Skip to content
Closed
Show file tree
Hide file tree
Changes from 2 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -127,11 +127,10 @@ class DB2IntegrationSuite extends DockerJDBCIntegrationSuite {
val types = rows(0).toSeq.map(x => x.getClass.toString)
assert(types.length == 3)
assert(types(0).equals("class java.sql.Date"))
assert(types(1).equals("class java.lang.Integer"))
assert(types(1).equals("class java.sql.Timestamp"))
assert(types(2).equals("class java.sql.Timestamp"))
assert(rows(0).getAs[Date](0).equals(Date.valueOf("1991-11-09")))
assert(
rows(0).getAs[Integer](1) === Timestamp.valueOf("1970-01-01 13:31:24").getTime)
assert(rows(0).getAs[Timestamp](1).equals(Timestamp.valueOf("1970-01-01 13:31:24")))
assert(rows(0).getAs[Timestamp](2).equals(Timestamp.valueOf("2009-02-13 23:31:30")))
}
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -219,14 +219,13 @@ class MsSqlServerIntegrationSuite extends DockerJDBCIntegrationSuite {
assert(types(2).equals("class java.sql.Timestamp"))
assert(types(3).equals("class java.lang.String"))
assert(types(4).equals("class java.sql.Timestamp"))
assert(types(5).equals("class java.lang.Integer"))
assert(types(5).equals("class java.sql.Timestamp"))
assert(row.getAs[Date](0).equals(Date.valueOf("1991-11-09")))
assert(row.getAs[Timestamp](1).equals(Timestamp.valueOf("1999-01-01 13:23:35.0")))
assert(row.getAs[Timestamp](2).equals(Timestamp.valueOf("9999-12-31 23:59:59.0")))
assert(row.getString(3).equals("1901-05-09 23:59:59.0000000 +14:00"))
assert(row.getAs[Timestamp](4).equals(Timestamp.valueOf("1996-01-01 23:24:00.0")))
assert(
row.getAs[Integer](5) === Timestamp.valueOf("1970-01-01 13:31:24.0").getTime)
assert(row.getAs[Timestamp](5).equals(Timestamp.valueOf("1970-01-01 13:31:24.0")))
}
}

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -119,13 +119,13 @@ class MySQLIntegrationSuite extends DockerJDBCIntegrationSuite {
val types = rows(0).toSeq.map(x => x.getClass.toString)
assert(types.length == 5)
assert(types(0).equals("class java.sql.Date"))
assert(types(1).equals("class java.lang.Integer"))
assert(types(1).equals("class java.sql.Timestamp"))
assert(types(2).equals("class java.sql.Timestamp"))
assert(types(3).equals("class java.sql.Timestamp"))
assert(types(4).equals("class java.sql.Date"))
assert(rows(0).getAs[Date](0).equals(Date.valueOf("1991-11-09")))
assert(
rows(0).getAs[Integer](1) === Timestamp.valueOf("1970-01-01 13:31:24").getTime)
rows(0).getAs[Timestamp](1) === Timestamp.valueOf("1970-01-01 13:31:24"))
assert(rows(0).getAs[Timestamp](2).equals(Timestamp.valueOf("1996-01-01 01:23:45")))
assert(rows(0).getAs[Timestamp](3).equals(Timestamp.valueOf("2009-02-13 23:31:30")))
assert(rows(0).getAs[Date](4).equals(Date.valueOf("2001-01-01")))
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -181,7 +181,7 @@ class PostgresIntegrationSuite extends DockerJDBCIntegrationSuite {
val rows = dfRead.collect()
val types = rows(0).toSeq.map(x => x.getClass.toString)
assert(types(1).equals("class java.sql.Timestamp"))
assert(types(2).equals("class java.lang.Integer"))
assert(types(2).equals("class java.sql.Timestamp"))
}

test("SPARK-22291: Conversion error when transforming array types of " +
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -19,12 +19,14 @@ package org.apache.spark.sql.execution.datasources.jdbc

import java.sql.{Connection, Driver, JDBCType, PreparedStatement, ResultSet, ResultSetMetaData, SQLException, SQLFeatureNotSupportedException}
import java.time.{Instant, LocalDate}
import java.util.Locale
import java.util.{Locale, TimeZone}
import java.util.concurrent.TimeUnit

import scala.util.Try
import scala.util.control.NonFatal

import sun.util.calendar.ZoneInfo

import org.apache.spark.TaskContext
import org.apache.spark.executor.InputMetrics
import org.apache.spark.internal.Logging
Expand Down Expand Up @@ -230,7 +232,7 @@ object JdbcUtils extends Logging {
case java.sql.Types.SMALLINT => IntegerType
case java.sql.Types.SQLXML => StringType
case java.sql.Types.STRUCT => StringType
case java.sql.Types.TIME => IntegerType
case java.sql.Types.TIME => TimestampType
case java.sql.Types.TIME_WITH_TIMEZONE
=> null
case java.sql.Types.TIMESTAMP => TimestampType
Expand Down Expand Up @@ -421,23 +423,6 @@ object JdbcUtils extends Logging {
(rs: ResultSet, row: InternalRow, pos: Int) =>
row.setFloat(pos, rs.getFloat(pos + 1))


