Skip to content
Merged
Show file tree
Hide file tree
Changes from all 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
5 changes: 5 additions & 0 deletions docs/changelog/142900.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
area: ES|QL
issues: []
pr: 142900
summary: Add support for ORC file format
type: feature
60 changes: 55 additions & 5 deletions gradle/verification-metadata.xml
Original file line number Diff line number Diff line change
Expand Up @@ -97,6 +97,16 @@
<sha256 value="ba6f338e8c02f56a7296bf669f4748f6a0506b6074452a59690da204d8f535e0" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.aayushatharva.brotli4j" name="brotli4j" version="1.18.0">
<artifact name="brotli4j-1.18.0.jar">
<sha256 value="0cab5c97314362a1d0d59206eb79ace72363ceac029f5e932acec6ce6bb23db8" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.aayushatharva.brotli4j" name="service" version="1.18.0">
<artifact name="service-1.18.0.jar">
<sha256 value="6b27c85555992438530a88ae8192b15589fdc21ea22dc3c597393bf8f2dd8805" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.avast.gradle" name="gradle-docker-compose-plugin" version="0.17.5">
<artifact name="gradle-docker-compose-plugin-0.17.5.jar">
<sha256 value="bc818ee3015f7cea73d5a603fc7a542ad82ebb5799e406d9abc81ac42caa90f0" origin="Generated by Gradle"/>
Expand Down Expand Up @@ -577,6 +587,11 @@
<sha256 value="a38a4a97f1b43b878c91e0dd7f1e3d17f0e70beec71d95bacaf56a2f207624a3" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.github.luben" name="zstd-jni" version="1.5.7-6">
<artifact name="zstd-jni-1.5.7-6.jar">
<sha256 value="8d6feb1da335f3ab13c584c613e23c7b3c61b392e37956872057baf8f0ca1d6f" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.github.spotbugs" name="spotbugs-annotations" version="4.0.2">
<artifact name="spotbugs-annotations-4.0.2.jar">
<sha256 value="3ef6c9f822b601aa151e10e123b49e5604243a4a99bcc47e4e1f9eea9781dc63" origin="Generated by Gradle"/>
Expand Down Expand Up @@ -792,16 +807,16 @@
<sha256 value="d1f3c66aa91ac52549e00ae3b208ba4b9af7d72d68f230643553beb38e6118ac" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.google.errorprone" name="error_prone_annotations" version="2.30.0">
<artifact name="error_prone_annotations-2.30.0.jar">
<sha256 value="144f3aefbd6e27daec55d3753b2c6b13c1afdaf0cf04816cdb564588ed92f1bd" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.google.errorprone" name="error_prone_annotations" version="2.3.4">
<artifact name="error_prone_annotations-2.3.4.jar">
<sha256 value="baf7d6ea97ce606c53e11b6854ba5f2ce7ef5c24dddf0afa18d1260bd25b002c" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.google.errorprone" name="error_prone_annotations" version="2.30.0">
<artifact name="error_prone_annotations-2.30.0.jar">
<sha256 value="144f3aefbd6e27daec55d3753b2c6b13c1afdaf0cf04816cdb564588ed92f1bd" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.google.errorprone" name="error_prone_annotations" version="2.36.0">
<artifact name="error_prone_annotations-2.36.0.jar">
<sha256 value="77440e270b0bc9a249903c5a076c36a722c4886ca4f42675f2903a1c53ed61a5" origin="Generated by Gradle"/>
Expand Down Expand Up @@ -1022,6 +1037,11 @@
<sha256 value="8540247fad9e06baefa8fb45eb313802d019f485f14300e0f9d6b556ed88e753" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.google.protobuf" name="protobuf-java" version="3.25.8">
<artifact name="protobuf-java-3.25.8.jar">
