Package net.yacy.search.index

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


        }

        // 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


            final Segment wordIndex = new Segment(
                    log,
                    new File(new File(indexPrimaryRoot, "freeworld"), "TEXT"),
                    10000,
                    (long) Integer.MAX_VALUE, false, false);
            final Iterator<ReferenceContainer<WordReference>> indexContainerIterator = wordIndex.termIndex().referenceContainerIterator("AAAAAAAAAAAA".getBytes(), false, false);

            long urlCounter = 0, wordCounter = 0;
            long wordChunkStart = System.currentTimeMillis(), wordChunkEnd = 0;
            String wordChunkStartHash = "AAAAAAAAAAAA", wordChunkEndHash;
View Full Code Here

                WordIndex = new Segment(
                        log,
                        new File(new File(indexPrimaryRoot, "freeworld"), "TEXT"),
                        10000,
                        (long) Integer.MAX_VALUE, false, false);
                indexContainerIterator = WordIndex.termIndex().referenceContainerIterator(wordChunkStartHash.getBytes(), false, false);
            }
            int counter = 0;
            ReferenceContainer<WordReference> container = null;
            if (format.equals("zip")) {
                log.logInfo("Writing Hashlist to ZIP-file: " + targetName + ".zip");
View Full Code Here

        }
        final Segment indexSegment = this.indexSegments.segment(segment);
        if (indexSegment.urlMetadata().size() < 10) {
            return "no DHT distribution: loadedURL.size() = " + indexSegment.urlMetadata().size();
        }
        if (indexSegment.termIndex().sizesMax() < 100) {
            return "no DHT distribution: not enough words - wordIndex.size() = " + indexSegment.termIndex().sizesMax();
        }
        if ((getConfig(SwitchboardConstants.INDEX_DIST_ALLOW_WHILE_CRAWLING, "false").equalsIgnoreCase("false")) && (this.crawlQueues.noticeURL.notEmptyLocal())) {
            return "no DHT distribution: crawl in progress: noticeURL.stackSize() = " + this.crawlQueues.noticeURL.size() + ", sbQueue.size() = " + getIndexingProcessorsQueueSize();
        }
View Full Code Here

        final Segment indexSegment = this.indexSegments.segment(segment);
        if (indexSegment.urlMetadata().size() < 10) {
            return "no DHT distribution: loadedURL.size() = " + indexSegment.urlMetadata().size();
        }
        if (indexSegment.termIndex().sizesMax() < 100) {
            return "no DHT distribution: not enough words - wordIndex.size() = " + indexSegment.termIndex().sizesMax();
        }
        if ((getConfig(SwitchboardConstants.INDEX_DIST_ALLOW_WHILE_CRAWLING, "false").equalsIgnoreCase("false")) && (this.crawlQueues.noticeURL.notEmptyLocal())) {
            return "no DHT distribution: crawl in progress: noticeURL.stackSize() = " + this.crawlQueues.noticeURL.size() + ", sbQueue.size() = " + getIndexingProcessorsQueueSize();
        }
        if ((getConfig(SwitchboardConstants.INDEX_DIST_ALLOW_WHILE_INDEXING, "false").equalsIgnoreCase("false")) && (getIndexingProcessorsQueueSize() > 1)) {
View Full Code Here

            // delete word
            if (post.containsKey("keyhashdeleteall")) try {
                if (delurl || delurlref) {
                    // generate urlx: an array of url hashes to be deleted
                    ReferenceContainer<WordReference> index = null;
                    index = segment.termIndex().get(keyhash, null);
                    final Iterator<WordReference> en = index.entries();
                    urlb = new HandleSet(URIMetadataRow.rowdef.primaryKeyLength, URIMetadataRow.rowdef.objectOrder, index.size());
                    while (en.hasNext()) try { urlb.put(en.next().urlhash()); } catch (final RowSpaceExceededException e) { Log.logException(e); }
                    index = null;
                }
View Full Code Here

                }
                if (delurlref) {
                    segment.removeAllUrlReferences(urlb, sb.loader, CacheStrategy.IFEXIST);
                }
                // delete the word first because that is much faster than the deletion of the urls from the url database
                segment.termIndex().delete(keyhash);
                // now delete all urls if demanded
                if (delurl || delurlref) {
                    for (final byte[] b: urlb) sb.urlRemove(segment, b);
                }
                post.remove("keyhashdeleteall");
View Full Code Here

                if (delurl || delurlref) {
                    for (final byte[] b: urlb) sb.urlRemove(segment, b);
                }
                final HandleSet urlHashes = new HandleSet(URIMetadataRow.rowdef.primaryKeyLength, URIMetadataRow.rowdef.objectOrder, 0);
                for (final byte[] b: urlb) try { urlHashes.put(b); } catch (final RowSpaceExceededException e) { Log.logException(e); }
                segment.termIndex().remove(keyhash, urlHashes);
                // this shall lead to a presentation of the list; so handle that the remaining program
                // thinks that it was called for a list presentation
                post.remove("keyhashdelete");
                post.put("urllist", "generated");
            } catch (final IOException e) {
View Full Code Here

                }

                // prepare index
                ReferenceContainer<WordReference> index;
                final long starttime = System.currentTimeMillis();
                index = segment.termIndex().get(keyhash, null);
                // built urlCache
                final Iterator<WordReference> urlIter = index.entries();
                final TreeMap<byte[], URIMetadataRow> knownURLs = new TreeMap<byte[], URIMetadataRow>(Base64Order.enhancedCoder);
                final HandleSet unknownURLEntries = new HandleSet(WordReferenceRow.urlEntryRow.primaryKeyLength, WordReferenceRow.urlEntryRow.objectOrder, index.size());
                Reference iEntry;
View Full Code Here

                Log.logException(e);
            }

            // generate list
            if (post.containsKey("keyhashsimilar")) try {
                final Iterator<ReferenceContainer<WordReference>> containerIt = segment.termIndex().referenceContainer(keyhash, true, 256, false).iterator();
                    ReferenceContainer<WordReference> container;
                    i = 0;
                    int rows = 0, cols = 0;
                    prop.put("keyhashsimilar", "1");
                    while (containerIt.hasNext() && i < 256) {
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.