encoding-map.xml

mapxtreme for java 的开发实例

<?xml version="1.0" standalone="yes"?>

<!-- 
     One of the Internet Assigned Numbers Authority's (IANA)
     (http://www.iana.org/) many duties is the maintenance of a database of 
		 registered encodings (character sets). For example; one such encoding
		 registered with IANA has the name ANSI_X3.4-1968 but its preferred MIME 
		 name is US-ASCII. A character set has a name, an optional preferred MIME 
		 name, and an optional list of aliases. See 
		 http://www.iana.org/assignments/character-sets for more information. The
		 encoding names found in IANA's registry are frequently used as the 
		 encoding "attribute" in an XML header.

		 Java also has character set names that are used when converting Java's
		 internal Unicode character set to a specific character set. However, these
		 names frequently do not match the names registered with IANA. Java's 
		 encoding name for US-ASCII is ASCII.

		 This file facilitates the mapping of Java's encoding names to ones 
		 registered with IANA. If a new Java encoding name appears just add it to
		 this list. The mapping facility is very flexible in that any name to be 
		 entered not just names registered with IANA.
		 
		 Two encodings are not included in this file and will not be read if added:
		 UTF-8 and UTF-16 are not allowed to be mapped to anything else.
 -->

<!DOCTYPE EncodingMap [

	<!ELEMENT EncodingMap (XmlEncoding?, JavaEncoding*)>

	<!-- The encoding for writing XML --> 
	<!ELEMENT XmlEncoding (#PCDATA) >

	<!-- Defines a mapping between a Java encoding name and a standard name -->
	<!ELEMENT JavaEncoding (JavaName, MimeName)>

	<!-- The name Java assigns to a specific encoding (Case sensative) -->
	<!ELEMENT JavaName (#PCDATA)>

	<!-- The IANA equivalent name for the Java encoding name --> 
	<!ELEMENT MimeName (Name, Alias*)>

	<!-- The name (Case insensative) -->
	<!ELEMENT Name (#PCDATA)>

	<!-- An IANA alias for a MIME name (Case insensative) -->
	<!ELEMENT Alias (#PCDATA)>
]>

<EncodingMap>

	<!-- Set to the desired MIME defined in this file -->
	<XmlEncoding>UTF-8</XmlEncoding>

	<!-- ASCII -->
	<JavaEncoding>
		<JavaName>ASCII</JavaName>
		<MimeName>
			<Name>US-ASCII</Name>
		</MimeName>
	</JavaEncoding>
	
	<!-- Latin1 -->
	<JavaEncoding>
		<JavaName>ISO8859_1</JavaName>
		<MimeName>
			<Name>ISO-8859-1</Name>
			<Alias>ISO_8859-1</Alias>
			<Alias>LATIN1</Alias>
			<Alias>L1</Alias>
			<Alias>IBM819</Alias>
			<Alias>CP819</Alias>
		</MimeName>
	</JavaEncoding>
	
	<!-- Latin2 -->
	<JavaEncoding>
		<JavaName>ISO8859_2</JavaName>
		<MimeName>
			<Name>ISO-8859-2</Name>
			<Alias>ISO_8859-2</Alias>
			<Alias>Latin2</Alias>
			<Alias>L2</Alias>
			<Alias>ISO-IR-101</Alias>
		</MimeName>
	</JavaEncoding>

	<!-- Latin3 -->
	<JavaEncoding>
		<JavaName>ISO8859_3</JavaName>
		<MimeName>
			<Name>ISO-8859-3</Name>
			<Alias>ISO_8859-3</Alias>
			<Alias>Latin3</Alias>
			<Alias>L3</Alias>
			<Alias>ISO-IR-109</Alias>
		</MimeName>
	</JavaEncoding>
	
	<!-- Latin4 -->
	<JavaEncoding>
		<JavaName>ISO8859_4</JavaName>
		<MimeName>
			<Name>ISO-8859-4</Name>
			<Alias>ISO_8859-4</Alias>
			<Alias>Latin4</Alias>
			<Alias>L4</Alias>
			<Alias>ISO-IR-110</Alias>
		</MimeName>
	</JavaEncoding>
	
