Enable setting max-occurrences in field match.

3 files changed, 10 insertions, 0 deletions

diff --git a/indexinglanguage/src/main/java/com/yahoo/vespa/indexinglanguage/expressions/TokenizeExpression.java b/indexinglanguage/src/main/java/com/yahoo/vespa/indexinglanguage/expressions/TokenizeExpression.java
index 169b79a62af..b807ad4cb65 100644
--- a/indexinglanguage/src/main/java/com/yahoo/vespa/indexinglanguage/expressions/TokenizeExpression.java
+++ b/indexinglanguage/src/main/java/com/yahoo/vespa/indexinglanguage/expressions/TokenizeExpression.java
@@ -69,6 +69,9 @@ public final class TokenizeExpression extends Expression {
         if (config.hasNonDefaultMaxTokenLength()) {
             ret.append(" max-length:" + config.getMaxTokenizeLength());
         }
+        if (config.hasNonDefaultMaxTermOccurrences()) {
+            ret.append(" max-occurrences:" + config.getMaxTermOccurrences());
+        }
         return ret.toString();
     }
 
diff --git a/indexinglanguage/src/main/java/com/yahoo/vespa/indexinglanguage/linguistics/AnnotatorConfig.java b/indexinglanguage/src/main/java/com/yahoo/vespa/indexinglanguage/linguistics/AnnotatorConfig.java
index 5c1bf0813c4..7b6f350d831 100644
--- a/indexinglanguage/src/main/java/com/yahoo/vespa/indexinglanguage/linguistics/AnnotatorConfig.java
+++ b/indexinglanguage/src/main/java/com/yahoo/vespa/indexinglanguage/linguistics/AnnotatorConfig.java
@@ -95,6 +95,10 @@ public class AnnotatorConfig implements Cloneable {
         return maxTokenizeLength != DEFAULT_MAX_TOKENIZE_LENGTH;
     }
 
+    public boolean hasNonDefaultMaxTermOccurrences() {
+        return maxTermOccurrences != DEFAULT_MAX_TERM_OCCURRENCES;
+    }
+
     @Override
     public boolean equals(Object obj) {
         if (!(obj instanceof AnnotatorConfig rhs)) {
diff --git a/indexinglanguage/src/main/javacc/IndexingParser.jj b/indexinglanguage/src/main/javacc/IndexingParser.jj
index ea05f33d745..42bbd26cee6 100644
--- a/indexinglanguage/src/main/javacc/IndexingParser.jj
+++ b/indexinglanguage/src/main/javacc/IndexingParser.jj
@@ -173,6 +173,7 @@ TOKEN :
     <JOIN: "join"> |
     <LOWER_CASE: "lowercase"> |
     <MAX_LENGTH: "max-length"> |
+    <MAX_OCCURRENCES: "max-occurrences"> |
     <NGRAM: "ngram"> |
     <NORMALIZE: "normalize"> |
     <NOW: "now"> |
@@ -664,10 +665,12 @@ AnnotatorConfig tokenizeCfg() :
     AnnotatorConfig val = new AnnotatorConfig(annotatorCfg);
     String str = "SHORTEST";
     Integer maxLength;
+    Integer maxTermOccurrences;
 }
 {
     ( <STEM> ( <COLON> str = string() ) ? { val.setStemMode(str); } |
       <MAX_LENGTH> <COLON>  maxLength = integer() { val.setMaxTokenLength(maxLength); } |
+      <MAX_OCCURRENCES> <COLON>  maxTermOccurrences = integer() { val.setMaxTermOccurrences(maxTermOccurrences); } |
       <NORMALIZE> { val.setRemoveAccents(true); } )+
     { return val; }
 }