From 45f50ce13cc3bbb7e64630df7fc19cde6ec37afe Mon Sep 17 00:00:00 2001
From: Sean Hatfield <seanhatfield5@gmail.com>
Date: Tue, 19 Mar 2024 18:14:34 -0700
Subject: [PATCH] [FIX] Update metadata tags in PDF collector script (#925)
update title in pdf collector script to be the filename instead of metadata title
---
collector/processSingleFile/convert/asPDF.js | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/collector/processSingleFile/convert/asPDF.js b/collector/processSingleFile/convert/asPDF.js
index 560c4939f..e81fe6c76 100644
--- a/collector/processSingleFile/convert/asPDF.js
+++ b/collector/processSingleFile/convert/asPDF.js
@@ -40,9 +40,9 @@ async function asPDF({ fullFilePath = "", filename = "" }) {
const data = {
id: v4(),
url: "file://" + fullFilePath,
- title: docs[0]?.metadata?.pdf?.info?.Title || filename,
+ title: filename,
docAuthor: docs[0]?.metadata?.pdf?.info?.Creator || "no author found",
- description: "No description found.",
+ description: docs[0]?.metadata?.pdf?.info?.Title || "No description found.",
docSource: "pdf file uploaded by the user.",
chunkSource: "",
published: createdDate(fullFilePath),
--
GitLab