get info changes

src/main/java/stirling/software/SPDF/controller/api/security/GetInfoOnPDF.java

@@ -73,7 +73,7 @@ import java.util.Set;
 import java.util.HashSet;
 @RestController
 @Tag(name = "Security", description = "Security APIs")
-public class PDFExtractor {
+public class GetInfoOnPDF {
 	
 	static ObjectMapper objectMapper = new ObjectMapper();
 
@@ -94,6 +94,13 @@ public class PDFExtractor {
             // Metadata using PDFBox
             PDDocumentInformation info = pdfBoxDoc.getDocumentInformation();
             ObjectNode metadata = objectMapper.createObjectNode();
+            ObjectNode basicInfo = objectMapper.createObjectNode();
+            ObjectNode docInfoNode = objectMapper.createObjectNode();
+            ObjectNode compliancy = objectMapper.createObjectNode();
+            ObjectNode encryption = objectMapper.createObjectNode();
+            ObjectNode other = objectMapper.createObjectNode();
+            
+            
             metadata.put("Title", info.getTitle());
             metadata.put("Author", info.getAuthor());
             metadata.put("Subject", info.getSubject());
@@ -102,25 +109,25 @@ public class PDFExtractor {
             metadata.put("Creator", info.getCreator());
             metadata.put("CreationDate", formatDate(info.getCreationDate()));
             metadata.put("ModificationDate", formatDate(info.getModificationDate()));
-            metadata.put("Trapped", info.getTrapped());
             jsonOutput.set("Metadata", metadata);
             
             
             
+            
             // Total file size of the PDF
             long fileSizeInBytes = inputFile.getSize();
-            jsonOutput.put("FileSizeInBytes", fileSizeInBytes);
+            basicInfo.put("FileSizeInBytes", fileSizeInBytes);
             
             // Number of words, paragraphs, and images in the entire document
             String fullText = new PDFTextStripper().getText(pdfBoxDoc);
             String[] words = fullText.split("\\s+");
             int wordCount = words.length;
             int paragraphCount = fullText.split("\r\n|\r|\n").length;
-            jsonOutput.put("WordCount", wordCount);
+            basicInfo.put("WordCount", wordCount);
-            jsonOutput.put("ParagraphCount", paragraphCount);
+            basicInfo.put("ParagraphCount", paragraphCount);
             // Number of characters in the entire document (including spaces and special characters)
             int charCount = fullText.length();
-            jsonOutput.put("CharacterCount", charCount);
+            basicInfo.put("CharacterCount", charCount);
             
             
             // Initialize the flags and types
@@ -142,23 +149,25 @@ public class PDFExtractor {
                 hasCompression = true;
                 compressionType = "Compressed Xref or Rebuilt Xref";
             }
-            jsonOutput.put("Compression", hasCompression);
+            basicInfo.put("Compression", hasCompression);
             if(hasCompression)
-            	jsonOutput.put("CompressionType", compressionType);
+            	basicInfo.put("CompressionType", compressionType);
             
             String language = pdfBoxDoc.getDocumentCatalog().getLanguage();
-            jsonOutput.put("Language", language);
+            basicInfo.put("Language", language);
-            
+            basicInfo.put("Number of pages", pdfBoxDoc.getNumberOfPages());
-            // Document Information using PDFBox
-            ObjectNode docInfoNode = objectMapper.createObjectNode();
-            docInfoNode.put("Number of pages", pdfBoxDoc.getNumberOfPages());
-            docInfoNode.put("PDF version", pdfBoxDoc.getVersion());
             
             
             // Page Mode using iText7
             PdfCatalog catalog = itextDoc.getCatalog();
             PdfName pageMode = catalog.getPdfObject().getAsName(PdfName.PageMode);
             
+            // Document Information using PDFBox
+            docInfoNode.put("PDF version", pdfBoxDoc.getVersion());
+            docInfoNode.put("Trapped", info.getTrapped());
+            docInfoNode.put("Page Mode", getPageModeDescription(pageMode));;
+            
+
             
             
             
@@ -193,7 +202,7 @@ public class PDFExtractor {
                 
             }
             }
-            jsonOutput.set("EmbeddedFiles", embeddedFilesArray);
+            other.set("EmbeddedFiles", embeddedFilesArray);
             
