Version 4.0.13.1
This commit is contained in:
1 parent
f9e857d255
commit
c6a86f0d9b
7517 files changed
+597400
-668041
No files matched your search
@@ -0,0 +1,274 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Archive table conversion module
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Tools
|
||||
* @since 4 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Convert;
|
||||
|
||||
/**
|
||||
* Conversion class
|
||||
*/
|
||||
class Archive extends \IPSUtf8\Convert
|
||||
{
|
||||
/**
|
||||
* @brief Instance
|
||||
*/
|
||||
protected static $instance = NULL;
|
||||
|
||||
/**
|
||||
* @brief Tables we need to convert
|
||||
*/
|
||||
protected static $nonUtf8Tables = NULL;
|
||||
|
||||
/**
|
||||
* @brief Tables we need to convert
|
||||
*/
|
||||
protected static $nonUtf8Collations = NULL;
|
||||
|
||||
/**
|
||||
* @brief Number of rows we need to convert
|
||||
*/
|
||||
protected static $rowsToConvert = NULL;
|
||||
|
||||
/**
|
||||
* @brief Table definition
|
||||
*/
|
||||
protected static $tableDefinition = NULL;
|
||||
|
||||
/**
|
||||
* @brief Post archive table name
|
||||
*/
|
||||
const ARCHIVE_TABLE = 'forums_archive_posts';
|
||||
|
||||
/**
|
||||
* @brief Native Database object
|
||||
*/
|
||||
protected static $db = NULL;
|
||||
|
||||
/**
|
||||
* @brief UTF-8 Database object
|
||||
*/
|
||||
protected static $utf = NULL;
|
||||
|
||||
/**
|
||||
* Get instance
|
||||
*
|
||||
* @return Output
|
||||
*/
|
||||
public static function i()
|
||||
{
|
||||
if ( self::$instance === NULL )
|
||||
{
|
||||
self::$instance = new self();
|
||||
|
||||
require( ROOT_PATH . '/conf_global.php' );
|
||||
|
||||
if ( $INFO['archive_remote_sql_database'] )
|
||||
{
|
||||
/* Set up two new database connections */
|
||||
static::$db = \IPSUtf8\Db::i('archive', array(
|
||||
'sql_host' => $INFO['archive_remote_sql_host'],
|
||||
'sql_user' => $INFO['archive_remote_sql_user'],
|
||||
'sql_pass' => $INFO['archive_remote_sql_pass'],
|
||||
'sql_database' => $INFO['archive_remote_sql_database'],
|
||||
'sql_tbl_prefix' => $INFO['sql_tbl_prefix']
|
||||
) );
|
||||
|
||||
$sessionData = \IPSUtf8\Session::i()->json;
|
||||
|
||||
static::$utf = \IPSUtf8\Db::i('utf8-archive', array(
|
||||
'sql_host' => $INFO['archive_remote_sql_host'],
|
||||
'sql_user' => $INFO['archive_remote_sql_user'],
|
||||
'sql_pass' => $INFO['archive_remote_sql_pass'],
|
||||
'sql_database' => $INFO['archive_remote_sql_database'],
|
||||
'sql_tbl_prefix' => $INFO['sql_tbl_prefix'],
|
||||
'sql_utf8mb4' => ( isset( $sessionData['use_utf8mb4'] ) AND ! empty( $sessionData['use_utf8mb4'] ) )
|
||||
) );
|
||||
|
||||
static::$tableDefinition = \IPSUtf8\Db::i('archive')->getTableDefinition( self::ARCHIVE_TABLE );
|
||||
if ( preg_match( '#\scharset=([a-z0-9]+?)(\s|$)#i', $row['Create Table'], $matches ) )
|
||||
{
|
||||
static::$tableDefinition['charset'] = mb_strtolower( $matches[1] );
|
||||
}
|
||||
static::$tableDefinition['definition'] = static::$tableDefinition;
|
||||
}
|
||||
|
||||
self::$instance->init();
|
||||
}
|
||||
|
||||
return static::$instance;
|
||||
}
|
||||
|
||||
/**
|
||||
* Set the current work table
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function getTable()
|
||||
{
|
||||
$table = self::$tableDefinition;
|
||||
|
||||
\IPSUtf8\Session::i()->current_table = self::ARCHIVE_TABLE;
|
||||
\IPSUtf8\Session::i()->current_pkey = 'archive_id';
|
||||
\IPSUtf8\Session::i()->save();
|
||||
|
||||
if ( in_array( self::ARCHIVE_TABLE, array_keys( \IPSUtf8\Session::i()->completed_json ) ) )
|
||||
{
|
||||
return null;
|
||||
}
|
||||
|
||||
static::log( "Continuing with " . $table['name'] . ' (PKEY: ' . \IPSUtf8\Session::i()->current_pkey . ')' );
|
||||
|
||||
if ( ! \IPSUtf8\Db::i('utf8-archive')->checkForTable( $table['name'] ) )
|
||||
{
|
||||
if ( \IPSUtf8\Db::i('utf8-archive')->createTable( $this->checkTable( $table['definition'] ) ) === false )
|
||||
{
|
||||
throw new \RuntimeException( \IPSUtf8\Db::i('utf8-archive')->error . "\n" . var_export( $table['definition'], true ) );
|
||||
}
|
||||
}
|
||||
|
||||
return $table;
|
||||
}
|
||||
|
||||
/**
|
||||
* Return tables that need converting
|
||||
*
|
||||
* @param boolean $force Force a recount
|
||||
* @return array
|
||||
*/
|
||||
public function getNonUtf8Tables( $force=false )
|
||||
{
|
||||
if ( static::$nonUtf8Tables === NULL or $force === TRUE )
|
||||
{
|
||||
$row = static::$db->query( "SHOW CREATE TABLE `" . \IPSUtf8\Db::i('archive')->prefix . self::ARCHIVE_TABLE . "`" )->fetch_assoc();
|
||||
$tblCharset = null;
|
||||
|
||||
if ( preg_match( '#\scharset=([a-z0-9]+?)(\s|$)#i', $row['Create Table'], $matches ) )
|
||||
{
|
||||
$tblCharset = mb_strtolower( $matches[1] );
|
||||
}
|
||||
|
||||
if ( $tblCharset !== 'utf8' )
|
||||
{
|
||||
static::$nonUtf8Tables = array( self::ARCHIVE_TABLE );
|
||||
}
|
||||
}
|
||||
|
||||
return static::$nonUtf8Tables;
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns total rows to convert
|
||||
*
|
||||
* @return array
|
||||
*/
|
||||
public function getTotalRowsToConvert()
|
||||
{
|
||||
if ( static::$rowsToConvert === NULL )
|
||||
{
|
||||
static::$rowsToConvert = static::$db->select('COUNT(*) as count', self::ARCHIVE_TABLE )->setKeyField('count')->first();
|
||||
}
|
||||
|
||||
return static::$rowsToConvert;
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns whether the DB has the correct collation
|
||||
*
|
||||
* @return bool
|
||||
*/
|
||||
public function getNonUtf8CollationTables()
|
||||
{
|
||||
if ( static::$nonUtf8Collations === null )
|
||||
{
|
||||
static::$nonUtf8Collations = array();
|
||||
|
||||
/* Best check the tables, then */
|
||||
foreach( self::$tableDefinition['definition']['columns'] as $name => $column )
|
||||
{
|
||||
if ( $column['collation'] and ! in_array( $column['collation'], array( 'utf8_unicode_ci', 'utf8mb4_unicode_ci' ) ) )
|
||||
{
|
||||
static::$nonUtf8Collations[] = self::$tableDefinition['name'];
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
return static::$nonUtf8Collations;
|
||||
}
|
||||
|
||||
/**
|
||||
* Return a list of numeric columns that need checking
|
||||
*
|
||||
* @param string $name Table
|
||||
* @return array Array of columns that need checking as they can contain INT
|
||||
*/
|
||||
public static function getNumericColumns( $name )
|
||||
{
|
||||
if ( ! is_string( $name ) )
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
$return = array();
|
||||
|
||||
foreach( self::$tableDefinition['definition']['columns'] as $col => $val )
|
||||
{
|
||||
if ( in_array( mb_strtolower( $val['type'] ), static::$numericCols ) )
|
||||
{
|
||||
$return[] = $val['name'];
|
||||
}
|
||||
}
|
||||
|
||||
return $return;
|
||||
}
|
||||
|
||||
/**
|
||||
* Return a list of columns that need converting
|
||||
*
|
||||
* @param string $name Table
|
||||
* @return array Array of columns that need converting as they can contain text
|
||||
*/
|
||||
public static function getConvertableColumns( $name )
|
||||
{
|
||||
if ( ! is_string( $name ) )
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
$return = array();
|
||||
|
||||
foreach( self::$tableDefinition['definition']['columns'] as $col => $val )
|
||||
{
|
||||
if ( in_array( mb_strtolower( $val['type'] ), static::$convertCols ) )
|
||||
{
|
||||
$return[] = $val['name'];
|
||||
}
|
||||
}
|
||||
|
||||
return $return;
|
||||
}
|
||||
|
||||
/**
|
||||
* Rename the tables
|
||||
*
|
||||
* @return null
|
||||
*/
|
||||
public function renameTables()
|
||||
{
|
||||
/* No need to bother with fancy stuffs to find the tables - we already know what they are */
|
||||
\IPSUtf8\Db::i('archive')->query( "RENAME TABLE `" . \IPSUtf8\Db::i('archive')->prefix . self::ARCHIVE_TABLE . "` TO `orig_" . \IPSUtf8\Db::i('archive')->prefix . self::ARCHIVE_TABLE . "`" );
|
||||
|
||||
/* Sleep for a second to avoid a race condition */
|
||||
sleep(1);
|
||||
|
||||
\IPSUtf8\Db::i('utf8-archive')->query( "RENAME TABLE `" . \IPSUtf8\Db::i('utf8-archive')->prefix . self::ARCHIVE_TABLE . "` TO `" . \IPSUtf8\Db::i('archive')->prefix . self::ARCHIVE_TABLE . "`" );
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large.
Load diff
Whitespace-only changes.
@@ -0,0 +1,68 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Binding Class for Prepared Statements
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Social Suite
|
||||
* @since 18 Feb 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Db;
|
||||
|
||||
/**
|
||||
* Binding Class for Prepared Statements
|
||||
*/
|
||||
class Bind
|
||||
{
|
||||
/**
|
||||
* @brief Values
|
||||
*/
|
||||
public $values = array();
|
||||
|
||||
/**
|
||||
* @brief Types
|
||||
*/
|
||||
protected $types = '';
|
||||
|
||||
/**
|
||||
* Add value
|
||||
*
|
||||
* @param string $type Type
|
||||
* @param mixed $value Value
|
||||
* @return void
|
||||
*/
|
||||
public function add( $type, $value )
|
||||
{
|
||||
$this->values[] = $value;
|
||||
$this->types .= $type;
|
||||
}
|
||||
|
||||
/**
|
||||
* Do we have any bound values?
|
||||
*
|
||||
* @return bool
|
||||
*/
|
||||
public function haveBinds()
|
||||
{
|
||||
return !( empty( $this->values ) );
|
||||
}
|
||||
|
||||
/**
|
||||
* Get array to pass to mysqli_stmt::bind_param
|
||||
*
|
||||
* @see <a href='http://php.net/manual/en/mysqli-stmt.bind-param.php'>mysqli_stmt::bind_param</a>
|
||||
* @return array
|
||||
*/
|
||||
public function get()
|
||||
{
|
||||
$values = array();
|
||||
foreach ( $this->values as $k => $v )
|
||||
{
|
||||
$values[ $k ] = &$this->values[ $k ];
|
||||
}
|
||||
|
||||
return array_merge( array( $this->types ), $values );
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,69 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Exception class for database errors
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Social Suite
|
||||
* @since 18 Feb 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Db;
|
||||
|
||||
/**
|
||||
* Exception class for database errors
|
||||
*/
|
||||
class Exception extends \RuntimeException
|
||||
{
|
||||
/**
|
||||
* @brief Query
|
||||
*/
|
||||
public $query;
|
||||
|
||||
/**
|
||||
* @brief Binds
|
||||
*/
|
||||
public $binds = array();
|
||||
|
||||
/**
|
||||
* Constructor
|
||||
*
|
||||
* @param string $message MySQL Error message
|
||||
* @param int $code MySQL Error Code
|
||||
* @param \Exception|NULL $previous Previous Exception
|
||||
* @param string|NULL $query MySQL Query that caused exception
|
||||
* @param array $binds Binds for query
|
||||
* @return void
|
||||
* @todo Log it
|
||||
*/
|
||||
public function __construct( $message = null, $code = 0, $previous = null, $query=NULL, $binds=array() )
|
||||
{
|
||||
$this->query = $query;
|
||||
$this->binds = $binds;
|
||||
|
||||
return parent::__construct( $message, $code, $previous );
|
||||
}
|
||||
|
||||
/**
|
||||
* Send to IPS?
|
||||
*
|
||||
* @return bool
|
||||
*/
|
||||
public function shouldSendDiagnosticsReport()
|
||||
{
|
||||
/* Low-end server errors */
|
||||
if ( $this->getCode() < 1046 or in_array( $this->getCode(), array( 1129, 1130, 1194, 1195, 1203 ) ) )
|
||||
{
|
||||
return FALSE;
|
||||
}
|
||||
|
||||
/* Low-end client errors */
|
||||
if ( $this->getCode() >= 2000 and $this->getCode() < 2029 )
|
||||
{
|
||||
return FALSE;
|
||||
}
|
||||
|
||||
return TRUE;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,329 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Database SELECT Statement
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Social Suite
|
||||
* @since 28 Aug 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Db;
|
||||
|
||||
/**
|
||||
* @brief Database SELECT Statement
|
||||
*/
|
||||
class Select implements \Iterator, \Countable
|
||||
{
|
||||
/**
|
||||
* @brief The query
|
||||
*/
|
||||
public $query;
|
||||
|
||||
/**
|
||||
* @brief Binds
|
||||
*/
|
||||
public $binds;
|
||||
|
||||
/**
|
||||
* @brief The database object
|
||||
*/
|
||||
protected $db;
|
||||
|
||||
/**
|
||||
* @brief The statement
|
||||
*/
|
||||
protected $stmt;
|
||||
|
||||
/**
|
||||
* Constuctor
|
||||
*
|
||||
* @param string $query The query
|
||||
* @param array $binds Binds
|
||||
* @param \IPSUtf8\Db $db The database object
|
||||
* @return void
|
||||
*/
|
||||
public function __construct( $query, array $binds, \IPSUtf8\Db $db )
|
||||
{
|
||||
$this->query = $query;
|
||||
$this->binds = $binds;
|
||||
$this->db = $db;
|
||||
}
|
||||
|
||||
/**
|
||||
* Add Join
|
||||
*
|
||||
* @param array|string $table The table to select from. Either (string) table_name or (array) ( name, alias )
|
||||
* @param
|
||||
* @return void
|
||||
*/
|
||||
public function join( $table, $on, $type='LEFT', $using=FALSE )
|
||||
{
|
||||
$query = '';
|
||||
$joinConditionIsOptional = TRUE;
|
||||
|
||||
switch ( $type )
|
||||
{
|
||||
case 'INNER':
|
||||
case 'CROSS':
|
||||
$query .= 'INNER JOIN ';
|
||||
break;
|
||||
|
||||
case 'STRAIGHT_JOIN':
|
||||
$query .= 'STRAIGHT_JOIN';
|
||||
if ( $using )
|
||||
{
|
||||
throw new \InvalidArgumentException; // USING cannot be used with STRAIGHT_JOIN
|
||||
}
|
||||
break;
|
||||
|
||||
case 'LEFT':
|
||||
case 'RIGHT':
|
||||
$query .= $type . ' JOIN';
|
||||
$joinConditionIsOptional = FALSE;
|
||||
break;
|
||||
}
|
||||
|
||||
if ( is_array( $table ) )
|
||||
{
|
||||
$query .= " `{$this->db->prefix}{$table[0]}` AS `{$table[1]}`";
|
||||
}
|
||||
else
|
||||
{
|
||||
$query .= " `{$this->db->prefix}{$table}` AS `{$table}`";
|
||||
}
|
||||
|
||||
if ( $on )
|
||||
{
|
||||
if ( $using )
|
||||
{
|
||||
$query .= ' USING ( ' . implode( ', ', array_map( function( $col )
|
||||
{
|
||||
return '`' . $col . '`';
|
||||
}, $on ) ) . ' ) ';
|
||||
}
|
||||
else
|
||||
{
|
||||
$where = $this->db->compileWhereClause( $on );
|
||||
$query .= ' ON ' . $where['clause'];
|
||||
$this->binds = array_merge( $where['binds'], $this->binds );
|
||||
}
|
||||
}
|
||||
elseif ( !$joinConditionIsOptional )
|
||||
{
|
||||
throw new \InvalidArgumentException;
|
||||
}
|
||||
|
||||
$this->query = preg_replace( '/(FROM `.+?` AS `.+?`)/', '$1 ' . $query, $this->query );
|
||||
|
||||
return $this;
|
||||
}
|
||||
|
||||
/**
|
||||
* @brief Columns in the resultset
|
||||
*/
|
||||
protected $columns = array();
|
||||
|
||||
/**
|
||||
* @brief Key Field
|
||||
*/
|
||||
protected $keyField = NULL;
|
||||
|
||||
/**
|
||||
* @brief Value Field
|
||||
*/
|
||||
protected $valueField = NULL;
|
||||
|
||||
/**
|
||||
* Set key field
|
||||
*
|
||||
* @param string $column Column to treat as the key
|
||||
* @return \IPSUtf8\Db\Select (for daisy=chaining)
|
||||
*/
|
||||
public function setKeyField( $column )
|
||||
{
|
||||
if ( !$this->stmt )
|
||||
{
|
||||
$this->rewind();
|
||||
}
|
||||
|
||||
if ( !in_array( $column, $this->columns ) )
|
||||
{
|
||||
throw new \InvalidArgumentException;
|
||||
}
|
||||
|
||||
$this->keyField = $column;
|
||||
|
||||
return $this;
|
||||
}
|
||||
|
||||
/**
|
||||
* Set value field
|
||||
*
|
||||
* @param string $column Column to treat as the key
|
||||
* @return \IPSUtf8\Db\Select (for daisy=chaining)
|
||||
*/
|
||||
public function setValueField( $column )
|
||||
{
|
||||
if ( !$this->stmt )
|
||||
{
|
||||
$this->rewind();
|
||||
}
|
||||
|
||||
if ( !in_array( $column, $this->columns ) )
|
||||
{
|
||||
throw new \InvalidArgumentException;
|
||||
}
|
||||
|
||||
$this->valueField = $column;
|
||||
|
||||
return $this;
|
||||
}
|
||||
|
||||
/**
|
||||
* @brief The current row
|
||||
*/
|
||||
protected $row;
|
||||
|
||||
/**
|
||||
* @brief The current key
|
||||
*/
|
||||
protected $key;
|
||||
|
||||
/**
|
||||
* Get first record
|
||||
*
|
||||
* @return array
|
||||
* @throws \OutOfRangeException
|
||||
*/
|
||||
public function first()
|
||||
{
|
||||
$this->rewind();
|
||||
if ( !$this->valid() )
|
||||
{
|
||||
throw new \UnderflowException;
|
||||
}
|
||||
return $this->current();
|
||||
}
|
||||
|
||||
/**
|
||||
* [Iterator] Rewind - will (re-)execute statement
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function rewind( $debug=FALSE )
|
||||
{
|
||||
/* Run the query */
|
||||
$this->stmt = $this->db->preparedQuery( $this->query, $this->binds );
|
||||
|
||||
/* Populate $this->row which we read into */
|
||||
$this->row = array();
|
||||
$params = array();
|
||||
$meta = $this->stmt->result_metadata();
|
||||
while ( $field = $meta->fetch_field() )
|
||||
{
|
||||
$params[] = &$this->row[ $field->name ];
|
||||
}
|
||||
$this->columns = array_keys( $this->row );
|
||||
call_user_func_array( array( $this->stmt, 'bind_result' ), $params );
|
||||
|
||||
/* Get the first result */
|
||||
$this->key = -1;
|
||||
$this->next();
|
||||
}
|
||||
|
||||
/**
|
||||
* [Iterator] Get current row
|
||||
*
|
||||
* @return array
|
||||
*/
|
||||
public function current()
|
||||
{
|
||||
if ( $this->valueField )
|
||||
{
|
||||
return $this->row[ $this->valueField ];
|
||||
}
|
||||
elseif ( count( $this->row ) === 1 )
|
||||
{
|
||||
foreach ( $this->row as $v )
|
||||
{
|
||||
return $v;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
$row = array();
|
||||
foreach ( $this->row as $k => $v )
|
||||
{
|
||||
$row[ $k ] = $v;
|
||||
}
|
||||
return $row;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* [Iterator] Get current key
|
||||
*
|
||||
* @return mixed
|
||||
*/
|
||||
public function key()
|
||||
{
|
||||
if ( $this->keyField )
|
||||
{
|
||||
return $this->row[ $this->keyField ];
|
||||
}
|
||||
else
|
||||
{
|
||||
return $this->key;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* [Iterator] Fetch next result
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function next()
|
||||
{
|
||||
if ( $this->stmt->fetch() === NULL )
|
||||
{
|
||||
$this->row = NULL;
|
||||
}
|
||||
$this->key++;
|
||||
}
|
||||
|
||||
/**
|
||||
* [Iterator] Is the current row valid?
|
||||
*
|
||||
* @return bool
|
||||
*/
|
||||
public function valid()
|
||||
{
|
||||
return ( $this->row !== NULL );
|
||||
}
|
||||
|
||||
/**
|
||||
* [Countable] Get number of rows
|
||||
*
|
||||
* @param bool $allRows If TRUE, will get the number of rows ignoring the limit. In order for this to work, the query must have been ran with SQL_CALC_FOUND_ROWS
|
||||
* @return int
|
||||
*/
|
||||
public function count( $allRows = FALSE )
|
||||
{
|
||||
if ( !$this->stmt )
|
||||
{
|
||||
$this->rewind();
|
||||
}
|
||||
|
||||
if ( $allRows )
|
||||
{
|
||||
$result = $this->db->query( 'SELECT FOUND_ROWS() AS count;' )->fetch_assoc();
|
||||
return $result['count'];
|
||||
}
|
||||
else
|
||||
{
|
||||
return $this->stmt->num_rows;
|
||||
}
|
||||
}
|
||||
}
|
||||
Whitespace-only changes.
@@ -0,0 +1,64 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Dispatcher (Web)
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Tools
|
||||
* @since 4 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Dispatcher;
|
||||
use \IPSUtf8\Output\Browser\Template;
|
||||
|
||||
/**
|
||||
* Web Dispatcher
|
||||
*/
|
||||
class Browser extends \IPSUtf8\Dispatcher
|
||||
{
|
||||
/**
|
||||
* Run
|
||||
*/
|
||||
public function run()
|
||||
{
|
||||
$this->controller = ( \IPSUtf8\Request::i()->controller ) ? \IPSUtf8\Request::i()->controller : 'browser';
|
||||
|
||||
$fileLocation = \THIS_PATH . '/modules/browser/' . $this->controller . '.php';
|
||||
$classname = 'IPSUtf8\\modules\\browser\\' . $this->controller;
|
||||
|
||||
if( !file_exists( $fileLocation ) )
|
||||
{
|
||||
\IPSUtf8\Output\Browser::i()->error( "Page doesn't exist" );
|
||||
}
|
||||
|
||||
/* Run */
|
||||
$this->controllerObj = new $classname;
|
||||
if( !( $this->controllerObj instanceof \IPSUtf8\Dispatcher\Controller ) )
|
||||
{
|
||||
\IPSUtf8\Output\Browser::i()->error( "Page doesn't exist" );
|
||||
}
|
||||
|
||||
$this->controllerObj->execute();
|
||||
|
||||
/* Output */
|
||||
if ( \IPSUtf8\Request::i()->isAjax() )
|
||||
{
|
||||
\IPSUtf8\Output\Browser::i()->sendOutput( Template::blankTemplate( \IPSUtf8\Output\Browser::i()->output ), 200, 'text/html', \IPSUtf8\Output\Browser::i()->httpHeaders );
|
||||
}
|
||||
else
|
||||
{
|
||||
\IPSUtf8\Output\Browser::i()->sendOutput( Template::wrapper( \IPSUtf8\Output\Browser::i()->title, \IPSUtf8\Output\Browser::i()->output ), 200, 'text/html', \IPSUtf8\Output\Browser::i()->httpHeaders );
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Init
|
||||
*/
|
||||
public function init()
|
||||
{
|
||||
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
@@ -0,0 +1,37 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Dispatcher (CLI)
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Tools
|
||||
* @since 4 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Dispatcher;
|
||||
|
||||
/**
|
||||
* CLI Dispatcher
|
||||
*/
|
||||
class Cli extends \IPSUtf8\Dispatcher
|
||||
{
|
||||
/**
|
||||
* Run
|
||||
*/
|
||||
public function run()
|
||||
{
|
||||
$obj = new \IPSUtf8\modules\cli\cli;
|
||||
$obj->execute();
|
||||
}
|
||||
|
||||
/**
|
||||
* Init
|
||||
*/
|
||||
public function init()
|
||||
{
|
||||
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
@@ -0,0 +1,47 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Abstract class that Controllers should extend
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Social Suite
|
||||
* @since 18 Feb 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Dispatcher;
|
||||
|
||||
/**
|
||||
* Abstract class that Controllers should extend
|
||||
*/
|
||||
abstract class Controller
|
||||
{
|
||||
|
||||
/**
|
||||
* Execute
|
||||
*
|
||||
* @param string $command The part of the query string which will be used to get the method
|
||||
* @param \IPS\Http\Url|NULL $url The base URL for this controller or NULL to calculate automatically
|
||||
* @return void
|
||||
*/
|
||||
public function execute()
|
||||
{
|
||||
if( \IPSUtf8\Request::i()->do and \substr( \IPSUtf8\Request::i()->do, 0, 1 ) !== '_' )
|
||||
{
|
||||
$method = ( \IPSUtf8\Request::i()->do and preg_match( '/^[a-zA-Z\x7f-\xff][a-zA-Z0-9_\x7f-\xff]*$/', \IPSUtf8\Request::i()->do ) ) ? \IPSUtf8\Request::i()->do : NULL;
|
||||
|
||||
if ( $method !== NULL AND method_exists( $this, $method ) )
|
||||
{
|
||||
call_user_func( array( $this, $method ) );
|
||||
}
|
||||
else
|
||||
{
|
||||
\IPSUtf8\Output\Browser::i()->error( "Page not found" );
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
$this->manage();
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,75 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Dispatcher
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Tools
|
||||
* @since 4 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8;
|
||||
|
||||
/**
|
||||
* Dispatcher
|
||||
*/
|
||||
abstract class Dispatcher
|
||||
{
|
||||
/**
|
||||
* @brief Singleton Instance
|
||||
*/
|
||||
protected static $instance = NULL;
|
||||
|
||||
/**
|
||||
* @brief Controller
|
||||
*/
|
||||
public $controller = 'browser';
|
||||
|
||||
/**
|
||||
* @brief Controller
|
||||
*/
|
||||
public $controllerObj = NULL;
|
||||
|
||||
/**
|
||||
* Get instance
|
||||
*
|
||||
* @return \IPS\Dispatcher
|
||||
*/
|
||||
public static function i()
|
||||
{
|
||||
if( self::$instance === NULL )
|
||||
{
|
||||
$classname = get_called_class();
|
||||
if ( $classname === 'IPSUtf8\Dispatcher' )
|
||||
{
|
||||
self::$instance = new \IPSUtf8\Dispatcher\Browser;
|
||||
}
|
||||
else
|
||||
{
|
||||
self::$instance = new $classname;
|
||||
}
|
||||
|
||||
self::$instance->init();
|
||||
}
|
||||
|
||||
return self::$instance;
|
||||
}
|
||||
|
||||
/**
|
||||
* Run the dispatcher
|
||||
*/
|
||||
public function run()
|
||||
{
|
||||
|
||||
}
|
||||
|
||||
/**
|
||||
* Init
|
||||
*/
|
||||
public function init()
|
||||
{
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
Whitespace-only changes.
@@ -0,0 +1,109 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Output Class
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Social Suite
|
||||
* @since 9 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Output;
|
||||
|
||||
/**
|
||||
* Output Class
|
||||
*/
|
||||
class Browser extends \IPSUtf8\Output
|
||||
{
|
||||
public static $url = null;
|
||||
|
||||
/**
|
||||
* Constructor
|
||||
*/
|
||||
public static function i()
|
||||
{
|
||||
if ( static::$url === null )
|
||||
{
|
||||
static::$url = 'index.php';
|
||||
}
|
||||
|
||||
return parent::i();
|
||||
}
|
||||
|
||||
/**
|
||||
* Redirect
|
||||
*
|
||||
* @param string $url Partial URL to redirect to
|
||||
* @return void
|
||||
*/
|
||||
public function redirect( $url )
|
||||
{
|
||||
$this->sendOutput( '', 303, '', array( "Location: {$url}" ) );
|
||||
}
|
||||
|
||||
/**
|
||||
* Display Error Screen
|
||||
*
|
||||
* @param string $message language string for error message
|
||||
* @return void
|
||||
*/
|
||||
public function error( $message )
|
||||
{
|
||||
/* Send output */
|
||||
$this->sendOutput( \IPSUtf8\Output\Browser\Template::wrapper( "IPS Converter", \IPSUtf8\Output\Browser\Template::error( $message ), 500 ) );
|
||||
exit();
|
||||
}
|
||||
|
||||
/**
|
||||
* Send output
|
||||
*
|
||||
* @param string $output Content to output
|
||||
* @param int $httpStatusCode HTTP Status Code
|
||||
* @param string $contentType HTTP Content-type
|
||||
* @param array $httpHeaders Additional HTTP Headers
|
||||
* @return void
|
||||
*/
|
||||
public function sendOutput( $output='', $httpStatusCode=200, $contentType='text/html', $httpHeaders=array() )
|
||||
{
|
||||
/* Set HTTP status */
|
||||
if( isset( $_SERVER['SERVER_PROTOCOL'] ) and \strstr( $_SERVER['SERVER_PROTOCOL'], '/1.0' ) !== false )
|
||||
{
|
||||
header( "HTTP/1.0 {$httpStatusCode} " . self::$httpStatuses[ $httpStatusCode ] );
|
||||
}
|
||||
else
|
||||
{
|
||||
header( "HTTP/1.1 {$httpStatusCode} " . self::$httpStatuses[ $httpStatusCode ] );
|
||||
}
|
||||
|
||||
while( @ob_end_clean() );
|
||||
|
||||
/* Buffer output */
|
||||
if ( $output )
|
||||
{
|
||||
if( isset( $_SERVER['HTTP_ACCEPT_ENCODING'] ) and \strpos( $_SERVER['HTTP_ACCEPT_ENCODING'], 'gzip' ) !== false and (bool) ini_get('zlib.output_compression') === false )
|
||||
{
|
||||
ob_start('ob_gzhandler');
|
||||
}
|
||||
else
|
||||
{
|
||||
ob_start();
|
||||
}
|
||||
|
||||
print $output;
|
||||
}
|
||||
|
||||
/* Send headers */
|
||||
header( "Content-type: {$contentType};charset=UTF-8" );
|
||||
foreach ( $httpHeaders as $header )
|
||||
{
|
||||
header( $header );
|
||||
}
|
||||
header( "Connection: close" );
|
||||
|
||||
/* Flush and exit */
|
||||
@ob_end_flush();
|
||||
|
||||
exit;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,465 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Template Class
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Social Suite
|
||||
* @since 9 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Output\Browser;
|
||||
|
||||
/**
|
||||
* Template Class
|
||||
*/
|
||||
class Template
|
||||
{
|
||||
public static function wrapper( $title="IPS Converter", $content="")
|
||||
{
|
||||
$iniTime = @ini_get('max_execution_time');
|
||||
$execTime = ( is_numeric( $iniTime ) ) ? $iniTime : 30;
|
||||
$url = \IPSUtf8\Output\Browser::$url;
|
||||
$title = ( empty( $title ) ) ? 'IPS Converter' : $title;
|
||||
$active = array( 'convert' => '', 'tools' => '', 'archive' => '' );
|
||||
$hasArchive = \IPSUtf8\Session::i()->has_archive;
|
||||
$controller = empty( \IPSUtf8\Request::i()->controller ) ? 'browser' : \IPSUtf8\Request::i()->controller;
|
||||
$version = \IPSUtf8\Convert::VERSION_ID;
|
||||
$copyrightDate = date('Y');
|
||||
|
||||
if ( $controller == 'browser' )
|
||||
{
|
||||
$active['convert'] = 'active';
|
||||
}
|
||||
else if ( $controller === 'archive' )
|
||||
{
|
||||
$active['archive'] = 'active';
|
||||
}
|
||||
else
|
||||
{
|
||||
$active['tools'] = 'active';
|
||||
}
|
||||
|
||||
$html = <<<EOFHTML
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<title>{$title}</title>
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<link href="css/bootstrap.min.css" rel="stylesheet" media="screen">
|
||||
<link href="css/jumbotron.css" rel="stylesheet" media="screen">
|
||||
</head>
|
||||
<body data-url="{$url}">
|
||||
<div class="container">
|
||||
<div class="header">
|
||||
<ul class="nav nav-pills pull-right">
|
||||
<li class="{$active['convert']}"><a href="{url="?controller=browser"}">Convert</a></li>
|
||||
EOFHTML;
|
||||
if ( $hasArchive )
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
<li class="{$active['archive']}"><a href="{url="?controller=archive"}">Archive</a></li>
|
||||
EOFHTML;
|
||||
}
|
||||
|
||||
$html .= <<<EOFHTML
|
||||
<li class="{$active['tools']}"><a href="{url="?controller=tools"}">Tools</a></li>
|
||||
</ul>
|
||||
<h3 class="text-muted">IPS UTF8 Converter</h3>
|
||||
</div>
|
||||
{$content}
|
||||
<div class="footer">
|
||||
<p>UTF8 Converter v{$version} © {$copyrightDate} Invision Power Services, Inc.</p>
|
||||
</div>
|
||||
</div>
|
||||
<script type="text/javascript">
|
||||
var ipsSettings = { maxExecTime: {$execTime}, 'controller': '{$controller}' };
|
||||
</script>
|
||||
<script src="js/jquery.min.js"></script>
|
||||
<script src="js/app.js?v=1"></script>
|
||||
<script src="js/bootstrap.min.js"></script>
|
||||
</body>
|
||||
</html>
|
||||
<div class="modal fade" id="confirmModal" data-url="" tabindex="-1" role="dialog" aria-labelledby="myModalLabel" aria-hidden="true">
|
||||
<div class="modal-dialog">
|
||||
<div class="modal-content">
|
||||
<div class="modal-header">
|
||||
<button type="button" class="close" data-dismiss="modal" aria-hidden="true">×</button>
|
||||
<h4 class="modal-title">Confirm</h4>
|
||||
</div>
|
||||
<div class="modal-body">
|
||||
<p id="confirmModalText">Please confirm this action</p>
|
||||
</div>
|
||||
<div class="modal-footer">
|
||||
<button type="button" class="btn btn-default" data-dismiss="modal">Cancel</button>
|
||||
<button type="button" class="btn btn-primary" data-modal="submit">Confirm</button>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
EOFHTML;
|
||||
|
||||
return static::parse( $html );
|
||||
}
|
||||
|
||||
/**
|
||||
* Tools page
|
||||
*/
|
||||
public static function tools( $isUtf8=false, $msg )
|
||||
{
|
||||
$html = <<<EOFHTML
|
||||
<div class="jumbotron">
|
||||
<h1>Tools</h1>
|
||||
EOFHTML;
|
||||
|
||||
if ( $msg !== null )
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
<p>
|
||||
<div class='alert alert-info'>{$msg}</div>
|
||||
</p>
|
||||
<p> </p>
|
||||
EOFHTML;
|
||||
}
|
||||
|
||||
if ( ! isset( \IPSUtf8\Request::i()->do ) )
|
||||
{
|
||||
if ( $isUtf8 === true )
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
<p class="text-info">The database is set to UTF-8.</p>
|
||||
<p><a class="btn btn-lg btn-info" href="{url="?controller=tools&do=collation"}">Check and fix UTF-8 collation</a></p>
|
||||
EOFHTML;
|
||||
}
|
||||
else
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
<p class="text-info">Please <a href="{url="?controller=browser"}">convert to UTF-8</a> first.</p>
|
||||
EOFHTML;
|
||||
}
|
||||
}
|
||||
|
||||
$html .= <<<EOFHTML
|
||||
</div>
|
||||
EOFHTML;
|
||||
|
||||
$code = implode( "<br />", \IPSUtf8\Convert::i()->getDebugString() );
|
||||
|
||||
$html .= <<<EOFHTML
|
||||
<div class="jumbotron">
|
||||
<h1>Info</h1>
|
||||
<code>
|
||||
{$code}
|
||||
</code>
|
||||
</div>
|
||||
EOFHTML;
|
||||
|
||||
return static::parse( $html );
|
||||
}
|
||||
|
||||
/**
|
||||
* Welcome page
|
||||
*/
|
||||
public static function error( $msg )
|
||||
{
|
||||
$html = <<<EOFHTML
|
||||
<div class="jumbotron">
|
||||
<h1>Error</h1>
|
||||
<p class="lead">{$msg}</p>
|
||||
</div>
|
||||
EOFHTML;
|
||||
|
||||
return static::parse( $html );
|
||||
}
|
||||
|
||||
/**
|
||||
* Welcome page
|
||||
*/
|
||||
public static function welcome( $isUtf8=false, $status, $percent=false, $controller='browser' )
|
||||
{
|
||||
$convertClass = ( $controller === 'browser' ) ? '\IPSUtf8\Convert' : '\IPSUtf8\Convert\Archive';
|
||||
$origUtf8Charset = \IPSUtf8\Db::i('utf8')->getCharset();
|
||||
$canUseMb4 = ( version_compare( \IPSUtf8\Db::i()->server_info, '5.5.3', '>=' ) AND \IPSUtf8\Db::i('utf8')->set_charset('utf8mb4') !== FALSE );
|
||||
\IPSUtf8\Db::i('utf8')->set_charset( $origUtf8Charset );
|
||||
$badCollations = $convertClass::i()->getNonUtf8CollationTables();
|
||||
$badTablesCnt = count( $convertClass::i()->getNonUtf8Tables() );
|
||||
$path = ROOT_PATH;
|
||||
$dbCharSetIsCorrect = TRUE;
|
||||
$isUtf8mb4 = ( $isUtf8 === TRUE AND \IPSUtf8\Convert::i()->database_charset == 'utf8mb4' );
|
||||
|
||||
if ( file_exists( ROOT_PATH . '/conf_global.php' ) )
|
||||
{
|
||||
require_once( ROOT_PATH . '/conf_global.php' );
|
||||
if ( !isset( $INFO['sql_charset'] ) OR ! in_array( $INFO['sql_charset'], array( 'utf8', 'utf8mb4' ) ) )
|
||||
{
|
||||
$dbCharSetIsCorrect = FALSE;
|
||||
}
|
||||
}
|
||||
|
||||
if ( isset( \IPSUtf8\Request::i()->convert_anyway ) AND \IPSUtf8\Request::i()->convert_anyway == 1 )
|
||||
{
|
||||
$badTablesCnt = \IPSUtf8\Session::i()->json['tableCount'];
|
||||
}
|
||||
|
||||
$html = <<<EOFHTML
|
||||
<div class="jumbotron">
|
||||
<h1>Welcome</h1>
|
||||
EOFHTML;
|
||||
|
||||
if ( $controller === 'archive' )
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
<p class="text-info">The converter has detected that you have an archive table in a different database.</p>
|
||||
EOFHTML;
|
||||
}
|
||||
|
||||
if ( $status === 'processing' )
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
<p class="text-warning">Conversion in progress ({$percent}% complete).</p>
|
||||
EOFHTML;
|
||||
}
|
||||
else if ( $isUtf8 !== true )
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
<p class="lead">You have {$badTablesCnt} table(s) in this database that are not UTF-8.\nYou must convert these tables to UTF-8 before you can proceed with the upgrade.</p>
|
||||
EOFHTML;
|
||||
}
|
||||
else if ( $isUtf8 === true )
|
||||
{
|
||||
if ( count( $badCollations ) )
|
||||
{
|
||||
$cnt = count( $badCollations );
|
||||
$html .= <<<EOFHTML
|
||||
<p class="text-info">
|
||||
The database is set to UTF-8, however {$cnt} table(s) have incorrect collations and need fixing.
|
||||
<p><a class="btn btn-lg btn-info" href="{url="?controller=tools&do=collation"}">Fix UTF-8 collations</a></p>
|
||||
</p>
|
||||
<p class="text-info">
|
||||
If, after this process completes, you start to experience errors or see corrupt text, it is likely that you need to convert your data anyway. You can do this by clicking the button below.<br>
|
||||
<a class='btn btn-info' href='{url="?controller={$controller}&convert_anyway=1"}'>Run the Conversion</a>
|
||||
</p>
|
||||
EOFHTML;
|
||||
}
|
||||
else
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
|
||||
<p class="text-info">
|
||||
The database tables are UTF-8, collations are correct and there is nothing to convert. You can <strong><a href="../upgrade">proceed with the upgrade</strong>.
|
||||
</p>
|
||||
EOFHTML;
|
||||
}
|
||||
}
|
||||
|
||||
if ( ! $isUtf8 and $canUseMb4 )
|
||||
{
|
||||
$buttonLabel = ( $isUtf8 ) ? "Convert anyway using 4-Byte UTF-8 (utf8mb4)" : "Start using 4-Byte UTF-8 (utf8mb4)";
|
||||
|
||||
$html .= <<<EOFHTML
|
||||
<p>
|
||||
<a data-status="Start" class="btn btn-lg btn-info" href="{url="?controller={$controller}&do=process&use_utf8mb4=1"}">{$buttonLabel}</a>
|
||||
<br />
|
||||
<div class='small'>
|
||||
<small>
|
||||
Some non-common symbols (such as historical scripts, music symbols and Emoji) require more space in the database to be stored. If you choose to convert using 4-Byte UTF-8, these characters will be able to be used, but the database will use more disk space.
|
||||
</small>
|
||||
</div>
|
||||
</p>
|
||||
EOFHTML;
|
||||
}
|
||||
|
||||
if ( ! $isUtf8 )
|
||||
{
|
||||
$label = 'Start using UTF-8 (utf8)';
|
||||
$selector = 'btn-success';
|
||||
$more = <<<EOFHTML
|
||||
<br />
|
||||
<div class='small'>
|
||||
<small>
|
||||
Choose this if you don't wish to store non-common symbols (such as historical scripts, music symbols and Emoji) and wish to use less disk space.
|
||||
</small>
|
||||
</div>
|
||||
<br>
|
||||
<div class='small'>
|
||||
<small>
|
||||
Please note that you should turn your community offline before starting any conversion on a live site.
|
||||
</small>
|
||||
</div>
|
||||
<br>
|
||||
<div class='small'>
|
||||
<small>
|
||||
If you have a large community, or are experiencing browser timeouts during conversion, you may wish to consider running the conversion via the Command Line.<br>
|
||||
<code>
|
||||
php {$path}/admin/convertutf8/cli.php
|
||||
</code>
|
||||
</small>
|
||||
</div>
|
||||
EOFHTML;
|
||||
}
|
||||
|
||||
if ( $status === 'processing' )
|
||||
{
|
||||
$label = 'Continue Conversion';
|
||||
$selector = 'btn-warning';
|
||||
$more = '';
|
||||
}
|
||||
else if ( ! $isUtf8 )
|
||||
{
|
||||
$label = "Convert as UTF-8 (utf8)";
|
||||
$selector = 'btn-info';
|
||||
}
|
||||
|
||||
if ( $label and $selector )
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
<p>
|
||||
<a data-status="{$status}" class="btn btn-lg {$selector}" href="{url="?controller={$controller}&do=process"}">{$label}</a>
|
||||
{$more}
|
||||
</p>
|
||||
EOFHTML;
|
||||
}
|
||||
|
||||
if ( $status === 'processing' )
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
<p><small><a data-status="reset" data-confirm="true" class='text-danger' href="{url="?controller={$controller}&do=reset"}">Reset conversion and restart</a></small></p>
|
||||
EOFHTML;
|
||||
}
|
||||
$html .= <<<EOFHTML
|
||||
</div>
|
||||
EOFHTML;
|
||||
|
||||
return static::parse( $html );
|
||||
}
|
||||
|
||||
/**
|
||||
* Process page
|
||||
*/
|
||||
public static function process( $status, $percent, $msg )
|
||||
{
|
||||
$utfPrefix = \IPSUtf8\Db::i('utf8')->prefix . \IPSUtf8\Db::i()->prefix;
|
||||
|
||||
$html = <<<EOFHTML
|
||||
<div class="jumbotron" data-init="processInit">
|
||||
<h1>Converting</h1>
|
||||
<p> </p>
|
||||
<p>
|
||||
<div class="progress progress-striped active">
|
||||
<div id="progressBar" data-start="{$percent}" class="progress-bar" role="progressbar" aria-valuenow="{$percent}" aria-valuemin="0" aria-valuemax="100" style="width: {$percent}%">
|
||||
<span class='sr-only'>{$msg}</span>
|
||||
</div>
|
||||
</div>
|
||||
</p>
|
||||
<p id="message">{$msg}</p>
|
||||
</div>
|
||||
EOFHTML;
|
||||
|
||||
return static::parse( $html );
|
||||
}
|
||||
|
||||
/**
|
||||
* Completed page
|
||||
*/
|
||||
public static function completed( $timeTaken )
|
||||
{
|
||||
$html = <<<EOFHTML
|
||||
<div class="jumbotron">
|
||||
<h1>Almost there!</h1>
|
||||
<p class="lead">The database has now been converted!</p>
|
||||
<p><small>Conversion took {$timeTaken}</small></p>
|
||||
<p> </p>
|
||||
<p><a class="btn btn-lg btn-info" href="{url="?controller=browser&do=finish"}">Click here to finish</a></p>
|
||||
</div>
|
||||
EOFHTML;
|
||||
|
||||
return static::parse( $html );
|
||||
}
|
||||
|
||||
/**
|
||||
* Finish page
|
||||
*/
|
||||
public static function finished( $updated )
|
||||
{
|
||||
$utfPrefix = \IPSUtf8\Db::i('utf8')->prefix;
|
||||
$normalPrefix = \IPSUtf8\Db::i()->prefix;
|
||||
$sessionData = \IPSUtf8\Session::i()->json;
|
||||
$sql_charset = ( array_key_exists( 'utf8mb4', $sessionData['charSets'] ) ) ? 'utf8mb4' : 'utf8';
|
||||
|
||||
/* Phil made me give him credit for some changes in this code */
|
||||
$html = <<<EOFHTML
|
||||
<div class="jumbotron">
|
||||
<h1>Finished!</h1>
|
||||
<p class="lead">The database has now been converted and the tables correctly renamed!</p>
|
||||
EOFHTML;
|
||||
|
||||
if ( \IPSUtf8\Request::i()->controller === 'browser' )
|
||||
{
|
||||
if( !$updated )
|
||||
{
|
||||
$utf8mb4 = ( $sql_charset == 'utf8mb4' ) ? "<br>\$INFO['sql_utf8mb4'] = true;" : '';
|
||||
$html .= <<<EOFHTML
|
||||
<p>You can now <strong>complete the conversion</strong> by editing conf_global.php to add <br><code>\$INFO['sql_charset'] = '{$sql_charset}';{$utf8mb4}</code>.<br>Afterwards, you can <strong><a href="../upgrade">proceed with the upgrade</strong>.</p>
|
||||
</div>
|
||||
EOFHTML;
|
||||
}
|
||||
else
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
<p>You can now <strong><a href="../upgrade">proceed with the upgrade</strong>.</p>
|
||||
</div>
|
||||
EOFHTML;
|
||||
}
|
||||
}
|
||||
else if ( \IPSUtf8\Request::i()->controller === 'archive' )
|
||||
{
|
||||
$html .= <<<EOFHTML
|
||||
<p>You can now <strong>complete the conversion</strong> by converting the <a href="{url="?controller=browser"}">main database</a> if you've not already done so.</p>
|
||||
</div>
|
||||
EOFHTML;
|
||||
}
|
||||
return static::parse( $html );
|
||||
}
|
||||
|
||||
/**
|
||||
* Basic HTML parsing
|
||||
*
|
||||
* @param string $html Raw HTML
|
||||
* @return string
|
||||
*/
|
||||
protected static function parse( $html )
|
||||
{
|
||||
/* Parse {plugin="foo"} tags */
|
||||
$html = preg_replace_callback
|
||||
(
|
||||
'/\{([a-z]+?=([\'"]).+?\\2 ?+)}/',
|
||||
function( $matches )
|
||||
{
|
||||
/* Work out the plugin and the values to pass */
|
||||
preg_match_all( '/(.+?)='.$matches[2].'(.+?)'.$matches[2].'\s?/', $matches[1], $submatches );
|
||||
|
||||
$plugin = array_shift( $submatches[1] );
|
||||
$value = array_shift( $submatches[2] );
|
||||
$options = array();
|
||||
|
||||
foreach ( $submatches[1] as $k => $v )
|
||||
{
|
||||
$options[ $v ] = $submatches[2][ $k ];
|
||||
}
|
||||
|
||||
switch( $plugin )
|
||||
{
|
||||
case 'url':
|
||||
return \IPSUtf8\Output\Browser::$url . $value;
|
||||
break;
|
||||
}
|
||||
},
|
||||
$html
|
||||
);
|
||||
|
||||
return $html;
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
Whitespace-only changes.
