GB18030 Charset Encoder Test

Character	Description	Encoded (bytes)
�	NULL (U+0000)	00
	START OF HEADING (U+0001)	01
	START OF TEXT (U+0002)	02
	END OF TEXT (U+0003)	03
	END OF TRANSMISSION (U+0004)	04
	ENQUIRY (U+0005)	05
	ACKNOWLEDGE (U+0006)	06
	BELL (U+0007)	07
	BACKSPACE (U+0008)	08
	CHARACTER TABULATION (U+0009)	09
	LINE FEED (LF) (U+000A)	0a
	LINE TABULATION (U+000B)	0b
	FORM FEED (FF) (U+000C)	0c
	CARRIAGE RETURN (CR) (U+000D)	0d
	SHIFT OUT (U+000E)	0e
	SHIFT IN (U+000F)	0f
	DATA LINK ESCAPE (U+0010)	10
	DEVICE CONTROL ONE (U+0011)	11
	DEVICE CONTROL TWO (U+0012)	12
	DEVICE CONTROL THREE (U+0013)	13
	DEVICE CONTROL FOUR (U+0014)	14
	NEGATIVE ACKNOWLEDGE (U+0015)	15
	SYNCHRONOUS IDLE (U+0016)	16
	END OF TRANSMISSION BLOCK (U+0017)	17
	CANCEL (U+0018)	18
	END OF MEDIUM (U+0019)	19
	SUBSTITUTE (U+001A)	1a
	ESCAPE (U+001B)	1b
	INFORMATION SEPARATOR FOUR (U+001C)	1c
	INFORMATION SEPARATOR THREE (U+001D)	1d
	INFORMATION SEPARATOR TWO (U+001E)	1e
	INFORMATION SEPARATOR ONE (U+001F)	1f
	SPACE (U+0020)	20
!	EXCLAMATION MARK (U+0021)	21
"	QUOTATION MARK (U+0022)	22
#	NUMBER SIGN (U+0023)	23
$	DOLLAR SIGN (U+0024)	24
%	PERCENT SIGN (U+0025)	25
&	AMPERSAND (U+0026)	26
'	APOSTROPHE (U+0027)	27
(	LEFT PARENTHESIS (U+0028)	28
)	RIGHT PARENTHESIS (U+0029)	29
*	ASTERISK (U+002A)	2a
+	PLUS SIGN (U+002B)	2b
,	COMMA (U+002C)	2c
-	HYPHEN-MINUS (U+002D)	2d
.	FULL STOP (U+002E)	2e
/	SOLIDUS (U+002F)	2f
0	DIGIT ZERO (U+0030)	30
1	DIGIT ONE (U+0031)	31
2	DIGIT TWO (U+0032)	32
3	DIGIT THREE (U+0033)	33
4	DIGIT FOUR (U+0034)	34
5	DIGIT FIVE (U+0035)	35
6	DIGIT SIX (U+0036)	36
7	DIGIT SEVEN (U+0037)	37
8	DIGIT EIGHT (U+0038)	38
9	DIGIT NINE (U+0039)	39
:	COLON (U+003A)	3a
;	SEMICOLON (U+003B)	3b
<	LESS-THAN SIGN (U+003C)	3c
=	EQUALS SIGN (U+003D)	3d
>	GREATER-THAN SIGN (U+003E)	3e
?	QUESTION MARK (U+003F)	3f
@	COMMERCIAL AT (U+0040)	40
A	LATIN CAPITAL LETTER A (U+0041)	41
B	LATIN CAPITAL LETTER B (U+0042)	42
C	LATIN CAPITAL LETTER C (U+0043)	43
D	LATIN CAPITAL LETTER D (U+0044)	44
E	LATIN CAPITAL LETTER E (U+0045)	45
F	LATIN CAPITAL LETTER F (U+0046)	46
G	LATIN CAPITAL LETTER G (U+0047)	47
H	LATIN CAPITAL LETTER H (U+0048)	48
I	LATIN CAPITAL LETTER I (U+0049)	49
J	LATIN CAPITAL LETTER J (U+004A)	4a
K	LATIN CAPITAL LETTER K (U+004B)	4b
L	LATIN CAPITAL LETTER L (U+004C)	4c
M	LATIN CAPITAL LETTER M (U+004D)	4d
N	LATIN CAPITAL LETTER N (U+004E)	4e
O	LATIN CAPITAL LETTER O (U+004F)	4f
P	LATIN CAPITAL LETTER P (U+0050)	50
Q	LATIN CAPITAL LETTER Q (U+0051)	51
