From 5213c588191209c02b2ce151f621c62f1816db35 Mon Sep 17 00:00:00 2001
From: "Denise D." <ddatinguinoo@gnet.it>
Date: Tue, 28 Jul 2026 12:52:00 +0200
Subject: [PATCH] Other improvements in the splitPDF() function

---
 file.js | 33 +++++++++++++++------------------
 temp.js |  0
 2 files changed, 15 insertions(+), 18 deletions(-)
 create mode 100644 temp.js

diff --git a/file.js b/file.js
index e37fbd7..073b1e6 100644
--- a/file.js
+++ b/file.js
@@ -227,6 +227,12 @@ async function splitExcelFile(inputFile) {
     }
 }
 
+const getCodiceFiscale = (pageText) => {
+    if (!pageText) return null;
+    const match = pageText.match(/Codice fiscale:\s*([A-Za-z0-9]+)/i);
+    return match ? match[1].toUpperCase() : null; // match[1] is the captured code
+};
+
 async function splitPDF(numRows, inputFile, tempFiles) {
     console.log(`Loading pdf file: ${ inputFile }...\n`);
     let parser;
@@ -242,27 +248,18 @@ async function splitPDF(numRows, inputFile, tempFiles) {
         // 2. we use pdf-lib to create and edit a pdf file
         const srcPdf = await PDFDocument.load(existingPdfBytes);
 
-        // if there are duplicates (back to back duplicates), I only have to print one copy
+        // if there are duplicates, I only have to print one copy
         if (pagesNumber > numRows) { // comparison between the number of pages of the pdf file and those of the excel file
-            let displayNumPage = 1;
-            let lastPrintedText = null;
-
+            let index = 1;
             for (let i = 0; i < pagesNumber; i++) {
-                let pageText = result.pages[i].text.trim();
-
-                // Only print if the current page is different from the immediate previous page
-                if (pageText !== lastPrintedText) {
-                    /*console.log(`--- PAGE ${displayNumPage} ---`);
-                    console.log(pageText);
-                    console.log("\n");*/
-
-                    // Remember this text for the next iteration
-                    lastPrintedText = pageText; 
-
-                    await processPage(srcPdf, i, tempFiles);
-                    displayNumPage++;
+                // we use optional chaining ?. so that when we encounter null or undefined values, the code doesn't crash
+                const prevCF = getCodiceFiscale(result.pages[i + 1]?.text);
+                const currentCF = getCodiceFiscale(result.pages[i].text);
+                if (prevCF && prevCF === currentCF) {
+                    continue;
                 }
-                i++;
+                await processPage(srcPdf, i, tempFiles);
+                index++;
             }
         }
         else {
diff --git a/temp.js b/temp.js
new file mode 100644
index 0000000..e69de29