Merge branch '2.x' of https://git-wip-us.apache.org/repos/asf/tika into 2.x
Project: http://git-wip-us.apache.org/repos/asf/tika/repo Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/58adf80d Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/58adf80d Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/58adf80d Branch: refs/heads/2.x Commit: 58adf80ddbb74ec577763944114e2722c38eff01 Parents: 02cae8a 251f680 Author: Ken Krugler <[email protected]> Authored: Thu Mar 10 11:36:21 2016 -0800 Committer: Ken Krugler <[email protected]> Committed: Thu Mar 10 11:36:21 2016 -0800 ---------------------------------------------------------------------- .gitignore | 3 +- CHANGES.txt | 11 +- pom.xml | 1 + .../main/java/org/apache/tika/cli/TikaCLI.java | 35 +- .../java/org/apache/tika/cli/TikaCLITest.java | 50 ++- .../test/resources/test-data/tika-config2.xml | 14 + tika-bundle/pom.xml | 3 - .../tika/config/TikaConfigSerializer.java | 256 +++++++++++++++ .../java/org/apache/tika/metadata/XMPMM.java | 44 +++ .../tika/osgi/TikaAbstractBundleActivator.java | 12 +- .../tika/config/TikaConfigSerializerTest.java | 62 ++++ .../tika/example/DumpTikaConfigExample.java | 233 +------------- .../tika/example/DumpTikaConfigExampleTest.java | 6 +- tika-parser-bundles/pom.xml | 66 +++- .../tika-multimedia-bundle/pom.xml | 102 ------ .../module/multimedia/internal/Activator.java | 49 --- .../java/org/apache/tika/module/BundleIT.java | 203 ------------ .../src/test/resources/hadoop.jpg | Bin 8362 -> 0 bytes .../src/test/resources/testFLV.flv | Bin 90580 -> 0 bytes .../src/test/resources/testMID.mid | Bin 322 -> 0 bytes .../src/test/resources/testMP3i18n.mp3 | Bin 40832 -> 0 bytes .../src/test/resources/tika.png | Bin 22216 -> 0 bytes .../module/BundleIT.java | 89 ++++++ .../tika-parser-advanced-bundle/pom.xml | 83 +++++ .../apache/tika/module/advanced/BundleIT.java | 98 ++++++ .../test-bundles.xml | 34 ++ .../tika-parser-cad-bundle/pom.xml | 73 +++++ .../org/apache/tika/module/cad/BundleIT.java | 96 ++++++ .../tika-parser-cad-bundle/test-bundles.xml | 34 ++ .../tika-parser-code-bundle/.gitignore | 1 + .../tika-parser-code-bundle/pom.xml | 76 +++++ .../org/apache/tika/module/code/BundleIT.java | 96 ++++++ .../tika-parser-code-bundle/test-bundles.xml | 34 ++ .../tika-parser-crypto-bundle/.gitignore | 1 + .../tika-parser-crypto-bundle/pom.xml | 79 +++++ .../org/apache/tika/module/crypto/BundleIT.java | 96 ++++++ .../tika-parser-crypto-bundle/test-bundles.xml | 34 ++ .../tika-parser-database-bundle/.gitignore | 1 + .../tika-parser-database-bundle/pom.xml | 68 ++++ .../apache/tika/module/database/BundleIT.java | 96 ++++++ .../test-bundles.xml | 34 ++ .../tika-parser-ebook-bundle/pom.xml | 72 +++++ .../org/apache/tika/module/ebook/BundleIT.java | 97 ++++++ .../tika-parser-ebook-bundle/test-bundles.xml | 35 ++ .../tika-parser-journal-bundle/pom.xml | 80 +++++ .../apache/tika/module/journal/BundleIT.java | 97 ++++++ .../tika-parser-journal-bundle/test-bundles.xml | 35 ++ .../tika-parser-multimedia-bundle/pom.xml | 86 +++++ .../apache/tika/module/multimedia/BundleIT.java | 212 ++++++++++++ .../src/test/resources/hadoop.jpg | Bin 0 -> 8362 bytes .../src/test/resources/testFLV.flv | Bin 0 -> 90580 bytes .../src/test/resources/testMID.mid | Bin 0 -> 322 bytes .../src/test/resources/testMP3i18n.mp3 | Bin 0 -> 40832 bytes .../src/test/resources/tika.png | Bin 0 -> 22216 bytes .../test-bundles.xml | 34 ++ .../tika-parser-office-bundle/pom.xml | 138 ++++++++ .../org/apache/tika/module/office/BundleIT.java | 87 +++++ .../tika-parser-office-bundle/test-bundles.xml | 37 +++ .../tika-parser-package-bundle/pom.xml | 134 ++++++++ .../org/apache/tika/module/pkg/BundleIT.java | 96 ++++++ .../tika-parser-package-bundle/test-bundles.xml | 34 ++ .../tika-parser-pdf-bundle/pom.xml | 88 +++++ .../org/apache/tika/module/pdf/BundleIT.java | 96 ++++++ .../tika-parser-pdf-bundle/test-bundles.xml | 34 ++ .../tika-parser-scientific-bundle/pom.xml | 202 ++++++++++++ .../apache/tika/module/scientific/BundleIT.java | 96 ++++++ .../test-bundles.xml | 34 ++ .../tika-parser-text-bundle/pom.xml | 79 +++++ .../org/apache/tika/module/text/BundleIT.java | 96 ++++++ .../tika-parser-text-bundle/test-bundles.xml | 34 ++ .../tika-parser-web-bundle/pom.xml | 93 ++++++ .../org/apache/tika/module/web/BundleIT.java | 96 ++++++ .../tika-parser-web-bundle/test-bundles.xml | 34 ++ tika-parser-modules/pom.xml | 124 ++++++- .../module/advanced/internal/Activator.java | 36 +++ .../tika/module/cad/internal/Activator.java | 36 +++ .../java/org/apache/tika/module/BundleIT.java | 88 +++++ .../tika/module/code/internal/Activator.java | 36 +++ .../tika/module/crypto/internal/Activator.java | 36 +++ .../module/database/internal/Activator.java | 36 +++ .../tika/module/ebook/internal/Activator.java | 36 +++ .../tika/module/journal/internal/Activator.java | 36 +++ .../tika-parser-multimedia-module/pom.xml | 10 +- .../module/multimedia/internal/Activator.java | 36 +++ .../apache/tika/parser/image/TiffParser.java | 2 +- .../tika/parser/image/xmp/JempboxExtractor.java | 97 ------ .../tika/parser/image/xmp/XMPPacketScanner.java | 113 ------- .../org/apache/tika/parser/jpeg/JpegParser.java | 2 +- .../parser/image/xmp/JempboxExtractorTest.java | 107 ------- .../apache/tika/parser/jpeg/JpegParserTest.java | 16 + .../tika/module/office/internal/Activator.java | 36 +++ .../ooxml/XSLFPowerPointExtractorDecorator.java | 4 +- .../ooxml/XSSFExcelExtractorDecorator.java | 1 + .../services/org.apache.tika.parser.Parser | 2 + .../tika-parser-package-module/pom.xml | 6 +- .../tika/module/pkg/internal/Activator.java | 36 +++ .../tika-parser-pdf-module/pom.xml | 5 + .../tika/module/pdf/internal/Activator.java | 36 +++ .../org/apache/tika/parser/pdf/PDF2XHTML.java | 20 ++ .../org/apache/tika/parser/pdf/PDFParser.java | 50 ++- .../apache/tika/parser/pdf/PDFParserConfig.java | 36 ++- .../apache/tika/parser/pdf/XFAExtractor.java | 319 +++++++++++++++++++ .../apache/tika/parser/pdf/PDFParser.properties | 3 +- .../apache/tika/parser/pdf/PDFParserTest.java | 87 +++++ .../module/scientific/internal/Activator.java | 36 +++ .../tika/module/text/internal/Activator.java | 20 ++ .../tika/module/web/internal/Activator.java | 36 +++ .../services/org.apache.tika.parser.Parser | 2 - .../tika-parser-xmp-module/pom.xml | 52 +++ .../tika/module/xmp/internal/Activator.java | 36 +++ .../tika/parser/xmp/JempboxExtractor.java | 187 +++++++++++ .../tika/parser/xmp/XMPPacketScanner.java | 113 +++++++ .../tika/parser/xmp/JempboxExtractorTest.java | 107 +++++++ tika-test-resources/pom.xml | 22 +- .../tika/parser/ner/opennlp/ModelGetter.groovy | 35 +- .../testPDF_XFA_govdocs1_258578.pdf | Bin 0 -> 168176 bytes 116 files changed, 5700 insertions(+), 963 deletions(-) ----------------------------------------------------------------------
