parquet
Used in:
components
- OverviewOverview
- VersionsVersions
- DependentsDependents
- DependenciesDependencies
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet</artifactId>
<version>1.15.1</version>
</dependency><project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>org.apache</groupId>
<artifactId>apache</artifactId>
<version>33</version>
</parent>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet</artifactId>
<version>1.15.1</version>
<packaging>pom</packaging>
<name>Apache Parquet Java</name>
<url>https://parquet.apache.org</url>
<description>Parquet is a columnar storage format that supports nested data. This provides the java implementation.</description>
<scm>
<connection>scm:git:git@github.com:apache/parquet-mr.git</connection>
<url>scm:git:git@github.com:apache/parquet-mr.git</url>
<developerConnection>scm:git:git@github.com:apache/parquet-mr.git</developerConnection>
<tag>apache-parquet-1.15.1-rc0</tag>
</scm>
<licenses>
<license>
<name>The Apache Software License, Version 2.0</name>
<url>https://www.apache.org/licenses/LICENSE-2.0.txt</url>
</license>
</licenses>
<issueManagement>
<system>GitHub</system>
<url>https://github.com/apache/parquet-java/issues</url>
</issueManagement>
<mailingLists>
<mailingList>
<name>Dev Mailing List</name>
<post>dev@parquet.apache.org</post>
<subscribe>dev-subscribe@parquet.apache.org</subscribe>
<unsubscribe>dev-unsubscribe@parquet.apache.org</unsubscribe>
</mailingList>
<mailingList>
<name>Commits Mailing List</name>
<post>commits@parquet.apache.org</post>
<subscribe>commits-subscribe@parquet.apache.org</subscribe>
<unsubscribe>commits-unsubscribe@parquet.apache.org</unsubscribe>
</mailingList>
</mailingLists>
<repositories>
<repository>
<id>jitpack.io</id>
<url>https://jitpack.io</url>
<name>Jitpack.io repository</name>
<!-- needed for brotli-codec -->
</repository>
</repositories>
<properties>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<github.global.server>github</github.global.server>
<jackson.groupId>com.fasterxml.jackson.core</jackson.groupId>
<jackson.datatype.groupId>com.fasterxml.jackson.datatype</jackson.datatype.groupId>
<jackson.package>com.fasterxml.jackson</jackson.package>
<!-- To upgrade jackson, check the jdk versions inside the jar and include any new versions in the shading in parquet-jackson. -->
<jackson.version>2.18.1</jackson.version>
<jackson-databind.version>2.18.1</jackson-databind.version>
<japicmp.version>0.21.0</japicmp.version>
<javax.annotation.version>1.3.2</javax.annotation.version>
<spotless.version>2.30.0</spotless.version>
<shade.prefix>shaded.parquet</shade.prefix>
<hadoop.version>3.3.6</hadoop.version>
<parquet.format.version>2.10.0</parquet.format.version>
<previous.version>1.15.0</previous.version>
<thrift.executable>thrift</thrift.executable>
<format.thrift.executable>${thrift.executable}</format.thrift.executable>
<scala.version>2.12.17</scala.version>
<!-- scala.binary.version is used for projects that fetch dependencies that are in scala -->
<scala.binary.version>2.12</scala.binary.version>
<scala.maven.test.skip>false</scala.maven.test.skip>
<pig.version>0.16.0</pig.version>
<pig.classifier>h2</pig.classifier>
<thrift-maven-plugin.version>0.10.0</thrift-maven-plugin.version>
<thrift.version>0.21.0</thrift.version>
<format.thrift.version>${thrift.version}</format.thrift.version>
<fastutil.version>8.5.13</fastutil.version>
<semver.api.version>0.9.33</semver.api.version>
<slf4j.version>1.7.33</slf4j.version>
<avro.version>1.11.4</avro.version>
