# Foldings.txt # DRAFT 1 - 2004-07-14 Asmus Freytag # Subject to change # # Base version of Unicode: 4.0.0 # # Datafile for Unicode Techical Report #30 # Copyright (c) 1991-2004 Unicode, Inc. # For terms of use, and documentation see # http://www.unicode.org/reports/tr30/ # ================================= # Specify all Folding operations # # Format # Field 0 - name of folding operation # Field 1 - operation # Map(\uXXXX) - replace source by constant character # Map(property) - replace source by string property # Map(XXXFolding) - replace source by mapping in # corresponding definition file # 'XXXFolding.txt' # "description" - folding operation cannot be # directly expressed as a map using # existing datafiles # Field 2 - set of source characters (filter) # Notes: # # 1) Sources are given by regular expressions, see UTS#18 # # 2) Sources may include some or all of the the target characters # # Stability # Syntax for this file may change. Content will change change when # new foldings are added, or set of source characters changes # ########################################################################### AccentRemoval; "Map(NFD) and replace combining sequences by base characters, if base character is in source set"; [:sc=Latin:]+[:sc=Greek:]+[:sc=Cyrillic:] CaseFolding; Map(CaseFolding); [:isCaseFolding:] CanonicalDuplicatesFolding; Map(NFC); [\u0374 \u037E \u0387 \u1FBE \u1FEF \u1FFD \u2000 \u2001 \u2126 \u212A \u212B \u2329-\u232A] DashesFolding; Map(\u002D); [:Gc=Pd:] GreekLetterformsFolding; Map(NFD); [\u03D0-\u03D2 \u03D5-\u03D6 \u03F0-\u03F2 \u03F4-\u03F5] HebrewAlternatesFolding; Map(NFD); [\uFB20-\uFB28] JamoFolding; Map(NFD); [\u3131-\u3183] MathSymbolFolding; Map(NFD); [:dt=font:]-[\uFB20-\uFB28] NativeDigitFolding; "Map to corresponding ASCII digit"; [:gc=Nd:] NobreakFolding; Map(NFD); [:dt=no-break:] OverlineFolding; Map(\u203E); [\uFE49-\uFE4C] PositionalFormsFolding; Map(NFD); [:dt=initial:]+[:dt=medial:]+[:dt=final, dt=isolate:] SmallFormsFolding; Map(NFD); [:dt=small:] SpaceFolding; Map(\u0020); [:gc=Zs:] SpacingAccentsFolding; Map(NFD); [\u00AF,\u00B4,\u00B8,\u02D8-\u02DD \u037A,\u0384,\u1FBD,\u1FBE-\u1FC0 \u1FFE,\u2017,\u203E,\u309B-\u309C] SubscriptFolding; Map(NFD); [:dt=sub:] SymbolFolding; Map(NFD); [\u00B5 \u2107 \u2135-\u2138] UnderlineFolding; Map(\u005E); [\u2017 \uFE4D-\uFE4F] VerticalFormsFolding; Map(NFD); [:dt=vertical:] CircledSymbolsExpansion; Map(NFD); [:dt=circled:] DottedExpansion; Map(NFD); [\u2488-\u249B] EllipsisExpansion; Map(NFD); [\u2024-\u2026] FractionExpansion; Map(NFD); [:dt=fraction:] IntegralExpansion; Map(NFD); [\u222C-\u222D,\u222F-\u2230] LigatureExpansion; Map(NFD); [\u0587 \u0675-\u0678 \u0E33 \u0EB3 \u0EDC-\u0EDD \u0F77 \u0F79 \uFB00-\uFB06 \uFB13-\uFB17 \uFB4F] ParenthesizedExpansion; Map(NFD); [\u2474-\u2487,\u249C-\u24B5 \u3200-\u3243] PrimesExpansion; Map(NFD); [\u2033-\u2034,\u2036-\u2037] RomanNumeralsExpansion; Map(NFD); [\u2160-\u2183] SquaredSymbolsExpansion; Map(NFD); [:dt=square:] OtherSquaredExpansion; Map(NFD); [\u3358-\u3370 \u33E0-\u33FE \u32C0-\u32CB] DigraphExpansion; Map(NFD); [\u0132-\u0133 \u013F-\u0140. \u0149 \u01C4-\u01CC \u01F1-\u01F3 \u1E9A] OtherMultigraphExpansion; Map(NFD); [\u203C \u2047-\u2049 \u20A8 \u2100-\u2101 \u2103 \u2105-\u2106 \u2109 \u2116 \u2121] DiacriticFolding; Map(DiacriticFolding); [:isDiacriticFolding:] HanRadicalFolding; Map(HanRadicalFolding); [\u2F00-\u2F5D \u2EF3 \u2E9F] HiraganaFolding; Map(HiraganaFolding); [:isHiraganaFolding:] KatakanaFolding; Map(KatakanaFolding); [:isKatakanaFolding:] LetterformsFolding; Map(LetterformFolding); [:isLetterformFolding:] SimplifiedHanFolding; Map(SimplifiedHanFolding); [:isSimplifiedHanFolding:] SuperscriptFolding; Map(SuperScriptFolding); [:isSuperScriptFolding:] SuzhouFolding; Map(SuzhouFolding); [\u3038-\u303A \u3021-\u3029] WidthFolding; Map(WidthFolding); [:dt=wide:]+[:dt=narrow:]