Add a prebuilt ICU Analyzer (#34958)

The ICU plugin provides the building blocks of an analysis chain, but doesn't actually have a prebuilt analyzer. It would be a better for users if there was a simple analyzer that they could use out of the box, and also something we can point to from the CJK Analyzer docs as a superior alternative.

Relates to #34285

Author: romseygeek

docs/plugins/analysis-icu.asciidoc

@@ -26,6 +26,24 @@ characters.
 :plugin_name: analysis-icu
 include::install_remove.asciidoc[]
 
+[[analysis-icu-analyzer]]
+==== ICU Analyzer
+
+Performs basic normalization, tokenization and character folding, using the
+`icu_normalizer` char filter, `icu_tokenizer` and `icu_normalizer` token filter
+
+The following parameters are accepted:
+
+[horizontal]
+
+`method`::
+
+    Normalization method.  Accepts `nfkc`, `nfc` or `nfkc_cf` (default)
+
+`mode`::
+
+    Normalization mode.  Accepts `compose` (default) or `decompose`.
+
 [[analysis-icu-normalization-charfilter]]
 ==== ICU Normalization Character Filter
 

docs/reference/analysis/analyzers/lang-analyzer.asciidoc

@@ -421,6 +421,9 @@ PUT /catalan_example
 [[cjk-analyzer]]
 ===== `cjk` analyzer
 
+NOTE: You may find that `icu_analyzer` in the ICU analysis plugin works better
+for CJK text than the `cjk` analyzer.  Experiment with your text and queries.
+
 The `cjk` analyzer could be reimplemented as a `custom` analyzer as follows:
 
 [source,js]

plugins/analysis-icu/src/main/java/org/elasticsearch/index/analysis/IcuAnalyzerProvider.java

@@ -0,0 +1,67 @@
+/*
+ * 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.index.analysis;
+
+import com.ibm.icu.text.Normalizer2;
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.icu.ICUFoldingFilter;
+import org.apache.lucene.analysis.icu.ICUNormalizer2CharFilter;
+import org.apache.lucene.analysis.icu.segmentation.ICUTokenizer;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.env.Environment;
+import org.elasticsearch.index.IndexSettings;
+
+import java.io.Reader;
+
+public class IcuAnalyzerProvider extends AbstractIndexAnalyzerProvider<Analyzer> {
+
+    private final Normalizer2 normalizer;
+
+    public IcuAnalyzerProvider(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
+        super(indexSettings, name, settings);
+        String method = settings.get("method", "nfkc_cf");
+        String mode = settings.get("mode", "compose");
+        if (!"compose".equals(mode) && !"decompose".equals(mode)) {
+            throw new IllegalArgumentException("Unknown mode [" + mode + "] in analyzer [" + name +
+                "], expected one of [compose, decompose]");
+        }
+        Normalizer2 normalizer = Normalizer2.getInstance(
+            null, method, "compose".equals(mode) ? Normalizer2.Mode.COMPOSE : Normalizer2.Mode.DECOMPOSE);
+        this.normalizer = IcuNormalizerTokenFilterFactory.wrapWithUnicodeSetFilter(indexSettings, normalizer, settings);
+    }
+
+    @Override
+    public Analyzer get() {
+        return new Analyzer() {
+
+            @Override
+            protected Reader initReader(String fieldName, Reader reader) {
+                return new ICUNormalizer2CharFilter(reader, normalizer);
+            }
+
+            @Override
+            protected TokenStreamComponents createComponents(String fieldName) {
+                Tokenizer source = new ICUTokenizer();
+                return new TokenStreamComponents(source, new ICUFoldingFilter(source));
+            }
+        };
+    }
+}

plugins/analysis-icu/src/main/java/org/elasticsearch/plugin/analysis/icu/AnalysisICUPlugin.java

@@ -21,8 +21,11 @@
 
 import static java.util.Collections.singletonMap;
 
+import org.apache.lucene.analysis.Analyzer;
 import org.elasticsearch.common.io.stream.NamedWriteableRegistry;
+import org.elasticsearch.index.analysis.AnalyzerProvider;
 import org.elasticsearch.index.analysis.CharFilterFactory;
+import org.elasticsearch.index.analysis.IcuAnalyzerProvider;
 import org.elasticsearch.index.analysis.IcuCollationTokenFilterFactory;
 import org.elasticsearch.index.analysis.IcuFoldingTokenFilterFactory;
 import org.elasticsearch.index.analysis.IcuNormalizerCharFilterFactory;
@@ -60,6 +63,11 @@ public Map<String, AnalysisProvider<TokenFilterFactory>> getTokenFilters() {
         return extra;
     }
 
