I want to extend my grammar, so that it is allowed to define a regex value inside double quotes, here is an example which I want to allow
matches(value, test| ".*foobar[A-Z]");
Actually this is not recognized, because the dot and brackets are recognized before. Here is the Parse Tree
How can I resolve this, I tried it with a new rule ANY: . but with that I could not solve it. Any ideas?
This is my grammar
grammar FEL;
prog: expr+ SEMI? EOF;
expr:
statement #StatementExpr
|NOT expr #NotExpr
| expr AND expr #AndExpr
| expr (OR | XOR) expr #OrExpr
| function #FunctionExpr
| LPAREN expr RPAREN #ParenExpr
| writeCommand #WriteExpr
;
writeCommand: setCommand | setIfCommand;
statement: ID '=' getCommand NEWLINE #Assign;
setCommand: 'set' LPAREN variable = variableType '|' value = parameter RPAREN;
setIfCommand: 'setIf' LPAREN variableType '|' expr '?' p1 = parameter ':' p2 = parameter RPAREN;
getCommand: getFieldValue #FieldValue
| getInstanceAttribValue #InstanceAttribValue
| getFormAttribValue #FormAttributeValue
| getMandatorAttribValue #MandatorAttributeValue
;
getFieldValue: 'getFieldValue' LPAREN instanceID=ID COMMA fieldname=ID RPAREN;
getInstanceAttribValue: 'getInstanceAttrib' LPAREN instanceId=ID COMMA moduleId=ID COMMA attribname=ID RPAREN;
getFormAttribValue: 'getFormAttrib' LPAREN formId=ID COMMA moduleId=ID COMMA attribname=ID RPAREN;
getMandatorAttribValue: 'getMandatorAttrib' LPAREN mandator=ID COMMA moduleId=ID COMMA attribname=ID RPAREN;
parameter:
variableType
| constType
;
anyType: DoubleQuote ANY DoubleQuote;
pdixFuncton:ID;
constType:
ID #ID_Without
| '"' ID '"' #ID_WITH
| INT #INT_VALUE
| DIGIT_DOT #DIGIT_DOT_VALUE
;
variableType:
valueType #Variable_Value
|instanceType #Variable_Instance
|formType #Variable_Form
|bufferType #Variable_Buffer
|instanceAttribType #Variable_Instance_Attrib
|formAttribType #Variable_Form_Attrib
|mandatorAttribType #Variable_Mandator_Attrib
|instanceAttachmentType #Variable_Instance_Attachment
|formAttachmentType #Variable_Form_Attachment
|mandatorAttachmentType #Variable_Mandator_Attachment
;
valueType:'value' COMMA par=parameter (COMMA functionParameter)?;
instanceType: 'instance' COMMA instanceParameter;
formType: 'form' COMMA formParameter;
bufferType: 'buffer' COMMA id=ID;
instanceParameter: 'instanceId'
| 'instanceKey'
| 'firstpenId'
| 'lastpenId'
| 'lastUpdate'
| 'started'
;
formParameter: 'formId'
|'formKey'
|'lastUpdate'
;
functionParameter: 'lastPen'
| 'fieldGroup'
| ' fieldType'
| 'fieldSource'
| 'updateId'
| 'sessionId'
| 'icrConfidence'
| 'icrRecognition'
| 'lastUpdate';
instanceAttribType: p = ('instattrib' | 'instanceattrib') COMMA attributeType;
formAttribType:'formattrib' COMMA attributeType;
mandatorAttribType: 'mandatorattrib' COMMA attributeType;
instanceAttachmentType:('instattachment' | 'instanceatt') COMMA attachmentType;
formAttachmentType:'formAtt' COMMA attachmentType;
mandatorAttachmentType: 'mandatoratt' COMMA attachmentType;
attributeType: module = ID '#' attribName = ID;
attachmentType: name = ID '#' page = INT '#' index = INT;
function:
commandIsSet
|commandIsEmpty
|commandIsEqual
|commandIsNumLessEqual
|commandIsNumLess
|commandIsNumGreaterEqual
|commandIsNumGreater
|commandIsNumEqual
|commandIsLess
|commandIsLessEqual
|commandIsGreater
|commandIsGreaterEqual
|commandMatches
