com.itextpdf.text.pdf.fonts.cmaps.CMapParser Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of itextpdf Show documentation
Show all versions of itextpdf Show documentation
iText, a free Java-PDF library
/**
* Copyright (c) 2005-2006, www.fontbox.org
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
* 3. Neither the name of fontbox; nor the names of its
* contributors may be used to endorse or promote products derived from this
* software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY
* DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
* ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* http://www.fontbox.org
*
*/
package com.itextpdf.text.pdf.fonts.cmaps;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.PushbackInputStream;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import com.itextpdf.text.error_messages.MessageLocalization;
/**
* This will parser a CMap stream.
*
* @author Ben Litchfield
* @version $Revision: 4645 $
* @since 2.1.4
*/
public class CMapParser
{
private static final String BEGIN_CODESPACE_RANGE = "begincodespacerange";
private static final String BEGIN_BASE_FONT_CHAR = "beginbfchar";
private static final String BEGIN_BASE_FONT_RANGE = "beginbfrange";
private static final String MARK_END_OF_DICTIONARY = ">>";
private static final String MARK_END_OF_ARRAY = "]";
private byte[] tokenParserByteBuffer = new byte[512];
/**
* Creates a new instance of CMapParser.
*/
public CMapParser()
{
}
/**
* This will parse the stream and create a cmap object.
*
* @param input The CMAP stream to parse.
* @return The parsed stream as a java object.
*
* @throws IOException If there is an error parsing the stream.
*/
@SuppressWarnings("unchecked")
public CMap parse( InputStream input ) throws IOException
{
PushbackInputStream cmapStream = new PushbackInputStream( input );
CMap result = new CMap();
Object token = null;
while( (token = parseNextToken( cmapStream )) != null )
{
if( token instanceof Operator )
{
Operator op = (Operator)token;
if( op.op.equals( BEGIN_CODESPACE_RANGE ) )
{
while (true)
{
Object nx = parseNextToken( cmapStream );
if (nx instanceof Operator && ((Operator)nx).op.equals("endcodespacerange"))
break;
byte[] startRange = (byte[])nx;
byte[] endRange = (byte[])parseNextToken( cmapStream );
CodespaceRange range = new CodespaceRange();
range.setStart( startRange );
range.setEnd( endRange );
result.addCodespaceRange( range );
}
}
else if( op.op.equals( BEGIN_BASE_FONT_CHAR ) )
{
while (true)
{
Object nx = parseNextToken( cmapStream );
if (nx instanceof Operator && ((Operator)nx).op.equals("endbfchar"))
break;
byte[] inputCode = (byte[])nx;
Object nextToken = parseNextToken( cmapStream );
if( nextToken instanceof byte[] )
{
byte[] bytes = (byte[])nextToken;
String value = createStringFromBytes( bytes );
result.addMapping( inputCode, value );
}
else if( nextToken instanceof LiteralName )
{
result.addMapping( inputCode, ((LiteralName)nextToken).name );
}
else
{
throw new IOException(MessageLocalization.getComposedMessage("error.parsing.cmap.beginbfchar.expected.cosstring.or.cosname.and.not.1", nextToken));
}
}
}
else if( op.op.equals( BEGIN_BASE_FONT_RANGE ) )
{
while (true)
{
Object nx = parseNextToken( cmapStream );
if (nx instanceof Operator && ((Operator)nx).op.equals("endbfrange"))
break;
byte[] startCode = (byte[])nx;
byte[] endCode = (byte[])parseNextToken( cmapStream );
Object nextToken = parseNextToken( cmapStream );
List array = null;
byte[] tokenBytes = null;
if( nextToken instanceof List )
{
array = (List)nextToken;
tokenBytes = array.get( 0 );
}
else
{
tokenBytes = (byte[])nextToken;
}
String value = null;
int arrayIndex = 0;
boolean done = false;
while( !done )
{
if( compare( startCode, endCode ) >= 0 )
{
done = true;
}
value = createStringFromBytes( tokenBytes );
result.addMapping( startCode, value );
increment( startCode );
if( array == null )
{
increment( tokenBytes );
}
else
{
arrayIndex++;
if( arrayIndex < array.size() )
{
tokenBytes = array.get( arrayIndex );
}
}
}
}
}
}
}
return result;
}
private Object parseNextToken( PushbackInputStream is ) throws IOException
{
Object retval = null;
int nextByte = is.read();
//skip whitespace
while( nextByte == 0x09 || nextByte == 0x20 || nextByte == 0x0D || nextByte == 0x0A )
{
nextByte = is.read();
}
switch( nextByte )
{
case '%':
{
//header operations, for now return the entire line
//may need to smarter in the future
StringBuffer buffer = new StringBuffer();
buffer.append( (char)nextByte );
readUntilEndOfLine( is, buffer );
retval = buffer.toString();
break;
}
case '(':
{
StringBuffer buffer = new StringBuffer();
int stringByte = is.read();
while( stringByte != -1 && stringByte != ')' )
{
buffer.append( (char)stringByte );
stringByte = is.read();
}
retval = buffer.toString();
break;
}
case '>':
{
int secondCloseBrace = is.read();
if( secondCloseBrace == '>' )
{
retval = MARK_END_OF_DICTIONARY;
}
else
{
throw new IOException(MessageLocalization.getComposedMessage("error.expected.the.end.of.a.dictionary"));
}
break;
}
case ']':
{
retval = MARK_END_OF_ARRAY;
break;
}
case '[':
{
List