Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Upgrade arden grammar to Arden syntax 3.0 R2 specification #4251

Merged
merged 2 commits into from
Sep 19, 2024
Merged

Upgrade arden grammar to Arden syntax 3.0 R2 specification #4251

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2755748
Upgrade arden grammar to Arden syntax 3.0 R2 specification
Sep 19, 2024
dbfdb99
Remove method names
Sep 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
222 changes: 99 additions & 123 deletions arden/ArdenLexer.g4
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,15 +1,10 @@
// $antlr-format alignTrailingComments true, columnLimit 150, maxEmptyLinesToKeep 1, reflowComments false, useTab false
// $antlr-format allowShortRulesOnASingleLine true, allowShortBlocksOnASingleLine true, minEmptyLines 0, alignSemicolons ownLine
// $antlr-format alignColons trailing, singleLineOverrulesHangingColon true, alignLexerCommands true, alignLabels true, alignTrailers true

lexer grammar ArdenLexer;
options {
caseInsensitive = true;
}

options { caseInsensitive = true; }

// Keywords
ABS : 'abs';
ACTION : 'action:';
ACTION : 'action';
ADD : 'add';
AFTER : 'after';
AGGREGATE : 'aggregate';
Expand All @@ -21,15 +16,15 @@ APPLICABILITY : 'applicability';
ARCCOS : 'arccos';
ARCSIN : 'arcsin';
ARCTAN : 'arctan';
ARDEN : 'arden:';
ARDEN_VERSION : 'version ' ('2' ('.' ( '1' | '2' | '5' | '6' | '7' | '8' | '9' | '10'))? | '3');
ARDEN : 'arden';
ARDEN_VERSION : 'version 3';
ARETRUE : 'aretrue';
ARGUMENT : 'argument';
AS : 'as';
AT : 'at';
ATTIME : 'attime';
ATTRIBUTE : 'attribute';
AUTHOR : 'author:' -> mode(TextMode);
AUTHOR : 'author' -> mode(TextMode);
AVERAGE : 'average' | 'avg';
BE : 'be';
BEFORE : 'before';
Expand All @@ -40,20 +35,19 @@ CALL : 'call';
CASE : 'case';
CEILING : 'ceiling';
CHARACTERS : 'characters';
CITATIONS : 'citations:';
CITATIONS : 'citations' -> mode(TextMode);
CLONE : 'clone';
CONCLUDE : 'conclude';
COSINE : 'cos' 'ine'?;
COUNT : 'count';
CRISP : 'crisp';
CURRENTTIME : 'currenttime';
DATA : 'data:';
DATAWC : 'data';
DATE : 'date:';
DATA : 'data';
DATE : 'date';
DAY : 'day' 's'?;
DECREASE : 'decrease';
DEFAULT : 'default';
DEFAULTCO : 'default:' -> mode(TwoCharMode);
DEFAULT_SLOT : DEFAULT COLON -> mode(TwoCharMode);
DEFUZZIFIED : 'defuzzified';
DELAY : 'delay';
DESTINATION : 'destination';
Expand All @@ -63,21 +57,21 @@ EARLIEST : 'earliest';
ELEMENTS : 'elements';
ELSE : 'else';
ELSEIF : 'elseif';
END : 'end:';
END : 'end';
ENDDO : 'enddo';
ENDIF : 'endif';
ENDSWITCH : 'endswitch';
EQUAL : 'equal';
EVENT : 'event';
EVENTTIME : 'eventtime';
EVERY : 'every';
EVOKE : 'evoke:';
EVOKE : 'evoke';
EXIST : 'exist' 's'?;
EXP : 'exp';
EXPLANATION : 'explanation:' -> mode(TextMode);
EXPLANATION : 'explanation' -> mode(TextMode);
EXTRACT : 'extract';
FALSE : 'false';
FILENAME : 'filename:' -> mode(MlmName);
FILENAME : 'filename' -> mode(MlmName);
FIND : 'find';
FIRST : 'first';
FLOOR : 'floor';
Expand All @@ -94,35 +88,35 @@ IN : 'in';
INCLUDE : 'include';
INCREASE : 'increase';
INDEX : 'index';
