From ec98687bdb44acaba17180eedbb1e966ac60dcfb Mon Sep 17 00:00:00 2001 From: shatfield4 Date: Mon, 14 Jul 2025 13:40:35 -0700 Subject: [PATCH] sanitize youtube transcription file paths --- collector/utils/extensions/YoutubeTranscript/index.js | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/collector/utils/extensions/YoutubeTranscript/index.js b/collector/utils/extensions/YoutubeTranscript/index.js index 0e1e13feb14..22352a4a968 100644 --- a/collector/utils/extensions/YoutubeTranscript/index.js +++ b/collector/utils/extensions/YoutubeTranscript/index.js @@ -2,7 +2,7 @@ const fs = require("fs"); const path = require("path"); const { default: slugify } = require("slugify"); const { v4 } = require("uuid"); -const { writeToServerDocuments } = require("../../files"); +const { writeToServerDocuments, sanitizeFileName } = require("../../files"); const { tokenizeString } = require("../../tokenizer"); const { YoutubeLoader } = require("./YoutubeLoader"); @@ -89,9 +89,9 @@ async function loadYouTubeTranscript({ url }) { }; } const { content, metadata } = transcriptResults; - const outFolder = slugify( - `${metadata.author} YouTube transcripts` - ).toLowerCase(); + const outFolder = sanitizeFileName( + slugify(`${metadata.author} YouTube transcripts`).toLowerCase() + ); const outFolderPath = process.env.NODE_ENV === "development" @@ -121,7 +121,7 @@ async function loadYouTubeTranscript({ url }) { console.log(`[YouTube Loader]: Saving ${metadata.title} to ${outFolder}`); writeToServerDocuments( data, - `${slugify(metadata.title)}-${data.id}`, + sanitizeFileName(`${slugify(metadata.title)}-${data.id}`), outFolderPath );