# Segmentation rules for WordBreak

#

# Character Classes

#

$CR=\p{Word_Break=CR}

$LF=\p{Word_Break=LF}

$Newline=\p{Word_Break=Newline}

$Extend=\p{Word_Break=Extend}

#

# Now normal variables

#

$Format=\p{Word_Break=Format}

$Katakana=\p{Word_Break=Katakana}

$ALetter=\p{Word_Break=ALetter}

$MidLetter=\p{Word_Break=MidLetter}

$MidNum=\p{Word_Break=MidNum}

$MidNumLet=\p{Word_Break=MidNumLet}

$Numeric=\p{Word_Break=Numeric}

$ExtendNumLet=\p{Word_Break=ExtendNumLet}

$RI=\p{Word_Break=Regional_Indicator}

$Hebrew_Letter=\p{Word_Break=Hebrew_Letter}

$Double_Quote=\p{Word_Break=Double_Quote}

$Single_Quote=\p{Word_Break=Single_Quote}

$E_Base=\p{Word_Break=E_Base}

$E_Modifier=\p{Word_Break=E_Modifier}

$ZWJ=\p{Word_Break=ZWJ}

$Glue_After_Zwj=\p{Word_Break=Glue_After_Zwj}

$EBG=\p{Word_Break=E_Base_GAZ}

#

# WARNING: For Rule 4: Fixes for GC, Format

#

# Add format and extend to everything

#

$FE=[$Format $Extend $ZWJ]

#

# Special rules

#

$NotBreak_=[^ $Newline $CR $LF ]

$Katakana=($Katakana $FE*)

$ALetter=($ALetter $FE*)

$MidLetter=($MidLetter $FE*)

$MidNum=($MidNum $FE*)

$MidNumLet=($MidNumLet $FE*)

$Numeric=($Numeric $FE*)

$ExtendNumLet=($ExtendNumLet $FE*)

$RI=($RI $FE*)

$Hebrew_Letter=($Hebrew_Letter $FE*)

$Double_Quote=($Double_Quote $FE*)

$Single_Quote=($Single_Quote $FE*)

$E_Base=($E_Base $FE*)

$E_Modifier=($E_Modifier $FE*)

$Glue_After_Zwj=($Glue_After_Zwj $FE*)

$EBG=($EBG $FE*)

#

# Macros

#

$AHLetter=($ALetter | $Hebrew_Letter)

$MidNumLetQ=($MidNumLet | $Single_Quote)

#

# Rules

#

# Break at the start and end of text, unless the text is empty.

#

# Do not break within CRLF.

#

3) $CR   ×   $LF

#

# Otherwise break before and after Newlines (including CR and LF)

#

3.1) ($Newline | $CR | $LF) ÷

3.2) ÷    ($Newline | $CR | $LF)

#

# Do not break within emoji zwj sequences.

#

3.3) $ZWJ × ($Glue_After_Zwj | $EBG)

#

# Ignore Format and Extend characters, except after sot, CR, LF, and Newline. (See Section 6.2, Replacing Ignore Rules.) This also has the effect of: Any × (Format | Extend)

#

# WARNING: Implemented as don't break before format (except after linebreaks),

#

# AND add format and extend in all variables definitions that appear after this point!

#

4) $NotBreak_ × [$Format $Extend $ZWJ]

#

# Vanilla rules

#

# Do not break between most letters.

#

5) $AHLetter   ×   $AHLetter

#

# Do not break letters across certain punctuation.

#

6) $AHLetter × ($MidLetter | $MidNumLetQ) $AHLetter

7) $AHLetter ($MidLetter | $MidNumLetQ) × $AHLetter

7.1) $Hebrew_Letter × $Single_Quote

7.2) $Hebrew_Letter × $Double_Quote $Hebrew_Letter

7.3) $Hebrew_Letter $Double_Quote × $Hebrew_Letter

#

# Do not break within sequences of digits, or digits adjacent to letters (“3a”, or “A3”).

#

8) $Numeric × $Numeric

9) $AHLetter × $Numeric

10) $Numeric × $AHLetter

#

# Do not break within sequences, such as “3.2” or “3,456.789”.

#

11) $Numeric ($MidNum | $MidNumLetQ) × $Numeric

12) $Numeric × ($MidNum | $MidNumLetQ) $Numeric

#

# Do not break between Katakana.

#

13) $Katakana × $Katakana

#

# Do not break from extenders.

#

13.1) ($AHLetter | $Numeric | $Katakana | $ExtendNumLet) × $ExtendNumLet

13.2) $ExtendNumLet × ($AHLetter | $Numeric | $Katakana)

#

# Do not break within emoji modifier sequences.

#

14) ($E_Base | $EBG) × $E_Modifier

#

# Do not break within emoji flag sequences. That is, do not break between regional indicator (RI) symbols if there is an odd number of RI characters before the break point.

#

15) ^ ($RI $RI)* $RI × $RI

16) [^$RI] ($RI $RI)* $RI × $RI

17) $RI ÷ $RI

#

# Otherwise, break everywhere (including around ideographs).

#