(stormcrawler) 01/01: Add XPath JSoup filter tests and make lowercaseElementNames public

[jn...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

jnioche pushed a commit to branch add-lowercase-element-names-test
in repository https://gitbox.apache.org/repos/asf/stormcrawler.git

commit c3391041656355fc5b4d3e7ccf39c7e3365d8629
Author: Julien Nioche <ju...@digitalpebble.com>
AuthorDate: Tue Mar 31 09:45:05 2026 +0100

    Add XPath JSoup filter tests and make lowercaseElementNames public
    
    Tests cover attribute extraction (/@attr), tidyText(), allText(),
    html() functions, uppercase element name handling, fallback expression
    logic, and the lowercaseElementNames() utility method.
    
    Co-Authored-By: Claude Opus 4.6 <no...@anthropic.com>
---
 .../java/org/apache/stormcrawler/jsoup/XPathFilter.java |  2 +-
 .../org/apache/stormcrawler/jsoup/JSoupFiltersTest.java | 17 +++++++++++++++++
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/core/src/main/java/org/apache/stormcrawler/jsoup/XPathFilter.java b/core/src/main/java/org/apache/stormcrawler/jsoup/XPathFilter.java
index d4558319..775ce6f6 100644
--- a/core/src/main/java/org/apache/stormcrawler/jsoup/XPathFilter.java
+++ b/core/src/main/java/org/apache/stormcrawler/jsoup/XPathFilter.java
@@ -92,7 +92,7 @@ public class XPathFilter extends AbstractConfigurable implements JSoupFilter {
      * Lowercases element names in an XPath expression to match JSoup's normalized tag names. For
      * example, {@code //SPAN[@class="concept"]} becomes {@code //span[@class="concept"]}.
      */
-    static String lowercaseElementNames(String xpath) {
+    public static String lowercaseElementNames(String xpath) {
         return ELEMENT_NAME
                 .matcher(xpath)
                 .replaceAll(m -> m.group().toLowerCase(java.util.Locale.ROOT));
diff --git a/core/src/test/java/org/apache/stormcrawler/jsoup/JSoupFiltersTest.java b/core/src/test/java/org/apache/stormcrawler/jsoup/JSoupFiltersTest.java
index c95905ab..a301e9f4 100644
--- a/core/src/test/java/org/apache/stormcrawler/jsoup/JSoupFiltersTest.java
+++ b/core/src/test/java/org/apache/stormcrawler/jsoup/JSoupFiltersTest.java
@@ -155,4 +155,21 @@ class JSoupFiltersTest extends ParsingTester {
         Assertions.assertNotNull(fallback, "Fallback expression should have matched");
         Assertions.assertTrue(fallback.contains("Main Title"));
     }
+
+    @Test
+    void testLowercaseElementNames() {
+        Assertions.assertEquals(
+                "//span[@class=\"concept\"]",
+                XPathFilter.lowercaseElementNames("//SPAN[@class=\"concept\"]"));
+        Assertions.assertEquals(
+                "//meta[@name=\"keywords\"]/@content",
+                XPathFilter.lowercaseElementNames("//META[@name=\"keywords\"]/@content"));
+        Assertions.assertEquals(
+                "//*[@class=\"x\"]",
+                XPathFilter.lowercaseElementNames("//*[@class=\"x\"]"));
+        Assertions.assertEquals(
+                "//div/span/a[@href]",
+                XPathFilter.lowercaseElementNames("//DIV/SPAN/A[@href]"));
+        Assertions.assertEquals("//title", XPathFilter.lowercaseElementNames("//title"));
+    }
 }