byteencoding.php

Bug tracker, and reporter.

<?php
/**
 * Zend Framework
 *
 * LICENSE
 *
 * This source file is subject to the new BSD license that is bundled
 * with this package in the file LICENSE.txt.
 * It is also available through the world-wide-web at this URL:
 * http://framework.zend.com/license/new-bsd
 * If you did not receive a copy of the license and are unable to
 * obtain it through the world-wide-web, please send an email
 * to [e-mail] so we can send you a copy immediately.
 *
 * @package    Zend_Pdf
 * @subpackage Fonts
 * @copyright  Copyright (c) 2005-2008 Zend Technologies USA Inc. (http://www.zend.com)
 * @license    http://framework.zend.com/license/new-bsd     New BSD License
 */

/** Zend_Pdf_Cmap */
require_once 'Zend/Pdf/Cmap.php';


/**
 * Implements the "byte encoding" character map (type 0).
 *
 * This is the (legacy) Apple standard encoding mechanism and provides coverage
 * for characters in the Mac Roman character set only. Consequently, this cmap
 * type should be used only as a last resort.
 *
 * The mapping from Mac Roman to Unicode can be found at
 * {@link http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/ROMAN.TXT}.
 *
 * @package    Zend_Pdf
 * @subpackage Fonts
 * @copyright  Copyright (c) 2005-2008 Zend Technologies USA Inc. (http://www.zend.com)
 * @license    http://framework.zend.com/license/new-bsd     New BSD License
 */
class Zend_Pdf_Cmap_ByteEncoding extends Zend_Pdf_Cmap
{
  /**** Instance Variables ****/


    /**
     * Glyph index array. Stores the actual glyph numbers. The array keys are
     * the translated Unicode code points.
     * @var array
     */
    protected $_glyphIndexArray = array();



  /**** Public Interface ****/


  /* Concrete Class Implementation */

    /**
     * Returns an array of glyph numbers corresponding to the Unicode characters.
     *
     * If a particular character doesn't exist in this font, the special 'missing
     * character glyph' will be substituted.
     *
     * See also {@link glyphNumberForCharacter()}.
     *
     * @param array $characterCodes Array of Unicode character codes (code points).
     * @return array Array of glyph numbers.
     */
    public function glyphNumbersForCharacters($characterCodes)
    {
        $glyphNumbers = array();
        foreach ($characterCodes as $key => $characterCode) {

           if (! isset($this->_glyphIndexArray[$characterCode])) {
                $glyphNumbers[$key] = Zend_Pdf_Cmap::MISSING_CHARACTER_GLYPH;
                continue;
            }

            $glyphNumbers[$key] = $this->_glyphIndexArray[$characterCode];

        }
        return $glyphNumbers;
    }

    /**
     * Returns the glyph number corresponding to the Unicode character.
     *
     * If a particular character doesn't exist in this font, the special 'missing
     * character glyph' will be substituted.
     *
     * See also {@link glyphNumbersForCharacters()} which is optimized for bulk
     * operations.
     *
     * @param integer $characterCode Unicode character code (code point).
     * @return integer Glyph number.
     */
    public function glyphNumberForCharacter($characterCode)
    {
        if (! isset($this->_glyphIndexArray[$characterCode])) {
            return Zend_Pdf_Cmap::MISSING_CHARACTER_GLYPH;
        }
        return $this->_glyphIndexArray[$characterCode];
    }

    /**
     * Returns an array containing the Unicode characters that have entries in
     * this character map.
     *
     * @return array Unicode character codes.
     */
    public function getCoveredCharacters()
    {
        return array_keys($this->_glyphIndexArray);
    }

    /**
     * Returns an array containing the glyphs numbers that have entries in this character map.
     * Keys are Unicode character codes (integers)
     * 
     * This functionality is partially covered by glyphNumbersForCharacters(getCoveredCharacters())
     * call, but this method do it in more effective way (prepare complete list instead of searching 
     * glyph for each character code).
     *
     * @internal
     * @return array Array representing <Unicode character code> => <glyph number> pairs.
     */
    public function getCoveredCharactersGlyphs()
    {
    	return $this->_glyphIndexArray;
    }


  /* Object Lifecycle */

    /**
     * Object constructor
     *
     * Parses the raw binary table data. Throws an exception if the table is
     * malformed.
     *
     * @param string $cmapData Raw binary cmap table data.
     * @throws Zend_Pdf_Exception
     */
    public function __construct($cmapData)
    {
        /* Sanity check: This table must be exactly 262 bytes long.
         */
        $actualLength = strlen($cmapData);
        if ($actualLength != 262) {
            throw new Zend_Pdf_Exception('Insufficient table data',
                                         Zend_Pdf_Exception::CMAP_TABLE_DATA_TOO_SMALL);
        }

        /* Sanity check: Make sure this is right data for this table type.
         */
        $type = $this->_extractUInt2($cmapData, 0);
        if ($type != Zend_Pdf_Cmap::TYPE_BYTE_ENCODING) {
            throw new Zend_Pdf_Exception('Wrong cmap table type',
                                         Zend_Pdf_Exception::CMAP_WRONG_TABLE_TYPE);
        }

        $length = $this->_extractUInt2($cmapData, 2);
        if ($length != $actualLength) {
            throw new Zend_Pdf_Exception("Table length ($length) does not match actual length ($actualLength)",
                                         Zend_Pdf_Exception::CMAP_WRONG_TABLE_LENGTH);
        }

        /* Mapping tables should be language-independent. The font may not work
         * as expected if they are not. Unfortunately, many font files in the
         * wild incorrectly record a language ID in this field, so we can't
         * call this a failure.
         */
        $language = $this->_extractUInt2($cmapData, 4);
        if ($language != 0) {
            // Record a warning here somehow?
        }

        /* The mapping between the Mac Roman and Unicode characters is static.
         * For simplicity, just put all 256 glyph indices into one array keyed
         * off the corresponding Unicode character.
         */
        $i = 6;
        $this->_glyphIndexArray[0x00]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x01]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x02]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x03]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x04]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x05]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x06]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x07]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x08]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x09]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x0a]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x0b]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x0c]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x0d]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x0e]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x0f]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x10]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x11]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x12]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x13]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x14]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x15]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x16]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x17]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x18]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x19]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x1a]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x1b]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x1c]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x1d]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x1e]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x1f]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x20]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x21]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x22]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x23]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x24]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x25]   = ord($cmapData[$i++]);
        $this->_glyphIndexArray[0x26]   = ord($cmapData[$i++]);