<sha256 value="72bdb32eb38cafb7dcd288262c29a34d57cba2e19101af9685155ba8c0a56008" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.google.protobuf" name="protobuf-java" version="4.30.2">
<artifact name="protobuf-java-4.30.2.jar">
<sha256 value="0f3a4e9264db07cec429f2a68a66030e9b7487277b76863cdd0e9238cece249b" origin="Generated by Gradle"/>
Expand Down Expand Up @@ -3285,6 +3305,11 @@
<sha256 value="4b4f70f14576cabec34607a035b58aaefa6c042d693328d90de79db581966f8b" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.hive" name="hive-storage-api" version="2.8.1">
<artifact name="hive-storage-api-2.8.1.jar">
<sha256 value="2bb77d246a9724a371301049239c6e53039efe4136b0ed34ee5a9c7b3cd861d8" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.htrace" name="htrace-core4" version="4.0.1-incubating">
<artifact name="htrace-core4-4.0.1-incubating.jar">
<sha256 value="0abe211fbe122dc18be76fe58fc366052ec1444e7afcbb29cc1bed828710e6de" origin="Generated by Gradle"/>
Expand Down Expand Up @@ -3940,6 +3965,21 @@
<sha256 value="39b2dfc8e84380bf7adab657d3d5e1625cb6592a885ebdb854ec5c6f7a3ec88d" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.orc" name="orc-core" version="2.2.2">
<artifact name="orc-core-2.2.2.jar">
<sha256 value="fac6d35cabb136f62932b17a687997ff5dd7e139ce1af4975f602fb8c7f0598a" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.orc" name="orc-format" version="1.1.1">
<artifact name="orc-format-1.1.1.jar">
<sha256 value="41d4e038913ba2ca5e7b9bd5a90c6f641879ef519b9763f39d7eb45e6e64e415" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.orc" name="orc-shims" version="2.2.2">
<artifact name="orc-shims-2.2.2.jar">
<sha256 value="46c730ca9aef90bd9df03bdfc50564a51a4cf5da9f2888e97b9b0faa1e88c260" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.parquet" name="parquet-avro" version="1.16.0">
<artifact name="parquet-avro-1.16.0.jar">
<sha256 value="31748bb5006d2f86ee1853754ea9d4bae26784d1a651aecd6fb87faf770ca0ba" origin="Generated by Gradle"/>
Expand Down Expand Up @@ -5563,6 +5603,11 @@
<sha256 value="18c4a0095d5c1da6b817592e767bb23d29dd2f560ad74df75ff3961dbde25b79" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.slf4j" name="slf4j-api" version="1.7.30">
<artifact name="slf4j-api-1.7.30.jar">
<sha256 value="cdba07964d1bb40a0761485c6b1e8c2f8fd9eb1d19c53928ac0d7f9510105c57" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.slf4j" name="slf4j-api" version="1.7.32">
<artifact name="slf4j-api-1.7.32.jar">
<sha256 value="3624f8474c1af46d75f98bc097d7864a323c81b3808aa43689a6e1c601c027be" origin="Generated by Gradle"/>
Expand Down Expand Up @@ -5653,6 +5698,11 @@
<sha256 value="edd5740fd67f1a1edd7dae4b08eef333c81cbe84a9d437f14ecdb9b82bc04688" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.threeten" name="threeten-extra" version="1.8.0">
<artifact name="threeten-extra-1.8.0.jar">
<sha256 value="51e4d21edc4e9447f7760c050e0baee75d7d973f387ba605a17abdc4d24fd6d8" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.threeten" name="threetenbp" version="1.7.0">
<artifact name="threetenbp-1.7.0.jar">
<sha256 value="857917d2319a4e92dc1c5e3aeb75a0dac84445ed315e7ac3d82bb8d2b298977f" origin="Generated by Gradle"/>
Expand Down
164 changes: 164 additions & 0 deletions x-pack/plugin/esql-datasource-orc/build.gradle
Original file line number Diff line number Diff line change
@@ -0,0 +1,164 @@
/*
* Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
* or more contributor license agreements. Licensed under the Elastic License
* 2.0; you may not use this file except in compliance with the Elastic License
* 2.0.
*/

