-
Notifications
You must be signed in to change notification settings - Fork 146
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* first try adding 3.4 support * first try adding 3.4 support * first try adding 3.4 support * first try adding 3.4 support * moved main logic of ExcelOptions to ExcelOptionsTrait * cleanup imports * removed accidental changes
- Loading branch information
1 parent
4b55f83
commit ea38542
Showing
11 changed files
with
282 additions
and
39 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
38 changes: 38 additions & 0 deletions
38
src/main/2.4/scala/com/crealytics/spark/excel/v2/ExcelOptions.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,38 @@ | ||
| /* | ||
| * Copyright 2022 Martin Mauch (@nightscape) | ||
| * | ||
| * Licensed under the Apache License, Version 2.0 (the "License"); | ||
| * you may not use this file except in compliance with the License. | ||
| * You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package com.crealytics.spark.excel.v2 | ||
|
|
||
| import org.apache.spark.sql.catalyst.util.CaseInsensitiveMap | ||
| import org.apache.spark.sql.internal.SQLConf | ||
|
|
||
| class ExcelOptions( | ||
| @transient | ||
| val parameters: CaseInsensitiveMap[String], | ||
| val defaultTimeZoneId: String, | ||
| val defaultColumnNameOfCorruptRecord: String | ||
| ) extends ExcelOptionsTrait with Serializable { | ||
| // all parameter handling is implemented in ExcelOptionsTrait | ||
|
|
||
| def this(parameters: Map[String, String], defaultTimeZoneId: String) = { | ||
| this(CaseInsensitiveMap(parameters), defaultTimeZoneId, SQLConf.get.columnNameOfCorruptRecord) | ||
| } | ||
|
|
||
| def this(parameters: Map[String, String], defaultTimeZoneId: String, defaultColumnNameOfCorruptRecord: String) = { | ||
| this(CaseInsensitiveMap(parameters), defaultTimeZoneId, defaultColumnNameOfCorruptRecord) | ||
| } | ||
|
|
||
| } |
38 changes: 38 additions & 0 deletions
38
src/main/3.0_3.1_3.2_3.3/scala/com/crealytics/spark/excel/v2/ExcelOptions.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,38 @@ | ||
| /* | ||
| * Copyright 2022 Martin Mauch (@nightscape) | ||
| * | ||
| * Licensed under the Apache License, Version 2.0 (the "License"); | ||
| * you may not use this file except in compliance with the License. | ||
| * You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package com.crealytics.spark.excel.v2 | ||
|
|
||
| import org.apache.spark.sql.catalyst.util.CaseInsensitiveMap | ||
| import org.apache.spark.sql.internal.SQLConf | ||
|
|
||
| class ExcelOptions( | ||
| @transient | ||
| val parameters: CaseInsensitiveMap[String], | ||
| val defaultTimeZoneId: String, | ||
| val defaultColumnNameOfCorruptRecord: String | ||
| ) extends ExcelOptionsTrait with Serializable { | ||
| // all parameter handling is implemented in ExcelOptionsTrait | ||
|
|
||
| def this(parameters: Map[String, String], defaultTimeZoneId: String) = { | ||
| this(CaseInsensitiveMap(parameters), defaultTimeZoneId, SQLConf.get.columnNameOfCorruptRecord) | ||
| } | ||
|
|
||
| def this(parameters: Map[String, String], defaultTimeZoneId: String, defaultColumnNameOfCorruptRecord: String) = { | ||
| this(CaseInsensitiveMap(parameters), defaultTimeZoneId, defaultColumnNameOfCorruptRecord) | ||
| } | ||
|
|
||
| } |
File renamed without changes.
File renamed without changes.
File renamed without changes.
