MNT-15219 - Excel (.xlsx) containing xmls (shapes/drawings) with mult…

…i byte characters may cause OutOfMemory in Tika - Make processing of shapes in XMLS files configurable
Alfresco · Aug 2, 2016 · 32aca3f · 32aca3f · Gagravarr · Apr 27, 2017
1 parent 6a9f5a5
commit 32aca3f
Show file tree

Hide file tree

Showing 4 changed files with 32 additions and 3 deletions.
diff --git a/tika-core/src/main/java/org/apache/tika/metadata/TikaMetadataKeys.java b/tika-core/src/main/java/org/apache/tika/metadata/TikaMetadataKeys.java
@@ -26,4 +26,7 @@ public interface TikaMetadataKeys {
     String PROTECTED = "protected";
 
     String EMBEDDED_RELATIONSHIP_ID = "embeddedRelationshipId";
+
+    String TIKA_PARSER_PARSE_SHAPES_KEY = "TIKA_PARSER_PARSE_SHAPES";
+
 }
diff --git a/...-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java b/...-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
@@ -39,16 +39,15 @@
 import org.apache.tika.exception.TikaException;
 import org.apache.tika.extractor.EmbeddedDocumentExtractor;
 import org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor;
-import org.apache.tika.io.FilenameUtils;
 import org.apache.tika.io.TikaInputStream;
 import org.apache.tika.metadata.Metadata;
 import org.apache.tika.metadata.TikaCoreProperties;
+import org.apache.tika.metadata.TikaMetadataKeys;
 import org.apache.tika.parser.ParseContext;
 import org.apache.tika.parser.microsoft.OfficeParser.POIFSDocumentType;
 import org.apache.tika.sax.EmbeddedContentHandler;
 import org.apache.tika.sax.XHTMLContentHandler;
 import org.apache.xmlbeans.XmlException;
-import org.xml.sax.Attributes;
 import org.xml.sax.ContentHandler;
 import org.xml.sax.SAXException;
 import org.xml.sax.helpers.AttributesImpl;
@@ -314,4 +313,19 @@ protected abstract void buildXHTML(XHTMLContentHandler xhtml)
      */
     protected abstract List<PackagePart> getMainDocumentParts()
             throws TikaException;
+
+    private static final boolean SHOULD_PROCESS_SHAPES_DEFAULT_VALUE = false;
+
+    public boolean shouldProcessShapes(Metadata metadata)
+    {
+        if (metadata != null)
+        {
+            String shouldProcessShapesValue = metadata.get(TikaMetadataKeys.TIKA_PARSER_PARSE_SHAPES_KEY);
+            if (shouldProcessShapesValue != null && !shouldProcessShapesValue.isEmpty())
+            {
+                return Boolean.valueOf(shouldProcessShapesValue);
+            }
+        }
+        return SHOULD_PROCESS_SHAPES_DEFAULT_VALUE;
+    }
 }
diff --git a/...rs/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java b/...rs/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java
@@ -21,6 +21,8 @@
 
 import org.apache.poi.POIXMLTextExtractor;
 import org.apache.poi.openxml4j.opc.PackagePart;
+import org.apache.poi.xssf.extractor.XSSFEventBasedExcelExtractor;
+import org.apache.poi.xssf.extractor.XSSFExcelExtractor;
 import org.apache.tika.parser.ParseContext;
 import org.apache.tika.sax.XHTMLContentHandler;
 import org.xml.sax.SAXException;
@@ -34,6 +36,14 @@ public POIXMLTextExtractorDecorator(ParseContext context, POIXMLTextExtractor ex
     @Override
     protected void buildXHTML(XHTMLContentHandler xhtml) throws SAXException {
         // extract document content as a single string (not structured)
+        if(extractor instanceof XSSFEventBasedExcelExtractor) 
+        {
+            ((XSSFEventBasedExcelExtractor)extractor).setIncludeTextBoxes(false);
+        }
+        else if(extractor instanceof XSSFExcelExtractor)
+        {
+            ((XSSFExcelExtractor)extractor).setIncludeTextBoxes(false);
+        }
         xhtml.element("p", extractor.getText());
     }
 

diff --git a/...ers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java b/...ers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
@@ -145,7 +145,9 @@ protected void buildXHTML(XHTMLContentHandler xhtml) throws SAXException,
            for(String footer : sheetExtractor.footers) {
               extractHeaderFooter(footer, xhtml);
            }
-           processShapes(iter.getShapes(), xhtml);
+           if (shouldProcessShapes(metadata)){
+              processShapes(iter.getShapes(), xhtml);
+           }
            // All done with this sheet
            xhtml.endElement("div");
        }