#Input is Main:Sub~Subsub

.*Category:(.* - [^ ]*)[ ](.*)~(.*)>$2:$1~$3

.*Category:([^ ]*)[ ](.*)~(.*)>$2:$1~$3

.*Category:(.*)~(.*)>$1:$2

.*Category:([^ ]*)[ ](.*)>$2:$1

.*Category:(.*)>$1:Miscellaneous



Mark:(.*) > Modifier:$1



Symbol:Latin 1 Supplement@Other Symbol~Latin-1 punctuation and symbols > Symbol:Miscellaneous



Symbol:.*@Currency Symbol.* > Symbol:Currency

Symbol:.*@Math Symbol.* > Symbol:Math

Symbol:.*Control Pictures.* > Symbol:Control Pictures

Symbol:.*~.*(arrows|harpoons).* > Symbol:Arrows



Symbol:(.*)symbols?>Symbol:$1

Symbol:.*(Gender|Genealogic).* > Symbol:Gender and Genealogical

Symbol:.*Star.* > Symbol:Stars/Asterisks

Symbol:.*(Dice|Chess|Go Markers|Playing|Checkers|Tiles).* > Symbol:Game Pieces

Symbol:.*(Box Drawing|Block Elements|Geometric Shapes|Miscellaneous Symbols And Arrows).*>Symbol:Geometric Shapes

Symbol:.*Musical.*>Symbol:Musical

Symbol:.*Halfwidth And Fullwidth Forms.*>Symbol:Geometric Shapes

Symbol:.*Optical Character Recognition.*>Symbol:Technical

Symbol:.*(weather|astrologic|zodiac).*>Symbol:Weather and Astrological

Symbol:.*(keyboard|\bGUI\b).*>Symbol:Keyboard and UI

Symbol:.*Letterlike Symbols.*>Symbol:Letterlike

Symbol:.*Modifier.*>Modifier:Spacing

Symbol:(Specials|Dingbat|Miscellaneous symbol).*>Symbol:Miscellaneous

Symbol:.*Miscellaneous Technical.* > Symbol:Technical

Symbol:.*(Tai Xuan Jing|Yijing).* > Symbol:Yijing / Tai Xuan Jing

Symbol:(.*)Historic.* > Symbol:$1Historic

Symbol:(.*)Letterlike(.*) > Symbol:$1Technical$2





#Punctuation:Other~(.*)>Punctuation:$1

Punctuation:(Open|Close|Initial|Final)(.*)>Punctuation:Paired

Punctuation:(Dash|Connector)~(.*)>Punctuation:Dash/Connector

#Punctuation:.*CJK.*>Punctuation:CJK

Punctuation:.*~(ASCII|Latin).*>Punctuation:ASCII Based

Punctuation:(.*(Compatibility|Historic)).* > Punctuation:$1

# rename category



Number:.*(circled|parenthesized|Numbers period).* > Number:Enclosed/Dotted

Number:.*Compatibility.*~.*(latin-1|fraction|scripts).* > Number:Fractions/Related

Number:(.*(Compatibility|Historic)).* > Number:$1

Number:.*(Letter|Less Common).* > Number:Other









#Modifier:(Spacing|Enclosing)~(.*)>Modifier:$1



Format & Whitespace:(Other)~(.*)>Format & Whitespace:$1

Format & Whitespace:(.*(Historic|Compatibility))(.*) > Format & Whitespace:$1

Format & Whitespace:.*Grapheme joiner.* > Format & Whitespace:Format

Format & Whitespace:Other > Format & Whitespace:Variation Selector





#(.*[^])Other(.*)>$1Other$2

#(.*)(.*)>$1$2



# remove duplication in names

(.*)Historic - Ancient(.*) > $1Historic - Other$2

(.*)Compatibility - Compatibility(.*) > $1Compatibility - Other$2



# remove "Other"



(Symbol|Punctuation|Modifier|Number|Format & Whitespace|Latin|Hangul|Han .*):(.*(Compatibility|Historic)).* > $1:$2



#Merge obsolete Han



##(.*CJK.*):(.*) > CJK (Han):Compatibility

(Han .*):.*(CJK strokes|CJK radicals supplement) > $1:CJK Strokes

(Han .*):.*Ideographic description characters > $1:Ideographic Description

(.*)Less Common(.*)Other.* > $1Less Common

##(.*Han.*)Compatibility(.*)Other.* > $1Other





#Fix Thai/Lao

Southeast Asian Scripts:(.*Compatibility - )(.*) > Southeast Asian Scripts:$2



Other European Scripts:Braille.* > Symbol:Braille



# Suppress all of the other third-level items after the above merges

(.*):(.*)~.* > $1:$2