@@ -0,0 +1,181 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Output Class
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Social Suite
|
||||
* @since 9 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Output;
|
||||
|
||||
/**
|
||||
* Output Class
|
||||
*/
|
||||
class Cli extends \IPSUtf8\Output
|
||||
{
|
||||
/**
|
||||
* @Brief STDIN Handle
|
||||
*/
|
||||
protected static $stdin = null;
|
||||
|
||||
/**
|
||||
* @Brief Progress bar has been drawn
|
||||
*/
|
||||
protected static $barDrawn = false;
|
||||
|
||||
/**
|
||||
* @Brief Response
|
||||
*/
|
||||
public $response = null;
|
||||
|
||||
/**
|
||||
* Display Error Screen
|
||||
*
|
||||
* @param string $message language string for error message
|
||||
* @return void
|
||||
*/
|
||||
public function error( $message )
|
||||
{
|
||||
/* Send output */
|
||||
parent::error( $message );
|
||||
exit();
|
||||
}
|
||||
|
||||
/**
|
||||
* Display a CLI progress bar
|
||||
*
|
||||
* @param string $table Table processing
|
||||
* @param int $total Total number
|
||||
* @param int $current Current number processed
|
||||
* @param int $size Total size of the bar
|
||||
* @return string
|
||||
*/
|
||||
public function progressBar( $table, $total, $current, $size=50 )
|
||||
{
|
||||
$percent = ( $current > 0 AND $total > 0 ) ? round( ($current / $total) * 100, 0 ) : 0;
|
||||
$percentString = str_pad( $percent, 6, ' ', STR_PAD_LEFT );
|
||||
$totalSize = $size + 9 + 33; # 23 is 'Processing: tablename'
|
||||
$output = '';
|
||||
|
||||
if ( $table !== null )
|
||||
{
|
||||
$tableName = ( mb_strlen( $table ) > 20 ) ? mb_substr( $table, 0, 20 ) : str_pad( $table, 20 );
|
||||
}
|
||||
else
|
||||
{
|
||||
$tableName = str_repeat( ' ', 20 );
|
||||
}
|
||||
|
||||
/* No progress bar for you! */
|
||||
if ( \IPSUtf8\Request::i()->isBasicClient() === true )
|
||||
{
|
||||
return "Processing: " . $tableName . '; Total complete: ' . $percent . "%\n";
|
||||
}
|
||||
|
||||
/* Remove previous bar */
|
||||
if ( static::$barDrawn === true )
|
||||
{
|
||||
for ( $i = $totalSize; $i > 0; $i-- )
|
||||
{
|
||||
$output .= "\x08";
|
||||
}
|
||||
}
|
||||
|
||||
$output .= "Processing: " . $tableName . ' ';
|
||||
|
||||
/* Print the bar */
|
||||
for ( $i = 0; $i <= $size; $i++ )
|
||||
{
|
||||
if ( $i <= ( $current / $total * $size ) )
|
||||
{
|
||||
$output .= "\033[42m \033[0m";
|
||||
}
|
||||
else
|
||||
{
|
||||
$output .= "\033[47m \033[0m";
|
||||
}
|
||||
}
|
||||
|
||||
$output .= ' ' . $percentString . '%';
|
||||
|
||||
static::$barDrawn = true;
|
||||
|
||||
return $output;
|
||||
}
|
||||
|
||||
/**
|
||||
* Send output and listen for a keypress
|
||||
*
|
||||
* @param string $output Content to output
|
||||
* @param int $httpStatusCode HTTP Status Code
|
||||
* @param string $contentType HTTP Content-type
|
||||
* @param array $httpHeaders Additional HTTP Headers
|
||||
* @return void
|
||||
*/
|
||||
public function sendOutput( $output='', $httpStatusCode=200, $contentType='text/plain', $httpHeaders=array() )
|
||||
{
|
||||
if ( mb_stristr( $output, "<warning>" ) )
|
||||
{
|
||||
if ( \IPSUtf8\Request::i()->isBasicClient() === true )
|
||||
{
|
||||
$output = str_replace( "<warning>" , "!! ", $output );
|
||||
$output = str_replace( "</warning>", " !!", $output );
|
||||
}
|
||||
else
|
||||
{
|
||||
$output = str_replace( "<warning>" , "\033[1;37m\033[41m", $output );
|
||||
$output = str_replace( "</warning>", "\033[0m", $output );
|
||||
}
|
||||
}
|
||||
|
||||
if ( mb_stristr( $output, "<good>" ) )
|
||||
{
|
||||
if ( \IPSUtf8\Request::i()->isBasicClient() === true )
|
||||
{
|
||||
$output = str_replace( "<good>" , "", $output );
|
||||
$output = str_replace( "</good>", "", $output );
|
||||
}
|
||||
else
|
||||
{
|
||||
$output = str_replace( "<good>" , "\033[1;37m\033[42m", $output );
|
||||
$output = str_replace( "</good>", "\033[0m", $output );
|
||||
}
|
||||
}
|
||||
|
||||
if ( mb_stristr( $output, "<choice>" ) )
|
||||
{
|
||||
if ( \IPSUtf8\Request::i()->isBasicClient() === true )
|
||||
{
|
||||
$output = str_replace( "<choice>" , "", $output );
|
||||
$output = str_replace( "</choice>", "", $output );
|
||||
}
|
||||
else
|
||||
{
|
||||
$output = str_replace( "<choice>" , "\033[1;32m", $output );
|
||||
$output = str_replace( "</choice>", "\033[0m", $output );
|
||||
}
|
||||
}
|
||||
|
||||
if ( $httpStatusCode != 101 )
|
||||
{
|
||||
$output .= "\n";
|
||||
}
|
||||
|
||||
$window = fopen('php://stdout', 'w');
|
||||
fwrite( $window, $output );
|
||||
fclose( $window );
|
||||
|
||||
if ( static::$stdin === null )
|
||||
{
|
||||
static::$stdin = fopen('php://stdin', 'r');
|
||||
}
|
||||
|
||||
if ( $httpStatusCode === 100 )
|
||||
{
|
||||
$this->response = trim( fgets( static::$stdin ) );
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,73 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Output Class
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Social Suite
|
||||
* @since 9 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8;
|
||||
|
||||
/**
|
||||
* Output Class
|
||||
*/
|
||||
abstract class Output
|
||||
{
|
||||
/**
|
||||
* @brief HTTP Statuses
|
||||
* @link http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html
|
||||
*/
|
||||
protected static $httpStatuses = array( 100 => 'Continue', 101 => 'Switching Protocols', 200 => 'OK', 201 => 'Created', 202 => 'Accepted', 203 => 'Non-Authoritative Information', 204 => 'No Content', 205 => 'Reset Content', 206 => 'Partial Content', 300 => 'Multiple Choices', 301 => 'Moved Permanently', 302 => 'Found', 303 => 'See Other', 304 => 'Not Modified', 305 => 'Use Proxy', 307 => 'Temporary Redirect', 400 => 'Bad Request', 401 => 'Unauthorized', 402 => 'Payment Required', 403 => 'Forbidden', 404 => 'Not Found', 405 => 'Method Not Allowed', 406 => 'Not Acceptable', 407 => 'Proxy Authentication Required', 408 => 'Request Timeout', 409 => 'Conflict', 411 => 'Length Required', 412 => 'Precondition Failed', 413 => 'Request Entity Too Large', 414 => 'Request-URI Too Long', 415 => 'Unsupported Media Type', 416 => 'Requested Range Not Satisfiable', 417 => 'Expectation Failed', 429 => 'Too Many Requests', 500 => 'Internal Server Error', 501 => 'Not Implemented', 502 => 'Bad Gateway', 503 => 'Service Unavailable', 504 => 'Gateway Timeout', 505 => 'HTTP Version Not Supported' );
|
||||
|
||||
/**
|
||||
* @brief Singleton Instance
|
||||
*/
|
||||
protected static $instance = NULL;
|
||||
|
||||
/**
|
||||
* Get instance
|
||||
*
|
||||
* @return \IPS\Request
|
||||
*/
|
||||
public static function i()
|
||||
{
|
||||
if( static::$instance === NULL )
|
||||
{
|
||||
$classname = get_called_class();
|
||||
static::$instance = new $classname;
|
||||
}
|
||||
|
||||
return static::$instance;
|
||||
}
|
||||
|
||||
/**
|
||||
* @brief Additional HTTP Headers
|
||||
*/
|
||||
public $httpHeaders = array();
|
||||
|
||||
/**
|
||||
* @brief Stored Page Title
|
||||
*/
|
||||
public $title = '';
|
||||
|
||||
/**
|
||||
* @brief Stored Content to output
|
||||
*/
|
||||
public $output = '';
|
||||
|
||||
|
||||
/**
|
||||
* Display Error Screen
|
||||
*
|
||||
* @param string $message language string for error message
|
||||
* @return void
|
||||
*/
|
||||
public function error( $message )
|
||||
{
|
||||
/* Send output */
|
||||
$this->sendOutput( "Error: " . $message );
|
||||
}
|
||||
}
|
||||
Whitespace-only changes.
@@ -0,0 +1,128 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Singleton Pattern
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Social Suite
|
||||
* @since 18 Feb 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Patterns;
|
||||
|
||||
/**
|
||||
* Singleton Pattern
|
||||
*/
|
||||
class Singleton implements \Iterator
|
||||
{
|
||||
/**
|
||||
* Get instance
|
||||
*
|
||||
* @return \IPS\Request
|
||||
*/
|
||||
public static function i()
|
||||
{
|
||||
if( static::$instance === NULL )
|
||||
{
|
||||
$classname = get_called_class();
|
||||
static::$instance = new $classname;
|
||||
}
|
||||
|
||||
return static::$instance;
|
||||
}
|
||||
|
||||
/**
|
||||
* @brief Data Store
|
||||
*/
|
||||
protected $data = array();
|
||||
|
||||
/**
|
||||
* Magic Method: Get
|
||||
*
|
||||
* @param mixed $key Key
|
||||
* @return mixed Value from the datastore
|
||||
*/
|
||||
public function __get( $key )
|
||||
{
|
||||
if( !isset( $this->data[ $key ] ) )
|
||||
{
|
||||
return NULL;
|
||||
}
|
||||
|
||||
return $this->data[ $key ];
|
||||
}
|
||||
|
||||
/**
|
||||
* Magic Method: Set
|
||||
*
|
||||
* @param mixed $key Key
|
||||
* @param mixed $value Value
|
||||
* @return void
|
||||
*/
|
||||
public function __set( $key, $value )
|
||||
{
|
||||
$this->data[ $key ] = $value;
|
||||
}
|
||||
|
||||
/**
|
||||
* Magic Method: Isset
|
||||
*
|
||||
* @param mixed $key Key
|
||||
* @return bool
|
||||
*/
|
||||
public function __isset( $key )
|
||||
{
|
||||
return isset( $this->data[ $key ] );
|
||||
}
|
||||
|
||||
/**
|
||||
* Iterator: Rewind
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
function rewind()
|
||||
{
|
||||
reset( $this->data );
|
||||
}
|
||||
|
||||
/**
|
||||
* Iterator: Current
|
||||
*
|
||||
* @return mixed
|
||||
*/
|
||||
function current()
|
||||
{
|
||||
return current( $this->data );
|
||||
}
|
||||
|
||||
/**
|
||||
* Iterator: Key
|
||||
*
|
||||
* @return mixed
|
||||
*/
|
||||
function key()
|
||||
{
|
||||
return key( $this->data );
|
||||
}
|
||||
|
||||
/**
|
||||
* Iterator: Next
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
function next()
|
||||
{
|
||||
next( $this->data );
|
||||
}
|
||||
|
||||
/**
|
||||
* Iterator: Valid
|
||||
*
|
||||
* @return bool
|
||||
*/
|
||||
function valid()
|
||||
{
|
||||
return key( $this->data ) !== null;
|
||||
}
|
||||
}
|
||||
Whitespace-only changes.
@@ -0,0 +1,284 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief HTTP Request Class
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Social Suite
|
||||
* @since 18 Feb 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8;
|
||||
|
||||
/**
|
||||
* HTTP Request Class
|
||||
*/
|
||||
class Request extends \IPSUtf8\Patterns\Singleton
|
||||
{
|
||||
/**
|
||||
* @brief Singleton Instance
|
||||
*/
|
||||
protected static $instance = NULL;
|
||||
|
||||
/**
|
||||
* @brief Cookie data
|
||||
*/
|
||||
public $cookie = array();
|
||||
|
||||
/**
|
||||
* Constructor
|
||||
*
|
||||
* @return void
|
||||
* @note We do not unset $_COOKIE as it is needed by session handling
|
||||
*/
|
||||
public function __construct()
|
||||
{
|
||||
$this->parseIncomingRecursively( $_GET );
|
||||
$this->parseIncomingRecursively( $_POST );
|
||||
|
||||
array_walk_recursive( $_COOKIE, array( $this, 'clean' ) );
|
||||
$this->cookie = $_COOKIE;
|
||||
|
||||
unset( $_GET );
|
||||
unset( $_POST );
|
||||
unset( $_REQUEST );
|
||||
}
|
||||
|
||||
/**
|
||||
* Delete original tables
|
||||
*
|
||||
* @return boolean
|
||||
*/
|
||||
public function isDeleteOriginals()
|
||||
{
|
||||
return ( IS_CLI AND $GLOBALS['argv'][1] == '--deleteOriginals' );
|
||||
}
|
||||
/**
|
||||
* Detect if this is using the "dump" method
|
||||
*
|
||||
* @return boolean
|
||||
*/
|
||||
public function isDumpMethod()
|
||||
{
|
||||
return ( IS_CLI AND $GLOBALS['argv'][1] == '--dump' );
|
||||
}
|
||||
|
||||
/**
|
||||
* Detect if this is using the "info" method
|
||||
*
|
||||
* @return boolean
|
||||
*/
|
||||
public function isInfo()
|
||||
{
|
||||
return ( IS_CLI AND $GLOBALS['argv'][1] == '--info' );
|
||||
}
|
||||
|
||||
/**
|
||||
* Detect if this is using the "restore orig tables" method
|
||||
*
|
||||
* @return boolean
|
||||
*/
|
||||
public function isRestore()
|
||||
{
|
||||
return ( IS_CLI AND $GLOBALS['argv'][1] == '--restore' );
|
||||
}
|
||||
|
||||
/**
|
||||
* Detect if this is windows command prompt or another similar basic client
|
||||
*
|
||||
* @return boolean
|
||||
*/
|
||||
public function isBasicClient()
|
||||
{
|
||||
return ( IS_CLI AND $GLOBALS['argv'][1] == '--basic' );
|
||||
}
|
||||
|
||||
/**
|
||||
* Parse Incoming Data
|
||||
*
|
||||
* @param array $data Data
|
||||
* @return void
|
||||
*/
|
||||
protected function parseIncomingRecursively( $data )
|
||||
{
|
||||
foreach( $data as $k => $v )
|
||||
{
|
||||
if ( is_array( $v ) )
|
||||
{
|
||||
array_walk_recursive( $v, array( $this, 'clean' ) );
|
||||
}
|
||||
else
|
||||
{
|
||||
$this->clean( $v, $k );
|
||||
}
|
||||
|
||||
$this->$k = $v;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Clean Value
|
||||
*
|
||||
* @param mixed $v Value
|
||||
* @param mixed $k Key
|
||||
* @return mixed
|
||||
*/
|
||||
protected function clean( &$v, $k )
|
||||
{
|
||||
/* Remove NULL bytes and the RTL control byte */
|
||||
$v = str_replace( array( "\0", "\u202E" ), '', $v );
|
||||
|
||||
/* Undo magic quote madness */
|
||||
if ( get_magic_quotes_gpc() === 1 )
|
||||
{
|
||||
$v = stripslashes( $v );
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Get value from array
|
||||
*
|
||||
* @param string Key with square brackets (e.g. "foo[bar]")
|
||||
* @return mixed Value
|
||||
*/
|
||||
public function valueFromArray( $key )
|
||||
{
|
||||
$array = $this->data;
|
||||
while ( $pos = mb_strpos( $key, '[' ) )
|
||||
{
|
||||
preg_match( '/^(.+?)\[(.+?)?\](.*)?$/', $key, $matches );
|
||||
|
||||
if ( !array_key_exists( $matches[1], $array ) )
|
||||
{
|
||||
return NULL;
|
||||
}
|
||||
|
||||
$array = $array[ $matches[1] ];
|
||||
$key = $matches[2] . $matches[3];
|
||||
}
|
||||
|
||||
if ( !isset( $array[ $key ] ) )
|
||||
{
|
||||
return NULL;
|
||||
}
|
||||
|
||||
return $array[ $key ];
|
||||
}
|
||||
|
||||
/**
|
||||
* Is this an AJAX request?
|
||||
*
|
||||
* @return bool
|
||||
*/
|
||||
public function isAjax()
|
||||
{
|
||||
return ( isset( $_SERVER['HTTP_X_REQUESTED_WITH'] ) and $_SERVER['HTTP_X_REQUESTED_WITH'] == 'XMLHttpRequest' );
|
||||
}
|
||||
|
||||
/**
|
||||
* Is this an SSL/Secure request?
|
||||
*
|
||||
* @return bool
|
||||
* @see <a href='http://community.invisionpower.com/resources/bugs.html/_/ip-board/ipboard-cant-detect-https-if-behind-an-ssl-terminating-load-balancer-r42909'>Load balancer SSL</a>
|
||||
* @note A common technique to check for SSL is to look for $_SERVER['SERVER_PORT'] == 443, however this is not a correct check. Nothing requires SSL to be on port 443, or http to be on port 80.
|
||||
* @see <a href='http://community.invisionpower.com/resources/bugs.html/_/ips-4-0/ipsrequestissecure-r45082'>Zeus load balancers set HTTP_SSLSESSIONID</a>
|
||||
*/
|
||||
public function isSecure()
|
||||
{
|
||||
if( !empty( $_SERVER['HTTPS'] ) AND mb_strtolower( $_SERVER['HTTPS'] ) == 'on' )
|
||||
{
|
||||
return TRUE;
|
||||
}
|
||||
else if( !empty( $_SERVER['HTTP_X_FORWARDED_PROTO'] ) AND mb_strtolower( $_SERVER['HTTP_X_FORWARDED_PROTO'] ) == 'https' )
|
||||
{
|
||||
return TRUE;
|
||||
}
|
||||
else if ( !empty( $_SERVER['HTTP_X_FORWARDED_HTTPS'] ) AND mb_strtolower( $_SERVER['HTTP_X_FORWARDED_HTTPS'] ) == 'https' )
|
||||
{
|
||||
return TRUE;
|
||||
}
|
||||
else if( !empty( $_SERVER['HTTP_FRONT_END_HTTPS'] ) AND mb_strtolower( $_SERVER['HTTP_FRONT_END_HTTPS'] ) == 'on' )
|
||||
{
|
||||
return TRUE;
|
||||
}
|
||||
else if( !empty( $_SERVER['HTTP_SSLSESSIONID'] ) )
|
||||
{
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
return FALSE;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get Current URL
|
||||
*
|
||||
* @return string
|
||||
*/
|
||||
public function url()
|
||||
{
|
||||
return ( ( static::isSecure() ? 'https://' : 'http://' ) . $_SERVER['SERVER_NAME'] . ( ( $_SERVER['SERVER_PORT'] != 80 ) ? ":{$_SERVER['SERVER_PORT']}" : '' ) . $_SERVER['REQUEST_URI'] );
|
||||
}
|
||||
|
||||
/**
|
||||
* Get IP Address
|
||||
*
|
||||
* @return string
|
||||
*/
|
||||
public function ipAddress()
|
||||
{
|
||||
if ( \IPS\Settings::i()->xforward_matching )
|
||||
{
|
||||
foreach( explode( ',', $_SERVER['HTTP_X_FORWARDED_FOR'] ) as $x_f )
|
||||
{
|
||||
$addrs[] = trim( $x_f );
|
||||
}
|
||||
|
||||
$addrs[] = $_SERVER['HTTP_CLIENT_IP'];
|
||||
$addrs[] = $_SERVER['HTTP_X_CLUSTER_CLIENT_IP'];
|
||||
$addrs[] = $_SERVER['HTTP_PROXY_USER'];
|
||||
}
|
||||
|
||||
$addrs[] = $_SERVER['REMOTE_ADDR'];
|
||||
|
||||
foreach ( $addrs as $ip )
|
||||
{
|
||||
if ( filter_var( $ip, FILTER_VALIDATE_IP ) )
|
||||
{
|
||||
return $ip;
|
||||
}
|
||||
}
|
||||
|
||||
return '';
|
||||
}
|
||||
|
||||
/**
|
||||
* Set a cookie
|
||||
*
|
||||
* @param string $name Name
|
||||
* @param mixed $value Value
|
||||
* @param \IPS\DateTime|null $expire Expiration date, or NULL for on session end
|
||||
* @param bool $httpOnly When TRUE the cookie will be made accessible only through the HTTP protocol
|
||||
* @param string|null $domain Domain to set to. If NULL, will be detected automatically.
|
||||
* @param string|null $path Path to set to. If NULL, will be detected automatically.
|
||||
* @return bool
|
||||
*/
|
||||
public function setCookie( $name, $value, $expire=NULL, $httpOnly=TRUE, $domain=NULL, $path=NULL )
|
||||
{
|
||||
/* Work out the path */
|
||||
if ( $path === NULL )
|
||||
{
|
||||
$path = mb_substr( \IPS\Settings::i()->base_url, mb_strpos( \IPS\Settings::i()->base_url, $_SERVER['SERVER_NAME'] ) + mb_strlen( $_SERVER['SERVER_NAME'] ) );
|
||||
$path = mb_substr( $path, mb_strpos( $path, '/' ) );
|
||||
}
|
||||
|
||||
/* Set the cookie */
|
||||
if ( setcookie( $name, $value, $expire ? $expire->getTimestamp() : 0, $path, $domain ?: $_SERVER['SERVER_NAME'], FALSE, $httpOnly ) === TRUE )
|
||||
{
|
||||
$this->cookie[ $name ] = $value;
|
||||
return TRUE;
|
||||
}
|
||||
return FALSE;
|
||||
}
|
||||
|
||||
}
|
||||
Whitespace-only changes.
@@ -0,0 +1,612 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Session Handler
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Social Suite
|
||||
* @since 6th Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8;
|
||||
|
||||
/**
|
||||
* Session Handler
|
||||
*/
|
||||
class Session
|
||||
{
|
||||
/**
|
||||
* @brief Tables
|
||||
*/
|
||||
public $tables = NULL;
|
||||
|
||||
/**
|
||||
* @brief Singleton Instance
|
||||
*/
|
||||
protected static $instance = NULL;
|
||||
|
||||
/**
|
||||
* @brief Database Table Columns
|
||||
*/
|
||||
protected static $tableTableColumns = array(
|
||||
array(
|
||||
'name' => 'table_name',
|
||||
'type' => 'TEXT',
|
||||
'length' => false,
|
||||
'null' => false,
|
||||
'default' => null
|
||||
),
|
||||
array(
|
||||
'name' => 'table_schema',
|
||||
'type' => 'MEDIUMTEXT',
|
||||
'length' => false,
|
||||
'null' => true,
|
||||
'default' => null
|
||||
)
|
||||
);
|
||||
|
||||
/**
|
||||
* @brief Database Table Columns
|
||||
*/
|
||||
protected static $sessionTableColumns = array(
|
||||
array(
|
||||
'name' => 'session_start',
|
||||
'type' => 'INT',
|
||||
'length' => 10,
|
||||
'null' => false,
|
||||
'default' => 0
|
||||
),
|
||||
array(
|
||||
'name' => 'session_updated',
|
||||
'type' => 'INT',
|
||||
'length' => 10,
|
||||
'null' => false,
|
||||
'default' => 0
|
||||
),
|
||||
array(
|
||||
'name' => 'session_status',
|
||||
'type' => 'VARCHAR',
|
||||
'length' => 255,
|
||||
'null' => true,
|
||||
'default' => 0
|
||||
),
|
||||
array(
|
||||
'name' => 'session_current_charset',
|
||||
'type' => 'VARCHAR',
|
||||
'length' => 255,
|
||||
'null' => true,
|
||||
'default' => 0
|
||||
),
|
||||
array(
|
||||
'name' => 'session_current_table',
|
||||
'type' => 'VARCHAR',
|
||||
'length' => 255,
|
||||
'null' => true,
|
||||
'default' => 0
|
||||
),
|
||||
array(
|
||||
'name' => 'session_current_pkey',
|
||||
'type' => 'VARCHAR',
|
||||
'length' => 255,
|
||||
'null' => true,
|
||||
'default' => 0
|
||||
),
|
||||
array(
|
||||
'name' => 'session_current_row',
|
||||
'type' => 'VARCHAR',
|
||||
'length' => 255,
|
||||
'null' => true,
|
||||
'default' => 0
|
||||
),
|
||||
array(
|
||||
'name' => 'session_completed_json',
|
||||
'type' => 'MEDIUMTEXT',
|
||||
'length' => false,
|
||||
'null' => true,
|
||||
'default' => 0
|
||||
),
|
||||
array(
|
||||
'name' => 'session_json',
|
||||
'type' => 'MEDIUMTEXT',
|
||||
'length' => false,
|
||||
'null' => true,
|
||||
'default' => 0
|
||||
),
|
||||
array(
|
||||
'name' => 'session_has_archive',
|
||||
'type' => 'INT',
|
||||
'length' => 1,
|
||||
'null' => true,
|
||||
'default' => 0
|
||||
),
|
||||
array(
|
||||
'name' => 'session_processing_archive',
|
||||
'type' => 'INT',
|
||||
'length' => 1,
|
||||
'null' => true,
|
||||
'default' => 0
|
||||
),
|
||||
array(
|
||||
'name' => 'session_is_ipb',
|
||||
'type' => 'INT',
|
||||
'length' => 1,
|
||||
'null' => true,
|
||||
'default' => 0
|
||||
),
|
||||
);
|
||||
|
||||
/**
|
||||
* @brief Data Store
|
||||
*/
|
||||
protected $_data = NULL;
|
||||
|
||||
/**
|
||||
* @brief Changed Columns
|
||||
*/
|
||||
public $changed = array();
|
||||
|
||||
/**
|
||||
* Get instance
|
||||
*
|
||||
* @return Output
|
||||
*/
|
||||
public static function i()
|
||||
{
|
||||
if ( self::$instance === NULL )
|
||||
{
|
||||
self::$instance = new self();
|
||||
self::$instance->init();
|
||||
}
|
||||
|
||||
return self::$instance;
|
||||
}
|
||||
|
||||
/**
|
||||
* Init
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function init()
|
||||
{
|
||||
/* Check to see if the session table exists */
|
||||
if ( file_exists( ROOT_PATH . '/conf_global.php' ) )
|
||||
{
|
||||
require( ROOT_PATH . '/conf_global.php' );
|
||||
}
|
||||
|
||||
$setDefault = false;
|
||||
|
||||
if ( ! \IPSUtf8\Db::i('utf8')->checkForTable( 'convert_session_tables' ) )
|
||||
{
|
||||
\IPSUtf8\Db::i('utf8')->createTable( array(
|
||||
'name' => 'convert_session_tables',
|
||||
'columns' => static::$tableTableColumns
|
||||
) );
|
||||
|
||||
$setDefault = true;
|
||||
}
|
||||
|
||||
if ( ! \IPSUtf8\Db::i('utf8')->checkForTable( 'convert_session' ) )
|
||||
{
|
||||
\IPSUtf8\Db::i('utf8')->createTable( array(
|
||||
'name' => 'convert_session',
|
||||
'columns' => static::$sessionTableColumns
|
||||
) );
|
||||
|
||||
$setDefault = true;
|
||||
}
|
||||
else
|
||||
{
|
||||
try
|
||||
{
|
||||
$this->_data = \IPSUtf8\Db::i('utf8')->select( '*', 'convert_session' )->first();
|
||||
|
||||
if ( ! isset( $this->_data['session_json'] ) )
|
||||
{
|
||||
$setDefault = true;
|
||||
}
|
||||
}
|
||||
catch( \UnderflowException $ex )
|
||||
{
|
||||
$setDefault = true;
|
||||
}
|
||||
}
|
||||
|
||||
if ( $setDefault === true )
|
||||
{
|
||||
$this->reset();
|
||||
}
|
||||
|
||||
/* Populate tables */
|
||||
foreach( \IPSUtf8\Db::i('utf8')->select( '*', 'convert_session_tables' ) as $row )
|
||||
{
|
||||
$this->tables[ $row['table_name'] ] = json_decode( $row['table_schema'], true );
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Reset the session and conversion process
|
||||
*/
|
||||
public function reset()
|
||||
{
|
||||
$charSet = null;
|
||||
$ipbVersion = null;
|
||||
|
||||
/* Is this an IPB? */
|
||||
if ( \IPSUtf8\Db::i()->checkForTable('core_applications' ) )
|
||||
{
|
||||
try
|
||||
{
|
||||
$row = \IPSUtf8\Db::i()->select( '*', 'core_applications', array( 'app_directory=?', 'core' ) )->first();
|
||||
|
||||
if ( ! empty( $row['app_directory'] ) )
|
||||
{
|
||||
$ipbVersion = $row['app_long_version'];
|
||||
}
|
||||
}
|
||||
catch( \UnderflowException $ex ) { }
|
||||
}
|
||||
|
||||
if ( $ipbVersion >= 40000 )
|
||||
{
|
||||
/* >= 4.0 is UTF-8 */
|
||||
$charSet = 'utf-8';
|
||||
}
|
||||
else if ( $ipbVersion !== null )
|
||||
{
|
||||
/* Attempt to grab current CHARSET if this is an IPB 3 */
|
||||
if ( \IPSUtf8\Db::i()->checkForTable('core_sys_conf_settings' ) )
|
||||
{
|
||||
try
|
||||
{
|
||||
$row = \IPSUtf8\Db::i()->select( '*', 'core_sys_conf_settings', array( 'conf_key=?', 'gb_char_set' ) )->first();
|
||||
|
||||
if ( ! empty( $row['conf_key'] ) )
|
||||
{
|
||||
$charSet = ( $row['conf_value'] ) ? $row['conf_value'] : $row['conf_default'];
|
||||
}
|
||||
}
|
||||
catch( \UnderflowException $ex ) { }
|
||||
}
|
||||
}
|
||||
|
||||
$tableData = $this->_getTables();
|
||||
|
||||
\IPSUtf8\Db::i('utf8')->delete( 'convert_session_tables' );
|
||||
|
||||
foreach( $tableData['tables'] as $name => $schema )
|
||||
{
|
||||
\IPSUtf8\Db::i('utf8')->insert( 'convert_session_tables', array(
|
||||
'table_name' => $name,
|
||||
'table_schema' => json_encode( $schema )
|
||||
) );
|
||||
}
|
||||
|
||||
$this->_data = array(
|
||||
'session_start' => time(),
|
||||
'session_updated' => time(),
|
||||
'session_status' => null,
|
||||
'session_current_charset' => strtolower( $charSet ),
|
||||
'session_current_table' => null,
|
||||
'session_current_pkey' => null,
|
||||
'session_current_row' => 0,
|
||||
'session_completed_json' => json_encode( array() ),
|
||||
'session_json' => json_encode( $tableData['data'] ),
|
||||
'session_has_archive' => 0,
|
||||
'session_processing_archive' => 0,
|
||||
'session_is_ipb' => $ipbVersion === null ? false : true
|
||||
|
||||
);
|
||||
|
||||
/* Change database collation */
|
||||
require( ROOT_PATH . '/conf_global.php' );
|
||||
|
||||
if ( ! empty( $INFO['archive_remote_sql_host'] ) AND ! empty( $INFO['archive_remote_sql_database'] ) AND ! empty( $INFO['archive_remote_sql_user'] ) )
|
||||
{
|
||||
$this->_data['session_has_archive'] = 1;
|
||||
}
|
||||
|
||||
\IPSUtf8\Db::i('utf8')->delete( 'convert_session' );
|
||||
\IPSUtf8\Db::i('utf8')->insert( 'convert_session', $this->_data );
|
||||
}
|
||||
|
||||
/**
|
||||
* Update 'all_tables'
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function updateTableData()
|
||||
{
|
||||
$tableData = $this->_getTables();
|
||||
|
||||
\IPSUtf8\Db::i('utf8')->delete( 'convert_session_tables' );
|
||||
|
||||
foreach( $tableData['tables'] as $name => $schema )
|
||||
{
|
||||
\IPSUtf8\Db::i('utf8')->insert( 'convert_session_tables', array(
|
||||
'table_name' => $name,
|
||||
'table_schema' => json_encode( $schema )
|
||||
) );
|
||||
}
|
||||
|
||||
/* Populate tables */
|
||||
foreach( \IPSUtf8\Db::i('utf8')->select( '*', 'convert_session_tables' ) as $row )
|
||||
{
|
||||
$this->tables[ $row['table_name'] ] = json_decode( $row['table_schema'], true );
|
||||
}
|
||||
|
||||
$this->save();
|
||||
}
|
||||
|
||||
/**
|
||||
* Grab all tables in the database that we're going to convert
|
||||
*
|
||||
* @return array
|
||||
*/
|
||||
protected function _getTables()
|
||||
{
|
||||
/* Grab all tables to convert */
|
||||
$stmt = \IPSUtf8\Db::i()->prepare( "SHOW TABLES" );
|
||||
$stmt->execute();
|
||||
$stmt->bind_result( $tableName );
|
||||
|
||||
$tables = array();
|
||||
$allTables = array();
|
||||
$data = array( 'version' => \IPSUtf8\Convert::VERSION_ID, 'tableCount' => 0, 'totalCount' => 0, 'convertedCount' => 0, 'charSets' => array() );
|
||||
|
||||
if ( defined( 'FORCE_CONVERT' ) AND FORCE_CONVERT === TRUE )
|
||||
{
|
||||
$data['force_conversion'] = 1;
|
||||
}
|
||||
|
||||
while ( $stmt->fetch() === true )
|
||||
{
|
||||
/* Skip x_utf_ prefixed tables in case we don't have a prefix set */
|
||||
if ( mb_substr( $tableName, 0, 6 ) === 'x_utf_' )
|
||||
{
|
||||
continue;
|
||||
}
|
||||
|
||||
if ( mb_substr( $tableName, 0, 5 ) === 'orig_' )
|
||||
{
|
||||
continue;
|
||||
}
|
||||
|
||||
if ( mb_substr( $tableName, 0, mb_strlen( \IPSUtf8\Db::i()->prefix ) ) === \IPSUtf8\Db::i()->prefix )
|
||||
{
|
||||
$tableNameNoPrefix = $tableName;
|
||||
|
||||
if ( \IPSUtf8\Db::i()->prefix )
|
||||
{
|
||||
$tableNameNoPrefix = mb_substr( $tableName, mb_strlen( \IPSUtf8\Db::i()->prefix ) );
|
||||
}
|
||||
|
||||
$tables[] = $tableNameNoPrefix;
|
||||
}
|
||||
}
|
||||
|
||||
foreach( $tables as $table )
|
||||
{
|
||||
/* Get count */
|
||||
$row = \IPSUtf8\Db::i()->query( "SELECT COUNT(*) as count FROM `" . \IPSUtf8\Db::i()->prefix . "{$table}`" )->fetch_assoc();
|
||||
$count = $row['count'];
|
||||
|
||||
$data['totalCount'] += $count;
|
||||
$data['tableCount']++;
|
||||
|
||||
$row = \IPSUtf8\Db::i()->query( "SHOW CREATE TABLE `" . \IPSUtf8\Db::i()->prefix . "{$table}`" )->fetch_assoc();
|
||||
|
||||
if ( preg_match( '#\scharset=([a-z0-9]+?)(\s|$)#i', $row['Create Table'], $matches ) )
|
||||
{
|
||||
$tblCharset = $matches[1];
|
||||
|
||||
$data['charSets'][ mb_strtolower( $tblCharset ) ][] = $table;
|
||||
}
|
||||
else
|
||||
{
|
||||
$row = \IPSUtf8\Db::i()->query( "SHOW TABLE STATUS WHERE Name='" . \IPSUtf8\Db::i()->prefix . "{$table}'" )->fetch_assoc();
|
||||
|
||||
if ( isset( $row['Collation'] ) )
|
||||
{
|
||||
$tblCharset = mb_substr( $row['Collation'], 0, strpos( $row['Collation'], '_' ) );
|
||||
|
||||
$data['charSets'][ mb_strtolower( $tblCharset ) ][] = $table;
|
||||
}
|
||||
else
|
||||
{
|
||||
$data['charSets'][ mb_strtolower( \IPSUtf8\Convert::i()->database_charset ) ][] = $table;
|
||||
}
|
||||
}
|
||||
|
||||
/* Make sure we can JSON Encode this table... MySQL Comments with UTF8 characters can cause it to fail */
|
||||
$definition = \IPSUtf8\Db::i()->getTableDefinition( $table );
|
||||
|
||||
try
|
||||
{
|
||||
$test = @json_encode( $definition );
|
||||
}
|
||||
catch( \ErrorException $e )
|
||||
{
|
||||
$definition = static::arrayWalkRecursive( $definition, function( $value ) { return utf8_encode( $value ); } );
|
||||
}
|
||||
|
||||
/* Get other data */
|
||||
$allTables[ $table ] = array(
|
||||
'name' => $table,
|
||||
'definition' => $definition,
|
||||
'count' => $count,
|
||||
'charset' => $tblCharset
|
||||
);
|
||||
}
|
||||
|
||||
return array( 'tables' => $allTables, 'data' => $data );
|
||||
}
|
||||
|
||||
/**
|
||||
* Save the state of the conversion
|
||||
*/
|
||||
public function __destruct()
|
||||
{
|
||||
$this->save();
|
||||
}
|
||||
|
||||
/**
|
||||
* Get value from data store
|
||||
*
|
||||
* @param mixed $key Key
|
||||
* @return mixed Value from the datastore
|
||||
*/
|
||||
public function __get( $key )
|
||||
{
|
||||
if ( mb_substr( $key, 0, 8 ) != 'session_' )
|
||||
{
|
||||
$key = 'session_' . $key;
|
||||
}
|
||||
|
||||
if( isset( $this->_data[ $key ] ) )
|
||||
{
|
||||
if ( mb_substr( $key, -5 ) == '_json' AND ! is_array( $this->_data[ $key ] ) )
|
||||
{
|
||||
$this->_data[ $key ] = json_decode( $this->_data[ $key ], true );
|
||||
}
|
||||
|
||||
return $this->_data[ $key ];
|
||||
}
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
/**
|
||||
* Magic isset method
|
||||
*
|
||||
* @param string $key Key
|
||||
*/
|
||||
public function __isset( $key )
|
||||
{
|
||||
if ( mb_substr( $key, 0, 8 ) != 'session_' )
|
||||
{
|
||||
$key = 'session_' . $key;
|
||||
}
|
||||
|
||||
return isset( $this->_data[ $key ] );
|
||||
}
|
||||
|
||||
/**
|
||||
* Set value in data store
|
||||
*
|
||||
* @param mixed $key Key
|
||||
* @param mixed $value Value
|
||||
* @return void
|
||||
*/
|
||||
public function __set( $key, $value )
|
||||
{
|
||||
if ( mb_substr( $key, 0, 8 ) != 'session_' )
|
||||
{
|
||||
$key = 'session_' . $key;
|
||||
}
|
||||
|
||||
if( array_key_exists( $key, $this->_data ) )
|
||||
{
|
||||
$this->_data[ $key ] = $value;
|
||||
$this->changed[ $key ] = $value;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Time taken for conversion
|
||||
*
|
||||
* @param bool $formatted Return the time formatted or in seconds
|
||||
* @return mixed
|
||||
*/
|
||||
public function timeTaken( $formatted=false )
|
||||
{
|
||||
$seconds = ( $this->_data['session_updated'] - $this->_data['session_start'] );
|
||||
|
||||
if ( $formatted )
|
||||
{
|
||||
$s = $seconds % 60;
|
||||
$m = floor( ( $seconds % 3600 ) / 60 );
|
||||
$h = floor( ( $seconds % 86400 ) / 3600 );
|
||||
|
||||
if ( $h )
|
||||
{
|
||||
return "{$h} hour(s), {$m} minute(s) and {$s} seconds.";
|
||||
}
|
||||
else
|
||||
{
|
||||
return "{$m} minute(s) and {$s} seconds.";
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
return $seconds;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Save Changed Columns
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function save()
|
||||
{
|
||||
$this->_data['session_updated'] = time();
|
||||
$insert = array( 'session_updated' => time() );
|
||||
|
||||
if ( ! empty( $this->changed ) )
|
||||
{
|
||||
/* JSON encode if required */
|
||||
foreach ( array_merge( $this->_data, $this->changed ) as $k => $v )
|
||||
{
|
||||
$insert[ $k ] = ( mb_substr( $k, -5 ) == '_json' AND is_array( $v ) ) ? json_encode( $v, true ) : $v;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
foreach ( $this->_data as $k => $v )
|
||||
{
|
||||
$insert[ $k ] = ( mb_substr( $k, -5 ) == '_json' AND is_array( $v ) ) ? json_encode( $v, true ) : $v;
|
||||
}
|
||||
}
|
||||
|
||||
/* Save */
|
||||
if ( count( $insert ) == count( static::$sessionTableColumns ) )
|
||||
{
|
||||
\IPSUtf8\Db::i('utf8')->update( 'convert_session', $insert );
|
||||
}
|
||||
|
||||
/* Reset our log of what's changed */
|
||||
$this->changed = array();
|
||||
|
||||
}
|
||||
|
||||
/**
|
||||
* Recursively apply a callback to an array - array_walk_recursive does not recurse into sub-sub-arrays, so we need a custom method
|
||||
*
|
||||
* @param array $array The array
|
||||
* @param callback $callback The callback
|
||||
* @return array The filtered array.
|
||||
*/
|
||||
public function arrayWalkRecursive( $array, $callback )
|
||||
{
|
||||
if ( ! is_array( $array ) )
|
||||
{
|
||||
trigger_error( "\$array is not an array in \IPSUtf8\Session::arrayWalkRecursive()", E_USER_ERROR );
|
||||
}
|
||||
|
||||
foreach( $array AS $key => $value )
|
||||
{
|
||||
if ( is_array( $array[$key] ) )
|
||||
{
|
||||
$array[$key] = static::arrayWalkRecursive( $array[$key], $callback );
|
||||
}
|
||||
else
|
||||
{
|
||||
$array[$key] = $callback( $value );
|
||||
}
|
||||
}
|
||||
|
||||
return $array;
|
||||
}
|
||||
}
|
||||
Whitespace-only changes.
