mirror of
https://github.com/arsvendg/Stirling-PDF.git
synced 2026-07-15 11:00:47 +02:00
restore OCRMyPDF and ghostscript compression (#3846)
# Description of Changes This pull request introduces enhancements to tool dependencies, endpoint configurations, and Dockerfile packages. The changes primarily focus on adding support for new tools (Ghostscript and OCRmyPDF), improving endpoint management, and refining dependency checks. Below is a summary of the most important changes grouped by theme: ### Tool Integration and Dependency Management: * Added support for Ghostscript and OCRmyPDF in the session limits and timeout configurations (`ApplicationProperties.java`). [[1]](diffhunk://#diff-0642cd5c54d57a80f1f9c26cb26677f58778dc889cb59ebfc07b7512e74a8886R548-R549) [[2]](diffhunk://#diff-0642cd5c54d57a80f1f9c26cb26677f58778dc889cb59ebfc07b7512e74a8886R582-R589) [[3]](diffhunk://#diff-0642cd5c54d57a80f1f9c26cb26677f58778dc889cb59ebfc07b7512e74a8886R602-R603) [[4]](diffhunk://#diff-0642cd5c54d57a80f1f9c26cb26677f58778dc889cb59ebfc07b7512e74a8886R636-R643) * Updated `Processes` enum and `ProcessExecutor` logic to include Ghostscript and OCRmyPDF, enabling their session limits and timeout handling. [[1]](diffhunk://#diff-b0afb37bdac8b0f1a10aca87b0244b133ac9b05518088b6f4c6c2bf48f859fdaR87-R96) [[2]](diffhunk://#diff-b0afb37bdac8b0f1a10aca87b0244b133ac9b05518088b6f4c6c2bf48f859fdaR141-R150) [[3]](diffhunk://#diff-b0afb37bdac8b0f1a10aca87b0244b133ac9b05518088b6f4c6c2bf48f859fdaL281-R303) * Integrated Ghostscript and OCRmyPDF into the external dependency check mechanism (`ExternalAppDepConfig.java`). [[1]](diffhunk://#diff-511713d04e0545670bfb44e70e84235288e91db0ef219e423628746f28e67cfcR37-R38) [[2]](diffhunk://#diff-511713d04e0545670bfb44e70e84235288e91db0ef219e423628746f28e67cfcR114-R115) ### Endpoint Configuration Enhancements: * Improved endpoint management by introducing functional group overrides, tool group fallbacks, and alternative tool group handling (`EndpointConfiguration.java`). [[1]](diffhunk://#diff-d6f76bfe88b1a7f347c10cc6956f8e7874b66772c6ac0ac432bedd3c7e8c372dR24-R25) [[2]](diffhunk://#diff-d6f76bfe88b1a7f347c10cc6956f8e7874b66772c6ac0ac432bedd3c7e8c372dR39-R178) [[3]](diffhunk://#diff-d6f76bfe88b1a7f347c10cc6956f8e7874b66772c6ac0ac432bedd3c7e8c372dL264-R357) [[4]](diffhunk://#diff-d6f76bfe88b1a7f347c10cc6956f8e7874b66772c6ac0ac432bedd3c7e8c372dR399-R437) * Added new endpoint groups and alternatives for multi-tool endpoints like "repair," "compress-pdf," and "ocr-pdf," supporting both Ghostscript and OCRmyPDF. [[1]](diffhunk://#diff-d6f76bfe88b1a7f347c10cc6956f8e7874b66772c6ac0ac432bedd3c7e8c372dL215-L216) [[2]](diffhunk://#diff-d6f76bfe88b1a7f347c10cc6956f8e7874b66772c6ac0ac432bedd3c7e8c372dL264-R357) ### Dockerfile Updates: * Removed `qpdf` and added `unpaper` and `ocrmypdf` to the package list in `Dockerfile` and `Dockerfile.fat` to enable advanced OCR and PDF manipulation