Mirror/MarginaliaSearch
1
0
Fork 0
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-02-23 21:18:58 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Better SiteWords extraction

Browse Source
This commit is contained in:
Viktor Lofgren 2023-01-30 09:42:46 +01:00
parent 5558af148e
commit 65b0ff26fc
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
marginalia_nu/src/main/java/nu/marginalia/wmsa/edge/converting/processor/SiteWords.java
View File

@ -33,8 +33,7 @@ public class SiteWords {
Set<String> commonSiteWords = new HashSet<>(10);
commonSiteWords.addAll(commonKeywordExtractor.getCommonSiteWords(processedDomain,
EdgePageWordFlags.Subjects,
EdgePageWordFlags.TfIdfHigh));
EdgePageWordFlags.Subjects));
commonSiteWords.addAll(commonKeywordExtractor.getCommonSiteWords(processedDomain,
EdgePageWordFlags.Title));