init home for toher featues

README.md

@@ -24,6 +24,8 @@ Feel free to request any features or bug fixes either in github issues or our [D
 - Add/Generate signatures
 - Flatten PDFs
 - Repair PDFs
+- Detect and remove blank pages
+- Compare 2 PDFs and show differences in text
 - Add images to PDFs
 - Rotating PDFs in 90 degree increments.
 - Compressing PDFs to decrease their filesize. (Using OCRMyPDF)
@@ -77,10 +79,12 @@ docker run -d \
   frooodle/s-pdf
   
   
-  Can also add these for customisation
+  Can also add these for customisation but are not required
   -e APP_HOME_NAME="Stirling PDF" \
   -e APP_HOME_DESCRIPTION="Your locally hosted one-stop-shop for all your PDF needs." \
   -e APP_NAVBAR_NAME="Stirling PDF" \
+  -e ALLOW_GOOGLE_VISABILITY="true" \
+  -e APP_LOCALE="en_GB" \
 ```
 Docker Compose
 ```
@@ -94,9 +98,11 @@ services:
       - /location/of/trainingData:/usr/share/tesseract-ocr/4.00/tessdata #Required for extra OCR languages
 #      - /location/of/extraConfigs:/configs
 #    environment:
+#      APP_LOCALE: en_GB
 #      APP_HOME_NAME: Stirling PDF
 #      APP_HOME_DESCRIPTION: Your locally hosted one-stop-shop for all your PDF needs.
 #      APP_NAVBAR_NAME: Stirling PDF
+#      ALLOW_GOOGLE_VISABILITY: true
 
 ```
 
@@ -122,7 +128,9 @@ Stirling PDF allows easy customization of the visible application name.
 Simply use environment variables APP_HOME_NAME, APP_HOME_DESCRIPTION and APP_NAVBAR_NAME with Docker or Java. 
 If running Java directly, you can also pass these as properties using -D arguments.
 
-Using the same method you can also change the default language by providing APP_LOCALE with values like de-DE fr-FR or ar-AR to select your default language (Will always default to English on invalid locale)
+Using the same method you can also change 
+- The default language by providing APP_LOCALE with values like de-DE fr-FR or ar-AR to select your default language (Will always default to English on invalid locale)
+- Enable/Disable search engine visablility with ALLOW_GOOGLE_VISABILITY with true / false values. Default disable visability.
 
 ## API
 For those wanting to use Stirling-PDFs backend API to link with their own custom scripting to edit PDFs you can view all existing API documentation

src/main/java/stirling/software/SPDF/controller/api/other/BlankPageController.java

@@ -30,8 +30,9 @@ public class BlankPageController {
 
     @PostMapping(consumes = "multipart/form-data", value = "/remove-blanks")
     public ResponseEntity<byte[]> removeBlankPages(@RequestPart(required = true, value = "fileInput") MultipartFile inputFile) throws IOException, InterruptedException {
+        PDDocument document = null;
         try {
-            PDDocument document = PDDocument.load(inputFile.getInputStream());
+            document = PDDocument.load(inputFile.getInputStream());
             PDPageTree pages = document.getDocumentCatalog().getPages();
             PDFTextStripper textStripper = new PDFTextStripper();
 
@@ -67,7 +68,7 @@ public class BlankPageController {
                 BufferedImage image = pdfRenderer.renderImageWithDPI(i - 1, 300);
                 ImageIO.write(image, "png", tempFile.toFile());
                 
-                List<String> command = new ArrayList<>(Arrays.asList("python3", "./scripts/detect-blank-pages.py", tempFile.toString())); 
+                List<String> command = new ArrayList<>(Arrays.asList("python3", System.getProperty("user.dir") + "scripts/detect-blank-pages.py", tempFile.toString())); 
 
                 // Run CLI command
                 int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.PYTHON_OPENCV).runCommandWithOutputHandling(command);
@@ -81,12 +82,15 @@ public class BlankPageController {
             }
             
 
-            document.close();
+
             
             return PdfUtils.pdfDocToWebResponse(outputDocument, inputFile.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_blanksRemoved.pdf");
         } catch (IOException e) {
             e.printStackTrace();
             return new ResponseEntity<>(HttpStatus.INTERNAL_SERVER_ERROR);
+        } finally {
+            if(document != null)
+                document.close();
         }
     }
     

src/main/java/stirling/software/SPDF/controller/web/GeneralWebController.java

@@ -84,9 +84,9 @@ public class GeneralWebController {
         if (allowGoogleVisibility == null)
             allowGoogleVisibility = System.getenv("ALLOW_GOOGLE_VISABILITY");
         if (allowGoogleVisibility == null)
-            allowGoogleVisibility = "true";
+            allowGoogleVisibility = "false";
         if (Boolean.parseBoolean(allowGoogleVisibility)) {
