1013 lines
31 KiB
Plaintext
1013 lines
31 KiB
Plaintext
# PropertyValueAliases-5.1.0.txt
|
|
# Date: 2008-03-03, 21:58:08 GMT [MD]
|
|
#
|
|
# Unicode Character Database
|
|
# Copyright (c) 1991-2008 Unicode, Inc.
|
|
# For terms of use, see http://www.unicode.org/terms_of_use.html
|
|
# For documentation, see UCD.html
|
|
#
|
|
# This file contains aliases for property values used in the UCD.
|
|
# These names can be used for XML formats of UCD data, for regular-expression
|
|
# property tests, and other programmatic textual descriptions of Unicode data.
|
|
# For information on which properties are normative, see UCD.html.
|
|
#
|
|
# The names may be translated in appropriate environments, and additional
|
|
# aliases may be useful.
|
|
#
|
|
# FORMAT
|
|
#
|
|
# Each line describes a property value name.
|
|
# This consists of three or more fields, separated by semicolons.
|
|
#
|
|
# First Field: The first field describes the property for which that
|
|
# property value name is used.
|
|
#
|
|
# Second Field: The second field is an abbreviated name.
|
|
# If there is no abbreviated name available, the field is marked with "n/a".
|
|
#
|
|
# Third Field: The third field is a long name.
|
|
#
|
|
# In the case of ccc, there are 4 fields. The second field is numeric, third
|
|
# is abbreviated, and fourth is long.
|
|
#
|
|
# The above are the preferred aliases. Other aliases may be listed in additional fields.
|
|
#
|
|
# Loose matching should be applied to all property names and property values, with
|
|
# the exception of String Property values. With loose matching of property names and
|
|
# values, the case distinctions, whitespace, and '_' are ignored. For Numeric Property
|
|
# values, numeric equivalencies are applied: thus "01.00" is equivalent to "1".
|
|
#
|
|
# NOTE: Property value names are NOT unique across properties. For example:
|
|
#
|
|
# AL means Arabic Letter for the Bidi_Class property, and
|
|
# AL means Alpha_Left for the Combining_Class property, and
|
|
# AL means Alphabetic for the Line_Break property.
|
|
#
|
|
# In addition, some property names may be the same as some property value names.
|
|
# For example:
|
|
#
|
|
# sc means the Script property, and
|
|
# Sc means the General_Category property value Currency_Symbol (Sc)
|
|
#
|
|
# The combination of property value and property name is, however, unique.
|
|
#
|
|
# For more information, see UTS #18: Regular Expression Guidelines
|
|
# ================================================
|
|
|
|
|
|
# ASCII_Hex_Digit (AHex)
|
|
|
|
AHex; N ; No ; F ; False
|
|
AHex; Y ; Yes ; T ; True
|
|
|
|
# Age (age)
|
|
|
|
age; n/a ; 1.1
|
|
age; n/a ; 2.0
|
|
age; n/a ; 2.1
|
|
age; n/a ; 3.0
|
|
age; n/a ; 3.1
|
|
age; n/a ; 3.2
|
|
age; n/a ; 4.0
|
|
age; n/a ; 4.1
|
|
age; n/a ; 5.0
|
|
age; n/a ; 5.1
|
|
age; n/a ; unassigned
|
|
|
|
# Alphabetic (Alpha)
|
|
|
|
Alpha; N ; No ; F ; False
|
|
Alpha; Y ; Yes ; T ; True
|
|
|
|
# Bidi_Class (bc)
|
|
|
|
bc ; AL ; Arabic_Letter
|
|
bc ; AN ; Arabic_Number
|
|
bc ; B ; Paragraph_Separator
|
|
bc ; BN ; Boundary_Neutral
|
|
bc ; CS ; Common_Separator
|
|
bc ; EN ; European_Number
|
|
bc ; ES ; European_Separator
|
|
bc ; ET ; European_Terminator
|
|
bc ; L ; Left_To_Right
|
|
bc ; LRE ; Left_To_Right_Embedding
|
|
bc ; LRO ; Left_To_Right_Override
|
|
bc ; NSM ; Nonspacing_Mark
|
|
bc ; ON ; Other_Neutral
|
|
bc ; PDF ; Pop_Directional_Format
|
|
bc ; R ; Right_To_Left
|
|
bc ; RLE ; Right_To_Left_Embedding
|
|
bc ; RLO ; Right_To_Left_Override
|
|
bc ; S ; Segment_Separator
|
|
bc ; WS ; White_Space
|
|
|
|
# Bidi_Control (Bidi_C)
|
|
|
|
Bidi_C; N ; No ; F ; False
|
|
Bidi_C; Y ; Yes ; T ; True
|
|
|
|
# Bidi_Mirrored (Bidi_M)
|
|
|
|
Bidi_M; N ; No ; F ; False
|
|
Bidi_M; Y ; Yes ; T ; True
|
|
|
|
# Bidi_Mirroring_Glyph (bmg)
|
|
|
|
# @missing: 0000..10FFFF; Bidi_Mirroring_Glyph; <none>
|
|
|
|
# Block (blk)
|
|
|
|
blk; n/a ; Aegean_Numbers
|
|
blk; n/a ; Alphabetic_Presentation_Forms
|
|
blk; n/a ; Ancient_Greek_Musical_Notation
|
|
blk; n/a ; Ancient_Greek_Numbers
|
|
blk; n/a ; Ancient_Symbols
|
|
blk; n/a ; Arabic
|
|
blk; n/a ; Arabic_Presentation_Forms_A ; Arabic_Presentation_Forms-A
|
|
blk; n/a ; Arabic_Presentation_Forms_B
|
|
blk; n/a ; Arabic_Supplement
|
|
blk; n/a ; Armenian
|
|
blk; n/a ; Arrows
|
|
blk; n/a ; Balinese
|
|
blk; n/a ; Basic_Latin ; ASCII
|
|
blk; n/a ; Bengali
|
|
blk; n/a ; Block_Elements
|
|
blk; n/a ; Bopomofo
|
|
blk; n/a ; Bopomofo_Extended
|
|
blk; n/a ; Box_Drawing
|
|
blk; n/a ; Braille_Patterns
|
|
blk; n/a ; Buginese
|
|
blk; n/a ; Buhid
|
|
blk; n/a ; Byzantine_Musical_Symbols
|
|
blk; n/a ; Carian
|
|
blk; n/a ; Cham
|
|
blk; n/a ; Cherokee
|
|
blk; n/a ; CJK_Compatibility
|
|
blk; n/a ; CJK_Compatibility_Forms
|
|
blk; n/a ; CJK_Compatibility_Ideographs
|
|
blk; n/a ; CJK_Compatibility_Ideographs_Supplement
|
|
blk; n/a ; CJK_Radicals_Supplement
|
|
blk; n/a ; CJK_Strokes
|
|
blk; n/a ; CJK_Symbols_And_Punctuation
|
|
blk; n/a ; CJK_Unified_Ideographs
|
|
blk; n/a ; CJK_Unified_Ideographs_Extension_A
|
|
blk; n/a ; CJK_Unified_Ideographs_Extension_B
|
|
blk; n/a ; Combining_Diacritical_Marks
|
|
blk; n/a ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols
|
|
blk; n/a ; Combining_Diacritical_Marks_Supplement
|
|
blk; n/a ; Combining_Half_Marks
|
|
blk; n/a ; Control_Pictures
|
|
blk; n/a ; Coptic
|
|
blk; n/a ; Counting_Rod_Numerals
|
|
blk; n/a ; Cuneiform
|
|
blk; n/a ; Cuneiform_Numbers_And_Punctuation
|
|
blk; n/a ; Currency_Symbols
|
|
blk; n/a ; Cypriot_Syllabary
|
|
blk; n/a ; Cyrillic
|
|
blk; n/a ; Cyrillic_Extended_A
|
|
blk; n/a ; Cyrillic_Extended_B
|
|
blk; n/a ; Cyrillic_Supplement ; Cyrillic_Supplementary
|
|
blk; n/a ; Deseret
|
|
blk; n/a ; Devanagari
|
|
blk; n/a ; Dingbats
|
|
blk; n/a ; Domino_Tiles
|
|
blk; n/a ; Enclosed_Alphanumerics
|
|
blk; n/a ; Enclosed_CJK_Letters_And_Months
|
|
blk; n/a ; Ethiopic
|
|
blk; n/a ; Ethiopic_Extended
|
|
blk; n/a ; Ethiopic_Supplement
|
|
blk; n/a ; General_Punctuation
|
|
blk; n/a ; Geometric_Shapes
|
|
blk; n/a ; Georgian
|
|
blk; n/a ; Georgian_Supplement
|
|
blk; n/a ; Glagolitic
|
|
blk; n/a ; Gothic
|
|
blk; n/a ; Greek_And_Coptic ; Greek
|
|
blk; n/a ; Greek_Extended
|
|
blk; n/a ; Gujarati
|
|
blk; n/a ; Gurmukhi
|
|
blk; n/a ; Halfwidth_And_Fullwidth_Forms
|
|
blk; n/a ; Hangul_Compatibility_Jamo
|
|
blk; n/a ; Hangul_Jamo
|
|
blk; n/a ; Hangul_Syllables
|
|
blk; n/a ; Hanunoo
|
|
blk; n/a ; Hebrew
|
|
blk; n/a ; High_Private_Use_Surrogates
|
|
blk; n/a ; High_Surrogates
|
|
blk; n/a ; Hiragana
|
|
blk; n/a ; Ideographic_Description_Characters
|
|
blk; n/a ; IPA_Extensions
|
|
blk; n/a ; Kanbun
|
|
blk; n/a ; Kangxi_Radicals
|
|
blk; n/a ; Kannada
|
|
blk; n/a ; Katakana
|
|
blk; n/a ; Katakana_Phonetic_Extensions
|
|
blk; n/a ; Kayah_Li
|
|
blk; n/a ; Kharoshthi
|
|
blk; n/a ; Khmer
|
|
blk; n/a ; Khmer_Symbols
|
|
blk; n/a ; Lao
|
|
blk; n/a ; Latin_1_Supplement ; Latin_1
|
|
blk; n/a ; Latin_Extended_A
|
|
blk; n/a ; Latin_Extended_Additional
|
|
blk; n/a ; Latin_Extended_B
|
|
blk; n/a ; Latin_Extended_C
|
|
blk; n/a ; Latin_Extended_D
|
|
blk; n/a ; Lepcha
|
|
blk; n/a ; Letterlike_Symbols
|
|
blk; n/a ; Limbu
|
|
blk; n/a ; Linear_B_Ideograms
|
|
blk; n/a ; Linear_B_Syllabary
|
|
blk; n/a ; Low_Surrogates
|
|
blk; n/a ; Lycian
|
|
blk; n/a ; Lydian
|
|
blk; n/a ; Mahjong_Tiles
|
|
blk; n/a ; Malayalam
|
|
blk; n/a ; Mathematical_Alphanumeric_Symbols
|
|
blk; n/a ; Mathematical_Operators
|
|
blk; n/a ; Miscellaneous_Mathematical_Symbols_A
|
|
blk; n/a ; Miscellaneous_Mathematical_Symbols_B
|
|
blk; n/a ; Miscellaneous_Symbols
|
|
blk; n/a ; Miscellaneous_Symbols_And_Arrows
|
|
blk; n/a ; Miscellaneous_Technical
|
|
blk; n/a ; Modifier_Tone_Letters
|
|
blk; n/a ; Mongolian
|
|
blk; n/a ; Musical_Symbols
|
|
blk; n/a ; Myanmar
|
|
blk; n/a ; New_Tai_Lue
|
|
blk; n/a ; NKo
|
|
blk; n/a ; No_Block
|
|
blk; n/a ; Number_Forms
|
|
blk; n/a ; Ogham
|
|
blk; n/a ; Ol_Chiki
|
|
blk; n/a ; Old_Italic
|
|
blk; n/a ; Old_Persian
|
|
blk; n/a ; Optical_Character_Recognition
|
|
blk; n/a ; Oriya
|
|
blk; n/a ; Osmanya
|
|
blk; n/a ; Phags_Pa
|
|
blk; n/a ; Phaistos_Disc
|
|
blk; n/a ; Phoenician
|
|
blk; n/a ; Phonetic_Extensions
|
|
blk; n/a ; Phonetic_Extensions_Supplement
|
|
blk; n/a ; Private_Use_Area ; Private_Use
|
|
blk; n/a ; Rejang
|
|
blk; n/a ; Runic
|
|
blk; n/a ; Saurashtra
|
|
blk; n/a ; Shavian
|
|
blk; n/a ; Sinhala
|
|
blk; n/a ; Small_Form_Variants
|
|
blk; n/a ; Spacing_Modifier_Letters
|
|
blk; n/a ; Specials
|
|
blk; n/a ; Sundanese
|
|
blk; n/a ; Superscripts_And_Subscripts
|
|
blk; n/a ; Supplemental_Arrows_A
|
|
blk; n/a ; Supplemental_Arrows_B
|
|
blk; n/a ; Supplemental_Mathematical_Operators
|
|
blk; n/a ; Supplemental_Punctuation
|
|
blk; n/a ; Supplementary_Private_Use_Area_A
|
|
blk; n/a ; Supplementary_Private_Use_Area_B
|
|
blk; n/a ; Syloti_Nagri
|
|
blk; n/a ; Syriac
|
|
blk; n/a ; Tagalog
|
|
blk; n/a ; Tagbanwa
|
|
blk; n/a ; Tags
|
|
blk; n/a ; Tai_Le
|
|
blk; n/a ; Tai_Xuan_Jing_Symbols
|
|
blk; n/a ; Tamil
|
|
blk; n/a ; Telugu
|
|
blk; n/a ; Thaana
|
|
blk; n/a ; Thai
|
|
blk; n/a ; Tibetan
|
|
blk; n/a ; Tifinagh
|
|
blk; n/a ; Ugaritic
|
|
blk; n/a ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics
|
|
blk; n/a ; Vai
|
|
blk; n/a ; Variation_Selectors
|
|
blk; n/a ; Variation_Selectors_Supplement
|
|
blk; n/a ; Vertical_Forms
|
|
blk; n/a ; Yi_Radicals
|
|
blk; n/a ; Yi_Syllables
|
|
blk; n/a ; Yijing_Hexagram_Symbols
|
|
|
|
# Canonical_Combining_Class (ccc)
|
|
|
|
ccc; 0; NR ; Not_Reordered
|
|
ccc; 1; OV ; Overlay
|
|
ccc; 7; NK ; Nukta
|
|
ccc; 8; KV ; Kana_Voicing
|
|
ccc; 9; VR ; Virama
|
|
ccc; 200; ATBL ; Attached_Below_Left
|
|
ccc; 202; ATB ; Attached_Below
|
|
ccc; 216; ATAR ; Attached_Above_Right
|
|
ccc; 218; BL ; Below_Left
|
|
ccc; 220; B ; Below
|
|
ccc; 222; BR ; Below_Right
|
|
ccc; 224; L ; Left
|
|
ccc; 226; R ; Right
|
|
ccc; 228; AL ; Above_Left
|
|
ccc; 230; A ; Above
|
|
ccc; 232; AR ; Above_Right
|
|
ccc; 233; DB ; Double_Below
|
|
ccc; 234; DA ; Double_Above
|
|
ccc; 240; IS ; Iota_Subscript
|
|
|
|
# Case_Folding (cf)
|
|
|
|
# @missing: 0000..10FFFF; Case_Folding; <code point>
|
|
|
|
# Composition_Exclusion (CE)
|
|
|
|
CE ; N ; No ; F ; False
|
|
CE ; Y ; Yes ; T ; True
|
|
|
|
# Dash (Dash)
|
|
|
|
Dash; N ; No ; F ; False
|
|
Dash; Y ; Yes ; T ; True
|
|
|
|
# Decomposition_Mapping (dm)
|
|
|
|
# @missing: 0000..10FFFF; Decomposition_Mapping; <code point>
|
|
|
|
# Decomposition_Type (dt)
|
|
|
|
dt ; Can ; Canonical ; can
|
|
dt ; Com ; Compat ; com
|
|
dt ; Enc ; Circle ; enc
|
|
dt ; Fin ; Final ; fin
|
|
dt ; Font ; font
|
|
dt ; Fra ; Fraction ; fra
|
|
dt ; Init ; Initial ; init
|
|
dt ; Iso ; Isolated ; iso
|
|
dt ; Med ; Medial ; med
|
|
dt ; Nar ; Narrow ; nar
|
|
dt ; Nb ; Nobreak ; nb
|
|
dt ; None ; none
|
|
dt ; Sml ; Small ; sml
|
|
dt ; Sqr ; Square ; sqr
|
|
dt ; Sub ; sub
|
|
dt ; Sup ; Super ; sup
|
|
dt ; Vert ; Vertical ; vert
|
|
dt ; Wide ; wide
|
|
|
|
# Default_Ignorable_Code_Point (DI)
|
|
|
|
DI ; N ; No ; F ; False
|
|
DI ; Y ; Yes ; T ; True
|
|
|
|
# Deprecated (Dep)
|
|
|
|
Dep; N ; No ; F ; False
|
|
Dep; Y ; Yes ; T ; True
|
|
|
|
# Diacritic (Dia)
|
|
|
|
Dia; N ; No ; F ; False
|
|
Dia; Y ; Yes ; T ; True
|
|
|
|
# East_Asian_Width (ea)
|
|
|
|
ea ; A ; Ambiguous
|
|
ea ; F ; Fullwidth
|
|
ea ; H ; Halfwidth
|
|
ea ; N ; Neutral
|
|
ea ; Na ; Narrow
|
|
ea ; W ; Wide
|
|
|
|
# Expands_On_NFC (XO_NFC)
|
|
|
|
XO_NFC; N ; No ; F ; False
|
|
XO_NFC; Y ; Yes ; T ; True
|
|
|
|
# Expands_On_NFD (XO_NFD)
|
|
|
|
XO_NFD; N ; No ; F ; False
|
|
XO_NFD; Y ; Yes ; T ; True
|
|
|
|
# Expands_On_NFKC (XO_NFKC)
|
|
|
|
XO_NFKC; N ; No ; F ; False
|
|
XO_NFKC; Y ; Yes ; T ; True
|
|
|
|
# Expands_On_NFKD (XO_NFKD)
|
|
|
|
XO_NFKD; N ; No ; F ; False
|
|
XO_NFKD; Y ; Yes ; T ; True
|
|
|
|
# Extender (Ext)
|
|
|
|
Ext; N ; No ; F ; False
|
|
Ext; Y ; Yes ; T ; True
|
|
|
|
# FC_NFKC_Closure (FC_NFKC)
|
|
|
|
# @missing: 0000..10FFFF; FC_NFKC_Closure; <code point>
|
|
|
|
# Full_Composition_Exclusion (Comp_Ex)
|
|
|
|
Comp_Ex; N ; No ; F ; False
|
|
Comp_Ex; Y ; Yes ; T ; True
|
|
|
|
# General_Category (gc)
|
|
|
|
gc ; C ; Other # Cc | Cf | Cn | Co | Cs
|
|
gc ; Cc ; Control ; cntrl
|
|
gc ; Cf ; Format
|
|
gc ; Cn ; Unassigned
|
|
gc ; Co ; Private_Use
|
|
gc ; Cs ; Surrogate
|
|
gc ; L ; Letter # Ll | Lm | Lo | Lt | Lu
|
|
gc ; LC ; Cased_Letter # Ll | Lt | Lu
|
|
gc ; Ll ; Lowercase_Letter
|
|
gc ; Lm ; Modifier_Letter
|
|
gc ; Lo ; Other_Letter
|
|
gc ; Lt ; Titlecase_Letter
|
|
gc ; Lu ; Uppercase_Letter
|
|
gc ; M ; Mark # Mc | Me | Mn
|
|
gc ; Mc ; Spacing_Mark
|
|
gc ; Me ; Enclosing_Mark
|
|
gc ; Mn ; Nonspacing_Mark
|
|
gc ; N ; Number # Nd | Nl | No
|
|
gc ; Nd ; Decimal_Number ; digit
|
|
gc ; Nl ; Letter_Number
|
|
gc ; No ; Other_Number
|
|
gc ; P ; Punctuation ; punct # Pc | Pd | Pe | Pf | Pi | Po | Ps
|
|
gc ; Pc ; Connector_Punctuation
|
|
gc ; Pd ; Dash_Punctuation
|
|
gc ; Pe ; Close_Punctuation
|
|
gc ; Pf ; Final_Punctuation
|
|
gc ; Pi ; Initial_Punctuation
|
|
gc ; Po ; Other_Punctuation
|
|
gc ; Ps ; Open_Punctuation
|
|
gc ; S ; Symbol # Sc | Sk | Sm | So
|
|
gc ; Sc ; Currency_Symbol
|
|
gc ; Sk ; Modifier_Symbol
|
|
gc ; Sm ; Math_Symbol
|
|
gc ; So ; Other_Symbol
|
|
gc ; Z ; Separator # Zl | Zp | Zs
|
|
gc ; Zl ; Line_Separator
|
|
gc ; Zp ; Paragraph_Separator
|
|
gc ; Zs ; Space_Separator
|
|
|
|
# Grapheme_Base (Gr_Base)
|
|
|
|
Gr_Base; N ; No ; F ; False
|
|
Gr_Base; Y ; Yes ; T ; True
|
|
|
|
# Grapheme_Cluster_Break (GCB)
|
|
|
|
GCB; CN ; Control
|
|
GCB; CR ; CR
|
|
GCB; EX ; Extend
|
|
GCB; L ; L
|
|
GCB; LF ; LF
|
|
GCB; LV ; LV
|
|
GCB; LVT ; LVT
|
|
GCB; PP ; Prepend
|
|
GCB; SM ; SpacingMark
|
|
GCB; T ; T
|
|
GCB; V ; V
|
|
GCB; XX ; Other
|
|
|
|
# Grapheme_Extend (Gr_Ext)
|
|
|
|
Gr_Ext; N ; No ; F ; False
|
|
Gr_Ext; Y ; Yes ; T ; True
|
|
|
|
# Grapheme_Link (Gr_Link)
|
|
|
|
Gr_Link; N ; No ; F ; False
|
|
Gr_Link; Y ; Yes ; T ; True
|
|
|
|
# Hangul_Syllable_Type (hst)
|
|
|
|
hst; L ; Leading_Jamo
|
|
hst; LV ; LV_Syllable
|
|
hst; LVT ; LVT_Syllable
|
|
hst; NA ; Not_Applicable
|
|
hst; T ; Trailing_Jamo
|
|
hst; V ; Vowel_Jamo
|
|
|
|
# Hex_Digit (Hex)
|
|
|
|
Hex; N ; No ; F ; False
|
|
Hex; Y ; Yes ; T ; True
|
|
|
|
# Hyphen (Hyphen)
|
|
|
|
Hyphen; N ; No ; F ; False
|
|
Hyphen; Y ; Yes ; T ; True
|
|
|
|
# IDS_Binary_Operator (IDSB)
|
|
|
|
IDSB; N ; No ; F ; False
|
|
IDSB; Y ; Yes ; T ; True
|
|
|
|
# IDS_Trinary_Operator (IDST)
|
|
|
|
IDST; N ; No ; F ; False
|
|
IDST; Y ; Yes ; T ; True
|
|
|
|
# ID_Continue (IDC)
|
|
|
|
IDC; N ; No ; F ; False
|
|
IDC; Y ; Yes ; T ; True
|
|
|
|
# ID_Start (IDS)
|
|
|
|
IDS; N ; No ; F ; False
|
|
IDS; Y ; Yes ; T ; True
|
|
|
|
# ISO_Comment (isc)
|
|
|
|
# @missing: 0000..10FFFF; ISO_Comment; <none>
|
|
|
|
# Ideographic (Ideo)
|
|
|
|
Ideo; N ; No ; F ; False
|
|
Ideo; Y ; Yes ; T ; True
|
|
|
|
# Jamo_Short_Name (JSN)
|
|
|
|
# @missing: 0000..10FFFF; Jamo_Short_Name; <none>
|
|
JSN; A ; A
|
|
JSN; AE ; AE
|
|
JSN; B ; B
|
|
JSN; BB ; BB
|
|
JSN; BS ; BS
|
|
JSN; C ; C
|
|
JSN; D ; D
|
|
JSN; DD ; DD
|
|
JSN; E ; E
|
|
JSN; EO ; EO
|
|
JSN; EU ; EU
|
|
JSN; G ; G
|
|
JSN; GG ; GG
|
|
JSN; GS ; GS
|
|
JSN; H ; H
|
|
JSN; I ; I
|
|
JSN; J ; J
|
|
JSN; JJ ; JJ
|
|
JSN; K ; K
|
|
JSN; L ; L
|
|
JSN; LB ; LB
|
|
JSN; LG ; LG
|
|
JSN; LH ; LH
|
|
JSN; LM ; LM
|
|
JSN; LP ; LP
|
|
JSN; LS ; LS
|
|
JSN; LT ; LT
|
|
JSN; M ; M
|
|
JSN; N ; N
|
|
JSN; NG ; NG
|
|
JSN; NH ; NH
|
|
JSN; NJ ; NJ
|
|
JSN; O ; O
|
|
JSN; OE ; OE
|
|
JSN; P ; P
|
|
JSN; R ; R
|
|
JSN; S ; S
|
|
JSN; SS ; SS
|
|
JSN; T ; T
|
|
JSN; U ; U
|
|
JSN; WA ; WA
|
|
JSN; WAE ; WAE
|
|
JSN; WE ; WE
|
|
JSN; WEO ; WEO
|
|
JSN; WI ; WI
|
|
JSN; YA ; YA
|
|
JSN; YAE ; YAE
|
|
JSN; YE ; YE
|
|
JSN; YEO ; YEO
|
|
JSN; YI ; YI
|
|
JSN; YO ; YO
|
|
JSN; YU ; YU
|
|
|
|
# Join_Control (Join_C)
|
|
|
|
Join_C; N ; No ; F ; False
|
|
Join_C; Y ; Yes ; T ; True
|
|
|
|
# Joining_Group (jg)
|
|
|
|
jg ; n/a ; Ain
|
|
jg ; n/a ; Alaph
|
|
jg ; n/a ; Alef
|
|
jg ; n/a ; Beh
|
|
jg ; n/a ; Beth
|
|
jg ; n/a ; Burushaski_Yeh_Barree
|
|
jg ; n/a ; Dal
|
|
jg ; n/a ; Dalath_Rish
|
|
jg ; n/a ; E
|
|
jg ; n/a ; Fe
|
|
jg ; n/a ; Feh
|
|
jg ; n/a ; Final_Semkath
|
|
jg ; n/a ; Gaf
|
|
jg ; n/a ; Gamal
|
|
jg ; n/a ; Hah
|
|
jg ; n/a ; Hamza_On_Heh_Goal
|
|
jg ; n/a ; He
|
|
jg ; n/a ; Heh
|
|
jg ; n/a ; Heh_Goal
|
|
jg ; n/a ; Heth
|
|
jg ; n/a ; Kaf
|
|
jg ; n/a ; Kaph
|
|
jg ; n/a ; Khaph
|
|
jg ; n/a ; Knotted_Heh
|
|
jg ; n/a ; Lam
|
|
jg ; n/a ; Lamadh
|
|
jg ; n/a ; Meem
|
|
jg ; n/a ; Mim
|
|
jg ; n/a ; No_Joining_Group
|
|
jg ; n/a ; Noon
|
|
jg ; n/a ; Nun
|
|
jg ; n/a ; Pe
|
|
jg ; n/a ; Qaf
|
|
jg ; n/a ; Qaph
|
|
jg ; n/a ; Reh
|
|
jg ; n/a ; Reversed_Pe
|
|
jg ; n/a ; Sad
|
|
jg ; n/a ; Sadhe
|
|
jg ; n/a ; Seen
|
|
jg ; n/a ; Semkath
|
|
jg ; n/a ; Shin
|
|
jg ; n/a ; Swash_Kaf
|
|
jg ; n/a ; Syriac_Waw
|
|
jg ; n/a ; Tah
|
|
jg ; n/a ; Taw
|
|
jg ; n/a ; Teh_Marbuta
|
|
jg ; n/a ; Teth
|
|
jg ; n/a ; Waw
|
|
jg ; n/a ; Yeh
|
|
jg ; n/a ; Yeh_Barree
|
|
jg ; n/a ; Yeh_With_Tail
|
|
jg ; n/a ; Yudh
|
|
jg ; n/a ; Yudh_He
|
|
jg ; n/a ; Zain
|
|
jg ; n/a ; Zhain
|
|
|
|
# Joining_Type (jt)
|
|
|
|
jt ; C ; Join_Causing
|
|
jt ; D ; Dual_Joining
|
|
jt ; L ; Left_Joining
|
|
jt ; R ; Right_Joining
|
|
jt ; T ; Transparent
|
|
jt ; U ; Non_Joining
|
|
|
|
# Line_Break (lb)
|
|
|
|
lb ; AI ; Ambiguous
|
|
lb ; AL ; Alphabetic
|
|
lb ; B2 ; Break_Both
|
|
lb ; BA ; Break_After
|
|
lb ; BB ; Break_Before
|
|
lb ; BK ; Mandatory_Break
|
|
lb ; CB ; Contingent_Break
|
|
lb ; CL ; Close_Punctuation
|
|
lb ; CM ; Combining_Mark
|
|
lb ; CR ; Carriage_Return
|
|
lb ; EX ; Exclamation
|
|
lb ; GL ; Glue
|
|
lb ; H2 ; H2
|
|
lb ; H3 ; H3
|
|
lb ; HY ; Hyphen
|
|
lb ; ID ; Ideographic
|
|
lb ; IN ; Inseparable ; Inseperable
|
|
lb ; IS ; Infix_Numeric
|
|
lb ; JL ; JL
|
|
lb ; JT ; JT
|
|
lb ; JV ; JV
|
|
lb ; LF ; Line_Feed
|
|
lb ; NL ; Next_Line
|
|
lb ; NS ; Nonstarter
|
|
lb ; NU ; Numeric
|
|
lb ; OP ; Open_Punctuation
|
|
lb ; PO ; Postfix_Numeric
|
|
lb ; PR ; Prefix_Numeric
|
|
lb ; QU ; Quotation
|
|
lb ; SA ; Complex_Context
|
|
lb ; SG ; Surrogate
|
|
lb ; SP ; Space
|
|
lb ; SY ; Break_Symbols
|
|
lb ; WJ ; Word_Joiner
|
|
lb ; XX ; Unknown
|
|
lb ; ZW ; ZWSpace
|
|
|
|
# Logical_Order_Exception (LOE)
|
|
|
|
LOE; N ; No ; F ; False
|
|
LOE; Y ; Yes ; T ; True
|
|
|
|
# Lowercase (Lower)
|
|
|
|
Lower; N ; No ; F ; False
|
|
Lower; Y ; Yes ; T ; True
|
|
|
|
# Lowercase_Mapping (lc)
|
|
|
|
# @missing: 0000..10FFFF; Lowercase_Mapping; <code point>
|
|
|
|
# Math (Math)
|
|
|
|
Math; N ; No ; F ; False
|
|
Math; Y ; Yes ; T ; True
|
|
|
|
# NFC_Quick_Check (NFC_QC)
|
|
|
|
NFC_QC; M ; Maybe
|
|
NFC_QC; N ; No
|
|
NFC_QC; Y ; Yes
|
|
|
|
# NFD_Quick_Check (NFD_QC)
|
|
|
|
NFD_QC; N ; No
|
|
NFD_QC; Y ; Yes
|
|
|
|
# NFKC_Quick_Check (NFKC_QC)
|
|
|
|
NFKC_QC; M ; Maybe
|
|
NFKC_QC; N ; No
|
|
NFKC_QC; Y ; Yes
|
|
|
|
# NFKD_Quick_Check (NFKD_QC)
|
|
|
|
NFKD_QC; N ; No
|
|
NFKD_QC; Y ; Yes
|
|
|
|
# Name (na)
|
|
|
|
# @missing: 0000..10FFFF; Name; <none>
|
|
|
|
# Noncharacter_Code_Point (NChar)
|
|
|
|
NChar; N ; No ; F ; False
|
|
NChar; Y ; Yes ; T ; True
|
|
|
|
# Numeric_Type (nt)
|
|
|
|
nt ; De ; Decimal
|
|
nt ; Di ; Digit
|
|
nt ; None ; None
|
|
nt ; Nu ; Numeric
|
|
|
|
# Numeric_Value (nv)
|
|
|
|
# @missing: 0000..10FFFF; Numeric_Value; NaN
|
|
|
|
# Other_Alphabetic (OAlpha)
|
|
|
|
OAlpha; N ; No ; F ; False
|
|
OAlpha; Y ; Yes ; T ; True
|
|
|
|
# Other_Default_Ignorable_Code_Point (ODI)
|
|
|
|
ODI; N ; No ; F ; False
|
|
ODI; Y ; Yes ; T ; True
|
|
|
|
# Other_Grapheme_Extend (OGr_Ext)
|
|
|
|
OGr_Ext; N ; No ; F ; False
|
|
OGr_Ext; Y ; Yes ; T ; True
|
|
|
|
# Other_ID_Continue (OIDC)
|
|
|
|
OIDC; N ; No ; F ; False
|
|
OIDC; Y ; Yes ; T ; True
|
|
|
|
# Other_ID_Start (OIDS)
|
|
|
|
OIDS; N ; No ; F ; False
|
|
OIDS; Y ; Yes ; T ; True
|
|
|
|
# Other_Lowercase (OLower)
|
|
|
|
OLower; N ; No ; F ; False
|
|
OLower; Y ; Yes ; T ; True
|
|
|
|
# Other_Math (OMath)
|
|
|
|
OMath; N ; No ; F ; False
|
|
OMath; Y ; Yes ; T ; True
|
|
|
|
# Other_Uppercase (OUpper)
|
|
|
|
OUpper; N ; No ; F ; False
|
|
OUpper; Y ; Yes ; T ; True
|
|
|
|
# Pattern_Syntax (Pat_Syn)
|
|
|
|
Pat_Syn; N ; No ; F ; False
|
|
Pat_Syn; Y ; Yes ; T ; True
|
|
|
|
# Pattern_White_Space (Pat_WS)
|
|
|
|
Pat_WS; N ; No ; F ; False
|
|
Pat_WS; Y ; Yes ; T ; True
|
|
|
|
# Quotation_Mark (QMark)
|
|
|
|
QMark; N ; No ; F ; False
|
|
QMark; Y ; Yes ; T ; True
|
|
|
|
# Radical (Radical)
|
|
|
|
Radical; N ; No ; F ; False
|
|
Radical; Y ; Yes ; T ; True
|
|
|
|
# STerm (STerm)
|
|
|
|
STerm; N ; No ; F ; False
|
|
STerm; Y ; Yes ; T ; True
|
|
|
|
# Script (sc)
|
|
|
|
sc ; Arab ; Arabic
|
|
sc ; Armn ; Armenian
|
|
sc ; Bali ; Balinese
|
|
sc ; Beng ; Bengali
|
|
sc ; Bopo ; Bopomofo
|
|
sc ; Brai ; Braille
|
|
sc ; Bugi ; Buginese
|
|
sc ; Buhd ; Buhid
|
|
sc ; Cans ; Canadian_Aboriginal
|
|
sc ; Cari ; Carian
|
|
sc ; Cham ; Cham
|
|
sc ; Cher ; Cherokee
|
|
sc ; Copt ; Coptic ; Qaac
|
|
sc ; Cprt ; Cypriot
|
|
sc ; Cyrl ; Cyrillic
|
|
sc ; Deva ; Devanagari
|
|
sc ; Dsrt ; Deseret
|
|
sc ; Ethi ; Ethiopic
|
|
sc ; Geor ; Georgian
|
|
sc ; Glag ; Glagolitic
|
|
sc ; Goth ; Gothic
|
|
sc ; Grek ; Greek
|
|
sc ; Gujr ; Gujarati
|
|
sc ; Guru ; Gurmukhi
|
|
sc ; Hang ; Hangul
|
|
sc ; Hani ; Han
|
|
sc ; Hano ; Hanunoo
|
|
sc ; Hebr ; Hebrew
|
|
sc ; Hira ; Hiragana
|
|
sc ; Hrkt ; Katakana_Or_Hiragana
|
|
sc ; Ital ; Old_Italic
|
|
sc ; Kali ; Kayah_Li
|
|
sc ; Kana ; Katakana
|
|
sc ; Khar ; Kharoshthi
|
|
sc ; Khmr ; Khmer
|
|
sc ; Knda ; Kannada
|
|
sc ; Laoo ; Lao
|
|
sc ; Latn ; Latin
|
|
sc ; Lepc ; Lepcha
|
|
sc ; Limb ; Limbu
|
|
sc ; Linb ; Linear_B
|
|
sc ; Lyci ; Lycian
|
|
sc ; Lydi ; Lydian
|
|
sc ; Mlym ; Malayalam
|
|
sc ; Mong ; Mongolian
|
|
sc ; Mymr ; Myanmar
|
|
sc ; Nkoo ; Nko
|
|
sc ; Ogam ; Ogham
|
|
sc ; Olck ; Ol_Chiki
|
|
sc ; Orya ; Oriya
|
|
sc ; Osma ; Osmanya
|
|
sc ; Phag ; Phags_Pa
|
|
sc ; Phnx ; Phoenician
|
|
sc ; Qaai ; Inherited
|
|
sc ; Rjng ; Rejang
|
|
sc ; Runr ; Runic
|
|
sc ; Saur ; Saurashtra
|
|
sc ; Shaw ; Shavian
|
|
sc ; Sinh ; Sinhala
|
|
sc ; Sund ; Sundanese
|
|
sc ; Sylo ; Syloti_Nagri
|
|
sc ; Syrc ; Syriac
|
|
sc ; Tagb ; Tagbanwa
|
|
sc ; Tale ; Tai_Le
|
|
sc ; Talu ; New_Tai_Lue
|
|
sc ; Taml ; Tamil
|
|
sc ; Telu ; Telugu
|
|
sc ; Tfng ; Tifinagh
|
|
sc ; Tglg ; Tagalog
|
|
sc ; Thaa ; Thaana
|
|
sc ; Thai ; Thai
|
|
sc ; Tibt ; Tibetan
|
|
sc ; Ugar ; Ugaritic
|
|
sc ; Vaii ; Vai
|
|
sc ; Xpeo ; Old_Persian
|
|
sc ; Xsux ; Cuneiform
|
|
sc ; Yiii ; Yi
|
|
sc ; Zyyy ; Common
|
|
sc ; Zzzz ; Unknown
|
|
|
|
# Sentence_Break (SB)
|
|
|
|
SB ; AT ; ATerm
|
|
SB ; CL ; Close
|
|
SB ; CR ; CR
|
|
SB ; EX ; Extend
|
|
SB ; FO ; Format
|
|
SB ; LE ; OLetter
|
|
SB ; LF ; LF
|
|
SB ; LO ; Lower
|
|
SB ; NU ; Numeric
|
|
SB ; SC ; SContinue
|
|
SB ; SE ; Sep
|
|
SB ; SP ; Sp
|
|
SB ; ST ; STerm
|
|
SB ; UP ; Upper
|
|
SB ; XX ; Other
|
|
|
|
# Simple_Case_Folding (scf)
|
|
|
|
# @missing: 0000..10FFFF; Simple_Case_Folding; <code point>
|
|
|
|
# Simple_Lowercase_Mapping (slc)
|
|
|
|
# @missing: 0000..10FFFF; Simple_Lowercase_Mapping; <code point>
|
|
|
|
# Simple_Titlecase_Mapping (stc)
|
|
|
|
# @missing: 0000..10FFFF; Simple_Titlecase_Mapping; <code point>
|
|
|
|
# Simple_Uppercase_Mapping (suc)
|
|
|
|
# @missing: 0000..10FFFF; Simple_Uppercase_Mapping; <code point>
|
|
|
|
# Soft_Dotted (SD)
|
|
|
|
SD ; N ; No ; F ; False
|
|
SD ; Y ; Yes ; T ; True
|
|
|
|
# Terminal_Punctuation (Term)
|
|
|
|
Term; N ; No ; F ; False
|
|
Term; Y ; Yes ; T ; True
|
|
|
|
# Titlecase_Mapping (tc)
|
|
|
|
# @missing: 0000..10FFFF; Titlecase_Mapping; <code point>
|
|
|
|
# Unicode_1_Name (na1)
|
|
|
|
# @missing: 0000..10FFFF; Unicode_1_Name; <none>
|
|
|
|
# Unicode_Radical_Stroke (URS)
|
|
|
|
# @missing: 0000..10FFFF; Unicode_Radical_Stroke; <none>
|
|
|
|
# Unified_Ideograph (UIdeo)
|
|
|
|
UIdeo; N ; No ; F ; False
|
|
UIdeo; Y ; Yes ; T ; True
|
|
|
|
# Uppercase (Upper)
|
|
|
|
Upper; N ; No ; F ; False
|
|
Upper; Y ; Yes ; T ; True
|
|
|
|
# Uppercase_Mapping (uc)
|
|
|
|
# @missing: 0000..10FFFF; Uppercase_Mapping; <code point>
|
|
|
|
# Variation_Selector (VS)
|
|
|
|
VS ; N ; No ; F ; False
|
|
VS ; Y ; Yes ; T ; True
|
|
|
|
# White_Space (WSpace)
|
|
|
|
WSpace; N ; No ; F ; False
|
|
WSpace; Y ; Yes ; T ; True
|
|
|
|
# Word_Break (WB)
|
|
|
|
WB ; CR ; CR
|
|
WB ; EX ; ExtendNumLet
|
|
WB ; Extend ; Extend
|
|
WB ; FO ; Format
|
|
WB ; KA ; Katakana
|
|
WB ; LE ; ALetter
|
|
WB ; LF ; LF
|
|
WB ; MB ; MidNumLet
|
|
WB ; ML ; MidLetter
|
|
WB ; MN ; MidNum
|
|
WB ; NL ; Newline
|
|
WB ; NU ; Numeric
|
|
WB ; XX ; Other
|
|
|
|
# XID_Continue (XIDC)
|
|
|
|
XIDC; N ; No ; F ; False
|
|
XIDC; Y ; Yes ; T ; True
|
|
|
|
# XID_Start (XIDS)
|
|
|
|
XIDS; N ; No ; F ; False
|
|
XIDS; Y ; Yes ; T ; True
|
|
|
|
# EOF
|