Skip to content
62 changes: 62 additions & 0 deletions LineBreakClasses.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,62 @@
# Class name ; Class definition in UnicodeSet notation
CM ; [\p{Line_Break=Combining_Mark}]
BAmEastAsian ; [\p{Line_Break=Break_After}-[\p{ea=F}\p{ea=W}\p{ea=H}]]
LF ; [\p{Line_Break=Line_Feed}]
BK|NL ; [[\p{Line_Break=Mandatory_Break}] [\p{Line_Break=Next_Line}]]
CR ; [\p{Line_Break=Carriage_Return}]
SP ; [\p{Line_Break=Space}]
EXmEastAsian ; [\p{Line_Break=Exclamation}-[\p{ea=F}\p{ea=W}\p{ea=H}]]
QUmPimPf ; [\p{Line_Break=Quotation}-\p{gc=Pi}-\p{gc=Pf}]
AImEastAsian|ALmEastAsianmDottedCircle|SG|XXmExtPictUnassigned ; [[\p{Line_Break=Ambiguous}-[\p{ea=F}\p{ea=W}\p{ea=H}]] [\p{Line_Break=Alphabetic}-[\p{ea=F}\p{ea=W}\p{ea=H}]-[◌]] [\p{Line_Break=Surrogate}] [\p{Line_Break=Unknown}-[\p{Extended_Pictographic=True}&\p{gc=Cn}]]]
PRmEastAsian ; [\p{Line_Break=Prefix_Numeric}-[\p{ea=F}\p{ea=W}\p{ea=H}]]
POmEastAsian ; [\p{Line_Break=Postfix_Numeric}-[\p{ea=F}\p{ea=W}\p{ea=H}]]
OPmEastAsian ; [\p{Line_Break=Open_Punctuation}-[\p{ea=F}\p{ea=W}\p{ea=H}]]
CP ; [\p{Line_Break=CP}]
IS ; [\p{Line_Break=Infix_Numeric}]
HY ; [\p{Line_Break=Hyphen}]
SY ; [\p{Line_Break=Break_Symbols}]
NU ; [\p{Line_Break=Numeric}]
CLmEastAsian ; [\p{Line_Break=Close_Punctuation}-[\p{ea=F}\p{ea=W}\p{ea=H}]]
GLmEastAsian ; [\p{Line_Break=Glue}-[\p{ea=F}\p{ea=W}\p{ea=H}]]
QU_Pi ; [\p{Line_Break=Quotation}&\p{gc=Pi}]
BB ; [\p{Line_Break=Break_Before}]
QU_Pf ; [\p{Line_Break=Quotation}&\p{gc=Pf}]
HH ; [\p{Line_Break=Unambiguous_Hyphen}]
HL ; [\p{Line_Break=HL}]
JL ; [\p{Line_Break=JL}]
JV ; [\p{Line_Break=JV}]
JT ; [\p{Line_Break=JT}]
NSmEastAsian ; [\p{Line_Break=Nonstarter}-[\p{ea=F}\p{ea=W}\p{ea=H}]]
AK ; [\p{Line_Break=Aksara}]
VI ; [\p{Line_Break=Virama}]
AS ; [\p{Line_Break=Aksara_Start}]
IDmEastAsianmExtPictUnassigned ; [\p{Line_Break=Ideographic}-[\p{ea=F}\p{ea=W}\p{ea=H}]-[\p{Extended_Pictographic=True}&\p{gc=Cn}]]
VF ; [\p{Line_Break=Virama_Final}]
