RTF Parser Early Tests

MinRTF-control-rule.g4

grammar MinRtf ;

document : (control | text )+ ;

text : TEXT ;

control : KEYWORD INT? SPACE? ;

KEYWORD : '\\' (ASCIILETTER)+ ;

fragment ASCIILETTER : [A-Za-z] ;
fragment DIGIT : [0-9] ;

INT : '-'? DIGIT+ ;

WS : [\r\n] -> skip ;
SPACE : ' ' ;
TEXT : ~('\\' | '\r' | '\n' )+ ;

MinRTF-control-token.g4

grammar MinRtf ;

document : (control | text )+ ;

text : (TEXT | SPACE) ;
control : CONTROL ;
CONTROL : KEYWORD INT? SPACE? ;

KEYWORD : '\\' (ASCIILETTER)+ ;

fragment ASCIILETTER : [A-Za-z] ;
fragment DIGIT : [0-9] ;

INT : '-'? DIGIT+ ;

WS : [\r\n] -> skip ;
SPACE : ' ' ;

Results.md

Desired results

this one \b0 that one -> (document (text this one ) (control \b 0) (text that one))
this one \b0that one -> (document (text this one ) (control \b 0) (text that one))
this one \b that one -> (document (text this one ) (control \b) (text that one))
this one \b\i that one -> (document (text this one ) (control \b) (control \i) (text that one))

MinRtf-control-rule

this one \b0 that one -> (document (text this one ) (control \b) (text 0 that one))
this one \b0that one -> (document (text this one ) (control \b) (text 0that one))
this one \b that one -> (document (text this one ) (control \b) (text  that one))
this one \b\i that one -> (document (text this one ) (control \b) (control \i) (text that one))

MinRtf-control-token

this one \b0 that one -> (document (text this one ) (control \b0 ) (text that one))
this one \b0that one -> (document (text this one ) (control \b0) (text that one))
this one \b that one -> (document (text this one ) (control \b ) (text that one))
this one \b\i that one -> (document (text this one ) (control \b) (control \i ) (text that one))

TstLexer/TstParser

this one \b0 that one -> (document (text this one ) (control \b 0 ) (text that one))
this one \b0that one -> (document (text this one ) (control \b 0) (text that one))
this one \b that one -> (document (text this one ) (control \b) (text that one))
this one \b\i that one -> (document (text this one ) (control \b) (text that one)) plus token recognition error on '\' 'i'

TstLexer.g4

lexer grammar TstLexer;
KEYWORD : '\\' (ASCIILETTER)+ -> pushMode(CTRL) ;


fragment ASCIILETTER : [A-Za-z] ;
fragment DIGIT : [0-9] ;

WS : [\r\n] -> skip ;
SPACE : ' ' ;
TEXT : ~('\\' | '{' | '}' | '\n' | '\r')+ ;

mode CTRL;
IGNORE_SPACE : (' ' | '\n' | '\r') -> skip, popMode ;
INT : '-'? DIGIT+ SPACE? -> popMode ;

TstParser.g4

parser grammar TstParser ;

options { tokenVocab=TstLexer; }

document : (control | text )+ ;

text : (TEXT | SPACE) ;

control : KEYWORD INT* ;