001    /**
002     * Copyright (c) 2003 Daffodil Software Ltd all rights reserved,
003     * Modifications Copyright (c) 2008 Regiscope Digital Imaging Co, LLC, All rights reserved.
004     * This program is free software; you can redistribute it and/or modify
005     * it under the terms of version 2 of the GNU General Public License as
006     * published by the Free Software Foundation.
007     * There are special exceptions to the terms and conditions of the GPL
008     * as it is applied to this software. See the GNU General Public License for more details.
009     *
010     * This program is distributed in the hope that it will be useful,
011     * but WITHOUT ANY WARRANTY; without even the implied warranty of
012     * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
013     * GNU General Public License for more details.
014     *
015     * You should have received a copy of the GNU General Public License
016     * along with this program; if not, write to the Free Software
017     * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
018     */
019    
020    package org.dbreplicator.replication;
021    
022    import java.util.Locale;
023    import java.util.Map;
024    import java.util.Hashtable;
025    
026    /**
027     * <p>Title: </p>
028     * <p>Description: </p>
029     * <p>Copyright: Copyright (c) 2005</p>
030     * <p>Company: </p>
031     * @author not attributable
032     * @version 1.0
033     */
034    
035    public class EncoderDecoder {
036      private static Map entities;
037    
038      public EncoderDecoder() {
039      }
040    
041    
042      /**
043       * This method convert the ASCII value to UNICODE escape.
044       *
045       *  The uppercase letters 'A' through 'Z' ('\u0041' through '\u005a'),
046       *  The lowercase letters 'a' through 'z' ('\u0061' through '\u007a'),
047       *  The digits '0' through '9' ('\u0030' through '\u0039'),
048       *  The dash character '-' ('\u002d', HYPHEN-MINUS),
049       *  The colon character ':' ('\u003a', COLON), and
050       *  The underscore character '_' ('\u005f', LOW LINE).
051       *
052       *
053       * @param str
054       * @param escapeAscii
055       * @return String
056       */
057      public   static String escapeUnicodeStringOLD(String str, boolean escapeAscii)
058     {
059        String ostr = new String();
060        for(int i=0; i<str.length(); i++) {
061           char ch = str.charAt(i);
062           if (!escapeAscii && ((ch >= 0x0020) && (ch <= 0x007e)))
063              ostr += ch ;
064           else {
065              ostr += "\\u" ;
066              String hex = Integer.toHexString(str.charAt(i) & 0xFFFF);
067              if (hex.length() == 2)
068                 ostr += "00" ;
069              ostr += hex.toUpperCase(Locale.ENGLISH);
070           }
071        }
072        return (ostr);
073     }
074    
075    
076     public   static String escapeUnicodeString1(String str, boolean escapeAscii)
077    {
078      StringBuffer ostr = new StringBuffer();
079      for(int i=0; i<str.length(); i++) {
080         char ch = str.charAt(i);
081         if (!escapeAscii && ((ch >= 0x0020) && (ch <= 0x007e))){
082           ostr.append(ch)  ;
083         }
084         else {
085            ostr.append("\\u");
086            String hex = Integer.toHexString(str.charAt(i) & 0xFFFF);
087    //        System.out.println(ch+" hex string  "+ hex);
088            if (hex.length() == 2)
089               ostr.append("00");
090             else if(hex.length() == 1)
091               ostr.append("000");
092             else if(hex.length() == 3)
093               ostr.append("0");
094    
095            ostr.append( hex.toUpperCase(Locale.ENGLISH));
096         }
097      }
098    //System.out.println(" ostr.toString() ="+ostr.toString());
099      return ostr.toString();
100    }
101    
102    
103     private synchronized static Map getEntities()
104      {
105         if (entities==null)
106         {
107            entities=new Hashtable();
108            //Quotation mark
109            entities.put("quot","\"");
110            //Ampersand
111            entities.put("amp","\u0026");
112            //Less than
113            entities.put("lt","\u003C");
114            //Greater than
115            entities.put("gt","\u003E");
116            //Nonbreaking space
117            entities.put("nbsp","\u00A0");
118            //Inverted exclamation point
119            entities.put("iexcl","\u00A1");
120            //Cent sign
121            entities.put("cent","\u00A2");
122            //Pound sign
123            entities.put("pound","\u00A3");
124            //General currency sign
125            entities.put("curren","\u00A4");
126            //Yen sign
127            entities.put("yen","\u00A5");
128            //Broken vertical bar
129            entities.put("brvbar","\u00A6");
130            //Section sign