             //attachments TODO size
             ArrayNode attachmentsArray = objectMapper.createArrayNode();
@@ -207,7 +216,7 @@ public class PDFExtractor {
                     }
                 }
             }
-            jsonOutput.set("Attachments", attachmentsArray);
+            other.set("Attachments", attachmentsArray);
 
             //Javascript
             PdfDictionary namesDict = itextDoc.getCatalog().getPdfObject().getAsDictionary(PdfName.Names);
@@ -226,7 +235,7 @@ public class PDFExtractor {
                 
                 }
             }
-            jsonOutput.set("JavaScript", javascriptArray);
+            other.set("JavaScript", javascriptArray);
             
             //TODO size
             PdfOCProperties ocProperties = itextDoc.getCatalog().getOCProperties(false);
@@ -240,7 +249,7 @@ public class PDFExtractor {
                 }
                 
             }
-            jsonOutput.set("Layers", layersArray);
+            other.set("Layers", layersArray);
             
             //TODO Security
             
@@ -267,7 +276,7 @@ public class PDFExtractor {
                 }
                 
             }
-            jsonOutput.set("FormFields", formFieldsArray2);
+            jsonOutput.set("FormFields2", formFieldsArray2);
             
             
             PDStructureTreeRoot structureTreeRoot = pdfBoxDoc.getDocumentCatalog().getStructureTreeRoot();
@@ -275,7 +284,7 @@ public class PDFExtractor {
 			try {
 				if(structureTreeRoot != null) {
 					structureTreeArray = exploreStructureTree(structureTreeRoot.getKids());
-					jsonOutput.set("StructureTree", structureTreeArray);
+					other.set("StructureTree", structureTreeArray);
 				}
 			} catch (Exception e) {
 				// TODO Auto-generated catch block
@@ -283,12 +292,6 @@ public class PDFExtractor {
 			}
             
             
-            
-            
-            
-            
-            
-            
             boolean isPdfACompliant = checkOutputIntent(itextDoc, "PDF/A");
             boolean isPdfXCompliant = checkOutputIntent(itextDoc, "PDF/X");
             boolean isPdfECompliant = checkForStandard(itextDoc, "PDF/E");
@@ -297,7 +300,6 @@ public class PDFExtractor {
             boolean isPdfBCompliant = checkForStandard(itextDoc, "PDF/B"); // If you want to check for PDF/Broadcast, though this isn't an official ISO standard.
             boolean isPdfSECCompliant = checkForStandard(itextDoc, "PDF/SEC"); // This might not be effective since PDF/SEC was under development in 2021.
             
-            ObjectNode compliancy = objectMapper.createObjectNode();
             compliancy.put("IsPDF/ACompliant", isPdfACompliant);
             compliancy.put("IsPDF/XCompliant", isPdfXCompliant);
             compliancy.put("IsPDF/ECompliant", isPdfECompliant);
@@ -306,7 +308,6 @@ public class PDFExtractor {
             compliancy.put("IsPDF/BCompliant", isPdfBCompliant);
             compliancy.put("IsPDF/SECCompliant", isPdfSECCompliant);
 
-            jsonOutput.set("Compliancy", compliancy);
      
             
            
@@ -318,7 +319,7 @@ public class PDFExtractor {
                     addOutlinesToArray(child, bookmarksArray);
                 }
             }
-            jsonOutput.set("Bookmarks/Outline/TOC", bookmarksArray);
+            other.set("Bookmarks/Outline/TOC", bookmarksArray);
             
             String xmpString = null;
             try {
@@ -331,29 +332,27 @@ public class PDFExtractor {
             } catch (XMPException e) {
                 e.printStackTrace();
             }
-            jsonOutput.put("XMPMetadata", xmpString);
+            other.put("XMPMetadata", xmpString);
             
             
             
-            ObjectNode encryptionNode = objectMapper.createObjectNode();
             if (pdfBoxDoc.isEncrypted()) {
-                encryptionNode.put("IsEncrypted", true);
+            	encryption.put("IsEncrypted", true);
 
