[
https://issues.apache.org/jira/browse/TIKA-4744?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18084459#comment-18084459
]
Hudson commented on TIKA-4744:
------------------------------
SUCCESS: Integrated in Jenkins build Tika ยป tika-main-jdk17 #1394 (See
[https://ci-builds.apache.org/job/Tika/job/tika-main-jdk17/1394/])
TIKA-4744 (#2850) (github:
[https://github.com/apache/tika/commit/81d75a85d78d33aaa641e5ea69d34b65bd16800c])
* (add)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testWORD_emptyParaInTextbox.docx
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/rtf/TextExtractor.java
* (add)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testWORDML_tableInsideParagraph.doc
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/xml/XML2003ParserTest.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/rtf/RTFParser.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/FormattingTagManager.java
* (add)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testRTF_parInsideHyperlink.rtf
* (add)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/test/java/org/apache/tika/parser/iwork/KeynoteContentHandlerTest.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLTikaBodyPartHandler.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentBodyHandler.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/iwork/KeynoteContentHandler.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-miscoffice-module/src/test/resources/test-documents/testODT_svgTitleInStyledSpan.odt
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/rtf/RTFParserTest.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java
* (add)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testRTF_nestedHyperlinkPageRef.rtf
* (add)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testWORD_formattingFlipUnderlineOrder.docx
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/rtf/RTFEmbObjHandler.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/xml/WordMLParser.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
* (add)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/resources/test-documents/testFODS_embeddedChart.fods
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/FlatOpenDocumentParser.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/XFAExtractor.java
* (add)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_malformedXFA.pdf
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/xml/AbstractXML2003Parser.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/epub/EpubParser.java
* (add)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testWORD_tableInRunInsideParagraph.docx
> Further xhtml fixes in 4.x
> --------------------------
>
> Key: TIKA-4744
> URL: https://issues.apache.org/jira/browse/TIKA-4744
> Project: Tika
> Issue Type: Task
> Reporter: Tim Allison
> Priority: Minor
>
> In prep for 4.0.0-beta-1, I ran the full corpus with the strict xhtml
> validator on. This surfaced a few further areas for improvement.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)