Merge branch 'TIKA-2021' of https://github.com/Zarana-Parekh/tika
Project: http://git-wip-us.apache.org/repos/asf/tika/repo Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/1c6cff83 Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/1c6cff83 Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/1c6cff83 Branch: refs/heads/master Commit: 1c6cff83626f994e32beae8dce6f17ddf29cc45c Parents: 95b2cd1 4fd3e68 Author: Chris Mattmann <[email protected]> Authored: Wed Jul 6 22:42:57 2016 -0700 Committer: Chris Mattmann <[email protected]> Committed: Wed Jul 6 22:42:57 2016 -0700 ---------------------------------------------------------------------- tika-bundle/pom.xml | 2 +- tika-parsers/pom.xml | 17 +- .../tika/parser/ocr/TesseractOCRConfig.java | 181 ++++++++++++++++++- .../tika/parser/ocr/TesseractOCRParser.java | 113 +++++++++++- .../parser/ocr/TesseractOCRConfig.properties | 13 +- .../org/apache/tika/parser/ocr/rotation.py | 72 ++++++++ .../tika/parser/ocr/TesseractOCRConfigTest.java | 61 ++++++- .../tika/parser/ocr/TesseractOCRParserTest.java | 18 +- .../TesseractOCRConfig-full.properties | 6 + .../TesseractOCRConfig-partial.properties | 8 +- 10 files changed, 480 insertions(+), 11 deletions(-) ----------------------------------------------------------------------