-            return "User-agent: Googlebot\nAllow: /\n\nUser-agent: *\nDisallow: /";
+            return "User-agent: Googlebot\nAllow: /\n\nUser-agent: *\nAllow: /";
         } else {
             return "User-agent: Googlebot\nDisallow: /\n\nUser-agent: *\nDisallow: /";
         }

src/main/resources/messages_en_GB.properties

@@ -117,6 +117,12 @@ home.flatten.desc=Remove all interactive elements and forms from a PDF
 home.repair.title=Repair
 home.repair.desc=Tries to repair a corrupt/broken PDF
 
+home.removeBlanks.title=Remove Blank pages
+home.removeBlanks.desc=Detects and removes blank pages from a document
+
+home.compare.title=Compare
+home.compare.desc=Compares and shows the differences between 2 PDF Documents
+
 downloadPdf=Download PDF
 text=Text
 font=Font

src/main/resources/static/images/blank-file.svg

@@ -0,0 +1,3 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="bi bi-file" viewBox="0 0 16 16">
+  <path d="M4 0a2 2 0 0 0-2 2v12a2 2 0 0 0 2 2h8a2 2 0 0 0 2-2V2a2 2 0 0 0-2-2H4zm0 1h8a1 1 0 0 1 1 1v12a1 1 0 0 1-1 1H4a1 1 0 0 1-1-1V2a1 1 0 0 1 1-1z"/>
+</svg>

src/main/resources/static/images/scales.svg

@@ -0,0 +1,94 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Generator: Adobe Illustrator 13.0.2, SVG Export Plug-In . SVG Version: 6.00 Build 14948)  -->
+<svg
+    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+    xmlns="http://www.w3.org/2000/svg"
+    xmlns:cc="http://web.resource.org/cc/"
+    xmlns:xlink="http://www.w3.org/1999/xlink"
+    xmlns:dc="http://purl.org/dc/elements/1.1/"
+    xmlns:svg="http://www.w3.org/2000/svg"
+    xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+    xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+    xmlns:ns1="http://sozi.baierouge.fr"
+    id="Layer_1"
+    style="enable-background:new 0 0 333.33 287.889"
+    xml:space="preserve"
+    viewBox="0 0 333.33 287.889"
+    version="1.1"
+    y="0px"
+    x="0px"
+  >
+<g
+    >
+	<polygon
+        style="fill:none"
+        points="19.374 136.98 98.932 136.98 59.083 18.273"
+    />
+	<polygon
+        style="fill:none"
+        points="235.57 191.34 315.13 191.34 275.28 72.635"
+    />
+	<path
+        d="m318.63 191.34l-42.85-127.63 6.892 1.386c-0.563 2.401 0.902 4.816 3.304 5.41 2.419 0.599 4.869-0.877 5.47-3.298 0.602-2.42-0.878-4.868-3.301-5.469-2.095-0.518-4.205 0.523-5.125 2.384l-58.16-17.14-54.361-16.029-0.509-9.298c5.801-0.21 10.444-4.966 10.444-10.818 0.01-5.985-4.85-10.838-10.84-10.838-5.985 0-10.837 4.853-10.837 10.838 0 5.288 3.79 9.686 8.8 10.64l-0.477 8.708-53.87-10.838-60.542-12.179c0.08-2.094-1.315-4.028-3.429-4.552-2.419-0.599-4.867 0.879-5.466 3.299-0.599 2.421 0.877 4.869 3.297 5.468 2.418 0.598 4.865-0.876 5.468-3.292l5.889 1.736-42.537 127.15h-15.88s9.255 20.324 58.069 20.324 54.804-20.324 54.804-20.324h-10.446l-42.535-126.72 51.784 15.269 54.78 16.151-11.76 214.82s0.461 9.693-14.772 12.002c-15.234 2.308-34.621 3.229-43.853 8.309-9.233 5.078-10.617 11.078-10.617 11.078h166.64s-1.386-6-10.615-11.078c-9.234-5.079-28.621-6.001-43.854-8.309-15.233-2.309-14.772-12.002-14.772-12.002l-11.72-213.83 52.188 10.499 51.506 10.362-42.755 127.82h-11.623s9.255 20.324 58.068 20.324 54.804-20.324 54.804-20.324h-14.7zm-219.7-54.36h-79.558l39.709-118.71 39.849 118.71zm136.64 54.36l39.708-118.71 39.85 118.71h-79.56z"
+    />
+</g
+  >
+<metadata
+    ><rdf:RDF
+      ><cc:Work
+        ><dc:format
+          >image/svg+xml</dc:format
+        ><dc:type
+            rdf:resource="http://purl.org/dc/dcmitype/StillImage"
+        /><cc:license
+            rdf:resource="http://creativecommons.org/licenses/publicdomain/"
+        /><dc:publisher
+          ><cc:Agent
+              rdf:about="http://openclipart.org/"
+            ><dc:title
+              >Openclipart</dc:title
+            ></cc:Agent
+          ></dc:publisher
+        ><dc:title
+          >scales of justice</dc:title
+        ><dc:date
+          >2009-06-26T04:35:18</dc:date
+        ><dc:description
+        /><dc:source
+          >https://openclipart.org/detail/26849/scales-of-justice-by-johnny_automatic</dc:source
+        ><dc:creator
+          ><cc:Agent
+            ><dc:title
+              >johnny_automatic</dc:title
+            ></cc:Agent
+          ></dc:creator
+        ><dc:subject
+          ><rdf:Bag
+            ><rdf:li
+              >justice</rdf:li
+            ><rdf:li
+              >law</rdf:li
+            ><rdf:li
+              >measurement</rdf:li
+            ><rdf:li
+              >scales</rdf:li
+            ><rdf:li
+              >silhouette</rdf:li
+            ><rdf:li
+              >weight</rdf:li
+            ></rdf:Bag
+          ></dc:subject
+        ></cc:Work
