Initial commit of OpenSPARC T2 architecture model.

[OpenSPARC-T2-SAM] / sam-t2 / devtools / v8plus / lib / perl5 / 5.8.8 / unicore / NamesList.txt

@@@	The Unicode Standard 4.1
@@@+	U41M050317.lst
	Draft Unicode 4.1 names list.
	Major merger of post-Unicode 4.0 additions with Amd1 name file (xia050208.lst).
	Accumulation of fixes post-Unicode 4.0. (5th collection)
	Add alias for 2D53.
	Corrected alias for 2697.
	Subdivided headers for Modifier Tone Letters.
	Add xrefs for 1DC0 and 1DC3.
	Updated annotation for 301C.
	Add xref to 2026 and 22EE for FE19.
	This file is semi-automatically derived from UnicodeData.txt and
	a set of manually created annotations using a script to select
	or suppress information from the data file. The rules used
	for this process are aimed at readability for the human reader,
	at the expense of some details; therefore, this file should not
	be parsed for machine-readable information.
@+		Copyright (c) 1991-2005 Unicode, Inc.
	For terms of use, see http://www.unicode.org/terms_of_use.html
@@	0000	C0 Controls and Basic Latin (Basic Latin)	007F
@		C0 controls
@+		Alias names are those for ISO/IEC 6429:1992. Commonly used alternative aliases are also shown.
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>
	= CHARACTER TABULATION
	= horizontal tabulation (HT), tab
000A	<control>
	= LINE FEED (LF)
	= new line (NL), end of line (EOL)
000B	<control>
	= LINE TABULATION
	= vertical tabulation (VT)
000C	<control>
	= FORM FEED (FF)
000D	<control>
	= CARRIAGE RETURN (CR)
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>
	= INFORMATION SEPARATOR FOUR
	= file separator (FS)
001D	<control>
	= INFORMATION SEPARATOR THREE
	= group separator (GS)
001E	<control>
	= INFORMATION SEPARATOR TWO
	= record separator (RS)
001F	<control>
	= INFORMATION SEPARATOR ONE
	= unit separator (US)
@		ASCII punctuation and symbols
@+		Based on ISO/IEC 646 from here.
0020	SPACE
	* sometimes considered a control code
	* other space characters: 2000-200A
	x (no-break space - 00A0)
	x (zero width space - 200B)
	x (word joiner - 2060)
	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
	* 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
	x (music sharp sign - 266F)
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)
	x (commercial minus sign - 2052)
0026	AMPERSAND
0027	APOSTROPHE
	= APOSTROPHE-QUOTE
	= APL quote
	* neutral (vertical) glyph with mixed usage
	* 2019 is preferred for apostrophe
	* 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 (low asterisk - 204E)
	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)
@		ASCII digits
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
@		ASCII punctuation and symbols
003A	COLON
	x (armenian full stop - 0589)
	x (hebrew punctuation sof pasuq - 05C3)
	x (ratio - 2236)
003B	SEMICOLON
	* this, and not 037E, is the preferred character for 'Greek question mark'
	x (greek question mark - 037E)
	x (arabic semicolon - 061B)
	x (reversed semicolon - 204F)
003C	LESS-THAN SIGN
	x (single left-pointing angle quotation mark - 2039)
	x (left-pointing angle bracket - 2329)
	x (mathematical left angle bracket - 27E8)
	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 (mathematical right angle bracket - 27E9)
	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
	= Klammeraffe (common, humorous slang German name)
@		Uppercase Latin alphabet
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
	* invented circa 300 BCE by Spurius Carvilius Ruga, who added a stroke to the letter C
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)
@		ASCII punctuation and symbols
005B	LEFT SQUARE BRACKET
	= OPENING SQUARE BRACKET
	* other bracket characters: 3008-301B
005C	REVERSE SOLIDUS
	= BACKSLASH
	x (combining reverse solidus overlay - 20E5)
	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)
@		Lowercase Latin alphabet
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)
@		ASCII punctuation and symbols
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 (hebrew punctuation paseq - 05C0)
	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 (swung dash - 2053)
	x (tilde operator - 223C)
	x (fullwidth tilde - FF5E)
@		Control character
007F	<control>
	= DELETE
@@	0080	C1 Controls and Latin-1 Supplement (Latin-1 Supplement)	00FF
@		C1 controls
@+		Alias names are those for ISO/IEC 6429:1992.
