version 1.56, 2004/06/10 13:19:18
|
version 1.57, 2004/06/14 12:12:31
|
Line 12
|
Line 12
|
* rogo |
* rogo |
*/ |
*/ |
|
|
import java.util.*; |
|
import java.sql.*; |
|
import java.awt.Cursor; |
import java.awt.Cursor; |
import java.io.BufferedReader; |
import java.io.BufferedReader; |
import java.io.BufferedWriter; |
import java.io.BufferedWriter; |
Line 25 import java.io.InputStreamReader;
|
Line 23 import java.io.InputStreamReader;
|
import java.io.OutputStreamWriter; |
import java.io.OutputStreamWriter; |
import java.io.PrintStream; |
import java.io.PrintStream; |
import java.io.UnsupportedEncodingException; |
import java.io.UnsupportedEncodingException; |
|
import java.sql.PreparedStatement; |
|
import java.sql.SQLException; |
|
import java.sql.Statement; |
|
import java.sql.Types; |
|
import java.util.ArrayList; |
|
import java.util.Iterator; |
|
import java.util.List; |
|
import java.util.StringTokenizer; |
|
import java.util.TreeSet; |
|
import java.util.Vector; |
|
|
import com.exploringxml.xml.Node; |
import com.exploringxml.xml.Node; |
import com.exploringxml.xml.Xparse; |
import com.exploringxml.xml.Xparse; |
Line 1885 class Convert
|
Line 1893 class Convert
|
StringBuffer buf = new StringBuffer(); |
StringBuffer buf = new StringBuffer(); |
for (int i = 0; i < inp.length(); i++) { |
for (int i = 0; i < inp.length(); i++) { |
char c = inp.charAt(i); |
char c = inp.charAt(i); |
|
// System.out.println("char "+c+" "+(int)c); |
|
switch (c) { |
|
case 1: buf.append("\u00d0"); break; // Eth |
|
case 2: buf.append("\u00f0"); break; // eth |
|
case 3: buf.append("\u0141"); break; // Lslash |
|
case 4: buf.append("\u0142"); break; // lslash |
|
case 5: buf.append("\u0160"); break; // S caron |
|
case 6: buf.append("\u0161"); break; // s caron |
|
case 7: buf.append("\u00dd"); break; // Y acute |
|
case 8: buf.append("\u00fd"); break; // y acute |
|
case 11: buf.append("\u00de"); break; // Thorn |
|
case 12: buf.append("\u00fe"); break; // thorn |
|
case 14: buf.append("\u017d"); break; // Z caron |
|
case 15: buf.append("\u017e"); break; // z caron |
|
case 17: buf.append("\u0073"); break; // asciitilde |
|
case 18: buf.append("j\u0305"); break; // j macron [does a single char exist?] |
|
case 19: buf.append("^"); break; // circumflex |
|
case 20: buf.append("\u0303"); break; // tilde |
|
case 21: buf.append("\u00bd"); break; // onehalf |
|
case 22: buf.append("\u00bc"); break; // onequarter |
|
case 23: buf.append("\u00b9"); break; // onesuperior |
|
case 24: buf.append("\u00be"); break; // threequarters |
|
case 25: buf.append("\u00b3"); break; // threesuperior |
|
case 26: buf.append("\u00b2"); break; // twosuperior |
|
case 27: buf.append("\u00a6"); break; // brokenbar |
|
case 28: buf.append("-"); break; // minus |
|
case 29: buf.append("\u00d7"); break; // multiply |
|
case 39: buf.append("'"); break; // quotesingle |
|
case 94: buf.append("\u0302"); break; // circumflex |
|
case 96: buf.append("\u0300"); break; // grave |
|
case 196: buf.append("\u00c4"); break; // A dieresis |
|
case 197: buf.append("\u00c5"); break; // A ring |
|
case 201: buf.append("\u00c9"); break; // E acute |
|
case 209: buf.append("\u00d1"); break; // N tilde |
|
case 214: buf.append("\u00d6"); break; // O dieresis |
|
case 220: buf.append("\u00dc"); break; // U dieresis |
|
case 225: buf.append("\u00e1"); break; // a acute |
|
case 224: buf.append("\u00e0"); break; // a grave |
|
case 226: buf.append("\u00e2"); break; // a circumflex |
|
case 228: buf.append("\u00e4"); break; // a dieresis |
|
case 227: buf.append("\u00e3"); break; // a tilde |
|
case 229: buf.append("\u0101"); break; // a macron |
|
case 231: buf.append("\u00e7"); break; // c cedilla |