+      ><cc:License
+          rdf:about="http://creativecommons.org/licenses/publicdomain/"
+        ><cc:permits
+            rdf:resource="http://creativecommons.org/ns#Reproduction"
+        /><cc:permits
+            rdf:resource="http://creativecommons.org/ns#Distribution"
+        /><cc:permits
+            rdf:resource="http://creativecommons.org/ns#DerivativeWorks"
+        /></cc:License
+      ></rdf:RDF
+    ></metadata
+  ></svg
+>

src/main/resources/templates/home.html

@@ -112,8 +112,8 @@ filter: invert(0.2) sepia(2) saturate(50) hue-rotate(190deg);
                 <div th:replace="~{fragments/card :: card(cardTitle=#{home.flatten.title}, cardText=#{home.flatten.desc}, cardLink='flatten', svgPath='images/flatten.svg')}"></div>
                 
                 <div th:replace="~{fragments/card :: card(cardTitle=#{home.repair.title}, cardText=#{home.repair.desc}, cardLink='repair', svgPath='images/wrench.svg')}"></div>
-                <div th:replace="~{fragments/card :: card(cardTitle=#{home.removeBlanks.title}, cardText=#{home.removeBlanks.desc}, cardLink='remove-blanks', svgPath='images/wrench.svg')}"></div>
+                <div th:replace="~{fragments/card :: card(cardTitle=#{home.removeBlanks.title}, cardText=#{home.removeBlanks.desc}, cardLink='remove-blanks', svgPath='images/blank-file.svg')}"></div>
-                <div th:replace="~{fragments/card :: card(cardTitle=#{home.compare.title}, cardText=#{home.compare.desc}, cardLink='compare', svgPath='images/wrench.svg')}"></div>
+                <div th:replace="~{fragments/card :: card(cardTitle=#{home.compare.title}, cardText=#{home.compare.desc}, cardLink='compare', svgPath='images/scales.svg')}"></div>
             </div>
         </div>
         <div th:insert="~{fragments/footer.html :: footer}"></div>

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

@@ -18,7 +18,25 @@
                         <div th:replace="~{fragments/common :: fileSelector(name='fileInput', multiple=false, accept='application/pdf')}"></div>
                         <div th:replace="~{fragments/common :: fileSelector(name='fileInput2', multiple=false, accept='application/pdf')}"></div>
                         <button onclick="comparePDFs()">Compare</button>
-                        <div id="result"></div>
+                        <div class="row">
+                            <div class="col-md-6">
+                                <h3>Document 1</h3>
+                                <div id="result1" class="result-column"></div>
+                            </div>
+                            <div class="col-md-6">
+                                <h3>Document 2</h3>
+                                <div id="result2" class="result-column"></div>
+                            </div>
+                        </div>
+                        <style>
+                            .result-column {
+                                border: 1px solid #ccc;
+                                padding: 15px;
+                                overflow-y: scroll;
+                                height: 400px;
+                                white-space: pre-wrap;
+                            }
+                        </style>
                         <script>
                         async function comparePDFs() {
                             const file1 = document.getElementById("fileInput-input").files[0];
@@ -40,9 +58,9 @@
                                     const page = await pdf.getPage(i);
                                     const content = await page.getTextContent();
                                     const strings = content.items.map(item => item.str);
-                                    pages.push(strings.join(""));
+                                    pages.push(strings.join(" "));
                                 }
-                                return pages.join("\n");
+                                return pages.join(" ");
                             };
 
                             const [text1, text2] = await Promise.all([
@@ -50,78 +68,62 @@
                                 extractText(pdf2)
                             ]);
 
+                            if (text1.trim() === "" || text2.trim() === "") {
+                                alert("One or both of the selected PDFs have no text content. Please choose PDFs with text for comparison.");
+                                return;
+                            }
                             const diff = (text1, text2) => {
-                                const lines1 = text1.split("\n");
+                                // ... Keep the same diff function from the previous response ...
