This is an automated email from the ASF dual-hosted git repository.
sergeykamov pushed a commit to branch NLPCRAFT-472
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git
The following commit(s) were added to refs/heads/NLPCRAFT-472 by this push:
new d0060c7 WIP.
d0060c7 is described below
commit d0060c7e960f4bf62be33826a5601a8864a608d9
Author: Sergey Kamov <[email protected]>
AuthorDate: Wed Dec 29 21:51:37 2021 +0300
WIP.
---
.../scala/org/apache/nlpcraft/NCTokenizer.java | 27 ++++++++++
.../src/main/scala/org/apache/nlpcraft/NCWord.java | 47 ++++++++++++++++++
.../nlpcraft/nlp/tokenizer/NCOpenNlpTokenizer.java | 58 ++++++++++++++++++++++
.../tokenizer/impl/NCOpenNlpTokenizerImpl.scala | 44 ++++++++++++++++
.../nlpcraft/nlp/util/NCTestDefaultConfig.scala | 47 ++++++++++++++++++
5 files changed, 223 insertions(+)
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/NCTokenizer.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCTokenizer.java
new file mode 100644
index 0000000..a27c7f7
--- /dev/null
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCTokenizer.java
@@ -0,0 +1,27 @@
+/*
+ * 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;
+
+import java.util.List;
+
+/**
+ *
+ */
+public interface NCTokenizer extends NCLifecycle {
+ List<NCWord> tokenize(NCModelConfig cfg, String txt);
+}
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/NCWord.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCWord.java
new file mode 100644
index 0000000..d4a7eed
--- /dev/null
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCWord.java
@@ -0,0 +1,47 @@
+/*
+ * 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;
+
+/**
+ *
+ */
+public interface NCWord {
+ /**
+ *
+ * @return
+ */
+ String getText();
+
+ /**
+ *
+ * @return
+ */
+ int getStartCharIndex();
+
+ /**
+ *
+ * @return
+ */
+ int getEndCharIndex();
+
+ /**
+ *
+ * @return
+ */
+ int getLength();
+}
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/tokenizer/NCOpenNlpTokenizer.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/tokenizer/NCOpenNlpTokenizer.java
new file mode 100644
index 0000000..03e8c9a
--- /dev/null
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/tokenizer/NCOpenNlpTokenizer.java
@@ -0,0 +1,58 @@
+/*
+ * 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.tokenizer;
+
+import org.apache.nlpcraft.NCModelConfig;
+import org.apache.nlpcraft.NCTokenizer;
+import org.apache.nlpcraft.NCWord;
+import org.apache.nlpcraft.nlp.tokenizer.impl.NCOpenNlpTokenizerImpl;
+
+import java.io.File;
+import java.util.List;
+import java.util.Objects;
+
+public class NCOpenNlpTokenizer implements NCTokenizer {
+ private final NCOpenNlpTokenizerImpl impl;
+
+ public NCOpenNlpTokenizer(File tokMdl) {
+ Objects.requireNonNull(tokMdl, "Tokenizer model file cannot be null.");
+
+ impl = NCOpenNlpTokenizerImpl.apply(tokMdl);
+ }
+
+ public NCOpenNlpTokenizer(String tokMdl) {
+ Objects.requireNonNull(tokMdl, "Tokenizer model source cannot be
null.");
+
+ impl = NCOpenNlpTokenizerImpl.apply(tokMdl);
+ }
+
+ @Override
+ public List<NCWord> tokenize(NCModelConfig cfg, String txt) {
+ return impl.tokenize(cfg, txt);
+ }
+
+ @Override
+ public void start(NCModelConfig cfg) {
+ impl.start(cfg);
+ }
+
+ @Override
+ public void stop() {
+ impl.stop();
+ }
+}
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/tokenizer/impl/NCOpenNlpTokenizerImpl.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/tokenizer/impl/NCOpenNlpTokenizerImpl.scala
new file mode 100644
index 0000000..18d54b4
--- /dev/null
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/tokenizer/impl/NCOpenNlpTokenizerImpl.scala
@@ -0,0 +1,44 @@
+/*
+ * 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.tokenizer.impl
+
+import opennlp.tools.tokenize.*
+import org.apache.nlpcraft.*
+import org.apache.nlpcraft.internal.util.NCUtils
+
+import java.io.*
+import java.util
+import scala.jdk.CollectionConverters.*
+
+object NCOpenNlpTokenizerImpl:
+ def apply(file: File): NCOpenNlpTokenizerImpl = new
NCOpenNlpTokenizerImpl(new BufferedInputStream(new FileInputStream(file)))
+ def apply(src: String): NCOpenNlpTokenizerImpl = new
NCOpenNlpTokenizerImpl(NCUtils.getStream(src))
+
+class NCOpenNlpTokenizerImpl(is: InputStream) extends NCTokenizer:
+ @volatile var tokenizer: TokenizerME = _
+
+ override def start(cfg: NCModelConfig): Unit = tokenizer = new
TokenizerME(new TokenizerModel(is))
+ override def stop(): Unit = tokenizer = null
+ override def tokenize(cfg: NCModelConfig, txt: String): util.List[NCWord] =
+ tokenizer.tokenizePos(txt).
+ map(span =>
+ new NCWord:
+ override def getText: String =
span.getCoveredText(txt).toString
+ override def getStartCharIndex: Int = span.getStart
+ override def getEndCharIndex: Int = span.getEnd
+ override def getLength: Int = span.length()
+ ).toSeq.asJava
diff --git
a/nlpcraft/src/test/java/org/apache/nlpcraft/nlp/util/NCTestDefaultConfig.scala
b/nlpcraft/src/test/java/org/apache/nlpcraft/nlp/util/NCTestDefaultConfig.scala
new file mode 100644
index 0000000..e0016ab
--- /dev/null
+++
b/nlpcraft/src/test/java/org/apache/nlpcraft/nlp/util/NCTestDefaultConfig.scala
@@ -0,0 +1,47 @@
+/*
+ * 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.util
+
+import org.apache.nlpcraft.nlp.token.parser.opennlp.en.NCEnOpenNlpTokenParser
+import org.apache.nlpcraft.nlp.tokenizer.NCOpenNlpTokenizer
+import org.apache.nlpcraft.*
+
+import java.util
+import java.util.Optional
+
+object NCTestDefaultConfig:
+ final val EN_TOKENIZER = new NCOpenNlpTokenizer(
+ "opennlp/en-token.bin"
+ )
+ final val EN_PARSER: NCTokenParser = new NCEnOpenNlpTokenParser(
+ "opennlp/en-pos-maxent.bin",
+ "opennlp/en-lemmatizer.dict"
+ )
+
+ final val EN_MDL_CFG: NCModelConfig = new NCPropertyMapAdapter() with
NCModelConfig:
+ override def getTokenizer: NCTokenizer = EN_TOKENIZER
+ override def getTokenParsers: util.List[NCTokenParser] =
util.Collections.singletonList(EN_PARSER);
+ override def getTokenEnrichers: util.List[NCTokenEnricher] = new
util.ArrayList[NCTokenEnricher]()
+ override def getEntityEnrichers: util.List[NCEntityEnricher] = new
util.ArrayList[NCEntityEnricher]()
+ override def getEntityParsers: util.List[NCEntityParser] = new
util.ArrayList[NCEntityParser]()
+ override def getId: String = "test"
+ override def getName: String = "test"
+ override def getVersion: String = "1.0"
+
+ EN_TOKENIZER.start(EN_MDL_CFG)
+ EN_PARSER.start(EN_MDL_CFG)