|
case 233: buf.append("\u00e9"); break; // e acute |
|
case 232: buf.append("\u00e8"); break; // e grave |
|
case 234: buf.append("\u00ea"); break; // e circumflex |
|
case 235: buf.append("\u00eb"); break; // e dieresis |
|
case 237: buf.append("\u00ed"); break; // i acute |
|
case 236: buf.append("\u00ec"); break; // i grave |
|
case 238: buf.append("\u00ee"); break; // i circumflex |
|
case 239: buf.append("\u00ef"); break; // i dieresis |
|
case 241: buf.append("\u00f1"); break; // n tilde |
|
case 243: buf.append("\u00f3"); break; // o acute |
|
case 242: buf.append("\u00f2"); break; // o grave |
|
case 244: buf.append("\u00f4"); break; // o circumflex |
|
case 246: buf.append("\u00f6"); break; // o dieresis |
|
case 245: buf.append("\u00f5"); break; // o tilde |
|
case 250: buf.append("\u00fa"); break; // u acute |
|
case 249: buf.append("\u00f9"); break; // u grave |
|
case 251: buf.append("\u00fb"); break; // u circumflex |
|
case 252: buf.append("\u00fc"); break; // u dieresis |
|
case 8224: buf.append("\u1e6d"); break; // t underdot |
|
case 176: buf.append("\u00b0"); break; // degree |
|
case 162: buf.append("\u1ebd"); break; // e tilde |
|
case 163: buf.append("\u00a3"); break; // sterling |
|
case 167: buf.append("\u00a7"); break; // section |
|
case 182: buf.append("\u00b6"); break; // paragraph |
|
case 223: buf.append("\u015b"); break; // s acute |
|
case 174: buf.append("\u1e5b"); break; // r underdot |
|
case 169: buf.append("\u1e45"); break; // n overdot |
|
case 353: buf.append("\u1e45"); break; // n overdot |
|
case 180: buf.append("\u0301"); break; // acute |
|
case 168: buf.append("\u0308"); break; // dieresis |
|
case 8800: buf.append("\u1e6d"); break; // t underdot |
|
case 198: buf.append("\u00c6"); break; // AE |
|
case 216: buf.append("\u014d"); break; // o macron |
|
case 8734: buf.append("\u0129"); break; // i tilde |
|
case 177: buf.append("\u00b1"); break; // plusminus |
|
case 165: buf.append("\u012b"); break; // i macron |
|
case 181: buf.append("\u1e43"); break; // m underdot |
|
case 8706: buf.append("\u1e0d"); break; // d underdot |
|
case 240: buf.append("\u1e0d"); break; // d underdot |
|
|
|
case 8721: buf.append("\u1e63"); break; // s underdot |
|
case 960: buf.append("\u017a"); break; // z acute |
|
case 8747: buf.append("\u1e45"); break; // n overdot |
|
case 937: buf.append("\u0169"); break; // u tilde |
|
case 230: buf.append("\u00e6"); break; // ae |
|
case 248: buf.append("\u00f8"); break; // oslash |
|
case 191: buf.append("\u0304\u0306"); break; // macron breve |
|
case 172: buf.append("\u1e37"); break; // |
|
case 8730: buf.append("j\u0305"); break; // j macron [does a single char exist?] |
|
case 402: buf.append("\u0103"); break; // a breve |
|
case 8776: buf.append("\u016d"); break; // u breve |
|
case 187: buf.append("\u1e42"); break; // M underdot |
|
case 8230: buf.append("\u2026"); break; // ellipsis |
|
case 192: buf.append("\u00c0"); break; // A grave |
|
case 195: buf.append("\u00c3"); break; // A tilde |
|
case 213: buf.append("\u00d5"); break; // O tilde |
|
case 338: buf.append("m\u0306"); break; // m breve |
|
case 339: buf.append("\u0153"); break; // oe |
|
case 8211: buf.append("\u2013"); break; // endash |
|
case 8212: buf.append("\u2014"); break; // emdash |
|
case 8220: buf.append("\u201c"); break; // quotedblleft |
|
case 8221: buf.append("\u201d"); break; // quotedblright |
|
case 8216: buf.append("\u2018"); break; // quoteleft |
|
case 8217: buf.append("\u2019"); break; // quoteright |
|
case 247: buf.append("\u1e37"); break; // l underring [actually underdot] |
|
case 9674: buf.append("\u1e41"); break; // m overdot |
|
case 255: buf.append("n\u0306"); break; // n breve |
