[Java] Handle comment nodes (#764)

google · Oct 21, 2024 · 02fb71c · 02fb71c
1 parent 9f14646
commit 02fb71c
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 1 deletion.
diff --git a/java/src/main/java/com/google/budoux/HTMLProcessor.java b/java/src/main/java/com/google/budoux/HTMLProcessor.java
@@ -32,6 +32,7 @@
 import java.util.Set;
 import java.util.stream.Collectors;
 import org.jsoup.Jsoup;
+import org.jsoup.nodes.Comment;
 import org.jsoup.nodes.Document;
 import org.jsoup.nodes.Element;
 import org.jsoup.nodes.Node;
@@ -156,7 +157,7 @@ public void head(Node node, int depth) {
 
     @Override
     public void tail(Node node, int depth) {
-      if (node.nodeName().equals("body") || node instanceof TextNode) {
+      if (node.nodeName().equals("body") || node instanceof TextNode || node instanceof Comment) {
         return;
       }
       // assume node instanceof Element;

diff --git a/java/src/test/java/com/google/budoux/HTMLProcessorTest.java b/java/src/test/java/com/google/budoux/HTMLProcessorTest.java
@@ -136,4 +136,12 @@ public void testGetTextWhiteSpaceAcrossElements() {
     String result = HTMLProcessor.getText(html);
     assertEquals(" 1  2 ", result);
   }
+
+  @Test
+  public void testResolveWithComments() {
+    List<String> phrases = Arrays.asList("abc", "def", "ghi", "jkl");
+    String html = "abcdef<!-- comments should be ignored-->ghijkl";
+    String result = HTMLProcessor.resolve(phrases, html, "<wbr>");
+    assertEquals(this.wrap("abc<wbr>def<wbr>ghi<wbr>jkl"), result);
+  }
 }