(converter) Reduce DomSample logging for NOT_FOUND

This reverts commit b7a5219ed3.

code/functions/live-capture/api/java/nu/marginalia/api/domsample/DomSampleClient.java

@@ -41,7 +41,7 @@ public class DomSampleClient {
         }
         catch (StatusRuntimeException sre) {
             if (sre.getStatus() != Status.NOT_FOUND) {
-                logger.error("Failed to fetch DOM sample");
+                logger.error("Failed to fetch DOM sample", sre);
             }
             return Optional.empty();
         }

code/processes/converting-process/build.gradle

@@ -90,6 +90,7 @@ dependencies {
     implementation libs.commons.lang3
     implementation libs.commons.compress
     implementation libs.sqlite
+    implementation libs.bundles.grpc
 
     implementation libs.bundles.httpcomponents
 

code/processes/converting-process/ft-dom-classifier/resources/request-classifier.xml

@@ -15,6 +15,7 @@
     <classifier target="url-regex" rule="tracking">/ccm/collect$</classifier>
     <classifier target="url-regex" rule="tracking">^/[0-9]+\.js$</classifier>
     <classifier target="url-regex" rule="tracking">^/[a-z0-9]\.gif$</classifier>
+    <classifier target="url-regex" rule="tracking">^/pixel\.gif$</classifier>
     <classifier target="url-regex" rule="ads">/pagead/</classifier>
     <classifier target="url-regex" rule="ads">/google-ads/</classifier>
 

code/processes/converting-process/java/nu/marginalia/converting/processor/DomainProcessor.java

@@ -1,6 +1,8 @@
 package nu.marginalia.converting.processor;
 
 import com.google.inject.Inject;
+import io.grpc.Status;
+import io.grpc.StatusRuntimeException;
 import nu.marginalia.api.domsample.DomSampleClient;
 import nu.marginalia.atags.model.DomainLinks;
 import nu.marginalia.atags.source.AnchorTagsSource;
@@ -98,10 +100,15 @@ public class DomainProcessor {
         return domSampleClient
                 .getSampleAsync(domainName, domSampleExecutor)
                 .thenApply(domSampleClassifier::classifySample)
-                .handle((a,b) ->
+                .handle((a,b) -> {
-                        Objects.requireNonNullElseGet(a,
+                    if (b != null) {
-                                () -> EnumSet.of(DomSampleClassification.UNCLASSIFIED)))
+                        if (!(b instanceof StatusRuntimeException sre && sre.getStatus() != Status.NOT_FOUND)) {
-                .get();
+                            logger.warn("Exception when fetching sample data", b);
+                        }
+                        return EnumSet.of(DomSampleClassification.UNCLASSIFIED);
+                    }
+                    return a;
+                }).get();
     }
 
     @Nullable

code/processes/converting-process/java/nu/marginalia/converting/processor/plugin/HtmlDocumentProcessorPlugin.java

@@ -161,7 +161,6 @@ public class HtmlDocumentProcessorPlugin extends AbstractDocumentProcessorPlugin
 
         final Set<HtmlFeature> features = featureExtractor.getFeatures(url, doc, documentHeaders, dld);
 
-
         if (!documentLengthLogic.validateLength(dld, specialization.lengthModifier() * documentClass.lengthLimitModifier())) {
             features.add(HtmlFeature.SHORT_DOCUMENT);
         }

code/processes/converting-process/java/nu/marginalia/converting/processor/plugin/PdfDocumentProcessorPlugin.java

@@ -115,7 +115,9 @@ public class PdfDocumentProcessorPlugin extends AbstractDocumentProcessorPlugin
 
         ret.quality = -5;
 
-        ret.features = Set.of(HtmlFeature.PDF);
+        ret.features = new HashSet<>(); // must be mutable!
+        ret.features.add(HtmlFeature.PDF);
+
         ret.description = getDescription(doc);
         ret.hashCode = dld.localitySensitiveHashCode();
 

deploy.txt

@@ -10,4 +10,5 @@
 2025-05-08:  Deploy assistant.
 2025-05-17:  Redeploy all.
 2025-05-28:  Deploy assistant and browserless.
-2025-06-06:  Deploy assistant and browserless.
+2025-06-06:  Deploy assistant and browserless.
+2025-07-21:  Deploy executor partition 1.