Package bixo.datum

Examples of bixo.datum.GroupedUrlDatum

57
58
59
60
61
62
63
64
        }
    }
   
    private List<TupleEntry> getGroupedurlDatumList(String url) {
        List<TupleEntry> iterValues = new ArrayList<TupleEntry>();
        iterValues.add(new GroupedUrlDatum(url, url).getTupleEntry());
        return iterValues;
    }
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
58
    public void operate(FlowProcess process, FunctionCall<NullContext> funCall) {
        String key;
        try {
            UrlDatum datum = new UrlDatum(funCall.getArguments());
            key = _generator.getGroupingKey(datum);
            GroupedUrlDatum result = new GroupedUrlDatum(datum, key);
            funCall.getOutputCollector().add(BixoPlatform.clone(result.getTuple(), process));
        } catch (Exception e) {
            // TODO KKr - don't lose the tuple (skipping support)
            LOGGER.error("Unexpected exception while grouping URL (probably badly formed)", e);
        }
    }
View Full Code Here
145
146
147
148
149
150
151
152
153
154
155
        LOGGER.info("Processing tuple group: " + group);

        DiskQueue<GroupedUrlDatum> urls = new DiskQueue<GroupedUrlDatum>(MAX_URLS_IN_MEMORY);
        Iterator<TupleEntry> values = bufferCall.getArgumentsIterator();
        while (values.hasNext()) {
            urls.add(new GroupedUrlDatum(new TupleEntry(values.next())));
        }
       
        try {
            Runnable doRobots = new ProcessRobotsTask(protocolAndDomain, _scorer, urls, _fetcher, _parser, bufferCall.getOutputCollector(), _flowProcess);
            _executor.execute(doRobots);
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
87
88
     * @param urls Queue of URLs to empty out
     * @param groupingKey grouping key to use for all entries.
     * @param collector tuple output collector
     */
    public static void emptyQueue(Queue<GroupedUrlDatum> urls, String groupingKey, TupleEntryCollector collector, FlowProcess process) {
        GroupedUrlDatum datum;
        while ((datum = urls.poll()) != null) {
            ScoredUrlDatum scoreUrl = new ScoredUrlDatum(datum.getUrl(), groupingKey, UrlStatus.UNFETCHED, 1.0);
            scoreUrl.setPayload(datum.getPayload());
            // TODO KKr - move synchronization up, to avoid lots of contention with other threads?
            synchronized (collector) {
                collector.add(BixoPlatform.clone(scoreUrl.getTuple(), process));
            }
        }
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
                    validKey = GroupingKey.makeGroupingKey(domainInfo.getHostAddress(), robotRules.getCrawlDelay());
                    _flowProcess.increment(FetchCounters.DOMAINS_FINISHED, 1);
                }

                // Use the same key for every URL from this domain
                GroupedUrlDatum datum;
                while ((datum = _urls.poll()) != null) {
                    ScoredUrlDatum scoreUrl;
                    FetchCounters counter;
                    String url = datum.getUrl();

                    if (isDeferred) {
                        counter = FetchCounters.URLS_DEFERRED;
                        scoreUrl = new ScoredUrlDatum(url, GroupingKey.DEFERRED_GROUPING_KEY, UrlStatus.SKIPPED_DEFERRED, 0.0);
                    } else if (!robotRules.isAllowed(url)) {
                        counter = FetchCounters.URLS_BLOCKED;
                        scoreUrl = new ScoredUrlDatum(url, GroupingKey.BLOCKED_GROUPING_KEY, UrlStatus.SKIPPED_BLOCKED, 0.0);
                    } else {
                        double score = _scorer.generateScore(domain, pld, datum);
                        if (score == BaseScoreGenerator.SKIP_SCORE) {
                            counter = FetchCounters.URLS_SKIPPED;
                            scoreUrl = new ScoredUrlDatum(url, GroupingKey.SKIPPED_GROUPING_KEY, UrlStatus.UNFETCHED, score);
                        } else {
                            counter = FetchCounters.URLS_ACCEPTED;
                            scoreUrl = new ScoredUrlDatum(url, validKey, UrlStatus.UNFETCHED, score);
                        }
                    }
                   
                    scoreUrl.setPayload(datum.getPayload());
                    _flowProcess.increment(counter, 1);

                    // collectors aren't thread safe
                    synchronized (_collector) {
                        _collector.add(BixoPlatform.clone(scoreUrl.getTuple(), _flowProcess));
View Full Code Here
TOP

Related Classes of bixo.datum.GroupedUrlDatum

  • bixo.operations.FilterAndScoreByUrlAndRobots
  • bixo.operations.FilterAndScoreByUrlAndRobotsTest
  • bixo.operations.GroupFunction
  • bixo.operations.ProcessRobotsTask
  • cascading.tuple.Fields
    • 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.