* governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.filter;

/**
 * UrlFilter checks if a given url is a target one.
 *
 * @author shinsuke
 *
 */
public interface UrlFilter {

    /**
     * Initialize a url filter by sessionId.
     *
     * @param sessionId Session ID
     */
    void init(String sessionId);

    /**

  - Clone `kubernetes/kubernetes` in `update-vendor.sh` shallowly, instead of fetching all revisions
  - Speed up binpacking by reducing the number of PreFilter calls (call once per pod instead of #pods*#nodes times)
  - Speed up finding unneeded nodes by 5x+ in very large clusters by reducing the number of PreFilter calls
  - Expose `--max-nodes-total` as a metric
  - Errors in `IncreaseSize` changed from type `apiError` to `cloudProviderError`

- Consolidate ScoreWithNormalizePlugin into the ScorePlugin interface ([#83042](https://github.com/kubernetes/kubernetes/pull/83042), [@draveness](https://github.com/draveness))
- New APIs to allow adding/removing pods from pre-calculated prefilter state in the scheduling framework ([#82912](https://github.com/kubernetes/kubernetes/pull/82912), [@ahg-g](https://github.com/ahg-g))

 - The Scheduling Framework exposed `NodeInfos` to the PreFilter plugins. The PreFilter plugins now accepted the `NodeInfo` list from the arguments. ([#130720](https://github.com/kubernetes/kubernetes/pull/130720), [@saintube](https://github.com/saintube)) [SIG Node, Scheduling, Storage and Testing]
 

        crawler.crawlerContext.setMaxThreadCheckCount(3);
        crawler.crawlerContext.setMaxAccessCount(maxCount);
        crawler.crawlerContext.setNumOfThread(numOfThread);
        crawler.urlFilter.addInclude(url + ".*");
        crawler.urlFilter.addExclude(url + "/dir1/.*");
        final String sessionId = crawler.execute();
        assertEquals(maxCount, dataService.getCount(sessionId));
        dataService.delete(sessionId);
    }

        assertEquals(0, urlFilter.cachedIncludeSet.size());
        assertEquals(0, urlFilter.cachedExcludeSet.size());

        urlFilter.addExclude(".*[test.*");

        assertEquals(0, urlFilter.cachedIncludeSet.size());
        assertEquals(0, urlFilter.cachedExcludeSet.size());

        final String sessionId = "id1";
        urlFilter.init(sessionId);
        assertEquals(0, urlFilter.cachedIncludeSet.size());

        String sessionId = "test-session-006";
        urlFilter.init(sessionId);

        urlFilter.addExclude(".*\\.(css|js)$");
        urlFilter.addExclude(".*\\/admin\\/.*");
        urlFilter.addExclude(".*#.*");

        assertTrue(urlFilter.match("https://example.com/page.html"));
        assertFalse(urlFilter.match("https://example.com/style.css"));
        assertFalse(urlFilter.match("https://example.com/script.js"));

    /**
     * Returns the URL filter.
     * @return The UrlFilter instance.
     */
    public UrlFilter getUrlFilter() {
        return urlFilter;
    }

    /**
     * Sets the URL filter.
     * @param urlFilter The UrlFilter instance to set.
     */
    public void setUrlFilter(final UrlFilter urlFilter) {
        this.urlFilter = urlFilter;
    }

    /**
     * Returns the rule manager.

    text(
        "profiler",
        defaultProfiler,
        display = ParameterDisplay.PROMPT,
        allowEmpty = false,
        description =
            "Command line option for the performance test task to enable profiling. " +
                "For example `async-profiler`, `async-profiler-heap`, `async-profiler-all` or `jfr`. Use `none` for benchmarking only.",
    )
}

    }

    /**
     * Returns the URL filter.
     * @return The UrlFilter.
     */
    public UrlFilter getUrlFilter() {
        return urlFilter;
    }

    /**
     * Sets the URL filter.
     * @param urlFilter The UrlFilter.
     */
    public void setUrlFilter(final UrlFilter urlFilter) {
        this.urlFilter = urlFilter;
    }

    /**
     * Returns the rule manager.