Mirror/MarginaliaSearch
1
0
Fork 0
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-02-23 13:09:00 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

(encyclopedia) Add URLencoding to path element

Browse Source 
This prevents corruption of the links to the sideloaded encyclopedia data when the article path contains characters that are not valid in a URL.
This commit is contained in:
Viktor Lofgren 2024-03-01 17:28:09 +01:00
parent 9689f3faee
commit 29bf473d74
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
code/processes/converting-process/java/nu/marginalia/converting/sideload/encyclopedia/EncyclopediaMarginaliaNuSideloader.java
View File

@ -1,6 +1,7 @@
package nu.marginalia.converting.sideload.encyclopedia;
import com.github.luben.zstd.ZstdInputStream;
import com.google.common.base.Charsets;
import com.google.gson.Gson;
import lombok.SneakyThrows;
import nu.marginalia.atags.AnchorTextKeywords;
@ -110,7 +111,7 @@ public class EncyclopediaMarginaliaNuSideloader implements SideloadSource, AutoC
}
private ProcessedDocument convertDocument(List<String> parts, String title, String url, DomainLinks domainLinks) throws URISyntaxException, DisqualifiedException {
String fullUrl = baseUrl.toString() + url;
String fullUrl = baseUrl.toString() + URLEncoder.encode(url, Charsets.UTF_8);
StringBuilder fullHtml = new StringBuilder();
fullHtml