You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2026/02/03 13:10:32 UTC
(tika) branch branch_3x updated (7d48f34719 -> 65bf98d3c5)
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a change to branch branch_3x
in repository https://gitbox.apache.org/repos/asf/tika.git
from 7d48f34719 TIKA-4488: update logback
new 82f26b63dc TIKA-4646 -- extract hyperlinks from instrText and other areas in ooxml(#2578)
new 65bf98d3c5 TIKA-4646 -- extract hyperlinks from instrText and other areas in ooxml(#2578) fix merge conflicts
The 2 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
Summary of changes:
.../main/java/org/apache/tika/metadata/Office.java | 51 +++
.../org/apache/tika/parser/AutoDetectParser.java | 8 +-
.../microsoft/ooxml/AbstractOOXMLExtractor.java | 26 ++
.../microsoft/ooxml/FieldHyperlinkTracker.java | 168 +++++++++
.../microsoft/ooxml/OOXMLTikaBodyPartHandler.java | 25 ++
.../ooxml/OOXMLWordAndPowerPointTextHandler.java | 187 +++++++++-
.../ooxml/SXWPFWordExtractorDecorator.java | 179 +++++++++-
.../ooxml/XSSFExcelExtractorDecorator.java | 390 +++++++++++++++++++++
.../ooxml/XWPFWordExtractorDecorator.java | 95 ++++-
.../xslf/XSLFEventBasedPowerPointExtractor.java | 5 +
.../ooxml/xwpf/XWPFEventBasedWordExtractor.java | 5 +
.../tika/parser/microsoft/ExcelParserTest.java | 43 +++
.../parser/microsoft/ooxml/OOXMLParserTest.java | 39 +++
.../parser/microsoft/ooxml/SXWPFExtractorTest.java | 109 ++++++
.../parser/microsoft/pst/OutlookPSTParserTest.java | 3 +
.../test-documents/testAttachedTemplate.docx | Bin 0 -> 2284 bytes
.../test-documents/testDataConnections.xlsx | Bin 0 -> 2967 bytes
.../test/resources/test-documents/testDdeLink.xlsx | Bin 0 -> 3030 bytes
.../resources/test-documents/testExternalRefs.docx | Bin 0 -> 2125 bytes
.../resources/test-documents/testFrameset.docx | Bin 0 -> 2328 bytes
.../resources/test-documents/testHoverAndVml.docx | Bin 0 -> 2270 bytes
.../resources/test-documents/testInstrLink.docx | Bin 0 -> 14464 bytes
.../resources/test-documents/testMailMerge.docx | Bin 0 -> 2306 bytes
.../resources/test-documents/testSubdocument.docx | Bin 0 -> 1980 bytes
24 files changed, 1323 insertions(+), 10 deletions(-)
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/FieldHyperlinkTracker.java
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testAttachedTemplate.docx
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testDataConnections.xlsx
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testDdeLink.xlsx
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testExternalRefs.docx
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testFrameset.docx
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testHoverAndVml.docx
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testInstrLink.docx
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testMailMerge.docx
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testSubdocument.docx
(tika) 02/02: TIKA-4646 -- extract hyperlinks from instrText and other areas in ooxml(#2578) fix merge conflicts
Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch branch_3x
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 65bf98d3c54e1500878398210ef64aafe2dcb589
Author: tallison <ta...@apache.org>
AuthorDate: Tue Feb 3 08:10:23 2026 -0500
TIKA-4646 -- extract hyperlinks from instrText and other areas in ooxml(#2578) fix merge conflicts
(cherry picked from commit bef2d336b1e4e52e3ca262d656f93ee4d3145b5f)
---
.../src/main/java/org/apache/tika/parser/AutoDetectParser.java | 8 +-------
1 file changed, 1 insertion(+), 7 deletions(-)
diff --git a/tika-core/src/main/java/org/apache/tika/parser/AutoDetectParser.java b/tika-core/src/main/java/org/apache/tika/parser/AutoDetectParser.java
index 59882f8961..b4790e6980 100644
--- a/tika-core/src/main/java/org/apache/tika/parser/AutoDetectParser.java
+++ b/tika-core/src/main/java/org/apache/tika/parser/AutoDetectParser.java
@@ -34,7 +34,6 @@ import org.apache.tika.io.TemporaryResources;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.HttpHeaders;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MediaType;
import org.apache.tika.mime.MediaTypeRegistry;
import org.apache.tika.sax.SecureContentHandler;
@@ -177,12 +176,7 @@ public class AutoDetectParser extends CompositeParser {
// Automatically detect the MIME type of the document
MediaType type = detector.detect(tis, metadata);
- //update CONTENT_TYPE as long as it wasn't set by parser override
- if (metadata.get(TikaCoreProperties.CONTENT_TYPE_PARSER_OVERRIDE) == null ||
- !metadata.get(TikaCoreProperties.CONTENT_TYPE_PARSER_OVERRIDE)
- .equals(type.toString())) {
- metadata.set(Metadata.CONTENT_TYPE, type.toString());
- }
+ metadata.set(Metadata.CONTENT_TYPE, type.toString());
//check for zero-byte inputstream
if (tis.getOpenContainer() == null) {
if (autoDetectParserConfig.getThrowOnZeroBytes()) {
(tika) 01/02: TIKA-4646 -- extract hyperlinks from instrText and other areas in ooxml(#2578)
Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch branch_3x
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 82f26b63dc7aa6ccc23a25e57377ab9d851db448
Author: Tim Allison <ta...@apache.org>
AuthorDate: Tue Feb 3 06:32:51 2026 -0500
TIKA-4646 -- extract hyperlinks from instrText and other areas in ooxml(#2578)
(cherry picked from commit bef2d336b1e4e52e3ca262d656f93ee4d3145b5f)
---
.../main/java/org/apache/tika/metadata/Office.java | 51 +++
.../microsoft/ooxml/AbstractOOXMLExtractor.java | 26 ++
.../microsoft/ooxml/FieldHyperlinkTracker.java | 168 +++++++++
.../microsoft/ooxml/OOXMLTikaBodyPartHandler.java | 25 ++
.../ooxml/OOXMLWordAndPowerPointTextHandler.java | 187 +++++++++-
.../ooxml/SXWPFWordExtractorDecorator.java | 179 +++++++++-
.../ooxml/XSSFExcelExtractorDecorator.java | 390 +++++++++++++++++++++
.../ooxml/XWPFWordExtractorDecorator.java | 95 ++++-
.../xslf/XSLFEventBasedPowerPointExtractor.java | 5 +
.../ooxml/xwpf/XWPFEventBasedWordExtractor.java | 5 +
.../tika/parser/microsoft/ExcelParserTest.java | 43 +++
.../parser/microsoft/ooxml/OOXMLParserTest.java | 39 +++
.../parser/microsoft/ooxml/SXWPFExtractorTest.java | 109 ++++++
.../parser/microsoft/pst/OutlookPSTParserTest.java | 3 +
.../test-documents/testAttachedTemplate.docx | Bin 0 -> 2284 bytes
.../test-documents/testDataConnections.xlsx | Bin 0 -> 2967 bytes
.../test/resources/test-documents/testDdeLink.xlsx | Bin 0 -> 3030 bytes
.../resources/test-documents/testExternalRefs.docx | Bin 0 -> 2125 bytes
.../resources/test-documents/testFrameset.docx | Bin 0 -> 2328 bytes
.../resources/test-documents/testHoverAndVml.docx | Bin 0 -> 2270 bytes
.../resources/test-documents/testInstrLink.docx | Bin 0 -> 14464 bytes
.../resources/test-documents/testMailMerge.docx | Bin 0 -> 2306 bytes
.../resources/test-documents/testSubdocument.docx | Bin 0 -> 1980 bytes
23 files changed, 1322 insertions(+), 3 deletions(-)
diff --git a/tika-core/src/main/java/org/apache/tika/metadata/Office.java b/tika-core/src/main/java/org/apache/tika/metadata/Office.java
index 39607445f6..6e9a20e70b 100644
--- a/tika-core/src/main/java/org/apache/tika/metadata/Office.java
+++ b/tika-core/src/main/java/org/apache/tika/metadata/Office.java
@@ -201,8 +201,59 @@ public interface Office {
Property WORKBOOK_CODENAME = Property.internalText("msoffice:excel:workbook-codename");
+ Property HAS_DATA_CONNECTIONS = Property.internalBoolean("msoffice:excel:has-data-connections");
+
+ Property HAS_EXTERNAL_LINKS = Property.internalBoolean("msoffice:excel:has-external-links");
+
+ Property HAS_WEB_QUERIES = Property.internalBoolean("msoffice:excel:has-web-queries");
+
+ Property HAS_EXTERNAL_OLE_OBJECTS = Property.internalBoolean("msoffice:has-external-ole-objects");
+
+ Property HAS_FIELD_HYPERLINKS = Property.internalBoolean("msoffice:has-field-hyperlinks");