features. [[1]](diffhunk://#diff-dd2c0eb6ea5cfc6c4bd4eac30934e2d5746747af48fef6da689e85b752f39557L54) [[2]](diffhunk://#diff-dd2c0eb6ea5cfc6c4bd4eac30934e2d5746747af48fef6da689e85b752f39557R71-R75) [[3]](diffhunk://#diff-571631582b988e88c52c86960cc083b0b8fa63cf88f056f26e9e684195221c27L79-R89) ### Code Cleanup and Refactoring: * Refactored `TempFileRegistry` to improve readability by simplifying variable initialization. [[1]](diffhunk://#diff-ed08845255ade38ea6e28a959ed967957611025fb7f8f5dcf4543b5f200a5fecL12) [[2]](diffhunk://#diff-ed08845255ade38ea6e28a959ed967957611025fb7f8f5dcf4543b5f200a5fecL30-R29) * Updated `CompressController` to dynamically check tool group availability using the new endpoint configuration logic. [[1]](diffhunk://#diff-fc8dc1845d34077a089d9265521ce8c8d6104a8b79137e1de5310e30ffb0348aR50) [[2]](diffhunk://#diff-fc8dc1845d34077a089d9265521ce8c8d6104a8b79137e1de5310e30ffb0348aR65-R76) These changes collectively enhance the application's capabilities for PDF processing, improve dependency management, and streamline endpoint handling. --- ## 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/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/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/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/DeveloperGuide.md#6-testing) for more details.
This commit is contained in:
Anthony Stirling
@@ -545,6 +545,8 @@ public class ApplicationProperties {
|
||||
private int calibreSessionLimit;
|
||||
private int qpdfSessionLimit;
|
||||
private int tesseractSessionLimit;
|
||||
private int ghostscriptSessionLimit;
|
||||
private int ocrMyPdfSessionLimit;
|
||||
|
||||
public int getQpdfSessionLimit() {
|
||||
return qpdfSessionLimit > 0 ? qpdfSessionLimit : 2;
|
||||
@@ -577,6 +579,14 @@ public class ApplicationProperties {
|
||||
public int getCalibreSessionLimit() {
|
||||
return calibreSessionLimit > 0 ? calibreSessionLimit : 1;
|
||||
}
|
||||
|
||||
public int getGhostscriptSessionLimit() {
|
||||
return ghostscriptSessionLimit > 0 ? ghostscriptSessionLimit : 8;
|
||||
}
|
||||
|
||||
public int getOcrMyPdfSessionLimit() {
|
||||
return ocrMyPdfSessionLimit > 0 ? ocrMyPdfSessionLimit : 2;
|
||||
}
|
||||
}
|
||||
|
||||
@Data
|
||||
@@ -589,6 +599,8 @@ public class ApplicationProperties {
|
||||
private long calibreTimeoutMinutes;
|
||||
private long tesseractTimeoutMinutes;
|
||||
private long qpdfTimeoutMinutes;
|
||||
private long ghostscriptTimeoutMinutes;
|
||||
private long ocrMyPdfTimeoutMinutes;
|
||||
|
||||
public long getTesseractTimeoutMinutes() {
|
||||
return tesseractTimeoutMinutes > 0 ? tesseractTimeoutMinutes : 30;
|
||||
@@ -621,6 +633,14 @@ public class ApplicationProperties {
|
||||
public long getCalibreTimeoutMinutes() {
|
||||
return calibreTimeoutMinutes > 0 ? calibreTimeoutMinutes : 30;
|
||||
}
|
||||
|
||||
public long getGhostscriptTimeoutMinutes() {
|
||||
return ghostscriptTimeoutMinutes > 0 ? ghostscriptTimeoutMinutes : 30;
|
||||
}
|
||||
|
||||
public long getOcrMyPdfTimeoutMinutes() {
|
||||