R	LATIN CAPITAL LETTER R (U+0052)	52
S	LATIN CAPITAL LETTER S (U+0053)	53
T	LATIN CAPITAL LETTER T (U+0054)	54
U	LATIN CAPITAL LETTER U (U+0055)	55
V	LATIN CAPITAL LETTER V (U+0056)	56
W	LATIN CAPITAL LETTER W (U+0057)	57
X	LATIN CAPITAL LETTER X (U+0058)	58
Y	LATIN CAPITAL LETTER Y (U+0059)	59
Z	LATIN CAPITAL LETTER Z (U+005A)	5a
[	LEFT SQUARE BRACKET (U+005B)	5b
\	REVERSE SOLIDUS (U+005C)	5c
]	RIGHT SQUARE BRACKET (U+005D)	5d
^	CIRCUMFLEX ACCENT (U+005E)	5e
_	LOW LINE (U+005F)	5f
`	GRAVE ACCENT (U+0060)	60
a	LATIN SMALL LETTER A (U+0061)	61
b	LATIN SMALL LETTER B (U+0062)	62
c	LATIN SMALL LETTER C (U+0063)	63
d	LATIN SMALL LETTER D (U+0064)	64
e	LATIN SMALL LETTER E (U+0065)	65
f	LATIN SMALL LETTER F (U+0066)	66
g	LATIN SMALL LETTER G (U+0067)	67
h	LATIN SMALL LETTER H (U+0068)	68
i	LATIN SMALL LETTER I (U+0069)	69
j	LATIN SMALL LETTER J (U+006A)	6a
k	LATIN SMALL LETTER K (U+006B)	6b
l	LATIN SMALL LETTER L (U+006C)	6c
m	LATIN SMALL LETTER M (U+006D)	6d
n	LATIN SMALL LETTER N (U+006E)	6e
o	LATIN SMALL LETTER O (U+006F)	6f
p	LATIN SMALL LETTER P (U+0070)	70
q	LATIN SMALL LETTER Q (U+0071)	71
r	LATIN SMALL LETTER R (U+0072)	72
s	LATIN SMALL LETTER S (U+0073)	73
t	LATIN SMALL LETTER T (U+0074)	74
u	LATIN SMALL LETTER U (U+0075)	75
v	LATIN SMALL LETTER V (U+0076)	76
w	LATIN SMALL LETTER W (U+0077)	77
x	LATIN SMALL LETTER X (U+0078)	78
y	LATIN SMALL LETTER Y (U+0079)	79
z	LATIN SMALL LETTER Z (U+007A)	7a
{	LEFT CURLY BRACKET (U+007B)	7b
\|	VERTICAL LINE (U+007C)	7c
}	RIGHT CURLY BRACKET (U+007D)	7d
~	TILDE (U+007E)	7e
	DELETE (U+007F)	7f
€	<control> (U+0080)	81308130
	<control> (U+0081)	81308131
‚	BREAK PERMITTED HERE (U+0082)	81308132
ƒ	NO BREAK HERE (U+0083)	81308133
„	<control> (U+0084)	81308134
…	NEXT LINE (NEL) (U+0085)	81308135
†	START OF SELECTED AREA (U+0086)	81308136
‡	END OF SELECTED AREA (U+0087)	81308137
ˆ	CHARACTER TABULATION SET (U+0088)	81308138
‰	CHARACTER TABULATION WITH JUSTIFICATION (U+0089)	81308139
Š	LINE TABULATION SET (U+008A)	81308230
‹	PARTIAL LINE FORWARD (U+008B)	81308231
Œ	PARTIAL LINE BACKWARD (U+008C)	81308232
	REVERSE LINE FEED (U+008D)	81308233
Ž	SINGLE SHIFT TWO (U+008E)	81308234
	SINGLE SHIFT THREE (U+008F)	81308235
	DEVICE CONTROL STRING (U+0090)	81308236
‘	PRIVATE USE ONE (U+0091)	81308237
’	PRIVATE USE TWO (U+0092)	81308238
“	SET TRANSMIT STATE (U+0093)	81308239
”	CANCEL CHARACTER (U+0094)	81308330
•	MESSAGE WAITING (U+0095)	81308331
–	START OF GUARDED AREA (U+0096)	81308332
