WiktionaryDumps to words: Difference between revisions
Content added Content deleted
(Work in progress Java example) |
(→{{header|Java}}: Fixed regex using Pattern.DOTALL) |
||
Line 14: | Line 14: | ||
import javax.xml.parsers.SAXParserFactory; |
import javax.xml.parsers.SAXParserFactory; |
||
import javax.xml.parsers.ParserConfigurationException; |
import javax.xml.parsers.ParserConfigurationException; |
||
import java.util.regex.Pattern; |
|||
import java.util.regex.Matcher; |
|||
class MyHandler extends DefaultHandler { |
class MyHandler extends DefaultHandler { |
||
Line 24: | Line 27: | ||
@Override |
@Override |
||
public void characters(char[] ch, int start, int length) throws SAXException { |
public void characters(char[] ch, int start, int length) throws SAXException { |
||
String regex = ".*==French==.*"; |
|||
Pattern pat = Pattern.compile(regex, Pattern.DOTALL); |
|||
switch (lastTag) { |
switch (lastTag) { |
||
case TITLE: |
case TITLE: |
||
Line 30: | Line 36: | ||
case TEXT: |
case TEXT: |
||
String text = new String(ch, start, length); |
String text = new String(ch, start, length); |
||
Matcher mat = pat.matcher(text); |
|||
if (mat.matches()) { |
|||
System.out.println(title); |
System.out.println(title); |
||
} |
} |
||
Line 39: | Line 46: | ||
@Override |
@Override |
||
public void startElement(String uri, String localName, String qName, Attributes attrs) throws SAXException { |
public void startElement(String uri, String localName, String qName, Attributes attrs) throws SAXException { |
||
lastTag = qName; |
|||
} |
} |
||
@Override |
@Override |
||
public void endElement(String uri, String localName, String qName) throws SAXException { |
public void endElement(String uri, String localName, String qName) throws SAXException { |
||
lastTag = ""; |
|||
} |
} |
||
} |
} |