--- FM2SQL/Attic/Convert.java	2004/06/10 13:19:18	1.56
+++ FM2SQL/Attic/Convert.java	2004/07/12 10:15:13	1.61
@@ -12,8 +12,6 @@
  * rogo  
  */
 
-import java.util.*;
-import java.sql.*;
 import java.awt.Cursor;
 import java.io.BufferedReader;
 import java.io.BufferedWriter;
@@ -21,10 +19,23 @@ import java.io.File;
 import java.io.FileInputStream;
 import java.io.FileNotFoundException;
 import java.io.FileOutputStream;
+import java.io.InputStream;
 import java.io.InputStreamReader;
 import java.io.OutputStreamWriter;
 import java.io.PrintStream;
 import java.io.UnsupportedEncodingException;
+import java.net.URL;
+import java.net.URLConnection;
+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.Xparse;
@@ -57,8 +68,6 @@ class Convert
       System.out.println("Usage: java Convert <xml config file>");
       System.exit(-1);
     }
-    if (!(new File(args[0]).exists()))
-      System.exit(0);
     try
     {
       file = new FileOutputStream("./log.txt");
@@ -67,9 +76,13 @@ class Convert
       e1.printStackTrace();
     }
     PrintStream stream = new PrintStream(file);
-    System.setOut(stream);
-    System.setErr(stream);
+   // System.setOut(stream);
+    //System.setErr(stream);
+
     readXMLFile(args[0]);
+    if (!(new File(args[0]).exists()))
+      System.exit(0);
+
     System.out.println("Finished!");
     //convert("jdbc:fmpro:http://141.14.237.74:8050","jdbc:postgresql://erebos/test",null,null);
   }
@@ -1210,6 +1223,8 @@ class Convert
         Node node3 = root.find("convert/source/database", new int[] { 1, 1, i });
         Node nodeMode = root.find("convert/source/database/mode", new int[] { 1, 1, i, 1, 1 });
         Node delimiterNode = root.find("convert/source/database/delimiter", new int[] { 1, 1, i, 1, 1 });
+        Node useNormanToUnicodeMapper = root.find("convert/source/database/usenormantounicodemapper", new int[] { 1, 1, i, 1, 1 });
+    
         if (node3 == null)
           throw new Error("parse error database tag missing");
         if (node == null)
@@ -1220,6 +1235,12 @@ class Convert
           throw new Error("parse error password tag missing");
         if (delimiterNode != null)
           delimiter = delimiterNode.getCharacters();
+        if(useNormanToUnicodeMapper!=null)
+        {
+          database.setUseNormanToUnicodeMapper(Boolean.valueOf(useNormanToUnicodeMapper.getCharacters()).booleanValue());
+          System.out.println("useMapper "+Boolean.valueOf(useNormanToUnicodeMapper.getCharacters().trim()).booleanValue());
+        } 
+   
         String url = node.getCharacters();
         String user = node1.getCharacters();
         String password = node2.getCharacters();
@@ -1383,9 +1404,16 @@ class Convert
         Node node3 = root.find("convert/source/database", new int[] { 1, 1, i });
         Node nodeMode = root.find("convert/source/database/mode", new int[] { 1, 1, i, 1, 1 });
         Node delimiterNode = root.find("convert/source/database/delimiter", new int[] { 1, 1, i, 1, 1 });
+        Node useNormanToUnicodeMapper = root.find("convert/source/database/usenormantounicodemapper", new int[] { 1, 1, i, 1, 1 });
 
         if (delimiterNode != null)
           delimiter = delimiterNode.getCharacters();
+        if(useNormanToUnicodeMapper!=null)
+        {
+          database.setUseNormanToUnicodeMapper(Boolean.valueOf(useNormanToUnicodeMapper.getCharacters()).booleanValue());
+          System.out.println("useMapper "+Boolean.valueOf(useNormanToUnicodeMapper.getCharacters().trim()).booleanValue());
+        } 
+
         if (node3 == null)
           throw new Error("parse error database tag missing");
         if (node == null)
@@ -1540,9 +1568,17 @@ class Convert
   {
     try
     {
-      // read XML Metadata from a file
-      FileInputStream fi = new FileInputStream(xmlFile);
-      InputStreamReader isr = new InputStreamReader(fi, "UTF-8");
+      InputStream stream = null;
+      
