Skip to content

TIKA-4707 -- rm dom parsers for docx/pptx #2747

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tballison merged 2 commits into from
Apr 9, 2026
Merged

TIKA-4707 -- rm dom parsers for docx/pptx #2747

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
85c74b0
TIKA-4707 -- rm dom parsers for docx/pptx
tballison Apr 7, 2026
e4d7eb3
TIKA-4707 -- rm poi-ooxml-lite
tballison Apr 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .../tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,6 +93,12 @@
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<exclusions>
<exclusion>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml-lite</artifactId>
</exclusion>
</exclusions>
</dependency>
<!-- needed by jackcess -->
<dependency>
Expand Down
37 changes: 0 additions & 37 deletions ...r-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParserConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,9 +32,6 @@ public class OfficeParserConfig implements Serializable {
private boolean includeSlideMasterContent = true;
private boolean concatenatePhoneticRuns = true;

private boolean useSAXDocxExtractor = false;
private boolean useSAXPptxExtractor = false;

private boolean preferAlternateContentChoice = true;

private boolean writeSelectHeadersInBody = false;
Expand Down Expand Up @@ -142,40 +139,6 @@ public void setIncludeHeadersAndFooters(boolean includeHeadersAndFooters) {
this.includeHeadersAndFooters = includeHeadersAndFooters;
}

public boolean isUseSAXDocxExtractor() {
return useSAXDocxExtractor;
}

/**
* Use the experimental SAX-based streaming DOCX parser?
* If set to <code>false</code>, the classic parser will be used; if <code>true</code>,
* the new experimental parser will be used.
* <p/>
* Default: <code>false</code> (classic DOM parser)
*
* @param useSAXDocxExtractor
*/
public void setUseSAXDocxExtractor(boolean useSAXDocxExtractor) {
this.useSAXDocxExtractor = useSAXDocxExtractor;
}

public boolean isUseSAXPptxExtractor() {
return useSAXPptxExtractor;
}

/**
* Use the experimental SAX-based streaming DOCX parser?
* If set to <code>false</code>, the classic parser will be used; if <code>true</code>,
* the new experimental parser will be used.
* <p/>
* Default: <code>false</code> (classic DOM parser)
*
* @param useSAXPptxExtractor
*/
public void setUseSAXPptxExtractor(boolean useSAXPptxExtractor) {
this.useSAXPptxExtractor = useSAXPptxExtractor;
}

/**
* In OOXML, {@code mc:AlternateContent} wraps {@code mc:Choice} (newer/richer
* rendering, e.g. DrawingML text boxes) and {@code mc:Fallback} (degraded VML
Expand Down
36 changes: 15 additions & 21 deletions ...t-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,8 +30,6 @@
import java.util.Map;
import java.util.Set;

import org.apache.poi.ooxml.POIXMLDocument;
import org.apache.poi.ooxml.extractor.POIXMLTextExtractor;
import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.openxml4j.opc.PackagePart;
Expand All @@ -45,7 +43,6 @@
import org.apache.poi.poifs.filesystem.Ole10NativeException;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.xssf.usermodel.XSSFRelation;
import org.apache.poi.xwpf.usermodel.XWPFRelation;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.AttributesImpl;
Expand Down Expand Up @@ -93,9 +90,14 @@ public abstract class AbstractOOXMLExtractor implements OOXMLExtractor {
static final String RELATION_ALTERNATE_FORMAT_CHUNK =
"http://schemas.openxmlformats.org/officeDocument/2006/relationships/aFChunk";

private static final String PACK_OBJECT_REL_TYPE =
"http://schemas.openxmlformats.org/officeDocument/2006/relationships/package";
private static final String OLE_OBJECT_REL_TYPE =
"http://schemas.openxmlformats.org/officeDocument/2006/relationships/oleObject";