+
+ Property HAS_HOVER_HYPERLINKS = Property.internalBoolean("msoffice:has-hover-hyperlinks");
+
+ Property HAS_VML_HYPERLINKS = Property.internalBoolean("msoffice:has-vml-hyperlinks");
+
Property HAS_COMMENTS = Property.internalBoolean("msoffice:has-comments");
Property COMMENT_PERSONS = Property.internalTextBag("msoffice:comment-person-display-name");
+ Property HAS_HIDDEN_SLIDES = Property.internalBoolean("msoffice:ppt:has-hidden-slides");
+
+ Property NUM_HIDDEN_SLIDES = Property.internalInteger("msoffice:ppt:num-hidden-slides");
+
+ Property HAS_ANIMATIONS = Property.internalBoolean("msoffice:ppt:has-animations");
+
+ //w:vanish or isVanish or isFldVanish
+ Property HAS_HIDDEN_TEXT = Property.internalBoolean("msoffice:doc:has-hidden-text");
+
+ Property HAS_TRACK_CHANGES = Property.internalBoolean("msoffice:has-track-changes");
+
+ // Security-relevant: DDE (Dynamic Data Exchange) links can execute commands
+ Property HAS_DDE_LINKS = Property.internalBoolean("msoffice:excel:has-dde-links");
+
+ // Security-relevant: Mail merge can reference external data sources
+ Property HAS_MAIL_MERGE = Property.internalBoolean("msoffice:doc:has-mail-merge");
+
+ // Security-relevant: Attached templates can be fetched from external URLs
+ Property HAS_ATTACHED_TEMPLATE = Property.internalBoolean("msoffice:doc:has-attached-template");
+
+ // Security-relevant: SubDocuments reference external documents in master docs
+ Property HAS_SUBDOCUMENTS = Property.internalBoolean("msoffice:doc:has-subdocuments");
+
+ // Security-relevant: Pivot tables can reference external OLAP/database sources
+ Property HAS_EXTERNAL_PIVOT_DATA = Property.internalBoolean("msoffice:excel:has-external-pivot-data");
+
+ // Security-relevant: Power Query can contain URLs and connection strings
+ Property HAS_POWER_QUERY = Property.internalBoolean("msoffice:excel:has-power-query");
+
+ // Security-relevant: OLE objects can link to external files (vs embedded)
+ Property HAS_LINKED_OLE_OBJECTS = Property.internalBoolean("msoffice:has-linked-ole-objects");
+
+ // Security-relevant: Charts can reference external workbook data
+ Property HAS_EXTERNAL_CHART_DATA = Property.internalBoolean("msoffice:has-external-chart-data");
+
+ // Security-relevant: Framesets can load external URLs
+ Property HAS_FRAMESETS = Property.internalBoolean("msoffice:doc:has-framesets");
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
index c7cfecfa49..a8d65cd895 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
@@ -265,6 +265,16 @@ public abstract class AbstractOOXMLExtractor implements OOXMLExtractor {
sourceDesc = "";
}
if (rel.getTargetMode() != TargetMode.INTERNAL) {
+ // External target - emit as external reference for security analysis
+ String type = rel.getRelationshipType();
+ if (POIXMLDocument.OLE_OBJECT_REL_TYPE.equals(type)) {
+ emitExternalRef(xhtml, "externalOleObject", targetURI.toString());
+ parentMetadata.set(Office.HAS_EXTERNAL_OLE_OBJECTS, true);
+ } else if (PackageRelationshipTypes.IMAGE_PART.equals(type)) {
+ emitExternalRef(xhtml, "externalImage", targetURI.toString());
+ } else {
+ emitExternalRef(xhtml, "externalResource", targetURI.toString());
+ }
return;
}
PackagePart target;
@@ -489,6 +499,22 @@ public abstract class AbstractOOXMLExtractor implements OOXMLExtractor {
metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, name);
}
+ /**
+ * Emits an external reference as an anchor element with appropriate class.
+ * Used for detecting external resources that could be security risks.
+ */
+ private void emitExternalRef(XHTMLContentHandler xhtml, String refType, String url)
+ throws SAXException {
+ if (url == null || url.isEmpty()) {
+ return;
+ }
+ AttributesImpl attrs = new AttributesImpl();
+ attrs.addAttribute("", "class", "class", "CDATA", "external-ref-" + refType);
+ attrs.addAttribute("", "href", "href", "CDATA", url);
+ xhtml.startElement("a", attrs);
+ xhtml.endElement("a");
+ }
+
/**
* Populates the {@link XHTMLContentHandler} object received as parameter.
*/
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/FieldHyperlinkTracker.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/FieldHyperlinkTracker.java
new file mode 100644
index 0000000000..951711d99f
--- /dev/null
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/FieldHyperlinkTracker.java
@@ -0,0 +1,168 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.parser.microsoft.ooxml;
+
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+/**
+ * Tracks field hyperlink state across multiple runs within a paragraph.
+ * Field codes span multiple runs: begin -> instrText -> separate -> text runs -> end
+ * <p>
+ * This class handles HYPERLINK field codes as well as other external references
+ * like INCLUDEPICTURE, INCLUDETEXT, IMPORT, and LINK.
+ */
+class FieldHyperlinkTracker {
+
+ // Patterns for extracting URLs from field codes
+ private static final Pattern HYPERLINK_PATTERN =
+ Pattern.compile("HYPERLINK\\s{1,100}\"([^\"]{1,10000})\"", Pattern.CASE_INSENSITIVE);
+ private static final Pattern INCLUDEPICTURE_PATTERN =
+ Pattern.compile("INCLUDEPICTURE\\s{1,100}\"([^\"]{1,10000})\"", Pattern.CASE_INSENSITIVE);
+ private static final Pattern INCLUDETEXT_PATTERN =
+ Pattern.compile("INCLUDETEXT\\s{1,100}\"([^\"]{1,10000})\"", Pattern.CASE_INSENSITIVE);
+ private static final Pattern IMPORT_PATTERN =
+ Pattern.compile("IMPORT\\s{1,100}\"([^\"]{1,10000})\"", Pattern.CASE_INSENSITIVE);
+ private static final Pattern LINK_PATTERN =
+ Pattern.compile("LINK\\s{1,100}[\\w.]{1,50}\\s{1,100}\"([^\"]{1,10000})\"",
+ Pattern.CASE_INSENSITIVE);
+
+ private boolean inField = false;
+ private boolean inFieldHyperlink = false;
+ private final StringBuilder instrTextBuffer = new StringBuilder();
+ private String lastExternalRefType = null;
+ private String lastExternalRefUrl = null;
+
+ void startField() {
+ inField = true;
+ instrTextBuffer.setLength(0);
+ lastExternalRefType = null;
+ lastExternalRefUrl = null;
+ }
+
+ void addInstrText(String text) {
+ if (inField && text != null) {
+ instrTextBuffer.append(text);
+ }
+ }
+
+ /**
+ * Called when fldChar separate is encountered.
+ *
+ * @return the hyperlink URL if this is a HYPERLINK field, null otherwise
+ */
+ String separate() {
+ if (inField) {
+ String url = parseHyperlinkFromInstrText(instrTextBuffer.toString());
+ if (url != null) {
+ inFieldHyperlink = true;
+ return url;
+ }
+ // Check for other external refs (INCLUDEPICTURE, INCLUDETEXT, IMPORT, LINK)
+ StringBuilder fieldType = new StringBuilder();
+ String extUrl = parseExternalRefFromInstrText(instrTextBuffer.toString(), fieldType);
+ if (extUrl != null) {
+ lastExternalRefType = fieldType.toString();
+ lastExternalRefUrl = extUrl;
+ }
+ }
+ return null;
+ }
+
+ void endField() {
+ inField = false;
+ inFieldHyperlink = false;
+ instrTextBuffer.setLength(0);
+ lastExternalRefType = null;
+ lastExternalRefUrl = null;
+ }
+
+ boolean isInFieldHyperlink() {
+ return inFieldHyperlink;
+ }
+
+ String getLastExternalRefType() {
+ return lastExternalRefType;
+ }
+
+ String getLastExternalRefUrl() {
+ return lastExternalRefUrl;
+ }
+
+ void clearExternalRef() {
+ lastExternalRefType = null;
+ lastExternalRefUrl = null;
+ }
+
+ /**
+ * Parses a HYPERLINK URL from instrText field code content.
+ *
+ * @param instrText the accumulated instrText content
+ * @return the URL if found, or null
+ */
+ private static String parseHyperlinkFromInstrText(String instrText) {
+ if (instrText == null || instrText.isEmpty()) {
+ return null;
+ }
+ Matcher m = HYPERLINK_PATTERN.matcher(instrText.trim());
+ if (m.find()) {
+ return m.group(1);
+ }
+ return null;
+ }
+
+ /**
+ * Parses external reference URLs from instrText field codes
+ * (INCLUDEPICTURE, INCLUDETEXT, IMPORT, LINK).
