Expose preserve_original in edge_ngram token filter (#55766)

The Lucene `preserve_original` setting is currently not supported in the `edge_ngram`
token filter. This change adds it with a default value of `false`.

Closes #55767

docs/reference/analysis/tokenfilters/edgengram-tokenfilter.asciidoc

@@ -136,7 +136,7 @@ The filter produces the following tokens:
 ==== Add to an analyzer
 
 The following <<indices-create-index,create index API>> request uses the
-`edge_ngram` filter to configure a new 
+`edge_ngram` filter to configure a new
 <<analysis-custom-analyzer,custom analyzer>>.
 
 [source,console]
@@ -173,6 +173,10 @@ See <<analysis-edgengram-tokenfilter-max-gram-limits>>.
 (Optional, integer)
 Minimum character length of a gram. Defaults to `1`.
 
+`preserve_original`::
+(Optional, boolean)
+Emits original token when set to `true`. Defaults to `false`.
+
 `side`::
 +
 --

modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/EdgeNGramTokenFilterFactory.java

@@ -44,12 +44,15 @@ public class EdgeNGramTokenFilterFactory extends AbstractTokenFilterFactory {
     public static final int SIDE_FRONT = 1;
     public static final int SIDE_BACK = 2;
     private final int side;
+    private final boolean preserveOriginal;
+    private static final String PRESERVE_ORIG_KEY = "preserve_original";
 
     EdgeNGramTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
         super(indexSettings, name, settings);
         this.minGram = settings.getAsInt("min_gram", 1);
         this.maxGram = settings.getAsInt("max_gram", 2);
         this.side = parseSide(settings.get("side", "front"));
+        this.preserveOriginal = settings.getAsBoolean(PRESERVE_ORIG_KEY, false);
     }
 
     static int parseSide(String side) {
@@ -69,8 +72,7 @@ public TokenStream create(TokenStream tokenStream) {
             result = new ReverseStringFilter(result);
         }
 
-        // TODO: Expose preserveOriginal
-        result = new EdgeNGramTokenFilter(result, minGram, maxGram, false);
+        result = new EdgeNGramTokenFilter(result, minGram, maxGram, preserveOriginal);
 
         // side=BACK is not supported anymore but applying ReverseStringFilter up-front and after the token filter has the same effect
         if (side == SIDE_BACK) {

modules/analysis-common/src/test/java/org/elasticsearch/analysis/common/EdgeNGramTokenFilterFactoryTests.java

@@ -0,0 +1,66 @@
+/*
+ * Licensed to Elasticsearch under one or more contributor
+ * license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright
+ * ownership. Elasticsearch licenses this file to you under
+ * the Apache License, Version 2.0 (the "License"); you may
+ * not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.elasticsearch.analysis.common;
+
+import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.standard.StandardTokenizer;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.env.Environment;
+import org.elasticsearch.index.analysis.AnalysisTestsHelper;
+import org.elasticsearch.index.analysis.TokenFilterFactory;
+import org.elasticsearch.test.ESTestCase;
+import org.elasticsearch.test.ESTokenStreamTestCase;
+
+import java.io.IOException;
+import java.io.StringReader;
+
+public class EdgeNGramTokenFilterFactoryTests extends ESTokenStreamTestCase {
+
+    public void testDefault() throws IOException {
+        ESTestCase.TestAnalysis analysis = AnalysisTestsHelper.createTestAnalysisFromSettings(
+            Settings.builder()
+                .put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
+                .put("index.analysis.filter.my_edge_ngram.type", "edge_ngram")
+                .build(),
+            new CommonAnalysisPlugin());
+        TokenFilterFactory tokenFilter = analysis.tokenFilter.get("my_edge_ngram");
+        String source = "foo";
+        String[] expected = new String[]{"f", "fo"};
+        Tokenizer tokenizer = new StandardTokenizer();
+        tokenizer.setReader(new StringReader(source));
+        assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
+    }
+
+    public void testPreserveOriginal() throws IOException {
+        ESTestCase.TestAnalysis analysis = AnalysisTestsHelper.createTestAnalysisFromSettings(
+            Settings.builder()
+                .put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
+                .put("index.analysis.filter.my_edge_ngram.type", "edge_ngram")
+                .put("index.analysis.filter.my_edge_ngram.preserve_original", true)
+                .build(),
+            new CommonAnalysisPlugin());
+        TokenFilterFactory tokenFilter = analysis.tokenFilter.get("my_edge_ngram");
+        String source = "foo";
+        String[] expected = new String[]{"f", "fo", "foo"};
+        Tokenizer tokenizer = new StandardTokenizer();
+        tokenizer.setReader(new StringReader(source));
+        assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
+    }
+}