forked from apache/iceberg
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbuild.gradle
279 lines (243 loc) · 11.9 KB
/
build.gradle
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you 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.
*/
String sparkVersion = '3.2.1'
String sparkMajorVersion = '3.2'
String scalaVersion = System.getProperty("scalaVersion") != null ? System.getProperty("scalaVersion") : System.getProperty("defaultScalaVersion")
def sparkProjects = [
project(":iceberg-spark:iceberg-spark-${sparkMajorVersion}_${scalaVersion}"),
project(":iceberg-spark:iceberg-spark-extensions-${sparkMajorVersion}_${scalaVersion}"),
project(":iceberg-spark:iceberg-spark-runtime-${sparkMajorVersion}_${scalaVersion}"),
]
configure(sparkProjects) {
configurations {
all {
resolutionStrategy {
force "com.fasterxml.jackson.module:jackson-module-scala_${scalaVersion}:2.12.3"
force 'com.fasterxml.jackson.module:jackson-module-paranamer:2.12.3'
}
}
}
}
project(":iceberg-spark:iceberg-spark-${sparkMajorVersion}_${scalaVersion}") {
apply plugin: 'scala'
apply plugin: 'com.github.alisiikh.scalastyle'
sourceSets {
main {
scala.srcDirs = ['src/main/scala', 'src/main/java']
java.srcDirs = []
}
}
dependencies {
implementation project(path: ':iceberg-bundled-guava', configuration: 'shadow')
api project(':iceberg-api')
implementation project(':iceberg-common')
implementation project(':iceberg-core')
implementation project(':iceberg-data')
implementation project(':iceberg-orc')
implementation project(':iceberg-parquet')
implementation project(':iceberg-arrow')
implementation("org.scala-lang.modules:scala-collection-compat_${scalaVersion}")
compileOnly "com.google.errorprone:error_prone_annotations"
compileOnly "org.apache.avro:avro"
compileOnly("org.apache.spark:spark-hive_${scalaVersion}:${sparkVersion}") {
exclude group: 'org.apache.avro', module: 'avro'
exclude group: 'org.apache.arrow'
exclude group: 'org.apache.parquet'
// to make sure io.netty.buffer only comes from project(':iceberg-arrow')
exclude group: 'io.netty', module: 'netty-buffer'
exclude group: 'org.roaringbitmap'
}
implementation("org.apache.parquet:parquet-column")
implementation("org.apache.parquet:parquet-hadoop")
implementation("org.apache.orc:orc-core::nohive") {
exclude group: 'org.apache.hadoop'
exclude group: 'commons-lang'
// These artifacts are shaded and included in the orc-core fat jar
exclude group: 'com.google.protobuf', module: 'protobuf-java'
exclude group: 'org.apache.hive', module: 'hive-storage-api'
}
implementation("org.apache.arrow:arrow-vector") {
exclude group: 'io.netty', module: 'netty-buffer'
exclude group: 'io.netty', module: 'netty-common'
exclude group: 'com.google.code.findbugs', module: 'jsr305'
}
testImplementation("org.apache.hadoop:hadoop-minicluster") {
exclude group: 'org.apache.avro', module: 'avro'
// to make sure io.netty.buffer only comes from project(':iceberg-arrow')
exclude group: 'io.netty', module: 'netty-buffer'
}
testImplementation project(path: ':iceberg-hive-metastore')
testImplementation project(path: ':iceberg-hive-metastore', configuration: 'testArtifacts')
testImplementation project(path: ':iceberg-api', configuration: 'testArtifacts')
testImplementation project(path: ':iceberg-core', configuration: 'testArtifacts')
testImplementation project(path: ':iceberg-data', configuration: 'testArtifacts')
testImplementation "org.xerial:sqlite-jdbc"
}
tasks.withType(Test) {
// For vectorized reads
// Allow unsafe memory access to avoid the costly check arrow does to check if index is within bounds
systemProperty("arrow.enable_unsafe_memory_access", "true")
// Disable expensive null check for every get(index) call.
