[ 
https://issues.apache.org/jira/browse/TIKA-4707?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18072317#comment-18072317
 ] 

Hudson commented on TIKA-4707:
------------------------------

SUCCESS: Integrated in Jenkins build Tika ยป tika-main-jdk17 #1299 (See 
[https://ci-builds.apache.org/job/Tika/job/tika-main-jdk17/1299/])
TIKA-4707 -- rm dom parsers for docx/pptx (#2747) (github: 
[https://github.com/apache/tika/commit/8501894c11bf9ddc748e351de3c3aa6e7751295d])
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java
* (add) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testVISIO_60489.vsdx
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLPptxSAXTest.java
* (add) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/VSDXParserTest.java
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
* (add) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/TikaXSSFBCommentsTable.java
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLDocxTest.java
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLPptxDOMPackageTest.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/configs/tika-config-sax-macros.json
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/pom.xml
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSExtractorDecorator.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLDocxSAXPackageTest.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParserConfig.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xwpf/XWPFEventBasedWordExtractor.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXWPFWordExtractorDecorator.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xslf/XSLFEventBasedPowerPointExtractor.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractor.java
* (add) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testVISIO_text.vsdx
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLPptxPackageTest.java
* (add) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/VSDXExtractorDecorator.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLDocxSAXTest.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFBExcelExtractorDecorator.java
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLDocxDOMPackageTest.java
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLPptxSAXPackageTest.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SAXBasedMetadataExtractor.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/configs/tika-config-sax-docx.json
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSTextExtractor.java
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLPptxTest.java
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLPptxDOMTest.java
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLDocxPackageTest.java
* (delete) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLDocxDOMTest.java
* (add) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/TikaXSSFBSharedStringsTable.java
* (edit) 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXSLFPowerPointExtractorDecorator.java


> Remove dom pptx/docx parsers in 4.x
> -----------------------------------
>
>                 Key: TIKA-4707
>                 URL: https://issues.apache.org/jira/browse/TIKA-4707
>             Project: Tika
>          Issue Type: Task
>            Reporter: Tim Allison
>            Priority: Major
>
> Based on the findings on TIKA-4692, we should simplify our codebase by 
> removing the DOM options for pptx and docx in our 4.x branch.



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

Reply via email to