/* author: Christopher O'Neill date: Feb 2001 comments: cleaner reads in from a file cleans out none letter or digit chars and loLowerCases it before writing it to a new file*/ import java.io.*; import java.lang.*; import java.util.*; public class Clean { /**************************************************************** *Method: Clean * *Returns: String * *Recievs: String str * *Purpose: remove all non letter or digit characters from * * word and toLowerCase then return * ****************************************************************/ private String Cleaner( String word ) { String clean = ""; for ( int i=0; i < word.length(); i++ ) { if (Character.isLetterOrDigit(word.charAt(i))) { clean += word.charAt(i); } } clean = clean.toLowerCase(); //change all letters in the input to lowercase return clean; } // end of clean method public static void main(String args[] ) { Clean c= new Clean(); String text; StringTokenizer line = new StringTokenizer(""); String filein = args[0]; String fileout = args[1]; String snewline = args[2]; boolean newline = false; if (snewline.equals("/n")); { newline = true; } try { FileWriter fw = new FileWriter(fileout); BufferedWriter bw = new BufferedWriter(fw); FileReader fr = new FileReader(filein); BufferedReader br = new BufferedReader(fr); try { while ((text=br.readLine())!= null) { line= new StringTokenizer(text); try { while (line.hasMoreTokens()) { // read word from line and stem word String word = new String(); word = line.nextToken(); if (newline) { bw.write(c.Cleaner(word)); bw.newLine(); } else { bw.write(c.Cleaner(word)+" "); } } if (!newline) { bw.newLine(); } } catch (Exception e) { System.err.println(e); } } } catch(Exception e) { System.err.println("File Error Durring Reading"+e); System.exit(0); } // try to close file, file is not needed again so if can't close don't exit try { fr.close(); } catch(Exception e) { System.err.println("Error Closing File During Reading"); } try { bw.close(); } catch(Exception e) { System.err.println(e); } } catch(Exception e) { System.err.println("Input File" + filein +"not found"); System.exit(1); } }//main } //class