Added ::cdata node selector

Supplements #2324

Author: jhy

CHANGES.md

@@ -11,7 +11,7 @@
 * If you happen to be using any of the deprecated methods, please take the opportunity now to migrate away from them, as they will be removed in a future release.
 
 ### Improvements
-* Enhanced the `Selector` to support direct matching against nodes such as comments and text nodes. For example, you can now find an element that follows a specific comment: `::comment:contains(prices) + p` will select `p` elements immediately after a `<!-- prices: -->` comment. Supported types include `::node`, `::leafnode`, `::comment`, `::text`, and `::data`. Node contextual selectors like `::node:contains(text)`, `:matches(regex)`, and `:blank` are also supported. Introduced `Element#selectNodes(String css)` and `Element#selectNodes(String css, Class nodeType)` for direct node selection. [#2324](https://github.com/jhy/jsoup/pull/2324)
+* Enhanced the `Selector` to support direct matching against nodes such as comments and text nodes. For example, you can now find an element that follows a specific comment: `::comment:contains(prices) + p` will select `p` elements immediately after a `<!-- prices: -->` comment. Supported types include `::node`, `::leafnode`, `::comment`, `::text`, `::data`, and `::cdata`. Node contextual selectors like `::node:contains(text)`, `:matches(regex)`, and `:blank` are also supported. Introduced `Element#selectNodes(String css)` and `Element#selectNodes(String css, Class nodeType)` for direct node selection. [#2324](https://github.com/jhy/jsoup/pull/2324)
 * Added `TagSet#onNewTag(Consumer<Tag> customizer)`: register a callback that’s invoked for each new or cloned Tag when it’s inserted into the set. Enables dynamic tweaks of tag options (for example, marking all custom tags as self-closing, or everything in a given namespace as preserving whitespace).
 * Made `TokenQueue` and `CharacterReader` autocloseable, to ensure that they will release their buffers back to the buffer pool, for later reuse.
 * Added `Selector#evaluatorOf(String css)`, as a clearer way to obtain an Evaluator from a CSS query. An alias of `QueryParser.parse(String css)`.

src/main/java/org/jsoup/select/QueryParser.java

@@ -2,6 +2,7 @@
 
 import org.jsoup.internal.StringUtil;
 import org.jsoup.helper.Validate;
+import org.jsoup.nodes.CDataNode;
 import org.jsoup.nodes.Comment;
 import org.jsoup.nodes.DataNode;
 import org.jsoup.nodes.LeafNode;
@@ -281,6 +282,9 @@ private Evaluator parseNodeSelector() {
             case "data":
                 left = new NodeEvaluator.InstanceType(DataNode.class, pseudo);
                 break;
+            case "cdata":
+                left = new NodeEvaluator.InstanceType(CDataNode.class, pseudo);
+                break;
             default:
                 throw new Selector.SelectorParseException("Could not parse query '%s': unexpected token at '%s'", query,
                     tq.remainder());

src/main/java/org/jsoup/select/Selector.java

@@ -94,10 +94,11 @@
  <tr><td>::leafnode</td><td>Matches any leaf-node (this is, a Node which is not an Element)</td><td></td></tr>
  <tr><td>::comment</td><td>Matches a Comment node</td><td></td></tr>
  <tr><td>::text</td><td>Matches a TextNode</td><td></td></tr>
- <tr><td>::data</td><td>Matches a DataNode</td><td></td></tr>
- <tr><td>::node:contains(text)</td><td>Matches a node that has a (normalized, case-insensitive) value containing <i>text</i>.</td><td>::comment:contains(foo bar)</td></tr>
- <tr><td>::node:matches(regex)</td><td>Matches a node that has a value matching the regex.</td><td>::comment:matches(\\d+)</td></tr>
- <tr><td>::node:blank</td><td>Matches a node that has either no value, or a value of only whitespace.</td><td>::comment:not(:blank)</td></tr>
+ <tr><td>::data</td><td>Matches a DataNode (e.g. the content of a <code>script</code> or a <code>style</code> element)</td><td></td></tr>
+ <tr><td>::cdata</td><td>Matches a CDataNode (which are only present in XML)</td><td></td></tr>
+ <tr><td>::node:contains(text)</td><td>Matches a node that has a (normalized, case-insensitive) value containing <i>text</i>.</td><td><code>::comment:contains(foo bar)</code></td></tr>
+ <tr><td>::node:matches(regex)</td><td>Matches a node that has a value matching the regex.</td><td><code>::comment:matches(\\d+)</code></td></tr>
+ <tr><td>::node:blank</td><td>Matches a node that has either no value, or a value of only whitespace.</td><td><code>::comment:not(:blank)</code></td></tr>
  </table>
 
  <p>A word on using regular expressions in these selectors: depending on the content of the regex, you will need to quote the pattern using <b><code>Pattern.quote("regex")</code></b> for it to parse correctly through both the selector parser and the regex parser. E.g. <code>String query = "div:matches(" + Pattern.quote(regex) + ");"</code>.</p>

src/test/java/org/jsoup/select/SelectorTest.java

@@ -2,6 +2,7 @@
 
 import org.jsoup.Jsoup;
 import org.jsoup.MultiLocaleExtension.MultiLocaleTest;
+import org.jsoup.nodes.CDataNode;
 import org.jsoup.nodes.Comment;
 import org.jsoup.nodes.Document;
 import org.jsoup.nodes.Element;
@@ -1688,4 +1689,33 @@ public void testAncestorChain() {
         assertEquals("432", nodes.get(3).nodeValue());
     }
 
+    @Test void cdataNodes() {
+        String xml = "<body><![CDATA[One]]><p>Two</p><![CDATA[Three]]><x><![CDATA[ ]]></body>";
+        Document doc = Jsoup.parse(xml, Parser.xmlParser());
+
+        // via leafnode:
+        Nodes<CDataNode> leafnodes = doc.selectNodes("::leafnode", CDataNode.class);
+        assertEquals(3, leafnodes.size());
+
+        // cdata via unfiltered
+        Nodes<Node> nodes = doc.selectNodes("::cdata");
+        assertEquals(3, nodes.size());
+
+        // (not) blank:
+        Nodes<CDataNode> notBlanks = doc.selectNodes("::cdata:not(:blank)", CDataNode.class);
+        assertEquals(2, notBlanks.size());
+        assertEquals("One", notBlanks.get(0).nodeValue());
+        assertEquals("Three", notBlanks.get(1).nodeValue());
+
+        // contains:
+        Nodes<CDataNode> contains = doc.selectNodes("::cdata:contains(One)", CDataNode.class);
+        assertEquals(1, contains.size());
+        assertEquals("One", contains.get(0).nodeValue());
+
+        // matches:
+        Nodes<CDataNode> matches = doc.selectNodes("::cdata:matches(re)", CDataNode.class);
+        assertEquals(1, matches.size());
+        assertEquals("Three", matches.get(0).nodeValue());
+    }
+
 }