Skip to content

Reduce code duplication in PDF parser classes #1468

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
andreasrosdal merged 3 commits into from
Feb 16, 2026
Merged

Reduce code duplication in PDF parser classes #1468

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
eda9373
Initial plan
Copilot Feb 16, 2026
4175089
Refactor: Extract duplicated Do class and utility methods to PdfConte…
Copilot Feb 16, 2026
3f46595
Fix code review feedback: remove unnecessary fully qualified class names
Copilot Feb 16, 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
114 changes: 111 additions & 3 deletions openpdf-core/src/main/java/org/openpdf/text/pdf/parser/PdfContentStreamHandler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,17 +41,25 @@
*/
package org.openpdf.text.pdf.parser;

import org.openpdf.text.ExceptionConverter;
import org.openpdf.text.error_messages.MessageLocalization;
import org.openpdf.text.pdf.CMapAwareDocumentFont;
import org.openpdf.text.pdf.PdfArray;
import org.openpdf.text.pdf.PdfContentParser;
import org.openpdf.text.pdf.PdfDictionary;
import org.openpdf.text.pdf.PdfIndirectReference;
import org.openpdf.text.pdf.PdfLiteral;
import org.openpdf.text.pdf.PdfName;
import org.openpdf.text.pdf.PdfNumber;
import org.openpdf.text.pdf.PdfObject;
import org.openpdf.text.pdf.PdfReader;
import org.openpdf.text.pdf.PdfStream;
import org.openpdf.text.pdf.PdfString;
import org.openpdf.text.pdf.PdfName;
import org.openpdf.text.pdf.PdfArray;
import org.openpdf.text.pdf.PdfIndirectReference;
import org.openpdf.text.pdf.PRIndirectReference;
import org.openpdf.text.pdf.PRStream;
import org.openpdf.text.pdf.PRTokeniser;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
Expand Down Expand Up @@ -891,4 +899,104 @@
handler.popContext();
}
}

/**
* Processes PDF content stream bytes.
*
* @param contentBytes the bytes of a content stream
* @param resources the resources that come with the content stream
*/
protected void processContent(byte[] contentBytes, PdfDictionary resources) {
try {
PdfContentParser pdfContentParser = new PdfContentParser(new PRTokeniser(contentBytes));
List<PdfObject> operands = new ArrayList<>();
while (!pdfContentParser.parse(operands).isEmpty()) {
PdfLiteral operator = (PdfLiteral) operands.getLast();
invokeOperator(operator, operands, resources);
}
} catch (Exception e) {
throw new ExceptionConverter(e);
}
}

/**
* Gets the content bytes from a PdfObject, which may be a reference, a stream or an array.
* This is a utility method that can be used by subclasses and other classes in this package.
*
* @param object the object to read bytes from
* @return the content bytes
* @throws java.io.IOException if there's an error reading the content
*/
protected byte[] getContentBytesFromPdfObject(PdfObject object) throws java.io.IOException {

Check notice on line 930 in openpdf-core/src/main/java/org/openpdf/text/pdf/parser/PdfContentStreamHandler.java

View check run for this annotation

Codacy Production / Codacy Static Code Analysis

openpdf-core/src/main/java/org/openpdf/text/pdf/parser/PdfContentStreamHandler.java#L930 

Unnecessary use of fully qualified name 'java.io.IOException' due to existing import 'java.io.IOException'
return getContentBytesFromPdfObjectStatic(object);
}

/**
* Gets the content bytes from a PdfObject, which may be a reference, a stream or an array.
* This is a static utility method that can be used by any class in this package.
*
* @param object the object to read bytes from
* @return the content bytes
* @throws IOException if there's an error reading the content
*/
static byte[] getContentBytesFromPdfObjectStatic(PdfObject object) throws IOException {
switch (object.type()) {
case PdfObject.INDIRECT:
return getContentBytesFromPdfObjectStatic(PdfReader.getPdfObject(object));
case PdfObject.STREAM:
return PdfReader.getStreamBytes((PRStream) PdfReader.getPdfObject(object));
case PdfObject.ARRAY:
ByteArrayOutputStream baos = new ByteArrayOutputStream();
for (PdfObject element : ((PdfArray) object).getElements()) {
baos.write(getContentBytesFromPdfObjectStatic(element));
}
return baos.toByteArray();
default:
throw new IllegalStateException("Unsupported type: " + object.getClass().getCanonicalName());
}
}

