Add source fallback support for match_only_text mapped type (#89473)

This change adds access to mapped match_only_text fields via the Painless scripting fields API. The 
values returned from a match_only_text field via the scripting fields API always use source as described 
by (#81246). These are not available via doc values so there are no bwc issues.

docs/changelog/89473.yaml

@@ -0,0 +1,5 @@
+pr: 89473
+summary: Add source fallback support for `match_only_text` mapped type
+area: Mapping
+type: enhancement
+issues: []

modules/lang-painless/src/yamlRestTest/resources/rest-api-spec/test/painless/50_script_doc_values.yml

@@ -81,6 +81,8 @@ setup:
                             fielddata: true
                         text_no_field_data:
                             type: text
+                        match_only_text:
+                          type: match_only_text
                         token_count:
                             type: token_count
                             analyzer: standard
@@ -125,6 +127,7 @@ setup:
                 scaled_float_no_doc_values: 3.14
                 text: "Lots of text."
                 text_no_field_data: "Lots of text."
+                match_only_text: "Lots of text."
                 token_count: count all these words please
 
     - do:
@@ -169,7 +172,7 @@ setup:
               scaled_float_no_doc_values: [2.5, -3.5]
               text: ["Lots of text.", "even more text", "SOOOOO much text"]
               text_no_field_data: ["Lots of text.", "even more text", "SOOOOO much text"]
-
+              match_only_text: ["Lots of text.", "even more text", "SOOOOO much text"]
 
     - do:
         indices.refresh: {}
@@ -3234,6 +3237,136 @@ setup:
   - match: { hits.hits.1.fields.field.0: "0" }
   - match: { hits.hits.2.fields.field.0: "Lots of text.SOOOOO much texteven more text3" }
 
+---
+"match_only_text":
+  - do:
+      catch: bad_request
+      search:
+        rest_total_hits_as_int: true
+        body:
+          query: { term: { _id: "1" } }
+          script_fields:
+            field:
+              script:
+                source: "doc['match_only_text'].get(0)"
+  - match: { error.failed_shards.0.reason.caused_by.type: "illegal_argument_exception" }
+
+  - do:
+      catch: bad_request
+      search:
+        rest_total_hits_as_int: true
+        body:
+          query: { term: { _id: "1" } }
+          script_fields:
+            field:
+              script:
+                source: "doc['match_only_text'].value"
+  - match: { error.failed_shards.0.reason.caused_by.type: "illegal_argument_exception" }
+
+  - do:
+      search:
+        rest_total_hits_as_int: true
+        body:
+          sort: [ { rank: asc } ]
+          script_fields:
+            field:
+              script:
+                source: "field('match_only_text').get('')"
+  - match: { hits.hits.0.fields.field.0: "Lots of text." }
+  - match: { hits.hits.1.fields.field.0: "" }
+  - match: { hits.hits.2.fields.field.0: "Lots of text." }
+
+  - do:
+      search:
+        rest_total_hits_as_int: true
+        body:
+          sort: [ { rank: asc } ]
+          script_fields:
+            field:
+              script:
+                source: "/* avoid yaml stash */ $('match_only_text', '')"
+  - match: { hits.hits.0.fields.field.0: "Lots of text." }
+  - match: { hits.hits.1.fields.field.0: "" }
+  - match: { hits.hits.2.fields.field.0: "Lots of text." }
+
+  - do:
+      search:
+        rest_total_hits_as_int: true
+        body:
+          sort: [ { rank: asc } ]
+          script_fields:
+            field:
+              script:
+                source: "String defaultText = 'default text'; field('match_only_text').get(defaultText)"
+  - match: { hits.hits.0.fields.field.0: "Lots of text." }
+  - match: { hits.hits.1.fields.field.0: "default text" }
+  - match: { hits.hits.2.fields.field.0: "Lots of text." }
+
+  - do:
+      search:
+        rest_total_hits_as_int: true
+        body:
+          sort: [ { rank: asc } ]
+          script_fields:
+            field:
+              script:
+                source: "String defaultText = 'default text'; $('match_only_text', defaultText)"
+  - match: { hits.hits.0.fields.field.0: "Lots of text." }
+  - match: { hits.hits.1.fields.field.0: "default text" }
+  - match: { hits.hits.2.fields.field.0: "Lots of text." }
+
+  - do:
+      search:
+        rest_total_hits_as_int: true
+        body:
+          sort: [ { rank: asc } ]
+          script_fields:
+            field:
+              script:
+                source: "field('match_only_text').get(1, '')"
+  - match: { hits.hits.0.fields.field.0: "" }
+  - match: { hits.hits.1.fields.field.0: "" }
+  - match: { hits.hits.2.fields.field.0: "SOOOOO much text" }
+
+  - do:
+      search:
+        rest_total_hits_as_int: true
+        body:
+          sort: [ { rank: asc } ]
+          script_fields:
+            field:
+              script:
+                source: "String defaultText = 'default text'; field('match_only_text').get(1, defaultText)"
+  - match: { hits.hits.0.fields.field.0: "default text" }
+  - match: { hits.hits.1.fields.field.0: "default text" }
+  - match: { hits.hits.2.fields.field.0: "SOOOOO much text" }
+
+  - do:
+      search:
+        rest_total_hits_as_int: true
+        body:
+          sort: [ { rank: asc } ]
+          script_fields:
+            field:
+              script:
+                source: "field('match_only_text').get(1, '')"
+  - match: { hits.hits.0.fields.field.0: "" }
+  - match: { hits.hits.1.fields.field.0: "" }
+  - match: { hits.hits.2.fields.field.0: "SOOOOO much text" }
+
+  - do:
+      search:
+        rest_total_hits_as_int: true
+        body:
+          sort: [ { rank: asc } ]
+          script_fields:
+            field:
+              script:
+                source: "String cat = ''; for (String s : field('match_only_text')) { cat += s; } cat + field('match_only_text').size();"
+  - match: { hits.hits.0.fields.field.0: "Lots of text.1" }
+  - match: { hits.hits.1.fields.field.0: "0" }
+  - match: { hits.hits.2.fields.field.0: "Lots of text.SOOOOO much texteven more text3" }
+
 ---
 "version and sequence number":
   - do:

