remove stop words from string

java-strings-2/src/main/java/com/baeldung/string/performance/RemovingStopwordsPerformanceComparison.java

@@ -0,0 +1,73 @@
+package com.baeldung.string.performance;
+
+import java.io.IOException;
+import java.nio.file.Files;
+import java.nio.file.Paths;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.concurrent.TimeUnit;
+import java.util.stream.Collectors;
+import java.util.stream.Stream;
+
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Fork;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+import org.openjdk.jmh.annotations.Scope;
+import org.openjdk.jmh.annotations.Setup;
+import org.openjdk.jmh.annotations.State;
+
+
+@Fork(value = 3, warmups = 1)
+@State(Scope.Benchmark)
+@BenchmarkMode(Mode.AverageTime)
+@OutputTimeUnit(TimeUnit.MILLISECONDS)
+public class RemovingStopwordsPerformanceComparison {
+
+    private String data;
+    
+    private List<String> stopwords;
+
+    private String stopwordsRegex;
+    
+    
+    public static void main(String[] args) throws Exception {
+        org.openjdk.jmh.Main.main(args);
+    }
+
+    @Setup
+    public void setup() throws IOException {
+        data = new String(Files.readAllBytes(Paths.get("src/main/resources/shakespeare-hamlet.txt")));
+        data = data.toLowerCase();
+        stopwords = Files.readAllLines(Paths.get("src/main/resources/english_stopwords.txt"));
+        stopwordsRegex = stopwords.stream().collect(Collectors.joining("|", "\\b(", ")\\b\\s?"));
+    }
+
+    @Benchmark
+    public String removeManually() {
+        String[] allWords = data.split(" ");
+        StringBuilder builder = new StringBuilder();
+        for(String word:allWords) {
+            if(! stopwords.contains(word)) {
+                builder.append(word);
+                builder.append(' ');
+            }
+        }
+        return builder.toString().trim();
+    }
+
+    @Benchmark
+    public String removeAll() {
+        ArrayList<String> allWords = Stream.of(data.split(" "))
+            .collect(Collectors.toCollection(ArrayList<String>::new));
+        allWords.removeAll(stopwords);
+        return allWords.stream().collect(Collectors.joining(" "));
+    }
+
+    @Benchmark
+    public String replaceRegex() {
+        return data.replaceAll(stopwordsRegex, "");
+    }
+
+}