Mengenai hubungan antara Unicode dan UTF, Anda dapat mengingat: Unicode adalah organisasi pengkodean, spesifikasi pengkodean, dan mengacu pada UTF-16 di Java; baik di jaringan.
Salinan kode adalah sebagai berikut:
public static void main (string [] args) melempar UnsupportedencodingException {
Stringutil.str2all ("0 Deskripsi Model Produk");
Stringutil.str4all ("30000900A74EC1548B57F753CF63F08F");
}
/**
* Cobalah untuk menyandikan string numerik heksadesimal dalam semua format pengkodean
*
* @param hexstr
* @Throws UnsportedencodingException
*/
public static void str4all (string ustr) melempar UnsupportedencodingException {
System.out.println ("+++++++++++++++++++++++++++++++++++++++++++ ++++++++++++++++++++++ +++++++++ ");
byte [] bs = byte baru [ustr.length ()/2];
untuk (int i = 0; i <bs.length; i ++) {
bs [i] = (byte) integer.parseint (ustr.substring (i*2, i*2+2), 16);
}
System.out.println (string baru (BS, "UTF-8"));
// 16
System.out.println (string baru (BS, "UTF-16"));
System.out.println (string baru (BS, "UTF-16LE"));
System.out.println (string baru (BS, "X-UTF-16LE-BOM"));
System.out.println (string baru (BS, "UTF-16BE"));
//System.out.println( string baru (BS, "X-UTF-16BE-BOM"));
// 32
System.out.println (string baru (BS, "UTF-32"));
System.out.println (string baru (BS, "UTF-32LE"));
System.out.println (string baru (BS, "X-UTF-32LE-BOM"));
System.out.println (string baru (BS, "UTF-32BE"));
System.out.println (string baru (BS, "X-UTF-32LE-BOM"));
}
/**
* Sebutkan semua string numerik heksadesimal yang decoded yang sesuai dengan pengkodean
*
* @param ustr
* @Throws UnsportedencodingException
*/
public static void str2all (String USTR) melempar UnsupportedencodingException {
System.out.println ("+++++++++++++++++++++++++++++++++++++++++++ ++++++++++++++++++++++ +++++++++ ");
byte [] bs = byte baru [] {};
bs = ustr.getbytes ("UTF-8");
untuk (byte b: bs) {
System.out.print (integer.tohexstring (b & 0xff));
}
System.out.println ();
// 16
bs = ustr.getbytes ("UTF-16");
untuk (byte b: bs) {
System.out.print (integer.tohexstring (b & 0xff));
}
System.out.println ();
bs = ustr.getbytes ("UTF-16LE");
untuk (byte b: bs) {
System.out.print (integer.tohexstring (b & 0xff));
}
System.out.println ();
bs = ustr.getbytes ("x-UTF-16LE-bom");
untuk (byte b: bs) {
System.out.print (integer.tohexstring (b & 0xff));
}
System.out.println ();
bs = ustr.getbytes ("UTF-16BE");
untuk (byte b: bs) {
System.out.print (integer.tohexstring (b & 0xff));
}
System.out.println ();
// bs = ustr.getbytes ("x-utf-16be-bom");
// 32
bs = ustr.getbytes ("UTF-32");
untuk (byte b: bs) {
System.out.print (integer.tohexstring (b & 0xff));
}
System.out.println ();
bs = ustr.getbytes ("UTF-32LE");
untuk (byte b: bs) {