// Iceberg manages nullability checks itself instead of relying on arrow.
systemProperty("arrow.enable_null_check_for_get", "false")
// Vectorized reads need more memory
maxHeapSize '2560m'
}
}
project(":iceberg-spark:iceberg-spark-extensions-${sparkMajorVersion}_${scalaVersion}") {
apply plugin: 'java-library'
apply plugin: 'scala'
apply plugin: 'com.github.alisiikh.scalastyle'
apply plugin: 'antlr'
configurations {
/*
The Gradle Antlr plugin erroneously adds both antlr-build and runtime dependencies to the runtime path. This
bug https://github.com/gradle/gradle/issues/820 exists because older versions of Antlr do not have separate
runtime and implementation dependencies and they do not want to break backwards compatibility. So to only end up with
the runtime dependency on the runtime classpath we remove the dependencies added by the plugin here. Then add
the runtime dependency back to only the runtime configuration manually.
*/
implementation {
extendsFrom = extendsFrom.findAll { it != configurations.antlr }
}
}
dependencies {
implementation("org.scala-lang.modules:scala-collection-compat_${scalaVersion}")
compileOnly "org.scala-lang:scala-library:${scalaVersion}"
compileOnly project(path: ':iceberg-bundled-guava', configuration: 'shadow')
compileOnly project(':iceberg-api')
compileOnly project(':iceberg-core')
compileOnly project(':iceberg-common')
compileOnly project(":iceberg-spark:iceberg-spark-${sparkMajorVersion}_${scalaVersion}")
compileOnly("org.apache.spark:spark-hive_${scalaVersion}:${sparkVersion}") {
exclude group: 'org.apache.avro', module: 'avro'
exclude group: 'org.apache.arrow'
exclude group: 'org.apache.parquet'
// to make sure io.netty.buffer only comes from project(':iceberg-arrow')
exclude group: 'io.netty', module: 'netty-buffer'
exclude group: 'org.roaringbitmap'
}
testImplementation project(path: ':iceberg-hive-metastore')
testImplementation project(path: ':iceberg-hive-metastore', configuration: 'testArtifacts')
testImplementation project(path: ':iceberg-api', configuration: 'testArtifacts')
testImplementation project(path: ':iceberg-hive-metastore', configuration: 'testArtifacts')
testImplementation project(path: ":iceberg-spark:iceberg-spark-${sparkMajorVersion}_${scalaVersion}", configuration: 'testArtifacts')
testImplementation "org.apache.avro:avro"
// Required because we remove antlr plugin dependencies from the compile configuration, see note above
runtimeOnly "org.antlr:antlr4-runtime:4.8"
antlr "org.antlr:antlr4:4.8"
}
generateGrammarSource {
maxHeapSize = "64m"
arguments += ['-visitor', '-package', 'org.apache.spark.sql.catalyst.parser.extensions']
}
}
project(":iceberg-spark:iceberg-spark-runtime-${sparkMajorVersion}_${scalaVersion}") {
apply plugin: 'com.github.johnrengelman.shadow'
tasks.jar.dependsOn tasks.shadowJar
sourceSets {
integration {
java.srcDir "$projectDir/src/integration/java"
resources.srcDir "$projectDir/src/integration/resources"
}
}
configurations {
implementation {
exclude group: 'org.apache.spark'
// included in Spark
exclude group: 'org.slf4j'
exclude group: 'org.apache.commons'
exclude group: 'commons-pool'
exclude group: 'commons-codec'
exclude group: 'org.xerial.snappy'
exclude group: 'javax.xml.bind'
exclude group: 'javax.annotation'
exclude group: 'com.github.luben'
exclude group: 'com.ibm.icu'
exclude group: 'org.glassfish'
exclude group: 'org.abego.treelayout'
exclude group: 'org.antlr'
}
}
dependencies {
api project(':iceberg-api')
implementation project(":iceberg-spark:iceberg-spark-${sparkMajorVersion}_${scalaVersion}")
