Merge pull request #16762 from adalagandev/BAEL-5732_Unescape_HTML_Character_Entities_in_Java

BAEL-5732 Initial code changes for Unescaping html entities/chars.

Author: Maiklins

core-java-modules/core-java-string-operations-9/pom.xml

@@ -44,6 +44,27 @@
             <artifactId>commons-collections4</artifactId>
             <version>${apache.commons.collection.version}</version>
         </dependency>
+        <dependency>
+            <groupId>org.apache.commons</groupId>
+            <artifactId>commons-text</artifactId>
+            <version>${commons-text.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.unbescape</groupId>
+            <artifactId>unbescape</artifactId>
+            <version>1.1.6.RELEASE</version>
+        </dependency>
+        <dependency>
+            <groupId>org.jsoup</groupId>
+            <artifactId>jsoup</artifactId>
+            <version>1.14.3</version>
+        </dependency>
+        <dependency>
+            <groupId>org.springframework</groupId>
+            <artifactId>spring-web</artifactId>
+            <version>6.1.6</version>
+        </dependency>
+
     </dependencies>
 
     <build>
@@ -67,4 +88,4 @@
         <icu4j.version>74.1</icu4j.version>
     </properties>
 
-</project>
+</project>

core-java-modules/core-java-string-operations-9/src/test/java/com/baeldung/unescapehtml/HtmlUnescapeUnitTest.java

@@ -0,0 +1,53 @@
+package com.baeldung.unescapehtml;
+
+
+import org.apache.commons.text.StringEscapeUtils;
+import org.jsoup.nodes.Entities;
+import org.junit.Assert;
+import org.junit.jupiter.api.Test;
+import org.springframework.web.util.HtmlUtils;
+import org.unbescape.html.HtmlEscape;
+
+public class HtmlUnescapeUnitTest {
+    @Test
+    public void givenAStringsWithHTMLCharacters_whenConvertedWithApacheCommons_thenUnescape(){
+        String expectedQuote = "\"Hello\" Baeldung";
+        String escapedQuote = ""Hello" Baeldung";
+        Assert.assertEquals(expectedQuote, StringEscapeUtils.unescapeHtml4(escapedQuote));
+
+        String escapedStringsWithHtmlSymbol = "<p><strong>Test sentence in bold type.</strong></p>";
+        String expectedStringsWithHtmlSymbol = "<p><strong>Test sentence in bold type.</strong></p>";
+        Assert.assertEquals(expectedStringsWithHtmlSymbol, StringEscapeUtils.unescapeHtml4(escapedStringsWithHtmlSymbol));
+    }
+    @Test
+    public void givenAStringsWithHTMLCharacters_whenConvertedWithSpringHtmlUtil_thenUnescape() {
+        String expectedQuote = "\"Code smells\" -Martin Fowler";
+        String escapedQuote = "&quot;Code smells&quot; -Martin Fowler";
+        Assert.assertEquals(expectedQuote, HtmlUtils.htmlUnescape(escapedQuote));
+
+        String escapedStringsWithHtmlSymbol = "&lt;p&gt;Loren Ipsum is a popular paragraph.&lt;/p&gt;";
+        String expectedStringsWithHtmlSymbol = "<p>Loren Ipsum is a popular paragraph.</p>";
+        Assert.assertEquals(expectedStringsWithHtmlSymbol, HtmlUtils.htmlUnescape(escapedStringsWithHtmlSymbol));
+    }
+
+    @Test
+    public void givenAStringsWithHTMLCharacters_whenConvertedWithUnbescape_thenUnescape() {
+        String expectedQuote = "\"Carpe diem\" -Horace";
+        String escapedQuote = "&quot;Carpe diem&quot; -Horace";
+        Assert.assertEquals(expectedQuote, HtmlEscape.unescapeHtml(escapedQuote));
+
+        String escapedStringsWithHtmlSymbol = "&lt;p&gt;&lt;em&gt;Pizza is a famous Italian food. Duh.&lt;/em&gt;&lt;/p&gt;";
+        String expectedStringsWithHtmlSymbol = "<p><em>Pizza is a famous Italian food. Duh.</em></p>";
+        Assert.assertEquals(expectedStringsWithHtmlSymbol, HtmlEscape.unescapeHtml(escapedStringsWithHtmlSymbol));
+    }
+    @Test
+    public void givenAStringsWithHTMLCharacters_whenConvertedWithJsoup_thenUnescape() {
+        String expectedQuote = "\"Jsoup\" is another strong library";
+        String escapedQuote = "&quot;Jsoup&quot; is another strong library";
+        Assert.assertEquals(expectedQuote,  Entities.unescape(escapedQuote));
+
+        String escapedStringsWithHtmlSymbol = "&lt;p&gt;It simplifies working with real-world &lt;strong&gt;HTML&lt;/strong&gt; and &lt;strong&gt;XML&lt;/strong&gt;&lt;/p&gt;";
+        String expectedStringsWithHtmlSymbol = "<p>It simplifies working with real-world <strong>HTML</strong> and <strong>XML</strong></p>";
+        Assert.assertEquals(expectedStringsWithHtmlSymbol,  Entities.unescape(escapedStringsWithHtmlSymbol));
+    }
+}

spring-core-4/pom.xml

@@ -80,4 +80,4 @@
         <commons-text.version>1.10.0</commons-text.version>
     </properties>
 
-</project>
+</project>