+      if(xmlFile.indexOf("file://")>=0||xmlFile.indexOf("http://")>=0)
+      {
+        URL url=new URL(xmlFile);
+        stream = url.openStream();
+      }
+      else 
+     // read XML Metadata from a file
+       stream = new FileInputStream(xmlFile);
+      InputStreamReader isr = new InputStreamReader(stream, "UTF-8");
       BufferedReader buffr = new BufferedReader(isr);
       StringBuffer sb = new StringBuffer();
       int c = 0;
@@ -1574,6 +1610,8 @@ class Convert
     Vector tables;
     Vector ids;
     String delimiter = "//";
+    boolean useNormanToUnicodeMapper = false;
+    
     final static int CONVERT_MODE = 1;
     final static int APPEND_MODE = 2;
     final static int UPDATE_MODE = 3;
@@ -1616,6 +1654,8 @@ class Convert
         modeString = "delete";
 
       buffr.write("      <mode>" + modeString + "</mode>\n");
+      buffr.write("      <usenormantounicodemapper>" + useNormanToUnicodeMapper + "</usenormantounicodemapper>\n");
+      
       int index = 0;
       while (index < tables.size())
       {
@@ -1876,6 +1916,230 @@ class Convert
     }
   } // to method
   
+  
+  /**
+   * synchronize method based on delete method code
+   * 
+   * @param source
+   * @param destination
+   * @param names
+   * @param layouts
+   * @param selects
+   * @param creates
+   * @param ids
+   * @param mode
+   * @throws Exception
+   */
+  // TODO implement append,update and delete in one method
+  // TODO using id based algorithm
+  public static void synchronize(String source, String destination, Vector names, Vector layouts, Vector selects, Vector creates, Vector ids, int mode) throws Exception
+  {
+    FM2SQL.ProgressDialog dialog = null;
+    if (FM2SQL.fmInstance != null)
+    {
+      dialog = new FM2SQL.ProgressDialog(FM2SQL.fmInstance, bean);
+      dialog.setTitle("Synchronize running ...");
+      dialog.title.setText("Getting table data ...");
+      dialog.setLocation(FM2SQL.fmInstance.getLocationOnScreen().x + (FM2SQL.fmInstance.getWidth() - 400) / 2, FM2SQL.fmInstance.getLocationOnScreen().y + (FM2SQL.fmInstance.getHeight() - 250) / 2);
+      dialog.setCursor(Cursor.getPredefinedCursor(Cursor.WAIT_CURSOR));
+      FM2SQL.fmInstance.setCursor(Cursor.getPredefinedCursor(Cursor.WAIT_CURSOR));
+      dialog.thread = Thread.currentThread();
+    }
+    // setting user and passwd 
+    bean.setUserAndPasswd(user, passwd);
+    // setting user and passwd 
+    beanDest.setUserAndPasswd(userDest, passwdDest);
+    if (dialog != null)
+      dialog.setSize(400, 250);
+    StringBuffer command = null;
+    String query = null;
+    try
+    {
+      //bean.setConnection("jdbc:fmpro:http://141.14.237.74:8050");    
+      //bean.setConnection("jdbc:postgresql://erebos/test","postgres","rogo");
+      bean.setConnection(source);
+      if (names == null)
+        names = bean.getTableNames();
+      // Collections.sort(names);
+      int tbIndex = 1;
+
+      // System.out.println("Start at "+names.indexOf("archimedes_facsimiles"));
+      for (tbIndex = 0; tbIndex < names.size(); ++tbIndex)
+      {
+        Vector[] result = null;
+        java.util.TreeSet myIds = new TreeSet();
+        java.util.TreeSet myIdsDest = new TreeSet();
+        int deltaID = 1;
+        String idField = "";
+        String destTableName = "";
+
+        try
+        {
+          query = "select * from " + bean.getQC() + names.get(tbIndex).toString() + bean.getQC();
+          String layout = (layouts.isEmpty()) ? "" : layouts.get(tbIndex).toString();
+          query = (selects != null) ? selects.get(tbIndex).toString() : query;
+          //if  vectors[1].get(i) != null)
+          if (layout != "")
+          {
+            layout = " layout " + bean.getQC() + layout + bean.getQC();
+            String name = names.get(tbIndex).toString();
+            StringBuffer queryLayout = new StringBuffer(query);
+            queryLayout.insert(queryLayout.indexOf(name) + name.length() + 1, " " + layout);