implementation project(":iceberg-spark:iceberg-spark-extensions-${sparkMajorVersion}_${scalaVersion}")
implementation project(':iceberg-aws')
implementation(project(':iceberg-aliyun')) {
exclude group: 'edu.umd.cs.findbugs', module: 'findbugs'
exclude group: 'org.apache.httpcomponents', module: 'httpclient'
exclude group: 'commons-logging', module: 'commons-logging'
}
implementation project(':iceberg-hive-metastore')
implementation(project(':iceberg-nessie')) {
exclude group: 'com.google.code.findbugs', module: 'jsr305'
}
integrationImplementation "org.apache.spark:spark-hive_${scalaVersion}:${sparkVersion}"
integrationImplementation 'org.junit.vintage:junit-vintage-engine'
integrationImplementation 'org.slf4j:slf4j-simple'
integrationImplementation project(path: ':iceberg-api', configuration: 'testArtifacts')
integrationImplementation project(path: ':iceberg-hive-metastore', configuration: 'testArtifacts')
integrationImplementation project(path: ":iceberg-spark:iceberg-spark-${sparkMajorVersion}_${scalaVersion}", configuration: 'testArtifacts')
integrationImplementation project(path: ":iceberg-spark:iceberg-spark-extensions-${sparkMajorVersion}_${scalaVersion}", configuration: 'testArtifacts')
// Not allowed on our classpath, only the runtime jar is allowed
integrationCompileOnly project(":iceberg-spark:iceberg-spark-extensions-${sparkMajorVersion}_${scalaVersion}")
integrationCompileOnly project(":iceberg-spark:iceberg-spark-${sparkMajorVersion}_${scalaVersion}")
integrationCompileOnly project(':iceberg-api')
}
shadowJar {
configurations = [project.configurations.runtimeClasspath]
zip64 true
// include the LICENSE and NOTICE files for the shaded Jar
from(projectDir) {
include 'LICENSE'
include 'NOTICE'
}
// Relocate dependencies to avoid conflicts
relocate 'com.google', 'org.apache.iceberg.shaded.com.google'
relocate 'com.fasterxml', 'org.apache.iceberg.shaded.com.fasterxml'
relocate 'com.github.benmanes', 'org.apache.iceberg.shaded.com.github.benmanes'
relocate 'org.checkerframework', 'org.apache.iceberg.shaded.org.checkerframework'
relocate 'org.apache.avro', 'org.apache.iceberg.shaded.org.apache.avro'
relocate 'avro.shaded', 'org.apache.iceberg.shaded.org.apache.avro.shaded'
relocate 'com.thoughtworks.paranamer', 'org.apache.iceberg.shaded.com.thoughtworks.paranamer'
relocate 'org.apache.parquet', 'org.apache.iceberg.shaded.org.apache.parquet'
relocate 'shaded.parquet', 'org.apache.iceberg.shaded.org.apache.parquet.shaded'
relocate 'org.apache.orc', 'org.apache.iceberg.shaded.org.apache.orc'
relocate 'io.airlift', 'org.apache.iceberg.shaded.io.airlift'
// relocate Arrow and related deps to shade Iceberg specific version
relocate 'io.netty.buffer', 'org.apache.iceberg.shaded.io.netty.buffer'
relocate 'org.apache.arrow', 'org.apache.iceberg.shaded.org.apache.arrow'
relocate 'com.carrotsearch', 'org.apache.iceberg.shaded.com.carrotsearch'
relocate 'org.threeten.extra', 'org.apache.iceberg.shaded.org.threeten.extra'
relocate 'org.roaringbitmap', 'org.apache.iceberg.shaded.org.roaringbitmap'
classifier null
}
task integrationTest(type: Test) {
description = "Test Spark3 Runtime Jar against Spark ${sparkMajorVersion}"
group = "verification"
testClassesDirs = sourceSets.integration.output.classesDirs
classpath = sourceSets.integration.runtimeClasspath + files(shadowJar.archiveFile.get().asFile.path)
inputs.file(shadowJar.archiveFile.get().asFile.path)
}
integrationTest.dependsOn shadowJar
jar {
enabled = false
}
}