Package bixo.datum

Examples of bixo.datum.UrlDatum

68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
                    // have a fetchTime of 0, so in order to preserve say a SKIPPED status
                    // we set the fetch time here.

        _numCreated += 1;

        UrlDatum urlDatum = new UrlDatum(url);
        urlDatum.setPayloadValue(CrawlDbDatum.LAST_FETCHED_FIELD, fetchTime);
        urlDatum.setPayloadValue(CrawlDbDatum.LAST_UPDATED_FIELD, statusTime);
        urlDatum.setPayloadValue(CrawlDbDatum.LAST_STATUS_FIELD, status.name());
        // Don't change the crawl depth here - we do that only in the case of a
        // successful parse
        urlDatum.setPayloadValue(CrawlDbDatum.CRAWL_DEPTH, datum.getPayloadValue(CrawlDbDatum.CRAWL_DEPTH));

        funcCall.getOutputCollector().add(urlDatum.getTuple());
    }
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
       
        // Create a temp file with a fetched url
        BasePath workingDirPath = platform.makePath(WORKINGDIR);
        BasePath fetchedDatumsPath = platform.makePath(workingDirPath, "fetched");
        ArrayList<UrlDatum> fetchedDatums = new ArrayList<UrlDatum>();
        UrlDatum fetchedDatum1 = new UrlDatum("http://foo.com");
        fetchedDatum1.setPayloadValue(CrawlDbDatum.LAST_FETCHED_FIELD, 2L);
        fetchedDatums.add(fetchedDatum1);
        createDataFile(platform, fetchedDatumsPath, fetchedDatums);
       
        // And another with unfetched urls
        BasePath unfetchedDatumsPath = platform.makePath(workingDirPath, "unfetched");
        ArrayList<UrlDatum> unfetchedDatums = new ArrayList<UrlDatum>();
        UrlDatum unfetchedDatum1 = new UrlDatum("http://foo.com");
        unfetchedDatum1.setPayloadValue(CrawlDbDatum.LAST_FETCHED_FIELD, 0L);
        unfetchedDatums.add(unfetchedDatum1);
        UrlDatum unfetchedDatum2 = new UrlDatum("http://foo.com");
        unfetchedDatum2.setPayloadValue(CrawlDbDatum.LAST_FETCHED_FIELD, 0L);
        unfetchedDatums.add(unfetchedDatum2);
       
        createDataFile(platform, unfetchedDatumsPath, unfetchedDatums);

       
        // create a workflow
        Tap inputSource1 = platform.makeTap(platform.makeBinaryScheme(UrlDatum.FIELDS), fetchedDatumsPath);
        Pipe fetchedPipe = new Pipe("fetched");
        Tap inputSource2 = platform.makeTap(platform.makeBinaryScheme(UrlDatum.FIELDS), unfetchedDatumsPath);
        Pipe unfetchedPipe = new Pipe("unfetched");

        Map<String, Tap> sources = new HashMap<String, Tap>();
        sources.put(fetchedPipe.getName(), inputSource1);
        sources.put(unfetchedPipe.getName(), inputSource2);

        BasePath resultsPath = platform.makePath(workingDirPath, "results");
        Tap resultSink = platform.makeTap(platform.makeBinaryScheme(UrlDatum.FIELDS), resultsPath, SinkMode.REPLACE);

        Pipe resultsPipe = new GroupBy("results pipe", Pipe.pipes(fetchedPipe, unfetchedPipe),
                        new Fields(UrlDatum.URL_FN));
        resultsPipe = new Every(resultsPipe, new LatestUrlDatumBuffer(), Fields.RESULTS);


        FlowConnector flowConnector = platform.makeFlowConnector();
        Flow flow = flowConnector.connect(sources, resultSink, resultsPipe);
        flow.complete();
       
