arsvendg/Stirling-PDF
1
0
Fork 0
mirror of https://github.com/arsvendg/Stirling-PDF.git synced 2026-07-15 02:54:06 +02:00
Code Issues Actions 6 Packages Projects Releases 1 Wiki Activity

Memory enhancements and PDF decompress API (#3129)

Browse Source 
# Description of Changes

- PDF split by size to check size of PDF as it splits, avoids issue were
a PDFs size is different viewed vs saved due to compression caused by
repeated data etc.
- Additionally memory enhancements for PDF load to dynamically load in
memory vs scratch
- PDF Decompress API for PDF testing


## 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
2025-03-08 00:03:27 +00:00
committed by GitHub
parent 33eb3fd034
commit ed2ef01690
43 changed files with 1042 additions and 321 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/main/java/stirling/software/SPDF/controller/api/AnalysisController.java
+17 -9
View File
@@ -3,7 +3,6 @@ package stirling.software.SPDF.controller.api;
import java.io.IOException;
import java.util.*;
import org.apache.pdfbox.Loader;
import org.apache.pdfbox.cos.COSName;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDDocumentInformation;
@@ -12,24 +11,33 @@ import org.apache.pdfbox.pdmodel.PDPageTree;
import org.apache.pdfbox.pdmodel.encryption.PDEncryption;
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotation;
import org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.*;
import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.model.api.PDFFile;
import stirling.software.SPDF.service.CustomPDDocumentFactory;
@RestController
@RequestMapping("/api/v1/analysis")
@Tag(name = "Analysis", description = "Analysis APIs")
public class AnalysisController {
private final CustomPDDocumentFactory pdfDocumentFactory;
@Autowired
public AnalysisController(CustomPDDocumentFactory pdfDocumentFactory) {
this.pdfDocumentFactory = pdfDocumentFactory;
}
@PostMapping(value = "/page-count", consumes = "multipart/form-data")
@Operation(
summary = "Get PDF page count",
description = "Returns total number of pages in PDF. Input:PDF Output:JSON Type:SISO")
public Map<String, Integer> getPageCount(@ModelAttribute PDFFile file) throws IOException {
try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
try (PDDocument document = pdfDocumentFactory.load(file.getFileInput().getBytes())) {
return Map.of("pageCount", document.getNumberOfPages());
}
}
@@ -39,7 +47,7 @@ public class AnalysisController {
summary = "Get basic PDF information",
description = "Returns page count, version, file size. Input:PDF Output:JSON Type:SISO")
public Map<String, Object> getBasicInfo(@ModelAttribute PDFFile file) throws IOException {
try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
try (PDDocument document = pdfDocumentFactory.load(file.getFileInput().getBytes())) {
Map<String, Object> info = new HashMap<>();
info.put("pageCount", document.getNumberOfPages());
info.put("pdfVersion", document.getVersion());
@@ -54,7 +62,7 @@ public class AnalysisController {
description = "Returns title, author, subject, etc. Input:PDF Output:JSON Type:SISO")
public Map<String, String> getDocumentProperties(@ModelAttribute PDFFile file)
throws IOException {
try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
try (PDDocument document = pdfDocumentFactory.load(file.getFileInput().getBytes())) {
PDDocumentInformation info = document.getDocumentInformation();
Map<String, String> properties = new HashMap<>();
properties.put("title", info.getTitle());
@@ -75,7 +83,7 @@ public class AnalysisController {
description = "Returns width and height of each page. Input:PDF Output:JSON Type:SISO")
public List<Map<String, Float>> getPageDimensions(@ModelAttribute PDFFile file)
throws IOException {
try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
try (PDDocument document = pdfDocumentFactory.load(file.getFileInput().getBytes())) {
List<Map<String, Float>> dimensions = new ArrayList<>();
PDPageTree pages = document.getPages();
@@ -95,7 +103,7 @@ public class AnalysisController {
description =
"Returns count and details of form fields. Input:PDF Output:JSON Type:SISO")
public Map<String, Object> getFormFields(@ModelAttribute PDFFile file) throws IOException {
try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
try (PDDocument document = pdfDocumentFactory.load(file.getFileInput().getBytes())) {
Map<String, Object> formInfo = new HashMap<>();
PDAcroForm form = document.getDocumentCatalog().getAcroForm();
@@ -117,7 +125,7 @@ public class AnalysisController {
summary = "Get annotation information",
description = "Returns count and types of annotations. Input:PDF Output:JSON Type:SISO")
public Map<String, Object> getAnnotationInfo(@ModelAttribute PDFFile file) throws IOException {
try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
try (PDDocument document = pdfDocumentFactory.load(file.getFileInput().getBytes())) {
Map<String, Object> annotInfo = new HashMap<>();
int totalAnnotations = 0;
Map<String, Integer> annotationTypes = new HashMap<>();
@@ -142,7 +150,7 @@ public class AnalysisController {
description =
"Returns list of fonts used in the document. Input:PDF Output:JSON Type:SISO")
public Map<String, Object> getFontInfo(@ModelAttribute PDFFile file) throws IOException {
try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
try (PDDocument document = pdfDocumentFactory.load(file.getFileInput().getBytes())) {
Map<String, Object> fontInfo = new HashMap<>();
Set<String> fontNames = new HashSet<>();
@@ -164,7 +172,7 @@ public class AnalysisController {
description =
"Returns encryption and permission details. Input:PDF Output:JSON Type:SISO")
public Map<String, Object> getSecurityInfo(@ModelAttribute PDFFile file) throws IOException {
try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
try (PDDocument document = pdfDocumentFactory.load(file.getFileInput().getBytes())) {
Map<String, Object> securityInfo = new HashMap<>();
PDEncryption encryption = document.getEncryption();