+ *
+ * @param instrText the accumulated instrText content
+ * @param fieldType output parameter - will contain the field type if found
+ * @return the URL if found, or null
+ */
+ private static String parseExternalRefFromInstrText(String instrText, StringBuilder fieldType) {
+ if (instrText == null || instrText.isEmpty()) {
+ return null;
+ }
+ String trimmed = instrText.trim();
+
+ Matcher m = INCLUDEPICTURE_PATTERN.matcher(trimmed);
+ if (m.find()) {
+ fieldType.append("INCLUDEPICTURE");
+ return m.group(1);
+ }
+
+ m = INCLUDETEXT_PATTERN.matcher(trimmed);
+ if (m.find()) {
+ fieldType.append("INCLUDETEXT");
+ return m.group(1);
+ }
+
+ m = IMPORT_PATTERN.matcher(trimmed);
+ if (m.find()) {
+ fieldType.append("IMPORT");
+ return m.group(1);
+ }
+
+ m = LINK_PATTERN.matcher(trimmed);
+ if (m.find()) {
+ fieldType.append("LINK");
+ return m.group(1);
+ }
+
+ return null;
+ }
+}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLTikaBodyPartHandler.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLTikaBodyPartHandler.java
index 8ff630da14..4bc445fb5e 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLTikaBodyPartHandler.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLTikaBodyPartHandler.java
@@ -321,6 +321,19 @@ public class OOXMLTikaBodyPartHandler
xhtml.endElement("div");
}
+ @Override
+ public void linkedOLERef(String relId) throws SAXException {
+ if (relId == null) {
+ return;
+ }
+ // Emit as an external reference anchor - linked OLE objects reference external files
+ AttributesImpl attributes = new AttributesImpl();
+ attributes.addAttribute("", "class", "class", "CDATA", "external-ref-linkedOle");
+ attributes.addAttribute("", "id", "id", "CDATA", relId);
+ xhtml.startElement("a", attributes);
+ xhtml.endElement("a");
+ }
+
@Override
public void embeddedPicRef(String picFileName, String picDescription) throws SAXException {
@@ -338,6 +351,18 @@ public class OOXMLTikaBodyPartHandler
}
+ @Override
+ public void externalRef(String fieldType, String url) throws SAXException {
+ if (url == null || url.isEmpty()) {
+ return;
+ }
+ AttributesImpl attr = new AttributesImpl();
+ attr.addAttribute("", "class", "class", "CDATA", "external-ref-" + fieldType);
+ attr.addAttribute("", "href", "href", "CDATA", url);
+ xhtml.startElement("a", attr);
+ xhtml.endElement("a");
+ }
+
@Override
public void startBookmark(String id, String name) throws SAXException {
//skip bookmarks within hyperlinks
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java
index 6e355b8ff9..9e7110f773 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java
@@ -19,12 +19,16 @@ package org.apache.tika.parser.microsoft.ooxml;
import java.util.Date;
import java.util.Map;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
import org.apache.poi.xwpf.usermodel.UnderlinePatterns;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.Office;
import org.apache.tika.utils.DateUtils;
/**
@@ -106,12 +110,34 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
private final static String MOVE_TO = "moveTo";
private final static String ENDNOTE_REFERENCE = "endnoteReference";
private static final String TEXTBOX = "textbox";
+ private final static String FLD_CHAR = "fldChar";
+ private final static String INSTR_TEXT = "instrText";
+ private final static String FLD_CHAR_TYPE = "fldCharType";
+ // DrawingML hyperlinks on shapes/pictures
+ private final static String HLINK_HOVER = "hlinkHover";
+ private final static String C_NV_PR = "cNvPr";
+ // VML shape hyperlinks
+ private final static String SHAPE = "shape";
+ private final static String HREF = "href";
+
+ // Patterns for extracting URLs from field codes
+ private static final Pattern HYPERLINK_PATTERN =
+ Pattern.compile("HYPERLINK\\s{1,100}\"([^\"]{1,10000})\"", Pattern.CASE_INSENSITIVE);
+ private static final Pattern INCLUDEPICTURE_PATTERN =
+ Pattern.compile("INCLUDEPICTURE\\s{1,100}\"([^\"]{1,10000})\"", Pattern.CASE_INSENSITIVE);
+ private static final Pattern INCLUDETEXT_PATTERN =
+ Pattern.compile("INCLUDETEXT\\s{1,100}\"([^\"]{1,10000})\"", Pattern.CASE_INSENSITIVE);
+ private static final Pattern IMPORT_PATTERN =
+ Pattern.compile("IMPORT\\s{1,100}\"([^\"]{1,10000})\"", Pattern.CASE_INSENSITIVE);
+ private static final Pattern LINK_PATTERN =
+ Pattern.compile("LINK\\s{1,100}[\\w.]{1,50}\\s{1,100}\"([^\"]{1,10000})\"", Pattern.CASE_INSENSITIVE);
private final XWPFBodyContentsHandler bodyContentsHandler;
private final Map<String, String> linkedRelationships;
private final RunProperties currRunProperties = new RunProperties();
private final ParagraphProperties currPProperties = new ParagraphProperties();
private final boolean includeTextBox;
private final boolean concatenatePhoneticRuns;
+ private final Metadata metadata;
private final StringBuilder runBuffer = new StringBuilder();
private final StringBuilder rubyBuffer = new StringBuilder();
private boolean inR = false;
@@ -143,22 +169,34 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
private boolean inHlinkClick = false;
private boolean inTextBox = false;
private boolean inV = false; //in c:v in chart file
+ // Field code tracking for instrText-based hyperlinks
+ private boolean inField = false;
+ private boolean inInstrText = false;
+ private boolean inFieldHyperlink = false;
+ private final StringBuilder instrTextBuffer = new StringBuilder();
private OOXMLWordAndPowerPointTextHandler.EditType editType =
OOXMLWordAndPowerPointTextHandler.EditType.NONE;
private DateUtils dateUtils = new DateUtils();
public OOXMLWordAndPowerPointTextHandler(XWPFBodyContentsHandler bodyContentsHandler,
Map<String, String> hyperlinks) {
- this(bodyContentsHandler, hyperlinks, true, true);
+ this(bodyContentsHandler, hyperlinks, true, true, null);
}
public OOXMLWordAndPowerPointTextHandler(XWPFBodyContentsHandler bodyContentsHandler,
Map<String, String> hyperlinks, boolean includeTextBox,
boolean concatenatePhoneticRuns) {
+ this(bodyContentsHandler, hyperlinks, includeTextBox, concatenatePhoneticRuns, null);
+ }
+
+ public OOXMLWordAndPowerPointTextHandler(XWPFBodyContentsHandler bodyContentsHandler,
+ Map<String, String> hyperlinks, boolean includeTextBox,
+ boolean concatenatePhoneticRuns, Metadata metadata) {
this.bodyContentsHandler = bodyContentsHandler;
this.linkedRelationships = hyperlinks;
this.includeTextBox = includeTextBox;
this.concatenatePhoneticRuns = concatenatePhoneticRuns;
+ this.metadata = metadata;
}
@Override
@@ -322,6 +360,12 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
}
if ("Embed".equals(type)) {
bodyContentsHandler.embeddedOLERef(refId);
+ } else if ("Link".equals(type)) {
+ // Linked OLE object - references external file
+ bodyContentsHandler.linkedOLERef(refId);
+ if (metadata != null) {
+ metadata.set(Office.HAS_LINKED_OLE_OBJECTS, true);
+ }
}
} else if (CR.equals(localName)) {
runBuffer.append(NEWLINE);
@@ -332,6 +376,65 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
inV = true;
} else if (RT.equals(localName)) {
inRt = true;
+ } else if (FLD_CHAR.equals(localName)) {
+ String fldCharType = atts.getValue(W_NS, FLD_CHAR_TYPE);
+ if ("begin".equals(fldCharType)) {
+ inField = true;
+ instrTextBuffer.setLength(0);
+ } else if ("separate".equals(fldCharType)) {
+ // Parse instrText for HYPERLINK
+ String url = parseHyperlinkFromInstrText(instrTextBuffer.toString());
+ if (url != null) {
+ bodyContentsHandler.hyperlinkStart(url);
+ inFieldHyperlink = true;
+ if (metadata != null) {
+ metadata.set(Office.HAS_FIELD_HYPERLINKS, true);
+ }
+ } else {
+ // Check for external reference fields (INCLUDEPICTURE, INCLUDETEXT, etc.)
+ StringBuilder fieldType = new StringBuilder();
+ String extUrl = parseExternalRefFromInstrText(instrTextBuffer.toString(), fieldType);
+ if (extUrl != null) {
+ bodyContentsHandler.externalRef(fieldType.toString(), extUrl);
+ if (metadata != null) {
+ metadata.set(Office.HAS_FIELD_HYPERLINKS, true);
+ }
+ }
+ }
+ } else if ("end".equals(fldCharType)) {
+ if (inFieldHyperlink) {
+ bodyContentsHandler.hyperlinkEnd();
+ inFieldHyperlink = false;
+ }
+ inField = false;
+ instrTextBuffer.setLength(0);
+ }
+ } else if (INSTR_TEXT.equals(localName)) {
+ inInstrText = true;
+ } else if (HLINK_HOVER.equals(localName)) {
+ // DrawingML hover hyperlink on shapes/pictures
+ String hyperlinkId = atts.getValue(OFFICE_DOC_RELATIONSHIP_NS, "id");
+ if (hyperlinkId != null) {
+ String hyperlink = linkedRelationships.get(hyperlinkId);
+ if (hyperlink != null) {
+ bodyContentsHandler.externalRef("hlinkHover", hyperlink);
+ if (metadata != null) {
+ metadata.set(Office.HAS_HOVER_HYPERLINKS, true);
+ }
+ }
+ }
+ } else if (SHAPE.equals(localName) && V_NS.equals(uri)) {
+ // VML shape with href attribute
+ String href = atts.getValue(HREF);
+ if (href == null) {
+ href = atts.getValue(O_NS, HREF);
+ }
+ if (href != null && !href.isEmpty()) {
+ bodyContentsHandler.externalRef("vml-shape-href", href);
+ if (metadata != null) {
+ metadata.set(Office.HAS_VML_HYPERLINKS, true);
+ }
+ }
}
}
@@ -367,6 +470,65 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
return -1;
}
+ /**
+ * Parses a HYPERLINK URL from instrText field code content.
