| java.lang.Object
 org.w3c.tidy.EncodingUtils
| EncodingUtils | | final public class EncodingUtils (Code) | |
author:
Fabrizio Giustina
version:
$Revision: 1.7 $ ($Author: fgiust $) |
| Inner Class :static interface GetBytes | |
| Inner Class :static interface PutBytes | |
| Method Summary | |
| protected static int | decodeMacRoman(int c)
Function to convert from MacRoman to Unicode. | | static int | decodeSymbolFont(int c)
Function to convert from Symbol Font chars to Unicode. | | static boolean | decodeUTF8BytesToChar(int[] c, int firstByte, byte[] successorBytes, GetBytes getter, int[] count, int startInSuccessorBytesArray)
Decodes an array of bytes to a char. | | protected static int | decodeWin1252(int c)
Function for conversion from Windows-1252 to Unicode. | | static boolean | encodeCharToUTF8Bytes(int c, byte[] encodebuf, PutBytes putter, int[] count)
Encode a char to an array of bytes. |
| FSM_ASCII | | final public static int FSM_ASCII(Code) | | states for ISO 2022 A document in ISO-2022 based encoding uses some ESC sequences called "designator" to switch
character sets. The designators defined and used in ISO-2022-JP are: "ESC" + "(" + ? for ISO646 variants "ESC" +
"$" + ? and "ESC" + "$" + "(" + ? for multibyte character sets. State ASCII.
|
| FSM_ESC | | final public static int FSM_ESC(Code) | | state ESC.
|
| FSM_ESCD | | final public static int FSM_ESCD(Code) | | state ESCD.
|
| FSM_ESCDP | | final public static int FSM_ESCDP(Code) | | state ESCDP.
|
| FSM_ESCP | | final public static int FSM_ESCP(Code) | | state ESCP.
|
| FSM_NONASCII | | final public static int FSM_NONASCII(Code) | | state NONASCII.
|
| HIGH_UTF16_SURROGATE | | final public static int HIGH_UTF16_SURROGATE(Code) | | UTF-16 high surrogate.
|
| LOW_UTF16_SURROGATE | | final public static int LOW_UTF16_SURROGATE(Code) | | utf16 low surrogate.
|
| MAX_UTF16_FROM_UCS4 | | final public static int MAX_UTF16_FROM_UCS4(Code) | | Max UTF-16 value.
|
| MAX_UTF8_FROM_UCS4 | | final public static int MAX_UTF8_FROM_UCS4(Code) | | Max UTF-88 valid char value.
|
| UNICODE_BOM | | final public static int UNICODE_BOM(Code) | | the default (big-endian) UNICODE BOM.
|
| UNICODE_BOM_BE | | final public static int UNICODE_BOM_BE(Code) | | the big-endian (default) UNICODE BOM.
|
| UNICODE_BOM_LE | | final public static int UNICODE_BOM_LE(Code) | | the little-endian UNICODE BOM.
|
| UNICODE_BOM_UTF8 | | final public static int UNICODE_BOM_UTF8(Code) | | the UTF-8 UNICODE BOM.
|
| UTF16_HIGH_SURROGATE_BEGIN | | final public static int UTF16_HIGH_SURROGATE_BEGIN(Code) | | UTF-16 surrogate pair areas: high surrogates begin.
|
| UTF16_HIGH_SURROGATE_END | | final public static int UTF16_HIGH_SURROGATE_END(Code) | | UTF-16 surrogate pair areas: high surrogates end.
|
| UTF16_LOW_SURROGATE_BEGIN | | final public static int UTF16_LOW_SURROGATE_BEGIN(Code) | | UTF-16 surrogate pair areas: low surrogates begin.
|
| UTF16_LOW_SURROGATE_END | | final public static int UTF16_LOW_SURROGATE_END(Code) | | UTF-16 surrogate pair areas: low surrogates end.
|
| UTF16_SURROGATES_BEGIN | | final public static int UTF16_SURROGATES_BEGIN(Code) | | UTF-16 surrogates begin.
|
| decodeMacRoman | | protected static int decodeMacRoman(int c)(Code) | | Function to convert from MacRoman to Unicode.
Parameters:
c - char to decode decoded char |
| decodeSymbolFont | | static int decodeSymbolFont(int c)(Code) | | Function to convert from Symbol Font chars to Unicode.
Parameters:
c - char to decode decoded char |
| decodeUTF8BytesToChar | | static boolean decodeUTF8BytesToChar(int[] c, int firstByte, byte[] successorBytes, GetBytes getter, int[] count, int startInSuccessorBytesArray)(Code) | | Decodes an array of bytes to a char.
Parameters:
c - will contain the decoded char
Parameters:
firstByte - first input byte
Parameters:
successorBytes - array containing successor bytes (can be null if a getter is provided).
Parameters:
getter - callback used to get new bytes if successorBytes doesn't contain enough bytes
Parameters:
count - will contain the number of bytes read
Parameters:
startInSuccessorBytesArray - starting offset for bytes in successorBytes true if error |
| decodeWin1252 | | protected static int decodeWin1252(int c)(Code) | | Function for conversion from Windows-1252 to Unicode.
Parameters:
c - char to decode decoded char |
| encodeCharToUTF8Bytes | | static boolean encodeCharToUTF8Bytes(int c, byte[] encodebuf, PutBytes putter, int[] count)(Code) | | Encode a char to an array of bytes.
Parameters:
c - char to encode
Parameters:
encodebuf - will contain the decoded bytes
Parameters:
putter - if not null it will be called to write bytes to out
Parameters:
count - number of bytes written false= ok, true= error |
|
|