                 // Retrieve encryption details using getEncryption()
-                PDEncryption encryption = pdfBoxDoc.getEncryption();
+                PDEncryption pdfEncryption = pdfBoxDoc.getEncryption();
-                encryptionNode.put("EncryptionAlgorithm", encryption.getFilter());
+                encryption.put("EncryptionAlgorithm", pdfEncryption.getFilter());
-                encryptionNode.put("KeyLength", encryption.getLength());
+                encryption.put("KeyLength", pdfEncryption.getLength());
-                encryptionNode.put("Permissions", pdfBoxDoc.getCurrentAccessPermission().toString());
+                encryption.put("Permissions", pdfBoxDoc.getCurrentAccessPermission().toString());
                 
                 // Add other encryption-related properties as needed
             } else {
-                encryptionNode.put("IsEncrypted", false);
+            	encryption.put("IsEncrypted", false);
             }
-            jsonOutput.set("Encryption", encryptionNode);
             
-            docInfoNode.put("Page Mode", getPageModeDescription(pageMode));;
             
-            jsonOutput.set("Document Information", docInfoNode);
+            
+
             ObjectNode pageInfoParent = objectMapper.createObjectNode();
             for (int pageNum = 1; pageNum <= itextDoc.getNumberOfPages(); pageNum++) {
                 ObjectNode pageInfo = objectMapper.createObjectNode();
@@ -382,7 +381,6 @@ public class PDFExtractor {
                 pageInfo.put("Text Characters Count", pageText.length()); //
 
              // Annotations
-                ArrayNode annotationsArray = objectMapper.createArrayNode();
                 List<PdfAnnotation> annotations = itextDoc.getPage(pageNum).getAnnotations();
 
                 int subtypeCount = 0;
@@ -452,6 +450,8 @@ public class PDFExtractor {
                 PdfDictionary fontDicts = resources.getResource(PdfName.Font);
                 Set<String> uniqueSubtypes = new HashSet<>(); // To store unique subtypes
 
+                // Map to store unique fonts and their counts
+                Map<String, ObjectNode> uniqueFontsMap = new HashMap<>();
 
                 if (fontDicts != null) {
                     for (PdfName key : fontDicts.keySet()) {
@@ -463,38 +463,32 @@ public class PDFExtractor {
                                 font.containsKey(PdfName.FontFile3);
                         fontNode.put("IsEmbedded", isEmbedded);
 
-                    	
                         if (font.containsKey(PdfName.Encoding)) {
                             String encoding = font.getAsName(PdfName.Encoding).toString();
                             fontNode.put("Encoding", encoding);
                         }
 
-                    	
+                        if (font.getAsString(PdfName.BaseFont) != null) {
-                    	
-                        if(font.getAsString(PdfName.BaseFont) != null)
                             fontNode.put("Name", font.getAsString(PdfName.BaseFont).toString());
+                        }
 
                         String subtype = null;
-                        // Font Subtype (e.g., Type1, TrueType)
                         if (font.containsKey(PdfName.Subtype)) {
                             subtype = font.getAsName(PdfName.Subtype).toString();
                             uniqueSubtypes.add(subtype);  // Add to set to ensure uniqueness
                         }
                         fontNode.put("Subtype", subtype);
 
-                        // Font Descriptor
                         PdfDictionary fontDescriptor = font.getAsDictionary(PdfName.FontDescriptor);
                         if (fontDescriptor != null) {
-                            // Italic Angle
                             if (fontDescriptor.containsKey(PdfName.ItalicAngle)) {
                                 fontNode.put("ItalicAngle", fontDescriptor.getAsNumber(PdfName.ItalicAngle).floatValue());
                             }
 
-                            // Flags (e.g., italic, bold)
                             if (fontDescriptor.containsKey(PdfName.Flags)) {
                                 int flags = fontDescriptor.getAsNumber(PdfName.Flags).intValue();
-                                fontNode.put("IsItalic", (flags & 64) != 0);  // Existing italic flag
+                                fontNode.put("IsItalic", (flags & 64) != 0);
-                                fontNode.put("IsBold", (flags & 1 << 16) != 0);  // Existing bold flag
+                                fontNode.put("IsBold", (flags & 1 << 16) != 0);
                                 fontNode.put("IsFixedPitch", (flags & 1) != 0);
                                 fontNode.put("IsSerif", (flags & 2) != 0);
                                 fontNode.put("IsSymbolic", (flags & 4) != 0);
@@ -512,33 +506,42 @@ public class PDFExtractor {
                                 fontNode.put("FontStretch", fontStretch);
                             }
 
