This is an automated email from the ASF dual-hosted git repository.
sergeykamov pushed a commit to branch NLPCRAFT-483
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git
commit 7635454b90b2a4882af559dc4b951d65796e0e20
Author: Sergey Kamov <skhdlem...@gmail.com>
AuthorDate: Fri Feb 25 18:44:27 2022 +0300
EN adapters added.
---
.../apache/nlpcraft/nlp/NCENDefaultPipeline.java | 89 ++++++++++++++++++++++
.../nlpcraft/nlp/NCENSemanticEntityParser.java | 73 ++++++++++++++++++
.../nlpcraft/nlp/NCENDefaultPipelineSpec.scala | 60 +++++++++++++++
3 files changed, 222 insertions(+)
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/NCENDefaultPipeline.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/NCENDefaultPipeline.java
new file mode 100644
index 0000000..d679ed9
--- /dev/null
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/NCENDefaultPipeline.java
@@ -0,0 +1,89 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF 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
+ *
+ * https://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.apache.nlpcraft.nlp;
+
+import org.apache.nlpcraft.NCEntityParser;
+import org.apache.nlpcraft.NCModelPipeline;
+import org.apache.nlpcraft.NCTokenEnricher;
+import org.apache.nlpcraft.NCTokenParser;
+import org.apache.nlpcraft.internal.util.NCResourceReader;
+import org.apache.nlpcraft.nlp.token.enricher.en.NCBracketsTokenEnricher;
+import org.apache.nlpcraft.nlp.token.enricher.en.NCDictionaryTokenEnricher;
+import org.apache.nlpcraft.nlp.token.enricher.en.NCQuotesTokenEnricher;
+import org.apache.nlpcraft.nlp.token.enricher.en.NCStopWordsTokenEnricher;
+import org.apache.nlpcraft.nlp.token.enricher.en.NСSwearWordsTokenEnricher;
+import org.apache.nlpcraft.nlp.token.parser.opennlp.NCOpenNLPTokenParser;
+
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.List;
+
+/**
+ *
+ */
+public class NCENDefaultPipeline implements NCModelPipeline {
+ private static final NCResourceReader reader = new NCResourceReader();
+
+ private final NCTokenParser tp = new NCOpenNLPTokenParser(
+ reader.getPath("opennlp/en-token.bin"),
+ reader.getPath("opennlp/en-pos-maxent.bin"),
+ reader.getPath("opennlp/en-lemmatizer.dict")
+ );
+
+ private List<NCTokenEnricher> tokenEnrichers = Arrays.asList(
+ new NCStopWordsTokenEnricher(),
+ new
NСSwearWordsTokenEnricher(reader.getPath("badfilter/swear_words.txt")),
+ new NCQuotesTokenEnricher(),
+ new NCDictionaryTokenEnricher(),
+ new NCBracketsTokenEnricher()
+
+ );
+
+ private final List<NCEntityParser> parsers;
+
+ /**
+ *
+ * @param parsers
+ */
+ public NCENDefaultPipeline(List<NCEntityParser> parsers) {
+ this.parsers = parsers;
+ }
+
+ /**
+ *
+ * @param parser
+ */
+ public NCENDefaultPipeline(NCEntityParser parser) {
+ this.parsers = Collections.singletonList(parser);
+ }
+
+ @Override
+ public NCTokenParser getTokenParser() {
+ return tp;
+ }
+
+ @Override
+ public List<NCEntityParser> getEntityParsers() {
+ return parsers;
+ }
+
+ @Override
+ public List<NCTokenEnricher> getTokenEnrichers() {
+ return tokenEnrichers;
+ }
+}
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/NCENSemanticEntityParser.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/NCENSemanticEntityParser.java
new file mode 100644
index 0000000..9a099dd
--- /dev/null
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/NCENSemanticEntityParser.java
@@ -0,0 +1,73 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF 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
+ *
+ * https://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.apache.nlpcraft.nlp;
+
+import org.apache.nlpcraft.NCTokenParser;
