refactor(DisplayComponent): strip HTML using Jsoup, add Apache Common…

…s 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.
unit-mesh · Aug 7, 2024 · 53f3969 · 53f3969
1 parent 50f3c8b
commit 53f3969
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git 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
@@ -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)
     }
 }