upsert - Code Search

fess-crawler-opensearch/src/main/java/org/codelibs/fess/crawler/service/impl/OpenSearchUrlFilterService.java

        final OpenSearchUrlFilter esUrlFilter = new OpenSearchUrlFilter();
        esUrlFilter.setSessionId(sessionId);
        esUrlFilter.setFilterType(INCLUDE);
        esUrlFilter.setUrl(url);
        insert(esUrlFilter, OpType.INDEX);
        includeFilterCache.invalidate(sessionId);
    }

    /**
     * Adds multiple include URL filters for the specified session.
     *
     * @param sessionId The session ID.

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Thu Aug 07 02:55:08 UTC 2025

- 9.2K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-opensearch/src/main/java/org/codelibs/fess/crawler/service/impl/OpenSearchDataService.java

        super.insert(accessResult, accessResult.getId() == null ? OpType.CREATE : OpType.INDEX);
    }

    /**
     * Updates an access result in the OpenSearch index.
     *
     * @param accessResult The access result to update.
     */
    @Override
    public void update(final OpenSearchAccessResult accessResult) {
        super.insert(accessResult, OpType.INDEX);
    }

    /**

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Thu Aug 07 02:55:08 UTC 2025

- 10.9K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/service/impl/UrlQueueServiceImpl.java

        }
    }

    /*
     * (non-Javadoc)
     *
     * @see
     * org.codelibs.fess.crawler.service.UrlQueueService#insert(org.codelibs.fess.crawler.entity
     * .UrlQueue)
     */
    @Override
    public void insert(final UrlQueueImpl<Long> urlQueue) {
        final Queue<UrlQueueImpl<Long>> urlQueueList = dataHelper.getUrlQueueList(urlQueue.getSessionId());

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 9.3K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/resources/extractor/eml/sample2.eml

<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name="viewport" content="width=device-width, minimum-scale=1.0, maximum-scale=1.0, user-scalable=0" />
<meta name="apple-mobile-web-app-capable" content="yes" />
<style type="text/css">

@media only screen and (max-width: 420px) {
a[class="article-headline"] {
font-size:22px !important;

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Jan 16 07:50:35 UTC 2016

- 91.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/rule/impl/RuleManagerImpl.java

     */
    @Override
    public void addRule(final Rule rule) {
        ruleList.add(rule);
    }

    /**
     * Adds a rule at the specified position in the rule list.
     * @param index the position to insert the rule
     * @param rule the rule to add
     */
    @Override
    public void addRule(final int index, final Rule rule) {
        ruleList.add(index, rule);
    }

    /*
     * (non-Javadoc)
     *

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 3.4K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/ApiExtractor.java

    public void setAuthSchemeProviderMap(final Map<String, AuthSchemeProvider> authSchemeProviderMap) {
        this.authSchemeProviderMap = authSchemeProviderMap;
    }

    /**
     * Sets the user agent string.
     * @param userAgent The user agent string.
     */
    public void setUserAgent(final String userAgent) {
        this.userAgent = userAgent;
    }

    /**
     * Sets the credentials provider.

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Thu Aug 07 02:55:08 UTC 2025

- 12.2K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/client/http/HcHttpClient.java

     */
    public void setCookieSpec(final String cookieSpec) {
        this.cookieSpec = cookieSpec;
    }

    /**
     * Sets the user agent string.
     *
     * @param userAgent The user agent string
     */
    public void setUserAgent(final String userAgent) {
        this.userAgent = userAgent;
    }

    /**
     * Sets the proxy host name.

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Thu Aug 07 02:55:08 UTC 2025

- 52.2K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/RobotsTxtHelper.java

 * </a></li>
 * </ul>
 *
 * @author bowez
 * @author shinsuke
 *
 */
public class RobotsTxtHelper {

    /** Pattern for parsing user-agent records. */
    protected static final Pattern USER_AGENT_RECORD =
            Pattern.compile("^user-agent:\\s*([^\\t\\n\\x0B\\f\\r]+)\\s*$", Pattern.CASE_INSENSITIVE);

    /** Pattern for parsing disallow records. */

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 7.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-opensearch/src/test/java/org/codelibs/fess/crawler/util/CrawlerWebServer.java

            final File tempDir = File.createTempFile("crawlerDocRoot", "");
            tempDir.delete();
            tempDir.mkdirs();

            final StringBuilder buf = new StringBuilder();
            buf.append("User-agent: *").append('\n');
            buf.append("Disallow: /admin/").append('\n');
            buf.append("Disallow: /websvn/").append('\n');
            final File robotTxtFile = new File(tempDir, "robots.txt");

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/RuleManagerTest.java

        TestRule rule3 = new TestRule("rule3", true);

        ruleManager.addRule(rule1);
        ruleManager.addRule(rule3);
        ruleManager.addRule(1, rule2); // Insert in middle

        List<Rule> rules = ruleManager.getRules();
        assertEquals(3, rules.size());
        assertEquals("rule1", rules.get(0).getRuleId());
        assertEquals("rule2", rules.get(1).getRuleId());

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Sep 06 04:15:37 UTC 2025

- 23.8K bytes

- Viewed (0)

Search Options