Draft Chipmunk grammar tokens for ANTLR.

Lang/build.gradle

@@ -21,11 +21,13 @@
 
 plugins {
 	id 'maven-publish'
-	id 'org.asciidoctor.jvm.convert' version '3.1.0'
+	//id 'org.asciidoctor.jvm.convert' version '3.1.0'
+
 }
 
 apply plugin: 'java'
 apply plugin: 'groovy'
+apply plugin: 'antlr'
 
 group = 'myworld'
 version = rootProject.ext.buildVersion
@@ -41,6 +43,7 @@ configurations {
 dependencies {
 
 	implementation 'org.ow2.asm:asm:9.0'
+	antlr 'org.antlr:antlr4:4.13.2'
 
 	testImplementation 'org.apache.groovy:groovy:4.0.21'
     testImplementation 'org.spockframework:spock-core:2.3-groovy-4.0'
@@ -61,9 +64,12 @@ java {
 
 sourceSets {
 	main {
-	  java {
-		srcDir 'src/main/java'
-	  }
+	  	java {
+			srcDir 'src/main/java'
+	  	}
+		antlr {
+			srcDir 'src/main/antlr'
+		}
 	}
 
 	profiling {
@@ -119,9 +125,9 @@ publishing {
 	}
 }
 
-asciidoctor {
+/*asciidoctor {
 	sourceDir 'src/doc/asciidoc'
-}
+}*/
 
 clean {
 	delete 'build'

Lang/src/main/antlr/ChipmunkLexer.g4

@@ -0,0 +1,91 @@
+lexer grammar ChipmunkLexer;
+
+channels { WS_CHANNEL, NL_CHANNEL }
+
+WS: [ t]+ -> channel(WS_CHANNEL);
+NL: ('rn' | 'r' | 'n') -> channel(NL_CHANNEL);
+
+COMMENT: '#' . NL;
+
+BINARYLITERAL: ('0b' | '0B')[01_]+;
+OCTLITERAL: ('0o' |' 0O' )[0-7_]+;
+HEXLITERAL: ('0x'|'0X')[a-fA-F0-9_]+;
+FLOATLITERAL: [0-9]* '.'? [0-9]+ (('e'|'E')'-'? [0-9]+)?;
+INTLITERAL: [0-9][0-9_]*;
+BOOLLITERAL: 'true' | 'false';
+
+// TODO - probably need to move strings to the parser so we can handle interpolation
+STRINGLITERAL: ('"' ('\\"' | [^"])* '"') | ('\'' ('\\\'' | [^'])* '\'');
+
+LBRACE: '{';
+RBRACE: '}';
+LBRACKET: '[';
+RBRACKET: ']';
+LPAREN: '(';
+RPAREN: ')';
+COMMA: ',';
+
+DOUBLECOLON: '::';
+COLON: ':';
+DOUBLEEQUALS: '==';
+EQUALS: '=';
+DOUBLEDOTLESS: '..<';
+DOUBLEDOT: '..';
+DOT: '.';
+DOUBLESTAR: '**';
+STAR: '*';
+DOUBLEPLUS: '++';
+PLUS: '+';
+DOUBLEMINUS: '--';
+MINUS: '-';
+DOUBLEFSLASH: '//';
+FSLASH: '/';
+DOUBLEBAR: '||';
+BAR: '|';
+EXCLAMATION: '!';
+TILDE: '~';
+CARET: '^';
+DOUBLELESSTHAN: '<<';
+LESSTHAN: '<';
+TRIPLEMORETHAN: '>>>';
+DOUBLEMORETHAN: '>>';
+MORETHAN: '>';
+PERCENT: '%';
+DOUBLEAMPERSAND: '&&';
+AMPERSAND: '&';
+
+MODULE: 'module';
+FROM: 'from';
+IMPORT: 'import';
+AS: 'as';
+IN: 'in';
+CLASS: 'class';
+SHARED: 'shared';
+NULL: 'null';
+IF: 'if';
+ELSE: 'else';
+FOR: 'for';
+WHILE: 'while';
+BREAK: 'break';
+CONTINUE: 'continue';
+RETURN: 'return';
+TRY: 'try';
+CATCH: 'catch';
+FINALLY: 'finally';
+THROW: 'throw';
+DEF: 'def';
+VAR: 'var';
+TRAIT: 'trait';
+FINAL: 'final';
+INSTANCEOF: 'instanceof';
+IS: 'is';
+MATCH: 'match';
+CASE: 'case';
+WHEN: 'when';
+
+// identifiers go second to last so that they don't interfere with matching keywords
+IDENTIFIER: [a-zA-Z_][a-zA-Z0-9_]*;
+
+// Antlr automatically gives us EOF, but we also want a catch-all that we can use to try to keep
+// lexing/parsing past mistakes (for error analysis, tooling, etc.).
+UNRECOGNIZED: .;

Lang/src/main/antlr/ChipmunkParser.g4

@@ -0,0 +1,8 @@
+parser grammar ChipmunkParser;
+
+options {
+    tokenVocab=ChipmunkLexer;
+}
+
+module:
+    EOF;

Lang/src/main/java/module-info.java

@@ -1,6 +1,7 @@
 open module chipmunk.lang {
     requires jdk.dynalink;
     requires org.objectweb.asm;
+    requires org.antlr.antlr4.runtime;
     exports chipmunk;
     exports chipmunk.binary;
     exports chipmunk.compiler;