From 53f39693f740d12720032d7526d02be89e09e38e Mon Sep 17 00:00:00 2001
From: Phodal Huang <h@phodal.com>
Date: Wed, 7 Aug 2024 21:47:16 +0800
Subject: [PATCH] refactor(DisplayComponent): strip HTML using Jsoup, add
 Apache Commons Text for XML entity unescaping #218

Update `DisplayComponent` to use Jsoup for HTML stripping and include Apache Commons Text library for unescaping XML entities. This change improves the reliability of text processing by utilizing specialized libraries.
---
 build.gradle.kts                                                | 2 ++
 .../kotlin/cc/unitmesh/devti/gui/component/DisplayComponent.kt  | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/build.gradle.kts b/build.gradle.kts
index f1e72cd1a..1eedb4686 100644
--- a/build.gradle.kts
+++ b/build.gradle.kts
@@ -434,6 +434,8 @@ project(":") {
         // token count
         implementation("com.knuddels:jtokkit:1.0.0")
 
+        implementation("org.apache.commons:commons-text:1.12.0")
+
         // junit
         testImplementation("io.kotest:kotest-assertions-core:5.7.2")
         testImplementation("junit:junit:4.13.2")
diff --git a/src/main/kotlin/cc/unitmesh/devti/gui/component/DisplayComponent.kt b/src/main/kotlin/cc/unitmesh/devti/gui/component/DisplayComponent.kt
index b4bde9a25..3d90a44f5 100644
--- a/src/main/kotlin/cc/unitmesh/devti/gui/component/DisplayComponent.kt
+++ b/src/main/kotlin/cc/unitmesh/devti/gui/component/DisplayComponent.kt
@@ -30,9 +30,7 @@ class DisplayComponent(question: String) : JEditorPane() {
     }
 
     private fun stripHtmlAndUnescapeXmlEntities(input: String): String {
-        // 使用 Jsoup 去除HTML标签
         val text = Jsoup.parse(input).text()
-        // 使用 Apache Commons Text 解码XML实体
         return StringEscapeUtils.unescapeXml(text)
     }
 }
\ No newline at end of file