+import org.apache.nlpcraft.internal.util.NCResourceReader;
+import org.apache.nlpcraft.nlp.entity.parser.semantic.NCSemanticElement;
+import org.apache.nlpcraft.nlp.entity.parser.semantic.NCSemanticEntityParser;
+import org.apache.nlpcraft.nlp.entity.parser.semantic.NCSemanticStemmer;
+import
org.apache.nlpcraft.nlp.entity.parser.semantic.impl.en.NCEnSemanticPorterStemmer;
+import org.apache.nlpcraft.nlp.token.parser.opennlp.NCOpenNLPTokenParser;
+
+import java.util.List;
+import java.util.Map;
+
+/**
+ *
+ */
+public class NCENSemanticEntityParser extends NCSemanticEntityParser {
+ private static final NCResourceReader reader = new NCResourceReader();
+
+ private static NCSemanticStemmer mkStemmer() {
+ return new NCEnSemanticPorterStemmer();
+ }
+
+ private static NCOpenNLPTokenParser mkParser() {
+ return new NCOpenNLPTokenParser(
+ reader.getPath("opennlp/en-token.bin"),
+ reader.getPath("opennlp/en-pos-maxent.bin"),
+ reader.getPath("opennlp/en-lemmatizer.dict")
+ );
+ }
+
+ /**
+ *
+ * @param elms
+ */
+ public NCENSemanticEntityParser(List<NCSemanticElement> elms) {
+ super(mkStemmer(), mkParser(), elms);
+ }
+
+ /**
+ *
+ * @param macros
+ * @param elms
+ */
+ public NCENSemanticEntityParser(Map<String, String> macros,
List<NCSemanticElement> elms) {
+ super(mkStemmer(), mkParser(), macros, elms);
+ }
+
+ /**
+ *
+ * @param src
+ */
+ public NCENSemanticEntityParser(String src) {
+ super(mkStemmer(), mkParser(), src);
+ }
+}
diff --git
a/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/NCENDefaultPipelineSpec.scala
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/NCENDefaultPipelineSpec.scala
new file mode 100644
index 0000000..a8a6d1b
--- /dev/null
+++
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/NCENDefaultPipelineSpec.scala
@@ -0,0 +1,60 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF 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
+ *
+ * https://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.apache.nlpcraft.nlp
+
+import org.apache.nlpcraft.*
+import org.apache.nlpcraft.nlp.entity.parser.semantic.NCSemanticEntityParser
+import
org.apache.nlpcraft.nlp.entity.parser.semantic.impl.en.NCEnSemanticPorterStemmer
+import org.apache.nlpcraft.nlp.util.NCTestModelAdapter
+import org.junit.jupiter.api.Test
+
+import scala.util.Using
+
+class NCENDefaultPipelineSpec:
+ /**
+ *
+ * @param cfg
+ * @param pipeline
+ * @return
+ */
+ private def mkModel(cfg: NCModelConfig, pipeline: NCModelPipeline):
NCModel =
+ new NCModelAdapter(cfg, pipeline):
+ @NCIntent("intent=ls term(act)={has(ent_groups, 'act')}
term(loc)={# == 'ls:loc'}*")
+ @NCIntentSample(Array(
+ "Please, put the light out in the upstairs bedroom.",
+ ))
+ def onMatch(
+ @NCIntentTerm("act") actEnt: NCEntity,
+ @NCIntentTerm("loc") locEnts: List[NCEntity]
+ ): NCResult =
+ val status = if actEnt.getId == "ls:on" then "on" else "off"
+ val locations = if locEnts.isEmpty then "entire house" else
locEnts.map(_.mkText()).mkString(", ")
+ val res = new NCResult()
+ res.setType(NCResultType.ASK_RESULT)
+ res.setBody(s"Lights are [$status] in
[${locations.toLowerCase}].")
+ res
+
+ @Test
+ def test(): Unit =
+ val cfg = new NCModelConfig("test.id", "Test model", "1.0")
+ // Default EN pipeline with default EN semantic parser.
+ val pipeline = new NCENDefaultPipeline(new
NCENSemanticEntityParser("models/lightswitch_model.yaml"))
+
+ Using.resource(new NCModelClient(mkModel(cfg, pipeline))) { client =>
+ println(client.ask("Please, put the light out in the upstairs
bedroom.", null, "userId").getBody)
+ }
\ No newline at end of file
