- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Dependencies path like ".*/extern(al)?/.*" 141 files: external/solr/pom.xml external/solr/configsets/metrics/conf/schema.xml external/solr/configsets/metrics/conf/solrconfig.xml external/solr/configsets/docs/conf/schema.xml external/solr/configsets/docs/conf/synonyms.txt external/solr/configsets/docs/conf/solrconfig.xml external/solr/configsets/docs/conf/stopwords.txt external/solr/configsets/status/conf/schema.xml external/solr/configsets/status/conf/solrconfig.xml external/solr/README.md external/solr/src/main/java/org/apache/stormcrawler/solr/metrics/MetricsConsumer.java external/solr/src/main/java/org/apache/stormcrawler/solr/Constants.java external/solr/src/main/java/org/apache/stormcrawler/solr/persistence/SolrSpout.java external/solr/src/main/java/org/apache/stormcrawler/solr/persistence/StatusUpdaterBolt.java external/solr/src/main/java/org/apache/stormcrawler/solr/bolt/IndexerBolt.java external/solr/src/main/java/org/apache/stormcrawler/solr/bolt/DeletionBolt.java external/solr/src/main/java/org/apache/stormcrawler/solr/SolrConnection.java external/solr/src/test/java/org/apache/stormcrawler/solr/persistence/IndexerBoltTest.java external/solr/src/test/java/org/apache/stormcrawler/solr/persistence/SolrContainerTest.java external/solr/src/test/java/org/apache/stormcrawler/solr/persistence/StatusBoltTest.java external/solr/src/test/java/org/apache/stormcrawler/solr/persistence/SpoutTest.java external/solr/archetype/pom.xml external/solr/archetype/src/main/resources/archetype-resources/pom.xml external/solr/archetype/src/main/resources/archetype-resources/clear-collections.sh external/solr/archetype/src/main/resources/archetype-resources/configsets/metrics/conf/schema.xml external/solr/archetype/src/main/resources/archetype-resources/configsets/metrics/conf/solrconfig.xml external/solr/archetype/src/main/resources/archetype-resources/configsets/docs/conf/schema.xml external/solr/archetype/src/main/resources/archetype-resources/configsets/docs/conf/synonyms.txt external/solr/archetype/src/main/resources/archetype-resources/configsets/docs/conf/solrconfig.xml external/solr/archetype/src/main/resources/archetype-resources/configsets/docs/conf/stopwords.txt external/solr/archetype/src/main/resources/archetype-resources/configsets/status/conf/schema.xml external/solr/archetype/src/main/resources/archetype-resources/configsets/status/conf/solrconfig.xml external/solr/archetype/src/main/resources/archetype-resources/crawler-conf.yaml external/solr/archetype/src/main/resources/archetype-resources/solr-conf.yaml external/solr/archetype/src/main/resources/archetype-resources/README.md external/solr/archetype/src/main/resources/archetype-resources/src/main/resources/default-regex-filters.txt external/solr/archetype/src/main/resources/archetype-resources/src/main/resources/urlfilters.json external/solr/archetype/src/main/resources/archetype-resources/src/main/resources/jsoupfilters.json external/solr/archetype/src/main/resources/archetype-resources/src/main/resources/parsefilters.json external/solr/archetype/src/main/resources/archetype-resources/src/main/resources/default-regex-normalizers.xml external/solr/archetype/src/main/resources/archetype-resources/seeds.txt external/solr/archetype/src/main/resources/archetype-resources/crawler.flux external/solr/archetype/src/main/resources/archetype-resources/injection.flux external/solr/archetype/src/main/resources/archetype-resources/setup-solr.sh external/solr/archetype/src/main/resources/META-INF/maven/archetype-metadata.xml external/solr/archetype/src/main/resources/META-INF/archetype-post-generate.groovy external/pom.xml external/sql/pom.xml external/sql/README.md external/sql/src/main/java/org/apache/stormcrawler/sql/metrics/MetricsConsumer.java external/sql/src/main/java/org/apache/stormcrawler/sql/SQLUtil.java external/sql/src/main/java/org/apache/stormcrawler/sql/Constants.java external/sql/src/main/java/org/apache/stormcrawler/sql/SQLSpout.java external/sql/src/main/java/org/apache/stormcrawler/sql/IndexerBolt.java external/sql/src/main/java/org/apache/stormcrawler/sql/StatusUpdaterBolt.java external/sql/sql-conf.yaml external/tika/pom.xml external/tika/README.md external/tika/src/main/java/org/apache/stormcrawler/tika/DOMBuilder.java external/tika/src/main/java/org/apache/stormcrawler/tika/ParserBolt.java external/tika/src/main/java/org/apache/stormcrawler/tika/RedirectionBolt.java external/tika/src/main/java/org/apache/stormcrawler/tika/XMLCharacterRecognizer.java external/tika/src/main/resources/tika-config.xml external/tika/src/test/java/org/apache/stormcrawler/tika/ParserBoltTest.java external/elasticsearch/README.md external/aws/pom.xml external/aws/aws-conf.yaml external/aws/README.md external/aws/src/main/java/org/apache/stormcrawler/aws/bolt/CloudSearchUtils.java external/aws/src/main/java/org/apache/stormcrawler/aws/bolt/CloudSearchIndexerBolt.java external/aws/src/main/java/org/apache/stormcrawler/aws/bolt/CloudSearchConstants.java external/aws/src/main/java/org/apache/stormcrawler/aws/s3/S3Cacher.java external/aws/src/main/java/org/apache/stormcrawler/aws/s3/AbstractS3CacheBolt.java external/aws/src/main/java/org/apache/stormcrawler/aws/s3/S3ContentCacher.java external/aws/src/main/java/org/apache/stormcrawler/aws/s3/S3CacheChecker.java external/warc/pom.xml external/warc/README.md external/warc/src/main/java/org/apache/stormcrawler/warc/WARCRequestRecordFormat.java external/warc/src/main/java/org/apache/stormcrawler/warc/GzipHdfsBolt.java external/warc/src/main/java/org/apache/stormcrawler/warc/WARCHdfsBolt.java external/warc/src/main/java/org/apache/stormcrawler/warc/WARCFileNameFormat.java external/warc/src/main/java/org/apache/stormcrawler/warc/MetadataRecordFormat.java external/warc/src/main/java/org/apache/stormcrawler/warc/WARCRecordFormat.java external/warc/src/main/java/org/apache/stormcrawler/warc/WARCSpout.java external/warc/src/main/java/org/apache/stormcrawler/warc/FileTimeSizeRotationPolicy.java external/warc/src/test/java/org/apache/stormcrawler/warc/WARCRecordFormatTest.java external/warc/src/test/java/org/apache/stormcrawler/warc/WARCSpoutTest.java external/warc/src/test/java/org/apache/stormcrawler/warc/WARCHdfsBoltTest.java external/opensearch/pom.xml external/opensearch/opensearch-conf.yaml external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/metrics/MetricsConsumer.