[GitHub] [flink-ml] yunfengzhou-hub commented on a diff in pull request #129: [FLINK-28500] Add Transformer for Tokenizer

[GitBox <gi...@apache.org>]

yunfengzhou-hub commented on code in PR #129:
URL: https://github.com/apache/flink-ml/pull/129#discussion_r921758189


##########
flink-ml-lib/src/main/java/org/apache/flink/ml/feature/tokenizer/Tokenizer.java:
##########
@@ -0,0 +1,80 @@
+/*
+ * 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 org.apache.flink.ml.feature.tokenizer;
+
+import org.apache.flink.ml.api.Transformer;
+import org.apache.flink.ml.param.Param;
+import org.apache.flink.ml.util.ParamUtils;
+import org.apache.flink.ml.util.ReadWriteUtils;
+import org.apache.flink.table.api.Expressions;
+import org.apache.flink.table.api.Table;
+import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
+import org.apache.flink.table.expressions.Expression;
+import org.apache.flink.table.functions.ScalarFunction;
+import org.apache.flink.util.Preconditions;
+
+import java.io.IOException;
+import java.util.HashMap;
+import java.util.Map;
+
+import static org.apache.flink.table.api.Expressions.$;
+
+/**
+ * A tokenizer is a transformer that converts the input string to lowercase and then splits it by
+ * white spaces.
+ */
+public class Tokenizer implements Transformer<Tokenizer>, TokenizerParams<Tokenizer> {
+    private final Map<Param<?>, Object> paramMap = new HashMap<>();
+
+    public Tokenizer() {
+        ParamUtils.initializeMapWithDefaultValues(paramMap, this);
+    }
+
+    @Override
+    public Table[] transform(Table... inputs) {
+        Preconditions.checkArgument(inputs.length == 1);
+
+        Expression tokenizerUdf = Expressions.call(TokenizerUdf.class, $(getInputCol()));
+        Table output = inputs[0].addColumns(tokenizerUdf).as(getInputCol(), getOutputCol());

Review Comment:
   Could you please verify that the current implementation preserves columns that are not `getInputCol()` after this transformation? I'm a little concerned that if there are more than two input columns for this transformer, exceptions would be thrown.



-- 
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: issues-unsubscribe@flink.apache.org

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