Computer Science 15-110, Spring 2010
Class Notes: More IO:  Strings, Files, and Web Pages (Optional)

1. Other Input Sources
   1. Read from a String
   2. Read from a File
      1. Word-at-a-time (excluding whitespace)
      2. Line-at-a-time (including whitespace)
   3. (And Write to a File)
   4. Read from a Web Page

More IO:  Strings, Files, and Web Pages

1. Other Input Sources
    
   1. Read from a String

      import java.util.Scanner;
      class MyCode {
        public static void main(String[] args) {
          String s = "Douglas Noel Adams";
          Scanner scanner = new Scanner(s);
          while (scanner.hasNext())
            System.out.println(scanner.next());
        }
      }

      Another example (with a custom delimiter):

      import java.util.Scanner;
      class MyCode {
        public static void main(String[] args) {
          String s = "Rome,Paris,Peoria,London,Tokyo";
          Scanner scanner = new Scanner(s);
          scanner.useDelimiter(",");
          while (scanner.hasNext())
            System.out.println(scanner.next());
        }
      }

   2. Read from a File
       
      1. Word-at-a-time (excluding whitespace)

         import java.util.Scanner;
         class MyCode  {
           public static void main(String[] args) {
             Scanner scanner = getFileScanner("SampleFile.txt");
             while (scanner.hasNext())
               System.out.println(scanner.next());
           }
         
           // Convenient helper method for reading from a file.
           // Returns null if the file is not found (or for any other error).
           // You are responsible for using this method, but not
           // for writing it (neither on homeworks or tests)!
           public static Scanner getFileScanner(String filename) {
             Scanner scanner = null;
             try {
               java.io.File file = new java.io.File(filename);
               if (file.isAbsolute() == true) {
                 scanner = new Scanner(file);
               }
               else {
                 // treat relative files as resources so they work in jar files!
                 // Note that we cannot use the current thread's classLoader,
                 // since this does not work appropriately on Vista nor on some Macs.
                 java.io.InputStream is = getDefiningClass().getResourceAsStream(filename);
                 scanner = new Scanner(new java.io.BufferedReader(
                                        new java.io.InputStreamReader(is)));
               }
             }
             catch (Exception e) {
               System.out.println("File not found: " + filename);
               return null;
             }
             return scanner;
           }
         
           // Return an instance of the Class class representing the
           // class in which this method is defined.  
           public static Class getDefiningClass() {
             try {
               StackTraceElement[] em = new Exception().getStackTrace();
               return Class.forName(em[0].getClassName());
             } catch (Exception e) {
               throw new RuntimeException("Cannot find current class");
             }
           }
         }

      2. Line-at-a-time (including whitespace)

           public static void main(String[] args) {
             Scanner scanner = getFileScanner("SampleFile.txt");
             while (scanner.hasNext())
               System.out.println(scanner.nextLine());
           }

   3. (And Write to a File)

      import java.io.PrintStream;
      class MyCode  {
        public static void main(String[] args) {
          PrintStream out = getFilePrintStream("MyOutput.txt");
          out.println("This will output to the file 'MyOutput.txt'");
        }
      
        // Convenient helper method for writing to a file.
        // Returns null if the file cannot be opened (or for any other error).
        // You are responsible for using this method, but not
        // for writing it (neither on homeworks or tests)!
        public static PrintStream getFilePrintStream(String filename) {
          PrintStream out = null;
          try { out = new PrintStream(new java.io.File(filename)); }
          catch (Exception e) {
            System.out.println("Error opening file " + filename);
            return null;
          }
          return out;
        }
      }

   4. Read from a Web Page
       
      1. As HTML

         import java.util.Scanner;
         class MyCode  {
           public static void main(String[] args) {
             String url = "http://kosbie.net/cmu/fall-08/15-100/handouts/parsely.html";
             Scanner scanner = getUrlScanner(url);
             while (scanner.hasNext())
               System.out.println(scanner.nextLine());
           }
         
           // Convenient helper method for reading from a web page (url).
           // Returns null if the page cannot be opened (or for any other error).
           // You are responsible for using this method, but not
           // for writing it (neither on homeworks or tests)!
           public static Scanner getUrlScanner(String url) {
             Scanner scanner = null;
             try { scanner = new Scanner(new java.net.URL(url).openStream()); }
             catch (Exception e) {
               System.out.println("Error opening url " + url);
               return null;
             }
             return scanner;
           }
         }

      2. As Plain Text

         import java.util.Scanner;
         class MyCode  {
           public static void main(String[] args) {
             String url = "http://kosbie.net/cmu/fall-08/15-100/handouts/parsely.html";
             Scanner scanner = getUrlTextScanner(url);
             while (scanner.hasNext())
               System.out.println(scanner.nextLine());
           }
         
           // Convenient helper method for reading from a web page (url) as plain text.
           // Returns null if the page cannot be opened (or for any other error).
           // On some pages, especially if they contain XML, the spaces may be elided
           // (sothetextislikethis) -- in that case, try setting the second parameter
           // to " " or "\n", so spaces or newlines are added after each parsed element.
           // You are responsible for using this method, but not
           // for writing it (neither on homeworks or tests)!
         
           public static Scanner getUrlTextScanner(String url) { return getUrlTextScanner(url, null); }

           public static Scanner getUrlTextScanner(String url, final String dataDelimiter) {
             Scanner scanner = null;
             try {
               final StringBuffer sb = new StringBuffer();
               java.io.InputStreamReader reader = new java.io.InputStreamReader(
                                               new java.net.URL(url).openStream());
               javax.swing.text.html.HTMLEditorKit.ParserCallback parser =
                 new javax.swing.text.html.HTMLEditorKit.ParserCallback() {
                   public void handleText(char[] data, int pos) {
                     if (data != null) {
                       sb.append(data);
                       if (dataDelimiter != null) sb.append(dataDelimiter);
                     }
                   }
                   public void handleSimpleTag(javax.swing.text.html.HTML.Tag tag,
                                     javax.swing.text.MutableAttributeSet a,
                                     int pos) {
                    if (tag.breaksFlow()) sb.append("\n");
                   }
                 };
               new javax.swing.text.html.parser.ParserDelegator().parse(reader, parser, true);
               scanner = new Scanner(sb.toString());
             }
             catch (Exception e) {
               System.out.println("Error opening text reader for url: " + url);
               return null;
             }
             return scanner;
           }
         }

carpe diem   -   carpe diem   -   carpe diem   -   carpe diem   -   carpe diem   -   carpe diem   -   carpe diem   -   carpe diem   -   carpe diem