canonical - Code Search

src/main/java/org/codelibs/core/net/URLUtil.java

 *
 * @author higa
 */
public abstract class URLUtil {

    /** プロトコルを正規化するためのマップ */
    protected static final Map<String, String> CANONICAL_PROTOCOLS = newHashMap();
    static {
        CANONICAL_PROTOCOLS.put("wsjar", "jar"); // WebSphereがJarファイルのために使用する固有のプロトコル
        CANONICAL_PROTOCOLS.put("vfsfile", "file"); // JBossAS5がファイルシステムのために使用する固有のプロトコル
    }

    /**
     * URLをオープンして{@link InputStream}を返します。
     *

Java

- Registered: Fri May 03 20:58:11 GMT 2024

- Last Modified: Thu Mar 07 01:59:08 GMT 2024

- 7.3K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/es/config/exentity/CrawlingConfig.java

            public static final String CLEANUP_URL_FILTERS = "cleanup.urlFilters";
            public static final String JCIFS_PREFIX = "jcifs.";
            public static final String HTML_CANONICAL_XPATH = "html.canonical.xpath";
            public static final String HTML_PRUNED_TAGS = "html.pruned.tags";
            public static final String PIPELINE = "pipeline";

Java

- Registered: Mon Apr 29 08:04:11 GMT 2024

- Last Modified: Thu Feb 22 01:37:57 GMT 2024

- 5.5K bytes

- Viewed (0)

github.com/codelibs/fess

src/test/java/org/codelibs/fess/crawler/transformer/FessXpathTransformerTest.java

        data = "<html><head><link rel=\"canonical\" href=\"http://example.com/\"></head><body>aaa</body></html>";
        document = getDocument(data);
        value = transformer.getCanonicalUrl(responseData, document);
        assertEquals("http://example.com/", value);

        data = "<html><head><link rel=\"canonical\" href=\"http://example1.com/\"><link rel=\"canonical\" href=\"http://example2.com/\"></head><body>aaa</body></html>";

Java

- Registered: Mon Apr 29 08:04:11 GMT 2024

- Last Modified: Thu Feb 22 01:37:57 GMT 2024

- 38.6K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/crawler/transformer/FessXpathTransformer.java

                logger.debug("Invalid Canonical Url(https->http): {} -> {}", url, canonicalUrl);
            }
            return false;
        }
        return true;
    }

    protected void putAdditionalData(final Map<String, Object> dataMap, final ResponseData responseData, final Document document) {
        // canonical
        final String canonicalUrl = getCanonicalUrl(responseData, document);

Java

- Registered: Mon Apr 29 08:04:11 GMT 2024

- Last Modified: Thu Feb 22 01:37:57 GMT 2024

- 41.9K bytes

- Viewed (0)

github.com/codelibs/jcifs

src/main/java/jcifs/smb1/smb1/SmbFile.java

        return url;
    }

/**
 * Computes a hashCode for this file based on the URL string and IP
 * address if the server. The hashing function uses the hashcode of the
 * server address, the canonical representation of the URL, and does not
 * compare authentication information. In essance, two
 * <code>SmbFile</code> objects that refer to
 * the same file should generate the same hashcode provided it is possible

Java

- Registered: Sun May 05 00:10:10 GMT 2024

- Last Modified: Mon Mar 13 12:00:57 GMT 2023

- 107.9K bytes

- Viewed (2)

github.com/codelibs/jcifs

src/main/java/jcifs/smb/SmbResourceLocatorImpl.java

import jcifs.SmbResourceLocator;
import jcifs.internal.util.StringUtil;
import jcifs.netbios.NbtAddress;
import jcifs.netbios.UniAddress;


/**
 * 
 * 
 * This mainly tracks two locations:
 * - canonical URL path: path component of the URL: this is used to reconstruct URLs to resources and is not adjusted by
 * DFS referrals. (E.g. a resource with a DFS root's parent will still point to the DFS root not the share it's actually

Java

- Registered: Sun May 05 00:10:10 GMT 2024

- Last Modified: Sat Jul 20 08:24:53 GMT 2019

- 23.9K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/resources/fess_config.properties

# html
crawler.document.html.content.xpath=//BODY
crawler.document.html.lang.xpath=//HTML/@lang
crawler.document.html.digest.xpath=//META[@name='description']/@content
crawler.document.html.canonical.xpath=//LINK[@rel='canonical'][1]/@href
crawler.document.html.pruned.tags=noscript,script,style,header,footer,aside,nav,a[rel=nofollow]
crawler.document.html.max.digest.length=120
crawler.document.html.default.lang=

Properties

- Registered: Mon Apr 29 08:04:11 GMT 2024

- Last Modified: Thu Apr 11 02:34:53 GMT 2024

- 30.6K bytes

- Viewed (1)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/mylasta/direction/FessConfig.java

    String CRAWLER_DOCUMENT_HTML_DIGEST_XPATH = "crawler.document.html.digest.xpath";

    /** The key of the configuration. e.g. //LINK[@rel='canonical'][1]/@href */
    String CRAWLER_DOCUMENT_HTML_CANONICAL_XPATH = "crawler.document.html.canonical.xpath";

    /** The key of the configuration. e.g. noscript,script,style,header,footer,aside,nav,a[rel=nofollow] */

Java

- Registered: Mon Apr 29 08:04:11 GMT 2024

- Last Modified: Thu Apr 11 02:34:53 GMT 2024

- 459.2K bytes

- Viewed (4)

github.com/codelibs/jcifs

src/main/java/jcifs/smb/SmbFile.java

    }


    /**
     * Computes a hashCode for this file based on the URL string and IP
     * address if the server. The hashing function uses the hashcode of the
     * server address, the canonical representation of the URL, and does not
     * compare authentication information. In essence, two
     * <code>SmbFile</code> objects that refer to

Java

- Registered: Sun May 05 00:10:10 GMT 2024

- Last Modified: Mon Mar 13 12:00:57 GMT 2023

- 81.6K bytes

- Viewed (0)

Search Options