source: gs3-extensions/maori-lang-detection/src/org/greenstone/atea/MRIWebPageStats.java@ 33587

package org.greenstone.atea;


//import org.apache.log4j.Logger;


public class MRIWebPageStats {
    //private static Logger logger = Logger.getLogger(org.greenstone.atea.MRIWebPageStats.class.getName());

    public final String siteID; // crawled site's folder name e.g. 00510
    public final String URL; // URL of webpage
    public final int pageID; // index into NutchTextDumpProcessor::pages ArrayList

    public final boolean isMRI;
    public final int numSentences; // count of all sentences in the webpage's body
    public final int numSentencesInMRI; // count of sentences in the webpage's body in Māori (mri)

    
    public MRIWebPageStats(String siteID, String url, int pageID, boolean isMRI,
               int numSentences, int numSentencesInMRI)
    {
    this.siteID = siteID;
    this.URL = url;
    this.pageID = pageID;

    this.isMRI = isMRI;
    this.numSentences = numSentences;
    this.numSentencesInMRI = numSentencesInMRI;
    }

    public String toString() {
    StringBuilder str = new StringBuilder();
    str.append("URL: " + this.URL);
    str.append("\nsiteID: " + this.siteID);
    str.append("\nnum sentences in MRI: " + this.numSentencesInMRI+"/"+this.numSentences);  
    if(this.isMRI && this.numSentencesInMRI <= 0) {
        // one or more pages in the site were MRI, but they didn't contain proper sentences
        str.append(" (no PROPER sentences in MRI)");
    }
    return str.toString();
    }
}