expose simple pattern tokenizers (#25159)

Expose the experimental simplepattern and 
simplepatternsplit tokenizers in the common 
analysis plugin. They provide tokenization based 
on regular expressions, using Lucene's 
deterministic regex implementation that is usually 
faster than Java's and has protections against 
creating too-deep stacks during matching.

Both have a not-very-useful default pattern of the 
empty string because all tokenizer factories must 
be able to be instantiated at index creation time. 
They should always be configured by the user 
in practice.

docs/reference/analysis/tokenizers.asciidoc

@@ -97,6 +97,18 @@ The `pattern` tokenizer uses a regular expression to either split text into
 terms whenever it matches a word separator, or to capture matching text as
 terms.
 
+<<analysis-simplepattern-tokenizer,Simple Pattern Tokenizer>>::
+
+The `simplepattern` tokenizer uses a regular expression to capture matching
+text as terms. It uses a restricted subset of regular expression features
+and is generally faster than the `pattern` tokenizer.
+
+<<analysis-simplepatternsplit-tokenizer,Simple Pattern Split Tokenizer>>::
+
+The `simplepatternsplit` tokenizer uses the same restricted regular expression
+subset as the `simplepattern` tokenizer, but splits the input at matches rather
+than returning the matches as terms.
+
 <<analysis-pathhierarchy-tokenizer,Path Tokenizer>>::
 
 The `path_hierarchy` tokenizer takes a hierarchical value like a filesystem
@@ -131,6 +143,8 @@ include::tokenizers/keyword-tokenizer.asciidoc[]
 
 include::tokenizers/pattern-tokenizer.asciidoc[]
 
+include::tokenizers/simplepattern-tokenizer.asciidoc[]
+
+include::tokenizers/simplepatternsplit-tokenizer.asciidoc[]
+
 include::tokenizers/pathhierarchy-tokenizer.asciidoc[]
-
-

docs/reference/analysis/tokenizers/simplepattern-tokenizer.asciidoc

@@ -0,0 +1,105 @@
+[[analysis-simplepattern-tokenizer]]
+=== Simple Pattern Tokenizer
+
+experimental[]
+
+The `simplepattern` tokenizer uses a regular expression to capture matching
+text as terms. The set of regular expression features it supports is more
+limited than the <<analysis-pattern-tokenizer,`pattern`>> tokenizer, but the
+tokenization is generally faster.
+
+This tokenizer does not support splitting the input on a pattern match, unlike
+the <<analysis-pattern-tokenizer,`pattern`>> tokenizer. To split on pattern
+matches using the same restricted regular expression subset, see the
+<<analysis-simplepatternsplit-tokenizer,`simplepatternsplit`>> tokenizer.
+
+This tokenizer uses {lucene-core-javadoc}/org/apache/lucene/util/automaton/RegExp.html[Lucene regular expressions].
+For an explanation of the supported features and syntax, see <<regexp-syntax,Regular Expression Syntax>>.
+
+The default pattern is the empty string, which produces no terms. This
+tokenizer should always be configured with a non-default pattern.
+
+[float]
+=== Configuration
+
+The `simplepattern` tokenizer accepts the following parameters:
+
+[horizontal]
+`pattern`::
+    {lucene-core-javadoc}/org/apache/lucene/util/automaton/RegExp.html[Lucene regular expression], defaults to the empty string.
+
+[float]
+=== Example configuration
+
+This example configures the `simplepattern` tokenizer to produce terms that are
+three-digit numbers
+
+[source,js]
+----------------------------
+PUT my_index
+{
+  "settings": {
+    "analysis": {
+      "analyzer": {
+        "my_analyzer": {
+          "tokenizer": "my_tokenizer"
+        }
+      },
+      "tokenizer": {
+        "my_tokenizer": {
+          "type": "simplepattern",
+          "pattern": "[0123456789]{3}"
+        }
+      }
+    }
+  }
+}
+
+POST my_index/_analyze
+{
+  "analyzer": "my_analyzer",
+  "text": "fd-786-335-514-x"
+}
+----------------------------
+// CONSOLE
+
+/////////////////////
+
+[source,js]
+----------------------------
+{
+  "tokens" : [
+    {
+      "token" : "786",
+      "start_offset" : 3,
+      "end_offset" : 6,
+      "type" : "word",
+      "position" : 0
+    },
+    {
+      "token" : "335",
+      "start_offset" : 7,
+      "end_offset" : 10,
+      "type" : "word",
+      "position" : 1
+    },
+    {
+      "token" : "514",
+      "start_offset" : 11,
+      "end_offset" : 14,
+      "type" : "word",
+      "position" : 2
+    }
+  ]
+}
+----------------------------
+// TESTRESPONSE
+
+/////////////////////
+
+The above example produces these terms:
+
+[source,text]
+---------------------------
+[ 786, 335, 514 ]
+---------------------------