INSTITUTION : 'institution:' -> mode(TextMode);
INSTITUTIONWC : 'institution';
INSTITUTION : 'institution';
INSTITUTION_SLOT: INSTITUTION COLON -> mode(TextMode);
INT : 'int';
INTERFACE : 'interface';
INTERVAL : 'interval';
IS : 'is' | 'are' | 'was' | 'were';
ISTRUE : 'istrue';
IT : 'it' | 'they';
KEYWORDS : 'keywords' -> mode(TextMode);
KNOWLEDGE : 'knowledge:';
LANGUAGE : 'language:' -> mode(TwoCharMode);
KNOWLEDGE : 'knowledge';
LANGUAGE : 'language' -> mode(TwoCharMode);
LAST : 'last';
LATEST : 'latest';
LEAST : 'least';
LEFT : 'left';
LENGTH : 'length';
LESS : 'less';
LET : 'let';
LIBRARY : 'library:';
LIBRARY : 'library';
LINGUISTIC : 'linguistic';
LINKS : 'links:';
LINKS : 'links' -> mode(TextMode);
LINK_TYPE : 'url_link' | 'mesh_link' | 'other_link' | 'exe_link';
LIST : 'list';
LOCALIZED : 'localized';
LOG10 : 'log10';
LOG : 'log';
LOGIC : 'logic:';
LOGIC : 'logic';
LOWERCASE : 'lowercase';
MAINTENANCE : 'maintenance:';
MAINTENANCE : 'maintenance';
MATCHES : 'matches';
MAXIMUM : 'max' 'imum'?;
MEDIAN : 'median';
Expand All @@ -131,8 +125,8 @@ MESSAGE : 'message';
MINIMUM : 'min' 'imum'?;
MINUTE : 'minute' 's'?;
MLM : 'mlm';
MLMNAME : 'mlmname:' -> mode(MlmName);
MLM_SELF : 'mlm' [_-]'self';
MLMNAME : 'mlmname' -> mode(MlmName);
MLM_SELF : 'mlm'[_-]'self';
MONTH : 'month' 's'?;
MOST : 'most';
NAMES : 'names';
Expand All @@ -152,12 +146,12 @@ PATTERN : 'pattern';
PERCENT : 'percent' | '%';
PRECEDING : 'preceding';
PRESENT : 'present';
PRIORITY : 'priority:';
PURPOSE : 'purpose:' -> mode(TextMode);
PRIORITY : 'priority';
PURPOSE : 'purpose' -> mode(TextMode);
READ : 'read';
REMOVE : 'remove';
REPLACE : 'replace';
RESOURCES : 'resources:';
RESOURCES : 'resources';
RETURN : 'return';
REVERSE : 'reverse';
RIGHT : 'right';
Expand All @@ -169,7 +163,7 @@ SET : 'set';
SINE : 'sin' 'e'?;
SLOPE : 'slope';
SORT : 'sort';
SPECIALIST : 'specialist:' -> mode(TextMode);
SPECIALIST : 'specialist' -> mode(TextMode);
SQRT : 'sqrt';
STARTING : 'starting';
STDDEV : 'stddev';
Expand All @@ -184,7 +178,7 @@ THAN : 'than';
THE : 'the' -> channel(HIDDEN);
THEN : 'then';
TIME : 'time';
TITLE : 'title:' -> mode(TextMode);
TITLE : 'title' -> mode(TextMode);
TO : 'to';
TODAY : 'today';
TOMORROW : 'tomorrow';
Expand All @@ -193,144 +187,126 @@ TRIM : 'trim';
TRUE : 'true';
TRUNCATE : 'truncate';
TRUTHVALUE : 'truth value';
TYPE : 'type:';
TYPE_CODE : 'data' [_-]'driven';
TYPE : 'type';
TYPE_CODE : 'data'[_-]'driven';
UNTIL : 'until';
UPPERCASE : 'uppercase';
URGENCY : 'urgency:';
URGENCY : 'urgency';
USING : 'using';
VALIDATION : 'validation:';
VALIDATION : 'validation';
VALIDATION_CODE : 'production' | 'research' | 'testing' | 'expired';
VARIABLE : 'variable';
VARIANCE : 'variance';
VERSION : 'version:' -> mode(TextMode);
VERSION : 'version' -> mode(TextMode);
WEEK : 'week' 's'?;
WEEKDAYLITERAL:
WEEKDAYLITERAL :
'sunday'
| 'monday'
| 'tuesday'
| 'wednesday'
| 'thursday'
| 'friday'
| 'saturday'
;
WHERE : 'where';
WHILE : 'while';
WITH : 'with';
WITHIN : 'within';
WRITE : 'write';
YEAR : 'year' 's'?;