+ * Field codes like: HYPERLINK "https://example.com"
+ *
+ * @param instrText the accumulated instrText content
+ * @return the URL if found, or null
+ */
+ private String parseHyperlinkFromInstrText(String instrText) {
+ if (instrText == null || instrText.isEmpty()) {
+ return null;
+ }
+ Matcher m = HYPERLINK_PATTERN.matcher(instrText.trim());
+ if (m.find()) {
+ return m.group(1);
+ }
+ return null;
+ }
+
+ /**
+ * Parses URLs from instrText field codes that reference external resources.
+ * This includes INCLUDEPICTURE, INCLUDETEXT, IMPORT, and LINK fields.
+ *
+ * @param instrText the accumulated instrText content
+ * @param fieldType output parameter - will contain the field type if found
+ * @return the URL if found, or null
+ */
+ private String parseExternalRefFromInstrText(String instrText, StringBuilder fieldType) {
+ if (instrText == null || instrText.isEmpty()) {
+ return null;
+ }
+ String trimmed = instrText.trim();
+
+ Matcher m = INCLUDEPICTURE_PATTERN.matcher(trimmed);
+ if (m.find()) {
+ fieldType.append("INCLUDEPICTURE");
+ return m.group(1);
+ }
+
+ m = INCLUDETEXT_PATTERN.matcher(trimmed);
+ if (m.find()) {
+ fieldType.append("INCLUDETEXT");
+ return m.group(1);
+ }
+
+ m = IMPORT_PATTERN.matcher(trimmed);
+ if (m.find()) {
+ fieldType.append("IMPORT");
+ return m.group(1);
+ }
+
+ m = LINK_PATTERN.matcher(trimmed);
+ if (m.find()) {
+ fieldType.append("LINK");
+ return m.group(1);
+ }
+
+ return null;
+ }
+
@Override
public void endElement(String uri, String localName, String qName) throws SAXException {
@@ -432,6 +594,8 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
inRt = false;
} else if (RUBY.equals(localName)) {
handleEndOfRuby();
+ } else if (INSTR_TEXT.equals(localName)) {
+ inInstrText = false;
}
}
@@ -489,6 +653,9 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
} else if (inV) {
appendToBuffer(ch, start, length);
appendToBuffer(TAB_CHAR, 0, 1);
+ } else if (inInstrText && inField) {
+ // Accumulate instrText content for field code parsing (e.g., HYPERLINK)
+ instrTextBuffer.append(ch, start, length);
}
}
@@ -564,10 +731,28 @@ public class OOXMLWordAndPowerPointTextHandler extends DefaultHandler {
void embeddedOLERef(String refId) throws SAXException;
+ /**
+ * Called when a linked (vs embedded) OLE object is found.
+ * These reference external files and are a security concern.
+ */
+ void linkedOLERef(String refId) throws SAXException;
+
void embeddedPicRef(String picFileName, String picDescription) throws SAXException;
void startBookmark(String id, String name) throws SAXException;
void endBookmark(String id) throws SAXException;
+
+ /**
+ * Called when an external reference URL is found in a field code.
+ * This includes INCLUDEPICTURE, INCLUDETEXT, IMPORT, LINK fields,
+ * and DrawingML/VML hyperlinks on shapes.
+ *
+ * @param fieldType the type of field (e.g., "INCLUDEPICTURE", "hlinkHover", "vml-href")
+ * @param url the external URL
+ */
+ default void externalRef(String fieldType, String url) throws SAXException {
+ // Default no-op implementation for backward compatibility
+ }
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXWPFWordExtractorDecorator.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXWPFWordExtractorDecorator.java
index 2b4c52748c..fbe16d51a2 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXWPFWordExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXWPFWordExtractorDecorator.java
@@ -30,14 +30,18 @@ import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.openxml4j.opc.PackagePart;
import org.apache.poi.openxml4j.opc.PackageRelationship;
import org.apache.poi.openxml4j.opc.PackageRelationshipCollection;
+import org.apache.poi.openxml4j.opc.TargetMode;
import org.apache.poi.xssf.usermodel.XSSFRelation;
import org.apache.poi.xwpf.usermodel.XWPFNumbering;
import org.apache.poi.xwpf.usermodel.XWPFRelation;
import org.apache.xmlbeans.XmlException;
+import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
+import org.xml.sax.helpers.DefaultHandler;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.Office;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.microsoft.ooxml.xwpf.XWPFEventBasedWordExtractor;
@@ -69,6 +73,16 @@ public class SXWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
"http://schemas.openxmlformats.org/officeDocument/2006/relationships/endnotes",
"http://schemas.openxmlformats.org/officeDocument/2006/relationships/comments"};
+ // Relationship types for Word settings
+ private static final String SETTINGS_RELATION =
+ "http://schemas.openxmlformats.org/officeDocument/2006/relationships/settings";
+ private static final String WEB_SETTINGS_RELATION =
+ "http://schemas.openxmlformats.org/officeDocument/2006/relationships/webSettings";
+ private static final String ATTACHED_TEMPLATE_RELATION =
+ "http://schemas.openxmlformats.org/officeDocument/2006/relationships/attachedTemplate";
+ private static final String SUBDOCUMENT_RELATION =
+ "http://schemas.openxmlformats.org/officeDocument/2006/relationships/subDocument";
+
//a docx file should have one of these "main story" parts
private final static String[] MAIN_STORY_PART_RELATIONS =
new String[]{XWPFRelation.DOCUMENT.getContentType(),
@@ -116,6 +130,106 @@ public class SXWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
xhtml.endElement("div");
}
}
+
+ // Detect security-relevant features in main document
+ pps = getStoryDocumentParts();
+ if (pps != null && !pps.isEmpty()) {
+ PackagePart mainDoc = pps.get(0);
+ detectSecurityFeatures(mainDoc, xhtml);
+ }
+ }
+
+ /**
+ * Detects security-relevant features like mail merge, attached templates,
+ * subdocuments, and framesets.
+ */
+ private void detectSecurityFeatures(PackagePart documentPart, XHTMLContentHandler xhtml) {
+ // Check for attached template (external template reference)
+ try {
+ PackageRelationshipCollection templateRels =
+ documentPart.getRelationshipsByType(ATTACHED_TEMPLATE_RELATION);
+ if (templateRels != null && templateRels.size() > 0) {
+ metadata.set(Office.HAS_ATTACHED_TEMPLATE, true);
+ for (PackageRelationship rel : templateRels) {
+ if (rel.getTargetMode() == TargetMode.EXTERNAL) {
+ emitExternalRef(xhtml, "attachedTemplate", rel.getTargetURI().toString());
+ }
+ }
+ }
+ } catch (InvalidFormatException | SAXException e) {
+ // swallow
+ }
+
+ // Check for subdocuments (master document with external subdocs)
+ try {
+ PackageRelationshipCollection subDocRels =
+ documentPart.getRelationshipsByType(SUBDOCUMENT_RELATION);
+ if (subDocRels != null && subDocRels.size() > 0) {
+ metadata.set(Office.HAS_SUBDOCUMENTS, true);
+ for (PackageRelationship rel : subDocRels) {
+ if (rel.getTargetMode() == TargetMode.EXTERNAL) {
+ emitExternalRef(xhtml, "subDocument", rel.getTargetURI().toString());
+ }
+ }
+ }
+ } catch (InvalidFormatException | SAXException e) {
+ // swallow
+ }
+
+ // Check settings.xml for mail merge
+ try {
+ PackageRelationshipCollection settingsRels =
+ documentPart.getRelationshipsByType(SETTINGS_RELATION);
+ if (settingsRels != null && settingsRels.size() > 0) {
+ PackagePart settingsPart = documentPart.getRelatedPart(settingsRels.getRelationship(0));
+ if (settingsPart != null) {
+ try (InputStream is = settingsPart.getInputStream()) {
+ WordSettingsHandler handler = new WordSettingsHandler(xhtml);
+ XMLReaderUtils.parseSAX(is, handler, context);
+ if (handler.hasMailMerge()) {
+ metadata.set(Office.HAS_MAIL_MERGE, true);
+ }
+ }
+ }
+ }
+ } catch (InvalidFormatException | IOException | TikaException | SAXException e) {
+ // swallow
+ }
+
+ // Check webSettings.xml for framesets
+ try {
+ PackageRelationshipCollection webSettingsRels =
+ documentPart.getRelationshipsByType(WEB_SETTINGS_RELATION);
+ if (webSettingsRels != null && webSettingsRels.size() > 0) {
+ PackagePart webSettingsPart = documentPart.getRelatedPart(webSettingsRels.getRelationship(0));
+ if (webSettingsPart != null) {
+ try (InputStream is = webSettingsPart.getInputStream()) {
+ WebSettingsHandler handler = new WebSettingsHandler(xhtml);
+ XMLReaderUtils.parseSAX(is, handler, context);
+ if (handler.hasFrameset()) {
+ metadata.set(Office.HAS_FRAMESETS, true);
+ }
+ }
+ }
+ }
+ } catch (InvalidFormatException | IOException | TikaException | SAXException e) {
+ // swallow
+ }
+ }
+
+ /**
+ * Emits an external reference as an anchor element.
