mirror of
https://github.com/Frooodle/Stirling-PDF.git
synced 2026-02-17 13:52:14 +01:00
refactor: Replace manual resource handling with try-with-resources (#4593)
# Description of Changes
Explanation on try-with-resource:
> Many resources in Java need be closed after they have been used. If
they are not, the garbage collector cannot reclaim the resources'
memory, and they are still considered to be in use by the operating
system. Such resources are considered to be leaked, which can lead to
performance issues.
>
> Java 7 introduced the try-with-resources statement, which guarantees
that the resource in question will be closed.
>
> try (InputStream input = Files.newInputStream(path)) {
> // "input" will be closed after the execution of this block
> }
>
> This syntax is safer than the traditional method using try, catch, and
finally and hence should be preferred.
https://rules.sonarsource.com/java/tag/java8/RSPEC-2093/
<!--
Please provide a summary of the changes, including:
- What was changed
- Why the change was made
- Any challenges encountered
Closes #(issue_number)
-->
---
## Checklist
### General
- [ ] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [ ] I have read the [Stirling-PDF Developer
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md)
(if applicable)
- [ ] I have read the [How to add new languages to
Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md)
(if applicable)
- [ ] I have performed a self-review of my own code
- [ ] My changes generate no new warnings
### Documentation
- [ ] I have updated relevant docs on [Stirling-PDF's doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
(if functionality has heavily changed)
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)
### UI Changes (if applicable)
- [ ] Screenshots or videos demonstrating the UI changes are attached
(e.g., as comments or direct attachments in the PR)
### Testing (if applicable)
- [ ] I have tested my changes locally. Refer to the [Testing
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md#6-testing)
for more details.
---------
Signed-off-by: Balázs Szücs <bszucs1209@gmail.com>
This commit is contained in:
Balázs Szücs
GitHub
@@ -3,16 +3,22 @@ package stirling.software.SPDF.Factories;
|
||||
import org.springframework.stereotype.Component;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import lombok.RequiredArgsConstructor;
|
||||
|
||||
import stirling.software.common.model.api.misc.HighContrastColorCombination;
|
||||
import stirling.software.common.model.api.misc.ReplaceAndInvert;
|
||||
import stirling.software.common.util.TempFileManager;
|
||||
import stirling.software.common.util.misc.ColorSpaceConversionStrategy;
|
||||
import stirling.software.common.util.misc.CustomColorReplaceStrategy;
|
||||
import stirling.software.common.util.misc.InvertFullColorStrategy;
|
||||
import stirling.software.common.util.misc.ReplaceAndInvertColorStrategy;
|
||||
|
||||
@Component
|
||||
@RequiredArgsConstructor
|
||||
public class ReplaceAndInvertColorFactory {
|
||||
|
||||
private final TempFileManager tempFileManager;
|
||||
|
||||
public ReplaceAndInvertColorStrategy replaceAndInvert(
|
||||
MultipartFile file,
|
||||
ReplaceAndInvert replaceAndInvertOption,
|
||||
@@ -30,7 +36,7 @@ public class ReplaceAndInvertColorFactory {
|
||||
highContrastColorCombination);
|
||||
case FULL_INVERSION -> new InvertFullColorStrategy(file, replaceAndInvertOption);
|
||||
case COLOR_SPACE_CONVERSION ->
|
||||
new ColorSpaceConversionStrategy(file, replaceAndInvertOption);
|
||||
new ColorSpaceConversionStrategy(file, replaceAndInvertOption, tempFileManager);
