[GitHub] [opennlp] jzonthemtn commented on a diff in pull request #523: OPENNLP-1442: Sentence transformers

["jzonthemtn (via GitHub)" <gi...@apache.org>]

jzonthemtn commented on code in PR #523:
URL: https://github.com/apache/opennlp/pull/523#discussion_r1147990411


##########
opennlp-dl/src/main/java/opennlp/dl/AbstractDL.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
+ *
+ *   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 opennlp.dl;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.FileReader;
+import java.io.IOException;
+import java.util.HashMap;
+import java.util.Map;
+
+import ai.onnxruntime.OrtEnvironment;
+import ai.onnxruntime.OrtSession;
+
+import opennlp.tools.tokenize.Tokenizer;
+
+/**
+ * Base class for OpenNLP deep-learning classes using ONNX Runtime.
+ */
+public abstract class AbstractDL {
+
+  public static final String INPUT_IDS = "input_ids";
+  public static final String ATTENTION_MASK = "attention_mask";
+  public static final String TOKEN_TYPE_IDS = "token_type_ids";
+
+  protected OrtEnvironment env;
+  protected OrtSession session;
+  protected Tokenizer tokenizer;
+  protected Map<String, Integer> vocab;
+
+  /**
+   * Loads a vocabulary file from disk.
+   * @param vocabFile The vocabulary file.
+   * @return A map of vocabulary words to integer IDs.
+   * @throws IOException Thrown if the vocabulary file cannot be opened and read.
+   */
+  public Map<String, Integer> loadVocab(File vocabFile) throws IOException {
+
+    final Map<String, Integer> v = new HashMap<>();
+
+    BufferedReader br = new BufferedReader(new FileReader(vocabFile.getPath()));
+    String line = br.readLine();

Review Comment:
   I don't think so but I will check.



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: dev-unsubscribe@opennlp.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org