Package net.yacy.kelondro.data.word

Examples of net.yacy.kelondro.data.word.WordReference

99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
            Log.logException(e);
        }
        ReferenceContainer<WordReference> index = search.joined();
       
        Iterator<WordReference> i = index.entries();
        WordReference entry;
        int c = 0;
        Date lm;
        String lms;
        while (i.hasNext() && c < count) {
            entry = i.next();
            lm = new Date(entry.lastModified());
            lms = GenericFormatter.ANSIC_FORMATTER.format(lm);
            prop.put("event_" + c + "_start", lms); // like "Wed May 01 1963 00:00:00 GMT-0600"
            prop.put("event_" + c + "_end", lms); // like "Sat Jun 01 1963 00:00:00 GMT-0600"
            prop.put("event_" + c + "_isDuration", 0); // 0 (only a point) or 1 (period of time)
            prop.putHTML("event_" + c + "_title", "test"); // short title of the event
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
        public void add(ReferenceContainer<WordReference> container) throws RowSpaceExceededException {
            // iterate through the entries in the container and check if the reference is in the repository
            Iterator<WordReference>  i = container.entries();
            List<byte[]> notFoundx = new ArrayList<byte[]>();
            while (i.hasNext()) {
                WordReference e = i.next();
                if (references.containsKey(e.urlhash())) continue;
                if (badReferences.has(e.urlhash())) {
                    notFoundx.add(e.urlhash());
                    continue;
                }
                URIMetadataRow r = segment.urlMetadata().load(e.urlhash());
                if (r == null) {
                    notFoundx.add(e.urlhash());
                    badReferences.put(e.urlhash());
                } else {
                    references.put(e.urlhash(), r);
                }
            }
            // now delete all references that were not found
            for (final byte[] b : notFoundx) container.removeReference(b);
            // finally add the remaining container to the cache
View Full Code Here
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
        final List<ReferenceContainer<WordReference>>[] partitions = new ArrayList[partitionCount];
        for (int i = 0; i < partitions.length; i++) partitions[i] = new ArrayList<ReferenceContainer<WordReference>>();

        // check all entries and split them to the partitions
        final ReferenceContainer<WordReference>[] partitionBuffer = new ReferenceContainer[partitionCount];
        WordReference re;
        for (final ReferenceContainer<WordReference> container: containers) {
            // init the new partitions
            for (int j = 0; j < partitionBuffer.length; j++) {
                partitionBuffer[j] = new ReferenceContainer<WordReference>(Segment.wordReferenceFactory, container.getTermHash(), container.size() / partitionCount);
            }

            // split the container
            final Iterator<WordReference> i = container.entries();
            while (i.hasNext()) {
                re = i.next();
                if (re == null) continue;
                partitionBuffer[this.seeds.scheme.verticalPosition(re.urlhash())].add(re);
            }

            // add the containers to the result vector
            for (int j = 0; j < partitionBuffer.length; j++) {
                partitions[j].add(partitionBuffer[j]);
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
            Log.logException(e);
        }
        ReferenceContainer<WordReference> index = search.joined();
       
        Iterator<WordReference> i = index.entries();
        WordReference entry;
        int c = 0;
        Date lm;
        String lms;
        while (i.hasNext() && c < count) {
            entry = i.next();
            lm = new Date(entry.lastModified());
            lms = GenericFormatter.ANSIC_FORMATTER.format(lm);
            prop.put("event_" + c + "_start", lms); // like "Wed May 01 1963 00:00:00 GMT-0600"
            prop.put("event_" + c + "_end", lms); // like "Sat Jun 01 1963 00:00:00 GMT-0600"
            prop.put("event_" + c + "_isDuration", 0); // 0 (only a point) or 1 (period of time)
            prop.putHTML("event_" + c + "_title", "test"); // short title of the event
View Full Code Here
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
         */
        private ReferenceContainer<WordReference> trimContainer(final ReferenceContainer<WordReference> container, final int max) throws RowSpaceExceededException {
            final ReferenceContainer<WordReference> c = new ReferenceContainer<WordReference>(Segment.wordReferenceFactory, container.getTermHash(), max);
            final int part = container.size() / max + 1;
            final Random r = new Random();
            WordReference w;
            final List<byte[]> selected = new ArrayList<byte[]>();
            final Iterator<WordReference>  i = container.entries();
            while ((i.hasNext()) && (c.size() < max)) {
                w = i.next();
                if (r.nextInt(part) == 0) {
                    c.add(w);
                    selected.add(w.urlhash());
                }
            }
            // remove the selected entries from container
            for (final byte[] b : selected) container.removeReference(b);
            // put container back
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
            final ReferenceContainer<WordReference> c = (remaining >= container.size()) ? container : trimContainer(container, remaining);
            // iterate through the entries in the container and check if the reference is in the repository
            final Iterator<WordReference>  i = c.entries();
            final List<byte[]> notFoundx = new ArrayList<byte[]>();
            while (i.hasNext()) {
                final WordReference e = i.next();
                if (this.references.containsKey(e.urlhash())) continue;
                if (this.badReferences.has(e.urlhash())) {
                    notFoundx.add(e.urlhash());
                    continue;
                }
                final URIMetadataRow r = Transmission.this.segment.urlMetadata().load(e.urlhash());
                if (r == null) {
                    notFoundx.add(e.urlhash());
                    this.badReferences.put(e.urlhash());
                } else {
                    this.references.put(e.urlhash(), r);
                }
            }
            // now delete all references that were not found
            for (final byte[] b : notFoundx) c.removeReference(b);
            // finally add the remaining container to the cache
View Full Code Here
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
        final List<ReferenceContainer<WordReference>>[] partitions = new ArrayList[partitionCount];
        for (int i = 0; i < partitions.length; i++) partitions[i] = new ArrayList<ReferenceContainer<WordReference>>();

        // check all entries and split them to the partitions
        final ReferenceContainer<WordReference>[] partitionBuffer = new ReferenceContainer[partitionCount];
        WordReference re;
        for (final ReferenceContainer<WordReference> container: containers) {
            // init the new partitions
            for (int j = 0; j < partitionBuffer.length; j++) {
                partitionBuffer[j] = new ReferenceContainer<WordReference>(Segment.wordReferenceFactory, container.getTermHash(), container.size() / partitionCount);
            }

            // split the container
            final Iterator<WordReference> i = container.entries();
            while (i.hasNext()) {
                re = i.next();
                if (re == null) continue;
                partitionBuffer[this.seeds.scheme.verticalPosition(re.urlhash())].add(re);
            }

            // add the containers to the result vector
            for (int j = 0; j < partitionBuffer.length; j++) {
                partitions[j].add(partitionBuffer[j]);
View Full Code Here
TOP

Related Classes of net.yacy.kelondro.data.word.WordReference

  • de.anomic.yacy.dht.Dispatcher
  • de.anomic.yacy.dht.Transmission$Chunk
  • net.yacy.peers.dht.Dispatcher
  • net.yacy.peers.dht.Transmission$Chunk
  • timeline
    • Copyright © 2018 www.massapicom. 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.