// Seperators
LPAREN : '(';
RPAREN : ')';
LBRACE : '{' -> mode(DataMapping);
RBRACE : '}';
LBRACK : '[';
RBRACK : ']';
SC : ';';
DSC : ';;';
COLON : ':';
DOT : '.';
COMMA : ',';
;
WHERE : 'where';
WHILE : 'while';
WITH : 'with';
WITHIN : 'within';
WRITE : 'write';
YEAR : 'year' 's'?;

// Separators
LPAREN : '(';
RPAREN : ')';
LBRACE : '{' -> mode(DataMapping);
RBRACE : '}';
LBRACK : '[';
RBRACK : ']';
SC : ';';
DSC : ';;';
COLON : ':';
DOT : '.';
COMMA : ',';

// Operators
ASSIGN : ':=';
PLUS : '+';
MINUS : '-';
MUL : '*';
DIV : '/';
POWER : '**';
EQ : '=' | 'eq';
LT : '<' | 'lt';
GT : '>' | 'gt';
LE : '<=' | 'le';
GE : '>=' | 'ge';
NE : '<>' | 'ne';
DOR : '||';
ASSIGN : ':=';
PLUS : '+';
MINUS : '-';
MUL : '*';
DIV : '/';
POWER : '**';
EQ : '=' | 'eq';
LT : '<' | 'lt';
GT : '>' | 'gt';
LE : '<=' | 'le';
GE : '>=' | 'ge';
NE : '<>' | 'ne';
DOR : '||';

// Digit constructs
NUMBER: Digit+ DOT? Digit* Exponent | DOT Digit+ Exponent;
NUMBER : Digit+ (DOT Digit*)? Exponent? | DOT Digit+ Exponent?;

// Date constructs
TIMEOFDAY: Digit Digit COLON Digit Digit Seconds TimeZone;
TIME_OF_DAY : Digit Digit COLON Digit Digit Seconds? TimeZone?;

ISO_DATE: Digit Digit Digit Digit MINUS Digit Digit MINUS Digit Digit;
ISO_DATE : Digit Digit Digit Digit MINUS Digit Digit MINUS Digit Digit;

ISO_DATE_TIME:
Digit Digit Digit Digit MINUS Digit Digit MINUS Digit Digit 't' Digit Digit COLON Digit Digit COLON Digit Digit FractionalDigit TimeZone
;
ISO_DATE_TIME : Digit Digit Digit Digit MINUS Digit Digit MINUS Digit Digit 't' Digit Digit COLON Digit Digit COLON Digit Digit FractionalDigit? TimeZone?;

// String constructs
CITATION: Digit+ DOT ' ' ('support' | 'refute')?;
TERM : '\'' .*? '\'';

TERM: '\'' .*? '\'';

STRING: '"' ( '""' | ~'"')* '"';
STRING : '"' ( '""' | ~'"' )* '"';

// Creates an identifier with max of 80 chars
IDENTIFIER:
StartIdentifier RestIdentifier RestIdentifier RestIdentifier RestIdentifier RestIdentifier RestIdentifier RestIdentifier
;
IDENTIFIER : Letter ID*;