@@ -0,0 +1,131 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Conversion module
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Tools
|
||||
* @since 4 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Text;
|
||||
|
||||
/**
|
||||
* Conversion class
|
||||
* Refactored from IPB 3.x
|
||||
*/
|
||||
abstract class Charset
|
||||
{
|
||||
/**
|
||||
* @brief Array of error messages associated with the conversion
|
||||
*/
|
||||
public static $errors = array();
|
||||
|
||||
/**
|
||||
* @brief Conversion method to use
|
||||
*/
|
||||
public static $method = NULL;
|
||||
|
||||
/**
|
||||
* @brief Should characters be turned into numeric entities
|
||||
*/
|
||||
protected static $entities = false;
|
||||
|
||||
/**
|
||||
* @brief Path for character sets
|
||||
*/
|
||||
protected static $charsetPath = '';
|
||||
|
||||
/**
|
||||
* @brief Multiton Store
|
||||
*/
|
||||
protected static $multitons = array();
|
||||
|
||||
/**
|
||||
* Constructor
|
||||
*/
|
||||
public static function i()
|
||||
{
|
||||
if ( self::$method === NULL )
|
||||
{
|
||||
/* Try and pick best available */
|
||||
if ( FORCE_CONVERT_METHOD === NULL )
|
||||
{
|
||||
if ( function_exists( 'mb_convert_encoding' ) )
|
||||
{
|
||||
self::$method = 'mb';
|
||||
}
|
||||
else if ( function_exists( 'iconv' ) )
|
||||
{
|
||||
self::$method = 'iconv';
|
||||
}
|
||||
else if ( function_exists( 'recode_string' ) )
|
||||
{
|
||||
self::$method = 'recode';
|
||||
}
|
||||
else
|
||||
{
|
||||
self::$method = 'internal';
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
self::$method = FORCE_CONVERT_METHOD;
|
||||
}
|
||||
}
|
||||
|
||||
self::$method = ucfirst( self::$method );
|
||||
|
||||
if ( ! isset( static::$multitons[ self::$method ] ) )
|
||||
{
|
||||
$classname = "\\IPSUtf8\\Text\\Module\\" . self::$method;
|
||||
static::$multitons[ self::$method ] = new $classname;
|
||||
}
|
||||
|
||||
return new static::$multitons[ self::$method ];
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks a string to see if conversion is required
|
||||
*
|
||||
* @param string Text string
|
||||
* @param string Text string char set (original)
|
||||
* @param string Desired character set (destination)
|
||||
* @return @e string
|
||||
*/
|
||||
public static function needsConverting( $string, $from, $to='UTF-8' )
|
||||
{
|
||||
$from = strtolower($from);
|
||||
$to = strtolower($to);
|
||||
|
||||
/* Return bools, null, ints, etc. */
|
||||
if ( ! is_string( $string ) )
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
/* Return if latin only */
|
||||
if ( preg_match( '/^([a-zA-Z0-9_\-\.:;\[\]\{\}\!\@\£\$\%\^\&\*\(\)\+\=\"\'\<\>\/]+?)$/', $string ) )
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if ( $to == $from )
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if( ! $from )
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if( !$string OR $string == '' )
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,45 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Conversion module
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Tools
|
||||
* @since 4 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Text\Module;
|
||||
|
||||
/**
|
||||
* Native MB Conversion class
|
||||
*/
|
||||
class Iconv extends \IPSUtf8\Text\Charset
|
||||
{
|
||||
/**
|
||||
* Converts a text string from its current charset to a destination charset using iconv
|
||||
*
|
||||
* @param string Text string
|
||||
* @param string Text string char set (original)
|
||||
* @param string Desired character set (destination)
|
||||
* @return @e string
|
||||
*/
|
||||
public function convert( $string, $from, $to='UTF-8' )
|
||||
{
|
||||
if ( static::needsConverting( $string, $from, $to ) === false )
|
||||
{
|
||||
return $string;
|
||||
}
|
||||
|
||||
if ( function_exists( 'iconv' ) )
|
||||
{
|
||||
$text = iconv( $from, $to.'//TRANSLIT', $string );
|
||||
}
|
||||
else
|
||||
{
|
||||
static::$errors[] = "NO_ICONV_FUNCTION";
|
||||
}
|
||||
|
||||
return $text ? $text : $string;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,410 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Conversion module
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Tools
|
||||
* @since 4 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Text\Module;
|
||||
|
||||
/**
|
||||
* Native MB Conversion class
|
||||
*/
|
||||
class Internal extends \IPSUtf8\Text\Charset
|
||||
{
|
||||
/**
|
||||
* Converts a text string from its current charset to a destination charset using internal conversion class.
|
||||
* The bulk of this function was written by Mikolaj Jedrzejak and used with permission via the License
|
||||
*
|
||||
* @param string Text string
|
||||
* @param string Text string char set (original)
|
||||
* @param string Desired character set (destination)
|
||||
* @return @e string
|
||||
*/
|
||||
public function convert( $string, $from, $to='UTF-8' )
|
||||
{
|
||||
if ( static::needsConverting( $string, $from, $to ) === false )
|
||||
{
|
||||
return $string;
|
||||
}
|
||||
|
||||
$text = '';
|
||||
$original = $string;
|
||||
$from = strtolower( $from );
|
||||
$to = strtolower( $to );
|
||||
|
||||
if( !static::$charsetPath )
|
||||
{
|
||||
static::$charsetPath = THIS_PATH . '/system/i18n/ConvertTables/';
|
||||
}
|
||||
|
||||
/**
|
||||
* This divison was made to prevent errors during convertion to/from utf-8 with
|
||||
* "entities" enabled, because we need to use proper destination(to)/source(from)
|
||||
* encoding table to write proper entities.
|
||||
*
|
||||
* This is the first case. We are converting from 1byte chars...
|
||||
*/
|
||||
if ($from != "utf-8")
|
||||
{
|
||||
/* Cache the conversion table to prevent rebuilding on every request */
|
||||
static $charsetTables = array();
|
||||
|
||||
/**
|
||||
* Now build table with both charsets for encoding change.
|
||||
*/
|
||||
if( !isset( $charsetTables[ $from ] ) )
|
||||
{
|
||||
if ($to != "utf-8")
|
||||
{
|
||||
$charsetTables[ $from ] = self::_makeConversionTable( $from, $to );
|
||||
}
|
||||
else
|
||||
{
|
||||
$charsetTables[ $from ] = self::_makeConversionTable( $from );
|
||||
}
|
||||
}
|
||||
|
||||
$charsetTable = $charsetTables[ $from ];
|
||||
|
||||
if( !count($charsetTable) )
|
||||
{
|
||||
static::$errors[] = "Character set table not found";
|
||||
return $original;
|
||||
}
|
||||
|
||||
/**
|
||||
* For each char in a string...
|
||||
*/
|
||||
for ($i = 0; $i < strlen($string); $i++)
|
||||
{
|
||||
$hexChar = "";
|
||||
$unicodeHexChar = "";
|
||||
$hexChar = strtoupper(dechex(ord($string[$i])));
|
||||
|
||||
// This is fix from Mario Klingemann, it prevents
|
||||
// droping chars below 16 because of missing leading 0 [zeros]
|
||||
if ( strlen($hexChar)==1 )
|
||||
{
|
||||
$hexChar = "0" . $hexChar;
|
||||
}
|
||||
|
||||
// This is quick fix of 10 chars in gsm0338
|
||||
// Thanks goes to Andrea Carpani who pointed on this problem and solve it ;)
|
||||
if ( ( $from == "gsm0338" ) && ( $hexChar == '1B' ) )
|
||||
{
|
||||
$i++;
|
||||
$hexChar .= strtoupper(dechex(ord($string[$i])));
|
||||
}
|
||||
|
||||
if ( $to != "utf-8" )
|
||||
{
|
||||
if ( in_array( $hexChar, $charsetTable[$from] ) )
|
||||
{
|
||||
$unicodeHexChar = array_search( $hexChar, $charsetTable[$from] );
|
||||
$unicodeHexChars = explode( "+",$unicodeHexChar );
|
||||
|
||||
for( $unicodeHexCharElement = 0; $unicodeHexCharElement < count($unicodeHexChars); $unicodeHexCharElement++ )
|
||||
{
|
||||
if ( array_key_exists( $unicodeHexChars[$unicodeHexCharElement], $charsetTable[$to] ) )
|
||||
{
|
||||
if ( self::$entities == true )
|
||||
{
|
||||
$text .= self::_unicodeEntity( self::_hexToUtf( $unicodeHexChars[$unicodeHexCharElement] ) );
|
||||
}
|
||||
else
|
||||
{
|
||||
$text .= chr(hexdec($charsetTable[$to][$unicodeHexChars[$unicodeHexCharElement]]));
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
static::$errors[] = "NO_CHAR_IN_DESTINATION: {$string[$i]}";
|
||||
return $original;
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
static::$errors[] = "NO_CHAR_IN_SOURCE: {$string[$i]}";
|
||||
return $original;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
if ( in_array( $hexChar, $charsetTable[$from] ) )
|
||||
{
|
||||
$unicodeHexChar = array_search( $hexChar, $charsetTable[$from] );
|
||||
$unicodeHexChars = explode( "+", $unicodeHexChar );
|
||||
|
||||
/**
|
||||
* Sometimes there are two or more utf-8 chars per one regular char.
|
||||
* Extream, example is polish old Mazovia encoding, where one char contains
|
||||
* two lettes 007a (z) and 0142 (l slash), we need to figure out how to
|
||||
* solve this problem.
|
||||
* The letters are merge with "plus" sign, there can be more than two chars.
|
||||
* In Mazowia we have 007A+0142, but sometimes it can look like this
|
||||
* 0x007A+0x0142+0x2034 (that string means nothing, it just shows the possibility...)
|
||||
*/
|
||||
for( $unicodeHexCharElement = 0; $unicodeHexCharElement < count($unicodeHexChars); $unicodeHexCharElement++)
|
||||
{
|
||||
if ( self::$entities == true )
|
||||
{
|
||||
$text .= self::_unicodeEntity( self::_hexToUtf( $unicodeHexChars[$unicodeHexCharElement] ) );
|
||||
}
|
||||
else
|
||||
{
|
||||
$text .= self::_hexToUtf( $unicodeHexChars[$unicodeHexCharElement] );
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
static::$errors[] = "NO_CHAR_IN_SOURCE: {$string[$i]}";
|
||||
return $original;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* This is second case. We are encoding from multibyte char string.
|
||||
*/
|
||||
|
||||
else if( $from == "utf-8" )
|
||||
{
|
||||
$hexChar = "";
|
||||
$unicodeHexChar = "";
|
||||
$charsetTable = self::_makeConversionTable( $to );
|
||||
|
||||
if( is_array($charsetTable[$to]) AND count($charsetTable[$to]) )
|
||||
{
|
||||
foreach ( $charsetTable[$to] as $unicodeHexChar => $hexChar )
|
||||
{
|
||||
if (self::$entities == true)
|
||||
{
|
||||
$entityOrChar = self::_unicodeEntity(self::_hexToUtf($unicodeHexChar));
|
||||
}
|
||||
else
|
||||
{
|
||||
$entityOrChar = chr(hexdec($hexChar));
|
||||
}
|
||||
|
||||
$string = str_replace( self::_hexToUtf( $unicodeHexChar), $entityOrChar, $string );
|
||||
}
|
||||
}
|
||||
|
||||
$text = $string;
|
||||
}
|
||||
|
||||
return $text ? $text : $original;
|
||||
}
|
||||
|
||||
/**
|
||||
* Convert unicode characters to unicode HTML entities
|
||||
*
|
||||
* @param string $unicodeString Input Unicode string (1 char can take more than 1 byte)
|
||||
* @return @e string
|
||||
* @see _hexToUtf()
|
||||
*/
|
||||
protected static function _unicodeEntity( $unicodeString )
|
||||
{
|
||||
$outString = "";
|
||||
$stringLength = strlen( $unicodeString );
|
||||
|
||||
for( $charPosition = 0; $charPosition < $stringLength; $charPosition++ )
|
||||
{
|
||||
$char = $unicodeString [$charPosition];
|
||||
$asciiChar = ord ($char);
|
||||
|
||||
if ($asciiChar < 128) //1 7 0bbbbbbb (127)
|
||||
{
|
||||
$outString .= $char;
|
||||
}
|
||||
else if ($asciiChar >> 5 == 6) //2 11 110bbbbb 10bbbbbb (2047)
|
||||
{
|
||||
$firstByte = ($asciiChar & 31);
|
||||
$charPosition++;
|
||||
$char = $unicodeString [$charPosition];
|
||||
$asciiChar = ord ($char);
|
||||
$secondByte = ($asciiChar & 63);
|
||||
$asciiChar = ($firstByte * 64) + $secondByte;
|
||||
|
||||
$entity = sprintf ( "&#%d;", $asciiChar );
|
||||
$outString .= $entity;
|
||||
}
|
||||
else if ($asciiChar >> 4 == 14) //3 16 1110bbbb 10bbbbbb 10bbbbbb
|
||||
{
|
||||
$firstByte = ($asciiChar & 31);
|
||||
$charPosition++;
|
||||
$char = $unicodeString [$charPosition];
|
||||
$asciiChar = ord ($char);
|
||||
$secondByte = ($asciiChar & 63);
|
||||
$charPosition++;
|
||||
$char = $unicodeString [$charPosition];
|
||||
$asciiChar = ord ($char);
|
||||
$thirdByte = ($asciiChar & 63);
|
||||
$asciiChar = ((($firstByte * 64) + $secondByte) * 64) + $thirdByte;
|
||||
|
||||
$entity = sprintf ("&#%d;", $asciiChar);
|
||||
$outString .= $entity;
|
||||
}
|
||||
else if ($asciiChar >> 3 == 30) //4 21 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb
|
||||
{
|
||||
$firstByte = ($asciiChar & 31);
|
||||
$charPosition++;
|
||||
$char = $unicodeString [$charPosition];
|
||||
$asciiChar = ord ($char);
|
||||
$secondByte = ($asciiChar & 63);
|
||||
$charPosition++;
|
||||
$char = $unicodeString [$charPosition];
|
||||
$asciiChar = ord ($char);
|
||||
$thirdByte = ($asciiChar & 63);
|
||||
$charPosition++;
|
||||
$char = $unicodeString [$charPosition];
|
||||
$asciiChar = ord ($char);
|
||||
$fourthByte = ($asciiChar & 63);
|
||||
$asciiChar = ((((($firstByte * 64) + $secondByte) * 64) + $thirdByte) * 64) + $fourthByte;
|
||||
|
||||
$entity = sprintf ("&#%d;", $asciiChar);
|
||||
$outString .= $entity;
|
||||
}
|
||||
}
|
||||
|
||||
return $outString;
|
||||
}
|
||||
|
||||
/**
|
||||
* Convert unicode characters to unicode HTML entities.
|
||||
* It is very similar to _unicodeEntity function (link below). There is one difference
|
||||
* in returned format. This time it's a regular char(s), in most cases it will be one or two chars.
|
||||
*
|
||||
* @param string $utfCharInHex Hexadecimal value of a unicode char.
|
||||
* @return @e string
|
||||
* @see _unicodeEntity()
|
||||
*/
|
||||
protected static function _hexToUtf( $utfCharInHex )
|
||||
{
|
||||
$outputChar = "";
|
||||
$utfCharInDec = hexdec($utfCharInHex);
|
||||
|
||||
if( $utfCharInDec < 128 )
|
||||
{
|
||||
$outputChar .= chr($utfCharInDec);
|
||||
}
|
||||
else if( $utfCharInDec < 2048 )
|
||||
{
|
||||
$outputChar .= chr( ( $utfCharInDec>>6 ) + 192 ) . chr( ( $utfCharInDec&63 ) + 128 );
|
||||
}
|
||||
else if( $utfCharInDec < 65536 )
|
||||
{
|
||||
$outputChar .= chr( ( $utfCharInDec>>12 ) + 224 ) . chr( ( ( $utfCharInDec>>6 ) &63 ) + 128 ) . chr( ( $utfCharInDec&63 ) + 128 );
|
||||
}
|
||||
else if( $utfCharInDec < 2097152 )
|
||||
{
|
||||
$outputChar .= chr( $utfCharInDec>>18+240 ) . chr( ( ( $utfCharInDec>>12 ) &63 ) + 128 ) . chr( ( $utfCharInDec>>6 ) &63 + 128 ) . chr( $utfCharInDec&63 + 128 );
|
||||
}
|
||||
|
||||
return $outputChar;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Create the conversion tables to use.
|
||||
*
|
||||
* This function creates table with two SBCS (Single Byte Character Set). Every conversion is through this table.
|
||||
*
|
||||
* - The file with encoding tables have to be save in "Format A" of unicode.org charset table format.
|
||||
* - BOTH charsets MUST be SBCS
|
||||
* - The files with encoding tables have to be complete (None of chars can be missing, unles you are sure you are not going to use it)
|
||||
*
|
||||
* "Format A" encoding file, if you have to build it by yourself should aplly these rules:
|
||||
* - you can comment everything with #
|
||||
* - first column contains 1 byte chars in hex starting from 0x..
|
||||
* - second column contains unicode equivalent in hex starting from 0x....
|
||||
* - then every next column is optional, but in "Format A" it should contain unicode char name or/and your own comment
|
||||
* - the columns can be splited by "spaces", "tabs", "," or any combination of these
|
||||
* - below is an example
|
||||
*
|
||||
* <code>
|
||||
* #
|
||||
* # The entries are in ANSI X3.4 order.
|
||||
* #
|
||||
* 0x00 0x0000 # NULL end extra comment, if needed
|
||||
* 0x01 0x0001 # START OF HEADING
|
||||
* # Oh, one more thing, you can make comments inside of a rows if you like.
|
||||
* 0x02 0x0002 # START OF TEXT
|
||||
* 0x03 0x0003 # END OF TEXT
|
||||
* next line, and so on...
|
||||
* </code>
|
||||
*
|
||||
* You can get full tables with encodings from http://www.unicode.org
|
||||
*
|
||||
* @param string $firstEncoding Name of first encoding and first encoding filename (thay have to be the same)
|
||||
* @param string $secondEncoding Name of second encoding and second encoding filename (thay have to be the same). Optional for building a joined table.
|
||||
* @return @e array
|
||||
*/
|
||||
protected static function _makeConversionTable( $firstEncoding, $secondEncoding = "" )
|
||||
{
|
||||
$convertTable = array();
|
||||
|
||||
for( $i = 0; $i < func_num_args(); $i++ )
|
||||
{
|
||||
/**
|
||||
* Because func_*** can't be used inside of another function call
|
||||
* we have to save it as a separate value.
|
||||
*/
|
||||
$fileName = func_get_arg($i);
|
||||
|
||||
if ( !is_file( static::$charsetPath . $fileName ) )
|
||||
{
|
||||
static::$errors[] = "FILE_NOT_FOUND: {$fileName}";
|
||||
return;
|
||||
}
|
||||
|
||||
$fileWithEncTabe = fopen( static::$charsetPath . $fileName, "r" ) or die(); //This die(); is just to make sure...
|
||||
|
||||
while(!feof($fileWithEncTabe))
|
||||
{
|
||||
/**
|
||||
* We asume that line is not longer
|
||||
* than 1024 which is the default value for fgets function
|
||||
*/
|
||||
if( $oneLine = trim( fgets( $fileWithEncTabe, 1024 ) ) )
|
||||
{
|
||||
/**
|
||||
* We don't need all comment lines. I check only for "#" sign, because
|
||||
* this is a way of making comments by unicode.org in thair encoding files
|
||||
* and that's where the files are from :-)
|
||||
*/
|
||||
if ( substr( $oneLine, 0, 1 ) != "#" )
|
||||
{
|
||||
/**
|
||||
* Sometimes inside the charset file the hex walues are separated by
|
||||
* "space" and sometimes by "tab", the below preg_split can also be used
|
||||
* to split files where separator is a ",", "\r", "\n" and "\f"
|
||||
*/
|
||||
$hexValue = preg_split ( "/[\s,]+/", $oneLine, 3 ); //We need only first 2 values
|
||||
|
||||
/**
|
||||
* Sometimes char is UNDEFINED, or missing so we can't use it for convertion
|
||||
*/
|
||||
if (substr($hexValue[1], 0, 1) != "#")
|
||||
{
|
||||
$arrayKey = strtoupper(str_replace(strtolower("0x"), "", $hexValue[1]));
|
||||
$arrayValue = strtoupper(str_replace(strtolower("0x"), "", $hexValue[0]));
|
||||
|
||||
$convertTable[ func_get_arg($i) ][ $arrayKey ] = $arrayValue;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return $convertTable;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,54 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Conversion module
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Tools
|
||||
* @since 4 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Text\Module;
|
||||
|
||||
/**
|
||||
* Native MB Conversion class
|
||||
*/
|
||||
class Mb extends \IPSUtf8\Text\Charset
|
||||
{
|
||||
/**
|
||||
* Converts a text string from its current charset to a destination charset using mb_convert_encoding. If mb* functions are not available, logs an error to self::$errors.
|
||||
*
|
||||
* @param string Text string
|
||||
* @param string Text string char set (original)
|
||||
* @param string Desired character set (destination)
|
||||
* @return @e string
|
||||
*/
|
||||
public function convert( $string, $from, $to='UTF-8' )
|
||||
{
|
||||
if ( static::needsConverting( $string, $from, $to ) === false )
|
||||
{
|
||||
return $string;
|
||||
}
|
||||
|
||||
if ( function_exists( 'mb_convert_encoding' ) )
|
||||
{
|
||||
$encodings = array_map( 'strtolower', mb_list_encodings() );
|
||||
|
||||
if( in_array( strtolower( $to ), $encodings ) AND in_array( strtolower( $from ), $encodings ) )
|
||||
{
|
||||
$text = mb_convert_encoding( $string, $to, $from );
|
||||
}
|
||||
else
|
||||
{
|
||||
static::$errors[] = "NO_MB_FUNCTION";
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
static::$errors[] = "NO_MB_FUNCTION";
|
||||
}
|
||||
|
||||
return $text ? $text : $string;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,45 @@
|
||||
<?php
|
||||
/**
|
||||
* @brief Conversion module
|
||||
* @author <a href='http://www.invisionpower.com'>Invision Power Services, Inc.</a>
|
||||
* @copyright (c) 2001 - SVN_YYYY Invision Power Services, Inc.
|
||||
* @license http://www.invisionpower.com/legal/standards/
|
||||
* @package IPS Tools
|
||||
* @since 4 Sept 2013
|
||||
* @version SVN_VERSION_NUMBER
|
||||
*/
|
||||
|
||||
namespace IPSUtf8\Text\Module;
|
||||
|
||||
/**
|
||||
* Native MB Conversion class
|
||||
*/
|
||||
class Recode extends \IPSUtf8\Text\Charset
|
||||
{
|
||||
/**
|
||||
* Converts a text string from its current charset to a destination charset using recode_string
|
||||
*
|
||||
* @param string Text string
|
||||
* @param string Text string char set (original)
|
||||
* @param string Desired character set (destination)
|
||||
* @return @e string
|
||||
*/
|
||||
public function convert( $string, $from, $to='UTF-8' )
|
||||
{
|
||||
if ( static::needsConverting( $string, $from, $to ) === false )
|
||||
{
|
||||
return $string;
|
||||
}
|
||||
|
||||
if ( function_exists( 'recode_string' ) )
|
||||
{
|
||||
$text = recode_string( $from . '..' . $to, $string );
|
||||
}
|
||||
else
|
||||
{
|
||||
static::$errors[] = "NO_RECODE_FUNCTION";
|
||||
}
|
||||
|
||||
return $text ? $text : $string;
|
||||
}
|
||||
}
|
||||
Whitespace-only changes.
Whitespace-only changes.
@@ -0,0 +1,307 @@
|
||||
<?php
|
||||
|
||||
$PATH_TO_CLASS = dirname(ereg_replace("\\\\", "/", __FILE__)) . "/" . "ConvertTables" . "/";
|
||||
define ("CONVERT_TABLES_DIR", $PATH_TO_CLASS);
|
||||
define ("DEBUG_MODE", 1);
|
||||
|
||||
|
||||
class ConvertCharset{
|
||||
var $RecognizedEncoding; // (boolean) This value keeps information if string contains multibyte chars.
|
||||
var $Entities; // (boolean) This value keeps information if output should be with numeric entities.
|
||||
var $FromCharset; // (string) This value keeps information about source (from) encoding
|
||||
var $ToCharset; // (string) This value keeps information about destination (to) encoding
|
||||
var $CharsetTable; // (array) This property keeps convert Table inside
|
||||
|
||||
|
||||
|
||||
function ConvertCharset ($FromCharset, $ToCharset, $TurnOnEntities = false)
|
||||
{
|
||||
|
||||
$this -> FromCharset = strtolower($FromCharset);
|
||||
$this -> ToCharset = strtolower($ToCharset);
|
||||
$this -> Entities = $TurnOnEntities;
|
||||
|
||||
|
||||
if ($this -> FromCharset == $this -> ToCharset)
|
||||
{
|
||||
print $this -> DebugOutput(1, 0, $this -> FromCharset);
|
||||
}
|
||||
if (($this -> FromCharset == $this -> ToCharset) AND ($this -> FromCharset == "utf-8"))
|
||||
{
|
||||
print $this -> DebugOutput(0, 4, $this -> FromCharset);
|
||||
exit;
|
||||
}
|
||||
|
||||
|
||||
if ($this -> FromCharset == "utf-8")
|
||||
{
|
||||
$this -> CharsetTable = $this -> MakeConvertTable ($this -> ToCharset);
|
||||
}
|
||||
else if ($this -> ToCharset == "utf-8")
|
||||
{
|
||||
$this -> CharsetTable = $this -> MakeConvertTable ($this -> FromCharset);
|
||||
}
|
||||
else
|
||||
{
|
||||
$this -> CharsetTable = $this -> MakeConvertTable ($this -> FromCharset, $this -> ToCharset);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
function UnicodeEntity ($UnicodeString)
|
||||
{
|
||||
$OutString = "";
|
||||
$StringLenght = strlen ($UnicodeString);
|
||||
for ($CharPosition = 0; $CharPosition < $StringLenght; $CharPosition++)
|
||||
{
|
||||
$Char = $UnicodeString [$CharPosition];
|
||||
$AsciiChar = ord ($Char);
|
||||
|
||||
if ($AsciiChar < 128){
|
||||
$OutString .= $Char;
|
||||
}
|
||||
else if ($AsciiChar >> 5 == 6){
|
||||
$FirstByte = ($AsciiChar & 31);
|
||||
$CharPosition++;
|
||||
$Char = $UnicodeString [$CharPosition];
|
||||
$AsciiChar = ord ($Char);
|
||||
$SecondByte = ($AsciiChar & 63);
|
||||
$AsciiChar = ($FirstByte * 64) + $SecondByte;
|
||||
$Entity = sprintf ("&#%d;", $AsciiChar);
|
||||
$OutString .= $Entity;
|
||||
}
|
||||
else if ($AsciiChar >> 4 == 14){
|
||||
$FirstByte = ($AsciiChar & 31);
|
||||
$CharPosition++;
|
||||
$Char = $UnicodeString [$CharPosition];
|
||||
$AsciiChar = ord ($Char);
|
||||
$SecondByte = ($AsciiChar & 63);
|
||||
$CharPosition++;
|
||||
$Char = $UnicodeString [$CharPosition];
|
||||
$AsciiChar = ord ($Char);
|
||||
$ThidrByte = ($AsciiChar & 63);
|
||||
$AsciiChar = ((($FirstByte * 64) + $SecondByte) * 64) + $ThidrByte;
|
||||
|
||||
$Entity = sprintf ("&#%d;", $AsciiChar);
|
||||
$OutString .= $Entity;
|
||||
}
|
||||
else if ($AsciiChar >> 3 == 30){
|
||||
$FirstByte = ($AsciiChar & 31);
|
||||
$CharPosition++;
|
||||
$Char = $UnicodeString [$CharPosition];
|
||||
$AsciiChar = ord ($Char);
|
||||
$SecondByte = ($AsciiChar & 63);
|
||||
$CharPosition++;
|
||||
$Char = $UnicodeString [$CharPosition];
|
||||
$AsciiChar = ord ($Char);
|
||||
$ThidrByte = ($AsciiChar & 63);
|
||||
$CharPosition++;
|
||||
$Char = $UnicodeString [$CharPosition];
|
||||
$AsciiChar = ord ($Char);
|
||||
$FourthByte = ($AsciiChar & 63);
|
||||
$AsciiChar = ((((($FirstByte * 64) + $SecondByte) * 64) + $ThidrByte) * 64) + $FourthByte;
|
||||
|
||||
$Entity = sprintf ("&#%d;", $AsciiChar);
|
||||
$OutString .= $Entity;
|
||||
}
|
||||
}
|
||||
return $OutString;
|
||||
}
|
||||
|
||||
|
||||
function HexToUtf ($UtfCharInHex)
|
||||
{
|
||||
$OutputChar = "";
|
||||
$UtfCharInDec = hexdec($UtfCharInHex);
|
||||
if($UtfCharInDec < 128) $OutputChar .= chr($UtfCharInDec);
|
||||
else if($UtfCharInDec < 2048)$OutputChar .= chr(($UtfCharInDec >> 6) + 192) . chr(($UtfCharInDec & 63) + 128);
|
||||
else if($UtfCharInDec < 65536)$OutputChar .= chr(($UtfCharInDec >> 12) + 224) . chr((($UtfCharInDec >> 6) & 63) + 128) . chr(($UtfCharInDec & 63) + 128);
|
||||
else if($UtfCharInDec < 2097152)$OutputChar .= chr($UtfCharInDec >> 18 + 240) . chr((($UtfCharInDec >> 12) & 63) + 128) . chr(($UtfCharInDec >> 6) & 63 + 128) . chr($UtfCharInDec & 63 + 128);
|
||||
return $OutputChar;
|
||||
}
|
||||
|
||||
|
||||
|
||||
function MakeConvertTable ($FromCharset, $ToCharset = '')
|
||||
{
|
||||
$ConvertTable = array();
|
||||
for($i = 0; $i < func_num_args(); $i++)
|
||||
{
|
||||
|
||||
$FileName = func_get_arg($i);
|
||||
if (!is_file(CONVERT_TABLES_DIR . $FileName))
|
||||
{
|
||||
print $this -> DebugOutput(0, 0, CONVERT_TABLES_DIR . $FileName); //Print an error message
|
||||
exit;
|
||||
}
|
||||
$FileWithEncTabe = fopen(CONVERT_TABLES_DIR . $FileName, "r") or die(); //This die(); is just to make sure...
|
||||
while(!feof($FileWithEncTabe))
|
||||
{
|
||||
|
||||
if($OneLine = trim(fgets($FileWithEncTabe, 1024)))
|
||||
{
|
||||
|
||||
if (substr($OneLine, 0, 1) != "#")
|
||||
{
|
||||
|
||||
$HexValue = preg_split ("/[\s,]+/", $OneLine, 3); //We need only first 2 values
|
||||
|
||||
if (substr($HexValue[1], 0, 1) != "#")
|
||||
{
|
||||
$ArrayKey = strtoupper(str_replace(strtolower("0x"), "", $HexValue[1]));
|
||||
$ArrayValue = strtoupper(str_replace(strtolower("0x"), "", $HexValue[0]));
|
||||
$ConvertTable[func_get_arg($i)][$ArrayKey] = $ArrayValue;
|
||||
}
|
||||
} //if (substr($OneLine,...
|
||||
} //if($OneLine=trim(f...
|
||||
} //while(!feof($FirstFileWi...
|
||||
} //for($i = 0; $i < func_...
|
||||
|
||||
if(!is_array($ConvertTable[$FromCharset])) $ConvertTable[$FromCharset] = array();
|
||||
|
||||
if ((func_num_args() > 1) && (count($ConvertTable[$FromCharset]) == count($ConvertTable[$ToCharset])) && (count(array_diff_assoc($ConvertTable[$FromCharset], $ConvertTable[$ToCharset])) == 0))
|
||||
{
|
||||
print $this -> DebugOutput(1, 1, "$FromCharset, $ToCharset");
|
||||
}
|
||||
return $ConvertTable;
|
||||
}
|
||||
|
||||
|
||||
function Convert ($StringToChange)
|
||||
{
|
||||
if(!strlen($StringToChange)) return '';
|
||||
$StringToChange = (string)($StringToChange);
|
||||
|
||||
if($this -> FromCharset == $this -> ToCharset) return $StringToChange;
|
||||
|
||||
$NewString = "";
|
||||
|
||||
|
||||
if ($this -> FromCharset != "utf-8")
|
||||
{
|
||||
|
||||
for ($i = 0; $i < strlen($StringToChange); $i++)
|
||||
{
|
||||
$HexChar = "";
|
||||
$UnicodeHexChar = "";
|
||||
$HexChar = strtoupper(dechex(ord($StringToChange[$i])));
|
||||
if (strlen($HexChar) == 1) $HexChar = "0" . $HexChar;
|
||||
if (($this -> FromCharset == "gsm0338") && ($HexChar == '1B')){
|
||||
$i++;
|
||||
$HexChar .= strtoupper(dechex(ord($StringToChange[$i])));
|
||||
}
|
||||
if ($this -> ToCharset != "utf-8")
|
||||
{
|
||||
if (in_array($HexChar, $this -> CharsetTable[$this -> FromCharset]))
|
||||
{
|
||||
$UnicodeHexChar = array_search($HexChar, $this -> CharsetTable[$this -> FromCharset]);
|
||||
$UnicodeHexChars = explode("+", $UnicodeHexChar);
|
||||
for($UnicodeHexCharElement = 0; $UnicodeHexCharElement < count($UnicodeHexChars); $UnicodeHexCharElement++)
|
||||
{
|
||||
if (array_key_exists($UnicodeHexChars[$UnicodeHexCharElement], $this -> CharsetTable[$this -> ToCharset]))
|
||||
{
|
||||
if ($this -> Entities == true)
|
||||
{
|
||||
$NewString .= $this -> UnicodeEntity($this -> HexToUtf($UnicodeHexChars[$UnicodeHexCharElement]));
|
||||
}
|
||||
else
|
||||
{
|
||||
$NewString .= chr(hexdec($this -> CharsetTable[$this -> ToCharset][$UnicodeHexChars[$UnicodeHexCharElement]]));
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
print $this -> DebugOutput(0, 1, $StringToChange[$i]);
|
||||
}
|
||||
} //for($UnicodeH...
|
||||
}
|
||||
else
|
||||
{
|
||||
print $this -> DebugOutput(0, 2, $StringToChange[$i]);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
if (in_array("$HexChar", $this -> CharsetTable[$this -> FromCharset]))
|
||||
{
|
||||
$UnicodeHexChar = array_search($HexChar, $this -> CharsetTable[$this -> FromCharset]);
|
||||
|
||||
$UnicodeHexChars = explode("+", $UnicodeHexChar);
|
||||
for($UnicodeHexCharElement = 0; $UnicodeHexCharElement < count($UnicodeHexChars); $UnicodeHexCharElement++)
|
||||
{
|
||||
if ($this -> Entities == true)
|
||||
{
|
||||
$NewString .= $this -> UnicodeEntity($this -> HexToUtf($UnicodeHexChars[$UnicodeHexCharElement]));
|
||||
}
|
||||
else
|
||||
{
|
||||
$NewString .= $this -> HexToUtf($UnicodeHexChars[$UnicodeHexCharElement]);
|
||||
}
|
||||
} // for
|
||||
}
|
||||
else
|
||||
{
|
||||
print $this -> DebugOutput(0, 2, $StringToChange[$i]);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
else if($this -> FromCharset == "utf-8")
|
||||
{
|
||||
$HexChar = "";
|
||||
$UnicodeHexChar = "";
|
||||
$this -> CharsetTable = $this -> MakeConvertTable ($this -> ToCharset);
|
||||
foreach ($this -> CharsetTable[$this -> ToCharset] as $UnicodeHexChar => $HexChar)
|
||||
{
|
||||
if ($this -> Entities == true){
|
||||
$EntitieOrChar = $this -> UnicodeEntity($this -> HexToUtf($UnicodeHexChar));
|
||||
}
|
||||
else
|
||||
{
|
||||
$EntitieOrChar = chr(hexdec($HexChar));
|
||||
}
|
||||
$StringToChange = str_replace($this -> HexToUtf($UnicodeHexChar), $EntitieOrChar, $StringToChange);
|
||||
}
|
||||
$NewString = $StringToChange;
|
||||
}
|
||||
|
||||
return $NewString;
|
||||
}
|
||||
|
||||
|
||||
function ConvertArray(& $array)
|
||||
{
|
||||
if (!is_array($array))
|
||||
{
|
||||
$array = $this -> Convert($array);
|
||||
return;
|
||||
}
|
||||
while(list($k, $v) = each($array))
|
||||
{
|
||||
$this -> ConvertArray($v);
|
||||
$array[$k] = $v;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
function DebugOutput ($Group, $Number, $Value = false)
|
||||
{
|
||||
$Debug[0][0] = "Error, can NOT read file: " . $Value . "<br>";
|
||||
$Debug[0][1] = "Error, can't find maching char \"" . $Value . "\" in destination encoding table!" . "<br>";
|
||||
$Debug[0][2] = "Error, can't find maching char \"" . $Value . "\" in source encoding table!" . "<br>";
|
||||
$Debug[0][3] = "Error, you did NOT set variable " . $Value . " in Convert() function." . "<br>";
|
||||
$Debug[0][4] = "You can NOT convert string from " . $Value . " to " . $Value . "!" . "<BR>";
|
||||
$Debug[1][0] = "Notice, you are trying to convert string from " . $Value . " to " . $Value . ", don't you feel it's strange? ;-)" . "<br>";
|
||||
$Debug[1][1] = "Notice, both charsets " . $Value . " are identical! Check encoding tables files." . "<br>";
|
||||
$Debug[1][2] = "Notice, there is no unicode char in the string you are trying to convert." . "<br>";
|
||||
|
||||
if (DEBUG_MODE >= $Group)
|
||||
{
|
||||
return $Debug[$Group][$Number];
|
||||
}
|
||||
} // function DebugOutput
|
||||
|
||||
} //class ends here
|
||||
?>
|
||||
Whitespace-only changes.
