storm-crawler
Used in:
components
- OverviewOverview
- VersionsVersions
- DependentsDependents
- DependenciesDependencies
<dependency>
<groupId>com.digitalpebble.stormcrawler</groupId>
<artifactId>storm-crawler</artifactId>
<version>2.11</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.digitalpebble.stormcrawler</groupId>
<artifactId>storm-crawler</artifactId>
<version>2.11</version>
<packaging>pom</packaging>
<name>storm-crawler</name>
<description>A collection of resources for building low-latency, scalable
web crawlers on Apache Storm.</description>
<url>http://stormcrawler.net/</url>
<licenses>
<license>
<name>The Apache License, Version 2.0</name>
<url>http://www.apache.org/licenses/LICENSE-2.0.txt</url>
</license>
</licenses>
<organization>
<name>DigitalPebble Ltd</name>
<url>http://www.digitalpebble.com</url>
</organization>
<developers>
<developer>
<name>Julien Nioche</name>
<email>julien@digitalpebble.com</email>
<organization>DigitalPebble</organization>
<organizationUrl>http://www.digitalpebble.com</organizationUrl>
</developer>
</developers>
<contributors>
<contributor>
<name>Sebastian Nagel</name>
<email>sebastian@commoncrawl.org</email>
<organization>CommonCrawl</organization>
<organizationUrl>http://commoncrawl.org</organizationUrl>
</contributor>
<contributor>
<name>Jorge Luis Betancourt</name>
<email>betancourt.jorge@gmail.com</email>
<organization>trivago</organization>
<organizationUrl>https://www.trivago.com</organizationUrl>
</contributor>
<contributor>
<name>Richard Zowalla</name>
<email>richard.zowalla@hs-heilbronn.de</email>
<organization>Heilbronn University</organization>
<organizationUrl>https://www.mi.hs-heilbronn.de</organizationUrl>
</contributor>
<contributor>
<name>Michael Dinzinger</name>
<email>michael.dinzinger@uni-passau.de</email>
<organization>Universität Passau</organization>
<organizationUrl>https://www.fim.uni-passau.de</organizationUrl>
</contributor>
</contributors>
<scm>
<connection>scm:git:https://github.com/DigitalPebble/storm-crawler.git</connection>
<developerConnection>
scm:git:git@github.com:DigitalPebble/storm-crawler.git</developerConnection>
<url>https://github.com/DigitalPebble/storm-crawler</url>
<tag>2.11</tag>
</scm>
<issueManagement>
<system>GitHub Issues</system>
<url>https://github.com/DigitalPebble/storm-crawler/issues</url>
</issueManagement>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<additionalparam>-Xdoclint:none</additionalparam>
<!-- dependency versions -->
<junit.version>4.13.2</junit.version>
<storm-client.version>2.6.0</storm-client.version>
<jackson.version>2.15.2</jackson.version>
<tika.version>2.9.1</tika.version>
<mockito.version>5.8.0</mockito.version>
<jetbrains.annotations.version>24.1.0</jetbrains.annotations.version>
<log4j2.version>2.21.1</log4j2.version>
<git-code-format-maven-plugin.version>5.1</git-code-format-maven-plugin.version>
<testcontainers.version>1.19.3</testcontainers.version>
</properties>
<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>
<build>
<pluginManagement>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>3.2.1</version>
<configuration>
<argLine>${argLine}</argLine>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.11.0</version>
<configuration>
<source>11</source>
<target>11</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-jar-plugin</artifactId>
<version>3.3.0</version>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-release-plugin</artifactId>
<version>3.0.1</version>
<configuration>
<autoVersionSubmodules>true</autoVersionSubmodules>
<useReleaseProfile>false</useReleaseProfile>
<releaseProfiles>release</releaseProfiles>
<goals>deploy</goals>
</configuration>
</plugin>
</plugins>
</pluginManagement>
<plugins>
<plugin>
<groupId>org.jacoco</groupId>
<artifactId>jacoco-maven-plugin</artifactId>
<version>0.8.11</version>
<executions>
<execution>
<id>prepare-agent</id>
<goals>
<goal>prepare-agent</goal>
</goals>
</execution>
<execution>
<id>post-unit-test</id>
<phase>test</phase>
<goals>
<goal>report</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.eluder.coveralls</groupId>
<artifactId>coveralls-maven-plugin</artifactId>
<version>4.3.0</version>
<dependencies>
<dependency>
<groupId>javax.xml.bind</groupId>
<artifactId>jaxb-api</artifactId>