ZW ; [\p{Line_Break=ZWSpace}]
ZWJ ; [\p{Line_Break=ZWJ}]
B2 ; [\p{Line_Break=Break_Both}]
INmEastAsian ; [\p{Line_Break=Inseparable}-[\p{ea=F}\p{ea=W}\p{ea=H}]]
WJ ; [\p{Line_Break=Word_Joiner}]
PR_EastAsian ; [\p{Line_Break=Prefix_Numeric}&[\p{ea=F}\p{ea=W}\p{ea=H}]]
ID_EastAsian ; [\p{Line_Break=Ideographic}&[\p{ea=F}\p{ea=W}\p{ea=H}]]
OP_EastAsian ; [\p{Line_Break=Open_Punctuation}&[\p{ea=F}\p{ea=W}\p{ea=H}]]
CL_EastAsian ; [\p{Line_Break=Close_Punctuation}&[\p{ea=F}\p{ea=W}\p{ea=H}]]
AI_EastAsian|AL_EastAsian ; [[\p{Line_Break=Ambiguous}&[\p{ea=F}\p{ea=W}\p{ea=H}]] [\p{Line_Break=Alphabetic}&[\p{ea=F}\p{ea=W}\p{ea=H}]]]
AL_DottedCircle ; [\p{Line_Break=Alphabetic}&[◌]]
ID_ExtPictUnassigned|EBmEastAsian ; [[\p{Line_Break=Ideographic}&[\p{Extended_Pictographic=True}&\p{gc=Cn}]] [\p{Line_Break=E_Base}-[\p{ea=F}\p{ea=W}\p{ea=H}]]]
EB_EastAsian ; [\p{Line_Break=E_Base}&[\p{ea=F}\p{ea=W}\p{ea=H}]]
BA_EastAsian ; [\p{Line_Break=Break_After}&[\p{ea=F}\p{ea=W}\p{ea=H}]]
NS_EastAsian|CJ ; [[\p{Line_Break=Nonstarter}&[\p{ea=F}\p{ea=W}\p{ea=H}]] [\p{Line_Break=Conditional_Japanese_Starter}]]
H2 ; [\p{Line_Break=H2}]
H3 ; [\p{Line_Break=H3}]
EX_EastAsian ; [\p{Line_Break=Exclamation}&[\p{ea=F}\p{ea=W}\p{ea=H}]]
IN_EastAsian ; [\p{Line_Break=Inseparable}&[\p{ea=F}\p{ea=W}\p{ea=H}]]
PO_EastAsian ; [\p{Line_Break=Postfix_Numeric}&[\p{ea=F}\p{ea=W}\p{ea=H}]]
CB ; [\p{Line_Break=Contingent_Break}]
AP ; [\p{Line_Break=Aksara_Prebase}]
GL_EastAsian ; [\p{Line_Break=Glue}&[\p{ea=F}\p{ea=W}\p{ea=H}]]
RI ; [\p{Line_Break=Regional_Indicator}]
EM ; [\p{Line_Break=E_Modifier}]
XX_ExtPictUnassigned ; [\p{Line_Break=Unknown}&[\p{Extended_Pictographic=True}&\p{gc=Cn}]]
SAmMnmMc ; [[\p{Line_Break=Complex_Context}-\p{gc=Mn}-\p{gc=Mc}]]
SA_Mn|SA_Mc ; [[[\p{Line_Break=Complex_Context}&\p{gc=Mn}]] [[\p{Line_Break=Complex_Context}&\p{gc=Mc}]]]
201 changes: 201 additions & 0 deletions LineBreakStates.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,201 @@