—	END OF GUARDED AREA (U+0097)	81308333
˜	START OF STRING (U+0098)	81308334
™	<control> (U+0099)	81308335
š	SINGLE CHARACTER INTRODUCER (U+009A)	81308336
›	CONTROL SEQUENCE INTRODUCER (U+009B)	81308337
œ	STRING TERMINATOR (U+009C)	81308338
	OPERATING SYSTEM COMMAND (U+009D)	81308339
ž	PRIVACY MESSAGE (U+009E)	81308430
Ÿ	APPLICATION PROGRAM COMMAND (U+009F)	81308431
	NO-BREAK SPACE (U+00A0)	81308432
¡	INVERTED EXCLAMATION MARK (U+00A1)	81308433
¢	CENT SIGN (U+00A2)	81308434
£	POUND SIGN (U+00A3)	81308435
¤	CURRENCY SIGN (U+00A4)	a1e8
¥	YEN SIGN (U+00A5)	81308436
¦	BROKEN BAR (U+00A6)	81308437
§	SECTION SIGN (U+00A7)	a1ec
¨	DIAERESIS (U+00A8)	a1a7
©	COPYRIGHT SIGN (U+00A9)	81308438
ª	FEMININE ORDINAL INDICATOR (U+00AA)	81308439
«	LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (U+00AB)	81308530
¬	NOT SIGN (U+00AC)	81308531
	SOFT HYPHEN (U+00AD)	81308532
®	REGISTERED SIGN (U+00AE)	81308533
¯	MACRON (U+00AF)	81308534
°	DEGREE SIGN (U+00B0)	a1e3
±	PLUS-MINUS SIGN (U+00B1)	a1c0
²	SUPERSCRIPT TWO (U+00B2)	81308535
³	SUPERSCRIPT THREE (U+00B3)	81308536
´	ACUTE ACCENT (U+00B4)	81308537
µ	MICRO SIGN (U+00B5)	81308538
¶	PILCROW SIGN (U+00B6)	81308539
·	MIDDLE DOT (U+00B7)	a1a4
¸	CEDILLA (U+00B8)	81308630
¹	SUPERSCRIPT ONE (U+00B9)	81308631
º	MASCULINE ORDINAL INDICATOR (U+00BA)	81308632
»	RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (U+00BB)	81308633
¼	VULGAR FRACTION ONE QUARTER (U+00BC)	81308634
½	VULGAR FRACTION ONE HALF (U+00BD)	81308635
¾	VULGAR FRACTION THREE QUARTERS (U+00BE)	81308636
¿	INVERTED QUESTION MARK (U+00BF)	81308637
À	LATIN CAPITAL LETTER A WITH GRAVE (U+00C0)	81308638
Á	LATIN CAPITAL LETTER A WITH ACUTE (U+00C1)	81308639
Â	LATIN CAPITAL LETTER A WITH CIRCUMFLEX (U+00C2)	81308730
Ã	LATIN CAPITAL LETTER A WITH TILDE (U+00C3)	81308731
Ä	LATIN CAPITAL LETTER A WITH DIAERESIS (U+00C4)	81308732
Å	LATIN CAPITAL LETTER A WITH RING ABOVE (U+00C5)	81308733
Æ	LATIN CAPITAL LETTER AE (U+00C6)	81308734
Ç	LATIN CAPITAL LETTER C WITH CEDILLA (U+00C7)	81308735
È	LATIN CAPITAL LETTER E WITH GRAVE (U+00C8)	81308736
É	LATIN CAPITAL LETTER E WITH ACUTE (U+00C9)	81308737
Ê	LATIN CAPITAL LETTER E WITH CIRCUMFLEX (U+00CA)	81308738
Ë	LATIN CAPITAL LETTER E WITH DIAERESIS (U+00CB)	81308739
Ì	LATIN CAPITAL LETTER I WITH GRAVE (U+00CC)	81308830
Í	LATIN CAPITAL LETTER I WITH ACUTE (U+00CD)	81308831
Î	LATIN CAPITAL LETTER I WITH CIRCUMFLEX (U+00CE)	81308832
Ï	LATIN CAPITAL LETTER I WITH DIAERESIS (U+00CF)	81308833
