Package com.flaptor.util

Examples of com.flaptor.util.Config

46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
    private final float categoryThreshold; // threshold to add category to document
   
    public BayesianClassifierModule (String moduleName, Config globalConfig) {  
        super(moduleName, globalConfig);
        textLengthLimit = globalConfig.getInt("page.text.max.length");
        Config mdlConfig = getModuleConfig();
        String categoryList = mdlConfig.getString("categories");       
        if ((categoryList != null) && !"".equals(categoryList.trim())) {
            categories = categoryList.split(",");
            double unknownTermsProbability = mdlConfig.getFloat("unknown.terms.probability");
            categoryThreshold   = mdlConfig.getFloat("category.score.threshold");           
            multiClassifier = new MultiClassifier(categories, unknownTermsProbability);
        } else { // categories is null or ""
            // It makes no sense to have a BayesianClassifierModule that
            // has no categories. Someone misplaced this module in the modules
            // manager, or forgot to set categories. Either way, fail.
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
            xmlRpcServer = new XmlrpcServer(port);
            xmlRpcServer.addHandler(XMLRPC_CONTEXT, new VectorResults(baseSearcher));
            xmlRpcServer.start();
        }
        if (openSearch || web || xml) {
            Config config = Config.getConfig("searcher.properties");
            int httpServerPort = PortUtil.getPort("searcher.http");
            httpServer = new WebServer(httpServerPort);

            if (openSearch) {
                String context = config.getString("opensearch.context");
                logger.info("MultipleRpcSearcher constructor: starting OpenSearch searcher on port " + httpServerPort + " context "+context);
                httpServer.addHandler(context, new OpenSearchHandler(baseSearcher));
            }
            if (xml) {
                String context = config.getString("xmlsearch.context");
                logger.info("MultipleRpcSearcher constructor: starting xml searcher on port " + httpServerPort  + " context "+context);
                httpServer.addHandler(context, new XmlSearchHandler(baseSearcher));
            }
            if (web) {
                String context = config.getString("websearch.context");
                logger.info("MultipleRpcSearcher constructor: starting web searcher on port " + httpServerPort  + " context "+context);
                WebSearchUtil.setSearcher(baseSearcher);
                String webappPath = this.getClass().getClassLoader().getResource("web-searcher").getPath();
                httpServer.addWebAppHandler(context, webappPath);
            }
            boolean redirect = config.getBoolean("websearch.redirect");
            if (redirect) {
                String from = config.getString("websearch.redirect.from");
                String to = config.getString("websearch.redirect.to");
                httpServer.addHandler("/", new RedirectHandler(from,to));
            }
            try {httpServer.start();} catch (Exception e) {throw new RuntimeException(e);}
        }
    }
View Full Code Here
128
129
130
131
132
133
134
135
136
            PropertyConfigurator.configureAndWatch(log4jConfigPath);
        } else {
            logger.warn("log4j.properties not found in classpath! Reload disabled.");
        }

        Config conf = Config.getConfig("searcher.properties");
        ISearcher baseSearcher = new CompositeSearcher();
        new MultipleRpcSearcher(baseSearcher,conf.getBoolean("rmiInterface"), conf.getBoolean("xmlRpcInterface"), conf.getBoolean("openSearchInterface"), conf.getBoolean("webInterface"), conf.getBoolean("xmlInterface"));
    }
View Full Code Here
125
126
127
128
129
130
131
132
133
            PropertyConfigurator.configureAndWatch(log4jConfigPath);
        } else {
            logger.warn("log4j.properties not found in classpath! Reload disabled.");
        }

        Config conf = Config.getConfig("indexer.properties");
        IIndexer indexer = conf.getBoolean("isMultiIndexer") ? new MultiIndexer() : new Indexer();
        new MultipleRpcIndexer(indexer,conf.getBoolean("rmiInterface"), conf.getBoolean("xmlInterface"));
    }
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
    /**
     * Initialize the fetcher.
     */
    public Nutch9Fetcher() {
        Config config = Config.getConfig("nutchfetcher.properties");
        segmentsDir = config.getString("fetchlist.dir");
        keepUrl = config.getBoolean("keep.original.url.on.redirect");
        fetcher = new Fetcher();
        Configuration conf = new Configuration();
        // conf.addDefaultResource("crawl-tool.xml");
        conf.addDefaultResource("nutch-default.xml");
        conf.addDefaultResource("nutch-site.xml");
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
    public MultiSearcher() {
      this(new ExponentialFallbackPolicy());
    }

