Package org.exoplatform.services.chars.chardet

Examples of org.exoplatform.services.chars.chardet.Detector

45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
      FileInputStream input = new FileInputStream(file);
      BufferedInputStream buffer = new BufferedInputStream(input);
      byte[] data = new byte[buffer.available()];
      int available = -1;

      Detector det = new Detector(PSMDetector.ALL);

      //Set an observer...
      //The Notify() will be called when a matching charset is found.
      det.init(new ICharsetDetectionObserver()
      {
         public void notify(String charset)
         {
            System.out.println("CHARSET === " + charset);
         }
      });

      boolean done = false;
      boolean isAscii = true;

      while ((available = buffer.read(data)) > -1)
      {
         //Khoilv'code.
         //System.out.print(data);
         if (isAscii)
            isAscii = det.isAscii(data, available);

         //DoIt if non-ascii and not done yet.
         if (!isAscii && !done)
            done = det.doIt(data, available, false);
      }

      det.dataEnd();

      if (isAscii)
      {
         System.out.println("CHARSET = ASCII");
         found = true;
      }

      if (!found)
      {
         String prob[] = det.getProbableCharsets();
         for (int i = 0; i < prob.length; i++)
         {
            System.out.println("Probable Charset = " + prob[i]);
         }
      }
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
         return;
      }

      //Initialize the nsDetector();
      int lang = (argv.length == 2) ? Integer.parseInt(argv[1]) : PSMDetector.ALL;
      Detector det = new Detector(lang);

      //Set an observer...
      //The Notify() will be called when a matching charset is found.

      det.init(new ICharsetDetectionObserver()
      {
         public void notify(String charset)
         {
            HtmlCharsetDetector.found = true;
            System.out.println("CHARSET = " + charset);
         }
      });

      URL url = new URL(argv[0]);
      BufferedInputStream imp = new BufferedInputStream(url.openStream());

      byte[] buf = new byte[1024];
      int len;
      boolean done = false;
      boolean isAscii = true;

      while ((len = imp.read(buf, 0, buf.length)) != -1)
      {
         //Check if the stream is only ascii.
         if (isAscii)
            isAscii = det.isAscii(buf, len);

         //DoIt if non-ascii and not done yet.
         if (!isAscii && !done)
            done = det.doIt(buf, len, false);
      }
      det.dataEnd();

      if (isAscii)
      {
         System.out.println("CHARSET = ARSII");
         found = true;
      }

      if (!found)
      {
         String prob[] = det.getProbableCharsets();
         for (int i = 0; i < prob.length; i++)
         {
            System.out.println("Probable Charset = " + prob[i]);
         }
      }
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
      return createDocument(reader.load(file), charset);
   }

   public static String detect(byte[] buf)
   {
      Detector det = new Detector(PSMDetector.ALL);
      charset_ = null;
      det.init(new ICharsetDetectionObserver()
      {
         public void notify(String charset)
         {
            charset_ = charset;
         }
      });

      boolean isAscii = true;
      int len = buf.length;

      isAscii = det.isAscii(buf, len);
      if (!isAscii)
         det.doIt(buf, len, false);
      det.dataEnd();

      if (isAscii)
         charset_ = "ASCII";
      return charset_;
   }
View Full Code Here
TOP

Related Classes of org.exoplatform.services.chars.chardet.Detector

  • org.exoplatform.services.html.parser.HTMLParser
  • org.exoplatform.test.HtmlCharsetDetector
  • org.exoplatform.test.TestFile
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.