This is an automated email from the ASF dual-hosted git repository. tallison pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tika.git.
from 9405c5f TIKA-3179 -- Fix parent information in tika-parsers-extended TIKA-3183 -- alphabetize/normalize properties new aad9659 TIKA-3179 -- fix parent in tika-parsers module new c2a2567 TIKA-3176 -- modularize language detectors The 2 revisions listed above as "new" are entirely new to this repository and will be described in separate emails. The revisions listed as "add" were already present in the repository and have only been added to this reference. Summary of changes: pom.xml | 2 +- tika-app/pom.xml | 2 +- tika-langdetect/pom.xml | 227 +++------------------ .../tika-langdetect-commons}/pom.xml | 15 +- .../tika/langdetect/LanguageDetectorTest.java | 3 +- .../src/test/resources/log4j.properties | 0 .../apache/tika/langdetect/language-tests/da.test | 0 .../apache/tika/langdetect/language-tests/de.test | 0 .../apache/tika/langdetect/language-tests/el.test | 0 .../apache/tika/langdetect/language-tests/en.test | 0 .../apache/tika/langdetect/language-tests/es.test | 0 .../apache/tika/langdetect/language-tests/et.test | 0 .../apache/tika/langdetect/language-tests/fi.test | 0 .../apache/tika/langdetect/language-tests/fr.test | 0 .../apache/tika/langdetect/language-tests/it.test | 0 .../apache/tika/langdetect/language-tests/ja.test | 0 .../apache/tika/langdetect/language-tests/lt.test | 0 .../apache/tika/langdetect/language-tests/nl.test | 0 .../apache/tika/langdetect/language-tests/pt.test | 0 .../apache/tika/langdetect/language-tests/sv.test | 0 .../apache/tika/langdetect/language-tests/th.test | 0 .../apache/tika/langdetect/language-tests/zh.test | 0 .../org/apache/tika/langdetect/text-test.tsv | 0 tika-langdetect/tika-langdetect-lingo24/pom.xml | 74 +++++++ .../langdetect/lingo24}/Lingo24LangDetector.java | 2 +- ...rg.apache.tika.language.detect.LanguageDetector | 2 +- .../lingo24}/langdetect.lingo24.properties | 0 .../lingo24}/Lingo24LangDetectorTest.java | 19 +- tika-langdetect/tika-langdetect-mitll-text/pom.xml | 73 +++++++ .../tika/langdetect/mitll}/TextLangDetector.java | 2 +- ...rg.apache.tika.language.detect.LanguageDetector | 2 +- .../langdetect/mitll}/TextLangDetectorTest.java | 12 +- .../src/test/resources/log4j.properties | 0 .../tika-langdetect-optimaize}/pom.xml | 38 ++-- .../optimaize}/OptimaizeLangDetector.java | 2 +- ...rg.apache.tika.language.detect.LanguageDetector | 2 +- .../optimaize}/OptimaizeLangDetectorTest.java | 3 +- .../tika/langdetect/optimaize}/language-codes.txt | 0 .../tika/langdetect/optimaize}/udhr-known.txt | 0 .../tika/langdetect/optimaize}/udhr-unknown.txt | 0 tika-parsers/pom.xml | 15 +- tika-parsers/tika-parser-apple-module/pom.xml | 2 +- tika-parsers/tika-parser-audiovideo-module/pom.xml | 2 +- tika-parsers/tika-parser-cad-module/pom.xml | 2 +- tika-parsers/tika-parser-code-module/pom.xml | 2 +- tika-parsers/tika-parser-crypto-module/pom.xml | 2 +- tika-parsers/tika-parser-digest-commons/pom.xml | 2 +- tika-parsers/tika-parser-font-module/pom.xml | 2 +- tika-parsers/tika-parser-html-module/pom.xml | 2 +- tika-parsers/tika-parser-image-module/pom.xml | 2 +- tika-parsers/tika-parser-integration-tests/pom.xml | 2 +- tika-parsers/tika-parser-jdbc-commons/pom.xml | 2 +- tika-parsers/tika-parser-mail-commons/pom.xml | 2 +- tika-parsers/tika-parser-mail-module/pom.xml | 2 +- tika-parsers/tika-parser-microsoft-module/pom.xml | 2 +- tika-parsers/tika-parser-miscoffice-module/pom.xml | 2 +- tika-parsers/tika-parser-news-module/pom.xml | 2 +- tika-parsers/tika-parser-ocr-module/pom.xml | 2 +- tika-parsers/tika-parser-pdf-module/pom.xml | 2 +- tika-parsers/tika-parser-pkg-module/pom.xml | 2 +- tika-parsers/tika-parser-text-module/pom.xml | 2 +- tika-parsers/tika-parser-xml-module/pom.xml | 2 +- tika-parsers/tika-parser-xmp-commons/pom.xml | 2 +- tika-parsers/tika-parser-zip-commons/pom.xml | 2 +- tika-server/pom.xml | 2 +- .../tika/server/resource/LanguageResource.java | 3 +- .../tika/server/resource/TranslateResource.java | 2 +- tika-translate/pom.xml | 26 ++- .../language/translate/AbstractTranslator.java | 2 +- 69 files changed, 295 insertions(+), 281 deletions(-) copy {tika-parsers/tika-parser-font-module => tika-langdetect/tika-langdetect-commons}/pom.xml (78%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/java/org/apache/tika/langdetect/LanguageDetectorTest.java (95%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/log4j.properties (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/da.