- [Confluence/Jira](https://github.com/codelibs/fess-ds-atlassian)
 - [Box](https://github.com/codelibs/fess-ds-box)
 - [CSV](https://github.com/codelibs/fess-ds-csv)
 - [Database](https://github.com/codelibs/fess-ds-db)
 - [Dropbox](https://github.com/codelibs/fess-ds-dropbox)
 - [Elasticsearch](https://github.com/codelibs/fess-ds-elasticsearch)
 - [Git](https://github.com/codelibs/fess-ds-git)

        method.invoke(crawlerThread, "http://example.com/child", "http://example.com/", 1.0f, 2);

        verify(urlQueueService, times(1)).offerAll(anyString(), any());
    }

    /**
     * Test storeChildUrl with depth exceeding maxDepth.
     */
    public void test_storeChildUrl_exceedsMaxDepth() throws Exception {
        when(urlFilter.match("http://example.com/child")).thenReturn(true);

        assertEquals("http://www.example.com/page2.html", sitemaps[1].getLoc());
        assertEquals("http://www.example.com/page3.html", sitemaps[2].getLoc());
        assertEquals("https://www.example.com/page4.html", sitemaps[3].getLoc());
    }

    public void test_parseXmlSitemapsIndex_missingLoc() {
        // Sitemap index with missing loc should skip that entry

        RequestData data1 = context.build();
        assertEquals("https://example.com", data1.getUrl());

        // Modify context
        context.url("https://modified.com");

        RequestData data2 = context.build();
        assertEquals("https://modified.com", data2.getUrl());

        // data1 should also be modified (same object)
        assertEquals("https://modified.com", data1.getUrl());

        Proxy proxy = Proxy.NO_PROXY;

        CurlRequest result = request.proxy(proxy);

        assertSame(request, result); // Fluent API
        assertSame(proxy, request.proxy());
    }

    @Test
    public void testEncodingMethod() {
        CurlRequest request = new CurlRequest(Method.GET, "https://example.com");
        String encoding = "ISO-8859-1";

        assertTrue(patterns.get(0).matcher("http://example.com/page1").matches());
        assertFalse(patterns.get(0).matcher("http://other.com/page1").matches());

        urlFilterService.delete(sessionId);
    }

    public void test_addExcludeUrlFilter_singleTx() {
        final String sessionId = "session2";
        final String urlPattern = "http://example.com/admin/.*";

Name,Email,Age,Department
John Doe,john@example.com,30,Engineering
Jane Smith,jane@example.com,28,Marketing
Bob Johnson,bob@example.com,35,Sales

import org.codelibs.fess.exception.StorageException;

import com.google.api.gax.paging.Page;
import com.google.auth.oauth2.GoogleCredentials;
import com.google.cloud.NoCredentials;
import com.google.cloud.storage.Blob;
import com.google.cloud.storage.BlobId;
import com.google.cloud.storage.BlobInfo;
import com.google.cloud.storage.Bucket;
import com.google.cloud.storage.BucketInfo;
import com.google.cloud.storage.Storage;

        data.putValue(ExtractData.URL, "https://example.com/test.pdf");
        data.putValues(ExtractData.FILE_PASSWORDS, new String[] { "pass1", "pass2" });

        assertEquals("test.pdf", data.getValues(ExtractData.RESOURCE_NAME_KEY)[0]);
        assertEquals("https://example.com/test.pdf", data.getValues(ExtractData.URL)[0]);

                return new ByteArrayInputStream("Test response body".getBytes());
            }

            @Override
            public String getUrl() {
                return "http://example.com/test";
            }
        };

        File tempFile = ResponseDataUtil.createResponseBodyFile(responseData);

        assertNotNull(tempFile);
        assertTrue(tempFile.exists());