# State name ; Accepting (Yes, No, or lookahead name); lookahead name or empty.
START ; No ;
SP QU_Pf ; No ;
PRmEastAsian OPmEastAsian ; No ;
PRmEastAsian OPmEastAsian IS ; No ;
AK AK ; No ;
SP IS ZWJ ; No ;
CM ; Yes ;
NU ; Yes ;
HL ; Yes ;
OPmEastAsian SP CM ; Yes ;
BAmEastAsian ; Yes ;
SP ; Yes ;
EXmEastAsian ; Yes ;
CLmEastAsian ; Yes ;
QUmPimPf ; Yes ;
WJ ; Yes ;
OPmEastAsian ; Yes ;
GLmEastAsian ; Yes ;
ZWJ ; Yes ;
BAmEastAsian ZWJ ; Yes ;
EXmEastAsian ZWJ ; Yes ;
PRmEastAsian ZWJ ; Yes ;
POmEastAsian ZWJ ; Yes ;
IS ZWJ ; Yes ;
CP ZWJ ; Yes ;
HY ZWJ ; Yes ;
SY ZWJ ; Yes ;
NU ZWJ ; Yes ;
CLmEastAsian ZWJ ; Yes ;
BB ZWJ ; Yes ;
HH ZWJ ; Yes ;
HL ZWJ ; Yes ;
JV ZWJ ; Yes ;
JT ZWJ ; Yes ;
AK ZWJ ; Yes ;
IDmEastAsianmExtPictUnassigned ZWJ ; Yes ;
B2 ZWJ ; Yes ;
AL_DottedCircle ZWJ ; Yes ;
EBmEastAsian ZWJ ; Yes ;
CB ZWJ ; Yes ;
AP ZWJ ; Yes ;
XX_ExtPictUnassigned ZWJ ; Yes ;
CM HY ZWJ ; Yes ;
OPmEastAsian SP ZWJ ; Yes ;
NU CP ZWJ ; Yes ;
NU IS ZWJ ; Yes ;
NU SY ZWJ ; Yes ;
NU CLmEastAsian ZWJ ; Yes ;
HL HY ZWJ ; Yes ;
AK VI ZWJ ; Yes ;
PRmEastAsian ; Yes ;
POmEastAsian ; Yes ;
CP ; Yes ;
IS ; Yes ;
HY ; Yes ;
SY ; Yes ;
BB ; Yes ;
HH ; Yes ;
JV ; Yes ;
JT ; Yes ;
AK ; Yes ;
IDmEastAsianmExtPictUnassigned ; Yes ;
B2 ; Yes ;
OP_EastAsian ; Yes ;
GL_EastAsian ; Yes ;
AL_DottedCircle ; Yes ;
EBmEastAsian ; Yes ;
CB ; Yes ;
AP ; Yes ;
RI ; Yes ;
XX_ExtPictUnassigned ; Yes ;
CM HY ; Yes ;
CM QU_Pf ; Yes ;
OPmEastAsian SP ; Yes ;
CP SP ; Yes ;
NU CP ; Yes ;
NU IS ; Yes ;
NU SY ; Yes ;
NU CLmEastAsian ; Yes ;
HL HY ; Yes ;
JL QU_Pi ; Yes ;
JL ZWJ ; Yes ;
PR_EastAsian ZWJ ; Yes ;
ID_EastAsian ZWJ ; Yes ;
CL_EastAsian ZWJ ; Yes ;
AL_EastAsian ZWJ ; Yes ;
EB_EastAsian ZWJ ; Yes ;
BA_EastAsian ZWJ ; Yes ;
CJ ZWJ ; Yes ;
H2 ZWJ ; Yes ;
H3 ZWJ ; Yes ;
PO_EastAsian ZWJ ; Yes ;
NU CL_EastAsian ZWJ ; Yes ;
AK VI ; Yes ;
B2 SP ; Yes ;
RI ZWJ ; Yes ;
CM QU_Pf eot ; Yes ;
JL CM QU_Pi ; Yes ;
JL QU_Pf ZWJ ; Yes ;
RI RI ZWJ ; Yes ;
OPmEastAsian SP IS ZWJ ; Yes ;
RI ZWJ RI ZWJ ; Yes ;
LF ; Yes ;
CR ; Yes ;
JL ; Yes ; JL / QU_Pi JL
PR_EastAsian ; Yes ; JL / QU_Pi JL
ID_EastAsian ; Yes ; JL / QU_Pi JL
