources/error/error-classes.json | 102 ++++++++++-----------
.../main/scala/org/apache/spark/ErrorInfo.scala | 3 +-
2 files changed, 53 insertions(+), 52 deletions(-)
diff --git a/core/src/main/resources/error/error-classes.json
b/core/src/main/resources/error/error-classes.json
index 6d070c35c74..d6e510f659c 100644
--- a/core/src/main/resources/error/error-classes.json
+++ b/core/src/main/resources/error/error-classes.json
@@ -1,18 +1,18 @@
{
"AMBIGUOUS_FIELD_NAME" : {
- "message" : [ "Field name %s is ambiguous and has %s matching fields in
the struct." ],
+ "message" : [ "Field name <fieldName> is ambiguous and has <n> matching
fields in the struct." ],
"sqlState" : "42000"
},
"ARITHMETIC_OVERFLOW" : {
- "message" : [ "%s.%s If necessary set %s to false (except for ANSI
interval type) to bypass this error.%s" ],
+ "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 %s to %s." ],
+ "message" : [ "Cannot cast <sourceType> to <targetType>." ],
"sqlState" : "22005"
},
"CANNOT_CHANGE_DECIMAL_PRECISION" : {
- "message" : [ "%s cannot be represented as Decimal(%s, %s). If necessary
set %s to false to bypass this error.%s" ],
+ "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" : {
@@ -20,139 +20,139 @@
"sqlState" : "42000"
},
"CANNOT_UP_CAST_DATATYPE" : {
- "message" : [ "Cannot up cast %s from %s to %s.\n%s" ]
+ "message" : [ "Cannot up cast <value> from <sourceType> to
<targetType>.\n<details>" ]
},
"CAST_CAUSES_OVERFLOW" : {
- "message" : [ "Casting %s to %s causes overflow. To return NULL instead,
use 'try_cast'. If necessary set %s to false to bypass this error." ],
+ "message" : [ "Casting <value> to <type> causes overflow. To return NULL
instead, use 'try_cast'. If necessary set <config> to false to bypass this
error." ],
"sqlState" : "22005"
},
"CONCURRENT_QUERY" : {
"message" : [ "Another instance of this query was just started by a
concurrent session." ]
},
"DATETIME_OVERFLOW" : {
- "message" : [ "Datetime operation overflow: %s." ],
+ "message" : [ "Datetime operation overflow: <operation>." ],
"sqlState" : "22008"
},
"DIVIDE_BY_ZERO" : {
- "message" : [ "divide by zero. To return NULL instead, use 'try_divide'.
If necessary set %s to false (except for ANSI interval type) to bypass this
error.%s" ],
+ "message" : [ "divide 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" : {
- "message" : [ "Found duplicate keys %s" ],
+ "message" : [ "Found duplicate keys <keyColumn>" ],
"sqlState" : "23000"
},
"FAILED_EXECUTE_UDF" : {
- "message" : [ "Failed to execute user defined function (%s: (%s) => %s)" ]
+ "message" : [ "Failed to execute user defined function (<functionName>:
(<signature>) => <result>)" ]
},
"FAILED_RENAME_PATH" : {
- "message" : [ "Failed to rename %s to %s as destination already exists" ],
+ "message" : [ "Failed to rename <sourcePath> to <targetPath> as
destination already exists" ],
"sqlState" : "22023"
},
"FAILED_SET_ORIGINAL_PERMISSION_BACK" : {
- "message" : [ "Failed to set original permission %s back to the created
path: %s. Exception: %s" ]
+ "message" : [ "Failed to set original permission <permission> back to the
created path: <path>. Exception: <message>" ]
},
"FORBIDDEN_OPERATION" : {
- "message" : [ "The operation %s is not allowed on %s: %s" ]
+ "message" : [ "The operation <statement> is not allowed on <objectType>:
<objectName>" ]
},
"GRAPHITE_SINK_INVALID_PROTOCOL" : {
- "message" : [ "Invalid Graphite protocol: %s" ]
+ "message" : [ "Invalid Graphite protocol: <protocol>" ]
},
"GRAPHITE_SINK_PROPERTY_MISSING" : {
- "message" : [ "Graphite sink requires '%s' property." ]
+ "message" : [ "Graphite sink requires '<property>' property." ]
},
"GROUPING_COLUMN_MISMATCH" : {
- "message" : [ "Column of grouping (%s) can't be found in grouping columns
%s" ],
+ "message" : [ "Column of grouping (<grouping>) can't be found in grouping
columns <groupingColumns>" ],
"sqlState" : "42000"
},
"GROUPING_ID_COLUMN_MISMATCH" : {
- "message" : [ "Columns of grouping_id (%s) does not match grouping columns
(%s)" ],
+ "message" : [ "Columns of grouping_id (<groupingIdColumn>) does not match
grouping columns (<groupByColumns>)" ],
