fjy closed pull request #6727: move parquet extension input formats URL: https://github.com/apache/incubator-druid/pull/6727
This is a PR merged from a forked repository. As GitHub hides the original diff on merge, it is displayed below for the sake of provenance: As this is a foreign pull request (from a fork), the diff is supplied below (as it won't show otherwise due to GitHub magic): diff --git a/docs/content/development/extensions-core/parquet.md b/docs/content/development/extensions-core/parquet.md index a31a072f3b5..f3e8bcde121 100644 --- a/docs/content/development/extensions-core/parquet.md +++ b/docs/content/development/extensions-core/parquet.md @@ -37,8 +37,8 @@ This extension provides two ways to parse Parquet files: module to parse the avro data Selection of conversion method is controlled by parser type, and the correct hadoop input format must also be set in -the `ioConfig`, `org.apache.druid.data.input.parquet.simple.DruidParquetInputFormat` for `parquet` and -`org.apache.druid.data.input.parquet.avro.DruidParquetAvroInputFormat` for `parquet-avro`. +the `ioConfig`, `org.apache.druid.data.input.parquet.DruidParquetInputFormat` for `parquet` and +`org.apache.druid.data.input.parquet.DruidParquetAvroInputFormat` for `parquet-avro`. Both parse options support auto field discovery and flattening if provided with a @@ -74,7 +74,7 @@ When the time dimension is a [DateType column](https://github.com/apache/parquet "type": "hadoop", "inputSpec": { "type": "static", - "inputFormat": "org.apache.druid.data.input.parquet.simple.DruidParquetInputFormat", + "inputFormat": "org.apache.druid.data.input.parquet.DruidParquetInputFormat", "paths": "path/to/file.parquet" }, ... @@ -128,7 +128,7 @@ When the time dimension is a [DateType column](https://github.com/apache/parquet "type": "hadoop", "inputSpec": { "type": "static", - "inputFormat": "org.apache.druid.data.input.parquet.simple.DruidParquetInputFormat", + "inputFormat": "org.apache.druid.data.input.parquet.DruidParquetInputFormat", "paths": "path/to/file.parquet" }, ... @@ -171,7 +171,7 @@ When the time dimension is a [DateType column](https://github.com/apache/parquet "type": "hadoop", "inputSpec": { "type": "static", - "inputFormat": "org.apache.druid.data.input.parquet.avro.DruidParquetAvroInputFormat", + "inputFormat": "org.apache.druid.data.input.parquet.DruidParquetAvroInputFormat", "paths": "path/to/file.parquet" }, ... diff --git a/extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/avro/DruidParquetAvroInputFormat.java b/extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/DruidParquetAvroInputFormat.java similarity index 95% rename from extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/avro/DruidParquetAvroInputFormat.java rename to extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/DruidParquetAvroInputFormat.java index 109f315c4be..c169d95ad91 100755 --- a/extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/avro/DruidParquetAvroInputFormat.java +++ b/extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/DruidParquetAvroInputFormat.java @@ -17,7 +17,7 @@ * under the License. */ -package org.apache.druid.data.input.parquet.avro; +package org.apache.druid.data.input.parquet; import org.apache.avro.generic.GenericRecord; import org.apache.parquet.avro.DruidParquetAvroReadSupport; diff --git a/extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/simple/DruidParquetInputFormat.java b/extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/DruidParquetInputFormat.java similarity index 89% rename from extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/simple/DruidParquetInputFormat.java rename to extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/DruidParquetInputFormat.java index ed8e623c6ce..ff07adab228 100644 --- a/extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/simple/DruidParquetInputFormat.java +++ b/extensions-core/parquet-extensions/src/main/java/org/apache/druid/data/input/parquet/DruidParquetInputFormat.java @@ -17,8 +17,9 @@ * under the License. */ -package org.apache.druid.data.input.parquet.simple; +package org.apache.druid.data.input.parquet; +import org.apache.druid.data.input.parquet.simple.DruidParquetReadSupport; import org.apache.parquet.example.data.Group; import org.apache.parquet.hadoop.ParquetInputFormat; diff --git a/extensions-core/parquet-extensions/src/test/java/org/apache/druid/data/input/parquet/BaseParquetInputTest.java b/extensions-core/parquet-extensions/src/test/java/org/apache/druid/data/input/parquet/BaseParquetInputTest.java index 735f6d30ef2..253eea53e7c 100644 --- a/extensions-core/parquet-extensions/src/test/java/org/apache/druid/data/input/parquet/BaseParquetInputTest.java +++ b/extensions-core/parquet-extensions/src/test/java/org/apache/druid/data/input/parquet/BaseParquetInputTest.java @@ -23,8 +23,6 @@ import org.apache.directory.api.util.Strings; import org.apache.druid.data.input.InputRow; import org.apache.druid.data.input.impl.InputRowParser; -import org.apache.druid.data.input.parquet.avro.DruidParquetAvroInputFormat; -import org.apache.druid.data.input.parquet.simple.DruidParquetInputFormat; import org.apache.druid.indexer.HadoopDruidIndexerConfig; import org.apache.druid.indexer.path.StaticPathSpec; import org.apache.druid.java.util.common.StringUtils; @@ -58,9 +56,9 @@ private static Map<String, String> inputFormatType = ImmutableMap.of( ParquetExtensionsModule.PARQUET_AVRO_INPUT_PARSER_TYPE, - "org.apache.druid.data.input.parquet.avro.DruidParquetAvroInputFormat", + "org.apache.druid.data.input.parquet.DruidParquetAvroInputFormat", ParquetExtensionsModule.PARQUET_SIMPLE_INPUT_PARSER_TYPE, - "org.apache.druid.data.input.parquet.simple.DruidParquetInputFormat" + "org.apache.druid.data.input.parquet.DruidParquetInputFormat" ); private static Map<String, Class<? extends InputFormat>> inputFormatClass = ImmutableMap.of( ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