@@ -0,0 +1,303 @@
|
||||
#
|
||||
# Name: ISO/IEC 8859-1:1998 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 1999 July 27
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-1:1998 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-1 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-1 order.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version updates 0.1 version by adding mappings for all
|
||||
# control characters.
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x00A1 # INVERTED EXCLAMATION MARK
|
||||
0xA2 0x00A2 # CENT SIGN
|
||||
0xA3 0x00A3 # POUND SIGN
|
||||
0xA4 0x00A4 # CURRENCY SIGN
|
||||
0xA5 0x00A5 # YEN SIGN
|
||||
0xA6 0x00A6 # BROKEN BAR
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x00A8 # DIAERESIS
|
||||
0xA9 0x00A9 # COPYRIGHT SIGN
|
||||
0xAA 0x00AA # FEMININE ORDINAL INDICATOR
|
||||
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC # NOT SIGN
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAE 0x00AE # REGISTERED SIGN
|
||||
0xAF 0x00AF # MACRON
|
||||
0xB0 0x00B0 # DEGREE SIGN
|
||||
0xB1 0x00B1 # PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 # SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 # SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 # ACUTE ACCENT
|
||||
0xB5 0x00B5 # MICRO SIGN
|
||||
0xB6 0x00B6 # PILCROW SIGN
|
||||
0xB7 0x00B7 # MIDDLE DOT
|
||||
0xB8 0x00B8 # CEDILLA
|
||||
0xB9 0x00B9 # SUPERSCRIPT ONE
|
||||
0xBA 0x00BA # MASCULINE ORDINAL INDICATOR
|
||||
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC # VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD # VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00BF # INVERTED QUESTION MARK
|
||||
0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x00C6 # LATIN CAPITAL LETTER AE
|
||||
0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD0 0x00D0 # LATIN CAPITAL LETTER ETH (Icelandic)
|
||||
0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 # MULTIPLICATION SIGN
|
||||
0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0xDE 0x00DE # LATIN CAPITAL LETTER THORN (Icelandic)
|
||||
0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German)
|
||||
0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE
|
||||
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x00E6 # LATIN SMALL LETTER AE
|
||||
0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE
|
||||
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x00F0 # LATIN SMALL LETTER ETH (Icelandic)
|
||||
0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE
|
||||
0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
|
||||
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 # DIVISION SIGN
|
||||
0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
|
||||
0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0xFE 0x00FE # LATIN SMALL LETTER THORN (Icelandic)
|
||||
0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
@@ -0,0 +1,303 @@
|
||||
#
|
||||
# Name: ISO/IEC 8859-10:1998 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.1
|
||||
# Table format: Format A
|
||||
# Date: 1999 October 11
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-10:1998 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-10 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-10 order.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version new.
|
||||
# 1.1 corrected mistake in mapping of 0xA4
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0xA2 0x0112 # LATIN CAPITAL LETTER E WITH MACRON
|
||||
0xA3 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
0xA4 0x012A # LATIN CAPITAL LETTER I WITH MACRON
|
||||
0xA5 0x0128 # LATIN CAPITAL LETTER I WITH TILDE
|
||||
0xA6 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
0xA9 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
|
||||
0xAA 0x0160 # LATIN CAPITAL LETTER S WITH CARON
|
||||
0xAB 0x0166 # LATIN CAPITAL LETTER T WITH STROKE
|
||||
0xAC 0x017D # LATIN CAPITAL LETTER Z WITH CARON
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAE 0x016A # LATIN CAPITAL LETTER U WITH MACRON
|
||||
0xAF 0x014A # LATIN CAPITAL LETTER ENG
|
||||
0xB0 0x00B0 # DEGREE SIGN
|
||||
0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK
|
||||
0xB2 0x0113 # LATIN SMALL LETTER E WITH MACRON
|
||||
0xB3 0x0123 # LATIN SMALL LETTER G WITH CEDILLA
|
||||
0xB4 0x012B # LATIN SMALL LETTER I WITH MACRON
|
||||
0xB5 0x0129 # LATIN SMALL LETTER I WITH TILDE
|
||||
0xB6 0x0137 # LATIN SMALL LETTER K WITH CEDILLA
|
||||
0xB7 0x00B7 # MIDDLE DOT
|
||||
0xB8 0x013C # LATIN SMALL LETTER L WITH CEDILLA
|
||||
0xB9 0x0111 # LATIN SMALL LETTER D WITH STROKE
|
||||
0xBA 0x0161 # LATIN SMALL LETTER S WITH CARON
|
||||
0xBB 0x0167 # LATIN SMALL LETTER T WITH STROKE
|
||||
0xBC 0x017E # LATIN SMALL LETTER Z WITH CARON
|
||||
0xBD 0x2015 # HORIZONTAL BAR
|
||||
0xBE 0x016B # LATIN SMALL LETTER U WITH MACRON
|
||||
0xBF 0x014B # LATIN SMALL LETTER ENG
|
||||
0xC0 0x0100 # LATIN CAPITAL LETTER A WITH MACRON
|
||||
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x00C6 # LATIN CAPITAL LETTER AE
|
||||
0xC7 0x012E # LATIN CAPITAL LETTER I WITH OGONEK
|
||||
0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
|
||||
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD0 0x00D0 # LATIN CAPITAL LETTER ETH (Icelandic)
|
||||
0xD1 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
0xD2 0x014C # LATIN CAPITAL LETTER O WITH MACRON
|
||||
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x0168 # LATIN CAPITAL LETTER U WITH TILDE
|
||||
0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xD9 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK
|
||||
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0xDE 0x00DE # LATIN CAPITAL LETTER THORN (Icelandic)
|
||||
0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German)
|
||||
0xE0 0x0101 # LATIN SMALL LETTER A WITH MACRON
|
||||
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE
|
||||
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x00E6 # LATIN SMALL LETTER AE
|
||||
0xE7 0x012F # LATIN SMALL LETTER I WITH OGONEK
|
||||
0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
|
||||
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK
|
||||
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x00F0 # LATIN SMALL LETTER ETH (Icelandic)
|
||||
0xF1 0x0146 # LATIN SMALL LETTER N WITH CEDILLA
|
||||
0xF2 0x014D # LATIN SMALL LETTER O WITH MACRON
|
||||
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x0169 # LATIN SMALL LETTER U WITH TILDE
|
||||
0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
|
||||
0xF9 0x0173 # LATIN SMALL LETTER U WITH OGONEK
|
||||
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0xFE 0x00FE # LATIN SMALL LETTER THORN (Icelandic)
|
||||
0xFF 0x0138 # LATIN SMALL LETTER KRA
|
||||
@@ -0,0 +1,297 @@
|
||||
#
|
||||
# Name: ISO/IEC 8859-11:2001 to Unicode
|
||||
# Unicode version: 3.2
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 2002 October 7
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 2002 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-11:2001 characters map into Unicode.
|
||||
#
|
||||
# ISO/IEC 8859-11:2001 is equivalent to TIS 620-2533 (1990) with
|
||||
# the addition of 0xA0 NO-BREAK SPACE.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-11 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-11 order.
|
||||
#
|
||||
# Version history:
|
||||
# 2002 October 7 Created
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# For any comments or problems, please use the Unicode
|
||||
# web contact form at:
|
||||
# http://www.unicode.org/unicode/reporting.html
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x0E01 # THAI CHARACTER KO KAI
|
||||
0xA2 0x0E02 # THAI CHARACTER KHO KHAI
|
||||
0xA3 0x0E03 # THAI CHARACTER KHO KHUAT
|
||||
0xA4 0x0E04 # THAI CHARACTER KHO KHWAI
|
||||
0xA5 0x0E05 # THAI CHARACTER KHO KHON
|
||||
0xA6 0x0E06 # THAI CHARACTER KHO RAKHANG
|
||||
0xA7 0x0E07 # THAI CHARACTER NGO NGU
|
||||
0xA8 0x0E08 # THAI CHARACTER CHO CHAN
|
||||
0xA9 0x0E09 # THAI CHARACTER CHO CHING
|
||||
0xAA 0x0E0A # THAI CHARACTER CHO CHANG
|
||||
0xAB 0x0E0B # THAI CHARACTER SO SO
|
||||
0xAC 0x0E0C # THAI CHARACTER CHO CHOE
|
||||
0xAD 0x0E0D # THAI CHARACTER YO YING
|
||||
0xAE 0x0E0E # THAI CHARACTER DO CHADA
|
||||
0xAF 0x0E0F # THAI CHARACTER TO PATAK
|
||||
0xB0 0x0E10 # THAI CHARACTER THO THAN
|
||||
0xB1 0x0E11 # THAI CHARACTER THO NANGMONTHO
|
||||
0xB2 0x0E12 # THAI CHARACTER THO PHUTHAO
|
||||
0xB3 0x0E13 # THAI CHARACTER NO NEN
|
||||
0xB4 0x0E14 # THAI CHARACTER DO DEK
|
||||
0xB5 0x0E15 # THAI CHARACTER TO TAO
|
||||
0xB6 0x0E16 # THAI CHARACTER THO THUNG
|
||||
0xB7 0x0E17 # THAI CHARACTER THO THAHAN
|
||||
0xB8 0x0E18 # THAI CHARACTER THO THONG
|
||||
0xB9 0x0E19 # THAI CHARACTER NO NU
|
||||
0xBA 0x0E1A # THAI CHARACTER BO BAIMAI
|
||||
0xBB 0x0E1B # THAI CHARACTER PO PLA
|
||||
0xBC 0x0E1C # THAI CHARACTER PHO PHUNG
|
||||
0xBD 0x0E1D # THAI CHARACTER FO FA
|
||||
0xBE 0x0E1E # THAI CHARACTER PHO PHAN
|
||||
0xBF 0x0E1F # THAI CHARACTER FO FAN
|
||||
0xC0 0x0E20 # THAI CHARACTER PHO SAMPHAO
|
||||
0xC1 0x0E21 # THAI CHARACTER MO MA
|
||||
0xC2 0x0E22 # THAI CHARACTER YO YAK
|
||||
0xC3 0x0E23 # THAI CHARACTER RO RUA
|
||||
0xC4 0x0E24 # THAI CHARACTER RU
|
||||
0xC5 0x0E25 # THAI CHARACTER LO LING
|
||||
0xC6 0x0E26 # THAI CHARACTER LU
|
||||
0xC7 0x0E27 # THAI CHARACTER WO WAEN
|
||||
0xC8 0x0E28 # THAI CHARACTER SO SALA
|
||||
0xC9 0x0E29 # THAI CHARACTER SO RUSI
|
||||
0xCA 0x0E2A # THAI CHARACTER SO SUA
|
||||
0xCB 0x0E2B # THAI CHARACTER HO HIP
|
||||
0xCC 0x0E2C # THAI CHARACTER LO CHULA
|
||||
0xCD 0x0E2D # THAI CHARACTER O ANG
|
||||
0xCE 0x0E2E # THAI CHARACTER HO NOKHUK
|
||||
0xCF 0x0E2F # THAI CHARACTER PAIYANNOI
|
||||
0xD0 0x0E30 # THAI CHARACTER SARA A
|
||||
0xD1 0x0E31 # THAI CHARACTER MAI HAN-AKAT
|
||||
0xD2 0x0E32 # THAI CHARACTER SARA AA
|
||||
0xD3 0x0E33 # THAI CHARACTER SARA AM
|
||||
0xD4 0x0E34 # THAI CHARACTER SARA I
|
||||
0xD5 0x0E35 # THAI CHARACTER SARA II
|
||||
0xD6 0x0E36 # THAI CHARACTER SARA UE
|
||||
0xD7 0x0E37 # THAI CHARACTER SARA UEE
|
||||
0xD8 0x0E38 # THAI CHARACTER SARA U
|
||||
0xD9 0x0E39 # THAI CHARACTER SARA UU
|
||||
0xDA 0x0E3A # THAI CHARACTER PHINTHU
|
||||
0xDF 0x0E3F # THAI CURRENCY SYMBOL BAHT
|
||||
0xE0 0x0E40 # THAI CHARACTER SARA E
|
||||
0xE1 0x0E41 # THAI CHARACTER SARA AE
|
||||
0xE2 0x0E42 # THAI CHARACTER SARA O
|
||||
0xE3 0x0E43 # THAI CHARACTER SARA AI MAIMUAN
|
||||
0xE4 0x0E44 # THAI CHARACTER SARA AI MAIMALAI
|
||||
0xE5 0x0E45 # THAI CHARACTER LAKKHANGYAO
|
||||
0xE6 0x0E46 # THAI CHARACTER MAIYAMOK
|
||||
0xE7 0x0E47 # THAI CHARACTER MAITAIKHU
|
||||
0xE8 0x0E48 # THAI CHARACTER MAI EK
|
||||
0xE9 0x0E49 # THAI CHARACTER MAI THO
|
||||
0xEA 0x0E4A # THAI CHARACTER MAI TRI
|
||||
0xEB 0x0E4B # THAI CHARACTER MAI CHATTAWA
|
||||
0xEC 0x0E4C # THAI CHARACTER THANTHAKHAT
|
||||
0xED 0x0E4D # THAI CHARACTER NIKHAHIT
|
||||
0xEE 0x0E4E # THAI CHARACTER YAMAKKAN
|
||||
0xEF 0x0E4F # THAI CHARACTER FONGMAN
|
||||
0xF0 0x0E50 # THAI DIGIT ZERO
|
||||
0xF1 0x0E51 # THAI DIGIT ONE
|
||||
0xF2 0x0E52 # THAI DIGIT TWO
|
||||
0xF3 0x0E53 # THAI DIGIT THREE
|
||||
0xF4 0x0E54 # THAI DIGIT FOUR
|
||||
0xF5 0x0E55 # THAI DIGIT FIVE
|
||||
0xF6 0x0E56 # THAI DIGIT SIX
|
||||
0xF7 0x0E57 # THAI DIGIT SEVEN
|
||||
0xF8 0x0E58 # THAI DIGIT EIGHT
|
||||
0xF9 0x0E59 # THAI DIGIT NINE
|
||||
0xFA 0x0E5A # THAI CHARACTER ANGKHANKHU
|
||||
0xFB 0x0E5B # THAI CHARACTER KHOMUT
|
||||
@@ -0,0 +1,299 @@
|
||||
#
|
||||
# Name: ISO/IEC 8859-13:1998 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 1999 July 27
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-13:1998 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-13 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-13 order.
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x201D # RIGHT DOUBLE QUOTATION MARK
|
||||
0xA2 0x00A2 # CENT SIGN
|
||||
0xA3 0x00A3 # POUND SIGN
|
||||
0xA4 0x00A4 # CURRENCY SIGN
|
||||
0xA5 0x201E # DOUBLE LOW-9 QUOTATION MARK
|
||||
0xA6 0x00A6 # BROKEN BAR
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xA9 0x00A9 # COPYRIGHT SIGN
|
||||
0xAA 0x0156 # LATIN CAPITAL LETTER R WITH CEDILLA
|
||||
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC # NOT SIGN
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAE 0x00AE # REGISTERED SIGN
|
||||
0xAF 0x00C6 # LATIN CAPITAL LETTER AE
|
||||
0xB0 0x00B0 # DEGREE SIGN
|
||||
0xB1 0x00B1 # PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 # SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 # SUPERSCRIPT THREE
|
||||
0xB4 0x201C # LEFT DOUBLE QUOTATION MARK
|
||||
0xB5 0x00B5 # MICRO SIGN
|
||||
0xB6 0x00B6 # PILCROW SIGN
|
||||
0xB7 0x00B7 # MIDDLE DOT
|
||||
0xB8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
|
||||
0xB9 0x00B9 # SUPERSCRIPT ONE
|
||||
0xBA 0x0157 # LATIN SMALL LETTER R WITH CEDILLA
|
||||
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC # VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD # VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00E6 # LATIN SMALL LETTER AE
|
||||
0xC0 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0xC1 0x012E # LATIN CAPITAL LETTER I WITH OGONEK
|
||||
0xC2 0x0100 # LATIN CAPITAL LETTER A WITH MACRON
|
||||
0xC3 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE
|
||||
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0xC7 0x0112 # LATIN CAPITAL LETTER E WITH MACRON
|
||||
0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
|
||||
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
0xCB 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
0xCC 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
0xCD 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
0xCE 0x012A # LATIN CAPITAL LETTER I WITH MACRON
|
||||
0xCF 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
0xD0 0x0160 # LATIN CAPITAL LETTER S WITH CARON
|
||||
0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE
|
||||
0xD2 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x014C # LATIN CAPITAL LETTER O WITH MACRON
|
||||
0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 # MULTIPLICATION SIGN
|
||||
0xD8 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK
|
||||
0xD9 0x0141 # LATIN CAPITAL LETTER L WITH STROKE
|
||||
0xDA 0x015A # LATIN CAPITAL LETTER S WITH ACUTE
|
||||
0xDB 0x016A # LATIN CAPITAL LETTER U WITH MACRON
|
||||
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
0xDE 0x017D # LATIN CAPITAL LETTER Z WITH CARON
|
||||
0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German)
|
||||
0xE0 0x0105 # LATIN SMALL LETTER A WITH OGONEK
|
||||
0xE1 0x012F # LATIN SMALL LETTER I WITH OGONEK
|
||||
0xE2 0x0101 # LATIN SMALL LETTER A WITH MACRON
|
||||
0xE3 0x0107 # LATIN SMALL LETTER C WITH ACUTE
|
||||
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x0119 # LATIN SMALL LETTER E WITH OGONEK
|
||||
0xE7 0x0113 # LATIN SMALL LETTER E WITH MACRON
|
||||
0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
|
||||
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x017A # LATIN SMALL LETTER Z WITH ACUTE
|
||||
0xEB 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
0xEC 0x0123 # LATIN SMALL LETTER G WITH CEDILLA
|
||||
0xED 0x0137 # LATIN SMALL LETTER K WITH CEDILLA
|
||||
0xEE 0x012B # LATIN SMALL LETTER I WITH MACRON
|
||||
0xEF 0x013C # LATIN SMALL LETTER L WITH CEDILLA
|
||||
0xF0 0x0161 # LATIN SMALL LETTER S WITH CARON
|
||||
0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE
|
||||
0xF2 0x0146 # LATIN SMALL LETTER N WITH CEDILLA
|
||||
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x014D # LATIN SMALL LETTER O WITH MACRON
|
||||
0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 # DIVISION SIGN
|
||||
0xF8 0x0173 # LATIN SMALL LETTER U WITH OGONEK
|
||||
0xF9 0x0142 # LATIN SMALL LETTER L WITH STROKE
|
||||
0xFA 0x015B # LATIN SMALL LETTER S WITH ACUTE
|
||||
0xFB 0x016B # LATIN SMALL LETTER U WITH MACRON
|
||||
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
0xFE 0x017E # LATIN SMALL LETTER Z WITH CARON
|
||||
0xFF 0x2019 # RIGHT SINGLE QUOTATION MARK
|
||||
@@ -0,0 +1,300 @@
|
||||
#
|
||||
# Name: ISO/IEC 8859-14:1998 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 1999 July 27
|
||||
# Authors: Markus Kuhn <mkuhn@acm.org>
|
||||
# Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-14:1998 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-14 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-14 order.
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x1E02 # LATIN CAPITAL LETTER B WITH DOT ABOVE
|
||||
0xA2 0x1E03 # LATIN SMALL LETTER B WITH DOT ABOVE
|
||||
0xA3 0x00A3 # POUND SIGN
|
||||
0xA4 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE
|
||||
0xA5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE
|
||||
0xA6 0x1E0A # LATIN CAPITAL LETTER D WITH DOT ABOVE
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x1E80 # LATIN CAPITAL LETTER W WITH GRAVE
|
||||
0xA9 0x00A9 # COPYRIGHT SIGN
|
||||
0xAA 0x1E82 # LATIN CAPITAL LETTER W WITH ACUTE
|
||||
0xAB 0x1E0B # LATIN SMALL LETTER D WITH DOT ABOVE
|
||||
0xAC 0x1EF2 # LATIN CAPITAL LETTER Y WITH GRAVE
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAE 0x00AE # REGISTERED SIGN
|
||||
0xAF 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
0xB0 0x1E1E # LATIN CAPITAL LETTER F WITH DOT ABOVE
|
||||
0xB1 0x1E1F # LATIN SMALL LETTER F WITH DOT ABOVE
|
||||
0xB2 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE
|
||||
0xB3 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE
|
||||
0xB4 0x1E40 # LATIN CAPITAL LETTER M WITH DOT ABOVE
|
||||
0xB5 0x1E41 # LATIN SMALL LETTER M WITH DOT ABOVE
|
||||
0xB6 0x00B6 # PILCROW SIGN
|
||||
0xB7 0x1E56 # LATIN CAPITAL LETTER P WITH DOT ABOVE
|
||||
0xB8 0x1E81 # LATIN SMALL LETTER W WITH GRAVE
|
||||
0xB9 0x1E57 # LATIN SMALL LETTER P WITH DOT ABOVE
|
||||
0xBA 0x1E83 # LATIN SMALL LETTER W WITH ACUTE
|
||||
0xBB 0x1E60 # LATIN CAPITAL LETTER S WITH DOT ABOVE
|
||||
0xBC 0x1EF3 # LATIN SMALL LETTER Y WITH GRAVE
|
||||
0xBD 0x1E84 # LATIN CAPITAL LETTER W WITH DIAERESIS
|
||||
0xBE 0x1E85 # LATIN SMALL LETTER W WITH DIAERESIS
|
||||
0xBF 0x1E61 # LATIN SMALL LETTER S WITH DOT ABOVE
|
||||
0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x00C6 # LATIN CAPITAL LETTER AE
|
||||
0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD0 0x0174 # LATIN CAPITAL LETTER W WITH CIRCUMFLEX
|
||||
0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x1E6A # LATIN CAPITAL LETTER T WITH DOT ABOVE
|
||||
0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0xDE 0x0176 # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX
|
||||
0xDF 0x00DF # LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE
|
||||
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x00E6 # LATIN SMALL LETTER AE
|
||||
0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE
|
||||
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x0175 # LATIN SMALL LETTER W WITH CIRCUMFLEX
|
||||
0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE
|
||||
0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
|
||||
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x1E6B # LATIN SMALL LETTER T WITH DOT ABOVE
|
||||
0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
|
||||
0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0xFE 0x0177 # LATIN SMALL LETTER Y WITH CIRCUMFLEX
|
||||
0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
@@ -0,0 +1,302 @@
|
||||
#
|
||||
# Name: ISO/IEC 8859-15:1999 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 1999 July 27
|
||||
# Authors: Markus Kuhn <mkuhn@acm.org>
|
||||
# Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-15:1999 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-15 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-15 order.
|
||||
#
|
||||
# Version history
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x00A1 # INVERTED EXCLAMATION MARK
|
||||
0xA2 0x00A2 # CENT SIGN
|
||||
0xA3 0x00A3 # POUND SIGN
|
||||
0xA4 0x20AC # EURO SIGN
|
||||
0xA5 0x00A5 # YEN SIGN
|
||||
0xA6 0x0160 # LATIN CAPITAL LETTER S WITH CARON
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x0161 # LATIN SMALL LETTER S WITH CARON
|
||||
0xA9 0x00A9 # COPYRIGHT SIGN
|
||||
0xAA 0x00AA # FEMININE ORDINAL INDICATOR
|
||||
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC # NOT SIGN
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAE 0x00AE # REGISTERED SIGN
|
||||
0xAF 0x00AF # MACRON
|
||||
0xB0 0x00B0 # DEGREE SIGN
|
||||
0xB1 0x00B1 # PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 # SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 # SUPERSCRIPT THREE
|
||||
0xB4 0x017D # LATIN CAPITAL LETTER Z WITH CARON
|
||||
0xB5 0x00B5 # MICRO SIGN
|
||||
0xB6 0x00B6 # PILCROW SIGN
|
||||
0xB7 0x00B7 # MIDDLE DOT
|
||||
0xB8 0x017E # LATIN SMALL LETTER Z WITH CARON
|
||||
0xB9 0x00B9 # SUPERSCRIPT ONE
|
||||
0xBA 0x00BA # MASCULINE ORDINAL INDICATOR
|
||||
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x0152 # LATIN CAPITAL LIGATURE OE
|
||||
0xBD 0x0153 # LATIN SMALL LIGATURE OE
|
||||
0xBE 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
0xBF 0x00BF # INVERTED QUESTION MARK
|
||||
0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x00C6 # LATIN CAPITAL LETTER AE
|
||||
0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD0 0x00D0 # LATIN CAPITAL LETTER ETH
|
||||
0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 # MULTIPLICATION SIGN
|
||||
0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0xDE 0x00DE # LATIN CAPITAL LETTER THORN
|
||||
0xDF 0x00DF # LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE
|
||||
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x00E6 # LATIN SMALL LETTER AE
|
||||
0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE
|
||||
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x00F0 # LATIN SMALL LETTER ETH
|
||||
0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE
|
||||
0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
|
||||
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 # DIVISION SIGN
|
||||
0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
|
||||
0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0xFE 0x00FE # LATIN SMALL LETTER THORN
|
||||
0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
@@ -0,0 +1,299 @@
|
||||
#
|
||||
# Name: ISO/IEC 8859-16:2001 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 2001 July 26
|
||||
# Authors: Markus Kuhn <mkuhn@acm.org>
|
||||
#
|
||||
# Copyright (c) 1999-2001 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-16:2001 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-16 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-16 order.
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0xA2 0x0105 # LATIN SMALL LETTER A WITH OGONEK
|
||||
0xA3 0x0141 # LATIN CAPITAL LETTER L WITH STROKE
|
||||
0xA4 0x20AC # EURO SIGN
|
||||
0xA5 0x201E # DOUBLE LOW-9 QUOTATION MARK
|
||||
0xA6 0x0160 # LATIN CAPITAL LETTER S WITH CARON
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x0161 # LATIN SMALL LETTER S WITH CARON
|
||||
0xA9 0x00A9 # COPYRIGHT SIGN
|
||||
0xAA 0x0218 # LATIN CAPITAL LETTER S WITH COMMA BELOW
|
||||
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAE 0x017A # LATIN SMALL LETTER Z WITH ACUTE
|
||||
0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
0xB0 0x00B0 # DEGREE SIGN
|
||||
0xB1 0x00B1 # PLUS-MINUS SIGN
|
||||
0xB2 0x010C # LATIN CAPITAL LETTER C WITH CARON
|
||||
0xB3 0x0142 # LATIN SMALL LETTER L WITH STROKE
|
||||
0xB4 0x017D # LATIN CAPITAL LETTER Z WITH CARON
|
||||
0xB5 0x201D # RIGHT DOUBLE QUOTATION MARK
|
||||
0xB6 0x00B6 # PILCROW SIGN
|
||||
0xB7 0x00B7 # MIDDLE DOT
|
||||
0xB8 0x017E # LATIN SMALL LETTER Z WITH CARON
|
||||
0xB9 0x010D # LATIN SMALL LETTER C WITH CARON
|
||||
0xBA 0x0219 # LATIN SMALL LETTER S WITH COMMA BELOW
|
||||
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x0152 # LATIN CAPITAL LIGATURE OE
|
||||
0xBD 0x0153 # LATIN SMALL LIGATURE OE
|
||||
0xBE 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x0102 # LATIN CAPITAL LETTER A WITH BREVE
|
||||
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE
|
||||
0xC6 0x00C6 # LATIN CAPITAL LETTER AE
|
||||
0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
|
||||
0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE
|
||||
0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
|
||||
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x015A # LATIN CAPITAL LETTER S WITH ACUTE
|
||||
0xD8 0x0170 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
|
||||
0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0xDE 0x021A # LATIN CAPITAL LETTER T WITH COMMA BELOW
|
||||
0xDF 0x00DF # LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x0103 # LATIN SMALL LETTER A WITH BREVE
|
||||
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x0107 # LATIN SMALL LETTER C WITH ACUTE
|
||||
0xE6 0x00E6 # LATIN SMALL LETTER AE
|
||||
0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE
|
||||
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE
|
||||
0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE
|
||||
0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
|
||||
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE
|
||||
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x015B # LATIN SMALL LETTER S WITH ACUTE
|
||||
0xF8 0x0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE
|
||||
0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x0119 # LATIN SMALL LETTER E WITH OGONEK
|
||||
0xFE 0x021B # LATIN SMALL LETTER T WITH COMMA BELOW
|
||||
0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
@@ -0,0 +1,303 @@
|
||||
#
|
||||
# Name: ISO 8859-2:1999 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 1999 July 27
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-2:1999 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-2 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-2 order.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version updates 0.1 version by adding mappings for all
|
||||
# control characters.
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0xA2 0x02D8 # BREVE
|
||||
0xA3 0x0141 # LATIN CAPITAL LETTER L WITH STROKE
|
||||
0xA4 0x00A4 # CURRENCY SIGN
|
||||
0xA5 0x013D # LATIN CAPITAL LETTER L WITH CARON
|
||||
0xA6 0x015A # LATIN CAPITAL LETTER S WITH ACUTE
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x00A8 # DIAERESIS
|
||||
0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON
|
||||
0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
0xAB 0x0164 # LATIN CAPITAL LETTER T WITH CARON
|
||||
0xAC 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON
|
||||
0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
0xB0 0x00B0 # DEGREE SIGN
|
||||
0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK
|
||||
0xB2 0x02DB # OGONEK
|
||||
0xB3 0x0142 # LATIN SMALL LETTER L WITH STROKE
|
||||
0xB4 0x00B4 # ACUTE ACCENT
|
||||
0xB5 0x013E # LATIN SMALL LETTER L WITH CARON
|
||||
0xB6 0x015B # LATIN SMALL LETTER S WITH ACUTE
|
||||
0xB7 0x02C7 # CARON
|
||||
0xB8 0x00B8 # CEDILLA
|
||||
0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON
|
||||
0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA
|
||||
0xBB 0x0165 # LATIN SMALL LETTER T WITH CARON
|
||||
0xBC 0x017A # LATIN SMALL LETTER Z WITH ACUTE
|
||||
0xBD 0x02DD # DOUBLE ACUTE ACCENT
|
||||
0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON
|
||||
0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
0xC0 0x0154 # LATIN CAPITAL LETTER R WITH ACUTE
|
||||
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x0102 # LATIN CAPITAL LETTER A WITH BREVE
|
||||
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x0139 # LATIN CAPITAL LETTER L WITH ACUTE
|
||||
0xC6 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE
|
||||
0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
|
||||
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x011A # LATIN CAPITAL LETTER E WITH CARON
|
||||
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x010E # LATIN CAPITAL LETTER D WITH CARON
|
||||
0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
|
||||
0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE
|
||||
0xD2 0x0147 # LATIN CAPITAL LETTER N WITH CARON
|
||||
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
|
||||
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 # MULTIPLICATION SIGN
|
||||
0xD8 0x0158 # LATIN CAPITAL LETTER R WITH CARON
|
||||
0xD9 0x016E # LATIN CAPITAL LETTER U WITH RING ABOVE
|
||||
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x0170 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
|
||||
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0xDE 0x0162 # LATIN CAPITAL LETTER T WITH CEDILLA
|
||||
0xDF 0x00DF # LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x0155 # LATIN SMALL LETTER R WITH ACUTE
|
||||
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x0103 # LATIN SMALL LETTER A WITH BREVE
|
||||
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x013A # LATIN SMALL LETTER L WITH ACUTE
|
||||
0xE6 0x0107 # LATIN SMALL LETTER C WITH ACUTE
|
||||
0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
|
||||
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK
|
||||
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x011B # LATIN SMALL LETTER E WITH CARON
|
||||
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x010F # LATIN SMALL LETTER D WITH CARON
|
||||
0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE
|
||||
0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE
|
||||
0xF2 0x0148 # LATIN SMALL LETTER N WITH CARON
|
||||
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE
|
||||
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 # DIVISION SIGN
|
||||
0xF8 0x0159 # LATIN SMALL LETTER R WITH CARON
|
||||
0xF9 0x016F # LATIN SMALL LETTER U WITH RING ABOVE
|
||||
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE
|
||||
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0xFE 0x0163 # LATIN SMALL LETTER T WITH CEDILLA
|
||||
0xFF 0x02D9 # DOT ABOVE
|
||||
@@ -0,0 +1,296 @@
|
||||
#
|
||||
# Name: ISO/IEC 8859-3:1999 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 1999 July 27
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-3:1999 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-3 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-3 order.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version updates 0.1 version by adding mappings for all
|
||||
# control characters.
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x0126 # LATIN CAPITAL LETTER H WITH STROKE
|
||||
0xA2 0x02D8 # BREVE
|
||||
0xA3 0x00A3 # POUND SIGN
|
||||
0xA4 0x00A4 # CURRENCY SIGN
|
||||
0xA6 0x0124 # LATIN CAPITAL LETTER H WITH CIRCUMFLEX
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x00A8 # DIAERESIS
|
||||
0xA9 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
0xAB 0x011E # LATIN CAPITAL LETTER G WITH BREVE
|
||||
0xAC 0x0134 # LATIN CAPITAL LETTER J WITH CIRCUMFLEX
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
0xB0 0x00B0 # DEGREE SIGN
|
||||
0xB1 0x0127 # LATIN SMALL LETTER H WITH STROKE
|
||||
0xB2 0x00B2 # SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 # SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 # ACUTE ACCENT
|
||||
0xB5 0x00B5 # MICRO SIGN
|
||||
0xB6 0x0125 # LATIN SMALL LETTER H WITH CIRCUMFLEX
|
||||
0xB7 0x00B7 # MIDDLE DOT
|
||||
0xB8 0x00B8 # CEDILLA
|
||||
0xB9 0x0131 # LATIN SMALL LETTER DOTLESS I
|
||||
0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA
|
||||
0xBB 0x011F # LATIN SMALL LETTER G WITH BREVE
|
||||
0xBC 0x0135 # LATIN SMALL LETTER J WITH CIRCUMFLEX
|
||||
0xBD 0x00BD # VULGAR FRACTION ONE HALF
|
||||
0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE
|
||||
0xC6 0x0108 # LATIN CAPITAL LETTER C WITH CIRCUMFLEX
|
||||
0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE
|
||||
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 # MULTIPLICATION SIGN
|
||||
0xD8 0x011C # LATIN CAPITAL LETTER G WITH CIRCUMFLEX
|
||||
0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x016C # LATIN CAPITAL LETTER U WITH BREVE
|
||||
0xDE 0x015C # LATIN CAPITAL LETTER S WITH CIRCUMFLEX
|
||||
0xDF 0x00DF # LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE
|
||||
0xE6 0x0109 # LATIN SMALL LETTER C WITH CIRCUMFLEX
|
||||
0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE
|
||||
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE
|
||||
0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
|
||||
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE
|
||||
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 # DIVISION SIGN
|
||||
0xF8 0x011D # LATIN SMALL LETTER G WITH CIRCUMFLEX
|
||||
0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x016D # LATIN SMALL LETTER U WITH BREVE
|
||||
0xFE 0x015D # LATIN SMALL LETTER S WITH CIRCUMFLEX
|
||||
0xFF 0x02D9 # DOT ABOVE
|
||||
@@ -0,0 +1,303 @@
|
||||
#
|
||||
# Name: ISO/IEC 8859-4:1998 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 1999 July 27
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-4:1998 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-4 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-4 order.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version updates 0.1 version by adding mappings for all
|
||||
# control characters.
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0xA2 0x0138 # LATIN SMALL LETTER KRA
|
||||
0xA3 0x0156 # LATIN CAPITAL LETTER R WITH CEDILLA
|
||||
0xA4 0x00A4 # CURRENCY SIGN
|
||||
0xA5 0x0128 # LATIN CAPITAL LETTER I WITH TILDE
|
||||
0xA6 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x00A8 # DIAERESIS
|
||||
0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON
|
||||
0xAA 0x0112 # LATIN CAPITAL LETTER E WITH MACRON
|
||||
0xAB 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
0xAC 0x0166 # LATIN CAPITAL LETTER T WITH STROKE
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON
|
||||
0xAF 0x00AF # MACRON
|
||||
0xB0 0x00B0 # DEGREE SIGN
|
||||
0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK
|
||||
0xB2 0x02DB # OGONEK
|
||||
0xB3 0x0157 # LATIN SMALL LETTER R WITH CEDILLA
|
||||
0xB4 0x00B4 # ACUTE ACCENT
|
||||
0xB5 0x0129 # LATIN SMALL LETTER I WITH TILDE
|
||||
0xB6 0x013C # LATIN SMALL LETTER L WITH CEDILLA
|
||||
0xB7 0x02C7 # CARON
|
||||
0xB8 0x00B8 # CEDILLA
|
||||
0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON
|
||||
0xBA 0x0113 # LATIN SMALL LETTER E WITH MACRON
|
||||
0xBB 0x0123 # LATIN SMALL LETTER G WITH CEDILLA
|
||||
0xBC 0x0167 # LATIN SMALL LETTER T WITH STROKE
|
||||
0xBD 0x014A # LATIN CAPITAL LETTER ENG
|
||||
0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON
|
||||
0xBF 0x014B # LATIN SMALL LETTER ENG
|
||||
0xC0 0x0100 # LATIN CAPITAL LETTER A WITH MACRON
|
||||
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x00C6 # LATIN CAPITAL LETTER AE
|
||||
0xC7 0x012E # LATIN CAPITAL LETTER I WITH OGONEK
|
||||
0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
|
||||
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x012A # LATIN CAPITAL LETTER I WITH MACRON
|
||||
0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
|
||||
0xD1 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
0xD2 0x014C # LATIN CAPITAL LETTER O WITH MACRON
|
||||
0xD3 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 # MULTIPLICATION SIGN
|
||||
0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xD9 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK
|
||||
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x0168 # LATIN CAPITAL LETTER U WITH TILDE
|
||||
0xDE 0x016A # LATIN CAPITAL LETTER U WITH MACRON
|
||||
0xDF 0x00DF # LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x0101 # LATIN SMALL LETTER A WITH MACRON
|
||||
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE
|
||||
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x00E6 # LATIN SMALL LETTER AE
|
||||
0xE7 0x012F # LATIN SMALL LETTER I WITH OGONEK
|
||||
0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
|
||||
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK
|
||||
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x012B # LATIN SMALL LETTER I WITH MACRON
|
||||
0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE
|
||||
0xF1 0x0146 # LATIN SMALL LETTER N WITH CEDILLA
|
||||
0xF2 0x014D # LATIN SMALL LETTER O WITH MACRON
|
||||
0xF3 0x0137 # LATIN SMALL LETTER K WITH CEDILLA
|
||||
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 # DIVISION SIGN
|
||||
0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
|
||||
0xF9 0x0173 # LATIN SMALL LETTER U WITH OGONEK
|
||||
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x0169 # LATIN SMALL LETTER U WITH TILDE
|
||||
0xFE 0x016B # LATIN SMALL LETTER U WITH MACRON
|
||||
0xFF 0x02D9 # DOT ABOVE
|
||||
@@ -0,0 +1,303 @@
|
||||
#
|
||||
# Name: ISO 8859-5:1999 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 1999 July 27
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-5:1999 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-5 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-5 order.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version updates 0.1 version by adding mappings for all
|
||||
# control characters.
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x0401 # CYRILLIC CAPITAL LETTER IO
|
||||
0xA2 0x0402 # CYRILLIC CAPITAL LETTER DJE
|
||||
0xA3 0x0403 # CYRILLIC CAPITAL LETTER GJE
|
||||
0xA4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
0xA5 0x0405 # CYRILLIC CAPITAL LETTER DZE
|
||||
0xA6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0xA7 0x0407 # CYRILLIC CAPITAL LETTER YI
|
||||
0xA8 0x0408 # CYRILLIC CAPITAL LETTER JE
|
||||
0xA9 0x0409 # CYRILLIC CAPITAL LETTER LJE
|
||||
0xAA 0x040A # CYRILLIC CAPITAL LETTER NJE
|
||||
0xAB 0x040B # CYRILLIC CAPITAL LETTER TSHE
|
||||
0xAC 0x040C # CYRILLIC CAPITAL LETTER KJE
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAE 0x040E # CYRILLIC CAPITAL LETTER SHORT U
|
||||
0xAF 0x040F # CYRILLIC CAPITAL LETTER DZHE
|
||||
0xB0 0x0410 # CYRILLIC CAPITAL LETTER A
|
||||
0xB1 0x0411 # CYRILLIC CAPITAL LETTER BE
|
||||
0xB2 0x0412 # CYRILLIC CAPITAL LETTER VE
|
||||
0xB3 0x0413 # CYRILLIC CAPITAL LETTER GHE
|
||||
0xB4 0x0414 # CYRILLIC CAPITAL LETTER DE
|
||||
0xB5 0x0415 # CYRILLIC CAPITAL LETTER IE
|
||||
0xB6 0x0416 # CYRILLIC CAPITAL LETTER ZHE
|
||||
0xB7 0x0417 # CYRILLIC CAPITAL LETTER ZE
|
||||
0xB8 0x0418 # CYRILLIC CAPITAL LETTER I
|
||||
0xB9 0x0419 # CYRILLIC CAPITAL LETTER SHORT I
|
||||
0xBA 0x041A # CYRILLIC CAPITAL LETTER KA
|
||||
0xBB 0x041B # CYRILLIC CAPITAL LETTER EL
|
||||
0xBC 0x041C # CYRILLIC CAPITAL LETTER EM
|
||||
0xBD 0x041D # CYRILLIC CAPITAL LETTER EN
|
||||
0xBE 0x041E # CYRILLIC CAPITAL LETTER O
|
||||
0xBF 0x041F # CYRILLIC CAPITAL LETTER PE
|
||||
0xC0 0x0420 # CYRILLIC CAPITAL LETTER ER
|
||||
0xC1 0x0421 # CYRILLIC CAPITAL LETTER ES
|
||||
0xC2 0x0422 # CYRILLIC CAPITAL LETTER TE
|
||||
0xC3 0x0423 # CYRILLIC CAPITAL LETTER U
|
||||
0xC4 0x0424 # CYRILLIC CAPITAL LETTER EF
|
||||
0xC5 0x0425 # CYRILLIC CAPITAL LETTER HA
|
||||
0xC6 0x0426 # CYRILLIC CAPITAL LETTER TSE
|
||||
0xC7 0x0427 # CYRILLIC CAPITAL LETTER CHE
|
||||
0xC8 0x0428 # CYRILLIC CAPITAL LETTER SHA
|
||||
0xC9 0x0429 # CYRILLIC CAPITAL LETTER SHCHA
|
||||
0xCA 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
0xCB 0x042B # CYRILLIC CAPITAL LETTER YERU
|
||||
0xCC 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
0xCD 0x042D # CYRILLIC CAPITAL LETTER E
|
||||
0xCE 0x042E # CYRILLIC CAPITAL LETTER YU
|
||||
0xCF 0x042F # CYRILLIC CAPITAL LETTER YA
|
||||
0xD0 0x0430 # CYRILLIC SMALL LETTER A
|
||||
0xD1 0x0431 # CYRILLIC SMALL LETTER BE
|
||||
0xD2 0x0432 # CYRILLIC SMALL LETTER VE
|
||||
0xD3 0x0433 # CYRILLIC SMALL LETTER GHE
|
||||
0xD4 0x0434 # CYRILLIC SMALL LETTER DE
|
||||
0xD5 0x0435 # CYRILLIC SMALL LETTER IE
|
||||
0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE
|
||||
0xD7 0x0437 # CYRILLIC SMALL LETTER ZE
|
||||
0xD8 0x0438 # CYRILLIC SMALL LETTER I
|
||||
0xD9 0x0439 # CYRILLIC SMALL LETTER SHORT I
|
||||
0xDA 0x043A # CYRILLIC SMALL LETTER KA
|
||||
0xDB 0x043B # CYRILLIC SMALL LETTER EL
|
||||
0xDC 0x043C # CYRILLIC SMALL LETTER EM
|
||||
0xDD 0x043D # CYRILLIC SMALL LETTER EN
|
||||
0xDE 0x043E # CYRILLIC SMALL LETTER O
|
||||
0xDF 0x043F # CYRILLIC SMALL LETTER PE
|
||||
0xE0 0x0440 # CYRILLIC SMALL LETTER ER
|
||||
0xE1 0x0441 # CYRILLIC SMALL LETTER ES
|
||||
0xE2 0x0442 # CYRILLIC SMALL LETTER TE
|
||||
0xE3 0x0443 # CYRILLIC SMALL LETTER U
|
||||
0xE4 0x0444 # CYRILLIC SMALL LETTER EF
|
||||
0xE5 0x0445 # CYRILLIC SMALL LETTER HA
|
||||
0xE6 0x0446 # CYRILLIC SMALL LETTER TSE
|
||||
0xE7 0x0447 # CYRILLIC SMALL LETTER CHE
|
||||
0xE8 0x0448 # CYRILLIC SMALL LETTER SHA
|
||||
0xE9 0x0449 # CYRILLIC SMALL LETTER SHCHA
|
||||
0xEA 0x044A # CYRILLIC SMALL LETTER HARD SIGN
|
||||
0xEB 0x044B # CYRILLIC SMALL LETTER YERU
|
||||
0xEC 0x044C # CYRILLIC SMALL LETTER SOFT SIGN
|
||||
0xED 0x044D # CYRILLIC SMALL LETTER E
|
||||
0xEE 0x044E # CYRILLIC SMALL LETTER YU
|
||||
0xEF 0x044F # CYRILLIC SMALL LETTER YA
|
||||
0xF0 0x2116 # NUMERO SIGN
|
||||
0xF1 0x0451 # CYRILLIC SMALL LETTER IO
|
||||
0xF2 0x0452 # CYRILLIC SMALL LETTER DJE
|
||||
0xF3 0x0453 # CYRILLIC SMALL LETTER GJE
|
||||
0xF4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
0xF5 0x0455 # CYRILLIC SMALL LETTER DZE
|
||||
0xF6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0xF7 0x0457 # CYRILLIC SMALL LETTER YI
|
||||
0xF8 0x0458 # CYRILLIC SMALL LETTER JE
|
||||
0xF9 0x0459 # CYRILLIC SMALL LETTER LJE
|
||||
0xFA 0x045A # CYRILLIC SMALL LETTER NJE
|
||||
0xFB 0x045B # CYRILLIC SMALL LETTER TSHE
|
||||
0xFC 0x045C # CYRILLIC SMALL LETTER KJE
|
||||
0xFD 0x00A7 # SECTION SIGN
|
||||
0xFE 0x045E # CYRILLIC SMALL LETTER SHORT U
|
||||
0xFF 0x045F # CYRILLIC SMALL LETTER DZHE
|
||||
@@ -0,0 +1,260 @@
|
||||
#
|
||||
# Name: ISO 8859-6:1999 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 1999 July 27
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-6:1999 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-6 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-6 order.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version updates 0.1 version by adding mappings for all
