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

(index) Further ranking adjustments

Browse Source
This commit is contained in:
Viktor Lofgren 2024-01-01 18:51:03 +01:00
parent 50771045d0
commit fc6e3b6da0
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
code/features-index/result-ranking/src/main/java/nu/marginalia/ranking/ResultValuator.java
View File

@ -137,11 +137,13 @@ public class ResultValuator {
double penalty = 0;
boolean isForum = DocumentFlags.GeneratorForum.isPresent(docFlags);
boolean isWiki = DocumentFlags.GeneratorWiki.isPresent(docFlags);
boolean isDocs = DocumentFlags.GeneratorDocs.isPresent(docFlags);
// Penalize large sites harder for any bullshit as it's a strong signal of a low quality site
double largeSiteFactor = 1.;
if (!isForum && size > 400) {
if (!isForum && !isWiki && !isDocs && size > 400) {
// Long urls-that-look-like-this tend to be poor search results
if (DocumentMetadata.hasFlags(featureFlags, HtmlFeature.KEBAB_CASE_URL.getFeatureBit()))
penalty += 30.0;
@ -161,7 +163,7 @@ public class ResultValuator {
if (DocumentMetadata.hasFlags(featureFlags, HtmlFeature.TRACKING.getFeatureBit()))
penalty += 2.5 * largeSiteFactor;
if (isForum) {
if (isForum || isWiki || isDocs) {
penalty = Math.min(0, penalty - 2);
}