names.txt

UNIX下perl实现代码

@@@	The Unicode Standard 3.0
@@@+	Final Draft UC3M990825.lst
	More annotation fixes for Tibetan.
	Annotation added for 2231..2233.
@@	0000	C0 Controls and Basic Latin (Basic Latin)	007F
@		C0 controls
@+		Alias names are those for ISO 6429.
0000	<control>
	= NULL
0001	<control>
	= START OF HEADING
0002	<control>
	= START OF TEXT
0003	<control>
	= END OF TEXT
0004	<control>
	= END OF TRANSMISSION
0005	<control>
	= ENQUIRY
0006	<control>
	= ACKNOWLEDGE
0007	<control>
	= BELL
0008	<control>
	= BACKSPACE
0009	<control>
	= HORIZONTAL TABULATION
000A	<control>
	= LINE FEED
000B	<control>
	= VERTICAL TABULATION
000C	<control>
	= FORM FEED
000D	<control>
	= CARRIAGE RETURN
000E	<control>
	= SHIFT OUT
000F	<control>
	= SHIFT IN
0010	<control>
	= DATA LINK ESCAPE
0011	<control>
	= DEVICE CONTROL ONE
0012	<control>
	= DEVICE CONTROL TWO
0013	<control>
	= DEVICE CONTROL THREE
0014	<control>
	= DEVICE CONTROL FOUR
0015	<control>
	= NEGATIVE ACKNOWLEDGE
0016	<control>
	= SYNCHRONOUS IDLE
0017	<control>
	= END OF TRANSMISSION BLOCK
0018	<control>
	= CANCEL
0019	<control>
	= END OF MEDIUM
001A	<control>
	= SUBSTITUTE
	x (replacement character - FFFD)
001B	<control>
	= ESCAPE
001C	<control>
	= FILE SEPARATOR
001D	<control>
	= GROUP SEPARATOR
001E	<control>
	= RECORD SEPARATOR
001F	<control>
	= UNIT SEPARATOR
@		ASCII
0020	SPACE
	* sometimes considered a control code
	* other space characters: 2000-200A
	x (no-break space - 00A0)
	x (zero width space - 200B)
	x (ideographic space - 3000)
	x (zero width no-break space - FEFF)
0021	EXCLAMATION MARK
	= factorial
	= bang
	x (inverted exclamation mark - 00A1)
	x (latin letter retroflex click - 01C3)
	x (double exclamation mark - 203C)
	x (interrobang - 203D)
	x (heavy exclamation mark ornament - 2762)
0022	QUOTATION MARK
	= APL quote
	* neutral (vertical), used as opening or closing quotation mark
	* preferred characters in English for paired quotation marks are 201C & 201D
	x (modifier letter double prime - 02BA)
	x (combining double acute accent - 030B)
	x (combining double vertical line above - 030E)
	x (double prime - 2033)
	x (ditto mark - 3003)
0023	NUMBER SIGN
	= pound sign, hash, crosshatch, octothorpe
0024	DOLLAR SIGN
	= milreis, escudo
	* glyph may have one or two vertical bars
	* other currency symbol characters: 20A0-20AF
	x (currency sign - 00A4)
0025	PERCENT SIGN
	x (arabic percent sign - 066A)
	x (per mille sign - 2030)
	x (per ten thousand sign - 2031)
0026	AMPERSAND
0027	APOSTROPHE
	= APOSTROPHE-QUOTE
	* neutral (vertical) glyph having mixed usage
	* preferred character for apostrophe is 2019
	* preferred characters in English for paired quotation marks are 2018 & 2019
	x (modifier letter prime - 02B9)
	x (modifier letter apostrophe - 02BC)
	x (modifier letter vertical line - 02C8)
	x (combining acute accent - 0301)
	x (prime - 2032)
0028	LEFT PARENTHESIS
	= OPENING PARENTHESIS
0029	RIGHT PARENTHESIS
	= CLOSING PARENTHESIS
	* see discussion on semantics of paired bracketing characters