<version>2.3.1</version>
</dependency>
</dependencies>
</plugin>
<plugin>
<groupId>com.cosium.code</groupId>
<artifactId>git-code-format-maven-plugin</artifactId>
<version>${git-code-format-maven-plugin.version}</version>
<executions>
<!-- On commit, format the modified java files -->
<execution>
<id>install-formatter-hook</id>
<goals>
<goal>install-hooks</goal>
</goals>
</execution>
<!-- On Maven verify phase, fail if any file (including
unmodified)
is badly formatted -->
<execution>
<id>validate-code-format</id>
<goals>
<goal>validate-code-format</goal>
</goals>
</execution>
</executions>
<dependencies>
<!-- Enable https://github.com/google/google-java-format -->
<dependency>
<groupId>com.cosium.code</groupId>
<artifactId>google-java-format</artifactId>
<version>${git-code-format-maven-plugin.version}</version>
</dependency>
</dependencies>
<configuration>
<formatterOptions>
<googleJavaFormat.aosp>true</googleJavaFormat.aosp>
<googleJavaFormat.fixImportsOnly>false</googleJavaFormat.fixImportsOnly>
<googleJavaFormat.skipSortingImports>false</googleJavaFormat.skipSortingImports>
<googleJavaFormat.skipRemovingUnusedImports>false</googleJavaFormat.skipRemovingUnusedImports>
</formatterOptions>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-enforcer-plugin</artifactId>
<version>3.4.1</version>
<executions>
<execution>
<id>enforce-maven</id>
<configuration>
<rules>
<requireMavenVersion>
<version>3.5</version>
</requireMavenVersion>
</rules>
</configuration>
<goals>
<goal>enforce</goal>
</goals>
</execution>
<execution>
<id>exclude-vulnerable-log4j-versions</id>
<phase>validate</phase>
<goals>
<goal>enforce</goal>
</goals>
<configuration>
<rules>
<bannedDependencies>
<excludes>
<exclude>
org.apache.logging.log4j:log4j-core:(,2.17.0)</exclude>
</excludes>
</bannedDependencies>
</rules>
<fail>true</fail>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
<profiles>
<profile>
<id>release</id>
<build>
<pluginManagement>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-source-plugin</artifactId>
<version>3.3.0</version>
<executions>
<execution>
<id>attach-sources</id>
<goals>
<goal>jar-no-fork</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-jar-plugin</artifactId>
<version>3.3.0</version>
<executions>
<execution>
<id>attach-test</id>
<goals>
<goal>test-jar</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<version>3.6.0</version>
<executions>
<execution>
<id>attach-javadocs</id>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</pluginManagement>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-gpg-plugin</artifactId>
<version>3.1.0</version>
<executions>
<execution>
<id>sign-artifacts</id>
<phase>verify</phase>
<goals>
<goal>sign</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
</profile>
</profiles>
<dependencyManagement>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>${junit.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.storm</groupId>
<artifactId>storm-client</artifactId>
<version>${storm-client.version}</version>
<!-- keep storm out of the jar-with-dependencies -->
<scope>provided</scope>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
<version>${jackson.version}</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
<version>${jackson.version}</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.jetbrains/annotations -->
<dependency>
<groupId>org.jetbrains</groupId>
<artifactId>annotations</artifactId>
<version>${jetbrains.annotations.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>org.testcontainers</groupId>
<artifactId>testcontainers-bom</artifactId>
<version>${testcontainers.version}</version>
<type>pom</type>
<scope>import</scope>
</dependency>
</dependencies>
</dependencyManagement>
<modules>
<module>core</module>
<module>external</module>
<module>external/aws</module>
<module>external/elasticsearch</module>
<module>external/langid</module>
<module>external/opensearch</module>
<module>external/solr</module>
<module>external/sql</module>
<module>external/tika</module>
<module>external/urlfrontier</module>
<module>external/warc</module>
<module>archetype</module>
<module>external/elasticsearch/archetype</module>
<module>external/opensearch/archetype</module>
</modules>
</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