From 6aba5a5be4d419134e51cc9dffed985a8459d07f Mon Sep 17 00:00:00 2001 From: Richard Zowalla Date: Thu, 23 Jul 2026 12:17:48 +0200 Subject: [PATCH 1/3] Upgrade to Apache Storm 3.0.0 and Java 25 - bump storm-client.version to 3.0.0 and raise the compiler/javadoc level to Java 25 (Storm 3.0.0 requires Java 25) - bump storm.version and compiler level in the archetypes, update CI workflows to JDK 25 - WARC module: drop the obsolete jdk.tools/hive/hbase-server exclusions on storm-hdfs; the 3.0.0 artifact only pulls in the shaded hadoop-client-api/runtime. Exclude hbase-client, which is only needed by the AutoHBase credentials plugin - WARC module: replace the removed org.apache.storm.utils.Utils.gzip with a local GZIP helper in GzipHdfsBolt - update READMEs, quick-start docs and the regenerated THIRD-PARTY.txt Closes #2015 --- .github/workflows/main.yml | 4 ++-- .github/workflows/maven.yml | 4 ++-- README.md | 6 +++--- THIRD-PARTY.txt | 11 ++++++----- .../resources/archetype-resources/README.md | 2 +- .../main/resources/archetype-resources/pom.xml | 6 +++--- docs/src/main/asciidoc/quick-start.adoc | 2 +- .../main/resources/archetype-resources/pom.xml | 6 +++--- external/solr/README.md | 2 +- .../resources/archetype-resources/README.md | 2 +- .../main/resources/archetype-resources/pom.xml | 6 +++--- external/warc/README.md | 4 ++-- external/warc/pom.xml | 17 ++--------------- .../apache/stormcrawler/warc/GzipHdfsBolt.java | 14 ++++++++++++-- .../apache/stormcrawler/warc/WARCHdfsBolt.java | 3 +-- 15 files changed, 43 insertions(+), 46 deletions(-) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index bcc865847..99bd9bdf9 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -27,10 +27,10 @@ jobs: steps: - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 - - name: Set up JDK 17 + - name: Set up JDK 25 uses: actions/setup-java@03ad4de0992f5dab5e18fcb136590ce7c4a0ac95 # v5.6.0 with: - java-version: '17' + java-version: '25' distribution: 'temurin' - name: Cache Maven packages diff --git a/.github/workflows/maven.yml b/.github/workflows/maven.yml index 7da81f4d9..29af1bdf9 100644 --- a/.github/workflows/maven.yml +++ b/.github/workflows/maven.yml @@ -41,7 +41,7 @@ jobs: uses: actions/setup-java@03ad4de0992f5dab5e18fcb136590ce7c4a0ac95 # v5.6.0 with: distribution: adopt - java-version: 17 + java-version: 25 - name: Build with Maven run: mvn -B --no-transfer-progress -Prat -DskipTests verify -Dskip.format.code=false @@ -52,7 +52,7 @@ jobs: strategy: matrix: os: [ubuntu-latest] - java: [ 17 ] + java: [ 25 ] experimental: [false] steps: - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 diff --git a/README.md b/README.md index 31bf0727c..672e2c112 100644 --- a/README.md +++ b/README.md @@ -9,9 +9,9 @@ Apache StormCrawler is an open source collection of resources for building low-l ## Quickstart -NOTE: These instructions assume that you have [Apache Maven](https://maven.apache.org/install.html) installed. You will need to install [Apache Storm 2.8.9](http://storm.apache.org/) to run the crawler. +NOTE: These instructions assume that you have [Apache Maven](https://maven.apache.org/install.html) installed. You will need to install [Apache Storm 3.0.0](http://storm.apache.org/) to run the crawler. -StormCrawler requires Java 17 or above. To execute tests, it requires you to have a locally installed and working Docker environment. +StormCrawler requires Java 25 or above. To execute tests, it requires you to have a locally installed and working Docker environment. Once Storm is installed, the easiest way to get started is