+ */
+ private void emitExternalRef(XHTMLContentHandler xhtml, String refType, String url)
+ throws SAXException {
+ if (url == null || url.isEmpty()) {
+ return;
+ }
+ org.xml.sax.helpers.AttributesImpl attrs = new org.xml.sax.helpers.AttributesImpl();
+ attrs.addAttribute("", "class", "class", "CDATA", "external-ref-" + refType);
+ attrs.addAttribute("", "href", "href", "CDATA", url);
+ xhtml.startElement("a", attrs);
+ xhtml.endElement("a");
}
private void handleDocumentPart(PackagePart documentPart, XHTMLContentHandler xhtml)
@@ -195,7 +309,7 @@ public class SXWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
new EmbeddedContentHandler(new OOXMLWordAndPowerPointTextHandler(
new OOXMLTikaBodyPartHandler(xhtml, styles, listManager, config),
linkedRelationships, config.isIncludeShapeBasedContent(),
- config.isConcatenatePhoneticRuns())), context);
+ config.isConcatenatePhoneticRuns(), metadata)), context);
} catch (TikaException | IOException e) {
metadata.add(TikaCoreProperties.TIKA_META_EXCEPTION_WARNING,
ExceptionUtils.getStackTrace(e));
@@ -299,4 +413,67 @@ public class SXWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
}
return new ArrayList<>();
}
+
+ /**
+ * Handler for parsing Word settings.xml to detect mail merge and other features.
+ */
+ private static class WordSettingsHandler extends DefaultHandler {
+ private final XHTMLContentHandler xhtml;
+ private boolean hasMailMerge = false;
+
+ WordSettingsHandler(XHTMLContentHandler xhtml) {
+ this.xhtml = xhtml;
+ }
+
+ @Override
+ public void startElement(String uri, String localName, String qName, Attributes atts)
+ throws SAXException {
+ // Mail merge element indicates document has mail merge data source
+ if ("mailMerge".equals(localName)) {
+ hasMailMerge = true;
+ }
+ // dataSource element contains the external data source reference
+ if ("dataSource".equals(localName) || "query".equals(localName)) {
+ String rId = atts.getValue("http://schemas.openxmlformats.org/officeDocument/2006/relationships", "id");
+ // The actual data source location is in the relationship
+ }
+ }
+
+ boolean hasMailMerge() {
+ return hasMailMerge;
+ }
+ }
+
+ /**
+ * Handler for parsing Word webSettings.xml to detect framesets.
+ */
+ private static class WebSettingsHandler extends DefaultHandler {
+ private final XHTMLContentHandler xhtml;
+ private boolean hasFrameset = false;
+
+ WebSettingsHandler(XHTMLContentHandler xhtml) {
+ this.xhtml = xhtml;
+ }
+
+ @Override
+ public void startElement(String uri, String localName, String qName, Attributes atts)
+ throws SAXException {
+ // Frameset element indicates document contains frames
+ if ("frameset".equals(localName)) {
+ hasFrameset = true;
+ }
+ // Frame with src attribute contains URL
+ if ("frame".equals(localName)) {
+ String src = atts.getValue("src");
+ if (src != null && !src.isEmpty()) {
+ // Frame references an external URL
+ hasFrameset = true;
+ }
+ }
+ }
+
+ boolean hasFrameset() {
+ return hasFrameset;
+ }
+ }
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
index 873242927f..8b41630f32 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
@@ -79,6 +79,20 @@ import org.apache.tika.utils.StringUtils;
import org.apache.tika.utils.XMLReaderUtils;
public class XSSFExcelExtractorDecorator extends AbstractOOXMLExtractor {
+
+ // Relationship types for external data sources
+ private static final String EXTERNAL_LINK_RELATION =
+ "http://schemas.openxmlformats.org/officeDocument/2006/relationships/externalLink";
+ private static final String CONNECTIONS_RELATION =
+ "http://schemas.openxmlformats.org/officeDocument/2006/relationships/connections";
+ private static final String QUERY_TABLE_RELATION =
+ "http://schemas.openxmlformats.org/officeDocument/2006/relationships/queryTable";
+ private static final String PIVOT_CACHE_DEFINITION_RELATION =
+ "http://schemas.openxmlformats.org/officeDocument/2006/relationships/pivotCacheDefinition";
+ // Power Query stores data in customData parts
+ private static final String POWER_QUERY_CONTENT_TYPE =
+ "application/vnd.ms-excel.customDataProperties+xml";
+
/**
* Allows access to headers/footers from raw xml strings
*/
@@ -223,6 +237,382 @@ public class XSSFExcelExtractorDecorator extends AbstractOOXMLExtractor {
//swallow
}
+ // Extract external data sources (HIGH security risk - can hide malicious URLs)
+ try {
+ extractExternalDataSources(container, xhtml);
+ } catch (InvalidFormatException | TikaException | IOException | SAXException e) {
+ //swallow
+ }
+
+ }
+
+ /**
+ * Extracts external data sources from the workbook including:
+ * - External workbook links
+ * - Data connections (database, web queries)
+ * - Query tables
+ */
+ private void extractExternalDataSources(OPCPackage container, XHTMLContentHandler xhtml)
+ throws InvalidFormatException, TikaException, IOException, SAXException {
+
+ PackageRelationship coreDocRelationship = container.getRelationshipsByType(
+ PackageRelationshipTypes.CORE_DOCUMENT).getRelationship(0);
+ if (coreDocRelationship == null) {
+ return;
+ }
+ PackagePart workbookPart = container.getPart(coreDocRelationship);
+ if (workbookPart == null) {
+ return;
+ }
+
+ // Extract external workbook links
+ extractExternalLinks(workbookPart, xhtml);
+
+ // Extract connections (database, ODBC, web queries)
+ extractConnections(workbookPart, xhtml);
+
+ // Extract query tables from each sheet
+ for (PackagePart sheetPart : sheetParts) {
+ extractQueryTables(sheetPart, xhtml);
+ }
+
+ // Detect pivot cache with external data sources
+ extractPivotCacheExternalData(workbookPart, xhtml);
+
+ // Detect Power Query / Data Mashup
+ detectPowerQuery(container);
+ }
+
+ /**
+ * Detects pivot cache definitions with external data sources (OLAP, databases).
+ */
+ private void extractPivotCacheExternalData(PackagePart workbookPart, XHTMLContentHandler xhtml)
+ throws InvalidFormatException {
+ PackageRelationshipCollection coll = workbookPart.getRelationshipsByType(PIVOT_CACHE_DEFINITION_RELATION);
+ if (coll == null || coll.isEmpty()) {
+ return;
+ }
+ for (PackageRelationship rel : coll) {
+ try {
+ PackagePart pivotCachePart = workbookPart.getRelatedPart(rel);
+ if (pivotCachePart != null) {
+ PivotCacheHandler handler = new PivotCacheHandler(xhtml);
+ try (InputStream is = pivotCachePart.getInputStream()) {
+ XMLReaderUtils.parseSAX(is, handler, parseContext);
+ }
+ if (handler.hasExternalData()) {
+ metadata.set(Office.HAS_EXTERNAL_PIVOT_DATA, true);
+ }
+ }
+ } catch (IOException | TikaException | SAXException e) {
+ // swallow
+ }
+ }
+ }
+
+ /**
+ * Detects Power Query / Data Mashup presence.
+ */
+ private void detectPowerQuery(OPCPackage container) {
+ // Power Query data is stored in customData parts with specific content type
+ // or in xl/customData/ folder
+ try {
+ List<PackagePart> customDataParts = container.getPartsByContentType(POWER_QUERY_CONTENT_TYPE);
+ if (customDataParts != null && !customDataParts.isEmpty()) {
+ metadata.set(Office.HAS_POWER_QUERY, true);
+ }
+ // Also check for customData folder parts
+ for (PackagePart part : container.getParts()) {
+ String partName = part.getPartName().getName();
+ if (partName.contains("/customData/") || partName.contains("/dataMashup")) {
+ metadata.set(Office.HAS_POWER_QUERY, true);
+ break;
+ }
+ }
+ } catch (InvalidFormatException e) {
+ // swallow
+ }
+ }
+
+ /**
+ * Extracts external workbook links from externalLink parts.
+ */
+ private void extractExternalLinks(PackagePart workbookPart, XHTMLContentHandler xhtml)
+ throws InvalidFormatException, SAXException {
+ PackageRelationshipCollection coll = workbookPart.getRelationshipsByType(EXTERNAL_LINK_RELATION);
+ if (coll == null || coll.isEmpty()) {
+ return;
+ }
+ // If we have any external link relationships, set the metadata flag
+ if (coll.size() > 0) {
+ metadata.set(Office.HAS_EXTERNAL_LINKS, true);
+ }
+ for (PackageRelationship rel : coll) {
+ if (rel.getTargetMode() == TargetMode.EXTERNAL) {
+ // Direct external reference
+ emitExternalRef(xhtml, "externalLink", rel.getTargetURI().toString());
+ } else {
+ // Internal part that contains external reference - parse it
+ try {
+ PackagePart externalLinkPart = workbookPart.getRelatedPart(rel);
+ if (externalLinkPart != null) {
+ ExternalLinkHandler handler = new ExternalLinkHandler(xhtml);
+ try (InputStream is = externalLinkPart.getInputStream()) {
+ XMLReaderUtils.parseSAX(is, handler, parseContext);
+ }
+ if (handler.hasDdeLink()) {
+ metadata.set(Office.HAS_DDE_LINKS, true);
+ }
+ }
+ } catch (IOException | TikaException e) {
+ // swallow
+ }
+ }
+ }
+ }
+
+ /**
+ * Extracts data connections from connections.xml.