return ocrMyPdfTimeoutMinutes > 0 ? ocrMyPdfTimeoutMinutes : 30;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -308,7 +308,7 @@ public class TempFileCleanupService {
|
||||
}
|
||||
|
||||
java.util.List<Path> subdirectories = new java.util.ArrayList<>();
|
||||
|
||||
|
||||
try (Stream<Path> pathStream = Files.list(directory)) {
|
||||
pathStream.forEach(
|
||||
path -> {
|
||||
@@ -347,7 +347,7 @@ public class TempFileCleanupService {
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
|
||||
for (Path subdirectory : subdirectories) {
|
||||
try {
|
||||
cleanupDirectoryStreaming(
|
||||
|
||||
@@ -84,6 +84,16 @@ public class ProcessExecutor {
|
||||
.getProcessExecutor()
|
||||
.getSessionLimit()
|
||||
.getCalibreSessionLimit();
|
||||
case GHOSTSCRIPT ->
|
||||
applicationProperties
|
||||
.getProcessExecutor()
|
||||
.getSessionLimit()
|
||||
.getGhostscriptSessionLimit();
|
||||
case OCR_MY_PDF ->
|
||||
applicationProperties
|
||||
.getProcessExecutor()
|
||||
.getSessionLimit()
|
||||
.getOcrMyPdfSessionLimit();
|
||||
};
|
||||
|
||||
long timeoutMinutes =
|
||||
@@ -128,6 +138,16 @@ public class ProcessExecutor {
|
||||
.getProcessExecutor()
|
||||
.getTimeoutMinutes()
|
||||
.getCalibreTimeoutMinutes();
|
||||
case GHOSTSCRIPT ->
|
||||
applicationProperties
|
||||
.getProcessExecutor()
|
||||
.getTimeoutMinutes()
|
||||
.getGhostscriptTimeoutMinutes();
|
||||
case OCR_MY_PDF ->
|
||||
applicationProperties
|
||||
.getProcessExecutor()
|
||||
.getTimeoutMinutes()
|
||||
.getOcrMyPdfTimeoutMinutes();
|
||||
};
|
||||
return new ProcessExecutor(semaphoreLimit, liveUpdates, timeoutMinutes);
|
||||
});
|
||||
@@ -278,7 +298,9 @@ public class ProcessExecutor {
|
||||
INSTALL_APP,
|
||||
CALIBRE,
|
||||
TESSERACT,
|
||||
QPDF
|
||||
QPDF,
|
||||
GHOSTSCRIPT,
|
||||
OCR_MY_PDF
|
||||
}
|
||||
|
||||
public class ProcessExecutorResult {
|
||||
|
||||
@@ -9,7 +9,6 @@ import java.util.Map;
|
||||
import java.util.Set;
|
||||
import java.util.concurrent.ConcurrentHashMap;
|
||||
import java.util.concurrent.ConcurrentMap;
|
||||
import java.util.concurrent.ConcurrentSkipListSet;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
import org.springframework.stereotype.Component;
|
||||
@@ -24,11 +23,10 @@ import lombok.extern.slf4j.Slf4j;
|
||||
@Component
|
||||
public class TempFileRegistry {
|
||||
|
||||
private final ConcurrentMap<Path, Instant> registeredFiles = new ConcurrentHashMap<>();
|
||||
private final Set<Path> thirdPartyTempFiles =
|
||||
Collections.newSetFromMap(new ConcurrentHashMap<>());
|
||||
private final Set<Path> tempDirectories =
|
||||
Collections.newSetFromMap(new ConcurrentHashMap<>());
|
||||
private final ConcurrentMap<Path, Instant> registeredFiles = new ConcurrentHashMap<>();
|
||||
private final Set<Path> thirdPartyTempFiles =
|
||||
Collections.newSetFromMap(new ConcurrentHashMap<>());
|
||||
private final Set<Path> tempDirectories = Collections.newSetFromMap(new ConcurrentHashMap<>());
|
||||
|
||||
/**
|
||||
* Register a temporary file with the registry.
|
||||
|
||||
Reference in New Issue
Block a user