<guava.version>33.2.1-jre</guava.version>
<brotli-codec.version>0.1.1</brotli-codec.version>
<mockito.version>1.10.19</mockito.version>
<powermock.version>2.0.9</powermock.version>
<net.openhft.version>0.26ea0</net.openhft.version>
<exec-maven-plugin.version>1.6.0</exec-maven-plugin.version>
<!-- parquet-cli dependencies -->
<opencsv.version>2.3</opencsv.version>
<jcommander.version>1.82</jcommander.version>
<tukaani.version>1.10</tukaani.version>
<zstd-jni.version>1.5.6-6</zstd-jni.version>
<commons-text.version>1.12.0</commons-text.version>
<jsr305.version>3.0.2</jsr305.version>
<commons-lang3.version>3.17.0</commons-lang3.version>
<!-- properties for the profiles -->
<surefire.argLine>-XX:MaxJavaStackTraceDepth=8</surefire.argLine>
<surefire.logLevel>ERROR</surefire.logLevel>
<!-- Resource intesive tests are enabled by default but disabled in the CI envrionment -->
<enableResourceIntensiveTests>true</enableResourceIntensiveTests>
<extraJavaTestArgs>
-XX:+IgnoreUnrecognizedVMOptions
--add-opens=java.base/java.lang=ALL-UNNAMED
--add-opens=java.base/java.lang.invoke=ALL-UNNAMED
--add-opens=java.base/java.lang.reflect=ALL-UNNAMED
--add-opens=java.base/java.io=ALL-UNNAMED
--add-opens=java.base/java.net=ALL-UNNAMED
--add-opens=java.base/java.nio=ALL-UNNAMED
--add-opens=java.base/java.util=ALL-UNNAMED
--add-opens=java.base/java.util.concurrent=ALL-UNNAMED
--add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED
--add-opens=java.base/sun.nio.ch=ALL-UNNAMED
--add-opens=java.base/sun.nio.cs=ALL-UNNAMED
--add-opens=java.base/sun.security.action=ALL-UNNAMED
--add-opens=java.base/sun.util.calendar=ALL-UNNAMED
</extraJavaTestArgs>
</properties>
<modules>
<module>parquet-arrow</module>
<module>parquet-avro</module>
<module>parquet-benchmarks</module>
<module>parquet-cli</module>
<module>parquet-column</module>
<module>parquet-common</module>
<module>parquet-encoding</module>
<module>parquet-format-structures</module>
<module>parquet-generator</module>
<module>parquet-hadoop</module>
<module>parquet-jackson</module>
<module>parquet-pig</module>
<module>parquet-pig-bundle</module>
<module>parquet-protobuf</module>
<module>parquet-thrift</module>
<module>parquet-hadoop-bundle</module>
</modules>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.13.2</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.easymock</groupId>
<artifactId>easymock</artifactId>
<version>5.4.0</version>
<scope>test</scope>
</dependency>
</dependencies>
<dependencyManagement>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
<version>${hadoop.version}</version>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>*</artifactId>
</exclusion>
<exclusion>
<groupId>ch.qos.reload4j</groupId>
<artifactId>*</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>*</artifactId>
</exclusion>
<exclusion>
<groupId>ch.qos.reload4j</groupId>
<artifactId>*</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>${hadoop.version}</version>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>*</artifactId>
</exclusion>
<exclusion>
<groupId>ch.qos.reload4j</groupId>
<artifactId>*</artifactId>
</exclusion>
</exclusions>
</dependency>
</dependencies>
</dependencyManagement>
<reporting>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<reportSets>
<reportSet><!-- by default, id = "default" -->
<reports><!-- select non-aggregate reports -->
<report>javadoc</report>
<report>test-javadoc</report>
</reports>
</reportSet>
<reportSet><!-- aggregate reportSet, to define in poms having modules -->
<id>aggregate</id>