to generate a new StormCrawler project following the instructions below: @@ -53,7 +53,7 @@ mvn clean install -Dskip.format.code=false The requirements for building from source are as follows -- JDK 17+ +- JDK 25+ - Apache Maven 3 - Docker (if you want to run tests) diff --git a/THIRD-PARTY.txt b/THIRD-PARTY.txt index 2cefd8aff..c381dd065 100644 --- a/THIRD-PARTY.txt +++ b/THIRD-PARTY.txt @@ -28,6 +28,7 @@ List of third-party dependencies grouped by their license type. * Apache Commons CSV (org.apache.commons:commons-csv:1.14.1 - https://commons.apache.org/proper/commons-csv/) * Apache Commons Exec (org.apache.commons:commons-exec:1.6.0 - https://commons.apache.org/proper/commons-exec/) * Apache Commons IO (commons-io:commons-io:2.17.0 - https://commons.apache.org/proper/commons-io/) + * Apache Commons IO (commons-io:commons-io:2.20.0 - https://commons.apache.org/proper/commons-io/) * Apache Commons IO (commons-io:commons-io:2.22.0 - https://commons.apache.org/proper/commons-io/) * Apache Commons Lang (org.apache.commons:commons-lang3:3.20.0 - https://commons.apache.org/proper/commons-lang/) * Apache Commons Logging (commons-logging:commons-logging:1.2 - http://commons.apache.org/proper/commons-logging/) @@ -303,14 +304,14 @@ List of third-party dependencies grouped by their license type. * rome (com.rometools:rome:2.1.0 - http://rometools.com/rome) * rome-utils (com.rometools:rome-utils:2.1.0 - http://rometools.com/rome-utils) * server (org.opensearch:opensearch:2.19.6 - https://github.com/opensearch-project/OpenSearch.git) - * Shaded Deps for Storm Client (org.apache.storm:storm-shaded-deps:2.8.9 - https://storm.apache.org/storm-shaded-deps) * SnakeYAML (org.yaml:snakeyaml:2.6 - https://bitbucket.org/snakeyaml/snakeyaml) * snappy-java (org.xerial.snappy:snappy-java:1.1.10.4 - https://github.com/xerial/snappy-java) * sniffer (org.opensearch.client:opensearch-rest-client-sniffer:2.19.6 - https://github.com/opensearch-project/OpenSearch.git) * SparseBitSet (com.zaxxer:SparseBitSet:1.3 - https://github.com/brettwooldridge/SparseBitSet) - * storm-autocreds (org.apache.storm:storm-autocreds:2.8.9 - https://storm.apache.org/external/storm-autocreds) - * Storm Client (org.apache.storm:storm-client:2.8.9 - https://storm.apache.org/storm-client) - * storm-hdfs (org.apache.storm:storm-hdfs:2.8.9 - https://storm.apache.org/external/storm-hdfs) + * Storm Autocreds (org.apache.storm:storm-autocreds:3.0.0 - https://storm.apache.org/storm-external/storm-autocreds) + * Storm Client (org.apache.storm:storm-client:3.0.0 - https://storm.apache.org/storm-client) + * Storm HDFS (org.apache.storm:storm-hdfs:3.0.0 - https://storm.apache.org/storm-external/storm-hdfs) + * Storm Shaded Deps (org.apache.storm:storm-shaded-deps:3.0.0 - https://storm.apache.org/storm-shaded-deps) * swagger-annotations-jakarta (io.swagger.core.v3:swagger-annotations-jakarta:2.2.22 - https://github.com/swagger-api/swagger-core/modules/swagger-annotations-jakarta) * T-Digest (com.tdunning:t-digest:3.2 - https://github.com/tdunning/t-digest) * urlfrontier-API (com.github.crawler-commons:urlfrontier-API:2.5 - https://github.com/crawler-commons/url-frontier/urlfrontier-API) @@ -350,7 +351,7 @@ List of third-party dependencies grouped by their license type. BSD 2-Clause License - * zstd-jni (com.github.luben:zstd-jni:1.5.5-5 - https://github.com/luben/zstd-jni) + * zstd-jni (com.github.luben:zstd-jni:1.5.7-11 - https://github.com/luben/zstd-jni) BSD 3-Clause License diff --git a/archetype/src/main/resources/archetype-resources/README.md