update doc+test

digitalfondue · Jan 29, 2024 · e99ee54 · e99ee54
1 parent b0f9d94
commit e99ee54
Show file tree

Hide file tree

Showing 2 changed files with 19 additions and 6 deletions.
diff --git a/README.md b/README.md
@@ -130,11 +130,19 @@ static method in the helper class: `W3CDom.toW3CDocument`.
  - html by whatwg: https://html.spec.whatwg.org/multipage/syntax.html (of interest: tokenization, tree-construction)
  - entities: https://html.spec.whatwg.org/entities.json
 
-### template element handling
+### Template element handling
 
 The template element is a "normal" element, so the child nodes are _not_
 placed inside a documentFragment. This will be fixed.
 
+### Special parsing options
+
+The parser can be customized to allow some non-standard behaviour, you can see the following tests: https://github.com/digitalfondue/jfiveparse/blob/master/src/test/java/ch/digitalfondue/jfiveparse/OptionParseTest.java
+
+ - DISABLE_IGNORE_TOKEN_IN_BODY_START_TAG : allow to have for example "tr" tag without the containing table/tbody.
+ - INTERPRET_SELF_CLOSING_ANYTHING_ELSE :  When encountering unknown self-closing tag, they will be interpreted 
+   as it is and not as open tag only, thus creating a non-intuitive DOM.    
+
 ### Entities
 The &ntities; are by default (and by specification) parsed and interpreted. 
 This behavior can be disabled by:

diff --git a/src/test/java/ch/digitalfondue/jfiveparse/OptionParseTest.java b/src/test/java/ch/digitalfondue/jfiveparse/OptionParseTest.java
@@ -19,25 +19,30 @@
 import org.junit.Test;
 
 import java.util.Collections;
-import java.util.List;
 import java.util.stream.Collectors;
 
 public class OptionParseTest {
 
 
     @Test
-    public void testRawTableHanding() {
-        List<Node> l = JFiveParse.parseFragment("<tr><td>a</td></tr>", Collections.singleton(Option.DISABLE_IGNORE_TOKEN_IN_BODY_START_TAG));
-        Assert.assertEquals("<tr><td>a</td></tr>", JFiveParse.serialize(l.get(0)));
+    public void testRawTableHandling() {
+        // without option
+        Document dw = JFiveParse.parse("<html><body><tr><td>a</td></tr></body>");
+        Assert.assertEquals("<html><head></head><body>a</body></html>", JFiveParse.serialize(dw));
+
+        // with option
+        Document l = JFiveParse.parse("<html><body><tr><td>a</td></tr></body>", Collections.singleton(Option.DISABLE_IGNORE_TOKEN_IN_BODY_START_TAG));
+        Assert.assertEquals("<html><head></head><body><tr><td>a</td></tr></body></html>", JFiveParse.serialize(l));
     }
 
     @Test
     public void testOptionInterpretSelfClosing() {
+        // without option
         var res = JFiveParse.parseFragment("<hr /><sj-test /><sj-a><sj-b /></mj-a>");
         var html = res.stream().map(s -> ((Element) s).getOuterHTML()).collect(Collectors.joining());
         Assert.assertEquals("<hr><sj-test><sj-a><sj-b></sj-b></sj-a></sj-test>", html);
 
-        //
+        // with option
         var selfClosing = JFiveParse.parseFragment("<hr /><sj-test /><sj-a><sj-b /></mj-a>", Collections.singleton(Option.INTERPRET_SELF_CLOSING_ANYTHING_ELSE));
         var selfClosingHtml = selfClosing.stream().map(s -> ((Element) s).getOuterHTML()).collect(Collectors.joining());
         Assert.assertEquals("<hr><sj-test></sj-test><sj-a><sj-b></sj-b></sj-a>", selfClosingHtml);