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/de.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/el.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/en.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/es.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/et.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/fi.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/fr.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/it.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/ja.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/lt.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/nl.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/pt.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/sv.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/th.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/language-tests/zh.test (100%) rename tika-langdetect/{ => tika-langdetect-commons}/src/test/resources/org/apache/tika/langdetect/text-test.tsv (100%) create mode 100644 tika-langdetect/tika-langdetect-lingo24/pom.xml rename tika-langdetect/{src/main/java/org/apache/tika/langdetect => tika-langdetect-lingo24/src/main/java/org/apache/tika/langdetect/lingo24}/Lingo24LangDetector.java (99%) copy tika-langdetect/{ => tika-langdetect-lingo24}/src/main/resources/META-INF/services/org.apache.tika.language.detect.LanguageDetector (93%) rename tika-langdetect/{src/main/resources/org/apache/tika/langdetect => tika-langdetect-lingo24/src/main/resources/org/apache/tika/langdetect/lingo24}/langdetect.lingo24.properties (100%) rename tika-langdetect/{src/test/java/org/apache/tika/langdetect => tika-langdetect-lingo24/src/test/java/org/apache/tika/langdetect/lingo24}/Lingo24LangDetectorTest.java (83%) create mode 100644 tika-langdetect/tika-langdetect-mitll-text/pom.xml rename tika-langdetect/{src/main/java/org/apache/tika/langdetect => tika-langdetect-mitll-text/src/main/java/org/apache/tika/langdetect/mitll}/TextLangDetector.java (99%) copy tika-langdetect/{ => tika-langdetect-mitll-text}/src/main/resources/META-INF/services/org.apache.tika.language.detect.LanguageDetector (94%) rename tika-langdetect/{src/test/java/org/apache/tika/langdetect => tika-langdetect-mitll-text/src/test/java/org/apache/tika/langdetect/mitll}/TextLangDetectorTest.java (90%) copy {tika-parsers/tika-parser-integration-tests => tika-langdetect/tika-langdetect-mitll-text}/src/test/resources/log4j.properties (100%) copy {tika-parsers-extended/tika-parsers-extended-integration-tests => tika-langdetect/tika-langdetect-optimaize}/pom.xml (52%) rename tika-langdetect/{src/main/java/org/apache/tika/langdetect => tika-langdetect-optimaize/src/main/java/org/apache/tika/langdetect/optimaize}/OptimaizeLangDetector.java (99%) rename tika-langdetect/{ => tika-langdetect-optimaize}/src/main/resources/META-INF/services/org.apache.tika.language.detect.LanguageDetector (93%) rename tika-langdetect/{src/test/java/org/apache/tika/langdetect => tika-langdetect-optimaize/src/test/java/org/apache/tika/langdetect/optimaize}/OptimaizeLangDetectorTest.java (98%) rename tika-langdetect/{src/test/resources/org/apache/tika/langdetect => tika-langdetect-optimaize/src/test/resources/org/apache/tika/langdetect/optimaize}/language-codes.txt (100%) rename tika-langdetect/{src/test/resources/org/apache/tika/langdetect => tika-langdetect-optimaize/src/test/resources/org/apache/tika/langdetect/optimaize}/udhr-known.txt (100%) rename tika-langdetect/{src/test/resources/org/apache/tika/langdetect => tika-langdetect-optimaize/src/test/resources/org/apache/tika/langdetect/optimaize}/udhr-unknown.txt (100%)