[SPARK-45964][SQL] Remove private sql accessor in XML and JSON packag…

…e under catalyst package ### What changes were proposed in this pull request? This PR removes `private[sql]` in XML and JSON packages at `catalyst` package. ### Why are the changes needed? `catalyst` is already a private package: https://github.com/apache/spark/blob/master/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/package.scala#L21-L22 See also SPARK-16813 ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI in this PR should test them out. ### Was this patch authored or co-authored using generative AI tooling? No. Closes #43856 from HyukjinKwon/SPARK-45964. Authored-by: Hyukjin Kwon <gurwls223@apache.org> Signed-off-by: Dongjoon Hyun <dhyun@apple.com>
apache · Nov 17, 2023 · 8147620 · 8147620
1 parent db0da0c
commit 8147620
Show file tree

Hide file tree

Showing 10 changed files with 14 additions and 14 deletions.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/CreateJacksonParser.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/CreateJacksonParser.scala
@@ -29,7 +29,7 @@ import sun.nio.cs.StreamDecoder
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.unsafe.types.UTF8String
 
-private[sql] object CreateJacksonParser extends Serializable {
+object CreateJacksonParser extends Serializable {
   def string(jsonFactory: JsonFactory, record: String): JsonParser = {
     jsonFactory.createParser(record)
   }

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JSONOptions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JSONOptions.scala
@@ -34,7 +34,7 @@ import org.apache.spark.sql.internal.{LegacyBehaviorPolicy, SQLConf}
  *
  * Most of these map directly to Jackson's internal options, specified in [[JsonReadFeature]].
  */
-private[sql] class JSONOptions(
+class JSONOptions(
     @transient val parameters: CaseInsensitiveMap[String],
     defaultTimeZoneId: String,
     defaultColumnNameOfCorruptRecord: String)
@@ -212,7 +212,7 @@ private[sql] class JSONOptions(
   }
 }
 
-private[sql] class JSONOptionsInRead(
+class JSONOptionsInRead(
     @transient override val parameters: CaseInsensitiveMap[String],
     defaultTimeZoneId: String,
     defaultColumnNameOfCorruptRecord: String)
@@ -242,7 +242,7 @@ private[sql] class JSONOptionsInRead(
   }
 }
 
-private[sql] object JSONOptionsInRead {
+object JSONOptionsInRead {
   // The following encodings are not supported in per-line mode (multiline is false)
   // because they cause some problems in reading files with BOM which is supposed to
   // present in the files with such encodings. After splitting input files by lines,

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonGenerator.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonGenerator.scala
@@ -37,7 +37,7 @@ import org.apache.spark.util.ArrayImplicits._
  * of map. An exception will be thrown if trying to write out a struct if it is initialized with
  * a `MapType`, and vice verse.
  */
-private[sql] class JacksonGenerator(
+class JacksonGenerator(
     dataType: DataType,
     writer: Writer,
     options: JSONOptions) {

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JsonInferSchema.scala
@@ -37,7 +37,7 @@ import org.apache.spark.sql.internal.{LegacyBehaviorPolicy, SQLConf}
 import org.apache.spark.sql.types._
 import org.apache.spark.util.Utils
 
-private[sql] class JsonInferSchema(options: JSONOptions) extends Serializable with Logging {
+class JsonInferSchema(options: JSONOptions) extends Serializable with Logging {
 
   private val decimalParser = ExprUtils.getDecimalParser(options.locale)
 

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/CreateXmlParser.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/CreateXmlParser.scala
@@ -29,7 +29,7 @@ import sun.nio.cs.StreamDecoder
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.unsafe.types.UTF8String
 
-private[sql] object CreateXmlParser extends Serializable {
+object CreateXmlParser extends Serializable {
   val filter = new EventFilter {
     override def accept(event: XMLEvent): Boolean =
     // Ignore comments and processing instructions

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala
@@ -587,7 +587,7 @@ class StaxXmlParser(
  *
  * This implementation is ultimately loosely based on LineRecordReader in Hadoop.
  */
-private[xml] class XmlTokenizer(
+class XmlTokenizer(
   inputStream: InputStream,
   options: XmlOptions) {
   private val reader = new InputStreamReader(inputStream, Charset.forName(options.charset))
@@ -742,7 +742,7 @@ private[xml] class XmlTokenizer(
   }
 }
 
-private[sql] object StaxXmlParser {
+object StaxXmlParser {
   /**
    * Parses a stream that contains CSV strings and turns it into an iterator of tokens.
    */

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParserUtils.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParserUtils.scala
@@ -24,7 +24,7 @@ import javax.xml.stream.events._
 import scala.annotation.tailrec
 import scala.jdk.CollectionConverters._
 
-private[sql] object StaxXmlParserUtils {
+object StaxXmlParserUtils {
 
   private[sql] val factory: XMLInputFactory = {
     val factory = XMLInputFactory.newInstance()

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/ValidatorUtil.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/ValidatorUtil.scala
@@ -31,7 +31,7 @@ import org.apache.spark.internal.Logging
 /**
  * Utilities for working with XSD validation.
  */
-private[sql] object ValidatorUtil extends Logging{
+object ValidatorUtil extends Logging {
   // Parsing XSDs may be slow, so cache them by path:
 
   private val cache = CacheBuilder.newBuilder().softValues().build(

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala
@@ -36,7 +36,7 @@ import org.apache.spark.sql.catalyst.util.{DateFormatter, PermissiveMode, Timest
 import org.apache.spark.sql.catalyst.util.LegacyDateFormats.FAST_DATE_FORMAT
 import org.apache.spark.sql.types._
 
-private[sql] class XmlInferSchema(options: XmlOptions, caseSensitive: Boolean)
+class XmlInferSchema(options: XmlOptions, caseSensitive: Boolean)
     extends Serializable
     with Logging {
 

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlOptions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlOptions.scala
@@ -30,7 +30,7 @@ import org.apache.spark.sql.internal.{LegacyBehaviorPolicy, SQLConf}
 /**
  * Options for the XML data source.
  */
-private[sql] class XmlOptions(
+class XmlOptions(
     val parameters: CaseInsensitiveMap[String],
     defaultTimeZoneId: String,
     defaultColumnNameOfCorruptRecord: String,
@@ -172,7 +172,7 @@ private[sql] class XmlOptions(
   }
 }
 
-private[sql] object XmlOptions extends DataSourceOptions {
+object XmlOptions extends DataSourceOptions {
   val DEFAULT_ATTRIBUTE_PREFIX = "_"
   val DEFAULT_VALUE_TAG = "_VALUE"
   val DEFAULT_ROW_TAG = "ROW"