Alignment operator source adjust.

engine/src/main/java/nl/inl/blacklab/search/lucene/SpansCaptureRelationsBetweenSpans.java

@@ -117,6 +117,12 @@ public String toString() {
     /** List of relations captured for current hit */
     private List<RelationInfo> capturedRelations = new ArrayList<>();
 
+    /** Start of current (source) hit (covers all sources of captured relations) */
+    private int adjustedStart;
+
+    /** End of current (source) hit (covers all sources of captured relations) */
+    private int adjustedEnd;
+
     /**
      * Construct a SpansCaptureRelationsWithinSpan.
      *
@@ -128,6 +134,24 @@ public SpansCaptureRelationsBetweenSpans(BLSpans source, List<Target> targets) {
         this.targets = targets;
     }
 
+    @Override
+    public int startPosition() {
+        if (atFirstInCurrentDoc)
+            return -1;
+        if (startPos == -1 || startPos == NO_MORE_POSITIONS)
+            return startPos;
+        return adjustedStart;
+    }
+
+    @Override
+    public int endPosition() {
+        if (atFirstInCurrentDoc)
+            return -1;
+        if (startPos == -1 || startPos == NO_MORE_POSITIONS)
+            return startPos;
+        return adjustedEnd;
+    }
+
     @Override
     protected FilterSpans.AcceptStatus accept(BLSpans candidate) throws IOException {
         // Prepare matchInfo so we can add captured relations to it
@@ -139,8 +163,12 @@ protected FilterSpans.AcceptStatus accept(BLSpans candidate) throws IOException
         candidate.getMatchInfo(matchInfo);
 
         // Find current source span
-        int sourceStart = startPosition();
-        int sourceEnd = endPosition();
+        int sourceStart = candidate.startPosition();
+        int sourceEnd = candidate.endPosition();
+
+        // Our final (source) span will cover all captured relations.
+        adjustedStart = sourceStart;
+        adjustedEnd = sourceEnd;
 
         for (Target target: targets) {
 
@@ -198,6 +226,7 @@ protected FilterSpans.AcceptStatus accept(BLSpans candidate) throws IOException
                             target.targetField);
                 }
 
+                updateSourceStartEndWithCapturedRelations(); // update start/end to cover all captured relations
                 continue;
             }
 
@@ -244,6 +273,8 @@ protected FilterSpans.AcceptStatus accept(BLSpans candidate) throws IOException
                 capturedRelations.sort(RelationInfo::compareTo);
                 matchInfo[target.captureAsIndex] = RelationListInfo.create(capturedRelations, getOverriddenField());
                 target.target.getMatchInfo(finalTargetIndex, matchInfo); // also perform captures on the target
+
+                updateSourceStartEndWithCapturedRelations(); // update start/end to cover all captured relations
             } else {
                 // Target document has no matches. Reject this hit.
                 return FilterSpans.AcceptStatus.NO;
@@ -253,6 +284,17 @@ protected FilterSpans.AcceptStatus accept(BLSpans candidate) throws IOException
         return FilterSpans.AcceptStatus.YES;
     }
 
+    private void updateSourceStartEndWithCapturedRelations() {
+        // Our final (source) span will cover all captured relations, so that
+        // e.g. "the" =sentence-alignment=>nl "de" will have the aligned sentences as hits, not just single words.
+        capturedRelations.forEach(r -> {
+            if (r.getSourceStart() < adjustedStart)
+                adjustedStart = r.getSourceStart();
+            if (r.getSourceEnd() > adjustedEnd)
+                adjustedEnd = r.getSourceEnd();
+        });
+    }
+
     @Override
     public String toString() {
         return "==>(" + in + ", " + targets + ")";