|commandContains
|commandEndsWith
|commandStartsWith
;
commandIsSet: IS_SET LPAREN parameter RPAREN;
commandIsEmpty: IS_EMPTY LPAREN parameter RPAREN;
commandIsEqual: IS_EQUAL LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandStartsWith: 'startsWith' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandEndsWith: 'endsWith' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandContains: 'contains' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandMatches: 'matches' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandIsLess: 'isLess' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandIsLessEqual: 'isLessEqual' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandIsGreater: 'isGreater' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandIsGreaterEqual: 'isGreaterEqual' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandIsNumEqual: 'isNumEqual' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandIsNumGreater: 'isNumGreater' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandIsNumGreaterEqual: 'isNumGreaterEqual' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandIsNumLess: 'isNumLess' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
commandIsNumLessEqual: 'isNumLessEqual' LPAREN p1 = parameter '|' p2 = parameter RPAREN;
/*
stringFunctionType:
a=substringStrFunction
| a=cutStrFunction
| a=replaceStrFunction
| a=reformatDateStrFunction
| a=translateStrFunction
| a=fillStrFunction
| a=concatStrFunction
| a=justifyStrFunction
| a=ifElseStrFunction
| a=tokenStrFunction
| a=toLowerFunction
| a=toUpperFunction
| a=trimFunction
;
*/
LPAREN : '(';
RPAREN : ')';
LBRACE : '{';
RBRACE : '}';
LBRACK : '[';
RBRACK : ']';
SEMI : ';';
COMMA : ',';
DOT : '.';
ASSIGN : '=';
GT : '>';
LT : '<';
BANG : '!';
TILDE : '~';
QUESTION : '?';
COLON : ':';
EQUAL : '==';
LE : '<=';
GE : '>=';
NOTEQUAL : '!=';
AND : 'and';
OR : 'or';
XOR :'xor';
NOT :'not' ;
INC : '++';
DEC : '--';
ADD : '+';
SUB : '-';
MUL : '*';
DIV : '/';
INT: [0-9]+;
DIGIT_DOT: FloatNumber;
IS_SET:'isSet';
IS_EMPTY:'isEmpty';
IS_EQUAL:'isEqual';
WS: (' '|'' | NEWLINE | '
' )+ -> skip;
NEWLINE: '
';
ID: JavaLetter JavaLetterOrDigit* | ANY;
ANY: . ;
fragment FloatNumber: ('0'..'9')+ ('.' ('0'..'9')+)?;
fragment
JavaLetter
: [a-zA-Z$_] // these are the "java letters" below 0xFF
| // covers all characters above 0xFF which are not a surrogate
~[u0000-u00FFuD800-uDBFF]
{Character.isJavaIdentifierStart(_input.LA(-1))}?
| // covers UTF-16 surrogate pairs encodings for U+10000 to U+10FFFF
[uD800-uDBFF] [uDC00-uDFFF]
{Character.isJavaIdentifierStart(Character.toCodePoint((char)_input.LA(-2), (char)_input.LA(-1)))}?
;
fragment
JavaLetterOrDigit
: [a-zA-Z0-9$_] // these are the "java letters or digits" below 0xFF
| // covers all characters above 0xFF which are not a surrogate
~[u0000-u00FFuD800-uDBFF]
{Character.isJavaIdentifierPart(_input.LA(-1))}?
| // covers UTF-16 surrogate pairs encodings for U+10000 to U+10FFFF
[uD800-uDBFF] [uDC00-uDFFF]
{Character.isJavaIdentifierPart(Character.toCodePoint((char)_input.LA(-2), (char)_input.LA(-1)))}?
;
fragment DoubleQuote: '"' ; // Hard to read otherwise.
question from:
https://stackoverflow.com/questions/65854354/how-to-allow-all-chars-in-antlr-lexxer-inside-double-quotes-to-recognize-a-regex 与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…