-                            if (fontDescriptor != null && fontDescriptor.containsKey(PdfName.FontBBox)) {
+                            if (fontDescriptor.containsKey(PdfName.FontBBox)) {
                                 PdfArray bbox = fontDescriptor.getAsArray(PdfName.FontBBox);
                                 fontNode.put("FontBoundingBox", bbox.toString());
                             }
-                            if (fontDescriptor != null && fontDescriptor.containsKey(PdfName.FontWeight)) {
+
+                            if (fontDescriptor.containsKey(PdfName.FontWeight)) {
                                 float fontWeight = fontDescriptor.getAsNumber(PdfName.FontWeight).floatValue();
                                 fontNode.put("FontWeight", fontWeight);
                             }
-                            
                         }
+
                         if (font.containsKey(PdfName.ToUnicode)) {
-                            PdfStream toUnicodeStream = font.getAsStream(PdfName.ToUnicode);
-                            // Handle the stream as needed, maybe extract some details or just note its existence
                             fontNode.put("HasToUnicodeMap", true);
                         }
+
                         if (fontNode.size() > 0) {
-                        	fontsArray.add(fontNode);  // Add each font node to fontsArray
+                            // Create a unique key for this font node based on its attributes
+                            String uniqueKey = fontNode.toString(); 
+
+                            // Increment count if this font exists, or initialize it if new
+                            if (uniqueFontsMap.containsKey(uniqueKey)) {
+                                ObjectNode existingFontNode = uniqueFontsMap.get(uniqueKey);
+                                int count = existingFontNode.get("Count").asInt() + 1;
+                                existingFontNode.put("Count", count);
+                            } else {
+                                fontNode.put("Count", 1);
+                                uniqueFontsMap.put(uniqueKey, fontNode);
+                            }
                         }
                     }
                 }
 
-                // Add unique subtypes to fontsArray
+                // Add unique font entries to fontsArray
-                ArrayNode subtypesArray = objectMapper.createArrayNode();
+                for (ObjectNode uniqueFontNode : uniqueFontsMap.values()) {
-                for (String subtype : uniqueSubtypes) {
+                    fontsArray.add(uniqueFontNode);
-                    subtypesArray.add(subtype);
                 }
-                pageInfo.set("FontSubtypes", subtypesArray); // Changed from Fonts to FontSubtypes
 
                 pageInfo.set("Fonts", fontsArray);
                 
@@ -606,6 +609,12 @@ public class PDFExtractor {
                 pageInfoParent.set("Page " + pageNum, pageInfo);
             }
 
+            
+            jsonOutput.set("BasicInfo", basicInfo);
+            jsonOutput.set("DocumentInfo", docInfoNode);
+            jsonOutput.set("Compliancy", compliancy);
+            jsonOutput.set("Encryption", encryption);
+            jsonOutput.set("Other", other);
             jsonOutput.set("PerPageInfo", pageInfoParent);
             
             

src/main/resources/static/js/fileInput.js

@@ -1,4 +1,11 @@
 document.addEventListener('DOMContentLoaded', function() {
+    document.querySelectorAll('.custom-file-chooser').forEach(setupFileInput);
+});
+
+function setupFileInput(chooser) {
+    const elementId = chooser.getAttribute('data-element-id');
+    const filesSelected = chooser.getAttribute('data-files-selected');
+    const pdfPrompt = chooser.getAttribute('data-pdf-prompt');
     
     let overlay;
     let dragCounter = 0;
@@ -6,7 +13,6 @@ document.addEventListener('DOMContentLoaded', function() {
     const dragenterListener = function() {
         dragCounter++;
         if (!overlay) {
-            // Create and show the overlay
             overlay = document.createElement('div');
             overlay.style.position = 'fixed';
             overlay.style.top = 0;
@@ -28,7 +34,6 @@ document.addEventListener('DOMContentLoaded', function() {
     const dragleaveListener = function() {
         dragCounter--;
         if (dragCounter === 0) {
-            // Hide and remove the overlay
             if (overlay) {
                 overlay.remove();
                 overlay = null;
@@ -40,24 +45,19 @@ document.addEventListener('DOMContentLoaded', function() {
         const dt = e.dataTransfer;
         const files = dt.files;
 