41 changes: 41 additions & 0 deletions
41
src/main/3.4_and_up/scala/com/crealytics/spark/excel/v2/ExcelOptions.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,41 @@ | ||
| /* | ||
| * Copyright 2022 Martin Mauch (@nightscape) | ||
| * | ||
| * Licensed under the Apache License, Version 2.0 (the "License"); | ||
| * you may not use this file except in compliance with the License. | ||
| * You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package com.crealytics.spark.excel.v2 | ||
|
|
||
| import org.apache.spark.sql.catalyst.FileSourceOptions | ||
| import org.apache.spark.sql.catalyst.util.CaseInsensitiveMap | ||
| import org.apache.spark.sql.internal.SQLConf | ||
|
|
||
|
|
||
| class ExcelOptions( | ||
| @transient | ||
| val parameters: CaseInsensitiveMap[String], | ||
| val defaultTimeZoneId: String, | ||
| val defaultColumnNameOfCorruptRecord: String | ||
| ) extends FileSourceOptions(parameters) | ||
| with ExcelOptionsTrait { | ||
|
|
||
|
|
||
| def this(parameters: Map[String, String], defaultTimeZoneId: String) = { | ||
| this(CaseInsensitiveMap(parameters), defaultTimeZoneId, SQLConf.get.columnNameOfCorruptRecord) | ||
| } | ||
|
|
||
| def this(parameters: Map[String, String], defaultTimeZoneId: String, defaultColumnNameOfCorruptRecord: String) = { | ||
| this(CaseInsensitiveMap(parameters), defaultTimeZoneId, defaultColumnNameOfCorruptRecord) | ||
| } | ||
|
|
||
| } |
100 changes: 100 additions & 0 deletions
100
src/main/3.4_and_up/scala/com/crealytics/spark/excel/v2/ExcelPartitionReaderFactory.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,100 @@ | ||
| /* | ||
| * Copyright 2022 Martin Mauch (@nightscape) | ||
| * | ||
| * Licensed under the Apache License, Version 2.0 (the "License"); | ||
| * you may not use this file except in compliance with the License. | ||
| * You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package com.crealytics.spark.excel.v2 | ||
|
|
||
| import org.apache.hadoop.conf.Configuration | ||
| import org.apache.spark.broadcast.Broadcast | ||
| import org.apache.spark.sql.catalyst.InternalRow | ||
| import org.apache.spark.sql.connector.read.PartitionReader | ||
| import org.apache.spark.sql.execution.datasources.PartitionedFile | ||
| import org.apache.spark.sql.execution.datasources.v2._ | ||
| import org.apache.spark.sql.internal.SQLConf | ||
| import org.apache.spark.sql.sources.Filter | ||
| import org.apache.spark.sql.types.StructType | ||
| import org.apache.spark.util.SerializableConfiguration | ||
| import scala.util.control.NonFatal | ||
|
|
||
| /** A factory used to create Excel readers. | ||
| * | ||
| * @param sqlConf | ||
| * SQL configuration. | ||
| * @param broadcastedConf | ||
| * Broadcasted serializable Hadoop Configuration. | ||
| * @param dataSchema | ||
| * Schema of Excel files. | ||
| * @param readDataSchema | ||
| * Required data schema in the batch scan. | ||
| * @param partitionSchema | ||
| * Schema of partitions. | ||
| * @param options | ||
| * Options for parsing Excel files. | ||
| */ | ||
| case class ExcelPartitionReaderFactory( | ||
| sqlConf: SQLConf, | ||
| broadcastedConf: Broadcast[SerializableConfiguration], | ||
| dataSchema: StructType, | ||
| readDataSchema: StructType, | ||
| partitionSchema: StructType, | ||
| options: ExcelOptions, | ||
| filters: Seq[Filter] | ||
| ) extends FilePartitionReaderFactory { | ||
|
|
||
| override def buildReader(file: PartitionedFile): PartitionReader[InternalRow] = { | ||
| val conf = broadcastedConf.value.value | ||
| val actualDataSchema = | ||
| StructType(dataSchema.filterNot(_.name == options.columnNameOfCorruptRecord)) | ||
| val actualReadDataSchema = | ||
| StructType(readDataSchema.filterNot(_.name == options.columnNameOfCorruptRecord)) | ||
| val parser = new ExcelParser(actualDataSchema, actualReadDataSchema, options, filters) | ||
| val headerChecker = | ||
| new ExcelHeaderChecker(actualReadDataSchema, options, source = s"Excel file: ${file.filePath}") | ||
| val iter = readFile(conf, file, parser, headerChecker, readDataSchema) | ||
| val partitionReader = new SparkExcelPartitionReaderFromIterator(iter) | ||
| new PartitionReaderWithPartitionValues(partitionReader, readDataSchema, partitionSchema, file.partitionValues) | ||
| } | ||
|
|
||
| private def readFile( | ||
| conf: Configuration, | ||
| file: PartitionedFile, | ||
| parser: ExcelParser, | ||
| headerChecker: ExcelHeaderChecker, | ||
| requiredSchema: StructType | ||
| ): SheetData[InternalRow] = { | ||
| val excelHelper = ExcelHelper(options) | ||
| val sheetData = excelHelper.getSheetData(conf, file.filePath.toUri) | ||
| try { | ||
| SheetData( | ||
| ExcelParser.parseIterator(sheetData.rowIterator, parser, headerChecker, requiredSchema), | ||
| sheetData.resourcesToClose | ||
| ) | ||
| } catch { | ||
| case NonFatal(t) => { | ||
| sheetData.close() | ||
| throw t | ||
| } | ||
| } | ||
| } | ||
|
|
||
| } | ||
|
|
||
| private class SparkExcelPartitionReaderFromIterator(sheetData: SheetData[InternalRow]) | ||
| extends PartitionReaderFromIterator[InternalRow](sheetData.rowIterator) { | ||
| override def close(): Unit = { | ||
| super.close() | ||
| sheetData.close() | ||
| } | ||
| } |
Oops, something went wrong.