    public MultiSearcher(IRetryPolicy policy) {
        Config config = Config.getConfig("multiSearcher.properties");
        String[] hosts = config.getStringArray("multiSearcher.hosts");
        int workerThreads = config.getInt("multiSearcher.workerThreads");
        logger.info("init: number of worker threads set to " + workerThreads + " (from config file).");
        int maxThreadsPerSearcher = (workerThreads * 2 / hosts.length) + 1 ;
        logger.info("init: setting maxThreadsPerSearcher to " + maxThreadsPerSearcher);

        for (int i = 0; i < hosts.length; i++) {
            Pair<String, Integer> host = PortUtil.parseHost(hosts[i]);
            searchers.add(new RmiSearcherStub(host.last(), host.first(), policy, maxThreadsPerSearcher));
            searcherIPs.add(host.first());
        }
        timeout = config.getLong("multiSearcher.timeout");
        logger.info("init: timeout set to " + timeout + "ms (from config file).");
        multiQueryExecutor = new MultiExecutor<GroupedSearchResults>(workerThreads, "multiSearcher");
    }
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
  /**
   * Constructor.
   * @param indexer a reference to the indexer that contains this module.
   */
  public SanitizerModule() {
        Config config = Config.getConfig("indexer.properties");
        xpath = config.getString("SanitizerModule.XPath");
        htmlFields = new HashSet<String>(Arrays.asList(config.getStringArray("SanitizerModule.html")));
        xmlFields = new HashSet<String>(Arrays.asList(config.getStringArray("SanitizerModule.xml")));
        accentFields = new HashSet<String>(Arrays.asList(config.getStringArray("SanitizerModule.accents")));
        allFields = new HashSet<String>();
        allFields.addAll(htmlFields);
        allFields.addAll(xmlFields);
        allFields.addAll(accentFields);
  }
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
    private String docIdName = null;
    private static final Logger logger = Logger.getLogger(Execute.whoAmI());

    public Writer(final Indexer indexer) {
        super(indexer);
    Config config = Config.getConfig("indexer.properties");
    docIdName = config.getString("docIdName");
        if (docIdName.equals("")) {
            throw new IllegalArgumentException("The docIdName cannot be empty");
        }

    }
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
        seen = 0;
        fetched = 0;
        processed = 0;
        sorted = 0;
        trimmed = 0;
        Config config = Config.getConfig("crawler.properties");
        String baseFileName = config.getString("progress.report.filename");
        baseFile = new File(baseFileName);
        reportFile = new File(baseFileName+"."+cycle);
        binaryFile = new File(baseFileName+"-b."+cycle);
        startTime = new long[6];
        startTime[START] = System.currentTimeMillis();
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
117
     * Marks the start of the fetch stage.
     * @param max number of pages in the old pagedb.
     * @param known number of known pages in the old pagedb.
     */
    public void startFetch(long max, long known) {
        Config config = Config.getConfig("crawler.properties");
        int refetchPercent = config.getInt("priority.percentile.to.fetch");
        tosee = max > 0 ? max : 1;
        tofetch = (max-known)+known*refetchPercent/100;
        if (0 == tofetch) tofetch = 1;
        stage = FETCH;
        startTime[stage] = System.currentTimeMillis();
View Full Code Here
TOP

Related Classes of com.flaptor.util.Config

  • com.flaptor.hounder.cache.HttpCacheServer$CacheHandler
  • com.flaptor.hounder.classifier.bayes.BayesCalculatorTest
  • com.flaptor.hounder.classifier.WhyBean
  • com.flaptor.hounder.cluster.MultiSearcher
  • com.flaptor.hounder.crawler.bean.CrawlerBean
  • com.flaptor.hounder.crawler.Crawler
  • com.flaptor.hounder.crawler.CrawlerProgress
  • com.flaptor.hounder.crawler.CrawlerTest
  • com.flaptor.hounder.crawler.FetchdataProcessor
  • com.flaptor.hounder.crawler.FetcherTest
    • 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.