apply plugin: 'elasticsearch.internal-es-plugin'
apply plugin: 'elasticsearch.publish'

versions << [
'hadoop' : '3.4.2',
'orc' : '2.2.2',
]

esplugin {
name = 'esql-datasource-orc'
description = 'ORC format support for ESQL external data sources'
classname = 'org.elasticsearch.xpack.esql.datasource.orc.OrcDataSourcePlugin'
extendedPlugins = ['x-pack-esql']
}

base {
archivesName = 'esql-datasource-orc'
}

dependencies {
compileOnly project(path: xpackModule('esql'))
compileOnly project(path: xpackModule('esql-core'))
compileOnly project(path: xpackModule('core'))
compileOnly project(':server')
compileOnly project(xpackModule('esql:compute'))

implementation("org.apache.orc:orc-core:${versions.orc}") {
exclude group: 'org.slf4j', module: 'slf4j-api'
}

// Hive storage API - provides VectorizedRowBatch and ColumnVector classes used by ORC's
// reader API. ORC shades this during its Maven build but the published jar still references
// these classes in its public API (TypeDescription.createRowBatch(), Reader.rows(), etc.)
implementation('org.apache.hive:hive-storage-api:2.8.1')

// Protobuf - required by orc-format's generated classes (OrcProto) which reference
// com.google.protobuf.MessageOrBuilder at runtime
implementation('com.google.protobuf:protobuf-java:3.25.8')

// Hadoop dependencies - required because ORC's Reader API uses Hadoop Configuration,
// Path, and FileSystem in its public interfaces.
implementation('org.apache.hadoop:hadoop-client-api:3.4.2') {
exclude group: 'org.slf4j', module: 'slf4j-api'
}
implementation('org.apache.hadoop:hadoop-client-runtime:3.4.2') {
exclude group: 'org.slf4j', module: 'slf4j-api'
}

// Re-add slf4j-api at the platform version to avoid jar hell with x-pack-core
runtimeOnly "org.slf4j:slf4j-api:${versions.slf4j}"

testImplementation project(':test:framework')
testImplementation(testArtifact(project(xpackModule('core'))))
}

tasks.named("dependencyLicenses").configure {
mapping from: /lucene-.*/, to: 'lucene'
mapping from: /orc-.*/, to: 'orc'
mapping from: /hadoop-.*/, to: 'hadoop'
mapping from: /hive-.*/, to: 'orc'
mapping from: /aircompressor-.*/, to: 'orc'
mapping from: /threeten-extra-.*/, to: 'orc'
mapping from: /protobuf-.*/, to: 'orc'
mapping from: /brotli4j-.*/, to: 'orc'
mapping from: /service-.*/, to: 'orc'
mapping from: /zstd-jni-.*/, to: 'orc'
mapping from: /jts-core-.*/, to: 'orc'
}

