Package bixo.datum

Examples of bixo.datum.UrlStatus

56
57
58
59
60
61
62
63
64
65
66
    @Override
    public void operate(FlowProcess flowProcess, FunctionCall<NullContext> funcCall) {
        UrlDatum datum = new UrlDatum(funcCall.getArguments());
        Long lastFetched = (Long) datum.getPayloadValue(CrawlDbDatum.LAST_FETCHED_FIELD);
        Long lastUpdated = (Long) datum.getPayloadValue(CrawlDbDatum.LAST_UPDATED_FIELD);
        UrlStatus status = UrlStatus.valueOf((String) (datum.getPayloadValue(CrawlDbDatum.LAST_STATUS_FIELD)));
        Integer crawlDepth = (Integer) datum.getPayloadValue(CrawlDbDatum.CRAWL_DEPTH);

        CrawlDbDatum crawldbDatum = new CrawlDbDatum(datum.getUrl(), lastFetched, lastUpdated, status, crawlDepth);

        funcCall.getOutputCollector().add(crawldbDatum.getTuple());
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
            totalEntries += 1;
   
            String statusLine = entry.getString("line");
            String[] pieces = statusLine.split("\t");
            int pos = StatusDatum.FIELDS.getPos(StatusDatum.STATUS_FN);
            UrlStatus status = UrlStatus.valueOf(pieces[pos]);
            statusCounts[status.ordinal()] += 1;
        }
       
       
        for (int i = 0; i < statusCounts.length; i++) {
          if (statusCounts[i] != 0) {
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
        // [C | S | A | L] [C | S | A | L] [C | S | A | L] [C | S | A | L]

        CrawlDbDatum crawlDbDatum = null;
        StatusDatum statusDatum = null;
        AnalyzedDatum analyzedDatum = null;
        UrlStatus status = null;
        float pageScore = 0;
        float linkScore = 0;

        String url = null;
View Full Code Here
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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
            int numFetched = 0;
            int numPending = 0;
            while (iter.hasNext()) {
                CrawlDbDatum datum = new CrawlDbDatum(iter.next());
                UrlStatus status = datum.getLastStatus();
                int crawlDepth = datum.getCrawlDepth();
                if (datum.getLastFetched() != 0) {
                    numFetched += 1;

                    assertEquals(UrlStatus.FETCHED, status);
                    assertEquals(0, crawlDepth);
                } else {
                    numPending += 1;
                    assertEquals(UrlStatus.UNFETCHED, status);
                    assertEquals(1, crawlDepth);
                }
            }

            assertEquals(1, numFetched);
            assertEquals(10, numPending);

            // Do it one more time, to verify status gets propagated forward.
            curLoopDirPath = CrawlDirUtils.makeLoopDir(platform, baseDirPath, 2);

            flow = DemoCrawlWorkflow.createFlow(curLoopDirPath, crawlDbPath, defaultPolicy, userAgent, urlFilter, options);
            flow.complete();
            // Update crawldb path
            crawlDbPath = platform.makePath(curLoopDirPath, CrawlConfig.CRAWLDB_SUBDIR_NAME);

            crawldbTap = platform.makeTap(platform.makeBinaryScheme(CrawlDbDatum.FIELDS), crawlDbPath);
            iter = crawldbTap.openForRead(platform.makeFlowProcess());

            numFetched = 0;
            numPending = 0;
            int numDepth0 = 0;
            int numDepth1 = 0;
            int numDepth2 = 0;
            while (iter.hasNext()) {
                CrawlDbDatum datum = new CrawlDbDatum(iter.next());
                UrlStatus status = datum.getLastStatus();
                int depth = datum.getCrawlDepth();

                if (datum.getLastFetched() != 0) {
                    numFetched += 1;
                    assertEquals("URL has incorrect status: " + datum.getUrl(), UrlStatus.FETCHED, status);
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
    }

    @Override
    public void operate(FlowProcess process, FunctionCall<NullContext> funcCall) {
        StatusDatum datum = new StatusDatum(funcCall.getArguments());
        UrlStatus status = datum.getStatus();
        String url = datum.getUrl();
        long statusTime = datum.getStatusTime();
       
        long fetchTime = statusTime; // Not exactly true... since in some cases we
                    // may not have fetched the url. But because we are sharing this logic
                    // between the JDBCCrawlTool and the DemoCrawlTool, we use the value
                    // of the fetchTime while selecting the "latest" url. Newly added urls
                    // 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
84
85
86
87
88
89
90
91
92
93
94
        @Override
        // LHS represents unfetched tuples
        public boolean isLHS(TupleEntry tupleEntry) {
            CrawlDbDatum datum = new CrawlDbDatum(tupleEntry);
            UrlStatus status = datum.getLastStatus();
            if (status == UrlStatus.UNFETCHED               
                            || status == UrlStatus.SKIPPED_DEFERRED
                            || status == UrlStatus.SKIPPED_BY_SCORER
                            || status == UrlStatus.SKIPPED_BY_SCORE
                            || status == UrlStatus.SKIPPED_TIME_LIMIT
View Full Code Here
372
373
374
375
376
377
378
379
380
381
382
       
        // Skip all URLs that we've got left.
        if (!values.isEmpty()) {
            trace("Found unprocessed URLs");
           
            UrlStatus status = Thread.interrupted() ? UrlStatus.SKIPPED_INTERRUPTED : UrlStatus.SKIPPED_TIME_LIMIT;
           
            while (!values.isEmpty()) {
                FetchSetDatum datum = values.drain();
                List<ScoredUrlDatum> urls = datum.getUrls();
                trace("Skipping %d urls from %s (e.g. %s) ", urls.size(), datum.getGroupingRef(), urls.get(0).getUrl());
View Full Code Here
164
165
166
167
168
169
170
171
172
173
174
           
            // Note: Here we share the payload of the FetchedDatum with the
            // StatusDatum we're about to emit, but since we let go after we
            // emit, there shouldn't be an issue with this sharing.
            if (result instanceof String) {
                UrlStatus urlStatus = UrlStatus.valueOf((String)result);
                if (urlStatus == UrlStatus.FETCHED) {
                    status = new StatusDatum(fd.getUrl(), fd.getHeaders(), fd.getHostAddress(), fd.getPayload());
                } else {
                    status = new StatusDatum(fd.getUrl(), urlStatus, fd.getPayload());
                }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
            throw new RuntimeException("Invalid crawl delay in grouping key: " + key);
        }
    }
   
    public static UrlStatus makeUrlStatusFromKey(String key) {
        UrlStatus status;
       
        if (!isSpecialKey(key)) {
            status = UrlStatus.UNFETCHED;
        } else if (key.equals(GroupingKey.BLOCKED_GROUPING_KEY)) {
            status = UrlStatus.SKIPPED_BLOCKED;
View Full Code Here
TOP

Related Classes of bixo.datum.UrlStatus

  • bixo.examples.crawl.CreateCrawlDbDatumFromUrlFunction
  • bixo.examples.crawl.CreateUrlDatumFromStatusFunction
  • bixo.examples.crawl.DemoCrawlWorkflowLRTest
  • bixo.examples.crawl.DemoStatusTool
  • bixo.examples.webmining.DemoWebMiningWorkflow$SplitFetchedUnfetchedSSCrawlDatums
  • bixo.examples.webmining.UpdateCrawlDbBuffer
  • bixo.operations.FetchBuffer
  • bixo.pipes.FetchPipe$MakeStatusFunction
  • bixo.utils.GroupingKey
    • 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.