|
||||
# control characters.
|
||||
# 0x30..0x39 remapped to the ASCII digits (U+0030..U+0039) instead
|
||||
# of the Arabic digits (U+0660..U+0669).
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA4 0x00A4 # CURRENCY SIGN
|
||||
0xAC 0x060C # ARABIC COMMA
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xBB 0x061B # ARABIC SEMICOLON
|
||||
0xBF 0x061F # ARABIC QUESTION MARK
|
||||
0xC1 0x0621 # ARABIC LETTER HAMZA
|
||||
0xC2 0x0622 # ARABIC LETTER ALEF WITH MADDA ABOVE
|
||||
0xC3 0x0623 # ARABIC LETTER ALEF WITH HAMZA ABOVE
|
||||
0xC4 0x0624 # ARABIC LETTER WAW WITH HAMZA ABOVE
|
||||
0xC5 0x0625 # ARABIC LETTER ALEF WITH HAMZA BELOW
|
||||
0xC6 0x0626 # ARABIC LETTER YEH WITH HAMZA ABOVE
|
||||
0xC7 0x0627 # ARABIC LETTER ALEF
|
||||
0xC8 0x0628 # ARABIC LETTER BEH
|
||||
0xC9 0x0629 # ARABIC LETTER TEH MARBUTA
|
||||
0xCA 0x062A # ARABIC LETTER TEH
|
||||
0xCB 0x062B # ARABIC LETTER THEH
|
||||
0xCC 0x062C # ARABIC LETTER JEEM
|
||||
0xCD 0x062D # ARABIC LETTER HAH
|
||||
0xCE 0x062E # ARABIC LETTER KHAH
|
||||
0xCF 0x062F # ARABIC LETTER DAL
|
||||
0xD0 0x0630 # ARABIC LETTER THAL
|
||||
0xD1 0x0631 # ARABIC LETTER REH
|
||||
0xD2 0x0632 # ARABIC LETTER ZAIN
|
||||
0xD3 0x0633 # ARABIC LETTER SEEN
|
||||
0xD4 0x0634 # ARABIC LETTER SHEEN
|
||||
0xD5 0x0635 # ARABIC LETTER SAD
|
||||
0xD6 0x0636 # ARABIC LETTER DAD
|
||||
0xD7 0x0637 # ARABIC LETTER TAH
|
||||
0xD8 0x0638 # ARABIC LETTER ZAH
|
||||
0xD9 0x0639 # ARABIC LETTER AIN
|
||||
0xDA 0x063A # ARABIC LETTER GHAIN
|
||||
0xE0 0x0640 # ARABIC TATWEEL
|
||||
0xE1 0x0641 # ARABIC LETTER FEH
|
||||
0xE2 0x0642 # ARABIC LETTER QAF
|
||||
0xE3 0x0643 # ARABIC LETTER KAF
|
||||
0xE4 0x0644 # ARABIC LETTER LAM
|
||||
0xE5 0x0645 # ARABIC LETTER MEEM
|
||||
0xE6 0x0646 # ARABIC LETTER NOON
|
||||
0xE7 0x0647 # ARABIC LETTER HEH
|
||||
0xE8 0x0648 # ARABIC LETTER WAW
|
||||
0xE9 0x0649 # ARABIC LETTER ALEF MAKSURA
|
||||
0xEA 0x064A # ARABIC LETTER YEH
|
||||
0xEB 0x064B # ARABIC FATHATAN
|
||||
0xEC 0x064C # ARABIC DAMMATAN
|
||||
0xED 0x064D # ARABIC KASRATAN
|
||||
0xEE 0x064E # ARABIC FATHA
|
||||
0xEF 0x064F # ARABIC DAMMA
|
||||
0xF0 0x0650 # ARABIC KASRA
|
||||
0xF1 0x0651 # ARABIC SHADDA
|
||||
0xF2 0x0652 # ARABIC SUKUN
|
||||
@@ -0,0 +1,302 @@
|
||||
#
|
||||
# Name: ISO 8859-7:1987 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 1999 July 27
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO 8859-7:1987 characters map into Unicode.
|
||||
#
|
||||
# ISO 8859-7:1987 is equivalent to ISO-IR-126, ELOT 928,
|
||||
# and ECMA 118.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO 8859-7 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO 8859-7 order.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version updates 0.1 version by adding mappings for all
|
||||
# control characters.
|
||||
# Remap 0xA1 to U+2018 (instead of 0x02BD) to match text of 8859-7
|
||||
# Remap 0xA2 to U+2019 (instead of 0x02BC) to match text of 8859-7
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x2018 # LEFT SINGLE QUOTATION MARK
|
||||
0xA2 0x2019 # RIGHT SINGLE QUOTATION MARK
|
||||
0xA3 0x00A3 # POUND SIGN
|
||||
0xA6 0x00A6 # BROKEN BAR
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x00A8 # DIAERESIS
|
||||
0xA9 0x00A9 # COPYRIGHT SIGN
|
||||
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC # NOT SIGN
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAF 0x2015 # HORIZONTAL BAR
|
||||
0xB0 0x00B0 # DEGREE SIGN
|
||||
0xB1 0x00B1 # PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 # SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 # SUPERSCRIPT THREE
|
||||
0xB4 0x0384 # GREEK TONOS
|
||||
0xB5 0x0385 # GREEK DIALYTIKA TONOS
|
||||
0xB6 0x0386 # GREEK CAPITAL LETTER ALPHA WITH TONOS
|
||||
0xB7 0x00B7 # MIDDLE DOT
|
||||
0xB8 0x0388 # GREEK CAPITAL LETTER EPSILON WITH TONOS
|
||||
0xB9 0x0389 # GREEK CAPITAL LETTER ETA WITH TONOS
|
||||
0xBA 0x038A # GREEK CAPITAL LETTER IOTA WITH TONOS
|
||||
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x038C # GREEK CAPITAL LETTER OMICRON WITH TONOS
|
||||
0xBD 0x00BD # VULGAR FRACTION ONE HALF
|
||||
0xBE 0x038E # GREEK CAPITAL LETTER UPSILON WITH TONOS
|
||||
0xBF 0x038F # GREEK CAPITAL LETTER OMEGA WITH TONOS
|
||||
0xC0 0x0390 # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
|
||||
0xC1 0x0391 # GREEK CAPITAL LETTER ALPHA
|
||||
0xC2 0x0392 # GREEK CAPITAL LETTER BETA
|
||||
0xC3 0x0393 # GREEK CAPITAL LETTER GAMMA
|
||||
0xC4 0x0394 # GREEK CAPITAL LETTER DELTA
|
||||
0xC5 0x0395 # GREEK CAPITAL LETTER EPSILON
|
||||
0xC6 0x0396 # GREEK CAPITAL LETTER ZETA
|
||||
0xC7 0x0397 # GREEK CAPITAL LETTER ETA
|
||||
0xC8 0x0398 # GREEK CAPITAL LETTER THETA
|
||||
0xC9 0x0399 # GREEK CAPITAL LETTER IOTA
|
||||
0xCA 0x039A # GREEK CAPITAL LETTER KAPPA
|
||||
0xCB 0x039B # GREEK CAPITAL LETTER LAMDA
|
||||
0xCC 0x039C # GREEK CAPITAL LETTER MU
|
||||
0xCD 0x039D # GREEK CAPITAL LETTER NU
|
||||
0xCE 0x039E # GREEK CAPITAL LETTER XI
|
||||
0xCF 0x039F # GREEK CAPITAL LETTER OMICRON
|
||||
0xD0 0x03A0 # GREEK CAPITAL LETTER PI
|
||||
0xD1 0x03A1 # GREEK CAPITAL LETTER RHO
|
||||
0xD3 0x03A3 # GREEK CAPITAL LETTER SIGMA
|
||||
0xD4 0x03A4 # GREEK CAPITAL LETTER TAU
|
||||
0xD5 0x03A5 # GREEK CAPITAL LETTER UPSILON
|
||||
0xD6 0x03A6 # GREEK CAPITAL LETTER PHI
|
||||
0xD7 0x03A7 # GREEK CAPITAL LETTER CHI
|
||||
0xD8 0x03A8 # GREEK CAPITAL LETTER PSI
|
||||
0xD9 0x03A9 # GREEK CAPITAL LETTER OMEGA
|
||||
0xDA 0x03AA # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
|
||||
0xDB 0x03AB # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
|
||||
0xDC 0x03AC # GREEK SMALL LETTER ALPHA WITH TONOS
|
||||
0xDD 0x03AD # GREEK SMALL LETTER EPSILON WITH TONOS
|
||||
0xDE 0x03AE # GREEK SMALL LETTER ETA WITH TONOS
|
||||
0xDF 0x03AF # GREEK SMALL LETTER IOTA WITH TONOS
|
||||
0xE0 0x03B0 # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
|
||||
0xE1 0x03B1 # GREEK SMALL LETTER ALPHA
|
||||
0xE2 0x03B2 # GREEK SMALL LETTER BETA
|
||||
0xE3 0x03B3 # GREEK SMALL LETTER GAMMA
|
||||
0xE4 0x03B4 # GREEK SMALL LETTER DELTA
|
||||
0xE5 0x03B5 # GREEK SMALL LETTER EPSILON
|
||||
0xE6 0x03B6 # GREEK SMALL LETTER ZETA
|
||||
0xE7 0x03B7 # GREEK SMALL LETTER ETA
|
||||
0xE8 0x03B8 # GREEK SMALL LETTER THETA
|
||||
0xE9 0x03B9 # GREEK SMALL LETTER IOTA
|
||||
0xEA 0x03BA # GREEK SMALL LETTER KAPPA
|
||||
0xEB 0x03BB # GREEK SMALL LETTER LAMDA
|
||||
0xEC 0x03BC # GREEK SMALL LETTER MU
|
||||
0xED 0x03BD # GREEK SMALL LETTER NU
|
||||
0xEE 0x03BE # GREEK SMALL LETTER XI
|
||||
0xEF 0x03BF # GREEK SMALL LETTER OMICRON
|
||||
0xF0 0x03C0 # GREEK SMALL LETTER PI
|
||||
0xF1 0x03C1 # GREEK SMALL LETTER RHO
|
||||
0xF2 0x03C2 # GREEK SMALL LETTER FINAL SIGMA
|
||||
0xF3 0x03C3 # GREEK SMALL LETTER SIGMA
|
||||
0xF4 0x03C4 # GREEK SMALL LETTER TAU
|
||||
0xF5 0x03C5 # GREEK SMALL LETTER UPSILON
|
||||
0xF6 0x03C6 # GREEK SMALL LETTER PHI
|
||||
0xF7 0x03C7 # GREEK SMALL LETTER CHI
|
||||
0xF8 0x03C8 # GREEK SMALL LETTER PSI
|
||||
0xF9 0x03C9 # GREEK SMALL LETTER OMEGA
|
||||
0xFA 0x03CA # GREEK SMALL LETTER IOTA WITH DIALYTIKA
|
||||
0xFB 0x03CB # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
|
||||
0xFC 0x03CC # GREEK SMALL LETTER OMICRON WITH TONOS
|
||||
0xFD 0x03CD # GREEK SMALL LETTER UPSILON WITH TONOS
|
||||
0xFE 0x03CE # GREEK SMALL LETTER OMEGA WITH TONOS
|
||||
@@ -0,0 +1,269 @@
|
||||
#
|
||||
# Name: ISO/IEC 8859-8:1999 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.1
|
||||
# Table format: Format A
|
||||
# Date: 2000-Jan-03
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-8:1999 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-8 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-8 order.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version updates 0.1 version by adding mappings for all
|
||||
# control characters.
|
||||
# 1.1 version updates to the published 8859-8:1999, correcting
|
||||
# the mapping of 0xAF and adding mappings for LRM and RLM.
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA2 0x00A2 # CENT SIGN
|
||||
0xA3 0x00A3 # POUND SIGN
|
||||
0xA4 0x00A4 # CURRENCY SIGN
|
||||
0xA5 0x00A5 # YEN SIGN
|
||||
0xA6 0x00A6 # BROKEN BAR
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x00A8 # DIAERESIS
|
||||
0xA9 0x00A9 # COPYRIGHT SIGN
|
||||
0xAA 0x00D7 # MULTIPLICATION SIGN
|
||||
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC # NOT SIGN
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAE 0x00AE # REGISTERED SIGN
|
||||
0xAF 0x00AF # MACRON
|
||||
0xB0 0x00B0 # DEGREE SIGN
|
||||
0xB1 0x00B1 # PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 # SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 # SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 # ACUTE ACCENT
|
||||
0xB5 0x00B5 # MICRO SIGN
|
||||
0xB6 0x00B6 # PILCROW SIGN
|
||||
0xB7 0x00B7 # MIDDLE DOT
|
||||
0xB8 0x00B8 # CEDILLA
|
||||
0xB9 0x00B9 # SUPERSCRIPT ONE
|
||||
0xBA 0x00F7 # DIVISION SIGN
|
||||
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC # VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD # VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS
|
||||
0xDF 0x2017 # DOUBLE LOW LINE
|
||||
0xE0 0x05D0 # HEBREW LETTER ALEF
|
||||
0xE1 0x05D1 # HEBREW LETTER BET
|
||||
0xE2 0x05D2 # HEBREW LETTER GIMEL
|
||||
0xE3 0x05D3 # HEBREW LETTER DALET
|
||||
0xE4 0x05D4 # HEBREW LETTER HE
|
||||
0xE5 0x05D5 # HEBREW LETTER VAV
|
||||
0xE6 0x05D6 # HEBREW LETTER ZAYIN
|
||||
0xE7 0x05D7 # HEBREW LETTER HET
|
||||
0xE8 0x05D8 # HEBREW LETTER TET
|
||||
0xE9 0x05D9 # HEBREW LETTER YOD
|
||||
0xEA 0x05DA # HEBREW LETTER FINAL KAF
|
||||
0xEB 0x05DB # HEBREW LETTER KAF
|
||||
0xEC 0x05DC # HEBREW LETTER LAMED
|
||||
0xED 0x05DD # HEBREW LETTER FINAL MEM
|
||||
0xEE 0x05DE # HEBREW LETTER MEM
|
||||
0xEF 0x05DF # HEBREW LETTER FINAL NUN
|
||||
0xF0 0x05E0 # HEBREW LETTER NUN
|
||||
0xF1 0x05E1 # HEBREW LETTER SAMEKH
|
||||
0xF2 0x05E2 # HEBREW LETTER AYIN
|
||||
0xF3 0x05E3 # HEBREW LETTER FINAL PE
|
||||
0xF4 0x05E4 # HEBREW LETTER PE
|
||||
0xF5 0x05E5 # HEBREW LETTER FINAL TSADI
|
||||
0xF6 0x05E6 # HEBREW LETTER TSADI
|
||||
0xF7 0x05E7 # HEBREW LETTER QOF
|
||||
0xF8 0x05E8 # HEBREW LETTER RESH
|
||||
0xF9 0x05E9 # HEBREW LETTER SHIN
|
||||
0xFA 0x05EA # HEBREW LETTER TAV
|
||||
0xFD 0x200E # LEFT-TO-RIGHT MARK
|
||||
0xFE 0x200F # RIGHT-TO-LEFT MARK
|
||||
@@ -0,0 +1,305 @@
|
||||
#
|
||||
# Name: ISO/IEC 8859-9:1999 to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 1999 July 27
|
||||
# Authors: Ken Whistler <kenw@sybase.com>
|
||||
#
|
||||
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on magnetic media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# ISO/IEC 8859-9:1999 characters map into Unicode.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the ISO/IEC 8859-9 code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in ISO/IEC 8859-9 order.
|
||||
#
|
||||
# ISO/IEC 8859-9 is also equivalent to ISO-IR-148.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version updates 0.1 version by adding mappings for all
|
||||
# control characters.
|
||||
#
|
||||
# Updated versions of this file may be found in:
|
||||
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x0080 # <control>
|
||||
0x81 0x0081 # <control>
|
||||
0x82 0x0082 # <control>
|
||||
0x83 0x0083 # <control>
|
||||
0x84 0x0084 # <control>
|
||||
0x85 0x0085 # <control>
|
||||
0x86 0x0086 # <control>
|
||||
0x87 0x0087 # <control>
|
||||
0x88 0x0088 # <control>
|
||||
0x89 0x0089 # <control>
|
||||
0x8A 0x008A # <control>
|
||||
0x8B 0x008B # <control>
|
||||
0x8C 0x008C # <control>
|
||||
0x8D 0x008D # <control>
|
||||
0x8E 0x008E # <control>
|
||||
0x8F 0x008F # <control>
|
||||
0x90 0x0090 # <control>
|
||||
0x91 0x0091 # <control>
|
||||
0x92 0x0092 # <control>
|
||||
0x93 0x0093 # <control>
|
||||
0x94 0x0094 # <control>
|
||||
0x95 0x0095 # <control>
|
||||
0x96 0x0096 # <control>
|
||||
0x97 0x0097 # <control>
|
||||
0x98 0x0098 # <control>
|
||||
0x99 0x0099 # <control>
|
||||
0x9A 0x009A # <control>
|
||||
0x9B 0x009B # <control>
|
||||
0x9C 0x009C # <control>
|
||||
0x9D 0x009D # <control>
|
||||
0x9E 0x009E # <control>
|
||||
0x9F 0x009F # <control>
|
||||
0xA0 0x00A0 # NO-BREAK SPACE
|
||||
0xA1 0x00A1 # INVERTED EXCLAMATION MARK
|
||||
0xA2 0x00A2 # CENT SIGN
|
||||
0xA3 0x00A3 # POUND SIGN
|
||||
0xA4 0x00A4 # CURRENCY SIGN
|
||||
0xA5 0x00A5 # YEN SIGN
|
||||
0xA6 0x00A6 # BROKEN BAR
|
||||
0xA7 0x00A7 # SECTION SIGN
|
||||
0xA8 0x00A8 # DIAERESIS
|
||||
0xA9 0x00A9 # COPYRIGHT SIGN
|
||||
0xAA 0x00AA # FEMININE ORDINAL INDICATOR
|
||||
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC # NOT SIGN
|
||||
0xAD 0x00AD # SOFT HYPHEN
|
||||
0xAE 0x00AE # REGISTERED SIGN
|
||||
0xAF 0x00AF # MACRON
|
||||
0xB0 0x00B0 # DEGREE SIGN
|
||||
0xB1 0x00B1 # PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 # SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 # SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 # ACUTE ACCENT
|
||||
0xB5 0x00B5 # MICRO SIGN
|
||||
0xB6 0x00B6 # PILCROW SIGN
|
||||
0xB7 0x00B7 # MIDDLE DOT
|
||||
0xB8 0x00B8 # CEDILLA
|
||||
0xB9 0x00B9 # SUPERSCRIPT ONE
|
||||
0xBA 0x00BA # MASCULINE ORDINAL INDICATOR
|
||||
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC # VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD # VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00BF # INVERTED QUESTION MARK
|
||||
0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x00C6 # LATIN CAPITAL LETTER AE
|
||||
0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD0 0x011E # LATIN CAPITAL LETTER G WITH BREVE
|
||||
0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 # MULTIPLICATION SIGN
|
||||
0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
0xDE 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
0xDF 0x00DF # LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE
|
||||
0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x00E6 # LATIN SMALL LETTER AE
|
||||
0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE
|
||||
0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x011F # LATIN SMALL LETTER G WITH BREVE
|
||||
0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE
|
||||
0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
|
||||
0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 # DIVISION SIGN
|
||||
0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
|
||||
0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x0131 # LATIN SMALL LETTER DOTLESS I
|
||||
0xFE 0x015F # LATIN SMALL LETTER S WITH CEDILLA
|
||||
0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
@@ -0,0 +1,302 @@
|
||||
#
|
||||
# Name: KOI8-R (RFC1489) to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 18 August 1999
|
||||
# Authors: Helmut Richter <richter@lrz.de>
|
||||
#
|
||||
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
|
||||
#
|
||||
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
|
||||
# No claims are made as to fitness for any particular purpose. No
|
||||
# warranties of any kind are expressed or implied. The recipient
|
||||
# agrees to determine applicability of information provided. If this
|
||||
# file has been provided on optical media by Unicode, Inc., the sole
|
||||
# remedy for any claim will be exchange of defective media within 90
|
||||
# days of receipt.
|
||||
#
|
||||
# Unicode, Inc. hereby grants the right to freely use the information
|
||||
# supplied in this file in the creation of products supporting the
|
||||
# Unicode Standard, and to make copies of this file in any form for
|
||||
# internal or external distribution as long as this notice remains
|
||||
# attached.
|
||||
#
|
||||
# General notes:
|
||||
#
|
||||
# This table contains the data the Unicode Consortium has on how
|
||||
# KOI8-R characters map into Unicode. The underlying document is the
|
||||
# mapping described in RFC 1489. No statements are made as to whether
|
||||
# this mapping is the same as the mapping defined as "Code Page 878"
|
||||
# with some vendors.
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the KOI8-R code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in KOI8-R order.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version: created.
|
||||
#
|
||||
# Any comments or problems, contact <errata@unicode.org>
|
||||
# Please note that <errata@unicode.org> is an archival address;
|
||||
# notices will be checked, but do not expect an immediate response.
|
||||
#
|
||||
0x00 0x0000 # NULL
|
||||
0x01 0x0001 # START OF HEADING
|
||||
0x02 0x0002 # START OF TEXT
|
||||
0x03 0x0003 # END OF TEXT
|
||||
0x04 0x0004 # END OF TRANSMISSION
|
||||
0x05 0x0005 # ENQUIRY
|
||||
0x06 0x0006 # ACKNOWLEDGE
|
||||
0x07 0x0007 # BELL
|
||||
0x08 0x0008 # BACKSPACE
|
||||
0x09 0x0009 # HORIZONTAL TABULATION
|
||||
0x0A 0x000A # LINE FEED
|
||||
0x0B 0x000B # VERTICAL TABULATION
|
||||
0x0C 0x000C # FORM FEED
|
||||
0x0D 0x000D # CARRIAGE RETURN
|
||||
0x0E 0x000E # SHIFT OUT
|
||||
0x0F 0x000F # SHIFT IN
|
||||
0x10 0x0010 # DATA LINK ESCAPE
|
||||
0x11 0x0011 # DEVICE CONTROL ONE
|
||||
0x12 0x0012 # DEVICE CONTROL TWO
|
||||
0x13 0x0013 # DEVICE CONTROL THREE
|
||||
0x14 0x0014 # DEVICE CONTROL FOUR
|
||||
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 # SYNCHRONOUS IDLE
|
||||
0x17 0x0017 # END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 # CANCEL
|
||||
0x19 0x0019 # END OF MEDIUM
|
||||
0x1A 0x001A # SUBSTITUTE
|
||||
0x1B 0x001B # ESCAPE
|
||||
0x1C 0x001C # FILE SEPARATOR
|
||||
0x1D 0x001D # GROUP SEPARATOR
|
||||
0x1E 0x001E # RECORD SEPARATOR
|
||||
0x1F 0x001F # UNIT SEPARATOR
|
||||
0x20 0x0020 # SPACE
|
||||
0x21 0x0021 # EXCLAMATION MARK
|
||||
0x22 0x0022 # QUOTATION MARK
|
||||
0x23 0x0023 # NUMBER SIGN
|
||||
0x24 0x0024 # DOLLAR SIGN
|
||||
0x25 0x0025 # PERCENT SIGN
|
||||
0x26 0x0026 # AMPERSAND
|
||||
0x27 0x0027 # APOSTROPHE
|
||||
0x28 0x0028 # LEFT PARENTHESIS
|
||||
0x29 0x0029 # RIGHT PARENTHESIS
|
||||
0x2A 0x002A # ASTERISK
|
||||
0x2B 0x002B # PLUS SIGN
|
||||
0x2C 0x002C # COMMA
|
||||
0x2D 0x002D # HYPHEN-MINUS
|
||||
0x2E 0x002E # FULL STOP
|
||||
0x2F 0x002F # SOLIDUS
|
||||
0x30 0x0030 # DIGIT ZERO
|
||||
0x31 0x0031 # DIGIT ONE
|
||||
0x32 0x0032 # DIGIT TWO
|
||||
0x33 0x0033 # DIGIT THREE
|
||||
0x34 0x0034 # DIGIT FOUR
|
||||
0x35 0x0035 # DIGIT FIVE
|
||||
0x36 0x0036 # DIGIT SIX
|
||||
0x37 0x0037 # DIGIT SEVEN
|
||||
0x38 0x0038 # DIGIT EIGHT
|
||||
0x39 0x0039 # DIGIT NINE
|
||||
0x3A 0x003A # COLON
|
||||
0x3B 0x003B # SEMICOLON
|
||||
0x3C 0x003C # LESS-THAN SIGN
|
||||
0x3D 0x003D # EQUALS SIGN
|
||||
0x3E 0x003E # GREATER-THAN SIGN
|
||||
0x3F 0x003F # QUESTION MARK
|
||||
0x40 0x0040 # COMMERCIAL AT
|
||||
0x41 0x0041 # LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 # LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 # LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 # LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 # LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 # LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 # LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 # LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 # LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A # LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B # LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C # LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D # LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E # LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F # LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 # LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 # LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 # LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 # LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 # LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 # LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 # LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 # LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 # LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 # LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A # LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B # LEFT SQUARE BRACKET
|
||||
0x5C 0x005C # REVERSE SOLIDUS
|
||||
0x5D 0x005D # RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E # CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F # LOW LINE
|
||||
0x60 0x0060 # GRAVE ACCENT
|
||||
0x61 0x0061 # LATIN SMALL LETTER A
|
||||
0x62 0x0062 # LATIN SMALL LETTER B
|
||||
0x63 0x0063 # LATIN SMALL LETTER C
|
||||
0x64 0x0064 # LATIN SMALL LETTER D
|
||||
0x65 0x0065 # LATIN SMALL LETTER E
|
||||
0x66 0x0066 # LATIN SMALL LETTER F
|
||||
0x67 0x0067 # LATIN SMALL LETTER G
|
||||
0x68 0x0068 # LATIN SMALL LETTER H
|
||||
0x69 0x0069 # LATIN SMALL LETTER I
|
||||
0x6A 0x006A # LATIN SMALL LETTER J
|
||||
0x6B 0x006B # LATIN SMALL LETTER K
|
||||
0x6C 0x006C # LATIN SMALL LETTER L
|
||||
0x6D 0x006D # LATIN SMALL LETTER M
|
||||
0x6E 0x006E # LATIN SMALL LETTER N
|
||||
0x6F 0x006F # LATIN SMALL LETTER O
|
||||
0x70 0x0070 # LATIN SMALL LETTER P
|
||||
0x71 0x0071 # LATIN SMALL LETTER Q
|
||||
0x72 0x0072 # LATIN SMALL LETTER R
|
||||
0x73 0x0073 # LATIN SMALL LETTER S
|
||||
0x74 0x0074 # LATIN SMALL LETTER T
|
||||
0x75 0x0075 # LATIN SMALL LETTER U
|
||||
0x76 0x0076 # LATIN SMALL LETTER V
|
||||
0x77 0x0077 # LATIN SMALL LETTER W
|
||||
0x78 0x0078 # LATIN SMALL LETTER X
|
||||
0x79 0x0079 # LATIN SMALL LETTER Y
|
||||
0x7A 0x007A # LATIN SMALL LETTER Z
|
||||
0x7B 0x007B # LEFT CURLY BRACKET
|
||||
0x7C 0x007C # VERTICAL LINE
|
||||
0x7D 0x007D # RIGHT CURLY BRACKET
|
||||
0x7E 0x007E # TILDE
|
||||
0x7F 0x007F # DELETE
|
||||
0x80 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x8B 0x2580 # UPPER HALF BLOCK
|
||||
0x8C 0x2584 # LOWER HALF BLOCK
|
||||
0x8D 0x2588 # FULL BLOCK
|
||||
0x8E 0x258C # LEFT HALF BLOCK
|
||||
0x8F 0x2590 # RIGHT HALF BLOCK
|
||||
0x90 0x2591 # LIGHT SHADE
|
||||
0x91 0x2592 # MEDIUM SHADE
|
||||
0x92 0x2593 # DARK SHADE
|
||||
0x93 0x2320 # TOP HALF INTEGRAL
|
||||
0x94 0x25A0 # BLACK SQUARE
|
||||
0x95 0x2219 # BULLET OPERATOR
|
||||
0x96 0x221A # SQUARE ROOT
|
||||
0x97 0x2248 # ALMOST EQUAL TO
|
||||
0x98 0x2264 # LESS-THAN OR EQUAL TO
|
||||
0x99 0x2265 # GREATER-THAN OR EQUAL TO
|
||||
0x9A 0x00A0 # NO-BREAK SPACE
|
||||
0x9B 0x2321 # BOTTOM HALF INTEGRAL
|
||||
0x9C 0x00B0 # DEGREE SIGN
|
||||
0x9D 0x00B2 # SUPERSCRIPT TWO
|
||||
0x9E 0x00B7 # MIDDLE DOT
|
||||
0x9F 0x00F7 # DIVISION SIGN
|
||||
0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0xA3 0x0451 # CYRILLIC SMALL LETTER IO
|
||||
0xA4 0x2553 # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0xA6 0x2555 # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0xA7 0x2556 # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0xAD 0x255C # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO
|
||||
0xB4 0x2562 # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0xB6 0x2564 # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0xB7 0x2565 # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0xBD 0x256B # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0xBF 0x00A9 # COPYRIGHT SIGN