+            query = queryLayout.toString();
+            System.out.println("added layout  " + query);
+
+          }
+          dialog.title.setText("Getting table data ...");
+          dialog.table.setText(names.get(tbIndex).toString());
+          dialog.status.setText("Table " + (tbIndex + 1) + " of " + names.size());
+          dialog.show();
+          bean.getConnection();
+          bean.makeQuery(query, 50);
+          idField = ids.get(tbIndex).toString();
+
+        } catch (Exception e)
+        {
+          continue;
+        }
+        // determine destTableName from createStatement or from source table name
+        if (!creates.get(tbIndex).equals(""))
+        {
+          String create = creates.get(tbIndex).toString().toLowerCase();
+          int fromIndex = create.indexOf("table") + 5;
+          int toIndex = create.indexOf("(");
+          destTableName = create.substring(fromIndex, toIndex).replaceAll(beanDest.getQC(), "").trim();
+          System.out.println("destTable " + destTableName);
+
+        } else
+          destTableName = convertText(names.get(tbIndex).toString());
+
+        // for id kram
+        Vector vec = null;
+        Vector vecDest = null;
+        //      tempo
+        beanDest.setConnection(destination);
+        int rowCount = (idField != "") ? myIds.size() : bean.getRowCount(query);
+        String tempID = bean.getQC() + idField + bean.getQC();
+        String tempIDdest = beanDest.getQC() + convertText(idField) + beanDest.getQC();
+
+        int endIndex = -1;
+        String tempQuery = query;
+        String destQuery = query.replaceAll(names.get(tbIndex).toString(), destTableName);
+        String tempQueryDest = destQuery;
+        // remove extra query parts destQuery.substring(0,destQuery.lastIndexOf(destTableName)+destTableName.length()+1);
+        System.out.println("new Query " + tempQueryDest);
+        if (!idField.equals(""))
+        {
+          long startTime = System.currentTimeMillis();
+          int counter = -1;
+          while (true)
+          {
+            ++counter;
+            if (counter == 0 && dialog != null)
+              dialog.title.setText("Check if data  is available");
+            else if (dialog != null)
+              dialog.title.setText("Check if more  data  is available");
+            myIds = bean.getIDVector(ids.get(tbIndex).toString(), (String) names.get(tbIndex), tempQuery, numHits);
+            myIdsDest = beanDest.getIDVector(convertText(idField), destTableName, tempQueryDest, numHits);
+            if (myIds.isEmpty())
+              break;
+            vec = new Vector(myIds);
+            vecDest = new Vector(myIdsDest);
+            rowCount = vec.size();
+            // Deletion will work this way
+            Vector deleted = new Vector(vec);
+            Vector linesToDelete = new Vector(vecDest);
+            
+            Vector linesToAppend = new Vector(vec);
+            // remove all lines that are already in dest database
+            linesToAppend.removeAll(vecDest);
+            // remove all lines that should not be deleted
+            linesToDelete.removeAll(deleted);
+            // System.out.println("ID LIST SIZE " + Math.round((double) myIds.size() / (double) numIntervalls) + " " + myIdsDest.size());
+            /// @TODO complete delete task remove query show lines to be deleted let user choose if he wants that
+            System.out.println("number of lines to  be deleted " + linesToDelete.size());
+            deltaID = (int) Math.round((double) myIds.size() / (double) numIntervalls);
+            beanDest.setConnection(destination);
+
+            Statement stm = beanDest.getConnection().createStatement();
+
+            Vector tables = beanDest.getTableNames();
+            // Collections.sort(tables);
+            System.out.println(names.get(tbIndex) + " " + tables.indexOf(convertText((String) names.get(tbIndex)))); // "//beanDest.getTypeNames()); 