|
case 376: buf.append("\u00d7"); break; // multiply |
|
case 8364: buf.append("\u1e5b"); break; // r underring [actually underdot] |
|
case 8249: buf.append("\u1e44"); break; // N overdot |
|
case 8250: buf.append("\u1e62"); break; // S underdot |
|
case 64257: buf.append("\u1e24"); break; // H underdot |
|
case 64258: buf.append("\u1e0c"); break; // D underdot |
|
case 8225: buf.append("\u2021"); break; // daggerdbl |
|
case 8218: buf.append("\u1e36"); break; // L underdot |
|
case 8222: buf.append("\u0113"); break; // e macron |
|
case 194: buf.append("\u1e5f"); break; // r underbar |
|
case 202: buf.append("r\u0324"); break; // r underdieresis |
|
case 193: buf.append("\u012a"); break; // I macron |
|
case 8486: |
|
case 203: buf.append("\u016b"); break; // u macron |
|
case 200: buf.append("\u1e6c"); break; // T underdot |
|
case 205: buf.append("\u1e64"); break; // S acute |
|
case 206: buf.append("\u2020"); break; // dagger |
|
case 207: buf.append("\u0115"); break; // e breve |
|
case 204: buf.append("\u014f"); break; // o breve |
|
case 211: buf.append("\u0100"); break; // A macron |
|
case 212: buf.append("\u1e46"); break; // N underdot |
|
case 210: buf.append("\u1e3b"); break; // l underbar |
|
case 218: buf.append("\u016a"); break; // U macron |
|
case 219: buf.append("\u0179"); break; // Z acute |
|
case 217: buf.append("\u1e5a"); break; // R underdot |
|
case 305: buf.append("\u0131"); break; // dotlessi |
|
case 710: buf.append("\u1e47"); break; // n underdot |
|
case 732: buf.append("\u1e49"); break; // n underbar |
|
case 175: buf.append("\u0304"); break; // macron |
|
case 728: buf.append("\u0306"); break; // breve |
|
case 729:case 215: buf.append("\u1e25"); break; // h underdot |
|
case 730: buf.append("\u012d"); break; // i breve |
|
case 184: buf.append("\u0327"); break; // cedilla |
|
case 733: buf.append("\u030b"); break; // hungarumlaut |
|
case 731: buf.append("\u0328"); break; // ogonek |
|
case 711: buf.append("\u030c"); break; // caron |
|
case 199: buf.append("\u012b\u0303"); break; // imacron tilde |
|
case 8226: buf.append("\u1e5d"); break; // runderdot macron |
|
case 8482: buf.append("\u016b\0306"); break; // umacron breve |
|
case 8804: buf.append("\u0101\u0301"); break; // amacron acute |
|
case 8805: buf.append("\u016b\u0301"); break; // umacron acute |
|
case 8719: buf.append("\u0113\u0301"); break; // emacron acute |
|
case 170: buf.append("\u0113\u0300"); break; // emacron breve |
|
case 186: buf.append("\u014d\u0300"); break; // omacron breve |
|
case 161: buf.append("\u0101\u0306"); break; // amacron breve |
|
case 8710: buf.append("\u0101\u0303"); break; // amacron tilde |
|
case 171: buf.append("\u012b\u0301"); break; // imacron acute |
|
case 8260: buf.append("\u1e00"); break; // runderdotmacron acute |
|
case 183: buf.append("\u1e5b\u0301"); break; // runderdot acute |
|
case 8240: buf.append("\u012b\u0306"); break; // imacron breve |
|
case 63743: buf.append("\u016b\u0303"); break; // umacron tilde |
|
default: buf.append(c); |
|
if((int)c>127) |
|
System.out.println("char "+c+" "+(int)c); |
|
break; |
|
} |
|
} |
|
return buf.toString(); |
|
} |
|
|
|
static public String normanToUnicodeOld(String inp) { |
|
StringBuffer buf = new StringBuffer(); |
|
for (int i = 0; i < inp.length(); i++) { |
|
char c = inp.charAt(i); |
switch (c) { |
switch (c) { |
case 1: buf.append("\u00d0"); break; // Eth |
case 1: buf.append("\u00d0"); break; // Eth |
case 2: buf.append("\u00f0"); break; // eth |
case 2: buf.append("\u00f0"); break; // eth |
Line 2046 class Convert
|
Line 2228 class Convert
|
} |
} |
return buf.toString(); |
return buf.toString(); |
} |
} |
|
|
} |
} |
|
|