schema-inferer
Used in:
components
- OverviewOverview
- VersionsVersions
- DependentsDependents
- DependenciesDependencies
<dependency>
<groupId>com.groupon.dse</groupId>
<artifactId>schema-inferer</artifactId>
<version>1.0</version>
</dependency><?xml version="1.0" encoding="UTF-8"?>
<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/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.groupon.dse</groupId>
<artifactId>schema-inferer</artifactId>
<version>1.0</version>
<name>${project.groupId}:${project.artifactId}</name>
<description>
Schema Inferer is a library, based on Spark Streaming, that can be used to infer the schema of a given Kafka
data stream and continously monitor the stream for schema changes
</description>
<url>https://github.com/groupon/schema-inferer</url>
<licenses>
<license>
<name>The BSD 3-Clause License</name>
<url>https://opensource.org/licenses/BSD-3-Clause</url>
</license>
</licenses>
<developers>
<developer>
<name>Udit Mehta</name>
<email>umehta@groupon.com</email>
<organization>Groupon</organization>
<organizationUrl>http://www.groupon.com</organizationUrl>
</developer>
<developer>
<id>Rakesh Nair</id>
<email>rakesh@groupon.com</email>
<organization>Groupon</organization>
<organizationUrl>http://www.groupon.com</organizationUrl>
</developer>
</developers>
<scm>
<connection>scm:git:git@github.com:groupon/schema-inferer.git</connection>
<developerConnection>scm:git:git@github.com:groupon/schema-inferer.git</developerConnection>
<url>https://github.com/groupon/schema-inferer</url>
<tag>schema-inferer-1.0</tag>
</scm>
<distributionManagement>
<snapshotRepository>
<id>ossrh</id>
<url>https://oss.sonatype.org/content/repositories/snapshots</url>
</snapshotRepository>
<repository>
<id>ossrh</id>
<url>https://oss.sonatype.org/service/local/staging/deploy/maven2/</url>
</repository>
</distributionManagement>
<parent>
<groupId>org.basepom</groupId>
<artifactId>basepom-oss</artifactId>
<version>18</version>
</parent>
<properties>
<baryon.version>1.0</baryon.version>
<spark.version>1.5.2</spark.version>
<slf4j.version>1.7.10</slf4j.version>
<zkclient.version>0.7</zkclient.version>
<zookeeper.version>3.4.6</zookeeper.version>
<kafka.version>0.8.1.1</kafka.version>
<json4s.version>3.2.10</json4s.version>
<!-- Test Dependencies -->
<scalatest.version>2.2.4</scalatest.version>
<log4j.version>1.2.17</log4j.version>
<mockito.version>1.10.8</mockito.version>
<!-- Project and Plugin Settings -->
<project.maven.version>3.3.3</project.maven.version>
<project.build.targetJdk>1.7</project.build.targetJdk>
<dep.scala.version>2.10.4</dep.scala.version>
<project.plugin.scala.version>3.2.2</project.plugin.scala.version>
<project.plugin.scalatest.version>1.0</project.plugin.scalatest.version>
<project.plugin.scalastyle.version>0.6.0</project.plugin.scalastyle.version>
<basepom.check.fail-duplicate-finder>false</basepom.check.fail-duplicate-finder>
<basepom.check.fail-findbugs>false</basepom.check.fail-findbugs>
<basepom.oss.skip-scala-doc>false</basepom.oss.skip-scala-doc>
<basepom.release.push-changes>true</basepom.release.push-changes>
</properties>
<prerequisites>
<maven>${project.maven.version}</maven>
</prerequisites>
<build>
<plugins>
<plugin>
<groupId>org.scalatest</groupId>
<artifactId>scalatest-maven-plugin</artifactId>
<version>${project.plugin.scalatest.version}</version>
<configuration>
<reportsDirectory>${project.build.directory}/surefire-reports</reportsDirectory>
<junitxml>.</junitxml>
<filereports>WDF TestSuite.txt</filereports>
</configuration>
<executions>
<execution>
<id>test</id>
<goals>
<goal>test</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.scalastyle</groupId>
<artifactId>scalastyle-maven-plugin</artifactId>
<version>${project.plugin.scalastyle.version}</version>
<configuration>
<verbose>false</verbose>
<failOnViolation>true</failOnViolation>
<includeTestSourceDirectory>false</includeTestSourceDirectory>
<failOnWarning>false</failOnWarning>
<sourceDirectory>src/main/scala</sourceDirectory>
<testSourceDirectory>src/test/scala</testSourceDirectory>
<configLocation>src/main/resources/scalastyle_config.xml</configLocation>
<outputFile>scalastyle_output.xml</outputFile>
<outputEncoding>UTF-8</outputEncoding>
</configuration>
<executions>
<execution>
<phase>compile</phase>
<goals>
<goal>check</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
<pluginManagement>
<plugins>
<plugin>
<groupId>com.mycila</groupId>
<artifactId>license-maven-plugin</artifactId>
<configuration>
<excludes>
<exclude>**/pom.xml</exclude>
<exclude>**/scalastyle_config.xml</exclude>
</excludes>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-release-plugin</artifactId>
