findwordinlines.java

Java Crawler with domain knowledge path

package HtreeExa;

public class FindWordInLines {

public static void main(String[] args) {
String s = "http://www.google.com/intl/en/about.html";

String[] lines = s.split("//");

String searchWord = "en";
// this won't work for Interface CharSequence
searchWord=searchWord.toLowerCase();
char[] sequence = searchWord.toCharArray();
// this will work for CharSequence, thus we can use .contains()
StringBuilder sb = new StringBuilder(searchWord);

for (int i = 0; i < lines.length; i++) {
// you get -1, if not there
if (lines[i].indexOf(searchWord) > 0) {
// do a substring
String wordFound =
lines[i].substring(
lines[i].indexOf(searchWord),
lines[i].indexOf(searchWord)+ searchWord.length());
System.out.println("Line no. " + (i + 1) +" contains " + wordFound);
}
}
// to use .contains()
/*for (int i = 0; i < lines.length; i++) {
if( lines[i].contains( sb )) {
System.out.println("Line no. " + (i + 1) );
}

}*/

}
}