<inherited>false</inherited><!-- don't run aggregate in child modules -->
<reports>
<report>aggregate</report>
</reports>
</reportSet>
</reportSets>
<configuration>
<sourceFileExcludes>
<sourceFileExclude>**/generated-sources/**/*.java</sourceFileExclude>
</sourceFileExcludes>
<source>8</source>
<quiet>true</quiet>
</configuration>
</plugin>
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>cobertura-maven-plugin</artifactId>
<version>2.7</version>
<configuration>
<formats>
<format>html</format>
</formats>
<aggregate>true</aggregate>
<instrumentation>
<ignores>
<ignore>java.lang.UnsupportedOperationException.*</ignore>
</ignores>
<excludes>
<exclude>parquet/Log.class</exclude>
<exclude>**/*Exception.class</exclude>
<exclude>parquet/example/**/*.class</exclude>
</excludes>
</instrumentation>
</configuration>
</plugin>
</plugins>
</reporting>
<build>
<pluginManagement>
<plugins>
<plugin>
<!-- Disable the source artifact from ASF parent -->
<artifactId>maven-assembly-plugin</artifactId>
<executions>
<execution>
<id>source-release-assembly</id>
<phase>none</phase>
</execution>
</executions>
</plugin>
<plugin>
<artifactId>maven-enforcer-plugin</artifactId>
<executions>
<execution>
<id>enforce-banned-dependencies</id>
<goals>
<goal>enforce</goal>
</goals>
<configuration>
<rules>
<bannedDependencies>
<excludes>
<exclude>org.slf4j:slf4j-log4j12:*:*:compile</exclude>
<exclude>org.slf4j:slf4j-reload4j:*:*:compile</exclude>
</excludes>
</bannedDependencies>
</rules>
<fail>true</fail>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<minimizeJar>true</minimizeJar>
<artifactSet>
<includes>
<include>${jackson.groupId}:*</include>
<include>it.unimi.dsi:fastutil</include>
<include>net.openhft:*</include>
</includes>
</artifactSet>
<!-- Shade jackson but do not include any class. Let parquet-jackson handle this -->
<filters>
<filter>
<artifact>${jackson.groupId}:*</artifact>
<excludes>
<exclude>**</exclude>
</excludes>
</filter>
</filters>
<relocations>
<relocation>
<pattern>${jackson.package}</pattern>
<shadedPattern>${shade.prefix}.${jackson.package}</shadedPattern>
</relocation>
<relocation>
<pattern>it.unimi.dsi</pattern>
<shadedPattern>${shade.prefix}.it.unimi.dsi</shadedPattern>
</relocation>
<relocation>
<pattern>net.openhft</pattern>
<shadedPattern>${shade.prefix}.net.openhft</shadedPattern>
</relocation>
</relocations>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-jar-plugin</artifactId>
<configuration>
<archive>
<manifestEntries>
<git-SHA-1>${buildNumber}</git-SHA-1>
</manifestEntries>
</archive>
</configuration>
<executions>
<execution>
<goals>
<goal>test-jar</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</pluginManagement>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<configuration>
<sourceFileExcludes>
<sourceFileExclude>**/generated-sources/**/*.java</sourceFileExclude>
</sourceFileExcludes>
<source>8</source>
<quiet>true</quiet>
</configuration>
</plugin>
<plugin>
<groupId>com.mycila.maven-license-plugin</groupId>
<artifactId>maven-license-plugin</artifactId>
<version>1.10.b1</version>
<configuration>
<header>src/license.txt</header>
<strictCheck>true</strictCheck>
</configuration>
<!--executions>
<execution>
<phase>test</phase>
<goals>
<goal>check</goal>
</goals>
</execution>
</executions-->
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-remote-resources-plugin</artifactId>
<configuration>
<skip>true</skip>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-failsafe-plugin</artifactId>
<configuration>
<argLine>${extraJavaTestArgs}</argLine>