"sqlState" : "42000"
},
"GROUPING_SIZE_LIMIT_EXCEEDED" : {
- "message" : [ "Grouping sets size cannot be greater than %s" ]
+ "message" : [ "Grouping sets size cannot be greater than <maxSize>" ]
},
"ILLEGAL_SUBSTRING" : {
- "message" : [ "%s cannot contain %s." ]
+ "message" : [ "<subject> cannot contain <content>." ]
},
"INCOMPARABLE_PIVOT_COLUMN" : {
- "message" : [ "Invalid pivot column '%s'. Pivot columns must be
comparable." ],
+ "message" : [ "Invalid pivot column '<columnName>'. Pivot columns must be
comparable." ],
"sqlState" : "42000"
},
"INCOMPATIBLE_DATASOURCE_REGISTER" : {
- "message" : [ "Detected an incompatible DataSourceRegister. Please remove
the incompatible library from classpath or upgrade it. Error: %s" ]
+ "message" : [ "Detected an incompatible DataSourceRegister. Please remove
the incompatible library from classpath or upgrade it. Error: <message>" ]
},
"INCONSISTENT_BEHAVIOR_CROSS_VERSION" : {
- "message" : [ "You may get a different result due to the upgrading to
Spark >= %s: %s" ]
+ "message" : [ "You may get a different result due to the upgrading to
Spark >= <sparkVersion>: <details>" ]
},
"INDEX_OUT_OF_BOUNDS" : {
- "message" : [ "Index %s must be between 0 and the length of the
ArrayData." ],
+ "message" : [ "Index <indexValue> must be between 0 and the length of the
ArrayData." ],
"sqlState" : "22023"
},
"INTERNAL_ERROR" : {
- "message" : [ "%s" ]
+ "message" : [ "<message>" ]
},
"INVALID_ARRAY_INDEX" : {
- "message" : [ "Invalid index: %s, numElements: %s. If necessary set %s to
false to bypass this error." ]
+ "message" : [ "Invalid index: <indexValue>, numElements: <arraySize>. If
necessary set <config> to false to bypass this error." ]
},
"INVALID_ARRAY_INDEX_IN_ELEMENT_AT" : {
- "message" : [ "Invalid index: %s, numElements: %s. To return NULL instead,
use 'try_element_at'. If necessary set %s to false to bypass this error." ]
+ "message" : [ "Invalid index: <indexValue>, numElements: <arraySize>. To
return NULL instead, use 'try_element_at'. If necessary set <config> to false
to bypass this error." ]
},
"INVALID_FIELD_NAME" : {
- "message" : [ "Field name %s is invalid: %s is not a struct." ],
+ "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 %s 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_MAPTYPE" : {
- "message" : [ "Input schema %s can only contain StringType as a key type
for a MapType." ]
+ "message" : [ "Input schema <dataType> can only contain StringType as a
key type for a MapType." ]
},
"INVALID_PANDAS_UDF_PLACEMENT" : {
- "message" : [ "The group aggregate pandas UDF %s cannot be invoked
together with as other, non-pandas aggregate functions." ]
+ "message" : [ "The group aggregate pandas UDF <functionName> cannot be
invoked together with as other, non-pandas aggregate functions." ]
},
"INVALID_PARAMETER_VALUE" : {
- "message" : [ "The value of parameter(s) '%s' in %s is invalid: %s" ],
+ "message" : [ "The value of parameter(s) '<parameter>' in <functionName>
is invalid: <expected>" ],
"sqlState" : "22023"
},
"INVALID_SQL_SYNTAX" : {
- "message" : [ "Invalid SQL syntax: %s" ],
+ "message" : [ "Invalid SQL syntax: <inputString>" ],
"sqlState" : "42000"
},
"INVALID_SYNTAX_FOR_CAST" : {
- "message" : [ "Invalid input syntax for type %s: %s. To return NULL
instead, use 'try_cast'. If necessary set %s to false to bypass this error.%s"
],
+ "message" : [ "Invalid input syntax for type <typeName>: <value>. To
return NULL instead, use 'try_cast'. If necessary set <config> to false to
bypass this error.<details>" ],
"sqlState" : "42000"
},
"MAP_KEY_DOES_NOT_EXIST" : {
- "message" : [ "Key %s does not exist. To return NULL instead, use
'try_element_at'. If necessary set %s to false to bypass this error.%s" ]
+ "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 '%s' does not exist. Did you mean one of the
following? [%s]" ],
+ "message" : [ "Column '<columnName>' does not exist. Did you mean one of
the following? [<proposal>]" ],
"sqlState" : "42000"
},
"MISSING_STATIC_PARTITION_COLUMN" : {
- "message" : [ "Unknown static partition column: %s" ],
+ "message" : [ "Unknown static partition column: <columnName>" ],