+            tables = beanDest.getTableNames();
+            // System.out.println(beanDest.getTableNames(beanDest.getCatalogs().get(2).toString()));
+            stm = beanDest.getConnection().createStatement();
+
+            if (dialog != null)
+              dialog.title.setText(" Deleting table data ...");
+
+            int j = -1;
+
+            Vector row = null;
+            command = new StringBuffer();
+
+            command.append("DELETE FROM");
+            command.append(beanDest.getQC());
+            command.append(destTableName);
+            //command.append(convertText((String) names.get(tbIndex)));
+            command.append(beanDest.getQC());
+            int size = bean.getColumnNames().size();
+            command.append("WHERE " + convertText(ids.get(tbIndex).toString()) + " =  ?");
+            PreparedStatement pstm = beanDest.getConnection().prepareStatement(command.toString());
+            System.out.println(command + " " + tbIndex);
+            //int rowCount = bean.getRowCount(query);
+            //        int idIndex = bean.getColumnNames().indexOf(ids.get(tbIndex));
+            while (true)
+            {
+
+              ++j;
+              if (j == linesToDelete.size())
+                break;
+              //print rows
+              pstm.setString(1, linesToDelete.get(j).toString());
+              System.out.println(pstm.toString());
+              pstm.execute();
+              if (dialog != null)
+                dialog.progress.setValue((int) (((double) (j + 1) / (double) rowCount) * 100.0));
+              command = null;
+            }
+            // prepare new query for next chunk
+            if (query.indexOf("where") > 0)
+              tempQuery = query + " and " + tempID + ">'" + vec.lastElement() + "'";
+            else
+              tempQuery = query + " where " + tempID + ">'" + vec.lastElement() + "'";
+
+          } //to outer while
+        } // to idfield if  
+      } // table loop
+
+    } catch (Exception e)
+    {
+      System.out.println("Error while connecting to database " + e);
+      if (dialog != null)
+      {
+        dialog.setVisible(false);
+        dialog.setCursor(Cursor.getPredefinedCursor(Cursor.DEFAULT_CURSOR));
+        FM2SQL.fmInstance.setCursor(Cursor.getPredefinedCursor(Cursor.DEFAULT_CURSOR));
+      }
+      java.io.ByteArrayOutputStream b = new java.io.ByteArrayOutputStream();
+      java.io.PrintStream stream = new java.io.PrintStream(b);
+      stream.print(command + "\n\n");
+      e.printStackTrace(stream);
+      FM2SQL.showErrorDialog(b.toString(), "Error occured !");
+
+    }
+    if (dialog != null)
+    {
+      dialog.setCursor(Cursor.getPredefinedCursor(Cursor.DEFAULT_CURSOR));
+      FM2SQL.fmInstance.setCursor(Cursor.getPredefinedCursor(Cursor.DEFAULT_CURSOR));
+
+      dialog.setVisible(false);
+    }
+  } // to method
+  
+
+ 
   /**
    * Converts input String in norman encoding to unicode 
    * @param inp
@@ -1885,6 +2149,180 @@ class Convert
     StringBuffer buf = new StringBuffer();
     for (int i = 0; i < inp.length(); 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) {
       case 1: buf.append("\u00d0"); break; // Eth
       case 2: buf.append("\u00f0"); break; // eth
@@ -2046,5 +2484,171 @@ class Convert
     }
     return buf.toString();
   }
+  static public String normanToUnicodeNew(String inp) {
+    StringBuffer buf = new StringBuffer();
+    for (int i = 0; i < inp.length(); i++) {
+      char c = inp.charAt(i);
+      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 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 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 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: 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); break;
+      }
+    }
+    return buf.toString();
+  }
+
 
 }
\ No newline at end of file