131            entities.put("sect","\u00A7");
132            //Umlaut
133            entities.put("uml","\u00A8");
134            //Copyright
135            entities.put("copy","\u00A9");
136            //Feminine ordinal
137            entities.put("ordf","\u00AA");
138            //Left angle quote
139            entities.put("laquo","\u00AB");
140            //Not sign
141            entities.put("not","\u00AC");
142            //Soft hyphen
143            entities.put("shy","\u00AD");
144            //Registered trademark
145            entities.put("reg","\u00AE");
146            //Macron accent
147            entities.put("macr","\u00AF");
148            //Degree sign
149            entities.put("deg","\u00B0");
150            //Plus or minus
151            entities.put("plusmn","\u00B1");
152            //Superscript 2
153            entities.put("sup2","\u00B2");
154            //Superscript 3
155            entities.put("sup3","\u00B3");
156            //Acute accent
157            entities.put("acute","\u00B4");
158            //Micro sign (Greek mu)
159            entities.put("micro","\u00B5");
160            //Paragraph sign
161            entities.put("para","\u00B6");
162            //Middle dot
163            entities.put("middot","\u00B7");
164            //Cedilla
165            entities.put("cedil","\u00B8");
166            //Superscript 1
167            entities.put("sup1","\u00B9");
168            //Masculine ordinal
169            entities.put("ordm","\u00BA");
170            //Right angle quote
171            entities.put("raquo","\u00BB");
172            //Fraction one-fourth
173            entities.put("frac14","\u00BC");
174            //Fraction one-half
175            entities.put("frac12","\u00BD");
176            //Fraction three-fourths
177            entities.put("frac34","\u00BE");
178            //Inverted question mark
179            entities.put("iquest","\u00BF");
180            //Capital A, grave accent
181            entities.put("Agrave","\u00C0");
182            //Capital A, acute accent
183            entities.put("Aacute","\u00C1");
184            //Capital A, circumflex accent
185            entities.put("Acirc","\u00C2");
186            //Capital A, tilde
187            entities.put("Atilde","\u00C3");
188            //Capital A, umlaut
189            entities.put("Auml","\u00C4");
190            //Capital A, ring
191            entities.put("Aring","\u00C5");
192            //Capital AE ligature
193            entities.put("AElig","\u00C6");
194            //Capital C, cedilla
195            entities.put("Ccedil","\u00C7");
196            //Capital E, grave accent
197            entities.put("Egrave","\u00C8");
198            //Capital E, acute accent
199            entities.put("Eacute","\u00C9");
200            //Capital E, circumflex accent
201            entities.put("Ecirc","\u00CA");
202            //Capital E, umlaut
203            entities.put("Euml","\u00CB");
204            //Capital I, grave accent
205            entities.put("Igrave","\u00CC");
206            //Capital I, acute accent
207            entities.put("Iacute","\u00CD");
208            //Capital I, circumflex accent
209            entities.put("Icirc","\u00CE");
210            //Capital I, umlaut
211            entities.put("Iuml","\u00CF");
212            //Capital eth, Icelandic
213            entities.put("ETH","\u00D0");
214            //Capital N, tilde
215            entities.put("Ntilde","\u00D1");
216            //Capital O, grave accent
217            entities.put("Ograve","\u00D2");
218            //Capital O, acute accent
219            entities.put("Oacute","\u00D3");
220            //Capital O, circumflex accent
221            entities.put("Ocirc","\u00D4");
222            //Capital O, tilde
223            entities.put("Otilde","\u00D5");
224            //Capital O, umlaut
225            entities.put("Ouml","\u00D6");
226            //Multiply sign
227            entities.put("times","\u00D7");
228            //Capital O, slash
229            entities.put("Oslash","\u00D8");
230            //Capital U, grave accent
231            entities.put("Ugrave","\u00D9");
232            //Capital U, acute accent
233            entities.put("Uacute","\u00DA");
234            //Capital U, circumflex accent
235            entities.put("Ucirc","\u00DB");
236            //Capital U, umlaut
237            entities.put("Uuml","\u00DC");
238            //Capital Y, acute accent
239            entities.put("Yacute","\u00DD");
240            //Capital thorn, Icelandic
241            entities.put("THORN","\u00DE");
242            //Small sz ligature, German
243            entities.put("szlig","\u00DF");
244            //Small a, grave accent
245            entities.put("agrave","\u00E0");
246            //Small a, acute accent
247            entities.put("aacute","\u00E1");