System.out.print (integer.tohexstring (b & 0xff));
}
System.out.println ();
bs = ustr.getbytes ("x-UTF-32LE-bom");
untuk (byte b: bs) {
System.out.print (integer.tohexstring (b & 0xff));
}
System.out.println ();
bs = ustr.getbytes ("UTF-32BE");
untuk (byte b: bs) {
System.out.print (integer.tohexstring (b & 0xff));
}
System.out.println ();
bs = ustr.getbytes ("x-UTF-32LE-bom");
untuk (byte b: bs) {
System.out.print (integer.tohexstring (b & 0xff));
}
System.out.println ();
}
Koleksi nama pengkodean
Salinan kode adalah sebagai berikut:
Charset US-Ascii %s
HistoricalName ASCII
# Alias Iana
alias iso-ir-6
alias ANSI_X3.4-1986
Alias ISO_646.IRV: 1991
alias ascii
Alias ISO646-US
alias kami
alias IBM367
Alias CP367
alias csascii
alias default
# Alias lainnya
Alias 646 # Lokal Solaris Posix
Alias ISO_646.IRV: 1983
Alias ANSI_X3.4-1968 # Linux POSIX LOCAL (Redhat)
alias ascii7
Charset UTF-8 UTF_8
HistoricalName UTF8
alias utf8
Alias Unicode-1-1-UTF-8
Charset UTF-16 UTF_16
HistoricalName UTF-16
Alias UTF_16
Alias UTF16
Alias Unicode
alias unicodeBig
Charset UTF-16BE UTF_16BE
HistoricalName UnicodeBigunmarked
Alias UTF_16BE
Alias ISO-10646-UCS-2
Alias X-UTF-16BE
alias unicodeBigunmarked
Charset UTF-16LE UTF_16LE
HistoricalName Unicodelittleunmarked
Alias UTF_16LE
Alias X-UTF-16LE
alias unicodelittleunmarked
Charset X-UTF-16LE-BOM UTF_16LE_BOM
HistoricalName Unicodelittle
alias unicodelittle
Charset UTF-32 UTF_32
Alias UTF_32
Alias UTF32
Charset UTF-32LE UTF_32LE
Alias UTF_32LE
Alias X-UTF-32LE
Charset UTF-32BE UTF_32BE
Alias UTF_32BE
Alias X-UTF-32BE
Charset X-UTF-32LE-BOM UTF_32LE_BOM
Alias UTF_32LE_BOM
Alias UTF-32LE-BOM
Charset X-UTF-32BE-BOM UTF_32BE_BOM
Alias UTF_32BE_BOM
Alias UTF-32BE-BOM
Charset ISO-8859-1 %s
HistoricalName ISO8859_1
# Alias Iana
Alias ISO-IR-100
Alias ISO_8859-1
Alias Latin1
Alias L1
alias IBM819
Alias CP819
alias csisolatin1
# Alias lainnya
alias 819
alias IBM-819
Alias ISO8859_1
Alias ISO_8859-1: 1987
Alias ISO_8859_1
Alias 8859_1
Alias ISO8859-1
Charset ISO-8859-2 %s
HistoricalName ISO8859_2
Alias ISO8859_2
Alias 8859_2
alias iso-IR-101
Alias ISO_8859-2
Alias ISO_8859-2: 1987
Alias ISO8859-2
Alias Latin2
Alias L2
alias IBM912
alias IBM-912
Alias CP912
alias 912
alias csisolatin2
Charset ISO-8859-4 %s
HistoricalName ISO8859_4
Alias ISO8859_4
Alias ISO8859-4
Alias 8859_4
alias iso-IR-110
Alias ISO_8859-4
Alias ISO_8859-4: 1988
Alias Latin4
Alias L4
alias IBM914
alias IBM-914
Alias CP914
alias 914
alias csisolatin4
Charset ISO-8859-5 %s
HistoricalName ISO8859_5
Alias ISO8859_5
Alias 8859_5
alias iso-IR-144
Alias ISO_8859-5
Alias ISO_8859-5: 1988
Alias ISO8859-5
Alias Cyrillic
alias IBM915
alias IBM-915
Alias CP915
alias 915
alias csisolatincyrillic