+ */
+ private void extractConnections(PackagePart workbookPart, XHTMLContentHandler xhtml)
+ throws InvalidFormatException, SAXException {
+ PackageRelationshipCollection coll = workbookPart.getRelationshipsByType(CONNECTIONS_RELATION);
+ if (coll == null || coll.isEmpty()) {
+ return;
+ }
+ for (PackageRelationship rel : coll) {
+ try {
+ PackagePart connectionsPart = workbookPart.getRelatedPart(rel);
+ if (connectionsPart != null) {
+ ConnectionsHandler handler = new ConnectionsHandler(xhtml);
+ try (InputStream is = connectionsPart.getInputStream()) {
+ XMLReaderUtils.parseSAX(is, handler, parseContext);
+ }
+ if (handler.hasConnections()) {
+ metadata.set(Office.HAS_DATA_CONNECTIONS, true);
+ }
+ if (handler.hasWebQueries()) {
+ metadata.set(Office.HAS_WEB_QUERIES, true);
+ }
+ }
+ } catch (IOException | TikaException e) {
+ // swallow
+ }
+ }
+ }
+
+ /**
+ * Extracts query table external sources.
+ */
+ private void extractQueryTables(PackagePart sheetPart, XHTMLContentHandler xhtml)
+ throws InvalidFormatException, SAXException {
+ PackageRelationshipCollection coll = sheetPart.getRelationshipsByType(QUERY_TABLE_RELATION);
+ if (coll == null || coll.isEmpty()) {
+ return;
+ }
+ for (PackageRelationship rel : coll) {
+ try {
+ PackagePart queryTablePart = sheetPart.getRelatedPart(rel);
+ if (queryTablePart != null) {
+ try (InputStream is = queryTablePart.getInputStream()) {
+ XMLReaderUtils.parseSAX(is, new QueryTableHandler(xhtml), parseContext);
+ }
+ }
+ } catch (IOException | TikaException e) {
+ // swallow
+ }
+ }
+ }
+
+ /**
+ * Emits an external reference as an anchor element with appropriate class.
+ */
+ private void emitExternalRef(XHTMLContentHandler xhtml, String refType, String url)
+ throws SAXException {
+ if (url == null || url.isEmpty()) {
+ return;
+ }
+ org.xml.sax.helpers.AttributesImpl attrs = new org.xml.sax.helpers.AttributesImpl();
+ attrs.addAttribute("", "class", "class", "CDATA", "external-ref-" + refType);
+ attrs.addAttribute("", "href", "href", "CDATA", url);
+ xhtml.startElement("a", attrs);
+ xhtml.endElement("a");
+ }
+
+ /**
+ * Handler for parsing externalLink XML to extract external workbook references.
+ */
+ private class ExternalLinkHandler extends DefaultHandler {
+ private final XHTMLContentHandler xhtml;
+ private boolean foundDdeLink = false;
+
+ ExternalLinkHandler(XHTMLContentHandler xhtml) {
+ this.xhtml = xhtml;
+ }
+
+ @Override
+ public void startElement(String uri, String localName, String qName, Attributes atts)
+ throws SAXException {
+ // Look for externalBook element with r:id attribute
+ if ("externalBook".equals(localName)) {
+ String rId = atts.getValue("http://schemas.openxmlformats.org/officeDocument/2006/relationships", "id");
+ // The actual URL is in the relationship, not directly in the XML
+ // For now, we note that there's an external book reference
+ }
+ // Look for file element with href attribute (older format)
+ if ("file".equals(localName)) {
+ String href = atts.getValue("href");
+ if (href != null && !href.isEmpty()) {
+ emitExternalRef(xhtml, "externalWorkbook", href);
+ }
+ }
+ // Look for oleLink with r:id (OLE links to external files)
+ if ("oleLink".equals(localName)) {
+ String rId = atts.getValue("http://schemas.openxmlformats.org/officeDocument/2006/relationships", "id");
+ if (rId != null) {
+ emitExternalRef(xhtml, "oleLink", "relationship:" + rId);
+ }
+ }
+ // DDE links - security risk: can execute commands
+ if ("ddeLink".equals(localName)) {
+ foundDdeLink = true;
+ String ddeService = atts.getValue("ddeService");
+ String ddeTopic = atts.getValue("ddeTopic");
+ if (ddeService != null || ddeTopic != null) {
+ String ddeRef = (ddeService != null ? ddeService : "") + "|" +
+ (ddeTopic != null ? ddeTopic : "");
+ emitExternalRef(xhtml, "ddeLink", ddeRef);
+ }
+ }
+ }
+
+ boolean hasDdeLink() {
+ return foundDdeLink;
+ }
+ }
+
+ /**
+ * Handler for parsing connections.xml to extract external data connections.
+ */
+ private class ConnectionsHandler extends DefaultHandler {
+ private final XHTMLContentHandler xhtml;
+ private boolean foundConnection = false;
+ private boolean foundWebQuery = false;
+
+ ConnectionsHandler(XHTMLContentHandler xhtml) {
+ this.xhtml = xhtml;
+ }
+
+ @Override
+ public void startElement(String uri, String localName, String qName, Attributes atts)
+ throws SAXException {
+ if ("connection".equals(localName)) {
+ foundConnection = true;
+ }
+ // Database connection string
+ if ("dbPr".equals(localName)) {
+ String connection = atts.getValue("connection");
+ if (connection != null && !connection.isEmpty()) {
+ emitExternalRef(xhtml, "dbConnection", connection);
+ }
+ }
+ // Web query
+ if ("webPr".equals(localName)) {
+ foundWebQuery = true;
+ String url = atts.getValue("url");
+ if (url != null && !url.isEmpty()) {
+ emitExternalRef(xhtml, "webQuery", url);
+ }
+ }
+ // ODBC connection
+ if ("olapPr".equals(localName)) {
+ String connection = atts.getValue("connection");
+ if (connection != null && !connection.isEmpty()) {
+ emitExternalRef(xhtml, "olapConnection", connection);
+ }
+ }
+ // Text file import
+ if ("textPr".equals(localName)) {
+ String sourceFile = atts.getValue("sourceFile");
+ if (sourceFile != null && !sourceFile.isEmpty()) {
+ emitExternalRef(xhtml, "textFileImport", sourceFile);
+ }
+ }
+ }
+
+ boolean hasConnections() {
+ return foundConnection;
+ }
+
+ boolean hasWebQueries() {
+ return foundWebQuery;
+ }
+ }
+
+ /**
+ * Handler for parsing queryTable XML to extract web query sources.
+ */
+ private class QueryTableHandler extends DefaultHandler {
+ private final XHTMLContentHandler xhtml;
+
+ QueryTableHandler(XHTMLContentHandler xhtml) {
+ this.xhtml = xhtml;
+ }
+
+ @Override
+ public void startElement(String uri, String localName, String qName, Attributes atts)
+ throws SAXException {
+ if ("queryTable".equals(localName)) {
+ String connectionId = atts.getValue("connectionId");
+ // Connection details are in connections.xml
+ }
+ // Web query table refresh
+ if ("queryTableRefresh".equals(localName)) {
+ // Contains refresh settings
+ }
+ }
+ }
+
+ /**
+ * Handler for parsing pivotCacheDefinition XML to detect external data sources.
