- Sort Score
- Result 10 results
- Languages All
Results 1 - 10 of 34 for aient (2.82 sec)
-
fess-crawler/src/test/resources/org/codelibs/fess/crawler/helper/robots_wildcard.txt
User-agent: PriorityBot Disallow: /store Allow: /store/public Disallow: /store/public/sale # Test Allow vs Disallow with same length (Allow wins) User-agent: SameLengthBot Disallow: /page Allow: /page # Test multiple wildcards User-agent: MultiWildcardBot Disallow: /*.cgi* Disallow: /*?*id=* # Test literal $ in middle of pattern User-agent: DollarBot Disallow: /price$info
Registered: Sat Dec 20 11:21:39 UTC 2025 - Last Modified: Thu Nov 13 14:03:41 UTC 2025 - 910 bytes - Viewed (0) -
fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/RobotsTxt.java
* <li>Manages crawl delay settings per user agent</li> * <li>Stores sitemap URLs listed in robots.txt</li> * </ul> * * <p>The class uses case-insensitive pattern matching for user agents and supports * wildcard characters (*) in user agent strings. When multiple directives match a user agent, * the most specific (longest) match is used.</p> * */ public class RobotsTxt {
Registered: Sat Dec 20 11:21:39 UTC 2025 - Last Modified: Mon Nov 24 03:59:47 UTC 2025 - 18.5K bytes - Viewed (0) -
fess-crawler/src/test/resources/org/codelibs/fess/crawler/helper/robots_malformed.txt
NoValue: ::: : # Case 13: Numeric crawl-delay edge cases User-agent: NumericBot Crawl-delay: 0 Crawl-delay: 999999999 Crawl-delay: 1.23e10 # Case 14: Tab characters instead of spaces User-agent: TabBot Disallow: /tab1/ Allow: /tab2/ # Case 15: Unicode and special characters in user-agent User-agent: Bot™ Disallow: /trademark/ User-agent: Bot® Disallow: /registered/
Registered: Sat Dec 20 11:21:39 UTC 2025 - Last Modified: Fri Nov 14 12:52:01 UTC 2025 - 2.6K bytes - Viewed (0) -
fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/RobotsTxtHelperTest.java
RobotsTxt robotsTxt; final InputStream in = new java.io.ByteArrayInputStream(robotsTxtContent.getBytes()); try { robotsTxt = robotsTxtHelper.parse(in); } finally { CloseableUtil.closeQuietly(in); } // Directives before User-agent should be ignoredRegistered: Sat Dec 20 11:21:39 UTC 2025 - Last Modified: Mon Nov 24 03:59:47 UTC 2025 - 20.6K bytes - Viewed (0) -
fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/RobotsTxtHelper.java
* </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: Sat Dec 20 11:21:39 UTC 2025 - Last Modified: Fri Nov 14 12:52:01 UTC 2025 - 11.4K bytes - Viewed (0) -
fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/ApiExtractor.java
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: Sat Dec 20 11:21:39 UTC 2025 - Last Modified: Mon Nov 24 03:59:47 UTC 2025 - 12.2K bytes - Viewed (0) -
src/main/java/org/codelibs/fess/helper/PathMappingHelper.java
logger.debug("replace: {} -> {}", url, newUrl); } return newUrl; } /** * Checks if the user agent matches the path mapping. * * @param pathMapping the path mapping * @return true if the user agent matches */ protected boolean matchUserAgent(final PathMapping pathMapping) { if (!pathMapping.hasUAMathcer()) { return true;
Registered: Sat Dec 20 09:19:18 UTC 2025 - Last Modified: Fri Nov 28 16:29:12 UTC 2025 - 9.5K bytes - Viewed (0) -
src/main/java/org/codelibs/fess/Constants.java
// ============================================================ // User Agent Configuration // ============================================================ /** Prefix for Fess crawler user agent string. */ public static final String CRAWLING_USER_AGENT_PREFIX = "Mozilla/5.0 (compatible; Fess/"; /** Suffix for Fess crawler user agent string with bot information URL. */Registered: Sat Dec 20 09:19:18 UTC 2025 - Last Modified: Sat Dec 13 02:21:17 UTC 2025 - 35.2K bytes - Viewed (0) -
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: Sat Dec 20 11:21:39 UTC 2025 - Last Modified: Sun Nov 23 12:19:14 UTC 2025 - 53.7K bytes - Viewed (0) -
pom.xml
</plugin> <plugin> <groupId>org.jacoco</groupId> <artifactId>jacoco-maven-plugin</artifactId> <version>0.8.13</version> <executions> <execution> <goals> <goal>prepare-agent</goal> </goals> </execution> <execution> <id>report</id> <phase>prepare-package</phase> <goals> <goal>report</goal> </goals> </execution>
Registered: Sat Dec 20 08:55:33 UTC 2025 - Last Modified: Sat Dec 20 04:15:34 UTC 2025 - 4.9K bytes - Viewed (0)