+    @Override
+    public Map<String, AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
+        return singletonMap("icu_analyzer", IcuAnalyzerProvider::new);
+    }
+
     @Override
     public Map<String, AnalysisProvider<TokenizerFactory>> getTokenizers() {
         return singletonMap("icu_tokenizer", IcuTokenizerFactory::new);

plugins/analysis-icu/src/test/java/org/elasticsearch/index/analysis/IcuAnalyzerTests.java

@@ -0,0 +1,96 @@
+/*
+ * 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.index.analysis;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.elasticsearch.Version;
+import org.elasticsearch.cluster.metadata.IndexMetaData;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.plugin.analysis.icu.AnalysisICUPlugin;
+import org.elasticsearch.test.IndexSettingsModule;
+
+import java.io.IOException;
+
+import static org.hamcrest.Matchers.containsString;
+
+public class IcuAnalyzerTests extends BaseTokenStreamTestCase {
+
+    public void testMixedAlphabetTokenization() throws IOException {
+
+        Settings settings = Settings.builder()
+            .put(IndexMetaData.SETTING_VERSION_CREATED, Version.CURRENT)
+            .build();
+        IndexSettings idxSettings = IndexSettingsModule.newIndexSettings("index", settings);
+
+        String input = "안녕은하철도999극장판2.1981년8월8일.일본개봉작1999년재더빙video판";
+
+        AnalysisICUPlugin plugin = new AnalysisICUPlugin();
+        Analyzer analyzer = plugin.getAnalyzers().get("icu_analyzer").get(idxSettings, null, "icu", settings).get();
+        assertAnalyzesTo(analyzer, input,
+            new String[]{"안녕은하철도", "999", "극장판", "2.1981", "년", "8", "월", "8", "일", "일본개봉작", "1999", "년재더빙", "video", "판"});
+
+    }
+
+    public void testMiddleDots() throws IOException {
+        Settings settings = Settings.builder()
+            .put(IndexMetaData.SETTING_VERSION_CREATED, Version.CURRENT)
+            .build();
+        IndexSettings idxSettings = IndexSettingsModule.newIndexSettings("index", settings);
+
+        String input = "경승지·산악·협곡·해협·곶·심연·폭포·호수·급류";
+
+        Analyzer analyzer = new IcuAnalyzerProvider(idxSettings, null, "icu", settings).get();
+        assertAnalyzesTo(analyzer, input,
+            new String[]{"경승지", "산악", "협곡", "해협", "곶", "심연", "폭포", "호수", "급류"});
+    }
+
+    public void testUnicodeNumericCharacters() throws IOException {
+
+        Settings settings = Settings.builder()
+            .put(IndexMetaData.SETTING_VERSION_CREATED, Version.CURRENT)
+            .build();
+        IndexSettings idxSettings = IndexSettingsModule.newIndexSettings("index", settings);
+
+        String input = "① ② ③ ⑴ ⑵ ⑶ ¼ ⅓ ⅜ ¹ ² ³ ₁ ₂ ₃";
+
+        Analyzer analyzer = new IcuAnalyzerProvider(idxSettings, null, "icu", settings).get();
+        assertAnalyzesTo(analyzer, input,
+            new String[]{"1", "2", "3", "1", "2", "3", "1/4", "1/3", "3/8", "1", "2", "3", "1", "2", "3"});
+    }
+
+    public void testBadSettings() {
+
+        Settings settings = Settings.builder()
+            .put(IndexMetaData.SETTING_VERSION_CREATED, Version.CURRENT)
+            .put("mode", "wrong")
+            .build();
+        IndexSettings idxSettings = IndexSettingsModule.newIndexSettings("index", settings);
+
+        IllegalArgumentException e = expectThrows(IllegalArgumentException.class, () -> {
+            new IcuAnalyzerProvider(idxSettings, null, "icu", settings);
+        });
+
+        assertThat(e.getMessage(), containsString("Unknown mode [wrong] in analyzer [icu], expected one of [compose, decompose]"));
+
+    }
+
+}