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,14 +11,20 @@ import org.springframework.web.multipart.MultipartFile;
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
|
||||
import lombok.RequiredArgsConstructor;
|
||||
|
||||
import stirling.software.common.model.api.PDFFile;
|
||||
import stirling.software.common.util.PDFToFile;
|
||||
import stirling.software.common.util.TempFileManager;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Convert", description = "Convert APIs")
|
||||
@RequestMapping("/api/v1/convert")
|
||||
@RequiredArgsConstructor
|
||||
public class ConvertPDFToHtml {
|
||||
|
||||
private final TempFileManager tempFileManager;
|
||||
|
||||
@PostMapping(consumes = MediaType.MULTIPART_FORM_DATA_VALUE, value = "/pdf/html")
|
||||
@Operation(
|
||||
summary = "Convert PDF to HTML",
|
||||
@@ -26,7 +32,7 @@ public class ConvertPDFToHtml {
|
||||
"This endpoint converts a PDF file to HTML format. Input:PDF Output:HTML Type:SISO")
|
||||
public ResponseEntity<byte[]> processPdfToHTML(@ModelAttribute PDFFile file) throws Exception {
|
||||
MultipartFile inputFile = file.getFileInput();
|
||||
PDFToFile pdfToFile = new PDFToFile();
|
||||
PDFToFile pdfToFile = new PDFToFile(tempFileManager);
|
||||
return pdfToFile.processPdfToHtml(inputFile);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -24,6 +24,7 @@ import stirling.software.common.model.api.PDFFile;
|
||||
import stirling.software.common.service.CustomPDFDocumentFactory;
|
||||
import stirling.software.common.util.GeneralUtils;
|
||||
import stirling.software.common.util.PDFToFile;
|
||||
import stirling.software.common.util.TempFileManager;
|
||||
import stirling.software.common.util.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@@ -33,6 +34,7 @@ import stirling.software.common.util.WebResponseUtils;
|
||||
public class ConvertPDFToOffice {
|
||||
|
||||
private final CustomPDFDocumentFactory pdfDocumentFactory;
|
||||
private final TempFileManager tempFileManager;
|
||||
|
||||
@PostMapping(consumes = MediaType.MULTIPART_FORM_DATA_VALUE, value = "/pdf/presentation")
|
||||
@Operation(
|
||||
@@ -45,7 +47,7 @@ public class ConvertPDFToOffice {
|
||||
throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
String outputFormat = request.getOutputFormat();
|
||||
PDFToFile pdfToFile = new PDFToFile();
|
||||
PDFToFile pdfToFile = new PDFToFile(tempFileManager);
|
||||
return pdfToFile.processPdfToOfficeFormat(inputFile, outputFormat, "impress_pdf_import");
|
||||
}
|
||||
|
||||
@@ -70,7 +72,7 @@ public class ConvertPDFToOffice {
|
||||
MediaType.TEXT_PLAIN);
|
||||
}
|
||||
} else {
|
||||
PDFToFile pdfToFile = new PDFToFile();
|
||||
PDFToFile pdfToFile = new PDFToFile(tempFileManager);
|
||||
return pdfToFile.processPdfToOfficeFormat(inputFile, outputFormat, "writer_pdf_import");
|
||||
}
|
||||
}
|
||||
@@ -85,7 +87,7 @@ public class ConvertPDFToOffice {
|
||||
throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
String outputFormat = request.getOutputFormat();
|
||||
PDFToFile pdfToFile = new PDFToFile();
|
||||
PDFToFile pdfToFile = new PDFToFile(tempFileManager);
|
||||
return pdfToFile.processPdfToOfficeFormat(inputFile, outputFormat, "writer_pdf_import");
|
||||
}
|
||||
|
||||
@@ -98,7 +100,7 @@ public class ConvertPDFToOffice {
|
||||
public ResponseEntity<byte[]> processPdfToXML(@ModelAttribute PDFFile file) throws Exception {
|
||||
MultipartFile inputFile = file.getFileInput();
|
||||
|
||||
PDFToFile pdfToFile = new PDFToFile();
|
||||
PDFToFile pdfToFile = new PDFToFile(tempFileManager);
|
||||
return pdfToFile.processPdfToOfficeFormat(inputFile, "xml", "writer_pdf_import");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -116,101 +116,82 @@ public class OCRController {
