Package net.yacy.search.index

Examples of net.yacy.search.index.Segment.urlMetadata()

119
120
121
122
123
124
125
126
127
128
129
        // get the url hash from which the content should be loaded
        String urlHash = post.get("urlHash", "");
        URIMetadataRow urlEntry = null;
        // get the urlEntry that belongs to the url hash
        if (urlHash.length() > 0 && (urlEntry = indexSegment.urlMetadata().load(ASCII.getBytes(urlHash))) != null) {
            // get the url that belongs to the entry
            final URIMetadataRow.Components metadata = urlEntry.metadata();
            if ((metadata == null) || (metadata.url() == null)) {
                prop.put("error", "3");
                prop.put("viewMode", VIEW_MODE_NO_TEXT);
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
        }
       
        if (post!=null) {
            if (post.get("action").equals("ustart")) {
                if (urldbCleanerThread==null || !urldbCleanerThread.isAlive()) {
                    urldbCleanerThread = indexSegment.urlMetadata().getBlacklistCleaner(Switchboard.urlBlacklist, sb.crawlStacker);
                    urldbCleanerThread.start();
                }
                else {
                    urldbCleanerThread.endPause();
                }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
            prop.put("LOCATION","");
            return prop;
        }
        if (urldbCleanerThread!=null) {
            prop.put("urldb", "1");
            prop.putNum("urldb_percentUrls", ((double)urldbCleanerThread.totalSearchedUrls/indexSegment.urlMetadata().size())*100);
            prop.putNum("urldb_blacklisted", urldbCleanerThread.blacklistedUrls);
            prop.putNum("urldb_total", urldbCleanerThread.totalSearchedUrls);
            prop.putHTML("urldb_lastBlacklistedUrl", urldbCleanerThread.lastBlacklistedUrl);
            prop.put("urldb_lastBlacklistedHash", urldbCleanerThread.lastBlacklistedHash);
            prop.putHTML("urldb_lastUrl", urldbCleanerThread.lastUrl);
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
        //int showRejectedCount = 10;

        Seed initiator;

        // index size
        prop.putNum("urlpublictextSize", segment.urlMetadata().size());
        prop.putNum("rwipublictextSize", segment.termIndex().sizesMax());

        // loader queue
        prop.putNum("loaderSize", sb.crawlQueues.workerSize());
        prop.putNum("loaderMax", sb.getConfigLong(SwitchboardConstants.CRAWLER_THREADS_ACTIVE_MAX, 10));
View Full Code Here
303
304
305
306
307
308
309
310
311
312
313
                        // stack request
                        // first delete old entry, if exists
                        final DigestURI url = new DigestURI(crawlingStart);
                        final byte[] urlhash = url.hash();
                        indexSegment.urlMetadata().remove(urlhash);
                        sb.crawlQueues.noticeURL.removeByURLHash(urlhash);
                        sb.crawlQueues.errorURL.remove(urlhash);

                        // get a scraper to get the title
                        final ContentScraper scraper = sb.loader.parseResource(url, CacheStrategy.IFFRESH);
View Full Code Here
571
572
573
574
575
576
577
578
579
580
581
                            final Map.Entry<MultiProtocolURI, Properties> e = linkiterator.next();
                            if (e.getKey() == null) continue;
                            nexturl = new DigestURI(e.getKey());
                            // remove the url from the database to be prepared to crawl them again
                            final byte[] urlhash = nexturl.hash();
                            indexSegment.urlMetadata().remove(urlhash);
                            sb.crawlQueues.noticeURL.removeByURLHash(urlhash);
                            sb.crawlQueues.errorURL.remove(urlhash);
                            sb.crawlStacker.enqueueEntry(new Request(
                                    sb.peers.mySeed().hash.getBytes(),
                                    nexturl,
View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
            prop.put("lurlexport", 0);
            prop.put("reload", 0);
        }

        if (post.containsKey("urlhashdelete")) {
            final URIMetadataRow entry = segment.urlMetadata().load(ASCII.getBytes(urlhash));
            if (entry == null) {
                prop.putHTML("result", "No Entry for URL hash " + urlhash + "; nothing deleted.");
            } else {
                urlstring = entry.metadata().url().toNormalform(false, true);
                prop.put("urlstring", "");
View Full Code Here
186
187
188
189
190
191
192
193
194
195
196
        if (post.containsKey("urlstringsearch")) {
            try {
                final DigestURI url = new DigestURI(urlstring);
                urlhash = ASCII.String(url.hash());
                prop.put("urlhash", urlhash);
                final URIMetadataRow entry = segment.urlMetadata().load(ASCII.getBytes(urlhash));
                if (entry == null) {
                    prop.putHTML("result", "No Entry for URL " + url.toNormalform(true, true));
                    prop.putHTML("urlstring", urlstring);
                    prop.put("urlhash", "");
                } else {
View Full Code Here
204
205
206
207
208
209
210
211
212
213
214
            prop.put("lurlexport", 0);
            prop.put("reload", 0);
        }

        if (post.containsKey("urlhashsearch")) {
            final URIMetadataRow entry = segment.urlMetadata().load(ASCII.getBytes(urlhash));
            if (entry == null) {
                prop.putHTML("result", "No Entry for URL hash " + urlhash);
            } else {
                prop.putHTML("urlstring", entry.metadata().url().toNormalform(false, true));
                prop.putAll(genUrlProfile(segment, entry, urlhash));
View Full Code Here
219
220
221
222
223
224
225
226
227
228
229
        }

        // generate list
        if (post.containsKey("urlhashsimilar")) {
            try {
                final Iterator<URIMetadataRow> entryIt = new RotateIterator<URIMetadataRow>(segment.urlMetadata().entries(true, urlhash), ASCII.String(Base64Order.zero((urlhash == null ? 0 : urlhash.length()))), segment.termIndex().sizesMax());
                final StringBuilder result = new StringBuilder("Sequential List of URL-Hashes:<br />");
                URIMetadataRow entry;
                i = 0;
                int rows = 0, cols = 0;
                prop.put("urlhashsimilar", "1");
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.