protected static final String[] EMBEDDED_RELATIONSHIPS =
new String[]{RELATION_AUDIO, PackageRelationshipTypes.IMAGE_PART,
POIXMLDocument.PACK_OBJECT_REL_TYPE, PackageRelationshipTypes.CORE_DOCUMENT,
PACK_OBJECT_REL_TYPE, PackageRelationshipTypes.CORE_DOCUMENT,
RELATION_DIAGRAM_DATA};
private static final String TYPE_OLE_OBJECT =
"application/vnd.openxmlformats-officedocument.oleObject";
Expand All @@ -104,30 +106,23 @@ public abstract class AbstractOOXMLExtractor implements OOXMLExtractor {
private final EmbeddedDocumentExtractor embeddedExtractor;
private final ParseContext context;
protected OfficeParserConfig config;
protected POIXMLTextExtractor extractor;
protected OPCPackage opcPackage;

public AbstractOOXMLExtractor(ParseContext context, POIXMLTextExtractor extractor) {
public AbstractOOXMLExtractor(ParseContext context, OPCPackage opcPackage) {
this.context = context;
this.extractor = extractor;
this.opcPackage = opcPackage;
embeddedExtractor = EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);

// This has already been set by OOXMLParser's call to configure()
// We can rely on this being non-null.
this.config = context.get(OfficeParserConfig.class);
}

/**
* @see org.apache.tika.parser.microsoft.ooxml.OOXMLExtractor#getDocument()
*/
public POIXMLDocument getDocument() {
return (POIXMLDocument) extractor.getDocument();
}

/**
* @see org.apache.tika.parser.microsoft.ooxml.OOXMLExtractor#getMetadataExtractor()
*/
public MetadataExtractor getMetadataExtractor() {
return new MetadataExtractor(extractor);
return new SAXBasedMetadataExtractor(opcPackage, context);
}

ParseContext getParseContext() {
Expand Down Expand Up @@ -173,7 +168,6 @@ protected String getJustFileName(String desc) {

private void handleThumbnail(ContentHandler handler, Metadata metadata) throws SAXException {
try {
OPCPackage opcPackage = extractor.getPackage();
for (PackageRelationship rel : opcPackage
.getRelationshipsByType(PackageRelationshipTypes.THUMBNAIL)) {
PackagePart tPart = opcPackage.getPart(rel);
Expand Down Expand Up @@ -274,7 +268,7 @@ private void handleEmbeddedPart(PackagePart source, PackageRelationship rel,
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)) {
if (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)) {
Expand All @@ -293,7 +287,7 @@ private void handleEmbeddedPart(PackagePart source, PackageRelationship rel,
}
EmbeddedPartMetadata embeddedPartMetadata = embeddedPartMetadataMap.get(rel.getId());
String type = rel.getRelationshipType();
if (POIXMLDocument.OLE_OBJECT_REL_TYPE.equals(type) &&
if (OLE_OBJECT_REL_TYPE.equals(type) &&
TYPE_OLE_OBJECT.equals(target.getContentType())) {
handleEmbeddedOLE(target, xhtml, sourceDesc + rel.getId(), parentMetadata,
embeddedPartMetadata);
Expand All @@ -308,8 +302,8 @@ private void handleEmbeddedPart(PackagePart source, PackageRelationship rel,
}
} else if (RELATION_MEDIA.equals(type) || RELATION_VIDEO.equals(type) ||
RELATION_AUDIO.equals(type) ||
POIXMLDocument.PACK_OBJECT_REL_TYPE.equals(type) ||
POIXMLDocument.OLE_OBJECT_REL_TYPE.equals(type)) {
PACK_OBJECT_REL_TYPE.equals(type) ||
OLE_OBJECT_REL_TYPE.equals(type)) {
handleEmbeddedFile(target, xhtml, sourceDesc + rel.getId(),
embeddedPartMetadata,
TikaCoreProperties.EmbeddedResourceType.ATTACHMENT);
Expand Down Expand Up @@ -566,7 +560,7 @@ protected Map<String, String> loadLinkedRelationships(PackagePart bodyPart,
Map<String, String> linkedRelationships = new HashMap<>();
try {
PackageRelationshipCollection prc =
bodyPart.getRelationshipsByType(XWPFRelation.HYPERLINK.getRelation());
bodyPart.getRelationshipsByType(PackageRelationshipTypes.HYPERLINK_PART);
for (int i = 0; i < prc.size(); i++) {
PackageRelationship pr = prc.getRelationship(i);
if (pr == null) {
Expand Down
Loading
Loading