|
||||
|
||||
// Use try-with-resources for proper temp file management
|
||||
try (TempFile tempInputFile = new TempFile(tempFileManager, ".pdf");
|
||||
TempFile tempOutputFile = new TempFile(tempFileManager, ".pdf")) {
|
||||
TempFile tempOutputFile = new TempFile(tempFileManager, ".pdf");
|
||||
TempFile sidecarTextFile = sidecar ? new TempFile(tempFileManager, ".txt") : null) {
|
||||
|
||||
inputFile.transferTo(tempInputFile.getFile());
|
||||
|
||||
TempFile sidecarTextFile = null;
|
||||
// Use OCRmyPDF if available (no fallback - error if it fails)
|
||||
if (isOcrMyPdfEnabled()) {
|
||||
processWithOcrMyPdf(
|
||||
selectedLanguages,
|
||||
sidecar,
|
||||
deskew,
|
||||
clean,
|
||||
cleanFinal,
|
||||
ocrType,
|
||||
ocrRenderType,
|
||||
removeImagesAfter,
|
||||
tempInputFile.getPath(),
|
||||
tempOutputFile.getPath(),
|
||||
sidecarTextFile != null ? sidecarTextFile.getPath() : null);
|
||||
log.info("OCRmyPDF processing completed successfully");
|
||||
}
|
||||
// Use Tesseract only if OCRmyPDF is not available
|
||||
else if (isTesseractEnabled()) {
|
||||
processWithTesseract(
|
||||
selectedLanguages,
|
||||
ocrType,
|
||||
tempInputFile.getPath(),
|
||||
tempOutputFile.getPath());
|
||||
log.info("Tesseract processing completed successfully");
|
||||
} else {
|
||||
throw ExceptionUtils.createOcrToolsUnavailableException();
|
||||
}
|
||||
|
||||
try {
|
||||
// Use OCRmyPDF if available (no fallback - error if it fails)
|
||||
if (isOcrMyPdfEnabled()) {
|
||||
if (sidecar) {
|
||||
sidecarTextFile = new TempFile(tempFileManager, ".txt");
|
||||
}
|
||||
// Read the processed PDF file
|
||||
byte[] pdfBytes = Files.readAllBytes(tempOutputFile.getPath());
|
||||
|
||||
processWithOcrMyPdf(
|
||||
selectedLanguages,
|
||||
sidecar,
|
||||
deskew,
|
||||
clean,
|
||||
cleanFinal,
|
||||
ocrType,
|
||||
ocrRenderType,
|
||||
removeImagesAfter,
|
||||
tempInputFile.getPath(),
|
||||
tempOutputFile.getPath(),
|
||||
sidecarTextFile != null ? sidecarTextFile.getPath() : null);
|
||||
log.info("OCRmyPDF processing completed successfully");
|
||||
}
|
||||
// Use Tesseract only if OCRmyPDF is not available
|
||||
else if (isTesseractEnabled()) {
|
||||
processWithTesseract(
|
||||
selectedLanguages,
|
||||
ocrType,
|
||||
tempInputFile.getPath(),
|
||||
tempOutputFile.getPath());
|
||||
log.info("Tesseract processing completed successfully");
|
||||
} else {
|
||||
throw ExceptionUtils.createOcrToolsUnavailableException();
|
||||
}
|
||||
// Return the OCR processed PDF as a response
|
||||
String outputFilename =
|
||||
GeneralUtils.removeExtension(
|
||||
Filenames.toSimpleFileName(inputFile.getOriginalFilename()))
|
||||
+ "_OCR.pdf";
|
||||
|
||||
// Read the processed PDF file
|
||||
byte[] pdfBytes = Files.readAllBytes(tempOutputFile.getPath());
|
||||
|
||||
// Return the OCR processed PDF as a response
|
||||
String outputFilename =
|
||||
if (sidecar && sidecarTextFile != null) {
|
||||
// Create a zip file containing both the PDF and the text file
|
||||
String outputZipFilename =
|
||||
GeneralUtils.removeExtension(
|
||||
Filenames.toSimpleFileName(inputFile.getOriginalFilename()))
|
||||
+ "_OCR.pdf";
|
||||
+ "_OCR.zip";
|
||||
|
||||
if (sidecar && sidecarTextFile != null) {
|
||||
// Create a zip file containing both the PDF and the text file
|
||||
String outputZipFilename =
|
||||
GeneralUtils.removeExtension(
|
||||
Filenames.toSimpleFileName(
|
||||
inputFile.getOriginalFilename()))
|
||||
+ "_OCR.zip";
|
||||
try (TempFile tempZipFile = new TempFile(tempFileManager, ".zip");
