unicode-data.node.txt

                
   UNICODE-DATA  
                



TODO: finish documentation of this

VERSION ==>                       #0.1.0

require('@unicode/unicode-X.Y.Z') #UNICODE
                                  #UCD and emoji data.
                                  #Latest X.Y.Z: 15.1.0

CNUM                              #Codepoint NUM
CCHAR                             #Codepoint 'CHAR'
CODEPOINT_MAP                     #MAP where key is CNUM and value is STR
require('.../FILE')               #List of codepoints, with info spread across several FILEs:
                                  #  - code-points.js CNUM_ARR
                                  #  - symbols.js CCHAR_ARR
                                  #  - regex.js REGEXP
                                  #.../FILE is '@unicode/unicode-X.Y.Z/Names/NAME/index.js', e.g. '@unicode/unicode-X.Y.Z/Scripts/SCRIPT/FILE'
                                  #Applies to most UNICODE.* unless specified

UNICODE.Names                     #STR_ARR (empty)
import '@unicode/unicode-X.Y.Z/   #CODEPOINT_MAP of codepoint names, uppercased, e.g. 'EXCLAMATION MARK'
 Names/index.js'                  #Some names are shared:
                                  #  - '<control>' (0-1f, 7f-9f)
                                  #  - '[Non ]Private Use High Surrogate' (d800-db7f, db80-dbff), 'Low Surrogate' (dc00-dfff)
                                  #  - 'Private use' (e000-f8ff), 'Plane 15-16 Private use' (f0000-10ffff)
                                  #  - 'CJK Ideograph[ Extension A-G|K]' (3400-4dbf, 4e00-9ffc, 3400-9999, 20000-2ebe0, 30000-3134a),
                                  #    'Hangul Syllable' (ac00-d7a3), Tangut Ideograph (17000-187f7)

UNICODE.Block                     #STR_ARR, i.e. grouping close codepoints together.
                                  #Examples: 'Box_Drawing', 'Basic_Latin'
UNICODE.Script                    #STR_ARR, i.e. grouping close codepoints together.
                                  #Examples: 'Arabic', 'Basic_Latin'
UNICODE.Script_Extensions         #STR_ARR
UNICODE.General_Category          #STR_ARR, i.e. general attributes.
                                  #Examples: 'Letter', 'Punctuation', 'Number'
UNICODE.Binary_Property           #STR_ARR, i.e. specific attributes.
                                  #Examples: 'Cased', 'Dash', 'Alphabetic'
UNICODE.Sequence_Property         #STR_ARR, i.e. emoji data.
                                  #Example: 'RGI_Emoji' (main way to detect whether emoji)
UNICODE.Case_Folding              #STR_ARR, among 'C', 'F', 'S', 'T'
UNICODE.Line_Break                #STR_ARR
                                  #Example: 'Break_After'
UNICODE.Word_Break                #STR_ARR
                                  #Example: 'Double_Quote'
UNICODE.Names                     #STR_ARR
                                  #Example: 'Abbreviation'
UNICODE.Bidi_Class                #STR_ARR
UNICODE.Bidi_Mirroring_Glyph      #STR_ARR
UNICODE.Bidi_Paired_Bracket_Type  #STR_ARR, among 'Open', 'Close', 'None'