Discard html tags within custom tags while getting text in XHTML using SAX Parser in Groovy

Question

So I am trying to get the text between the tags. So far I have been successful. But sometimes when there are special characters or html tags inside my custom tags I am unable to

Answer 1

I'm not familiar with Groovy so here is a solution in Java. I believe the translation is straighforward.

import java.io.FileInputStream;
import java.io.InputStream;
import java.util.ArrayList;

import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.xml.sax.Attributes;
import org.xml.sax.helpers.DefaultHandler;

public class SaxHandler extends DefaultHandler {
    ArrayList<String> DefinedTermTitles = new ArrayList<>();
    ArrayList<String> ClauseTitles = new ArrayList<>();
    String currentMessage;
    boolean countryFlag = false;
    StringBuilder message = new StringBuilder();

    public void startElement(String ns, String localName, String qName, Attributes atts) {
        switch (qName) {
            case "ae_clauseTitleBegin":
                countryFlag = true;
                break;

            case "ae_definedTermTitleBegin":
                countryFlag = true; 
                break;           
         }      
    }   

    public void characters(char[] chars, int offset, int length) {
        if (countryFlag) {
            message.append(new String(chars, offset, length));
        }
    }

    public void endElement(String ns, String localName, String qName) {
        switch (qName) {        
            case "ae_clauseTitleEnd":
                ClauseTitles.add(message.toString());
                countryFlag = false;
                message.setLength(0);
                break;

            case "ae_definedTermTitleEnd":
                DefinedTermTitles.add(message.toString());
                countryFlag = false; 
                message.setLength(0);
                break;
         }
    }

    public static void main (String argv []) {
        SAXParserFactory factory = SAXParserFactory.newInstance();
        try {
            String path = "INPUT_PATH_HERE";
            InputStream xmlInput = new FileInputStream(path + "test.xml");
            SAXParser saxParser = factory.newSAXParser();
            SaxHandler handler   = new SaxHandler();
            saxParser.parse(xmlInput, handler);

            System.out.println(handler.DefinedTermTitles);
            System.out.println(handler.ClauseTitles);

        } catch (Exception err) {
            err.printStackTrace ();
        }
    }
}

Output

[Australia, Isle of Man, France]
[1.02 Accounting Terms., Smallest Street-Legal Car at 99cm wide and 59 kg in weight, Most Valuable Car at $15 million]

Answer 2

Since you have been asking this question now for different libraries, here is a solution with XMLParser. The author of this XML had maybe not the best understanding how XML works. If I where you I'd rather put some filtering in place, to make this sane again (e.g. <tagBegin/>X<tagEnd/> to <tag>x</tag>).

def xml = '''\
<records>
    <car name='HSV Maloo' make='Holden' year='2006'>
        <ae_definedTermTitleBegin />Australia<ae_definedTermTitleEnd />
        <ae_clauseTitleBegin />1.02 <u>Accounting Terms</u>.<ae_clauseTitleEnd />
    </car>
    <car name='P50' make='Peel' year='1962'>
        <ae_definedTermTitleBegin />Isle of Man<ae_definedTermTitleEnd />
        <ae_clauseTitleBegin />Smallest Street-Legal Car at 99cm wide and 59 kg in weight<ae_clauseTitleEnd />
    </car>
    <car name='Royale' make='Bugatti' year='1931'>
        <ae_definedTermTitleBegin />France<ae_definedTermTitleEnd />
        <ae_clauseTitleBegin />Most Valuable Car at $15 million<ae_clauseTitleEnd />
    </car>
</records>
'''

def underp = { l ->
    l.inject([texts: [:]]) { r, it ->
        if (it.respondsTo('name') && it.name().endsWith('Begin')) {
            r.texts[(r.last=it.name().replaceFirst(/Begin$/,''))] = ''
        } else if (it.respondsTo('name') && it.name().endsWith('End')) {
            r.last = null
        } else if (r.last) {
            r.texts[r.last] += (it instanceof String) ? it : it.text()
        }
        r
    }.texts
}

def root = new XmlParser().parseText(xml)
root.car.each{
    println underp(it.children()).inspect()
}

prints

['ae_definedTermTitle':'Australia', 'ae_clauseTitle':'1.02 Accounting Terms.']
['ae_definedTermTitle':'Isle of Man', 'ae_clauseTitle':'Smallest Street-Legal Car at 99cm wide and 59 kg in weight']
['ae_definedTermTitle':'France', 'ae_clauseTitle':'Most Valuable Car at $15 million']