[
https://issues.apache.org/jira/browse/TIKA-3266?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17262945#comment-17262945
]
Hudson commented on TIKA-3266:
------------------------------
SUCCESS: Integrated in Jenkins build Tika ยป tika-main-jdk8 #118 (See
[https://ci-builds.apache.org/job/Tika/job/tika-main-jdk8/118/])
TIKA-3266 (#396) (github:
[https://github.com/apache/tika/commit/b0fb00ef6a11db121c56436b9542a4cf248fef8b])
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/BPGParser.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/ImageParser.java
* (edit)
tika-core/src/main/java/org/apache/tika/extractor/ParsingEmbeddedDocumentExtractor.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/JpegParser.java
* (edit) tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/pom.xml
* (edit)
tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/TikaResource.java
* (edit)
tika-core/src/main/java/org/apache/tika/extractor/ParserContainerExtractor.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/resources/org/apache/tika/parser/pdf/tika-inline-config.xml
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/pom.xml
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
* (add)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/AbstractImageParser.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/TiffParser.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/resources/org/apache/tika/parser/pdf/PDFParser.properties
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/test/java/org/apache/tika/parser/image/ImageParserTest.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
* (add) tika-core/src/main/java/org/apache/tika/parser/StatefulParser.java
* (edit)
tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentUtil.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/HeifParser.java
* (edit)
tika-core/src/main/java/org/apache/tika/parser/RecursiveParserWrapper.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/pom.xml
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
* (edit)
tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRParser.java
> Generalize OCRParser so that users can service load custom ocr parsers
> ----------------------------------------------------------------------
>
> Key: TIKA-3266
> URL: https://issues.apache.org/jira/browse/TIKA-3266
> Project: Tika
> Issue Type: Improvement
> Reporter: Tim Allison
> Priority: Major
> Fix For: 2.0.0
>
>
> For Tika 2.0.0, it would be great if we could allow users to add custom OCR
> parsers. We've hardcoded Tesseract a bit much...
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
