StreamTokenizer

Bruce Eckel's Thinking in Java Contents | Prev | Next

//: SortedWordCount.java
// Counts words in a file, outputs
// results in sorted form.
import java.io.*;
import java.util.*;
import c08.*; // Contains StrSortVector
 
class Counter {
  private int i = 1;
  int read() { return i; }
  void increment() { i++; }
}
 
public class SortedWordCount {
  private FileInputStream file;
  private StreamTokenizer st;
  private Hashtable counts = new Hashtable();
  SortedWordCount(String filename)
    throws FileNotFoundException {
    try {
      file = new FileInputStream(filename);
      st = new StreamTokenizer(file);
      st.ordinaryChar('.');
      st.ordinaryChar('-');
    } catch(FileNotFoundException e) {
      System.out.println(
        "Could not open " + filename);
      throw e;
    }
  }
  void cleanup() {
    try {
      file.close();
    } catch(IOException e) {
      System.out.println(
        "file.close() unsuccessful");
    }
  }
  void countWords() {
    try {
      while(st.nextToken() !=
        StreamTokenizer.TT_EOF) {
        String s;
        switch(st.ttype) {
          case StreamTokenizer.TT_EOL:
            s = new String("EOL");
            break;
          case StreamTokenizer.TT_NUMBER:
            s = Double.toString(st.nval);
            break;
          case StreamTokenizer.TT_WORD:
            s = st.sval; // Already a String
            break;
          default: // single character in ttype
            s = String.valueOf((char)st.ttype);
        }
        if(counts.containsKey(s))
          ((Counter)counts.get(s)).increment();
        else
          counts.put(s, new Counter());
      }
    } catch(IOException e) {
      System.out.println(
        "st.nextToken() unsuccessful");
    }
  }
  Enumeration values() {
    return counts.elements();
  }
  Enumeration keys() { return counts.keys(); }
  Counter getCounter(String s) {
    return (Counter)counts.get(s);
  }
  Enumeration sortedKeys() {
    Enumeration e = counts.keys();
    StrSortVector sv = new StrSortVector();
    while(e.hasMoreElements())
      sv.addElement((String)e.nextElement());
    // This call forces a sort:
    return sv.elements();
  }
  public static void main(String[] args) {
    try {
      SortedWordCount wc =
        new SortedWordCount(args[0]);
      wc.countWords();
      Enumeration keys = wc.sortedKeys();
      while(keys.hasMoreElements()) {
        String key = (String)keys.nextElement();
        System.out.println(key + ": "
                 + wc.getCounter(key).read());
      }
      wc.cleanup();
    } catch(Exception e) {
      e.printStackTrace();
    }
  }
} ///:~ 

StringTokenizer

Although it isn’t part of the IO library, the StringTokenizer has sufficiently similar functionality to StreamTokenizer that it will be described here.

//: AnalyzeSentence.java
// Look for particular sequences
// within sentences.
import java.util.*;
 
public class AnalyzeSentence {
  public static void main(String[] args) {
    analyze("I am happy about this");
    analyze("I am not happy about this");
    analyze("I am not! I am happy");
    analyze("I am sad about this");
    analyze("I am not sad about this");
    analyze("I am not! I am sad");
    analyze("Are you happy about this?");
    analyze("Are you sad about this?");
    analyze("It's you! I am happy");
    analyze("It's you! I am sad");
  }
  static StringTokenizer st;
  static void analyze(String s) {
    prt("\nnew sentence >> " + s);
    boolean sad = false;
    st = new StringTokenizer(s);
    while (st.hasMoreTokens()) {
      String token = next();
      // Look until you find one of the
      // two starting tokens:
      if(!token.equals("I") &&
         !token.equals("Are"))
        continue; // Top of while loop
      if(token.equals("I")) {
        String tk2 = next();
        if(!tk2.equals("am")) // Must be after I
          break; // Out of while loop
        else {
          String tk3 = next();
          if(tk3.equals("sad")) {
            sad = true;
            break; // Out of while loop
          }
          if (tk3.equals("not")) {
            String tk4 = next();
            if(tk4.equals("sad"))
              break; // Leave sad false
            if(tk4.equals("happy")) {
              sad = true;
              break;
            }
          }
        }
      }
      if(token.equals("Are")) {
        String tk2 = next();
        if(!tk2.equals("you"))
          break; // Must be after Are
        String tk3 = next();
        if(tk3.equals("sad"))
          sad = true;
        break; // Out of while loop
      }
    }
    if(sad) prt("Sad detected");
  }
  static String next() {
    if(st.hasMoreTokens()) {
      String s = st.nextToken();
      prt(s);
      return s;
    } 
    else
      return "";
  }
  static void prt(String s) {
    System.out.println(s);
  }
} ///:~ 

For each string being analyzed, a while loop is entered and tokens are pulled off the string. Notice the first if statement, which says to continue (go back to the beginning of the loop and start again) if the token is neither an “I” nor an “Are.” This means that it will get tokens until an “I” or an “Are” is found. You might think to use the == instead of the equals( ) method, but that won’t work correctly, since == compares handle values while equals( ) compares contents.



Comments

  • There are no comments yet. Be the first to comment!

Leave a Comment
  • Your email address will not be published. All fields are required.

Top White Papers and Webcasts

  • When individual departments procure cloud service for their own use, they usually don't consider the hazardous organization-wide implications. Read this paper to learn best practices for setting up an internal, IT-based cloud brokerage function that service the entire organization. Find out how this approach enables you to retain top-down visibility and control of network security and manage the impact of cloud traffic on your WAN.

  • U.S. companies are desperately trying to recruit and hire skilled software engineers and developers, but there is simply not enough quality talent to go around. Tiempo Development is a nearshore software development company. Our headquarters are in AZ, but we are a pioneer and leader in outsourcing to Mexico, based on our three software development centers there. We have a proven process and we are experts at providing our customers with powerful solutions. We transform ideas into reality.

Most Popular Programming Stories

More for Developers

RSS Feeds

Thanks for your registration, follow us on our social networks to keep up-to-date