Support html when parsing arXiv identifiers (#14474)

* Support html when parsing arXiv identifiers

- Added 'html' to ARXIV_PREFIX regex pattern to recognize arxiv.org/html/ URLs
- Added test cases for HTML URLs with HTTP/HTTPS and with/without version numbers

Fixes #14451

* Fix checkstyle violations - separate variable declarations

* Discard changes to .idea/codeStyles/Project.xml

* Add CHANGELOG.md entry

* Fix alphabetical ordering

---------

Co-authored-by: Oliver Kopp <[email protected]>

Author: omkarrr2533

CHANGELOG.md

@@ -29,6 +29,7 @@ Note that this project **does not** adhere to [Semantic Versioning](https://semv
 - We added the generation of follow-up questions in AI chat. [#12243](https://github.com/JabRef/jabref/issues/12243)
 - We added support for getting bibliographic information based on the arXiv ID or the ISSN. [#14458](https://github.com/JabRef/jabref/pull/14458)
 - We added support for "Search Google Scholar" and "Search Semantic Scholar" to quickly search for a selected entry's title in Google Scholar or Semantic Scholar directly from the main table's context menu [#12268](https://github.com/JabRef/jabref/issues/12268)
+- We added support for `html` when parsing the arXiv identifiers. [#14451](https://github.com/JabRef/jabref/issues/14451)
 - When parsing a plain text citation, we added support for recognizing and extracting arXiv identifiers. [#14455](https://github.com/JabRef/jabref/pull/14455)
 - We introduced a new "Search Engine URL Template" setting in Preferences to allow users to customize their search engine URL templates [#12268](https://github.com/JabRef/jabref/issues/12268)
 

jablib/src/main/java/org/jabref/model/entry/identifier/ArXivIdentifier.java

@@ -20,7 +20,7 @@
 public class ArXivIdentifier extends EprintIdentifier {
     private static final Logger LOGGER = LoggerFactory.getLogger(ArXivIdentifier.class);
 
-    private static final String ARXIV_PREFIX = "http(s)?://arxiv.org/(abs|pdf)/|arxiv|arXiv";
+    private static final String ARXIV_PREFIX = "http(s)?://arxiv.org/(abs|html|pdf)/|arxiv|arXiv";
     private final String identifier;
     private final String classification;
     private final String version;

jablib/src/test/java/org/jabref/model/entry/identifier/ArXivIdentifierTest.java

@@ -171,4 +171,25 @@ void constructCorrectURLForEprint() throws URISyntaxException {
         Optional<ArXivIdentifier> parsed = ArXivIdentifier.parse("0706.0001v1");
         assertEquals(Optional.of(new URI("https://arxiv.org/abs/0706.0001v1")), parsed.get().getExternalURI());
     }
+
+    @Test
+    void parseHtmlUrl() {
+        Optional<ArXivIdentifier> parsed = ArXivIdentifier.parse("https://arxiv.org/html/2511.01348v2");
+
+        assertEquals(Optional.of(new ArXivIdentifier("2511.01348", "2", "")), parsed);
+    }
+
+    @Test
+    void parseHtmlUrlWithoutVersion() {
+        Optional<ArXivIdentifier> parsed = ArXivIdentifier.parse("https://arxiv.org/html/2511.01348");
+
+        assertEquals(Optional.of(new ArXivIdentifier("2511.01348", "", "")), parsed);
+    }
+
+    @Test
+    void parseHttpHtmlUrl() {
+        Optional<ArXivIdentifier> parsed = ArXivIdentifier.parse("http://arxiv.org/html/1502.05795v1");
+
+        assertEquals(Optional.of(new ArXivIdentifier("1502.05795", "1", "")), parsed);
+    }
 }