docs/reference/analysis/tokenizers/simplepatternsplit-tokenizer.asciidoc

@@ -0,0 +1,106 @@
+[[analysis-simplepatternsplit-tokenizer]]
+=== Simple Pattern Split Tokenizer
+
+experimental[]
+
+The `simplepatternsplit` tokenizer uses a regular expression to split the
+input into terms at pattern matches. The set of regular expression features it
+supports is more limited than the <<analysis-pattern-tokenizer,`pattern`>>
+tokenizer, but the tokenization is generally faster.
+
+This tokenizer does not produce terms from the matches themselves. To produce
+terms from matches using patterns in the same restricted regular expression
+subset, see the <<analysis-simplepattern-tokenizer,`simplepattern`>>
+tokenizer.
+
+This tokenizer uses {lucene-core-javadoc}/org/apache/lucene/util/automaton/RegExp.html[Lucene regular expressions].
+For an explanation of the supported features and syntax, see <<regexp-syntax,Regular Expression Syntax>>.
+
+The default pattern is the empty string, which produces one term containing the
+full input. This tokenizer should always be configured with a non-default
+pattern.
+
+[float]
+=== Configuration
+
+The `simplepatternsplit` tokenizer accepts the following parameters:
+
+[horizontal]
+`pattern`::
+    A {lucene-core-javadoc}/org/apache/lucene/util/automaton/RegExp.html[Lucene regular expression], defaults to the empty string.
+
+[float]
+=== Example configuration
+
+This example configures the `simplepatternsplit` tokenizer to split the input
+text on underscores.
+
+[source,js]
+----------------------------
+PUT my_index
+{
+  "settings": {
+    "analysis": {
+      "analyzer": {
+        "my_analyzer": {
+          "tokenizer": "my_tokenizer"
+        }
+      },
+      "tokenizer": {
+        "my_tokenizer": {
+          "type": "simplepatternsplit",
+          "pattern": "_"
+        }
+      }
+    }
+  }
+}
+
+POST my_index/_analyze
+{
+  "analyzer": "my_analyzer",
+  "text": "an_underscored_phrase"
+}
+----------------------------
+// CONSOLE
+
+/////////////////////
+
+[source,js]
+----------------------------
+{
+  "tokens" : [
+    {
+      "token" : "an",
+      "start_offset" : 0,
+      "end_offset" : 2,
+      "type" : "word",
+      "position" : 0
+    },
+    {
+      "token" : "underscored",
+      "start_offset" : 3,
+      "end_offset" : 14,
+      "type" : "word",
+      "position" : 1
+    },
+    {
+      "token" : "phrase",
+      "start_offset" : 15,
+      "end_offset" : 21,
+      "type" : "word",
+      "position" : 2
+    }
+  ]
+}
+----------------------------
+// TESTRESPONSE
+
+/////////////////////
+
+The above example produces these terms:
+
+[source,text]
+---------------------------
+[ an, underscored, phrase ]
+---------------------------

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

@@ -73,6 +73,7 @@ import org.elasticsearch.index.analysis.PreConfiguredCharFilter;
 import org.elasticsearch.index.analysis.PreConfiguredTokenFilter;
 import org.elasticsearch.index.analysis.PreConfiguredTokenizer;
 import org.elasticsearch.index.analysis.TokenFilterFactory;
+import org.elasticsearch.index.analysis.TokenizerFactory;
 import org.elasticsearch.indices.analysis.AnalysisModule.AnalysisProvider;
 import org.elasticsearch.plugins.AnalysisPlugin;
 import org.elasticsearch.plugins.Plugin;
@@ -100,6 +101,7 @@ public class CommonAnalysisPlugin extends Plugin implements AnalysisPlugin {
         return filters;
     }
 
+    @Override
     public Map<String, AnalysisProvider<CharFilterFactory>> getCharFilters() {
         Map<String, AnalysisProvider<CharFilterFactory>> filters = new TreeMap<>();
         filters.put("html_strip", HtmlStripCharFilterFactory::new);
@@ -108,6 +110,14 @@ public class CommonAnalysisPlugin extends Plugin implements AnalysisPlugin {
         return filters;
     }
 