// Comment
COMMENT: '/*' .*? '*/' -> channel(HIDDEN);
COMMENT : '/*' .*? '*/' -> channel(HIDDEN);

LINE_COMMENT: '//' ~[\r\n]* -> channel(HIDDEN);
LINE_COMMENT : '//' ~[\r\n]* -> channel(HIDDEN);

// Whitespace
WS: [ \t\r\n]+ -> channel(HIDDEN);
WS : [ \t\r\n]+ -> channel(HIDDEN);

ERROR : .;

// Fragment rules
// Digit fragments
fragment Digit: [0-9];
fragment Digit : [0-9];

fragment FractionalDigit: (DOT Digit+)?;
fragment FractionalDigit : DOT Digit+;

fragment Exponent: ('e' [+-]? Digit+)?;
fragment Exponent : 'e' [+-]? Digit+;

// Date fragments
fragment Seconds: (COLON Digit Digit FractionalDigit)?;
fragment Seconds : COLON Digit Digit FractionalDigit?;

fragment TimeZone: 'z'? | (PLUS | MINUS) Digit Digit COLON Digit Digit;
fragment TimeZone : 'z' | (PLUS | MINUS) Digit Digit COLON Digit Digit;

// String fragments
fragment Letter: [a-z];
fragment Letter : [a-z];

// Start of the identifier 10 chars, starting with a letter
fragment StartIdentifier: Letter (ID (ID (ID (ID (ID (ID (ID (ID (ID?)?)?)?)?)?)?)?)?)?;

// Rest of the identifier 10 chars
fragment RestIdentifier: (ID (ID (ID (ID (ID (ID (ID (ID (ID (ID?)?)?)?)?)?)?)?)?)?)?;

fragment ID: Letter | [0-9] | '_';

fragment MlmID: ID | DOT | MINUS;
fragment ID : Letter | Digit | '_';

// Lexer modes
mode TextMode;
TEXT: .+? ';;' -> mode(DEFAULT_MODE);
TEXTMODECOLON : ':';
TEXT : .+?;
UTEXT : ~[;:^]+;
ADSC : ';;' -> mode(DEFAULT_MODE);

mode DataMapping;
DATA_MAPPING: (~'}' | '\\' .)+ -> mode(DEFAULT_MODE);
DATA_MAPPING : (~'}' | '\\' .)+ -> mode(DEFAULT_MODE);

mode MlmName;
MLMID:
MlmIDStart MlmIDRest MlmIDRest MlmIDRest MlmIDRest MlmIDRest MlmIDRest MlmIDRest -> mode(DEFAULT_MODE)
;
MlMCOLON : ':';
MLMID : Letter MlmID* -> mode(DEFAULT_MODE);
WS_ID : [ \t\r\n]+ -> channel(HIDDEN);

WS_ID: [ \t\r\n]+ -> channel(HIDDEN);

fragment MlmIDStart:
Letter (MlmID (MlmID (MlmID (MlmID (MlmID (MlmID (MlmID (MlmID (MlmID?)?)?)?)?)?)?)?)?)?
;
fragment MlmIDRest:
(MlmID (MlmID (MlmID (MlmID (MlmID (MlmID (MlmID (MlmID (MlmID (MlmID?)?)?)?)?)?)?)?)?)?)?
;
fragment MlmID : ID | DOT | MINUS;

mode TwoCharMode;
TWOCHARCODE options {
caseInsensitive = false;
}: Letter Letter ('_' [A-Z] [A-Z])? -> mode(DEFAULT_MODE);

WS_TCM: WS -> channel(HIDDEN);
TWOCHARCOLON : ':';
TWOCHARCODE options {caseInsensitive = false; }: Letter Letter ('_' [A-Z] [A-Z])? -> mode(DEFAULT_MODE);
WS_TCM : WS -> channel(HIDDEN);
Loading
Loading