modules/mapper-extras/src/main/java/org/elasticsearch/index/mapper/extras/MatchOnlyTextFieldMapper.java

@@ -33,6 +33,7 @@
 import org.elasticsearch.index.analysis.NamedAnalyzer;
 import org.elasticsearch.index.fielddata.FieldDataContext;
 import org.elasticsearch.index.fielddata.IndexFieldData;
+import org.elasticsearch.index.fielddata.SourceValueFetcherSortedBinaryIndexFieldData;
 import org.elasticsearch.index.mapper.DocumentParserContext;
 import org.elasticsearch.index.mapper.FieldMapper;
 import org.elasticsearch.index.mapper.MapperBuilderContext;
@@ -44,6 +45,8 @@
 import org.elasticsearch.index.mapper.TextSearchInfo;
 import org.elasticsearch.index.mapper.ValueFetcher;
 import org.elasticsearch.index.query.SearchExecutionContext;
+import org.elasticsearch.script.field.TextDocValuesField;
+import org.elasticsearch.search.aggregations.support.CoreValuesSourceType;
 import org.elasticsearch.search.lookup.SourceLookup;
 
 import java.io.IOException;
@@ -276,6 +279,16 @@ public Query phrasePrefixQuery(TokenStream stream, int slop, int maxExpansions,
 
         @Override
         public IndexFieldData.Builder fielddataBuilder(FieldDataContext fieldDataContext) {
+            if (fieldDataContext.fielddataOperation() == FielddataOperation.SCRIPT) {
+                return new SourceValueFetcherSortedBinaryIndexFieldData.Builder(
+                    name(),
+                    CoreValuesSourceType.KEYWORD,
+                    SourceValueFetcher.toString(fieldDataContext.sourcePathsLookup().apply(name())),
+                    fieldDataContext.lookupSupplier().get().source(),
+                    TextDocValuesField::new
+                );
+            }
+
             throw new IllegalArgumentException(CONTENT_TYPE + " fields do not support sorting and aggregations");
         }
 

server/src/main/java/org/elasticsearch/script/field/MatchOnlyTextDocValuesField.java

@@ -0,0 +1,18 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0 and the Server Side Public License, v 1; you may not use this file except
+ * in compliance with, at your election, the Elastic License 2.0 or the Server
+ * Side Public License, v 1.
+ */
+
+package org.elasticsearch.script.field;
+
+import org.elasticsearch.index.fielddata.SortedBinaryDocValues;
+
+public class MatchOnlyTextDocValuesField extends BaseKeywordDocValuesField {
+
+    public MatchOnlyTextDocValuesField(SortedBinaryDocValues input, String name) {
+        super(input, name);
+    }
+}