-                                const lines2 = text2.split("\n");
-
-                                const result = [];
-                                let i = 0, j = 0;
-
-                                while (i < lines1.length || j < lines2.length) {
-                                	console.log(`lines1[${i}]='${lines1[i]}', lines2[${j}]='${lines2[j]}'`);
-                                	console.log(`i=${i}, j=${j}`);
-                                    if (lines1[i] === lines2[j]) {
-                                        result.push([i, j, lines1[i]]);
-                                        i++;
-                                        j++;
-                                        console.log(`i=${i}, j=${j}`);
-
-                                    } else {
-                                        let k = i, l = j;
-                                        while (k < lines1.length && l < lines2.length && lines1[k] !== lines2[l]) {
-                                            k++;
-                                            l++;
-                                        }
-
-                                        for (let x = i; x < k; x++) {
-                                            result.push([x, -1, lines1[x]]);
-                                        }
-
-                                        for (let y = j; y < l; y++) {
-                                            result.push([-1, y, lines2[y]]);
-                                        }
-
-                                        i = k;
-                                        j = l;
-                                    }
-                                }
-
-                                return result;
                             };
 
                             const differences = diff(text1, text2);
-                            const highlightDifferences = async (pdf, differences) => {
+
-                                for (const difference of differences) {
+                            const displayDifferences = (differences) => {
-                                    const [pageIndex, lineIndex, lineText] = difference;
+                                const resultDiv1 = document.getElementById("result1");
-                                    if (lineIndex === -1) {
+                                const resultDiv2 = document.getElementById("result2");
-                                        continue;
+                                resultDiv1.innerHTML = "";
+                                resultDiv2.innerHTML = "";
+                                
+                                let doc1Pointer = 0;
+                                let doc2Pointer = 0;
+                                differences.forEach(([color, word]) => {
+                                    const span1 = document.createElement("span");
+                                    const span2 = document.createElement("span");
+
+                                    if (color === "green") {
+                                        span1.style.color = color;
+                                        span1.textContent = word;
+                                        resultDiv1.appendChild(span1);
+                                        doc1Pointer++;
+                                    } else if (color === "red") {
+                                        span2.style.color = color;
+                                        span2.textContent = word;
+                                        resultDiv2.appendChild(span2);
+                                        doc2Pointer++;
+                                    } else {
+                                        span1.style.color = color;
+                                        span1.textContent = word;
+                                        resultDiv1.appendChild(span1);
+                                        doc1Pointer++;
+
+                                        span2.style.color = color;
+                                        span2.textContent = word;
+                                        resultDiv2.appendChild(span2);
+                                        doc2Pointer++;
                                     }
-                                    console.log(pageIndex);
+
-                                    const page = await pdf.getPage(pageIndex);
+                                    // Add space after each word
-                                    const viewport = page.getViewport({ scale: 1 });
+                                    const space1 = document.createElement("span");
-                                    const [left,top] = viewport.convertToViewportPoint(0, lineIndex * 20);
+                                    const space2 = document.createElement("span");
-                                    const [right, bottom] = viewport.convertToViewportPoint(500, (lineIndex + 1) * 20);
+                                    space1.textContent = " ";
-                                    const annotation = {
+                                    space2.textContent = " ";
-                                            type: "Highlight",
+                                    resultDiv1.appendChild(space1);
-                                            rect: [left, top, right - left, bottom - top],
+                                    resultDiv2.appendChild(space2);
-                                            color: [255, 255, 0],
+                                });
-                                            opacity: 0.5,
+                                return result;
-                                            quadPoints:
-                                            [
-                                                left, top, right, top, right, bottom, left, bottom
-                                            ]
                             };
-            
+                            console.log('Differences:', differences);
-                                        await page.addAnnotation(annotation);
+                            displayDifferences(differences);
-                                
-                                        const message = `Difference found in page ${pageIndex }, line ${lineIndex + 1}: ${lineText}`;
-                                        const p = document.createElement("p");
-                                        p.textContent = message;
-                                        document.getElementById("result").appendChild(p);
-                                    }
-                                };
-            
-                                await highlightDifferences(pdf1, differences);
                         }
                         </script>
                     </div>
@@ -130,6 +132,3 @@
         </div>
         <div th:insert="~{fragments/footer.html :: footer}"></div>
     </div>
-</body>
-
-</html>