From fc69f3b8f3a538e5b8d89c197081a28f6e501b4f Mon Sep 17 00:00:00 2001
From: Sylvain Pasche <sylvain.pasche@gmail.com>
Date: Sun, 18 Sep 2022 18:14:25 +0200
Subject: [PATCH] let import continue when malformed URLs are encountered

In case of malformed URLs in imported HTML, keep original URL instead
of having the import get stuck.
---
 src/services/import/zip.js | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/src/services/import/zip.js b/src/services/import/zip.js
index 09639c3b1..e182126c1 100644
--- a/src/services/import/zip.js
+++ b/src/services/import/zip.js
@@ -292,7 +292,12 @@ async function importZip(taskContext, fileBuffer, importRootNote) {
             content = content.replace(/<\/body>.*<\/html>/gis, "");
 
             content = content.replace(/src="([^"]*)"/g, (match, url) => {
-                url = decodeURIComponent(url);
+                try {
+                    url = decodeURIComponent(url);
+                } catch (e) {
+                    log.error(`Cannot parse image URL '${url}', keeping original (${e}).`);
+                    return `src="${url}"`;
+                }
 
                 if (isUrlAbsolute(url) || url.startsWith("/")) {
                     return match;
@@ -304,7 +309,12 @@ async function importZip(taskContext, fileBuffer, importRootNote) {
             });
 
             content = content.replace(/href="([^"]*)"/g, (match, url) => {
-                url = decodeURIComponent(url);
+                try {
+                    url = decodeURIComponent(url);
+                } catch (e) {
+                    log.error(`Cannot parse link URL '${url}', keeping original (${e}).`);
+                    return `href="${url}"`;
+                }
 
                 if (isUrlAbsolute(url)) {
                     return match;