002A	ASTERISK
	= star (on phone keypads)
	x (arabic five pointed star - 066D)
	x (asterisk operator - 2217)
	x (heavy asterisk - 2731)
002B	PLUS SIGN
002C	COMMA
	= decimal separator
	x (arabic comma - 060C)
	x (single low-9 quotation mark - 201A)
	x (ideographic comma - 3001)
002D	HYPHEN-MINUS
	= hyphen or minus sign
	* used for either hyphen or minus sign
	x (hyphen - 2010)
	x (non-breaking hyphen - 2011)
	x (figure dash - 2012)
	x (en dash - 2013)
	x (minus sign - 2212)
002E	FULL STOP
	= PERIOD
	= dot, decimal point
	* may be rendered as a raised decimal point in old style numbers
	x (arabic full stop - 06D4)
	x (ideographic full stop - 3002)
002F	SOLIDUS
	= SLASH
	= virgule, shilling (British)
	x (latin letter dental click - 01C0)
	x (combining long solidus overlay - 0338)
	x (fraction slash - 2044)
	x (division slash - 2215)
0030	DIGIT ZERO
0031	DIGIT ONE
0032	DIGIT TWO
0033	DIGIT THREE
0034	DIGIT FOUR
0035	DIGIT FIVE
0036	DIGIT SIX
0037	DIGIT SEVEN
0038	DIGIT EIGHT
0039	DIGIT NINE
003A	COLON
	x (armenian full stop - 0589)
	x (ratio - 2236)
003B	SEMICOLON
	x (greek question mark - 037E)
	x (arabic semicolon - 061B)
003C	LESS-THAN SIGN
	x (single left-pointing angle quotation mark - 2039)
	x (left-pointing angle bracket - 2329)
	x (left angle bracket - 3008)
003D	EQUALS SIGN
	* other related characters: 2241-2263
	x (not equal to - 2260)
	x (identical to - 2261)
003E	GREATER-THAN SIGN
	x (single right-pointing angle quotation mark - 203A)
	x (right-pointing angle bracket - 232A)
	x (right angle bracket - 3009)
003F	QUESTION MARK
	x (inverted question mark - 00BF)
	x (greek question mark - 037E)
	x (arabic question mark - 061F)
	x (interrobang - 203D)
	x (question exclamation mark - 2048)
	x (exclamation question mark - 2049)
0040	COMMERCIAL AT
0041	LATIN CAPITAL LETTER A
0042	LATIN CAPITAL LETTER B
	x (script capital b - 212C)
0043	LATIN CAPITAL LETTER C
	x (double-struck capital c - 2102)
	x (black-letter capital c - 212D)
0044	LATIN CAPITAL LETTER D
0045	LATIN CAPITAL LETTER E
	x (euler constant - 2107)
	x (script capital e - 2130)
0046	LATIN CAPITAL LETTER F
	x (script capital f - 2131)
	x (turned capital f - 2132)
0047	LATIN CAPITAL LETTER G
0048	LATIN CAPITAL LETTER H
	x (script capital h - 210B)
	x (black-letter capital h - 210C)
	x (double-struck capital h - 210D)
0049	LATIN CAPITAL LETTER I
	* Turkish and Azerbaijani use 0131 for lowercase
	x (latin capital letter i with dot above - 0130)
	x (cyrillic capital letter byelorussian-ukrainian i - 0406)
	x (cyrillic letter palochka - 04C0)
	x (script capital i - 2110)
	x (black-letter capital i - 2111)
	x (roman numeral one - 2160)
004A	LATIN CAPITAL LETTER J
004B	LATIN CAPITAL LETTER K
	x (kelvin sign - 212A)
004C	LATIN CAPITAL LETTER L
	x (script capital l - 2112)
004D	LATIN CAPITAL LETTER M
	x (script capital m - 2133)
004E	LATIN CAPITAL LETTER N
	x (double-struck capital n - 2115)
004F	LATIN CAPITAL LETTER O
0050	LATIN CAPITAL LETTER P