|
||||
0xC0 0x044E # CYRILLIC SMALL LETTER YU
|
||||
0xC1 0x0430 # CYRILLIC SMALL LETTER A
|
||||
0xC2 0x0431 # CYRILLIC SMALL LETTER BE
|
||||
0xC3 0x0446 # CYRILLIC SMALL LETTER TSE
|
||||
0xC4 0x0434 # CYRILLIC SMALL LETTER DE
|
||||
0xC5 0x0435 # CYRILLIC SMALL LETTER IE
|
||||
0xC6 0x0444 # CYRILLIC SMALL LETTER EF
|
||||
0xC7 0x0433 # CYRILLIC SMALL LETTER GHE
|
||||
0xC8 0x0445 # CYRILLIC SMALL LETTER HA
|
||||
0xC9 0x0438 # CYRILLIC SMALL LETTER I
|
||||
0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I
|
||||
0xCB 0x043A # CYRILLIC SMALL LETTER KA
|
||||
0xCC 0x043B # CYRILLIC SMALL LETTER EL
|
||||
0xCD 0x043C # CYRILLIC SMALL LETTER EM
|
||||
0xCE 0x043D # CYRILLIC SMALL LETTER EN
|
||||
0xCF 0x043E # CYRILLIC SMALL LETTER O
|
||||
0xD0 0x043F # CYRILLIC SMALL LETTER PE
|
||||
0xD1 0x044F # CYRILLIC SMALL LETTER YA
|
||||
0xD2 0x0440 # CYRILLIC SMALL LETTER ER
|
||||
0xD3 0x0441 # CYRILLIC SMALL LETTER ES
|
||||
0xD4 0x0442 # CYRILLIC SMALL LETTER TE
|
||||
0xD5 0x0443 # CYRILLIC SMALL LETTER U
|
||||
0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE
|
||||
0xD7 0x0432 # CYRILLIC SMALL LETTER VE
|
||||
0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN
|
||||
0xD9 0x044B # CYRILLIC SMALL LETTER YERU
|
||||
0xDA 0x0437 # CYRILLIC SMALL LETTER ZE
|
||||
0xDB 0x0448 # CYRILLIC SMALL LETTER SHA
|
||||
0xDC 0x044D # CYRILLIC SMALL LETTER E
|
||||
0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA
|
||||
0xDE 0x0447 # CYRILLIC SMALL LETTER CHE
|
||||
0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN
|
||||
0xE0 0x042E # CYRILLIC CAPITAL LETTER YU
|
||||
0xE1 0x0410 # CYRILLIC CAPITAL LETTER A
|
||||
0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE
|
||||
0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE
|
||||
0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE
|
||||
0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE
|
||||
0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF
|
||||
0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE
|
||||
0xE8 0x0425 # CYRILLIC CAPITAL LETTER HA
|
||||
0xE9 0x0418 # CYRILLIC CAPITAL LETTER I
|
||||
0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I
|
||||
0xEB 0x041A # CYRILLIC CAPITAL LETTER KA
|
||||
0xEC 0x041B # CYRILLIC CAPITAL LETTER EL
|
||||
0xED 0x041C # CYRILLIC CAPITAL LETTER EM
|
||||
0xEE 0x041D # CYRILLIC CAPITAL LETTER EN
|
||||
0xEF 0x041E # CYRILLIC CAPITAL LETTER O
|
||||
0xF0 0x041F # CYRILLIC CAPITAL LETTER PE
|
||||
0xF1 0x042F # CYRILLIC CAPITAL LETTER YA
|
||||
0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER
|
||||
0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES
|
||||
0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE
|
||||
0xF5 0x0423 # CYRILLIC CAPITAL LETTER U
|
||||
0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE
|
||||
0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE
|
||||
0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU
|
||||
0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE
|
||||
0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA
|
||||
0xFC 0x042D # CYRILLIC CAPITAL LETTER E
|
||||
0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA
|
||||
0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE
|
||||
0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
@@ -0,0 +1,277 @@
|
||||
#
|
||||
# Name: KOI8-U to Unicode
|
||||
# Unicode version: 3.0
|
||||
# Table version: 1.0
|
||||
# Table format: Format A
|
||||
# Date: 18 October 2003
|
||||
# Authors: Mikolaj Jedrzejak <mikolajj@op.pl>
|
||||
# (I'm not an author :-) I have just rote down few things from www.net.ua)
|
||||
#
|
||||
# Format: Three columns
|
||||
# Column #1 is the KOI8-U code (in hex as 0xXX)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in KOI8-U order.
|
||||
#
|
||||
# Version history
|
||||
# 1.0 version: created.
|
||||
#
|
||||
# Any comments or problems, contact at www.net.ua
|
||||
#
|
||||
0x00 0x0000 #NULL (NUL)
|
||||
0x01 0x0001 #START OF HEADING (SOH)
|
||||
0x02 0x0002 #START OF TEXT (STX)
|
||||
0x03 0x0003 #END OF TEXT (ETX)
|
||||
0x04 0x0004 #END OF TRANSMISSION (EOT)
|
||||
0x05 0x0005 #ENQUIRY (ENQ)
|
||||
0x06 0x0006 #ACKNOWLEDGE (ACK)
|
||||
0x07 0x0007 #BELL (BEL)
|
||||
0x08 0x0008 #BACKSPACE (BS)
|
||||
0x09 0x0009 #CHARACTER TABULATION (HT)
|
||||
0x0A 0x000A #LINE FEED (LF)
|
||||
0x0B 0x000B #LINE TABULATION (VT)
|
||||
0x0C 0x000C #FORM FEED (FF)
|
||||
0x0D 0x000D #CARRIAGE RETURN (CR)
|
||||
0x0E 0x000E #SHIFT OUT (SO)
|
||||
0x0F 0x000F #SHIFT IN (SI)
|
||||
0x10 0x0010 #DATALINK ESCAPE (DLE)
|
||||
0x11 0x0011 #DEVICE CONTROL ONE (DC1)
|
||||
0x12 0x0012 #DEVICE CONTROL TWO (DC2)
|
||||
0x13 0x0013 #DEVICE CONTROL THREE (DC3)
|
||||
0x14 0x0014 #DEVICE CONTROL FOUR (DC4)
|
||||
0x15 0x0015 #NEGATIVE ACKNOWLEDGE (NAK)
|
||||
0x16 0x0016 #SYNCHRONOUS IDLE (SYN)
|
||||
0x17 0x0017 #END OF TRANSMISSION BLOCK (ETB)
|
||||
0x18 0x0018 #CANCEL (CAN)
|
||||
0x19 0x0019 #END OF MEDIUM (EM)
|
||||
0x1A 0x001A #SUBSTITUTE (SUB)
|
||||
0x1B 0x001B #ESCAPE (ESC)
|
||||
0x1C 0x001C #FILE SEPARATOR (IS4)
|
||||
0x1D 0x001D #GROUP SEPARATOR (IS3)
|
||||
0x1E 0x001E #RECORD SEPARATOR (IS2)
|
||||
0x1F 0x001F #UNIT SEPARATOR (IS1)
|
||||
0x20 0x0020 #SPACE
|
||||
0x21 0x0021 #EXCLAMATION MARK
|
||||
0x22 0x0022 #QUOTATION MARK
|
||||
0x23 0x0023 #NUMBER SIGN
|
||||
0x24 0x0024 #DOLLAR SIGN
|
||||
0x25 0x0025 #PERCENT SIGN
|
||||
0x26 0x0026 #AMPERSAND
|
||||
0x27 0x0027 #APOSTROPHE
|
||||
0x28 0x0028 #LEFT PARENTHESIS
|
||||
0x29 0x0029 #RIGHT PARENTHESIS
|
||||
0x2A 0x002A #ASTERISK
|
||||
0x2B 0x002B #PLUS SIGN
|
||||
0x2C 0x002C #COMMA
|
||||
0x2D 0x002D #HYPHEN-MINUS
|
||||
0x2E 0x002E #FULL STOP
|
||||
0x2F 0x002F #SOLIDUS
|
||||
0x30 0x0030 #DIGIT ZERO
|
||||
0x31 0x0031 #DIGIT ONE
|
||||
0x32 0x0032 #DIGIT TWO
|
||||
0x33 0x0033 #DIGIT THREE
|
||||
0x34 0x0034 #DIGIT FOUR
|
||||
0x35 0x0035 #DIGIT FIVE
|
||||
0x36 0x0036 #DIGIT SIX
|
||||
0x37 0x0037 #DIGIT SEVEN
|
||||
0x38 0x0038 #DIGIT EIGHT
|
||||
0x39 0x0039 #DIGIT NINE
|
||||
0x3A 0x003A #COLON
|
||||
0x3B 0x003B #SEMICOLON
|
||||
0x3C 0x003C #LESS-THAN SIGN
|
||||
0x3D 0x003D #EQUALS SIGN
|
||||
0x3E 0x003E #GREATER-THAN SIGN
|
||||
0x3F 0x003F #QUESTION MARK
|
||||
0x40 0x0040 #COMMERCIAL AT
|
||||
0x41 0x0041 #LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 #LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 #LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 #LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 #LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 #LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 #LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 #LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 #LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A #LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B #LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C #LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D #LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E #LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F #LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 #LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 #LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 #LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 #LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 #LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 #LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 #LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 #LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A #LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B #LEFT SQUARE BRACKET
|
||||
0x5C 0x005C #REVERSE SOLIDUS
|
||||
0x5D 0x005D #RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E #CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F #LOW LINE
|
||||
0x60 0x0060 #GRAVE ACCENT
|
||||
0x61 0x0061 #LATIN SMALL LETTER A
|
||||
0x62 0x0062 #LATIN SMALL LETTER B
|
||||
0x63 0x0063 #LATIN SMALL LETTER C
|
||||
0x64 0x0064 #LATIN SMALL LETTER D
|
||||
0x65 0x0065 #LATIN SMALL LETTER E
|
||||
0x66 0x0066 #LATIN SMALL LETTER F
|
||||
0x67 0x0067 #LATIN SMALL LETTER G
|
||||
0x68 0x0068 #LATIN SMALL LETTER H
|
||||
0x69 0x0069 #LATIN SMALL LETTER I
|
||||
0x6A 0x006A #LATIN SMALL LETTER J
|
||||
0x6B 0x006B #LATIN SMALL LETTER K
|
||||
0x6C 0x006C #LATIN SMALL LETTER L
|
||||
0x6D 0x006D #LATIN SMALL LETTER M
|
||||
0x6E 0x006E #LATIN SMALL LETTER N
|
||||
0x6F 0x006F #LATIN SMALL LETTER O
|
||||
0x70 0x0070 #LATIN SMALL LETTER P
|
||||
0x71 0x0071 #LATIN SMALL LETTER Q
|
||||
0x72 0x0072 #LATIN SMALL LETTER R
|
||||
0x73 0x0073 #LATIN SMALL LETTER S
|
||||
0x74 0x0074 #LATIN SMALL LETTER T
|
||||
0x75 0x0075 #LATIN SMALL LETTER U
|
||||
0x76 0x0076 #LATIN SMALL LETTER V
|
||||
0x77 0x0077 #LATIN SMALL LETTER W
|
||||
0x78 0x0078 #LATIN SMALL LETTER X
|
||||
0x79 0x0079 #LATIN SMALL LETTER Y
|
||||
0x7A 0x007A #LATIN SMALL LETTER Z
|
||||
0x7B 0x007B #LEFT CURLY BRACKET
|
||||
0x7C 0x007C #VERTICAL LINE
|
||||
0x7D 0x007D #RIGHT CURLY BRACKET
|
||||
0x7E 0x007E #TILDE
|
||||
0x7F 0x007F #DELETE (DEL)
|
||||
0x80 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x81 0x2502 #BOX DRAWINGS LIGHT VERTICAL
|
||||
0x82 0x250C #BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x83 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x84 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x85 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x86 0x251C #BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x87 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x88 0x252C #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x89 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x8A 0x253C #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x8B 0x2580 #UPPER HALF BLOCK
|
||||
0x8C 0x2584 #LOWER HALF BLOCK
|
||||
0x8D 0x2588 #FULL BLOCK
|
||||
0x8E 0x258C #LEFT HALF BLOCK
|
||||
0x8F 0x2590 #RIGHT HALF BLOCK
|
||||
0x90 0x2591 #LIGHT SHADE
|
||||
0x91 0x2592 #MEDIUM SHADE
|
||||
0x92 0x2593 #DARK SHADE
|
||||
0x93 0x2320 #TOP HALF INTEGRAL
|
||||
0x94 0x25A0 #BLACK SQUARE
|
||||
0x95 0x2022 #BULLET
|
||||
0x96 0x221A #SQUARE ROOT
|
||||
0x97 0x2248 #ALMOST EQUAL TO
|
||||
0x98 0x2264 #LESS-THAN OR EQUAL TO
|
||||
0x99 0x2265 #GREATER-THAN OR EQUAL TO
|
||||
0x9A 0x00A0 #NO-BREAK SPACE
|
||||
0x9B 0x2321 #BOTTOM HALF INTEGRAL
|
||||
0x9C 0x00B0 #DEGREE SIGN
|
||||
0x9D 0x00B2 #SUPERSCRIPT TWO
|
||||
0x9E 0x00B7 #MIDDLE DOT
|
||||
0x9F 0x00F7 #DIVISION SIGN
|
||||
0xA0 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0xA1 0x2551 #BOX DRAWINGS DOUBLE VERTICAL
|
||||
0xA2 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0xA3 0x0451 #CYRILLIC SMALL LETTER IO
|
||||
0xA4 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
0xA5 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0xA6 0x0456 #CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0xA7 0x0457 #CYRILLIC SMALL LETTER YI (Ukrainian)
|
||||
0xA8 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0xA9 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0xAA 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0xAB 0x255A #BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0xAC 0x255B #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0xAD 0x0491 #CYRILLIC SMALL LETTER GHE WITH UPTURN
|
||||
0xAE 0x255D #BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0xAF 0x255E #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0xB0 0x255F #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0xB1 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0xB2 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0xB3 0x0401 #CYRILLIC CAPITAL LETTER IO
|
||||
0xB4 0x0403 #CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
0xB5 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0xB6 0x0406 #CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0xB7 0x0407 #CYRILLIC CAPITAL LETTER YI (Ukrainian)
|
||||
0xB8 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0xB9 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0xBA 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0xBB 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0xBC 0x256A #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0xBD 0x0490 #CYRILLIC CAPITAL LETTER GHE WITH UPTURN
|
||||
0xBE 0x256C #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0xBF 0x00A9 #COPYRIGHT SIGN
|
||||
0xC0 0x044E #CYRILLIC SMALL LETTER YU
|
||||
0xC1 0x0430 #CYRILLIC SMALL LETTER A
|
||||
0xC2 0x0431 #CYRILLIC SMALL LETTER BE
|
||||
0xC3 0x0446 #CYRILLIC SMALL LETTER TSE
|
||||
0xC4 0x0434 #CYRILLIC SMALL LETTER DE
|
||||
0xC5 0x0435 #CYRILLIC SMALL LETTER IE
|
||||
0xC6 0x0444 #CYRILLIC SMALL LETTER EF
|
||||
0xC7 0x0433 #CYRILLIC SMALL LETTER GHE
|
||||
0xC8 0x0445 #CYRILLIC SMALL LETTER HA
|
||||
0xC9 0x0438 #CYRILLIC SMALL LETTER I
|
||||
0xCA 0x0439 #CYRILLIC SMALL LETTER SHORT I
|
||||
0xCB 0x043A #CYRILLIC SMALL LETTER KA
|
||||
0xCC 0x043B #CYRILLIC SMALL LETTER EL
|
||||
0xCD 0x043C #CYRILLIC SMALL LETTER EM
|
||||
0xCE 0x043D #CYRILLIC SMALL LETTER EN
|
||||
0xCF 0x043E #CYRILLIC SMALL LETTER O
|
||||
0xD0 0x043F #CYRILLIC SMALL LETTER PE
|
||||
0xD1 0x044F #CYRILLIC SMALL LETTER YA
|
||||
0xD2 0x0440 #CYRILLIC SMALL LETTER ER
|
||||
0xD3 0x0441 #CYRILLIC SMALL LETTER ES
|
||||
0xD4 0x0442 #CYRILLIC SMALL LETTER TE
|
||||
0xD5 0x0443 #CYRILLIC SMALL LETTER U
|
||||
0xD6 0x0436 #CYRILLIC SMALL LETTER ZHE
|
||||
0xD7 0x0432 #CYRILLIC SMALL LETTER VE
|
||||
0xD8 0x044C #CYRILLIC SMALL LETTER SOFT SIGN
|
||||
0xD9 0x044B #CYRILLIC SMALL LETTER YERU
|
||||
0xDA 0x0437 #CYRILLIC SMALL LETTER ZE
|
||||
0xDB 0x0448 #CYRILLIC SMALL LETTER SHA
|
||||
0xDC 0x044D #CYRILLIC SMALL LETTER E
|
||||
0xDD 0x0449 #CYRILLIC SMALL LETTER SHCHA
|
||||
0xDE 0x0447 #CYRILLIC SMALL LETTER CHE
|
||||
0xDF 0x044A #CYRILLIC SMALL LETTER HARD SIGN
|
||||
0xE0 0x042E #CYRILLIC CAPITAL LETTER YU
|
||||
0xE1 0x0410 #CYRILLIC CAPITAL LETTER A
|
||||
0xE2 0x0411 #CYRILLIC CAPITAL LETTER BE
|
||||
0xE3 0x0426 #CYRILLIC CAPITAL LETTER TSE
|
||||
0xE4 0x0414 #CYRILLIC CAPITAL LETTER DE
|
||||
0xE5 0x0415 #CYRILLIC CAPITAL LETTER IE
|
||||
0xE6 0x0424 #CYRILLIC CAPITAL LETTER EF
|
||||
0xE7 0x0413 #CYRILLIC CAPITAL LETTER GHE
|
||||
0xE8 0x0425 #CYRILLIC CAPITAL LETTER HA
|
||||
0xE9 0x0418 #CYRILLIC CAPITAL LETTER I
|
||||
0xEA 0x0419 #CYRILLIC CAPITAL LETTER SHORT I
|
||||
0xEB 0x041A #CYRILLIC CAPITAL LETTER KA
|
||||
0xEC 0x041B #CYRILLIC CAPITAL LETTER EL
|
||||
0xED 0x041C #CYRILLIC CAPITAL LETTER EM
|
||||
0xEE 0x041D #CYRILLIC CAPITAL LETTER EN
|
||||
0xEF 0x041E #CYRILLIC CAPITAL LETTER O
|
||||
0xF0 0x041F #CYRILLIC CAPITAL LETTER PE
|
||||
0xF1 0x042F #CYRILLIC CAPITAL LETTER YA
|
||||
0xF2 0x0420 #CYRILLIC CAPITAL LETTER ER
|
||||
0xF3 0x0421 #CYRILLIC CAPITAL LETTER ES
|
||||
0xF4 0x0422 #CYRILLIC CAPITAL LETTER TE
|
||||
0xF5 0x0423 #CYRILLIC CAPITAL LETTER U
|
||||
0xF6 0x0416 #CYRILLIC CAPITAL LETTER ZHE
|
||||
0xF7 0x0412 #CYRILLIC CAPITAL LETTER VE
|
||||
0xF8 0x042C #CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
0xF9 0x042B #CYRILLIC CAPITAL LETTER YERU
|
||||
0xFA 0x0417 #CYRILLIC CAPITAL LETTER ZE
|
||||
0xFB 0x0428 #CYRILLIC CAPITAL LETTER SHA
|
||||
0xFC 0x042D #CYRILLIC CAPITAL LETTER E
|
||||
0xFD 0x0429 #CYRILLIC CAPITAL LETTER SHCHA
|
||||
0xFE 0x0427 #CYRILLIC CAPITAL LETTER CHE
|
||||
0xFF 0x042A #CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
@@ -0,0 +1,273 @@
|
||||
#
|
||||
# Name: cp10081_MacTurkish to Unicode table
|
||||
# Unicode version: 2.0
|
||||
# Table version: 2.00
|
||||
# Table format: Format A
|
||||
# Date: 04/24/96
|
||||
# Authors: Lori Brownell <loribr@microsoft.com>
|
||||
# K.D. Chang <a-kchang@microsoft.com>
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp10081_MacTurkish code (in hex)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 is the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in cp10081_MacTurkish order
|
||||
#
|
||||
0x00 0x0000 #NULL
|
||||
0x01 0x0001 #START OF HEADING
|
||||
0x02 0x0002 #START OF TEXT
|
||||
0x03 0x0003 #END OF TEXT
|
||||
0x04 0x0004 #END OF TRANSMISSION
|
||||
0x05 0x0005 #ENQUIRY
|
||||
0x06 0x0006 #ACKNOWLEDGE
|
||||
0x07 0x0007 #BELL
|
||||
0x08 0x0008 #BACKSPACE
|
||||
0x09 0x0009 #HORIZONTAL TABULATION
|
||||
0x0A 0x000A #LINE FEED
|
||||
0x0B 0x000B #VERTICAL TABULATION
|
||||
0x0C 0x000C #FORM FEED
|
||||
0x0D 0x000D #CARRIAGE RETURN
|
||||
0x0E 0x000E #SHIFT OUT
|
||||
0x0F 0x000F #SHIFT IN
|
||||
0x10 0x0010 #DATA LINK ESCAPE
|
||||
0x11 0x0011 #DEVICE CONTROL ONE
|
||||
0x12 0x0012 #DEVICE CONTROL TWO
|
||||
0x13 0x0013 #DEVICE CONTROL THREE
|
||||
0x14 0x0014 #DEVICE CONTROL FOUR
|
||||
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 #SYNCHRONOUS IDLE
|
||||
0x17 0x0017 #END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 #CANCEL
|
||||
0x19 0x0019 #END OF MEDIUM
|
||||
0x1A 0x001A #SUBSTITUTE
|
||||
0x1B 0x001B #ESCAPE
|
||||
0x1C 0x001C #FILE SEPARATOR
|
||||
0x1D 0x001D #GROUP SEPARATOR
|
||||
0x1E 0x001E #RECORD SEPARATOR
|
||||
0x1F 0x001F #UNIT SEPARATOR
|
||||
0x20 0x0020 #SPACE
|
||||
0x21 0x0021 #EXCLAMATION MARK
|
||||
0x22 0x0022 #QUOTATION MARK
|
||||
0x23 0x0023 #NUMBER SIGN
|
||||
0x24 0x0024 #DOLLAR SIGN
|
||||
0x25 0x0025 #PERCENT SIGN
|
||||
0x26 0x0026 #AMPERSAND
|
||||
0x27 0x0027 #APOSTROPHE
|
||||
0x28 0x0028 #LEFT PARENTHESIS
|
||||
0x29 0x0029 #RIGHT PARENTHESIS
|
||||
0x2A 0x002A #ASTERISK
|
||||
0x2B 0x002B #PLUS SIGN
|
||||
0x2C 0x002C #COMMA
|
||||
0x2D 0x002D #HYPHEN-MINUS
|
||||
0x2E 0x002E #FULL STOP
|
||||
0x2F 0x002F #SOLIDUS
|
||||
0x30 0x0030 #DIGIT ZERO
|
||||
0x31 0x0031 #DIGIT ONE
|
||||
0x32 0x0032 #DIGIT TWO
|
||||
0x33 0x0033 #DIGIT THREE
|
||||
0x34 0x0034 #DIGIT FOUR
|
||||
0x35 0x0035 #DIGIT FIVE
|
||||
0x36 0x0036 #DIGIT SIX
|
||||
0x37 0x0037 #DIGIT SEVEN
|
||||
0x38 0x0038 #DIGIT EIGHT
|
||||
0x39 0x0039 #DIGIT NINE
|
||||
0x3A 0x003A #COLON
|
||||
0x3B 0x003B #SEMICOLON
|
||||
0x3C 0x003C #LESS-THAN SIGN
|
||||
0x3D 0x003D #EQUALS SIGN
|
||||
0x3E 0x003E #GREATER-THAN SIGN
|
||||
0x3F 0x003F #QUESTION MARK
|
||||
0x40 0x0040 #COMMERCIAL AT
|
||||
0x41 0x0041 #LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 #LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 #LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 #LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 #LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 #LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 #LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 #LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 #LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A #LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B #LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C #LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D #LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E #LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F #LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 #LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 #LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 #LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 #LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 #LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 #LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 #LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 #LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A #LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B #LEFT SQUARE BRACKET
|
||||
0x5C 0x005C #REVERSE SOLIDUS
|
||||
0x5D 0x005D #RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E #CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F #LOW LINE
|
||||
0x60 0x0060 #GRAVE ACCENT
|
||||
0x61 0x0061 #LATIN SMALL LETTER A
|
||||
0x62 0x0062 #LATIN SMALL LETTER B
|
||||
0x63 0x0063 #LATIN SMALL LETTER C
|
||||
0x64 0x0064 #LATIN SMALL LETTER D
|
||||
0x65 0x0065 #LATIN SMALL LETTER E
|
||||
0x66 0x0066 #LATIN SMALL LETTER F
|
||||
0x67 0x0067 #LATIN SMALL LETTER G
|
||||
0x68 0x0068 #LATIN SMALL LETTER H
|
||||
0x69 0x0069 #LATIN SMALL LETTER I
|
||||
0x6A 0x006A #LATIN SMALL LETTER J
|
||||
0x6B 0x006B #LATIN SMALL LETTER K
|
||||
0x6C 0x006C #LATIN SMALL LETTER L
|
||||
0x6D 0x006D #LATIN SMALL LETTER M
|
||||
0x6E 0x006E #LATIN SMALL LETTER N
|
||||
0x6F 0x006F #LATIN SMALL LETTER O
|
||||
0x70 0x0070 #LATIN SMALL LETTER P
|
||||
0x71 0x0071 #LATIN SMALL LETTER Q
|
||||
0x72 0x0072 #LATIN SMALL LETTER R
|
||||
0x73 0x0073 #LATIN SMALL LETTER S
|
||||
0x74 0x0074 #LATIN SMALL LETTER T
|
||||
0x75 0x0075 #LATIN SMALL LETTER U
|
||||
0x76 0x0076 #LATIN SMALL LETTER V
|
||||
0x77 0x0077 #LATIN SMALL LETTER W
|
||||
0x78 0x0078 #LATIN SMALL LETTER X
|
||||
0x79 0x0079 #LATIN SMALL LETTER Y
|
||||
0x7A 0x007A #LATIN SMALL LETTER Z
|
||||
0x7B 0x007B #LEFT CURLY BRACKET
|
||||
0x7C 0x007C #VERTICAL LINE
|
||||
0x7D 0x007D #RIGHT CURLY BRACKET
|
||||
0x7E 0x007E #TILDE
|
||||
0x7F 0x007F #DELETE
|
||||
0x80 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x81 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x82 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x83 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x84 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x85 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x86 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x87 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
|
||||
0x88 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
|
||||
0x89 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x8A 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x8B 0x00E3 #LATIN SMALL LETTER A WITH TILDE
|
||||
0x8C 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x8D 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x8E 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0x8F 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
|
||||
0x90 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x91 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x92 0x00ED #LATIN SMALL LETTER I WITH ACUTE
|
||||
0x93 0x00EC #LATIN SMALL LETTER I WITH GRAVE
|
||||
0x94 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x95 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x96 0x00F1 #LATIN SMALL LETTER N WITH TILDE
|
||||
0x97 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
|
||||
0x98 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
|
||||
0x99 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x9A 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x9B 0x00F5 #LATIN SMALL LETTER O WITH TILDE
|
||||
0x9C 0x00FA #LATIN SMALL LETTER U WITH ACUTE
|
||||
0x9D 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
|
||||
0x9E 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x9F 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xA0 0x2020 #DAGGER
|
||||
0xA1 0x00B0 #DEGREE SIGN
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
0xA3 0x00A3 #POUND SIGN
|
||||
0xA4 0x00A7 #SECTION SIGN
|
||||
0xA5 0x2022 #BULLET
|
||||
0xA6 0x00B6 #PILCROW SIGN
|
||||
0xA7 0x00DF #LATIN SMALL LETTER SHARP S
|
||||
0xA8 0x00AE #REGISTERED SIGN
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x2122 #TRADE MARK SIGN
|
||||
0xAB 0x00B4 #ACUTE ACCENT
|
||||
0xAC 0x00A8 #DIAERESIS
|
||||
0xAD 0x2260 #NOT EQUAL TO
|
||||
0xAE 0x00C6 #LATIN CAPITAL LIGATURE AE
|
||||
0xAF 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xB0 0x221E #INFINITY
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x2264 #LESS-THAN OR EQUAL TO
|
||||
0xB3 0x2265 #GREATER-THAN OR EQUAL TO
|
||||
0xB4 0x00A5 #YEN SIGN
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x2202 #PARTIAL DIFFERENTIAL
|
||||
0xB7 0x2211 #N-ARY SUMMATION
|
||||
0xB8 0x220F #N-ARY PRODUCT
|
||||
0xB9 0x03C0 #GREEK SMALL LETTER PI
|
||||
0xBA 0x222B #INTEGRAL
|
||||
0xBB 0x00AA #FEMININE ORDINAL INDICATOR
|
||||
0xBC 0x00BA #MASCULINE ORDINAL INDICATOR
|
||||
0xBD 0x2126 #OHM SIGN
|
||||
0xBE 0x00E6 #LATIN SMALL LIGATURE AE
|
||||
0xBF 0x00F8 #LATIN SMALL LETTER O WITH STROKE
|
||||
0xC0 0x00BF #INVERTED QUESTION MARK
|
||||
0xC1 0x00A1 #INVERTED EXCLAMATION MARK
|
||||
0xC2 0x00AC #NOT SIGN
|
||||
0xC3 0x221A #SQUARE ROOT
|
||||
0xC4 0x0192 #LATIN SMALL LETTER F WITH HOOK
|
||||
0xC5 0x2248 #ALMOST EQUAL TO
|
||||
0xC6 0x2206 #INCREMENT
|
||||
0xC7 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xC8 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xC9 0x2026 #HORIZONTAL ELLIPSIS
|
||||
0xCA 0x00A0 #NO-BREAK SPACE
|
||||
0xCB 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xCC 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
|
||||
0xCD 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xCE 0x0152 #LATIN CAPITAL LIGATURE OE
|
||||
0xCF 0x0153 #LATIN SMALL LIGATURE OE
|
||||
0xD0 0x2013 #EN DASH
|
||||
0xD1 0x2014 #EM DASH
|
||||
0xD2 0x201C #LEFT DOUBLE QUOTATION MARK
|
||||
0xD3 0x201D #RIGHT DOUBLE QUOTATION MARK
|
||||
0xD4 0x2018 #LEFT SINGLE QUOTATION MARK
|
||||
0xD5 0x2019 #RIGHT SINGLE QUOTATION MARK
|
||||
0xD6 0x00F7 #DIVISION SIGN
|
||||
0xD7 0x25CA #LOZENGE
|
||||
0xD8 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0xD9 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
0xDA 0x011E #LATIN CAPITAL LETTER G WITH BREVE
|
||||
0xDB 0x011F #LATIN SMALL LETTER G WITH BREVE
|
||||
0xDC 0x0130 #LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
0xDD 0x0131 #LATIN SMALL LETTER DOTLESS I
|
||||
0xDE 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
0xDF 0x015F #LATIN SMALL LETTER S WITH CEDILLA
|
||||
0xE0 0x2021 #DOUBLE DAGGER
|
||||
0xE1 0x00B7 #MIDDLE DOT
|
||||
0xE2 0x201A #SINGLE LOW-9 QUOTATION MARK
|
||||
0xE3 0x201E #DOUBLE LOW-9 QUOTATION MARK
|
||||
0xE4 0x2030 #PER MILLE SIGN
|
||||
0xE5 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xE6 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xE7 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xE8 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xE9 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xEA 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xEB 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xEC 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xED 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xEF 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xF0 #UNDEFINED
|
||||
0xF1 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xF2 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xF3 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xF4 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xF5 #UNDEFINED
|
||||
0xF6 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
0xF7 0x02DC #SMALL TILDE
|
||||
0xF8 0x00AF #MACRON
|
||||
0xF9 0x02D8 #BREVE
|
||||
0xFA 0x02D9 #DOT ABOVE
|
||||
0xFB 0x02DA #RING ABOVE
|
||||
0xFC 0x00B8 #CEDILLA
|
||||
0xFD 0x02DD #DOUBLE ACUTE ACCENT
|
||||
0xFE 0x02DB #OGONEK
|
||||
0xFF 0x02C7 #CARON
|
||||
@@ -0,0 +1,274 @@
|
||||
#
|
||||
# Name: cp1250 to Unicode table
|
||||
# Unicode version: 2.0
|
||||
# Table version: 2.01
|
||||
# Table format: Format A
|
||||
# Date: 04/15/98
|
||||
#
|
||||
# Contact: cpxlate@microsoft.com
|
||||
#
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp1250 code (in hex)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 is the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in cp1250 order
|
||||
#
|
||||
0x00 0x0000 #NULL
|
||||
0x01 0x0001 #START OF HEADING
|
||||
0x02 0x0002 #START OF TEXT
|
||||
0x03 0x0003 #END OF TEXT
|
||||
0x04 0x0004 #END OF TRANSMISSION
|
||||
0x05 0x0005 #ENQUIRY
|
||||
0x06 0x0006 #ACKNOWLEDGE
|
||||
0x07 0x0007 #BELL
|
||||
0x08 0x0008 #BACKSPACE
|
||||
0x09 0x0009 #HORIZONTAL TABULATION
|
||||
0x0A 0x000A #LINE FEED
|
||||
0x0B 0x000B #VERTICAL TABULATION
|
||||
0x0C 0x000C #FORM FEED
|
||||
0x0D 0x000D #CARRIAGE RETURN
|
||||
0x0E 0x000E #SHIFT OUT
|
||||
0x0F 0x000F #SHIFT IN
|
||||
0x10 0x0010 #DATA LINK ESCAPE
|
||||
0x11 0x0011 #DEVICE CONTROL ONE
|
||||
0x12 0x0012 #DEVICE CONTROL TWO
|
||||
0x13 0x0013 #DEVICE CONTROL THREE
|
||||
0x14 0x0014 #DEVICE CONTROL FOUR
|
||||
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 #SYNCHRONOUS IDLE
|
||||
0x17 0x0017 #END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 #CANCEL
|
||||
0x19 0x0019 #END OF MEDIUM
|
||||
0x1A 0x001A #SUBSTITUTE
|
||||
0x1B 0x001B #ESCAPE
|
||||
0x1C 0x001C #FILE SEPARATOR
|
||||
0x1D 0x001D #GROUP SEPARATOR
|
||||
0x1E 0x001E #RECORD SEPARATOR
|
||||
0x1F 0x001F #UNIT SEPARATOR
|
||||
0x20 0x0020 #SPACE
|
||||
0x21 0x0021 #EXCLAMATION MARK
|
||||
0x22 0x0022 #QUOTATION MARK
|
||||
0x23 0x0023 #NUMBER SIGN
|
||||
0x24 0x0024 #DOLLAR SIGN
|
||||
0x25 0x0025 #PERCENT SIGN
|
||||
0x26 0x0026 #AMPERSAND
|
||||
0x27 0x0027 #APOSTROPHE
|
||||
0x28 0x0028 #LEFT PARENTHESIS
|
||||
0x29 0x0029 #RIGHT PARENTHESIS
|
||||
0x2A 0x002A #ASTERISK
|
||||
0x2B 0x002B #PLUS SIGN
|
||||
0x2C 0x002C #COMMA
|
||||
0x2D 0x002D #HYPHEN-MINUS
|
||||
0x2E 0x002E #FULL STOP
|
||||
0x2F 0x002F #SOLIDUS
|
||||
0x30 0x0030 #DIGIT ZERO
|
||||
0x31 0x0031 #DIGIT ONE
|
||||
0x32 0x0032 #DIGIT TWO
|
||||
0x33 0x0033 #DIGIT THREE
|
||||
0x34 0x0034 #DIGIT FOUR
|
||||
0x35 0x0035 #DIGIT FIVE
|
||||
0x36 0x0036 #DIGIT SIX
|
||||
0x37 0x0037 #DIGIT SEVEN
|
||||
0x38 0x0038 #DIGIT EIGHT
|
||||
0x39 0x0039 #DIGIT NINE
|
||||
0x3A 0x003A #COLON
|
||||
0x3B 0x003B #SEMICOLON
|
||||
0x3C 0x003C #LESS-THAN SIGN
|
||||
0x3D 0x003D #EQUALS SIGN
|
||||
0x3E 0x003E #GREATER-THAN SIGN
|
||||
0x3F 0x003F #QUESTION MARK
|
||||
0x40 0x0040 #COMMERCIAL AT
|
||||
0x41 0x0041 #LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 #LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 #LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 #LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 #LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 #LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 #LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 #LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 #LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A #LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B #LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C #LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D #LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E #LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F #LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 #LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 #LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 #LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 #LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 #LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 #LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 #LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 #LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A #LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B #LEFT SQUARE BRACKET
|
||||
0x5C 0x005C #REVERSE SOLIDUS
|
||||
0x5D 0x005D #RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E #CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F #LOW LINE
|
||||
0x60 0x0060 #GRAVE ACCENT
|
||||
0x61 0x0061 #LATIN SMALL LETTER A
|
||||
0x62 0x0062 #LATIN SMALL LETTER B
|
||||
0x63 0x0063 #LATIN SMALL LETTER C
|
||||
0x64 0x0064 #LATIN SMALL LETTER D
|
||||
0x65 0x0065 #LATIN SMALL LETTER E
|
||||
0x66 0x0066 #LATIN SMALL LETTER F
|
||||
0x67 0x0067 #LATIN SMALL LETTER G
|
||||
0x68 0x0068 #LATIN SMALL LETTER H
|
||||
0x69 0x0069 #LATIN SMALL LETTER I
|
||||
0x6A 0x006A #LATIN SMALL LETTER J
|
||||
0x6B 0x006B #LATIN SMALL LETTER K
|
||||
0x6C 0x006C #LATIN SMALL LETTER L
|
||||
0x6D 0x006D #LATIN SMALL LETTER M
|
||||
0x6E 0x006E #LATIN SMALL LETTER N
|
||||
0x6F 0x006F #LATIN SMALL LETTER O
|
||||
0x70 0x0070 #LATIN SMALL LETTER P
|
||||
0x71 0x0071 #LATIN SMALL LETTER Q
|
||||
0x72 0x0072 #LATIN SMALL LETTER R
|
||||
0x73 0x0073 #LATIN SMALL LETTER S
|
||||
0x74 0x0074 #LATIN SMALL LETTER T
|
||||
0x75 0x0075 #LATIN SMALL LETTER U
|
||||
0x76 0x0076 #LATIN SMALL LETTER V
|
||||
0x77 0x0077 #LATIN SMALL LETTER W
|
||||
0x78 0x0078 #LATIN SMALL LETTER X
|
||||
0x79 0x0079 #LATIN SMALL LETTER Y
|
||||
0x7A 0x007A #LATIN SMALL LETTER Z
|
||||
0x7B 0x007B #LEFT CURLY BRACKET
|
||||
0x7C 0x007C #VERTICAL LINE
|
||||
0x7D 0x007D #RIGHT CURLY BRACKET
|
||||
0x7E 0x007E #TILDE
|
||||
0x7F 0x007F #DELETE
|
||||
0x80 0x20AC #EURO SIGN
|
||||
0x81 #UNDEFINED
|
||||
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
|
||||
0x83 #UNDEFINED
|
||||
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
|
||||
0x85 0x2026 #HORIZONTAL ELLIPSIS
|
||||
0x86 0x2020 #DAGGER
|
||||
0x87 0x2021 #DOUBLE DAGGER
|
||||
0x88 #UNDEFINED
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C 0x015A #LATIN CAPITAL LETTER S WITH ACUTE
|
||||
0x8D 0x0164 #LATIN CAPITAL LETTER T WITH CARON
|
||||
0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON
|
||||
0x8F 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
0x90 #UNDEFINED
|
||||
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
|
||||
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
|
||||
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
|
||||
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
|
||||
0x95 0x2022 #BULLET
|
||||
0x96 0x2013 #EN DASH
|
||||
0x97 0x2014 #EM DASH
|
||||
0x98 #UNDEFINED
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C 0x015B #LATIN SMALL LETTER S WITH ACUTE
|
||||
0x9D 0x0165 #LATIN SMALL LETTER T WITH CARON
|
||||
0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON
|
||||
0x9F 0x017A #LATIN SMALL LETTER Z WITH ACUTE
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x02C7 #CARON
|
||||
0xA2 0x02D8 #BREVE
|
||||
0xA3 0x0141 #LATIN CAPITAL LETTER L WITH STROKE
|
||||
0xA4 0x00A4 #CURRENCY SIGN
|
||||
0xA5 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x00A8 #DIAERESIS
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x02DB #OGONEK
|
||||
0xB3 0x0142 #LATIN SMALL LETTER L WITH STROKE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00B8 #CEDILLA
|
||||
0xB9 0x0105 #LATIN SMALL LETTER A WITH OGONEK
|
||||
0xBA 0x015F #LATIN SMALL LETTER S WITH CEDILLA
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x013D #LATIN CAPITAL LETTER L WITH CARON
|
||||
0xBD 0x02DD #DOUBLE ACUTE ACCENT
|
||||
0xBE 0x013E #LATIN SMALL LETTER L WITH CARON
|
||||
0xBF 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
0xC0 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE
|
||||
0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE
|
||||
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE
|
||||
0xC6 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE
|
||||
0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON
|
||||
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x011A #LATIN CAPITAL LETTER E WITH CARON
|
||||
0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x010E #LATIN CAPITAL LETTER D WITH CARON
|
||||
0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE
|
||||
0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE
|
||||
0xD2 0x0147 #LATIN CAPITAL LETTER N WITH CARON
|
||||
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
|
||||
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 #MULTIPLICATION SIGN
|
||||
0xD8 0x0158 #LATIN CAPITAL LETTER R WITH CARON
|
||||
0xD9 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE
|
||||
0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
|
||||
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0xDE 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA
|
||||
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x0155 #LATIN SMALL LETTER R WITH ACUTE
|
||||
0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE
|
||||
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x013A #LATIN SMALL LETTER L WITH ACUTE
|
||||
0xE6 0x0107 #LATIN SMALL LETTER C WITH ACUTE
|
||||
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x010D #LATIN SMALL LETTER C WITH CARON
|
||||
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x0119 #LATIN SMALL LETTER E WITH OGONEK
|
||||
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x011B #LATIN SMALL LETTER E WITH CARON
|
||||
0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x010F #LATIN SMALL LETTER D WITH CARON
|
||||
0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE
|
||||
0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE
|
||||
0xF2 0x0148 #LATIN SMALL LETTER N WITH CARON
|
||||
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE
|
||||
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 #DIVISION SIGN
|
||||
0xF8 0x0159 #LATIN SMALL LETTER R WITH CARON
|
||||
0xF9 0x016F #LATIN SMALL LETTER U WITH RING ABOVE
|
||||
0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE
|
||||
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
|
||||
0xFE 0x0163 #LATIN SMALL LETTER T WITH CEDILLA
|
||||
0xFF 0x02D9 #DOT ABOVE
|
||||
@@ -0,0 +1,274 @@
|
||||
#
|
||||
# Name: cp1251 to Unicode table
|
||||
# Unicode version: 2.0
|
||||
# Table version: 2.01
|
||||
# Table format: Format A
|
||||
# Date: 04/15/98
|
||||
#
|
||||
# Contact: cpxlate@microsoft.com
|
||||
#
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp1251 code (in hex)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 is the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in cp1251 order
|
||||
#
|
||||
0x00 0x0000 #NULL
|
||||
0x01 0x0001 #START OF HEADING
|
||||
0x02 0x0002 #START OF TEXT
|
||||
0x03 0x0003 #END OF TEXT
|
||||
0x04 0x0004 #END OF TRANSMISSION
|
||||
0x05 0x0005 #ENQUIRY
|
||||
0x06 0x0006 #ACKNOWLEDGE
|
||||
0x07 0x0007 #BELL
|
||||
0x08 0x0008 #BACKSPACE
|
||||
0x09 0x0009 #HORIZONTAL TABULATION
|
||||
0x0A 0x000A #LINE FEED
|
||||
0x0B 0x000B #VERTICAL TABULATION
|
||||
0x0C 0x000C #FORM FEED
|
||||
0x0D 0x000D #CARRIAGE RETURN
|
||||
0x0E 0x000E #SHIFT OUT
|
||||
0x0F 0x000F #SHIFT IN
|
||||
0x10 0x0010 #DATA LINK ESCAPE
|
||||
0x11 0x0011 #DEVICE CONTROL ONE
|
||||
0x12 0x0012 #DEVICE CONTROL TWO
|
||||
0x13 0x0013 #DEVICE CONTROL THREE
|
||||
0x14 0x0014 #DEVICE CONTROL FOUR
|
||||
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 #SYNCHRONOUS IDLE
|
||||
0x17 0x0017 #END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 #CANCEL
|
||||
0x19 0x0019 #END OF MEDIUM
|
||||
0x1A 0x001A #SUBSTITUTE
|
||||