	<!-- Latin/Cyrillic -->
	<JavaEncoding>
		<JavaName>ISO8859_5</JavaName>
		<MimeName>
			<Name>ISO-8859-5</Name>
			<Alias>ISO_8859-5</Alias>
			<Alias>CYRILLIC</Alias>
			<Alias>ISO-IR-144</Alias>
		</MimeName>
	</JavaEncoding>
	
	<!-- Latin/Arabic -->
	<JavaEncoding>
		<JavaName>ISO8859_6</JavaName>
		<MimeName>
			<Name>ISO-8859-6</Name>
			<Alias>ISO_8859-6</Alias>
			<Alias>ISO-IR-127</Alias>
			<Alias>ECMA-114</Alias>
			<Alias>ASMO-708</Alias>
			<Alias>ARABIC</Alias>
		</MimeName>
	</JavaEncoding>

	<!-- Latin/Greek -->
	<JavaEncoding>
		<JavaName>ISO8859_7</JavaName>
		<MimeName>
			<Name>ISO-8859-7</Name>
			<Alias>ISO_8859-7</Alias>
			<Alias>ISO-IR-126</Alias>
			<Alias>ECMA-118</Alias>
			<Alias>ELOT_928</Alias>
			<Alias>GREEK</Alias>
			<Alias>GREEK8</Alias>
		</MimeName>
	</JavaEncoding>

	<!-- Latin/Hebrew -->
	<JavaEncoding>
		<JavaName>ISO8859_8</JavaName>
		<MimeName>
			<Name>ISO-8859-8</Name>
			<Alias>ISO_8859-8</Alias>
			<Alias>ISO-IR-138</Alias>
			<Alias>HEBREW</Alias>
		</MimeName>
	</JavaEncoding>

	<!-- Latin9 -->
	<JavaEncoding>
		<JavaName>ISO8859_9</JavaName>
		<MimeName>
			<Name>ISO-8859-9</Name>
			<Alias>ISO_8859-9</Alias>
			<Alias>ISO-IR-148</Alias>
			<Alias>LATIN9</Alias>
			<Alias>L9</Alias>
		</MimeName>
	</JavaEncoding>

	<!-- Traditional Chinese -->
	<JavaEncoding>
		<JavaName>Big5</JavaName>
		<MimeName>
			<Name>Big5</Name>
		</MimeName>
	</JavaEncoding>

	<!-- Traditional Chinese with Hong Kong Supplementary Character Set --> 
	<JavaEncoding>
		<JavaName>Big5_HKSCS</JavaName>
		<MimeName>
			<Name>Big5-HKSCS</Name>
		</MimeName>
	</JavaEncoding>
	
	<!-- Simplified Chinese  -->
	<JavaEncoding>
		<JavaName>GB2312</JavaName>
		<MimeName>
			<Name>GB2312</Name>
		</MimeName>
	</JavaEncoding>
	
	<!-- Korean -->
	<JavaEncoding>
		<JavaName>ISO2022KR</JavaName>
		<MimeName>
			<Name>ISO-2022-KR</Name>
		</MimeName>
	</JavaEncoding>

	<!-- Korean, EUC encoding -->
	<JavaEncoding>
		<JavaName>EUC_KR</JavaName>
		<MimeName>
			<Name>EUC-KR</Name>
		</MimeName>
	</JavaEncoding>
	
	<!-- Japanese -->
	<JavaEncoding>
		<JavaName>ISO2022JP</JavaName>
		<MimeName>
			<Name>ISO-2022-JP</Name>
		</MimeName>
	</JavaEncoding>
	
	<!-- Japanese, EUC encoding -->
	<JavaEncoding>
		<JavaName>EUC_JP</JavaName>
		<MimeName>
			<Name>EUC-JP</Name>
		</MimeName>
	</JavaEncoding>
	
	<!-- Japanese (Shift_JIS) -->
	<JavaEncoding>
		<JavaName>SJIS</JavaName>
		<MimeName>
			<Name>SHIFT_JIS</Name>
			<Alias>MS_Kanji</Alias>
		</MimeName>
	</JavaEncoding>
	
	<!-- Windows-1252 -->
	<JavaEncoding>
		<JavaName>Cp1252</JavaName>
		<MimeName>
			<Name>WINDOWS-1252</Name>
		</MimeName>
	</JavaEncoding>

</EncodingMap>