	x (double-struck capital p - 2119)
0051	LATIN CAPITAL LETTER Q
	x (double-struck capital q - 211A)
0052	LATIN CAPITAL LETTER R
	x (script capital r - 211B)
	x (black-letter capital r - 211C)
	x (double-struck capital r - 211D)
0053	LATIN CAPITAL LETTER S
0054	LATIN CAPITAL LETTER T
0055	LATIN CAPITAL LETTER U
0056	LATIN CAPITAL LETTER V
0057	LATIN CAPITAL LETTER W
0058	LATIN CAPITAL LETTER X
0059	LATIN CAPITAL LETTER Y
005A	LATIN CAPITAL LETTER Z
	x (double-struck capital z - 2124)
	x (black-letter capital z - 2128)
005B	LEFT SQUARE BRACKET
	= OPENING SQUARE BRACKET
	* other bracket characters: 3008-301B
005C	REVERSE SOLIDUS
	= BACKSLASH
	x (set minus - 2216)
005D	RIGHT SQUARE BRACKET
	= CLOSING SQUARE BRACKET
005E	CIRCUMFLEX ACCENT
	* this is a spacing character
	x (modifier letter up arrowhead - 02C4)
	x (modifier letter circumflex accent - 02C6)
	x (combining circumflex accent - 0302)
	x (up arrowhead - 2303)
005F	LOW LINE
	= SPACING UNDERSCORE
	* this is a spacing character
	x (modifier letter low macron - 02CD)
	x (combining macron below - 0331)
	x (combining low line - 0332)
	x (double low line - 2017)
0060	GRAVE ACCENT
	* this is a spacing character
	x (modifier letter grave accent - 02CB)
	x (combining grave accent - 0300)
	x (reversed prime - 2035)
0061	LATIN SMALL LETTER A
0062	LATIN SMALL LETTER B
0063	LATIN SMALL LETTER C
0064	LATIN SMALL LETTER D
0065	LATIN SMALL LETTER E
	x (estimated symbol - 212E)
	x (script small e - 212F)
0066	LATIN SMALL LETTER F
0067	LATIN SMALL LETTER G
	x (latin small letter script g - 0261)
	x (script small g - 210A)
0068	LATIN SMALL LETTER H
	x (cyrillic small letter shha - 04BB)
	x (planck constant - 210E)
0069	LATIN SMALL LETTER I
	* Turkish and Azerbaijani use 0130 for uppercase
	x (latin small letter dotless i - 0131)
006A	LATIN SMALL LETTER J
006B	LATIN SMALL LETTER K
006C	LATIN SMALL LETTER L
	x (script small l - 2113)
006D	LATIN SMALL LETTER M
006E	LATIN SMALL LETTER N
	x (superscript latin small letter n - 207F)
006F	LATIN SMALL LETTER O
	x (script small o - 2134)
0070	LATIN SMALL LETTER P
0071	LATIN SMALL LETTER Q
0072	LATIN SMALL LETTER R
0073	LATIN SMALL LETTER S
0074	LATIN SMALL LETTER T
0075	LATIN SMALL LETTER U
0076	LATIN SMALL LETTER V
0077	LATIN SMALL LETTER W
0078	LATIN SMALL LETTER X
0079	LATIN SMALL LETTER Y
007A	LATIN SMALL LETTER Z
	x (latin small letter z with stroke - 01B6)
007B	LEFT CURLY BRACKET
	= OPENING CURLY BRACKET
	= opening brace
007C	VERTICAL LINE
	= VERTICAL BAR
	* used in pairs to indicate absolute value
	x (latin letter dental click - 01C0)
	x (divides - 2223)
	x (light vertical bar - 2758)
007D	RIGHT CURLY BRACKET
	= CLOSING CURLY BRACKET
	= closing brace
007E	TILDE
	* this is a spacing character
	x (small tilde - 02DC)
	x (combining tilde - 0303)
	x (tilde operator - 223C)
	x (fullwidth tilde - FF5E)
007F	<control>
	= DELETE
@@	0080	C1 Controls and Latin-1 Supplement (Latin-1 Supplement)	00FF
@		C1 controls
@+		Alias names are those for ISO 6429.