/**
* A content operator implementation (Do) for handling XObject forms.
*/
protected class Do implements ContentOperator {

/**
* @see ContentOperator#getOperatorName()
*/
@Override
public String getOperatorName() {
return "Do";
}

@Override
public void invoke(List<PdfObject> operands, PdfContentStreamHandler handler, PdfDictionary resources) {
PdfObject firstOperand = operands.getFirst();
if (firstOperand instanceof PdfName) {
PdfName name = (PdfName) firstOperand;
PdfDictionary dictionary = resources.getAsDict(PdfName.XOBJECT);
if (dictionary == null) {
return;
}
PdfStream stream = (PdfStream) dictionary.getDirectObject(name);
PdfName subType = stream.getAsName(PdfName.SUBTYPE);
if (PdfName.FORM.equals(subType)) {
PdfDictionary resources2 = stream.getAsDict(PdfName.RESOURCES);
if (resources2 == null) {
resources2 = resources;
}

byte[] data;
try {
data = handler.getContentBytesFromPdfObject(stream);
} catch (IOException ex) {
throw new ExceptionConverter(ex);
}
new PushGraphicsState().invoke(operands, handler, resources);
handler.processContent(data, resources2);
new PopGraphicsState().invoke(operands, handler, resources);
}
}
}
}
}
75 changes: 1 addition & 74 deletions openpdf-core/src/main/java/org/openpdf/text/pdf/parser/PdfContentTextExtractor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,7 @@ public PdfContentTextExtractor(TextAssembler renderListener) {
@Override
protected void installDefaultOperators() {
super.installDefaultOperators();
registerContentOperator(new Do());
registerContentOperator(this.new Do());
}

void popContext() {
Expand Down Expand Up @@ -149,77 +149,4 @@ public String getResultantText() {
}
return res.toString().trim();
}

private class Do implements ContentOperator {

/**
* @see ContentOperator#getOperatorName()
*/
@Override
public String getOperatorName() {
return "Do";
}

@Override
public void invoke(List<PdfObject> operands, PdfContentStreamHandler handler, PdfDictionary resources) {
PdfObject firstOperand = operands.get(0);
if (firstOperand instanceof PdfName) {
PdfName name = (PdfName) firstOperand;
PdfDictionary dictionary = resources.getAsDict(PdfName.XOBJECT);
if (dictionary == null) {
return;
}
PdfStream stream = (PdfStream) dictionary.getDirectObject(name);
PdfName subType = stream.getAsName(PdfName.SUBTYPE);
if (PdfName.FORM.equals(subType)) {
PdfDictionary resources2 = stream.getAsDict(PdfName.RESOURCES);
if (resources2 == null) {
resources2 = resources;
}

byte[] data;
try {
data = getContentBytesFromPdfObject(stream);
} catch (IOException ex) {
throw new ExceptionConverter(ex);
}
new PushGraphicsState().invoke(operands, handler, resources);
processContent(data, resources2);
new PopGraphicsState().invoke(operands, handler, resources);
}
}

}

private void processContent(byte[] contentBytes, PdfDictionary resources) {
try {
PdfContentParser pdfContentParser = new PdfContentParser(new PRTokeniser(contentBytes));
List<PdfObject> operands = new ArrayList<>();
while (!pdfContentParser.parse(operands).isEmpty()) {
PdfLiteral operator = (PdfLiteral) operands.get(operands.size() - 1);
invokeOperator(operator, operands, resources);
}
} catch (Exception e) {
throw new ExceptionConverter(e);
}
}


private byte[] getContentBytesFromPdfObject(PdfObject object) throws IOException {
switch (object.type()) {
case PdfObject.INDIRECT:
return getContentBytesFromPdfObject(PdfReader.getPdfObject(object));
case PdfObject.STREAM:
return PdfReader.getStreamBytes((PRStream) PdfReader.getPdfObject(object));
case PdfObject.ARRAY:
ByteArrayOutputStream baos = new ByteArrayOutputStream();
for (PdfObject element : ((PdfArray) object).getElements()) {
baos.write(getContentBytesFromPdfObject(element));
}
return baos.toByteArray();
default:
throw new IllegalStateException("Unsupported type: " + object.getClass().getCanonicalName());
}
}
}
}
75 changes: 1 addition & 74 deletions openpdf-core/src/main/java/org/openpdf/text/pdf/parser/PdfContentTextLocator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@ public PdfContentTextLocator(TextAssembler renderListener, String pattern, int p
@Override
protected void installDefaultOperators() {
super.installDefaultOperators();
registerContentOperator(new Do());
registerContentOperator(this.new Do());
}

void popContext() {
Expand Down Expand Up @@ -167,77 +167,4 @@ public String getResultantText() {
public ArrayList<MatchedPattern> getMatchedPatterns() {
return this.accumulator;
}

private class Do implements ContentOperator {

/**
* @see ContentOperator#getOperatorName()
*/
@Override
public String getOperatorName() {
return "Do";
}

