uros-b commented on code in PR #56688:
URL: https://github.com/apache/spark/pull/56688#discussion_r3462660942
##########
sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala:
##########
@@ -816,4 +882,77 @@ object SparkConnectDatabaseMetaData {
)
private[jdbc] val TABLE_TYPES = Seq("TABLE", "VIEW")
+
+ // One row of the java.sql.DatabaseMetaData.getTypeInfo result.
+ private type TypeInfoRow =
+ (
+ String, // TYPE_NAME
+ Int, // DATA_TYPE
+ Int, // PRECISION
+ String, // LITERAL_PREFIX
+ String, // LITERAL_SUFFIX
+ String, // CREATE_PARAMS
+ Short, // NULLABLE
+ Boolean, // CASE_SENSITIVE
+ Short, // SEARCHABLE
+ Boolean, // UNSIGNED_ATTRIBUTE
+ Boolean, // FIXED_PREC_SCALE
+ Boolean, // AUTO_INCREMENT
+ String, // LOCAL_TYPE_NAME
+ Short, // MINIMUM_SCALE
+ Short, // MAXIMUM_SCALE
+ Int, // SQL_DATA_TYPE
+ Int, // SQL_DATETIME_SUB
+ Int // NUM_PREC_RADIX
+ )
+
+ // Fills the columns that are constant across all Spark atomic types: every
type is
+ // nullable and searchable, and none are unsigned, fixed-prec-scale, or
auto-increment.
+ // `literalQuote` is used as both the literal prefix and suffix.
+ private def typeRow(
+ typeName: String,
+ dataType: Int,
+ precision: Int,
+ literalQuote: String,
+ createParams: String,
+ caseSensitive: Boolean,
+ minScale: Short,
+ maxScale: Short,
+ numPrecRadix: Int): TypeInfoRow =
+ (
+ typeName,
+ dataType,
+ precision,
+ literalQuote,
+ literalQuote,
+ createParams,
+ typeNullable.toShort,
+ caseSensitive,
+ typeSearchable.toShort,
+ false,
+ false,
+ false,
+ null,
+ minScale,
+ maxScale,
+ 0,
+ 0,
+ numPrecRadix)
+
+ // Static JDBC type metadata for the Spark SQL atomic types, mirroring the
+ // JdbcTypeUtils type-code/precision mapping. Only STRING is case-sensitive.
+ // TIME and TIMESTAMP_NTZ are omitted (new and duplicate JDBC type codes).
+ private[jdbc] val TYPE_INFO: Seq[TypeInfoRow] = Seq(
+ typeRow("BOOLEAN", Types.BOOLEAN, 1, null, null, false, 0, 0, 0),
+ typeRow("TINYINT", Types.TINYINT, 3, null, null, false, 0, 0, 10),
+ typeRow("SMALLINT", Types.SMALLINT, 5, null, null, false, 0, 0, 10),
+ typeRow("INT", Types.INTEGER, 10, null, null, false, 0, 0, 10),
+ typeRow("BIGINT", Types.BIGINT, 19, null, null, false, 0, 0, 10),
+ typeRow("FLOAT", Types.FLOAT, 7, null, null, false, 0, 0, 10),
+ typeRow("DOUBLE", Types.DOUBLE, 15, null, null, false, 0, 0, 10),
+ typeRow("DECIMAL", Types.DECIMAL, 38, null, "precision,scale", false, 0,
38, 10),
+ typeRow("STRING", Types.VARCHAR, Int.MaxValue, "'", null, true, 0, 0, 0),
+ typeRow("BINARY", Types.VARBINARY, Int.MaxValue, "'", null, false, 0, 0,
0),
Review Comment:
SparkConnectDatabaseMetaData getTypeInfo TYPE_INFO — BINARY
(Types.VARBINARY) is given LITERAL_PREFIX = "'", but Spark SQL binary literals
are X'<hex>', so the prefix should be "X'" (Hive returns null for the same
reason). This is a real fidelity bug: JDBC tooling that builds SQL from
LITERAL_PREFIX/LITERAL_SUFFIX would emit invalid literals for binary.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
