This is an automated email from the ASF dual-hosted git repository. totaro pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/tika.git
commit 7dd38d5500c539328e2b0a083e1998a28e680539 Merge: 31625a2 d1a8bff Author: Giuseppe Totaro <[email protected]> AuthorDate: Wed Sep 13 17:33:22 2017 -0700 Merge branch 'master' of https://github.com/apache/tika CHANGES.txt | 18 +++++- .../org/apache/tika/batch/fs/BatchProcessTest.java | 7 +-- .../org/apache/tika/detect/CompositeDetector.java | 7 +++ .../org/apache/tika/detect/OverrideDetector.java | 41 +++++++++++++ .../tika/exception/ZeroByteFileException.java | 11 ++++ .../main/java/org/apache/tika/metadata/TIFF.java | 3 + .../apache/tika/metadata/TikaCoreProperties.java | 3 + .../org/apache/tika/mime/MimeTypesFactory.java | 19 ++++++ .../org/apache/tika/parser/AutoDetectParser.java | 10 +++- .../org/apache/tika/mime/MimeTypesReaderTest.java | 16 ++++++ .../org/apache/tika/mime/external-mimetypes.xml | 22 +++++++ .../apache/tika/eval/reports/ResultsReporter.java | 10 +++- .../tika/parser/image/ImageMetadataExtractor.java | 24 ++++++++ .../org/apache/tika/parser/mbox/MboxParser.java | 1 + .../apache/tika/parser/mbox/OutlookPSTParser.java | 14 +++++ .../tika/parser/microsoft/WordExtractor.java | 5 ++ .../ooxml/OOXMLWordAndPowerPointTextHandler.java | 51 ++++++++++++---- .../ooxml/SXWPFWordExtractorDecorator.java | 2 +- .../recognition/tf/TensorflowRESTRecogniser.java | 12 +++- .../services/org.apache.tika.detect.Detector | 1 + .../parser/recognition/tf/InceptionRestDockerfile | 4 +- .../tika/parser/recognition/tf/inceptionapi.py | 29 ++++++++-- .../apache/tika/parser/AutoDetectParserTest.java | 64 +++++++++++++++------ .../apache/tika/parser/image/TiffParserTest.java | 13 ++++- .../apache/tika/parser/mbox/MboxParserTest.java | 15 +++++ .../tika/parser/mbox/OutlookPSTParserTest.java | 15 +++++ .../tika/parser/microsoft/WordParserTest.java | 16 ++++++ .../parser/microsoft/ooxml/OOXMLParserTest.java | 17 ++++++ .../parser/microsoft/ooxml/SXWPFExtractorTest.java | 16 ++++++ .../tika/parser/ocr/TesseractOCRParserTest.java | 9 +++ .../recognition/ObjectRecognitionParserTest.java | 35 +++++++++++ .../parser/recognition/tika-config-tflow-rest.xml | 2 + .../test/resources/test-documents/single_mail.mbox | 25 ++++++++ .../test-documents/testPST_variousBodyTypes.pst | Bin 0 -> 271360 bytes .../test-documents/testTIFF_multipage.tif | Bin 0 -> 156867 bytes .../resources/test-documents/testWORD_phonetic.doc | Bin 0 -> 27136 bytes .../test-documents/testWORD_phonetic.docx | Bin 0 -> 12523 bytes .../testWORD_specialControlCharacter1415.doc | Bin 0 -> 25600 bytes 38 files changed, 492 insertions(+), 45 deletions(-) -- To stop receiving notification emails like this one, please contact "[email protected]" <[email protected]>.