+ */
+ private class PivotCacheHandler extends DefaultHandler {
+ private final XHTMLContentHandler xhtml;
+ private boolean hasExternalData = false;
+
+ PivotCacheHandler(XHTMLContentHandler xhtml) {
+ this.xhtml = xhtml;
+ }
+
+ @Override
+ public void startElement(String uri, String localName, String qName, Attributes atts)
+ throws SAXException {
+ // cacheSource with type="external" indicates external data
+ if ("cacheSource".equals(localName)) {
+ String type = atts.getValue("type");
+ if ("external".equals(type) || "consolidation".equals(type)) {
+ hasExternalData = true;
+ }
+ }
+ // worksheetSource can have external references
+ if ("worksheetSource".equals(localName)) {
+ String ref = atts.getValue("ref");
+ String sheet = atts.getValue("sheet");
+ String rId = atts.getValue("http://schemas.openxmlformats.org/officeDocument/2006/relationships", "id");
+ // If there's a relationship ID, it likely points to external workbook
+ if (rId != null) {
+ hasExternalData = true;
+ }
+ }
+ // consolidation source (multiple ranges, possibly external)
+ if ("consolidation".equals(localName) || "rangeSets".equals(localName)) {
+ hasExternalData = true;
+ }
+ }
+
+ boolean hasExternalData() {
+ return hasExternalData;
+ }
}
private void getThreadedComments(OPCPackage container, PackagePart sheetPart, XHTMLContentHandler xhtml) throws TikaException,
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
index 922cdbd01d..a44f4525d7 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
@@ -61,13 +61,18 @@ import org.apache.xmlbeans.XmlCursor;
import org.apache.xmlbeans.XmlException;
import org.apache.xmlbeans.XmlObject;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTBookmark;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTFldChar;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTObject;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTP;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTR;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTSectPr;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTText;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.STFldCharType;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.AttributesImpl;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.Office;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.microsoft.EMFParser;
import org.apache.tika.parser.microsoft.FormattingUtils;
@@ -83,7 +88,6 @@ public class XWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
// Part 3, Step 3
private static final String LIST_DELIMITER = " ";
-
//include all parts that might have embedded objects
private final static String[] MAIN_PART_RELATIONS =
new String[]{XWPFRelation.HEADER.getRelation(), XWPFRelation.FOOTER.getRelation(),
@@ -233,8 +237,54 @@ public class XWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
//hyperlinks may or may not have hyperlink ids
String lastHyperlinkId = null;
boolean inHyperlink = false;
+ // Track field-based hyperlinks (using instrText/fldChar)
+ FieldHyperlinkTracker fieldTracker = new FieldHyperlinkTracker();
+ boolean inFieldHyperlink = false;
+
// Do the iruns
for (IRunElement run : paragraph.getIRuns()) {
+ // Check for field-based hyperlinks first (instrText HYPERLINK)
+ if (run instanceof XWPFRun) {
+ XWPFRun xwpfRun = (XWPFRun) run;
+ boolean wasInFieldHyperlink = fieldTracker.isInFieldHyperlink();
+ String fieldUrl = extractFieldLinks(xwpfRun, fieldTracker);
+
+ // If we just entered a field hyperlink, open the anchor tag
+ if (fieldUrl != null && !inFieldHyperlink) {
+ // Close any existing relationship-based hyperlink first
+ if (inHyperlink) {
+ FormattingUtils.closeStyleTags(xhtml, formattingState);
+ xhtml.endElement("a");
+ inHyperlink = false;
+ lastHyperlinkId = null;
+ }
+ FormattingUtils.closeStyleTags(xhtml, formattingState);
+ xhtml.startElement("a", "href", fieldUrl);
+ inFieldHyperlink = true;
+ metadata.set(Office.HAS_FIELD_HYPERLINKS, true);
+ }
+
+ // If we just exited a field hyperlink, close the anchor tag
+ if (wasInFieldHyperlink && !fieldTracker.isInFieldHyperlink() && inFieldHyperlink) {
+ FormattingUtils.closeStyleTags(xhtml, formattingState);
+ xhtml.endElement("a");
+ inFieldHyperlink = false;
+ }
+
+ // Emit any external refs (INCLUDEPICTURE, INCLUDETEXT, IMPORT, LINK) as anchors
+ if (fieldTracker.getLastExternalRefUrl() != null) {
+ AttributesImpl extRefAtts = new AttributesImpl();
+ extRefAtts.addAttribute("", "class", "class", "CDATA",
+ "external-ref-" + fieldTracker.getLastExternalRefType());
+ extRefAtts.addAttribute("", "href", "href", "CDATA",
+ fieldTracker.getLastExternalRefUrl());
+ xhtml.startElement("a", extRefAtts);
+ xhtml.endElement("a");
+ metadata.set(Office.HAS_FIELD_HYPERLINKS, true);
+ fieldTracker.clearExternalRef();
+ }
+ }
+
if (run instanceof XWPFHyperlinkRun) {
XWPFHyperlinkRun hyperlinkRun = (XWPFHyperlinkRun) run;
if (hyperlinkRun.getHyperlinkId() == null ||
@@ -278,6 +328,9 @@ public class XWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
if (inHyperlink) {
xhtml.endElement("a");
}
+ if (inFieldHyperlink) {
+ xhtml.endElement("a");
+ }
// Now do any comments for the paragraph
@@ -463,6 +516,46 @@ public class XWPFWordExtractorDecorator extends AbstractOOXMLExtractor {
xhtml.characters(run.getContent().getText());
}
+ /**
+ * Extracts field-based hyperlinks from a run by examining fldChar and instrText elements.
+ * This handles HYPERLINK field codes that are not relationship-based.
+ *
+ * @param run the run to examine
+ * @param tracker the field hyperlink tracker maintaining state across runs
+ * @return the hyperlink URL if this run starts a hyperlink, null otherwise
+ */
+ private String extractFieldLinks(XWPFRun run, FieldHyperlinkTracker tracker) {
+ CTR ctr = run.getCTR();
+ try (XmlCursor cursor = ctr.newCursor()) {
+ if (cursor.toFirstChild()) {
+ do {
+ String localName = cursor.getName().getLocalPart();
+ if ("fldChar".equals(localName)) {
+ XmlObject obj = cursor.getObject();
+ if (obj instanceof CTFldChar) {
+ CTFldChar fldChar = (CTFldChar) obj;
+ STFldCharType.Enum fldType = fldChar.getFldCharType();
+ if (fldType == STFldCharType.BEGIN) {
+ tracker.startField();
+ } else if (fldType == STFldCharType.SEPARATE) {
+ return tracker.separate();
+ } else if (fldType == STFldCharType.END) {
+ tracker.endField();
+ }
+ }
+ } else if ("instrText".equals(localName)) {
+ XmlObject obj = cursor.getObject();
+ if (obj instanceof CTText) {
+ CTText text = (CTText) obj;
+ tracker.addInstrText(text.getStringValue());
+ }
+ }
+ } while (cursor.toNextSibling());
+ }
+ }
+ return null;
+ }
+
private void extractTable(XWPFTable table, XWPFListManager listManager,
XHTMLContentHandler xhtml)
throws SAXException, XmlException, IOException {
diff --git a/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 b/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
index 72767fa15c..2950e46be3 100644
--- a/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
+++ b/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
@@ -201,6 +201,11 @@ public class XSLFEventBasedPowerPointExtractor implements POIXMLTextExtractor {
//no-op
}
+ @Override
+ public void linkedOLERef(String refId) {
+ //no-op
+ }
+
@Override
public void embeddedPicRef(String picFileName, String picDescription) {
//no-op
diff --git a/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 b/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
index 26cda41385..2fb45ca7fd 100644
--- a/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
+++ b/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
@@ -363,6 +363,11 @@ public class XWPFEventBasedWordExtractor implements POIXMLTextExtractor {
//no-op
}
+ @Override
+ public void linkedOLERef(String refId) {
+ //no-op
+ }
+
@Override
public void embeddedPicRef(String picFileName, String picDescription) {
//no-op
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
index a90d79445f..1cced50eeb 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
@@ -592,4 +592,47 @@ public class ExcelParserTest extends TikaTest {
assertEquals("true", m.get(Office.HAS_COMMENTS));
assertEquals("true", m.get(Office.HAS_HIDDEN_COLUMNS));
}
+
+ /**
+ * Test extraction of external data connections from XLSX files.
+ * These can be used to exfiltrate data or load malicious content.
+ */
+ @Test
+ public void testDataConnections() throws Exception {
+ List<Metadata> metadataList = getRecursiveMetadata("testDataConnections.xlsx");
+ Metadata m = metadataList.get(0);
+ // Check metadata flags are set
+ assertEquals("true", m.get(Office.HAS_DATA_CONNECTIONS));
+ assertEquals("true", m.get(Office.HAS_WEB_QUERIES));
+
+ String xml = getXML("testDataConnections.xlsx").xml;
+ // Test web query extraction
+ assertContains("class=\"external-ref-webQuery\"", xml);
+ assertContains("http://example.com/data.html", xml);
+ // Test database connection extraction
+ assertContains("class=\"external-ref-dbConnection\"", xml);
+ assertContains("db.example.org", xml);
+ // Test text file import
+ assertContains("class=\"external-ref-textFileImport\"", xml);
+ assertContains("http://example.net/data.csv", xml);
+ }
+
+ /**
+ * Test detection of DDE links in Excel files.
+ * DDE (Dynamic Data Exchange) links are a security risk as they can execute commands.
+ */
+ @Test
+ public void testDdeLinks() throws Exception {
+ List<Metadata> metadataList = getRecursiveMetadata("testDdeLink.xlsx");
+ Metadata m = metadataList.get(0);
+ // Check DDE link metadata flag is set
+ assertEquals("true", m.get(Office.HAS_DDE_LINKS));
+ // Also check external links flag since DDE is in externalLinks
+ assertEquals("true", m.get(Office.HAS_EXTERNAL_LINKS));
+
+ String xml = getXML("testDdeLink.xlsx").xml;
+ // Test DDE link extraction (service|topic format)
+ assertContains("class=\"external-ref-ddeLink\"", xml);
+ assertContains("cmd|", xml);
+ }
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
index 718c0e07c9..d75c7a20a8 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
@@ -1812,4 +1812,43 @@ public class OOXMLParserTest extends MultiThreadedTikaTest {
String content = getText("testRecordSizeExceeded.xlsx");
assertContains("Repetitive content pattern 3 for compression test row 1", content);
}
+
+ /**
+ * Test extraction of field-based hyperlinks using instrText/fldChar.
+ * These are hyperlinks embedded as field codes rather than relationship-based hyperlinks.
+ * Uses the DOM-based XWPFWordExtractorDecorator.