b/archetype/src/main/resources/archetype-resources/README.md index 21812d8c8..92f096b7f 100644 --- a/archetype/src/main/resources/archetype-resources/README.md +++ b/archetype/src/main/resources/archetype-resources/README.md @@ -5,7 +5,7 @@ Have a look at the code and resources and modify them to your heart's content. ## Native -You need to install Apache Storm. The instructions on [setting up a Storm cluster](https://storm.apache.org/releases/2.8.9/Setting-up-a-Storm-cluster.html) should help. +You need to install Apache Storm. The instructions on [setting up a Storm cluster](https://storm.apache.org/releases/3.0.0/Setting-up-a-Storm-cluster.html) should help. You also need to have an instance of URLFrontier running. See [the URLFrontier README](https://github.com/crawler-commons/url-frontier/tree/master/service); the easiest way is to use Docker, like so: ``` diff --git a/archetype/src/main/resources/archetype-resources/pom.xml b/archetype/src/main/resources/archetype-resources/pom.xml index ceb94aa5d..c57c09b92 100644 --- a/archetype/src/main/resources/archetype-resources/pom.xml +++ b/archetype/src/main/resources/archetype-resources/pom.xml @@ -32,7 +32,7 @@ under the License. UTF-8 ${project.version} - 2.8.9 + 3.0.0 2.4 @@ -43,8 +43,8 @@ under the License. maven-compiler-plugin 3.11.0 - 17 - 17 + 25 + 25 diff --git a/docs/src/main/asciidoc/quick-start.adoc b/docs/src/main/asciidoc/quick-start.adoc index ce780f10d..e42b27eb3 100644 --- a/docs/src/main/asciidoc/quick-start.adoc +++ b/docs/src/main/asciidoc/quick-start.adoc @@ -10,7 +10,7 @@ These instructions should help you get Apache StormCrawler up and running in 5 t === Prerequisites -To run StormCrawler, you will need Java SE 17 or later. +To run StormCrawler, you will need Java SE 25 or later. Additionally, since we'll be running the required Apache Storm cluster using Docker Compose, make sure Docker is installed on your operating system. diff --git a/external/opensearch/archetype/src/main/resources/archetype-resources/pom.xml b/external/opensearch/archetype/src/main/resources/archetype-resources/pom.xml index 6a0228f75..eff9791d4 100644 --- a/external/opensearch/archetype/src/main/resources/archetype-resources/pom.xml +++ b/external/opensearch/archetype/src/main/resources/archetype-resources/pom.xml @@ -34,7 +34,7 @@ under the License. UTF-8 ${StormCrawlerVersion} - 2.8.9 + 3.0.0 @@ -44,8 +44,8 @@ under the License. maven-compiler-plugin 3.11.0 - 17 - 17 + 25 + 25 diff --git a/external/solr/README.md b/external/solr/README.md index af8998b6e..226db5fbb 100644 --- a/external/solr/README.md +++ b/external/solr/README.md @@ -14,7 +14,7 @@ You'll be asked to enter a groupId (e.g. com.mycompany.crawler), an artefactId ( This will not only create a fully formed project containing a POM with the dependency above but also a set of resources, configuration files and sample topology classes. Enter the directory you just created (should be the same as the artefactId you specified earlier) and follow the instructions on the README file. -You will of course need to have both Apache Storm (2.8.9) and Apache Solr (10.0.0) installed. +You will of course need to have both Apache Storm (3.0.0) and Apache Solr (10.0.0) installed. Official references: * [Apache Storm: Setting Up a Development Environment](https://storm.apache.org/releases/current/Setting-up-development-environment.html) diff --git a/external/solr/archetype/src/main/resources/archetype-resources/README.md b/external/solr/archetype/src/main/resources/archetype-resources/README.md index 2a358bcf8..d6439caa6 100644 --- a/external/solr/archetype/src/main/resources/archetype-resources/README.md +++ b/external/solr/archetype/src/main/resources/archetype-resources/README.md @@ -1,7 +1,7 @@ This has been generated by the StormCrawler Maven Archetype as a starting point for building your own crawler with [Apache Solr](https://solr.apache.org/) as a backend. Have a look at the code and resources and modify them to your heart's content. -You need to have Apache Storm (2.8.9) installed, as well as a running instance of Apache Solr (10.0.0). +You need to have Apache Storm (3.0.0) installed, as well as a running instance of Apache Solr (9.8.0). ## Generated resources diff --git a/external/solr/archetype/src/main/resources/archetype-resources/pom.xml b/external/solr/archetype/src/main/resources/archetype-resources/pom.xml index dbcef9eb2..b0da46fd1 100644 --- a/external/solr/archetype/src/main/resources/archetype-resources/pom.xml +++ b/external/solr/archetype/src/main/resources/archetype-resources/pom.xml @@ -34,7 +34,7 @@ under the License. UTF-8 ${StormCrawlerVersion} - 2.8.9 + 3.0.0 @@ -44,8 +44,8 @@ under the License. maven-compiler-plugin 3.11.0 - 17 - 17 + 25 + 25 diff --git a/external/warc/README.md b/external/warc/README.md index b1b0466f4..8f22aa117 100644 --- a/external/warc/README.md +++ b/external/warc/README.md @@ -185,14 +185,14 @@ Please note that in order to access WARC files on AWS S3, you will need to add t org.apache.hadoop hadoop-aws - 2.10.1 + 3.5.0 ``` where the version should match the one used by Apache Storm. In doubt, you can check with ``` -mvn dependency:tree | grep "org.apache.hadoop:hadoop-hdfs:jar" +mvn dependency:tree | grep "org.apache.hadoop:hadoop-client-api:jar" ``` diff --git a/external/warc/pom.xml b/external/warc/pom.xml index fd52c5c00..87a4d8efb 100644 --- a/external/warc/pom.xml +++ b/external/warc/pom.xml @@ -63,22 +63,9 @@ under the License. ${storm-client.version} - - jdk.tools - jdk.tools - - - - org.apache.hive.hcatalog - hive-webhcat-java-client - - + org.apache.hbase - hbase-server - - - org.apache.hive.hcatalog - hive-hcatalog-streaming + hbase-client diff --git a/external/warc/src/main/java/org/apache/stormcrawler/warc/GzipHdfsBolt.java b/external/warc/src/main/java/org/apache/stormcrawler/warc/GzipHdfsBolt.java index 8342e7d91..a2d70d83b 100644 --- a/external/warc/src/main/java/org/apache/stormcrawler/warc/GzipHdfsBolt.java +++ b/external/warc/src/main/java/org/apache/stormcrawler/warc/GzipHdfsBolt.java @@ -15,9 +15,11 @@ package org.apache.stormcrawler.warc; +import java.io.ByteArrayOutputStream; import java.io.IOException; import java.util.ArrayList; import java.util.List; +import java.util.zip.GZIPOutputStream; import org.apache.hadoop.fs.FSDataOutputStream; import org.apache.hadoop.fs.Path; import org.apache.storm.hdfs.bolt.HdfsBolt; @@ -25,7 +27,6 @@ import org.apache.storm.hdfs.common.AbstractHDFSWriter; import org.apache.storm.hdfs.common.HDFSWriter; import org.apache.storm.tuple.Tuple; -import org.apache.storm.utils.Utils; import org.slf4j.Logger; import org.slf4j.LoggerFactory; @@ -34,6 +35,15 @@ public class GzipHdfsBolt extends HdfsBolt { private static final Logger LOG = LoggerFactory.getLogger(GzipHdfsBolt.class); + /** Compresses the given bytes into a standalone gzip container. */ + protected static byte[] gzip(byte[] bytes) throws IOException { + ByteArrayOutputStream bos = new ByteArrayOutputStream(bytes.length / 2 + 64); + try (GZIPOutputStream gzos = new GZIPOutputStream(bos)) { + gzos.write(bytes); + } + return bos.toByteArray(); + } + protected transient FSDataOutputStream out = null; protected RecordFormat format; @@ -59,7 +69,7 @@ public byte[] format(Tuple tuple) { if (bytes.length == 0 && !compressEmpty) { return new byte[0]; } - return Utils.gzip(bytes); + return gzip(bytes); } catch (Exception e) { LOG.error("Exception caught when formatting - skipping the whole tuple"); return new byte[0]; diff --git a/external/warc/src/main/java/org/apache/stormcrawler/warc/WARCHdfsBolt.java b/external/warc/src/main/java/org/apache/stormcrawler/warc/WARCHdfsBolt.java index 5b77a7289..48dcf32d9 100644 --- a/external/warc/src/main/java/org/apache/stormcrawler/warc/WARCHdfsBolt.java +++ b/external/warc/src/main/java/org/apache/stormcrawler/warc/WARCHdfsBolt.java @@ -30,7 +30,6 @@ import org.apache.storm.task.OutputCollector; import org.apache.storm.task.TopologyContext; import org.apache.storm.tuple.Tuple; -import org.apache.storm.utils.Utils; import org.apache.stormcrawler.protocol.ProtocolResponse; import org.apache.stormcrawler.util.ConfUtils; import org.slf4j.Logger; @@ -102,7 +101,7 @@ protected AbstractHDFSWriter makeNewWriter(Path path, Tuple tuple) throws IOExce // write the header at the beginning of the file if (header != null && header.length > 0) { - super.out.write(Utils.gzip(header)); + super.out.write(gzip(header)); } return writer; From 6976bc9a81d70fe4c37bf7aa672f3b05d56c902d Mon Sep 17 00:00:00 2001 From: Richard Zowalla Date: Sat, 1 Aug 2026 19:08:20 +0200 Subject: [PATCH 2/3] Move to StormCrawler 4 --- archetype/pom.xml | 2 +- core/pom.xml | 2 +- docs/pom.xml | 2 +- external/ai/pom.xml | 2 +- external/aws/pom.xml | 2 +- external/langid/pom.xml | 2 +- external/opensearch-java/pom.xml | 2 +- external/opensearch/archetype/pom.xml | 2 +- external/opensearch/pom.xml | 2 +- external/playwright/pom.xml | 2 +- external/pom.xml | 2 +- external/selenium/pom.xml | 2 +- external/solr/archetype/pom.xml | 2 +- external/solr/pom.xml | 2 +- external/sql/pom.xml | 2 +- external/tika/pom.xml | 2 +- external/urlfrontier/pom.xml | 2 +- external/warc/pom.xml | 2 +- pom.xml | 2 +- 19 files changed, 19 insertions(+), 19 deletions(-) diff --git a/archetype/pom.xml b/archetype/pom.xml index ac53b8055..388699d55 100644 --- a/archetype/pom.xml +++ b/archetype/pom.xml @@ -24,7 +24,7 @@ under the License. org.apache.stormcrawler stormcrawler - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT stormcrawler-archetype stormcrawler-archetype diff --git a/core/pom.xml b/core/pom.xml index 05c72aba4..a7ee05940 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT stormcrawler-core diff --git a/docs/pom.xml b/docs/pom.xml index e0b68c11f..2d4f33986 100644 --- a/docs/pom.xml +++ b/docs/pom.xml @@ -22,7 +22,7 @@ under the License. org.apache.stormcrawler stormcrawler - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT stormcrawler-docs diff --git a/external/ai/pom.xml b/external/ai/pom.xml index 3eb63a50f..c53ec25cc 100644 --- a/external/ai/pom.xml +++ b/external/ai/pom.xml @@ -24,7 +24,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/aws/pom.xml b/external/aws/pom.xml index 0074ad4b5..8bff15ff6 100644 --- a/external/aws/pom.xml +++ b/external/aws/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/langid/pom.xml b/external/langid/pom.xml index 18489a898..6621f7416 100644 --- a/external/langid/pom.xml +++ b/external/langid/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/opensearch-java/pom.xml b/external/opensearch-java/pom.xml index 4426bd5a5..acc965b1e 100644 --- a/external/opensearch-java/pom.xml +++ b/external/opensearch-java/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/opensearch/archetype/pom.xml