codex-admin/autopsy
1
0
Fork 0
mirror of https://github.com/elisspace/autopsy.git synced 2026-09-29 05:49:50 +00:00
Code Issues Releases Wiki Activity

Merge remote-tracking branch 'upstream/custom-release-2.11.0' into develop

Browse Source
This commit is contained in:
Richard Cordovano
2018-01-18 10:56:06 -05:00
parent 180a376c4f 800d98497b
commit a49043d0ab
3 changed files with 74 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Core/src/org/sleuthkit/autopsy/modules/embeddedfileextractor/MSOfficeEmbeddedContentExtractor.java
+8 -5
View File
@@ -51,6 +51,7 @@ import org.apache.tika.mime.MimeTypeException;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.microsoft.OfficeParserConfig;
import org.apache.tika.sax.BodyContentHandler;
import org.openide.util.NbBundle;
import org.sleuthkit.autopsy.casemodule.Case;
@@ -231,11 +232,13 @@ class MSOfficeEmbeddedContentExtractor {
// write limit (which defaults to 100,000 characters.
ContentHandler contentHandler = new BodyContentHandler(-1);
// TODO: this will be needed once we upgrade to Tika 1.16 or later.
// OfficeParserConfig officeParserConfig = new OfficeParserConfig();
// officeParserConfig.setUseSAXPptxExtractor(true);
// officeParserConfig.setUseSAXDocxExtractor(true);
// parseContext.set(OfficeParserConfig.class, officeParserConfig);
// Use the more memory efficient Tika SAX parsers for DOCX and
// PPTX files (it already uses SAX for XLSX).
OfficeParserConfig officeParserConfig = new OfficeParserConfig();
officeParserConfig.setUseSAXPptxExtractor(true);
officeParserConfig.setUseSAXDocxExtractor(true);
parseContext.set(OfficeParserConfig.class, officeParserConfig);
EmbeddedDocumentExtractor extractor = new EmbeddedContentExtractor(parseContext);
parseContext.set(EmbeddedDocumentExtractor.class, extractor);
ReadContentInputStream stream = new ReadContentInputStream(abstractFile);