Repository: tika Updated Branches: refs/heads/master c5d4ec6c5 -> 1caa4fb6a
TIKA-1853: upgrade to POI 3.14-final Project: http://git-wip-us.apache.org/repos/asf/tika/repo Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/1caa4fb6 Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/1caa4fb6 Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/1caa4fb6 Branch: refs/heads/master Commit: 1caa4fb6ac971dbcdcbb22b9c2f77d7051e922b9 Parents: c5d4ec6 Author: tballison <[email protected]> Authored: Mon Mar 7 20:21:56 2016 -0500 Committer: tballison <[email protected]> Committed: Mon Mar 7 20:21:56 2016 -0500 ---------------------------------------------------------------------- CHANGES.txt | 4 ++-- tika-parsers/pom.xml | 4 ++-- .../parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java | 4 ++-- .../tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java | 1 + 4 files changed, 7 insertions(+), 6 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/tika/blob/1caa4fb6/CHANGES.txt ---------------------------------------------------------------------- diff --git a/CHANGES.txt b/CHANGES.txt index 91bc623..ed825cb 100644 --- a/CHANGES.txt +++ b/CHANGES.txt @@ -12,9 +12,9 @@ Release 1.13 - ??? * Upgrade to sqlite-jdbc 3.8.11.2 (TIKA-1861). NOTE: this dependency is still <scope>provided</scope>. You need to include this dependency - in order to parser sqlite files. + in order to parse sqlite files. - * Upgrade to POI 3.14-beta1 (TIKA-1799). + * Upgrade to POI 3.14-final (TIKA-1853). * Upgrade to PDFBox 1.8.11 (TIKA-1830). http://git-wip-us.apache.org/repos/asf/tika/blob/1caa4fb6/tika-parsers/pom.xml ---------------------------------------------------------------------- diff --git a/tika-parsers/pom.xml b/tika-parsers/pom.xml index 0842c1f..8c67c68 100644 --- a/tika-parsers/pom.xml +++ b/tika-parsers/pom.xml @@ -35,9 +35,9 @@ <url>http://tika.apache.org/</url> <properties> - <poi.version>3.14-beta1</poi.version> + <poi.version>3.14</poi.version> <!-- NOTE: sync codec version with POI --> - <codec.version>1.9</codec.version> + <codec.version>1.10</codec.version> <!-- NOTE: sync tukaani version with commons-compress --> <tukaani.version>1.5</tukaani.version> <mime4j.version>0.7.2</mime4j.version> http://git-wip-us.apache.org/repos/asf/tika/blob/1caa4fb6/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java ---------------------------------------------------------------------- diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java index e62d50b..e58c040 100644 --- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java +++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java @@ -27,7 +27,7 @@ import org.apache.poi.openxml4j.opc.PackagePartName; import org.apache.poi.openxml4j.opc.PackageRelationship; import org.apache.poi.openxml4j.opc.PackagingURIHelper; import org.apache.poi.openxml4j.opc.TargetMode; -import org.apache.poi.sl.usermodel.SimpleShape; +import org.apache.poi.sl.usermodel.Placeholder; import org.apache.poi.xslf.extractor.XSLFPowerPointExtractor; import org.apache.poi.xslf.usermodel.XMLSlideShow; import org.apache.poi.xslf.usermodel.XSLFCommentAuthors; @@ -151,7 +151,7 @@ public class XSLFPowerPointExtractorDecorator extends AbstractOOXMLExtractor { for (XSLFShape sh : shapes) { if (sh instanceof XSLFTextShape) { XSLFTextShape txt = (XSLFTextShape) sh; - SimpleShape.Placeholder ph = txt.getTextType(); + Placeholder ph = txt.getTextType(); if (skipPlaceholders && ph != null) { continue; } http://git-wip-us.apache.org/repos/asf/tika/blob/1caa4fb6/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java ---------------------------------------------------------------------- diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java index 433b9a4..5006d0b 100644 --- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java +++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java @@ -187,6 +187,7 @@ public class XSSFExcelExtractorDecorator extends AbstractOOXMLExtractor { throws IOException, SAXException { InputSource sheetSource = new InputSource(sheetInputStream); SAXParserFactory saxFactory = SAXParserFactory.newInstance(); + saxFactory.setNamespaceAware(true); try { SAXParser saxParser = saxFactory.newSAXParser(); XMLReader sheetParser = saxParser.getXMLReader();