CL_EastAsian ; Yes ; JL / QU_Pi JL
CJ ; Yes ; JL / QU_Pi JL
AL_EastAsian ; Yes ; JL / QU_Pi JL
EB_EastAsian ; Yes ; JL / QU_Pi JL
BA_EastAsian ; Yes ; JL / QU_Pi JL
H2 ; Yes ; JL / QU_Pi JL
H3 ; Yes ; JL / QU_Pi JL
PO_EastAsian ; Yes ; JL / QU_Pi JL
NU CL_EastAsian ; Yes ; JL / QU_Pi JL
ZW ; Yes ; ZW / CM
ZW SP ; Yes ; ZW / CM
SP IS ; No ; SP IS / PRmEastAsian
JL CM ; Yes ; JL CM / QU_Pi JL
PR_EastAsian CM ; Yes ; JL CM / QU_Pi JL
ID_EastAsian CM ; Yes ; JL CM / QU_Pi JL
CL_EastAsian CM ; Yes ; JL CM / QU_Pi JL
CJ CM ; Yes ; JL CM / QU_Pi JL
AL_EastAsian CM ; Yes ; JL CM / QU_Pi JL
EB_EastAsian CM ; Yes ; JL CM / QU_Pi JL
BA_EastAsian CM ; Yes ; JL CM / QU_Pi JL
H2 CM ; Yes ; JL CM / QU_Pi JL
H3 CM ; Yes ; JL CM / QU_Pi JL
PO_EastAsian CM ; Yes ; JL CM / QU_Pi JL
NU CL_EastAsian CM ; Yes ; JL CM / QU_Pi JL
JL QU_Pf ; Yes ; JL QU_Pf / JL
ZW CM ; ZW / CM ;
ZW SP EXmEastAsian ; ZW / CM ;
ZW SP CLmEastAsian ; ZW / CM ;
ZW SP CP ; ZW / CM ;
ZW SP SY ; ZW / CM ;
ZW SP QU_Pf ; ZW / CM ;
ZW SP WJ ; ZW / CM ;
RI RI ; No ; RI RI / ALmEastAsianmDottedCircle
SP IS CM ; No ; SP IS CM / PRmEastAsian
SP IS PRmEastAsian ; SP IS / PRmEastAsian ;
OPmEastAsian SP IS ; Yes ; SP IS / PRmEastAsian
JL QU_Pi JL ; JL / QU_Pi JL ; JL / QU_Pi JL
JL QU_Pi PR_EastAsian ; JL / QU_Pi JL ; JL / QU_Pi JL
JL QU_Pi ID_EastAsian ; JL / QU_Pi JL ; JL / QU_Pi JL
JL QU_Pi CL_EastAsian ; JL / QU_Pi JL ; JL / QU_Pi JL
JL QU_Pi CJ ; JL / QU_Pi JL ; JL / QU_Pi JL
JL QU_Pi AL_EastAsian ; JL / QU_Pi JL ; JL / QU_Pi JL
JL QU_Pi EB_EastAsian ; JL / QU_Pi JL ; JL / QU_Pi JL
JL QU_Pi BA_EastAsian ; JL / QU_Pi JL ; JL / QU_Pi JL
JL QU_Pi H2 ; JL / QU_Pi JL ; JL / QU_Pi JL
JL QU_Pi H3 ; JL / QU_Pi JL ; JL / QU_Pi JL
JL QU_Pi PO_EastAsian ; JL / QU_Pi JL ; JL / QU_Pi JL
JL QU_Pi OP_EastAsian ; JL / QU_Pi JL ;
JL QU_Pi GL_EastAsian ; JL / QU_Pi JL ;
JL QU_Pf CM ; Yes ; JL QU_Pf CM / JL
JL QU_Pf JL ; JL QU_Pf / JL ; JL / QU_Pi JL
JL QU_Pf PR_EastAsian ; JL QU_Pf / JL ; JL / QU_Pi JL
JL QU_Pf ID_EastAsian ; JL QU_Pf / JL ; JL / QU_Pi JL
JL QU_Pf AL_EastAsian ; JL QU_Pf / JL ; JL / QU_Pi JL
JL QU_Pf EB_EastAsian ; JL QU_Pf / JL ; JL / QU_Pi JL