|
||||
ZipOutputStream zipOut =
|
||||
new ZipOutputStream(Files.newOutputStream(tempZipFile.getPath()))) {
|
||||
|
||||
try (TempFile tempZipFile = new TempFile(tempFileManager, ".zip");
|
||||
ZipOutputStream zipOut =
|
||||
new ZipOutputStream(
|
||||
Files.newOutputStream(tempZipFile.getPath()))) {
|
||||
// Add PDF file to the zip
|
||||
ZipEntry pdfEntry = new ZipEntry(outputFilename);
|
||||
zipOut.putNextEntry(pdfEntry);
|
||||
zipOut.write(pdfBytes);
|
||||
zipOut.closeEntry();
|
||||
|
||||
// Add PDF file to the zip
|
||||
ZipEntry pdfEntry = new ZipEntry(outputFilename);
|
||||
zipOut.putNextEntry(pdfEntry);
|
||||
zipOut.write(pdfBytes);
|
||||
zipOut.closeEntry();
|
||||
// Add text file to the zip
|
||||
ZipEntry txtEntry = new ZipEntry(outputFilename.replace(".pdf", ".txt"));
|
||||
zipOut.putNextEntry(txtEntry);
|
||||
Files.copy(sidecarTextFile.getPath(), zipOut);
|
||||
zipOut.closeEntry();
|
||||
|
||||
// Add text file to the zip
|
||||
ZipEntry txtEntry = new ZipEntry(outputFilename.replace(".pdf", ".txt"));
|
||||
zipOut.putNextEntry(txtEntry);
|
||||
Files.copy(sidecarTextFile.getPath(), zipOut);
|
||||
zipOut.closeEntry();
|
||||
zipOut.finish();
|
||||
|
||||
zipOut.finish();
|
||||
byte[] zipBytes = Files.readAllBytes(tempZipFile.getPath());
|
||||
|
||||
byte[] zipBytes = Files.readAllBytes(tempZipFile.getPath());
|
||||
|
||||
// Return the zip file containing both the PDF and the text file
|
||||
return WebResponseUtils.bytesToWebResponse(
|
||||
zipBytes, outputZipFilename, MediaType.APPLICATION_OCTET_STREAM);
|
||||
}
|
||||
} else {
|
||||
// Return the OCR processed PDF as a response
|
||||
return WebResponseUtils.bytesToWebResponse(pdfBytes, outputFilename);
|
||||
}
|
||||
|
||||
} finally {
|
||||
// Clean up sidecar temp file if created
|
||||
if (sidecarTextFile != null) {
|
||||
try {
|
||||
sidecarTextFile.close();
|
||||
} catch (Exception e) {
|
||||
log.warn("Failed to close sidecar temp file", e);
|
||||
}
|
||||
// Return the zip file containing both the PDF and the text file
|
||||
return WebResponseUtils.bytesToWebResponse(
|
||||
zipBytes, outputZipFilename, MediaType.APPLICATION_OCTET_STREAM);
|
||||
}
|
||||
} else {
|
||||
// Return the OCR processed PDF as a response
|
||||
return WebResponseUtils.bytesToWebResponse(pdfBytes, outputFilename);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,14 +11,20 @@ import org.springframework.web.multipart.MultipartFile;
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
|
||||
import lombok.RequiredArgsConstructor;
|
||||
|
||||
import stirling.software.common.model.api.PDFFile;
|
||||
import stirling.software.common.util.PDFToFile;
|
||||
import stirling.software.common.util.TempFileManager;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Convert", description = "Convert APIs")
|
||||
@RequestMapping("/api/v1/convert")
|
||||
@RequiredArgsConstructor
|
||||
public class ConvertPDFToMarkdown {
|
||||
|
||||
private final TempFileManager tempFileManager;
|
||||
|
||||
@PostMapping(consumes = MediaType.MULTIPART_FORM_DATA_VALUE, value = "/pdf/markdown")
|
||||
@Operation(
|
||||
summary = "Convert PDF to Markdown",
|
||||
@@ -27,7 +33,7 @@ public class ConvertPDFToMarkdown {
|
||||
public ResponseEntity<byte[]> processPdfToMarkdown(@ModelAttribute PDFFile file)
|
||||
throws Exception {
|
||||
MultipartFile inputFile = file.getFileInput();
|
||||
PDFToFile pdfToFile = new PDFToFile();
|
||||
PDFToFile pdfToFile = new PDFToFile(tempFileManager);
|
||||
return pdfToFile.processPdfToMarkdown(inputFile);
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user