248            //Small a, circumflex accent
249            entities.put("acirc","\u00E2");
250            //Small a, tilde
251            entities.put("atilde","\u00E3");
252            //Small a, umlaut
253            entities.put("auml","\u00E4");
254            //Small a, ring
255            entities.put("aring","\u00E5");
256            //Small ae ligature
257            entities.put("aelig","\u00E6");
258            //Small c, cedilla
259            entities.put("ccedil","\u00E7");
260            //Small e, grave accent
261            entities.put("egrave","\u00E8");
262            //Small e, acute accent
263            entities.put("eacute","\u00E9");
264            //Small e, circumflex accent
265            entities.put("ecirc","\u00EA");
266            //Small e, umlaut
267            entities.put("euml","\u00EB");
268            //Small i, grave accent
269            entities.put("igrave","\u00EC");
270            //Small i, acute accent
271            entities.put("iacute","\u00ED");
272            //Small i, circumflex accent
273            entities.put("icirc","\u00EE");
274            //Small i, umlaut
275            entities.put("iuml","\u00EF");
276            //Small eth, Icelandic
277            entities.put("eth","\u00F0");
278            //Small n, tilde
279            entities.put("ntilde","\u00F1");
280            //Small o, grave accent
281            entities.put("ograve","\u00F2");
282            //Small o, acute accent
283            entities.put("oacute","\u00F3");
284            //Small o, circumflex accent
285            entities.put("ocirc","\u00F4");
286            //Small o, tilde
287            entities.put("otilde","\u00F5");
288            //Small o, umlaut
289            entities.put("ouml","\u00F6");
290            //Division sign
291            entities.put("divide","\u00F7");
292            //Small o, slash
293            entities.put("oslash","\u00F8");
294            //Small u, grave accent
295            entities.put("ugrave","\u00F9");
296            //Small u, acute accent
297            entities.put("uacute","\u00FA");
298            //Small u, circumflex accent
299            entities.put("ucirc","\u00FB");
300            //Small u, umlaut
301            entities.put("uuml","\u00FC");
302            //Small y, acute accent
303            entities.put("yacute","\u00FD");
304            //Small thorn, Icelandic
305            entities.put("thorn","\u00FE");
306            //Small y, umlaut
307            entities.put("yuml","\u00FF");
308         }
309         return entities;
310      }
311    
312    
313      /**
314       * This method convert the UNICODE value to ASCII
315       * For example  '\u0061' to 'a'
316       * @param str
317       * @return String
318       */
319    
320      public static String decode(String str)
321      {
322           StringBuffer ostr = new StringBuffer();
323           int i1=0;
324           int i2=0;
325    
326           while(i2<str.length())
327           {
328              i1 = str.indexOf("&",i2);
329              if (i1 == -1 ) {
330                   ostr.append(str.substring(i2, str.length()));
331                   break ;
332              }
333              ostr.append(str.substring(i2, i1));
334              i2 = str.indexOf(";", i1);
335              if (i2 == -1 ) {
336                   ostr.append(str.substring(i1, str.length()));
337                   break ;
338              }
339    
340              String tok = str.substring(i1+1, i2);
341              if (tok.charAt(0)=='#')
342              {
343                 tok=tok.substring(1);
344                 try {
345                      int radix = 10 ;
346                      if (tok.trim().charAt(0) == 'x') {
347                         radix = 16 ;
348                         tok = tok.substring(1,tok.length());
349                      }
350                      ostr.append((char) Integer.parseInt(tok, radix));
351                 } catch (NumberFormatException exp) {
352                      ostr.append('?');
353                 }
354              } else
355              {
356                 tok=(String)getEntities().get(tok);
357                 if (tok!=null)
358                    ostr.append(tok);
359                 else
360                    ostr.append('?');
361              }
362              i2++ ;
363           }
364           return ostr.toString();
365      }
366    
367      public static String decodeNew(String str){
368          StringBuffer sb = new StringBuffer();
369          int i =2,j=6;
370    //System.out.println("EncoderDecoder.decodeNew(str) ="+str);
371          while(i<=str.length()){
372            String ss= str.substring(i,j);
373             char c2 =(char) Integer.parseInt(ss,16);
374             i+=6;
375             j+=6;
376             sb.append(c2);
377          }
378          return sb.toString();
379        }
380    
381    
382    }