b/external/opensearch/archetype/pom.xml index 018fea71a..6e19c4286 100644 --- a/external/opensearch/archetype/pom.xml +++ b/external/opensearch/archetype/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../../../pom.xml diff --git a/external/opensearch/pom.xml b/external/opensearch/pom.xml index a545d4d12..7813de106 100644 --- a/external/opensearch/pom.xml +++ b/external/opensearch/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/playwright/pom.xml b/external/playwright/pom.xml index 800533e4d..4a1225a2a 100644 --- a/external/playwright/pom.xml +++ b/external/playwright/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/pom.xml b/external/pom.xml index 09d4ba3bf..46cc8b675 100644 --- a/external/pom.xml +++ b/external/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/selenium/pom.xml b/external/selenium/pom.xml index 0227df460..d2e5d02e5 100644 --- a/external/selenium/pom.xml +++ b/external/selenium/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/solr/archetype/pom.xml b/external/solr/archetype/pom.xml index 2680a72c0..c72c4409f 100644 --- a/external/solr/archetype/pom.xml +++ b/external/solr/archetype/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../../../pom.xml diff --git a/external/solr/pom.xml b/external/solr/pom.xml index ad0d34ea1..2353ce8c8 100644 --- a/external/solr/pom.xml +++ b/external/solr/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/sql/pom.xml b/external/sql/pom.xml index 3914fc125..1dfe7d55f 100644 --- a/external/sql/pom.xml +++ b/external/sql/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/tika/pom.xml b/external/tika/pom.xml index b7c50a078..f1eba0922 100644 --- a/external/tika/pom.xml +++ b/external/tika/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/urlfrontier/pom.xml b/external/urlfrontier/pom.xml index aa76b8da1..de0c24966 100644 --- a/external/urlfrontier/pom.xml +++ b/external/urlfrontier/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/external/warc/pom.xml b/external/warc/pom.xml index 87a4d8efb..c97c1e697 100644 --- a/external/warc/pom.xml +++ b/external/warc/pom.xml @@ -25,7 +25,7 @@ under the License. org.apache.stormcrawler stormcrawler-external - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT ../pom.xml diff --git a/pom.xml b/pom.xml index 86884ada5..c78bd45f3 100644 --- a/pom.xml +++ b/pom.xml @@ -30,7 +30,7 @@ under the License. org.apache.stormcrawler stormcrawler - 3.7.1-SNAPSHOT + 4.0.0-SNAPSHOT pom stormcrawler From 1dbe0079c510c217782078843e532228b34a94b6 Mon Sep 17 00:00:00 2001 From: Richard Zowalla Date: Sat, 1 Aug 2026 19:09:09 +0200 Subject: [PATCH 3/3] Fix SOLR readme --- .../archetype/src/main/resources/archetype-resources/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/external/solr/archetype/src/main/resources/archetype-resources/README.md b/external/solr/archetype/src/main/resources/archetype-resources/README.md index d6439caa6..7ff319380 100644 --- a/external/solr/archetype/src/main/resources/archetype-resources/README.md +++ b/external/solr/archetype/src/main/resources/archetype-resources/README.md @@ -1,7 +1,7 @@ This has been generated by the StormCrawler Maven Archetype as a starting point for building your own crawler with [Apache Solr](https://solr.apache.org/) as a backend. Have a look at the code and resources and modify them to your heart's content. -You need to have Apache Storm (3.0.0) installed, as well as a running instance of Apache Solr (9.8.0). +You need to have Apache Storm (3.0.0) installed, as well as a running instance of Apache Solr (10.0.0). ## Generated resources