From f55e3796d98e6e239bf637be7a3561885e3bc1cb Mon Sep 17 00:00:00 2001
From: Felipe Santiago Corro <santiago.corro@gmail.com>
Date: Tue, 14 Aug 2018 07:24:28 -0300
Subject: [PATCH] optimizing regex expressions (#4961)

---
 .../optmization/OptimizedMatcher.java         |   6 +
 .../optmization/OptimizedMatcherUnitTest.java | 109 ++++++++++++++++++
 2 files changed, 115 insertions(+)
 create mode 100644 core-java/src/main/java/com/baeldung/regexp/datepattern/optmization/OptimizedMatcher.java
 create mode 100644 core-java/src/test/java/com/baeldung/regexp/optmization/OptimizedMatcherUnitTest.java

diff --git a/core-java/src/main/java/com/baeldung/regexp/datepattern/optmization/OptimizedMatcher.java b/core-java/src/main/java/com/baeldung/regexp/datepattern/optmization/OptimizedMatcher.java
new file mode 100644
index 0000000000..ccae942dcc
--- /dev/null
+++ b/core-java/src/main/java/com/baeldung/regexp/datepattern/optmization/OptimizedMatcher.java
@@ -0,0 +1,6 @@
+package com.baeldung.regexp.datepattern.optmization;
+
+public class OptimizedMatcher {
+
+
+}
diff --git a/core-java/src/test/java/com/baeldung/regexp/optmization/OptimizedMatcherUnitTest.java b/core-java/src/test/java/com/baeldung/regexp/optmization/OptimizedMatcherUnitTest.java
new file mode 100644
index 0000000000..f21a755b01
--- /dev/null
+++ b/core-java/src/test/java/com/baeldung/regexp/optmization/OptimizedMatcherUnitTest.java
@@ -0,0 +1,109 @@
+package com.baeldung.regexp.optmization;
+
+import org.junit.After;
+import org.junit.Before;
+import org.junit.Test;
+
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Random;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+import static org.junit.Assert.assertTrue;
+
+public class OptimizedMatcherUnitTest {
+
+    private long time;
+    private long mstimePreCompiled;
+    private long mstimeNotPreCompiled;
+
+    private String action;
+
+    private List<String> items;
+
+    @Before
+    public void setup() {
+        Random random = new Random();
+        items = new ArrayList<String>();
+        long average = 0;
+
+        for (int i = 0; i < 100000; ++i) {
+            StringBuilder s = new StringBuilder();
+            int characters = random.nextInt(7) + 1;
+            for (int k = 0; k < characters; ++ k) {
+                char c = (char)(random.nextInt('Z' - 'A') + 'A');
+                int rep = random.nextInt(95) + 5;
+                for (int j = 0; j < rep; ++ j)
+                    s.append(c);
+                average += rep;
+            }
+            items.add(s.toString());
+        }
+
+        average /= 100000;
+        System.out.println("generated data, average length: " + average);
+    }
+
+
+    @Test
+    public void givenANotPreCompiledAndAPreCompiledPatternA_whenMatcheItems_thenPreCompiledFasterThanNotPreCompiled() {
+
+        testPatterns("A*");
+        assertTrue(mstimePreCompiled < mstimeNotPreCompiled);
+    }
+
+    @Test
+    public void givenANotPreCompiledAndAPreCompiledPatternABC_whenMatcheItems_thenPreCompiledFasterThanNotPreCompiled() {
+
+        testPatterns("A*B*C*");
+        assertTrue(mstimePreCompiled < mstimeNotPreCompiled);
+    }
+
+    @Test
+    public void givenANotPreCompiledAndAPreCompiledPatternECWF_whenMatcheItems_thenPreCompiledFasterThanNotPreCompiled() {
+
+        testPatterns("E*C*W*F*");
+        assertTrue(mstimePreCompiled < mstimeNotPreCompiled);
+    }
+
+    private void testPatterns(String regex) {
+        time = System.nanoTime();
+        int matched = 0;
+        int unmatched = 0;
+
+        for (String item : this.items) {
+            if (item.matches(regex)) {
+                ++matched;
+            }
+            else {
+                ++unmatched;
+            }
+        }
+
+        this.action = "uncompiled: regex=" + regex + " matched=" + matched + " unmatched=" + unmatched;
+
+        this.mstimeNotPreCompiled = (System.nanoTime() - time) / 1000000;
+        System.out.println(this.action + ": " + mstimeNotPreCompiled + "ms");
+
+        time = System.nanoTime();
+
+        Matcher matcher = Pattern.compile(regex).matcher("");
+        matched = 0;
+        unmatched = 0;
+
+        for (String item : this.items) {
+            if (matcher.reset(item).matches()) {
+                ++matched;
+            }
+            else {
+                ++unmatched;
+            }
+        }
+
+        this.action = "compiled: regex=" + regex + " matched=" + matched + " unmatched=" + unmatched;
+
+        this.mstimePreCompiled = (System.nanoTime() - time) / 1000000;
+        System.out.println(this.action + ": " + mstimePreCompiled + "ms");
+    }
+}