</configuration>
<executions>
<execution>
<goals>
<goal>integration-test</goal>
<goal>verify</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<configuration>
<argLine>${surefire.argLine} ${extraJavaTestArgs}</argLine>
<systemPropertyVariables>
<!-- Configure Parquet logging during tests
See http://www.slf4j.org/api/org/slf4j/impl/SimpleLogger.html
-->
<org.slf4j.simpleLogger.defaultLogLevel>${surefire.logLevel}</org.slf4j.simpleLogger.defaultLogLevel>
<org.slf4j.simpleLogger.showDateTime>true</org.slf4j.simpleLogger.showDateTime>
<org.slf4j.simpleLogger.dateTimeFormat>YYYY-MM-dd HH:mm:ss</org.slf4j.simpleLogger.dateTimeFormat>
<org.slf4j.simpleLogger.showThreadName>false</org.slf4j.simpleLogger.showThreadName>
<org.slf4j.simpleLogger.showShortLogName>true</org.slf4j.simpleLogger.showShortLogName>
<!-- Configure log level for Hadoop -->
<hadoop.logLevel>${surefire.logLevel}</hadoop.logLevel>
<enableResourceIntensiveTests>${enableResourceIntensiveTests}</enableResourceIntensiveTests>
</systemPropertyVariables>
<excludes>
<exclude>**/benchmark/*.java</exclude>
</excludes>
</configuration>
</plugin>
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>buildnumber-maven-plugin</artifactId>
<!-- Warning! 3.2.1 caused issues during verification, 3.2.0 is known to work correctly. -->
<version>3.2.0</version>
<executions>
<execution>
<phase>validate</phase>
<goals>
<goal>create</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.rat</groupId>
<artifactId>apache-rat-plugin</artifactId>
<executions>
<execution>
<phase>test</phase>
<goals>
<goal>check</goal>
</goals>
</execution>
</executions>
<configuration>
<consoleOutput>true</consoleOutput>
<excludes>
<exclude>.github/PULL_REQUEST_TEMPLATE.md</exclude>
<exclude>**/*.parquet</exclude>
<exclude>**/*.avro</exclude>
<exclude>**/*.json</exclude>
<exclude>**/*.avsc</exclude>
<exclude>**/*.iml</exclude>
<exclude>**/*.log</exclude>
<exclude>**/*.md.vm</exclude>
<exclude>**/.classpath</exclude>
<exclude>**/.project</exclude>
<exclude>**/.settings/**</exclude>
<exclude>**/build/**</exclude>
<exclude>**/target/**</exclude>
<exclude>.git/**</exclude>
<exclude>.gitignore</exclude>
<exclude>.gitmodules</exclude>
<exclude>.idea/**</exclude>
<exclude>*/jdiff/*.xml</exclude>
<exclude>licenses/**</exclude>
<exclude>protobuf_install/**</exclude>
<exclude>thrift-${thrift.version}/**</exclude>
<exclude>thrift-${thrift.version}.tar.gz</exclude>
<exclude>**/dependency-reduced-pom.xml</exclude>
<exclude>**/*.rej</exclude>
</excludes>
</configuration>
</plugin>
<!-- https://mvnrepository.com/artifact/com.diffplug.spotless/spotless-maven-plugin -->
<plugin>
<groupId>com.diffplug.spotless</groupId>
<artifactId>spotless-maven-plugin</artifactId>
<version>${spotless.version}</version>
<configuration>
<java>
<excludes>
<exclude>**/generated-sources/**</exclude>
</excludes>
<toggleOffOn />
<removeUnusedImports />
<importOrder />
<trimTrailingWhitespace />
<palantirJavaFormat />
<endWithNewline />
<formatAnnotations />
<indent>
<tabs>true</tabs>
<spacesPerTab>4</spacesPerTab>
</indent>
<indent>
<spaces>true</spaces>
<spacesPerTab>2</spacesPerTab>
</indent>
</java>
</configuration>
<executions>
<execution>
<phase>verify</phase>
<goals>
<goal>check</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>com.github.siom79.japicmp</groupId>
<artifactId>japicmp-maven-plugin</artifactId>
<version>${japicmp.version}</version>
<configuration>
<parameter>
<oldVersionPattern>${previous.version}</oldVersionPattern>
<breakBuildOnSourceIncompatibleModifications>true</breakBuildOnSourceIncompatibleModifications>