tasks.named("thirdPartyAudit").configure {
ignoreMissingClasses()
ignoreViolations(
// Hadoop internal uses sun.misc.Unsafe
'org.apache.hadoop.hdfs.shortcircuit.ShortCircuitShm',
'org.apache.hadoop.hdfs.shortcircuit.ShortCircuitShm$Slot',
'org.apache.hadoop.io.FastByteComparisons$LexicographicalComparerHolder$UnsafeComparer',
'org.apache.hadoop.io.FastByteComparisons$LexicographicalComparerHolder$UnsafeComparer$1',
'org.apache.hadoop.io.nativeio.NativeIO',
'org.apache.hadoop.service.launcher.InterruptEscalator',
'org.apache.hadoop.service.launcher.IrqHandler',
'org.apache.hadoop.util.SignalLogger$Handler',
// Hadoop shaded Guava uses sun.misc.Unsafe
'org.apache.hadoop.shaded.com.google.common.cache.Striped64',
'org.apache.hadoop.shaded.com.google.common.cache.Striped64$1',
'org.apache.hadoop.shaded.com.google.common.cache.Striped64$Cell',
'org.apache.hadoop.shaded.com.google.common.hash.LittleEndianByteArray$UnsafeByteArray',
'org.apache.hadoop.shaded.com.google.common.hash.LittleEndianByteArray$UnsafeByteArray$1',
'org.apache.hadoop.shaded.com.google.common.hash.LittleEndianByteArray$UnsafeByteArray$2',
'org.apache.hadoop.shaded.com.google.common.hash.LittleEndianByteArray$UnsafeByteArray$3',
'org.apache.hadoop.shaded.com.google.common.hash.Striped64',
'org.apache.hadoop.shaded.com.google.common.hash.Striped64$1',
'org.apache.hadoop.shaded.com.google.common.hash.Striped64$Cell',
'org.apache.hadoop.shaded.com.google.common.primitives.UnsignedBytes$LexicographicalComparatorHolder$UnsafeComparator',
'org.apache.hadoop.shaded.com.google.common.primitives.UnsignedBytes$LexicographicalComparatorHolder$UnsafeComparator$1',
'org.apache.hadoop.shaded.com.google.common.util.concurrent.AbstractFuture$UnsafeAtomicHelper',
'org.apache.hadoop.shaded.com.google.common.util.concurrent.AbstractFuture$UnsafeAtomicHelper$1',
// Hadoop shaded Avro uses sun.misc.Unsafe
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe',
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe$UnsafeBooleanField',
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe$UnsafeByteField',
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe$UnsafeCachedField',
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe$UnsafeCharField',
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe$UnsafeCustomEncodedField',
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe$UnsafeDoubleField',
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe$UnsafeFloatField',
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe$UnsafeIntField',
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe$UnsafeLongField',
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe$UnsafeObjectField',
'org.apache.hadoop.shaded.org.apache.avro.reflect.FieldAccessUnsafe$UnsafeShortField',
// Hadoop shaded Curator Guava uses sun.misc.Unsafe
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.cache.Striped64',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.cache.Striped64$1',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.cache.Striped64$Cell',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.hash.LittleEndianByteArray$UnsafeByteArray',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.hash.LittleEndianByteArray$UnsafeByteArray$1',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.hash.LittleEndianByteArray$UnsafeByteArray$2',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.hash.LittleEndianByteArray$UnsafeByteArray$3',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.hash.Striped64',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.hash.Striped64$1',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.hash.Striped64$Cell',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.primitives.UnsignedBytes$LexicographicalComparatorHolder$UnsafeComparator',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.primitives.UnsignedBytes$LexicographicalComparatorHolder$UnsafeComparator$1',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.util.concurrent.AbstractFuture$UnsafeAtomicHelper',
'org.apache.hadoop.shaded.org.apache.curator.shaded.com.google.common.util.concurrent.AbstractFuture$UnsafeAtomicHelper$1',
'org.apache.hadoop.shaded.org.xbill.DNS.spi.DNSJavaNameServiceDescriptor',
// Hadoop thirdparty Protobuf uses sun.misc.Unsafe
'org.apache.hadoop.thirdparty.protobuf.MessageSchema',
'org.apache.hadoop.thirdparty.protobuf.UnsafeUtil',
'org.apache.hadoop.thirdparty.protobuf.UnsafeUtil$1',
'org.apache.hadoop.thirdparty.protobuf.UnsafeUtil$Android32MemoryAccessor',
'org.apache.hadoop.thirdparty.protobuf.UnsafeUtil$Android64MemoryAccessor',
'org.apache.hadoop.thirdparty.protobuf.UnsafeUtil$JvmMemoryAccessor',
'org.apache.hadoop.thirdparty.protobuf.UnsafeUtil$MemoryAccessor',
// Hadoop thirdparty Guava uses sun.misc.Unsafe
'org.apache.hadoop.thirdparty.com.google.common.cache.Striped64',
'org.apache.hadoop.thirdparty.com.google.common.cache.Striped64$1',
'org.apache.hadoop.thirdparty.com.google.common.cache.Striped64$Cell',
'org.apache.hadoop.thirdparty.com.google.common.hash.LittleEndianByteArray$UnsafeByteArray',
'org.apache.hadoop.thirdparty.com.google.common.hash.LittleEndianByteArray$UnsafeByteArray$1',
'org.apache.hadoop.thirdparty.com.google.common.hash.LittleEndianByteArray$UnsafeByteArray$2',
'org.apache.hadoop.thirdparty.com.google.common.hash.Striped64',
'org.apache.hadoop.thirdparty.com.google.common.hash.Striped64$1',
'org.apache.hadoop.thirdparty.com.google.common.hash.Striped64$Cell',
'org.apache.hadoop.thirdparty.com.google.common.primitives.UnsignedBytes$LexicographicalComparatorHolder$UnsafeComparator',
'org.apache.hadoop.thirdparty.com.google.common.primitives.UnsignedBytes$LexicographicalComparatorHolder$UnsafeComparator$1',
'org.apache.hadoop.thirdparty.com.google.common.util.concurrent.AbstractFuture$UnsafeAtomicHelper',
'org.apache.hadoop.thirdparty.com.google.common.util.concurrent.AbstractFuture$UnsafeAtomicHelper$1',
// Protobuf uses sun.misc.Unsafe
'com.google.protobuf.MessageSchema',
'com.google.protobuf.UnsafeUtil',
'com.google.protobuf.UnsafeUtil$1',
'com.google.protobuf.UnsafeUtil$Android32MemoryAccessor',
'com.google.protobuf.UnsafeUtil$Android64MemoryAccessor',
'com.google.protobuf.UnsafeUtil$JvmMemoryAccessor',
'com.google.protobuf.UnsafeUtil$MemoryAccessor',
)
}
Loading