0080	<control>
0081	<control>
0082	<control>
	= BREAK PERMITTED HERE
0083	<control>
	= NO BREAK HERE
0084	<control>
0085	<control>
	= NEXT LINE (NEL)
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 FORWARD
008C	<control>
	= PARTIAL LINE BACKWARD
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
@		Latin-1 punctuation and symbols
@+		Based on ISO/IEC 8859-1 (aka Latin-1) from here.
00A0	NO-BREAK SPACE
	= NBSP
	x (space - 0020)
	x (figure space - 2007)
	x (narrow no-break space - 202F)
	x (word joiner - 2060)
	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, Italian lira, Turkish lira, etc.
	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
	= SHY
	= discretionary hyphen
	x (mongolian todo soft hyphen - 1806)
00AE	REGISTERED SIGN
	= REGISTERED TRADE MARK SIGN
00AF	MACRON
	= overline, APL overbar
	* this is a spacing character
	x (modifier letter macron - 02C9)
	x (combining macron - 0304)
	x (combining overline - 0305)
	# 0020 0304
00B0	DEGREE SIGN
	* this is a spacing character
	x (ring above - 02DA)
	x (combining ring above - 030A)
	x (superscript zero - 2070)
	x (ring operator - 2218)
00B1	PLUS-MINUS SIGN
	x (minus-or-plus sign - 2213)
00B2	SUPERSCRIPT TWO
	= squared
	* other superscript digit characters: 2070-2079
	x (superscript one - 00B9)
	# <super> 0032
00B3	SUPERSCRIPT THREE
	= cubed
	x (superscript one - 00B9)
	# <super> 0033
00B4	ACUTE ACCENT
	* this is a spacing character
	x (modifier letter prime - 02B9)
	x (modifier letter acute accent - 02CA)
	x (combining acute accent - 0301)
	x (prime - 2032)
	# 0020 0301
00B5	MICRO SIGN
	# 03BC greek small letter mu
00B6	PILCROW SIGN
	= PARAGRAPH SIGN
	* section sign in some European usage
	x (reversed pilcrow sign - 204B)
	x (curved stem paragraph sign ornament - 2761)
00B7	MIDDLE DOT
	= midpoint (in typography)
	= Georgian comma
	= Greek middle dot (ano teleia)
	x (greek ano teleia - 0387)
	x (bullet - 2022)
	x (one dot leader - 2024)
	x (hyphenation point - 2027)
	x (bullet operator - 2219)
	x (dot operator - 22C5)
	x (katakana middle dot - 30FB)
00B8	CEDILLA
	* this is a spacing character
	* other spacing accent characters: 02D8-02DB
	x (combining cedilla - 0327)
	# 0020 0327
00B9	SUPERSCRIPT ONE
	x (superscript two - 00B2)
	x (superscript three - 00B3)
	# <super> 0031
00BA	MASCULINE ORDINAL INDICATOR
	* Spanish
	# <super> 006F
00BB	RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK *
	= RIGHT POINTING GUILLEMET
	* usually closing, sometimes opening
	x (much greater-than - 226B)
	x (right double angle bracket - 300B)
00BC	VULGAR FRACTION ONE QUARTER
	* bar may be horizontal or slanted
	* other fraction characters: 2153-215E
	# <fraction> 0031 2044 0034
00BD	VULGAR FRACTION ONE HALF
	* bar may be horizontal or slanted
	# <fraction> 0031 2044 0032
00BE	VULGAR FRACTION THREE QUARTERS
	* bar may be horizontal or slanted
	# <fraction> 0033 2044 0034
00BF	INVERTED QUESTION MARK
	= turned question mark
	* Spanish
	x (question mark - 003F)
@		Letters
00C0	LATIN CAPITAL LETTER A WITH GRAVE
	: 0041 0300
00C1	LATIN CAPITAL LETTER A WITH ACUTE
	: 0041 0301
00C2	LATIN CAPITAL LETTER A WITH CIRCUMFLEX
	: 0041 0302
00C3	LATIN CAPITAL LETTER A WITH TILDE
	: 0041 0303
00C4	LATIN CAPITAL LETTER A WITH DIAERESIS
	: 0041 0308
00C5	LATIN CAPITAL LETTER A WITH RING ABOVE
	x (angstrom sign - 212B)
	: 0041 030A
00C6	LATIN CAPITAL LETTER AE (ash) *
	= LATIN CAPITAL LIGATURE AE
00C7	LATIN CAPITAL LETTER C WITH CEDILLA
	: 0043 0327
00C8	LATIN CAPITAL LETTER E WITH GRAVE
	: 0045 0300
00C9	LATIN CAPITAL LETTER E WITH ACUTE
	: 0045 0301
00CA	LATIN CAPITAL LETTER E WITH CIRCUMFLEX
	: 0045 0302
00CB	LATIN CAPITAL LETTER E WITH DIAERESIS
	: 0045 0308
00CC	LATIN CAPITAL LETTER I WITH GRAVE
	: 0049 0300
00CD	LATIN CAPITAL LETTER I WITH ACUTE
	: 0049 0301
00CE	LATIN CAPITAL LETTER I WITH CIRCUMFLEX
	: 0049 0302
00CF	LATIN CAPITAL LETTER I WITH DIAERESIS
	: 0049 0308
00D0	LATIN CAPITAL LETTER ETH (Icelandic)
	x (latin small letter eth - 00F0)
	x (latin capital letter d with stroke - 0110)
	x (latin capital letter african d - 0189)
00D1	LATIN CAPITAL LETTER N WITH TILDE
	: 004E 0303
00D2	LATIN CAPITAL LETTER O WITH GRAVE
	: 004F 0300
00D3	LATIN CAPITAL LETTER O WITH ACUTE
	: 004F 0301
00D4	LATIN CAPITAL LETTER O WITH CIRCUMFLEX
	: 004F 0302
00D5	LATIN CAPITAL LETTER O WITH TILDE
	: 004F 0303
00D6	LATIN CAPITAL LETTER O WITH DIAERESIS
	: 004F 0308
@		Mathematical operator
00D7	MULTIPLICATION SIGN
	= z notation Cartesian product
@		Letters
00D8	LATIN CAPITAL LETTER O WITH STROKE
	= LATIN CAPITAL LETTER O SLASH
	x (empty set - 2205)
00D9	LATIN CAPITAL LETTER U WITH GRAVE
	: 0055 0300
00DA	LATIN CAPITAL LETTER U WITH ACUTE
	: 0055 0301
00DB	LATIN CAPITAL LETTER U WITH CIRCUMFLEX
	: 0055 0302
00DC	LATIN CAPITAL LETTER U WITH DIAERESIS
	: 0055 0308
00DD	LATIN CAPITAL LETTER Y WITH ACUTE
	: 0059 0301
00DE	LATIN CAPITAL LETTER THORN (Icelandic)
00DF	LATIN SMALL LETTER SHARP S (German)
	= Eszett
	* German
	* uppercase is "SS"
	* in origin a ligature of 017F and 0073
	x (greek small letter beta - 03B2)
00E0	LATIN SMALL LETTER A WITH GRAVE
	: 0061 0300
00E1	LATIN SMALL LETTER A WITH ACUTE
	: 0061 0301
00E2	LATIN SMALL LETTER A WITH CIRCUMFLEX
	: 0061 0302
00E3	LATIN SMALL LETTER A WITH TILDE
	* Portuguese
	: 0061 0303
00E4	LATIN SMALL LETTER A WITH DIAERESIS
	: 0061 0308
00E5	LATIN SMALL LETTER A WITH RING ABOVE
	* Danish, Norwegian, Swedish, Walloon
	: 0061 030A
00E6	LATIN SMALL LETTER AE (ash) *
	= LATIN SMALL LIGATURE AE