-        // Access the file input element and assign dropped files
+        const fileInput = document.getElementById(elementId);
-        const fileInput = document.getElementById(elementID);
         fileInput.files = files;
 
-        // Hide and remove the overlay
         if (overlay) {
             overlay.remove();
             overlay = null;
         }
 
-        // Reset drag counter
         dragCounter = 0;
 
-        //handleFileInputChange(fileInput);
         fileInput.dispatchEvent(new Event('change', { bubbles: true }));
     };
 
-    // Prevent default behavior for drag events
     ['dragenter', 'dragover', 'dragleave', 'drop'].forEach(eventName => {
         document.body.addEventListener(eventName, preventDefaults, false);
     });
@@ -69,16 +69,12 @@ document.addEventListener('DOMContentLoaded', function() {
 
     document.body.addEventListener('dragenter', dragenterListener);
     document.body.addEventListener('dragleave', dragleaveListener);
-    // Add drop event listener
     document.body.addEventListener('drop', dropListener);
 
-});
+    $("#" + elementId).on("change", function() {
-
-$("#"+elementID).on("change", function() {
         handleFileInputChange(this);
     });
 
-
     function handleFileInputChange(inputElement) {
         const files = $(inputElement).get(0).files;
         const fileNames = Array.from(files).map(f => f.name);
@@ -95,3 +91,4 @@ function handleFileInputChange(inputElement) {
             $(inputElement).siblings(".custom-file-label").addClass("selected").html(pdfPrompt);
         }
     }
+}

src/main/resources/templates/fragments/common.html

@@ -98,7 +98,10 @@
 	</script>
     <script src="js/downloader.js"></script>
 
-    <div class="custom-file-chooser">
+    <div class="custom-file-chooser" th:attr="data-unique-id=${name}, 
+              data-element-id=${name+'-input'}, 
+              data-files-selected=#{filesSelected}, 
+              data-pdf-prompt=#{pdfPrompt}">
         <div class="custom-file">
             <input type="file" class="custom-file-input" th:name="${name}" th:id="${name}+'-input'" th:accept="${accept}" multiple th:classappend="${notRequired ? '' : 'required'}">
             <label class="custom-file-label" th:for="${name}+'-input'" th:text="${inputText}"></label>
@@ -115,11 +118,6 @@
     <button type="button" class="btn btn-primary" id="show-game-btn" style="display:none;">Bored waiting?</button>
 
 
-	<script th:inline="javascript">
-		const elementID =  /*[[${name+"-input"}]]*/ '';
-		const filesSelected =  /*[[#{filesSelected}]]*/ '';
-		const pdfPrompt =  /*[[#{pdfPrompt}]]*/ '';
-	</script>
 	
     <script src="js/fileInput.js"></script>
     <link rel="stylesheet" href="css/fileSelect.css">

src/main/resources/templates/other/compare.html

@@ -15,8 +15,8 @@
                     <div class="col-md-9">
                         <h2 th:text="#{compare.header}"></h2>
                          
-                        <div th:replace="~{fragments/common :: fileSelector(name='fileInput', multiple=false, accept='application/pdf')}"></div>
+                        <div th:replace="~{fragments/common :: fileSelector(name='fileInput', multiple=false, accept='application/pdf', remoteCall='false')}"></div>
-                        <div th:replace="~{fragments/common :: fileSelector(name='fileInput2', multiple=false, accept='application/pdf')}"></div>
+                        <div th:replace="~{fragments/common :: fileSelector(name='fileInput2', multiple=false, accept='application/pdf', remoteCall='false')}"></div>
                         <button class="btn btn-primary"  onclick="comparePDFs()" th:text="#{compare.submit}"></button>
 
