Save This Page
Home » pdfbox-1.1.0-src » org.apache.pdfbox.encoding.conversion » [javadoc | source]
    1   /*
    2    * Licensed to the Apache Software Foundation (ASF) under one or more
    3    * contributor license agreements.  See the NOTICE file distributed with
    4    * this work for additional information regarding copyright ownership.
    5    * The ASF licenses this file to You under the Apache License, Version 2.0
    6    * (the "License"); you may not use this file except in compliance with
    7    * the License.  You may obtain a copy of the License at
    8    *
    9    *      http://www.apache.org/licenses/LICENSE-2.0
   10    *
   11    * Unless required by applicable law or agreed to in writing, software
   12    * distributed under the License is distributed on an "AS IS" BASIS,
   13    * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   14    * See the License for the specific language governing permissions and
   15    * limitations under the License.
   16    */
   17   package org.apache.pdfbox.encoding.conversion;
   18   
   19   import java.util.HashMap;
   20   
   21   /**
   22    * This class provides a mapping from char code to unicode mapping files used for CJK-encoding.
   23    * @author Andreas Lehmkühler
   24    * @version $Revision: 1.0 $
   25    *
   26    */
   27   
   28   public class CMapSubstitution 
   29   {
   30   
   31       private static HashMap<String,String> cmapSubstitutions = new HashMap<String,String>();
   32   
   33       private CMapSubstitution()
   34       {
   35       }
   36   
   37       static 
   38       {
   39           // I don't know if these mappings are complete. Perhaps there 
   40           // has to be added still one or more
   41   
   42           // chinese simplified
   43           cmapSubstitutions.put( "Adobe-GB1-4", "Adobe-GB1-UCS2" );
   44           cmapSubstitutions.put( "GBK-EUC-H", "GBK-EUC-UCS2" );
   45           cmapSubstitutions.put( "GBK-EUC-V", "GBK-EUC-UCS2" );
   46           cmapSubstitutions.put( "GBpc-EUC-H", "GBpc-EUC-UCS2C" );
   47           cmapSubstitutions.put( "GBpc-EUC-V", "GBpc-EUC-UCS2C" );
   48   
   49           // chinese traditional
   50           cmapSubstitutions.put( "Adobe-CNS1-4", "Adobe-CNS1-UCS2" );
   51           cmapSubstitutions.put( "B5pc-H", "B5pc-UCS2" );
   52           cmapSubstitutions.put( "B5pc-V", "B5pc-UCS2" );
   53           cmapSubstitutions.put( "ETen-B5-H", "ETen-B5-UCS2" );
   54           cmapSubstitutions.put( "ETen-B5-V", "ETen-B5-UCS2" );
   55           cmapSubstitutions.put( "ETenms-B5-H", "ETen-B5-UCS2" );
   56           cmapSubstitutions.put( "ETenms-B5-V", "ETen-B5-UCS2" );
   57   
   58           // japanese
   59           cmapSubstitutions.put( "90ms-RKSJ-H", "90ms-RKSJ-UCS2" );
   60           cmapSubstitutions.put( "90ms-RKSJ-V", "90ms-RKSJ-UCS2" );
   61           cmapSubstitutions.put( "90msp-RKSJ-H", "90ms-RKSJ-UCS2" );
   62           cmapSubstitutions.put( "90msp-RKSJ-V", "90ms-RKSJ-UCS2" );
   63           cmapSubstitutions.put( "90pv-RKSJ-H", "90pv-RKSJ-UCS2");
   64           cmapSubstitutions.put( "UniJIS-UCS2-HW-H", "UniJIS-UCS2-H" );
   65           cmapSubstitutions.put( "Adobe-Japan1-4", "Adobe-Japan1-UCS2");
   66   
   67       }
   68   
   69       /**
   70        * 
   71        * @param cmapName The name of a cmap for which we have to find a possible substitution
   72        * @return the substitution for the given cmap name
   73        */
   74       public static String substituteCMap(String cmapName) 
   75       {
   76           if (cmapSubstitutions.containsKey(cmapName))
   77           {
   78               return (String)cmapSubstitutions.get(cmapName);
   79           }
   80           return cmapName;
   81       }
   82   }

Save This Page
Home » pdfbox-1.1.0-src » org.apache.pdfbox.encoding.conversion » [javadoc | source]