0x1B 0x001B #ESCAPE
|
||||
0x1C 0x001C #FILE SEPARATOR
|
||||
0x1D 0x001D #GROUP SEPARATOR
|
||||
0x1E 0x001E #RECORD SEPARATOR
|
||||
0x1F 0x001F #UNIT SEPARATOR
|
||||
0x20 0x0020 #SPACE
|
||||
0x21 0x0021 #EXCLAMATION MARK
|
||||
0x22 0x0022 #QUOTATION MARK
|
||||
0x23 0x0023 #NUMBER SIGN
|
||||
0x24 0x0024 #DOLLAR SIGN
|
||||
0x25 0x0025 #PERCENT SIGN
|
||||
0x26 0x0026 #AMPERSAND
|
||||
0x27 0x0027 #APOSTROPHE
|
||||
0x28 0x0028 #LEFT PARENTHESIS
|
||||
0x29 0x0029 #RIGHT PARENTHESIS
|
||||
0x2A 0x002A #ASTERISK
|
||||
0x2B 0x002B #PLUS SIGN
|
||||
0x2C 0x002C #COMMA
|
||||
0x2D 0x002D #HYPHEN-MINUS
|
||||
0x2E 0x002E #FULL STOP
|
||||
0x2F 0x002F #SOLIDUS
|
||||
0x30 0x0030 #DIGIT ZERO
|
||||
0x31 0x0031 #DIGIT ONE
|
||||
0x32 0x0032 #DIGIT TWO
|
||||
0x33 0x0033 #DIGIT THREE
|
||||
0x34 0x0034 #DIGIT FOUR
|
||||
0x35 0x0035 #DIGIT FIVE
|
||||
0x36 0x0036 #DIGIT SIX
|
||||
0x37 0x0037 #DIGIT SEVEN
|
||||
0x38 0x0038 #DIGIT EIGHT
|
||||
0x39 0x0039 #DIGIT NINE
|
||||
0x3A 0x003A #COLON
|
||||
0x3B 0x003B #SEMICOLON
|
||||
0x3C 0x003C #LESS-THAN SIGN
|
||||
0x3D 0x003D #EQUALS SIGN
|
||||
0x3E 0x003E #GREATER-THAN SIGN
|
||||
0x3F 0x003F #QUESTION MARK
|
||||
0x40 0x0040 #COMMERCIAL AT
|
||||
0x41 0x0041 #LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 #LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 #LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 #LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 #LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 #LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 #LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 #LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 #LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A #LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B #LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C #LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D #LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E #LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F #LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 #LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 #LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 #LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 #LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 #LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 #LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 #LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 #LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A #LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B #LEFT SQUARE BRACKET
|
||||
0x5C 0x005C #REVERSE SOLIDUS
|
||||
0x5D 0x005D #RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E #CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F #LOW LINE
|
||||
0x60 0x0060 #GRAVE ACCENT
|
||||
0x61 0x0061 #LATIN SMALL LETTER A
|
||||
0x62 0x0062 #LATIN SMALL LETTER B
|
||||
0x63 0x0063 #LATIN SMALL LETTER C
|
||||
0x64 0x0064 #LATIN SMALL LETTER D
|
||||
0x65 0x0065 #LATIN SMALL LETTER E
|
||||
0x66 0x0066 #LATIN SMALL LETTER F
|
||||
0x67 0x0067 #LATIN SMALL LETTER G
|
||||
0x68 0x0068 #LATIN SMALL LETTER H
|
||||
0x69 0x0069 #LATIN SMALL LETTER I
|
||||
0x6A 0x006A #LATIN SMALL LETTER J
|
||||
0x6B 0x006B #LATIN SMALL LETTER K
|
||||
0x6C 0x006C #LATIN SMALL LETTER L
|
||||
0x6D 0x006D #LATIN SMALL LETTER M
|
||||
0x6E 0x006E #LATIN SMALL LETTER N
|
||||
0x6F 0x006F #LATIN SMALL LETTER O
|
||||
0x70 0x0070 #LATIN SMALL LETTER P
|
||||
0x71 0x0071 #LATIN SMALL LETTER Q
|
||||
0x72 0x0072 #LATIN SMALL LETTER R
|
||||
0x73 0x0073 #LATIN SMALL LETTER S
|
||||
0x74 0x0074 #LATIN SMALL LETTER T
|
||||
0x75 0x0075 #LATIN SMALL LETTER U
|
||||
0x76 0x0076 #LATIN SMALL LETTER V
|
||||
0x77 0x0077 #LATIN SMALL LETTER W
|
||||
0x78 0x0078 #LATIN SMALL LETTER X
|
||||
0x79 0x0079 #LATIN SMALL LETTER Y
|
||||
0x7A 0x007A #LATIN SMALL LETTER Z
|
||||
0x7B 0x007B #LEFT CURLY BRACKET
|
||||
0x7C 0x007C #VERTICAL LINE
|
||||
0x7D 0x007D #RIGHT CURLY BRACKET
|
||||
0x7E 0x007E #TILDE
|
||||
0x7F 0x007F #DELETE
|
||||
0x80 0x0402 #CYRILLIC CAPITAL LETTER DJE
|
||||
0x81 0x0403 #CYRILLIC CAPITAL LETTER GJE
|
||||
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
|
||||
0x83 0x0453 #CYRILLIC SMALL LETTER GJE
|
||||
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
|
||||
0x85 0x2026 #HORIZONTAL ELLIPSIS
|
||||
0x86 0x2020 #DAGGER
|
||||
0x87 0x2021 #DOUBLE DAGGER
|
||||
0x88 0x20AC #EURO SIGN
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A 0x0409 #CYRILLIC CAPITAL LETTER LJE
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C 0x040A #CYRILLIC CAPITAL LETTER NJE
|
||||
0x8D 0x040C #CYRILLIC CAPITAL LETTER KJE
|
||||
0x8E 0x040B #CYRILLIC CAPITAL LETTER TSHE
|
||||
0x8F 0x040F #CYRILLIC CAPITAL LETTER DZHE
|
||||
0x90 0x0452 #CYRILLIC SMALL LETTER DJE
|
||||
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
|
||||
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
|
||||
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
|
||||
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
|
||||
0x95 0x2022 #BULLET
|
||||
0x96 0x2013 #EN DASH
|
||||
0x97 0x2014 #EM DASH
|
||||
0x98 #UNDEFINED
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A 0x0459 #CYRILLIC SMALL LETTER LJE
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C 0x045A #CYRILLIC SMALL LETTER NJE
|
||||
0x9D 0x045C #CYRILLIC SMALL LETTER KJE
|
||||
0x9E 0x045B #CYRILLIC SMALL LETTER TSHE
|
||||
0x9F 0x045F #CYRILLIC SMALL LETTER DZHE
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x040E #CYRILLIC CAPITAL LETTER SHORT U
|
||||
0xA2 0x045E #CYRILLIC SMALL LETTER SHORT U
|
||||
0xA3 0x0408 #CYRILLIC CAPITAL LETTER JE
|
||||
0xA4 0x00A4 #CURRENCY SIGN
|
||||
0xA5 0x0490 #CYRILLIC CAPITAL LETTER GHE WITH UPTURN
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x0401 #CYRILLIC CAPITAL LETTER IO
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x0404 #CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x0407 #CYRILLIC CAPITAL LETTER YI
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x0406 #CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0xB3 0x0456 #CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0xB4 0x0491 #CYRILLIC SMALL LETTER GHE WITH UPTURN
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x0451 #CYRILLIC SMALL LETTER IO
|
||||
0xB9 0x2116 #NUMERO SIGN
|
||||
0xBA 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x0458 #CYRILLIC SMALL LETTER JE
|
||||
0xBD 0x0405 #CYRILLIC CAPITAL LETTER DZE
|
||||
0xBE 0x0455 #CYRILLIC SMALL LETTER DZE
|
||||
0xBF 0x0457 #CYRILLIC SMALL LETTER YI
|
||||
0xC0 0x0410 #CYRILLIC CAPITAL LETTER A
|
||||
0xC1 0x0411 #CYRILLIC CAPITAL LETTER BE
|
||||
0xC2 0x0412 #CYRILLIC CAPITAL LETTER VE
|
||||
0xC3 0x0413 #CYRILLIC CAPITAL LETTER GHE
|
||||
0xC4 0x0414 #CYRILLIC CAPITAL LETTER DE
|
||||
0xC5 0x0415 #CYRILLIC CAPITAL LETTER IE
|
||||
0xC6 0x0416 #CYRILLIC CAPITAL LETTER ZHE
|
||||
0xC7 0x0417 #CYRILLIC CAPITAL LETTER ZE
|
||||
0xC8 0x0418 #CYRILLIC CAPITAL LETTER I
|
||||
0xC9 0x0419 #CYRILLIC CAPITAL LETTER SHORT I
|
||||
0xCA 0x041A #CYRILLIC CAPITAL LETTER KA
|
||||
0xCB 0x041B #CYRILLIC CAPITAL LETTER EL
|
||||
0xCC 0x041C #CYRILLIC CAPITAL LETTER EM
|
||||
0xCD 0x041D #CYRILLIC CAPITAL LETTER EN
|
||||
0xCE 0x041E #CYRILLIC CAPITAL LETTER O
|
||||
0xCF 0x041F #CYRILLIC CAPITAL LETTER PE
|
||||
0xD0 0x0420 #CYRILLIC CAPITAL LETTER ER
|
||||
0xD1 0x0421 #CYRILLIC CAPITAL LETTER ES
|
||||
0xD2 0x0422 #CYRILLIC CAPITAL LETTER TE
|
||||
0xD3 0x0423 #CYRILLIC CAPITAL LETTER U
|
||||
0xD4 0x0424 #CYRILLIC CAPITAL LETTER EF
|
||||
0xD5 0x0425 #CYRILLIC CAPITAL LETTER HA
|
||||
0xD6 0x0426 #CYRILLIC CAPITAL LETTER TSE
|
||||
0xD7 0x0427 #CYRILLIC CAPITAL LETTER CHE
|
||||
0xD8 0x0428 #CYRILLIC CAPITAL LETTER SHA
|
||||
0xD9 0x0429 #CYRILLIC CAPITAL LETTER SHCHA
|
||||
0xDA 0x042A #CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
0xDB 0x042B #CYRILLIC CAPITAL LETTER YERU
|
||||
0xDC 0x042C #CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
0xDD 0x042D #CYRILLIC CAPITAL LETTER E
|
||||
0xDE 0x042E #CYRILLIC CAPITAL LETTER YU
|
||||
0xDF 0x042F #CYRILLIC CAPITAL LETTER YA
|
||||
0xE0 0x0430 #CYRILLIC SMALL LETTER A
|
||||
0xE1 0x0431 #CYRILLIC SMALL LETTER BE
|
||||
0xE2 0x0432 #CYRILLIC SMALL LETTER VE
|
||||
0xE3 0x0433 #CYRILLIC SMALL LETTER GHE
|
||||
0xE4 0x0434 #CYRILLIC SMALL LETTER DE
|
||||
0xE5 0x0435 #CYRILLIC SMALL LETTER IE
|
||||
0xE6 0x0436 #CYRILLIC SMALL LETTER ZHE
|
||||
0xE7 0x0437 #CYRILLIC SMALL LETTER ZE
|
||||
0xE8 0x0438 #CYRILLIC SMALL LETTER I
|
||||
0xE9 0x0439 #CYRILLIC SMALL LETTER SHORT I
|
||||
0xEA 0x043A #CYRILLIC SMALL LETTER KA
|
||||
0xEB 0x043B #CYRILLIC SMALL LETTER EL
|
||||
0xEC 0x043C #CYRILLIC SMALL LETTER EM
|
||||
0xED 0x043D #CYRILLIC SMALL LETTER EN
|
||||
0xEE 0x043E #CYRILLIC SMALL LETTER O
|
||||
0xEF 0x043F #CYRILLIC SMALL LETTER PE
|
||||
0xF0 0x0440 #CYRILLIC SMALL LETTER ER
|
||||
0xF1 0x0441 #CYRILLIC SMALL LETTER ES
|
||||
0xF2 0x0442 #CYRILLIC SMALL LETTER TE
|
||||
0xF3 0x0443 #CYRILLIC SMALL LETTER U
|
||||
0xF4 0x0444 #CYRILLIC SMALL LETTER EF
|
||||
0xF5 0x0445 #CYRILLIC SMALL LETTER HA
|
||||
0xF6 0x0446 #CYRILLIC SMALL LETTER TSE
|
||||
0xF7 0x0447 #CYRILLIC SMALL LETTER CHE
|
||||
0xF8 0x0448 #CYRILLIC SMALL LETTER SHA
|
||||
0xF9 0x0449 #CYRILLIC SMALL LETTER SHCHA
|
||||
0xFA 0x044A #CYRILLIC SMALL LETTER HARD SIGN
|
||||
0xFB 0x044B #CYRILLIC SMALL LETTER YERU
|
||||
0xFC 0x044C #CYRILLIC SMALL LETTER SOFT SIGN
|
||||
0xFD 0x044D #CYRILLIC SMALL LETTER E
|
||||
0xFE 0x044E #CYRILLIC SMALL LETTER YU
|
||||
0xFF 0x044F #CYRILLIC SMALL LETTER YA
|
||||
@@ -0,0 +1,274 @@
|
||||
#
|
||||
# Name: cp1252 to Unicode table
|
||||
# Unicode version: 2.0
|
||||
# Table version: 2.01
|
||||
# Table format: Format A
|
||||
# Date: 04/15/98
|
||||
#
|
||||
# Contact: cpxlate@microsoft.com
|
||||
#
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp1252 code (in hex)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 is the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in cp1252 order
|
||||
#
|
||||
0x00 0x0000 #NULL
|
||||
0x01 0x0001 #START OF HEADING
|
||||
0x02 0x0002 #START OF TEXT
|
||||
0x03 0x0003 #END OF TEXT
|
||||
0x04 0x0004 #END OF TRANSMISSION
|
||||
0x05 0x0005 #ENQUIRY
|
||||
0x06 0x0006 #ACKNOWLEDGE
|
||||
0x07 0x0007 #BELL
|
||||
0x08 0x0008 #BACKSPACE
|
||||
0x09 0x0009 #HORIZONTAL TABULATION
|
||||
0x0A 0x000A #LINE FEED
|
||||
0x0B 0x000B #VERTICAL TABULATION
|
||||
0x0C 0x000C #FORM FEED
|
||||
0x0D 0x000D #CARRIAGE RETURN
|
||||
0x0E 0x000E #SHIFT OUT
|
||||
0x0F 0x000F #SHIFT IN
|
||||
0x10 0x0010 #DATA LINK ESCAPE
|
||||
0x11 0x0011 #DEVICE CONTROL ONE
|
||||
0x12 0x0012 #DEVICE CONTROL TWO
|
||||
0x13 0x0013 #DEVICE CONTROL THREE
|
||||
0x14 0x0014 #DEVICE CONTROL FOUR
|
||||
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 #SYNCHRONOUS IDLE
|
||||
0x17 0x0017 #END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 #CANCEL
|
||||
0x19 0x0019 #END OF MEDIUM
|
||||
0x1A 0x001A #SUBSTITUTE
|
||||
0x1B 0x001B #ESCAPE
|
||||
0x1C 0x001C #FILE SEPARATOR
|
||||
0x1D 0x001D #GROUP SEPARATOR
|
||||
0x1E 0x001E #RECORD SEPARATOR
|
||||
0x1F 0x001F #UNIT SEPARATOR
|
||||
0x20 0x0020 #SPACE
|
||||
0x21 0x0021 #EXCLAMATION MARK
|
||||
0x22 0x0022 #QUOTATION MARK
|
||||
0x23 0x0023 #NUMBER SIGN
|
||||
0x24 0x0024 #DOLLAR SIGN
|
||||
0x25 0x0025 #PERCENT SIGN
|
||||
0x26 0x0026 #AMPERSAND
|
||||
0x27 0x0027 #APOSTROPHE
|
||||
0x28 0x0028 #LEFT PARENTHESIS
|
||||
0x29 0x0029 #RIGHT PARENTHESIS
|
||||
0x2A 0x002A #ASTERISK
|
||||
0x2B 0x002B #PLUS SIGN
|
||||
0x2C 0x002C #COMMA
|
||||
0x2D 0x002D #HYPHEN-MINUS
|
||||
0x2E 0x002E #FULL STOP
|
||||
0x2F 0x002F #SOLIDUS
|
||||
0x30 0x0030 #DIGIT ZERO
|
||||
0x31 0x0031 #DIGIT ONE
|
||||
0x32 0x0032 #DIGIT TWO
|
||||
0x33 0x0033 #DIGIT THREE
|
||||
0x34 0x0034 #DIGIT FOUR
|
||||
0x35 0x0035 #DIGIT FIVE
|
||||
0x36 0x0036 #DIGIT SIX
|
||||
0x37 0x0037 #DIGIT SEVEN
|
||||
0x38 0x0038 #DIGIT EIGHT
|
||||
0x39 0x0039 #DIGIT NINE
|
||||
0x3A 0x003A #COLON
|
||||
0x3B 0x003B #SEMICOLON
|
||||
0x3C 0x003C #LESS-THAN SIGN
|
||||
0x3D 0x003D #EQUALS SIGN
|
||||
0x3E 0x003E #GREATER-THAN SIGN
|
||||
0x3F 0x003F #QUESTION MARK
|
||||
0x40 0x0040 #COMMERCIAL AT
|
||||
0x41 0x0041 #LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 #LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 #LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 #LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 #LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 #LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 #LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 #LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 #LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A #LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B #LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C #LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D #LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E #LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F #LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 #LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 #LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 #LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 #LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 #LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 #LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 #LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 #LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A #LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B #LEFT SQUARE BRACKET
|
||||
0x5C 0x005C #REVERSE SOLIDUS
|
||||
0x5D 0x005D #RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E #CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F #LOW LINE
|
||||
0x60 0x0060 #GRAVE ACCENT
|
||||
0x61 0x0061 #LATIN SMALL LETTER A
|
||||
0x62 0x0062 #LATIN SMALL LETTER B
|
||||
0x63 0x0063 #LATIN SMALL LETTER C
|
||||
0x64 0x0064 #LATIN SMALL LETTER D
|
||||
0x65 0x0065 #LATIN SMALL LETTER E
|
||||
0x66 0x0066 #LATIN SMALL LETTER F
|
||||
0x67 0x0067 #LATIN SMALL LETTER G
|
||||
0x68 0x0068 #LATIN SMALL LETTER H
|
||||
0x69 0x0069 #LATIN SMALL LETTER I
|
||||
0x6A 0x006A #LATIN SMALL LETTER J
|
||||
0x6B 0x006B #LATIN SMALL LETTER K
|
||||
0x6C 0x006C #LATIN SMALL LETTER L
|
||||
0x6D 0x006D #LATIN SMALL LETTER M
|
||||
0x6E 0x006E #LATIN SMALL LETTER N
|
||||
0x6F 0x006F #LATIN SMALL LETTER O
|
||||
0x70 0x0070 #LATIN SMALL LETTER P
|
||||
0x71 0x0071 #LATIN SMALL LETTER Q
|
||||
0x72 0x0072 #LATIN SMALL LETTER R
|
||||
0x73 0x0073 #LATIN SMALL LETTER S
|
||||
0x74 0x0074 #LATIN SMALL LETTER T
|
||||
0x75 0x0075 #LATIN SMALL LETTER U
|
||||
0x76 0x0076 #LATIN SMALL LETTER V
|
||||
0x77 0x0077 #LATIN SMALL LETTER W
|
||||
0x78 0x0078 #LATIN SMALL LETTER X
|
||||
0x79 0x0079 #LATIN SMALL LETTER Y
|
||||
0x7A 0x007A #LATIN SMALL LETTER Z
|
||||
0x7B 0x007B #LEFT CURLY BRACKET
|
||||
0x7C 0x007C #VERTICAL LINE
|
||||
0x7D 0x007D #RIGHT CURLY BRACKET
|
||||
0x7E 0x007E #TILDE
|
||||
0x7F 0x007F #DELETE
|
||||
0x80 0x20AC #EURO SIGN
|
||||
0x81 #UNDEFINED
|
||||
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
|
||||
0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK
|
||||
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
|
||||
0x85 0x2026 #HORIZONTAL ELLIPSIS
|
||||
0x86 0x2020 #DAGGER
|
||||
0x87 0x2021 #DOUBLE DAGGER
|
||||
0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C 0x0152 #LATIN CAPITAL LIGATURE OE
|
||||
0x8D #UNDEFINED
|
||||
0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON
|
||||
0x8F #UNDEFINED
|
||||
0x90 #UNDEFINED
|
||||
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
|
||||
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
|
||||
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
|
||||
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
|
||||
0x95 0x2022 #BULLET
|
||||
0x96 0x2013 #EN DASH
|
||||
0x97 0x2014 #EM DASH
|
||||
0x98 0x02DC #SMALL TILDE
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C 0x0153 #LATIN SMALL LIGATURE OE
|
||||
0x9D #UNDEFINED
|
||||
0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON
|
||||
0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x00A1 #INVERTED EXCLAMATION MARK
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
0xA3 0x00A3 #POUND SIGN
|
||||
0xA4 0x00A4 #CURRENCY SIGN
|
||||
0xA5 0x00A5 #YEN SIGN
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x00A8 #DIAERESIS
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x00AA #FEMININE ORDINAL INDICATOR
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x00AF #MACRON
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00B8 #CEDILLA
|
||||
0xB9 0x00B9 #SUPERSCRIPT ONE
|
||||
0xBA 0x00BA #MASCULINE ORDINAL INDICATOR
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00BF #INVERTED QUESTION MARK
|
||||
0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
|
||||
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x00C6 #LATIN CAPITAL LETTER AE
|
||||
0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD0 0x00D0 #LATIN CAPITAL LETTER ETH
|
||||
0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
|
||||
0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 #MULTIPLICATION SIGN
|
||||
0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0xDE 0x00DE #LATIN CAPITAL LETTER THORN
|
||||
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE
|
||||
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x00E6 #LATIN SMALL LETTER AE
|
||||
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE
|
||||
0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x00F0 #LATIN SMALL LETTER ETH
|
||||
0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE
|
||||
0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
|
||||
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 #DIVISION SIGN
|
||||
0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE
|
||||
0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
|
||||
0xFE 0x00FE #LATIN SMALL LETTER THORN
|
||||
0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
@@ -0,0 +1,274 @@
|
||||
#
|
||||
# Name: cp1253 to Unicode table
|
||||
# Unicode version: 2.0
|
||||
# Table version: 2.01
|
||||
# Table format: Format A
|
||||
# Date: 04/15/98
|
||||
#
|
||||
# Contact: cpxlate@microsoft.com
|
||||
#
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp1253 code (in hex)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 is the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in cp1253 order
|
||||
#
|
||||
0x00 0x0000 #NULL
|
||||
0x01 0x0001 #START OF HEADING
|
||||
0x02 0x0002 #START OF TEXT
|
||||
0x03 0x0003 #END OF TEXT
|
||||
0x04 0x0004 #END OF TRANSMISSION
|
||||
0x05 0x0005 #ENQUIRY
|
||||
0x06 0x0006 #ACKNOWLEDGE
|
||||
0x07 0x0007 #BELL
|
||||
0x08 0x0008 #BACKSPACE
|
||||
0x09 0x0009 #HORIZONTAL TABULATION
|
||||
0x0A 0x000A #LINE FEED
|
||||
0x0B 0x000B #VERTICAL TABULATION
|
||||
0x0C 0x000C #FORM FEED
|
||||
0x0D 0x000D #CARRIAGE RETURN
|
||||
0x0E 0x000E #SHIFT OUT
|
||||
0x0F 0x000F #SHIFT IN
|
||||
0x10 0x0010 #DATA LINK ESCAPE
|
||||
0x11 0x0011 #DEVICE CONTROL ONE
|
||||
0x12 0x0012 #DEVICE CONTROL TWO
|
||||
0x13 0x0013 #DEVICE CONTROL THREE
|
||||
0x14 0x0014 #DEVICE CONTROL FOUR
|
||||
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 #SYNCHRONOUS IDLE
|
||||
0x17 0x0017 #END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 #CANCEL
|
||||
0x19 0x0019 #END OF MEDIUM
|
||||
0x1A 0x001A #SUBSTITUTE
|
||||
0x1B 0x001B #ESCAPE
|
||||
0x1C 0x001C #FILE SEPARATOR
|
||||
0x1D 0x001D #GROUP SEPARATOR
|
||||
0x1E 0x001E #RECORD SEPARATOR
|
||||
0x1F 0x001F #UNIT SEPARATOR
|
||||
0x20 0x0020 #SPACE
|
||||
0x21 0x0021 #EXCLAMATION MARK
|
||||
0x22 0x0022 #QUOTATION MARK
|
||||
0x23 0x0023 #NUMBER SIGN
|
||||
0x24 0x0024 #DOLLAR SIGN
|
||||
0x25 0x0025 #PERCENT SIGN
|
||||
0x26 0x0026 #AMPERSAND
|
||||
0x27 0x0027 #APOSTROPHE
|
||||
0x28 0x0028 #LEFT PARENTHESIS
|
||||
0x29 0x0029 #RIGHT PARENTHESIS
|
||||
0x2A 0x002A #ASTERISK
|
||||
0x2B 0x002B #PLUS SIGN
|
||||
0x2C 0x002C #COMMA
|
||||
0x2D 0x002D #HYPHEN-MINUS
|
||||
0x2E 0x002E #FULL STOP
|
||||
0x2F 0x002F #SOLIDUS
|
||||
0x30 0x0030 #DIGIT ZERO
|
||||
0x31 0x0031 #DIGIT ONE
|
||||
0x32 0x0032 #DIGIT TWO
|
||||
0x33 0x0033 #DIGIT THREE
|
||||
0x34 0x0034 #DIGIT FOUR
|
||||
0x35 0x0035 #DIGIT FIVE
|
||||
0x36 0x0036 #DIGIT SIX
|
||||
0x37 0x0037 #DIGIT SEVEN
|
||||
0x38 0x0038 #DIGIT EIGHT
|
||||
0x39 0x0039 #DIGIT NINE
|
||||
0x3A 0x003A #COLON
|
||||
0x3B 0x003B #SEMICOLON
|
||||
0x3C 0x003C #LESS-THAN SIGN
|
||||
0x3D 0x003D #EQUALS SIGN
|
||||
0x3E 0x003E #GREATER-THAN SIGN
|
||||
0x3F 0x003F #QUESTION MARK
|
||||
0x40 0x0040 #COMMERCIAL AT
|
||||
0x41 0x0041 #LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 #LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 #LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 #LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 #LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 #LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 #LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 #LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 #LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A #LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B #LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C #LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D #LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E #LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F #LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 #LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 #LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 #LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 #LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 #LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 #LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 #LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 #LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A #LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B #LEFT SQUARE BRACKET
|
||||
0x5C 0x005C #REVERSE SOLIDUS
|
||||
0x5D 0x005D #RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E #CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F #LOW LINE
|
||||
0x60 0x0060 #GRAVE ACCENT
|
||||
0x61 0x0061 #LATIN SMALL LETTER A
|
||||
0x62 0x0062 #LATIN SMALL LETTER B
|
||||
0x63 0x0063 #LATIN SMALL LETTER C
|
||||
0x64 0x0064 #LATIN SMALL LETTER D
|
||||
0x65 0x0065 #LATIN SMALL LETTER E
|
||||
0x66 0x0066 #LATIN SMALL LETTER F
|
||||
0x67 0x0067 #LATIN SMALL LETTER G
|
||||
0x68 0x0068 #LATIN SMALL LETTER H
|
||||
0x69 0x0069 #LATIN SMALL LETTER I
|
||||
0x6A 0x006A #LATIN SMALL LETTER J
|
||||
0x6B 0x006B #LATIN SMALL LETTER K
|
||||
0x6C 0x006C #LATIN SMALL LETTER L
|
||||
0x6D 0x006D #LATIN SMALL LETTER M
|
||||
0x6E 0x006E #LATIN SMALL LETTER N
|
||||
0x6F 0x006F #LATIN SMALL LETTER O
|
||||
0x70 0x0070 #LATIN SMALL LETTER P
|
||||
0x71 0x0071 #LATIN SMALL LETTER Q
|
||||
0x72 0x0072 #LATIN SMALL LETTER R
|
||||
0x73 0x0073 #LATIN SMALL LETTER S
|
||||
0x74 0x0074 #LATIN SMALL LETTER T
|
||||
0x75 0x0075 #LATIN SMALL LETTER U
|
||||
0x76 0x0076 #LATIN SMALL LETTER V
|
||||
0x77 0x0077 #LATIN SMALL LETTER W
|
||||
0x78 0x0078 #LATIN SMALL LETTER X
|
||||
0x79 0x0079 #LATIN SMALL LETTER Y
|
||||
0x7A 0x007A #LATIN SMALL LETTER Z
|
||||
0x7B 0x007B #LEFT CURLY BRACKET
|
||||
0x7C 0x007C #VERTICAL LINE
|
||||
0x7D 0x007D #RIGHT CURLY BRACKET
|
||||
0x7E 0x007E #TILDE
|
||||
0x7F 0x007F #DELETE
|
||||
0x80 0x20AC #EURO SIGN
|
||||
0x81 #UNDEFINED
|
||||
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
|
||||
0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK
|
||||
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
|
||||
0x85 0x2026 #HORIZONTAL ELLIPSIS
|
||||
0x86 0x2020 #DAGGER
|
||||
0x87 0x2021 #DOUBLE DAGGER
|
||||
0x88 #UNDEFINED
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A #UNDEFINED
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C #UNDEFINED
|
||||
0x8D #UNDEFINED
|
||||
0x8E #UNDEFINED
|
||||
0x8F #UNDEFINED
|
||||
0x90 #UNDEFINED
|
||||
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
|
||||
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
|
||||
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
|
||||
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
|
||||
0x95 0x2022 #BULLET
|
||||
0x96 0x2013 #EN DASH
|
||||
0x97 0x2014 #EM DASH
|
||||
0x98 #UNDEFINED
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A #UNDEFINED
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C #UNDEFINED
|
||||
0x9D #UNDEFINED
|
||||
0x9E #UNDEFINED
|
||||
0x9F #UNDEFINED
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x0385 #GREEK DIALYTIKA TONOS
|
||||
0xA2 0x0386 #GREEK CAPITAL LETTER ALPHA WITH TONOS
|
||||
0xA3 0x00A3 #POUND SIGN
|
||||
0xA4 0x00A4 #CURRENCY SIGN
|
||||
0xA5 0x00A5 #YEN SIGN
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x00A8 #DIAERESIS
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA #UNDEFINED
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x2015 #HORIZONTAL BAR
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x0384 #GREEK TONOS
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x0388 #GREEK CAPITAL LETTER EPSILON WITH TONOS
|
||||
0xB9 0x0389 #GREEK CAPITAL LETTER ETA WITH TONOS
|
||||
0xBA 0x038A #GREEK CAPITAL LETTER IOTA WITH TONOS
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x038C #GREEK CAPITAL LETTER OMICRON WITH TONOS
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x038E #GREEK CAPITAL LETTER UPSILON WITH TONOS
|
||||
0xBF 0x038F #GREEK CAPITAL LETTER OMEGA WITH TONOS
|
||||
0xC0 0x0390 #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
|
||||
0xC1 0x0391 #GREEK CAPITAL LETTER ALPHA
|
||||
0xC2 0x0392 #GREEK CAPITAL LETTER BETA
|
||||
0xC3 0x0393 #GREEK CAPITAL LETTER GAMMA
|
||||
0xC4 0x0394 #GREEK CAPITAL LETTER DELTA
|
||||
0xC5 0x0395 #GREEK CAPITAL LETTER EPSILON
|
||||
0xC6 0x0396 #GREEK CAPITAL LETTER ZETA
|
||||
0xC7 0x0397 #GREEK CAPITAL LETTER ETA
|
||||
0xC8 0x0398 #GREEK CAPITAL LETTER THETA
|
||||
0xC9 0x0399 #GREEK CAPITAL LETTER IOTA
|
||||
0xCA 0x039A #GREEK CAPITAL LETTER KAPPA
|
||||
0xCB 0x039B #GREEK CAPITAL LETTER LAMDA
|
||||
0xCC 0x039C #GREEK CAPITAL LETTER MU
|
||||
0xCD 0x039D #GREEK CAPITAL LETTER NU
|
||||
0xCE 0x039E #GREEK CAPITAL LETTER XI
|
||||
0xCF 0x039F #GREEK CAPITAL LETTER OMICRON
|
||||
0xD0 0x03A0 #GREEK CAPITAL LETTER PI
|
||||
0xD1 0x03A1 #GREEK CAPITAL LETTER RHO
|
||||
0xD2 #UNDEFINED
|
||||
0xD3 0x03A3 #GREEK CAPITAL LETTER SIGMA
|
||||
0xD4 0x03A4 #GREEK CAPITAL LETTER TAU
|
||||
0xD5 0x03A5 #GREEK CAPITAL LETTER UPSILON
|
||||
0xD6 0x03A6 #GREEK CAPITAL LETTER PHI
|
||||
0xD7 0x03A7 #GREEK CAPITAL LETTER CHI
|
||||
0xD8 0x03A8 #GREEK CAPITAL LETTER PSI
|
||||
0xD9 0x03A9 #GREEK CAPITAL LETTER OMEGA
|
||||
0xDA 0x03AA #GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
|
||||
0xDB 0x03AB #GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
|
||||
0xDC 0x03AC #GREEK SMALL LETTER ALPHA WITH TONOS
|
||||
0xDD 0x03AD #GREEK SMALL LETTER EPSILON WITH TONOS
|
||||
0xDE 0x03AE #GREEK SMALL LETTER ETA WITH TONOS
|
||||
0xDF 0x03AF #GREEK SMALL LETTER IOTA WITH TONOS
|
||||
0xE0 0x03B0 #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
|
||||
0xE1 0x03B1 #GREEK SMALL LETTER ALPHA
|
||||
0xE2 0x03B2 #GREEK SMALL LETTER BETA
|
||||
0xE3 0x03B3 #GREEK SMALL LETTER GAMMA
|
||||
0xE4 0x03B4 #GREEK SMALL LETTER DELTA
|
||||
0xE5 0x03B5 #GREEK SMALL LETTER EPSILON
|
||||
0xE6 0x03B6 #GREEK SMALL LETTER ZETA
|
||||
0xE7 0x03B7 #GREEK SMALL LETTER ETA
|
||||
0xE8 0x03B8 #GREEK SMALL LETTER THETA
|
||||
0xE9 0x03B9 #GREEK SMALL LETTER IOTA
|
||||
0xEA 0x03BA #GREEK SMALL LETTER KAPPA
|
||||
0xEB 0x03BB #GREEK SMALL LETTER LAMDA
|
||||
0xEC 0x03BC #GREEK SMALL LETTER MU
|
||||
0xED 0x03BD #GREEK SMALL LETTER NU
|
||||
0xEE 0x03BE #GREEK SMALL LETTER XI
|
||||
0xEF 0x03BF #GREEK SMALL LETTER OMICRON
|
||||
0xF0 0x03C0 #GREEK SMALL LETTER PI
|
||||
0xF1 0x03C1 #GREEK SMALL LETTER RHO
|
||||
0xF2 0x03C2 #GREEK SMALL LETTER FINAL SIGMA
|
||||
0xF3 0x03C3 #GREEK SMALL LETTER SIGMA
|
||||
0xF4 0x03C4 #GREEK SMALL LETTER TAU
|
||||
0xF5 0x03C5 #GREEK SMALL LETTER UPSILON
|
||||
0xF6 0x03C6 #GREEK SMALL LETTER PHI
|
||||
0xF7 0x03C7 #GREEK SMALL LETTER CHI
|
||||
0xF8 0x03C8 #GREEK SMALL LETTER PSI
|
||||
0xF9 0x03C9 #GREEK SMALL LETTER OMEGA
|
||||
0xFA 0x03CA #GREEK SMALL LETTER IOTA WITH DIALYTIKA
|
||||
0xFB 0x03CB #GREEK SMALL LETTER UPSILON WITH DIALYTIKA
|
||||
0xFC 0x03CC #GREEK SMALL LETTER OMICRON WITH TONOS
|
||||
0xFD 0x03CD #GREEK SMALL LETTER UPSILON WITH TONOS
|
||||
0xFE 0x03CE #GREEK SMALL LETTER OMEGA WITH TONOS
|
||||
0xFF #UNDEFINED
|
||||
@@ -0,0 +1,274 @@
|
||||
#
|
||||
# Name: cp1254 to Unicode table
|
||||
# Unicode version: 2.0
|
||||
# Table version: 2.01
|
||||
# Table format: Format A
|
||||
# Date: 04/15/98
|
||||
#
|
||||
# Contact: cpxlate@microsoft.com
|
||||
#
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp1254 code (in hex)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 is the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in cp1254 order
|
||||
#
|
||||
0x00 0x0000 #NULL
|
||||
0x01 0x0001 #START OF HEADING
|
||||
0x02 0x0002 #START OF TEXT
|
||||
0x03 0x0003 #END OF TEXT
|
||||
0x04 0x0004 #END OF TRANSMISSION
|
||||
0x05 0x0005 #ENQUIRY
|
||||
0x06 0x0006 #ACKNOWLEDGE
|
||||
0x07 0x0007 #BELL
|
||||
0x08 0x0008 #BACKSPACE
|
||||
0x09 0x0009 #HORIZONTAL TABULATION
|
||||
0x0A 0x000A #LINE FEED
|
||||
0x0B 0x000B #VERTICAL TABULATION
|
||||
0x0C 0x000C #FORM FEED
|
||||
0x0D 0x000D #CARRIAGE RETURN
|
||||
0x0E 0x000E #SHIFT OUT
|
||||
0x0F 0x000F #SHIFT IN
|
||||
0x10 0x0010 #DATA LINK ESCAPE
|
||||
0x11 0x0011 #DEVICE CONTROL ONE
|
||||
0x12 0x0012 #DEVICE CONTROL TWO
|
||||
0x13 0x0013 #DEVICE CONTROL THREE
|
||||
0x14 0x0014 #DEVICE CONTROL FOUR
|
||||
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 #SYNCHRONOUS IDLE
|
||||
0x17 0x0017 #END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 #CANCEL
|
||||
0x19 0x0019 #END OF MEDIUM
|
||||
0x1A 0x001A #SUBSTITUTE
|
||||
0x1B 0x001B #ESCAPE
|
||||
0x1C 0x001C #FILE SEPARATOR
|
||||
0x1D 0x001D #GROUP SEPARATOR
|
||||
0x1E 0x001E #RECORD SEPARATOR
|
||||
0x1F 0x001F #UNIT SEPARATOR
|
||||
0x20 0x0020 #SPACE
|
||||
0x21 0x0021 #EXCLAMATION MARK
|
||||
0x22 0x0022 #QUOTATION MARK
|
||||
0x23 0x0023 #NUMBER SIGN
|
||||
0x24 0x0024 #DOLLAR SIGN
|
||||
0x25 0x0025 #PERCENT SIGN
|
||||
0x26 0x0026 #AMPERSAND
|
||||
0x27 0x0027 #APOSTROPHE
|
||||
0x28 0x0028 #LEFT PARENTHESIS
|
||||
0x29 0x0029 #RIGHT PARENTHESIS
|
||||
0x2A 0x002A #ASTERISK
|
||||
0x2B 0x002B #PLUS SIGN
|
||||
0x2C 0x002C #COMMA
|
||||
0x2D 0x002D #HYPHEN-MINUS
|
||||
0x2E 0x002E #FULL STOP
|
||||
0x2F 0x002F #SOLIDUS
|
||||
0x30 0x0030 #DIGIT ZERO
|
||||
0x31 0x0031 #DIGIT ONE
|
||||
0x32 0x0032 #DIGIT TWO
|
||||
0x33 0x0033 #DIGIT THREE
|
||||
0x34 0x0034 #DIGIT FOUR
|
||||
0x35 0x0035 #DIGIT FIVE
|
||||
0x36 0x0036 #DIGIT SIX
|
||||
0x37 0x0037 #DIGIT SEVEN
|
||||
0x38 0x0038 #DIGIT EIGHT
|
||||
0x39 0x0039 #DIGIT NINE
|
||||
0x3A 0x003A #COLON
|
||||
0x3B 0x003B #SEMICOLON
|
||||
0x3C 0x003C #LESS-THAN SIGN
|
||||
0x3D 0x003D #EQUALS SIGN
|
||||
0x3E 0x003E #GREATER-THAN SIGN
|
||||
0x3F 0x003F #QUESTION MARK
|
||||
0x40 0x0040 #COMMERCIAL AT
|
||||
0x41 0x0041 #LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 #LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 #LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 #LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 #LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 #LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 #LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 #LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 #LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A #LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B #LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C #LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D #LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E #LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F #LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 #LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 #LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 #LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 #LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 #LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 #LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 #LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 #LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A #LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B #LEFT SQUARE BRACKET
|
||||
0x5C 0x005C #REVERSE SOLIDUS
|
||||
0x5D 0x005D #RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E #CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F #LOW LINE
|
||||
0x60 0x0060 #GRAVE ACCENT
|
||||
0x61 0x0061 #LATIN SMALL LETTER A
|
||||
0x62 0x0062 #LATIN SMALL LETTER B
|
||||
0x63 0x0063 #LATIN SMALL LETTER C
|
||||
0x64 0x0064 #LATIN SMALL LETTER D
|
||||
0x65 0x0065 #LATIN SMALL LETTER E
|
||||
0x66 0x0066 #LATIN SMALL LETTER F
|
||||
0x67 0x0067 #LATIN SMALL LETTER G
|
||||
0x68 0x0068 #LATIN SMALL LETTER H
|
||||
0x69 0x0069 #LATIN SMALL LETTER I
|
||||
0x6A 0x006A #LATIN SMALL LETTER J
|
||||
0x6B 0x006B #LATIN SMALL LETTER K
|
||||
0x6C 0x006C #LATIN SMALL LETTER L
|
||||
0x6D 0x006D #LATIN SMALL LETTER M
|
||||
0x6E 0x006E #LATIN SMALL LETTER N
|
||||
0x6F 0x006F #LATIN SMALL LETTER O
|
||||
0x70 0x0070 #LATIN SMALL LETTER P
|
||||
0x71 0x0071 #LATIN SMALL LETTER Q
|
||||
0x72 0x0072 #LATIN SMALL LETTER R
|
||||
0x73 0x0073 #LATIN SMALL LETTER S
|
||||
0x74 0x0074 #LATIN SMALL LETTER T
|
||||
0x75 0x0075 #LATIN SMALL LETTER U
|
||||
0x76 0x0076 #LATIN SMALL LETTER V
|
||||
0x77 0x0077 #LATIN SMALL LETTER W
|
||||
0x78 0x0078 #LATIN SMALL LETTER X
|
||||
0x79 0x0079 #LATIN SMALL LETTER Y
|
||||
0x7A 0x007A #LATIN SMALL LETTER Z
|
||||
0x7B 0x007B #LEFT CURLY BRACKET
|
||||
0x7C 0x007C #VERTICAL LINE
|
||||
0x7D 0x007D #RIGHT CURLY BRACKET
|
||||
0x7E 0x007E #TILDE
|
||||
0x7F 0x007F #DELETE
|
||||
0x80 0x20AC #EURO SIGN
|
||||
0x81 #UNDEFINED
|
||||
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
|
||||
0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK
|
||||
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
|
||||
0x85 0x2026 #HORIZONTAL ELLIPSIS
|
||||
0x86 0x2020 #DAGGER
|
||||
0x87 0x2021 #DOUBLE DAGGER
|
||||
0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C 0x0152 #LATIN CAPITAL LIGATURE OE
|
||||
0x8D #UNDEFINED
|
||||
0x8E #UNDEFINED
|
||||
0x8F #UNDEFINED
|
||||
0x90 #UNDEFINED
|
||||
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
|
||||
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
|
||||
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
|
||||
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
|
||||
0x95 0x2022 #BULLET
|
||||
0x96 0x2013 #EN DASH
|
||||
0x97 0x2014 #EM DASH
|
||||
0x98 0x02DC #SMALL TILDE
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C 0x0153 #LATIN SMALL LIGATURE OE
|
||||
0x9D #UNDEFINED
|
||||
0x9E #UNDEFINED
|
||||
0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x00A1 #INVERTED EXCLAMATION MARK
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
0xA3 0x00A3 #POUND SIGN
|
||||
0xA4 0x00A4 #CURRENCY SIGN
|
||||
0xA5 0x00A5 #YEN SIGN
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x00A8 #DIAERESIS
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x00AA #FEMININE ORDINAL INDICATOR
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x00AF #MACRON
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00B8 #CEDILLA
|
||||
0xB9 0x00B9 #SUPERSCRIPT ONE
|
||||
0xBA 0x00BA #MASCULINE ORDINAL INDICATOR
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00BF #INVERTED QUESTION MARK
|
||||
0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
|
||||
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x00C6 #LATIN CAPITAL LETTER AE
|
||||
0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD0 0x011E #LATIN CAPITAL LETTER G WITH BREVE
|
||||
0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
|
||||
0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 #MULTIPLICATION SIGN
|
||||
0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x0130 #LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
0xDE 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE
|
||||
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x00E6 #LATIN SMALL LETTER AE
|
||||
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE
|
||||
0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x011F #LATIN SMALL LETTER G WITH BREVE
|
||||
0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE
|
||||
0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
|
||||
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 #DIVISION SIGN
|
||||
0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE
|
||||
0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x0131 #LATIN SMALL LETTER DOTLESS I
|
||||
0xFE 0x015F #LATIN SMALL LETTER S WITH CEDILLA
|
||||
0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
@@ -0,0 +1,274 @@
|
||||
#
|
||||
# Name: cp1255 to Unicode table
|
||||
# Unicode version: 2.0
|
||||
# Table version: 2.01
|
||||
# Table format: Format A
|
||||
# Date: 1/7/2000
|
||||
#
|
||||
# Contact: cpxlate@microsoft.com
|
||||
#
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp1255 code (in hex)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 is the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in cp1255 order
|
||||
#
|
||||
0x00 0x0000 #NULL
|
||||
0x01 0x0001 #START OF HEADING
|
||||
0x02 0x0002 #START OF TEXT
|
||||
0x03 0x0003 #END OF TEXT
|
||||
0x04 0x0004 #END OF TRANSMISSION
|
||||
0x05 0x0005 #ENQUIRY
|
||||
0x06 0x0006 #ACKNOWLEDGE
|
||||
0x07 0x0007 #BELL
|
||||
0x08 0x0008 #BACKSPACE
|
||||
0x09 0x0009 #HORIZONTAL TABULATION
|
||||
0x0A 0x000A #LINE FEED
|
||||
0x0B 0x000B #VERTICAL TABULATION
|
||||
0x0C 0x000C #FORM FEED
|
||||
0x0D 0x000D #CARRIAGE RETURN
|
||||
0x0E 0x000E #SHIFT OUT
|
||||
0x0F 0x000F #SHIFT IN
|
||||
0x10 0x0010 #DATA LINK ESCAPE
|
||||