             

src/main/resources/templates/security/get-info-on-pdf.html

@@ -15,13 +15,109 @@
                     <div class="col-md-6">
                         <h2 th:text="#{getPdfInfo.header}"></h2>
 						<p th:text="#{processTimeWarning}">
-                        <form method="post" enctype="multipart/form-data" th:action="@{get-info-on-pdf}">
+                        <form id="pdfInfoForm" method="post" enctype="multipart/form-data" th:action="@{get-info-on-pdf}">
-                            <div th:replace="~{fragments/common :: fileSelector(name='fileInput', multiple=false)}"></div>
+                            <div th:replace="~{fragments/common :: fileSelector(name='fileInput', multiple=false, remoteCall='false')}"></div>
                             <br>
                             <button type="submit" id="submitBtn" class="btn btn-primary" th:text="#{getPdfInfo.submit}"></button>
 
                         </form>
+                       <div class="container mt-5">
+						    <!-- Iterate over each main section in the JSON -->
+						    <div id="json-content">
+						        <!-- JavaScript will populate this section -->
+						    </div>
 						
+						    <!-- Button to download the JSON -->
+						    <a href="#" id="downloadJson" class="btn btn-primary mt-3">Download JSON</a>
+						</div>
+                       <script>
+                       
+
+                    // Prevent the form from submitting the traditional way
+                       document.getElementById("pdfInfoForm").addEventListener("submit", function(event) {
+                           event.preventDefault();
+
+                           // Fetch the formData
+                           const formData = new FormData(event.target);
+                           
+                           fetch('get-info-on-pdf', { 
+                               method: 'POST',
+                               body: formData
+                           })
+                           .then(response => response.json())
+                           .then(data => {
+                               displayJsonData(data); // Display the data
+                               setDownloadLink(data); // Set download link
+                           })
+                           .catch(error => console.error('Error:', error));
+                       });
+
+                       function displayJsonData(jsonData) {
+                           let content = '';
+                           for (const key in jsonData) {
+                               content += renderJsonSection(key, jsonData[key]);
+                           }
+                           document.getElementById('json-content').innerHTML = content;
+                       }
+
+                       function setDownloadLink(jsonData) {
+                           const downloadLink = document.getElementById('downloadJson');
+                           const dataStr = "data:text/json;charset=utf-8," + encodeURIComponent(JSON.stringify(jsonData, null, 4));
+                           downloadLink.setAttribute("href", dataStr);
+                           downloadLink.setAttribute("download", "data.json");
+                       }
+
+
+                    	
+                    	
+                       function renderJsonSection(key, value, depth = 0) {
+                    	    let output = `<div class="card mb-3">
+                    	        <div class="card-header" id="${key}-heading-${depth}">
+                    	            <h5 class="mb-0">`;
+
+                    	    // Check if the value is an object and has children
+                    	    if (value && typeof value === 'object' && Object.keys(value).length) {
+                    	        output += `
+                    	            <button class="btn btn-link" type="button" data-toggle="collapse" data-target="#${key}-content-${depth}" aria-expanded="true" aria-controls="${key}-content-${depth}">
+                    	                ${key}
+                    	            </button>`;
+                    	    } else {
+                    	        // Display both key and value for simple entries
+                    	        output += `${key}: ${value}`;
+                    	    }
+
+                    	    output += `
+                    	            </h5>
+                    	        </div>
+                    	        <div id="${key}-content-${depth}" class="collapse" aria-labelledby="${key}-heading-${depth}">`;
+
+                    	    // Check if the value is a nested object
+                    	    if (typeof value === 'object' && !Array.isArray(value)) {
+                    	        output += '<div class="card-body">';
+                    	        for (const subKey in value) {
+                    	            output += renderJsonSection(subKey, value[subKey], depth + 1);
+                    	        }
+                    	        output += '</div>';
+                    	    } else if (typeof value === 'object' && Array.isArray(value) && value.length) { // Array values
+                    	        value.forEach((val, index) => {
+                    	            output += renderJsonSection(index, val, depth + 1);
+                    	        });
+                    	    }
+
+                    	    output += '</div></div>';
+
+                    	    return output;
+                    	}
+
+                    
+
+                   
+
+                   
+
+
+                       
+                       </script>
                     </div>
                 </div>
             </div>