Charset ISO-8859-7 %s
HistoricalName ISO8859_7
Alias ISO8859_7
Alias 8859_7
alias iso-IR-126
Alias ISO_8859-7
Alias ISO_8859-7: 1987
alias elot_928
Alias ECMA-118
Alias Yunani
Alias Greek8
alias csisolatingreek
Alias Sun_eu_Greek # Solaris 7/8 Kompatibilitas
alias IBM813
alias IBM-813
alias 813
Alias CP813
Alias ISO8859-7 # Solaris 9 Kompatibilitas
Charset ISO-8859-9 %s
HistoricalName ISO8859_9
Alias ISO8859_9
Alias 8859_9
alias iso-IR-148
Alias ISO_8859-9
Alias ISO_8859-9: 1989
Alias ISO8859-9
Alias Latin5
Alias L5
alias IBM920
alias IBM-920
alias 920
Alias CP920
alias csisolatin5
Charset ISO-8859-13 %s
HistoricalName ISO8859_13
Alias ISO8859_13
Alias 8859_13
Alias ISO_8859-13
Alias ISO8859-13
Charset ISO-8859-15 %s
HistoricalName ISO8859_15
# IANA alias
Alias ISO_8859-15
# Alias lainnya
Alias 8859_15
Alias ISO8859_15
Alias ISO8859-15
alias IBM923
Alias IBM-923
Alias CP923
alias 923
Alias Latin0
Alias Latin9
alias l9
alias csisolatin0
alias csisolatin9
Alias ISO8859_15_FDIS
Charset KOI8-R %s
HistoricalName KOI8_R
Alias KOI8_R
alias koi8
Alias CSKOI8R
Charset KOI8-U %s
alias koi8_u
Charset Windows-1250 %s
HistoricalName CP1250
Alias CP1250
Alias CP5346 # Euro IBM CCSID
Charset Windows-1251 %s
HistoricalName CP1251
Alias CP1251
Alias CP5347 # Euro IBM CCSID
Alias ANSI-1251 # Solaris Compatibility
Charset Windows-1252 %s
HistoricalName CP1252
Alias CP1252
Alias CP5348 # Euro IBM CCSID
Charset Windows-1253 %s
HistoricalName CP1253
Alias CP1253
Alias CP5349 # Euro IBM CCSID
Charset Windows-1254 %s
HistoricalName CP1254
Alias CP1254
Alias CP5350 # Euro IBM CCSID
Charset Windows-1257 %s
HistoricalName CP1257
Alias CP1257
Alias CP5353 # Euro IBM CCSID
Charset IBM437 %s
HistoricalName CP437
Alias CP437
Alias IBM-437
alias 437
Alias CSPC8CODEPAGE437
Alias Windows-437
Charset X-IBM737 %s
HistoricalName CP737
Alias CP737
alias IBM737
Alias IBM-737
alias 737
Charset IBM775 %s
HistoricalName CP775
Alias CP775
alias IBM-775
alias 775
Charset IBM850 %s
HistoricalName CP850
Alias CP850
alias IBM-850
alias 850
alias CSPC850 Multilingual
Charset IBM852 %s
HistoricalName CP852
Alias CP852
Alias IBM-852
alias 852
Alias CSPCP852
Charset IBM855 %s
HistoricalName CP855
Alias CP855
alias IBM-855
alias 855
Alias CSPCP855
Charset IBM857 %s
HistoricalName CP857
Alias CP857
Alias IBM-857
alias 857
Alias CSIBM857
Charset IBM00858 %s
HistoricalName CP858
Alias CP858
Alias CCSID00858
Alias CP00858
alias 858
Charset IBM862 %s
HistoricalName CP862
Alias CP862
alias IBM-862
alias 862
Alias CSIBM862
Alias CSPC862LATINHEBREW
Charset IBM866 %s
HistoricalName CP866
Alias CP866
alias IBM-866
alias 866
Alias CSIBM866
Charset X-IBM874 %s
HistoricalName CP874
Alias CP874
alias IBM874
Alias IBM-874
alias 874