mirror of
https://github.com/arsvendg/Stirling-PDF.git
synced 2026-07-15 02:54:06 +02:00
pipeline bug, doc bugs, auto split new URL and doc (#2906)
# Description of Changes Please provide a summary of the changes, including: - What was changed Pipeline bug where files would be processed even when incorrect format some API docs had spaces causing format issues Auto split doc now links to [stirlingpdf.com](http://stirlingpdf.com/) not github + updated old logo removed old docs not used - 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/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. --------- Co-authored-by: a <a>
This commit is contained in:
Anthony Stirling
co-authored by
a <a>
a <a>
parent
242aa5eae1
commit
0233086487
+17
-7
@@ -8,7 +8,9 @@ import java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Path;
|
||||
import java.util.ArrayList;
|
||||
import java.util.HashSet;
|
||||
import java.util.List;
|
||||
import java.util.Set;
|
||||
import java.util.zip.ZipEntry;
|
||||
import java.util.zip.ZipOutputStream;
|
||||
|
||||
@@ -41,8 +43,12 @@ import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class AutoSplitPdfController {
|
||||
|
||||
private static final String QR_CONTENT = "https://github.com/Stirling-Tools/Stirling-PDF";
|
||||
private static final String QR_CONTENT_OLD = "https://github.com/Frooodle/Stirling-PDF";
|
||||
private static final Set<String> VALID_QR_CONTENTS =
|
||||
new HashSet<>(
|
||||
Set.of(
|
||||
"https://github.com/Stirling-Tools/Stirling-PDF",
|
||||
"https://github.com/Frooodle/Stirling-PDF",
|
||||
"https://stirlingpdf.com"));
|
||||
|
||||
private final CustomPDDocumentFactory pdfDocumentFactory;
|
||||
|
||||
@@ -120,13 +126,14 @@ public class AutoSplitPdfController {
|
||||
for (int page = 0; page < document.getNumberOfPages(); ++page) {
|
||||
BufferedImage bim = pdfRenderer.renderImageWithDPI(page, 150);
|
||||
String result = decodeQRCode(bim);
|
||||
if ((QR_CONTENT.equals(result) || QR_CONTENT_OLD.equals(result)) && page != 0) {
|
||||
|
||||
boolean isValidQrCode = VALID_QR_CONTENTS.contains(result);
|
||||
log.debug("detected qr code {}, code is vale={}", result, isValidQrCode);
|
||||
if (isValidQrCode && page != 0) {
|
||||
splitDocuments.add(new PDDocument());
|
||||
}
|
||||
|
||||
if (!splitDocuments.isEmpty()
|
||||
&& !QR_CONTENT.equals(result)
|
||||
&& !QR_CONTENT_OLD.equals(result)) {
|
||||
if (!splitDocuments.isEmpty() && !isValidQrCode) {
|
||||
splitDocuments.get(splitDocuments.size() - 1).addPage(document.getPage(page));
|
||||
} else if (page == 0) {
|
||||
PDDocument firstDocument = new PDDocument();
|
||||
@@ -135,7 +142,7 @@ public class AutoSplitPdfController {
|
||||
}
|
||||
|
||||
// If duplexMode is true and current page is a divider, then skip next page
|
||||
if (duplexMode && (QR_CONTENT.equals(result) || QR_CONTENT_OLD.equals(result))) {
|
||||
if (duplexMode && isValidQrCode) {
|
||||
page++;
|
||||
}
|
||||
}
|
||||
@@ -168,6 +175,9 @@ public class AutoSplitPdfController {
|
||||
|
||||
return WebResponseUtils.bytesToWebResponse(
|
||||
data, filename + ".zip", MediaType.APPLICATION_OCTET_STREAM);
|
||||
} catch (Exception e) {
|
||||
log.error("Error in auto split", e);
|
||||
throw e;
|
||||
} finally {
|
||||
// Clean up resources
|
||||
if (document != null) {
|
||||
|
||||
+1
-1
@@ -52,7 +52,7 @@ public class ExtractImagesController {
|
||||
@Operation(
|
||||
summary = "Extract images from a PDF file",
|
||||
description =
|
||||
"This endpoint extracts images from a given PDF file and returns them in a zip file. Users can specify the output image format. Input: PDF Output: IMAGE/ZIP Type: SIMO")
|
||||
"This endpoint extracts images from a given PDF file and returns them in a zip file. Users can specify the output image format. Input:PDF Output:IMAGE/ZIP Type:SIMO")
|
||||
public ResponseEntity<byte[]> extractImages(@ModelAttribute PDFExtractImagesRequest request)
|
||||
throws IOException, InterruptedException, ExecutionException {
|
||||
MultipartFile file = request.getFileInput();
|
||||
|
||||
@@ -46,7 +46,7 @@ public class FlattenController {
|
||||
@Operation(
|
||||
summary = "Flatten PDF form fields or full page",
|
||||
description =
|
||||
"Flattening just PDF form fields or converting each page to images to make text unselectable. Input: PDF, Output: PDF. Type: SISO")
|
||||
"Flattening just PDF form fields or converting each page to images to make text unselectable. Input:PDF, Output:PDF. Type:SISO")
|
||||
public ResponseEntity<byte[]> flatten(@ModelAttribute FlattenRequest request) throws Exception {
|
||||
MultipartFile file = request.getFileInput();
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@ import java.util.*;
|
||||
import java.util.stream.Collectors;
|
||||
import java.util.zip.ZipEntry;
|
||||
import java.util.zip.ZipOutputStream;
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
|
||||
import javax.imageio.ImageIO;
|
||||
|
||||
import org.apache.pdfbox.multipdf.PDFMergerUtility;
|
||||
@@ -26,6 +26,7 @@ import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.github.pixee.security.BoundedLineReader;
|
||||
import io.github.pixee.security.Filenames;
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
@@ -65,9 +66,10 @@ public class OCRController {
|
||||
}
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/ocr-pdf")
|
||||
@Operation(
|
||||
summary = "Process PDF files with OCR using Tesseract",
|
||||
description = "Takes a PDF file as input, performs OCR using specified languages and OCR type (skip-text/force-ocr), and returns the processed PDF. Input:PDF Output:PDF Type:SISO")
|
||||
@Operation(
|
||||
summary = "Process PDF files with OCR using Tesseract",
|
||||
description =
|
||||
"Takes a PDF file as input, performs OCR using specified languages and OCR type (skip-text/force-ocr), and returns the processed PDF. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> processPdfWithOCR(
|
||||
@ModelAttribute ProcessPdfWithOcrRequest request)
|
||||
throws IOException, InterruptedException {
|
||||
|
||||
Reference in New Issue
Block a user