+ */
+ @Test
+ public void testInstrTextHyperlink() throws Exception {
+ String xml = getXML("testInstrLink.docx").xml;
+ // The document contains a HYPERLINK field code in instrText
+ assertContains("<a href=\"https://exmaple.com/file\">", xml);
+ assertContains("Access Document(s)", xml);
+ }
+
+ /**
+ * Test extraction of external reference field codes (INCLUDEPICTURE, INCLUDETEXT, IMPORT, LINK).
+ * These can be used to hide malicious URLs in documents.
+ */
+ @Test
+ public void testExternalRefFieldCodes() throws Exception {
+ List<Metadata> metadataList = getRecursiveMetadata("testExternalRefs.docx");
+ Metadata m = metadataList.get(0);
+ // Check metadata flag is set
+ assertEquals("true", m.get(Office.HAS_FIELD_HYPERLINKS));
+
+ String xml = getXML("testExternalRefs.docx").xml;
+ // Test INCLUDEPICTURE field code
+ assertContains("class=\"external-ref-INCLUDEPICTURE\"", xml);
+ assertContains("http://example.com/tracking.png", xml);
+ // Test INCLUDETEXT field code
+ assertContains("class=\"external-ref-INCLUDETEXT\"", xml);
+ assertContains("http://example.org/payload.txt", xml);
+ // Test IMPORT field code
+ assertContains("class=\"external-ref-IMPORT\"", xml);
+ assertContains("http://example.net/exploit.wmf", xml);
+ // Test LINK field code
+ assertContains("class=\"external-ref-LINK\"", xml);
+ assertContains("http://test.invalid/cmd.docx", xml);
+ }
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXWPFExtractorTest.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXWPFExtractorTest.java
index 91cb801ed1..c0482bd304 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXWPFExtractorTest.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXWPFExtractorTest.java
@@ -850,4 +850,113 @@ public class SXWPFExtractorTest extends TikaTest {
assertContainsCount("inside-text", xml, 1);
}
+ /**
+ * Test extraction of field-based hyperlinks using instrText/fldChar.
+ * These are hyperlinks embedded as field codes rather than relationship-based hyperlinks.
+ */
+ @Test
+ public void testInstrTextHyperlink() throws Exception {
+ String xml = getXML("testInstrLink.docx", parseContext).xml;
+ // The document contains a HYPERLINK field code in instrText
+ assertContains("<a href=\"https://exmaple.com/file\">", xml);
+ assertContains("Access Document(s)", xml);
+ }
+
+ /**
+ * Test extraction of external reference field codes (INCLUDEPICTURE, INCLUDETEXT, IMPORT, LINK).
+ * These can be used to hide malicious URLs in documents.
+ */
+ @Test
+ public void testExternalRefFieldCodes() throws Exception {
+ List<Metadata> metadataList = getRecursiveMetadata("testExternalRefs.docx", parseContext);
+ Metadata m = metadataList.get(0);
+ // Check metadata flag is set
+ assertEquals("true", m.get(Office.HAS_FIELD_HYPERLINKS));
+
+ String xml = getXML("testExternalRefs.docx", parseContext).xml;
+ // Test INCLUDEPICTURE field code
+ assertContains("class=\"external-ref-INCLUDEPICTURE\"", xml);
+ assertContains("http://example.com/tracking.png", xml);
+ // Test INCLUDETEXT field code
+ assertContains("class=\"external-ref-INCLUDETEXT\"", xml);
+ assertContains("http://example.org/payload.txt", xml);
+ // Test IMPORT field code
+ assertContains("class=\"external-ref-IMPORT\"", xml);
+ assertContains("http://example.net/exploit.wmf", xml);
+ // Test LINK field code
+ assertContains("class=\"external-ref-LINK\"", xml);
+ assertContains("http://test.invalid/cmd.docx", xml);
+ }
+
+ /**
+ * Test extraction of hlinkHover (hover hyperlinks) and VML shape hrefs.
+ * These are sneaky ways to hide malicious URLs.
+ */
+ @Test
+ public void testHoverAndVmlHyperlinks() throws Exception {
+ List<Metadata> metadataList = getRecursiveMetadata("testHoverAndVml.docx", parseContext);
+ Metadata m = metadataList.get(0);
+ // Check metadata flags are set
+ assertEquals("true", m.get(Office.HAS_HOVER_HYPERLINKS));
+ assertEquals("true", m.get(Office.HAS_VML_HYPERLINKS));
+
+ String xml = getXML("testHoverAndVml.docx", parseContext).xml;
+ // Test hlinkHover (activates on mouse hover, not click)
+ assertContains("class=\"external-ref-hlinkHover\"", xml);
+ assertContains("http://hover.example.com/phishing", xml);
+ // Test VML shape href
+ assertContains("class=\"external-ref-vml-shape-href\"", xml);
+ assertContains("http://vml.example.org/shape-link", xml);
+ }
+
+ /**
+ * Test detection of mail merge in Word documents.
+ * Mail merge can reference external data sources.
+ */
+ @Test
+ public void testMailMerge() throws Exception {
+ List<Metadata> metadataList = getRecursiveMetadata("testMailMerge.docx", parseContext);
+ Metadata m = metadataList.get(0);
+ assertEquals("true", m.get(Office.HAS_MAIL_MERGE));
+ }
+
+ /**
+ * Test detection of attached external template.
+ * Templates can be fetched from malicious URLs.
+ */
+ @Test
+ public void testAttachedTemplate() throws Exception {
+ List<Metadata> metadataList = getRecursiveMetadata("testAttachedTemplate.docx", parseContext);
+ Metadata m = metadataList.get(0);
+ assertEquals("true", m.get(Office.HAS_ATTACHED_TEMPLATE));
+
+ String xml = getXML("testAttachedTemplate.docx", parseContext).xml;
+ assertContains("class=\"external-ref-attachedTemplate\"", xml);
+ assertContains("example.com/templates", xml);
+ }
+
+ /**
+ * Test detection of subdocuments (master document linking external docs).
+ */
+ @Test
+ public void testSubdocument() throws Exception {
+ List<Metadata> metadataList = getRecursiveMetadata("testSubdocument.docx", parseContext);
+ Metadata m = metadataList.get(0);
+ assertEquals("true", m.get(Office.HAS_SUBDOCUMENTS));
+
+ String xml = getXML("testSubdocument.docx", parseContext).xml;
+ assertContains("class=\"external-ref-subDocument\"", xml);
+ assertContains("example.org/chapters", xml);
+ }
+
+ /**
+ * Test detection of framesets (HTML frames loading external URLs).
+ */
+ @Test
+ public void testFrameset() throws Exception {
+ List<Metadata> metadataList = getRecursiveMetadata("testFrameset.docx", parseContext);
+ Metadata m = metadataList.get(0);
+ assertEquals("true", m.get(Office.HAS_FRAMESETS));
+ }
+
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/pst/OutlookPSTParserTest.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/pst/OutlookPSTParserTest.java
index 6e9a6d6d1b..7cff052cf8 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/pst/OutlookPSTParserTest.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/pst/OutlookPSTParserTest.java
@@ -67,6 +67,9 @@ public class OutlookPSTParserTest extends TikaTest {
assertEquals(10, metadataList.size());
Metadata m1 = metadataList.get(1);
+ assertEquals("application/x-tika-pst-mail-item", m1.get(TikaCoreProperties.CONTENT_TYPE_PARSER_OVERRIDE));
+ assertEquals("application/x-tika-pst-mail-item", m1.get(Metadata.CONTENT_TYPE));
+
assertEquals("Jörn Kottmann", m1.get(Message.MESSAGE_FROM_NAME));
assertEquals("Jörn Kottmann", m1.get(TikaCoreProperties.CREATOR));
assertEquals("Re: Feature Generators", m1.get(TikaCoreProperties.TITLE));
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testAttachedTemplate.docx b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testAttachedTemplate.docx
new file mode 100644
index 0000000000..768258ad11
Binary files /dev/null and b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testAttachedTemplate.docx differ
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testDataConnections.xlsx b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testDataConnections.xlsx
new file mode 100644
index 0000000000..af76b99347
Binary files /dev/null and b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testDataConnections.xlsx differ
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testDdeLink.xlsx b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testDdeLink.xlsx
new file mode 100644
index 0000000000..be4912b4b5
Binary files /dev/null and b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testDdeLink.xlsx differ
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testExternalRefs.docx b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testExternalRefs.docx
new file mode 100644
index 0000000000..8b8d3c1adc
Binary files /dev/null and b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testExternalRefs.docx differ
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testFrameset.docx b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testFrameset.docx
new file mode 100644
index 0000000000..d19070fe07
Binary files /dev/null and b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testFrameset.docx differ
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testHoverAndVml.docx b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testHoverAndVml.docx
new file mode 100644
index 0000000000..2b43e1e047
Binary files /dev/null and b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testHoverAndVml.docx differ
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testInstrLink.docx b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testInstrLink.docx
new file mode 100644
index 0000000000..3b2fc9257b
Binary files /dev/null and b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testInstrLink.docx differ
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testMailMerge.docx b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testMailMerge.docx
new file mode 100644
index 0000000000..e0c8f00b03
Binary files /dev/null and b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testMailMerge.docx differ
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testSubdocument.docx b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testSubdocument.docx
new file mode 100644
index 0000000000..7bf396e35b
Binary files /dev/null and b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testSubdocument.docx differ