From ddf531faa7b99d06eae049fd6058fe72e32d4aaa Mon Sep 17 00:00:00 2001
From: Kai Yuan <kent.yuan@Gmail.com>
Date: Thu, 11 Nov 2021 23:19:32 +0100
Subject: [PATCH] BAEL-5194 rm html tags (#11404)

---
 xml/pom.xml                                   | 19 ++++++
 .../delhtmltags/RemoveHtmlTagsLiveTest.java   | 61 +++++++++++++++++++
 .../xmlhtml/delhtmltags/example1.html         | 15 +++++
 .../xmlhtml/delhtmltags/example2.html         | 22 +++++++
 4 files changed, 117 insertions(+)
 create mode 100644 xml/src/test/java/com/baeldung/xmlhtml/delhtmltags/RemoveHtmlTagsLiveTest.java
 create mode 100644 xml/src/test/resources/xmlhtml/delhtmltags/example1.html
 create mode 100644 xml/src/test/resources/xmlhtml/delhtmltags/example2.html

diff --git a/xml/pom.xml b/xml/pom.xml
index d8aa77583b..d05f2401e3 100644
--- a/xml/pom.xml
+++ b/xml/pom.xml
@@ -14,6 +14,22 @@
     </parent>
 
     <dependencies>
+        <dependency>
+            <groupId>org.jsoup</groupId>
+            <artifactId>jsoup</artifactId>
+            <version>${jsoup.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>net.sourceforge.htmlcleaner</groupId>
+            <artifactId>htmlcleaner</artifactId>
+            <version>${htmlcleaner.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>net.htmlparser.jericho</groupId>
+            <artifactId>jericho-html</artifactId>
+            <version>${jericho.version}</version>
+        </dependency>
+
         <!-- xml libraries -->
         <dependency>
             <groupId>org.dom4j</groupId>
@@ -361,6 +377,9 @@
         <!-- maven plugins -->
         <maven-jibx-plugin.version>1.3.1</maven-jibx-plugin.version>
         <maven-compiler-plugin.version>3.8.0</maven-compiler-plugin.version>
+        <jsoup.version>1.14.3</jsoup.version>
+        <htmlcleaner.version>2.25</htmlcleaner.version>
+        <jericho.version>3.4</jericho.version>
     </properties>
 
 </project>
\ No newline at end of file
diff --git a/xml/src/test/java/com/baeldung/xmlhtml/delhtmltags/RemoveHtmlTagsLiveTest.java b/xml/src/test/java/com/baeldung/xmlhtml/delhtmltags/RemoveHtmlTagsLiveTest.java
new file mode 100644
index 0000000000..b05123cbdc
--- /dev/null
+++ b/xml/src/test/java/com/baeldung/xmlhtml/delhtmltags/RemoveHtmlTagsLiveTest.java
@@ -0,0 +1,61 @@
+package com.baeldung.xmlhtml.delhtmltags;
+
+import net.htmlparser.jericho.Renderer;
+import net.htmlparser.jericho.Segment;
+import net.htmlparser.jericho.Source;
+import org.htmlcleaner.CleanerProperties;
+import org.htmlcleaner.HtmlCleaner;
+import org.jsoup.Jsoup;
+import org.junit.jupiter.api.Test;
+
+import java.io.IOException;
+import java.net.URISyntaxException;
+import java.nio.file.Files;
+import java.nio.file.Paths;
+
+class RemoveHtmlTagsLiveTest {
+
+    @Test
+    void givenHtml1_whenRemoveTagsByRegex_thenPrintText() throws IOException, URISyntaxException {
+        String html = new String(Files.readAllBytes(
+            (Paths.get(getClass().getResource("/xmlhtml/delhtmltags/example1.html").toURI()))));
+        String result = html.replaceAll("<[^>]*>", "")
+            .replaceAll("(?m)^\\s*$", ""); // remove empty and blank lines
+        System.out.println(result);
+    }
+
+    @Test
+    void givenHtml2_whenRemoveTagsByRegex_thenPrintText() throws IOException, URISyntaxException {
+        String html = new String(Files.readAllBytes(
+            (Paths.get(getClass().getResource("/xmlhtml/delhtmltags/example2.html").toURI()))));
+        String result = html.replaceAll("<[^>]*>", "");
+        System.out.println(result);
+    }
+
+    @Test
+    void givenHtml2_whenRemoveTagsByJsoup_thenPrintText() throws IOException, URISyntaxException {
+        String html = new String(Files.readAllBytes(
+            (Paths.get(getClass().getResource("/xmlhtml/delhtmltags/example2.html").toURI()))));
+        System.out.println(Jsoup.parse(html).text());
+    }
+
+    @Test
+    void givenHtml2_whenRemoveTagsByHtmlCleaner_thenPrintText() throws IOException, URISyntaxException {
+        String html = new String(Files.readAllBytes(
+            (Paths.get(getClass().getResource("/xmlhtml/delhtmltags/example2.html").toURI()))));
+        CleanerProperties props = new CleanerProperties();
+        props.setPruneTags("script");
+        String result = new HtmlCleaner(props).clean(html).getText().toString();
+        System.out.println(result);
+    }
+
+    @Test
+    void givenHtml2_whenRemoveTagsByJericho_thenPrintText() throws IOException, URISyntaxException {
+        String html = new String(Files.readAllBytes(
+            (Paths.get(getClass().getResource("/xmlhtml/delhtmltags/example2.html").toURI()))));
+        Source htmlSource = new Source(html);
+        Segment segment = new Segment(htmlSource, 0, htmlSource.length());
+        Renderer htmlRender = new Renderer(segment).setIncludeHyperlinkURLs(true);
+        System.out.println(htmlRender);
+    }
+}
diff --git a/xml/src/test/resources/xmlhtml/delhtmltags/example1.html b/xml/src/test/resources/xmlhtml/delhtmltags/example1.html
new file mode 100644
index 0000000000..43f3a22ef4
--- /dev/null
+++ b/xml/src/test/resources/xmlhtml/delhtmltags/example1.html
@@ -0,0 +1,15 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+        "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+<head>
+    <title>This is the page title</title>
+</head>
+<body>
+    <p>
+        If the application X doesn't start, the possible causes could be:<br/>
+        1. <a href="maven.com">Maven</a> is not installed.<br/>
+        2. Not enough disk space.<br/>
+        3. Not enough memory.
+    </p>
+</body>
+</html>
\ No newline at end of file
diff --git a/xml/src/test/resources/xmlhtml/delhtmltags/example2.html b/xml/src/test/resources/xmlhtml/delhtmltags/example2.html
new file mode 100644
index 0000000000..532eadc101
--- /dev/null
+++ b/xml/src/test/resources/xmlhtml/delhtmltags/example2.html
@@ -0,0 +1,22 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+        "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+<head>
+    <title>This is the page title</title>
+</head>
+<script>
+    // some interesting script functions
+</script>
+<body>
+    <p>
+        If the application X doesn't start, the possible causes could be:<br/>
+        1. <a
+            id="link"
+            href="http://maven.apache.org/">
+            Maven
+            </a> is not installed.<br/>
+        2. Not enough (<1G) disk space.<br/>
+        3. Not enough (<64MB) memory.<br/>
+    </p>
+</body>
+</html>
\ No newline at end of file