java删除重复行,使用Java从文本中删除重复的行

I was wondering if anyone has logic in java that removes duplicate lines while maintaining the lines order.

I would prefer no regex solution.

解决方案

public class UniqueLineReader extends BufferedReader {

Set lines = new HashSet();

public UniqueLineReader(Reader arg0) {

super(arg0);

}

@Override

public String readLine() throws IOException {

String uniqueLine;

if (lines.add(uniqueLine = super.readLine()))

return uniqueLine;

return "";

}

//for testing..

public static void main(String args[]) {

try {

// Open the file that is the first

// command line parameter

FileInputStream fstream = new FileInputStream(

"test.txt");

UniqueLineReader br = new UniqueLineReader(new InputStreamReader(fstream));

String strLine;

// Read File Line By Line

while ((strLine = br.readLine()) != null) {

// Print the content on the console

if (strLine != "")

System.out.println(strLine);

}

// Close the input stream

in.close();

} catch (Exception e) {// Catch exception if any

System.err.println("Error: " + e.getMessage());

}

}

}

Modified Version:

public class UniqueLineReader extends BufferedReader {

Set lines = new HashSet();

public UniqueLineReader(Reader arg0) {

super(arg0);

}

@Override

public String readLine() throws IOException {

String uniqueLine;

while (lines.add(uniqueLine = super.readLine()) == false); //read until encountering a unique line

return uniqueLine;

}

public static void main(String args[]) {

try {

// Open the file that is the first

// command line parameter

FileInputStream fstream = new FileInputStream(

"/home/emil/Desktop/ff.txt");

UniqueLineReader br = new UniqueLineReader(new InputStreamReader(fstream));

String strLine;

// Read File Line By Line

while ((strLine = br.readLine()) != null) {

// Print the content on the console

System.out.println(strLine);

}

// Close the input stream

in.close();

} catch (Exception e) {// Catch exception if any

System.err.println("Error: " + e.getMessage());

}

}

}