+    @Override
+    public Map<String, AnalysisProvider<TokenizerFactory>> getTokenizers() {
+        Map<String, AnalysisProvider<TokenizerFactory>> tokenizers = new TreeMap<>();
+        tokenizers.put("simplepattern", SimplePatternTokenizerFactory::new);
+        tokenizers.put("simplepatternsplit", SimplePatternSplitTokenizerFactory::new);
+        return tokenizers;
+    }
+
     @Override
     public List<PreConfiguredCharFilter> getPreConfiguredCharFilters() {
         List<PreConfiguredCharFilter> filters = new ArrayList<>();

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

@@ -0,0 +1,43 @@
+/*
+ * 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.pattern.SimplePatternSplitTokenizer;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.env.Environment;
+import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenizerFactory;
+
+public class SimplePatternSplitTokenizerFactory extends AbstractTokenizerFactory {
+
+    private final String pattern;
+
+    public SimplePatternSplitTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
+        super(indexSettings, name, settings);
+
+        pattern = settings.get("pattern", "");
+    }
+
+    @Override
+    public Tokenizer create() {
+        return new SimplePatternSplitTokenizer(pattern);
+    }
+}

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

@@ -0,0 +1,43 @@
+/*
+ * 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.pattern.SimplePatternTokenizer;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.env.Environment;
+import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenizerFactory;
+
+public class SimplePatternTokenizerFactory extends AbstractTokenizerFactory {
+
+    private final String pattern;
+
+    public SimplePatternTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
+        super(indexSettings, name, settings);
+
+        pattern = settings.get("pattern", "");
+    }
+
+    @Override
+    public Tokenizer create() {
+        return new SimplePatternTokenizer(pattern);
+    }
+}

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

@@ -43,6 +43,8 @@ public class CommonAnalysisFactoryTests extends AnalysisFactoryTestCase {
     @Override
     protected Map<String, Class<?>> getTokenizers() {
         Map<String, Class<?>> tokenizers = new TreeMap<>(super.getTokenizers());
+        tokenizers.put("simplepattern", SimplePatternTokenizerFactory.class);
+        tokenizers.put("simplepatternsplit", SimplePatternSplitTokenizerFactory.class);
         return tokenizers;
     }
 

modules/analysis-common/src/test/resources/rest-api-spec/test/analysis-common/30_tokenizers.yml

@@ -25,3 +25,33 @@
     - match:  { detail.tokenizer.tokens.0.token: go }
     - match:  { detail.tokenizer.tokens.1.token: oo }
     - match:  { detail.tokenizer.tokens.2.token: od }
+
+---
+"simplepattern":
+    - do:
+        indices.analyze:
+          body:
+            text: "a6bf fooo ff61"
+            explain: true
+            tokenizer:
+              type: simplepattern
+              pattern: "[abcdef0123456789]{4}"
+    - length: { detail.tokenizer.tokens: 2 }
+    - match:  { detail.tokenizer.name: _anonymous_tokenizer }
+    - match:  { detail.tokenizer.tokens.0.token: a6bf }
+    - match:  { detail.tokenizer.tokens.1.token: ff61 }
+
+---
+"simplepatternsplit":
+    - do:
+        indices.analyze:
+          body:
+            text: "foo==bar"
+            explain: true
+            tokenizer:
+              type: simplepatternsplit
+              pattern: ==
+    - length: { detail.tokenizer.tokens: 2 }
+    - match:  { detail.tokenizer.name: _anonymous_tokenizer }
+    - match:  { detail.tokenizer.tokens.0.token: foo }
+    - match:  { detail.tokenizer.tokens.1.token: bar }

test/framework/src/main/java/org/elasticsearch/indices/analysis/AnalysisFactoryTestCase.java

@@ -137,6 +137,8 @@ public abstract class AnalysisFactoryTestCase extends ESTestCase {
         .put("ngram", NGramTokenizerFactory.class)
         .put("pathhierarchy", PathHierarchyTokenizerFactory.class)
         .put("pattern", PatternTokenizerFactory.class)
+        .put("simplepattern", MovedToAnalysisCommon.class)
+        .put("simplepatternsplit", MovedToAnalysisCommon.class)
         .put("standard", StandardTokenizerFactory.class)
         .put("thai", ThaiTokenizerFactory.class)
         .put("uax29urlemail", UAX29URLEmailTokenizerFactory.class)
@@ -144,10 +146,6 @@ public abstract class AnalysisFactoryTestCase extends ESTestCase {
 
         // this one "seems to mess up offsets". probably shouldn't be a tokenizer...
         .put("wikipedia", Void.class)
-
-        // TODO: expose these
-        .put("simplepattern",    Void.class)
-        .put("simplepatternsplit",    Void.class)
         .immutableMap();
 
     static final Map<String,Class<?>> KNOWN_TOKENFILTERS = new MapBuilder<String,Class<?>>()