Skip to content
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

Jump to bottom

Bump org.apache.pdfbox:pdfbox from 2.0.29 to 3.0.1 #1378

Merged
merged 2 commits into from
Dec 18, 2023
Merged

Bump org.apache.pdfbox:pdfbox from 2.0.29 to 3.0.1 #1378

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
ce9052a
Bump org.apache.pdfbox:pdfbox from 2.0.29 to 3.0.1
dependabot[bot] Dec 11, 2023
e19bf5e
refactoring code to upgraded dependency
MohabMohie Dec 18, 2023
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
2 changes: 1 addition & 1 deletion pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -288,7 +288,7 @@
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>2.0.29</version>
<version>3.0.1</version>
</dependency>

<!-- REST ASSURED -->
Expand Down
57 changes: 20 additions & 37 deletions src/main/java/com/shaft/tools/io/PdfFileManager.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
import com.shaft.tools.io.internal.FailureReporter;
import org.apache.commons.io.FileUtils;
import org.apache.pdfbox.cos.COSDocument;
import org.apache.pdfbox.io.RandomAccessBufferedFileInputStream;
import org.apache.pdfbox.io.RandomAccessReadBufferedFile;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
Expand All @@ -17,7 +17,7 @@
public class PdfFileManager {

private final File file;
private RandomAccessBufferedFileInputStream stream = null;
private RandomAccessReadBufferedFile stream = null;
private PDFParser parser = null;
private COSDocument cosDoc = null;
private PDFTextStripper strip = null;
Expand Down Expand Up @@ -57,22 +57,17 @@ public String readFileContent() {
*/
public static String readFileContent(String relativeFilePath, boolean... deleteFileAfterReading) {
if (FileActions.getInstance().doesFileExist(relativeFilePath)) {
try {
var randomAccessBufferedFileInputStream = new RandomAccessBufferedFileInputStream(new File(FileActions.getInstance().getAbsolutePath(relativeFilePath)));
var pdfParser = new PDFParser(randomAccessBufferedFileInputStream);
pdfParser.parse();
try (var pdfParser = new PDFParser(new RandomAccessReadBufferedFile(new File(FileActions.getInstance().getAbsolutePath(relativeFilePath)))).parse()) {
var pdfTextStripper = new PDFTextStripper();
pdfTextStripper.setSortByPosition(true);
var fileContent = pdfTextStripper.getText(new PDDocument(pdfParser.getDocument()));
randomAccessBufferedFileInputStream.close();

if (deleteFileAfterReading != null
&& deleteFileAfterReading.length > 0
&& deleteFileAfterReading[0]) {
FileActions.getInstance().deleteFile(relativeFilePath);
}
return fileContent;
} catch (java.io.IOException rootCauseException) {
} catch (IOException rootCauseException) {
FailureReporter.fail(PdfFileManager.class, "Failed to read this PDF file [" + relativeFilePath + "].", rootCauseException);
}

Expand All @@ -96,7 +91,6 @@ public String readPDFContentFromDownloadedPDF(int startPageNumber, int endPageNu

stream = readFileInputStream(file);
parser = parseStreamDocument(stream);

cosDoc = getParsedDocument(parser);
String content = getPdfText(cosDoc, startPageNumber, endPageNumber);
closeStreamAndDeleteFile(file, stream, deleteFileAfterValidationStatus);
Expand All @@ -105,27 +99,24 @@ public String readPDFContentFromDownloadedPDF(int startPageNumber, int endPageNu
}

public String readPDFContentFromDownloadedPDF(DeleteFileAfterValidationStatus deleteFileAfterValidationStatus) {

stream = readFileInputStream(file);
parser = parseStreamDocument(stream);

cosDoc = getParsedDocument(parser);
String content = getPdfText(cosDoc);
closeStreamAndDeleteFile(file, stream, deleteFileAfterValidationStatus);

return content;
}

private RandomAccessBufferedFileInputStream readFileInputStream(File file) {
private RandomAccessReadBufferedFile readFileInputStream(File file) {
try {
stream = new RandomAccessBufferedFileInputStream(file);
stream = new RandomAccessReadBufferedFile(file);
} catch (IOException rootCauseException) {
FailureReporter.fail(PdfFileManager.class, "Couldn't read the data from the provided file [" + file + "].", rootCauseException);
}
return stream;
}

private PDFParser parseStreamDocument(RandomAccessBufferedFileInputStream stream) {
private PDFParser parseStreamDocument(RandomAccessReadBufferedFile stream) {
try {
parser = new PDFParser(stream);
parser.parse();
Expand All @@ -136,27 +127,23 @@ private PDFParser parseStreamDocument(RandomAccessBufferedFileInputStream stream
}

private COSDocument getParsedDocument(PDFParser parser) {
try {
cosDoc = parser.getDocument();
try (var parsedDocument = parser.parse()){
cosDoc = parsedDocument.getDocument();
} catch (IOException rootCauseException) {
FailureReporter.fail(PdfFileManager.class, "Couldn't get the document that was parsed. Check that the document parsed before get the document.", rootCauseException);
}
return cosDoc;
}

private String getPdfText(COSDocument cosDoc, int startPageNumber, int endPageNumber) {
try {
strip = new PDFTextStripper();
// By default, text extraction is done in the same sequence as the text in the
// PDF page content stream. PDF is a graphic format, not a text format, and
// unlike HTML, it has no requirements that text one on page be rendered in a
// certain order. The order is the one that was determined by the software that
// created the PDF
// To get text sorted from left to right and top to bottom
strip.setSortByPosition(true);
} catch (IOException rootCauseException) {
FailureReporter.fail(PdfFileManager.class, "Couldn't load PDFTextStripper properties.", rootCauseException);
}
strip = new PDFTextStripper();
// By default, text extraction is done in the same sequence as the text in the
// PDF page content stream. PDF is a graphic format, not a text format, and
// unlike HTML, it has no requirements that text one on page be rendered in a
// certain order. The order is the one that was determined by the software that
// created the PDF
// To get text sorted from left to right and top to bottom
strip.setSortByPosition(true);

strip.setStartPage(startPageNumber);
strip.setEndPage(endPageNumber);
Expand All @@ -172,12 +159,8 @@ private String getPdfText(COSDocument cosDoc, int startPageNumber, int endPageNu
}

private String getPdfText(COSDocument cosDoc) {
try {
strip = new PDFTextStripper();
strip.setSortByPosition(true);
} catch (IOException rootCauseException) {
FailureReporter.fail(PdfFileManager.class, "Couldn't load PDFTextStripper properties.", rootCauseException);
}
strip = new PDFTextStripper();
strip.setSortByPosition(true);

PDDocument pdDoc = new PDDocument(cosDoc);

Expand All @@ -190,7 +173,7 @@ private String getPdfText(COSDocument cosDoc) {
return content;
}

private void closeStreamAndDeleteFile(File file, RandomAccessBufferedFileInputStream stream,
private void closeStreamAndDeleteFile(File file, RandomAccessReadBufferedFile stream,
DeleteFileAfterValidationStatus deleteFileAfterValidation) {
try {
stream.close();
Expand Down
Loading