// SPARK-33888 - sql TIME type represents as physical int in millis
// Represents a time of day, with no reference to a particular calendar,
// time zone or date, with a precision of one millisecond.
// It stores the number of milliseconds after midnight, 00:00:00.000.
case IntegerType if metadata.contains("logical_time_type") =>
(rs: ResultSet, row: InternalRow, pos: Int) => {
val rawTime = rs.getTime(pos + 1)
if (rawTime != null) {
val rawTimeInNano = rawTime.toLocalTime().toNanoOfDay()
val timeInMillis = Math.toIntExact(TimeUnit.NANOSECONDS.toMillis(rawTimeInNano))
row.setInt(pos, timeInMillis)
} else {
row.update(pos, null)
}
}

case IntegerType =>
(rs: ResultSet, row: InternalRow, pos: Int) =>
row.setInt(pos, rs.getInt(pos + 1))
Expand Down Expand Up @@ -470,6 +455,27 @@ object JdbcUtils extends Logging {
// TODO(davies): use getBytes for better performance, if the encoding is UTF-8
row.update(pos, UTF8String.fromString(rs.getString(pos + 1)))

// SPARK-34357 - sql TIME type represents as zero epoch timestamp.
// It is represented as Spark TimestampType but fixed at 1970-01-01 for day,
// time portion is time of day, with no reference to a particular calendar,
// time zone or date, with a precision till microseconds.
// It stores the number of milliseconds after midnight, 00:00:00.000000
case TimestampType if metadata.contains("logical_time_type") =>
(rs: ResultSet, row: InternalRow, pos: Int) => {
val rawTime = rs.getTime(pos + 1)
if (rawTime != null) {
val localTimeMicro = TimeUnit.NANOSECONDS.toMicros(rawTime.toLocalTime().toNanoOfDay())
val localTimeMillis = DateTimeUtils.microsToMillis(localTimeMicro)
val timeZoneOffset = TimeZone.getDefault match {

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In most cases, session timezone should be the same as JVM default timezone, but ideally we should use session timezone for datetime operations: SQLConf.get.sessionLocalTimeZone

case zoneInfo: ZoneInfo => zoneInfo.getOffsetsByWall(localTimeMillis, null)
case timeZone: TimeZone => timeZone.getOffset(localTimeMillis - timeZone.getRawOffset)
}

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Seems we can just do DateTimeUtils.toUTCTime(localTimeMicro, SQLConf.get.sessionLocalTimeZone)

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Superb! This is really more elegant. Thanks for this suggestion!

row.setLong(pos, localTimeMicro - DateTimeUtils.millisToMicros(timeZoneOffset))
} else {
row.update(pos, null)
}
}

case TimestampType =>
(rs: ResultSet, row: InternalRow, pos: Int) =>
val t = rs.getTimestamp(pos + 1)
Expand Down
24 changes: 6 additions & 18 deletions sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ import java.math.BigDecimal
import java.sql.{Date, DriverManager, SQLException, Timestamp}
import java.time.{Instant, LocalDate}
import java.util.{Calendar, GregorianCalendar, Properties}
import java.util.concurrent.TimeUnit

import scala.collection.JavaConverters._

Expand Down Expand Up @@ -614,13 +613,7 @@ class JDBCSuite extends QueryTest
test("H2 time types") {
val rows = sql("SELECT * FROM timetypes").collect()
val cal = new GregorianCalendar(java.util.Locale.ROOT)
val epochMillis = java.time.LocalTime.ofNanoOfDay(
TimeUnit.MILLISECONDS.toNanos(rows(0).getAs[Int](0)))
.atDate(java.time.LocalDate.ofEpochDay(0))
.atZone(java.time.ZoneId.systemDefault())
.toInstant()
.toEpochMilli()
cal.setTime(new Date(epochMillis))
cal.setTime(rows(0).getAs[java.sql.Timestamp](0))
assert(cal.get(Calendar.HOUR_OF_DAY) === 12)
assert(cal.get(Calendar.MINUTE) === 34)
assert(cal.get(Calendar.SECOND) === 56)
Expand All @@ -639,20 +632,15 @@ class JDBCSuite extends QueryTest
assert(rows(0).getAs[java.sql.Timestamp](2).getNanos === 543543000)
}

test("SPARK-33888: test TIME types") {
test("SPARK-34357: test TIME types") {
val rows = spark.read.jdbc(
urlWithUserAndPass, "TEST.TIMETYPES", new Properties()).collect()
val cachedRows = spark.read.jdbc(urlWithUserAndPass, "TEST.TIMETYPES", new Properties())
.cache().collect()
val expectedTimeRaw = java.sql.Time.valueOf("12:34:56")
val expectedTimeMillis = Math.toIntExact(
java.util.concurrent.TimeUnit.NANOSECONDS.toMillis(
expectedTimeRaw.toLocalTime().toNanoOfDay()
)
)
assert(rows(0).getAs[Int](0) === expectedTimeMillis)
assert(rows(1).getAs[Int](0) === expectedTimeMillis)
assert(cachedRows(0).getAs[Int](0) === expectedTimeMillis)
val expectedTimeAtEpoch = java.sql.Timestamp.valueOf("1970-01-01 12:34:56.0")
assert(rows(0).getAs[java.sql.Timestamp](0) === expectedTimeAtEpoch)
assert(rows(1).getAs[java.sql.Timestamp](0) === expectedTimeAtEpoch)
assert(cachedRows(0).getAs[java.sql.Timestamp](0) === expectedTimeAtEpoch)
}

test("test DATE types") {
Expand Down