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/metrics/StatusMetricsBolt.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/parse/filter/JSONResourceWrapper.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/Constants.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/persistence/AggregationSpout.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/persistence/AbstractSpout.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/persistence/StatusUpdaterBolt.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/persistence/HybridSpout.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/bolt/IndexerBolt.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/bolt/DeletionBolt.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/filtering/JSONURLFilterWrapper.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/IndexCreation.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/OpenSearchConnection.java external/opensearch/src/main/java/org/apache/stormcrawler/opensearch/BulkItemResponseToFailedFlag.java external/opensearch/src/test/java/org/apache/stormcrawler/opensearch/bolt/IndexerBoltTest.java external/opensearch/src/test/java/org/apache/stormcrawler/opensearch/bolt/AbstractOpenSearchTest.java external/opensearch/src/test/java/org/apache/stormcrawler/opensearch/bolt/StatusBoltTest.java external/opensearch/archetype/pom.xml external/opensearch/archetype/src/main/resources/archetype-resources/pom.xml external/opensearch/archetype/src/main/resources/archetype-resources/OS_IndexInit.sh external/opensearch/archetype/src/main/resources/archetype-resources/opensearch-conf.yaml external/opensearch/archetype/src/main/resources/archetype-resources/crawler-conf.yaml external/opensearch/archetype/src/main/resources/archetype-resources/src/main/resources/default-regex-filters.txt external/opensearch/archetype/src/main/resources/archetype-resources/src/main/resources/urlfilters.json external/opensearch/archetype/src/main/resources/archetype-resources/src/main/resources/jsoupfilters.json external/opensearch/archetype/src/main/resources/archetype-resources/src/main/resources/parsefilters.json external/opensearch/archetype/src/main/resources/archetype-resources/src/main/resources/default-regex-normalizers.xml external/opensearch/archetype/src/main/resources/archetype-resources/crawler.flux external/opensearch/archetype/src/main/resources/archetype-resources/injection.flux external/opensearch/archetype/src/main/resources/archetype-resources/dashboards/importDashboards.sh external/opensearch/archetype/src/main/resources/META-INF/maven/archetype-metadata.xml external/opensearch/archetype/src/main/resources/META-INF/archetype-post-generate.groovy external/opensearch/dashboards/importDashboards.sh external/urlfrontier/pom.xml external/urlfrontier/README.md external/urlfrontier/src/main/java/org/apache/stormcrawler/urlfrontier/ManagedChannelUtil.java external/urlfrontier/src/main/java/org/apache/stormcrawler/urlfrontier/Constants.java external/urlfrontier/src/main/java/org/apache/stormcrawler/urlfrontier/StatusUpdaterBolt.java external/urlfrontier/src/main/java/org/apache/stormcrawler/urlfrontier/Spout.java external/urlfrontier/src/test/java/org/apache/stormcrawler/urlfrontier/URLFrontierContainer.java external/urlfrontier/src/test/java/org/apache/stormcrawler/urlfrontier/URLFrontierContainerConfig.java external/urlfrontier/src/test/java/org/apache/stormcrawler/urlfrontier/StatusUpdaterBoltTest.java external/playwright/pom.xml external/playwright/README.md external/playwright/src/main/java/org/apache/stormcrawler/protocol/playwright/HttpProtocol.java external/playwright/src/test/java/org/apache/stormcrawler/protocol/playwright/LocalResourceHandler.java external/playwright/src/test/java/org/apache/stormcrawler/protocol/playwright/ProtocolTest.java external/playwright/src/test/resources/dynamic-scraping.html external/playwright/playwright-conf.yaml external/langid/pom.xml external/langid/src/main/java/org/apache/stormcrawler/parse/filter/LanguageID.java - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Hidden files and folders path like ".*/[.][a-zA-Z0-9_]+.*" 6 files: .github/workflows/snapshots.yaml .github/PULL_REQUEST_TEMPLATE.md .gitignore .asf.yaml archetype/src/main/resources/archetype-resources/.gitignore .gitattributes - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Too long lines (1000+ characters) 3 files: external/opensearch/README.md external/opensearch/archetype/src/main/resources/archetype-resources/README.md core/src/test/resources/stackexception.html - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Too long file (1000000+ bytes) 2 files: git-history.txt core/src/test/resources/longtext.html - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -