1
1
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-10-05 21:22:39 +02:00

Compare commits

...

4 Commits

Author SHA1 Message Date
Viktor Lofgren
97a6780ea3 (search) Add debug logging for specific query 2025-05-16 23:41:35 +02:00
Viktor Lofgren
eb634beec8 (search) Add debug logging for specific query 2025-05-16 23:34:03 +02:00
Viktor Lofgren
269ebd1654 Revert "(query) Add debug logging for specific query"
This reverts commit 39ce40bfeb.
2025-05-16 23:29:06 +02:00
Viktor Lofgren
39ce40bfeb (query) Add debug logging for specific query 2025-05-16 23:23:53 +02:00
2 changed files with 29 additions and 7 deletions

View File

@@ -112,6 +112,13 @@ public class SearchOperator {
.selectStrategy(queryResponse)
.clusterResults(queryResults, 25);
if (queryParams.humanQuery().equals("slackware linux")) {
logger.info("Query response: {}", queryResponse.results().subList(0, 5));
logger.info("Query results: {}", queryResults.subList(0, 5));
logger.info("Clustered results: {}", clusteredResults.subList(0, 5));
}
// Log the query and results
logger.info(queryMarker, "Human terms: {}", Strings.join(queryResponse.searchTermsHuman(), ','));

View File

@@ -25,13 +25,28 @@ public class UrlDeduplicator {
}
public boolean shouldRemove(DecoratedSearchResultItem details) {
if (!deduplicateOnSuperficialHash(details))
return true;
if (!deduplicateOnLSH(details))
return true;
if (!limitResultsPerDomain(details))
return true;
if (details.url.domain.topDomain.equals("slackware.com")) {
if (!deduplicateOnSuperficialHash(details)) {
logger.info("Rejecting on superficial hash " + details.url);
return true;
}
if (!deduplicateOnLSH(details)) {
logger.info("Rejecting on LSH for " + details.url);
return true;
}
if (!limitResultsPerDomain(details)) {
logger.info("Rejecting on limitResultsPerDomain for " + details.url);
return true;
}
}
else {
if (!deduplicateOnSuperficialHash(details))
return true;
if (!deduplicateOnLSH(details))
return true;
if (!limitResultsPerDomain(details))
return true;
}
return false;
}