Ð	LATIN CAPITAL LETTER ETH (U+00D0)	81308834
Ñ	LATIN CAPITAL LETTER N WITH TILDE (U+00D1)	81308835
Ò	LATIN CAPITAL LETTER O WITH GRAVE (U+00D2)	81308836
Ó	LATIN CAPITAL LETTER O WITH ACUTE (U+00D3)	81308837
Ô	LATIN CAPITAL LETTER O WITH CIRCUMFLEX (U+00D4)	81308838
Õ	LATIN CAPITAL LETTER O WITH TILDE (U+00D5)	81308839
Ö	LATIN CAPITAL LETTER O WITH DIAERESIS (U+00D6)	81308930
×	MULTIPLICATION SIGN (U+00D7)	a1c1
Ø	LATIN CAPITAL LETTER O WITH STROKE (U+00D8)	81308931
Ù	LATIN CAPITAL LETTER U WITH GRAVE (U+00D9)	81308932
Ú	LATIN CAPITAL LETTER U WITH ACUTE (U+00DA)	81308933
Û	LATIN CAPITAL LETTER U WITH CIRCUMFLEX (U+00DB)	81308934
Ü	LATIN CAPITAL LETTER U WITH DIAERESIS (U+00DC)	81308935
Ý	LATIN CAPITAL LETTER Y WITH ACUTE (U+00DD)	81308936
Þ	LATIN CAPITAL LETTER THORN (U+00DE)	81308937
ß	LATIN SMALL LETTER SHARP S (U+00DF)	81308938
à	LATIN SMALL LETTER A WITH GRAVE (U+00E0)	a8a4
á	LATIN SMALL LETTER A WITH ACUTE (U+00E1)	a8a2
â	LATIN SMALL LETTER A WITH CIRCUMFLEX (U+00E2)	81308939
ã	LATIN SMALL LETTER A WITH TILDE (U+00E3)	81308a30
ä	LATIN SMALL LETTER A WITH DIAERESIS (U+00E4)	81308a31
å	LATIN SMALL LETTER A WITH RING ABOVE (U+00E5)	81308a32
æ	LATIN SMALL LETTER AE (U+00E6)	81308a33
ç	LATIN SMALL LETTER C WITH CEDILLA (U+00E7)	81308a34
è	LATIN SMALL LETTER E WITH GRAVE (U+00E8)	a8a8
é	LATIN SMALL LETTER E WITH ACUTE (U+00E9)	a8a6
ê	LATIN SMALL LETTER E WITH CIRCUMFLEX (U+00EA)	a8ba
ë	LATIN SMALL LETTER E WITH DIAERESIS (U+00EB)	81308a35
ì	LATIN SMALL LETTER I WITH GRAVE (U+00EC)	a8ac
í	LATIN SMALL LETTER I WITH ACUTE (U+00ED)	a8aa
î	LATIN SMALL LETTER I WITH CIRCUMFLEX (U+00EE)	81308a36
ï	LATIN SMALL LETTER I WITH DIAERESIS (U+00EF)	81308a37
ð	LATIN SMALL LETTER ETH (U+00F0)	81308a38
ñ	LATIN SMALL LETTER N WITH TILDE (U+00F1)	81308a39
ò	LATIN SMALL LETTER O WITH GRAVE (U+00F2)	a8b0
ó	LATIN SMALL LETTER O WITH ACUTE (U+00F3)	a8ae
ô	LATIN SMALL LETTER O WITH CIRCUMFLEX (U+00F4)	81308b30
õ	LATIN SMALL LETTER O WITH TILDE (U+00F5)	81308b31
ö	LATIN SMALL LETTER O WITH DIAERESIS (U+00F6)	81308b32
÷	DIVISION SIGN (U+00F7)	a1c2
ø	LATIN SMALL LETTER O WITH STROKE (U+00F8)	81308b33
ù	LATIN SMALL LETTER U WITH GRAVE (U+00F9)	a8b4
ú	LATIN SMALL LETTER U WITH ACUTE (U+00FA)	a8b2
û	LATIN SMALL LETTER U WITH CIRCUMFLEX (U+00FB)	81308b34
ü	LATIN SMALL LETTER U WITH DIAERESIS (U+00FC)	a8b9
ý	LATIN SMALL LETTER Y WITH ACUTE (U+00FD)	81308b35
þ	LATIN SMALL LETTER THORN (U+00FE)	81308b36
ÿ	LATIN SMALL LETTER Y WITH DIAERESIS (U+00FF)	81308b37