0x11 0x0011 #DEVICE CONTROL ONE
|
||||
0x12 0x0012 #DEVICE CONTROL TWO
|
||||
0x13 0x0013 #DEVICE CONTROL THREE
|
||||
0x14 0x0014 #DEVICE CONTROL FOUR
|
||||
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 #SYNCHRONOUS IDLE
|
||||
0x17 0x0017 #END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 #CANCEL
|
||||
0x19 0x0019 #END OF MEDIUM
|
||||
0x1A 0x001A #SUBSTITUTE
|
||||
0x1B 0x001B #ESCAPE
|
||||
0x1C 0x001C #FILE SEPARATOR
|
||||
0x1D 0x001D #GROUP SEPARATOR
|
||||
0x1E 0x001E #RECORD SEPARATOR
|
||||
0x1F 0x001F #UNIT SEPARATOR
|
||||
0x20 0x0020 #SPACE
|
||||
0x21 0x0021 #EXCLAMATION MARK
|
||||
0x22 0x0022 #QUOTATION MARK
|
||||
0x23 0x0023 #NUMBER SIGN
|
||||
0x24 0x0024 #DOLLAR SIGN
|
||||
0x25 0x0025 #PERCENT SIGN
|
||||
0x26 0x0026 #AMPERSAND
|
||||
0x27 0x0027 #APOSTROPHE
|
||||
0x28 0x0028 #LEFT PARENTHESIS
|
||||
0x29 0x0029 #RIGHT PARENTHESIS
|
||||
0x2A 0x002A #ASTERISK
|
||||
0x2B 0x002B #PLUS SIGN
|
||||
0x2C 0x002C #COMMA
|
||||
0x2D 0x002D #HYPHEN-MINUS
|
||||
0x2E 0x002E #FULL STOP
|
||||
0x2F 0x002F #SOLIDUS
|
||||
0x30 0x0030 #DIGIT ZERO
|
||||
0x31 0x0031 #DIGIT ONE
|
||||
0x32 0x0032 #DIGIT TWO
|
||||
0x33 0x0033 #DIGIT THREE
|
||||
0x34 0x0034 #DIGIT FOUR
|
||||
0x35 0x0035 #DIGIT FIVE
|
||||
0x36 0x0036 #DIGIT SIX
|
||||
0x37 0x0037 #DIGIT SEVEN
|
||||
0x38 0x0038 #DIGIT EIGHT
|
||||
0x39 0x0039 #DIGIT NINE
|
||||
0x3A 0x003A #COLON
|
||||
0x3B 0x003B #SEMICOLON
|
||||
0x3C 0x003C #LESS-THAN SIGN
|
||||
0x3D 0x003D #EQUALS SIGN
|
||||
0x3E 0x003E #GREATER-THAN SIGN
|
||||
0x3F 0x003F #QUESTION MARK
|
||||
0x40 0x0040 #COMMERCIAL AT
|
||||
0x41 0x0041 #LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 #LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 #LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 #LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 #LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 #LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 #LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 #LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 #LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A #LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B #LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C #LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D #LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E #LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F #LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 #LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 #LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 #LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 #LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 #LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 #LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 #LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 #LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A #LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B #LEFT SQUARE BRACKET
|
||||
0x5C 0x005C #REVERSE SOLIDUS
|
||||
0x5D 0x005D #RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E #CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F #LOW LINE
|
||||
0x60 0x0060 #GRAVE ACCENT
|
||||
0x61 0x0061 #LATIN SMALL LETTER A
|
||||
0x62 0x0062 #LATIN SMALL LETTER B
|
||||
0x63 0x0063 #LATIN SMALL LETTER C
|
||||
0x64 0x0064 #LATIN SMALL LETTER D
|
||||
0x65 0x0065 #LATIN SMALL LETTER E
|
||||
0x66 0x0066 #LATIN SMALL LETTER F
|
||||
0x67 0x0067 #LATIN SMALL LETTER G
|
||||
0x68 0x0068 #LATIN SMALL LETTER H
|
||||
0x69 0x0069 #LATIN SMALL LETTER I
|
||||
0x6A 0x006A #LATIN SMALL LETTER J
|
||||
0x6B 0x006B #LATIN SMALL LETTER K
|
||||
0x6C 0x006C #LATIN SMALL LETTER L
|
||||
0x6D 0x006D #LATIN SMALL LETTER M
|
||||
0x6E 0x006E #LATIN SMALL LETTER N
|
||||
0x6F 0x006F #LATIN SMALL LETTER O
|
||||
0x70 0x0070 #LATIN SMALL LETTER P
|
||||
0x71 0x0071 #LATIN SMALL LETTER Q
|
||||
0x72 0x0072 #LATIN SMALL LETTER R
|
||||
0x73 0x0073 #LATIN SMALL LETTER S
|
||||
0x74 0x0074 #LATIN SMALL LETTER T
|
||||
0x75 0x0075 #LATIN SMALL LETTER U
|
||||
0x76 0x0076 #LATIN SMALL LETTER V
|
||||
0x77 0x0077 #LATIN SMALL LETTER W
|
||||
0x78 0x0078 #LATIN SMALL LETTER X
|
||||
0x79 0x0079 #LATIN SMALL LETTER Y
|
||||
0x7A 0x007A #LATIN SMALL LETTER Z
|
||||
0x7B 0x007B #LEFT CURLY BRACKET
|
||||
0x7C 0x007C #VERTICAL LINE
|
||||
0x7D 0x007D #RIGHT CURLY BRACKET
|
||||
0x7E 0x007E #TILDE
|
||||
0x7F 0x007F #DELETE
|
||||
0x80 0x20AC #EURO SIGN
|
||||
0x81 #UNDEFINED
|
||||
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
|
||||
0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK
|
||||
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
|
||||
0x85 0x2026 #HORIZONTAL ELLIPSIS
|
||||
0x86 0x2020 #DAGGER
|
||||
0x87 0x2021 #DOUBLE DAGGER
|
||||
0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A #UNDEFINED
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C #UNDEFINED
|
||||
0x8D #UNDEFINED
|
||||
0x8E #UNDEFINED
|
||||
0x8F #UNDEFINED
|
||||
0x90 #UNDEFINED
|
||||
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
|
||||
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
|
||||
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
|
||||
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
|
||||
0x95 0x2022 #BULLET
|
||||
0x96 0x2013 #EN DASH
|
||||
0x97 0x2014 #EM DASH
|
||||
0x98 0x02DC #SMALL TILDE
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A #UNDEFINED
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C #UNDEFINED
|
||||
0x9D #UNDEFINED
|
||||
0x9E #UNDEFINED
|
||||
0x9F #UNDEFINED
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x00A1 #INVERTED EXCLAMATION MARK
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
0xA3 0x00A3 #POUND SIGN
|
||||
0xA4 0x20AA #NEW SHEQEL SIGN
|
||||
0xA5 0x00A5 #YEN SIGN
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x00A8 #DIAERESIS
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x00D7 #MULTIPLICATION SIGN
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x00AF #MACRON
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00B8 #CEDILLA
|
||||
0xB9 0x00B9 #SUPERSCRIPT ONE
|
||||
0xBA 0x00F7 #DIVISION SIGN
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00BF #INVERTED QUESTION MARK
|
||||
0xC0 0x05B0 #HEBREW POINT SHEVA
|
||||
0xC1 0x05B1 #HEBREW POINT HATAF SEGOL
|
||||
0xC2 0x05B2 #HEBREW POINT HATAF PATAH
|
||||
0xC3 0x05B3 #HEBREW POINT HATAF QAMATS
|
||||
0xC4 0x05B4 #HEBREW POINT HIRIQ
|
||||
0xC5 0x05B5 #HEBREW POINT TSERE
|
||||
0xC6 0x05B6 #HEBREW POINT SEGOL
|
||||
0xC7 0x05B7 #HEBREW POINT PATAH
|
||||
0xC8 0x05B8 #HEBREW POINT QAMATS
|
||||
0xC9 0x05B9 #HEBREW POINT HOLAM
|
||||
0xCA #UNDEFINED
|
||||
0xCB 0x05BB #HEBREW POINT QUBUTS
|
||||
0xCC 0x05BC #HEBREW POINT DAGESH OR MAPIQ
|
||||
0xCD 0x05BD #HEBREW POINT METEG
|
||||
0xCE 0x05BE #HEBREW PUNCTUATION MAQAF
|
||||
0xCF 0x05BF #HEBREW POINT RAFE
|
||||
0xD0 0x05C0 #HEBREW PUNCTUATION PASEQ
|
||||
0xD1 0x05C1 #HEBREW POINT SHIN DOT
|
||||
0xD2 0x05C2 #HEBREW POINT SIN DOT
|
||||
0xD3 0x05C3 #HEBREW PUNCTUATION SOF PASUQ
|
||||
0xD4 0x05F0 #HEBREW LIGATURE YIDDISH DOUBLE VAV
|
||||
0xD5 0x05F1 #HEBREW LIGATURE YIDDISH VAV YOD
|
||||
0xD6 0x05F2 #HEBREW LIGATURE YIDDISH DOUBLE YOD
|
||||
0xD7 0x05F3 #HEBREW PUNCTUATION GERESH
|
||||
0xD8 0x05F4 #HEBREW PUNCTUATION GERSHAYIM
|
||||
0xD9 #UNDEFINED
|
||||
0xDA #UNDEFINED
|
||||
0xDB #UNDEFINED
|
||||
0xDC #UNDEFINED
|
||||
0xDD #UNDEFINED
|
||||
0xDE #UNDEFINED
|
||||
0xDF #UNDEFINED
|
||||
0xE0 0x05D0 #HEBREW LETTER ALEF
|
||||
0xE1 0x05D1 #HEBREW LETTER BET
|
||||
0xE2 0x05D2 #HEBREW LETTER GIMEL
|
||||
0xE3 0x05D3 #HEBREW LETTER DALET
|
||||
0xE4 0x05D4 #HEBREW LETTER HE
|
||||
0xE5 0x05D5 #HEBREW LETTER VAV
|
||||
0xE6 0x05D6 #HEBREW LETTER ZAYIN
|
||||
0xE7 0x05D7 #HEBREW LETTER HET
|
||||
0xE8 0x05D8 #HEBREW LETTER TET
|
||||
0xE9 0x05D9 #HEBREW LETTER YOD
|
||||
0xEA 0x05DA #HEBREW LETTER FINAL KAF
|
||||
0xEB 0x05DB #HEBREW LETTER KAF
|
||||
0xEC 0x05DC #HEBREW LETTER LAMED
|
||||
0xED 0x05DD #HEBREW LETTER FINAL MEM
|
||||
0xEE 0x05DE #HEBREW LETTER MEM
|
||||
0xEF 0x05DF #HEBREW LETTER FINAL NUN
|
||||
0xF0 0x05E0 #HEBREW LETTER NUN
|
||||
0xF1 0x05E1 #HEBREW LETTER SAMEKH
|
||||
0xF2 0x05E2 #HEBREW LETTER AYIN
|
||||
0xF3 0x05E3 #HEBREW LETTER FINAL PE
|
||||
0xF4 0x05E4 #HEBREW LETTER PE
|
||||
0xF5 0x05E5 #HEBREW LETTER FINAL TSADI
|
||||
0xF6 0x05E6 #HEBREW LETTER TSADI
|
||||
0xF7 0x05E7 #HEBREW LETTER QOF
|
||||
0xF8 0x05E8 #HEBREW LETTER RESH
|
||||
0xF9 0x05E9 #HEBREW LETTER SHIN
|
||||
0xFA 0x05EA #HEBREW LETTER TAV
|
||||
0xFB #UNDEFINED
|
||||
0xFC #UNDEFINED
|
||||
0xFD 0x200E #LEFT-TO-RIGHT MARK
|
||||
0xFE 0x200F #RIGHT-TO-LEFT MARK
|
||||
0xFF #UNDEFINED
|
||||
@@ -0,0 +1,274 @@
|
||||
#
|
||||
# Name: cp1256 to Unicode table
|
||||
# Unicode version: 2.1
|
||||
# Table version: 2.01
|
||||
# Table format: Format A
|
||||
# Date: 01/5/99
|
||||
#
|
||||
# Contact: cpxlate@microsoft.com
|
||||
#
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp1256 code (in hex)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 is the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in cp1256 order
|
||||
#
|
||||
0x00 0x0000 #NULL
|
||||
0x01 0x0001 #START OF HEADING
|
||||
0x02 0x0002 #START OF TEXT
|
||||
0x03 0x0003 #END OF TEXT
|
||||
0x04 0x0004 #END OF TRANSMISSION
|
||||
0x05 0x0005 #ENQUIRY
|
||||
0x06 0x0006 #ACKNOWLEDGE
|
||||
0x07 0x0007 #BELL
|
||||
0x08 0x0008 #BACKSPACE
|
||||
0x09 0x0009 #HORIZONTAL TABULATION
|
||||
0x0A 0x000A #LINE FEED
|
||||
0x0B 0x000B #VERTICAL TABULATION
|
||||
0x0C 0x000C #FORM FEED
|
||||
0x0D 0x000D #CARRIAGE RETURN
|
||||
0x0E 0x000E #SHIFT OUT
|
||||
0x0F 0x000F #SHIFT IN
|
||||
0x10 0x0010 #DATA LINK ESCAPE
|
||||
0x11 0x0011 #DEVICE CONTROL ONE
|
||||
0x12 0x0012 #DEVICE CONTROL TWO
|
||||
0x13 0x0013 #DEVICE CONTROL THREE
|
||||
0x14 0x0014 #DEVICE CONTROL FOUR
|
||||
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 #SYNCHRONOUS IDLE
|
||||
0x17 0x0017 #END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 #CANCEL
|
||||
0x19 0x0019 #END OF MEDIUM
|
||||
0x1A 0x001A #SUBSTITUTE
|
||||
0x1B 0x001B #ESCAPE
|
||||
0x1C 0x001C #FILE SEPARATOR
|
||||
0x1D 0x001D #GROUP SEPARATOR
|
||||
0x1E 0x001E #RECORD SEPARATOR
|
||||
0x1F 0x001F #UNIT SEPARATOR
|
||||
0x20 0x0020 #SPACE
|
||||
0x21 0x0021 #EXCLAMATION MARK
|
||||
0x22 0x0022 #QUOTATION MARK
|
||||
0x23 0x0023 #NUMBER SIGN
|
||||
0x24 0x0024 #DOLLAR SIGN
|
||||
0x25 0x0025 #PERCENT SIGN
|
||||
0x26 0x0026 #AMPERSAND
|
||||
0x27 0x0027 #APOSTROPHE
|
||||
0x28 0x0028 #LEFT PARENTHESIS
|
||||
0x29 0x0029 #RIGHT PARENTHESIS
|
||||
0x2A 0x002A #ASTERISK
|
||||
0x2B 0x002B #PLUS SIGN
|
||||
0x2C 0x002C #COMMA
|
||||
0x2D 0x002D #HYPHEN-MINUS
|
||||
0x2E 0x002E #FULL STOP
|
||||
0x2F 0x002F #SOLIDUS
|
||||
0x30 0x0030 #DIGIT ZERO
|
||||
0x31 0x0031 #DIGIT ONE
|
||||
0x32 0x0032 #DIGIT TWO
|
||||
0x33 0x0033 #DIGIT THREE
|
||||
0x34 0x0034 #DIGIT FOUR
|
||||
0x35 0x0035 #DIGIT FIVE
|
||||
0x36 0x0036 #DIGIT SIX
|
||||
0x37 0x0037 #DIGIT SEVEN
|
||||
0x38 0x0038 #DIGIT EIGHT
|
||||
0x39 0x0039 #DIGIT NINE
|
||||
0x3A 0x003A #COLON
|
||||
0x3B 0x003B #SEMICOLON
|
||||
0x3C 0x003C #LESS-THAN SIGN
|
||||
0x3D 0x003D #EQUALS SIGN
|
||||
0x3E 0x003E #GREATER-THAN SIGN
|
||||
0x3F 0x003F #QUESTION MARK
|
||||
0x40 0x0040 #COMMERCIAL AT
|
||||
0x41 0x0041 #LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 #LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 #LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 #LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 #LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 #LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 #LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 #LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 #LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A #LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B #LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C #LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D #LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E #LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F #LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 #LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 #LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 #LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 #LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 #LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 #LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 #LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 #LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A #LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B #LEFT SQUARE BRACKET
|
||||
0x5C 0x005C #REVERSE SOLIDUS
|
||||
0x5D 0x005D #RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E #CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F #LOW LINE
|
||||
0x60 0x0060 #GRAVE ACCENT
|
||||
0x61 0x0061 #LATIN SMALL LETTER A
|
||||
0x62 0x0062 #LATIN SMALL LETTER B
|
||||
0x63 0x0063 #LATIN SMALL LETTER C
|
||||
0x64 0x0064 #LATIN SMALL LETTER D
|
||||
0x65 0x0065 #LATIN SMALL LETTER E
|
||||
0x66 0x0066 #LATIN SMALL LETTER F
|
||||
0x67 0x0067 #LATIN SMALL LETTER G
|
||||
0x68 0x0068 #LATIN SMALL LETTER H
|
||||
0x69 0x0069 #LATIN SMALL LETTER I
|
||||
0x6A 0x006A #LATIN SMALL LETTER J
|
||||
0x6B 0x006B #LATIN SMALL LETTER K
|
||||
0x6C 0x006C #LATIN SMALL LETTER L
|
||||
0x6D 0x006D #LATIN SMALL LETTER M
|
||||
0x6E 0x006E #LATIN SMALL LETTER N
|
||||
0x6F 0x006F #LATIN SMALL LETTER O
|
||||
0x70 0x0070 #LATIN SMALL LETTER P
|
||||
0x71 0x0071 #LATIN SMALL LETTER Q
|
||||
0x72 0x0072 #LATIN SMALL LETTER R
|
||||
0x73 0x0073 #LATIN SMALL LETTER S
|
||||
0x74 0x0074 #LATIN SMALL LETTER T
|
||||
0x75 0x0075 #LATIN SMALL LETTER U
|
||||
0x76 0x0076 #LATIN SMALL LETTER V
|
||||
0x77 0x0077 #LATIN SMALL LETTER W
|
||||
0x78 0x0078 #LATIN SMALL LETTER X
|
||||
0x79 0x0079 #LATIN SMALL LETTER Y
|
||||
0x7A 0x007A #LATIN SMALL LETTER Z
|
||||
0x7B 0x007B #LEFT CURLY BRACKET
|
||||
0x7C 0x007C #VERTICAL LINE
|
||||
0x7D 0x007D #RIGHT CURLY BRACKET
|
||||
0x7E 0x007E #TILDE
|
||||
0x7F 0x007F #DELETE
|
||||
0x80 0x20AC #EURO SIGN
|
||||
0x81 0x067E #ARABIC LETTER PEH
|
||||
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
|
||||
0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK
|
||||
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
|
||||
0x85 0x2026 #HORIZONTAL ELLIPSIS
|
||||
0x86 0x2020 #DAGGER
|
||||
0x87 0x2021 #DOUBLE DAGGER
|
||||
0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A 0x0679 #ARABIC LETTER TTEH
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C 0x0152 #LATIN CAPITAL LIGATURE OE
|
||||
0x8D 0x0686 #ARABIC LETTER TCHEH
|
||||
0x8E 0x0698 #ARABIC LETTER JEH
|
||||
0x8F 0x0688 #ARABIC LETTER DDAL
|
||||
0x90 0x06AF #ARABIC LETTER GAF
|
||||
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
|
||||
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
|
||||
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
|
||||
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
|
||||
0x95 0x2022 #BULLET
|
||||
0x96 0x2013 #EN DASH
|
||||
0x97 0x2014 #EM DASH
|
||||
0x98 0x06A9 #ARABIC LETTER KEHEH
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A 0x0691 #ARABIC LETTER RREH
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C 0x0153 #LATIN SMALL LIGATURE OE
|
||||
0x9D 0x200C #ZERO WIDTH NON-JOINER
|
||||
0x9E 0x200D #ZERO WIDTH JOINER
|
||||
0x9F 0x06BA #ARABIC LETTER NOON GHUNNA
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x060C #ARABIC COMMA
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
0xA3 0x00A3 #POUND SIGN
|
||||
0xA4 0x00A4 #CURRENCY SIGN
|
||||
0xA5 0x00A5 #YEN SIGN
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x00A8 #DIAERESIS
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x06BE #ARABIC LETTER HEH DOACHASHMEE
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x00AF #MACRON
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00B8 #CEDILLA
|
||||
0xB9 0x00B9 #SUPERSCRIPT ONE
|
||||
0xBA 0x061B #ARABIC SEMICOLON
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x061F #ARABIC QUESTION MARK
|
||||
0xC0 0x06C1 #ARABIC LETTER HEH GOAL
|
||||
0xC1 0x0621 #ARABIC LETTER HAMZA
|
||||
0xC2 0x0622 #ARABIC LETTER ALEF WITH MADDA ABOVE
|
||||
0xC3 0x0623 #ARABIC LETTER ALEF WITH HAMZA ABOVE
|
||||
0xC4 0x0624 #ARABIC LETTER WAW WITH HAMZA ABOVE
|
||||
0xC5 0x0625 #ARABIC LETTER ALEF WITH HAMZA BELOW
|
||||
0xC6 0x0626 #ARABIC LETTER YEH WITH HAMZA ABOVE
|
||||
0xC7 0x0627 #ARABIC LETTER ALEF
|
||||
0xC8 0x0628 #ARABIC LETTER BEH
|
||||
0xC9 0x0629 #ARABIC LETTER TEH MARBUTA
|
||||
0xCA 0x062A #ARABIC LETTER TEH
|
||||
0xCB 0x062B #ARABIC LETTER THEH
|
||||
0xCC 0x062C #ARABIC LETTER JEEM
|
||||
0xCD 0x062D #ARABIC LETTER HAH
|
||||
0xCE 0x062E #ARABIC LETTER KHAH
|
||||
0xCF 0x062F #ARABIC LETTER DAL
|
||||
0xD0 0x0630 #ARABIC LETTER THAL
|
||||
0xD1 0x0631 #ARABIC LETTER REH
|
||||
0xD2 0x0632 #ARABIC LETTER ZAIN
|
||||
0xD3 0x0633 #ARABIC LETTER SEEN
|
||||
0xD4 0x0634 #ARABIC LETTER SHEEN
|
||||
0xD5 0x0635 #ARABIC LETTER SAD
|
||||
0xD6 0x0636 #ARABIC LETTER DAD
|
||||
0xD7 0x00D7 #MULTIPLICATION SIGN
|
||||
0xD8 0x0637 #ARABIC LETTER TAH
|
||||
0xD9 0x0638 #ARABIC LETTER ZAH
|
||||
0xDA 0x0639 #ARABIC LETTER AIN
|
||||
0xDB 0x063A #ARABIC LETTER GHAIN
|
||||
0xDC 0x0640 #ARABIC TATWEEL
|
||||
0xDD 0x0641 #ARABIC LETTER FEH
|
||||
0xDE 0x0642 #ARABIC LETTER QAF
|
||||
0xDF 0x0643 #ARABIC LETTER KAF
|
||||
0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x0644 #ARABIC LETTER LAM
|
||||
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x0645 #ARABIC LETTER MEEM
|
||||
0xE4 0x0646 #ARABIC LETTER NOON
|
||||
0xE5 0x0647 #ARABIC LETTER HEH
|
||||
0xE6 0x0648 #ARABIC LETTER WAW
|
||||
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x0649 #ARABIC LETTER ALEF MAKSURA
|
||||
0xED 0x064A #ARABIC LETTER YEH
|
||||
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x064B #ARABIC FATHATAN
|
||||
0xF1 0x064C #ARABIC DAMMATAN
|
||||
0xF2 0x064D #ARABIC KASRATAN
|
||||
0xF3 0x064E #ARABIC FATHA
|
||||
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x064F #ARABIC DAMMA
|
||||
0xF6 0x0650 #ARABIC KASRA
|
||||
0xF7 0x00F7 #DIVISION SIGN
|
||||
0xF8 0x0651 #ARABIC SHADDA
|
||||
0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x0652 #ARABIC SUKUN
|
||||
0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x200E #LEFT-TO-RIGHT MARK
|
||||
0xFE 0x200F #RIGHT-TO-LEFT MARK
|
||||
0xFF 0x06D2 #ARABIC LETTER YEH BARREE
|
||||
@@ -0,0 +1,274 @@
|
||||
#
|
||||
# Name: cp1257 to Unicode table
|
||||
# Unicode version: 2.0
|
||||
# Table version: 2.01
|
||||
# Table format: Format A
|
||||
# Date: 04/15/98
|
||||
#
|
||||
# Contact: cpxlate@microsoft.com
|
||||
#
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp1257 code (in hex)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 is the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in cp1257 order
|
||||
#
|
||||
0x00 0x0000 #NULL
|
||||
0x01 0x0001 #START OF HEADING
|
||||
0x02 0x0002 #START OF TEXT
|
||||
0x03 0x0003 #END OF TEXT
|
||||
0x04 0x0004 #END OF TRANSMISSION
|
||||
0x05 0x0005 #ENQUIRY
|
||||
0x06 0x0006 #ACKNOWLEDGE
|
||||
0x07 0x0007 #BELL
|
||||
0x08 0x0008 #BACKSPACE
|
||||
0x09 0x0009 #HORIZONTAL TABULATION
|
||||
0x0A 0x000A #LINE FEED
|
||||
0x0B 0x000B #VERTICAL TABULATION
|
||||
0x0C 0x000C #FORM FEED
|
||||
0x0D 0x000D #CARRIAGE RETURN
|
||||
0x0E 0x000E #SHIFT OUT
|
||||
0x0F 0x000F #SHIFT IN
|
||||
0x10 0x0010 #DATA LINK ESCAPE
|
||||
0x11 0x0011 #DEVICE CONTROL ONE
|
||||
0x12 0x0012 #DEVICE CONTROL TWO
|
||||
0x13 0x0013 #DEVICE CONTROL THREE
|
||||
0x14 0x0014 #DEVICE CONTROL FOUR
|
||||
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 #SYNCHRONOUS IDLE
|
||||
0x17 0x0017 #END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 #CANCEL
|
||||
0x19 0x0019 #END OF MEDIUM
|
||||
0x1A 0x001A #SUBSTITUTE
|
||||
0x1B 0x001B #ESCAPE
|
||||
0x1C 0x001C #FILE SEPARATOR
|
||||
0x1D 0x001D #GROUP SEPARATOR
|
||||
0x1E 0x001E #RECORD SEPARATOR
|
||||
0x1F 0x001F #UNIT SEPARATOR
|
||||
0x20 0x0020 #SPACE
|
||||
0x21 0x0021 #EXCLAMATION MARK
|
||||
0x22 0x0022 #QUOTATION MARK
|
||||
0x23 0x0023 #NUMBER SIGN
|
||||
0x24 0x0024 #DOLLAR SIGN
|
||||
0x25 0x0025 #PERCENT SIGN
|
||||
0x26 0x0026 #AMPERSAND
|
||||
0x27 0x0027 #APOSTROPHE
|
||||
0x28 0x0028 #LEFT PARENTHESIS
|
||||
0x29 0x0029 #RIGHT PARENTHESIS
|
||||
0x2A 0x002A #ASTERISK
|
||||
0x2B 0x002B #PLUS SIGN
|
||||
0x2C 0x002C #COMMA
|
||||
0x2D 0x002D #HYPHEN-MINUS
|
||||
0x2E 0x002E #FULL STOP
|
||||
0x2F 0x002F #SOLIDUS
|
||||
0x30 0x0030 #DIGIT ZERO
|
||||
0x31 0x0031 #DIGIT ONE
|
||||
0x32 0x0032 #DIGIT TWO
|
||||
0x33 0x0033 #DIGIT THREE
|
||||
0x34 0x0034 #DIGIT FOUR
|
||||
0x35 0x0035 #DIGIT FIVE
|
||||
0x36 0x0036 #DIGIT SIX
|
||||
0x37 0x0037 #DIGIT SEVEN
|
||||
0x38 0x0038 #DIGIT EIGHT
|
||||
0x39 0x0039 #DIGIT NINE
|
||||
0x3A 0x003A #COLON
|
||||
0x3B 0x003B #SEMICOLON
|
||||
0x3C 0x003C #LESS-THAN SIGN
|
||||
0x3D 0x003D #EQUALS SIGN
|
||||
0x3E 0x003E #GREATER-THAN SIGN
|
||||
0x3F 0x003F #QUESTION MARK
|
||||
0x40 0x0040 #COMMERCIAL AT
|
||||
0x41 0x0041 #LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 #LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 #LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 #LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 #LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 #LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 #LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 #LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 #LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A #LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B #LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C #LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D #LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E #LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F #LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 #LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 #LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 #LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 #LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 #LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 #LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 #LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 #LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A #LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B #LEFT SQUARE BRACKET
|
||||
0x5C 0x005C #REVERSE SOLIDUS
|
||||
0x5D 0x005D #RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E #CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F #LOW LINE
|
||||
0x60 0x0060 #GRAVE ACCENT
|
||||
0x61 0x0061 #LATIN SMALL LETTER A
|
||||
0x62 0x0062 #LATIN SMALL LETTER B
|
||||
0x63 0x0063 #LATIN SMALL LETTER C
|
||||
0x64 0x0064 #LATIN SMALL LETTER D
|
||||
0x65 0x0065 #LATIN SMALL LETTER E
|
||||
0x66 0x0066 #LATIN SMALL LETTER F
|
||||
0x67 0x0067 #LATIN SMALL LETTER G
|
||||
0x68 0x0068 #LATIN SMALL LETTER H
|
||||
0x69 0x0069 #LATIN SMALL LETTER I
|
||||
0x6A 0x006A #LATIN SMALL LETTER J
|
||||
0x6B 0x006B #LATIN SMALL LETTER K
|
||||
0x6C 0x006C #LATIN SMALL LETTER L
|
||||
0x6D 0x006D #LATIN SMALL LETTER M
|
||||
0x6E 0x006E #LATIN SMALL LETTER N
|
||||
0x6F 0x006F #LATIN SMALL LETTER O
|
||||
0x70 0x0070 #LATIN SMALL LETTER P
|
||||
0x71 0x0071 #LATIN SMALL LETTER Q
|
||||
0x72 0x0072 #LATIN SMALL LETTER R
|
||||
0x73 0x0073 #LATIN SMALL LETTER S
|
||||
0x74 0x0074 #LATIN SMALL LETTER T
|
||||
0x75 0x0075 #LATIN SMALL LETTER U
|
||||
0x76 0x0076 #LATIN SMALL LETTER V
|
||||
0x77 0x0077 #LATIN SMALL LETTER W
|
||||
0x78 0x0078 #LATIN SMALL LETTER X
|
||||
0x79 0x0079 #LATIN SMALL LETTER Y
|
||||
0x7A 0x007A #LATIN SMALL LETTER Z
|
||||
0x7B 0x007B #LEFT CURLY BRACKET
|
||||
0x7C 0x007C #VERTICAL LINE
|
||||
0x7D 0x007D #RIGHT CURLY BRACKET
|
||||
0x7E 0x007E #TILDE
|
||||
0x7F 0x007F #DELETE
|
||||
0x80 0x20AC #EURO SIGN
|
||||
0x81 #UNDEFINED
|
||||
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
|
||||
0x83 #UNDEFINED
|
||||
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
|
||||
0x85 0x2026 #HORIZONTAL ELLIPSIS
|
||||
0x86 0x2020 #DAGGER
|
||||
0x87 0x2021 #DOUBLE DAGGER
|
||||
0x88 #UNDEFINED
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A #UNDEFINED
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C #UNDEFINED
|
||||
0x8D 0x00A8 #DIAERESIS
|
||||
0x8E 0x02C7 #CARON
|
||||
0x8F 0x00B8 #CEDILLA
|
||||
0x90 #UNDEFINED
|
||||
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
|
||||
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
|
||||
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
|
||||
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
|
||||
0x95 0x2022 #BULLET
|
||||
0x96 0x2013 #EN DASH
|
||||
0x97 0x2014 #EM DASH
|
||||
0x98 #UNDEFINED
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A #UNDEFINED
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C #UNDEFINED
|
||||
0x9D 0x00AF #MACRON
|
||||
0x9E 0x02DB #OGONEK
|
||||
0x9F #UNDEFINED
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 #UNDEFINED
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
0xA3 0x00A3 #POUND SIGN
|
||||
0xA4 0x00A4 #CURRENCY SIGN
|
||||
0xA5 #UNDEFINED
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x0156 #LATIN CAPITAL LETTER R WITH CEDILLA
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x00C6 #LATIN CAPITAL LETTER AE
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00F8 #LATIN SMALL LETTER O WITH STROKE
|
||||
0xB9 0x00B9 #SUPERSCRIPT ONE
|
||||
0xBA 0x0157 #LATIN SMALL LETTER R WITH CEDILLA
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00E6 #LATIN SMALL LETTER AE
|
||||
0xC0 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0xC1 0x012E #LATIN CAPITAL LETTER I WITH OGONEK
|
||||
0xC2 0x0100 #LATIN CAPITAL LETTER A WITH MACRON
|
||||
0xC3 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE
|
||||
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0xC7 0x0112 #LATIN CAPITAL LETTER E WITH MACRON
|
||||
0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON
|
||||
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
0xCB 0x0116 #LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
0xCC 0x0122 #LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
0xCD 0x0136 #LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
0xCE 0x012A #LATIN CAPITAL LETTER I WITH MACRON
|
||||
0xCF 0x013B #LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
0xD0 0x0160 #LATIN CAPITAL LETTER S WITH CARON
|
||||
0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE
|
||||
0xD2 0x0145 #LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x014C #LATIN CAPITAL LETTER O WITH MACRON
|
||||
0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 #MULTIPLICATION SIGN
|
||||
0xD8 0x0172 #LATIN CAPITAL LETTER U WITH OGONEK
|
||||
0xD9 0x0141 #LATIN CAPITAL LETTER L WITH STROKE
|
||||
0xDA 0x015A #LATIN CAPITAL LETTER S WITH ACUTE
|
||||
0xDB 0x016A #LATIN CAPITAL LETTER U WITH MACRON
|
||||
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
0xDE 0x017D #LATIN CAPITAL LETTER Z WITH CARON
|
||||
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x0105 #LATIN SMALL LETTER A WITH OGONEK
|
||||
0xE1 0x012F #LATIN SMALL LETTER I WITH OGONEK
|
||||
0xE2 0x0101 #LATIN SMALL LETTER A WITH MACRON
|
||||
0xE3 0x0107 #LATIN SMALL LETTER C WITH ACUTE
|
||||
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x0119 #LATIN SMALL LETTER E WITH OGONEK
|
||||
0xE7 0x0113 #LATIN SMALL LETTER E WITH MACRON
|
||||
0xE8 0x010D #LATIN SMALL LETTER C WITH CARON
|
||||
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x017A #LATIN SMALL LETTER Z WITH ACUTE
|
||||
0xEB 0x0117 #LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
0xEC 0x0123 #LATIN SMALL LETTER G WITH CEDILLA
|
||||
0xED 0x0137 #LATIN SMALL LETTER K WITH CEDILLA
|
||||
0xEE 0x012B #LATIN SMALL LETTER I WITH MACRON
|
||||
0xEF 0x013C #LATIN SMALL LETTER L WITH CEDILLA
|
||||
0xF0 0x0161 #LATIN SMALL LETTER S WITH CARON
|
||||
0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE
|
||||
0xF2 0x0146 #LATIN SMALL LETTER N WITH CEDILLA
|
||||
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x014D #LATIN SMALL LETTER O WITH MACRON
|
||||
0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 #DIVISION SIGN
|
||||
0xF8 0x0173 #LATIN SMALL LETTER U WITH OGONEK
|
||||
0xF9 0x0142 #LATIN SMALL LETTER L WITH STROKE
|
||||
0xFA 0x015B #LATIN SMALL LETTER S WITH ACUTE
|
||||
0xFB 0x016B #LATIN SMALL LETTER U WITH MACRON
|
||||
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
0xFE 0x017E #LATIN SMALL LETTER Z WITH CARON
|
||||
0xFF 0x02D9 #DOT ABOVE
|
||||
@@ -0,0 +1,274 @@
|
||||
#
|
||||
# Name: cp1258 to Unicode table
|
||||
# Unicode version: 2.0
|
||||
# Table version: 2.01
|
||||
# Table format: Format A
|
||||
# Date: 04/15/98
|
||||
#
|
||||
# Contact: cpxlate@microsoft.com
|
||||
#
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp1258 code (in hex)
|
||||
# Column #2 is the Unicode (in hex as 0xXXXX)
|
||||
# Column #3 is the Unicode name (follows a comment sign, '#')
|
||||
#
|
||||
# The entries are in cp1258 order
|
||||
#
|
||||
0x00 0x0000 #NULL
|
||||
0x01 0x0001 #START OF HEADING
|
||||
0x02 0x0002 #START OF TEXT
|
||||
0x03 0x0003 #END OF TEXT
|
||||
0x04 0x0004 #END OF TRANSMISSION
|
||||
0x05 0x0005 #ENQUIRY
|
||||
0x06 0x0006 #ACKNOWLEDGE
|
||||
0x07 0x0007 #BELL
|
||||
0x08 0x0008 #BACKSPACE
|
||||
0x09 0x0009 #HORIZONTAL TABULATION
|
||||
0x0A 0x000A #LINE FEED
|
||||
0x0B 0x000B #VERTICAL TABULATION
|
||||
0x0C 0x000C #FORM FEED
|
||||
0x0D 0x000D #CARRIAGE RETURN
|
||||
0x0E 0x000E #SHIFT OUT
|
||||
0x0F 0x000F #SHIFT IN
|
||||
0x10 0x0010 #DATA LINK ESCAPE
|
||||
0x11 0x0011 #DEVICE CONTROL ONE
|
||||
0x12 0x0012 #DEVICE CONTROL TWO
|
||||
0x13 0x0013 #DEVICE CONTROL THREE
|
||||
0x14 0x0014 #DEVICE CONTROL FOUR
|
||||
0x15 0x0015 #NEGATIVE ACKNOWLEDGE
|
||||
0x16 0x0016 #SYNCHRONOUS IDLE
|
||||
0x17 0x0017 #END OF TRANSMISSION BLOCK
|
||||
0x18 0x0018 #CANCEL
|
||||
0x19 0x0019 #END OF MEDIUM
|
||||
0x1A 0x001A #SUBSTITUTE
|
||||
0x1B 0x001B #ESCAPE
|
||||
0x1C 0x001C #FILE SEPARATOR
|
||||
0x1D 0x001D #GROUP SEPARATOR
|
||||
0x1E 0x001E #RECORD SEPARATOR
|
||||
0x1F 0x001F #UNIT SEPARATOR
|
||||
0x20 0x0020 #SPACE
|
||||
0x21 0x0021 #EXCLAMATION MARK
|
||||
0x22 0x0022 #QUOTATION MARK
|
||||
0x23 0x0023 #NUMBER SIGN
|
||||
0x24 0x0024 #DOLLAR SIGN
|
||||
0x25 0x0025 #PERCENT SIGN
|
||||
0x26 0x0026 #AMPERSAND
|
||||
0x27 0x0027 #APOSTROPHE
|
||||
0x28 0x0028 #LEFT PARENTHESIS
|
||||
0x29 0x0029 #RIGHT PARENTHESIS
|
||||
0x2A 0x002A #ASTERISK
|
||||
0x2B 0x002B #PLUS SIGN
|
||||
0x2C 0x002C #COMMA
|
||||
0x2D 0x002D #HYPHEN-MINUS
|
||||
0x2E 0x002E #FULL STOP
|
||||
0x2F 0x002F #SOLIDUS
|
||||
0x30 0x0030 #DIGIT ZERO
|
||||
0x31 0x0031 #DIGIT ONE
|
||||
0x32 0x0032 #DIGIT TWO
|
||||
0x33 0x0033 #DIGIT THREE
|
||||
0x34 0x0034 #DIGIT FOUR
|
||||
0x35 0x0035 #DIGIT FIVE
|
||||
0x36 0x0036 #DIGIT SIX
|
||||
0x37 0x0037 #DIGIT SEVEN
|
||||
0x38 0x0038 #DIGIT EIGHT
|
||||
0x39 0x0039 #DIGIT NINE
|
||||
0x3A 0x003A #COLON
|
||||
0x3B 0x003B #SEMICOLON
|
||||
0x3C 0x003C #LESS-THAN SIGN
|
||||
0x3D 0x003D #EQUALS SIGN
|
||||
0x3E 0x003E #GREATER-THAN SIGN
|
||||
0x3F 0x003F #QUESTION MARK
|
||||
0x40 0x0040 #COMMERCIAL AT
|
||||
0x41 0x0041 #LATIN CAPITAL LETTER A
|
||||
0x42 0x0042 #LATIN CAPITAL LETTER B
|
||||
0x43 0x0043 #LATIN CAPITAL LETTER C
|
||||
0x44 0x0044 #LATIN CAPITAL LETTER D
|
||||
0x45 0x0045 #LATIN CAPITAL LETTER E
|
||||
0x46 0x0046 #LATIN CAPITAL LETTER F
|
||||
0x47 0x0047 #LATIN CAPITAL LETTER G
|
||||
0x48 0x0048 #LATIN CAPITAL LETTER H
|
||||
0x49 0x0049 #LATIN CAPITAL LETTER I
|
||||
0x4A 0x004A #LATIN CAPITAL LETTER J
|
||||
0x4B 0x004B #LATIN CAPITAL LETTER K
|
||||
0x4C 0x004C #LATIN CAPITAL LETTER L
|
||||
0x4D 0x004D #LATIN CAPITAL LETTER M
|
||||
0x4E 0x004E #LATIN CAPITAL LETTER N
|
||||
0x4F 0x004F #LATIN CAPITAL LETTER O
|
||||
0x50 0x0050 #LATIN CAPITAL LETTER P
|
||||
0x51 0x0051 #LATIN CAPITAL LETTER Q
|
||||
0x52 0x0052 #LATIN CAPITAL LETTER R
|
||||
0x53 0x0053 #LATIN CAPITAL LETTER S
|
||||
0x54 0x0054 #LATIN CAPITAL LETTER T
|
||||
0x55 0x0055 #LATIN CAPITAL LETTER U
|
||||
0x56 0x0056 #LATIN CAPITAL LETTER V
|
||||
0x57 0x0057 #LATIN CAPITAL LETTER W
|
||||
0x58 0x0058 #LATIN CAPITAL LETTER X
|
||||
0x59 0x0059 #LATIN CAPITAL LETTER Y
|
||||
0x5A 0x005A #LATIN CAPITAL LETTER Z
|
||||
0x5B 0x005B #LEFT SQUARE BRACKET
|
||||
0x5C 0x005C #REVERSE SOLIDUS
|
||||
0x5D 0x005D #RIGHT SQUARE BRACKET
|
||||
0x5E 0x005E #CIRCUMFLEX ACCENT
|
||||
0x5F 0x005F #LOW LINE
|
||||
0x60 0x0060 #GRAVE ACCENT
|
||||
0x61 0x0061 #LATIN SMALL LETTER A
|
||||
0x62 0x0062 #LATIN SMALL LETTER B
|
||||
0x63 0x0063 #LATIN SMALL LETTER C
|
||||
0x64 0x0064 #LATIN SMALL LETTER D
|
||||
0x65 0x0065 #LATIN SMALL LETTER E
|
||||
0x66 0x0066 #LATIN SMALL LETTER F
|
||||
0x67 0x0067 #LATIN SMALL LETTER G
|
||||
0x68 0x0068 #LATIN SMALL LETTER H
|
||||
0x69 0x0069 #LATIN SMALL LETTER I
|
||||
0x6A 0x006A #LATIN SMALL LETTER J
|
||||
0x6B 0x006B #LATIN SMALL LETTER K
|
||||
0x6C 0x006C #LATIN SMALL LETTER L
|
||||
0x6D 0x006D #LATIN SMALL LETTER M
|
||||
0x6E 0x006E #LATIN SMALL LETTER N
|
||||
0x6F 0x006F #LATIN SMALL LETTER O
|
||||
0x70 0x0070 #LATIN SMALL LETTER P
|
||||
0x71 0x0071 #LATIN SMALL LETTER Q
|
||||
0x72 0x0072 #LATIN SMALL LETTER R
|
||||
0x73 0x0073 #LATIN SMALL LETTER S
|
||||
0x74 0x0074 #LATIN SMALL LETTER T
|
||||
0x75 0x0075 #LATIN SMALL LETTER U
|
||||
0x76 0x0076 #LATIN SMALL LETTER V
|
||||
0x77 0x0077 #LATIN SMALL LETTER W
|
||||
0x78 0x0078 #LATIN SMALL LETTER X
|
||||
0x79 0x0079 #LATIN SMALL LETTER Y
|
||||
0x7A 0x007A #LATIN SMALL LETTER Z
|
||||
0x7B 0x007B #LEFT CURLY BRACKET
|
||||
0x7C 0x007C #VERTICAL LINE
|
||||
0x7D 0x007D #RIGHT CURLY BRACKET
|
||||
0x7E 0x007E #TILDE
|
||||
0x7F 0x007F #DELETE
|
||||
0x80 0x20AC #EURO SIGN
|
||||
0x81 #UNDEFINED
|
||||
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
|
||||
0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK
|
||||
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
|
||||
0x85 0x2026 #HORIZONTAL ELLIPSIS
|
||||
0x86 0x2020 #DAGGER
|
||||
0x87 0x2021 #DOUBLE DAGGER
|
||||
0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A #UNDEFINED
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C 0x0152 #LATIN CAPITAL LIGATURE OE
|
||||
0x8D #UNDEFINED
|
||||
0x8E #UNDEFINED
|
||||
0x8F #UNDEFINED
|
||||
0x90 #UNDEFINED
|
||||
0x91 0x2018 #LEFT SINGLE QUOTATION MARK
|
||||
0x92 0x2019 #RIGHT SINGLE QUOTATION MARK
|
||||
0x93 0x201C #LEFT DOUBLE QUOTATION MARK
|
||||
0x94 0x201D #RIGHT DOUBLE QUOTATION MARK
|
||||
0x95 0x2022 #BULLET
|
||||
0x96 0x2013 #EN DASH
|
||||
0x97 0x2014 #EM DASH
|
||||
0x98 0x02DC #SMALL TILDE
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A #UNDEFINED
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C 0x0153 #LATIN SMALL LIGATURE OE
|
||||
0x9D #UNDEFINED
|
||||
0x9E #UNDEFINED
|
||||
0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x00A1 #INVERTED EXCLAMATION MARK
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
0xA3 0x00A3 #POUND SIGN
|
||||
0xA4 0x00A4 #CURRENCY SIGN
|
||||
0xA5 0x00A5 #YEN SIGN
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x00A8 #DIAERESIS
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x00AA #FEMININE ORDINAL INDICATOR
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x00AF #MACRON
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00B8 #CEDILLA
|
||||
0xB9 0x00B9 #SUPERSCRIPT ONE
|
||||
0xBA 0x00BA #MASCULINE ORDINAL INDICATOR
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00BF #INVERTED QUESTION MARK
|
||||
0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE
|
||||
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x00C6 #LATIN CAPITAL LETTER AE
|
||||
0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x0300 #COMBINING GRAVE ACCENT
|
||||
0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE
|
||||
0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
|
||||
0xD2 0x0309 #COMBINING HOOK ABOVE
|
||||
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x01A0 #LATIN CAPITAL LETTER O WITH HORN
|
||||
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 #MULTIPLICATION SIGN
|
||||
0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x01AF #LATIN CAPITAL LETTER U WITH HORN
|
||||
0xDE 0x0303 #COMBINING TILDE
|
||||
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE
|
||||
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x00E6 #LATIN SMALL LETTER AE
|
||||
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x0301 #COMBINING ACUTE ACCENT
|
||||
0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE
|
||||
0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE
|
||||
0xF2 0x0323 #COMBINING DOT BELOW
|
||||
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x01A1 #LATIN SMALL LETTER O WITH HORN
|
||||
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 #DIVISION SIGN
|
||||
0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE
|
||||
0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x01B0 #LATIN SMALL LETTER U WITH HORN
|
||||
0xFE 0x20AB #DONG SIGN
|
||||
0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
@@ -0,0 +1,25 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* L I C E N S E
|
||||
*
|
||||
* Because nobody have time to read all that public licenses etc... this are the rules you have to obey
|
||||
* when you use this class.
|
||||
*
|
||||
* You can do anything with this class, you can sell it, change it, even put your name insted of mine
|
||||
* if you feel it is the right way.
|
||||
*
|
||||
* There is only one condition. If you find this class usefull, please sent an email (empty or with comment)
|
||||
* to my email mikolajj@op.pl with subject [ConvertCharset].
|
||||
*
|
||||
* <code>
|
||||
* To: mikolajj@op.pl
|
||||
* Subject: [ConvertCharset] I really like your... blah blah blah ;-)
|
||||
* </code>
|
||||
*
|
||||
* @copyright Copyright Mikolaj Jedrzejak (c) 2003-2007
|
||||
* @version 1.1 2007-10-30 00:34
|
||||
**/
|
||||
|
||||
|
||||
?>
|
||||
Whitespace-only changes.
Whitespace-only changes.
Reference in new issue
Block a user