0080	<control>
0081	<control>
0082	<control>
	= BREAK PERMITTED HERE
0083	<control>
	= NO BREAK HERE
0084	<control>
	= INDEX
0085	<control>
	= NEXT LINE
0086	<control>
	= START OF SELECTED AREA
0087	<control>
	= END OF SELECTED AREA
0088	<control>
	= CHARACTER TABULATION SET
0089	<control>
	= CHARACTER TABULATION WITH JUSTIFICATION
008A	<control>
	= LINE TABULATION SET
008B	<control>
	= PARTIAL LINE DOWN
008C	<control>
	= PARTIAL LINE UP
008D	<control>
	= REVERSE LINE FEED
008E	<control>
	= SINGLE SHIFT TWO
008F	<control>
	= SINGLE SHIFT THREE
0090	<control>
	= DEVICE CONTROL STRING
0091	<control>
	= PRIVATE USE ONE
0092	<control>
	= PRIVATE USE TWO
0093	<control>
	= SET TRANSMIT STATE
0094	<control>
	= CANCEL CHARACTER
0095	<control>
	= MESSAGE WAITING
0096	<control>
	= START OF GUARDED AREA
0097	<control>
	= END OF GUARDED AREA
0098	<control>
	= START OF STRING
0099	<control>
009A	<control>
	= SINGLE CHARACTER INTRODUCER
009B	<control>
	= CONTROL SEQUENCE INTRODUCER
009C	<control>
	= STRING TERMINATOR
009D	<control>
	= OPERATING SYSTEM COMMAND
009E	<control>
	= PRIVACY MESSAGE
009F	<control>
	= APPLICATION PROGRAM COMMAND
@		ISO 8859-1 (aka Latin-1)
00A0	NO-BREAK SPACE
	x (space - 0020)
	x (figure space - 2007)
	x (narrow no-break space - 202F)
	x (zero width no-break space - FEFF)
	# <noBreak> 0020
00A1	INVERTED EXCLAMATION MARK
	* Spanish, Asturian, Galician
	x (exclamation mark - 0021)
00A2	CENT SIGN
00A3	POUND SIGN
	= pound sterling, Irish punt
	x (lira sign - 20A4)
00A4	CURRENCY SIGN
	* other currency symbol characters: 20A0-20AF
	x (dollar sign - 0024)
00A5	YEN SIGN
	= yuan sign
	* glyph may have one or two crossbars
00A6	BROKEN BAR
	= BROKEN VERTICAL BAR
	= parted rule (in typography)
00A7	SECTION SIGN
	* paragraph sign in some European usage
00A8	DIAERESIS
	* this is a spacing character
	x (combining diaeresis - 0308)
	# 0020 0308
00A9	COPYRIGHT SIGN
	x (sound recording copyright - 2117)
00AA	FEMININE ORDINAL INDICATOR
	* Spanish
	# <super> 0061
00AB	LEFT-POINTING DOUBLE ANGLE QUOTATION MARK *
	= LEFT POINTING GUILLEMET
	= chevrons (in typography)
	* usually opening, sometimes closing
	x (much less-than - 226A)
	x (left double angle bracket - 300A)
00AC	NOT SIGN
	= angled dash (in typography)
	x (reversed not sign - 2310)
00AD	SOFT HYPHEN
	= discretionary hyphen
	x (mongolian todo soft hyphen - 1806)
00AE	REGISTERED SIGN
	= REGISTERED TRADE MARK SIGN