<version>${dep.plugin.release.version}</version>
<configuration>
<useReleaseProfile>true</useReleaseProfile>
<releaseProfiles>basepom.oss-release</releaseProfiles>
</configuration>
</plugin>
</plugins>
</pluginManagement>
</build>
<dependencies>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${dep.scala.version}</version>
</dependency>
<dependency>
<groupId>com.groupon.dse</groupId>
<artifactId>baryon</artifactId>
<version>${baryon.version}</version>
<exclusions>
<exclusion>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpcore</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
<exclusion>
<groupId>org.xerial.snappy</groupId>
<artifactId>snappy-java</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.10</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
<exclusions>
<exclusion>
<groupId>com.google.code.findbugs</groupId>
<artifactId>jsr305</artifactId>
</exclusion>
<exclusion>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.10</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
<exclusions>
<exclusion>
<groupId>org.apache.zookeeper</groupId>
<artifactId>zookeeper</artifactId>
</exclusion>
<exclusion>
<groupId>com.google.code.findbugs</groupId>
<artifactId>jsr305</artifactId>
</exclusion>
<exclusion>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-catalyst_2.10</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
<exclusions>
<exclusion>
<groupId>com.google.code.findbugs</groupId>
<artifactId>jsr305</artifactId>
</exclusion>
<exclusion>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.10</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
<exclusions>
<exclusion>
<groupId>com.google.code.findbugs</groupId>
<artifactId>jsr305</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_2.10</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
<exclusions>
<exclusion>
<groupId>org.apache.zookeeper</groupId>
<artifactId>zookeeper</artifactId>
</exclusion>
<exclusion>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</exclusion>
<exclusion>
<groupId>com.thoughtworks.paranamer</groupId>
<artifactId>paranamer</artifactId>
</exclusion>
<exclusion>
<groupId>commons-collections</groupId>
<artifactId>commons-collections</artifactId>
</exclusion>
<exclusion>
<groupId>commons-lang</groupId>
<artifactId>commons-lang</artifactId>
</exclusion>
<exclusion>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-core</artifactId>
</exclusion>
<exclusion>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
</exclusion>
<exclusion>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
</exclusion>
<exclusion>
<groupId>com.google.code.findbugs</groupId>
<artifactId>jsr305</artifactId>
</exclusion>
<exclusion>
<groupId>jline</groupId>
<artifactId>jline</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka_2.10</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
<exclusions>
<exclusion>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka_2.10</artifactId>
</exclusion>
<exclusion>
<groupId>com.101tec</groupId>
<artifactId>zkclient</artifactId>
</exclusion>
<exclusion>
<groupId>org.xerial.snappy</groupId>
<artifactId>snappy-java</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka_2.10</artifactId>
<version>${kafka.version}</version>
<exclusions>
<exclusion>
<groupId>com.101tec</groupId>
<artifactId>zkclient</artifactId>
</exclusion>
<exclusion>
<groupId>org.xerial.snappy</groupId>
<artifactId>snappy-java</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>com.101tec</groupId>
<artifactId>zkclient</artifactId>
<version>${zkclient.version}</version>
<exclusions>
<exclusion>
<groupId>io.netty</groupId>
<artifactId>netty</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.zookeeper</groupId>
<artifactId>zookeeper</artifactId>
<version>${zookeeper.version}</version>
<exclusions>
<exclusion>
<groupId>io.netty</groupId>
<artifactId>netty</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.json4s</groupId>
<artifactId>json4s-core_2.10</artifactId>
<version>${json4s.version}</version>
</dependency>
<dependency>
<groupId>org.json4s</groupId>
<artifactId>json4s-jackson_2.10</artifactId>
<version>${json4s.version}</version>
</dependency>
<!-- Resolve dependency issues -->
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
<version>${slf4j.version}</version>
</dependency>
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>${log4j.version}</version>
<scope>provided</scope>
</dependency>
<!-- Test dependencies -->
<dependency>
<groupId>org.scalatest</groupId>
<artifactId>scalatest_2.10</artifactId>
<version>${scalatest.version}</version>
<scope>test</scope>
</dependency>
</dependencies>
</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