"sqlState" : "42000"
},
"MULTI_UDF_INTERFACE_ERROR" : {
- "message" : [ "Not allowed to implement multiple UDF interfaces, UDF class
%s" ]
+ "message" : [ "Not allowed to implement multiple UDF interfaces, UDF class
<class>" ]
},
"NON_LITERAL_PIVOT_VALUES" : {
- "message" : [ "Literal expressions required for pivot values, found '%s'"
],
+ "message" : [ "Literal expressions required for pivot values, found
'<expression>'" ],
"sqlState" : "42000"
},
"NON_PARTITION_COLUMN" : {
- "message" : [ "PARTITION clause cannot contain a non-partition column
name: %s" ],
+ "message" : [ "PARTITION clause cannot contain a non-partition column
name: <columnName>" ],
"sqlState" : "42000"
},
"NO_HANDLER_FOR_UDAF" : {
- "message" : [ "No handler for UDAF '%s'. Use
sparkSession.udf.register(...) instead." ]
+ "message" : [ "No handler for UDAF '<functionName>'. Use
sparkSession.udf.register(...) instead." ]
},
"NO_UDF_INTERFACE_ERROR" : {
- "message" : [ "UDF class %s doesn't implement any UDF interface" ]
+ "message" : [ "UDF class <class> doesn't implement any UDF interface" ]
},
"PARSE_CHAR_MISSING_LENGTH" : {
- "message" : [ "DataType %s requires a length parameter, for example
%s(10). Please specify the length." ],
+ "message" : [ "DataType <type> requires a length parameter, for example
<type>(10). Please specify the length." ],
"sqlState" : "42000"
},
"PARSE_EMPTY_STATEMENT" : {
@@ -160,41 +160,41 @@
"sqlState" : "42000"
},
"PARSE_SYNTAX_ERROR" : {
- "message" : [ "Syntax error at or near %s%s" ],
+ "message" : [ "Syntax error at or near <error><hint>" ],
"sqlState" : "42000"
},
"PIVOT_VALUE_DATA_TYPE_MISMATCH" : {
- "message" : [ "Invalid pivot value '%s': value data type %s does not match
pivot column data type %s" ],
+ "message" : [ "Invalid pivot value '<value>': value data type <valueType>
does not match pivot column data type <pivotType>" ],
"sqlState" : "42000"
},
"RENAME_SRC_PATH_NOT_FOUND" : {
- "message" : [ "Failed to rename as %s was not found" ],
+ "message" : [ "Failed to rename as <sourcePath> was not found" ],
"sqlState" : "22023"
},
"SECOND_FUNCTION_ARGUMENT_NOT_INTEGER" : {
- "message" : [ "The second argument of '%s' function needs to be an
integer." ],
+ "message" : [ "The second argument of '<functionName>' function needs to
be an integer." ],
"sqlState" : "22023"
},
"UNABLE_TO_ACQUIRE_MEMORY" : {
- "message" : [ "Unable to acquire %s bytes of memory, got %s" ]
+ "message" : [ "Unable to acquire <requestedBytes> bytes of memory, got
<receivedBytes>" ]
},
"UNRECOGNIZED_SQL_TYPE" : {
- "message" : [ "Unrecognized SQL type %s" ],
+ "message" : [ "Unrecognized SQL type <typeName>" ],
"sqlState" : "42000"
},
"UNSUPPORTED_DATATYPE" : {
- "message" : [ "Unsupported data type %s" ],
+ "message" : [ "Unsupported data type <typeName>" ],
"sqlState" : "0A000"
},
"UNSUPPORTED_FEATURE" : {
- "message" : [ "The feature is not supported: %s" ],
+ "message" : [ "The feature is not supported: <feature>" ],
"sqlState" : "0A000"
},
"UNSUPPORTED_GROUPING_EXPRESSION" : {
"message" : [ "grouping()/grouping_id() can only be used with
GroupingSets/Cube/Rollup" ]
},
"UNSUPPORTED_OPERATION" : {
- "message" : [ "The operation is not supported: %s" ]
+ "message" : [ "The operation is not supported: <operation>" ]
},
"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(ne [...]
diff --git a/core/src/main/scala/org/apache/spark/ErrorInfo.scala
b/core/src/main/scala/org/apache/spark/ErrorInfo.scala
index 0917085c01b..6cb8f4d8ed3 100644
--- a/core/src/main/scala/org/apache/spark/ErrorInfo.scala
+++ b/core/src/main/scala/org/apache/spark/ErrorInfo.scala
@@ -58,7 +58,8 @@ private[spark] object SparkThrowableHelper {
def getMessage(errorClass: String, messageParameters: Array[String]): String
= {
val errorInfo = errorClassToInfoMap.getOrElse(errorClass,
throw new IllegalArgumentException(s"Cannot find error class
'$errorClass'"))
- String.format(errorInfo.messageFormat, messageParameters: _*)
+ String.format(errorInfo.messageFormat.replaceAll("<[a-zA-Z0-9_-]+>", "%s"),
+ messageParameters: _*)
}
def getSqlState(errorClass: String): String = {
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