<onlyModified>true</onlyModified>
<ignoreMissingClassesByRegularExpressions>
<ignoreMissingClassesByRegularExpression>${shade.prefix}.*</ignoreMissingClassesByRegularExpression>
</ignoreMissingClassesByRegularExpressions>
<ignoreMissingOldVersion>true</ignoreMissingOldVersion>
<excludeModules>
<!-- Excluding the following modules because they are not part of the parquet public API -->
<excludeModule>parquet-benchmarks</excludeModule>
<excludeModule>parquet-cli</excludeModule>
<excludeModule>parquet-tools-deprecated</excludeModule>
<excludeModule>parquet-format-structures</excludeModule>
<!-- Excluding the following modules because bundles do not contain any java classes while they still fail the
compatibility check because of missing dependencies -->
<excludeModule>parquet-hadoop-bundle</excludeModule>
<excludeModule>parquet-pig-bundle</excludeModule>
</excludeModules>
<excludes>
<exclude>${shade.prefix}</exclude>
<!-- Removal of a protected method in a class that's not supposed to be subclassed by third-party code -->
<exclude>org.apache.parquet.column.values.bytestreamsplit.ByteStreamSplitValuesReader#gatherElementDataFromStreams(byte[])</exclude>
<!-- Due to the removal of deprecated methods -->
<exclude>org.apache.parquet.arrow.schema.SchemaMapping$TypeMappingVisitor#visit(org.apache.parquet.arrow.schema.SchemaMapping$MapTypeMapping)</exclude>
<!-- Make static variables final -->
<exclude>org.apache.parquet.avro.AvroReadSupport#AVRO_REQUESTED_PROJECTION</exclude>
<exclude>org.apache.parquet.avro.AvroReadSupport#AVRO_DATA_SUPPLIER</exclude>
<exclude>org.apache.parquet.hadoop.ParquetFileReader#PARQUET_READ_PARALLELISM</exclude>
</excludes>
</parameter>
</configuration>
<executions>
<execution>
<phase>verify</phase>
<goals>
<goal>cmp</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-dependency-plugin</artifactId>
<executions>
<execution>
<goals>
<goal>analyze-only</goal>
</goals>
<configuration>
<failOnWarning>true</failOnWarning>
<ignoreNonCompile>true</ignoreNonCompile>
<ignoredDependencies>
<dependency>javax.annotation:javax.annotation-api:jar:1.3.2</dependency>
</ignoredDependencies>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.cyclonedx</groupId>
<artifactId>cyclonedx-maven-plugin</artifactId>
<version>2.8.0</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>makeBom</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
<profiles>
<profile>
<id>jdk9+</id>
<activation>
<jdk>[9,)</jdk>
</activation>
<properties>
<!-- release takes precedence over source/target if java version is 9 or higher -->
<maven.compiler.release>8</maven.compiler.release>
</properties>
</profile>
<profile>
<id>hadoop2</id>
<properties>
<hadoop.version>2.7.3</hadoop.version>
</properties>
</profile>
<!-- Profile for tests to have more output -->
<profile>
<id>verbose-test</id>
<properties>
<surefire.logLevel>INFO</surefire.logLevel>
<surefire.argLine>-XX:MaxJavaStackTraceDepth=1024</surefire.argLine>
</properties>
</profile>
<profile>
<id>vector-plugins</id>
<modules>
<module>parquet-plugins/parquet-encoding-vector</module>
<module>parquet-plugins/parquet-plugins-benchmarks</module>
</modules>
</profile>
</profiles>
</project>
Open source consumption has exploded, with estimates placing this year’s downloads at over 6.6 trillion. This reliance on open source components, now making up to 90% of the modern software application, has ushered in both unprecedented innovation and complex challenges for software supply chains.
View the Report