        // verify that the resulting pipe has the latest tuple
       
        Tap testSink = platform.makeTap(platform.makeBinaryScheme(UrlDatum.FIELDS), resultsPath);
        TupleEntryIterator reader = testSink.openForRead(platform.makeFlowProcess());
        int count = 0;
        long latest = 0;
        while (reader.hasNext()) {
            TupleEntry next = reader.next();
            UrlDatum datum = new UrlDatum(next);
            latest = (Long) datum.getPayloadValue(CrawlDbDatum.LAST_FETCHED_FIELD);
            count++;
        }
       
        assertEquals(1, count);
        assertEquals(2, latest);
View Full Code Here
697
698
699
700
701
702
703
704
705
        return platform.makePath(BASE_OUTPUT_PATH + testname + "/" + platformName + "/out");
    }


    private Tuple makeTuple(String domain, int pageNumber, Payload payload) {
        UrlDatum url = new UrlDatum("http://" + domain + "/page-" + pageNumber + ".html?size=10");
        url.setPayload(payload);
        return url.getTuple();
    }
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
72
73
        public void operate(FlowProcess process, FunctionCall<NullContext> funcCall) {
            String urlAsString = funcCall.getArguments().getString("line");
            try {
                URL url = new URL(urlAsString);

                UrlDatum urlDatum = new UrlDatum(url.toString());

                funcCall.getOutputCollector().add(BixoPlatform.clone(urlDatum.getTuple(), process));
            } catch (MalformedURLException e) {
                LOGGER.warn("Invalid URL: " + urlAsString);
                // throw new RuntimeException("Invalid URL: " + urlAsString, e);
            }
        }
View Full Code Here
135
136
137
138
139
140
141
142
143
144
145
146
147
        }
       
        @Override
        public void operate(FlowProcess flowProcess, FunctionCall<Limit.Context> funcCall) {
            CrawlDbDatum datum = new CrawlDbDatum(funcCall.getArguments());
            UrlDatum urlDatum = new UrlDatum(datum.getUrl());
            urlDatum.setPayloadValue(CustomFields.PAGE_SCORE_FN, datum.getPageScore());
            urlDatum.setPayloadValue(CustomFields.LINKS_SCORE_FN, datum.getLinksScore());
            urlDatum.setPayloadValue(CustomFields.STATUS_FN, datum.getLastStatus().toString());
            urlDatum.setPayloadValue(CustomFields.SKIP_BY_LIMIT_FN, funcCall.getContext().increment());
           
            funcCall.getOutputCollector().add(urlDatum.getTuple());
        }
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
50
    }

    @SuppressWarnings("rawtypes")
    @Override
    public void operate(FlowProcess process, FunctionCall<NullContext> funCall) {
        UrlDatum datum = new UrlDatum(funCall.getArguments());
       
        // Create copy, since we're setting a field, and the tuple is going to be unmodifiable.
        UrlDatum result = new UrlDatum(datum);
        result.setUrl(_normalizer.normalize(datum.getUrl()));
        funCall.getOutputCollector().add(BixoPlatform.clone(result.getTuple(), process));
    }
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
  }
 
  @SuppressWarnings("rawtypes")
    @Override
  public boolean isRemove(FlowProcess process, FilterCall<NullContext> filterCall) {
    UrlDatum datum = new UrlDatum(filterCall.getArguments());
    if (_filter.isRemove(datum)) {
        process.increment(ImportCounters.URLS_FILTERED, 1);
      _numFiltered += 1;
      return true;
    } else {
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
79
       
        try {
            // Validate the URL
            new URL(url);
           
            UrlDatum urlDatum = new UrlDatum(url);
            funcCall.getOutputCollector().add(BixoPlatform.clone(urlDatum.getTuple(), process));
           
            _numUrls += 1;
            process.increment(ImportCounters.URLS_ACCEPTED, 1);
        } catch (MalformedURLException e) {
            LOGGER.warn("Invalid URL in input data file: " + url);
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
    @Override
    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)
View Full Code Here
TOP

Related Classes of bixo.datum.UrlDatum

  • bixo.examples.crawl.CreateCrawlDbDatumFromUrlFunction
  • bixo.examples.crawl.CreateUrlDatumFromOutlinksFunction
  • bixo.examples.crawl.CreateUrlDatumFromStatusFunction
  • bixo.examples.crawl.DemoCrawlWorkflow$CreateUrlDatumFromCrawlDbFunction
  • bixo.examples.crawl.LatestUrlDatumBuffer
  • bixo.examples.crawl.LatestUrlDatumBufferTest
  • bixo.examples.crawl.RegexUrlFilterTest
  • bixo.examples.webmining.DemoWebMiningWorkflow$CreateUrlDatumFromCrawlDbDatum
  • bixo.operations.GroupFunction
  • bixo.operations.LoadUrlsFunction
    • 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.