BAEL-5149 Remove accents from String in Java

core-java-modules/core-java-string-operations-3/src/main/java/com/baeldung/accentsanddiacriticsremoval/StringNormalizer.java

@@ -0,0 +1,49 @@
+package com.baeldung.accentsanddiacriticsremoval;
+
+import org.apache.commons.lang3.StringUtils;
+
+import java.text.Normalizer;
+import java.util.StringJoiner;
+
+class StringNormalizer {
+
+    static String removeAccentsWithApacheCommons(String input) {
+        return StringUtils.stripAccents(input);
+    }
+
+    static String removeAccents(String input) {
+        return normalize(input).replaceAll("\\p{InCombiningDiacriticalMarks}+", "");
+    }
+
+    static String unicodeValueOfNormalizedString(String input) {
+        return toUnicode(normalize(input));
+    }
+
+    private static String normalize(String input) {
+        return input == null ? null : Normalizer.normalize(input, Normalizer.Form.NFD);
+    }
+
+    private static String toUnicode(String input) {
+        if (input.length() == 1) {
+            return toUnicode(input.charAt(0));
+        } else {
+            StringJoiner stringJoiner = new StringJoiner(" ");
+            for (char c : input.toCharArray()) {
+                stringJoiner.add(toUnicode(c));
+            }
+            return stringJoiner.toString();
+        }
+    }
+
+    private static String toUnicode(char input) {
+
+        String hex = Integer.toHexString(input);
+        StringBuilder sb = new StringBuilder(hex);
+
+        while (sb.length() < 4) {
+            sb.insert(0, "0");
+        }
+        sb.insert(0, "\\u");
+        return sb.toString();
+    }
+}

core-java-modules/core-java-string-operations-3/src/test/java/com/baeldung/accentsanddiacriticsremoval/StringNormalizerUnitTest.java

@@ -0,0 +1,44 @@
+package com.baeldung.accentsanddiacriticsremoval;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+import org.junit.jupiter.api.Test;
+
+import com.baeldung.accentsanddiacriticsremoval.StringNormalizer;
+
+class StringNormalizerUnitTest {
+
+    @Test
+    void givenStringWithDecomposableUnicodeCharacters_whenRemoveAccents_thenReturnASCIIString() {
+        assertEquals("aaaeiiiiggnnsssuuy", StringNormalizer.removeAccents("āăąēîïĩíĝġńñšŝśûůŷ"));
+    }
+
+    @Test
+    void givenStringWithDecomposableUnicodeCharacters_whenRemoveAccentsWithApacheCommons_thenReturnASCIIString() {
+        assertEquals("aaaeiiiiggnnsssuuy", StringNormalizer.removeAccentsWithApacheCommons("āăąēîïĩíĝġńñšŝśûůŷ"));
+    }
+
+    @Test
+    void givenStringWithNondecomposableUnicodeCharacters_whenRemoveAccents_thenReturnOriginalString() {
+        assertEquals("łđħœ", StringNormalizer.removeAccents("łđħœ"));
+    }
+
+    @Test
+    void givenStringWithNondecomposableUnicodeCharacters_whenRemoveAccentsWithApacheCommons_thenReturnModifiedString() {
+        assertEquals("lđħœ", StringNormalizer.removeAccentsWithApacheCommons("łđħœ"));
+    }
+
+    @Test
+    void givenStringWithDecomposableUnicodeCharacters_whenUnicodeValueOfNormalizedString_thenReturnUnicodeValue() {
+        assertEquals("\\u0061 \\u0304", StringNormalizer.unicodeValueOfNormalizedString("ā"));
+        assertEquals("\\u0069 \\u0308", StringNormalizer.unicodeValueOfNormalizedString("ï"));
+        assertEquals("\\u006e \\u0301", StringNormalizer.unicodeValueOfNormalizedString("ń"));
+    }
+
+    @Test
+    void givenStringWithNonDecomposableUnicodeCharacters_whenUnicodeValueOfNormalizedString_thenReturnOriginalValue() {
+        assertEquals("\\u0142", StringNormalizer.unicodeValueOfNormalizedString("ł"));
+        assertEquals("\\u0127", StringNormalizer.unicodeValueOfNormalizedString("ħ"));
+        assertEquals("\\u0111", StringNormalizer.unicodeValueOfNormalizedString("đ"));
+    }
+}