- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.template files (30): conf/date-styles.txt.template conf/regex-normalize.xml.template conf/contenttype-mapping.txt.template conf/adaptive-mimetypes.txt.template conf/prefix-urlfilter.txt.template conf/fast-urlfilter.txt.template conf/naivebayes-train.txt.template conf/protocols.txt.template conf/subcollections.xml.template conf/mimetype-filter.txt.template conf/index-writers.xml.template conf/parse-plugins.xml.template conf/httpclient-auth.xml.template conf/exchanges.xml.template conf/domaindenylist-urlfilter.txt.template conf/automaton-urlfilter.txt.template conf/naivebayes-wordlist.txt.template conf/adaptive-host-specific-intervals.txt.template conf/regex-parsefilter.txt.template conf/suffix-urlfilter.txt.template conf/nutch-site.xml.template conf/cookies.txt.template conf/host-urlnormalizer.txt.template conf/regex-urlfilter.txt.template conf/db-ignore-external-exemptions.txt.template conf/tika-config.xml.template conf/domain-urlfilter.txt.template conf/stopwords.txt.template conf/host-protocol-mapping.txt.template ivy/mvn.template - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *. files (29): src/bin/crawl src/bin/nutch src/plugin/parse-ext/command src/testresources/test-segments/20150309101625/crawl_fetch/part-00000/data src/testresources/test-segments/20150309101625/crawl_fetch/part-00000/index src/testresources/test-segments/20150309101625/parse_text/part-00000/data src/testresources/test-segments/20150309101625/parse_text/part-00000/index src/testresources/test-segments/20150309101625/parse_data/part-00000/data src/testresources/test-segments/20150309101625/parse_data/part-00000/index src/testresources/test-segments/20150309101625/crawl_generate/part-00000 src/testresources/test-segments/20150309101625/crawl_parse/part-00000 src/testresources/test-segments/20150309101625/content/part-00000/data src/testresources/test-segments/20150309101625/content/part-00000/index src/testresources/test-segments/20150309101656/crawl_fetch/part-00000/data src/testresources/test-segments/20150309101656/crawl_fetch/part-00000/index src/testresources/test-segments/20150309101656/parse_text/part-00000/data src/testresources/test-segments/20150309101656/parse_text/part-00000/index src/testresources/test-segments/20150309101656/parse_data/part-00000/data src/testresources/test-segments/20150309101656/parse_data/part-00000/index src/testresources/test-segments/20150309101656/crawl_generate/part-00000 src/testresources/test-segments/20150309101656/crawl_parse/part-00000 src/testresources/test-segments/20150309101656/content/part-00000/data src/testresources/test-segments/20150309101656/content/part-00000/index src/testresources/deduplication-crawldb/current/part-r-00000/data src/testresources/deduplication-crawldb/current/part-r-00000/index KEYS NOTICE-binary LICENSE-binary docker/Dockerfile - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.crc files (22): src/testresources/test-segments/20150309101625/crawl_fetch/part-00000/.index.crc src/testresources/test-segments/20150309101625/crawl_fetch/part-00000/.data.crc src/testresources/test-segments/20150309101625/parse_text/part-00000/.index.crc src/testresources/test-segments/20150309101625/parse_text/part-00000/.data.crc src/testresources/test-segments/20150309101625/parse_data/part-00000/.index.crc src/testresources/test-segments/20150309101625/parse_data/part-00000/.data.crc src/testresources/test-segments/20150309101625/crawl_generate/.part-00000.crc src/testresources/test-segments/20150309101625/crawl_parse/.part-00000.crc src/testresources/test-segments/20150309101625/content/part-00000/.index.crc src/testresources/test-segments/20150309101625/content/part-00000/.data.crc src/testresources/test-segments/20150309101656/crawl_fetch/part-00000/.index.crc src/testresources/test-segments/20150309101656/crawl_fetch/part-00000/.data.crc src/testresources/test-segments/20150309101656/parse_text/part-00000/.index.crc src/testresources/test-segments/20150309101656/parse_text/part-00000/.data.crc src/testresources/test-segments/20150309101656/parse_data/part-00000/.index.crc src/testresources/test-segments/20150309101656/parse_data/part-00000/.data.crc src/testresources/test-segments/20150309101656/crawl_generate/.part-00000.crc src/testresources/test-segments/20150309101656/crawl_parse/.part-00000.crc src/testresources/test-segments/20150309101656/content/part-00000/.index.crc src/testresources/test-segments/20150309101656/content/part-00000/.data.crc src/testresources/deduplication-crawldb/current/part-r-00000/.index.crc src/testresources/deduplication-crawldb/current/part-r-00000/.data.crc - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.test files (13): src/plugin/urlnormalizer-regex/sample/regex-normalize-default.test src/plugin/urlnormalizer-regex/sample/regex-normalize-scope1.test src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/en.test src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/sv.test src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/nl.test src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/pt.test src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/es.test src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/da.test src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/el.test src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/de.test src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/it.test src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/fi.test src/plugin/language-identifier/src/test/org/apache/nutch/analysis/lang/fr.test - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.urls files (9): src/plugin/urlfilter-automaton/sample/WholeWebCrawling.urls src/plugin/urlfilter-automaton/sample/IntranetCrawling.urls src/plugin/urlfilter-automaton/sample/Benchmarks.urls src/plugin/urlfilter-fast/sample/Benchmarks.urls src/plugin/urlfilter-fast/sample/test.urls src/plugin/urlfilter-regex/sample/nutch1838.urls src/plugin/urlfilter-regex/sample/WholeWebCrawling.urls src/plugin/urlfilter-regex/sample/IntranetCrawling.urls src/plugin/urlfilter-regex/sample/Benchmarks.urls - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.rules files (7): src/plugin/urlfilter-automaton/sample/WholeWebCrawling.rules src/plugin/urlfilter-automaton/sample/IntranetCrawling.rules src/plugin/urlfilter-automaton/sample/Benchmarks.rules src/plugin/urlfilter-regex/sample/WholeWebCrawling.rules src/plugin/urlfilter-regex/sample/IntranetCrawling.rules src/plugin/urlfilter-regex/sample/nutch1838.rules src/plugin/urlfilter-regex/sample/Benchmarks.rules - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.xlsx files (2): src/plugin/parse-tika/sample/test.xlsx src/testresources/test-mime-util/test.xlsx - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.conf files (2): docker/config/supervisord_startserver.conf docker/config/supervisord_startserver_webapp.conf - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.pdf files (2): src/plugin/parse-tika/sample/encrypted.pdf src/plugin/parse-tika/sample/pdftest.pdf - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.dtd files (2): conf/parse-plugins.dtd src/plugin/plugin.dtd - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.zip files (1): src/plugin/parse-zip/sample/test.zip - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.donotdelete files (1): src/plugin/urlfilter-ignoreexempt/data/.donotdelete - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.gif files (1): src/plugin/parse-tika/sample/nutch_logo_tm.gif - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.rtf files (1): src/plugin/parse-tika/sample/test.rtf - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.docx files (1): src/plugin/parse-tika/sample/test_recursive_embedded.docx - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.sxw files (1): src/plugin/parse-tika/sample/ootest.sxw - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.dockerfilelintrc files (1): docker/.dockerfilelintrc - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.doc files (1): src/plugin/parse-tika/sample/word97.doc - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.odt files (1): src/plugin/parse-tika/sample/ootest.odt - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *.yaml files (1): .github/workflows/master-build.yml - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -