mirror of
https://github.com/symbl-cc/symbl-data.git
synced 2025-10-27 11:41:10 -04:00
1232 lines
23 KiB
Plaintext
1232 lines
23 KiB
Plaintext
[cf]: Case change
|
|
[scf]: Simple case change
|
|
[bpb]: Bidi Paired Bracket
|
|
[AHex]
|
|
n: No
|
|
y: Yes
|
|
[age]: Version
|
|
1.1: V1_1
|
|
2.0: V2_0
|
|
2.1: V2_1
|
|
3.0: V3_0
|
|
3.1: V3_1
|
|
3.2: V3_2
|
|
4.0: V4_0
|
|
4.1: V4_1
|
|
5.0: V5_0
|
|
5.1: V5_1
|
|
5.2: V5_2
|
|
6.0: V6_0
|
|
6.1: V6_1
|
|
6.2: V6_2
|
|
6.3: V6_3
|
|
7.0: V7_0
|
|
8.0: V8_0
|
|
9.0: V9_0
|
|
10.0: V10_0
|
|
11.0: V11_0
|
|
12.0: V12_0
|
|
12.1: V12_1
|
|
13.0: V13_0
|
|
na: Unassigned
|
|
14.0: V14_0
|
|
15.0: V15_0
|
|
[Alpha]
|
|
n: No
|
|
y: Yes
|
|
[bc]
|
|
al: Arabic_Letter
|
|
an: Arabic_Number
|
|
b: Paragraph_Separator
|
|
bn: Boundary_Neutral
|
|
cs: Common_Separator
|
|
en: European_Number
|
|
es: European_Separator
|
|
et: European_Terminator
|
|
fsi: First_Strong_Isolate
|
|
l: Left_To_Right
|
|
lre: Left_To_Right_Embedding
|
|
lri: Left_To_Right_Isolate
|
|
lro: Left_To_Right_Override
|
|
nsm: Nonspacing_Mark
|
|
on: Other_Neutral
|
|
pdf: Pop_Directional_Format
|
|
pdi: Pop_Directional_Isolate
|
|
r: Right_To_Left
|
|
rle: Right_To_Left_Embedding
|
|
rli: Right_To_Left_Isolate
|
|
rlo: Right_To_Left_Override
|
|
s: Segment_Separator
|
|
ws: White_Space
|
|
[Bidi_C]
|
|
n: No
|
|
y: Yes
|
|
[Bidi_M]
|
|
n: No
|
|
y: Yes
|
|
[bpt]: Type of paired mirror bracket (bidi)
|
|
c: Close
|
|
n: None
|
|
o: Open
|
|
[blk]: Block
|
|
adlam: Adlam
|
|
aegean_numbers: Aegean_Numbers
|
|
ahom: Ahom
|
|
alchemical: Alchemical_Symbols
|
|
alphabetic_pf: Alphabetic_Presentation_Forms
|
|
anatolian_hieroglyphs: Anatolian_Hieroglyphs
|
|
ancient_greek_music: Ancient_Greek_Musical_Notation
|
|
ancient_greek_numbers: Ancient_Greek_Numbers
|
|
ancient_symbols: Ancient_Symbols
|
|
arabic: Arabic
|
|
arabic_ext_a: Arabic_Extended_A
|
|
arabic_math: Arabic_Mathematical_Alphabetic_Symbols
|
|
arabic_pf_a: Arabic_Presentation_Forms_A
|
|
arabic_pf_b: Arabic_Presentation_Forms_B
|
|
arabic_sup: Arabic_Supplement
|
|
armenian: Armenian
|
|
arrows: Arrows
|
|
ascii: Basic_Latin
|
|
avestan: Avestan
|
|
balinese: Balinese
|
|
bamum: Bamum
|
|
bamum_sup: Bamum_Supplement
|
|
bassa_vah: Bassa_Vah
|
|
batak: Batak
|
|
bengali: Bengali
|
|
bhaiksuki: Bhaiksuki
|
|
block_elements: Block_Elements
|
|
bopomofo: Bopomofo
|
|
bopomofo_ext: Bopomofo_Extended
|
|
box_drawing: Box_Drawing
|
|
brahmi: Brahmi
|
|
braille: Braille_Patterns
|
|
buginese: Buginese
|
|
buhid: Buhid
|
|
byzantine_music: Byzantine_Musical_Symbols
|
|
carian: Carian
|
|
caucasian_albanian: Caucasian_Albanian
|
|
chakma: Chakma
|
|
cham: Cham
|
|
cherokee: Cherokee
|
|
cherokee_sup: Cherokee_Supplement
|
|
chess_symbols: Chess_Symbols
|
|
chorasmian: Chorasmian
|
|
cjk: CJK_Unified_Ideographs
|
|
cjk_compat: CJK_Compatibility
|
|
cjk_compat_forms: CJK_Compatibility_Forms
|
|
cjk_compat_ideographs: CJK_Compatibility_Ideographs
|
|
cjk_compat_ideographs_sup: CJK_Compatibility_Ideographs_Supplement
|
|
cjk_ext_a: CJK_Unified_Ideographs_Extension_A
|
|
cjk_ext_b: CJK_Unified_Ideographs_Extension_B
|
|
cjk_ext_c: CJK_Unified_Ideographs_Extension_C
|
|
cjk_ext_d: CJK_Unified_Ideographs_Extension_D
|
|
cjk_ext_e: CJK_Unified_Ideographs_Extension_E
|
|
cjk_ext_f: CJK_Unified_Ideographs_Extension_F
|
|
cjk_ext_g: CJK_Unified_Ideographs_Extension_G
|
|
cjk_radicals_sup: CJK_Radicals_Supplement
|
|
cjk_strokes: CJK_Strokes
|
|
cjk_symbols: CJK_Symbols_And_Punctuation
|
|
compat_jamo: Hangul_Compatibility_Jamo
|
|
control_pictures: Control_Pictures
|
|
coptic: Coptic
|
|
coptic_epact_numbers: Coptic_Epact_Numbers
|
|
counting_rod: Counting_Rod_Numerals
|
|
cuneiform: Cuneiform
|
|
cuneiform_numbers: Cuneiform_Numbers_And_Punctuation
|
|
currency_symbols: Currency_Symbols
|
|
cypriot_syllabary: Cypriot_Syllabary
|
|
cyrillic: Cyrillic
|
|
cyrillic_ext_a: Cyrillic_Extended_A
|
|
cyrillic_ext_b: Cyrillic_Extended_B
|
|
cyrillic_ext_c: Cyrillic_Extended_C
|
|
cyrillic_sup: Cyrillic_Supplement
|
|
deseret: Deseret
|
|
devanagari: Devanagari
|
|
devanagari_ext: Devanagari_Extended
|
|
diacriticals: Combining_Diacritical_Marks
|
|
diacriticals_ext: Combining_Diacritical_Marks_Extended
|
|
diacriticals_for_symbols: Combining_Diacritical_Marks_For_Symbols
|
|
diacriticals_sup: Combining_Diacritical_Marks_Supplement
|
|
dingbats: Dingbats
|
|
dives_akuru: Dives_Akuru
|
|
dogra: Dogra
|
|
domino: Domino_Tiles
|
|
duployan: Duployan
|
|
early_dynastic_cuneiform: Early_Dynastic_Cuneiform
|
|
egyptian_hieroglyph_format_controls: Egyptian_Hieroglyph_Format_Controls
|
|
egyptian_hieroglyphs: Egyptian_Hieroglyphs
|
|
elbasan: Elbasan
|
|
elymaic: Elymaic
|
|
emoticons: Emoticons
|
|
enclosed_alphanum: Enclosed_Alphanumerics
|
|
enclosed_alphanum_sup: Enclosed_Alphanumeric_Supplement
|
|
enclosed_cjk: Enclosed_CJK_Letters_And_Months
|
|
enclosed_ideographic_sup: Enclosed_Ideographic_Supplement
|
|
ethiopic: Ethiopic
|
|
ethiopic_ext: Ethiopic_Extended
|
|
ethiopic_ext_a: Ethiopic_Extended_A
|
|
ethiopic_sup: Ethiopic_Supplement
|
|
geometric_shapes: Geometric_Shapes
|
|
geometric_shapes_ext: Geometric_Shapes_Extended
|
|
georgian: Georgian
|
|
georgian_ext: Georgian_Extended
|
|
georgian_sup: Georgian_Supplement
|
|
glagolitic: Glagolitic
|
|
glagolitic_sup: Glagolitic_Supplement
|
|
gothic: Gothic
|
|
grantha: Grantha
|
|
greek: Greek_And_Coptic
|
|
greek_ext: Greek_Extended
|
|
gujarati: Gujarati
|
|
gunjala_gondi: Gunjala_Gondi
|
|
gurmukhi: Gurmukhi
|
|
half_and_full_forms: Halfwidth_And_Fullwidth_Forms
|
|
half_marks: Combining_Half_Marks
|
|
hangul: Hangul_Syllables
|
|
hanifi_rohingya: Hanifi_Rohingya
|
|
hanunoo: Hanunoo
|
|
hatran: Hatran
|
|
hebrew: Hebrew
|
|
high_pu_surrogates: High_Private_Use_Surrogates
|
|
high_surrogates: High_Surrogates
|
|
hiragana: Hiragana
|
|
idc: Ideographic_Description_Characters
|
|
ideographic_symbols: Ideographic_Symbols_And_Punctuation
|
|
imperial_aramaic: Imperial_Aramaic
|
|
indic_number_forms: Common_Indic_Number_Forms
|
|
indic_siyaq_numbers: Indic_Siyaq_Numbers
|
|
inscriptional_pahlavi: Inscriptional_Pahlavi
|
|
inscriptional_parthian: Inscriptional_Parthian
|
|
ipa_ext: IPA_Extensions
|
|
jamo: Hangul_Jamo
|
|
jamo_ext_a: Hangul_Jamo_Extended_A
|
|
jamo_ext_b: Hangul_Jamo_Extended_B
|
|
javanese: Javanese
|
|
kaithi: Kaithi
|
|
kana_ext_a: Kana_Extended_A
|
|
kana_sup: Kana_Supplement
|
|
kanbun: Kanbun
|
|
kangxi: Kangxi_Radicals
|
|
kannada: Kannada
|
|
katakana: Katakana
|
|
katakana_ext: Katakana_Phonetic_Extensions
|
|
kayah_li: Kayah_Li
|
|
kharoshthi: Kharoshthi
|
|
khitan_small_script: Khitan_Small_Script
|
|
khmer: Khmer
|
|
khmer_symbols: Khmer_Symbols
|
|
khojki: Khojki
|
|
khudawadi: Khudawadi
|
|
lao: Lao
|
|
latin_1_sup: Latin_1_Supplement
|
|
latin_ext_a: Latin_Extended_A
|
|
latin_ext_additional: Latin_Extended_Additional
|
|
latin_ext_b: Latin_Extended_B
|
|
latin_ext_c: Latin_Extended_C
|
|
latin_ext_d: Latin_Extended_D
|
|
latin_ext_e: Latin_Extended_E
|
|
lepcha: Lepcha
|
|
letterlike_symbols: Letterlike_Symbols
|
|
limbu: Limbu
|
|
linear_a: Linear_A
|
|
linear_b_ideograms: Linear_B_Ideograms
|
|
linear_b_syllabary: Linear_B_Syllabary
|
|
lisu: Lisu
|
|
lisu_sup: Lisu_Supplement
|
|
low_surrogates: Low_Surrogates
|
|
lycian: Lycian
|
|
lydian: Lydian
|
|
mahajani: Mahajani
|
|
mahjong: Mahjong_Tiles
|
|
makasar: Makasar
|
|
malayalam: Malayalam
|
|
mandaic: Mandaic
|
|
manichaean: Manichaean
|
|
marchen: Marchen
|
|
masaram_gondi: Masaram_Gondi
|
|
math_alphanum: Mathematical_Alphanumeric_Symbols
|
|
math_operators: Mathematical_Operators
|
|
mayan_numerals: Mayan_Numerals
|
|
medefaidrin: Medefaidrin
|
|
meetei_mayek: Meetei_Mayek
|
|
meetei_mayek_ext: Meetei_Mayek_Extensions
|
|
mende_kikakui: Mende_Kikakui
|
|
meroitic_cursive: Meroitic_Cursive
|
|
meroitic_hieroglyphs: Meroitic_Hieroglyphs
|
|
miao: Miao
|
|
misc_arrows: Miscellaneous_Symbols_And_Arrows
|
|
misc_math_symbols_a: Miscellaneous_Mathematical_Symbols_A
|
|
misc_math_symbols_b: Miscellaneous_Mathematical_Symbols_B
|
|
misc_pictographs: Miscellaneous_Symbols_And_Pictographs
|
|
misc_symbols: Miscellaneous_Symbols
|
|
misc_technical: Miscellaneous_Technical
|
|
modi: Modi
|
|
modifier_letters: Spacing_Modifier_Letters
|
|
modifier_tone_letters: Modifier_Tone_Letters
|
|
mongolian: Mongolian
|
|
mongolian_sup: Mongolian_Supplement
|
|
mro: Mro
|
|
multani: Multani
|
|
music: Musical_Symbols
|
|
myanmar: Myanmar
|
|
myanmar_ext_a: Myanmar_Extended_A
|
|
myanmar_ext_b: Myanmar_Extended_B
|
|
nabataean: Nabataean
|
|
nandinagari: Nandinagari
|
|
nb: No_Block
|
|
new_tai_lue: New_Tai_Lue
|
|
newa: Newa
|
|
nko: NKo
|
|
number_forms: Number_Forms
|
|
nushu: Nushu
|
|
nyiakeng_puachue_hmong: Nyiakeng_Puachue_Hmong
|
|
ocr: Optical_Character_Recognition
|
|
ogham: Ogham
|
|
ol_chiki: Ol_Chiki
|
|
old_hungarian: Old_Hungarian
|
|
old_italic: Old_Italic
|
|
old_north_arabian: Old_North_Arabian
|
|
old_permic: Old_Permic
|
|
old_persian: Old_Persian
|
|
old_sogdian: Old_Sogdian
|
|
old_south_arabian: Old_South_Arabian
|
|
old_turkic: Old_Turkic
|
|
oriya: Oriya
|
|
ornamental_dingbats: Ornamental_Dingbats
|
|
osage: Osage
|
|
osmanya: Osmanya
|
|
ottoman_siyaq_numbers: Ottoman_Siyaq_Numbers
|
|
pahawh_hmong: Pahawh_Hmong
|
|
palmyrene: Palmyrene
|
|
pau_cin_hau: Pau_Cin_Hau
|
|
phags_pa: Phags_Pa
|
|
phaistos: Phaistos_Disc
|
|
phoenician: Phoenician
|
|
phonetic_ext: Phonetic_Extensions
|
|
phonetic_ext_sup: Phonetic_Extensions_Supplement
|
|
playing_cards: Playing_Cards
|
|
psalter_pahlavi: Psalter_Pahlavi
|
|
pua: Private_Use_Area
|
|
punctuation: General_Punctuation
|
|
rejang: Rejang
|
|
rumi: Rumi_Numeral_Symbols
|
|
runic: Runic
|
|
samaritan: Samaritan
|
|
saurashtra: Saurashtra
|
|
sharada: Sharada
|
|
shavian: Shavian
|
|
shorthand_format_controls: Shorthand_Format_Controls
|
|
siddham: Siddham
|
|
sinhala: Sinhala
|
|
sinhala_archaic_numbers: Sinhala_Archaic_Numbers
|
|
small_forms: Small_Form_Variants
|
|
small_kana_ext: Small_Kana_Extension
|
|
sogdian: Sogdian
|
|
sora_sompeng: Sora_Sompeng
|
|
soyombo: Soyombo
|
|
specials: Specials
|
|
sundanese: Sundanese
|
|
sundanese_sup: Sundanese_Supplement
|
|
sup_arrows_a: Supplemental_Arrows_A
|
|
sup_arrows_b: Supplemental_Arrows_B
|
|
sup_arrows_c: Supplemental_Arrows_C
|
|
sup_math_operators: Supplemental_Mathematical_Operators
|
|
sup_pua_a: Supplementary_Private_Use_Area_A
|
|
sup_pua_b: Supplementary_Private_Use_Area_B
|
|
sup_punctuation: Supplemental_Punctuation
|
|
sup_symbols_and_pictographs: Supplemental_Symbols_And_Pictographs
|
|
super_and_sub: Superscripts_And_Subscripts
|
|
sutton_signwriting: Sutton_SignWriting
|
|
syloti_nagri: Syloti_Nagri
|
|
symbols_and_pictographs_ext_a: Symbols_And_Pictographs_Extended_A
|
|
symbols_for_legacy_computing: Symbols_For_Legacy_Computing
|
|
syriac: Syriac
|
|
syriac_sup: Syriac_Supplement
|
|
tagalog: Tagalog
|
|
tagbanwa: Tagbanwa
|
|
tags: Tags
|
|
tai_le: Tai_Le
|
|
tai_tham: Tai_Tham
|
|
tai_viet: Tai_Viet
|
|
tai_xuan_jing: Tai_Xuan_Jing_Symbols
|
|
takri: Takri
|
|
tamil: Tamil
|
|
tamil_sup: Tamil_Supplement
|
|
tangut: Tangut
|
|
tangut_components: Tangut_Components
|
|
tangut_sup: Tangut_Supplement
|
|
telugu: Telugu
|
|
thaana: Thaana
|
|
thai: Thai
|
|
tibetan: Tibetan
|
|
tifinagh: Tifinagh
|
|
tirhuta: Tirhuta
|
|
transport_and_map: Transport_And_Map_Symbols
|
|
ucas: Unified_Canadian_Aboriginal_Syllabics
|
|
ucas_ext: Unified_Canadian_Aboriginal_Syllabics_Extended
|
|
ugaritic: Ugaritic
|
|
vai: Vai
|
|
vedic_ext: Vedic_Extensions
|
|
vertical_forms: Vertical_Forms
|
|
vs: Variation_Selectors
|
|
vs_sup: Variation_Selectors_Supplement
|
|
wancho: Wancho
|
|
warang_citi: Warang_Citi
|
|
yezidi: Yezidi
|
|
yi_radicals: Yi_Radicals
|
|
yi_syllables: Yi_Syllables
|
|
yijing: Yijing_Hexagram_Symbols
|
|
zanabazar_square: Zanabazar_Square
|
|
arabic_ext_b: Arabic_Extended_B
|
|
arabic_ext_c: Arabic_Extended_C
|
|
cjk_ext_h: CJK_Unified_Ideographs_Extension_H
|
|
cypro_minoan: Cypro_Minoan
|
|
cyrillic_ext_d: Cyrillic_Extended_D
|
|
devanagari_ext_a: Devanagari_Extended_A
|
|
ethiopic_ext_b: Ethiopic_Extended_B
|
|
kaktovik_numerals: Kaktovik_Numerals
|
|
kana_ext_b: Kana_Extended_B
|
|
kawi: Kawi
|
|
latin_ext_f: Latin_Extended_F
|
|
latin_ext_g: Latin_Extended_G
|
|
nag_mundari: Nag_Mundari
|
|
old_uyghur: Old_Uyghur
|
|
tangsa: Tangsa
|
|
toto: Toto
|
|
ucas_ext_a: Unified_Canadian_Aboriginal_Syllabics_Extended_A
|
|
vithkuqi: Vithkuqi
|
|
znamenny_music: Znamenny_Musical_Notation
|
|
[ccc]
|
|
nr: Not_Reordered
|
|
ov: Overlay
|
|
hanr: Han_Reading
|
|
nk: Nukta
|
|
kv: Kana_Voicing
|
|
vr: Virama
|
|
ccc10: CCC10
|
|
ccc11: CCC11
|
|
ccc12: CCC12
|
|
ccc13: CCC13
|
|
ccc14: CCC14
|
|
ccc15: CCC15
|
|
ccc16: CCC16
|
|
ccc17: CCC17
|
|
ccc18: CCC18
|
|
ccc19: CCC19
|
|
ccc20: CCC20
|
|
ccc21: CCC21
|
|
ccc22: CCC22
|
|
ccc23: CCC23
|
|
ccc24: CCC24
|
|
ccc25: CCC25
|
|
ccc26: CCC26
|
|
ccc27: CCC27
|
|
ccc28: CCC28
|
|
ccc29: CCC29
|
|
ccc30: CCC30
|
|
ccc31: CCC31
|
|
ccc32: CCC32
|
|
ccc33: CCC33
|
|
ccc34: CCC34
|
|
ccc35: CCC35
|
|
ccc36: CCC36
|
|
ccc84: CCC84
|
|
ccc91: CCC91
|
|
ccc103: CCC103
|
|
ccc107: CCC107
|
|
ccc118: CCC118
|
|
ccc122: CCC122
|
|
ccc129: CCC129
|
|
ccc130: CCC130
|
|
ccc132: CCC132
|
|
ccc133: CCC133 # RESERVED
|
|
atbl: Attached_Below_Left
|
|
atb: Attached_Below
|
|
ata: Attached_Above
|
|
atar: Attached_Above_Right
|
|
bl: Below_Left
|
|
b: Below
|
|
br: Below_Right
|
|
l: Left
|
|
r: Right
|
|
al: Above_Left
|
|
a: Above
|
|
ar: Above_Right
|
|
db: Double_Below
|
|
da: Double_Above
|
|
is: Iota_Subscript
|
|
[CI]
|
|
n: No
|
|
y: Yes
|
|
[Cased]
|
|
n: No
|
|
y: Yes
|
|
[CWCF]
|
|
n: No
|
|
y: Yes
|
|
[CWCM]
|
|
n: No
|
|
y: Yes
|
|
[CWL]
|
|
n: No
|
|
y: Yes
|
|
[CWKCF]
|
|
n: No
|
|
y: Yes
|
|
[CWT]
|
|
n: No
|
|
y: Yes
|
|
[CWU]
|
|
n: No
|
|
y: Yes
|
|
[CE]: Composition Exclusion
|
|
n: No
|
|
y: Yes
|
|
[Dash]
|
|
n: No
|
|
y: Yes
|
|
[dt]
|
|
can: Canonical
|
|
com: Compat
|
|
enc: Circle
|
|
fin: Final
|
|
font: Font
|
|
fra: Fraction
|
|
init: Initial
|
|
iso: Isolated
|
|
med: Medial
|
|
nar: Narrow
|
|
nb: Nobreak
|
|
none: None
|
|
sml: Small
|
|
sqr: Square
|
|
sub: Sub
|
|
sup: Super
|
|
vert: Vertical
|
|
wide: Wide
|
|
[DI]
|
|
n: No
|
|
y: Yes
|
|
[Dep]
|
|
n: No
|
|
y: Yes
|
|
[Dia]
|
|
n: No
|
|
y: Yes
|
|
[ea]
|
|
a: Ambiguous
|
|
f: Fullwidth
|
|
h: Halfwidth
|
|
n: Neutral
|
|
na: Narrow
|
|
w: Wide
|
|
[Emoji]
|
|
n: No
|
|
y: Yes
|
|
[EComp]
|
|
n: No
|
|
y: Yes
|
|
[EMod]
|
|
n: No
|
|
y: Yes
|
|
[EBase]
|
|
n: No
|
|
y: Yes
|
|
[EPres]
|
|
n: No
|
|
y: Yes
|
|
[XO_NFC]
|
|
n: No
|
|
y: Yes
|
|
[XO_NFD]
|
|
n: No
|
|
y: Yes
|
|
[XO_NFKC]
|
|
n: No
|
|
y: Yes
|
|
[XO_NFKD]
|
|
n: No
|
|
y: Yes
|
|
[ExtPict]
|
|
n: No
|
|
y: Yes
|
|
[Ext]
|
|
n: No
|
|
y: Yes
|
|
[Comp_Ex]
|
|
n: No
|
|
y: Yes
|
|
[gc]
|
|
c: Other # Cc | Cf | Cn | Co | Cs
|
|
cc: Control
|
|
cf: Format
|
|
cn: Unassigned
|
|
co: Private_Use
|
|
cs: Surrogate
|
|
l: Letter # Ll | Lm | Lo | Lt | Lu
|
|
lc: Cased_Letter # Ll | Lt | Lu
|
|
ll: Lowercase_Letter
|
|
lm: Modifier_Letter
|
|
lo: Other_Letter
|
|
lt: Titlecase_Letter
|
|
lu: Uppercase_Letter
|
|
m: Mark
|
|
mc: Spacing_Mark
|
|
me: Enclosing_Mark
|
|
mn: Nonspacing_Mark
|
|
n: Number # Nd | Nl | No
|
|
nd: Decimal_Number
|
|
nl: Letter_Number
|
|
no: Other_Number
|
|
p: Punctuation
|
|
pc: Connector_Punctuation
|
|
pd: Dash_Punctuation
|
|
pe: Close_Punctuation
|
|
pf: Final_Punctuation
|
|
pi: Initial_Punctuation
|
|
po: Other_Punctuation
|
|
ps: Open_Punctuation
|
|
s: Symbol # Sc | Sk | Sm | So
|
|
sc: Currency_Symbol
|
|
sk: Modifier_Symbol
|
|
sm: Math_Symbol
|
|
so: Other_Symbol
|
|
z: Separator # Zl | Zp | Zs
|
|
zl: Line_Separator
|
|
zp: Paragraph_Separator
|
|
zs: Space_Separator
|
|
[Gr_Base]
|
|
n: No
|
|
y: Yes
|
|
[GCB]
|
|
cn: Control
|
|
cr: CR
|
|
eb: E_Base
|
|
ebg: E_Base_GAZ
|
|
em: E_Modifier
|
|
ex: Extend
|
|
gaz: Glue_After_Zwj
|
|
l: L
|
|
lf: LF
|
|
lv: LV
|
|
lvt: LVT
|
|
pp: Prepend
|
|
ri: Regional_Indicator
|
|
sm: SpacingMark
|
|
t: T
|
|
v: V
|
|
xx: Other
|
|
zwj: ZWJ
|
|
[Gr_Ext]
|
|
n: No
|
|
y: Yes
|
|
[Gr_Link]
|
|
n: No
|
|
y: Yes
|
|
[hst]
|
|
l: Leading_Jamo
|
|
lv: LV_Syllable
|
|
lvt: LVT_Syllable
|
|
na: Not_Applicable
|
|
t: Trailing_Jamo
|
|
v: Vowel_Jamo
|
|
[Hex]
|
|
n: No
|
|
y: Yes
|
|
[Hyphen]
|
|
n: No
|
|
y: Yes
|
|
[IDSB]
|
|
n: No
|
|
y: Yes
|
|
[IDST]
|
|
n: No
|
|
y: Yes
|
|
[IDC]
|
|
n: No
|
|
y: Yes
|
|
[IDS]
|
|
n: No
|
|
y: Yes
|
|
[Ideo]
|
|
n: No
|
|
y: Yes
|
|
[InPC]
|
|
bottom: Bottom
|
|
bottom_and_left: Bottom_And_Left
|
|
bottom_and_right: Bottom_And_Right
|
|
left: Left
|
|
left_and_right: Left_And_Right
|
|
na: NA
|
|
overstruck: Overstruck
|
|
right: Right
|
|
top: Top
|
|
top_and_bottom: Top_And_Bottom
|
|
top_and_bottom_and_left: Top_And_Bottom_And_Left
|
|
top_and_bottom_and_right: Top_And_Bottom_And_Right
|
|
top_and_left: Top_And_Left
|
|
top_and_left_and_right: Top_And_Left_And_Right
|
|
top_and_right: Top_And_Right
|
|
visual_order_left: Visual_Order_Left
|
|
[InSC]
|
|
avagraha: Avagraha
|
|
bindu: Bindu
|
|
brahmi_joining_number: Brahmi_Joining_Number
|
|
cantillation_mark: Cantillation_Mark
|
|
consonant: Consonant
|
|
consonant_dead: Consonant_Dead
|
|
consonant_final: Consonant_Final
|
|
consonant_head_letter: Consonant_Head_Letter
|
|
consonant_initial_postfixed: Consonant_Initial_Postfixed
|
|
consonant_killer: Consonant_Killer
|
|
consonant_medial: Consonant_Medial
|
|
consonant_placeholder: Consonant_Placeholder
|
|
consonant_preceding_repha: Consonant_Preceding_Repha
|
|
consonant_prefixed: Consonant_Prefixed
|
|
consonant_subjoined: Consonant_Subjoined
|
|
consonant_succeeding_repha: Consonant_Succeeding_Repha
|
|
consonant_with_stacker: Consonant_With_Stacker
|
|
gemination_mark: Gemination_Mark
|
|
invisible_stacker: Invisible_Stacker
|
|
joiner: Joiner
|
|
modifying_letter: Modifying_Letter
|
|
non_joiner: Non_Joiner
|
|
nukta: Nukta
|
|
number: Number
|
|
number_joiner: Number_Joiner
|
|
other: Other
|
|
pure_killer: Pure_Killer
|
|
register_shifter: Register_Shifter
|
|
syllable_modifier: Syllable_Modifier
|
|
tone_letter: Tone_Letter
|
|
tone_mark: Tone_Mark
|
|
virama: Virama
|
|
visarga: Visarga
|
|
vowel: Vowel
|
|
vowel_dependent: Vowel_Dependent
|
|
vowel_independent: Vowel_Independent
|
|
[JSN]
|
|
a: A
|
|
ae: AE
|
|
b: B
|
|
bb: BB
|
|
bs: BS
|
|
c: C
|
|
d: D
|
|
dd: DD
|
|
e: E
|
|
eo: EO
|
|
eu: EU
|
|
g: G
|
|
gg: GG
|
|
gs: GS
|
|
h: H
|
|
i: I
|
|
j: J
|
|
jj: JJ
|
|
k: K
|
|
l: L
|
|
lb: LB
|
|
lg: LG
|
|
lh: LH
|
|
lm: LM
|
|
lp: LP
|
|
ls: LS
|
|
lt: LT
|
|
m: M
|
|
n: N
|
|
ng: NG
|
|
nh: NH
|
|
nj: NJ
|
|
o: O
|
|
oe: OE
|
|
p: P
|
|
r: R
|
|
s: S
|
|
ss: SS
|
|
t: T
|
|
u: U
|
|
wa: WA
|
|
wae: WAE
|
|
we: WE
|
|
weo: WEO
|
|
wi: WI
|
|
ya: YA
|
|
yae: YAE
|
|
ye: YE
|
|
yeo: YEO
|
|
yi: YI
|
|
yo: YO
|
|
yu: YU
|
|
[Join_C]
|
|
n: No
|
|
y: Yes
|
|
[jg]: Joining Group
|
|
african_feh: AFRICAN FEH
|
|
african_noon: AFRICAN NOON
|
|
african_qaf: AFRICAN QAF
|
|
ain: Ain
|
|
alaph: Alaph
|
|
alef: Alef
|
|
beh: Beh
|
|
beth: Beth
|
|
burushaski_yeh_barree: BURUSHASKI YEH BARREE
|
|
dal: Dal
|
|
dalath_rish: DALATH RISH
|
|
e: E
|
|
farsi_yeh: FARSI YEH
|
|
fe: Fe
|
|
feh: Feh
|
|
final_semkath: FINAL SEMKATH
|
|
gaf: Gaf
|
|
gamal: Gamal
|
|
hah: Hah
|
|
hanifi_rohingya_kinna_ya: HANIFI ROHINGYA KINNA YA
|
|
hanifi_rohingya_pa: HANIFI ROHINGYA PA
|
|
he: He
|
|
heh: Heh
|
|
heh_goal: HEH GOAL
|
|
heth: Heth
|
|
kaf: Kaf
|
|
kaph: Kaph
|
|
khaph: Khaph
|
|
knotted_heh: KNOTTED HEH
|
|
lam: Lam
|
|
lamadh: Lamadh
|
|
malayalam_bha: MALAYALAM BHA
|
|
malayalam_ja: MALAYALAM JA
|
|
malayalam_lla: MALAYALAM LLA
|
|
malayalam_llla: MALAYALAM LLLA
|
|
malayalam_nga: MALAYALAM NGA
|
|
malayalam_nna: MALAYALAM NNA
|
|
malayalam_nnna: MALAYALAM NNNA
|
|
malayalam_nya: MALAYALAM NYA
|
|
malayalam_ra: MALAYALAM RA
|
|
malayalam_ssa: MALAYALAM SSA
|
|
malayalam_tta: MALAYALAM TTA
|
|
manichaean_aleph: MANICHAEAN ALEPH
|
|
manichaean_ayin: MANICHAEAN AYIN
|
|
manichaean_beth: MANICHAEAN BETH
|
|
manichaean_daleth: MANICHAEAN DALETH
|
|
manichaean_dhamedh: MANICHAEAN DHAMEDH
|
|
manichaean_five: MANICHAEAN FIVE
|
|
manichaean_gimel: MANICHAEAN GIMEL
|
|
manichaean_heth: MANICHAEAN HETH
|
|
manichaean_hundred: MANICHAEAN HUNDRED
|
|
manichaean_kaph: MANICHAEAN KAPH
|
|
manichaean_lamedh: MANICHAEAN LAMEDH
|
|
manichaean_mem: MANICHAEAN MEM
|
|
manichaean_nun: MANICHAEAN NUN
|
|
manichaean_one: MANICHAEAN ONE
|
|
manichaean_pe: MANICHAEAN PE
|
|
manichaean_qoph: MANICHAEAN QOPH
|
|
manichaean_resh: MANICHAEAN RESH
|
|
manichaean_sadhe: MANICHAEAN SADHE
|
|
manichaean_samekh: MANICHAEAN SAMEKH
|
|
manichaean_taw: MANICHAEAN TAW
|
|
manichaean_ten: MANICHAEAN TEN
|
|
manichaean_teth: MANICHAEAN TETH
|
|
manichaean_thamedh: MANICHAEAN THAMEDH
|
|
manichaean_twenty: MANICHAEAN TWENTY
|
|
manichaean_waw: MANICHAEAN WAW
|
|
manichaean_yodh: MANICHAEAN YODH
|
|
manichaean_zayin: MANICHAEAN ZAYIN
|
|
meem: Meem
|
|
mim: Mim
|
|
no_joining_group: No_Joining_Group
|
|
noon: Noon
|
|
nun: Nun
|
|
nya: Nya
|
|
pe: Pe
|
|
qaf: Qaf
|
|
qaph: Qaph
|
|
reh: Reh
|
|
reversed_pe: REVERSED PE
|
|
rohingya_yeh: ROHINGYA YEH
|
|
sad: Sad
|
|
sadhe: Sadhe
|
|
seen: Seen
|
|
semkath: Semkath
|
|
shin: Shin
|
|
straight_waw: STRAIGHT WAW
|
|
swash_kaf: SWASH KAF
|
|
syriac_waw: SYRIAC WAW
|
|
tah: Tah
|
|
taw: Taw
|
|
teh_marbuta: TEH MARBUTA
|
|
teh_marbuta_goal: TEH MARBUTA GOAL
|
|
teth: Teth
|
|
waw: Waw
|
|
yeh: Yeh
|
|
yeh_barree: YEH BARREE
|
|
yeh_with_tail: YEH WITH TAIL
|
|
yudh: Yudh
|
|
yudh_he: YUDH HE
|
|
zain: Zain
|
|
zhain: Zhain
|
|
thin_yeh: THIN YEH
|
|
vertical_tail: VERTICAL TAIL
|
|
[jt]: Joining Type
|
|
c: Join_Causing
|
|
d: Dual_Joining
|
|
l: Left_Joining
|
|
r: Right_Joining
|
|
t: Transparent
|
|
u: Non_Joining
|
|
[lb]
|
|
ai: Ambiguous
|
|
al: Alphabetic
|
|
b2: Break_Both
|
|
ba: Break_After
|
|
bb: Break_Before
|
|
bk: Mandatory_Break
|
|
cb: Contingent_Break
|
|
cj: Conditional_Japanese_Starter
|
|
cl: Close_Punctuation
|
|
cm: Combining_Mark
|
|
cp: Close_Parenthesis
|
|
cr: Carriage_Return
|
|
eb: E_Base
|
|
em: E_Modifier
|
|
ex: Exclamation
|
|
gl: Glue
|
|
h2: H2
|
|
h3: H3
|
|
hl: Hebrew_Letter
|
|
hy: Hyphen
|
|
id: Ideographic
|
|
in: Inseparable
|
|
is: Infix_Numeric
|
|
jl: JL
|
|
jt: JT
|
|
jv: JV
|
|
lf: Line_Feed
|
|
nl: Next_Line
|
|
ns: Nonstarter
|
|
nu: Numeric
|
|
op: Open_Punctuation
|
|
po: Postfix_Numeric
|
|
pr: Prefix_Numeric
|
|
qu: Quotation
|
|
ri: Regional_Indicator
|
|
sa: Complex_Context
|
|
sg: Surrogate
|
|
sp: Space
|
|
sy: Break_Symbols
|
|
wj: Word_Joiner
|
|
xx: Unknown
|
|
zw: ZWSpace
|
|
zwj: ZWJ
|
|
[LOE]
|
|
n: No
|
|
y: Yes
|
|
[Lower]
|
|
n: No
|
|
y: Yes
|
|
[Math]
|
|
n: No
|
|
y: Yes
|
|
[NFC_QC]
|
|
m: Maybe
|
|
n: No
|
|
y: Yes
|
|
[NFD_QC]
|
|
n: No
|
|
y: Yes
|
|
[NFKC_QC]
|
|
m: Maybe
|
|
n: No
|
|
y: Yes
|
|
[NFKD_QC]
|
|
n: No
|
|
y: Yes
|
|
[NChar]
|
|
n: No
|
|
y: Yes
|
|
[nt]
|
|
de: Decimal
|
|
di: Digit
|
|
none: None
|
|
nu: Numeric
|
|
[OAlpha]
|
|
n: No
|
|
y: Yes
|
|
[ODI]
|
|
n: No
|
|
y: Yes
|
|
[OGr_Ext]
|
|
n: No
|
|
y: Yes
|
|
[OIDC]
|
|
n: No
|
|
y: Yes
|
|
[OIDS]
|
|
n: No
|
|
y: Yes
|
|
[OLower]
|
|
n: No
|
|
y: Yes
|
|
[OMath]
|
|
n: No
|
|
y: Yes
|
|
[OUpper]
|
|
n: No
|
|
y: Yes
|
|
[Pat_Syn]
|
|
n: No
|
|
y: Yes
|
|
[Pat_WS]
|
|
n: No
|
|
y: Yes
|
|
[PCM]
|
|
n: No
|
|
y: Yes
|
|
[QMark]
|
|
n: No
|
|
y: Yes
|
|
[Radical]
|
|
n: No
|
|
y: Yes
|
|
[RI]
|
|
n: No
|
|
y: Yes
|
|
[sc]
|
|
adlm: Adlam
|
|
aghb: Caucasian_Albanian
|
|
ahom: Ahom
|
|
arab: Arabic
|
|
armi: Imperial_Aramaic
|
|
armn: Armenian
|
|
avst: Avestan
|
|
bali: Balinese
|
|
bamu: Bamum
|
|
bass: Bassa_Vah
|
|
batk: Batak
|
|
beng: Bengali
|
|
bhks: Bhaiksuki
|
|
bopo: Bopomofo
|
|
brah: Brahmi
|
|
brai: Braille
|
|
bugi: Buginese
|
|
buhd: Buhid
|
|
cakm: Chakma
|
|
cans: Canadian_Aboriginal
|
|
cari: Carian
|
|
cham: Cham
|
|
cher: Cherokee
|
|
chrs: Chorasmian
|
|
copt: Coptic
|
|
cprt: Cypriot
|
|
cyrl: Cyrillic
|
|
deva: Devanagari
|
|
diak: Dives_Akuru
|
|
dogr: Dogra
|
|
dsrt: Deseret
|
|
dupl: Duployan
|
|
egyp: Egyptian_Hieroglyphs
|
|
elba: Elbasan
|
|
elym: Elymaic
|
|
ethi: Ethiopic
|
|
geor: Georgian
|
|
glag: Glagolitic
|
|
gong: Gunjala_Gondi
|
|
gonm: Masaram_Gondi
|
|
goth: Gothic
|
|
gran: Grantha
|
|
grek: Greek
|
|
gujr: Gujarati
|
|
guru: Gurmukhi
|
|
hang: Hangul
|
|
hani: Han
|
|
hano: Hanunoo
|
|
hatr: Hatran
|
|
hebr: Hebrew
|
|
hira: Hiragana
|
|
hluw: Anatolian_Hieroglyphs
|
|
hmng: Pahawh_Hmong
|
|
hmnp: Nyiakeng_Puachue_Hmong
|
|
hrkt: Katakana_Or_Hiragana
|
|
hung: Old_Hungarian
|
|
ital: Old_Italic
|
|
java: Javanese
|
|
kali: Kayah_Li
|
|
kana: Katakana
|
|
khar: Kharoshthi
|
|
khmr: Khmer
|
|
khoj: Khojki
|
|
kits: Khitan_Small_Script
|
|
knda: Kannada
|
|
kthi: Kaithi
|
|
lana: Tai_Tham
|
|
laoo: Lao
|
|
latn: Latin
|
|
lepc: Lepcha
|
|
limb: Limbu
|
|
lina: Linear_A
|
|
linb: Linear_B
|
|
lisu: Lisu
|
|
lyci: Lycian
|
|
lydi: Lydian
|
|
mahj: Mahajani
|
|
maka: Makasar
|
|
mand: Mandaic
|
|
mani: Manichaean
|
|
marc: Marchen
|
|
medf: Medefaidrin
|
|
mend: Mende_Kikakui
|
|
merc: Meroitic_Cursive
|
|
mero: Meroitic_Hieroglyphs
|
|
mlym: Malayalam
|
|
modi: Modi
|
|
mong: Mongolian
|
|
mroo: Mro
|
|
mtei: Meetei_Mayek
|
|
mult: Multani
|
|
mymr: Myanmar
|
|
nand: Nandinagari
|
|
narb: Old_North_Arabian
|
|
nbat: Nabataean
|
|
newa: Newa
|
|
nkoo: Nko
|
|
nshu: Nushu
|
|
ogam: Ogham
|
|
olck: Ol_Chiki
|
|
orkh: Old_Turkic
|
|
orya: Oriya
|
|
osge: Osage
|
|
osma: Osmanya
|
|
palm: Palmyrene
|
|
pauc: Pau_Cin_Hau
|
|
perm: Old_Permic
|
|
phag: Phags_Pa
|
|
phli: Inscriptional_Pahlavi
|
|
phlp: Psalter_Pahlavi
|
|
phnx: Phoenician
|
|
plrd: Miao
|
|
prti: Inscriptional_Parthian
|
|
rjng: Rejang
|
|
rohg: Hanifi_Rohingya
|
|
runr: Runic
|
|
samr: Samaritan
|
|
sarb: Old_South_Arabian
|
|
saur: Saurashtra
|
|
sgnw: SignWriting
|
|
shaw: Shavian
|
|
shrd: Sharada
|
|
sidd: Siddham
|
|
sind: Khudawadi
|
|
sinh: Sinhala
|
|
sogd: Sogdian
|
|
sogo: Old_Sogdian
|
|
sora: Sora_Sompeng
|
|
soyo: Soyombo
|
|
sund: Sundanese
|
|
sylo: Syloti_Nagri
|
|
syrc: Syriac
|
|
tagb: Tagbanwa
|
|
takr: Takri
|
|
tale: Tai_Le
|
|
talu: New_Tai_Lue
|
|
taml: Tamil
|
|
tang: Tangut
|
|
tavt: Tai_Viet
|
|
telu: Telugu
|
|
tfng: Tifinagh
|
|
tglg: Tagalog
|
|
thaa: Thaana
|
|
thai: Thai
|
|
tibt: Tibetan
|
|
tirh: Tirhuta
|
|
ugar: Ugaritic
|
|
vaii: Vai
|
|
wara: Warang_Citi
|
|
wcho: Wancho
|
|
xpeo: Old_Persian
|
|
xsux: Cuneiform
|
|
yezi: Yezidi
|
|
yiii: Yi
|
|
zanb: Zanabazar_Square
|
|
zinh: Inherited
|
|
zyyy: Common
|
|
zzzz: Unknown
|
|
cpmn: Cypro_Minoan
|
|
kawi: Kawi
|
|
nagm: Nag_Mundari
|
|
ougr: Old_Uyghur
|
|
tnsa: Tangsa
|
|
toto: Toto
|
|
vith: Vithkuqi
|
|
[SB]
|
|
at: ATerm
|
|
cl: Close
|
|
cr: CR
|
|
ex: Extend
|
|
fo: Format
|
|
le: OLetter
|
|
lf: LF
|
|
lo: Lower
|
|
nu: Numeric
|
|
sc: SContinue
|
|
se: Sep
|
|
sp: Sp
|
|
st: STerm
|
|
up: Upper
|
|
xx: Other
|
|
[STerm]
|
|
n: No
|
|
y: Yes
|
|
[SD]
|
|
n: No
|
|
y: Yes
|
|
[Term]
|
|
n: No
|
|
y: Yes
|
|
[UIdeo]
|
|
n: No
|
|
y: Yes
|
|
[Upper]
|
|
n: No
|
|
y: Yes
|
|
[VS]
|
|
n: No
|
|
y: Yes
|
|
[vo]
|
|
r: Rotated
|
|
tr: Transformed_Rotated
|
|
tu: Transformed_Upright
|
|
u: Upright
|
|
[WSpace]
|
|
n: No
|
|
y: Yes
|
|
[WB]
|
|
cr: CR
|
|
dq: Double_Quote
|
|
eb: E_Base
|
|
ebg: E_Base_GAZ
|
|
em: E_Modifier
|
|
ex: ExtendNumLet
|
|
extend: Extend
|
|
fo: Format
|
|
gaz: Glue_After_Zwj
|
|
hl: Hebrew_Letter
|
|
ka: Katakana
|
|
le: ALetter
|
|
lf: LF
|
|
mb: MidNumLet
|
|
ml: MidLetter
|
|
mn: MidNum
|
|
nl: Newline
|
|
nu: Numeric
|
|
ri: Regional_Indicator
|
|
sq: Single_Quote
|
|
wsegspace: WSegSpace
|
|
xx: Other
|
|
zwj: ZWJ
|
|
[XIDC]
|
|
n: No
|
|
y: Yes
|
|
[XIDS]
|
|
n: No
|
|
y: Yes
|