JL QU_Pf H2 ; JL QU_Pf / JL ; JL / QU_Pi JL
JL QU_Pf H3 ; JL QU_Pf / JL ; JL / QU_Pi JL
JL QU_Pf PO_EastAsian ; JL QU_Pf / JL ; JL / QU_Pi JL
JL QU_Pf OP_EastAsian ; JL QU_Pf / JL ;
ZW SP IS ; ZW / CM ; SP IS / PRmEastAsian
ZW SP CL_EastAsian ; ZW / CM ; JL / QU_Pi JL
ZW SP EX_EastAsian ; ZW / CM ; JL / QU_Pi JL
RI ZWJ RI ; Yes ; RI RI / ALmEastAsianmDottedCircle
RI RI CM ; No ; RI RI CM / ALmEastAsianmDottedCircle
RI RI ALmEastAsianmDottedCircle ; RI RI / ALmEastAsianmDottedCircle ;
SP IS CM PRmEastAsian ; SP IS CM / PRmEastAsian ;
OPmEastAsian SP IS CM ; Yes ; SP IS CM / PRmEastAsian
JL CM QU_Pi JL ; JL CM / QU_Pi JL ; JL / QU_Pi JL
JL CM QU_Pi PR_EastAsian ; JL CM / QU_Pi JL ; JL / QU_Pi JL
JL CM QU_Pi ID_EastAsian ; JL CM / QU_Pi JL ; JL / QU_Pi JL
JL CM QU_Pi CL_EastAsian ; JL CM / QU_Pi JL ; JL / QU_Pi JL
JL CM QU_Pi CJ ; JL CM / QU_Pi JL ; JL / QU_Pi JL
JL CM QU_Pi AL_EastAsian ; JL CM / QU_Pi JL ; JL / QU_Pi JL
JL CM QU_Pi EB_EastAsian ; JL CM / QU_Pi JL ; JL / QU_Pi JL
JL CM QU_Pi BA_EastAsian ; JL CM / QU_Pi JL ; JL / QU_Pi JL
JL CM QU_Pi H2 ; JL CM / QU_Pi JL ; JL / QU_Pi JL
JL CM QU_Pi H3 ; JL CM / QU_Pi JL ; JL / QU_Pi JL
JL CM QU_Pi PO_EastAsian ; JL CM / QU_Pi JL ; JL / QU_Pi JL
JL CM QU_Pi OP_EastAsian ; JL CM / QU_Pi JL ;
JL CM QU_Pi GL_EastAsian ; JL CM / QU_Pi JL ;
JL QU_Pf CM JL ; JL QU_Pf CM / JL ; JL / QU_Pi JL
JL QU_Pf CM PR_EastAsian ; JL QU_Pf CM / JL ; JL / QU_Pi JL
JL QU_Pf CM ID_EastAsian ; JL QU_Pf CM / JL ; JL / QU_Pi JL
JL QU_Pf CM AL_EastAsian ; JL QU_Pf CM / JL ; JL / QU_Pi JL
JL QU_Pf CM EB_EastAsian ; JL QU_Pf CM / JL ; JL / QU_Pi JL
JL QU_Pf CM H2 ; JL QU_Pf CM / JL ; JL / QU_Pi JL
JL QU_Pf CM H3 ; JL QU_Pf CM / JL ; JL / QU_Pi JL
JL QU_Pf CM PO_EastAsian ; JL QU_Pf CM / JL ; JL / QU_Pi JL
JL QU_Pf CM OP_EastAsian ; JL QU_Pf CM / JL ;
RI ZWJ RI CM ; Yes ; RI RI CM / ALmEastAsianmDottedCircle
RI ZWJ RI RI ; RI RI / ALmEastAsianmDottedCircle ; RI RI / ALmEastAsianmDottedCircle
RI RI CM ALmEastAsianmDottedCircle ; RI RI CM / ALmEastAsianmDottedCircle ;
RI ZWJ RI CM RI ; RI RI CM / ALmEastAsianmDottedCircle ; RI RI / ALmEastAsianmDottedCircle
Loading
Loading