Merge branch 'BAEL-3283-latest' into BAEL-3283

This commit is contained in:
sandip singh
2019-10-31 23:25:14 +05:30
parent db85c8f275
commit f6c3f9ebcb
20562 changed files with 1643286 additions and 0 deletions
@@ -0,0 +1,23 @@
package com.baeldung.crunch;
import org.apache.crunch.DoFn;
import org.apache.crunch.Emitter;
import com.google.common.base.Splitter;
/**
* Splits a line of text, filtering known stop words.
*/
public class Tokenizer extends DoFn<String, String> {
private static final Splitter SPLITTER = Splitter
.onPattern("\\s+")
.omitEmptyStrings();
@Override
public void process(String line,
Emitter<String> emitter) {
for (String word : SPLITTER.split(line)) {
emitter.emit(word);
}
}
}