@Override
public void invoke(List<PdfObject> operands, PdfContentStreamHandler handler, PdfDictionary resources) {
PdfObject firstOperand = operands.getFirst();
if (firstOperand instanceof PdfName) {
PdfName name = (PdfName) firstOperand;
PdfDictionary dictionary = resources.getAsDict(PdfName.XOBJECT);
if (dictionary == null) {
return;
}
PdfStream stream = (PdfStream) dictionary.getDirectObject(name);
PdfName subType = stream.getAsName(PdfName.SUBTYPE);
if (PdfName.FORM.equals(subType)) {
PdfDictionary resources2 = stream.getAsDict(PdfName.RESOURCES);
if (resources2 == null) {
resources2 = resources;
}

byte[] data;
try {
data = getContentBytesFromPdfObject(stream);
} catch (IOException ex) {
throw new ExceptionConverter(ex);
}
new PushGraphicsState().invoke(operands, handler, resources);
processContent(data, resources2);
new PopGraphicsState().invoke(operands, handler, resources);
}
}

}

private void processContent(byte[] contentBytes, PdfDictionary resources) {
try {
PdfContentParser pdfContentParser = new PdfContentParser(new PRTokeniser(contentBytes));
List<PdfObject> operands = new ArrayList<>();
while (!pdfContentParser.parse(operands).isEmpty()) {
PdfLiteral operator = (PdfLiteral) operands.getLast();
invokeOperator(operator, operands, resources);
}
} catch (Exception e) {
throw new ExceptionConverter(e);
}
}


private byte[] getContentBytesFromPdfObject(PdfObject object) throws IOException {
switch (object.type()) {
case PdfObject.INDIRECT:
return getContentBytesFromPdfObject(PdfReader.getPdfObject(object));
case PdfObject.STREAM:
return PdfReader.getStreamBytes((PRStream) PdfReader.getPdfObject(object));
case PdfObject.ARRAY:
ByteArrayOutputStream baos = new ByteArrayOutputStream();
for (PdfObject element : ((PdfArray) object).getElements()) {
baos.write(getContentBytesFromPdfObject(element));
}
return baos.toByteArray();
default:
throw new IllegalStateException("Unsupported type: " + object.getClass().getCanonicalName());
}
}
}
}
27 changes: 1 addition & 26 deletions openpdf-core/src/main/java/org/openpdf/text/pdf/parser/PdfTextLocator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,32 +138,7 @@ private byte[] getContentBytesForPage(int pageNum) throws IOException {
* @throws IOException
*/
private byte[] getContentBytesFromContentObject(PdfObject contentObject) throws IOException {
final byte[] result;
switch (contentObject.type()) {
case PdfObject.INDIRECT:
PRIndirectReference ref = (PRIndirectReference) contentObject;
PdfObject directObject = PdfReader.getPdfObject(ref);
result = getContentBytesFromContentObject(directObject);
break;
case PdfObject.STREAM:
PRStream stream = (PRStream) PdfReader.getPdfObject(contentObject);
result = PdfReader.getStreamBytes(stream);
break;
case PdfObject.ARRAY:
// Stitch together all content before calling processContent(),
// because
// processContent() resets state.
ByteArrayOutputStream allBytes = new ByteArrayOutputStream();
PdfArray contentArray = (PdfArray) contentObject;
for (PdfObject pdfObject : contentArray.getElements()) {
allBytes.write(getContentBytesFromContentObject(pdfObject));
}
result = allBytes.toByteArray();
break;
default:
throw new IllegalStateException("Unable to handle Content of type " + contentObject.getClass());
}
return result;
return PdfContentStreamHandler.getContentBytesFromPdfObjectStatic(contentObject);
}

/**
Expand Down
Loading