Package net.yacy.kelondro.data.meta

Examples of net.yacy.kelondro.data.meta.URIMetadataRow.metadata()


        this.statsDump = new ArrayList<HostStat>();
        final TreeSet<String> set = new TreeSet<String>();
        for (final URLHashCounter hs: domainSamples.values()) {
            if (hs == null) continue;
            urlref = this.load(hs.urlhashb);
            if (urlref == null || urlref.metadata() == null || urlref.metadata().url() == null || urlref.metadata().url().getHost() == null) continue;
            set.add(urlref.metadata().url().getHost());
            count--;
            if (count == 0) break;
        }
        return set;
View Full Code Here


        final TreeSet<String> set = new TreeSet<String>();
        for (final URLHashCounter hs: domainSamples.values()) {
            if (hs == null) continue;
            urlref = this.load(hs.urlhashb);
            if (urlref == null || urlref.metadata() == null || urlref.metadata().url() == null || urlref.metadata().url().getHost() == null) continue;
            set.add(urlref.metadata().url().getHost());
            count--;
            if (count == 0) break;
        }
        return set;
    }
View Full Code Here

        }
        URIMetadataRow.Components comps;
        DigestURI url;
        for (final Map.Entry<String, URLHashCounter> e: domainSamples.entrySet()) {
            urlref = this.load(e.getValue().urlhashb);
            comps = urlref.metadata();
            url = comps.url();
            hostMap.put(e.getKey(), new HostStat(url.getHost(), url.getPort(), e.getKey(), hosthashScore.get(e.getKey())));
        }
        return hostMap;
    }
View Full Code Here

        DigestURI url;
        while (j.hasNext()) {
            urlhash = j.next();
            if (urlhash == null) continue;
            urlref = this.load(ASCII.getBytes(urlhash));
            if (urlref == null || urlref.metadata() == null || urlref.metadata().url() == null || urlref.metadata().url().getHost() == null) continue;
            if (this.statsDump == null) return new ArrayList<HostStat>().iterator(); // some other operation has destroyed the object
            comps = urlref.metadata();
            url = comps.url();
            this.statsDump.add(new HostStat(url.getHost(), url.getPort(), urlhash.substring(6), domainScore.get(urlhash)));
            count--;
View Full Code Here

        DigestURI url;
        while (j.hasNext()) {
            urlhash = j.next();
            if (urlhash == null) continue;
            urlref = this.load(ASCII.getBytes(urlhash));
            if (urlref == null || urlref.metadata() == null || urlref.metadata().url() == null || urlref.metadata().url().getHost() == null) continue;
            if (this.statsDump == null) return new ArrayList<HostStat>().iterator(); // some other operation has destroyed the object
            comps = urlref.metadata();
            url = comps.url();
            this.statsDump.add(new HostStat(url.getHost(), url.getPort(), urlhash.substring(6), domainScore.get(urlhash)));
            count--;
View Full Code Here

        DigestURI url;
        while (j.hasNext()) {
            urlhash = j.next();
            if (urlhash == null) continue;
            urlref = this.load(ASCII.getBytes(urlhash));
            if (urlref == null || urlref.metadata() == null || urlref.metadata().url() == null || urlref.metadata().url().getHost() == null) continue;
            if (this.statsDump == null) return new ArrayList<HostStat>().iterator(); // some other operation has destroyed the object
            comps = urlref.metadata();
            url = comps.url();
            this.statsDump.add(new HostStat(url.getHost(), url.getPort(), urlhash.substring(6), domainScore.get(urlhash)));
            count--;
View Full Code Here

            urlhash = j.next();
            if (urlhash == null) continue;
            urlref = this.load(ASCII.getBytes(urlhash));
            if (urlref == null || urlref.metadata() == null || urlref.metadata().url() == null || urlref.metadata().url().getHost() == null) continue;
            if (this.statsDump == null) return new ArrayList<HostStat>().iterator(); // some other operation has destroyed the object
            comps = urlref.metadata();
            url = comps.url();
            this.statsDump.add(new HostStat(url.getHost(), url.getPort(), urlhash.substring(6), domainScore.get(urlhash)));
            count--;
            if (count == 0) break;
        }
View Full Code Here

                    if (entry == null) {
                        if (Log.isFine("URLDBCLEANER")) Log.logFine("URLDBCLEANER", "entry == null");
                    } else if (entry.hash() == null) {
                        if (Log.isFine("URLDBCLEANER")) Log.logFine("URLDBCLEANER", ++this.blacklistedUrls + " blacklisted (" + ((double) this.blacklistedUrls / this.totalSearchedUrls) * 100 + "%): " + "hash == null");
                    } else {
                        final URIMetadataRow.Components metadata = entry.metadata();
                        this.totalSearchedUrls++;
                        if (metadata == null) {
                            if (Log.isFine("URLDBCLEANER")) Log.logFine("URLDBCLEANER", "corrupted entry for hash = " + ASCII.String(entry.hash()));
                            remove(entry.hash());
                            continue;
View Full Code Here

                    URIMetadataRow.Components metadata;
                    String url;
                    while (i.hasNext()) {
                        entry = i.next();
                        if (this.set != null && !this.set.has(entry.hash())) continue;
                        metadata = entry.metadata();
                        url = metadata.url().toNormalform(true, false);
                        if (!url.matches(this.filter)) continue;
                        if (this.format == 0) {
                            pw.println(url);
                        }
View Full Code Here

        // search is running; retrieve results
        URIMetadataRow row;
        final ArrayList<DigestURI> files = new ArrayList<DigestURI>();
        Components metadata;
        while ((row = rankedCache.takeURL(false, 1000)) != null) {
            metadata = row.metadata();
            if (metadata == null) continue;
            files.add(metadata.url());
            count--;
            if (count == 0) break;
        }
View Full Code Here

TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.