From 2e304ed09a9b475187328803c5fa0f095a2deaf2 Mon Sep 17 00:00:00 2001
From: Tatu Wikman <tatu.wikman@gmail.com>
Date: Wed, 18 Dec 2024 13:33:30 +0200
Subject: [PATCH] better documentation deleteComma in isTextInPDF

---
 src/utils/file.ts | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/src/utils/file.ts b/src/utils/file.ts
index 82045efe..36c44524 100644
--- a/src/utils/file.ts
+++ b/src/utils/file.ts
@@ -100,7 +100,7 @@ export default {
    * Check text in PDF
    * @param filePath {string|null} Path of the PDF file
    * @param text {string} Text to check on the file
-   * @param deleteComma {boolean} True if we need to delete comma
+   * @param deleteComma {boolean} True if we need to delete comma. PDF to txt conversion adds comma where newlines are.
    * @returns {Promise<boolean>}
    */
   async isTextInPDF(filePath: string | null, text: string, deleteComma: boolean = false): Promise<boolean> {
@@ -120,6 +120,7 @@ export default {
 
     const pageTexts = await Promise.all(pageTextPromises);
 
+    // delete commas from the page text. getPageTextFromPdf adds commas to newlines in some cases
     if (deleteComma) {
       return ((pageTexts.join(' ').split(/,\//).join('/').split(/,\s*,?/)
         .join(' '))