// This file was generated by DAJ from program.cd. header { import edu.neu.ccs.demeter.*; } class programParser extends Parser; options { // DAJ options for Parser defaultErrorHandler=false; } { static char unescapifyChar(String s) { char c = s.charAt(0); if (c == '\\') { switch (s.charAt(1)) { case 'n': c = '\n'; break; case 't': c = '\t'; break; case 'b': c = '\b'; break; case 'r': c = '\r'; break; case 'f': c = '\f'; break; case '\\': c = '\\'; break; case '\'': c = '\''; break; case '\"': c = '\"'; break; default: c = (char) Integer.parseInt(s.substring(1, s.length()), 8); break; } } return c; } static String unescapify(String s) { char str[] = new char[s.length()]; int i = 0, o = 0; while (i < s.length()) { char c = s.charAt(i++); if (c == '\\') { int j = i + 1; while (j < s.length() && Character.digit(s.charAt(j), 8) != -1) { j++; } c = unescapifyChar(s.substring(i-1, j)); i = j; } str[o++] = c; } return String.valueOf(str, 0, o); } } parseS returns [S it] { it = new S(); X1 the_x1 = null; NX1 the_nX1 = null; } : ( "x1" the_x1=parseX1 { it.x1 = the_x1; } )? ( "nx1" the_nX1=parseNX1 { it.nX1 = the_nX1; } )? ; parseH1 returns [H1 it] { it = new H1(); X2 the_x2 = null; NX2 the_nX2 = null; } : ( "x2" the_x2=parseX2 { it.x2 = the_x2; } )? ( "nx2" the_nX2=parseNX2 { it.nX2 = the_nX2; } )? ; parseX1 returns [X1 it] { it = new X1(); H1 the_h1 = null; } : the_h1=parseH1 { it.h1 = the_h1; } ; parseNX1 returns [NX1 it] { it = new NX1(); H1 the_h1 = null; } : the_h1=parseH1 { it.h1 = the_h1; } ; parseH2 returns [H2 it] { it = new H2(); X3 the_x3 = null; NX3 the_nX3 = null; } : ( "x3" the_x3=parseX3 { it.x3 = the_x3; } )? ( "nx3" the_nX3=parseNX3 { it.nX3 = the_nX3; } )? ; parseX2 returns [X2 it] { it = new X2(); H2 the_h2 = null; } : the_h2=parseH2 { it.h2 = the_h2; } ; parseNX2 returns [NX2 it] { it = new NX2(); H2 the_h2 = null; } : the_h2=parseH2 { it.h2 = the_h2; } ; parseX3 returns [X3 it] { it = new X3(); T the_t = null; } : the_t=parseT { it.t = the_t; } ; parseNX3 returns [NX3 it] { it = new NX3(); T the_t = null; } : the_t=parseT { it.t = the_t; } ; parseT returns [T it] { it = new T(); } : "t" ; parseboolean returns [boolean it] : "true" { it = true; } | "false" { it = false; } ; parsechar returns [char it] : t:CHAR_LITERAL { String s = t.getText(); it = unescapifyChar(s.substring(1, s.length()-1)); } ; parsebyte returns [byte it] { int i; } : i=parseint { it = (byte) i; } ; parseshort returns [short it] { int i; } : i=parseint { it = (short) i; } ; parseint returns [int it] : t:NUM_INT { it = Integer.parseInt(t.getText()); } ; parselong returns [long it] : t:NUM_LONG { String s = t.getText(); it = Long.parseLong(s.substring(0,s.length()-1)); } ; parsefloat returns [float it] : t:NUM_FLOAT { String s = t.getText(); it = Float.parseFloat(s.substring(0,s.length()-1)); } ; parsedouble returns [double it] : t:NUM_DOUBLE { String s = t.getText(); if (s.endsWith("D") || s.endsWith("d")) it = Double.parseDouble(s.substring(0,s.length()-1)); else it = Double.parseDouble(s); } ; parseBoolean returns [Boolean it] : "true" { it = Boolean.TRUE; } | "false" { it = Boolean.FALSE; } ; parseCharacter returns [Character it] { char c; } : c=parsechar { it = new Character(c); } ; parseByte returns [Byte it] { byte b; } : b=parsebyte { it = new Byte(b); } ; parseInteger returns [Integer it] { int i; } : i=parseint { it = new Integer(i); } ; parseLong returns [Long it] { long l; } : l=parselong { it = new Long(l); } ; parseFloat returns [Float it] { float f; } : f=parsefloat { it = new Float(f); } ; parseDouble returns [Double it] { double d; } : d=parsedouble { it = new Double(d); } ; parseNumber returns [Number it] : it=parseInteger | it=parseLong | it=parseFloat | it=parseDouble ; parseString returns [String it] : t:STRING_LITERAL { String s = t.getText(); it = unescapify(s.substring(1, s.length()-1)); } ; parseIdent returns [Ident it] : t:IDENT { it = new Ident(t.getText()); } ; class programLexer extends Lexer; options { // Default Lexer Options k=2; testLiterals=false; charVocabulary='\u0003'..'\uFFFF'; codeGenBitsetTestThreshold=20; defaultErrorHandler=false; } tokens { DOT; } IDENT options { testLiterals=true; }: ('a'..'z'|'A'..'Z'|'_'|'$') ('a'..'z'|'A'..'Z'|'_'|'0'..'9'|'$')* ; // Mostly copied from JavaLexer in antlr/examples/java/java/java.g: // Exception: NUM_INT, added a sub-option to first choice to deal with "." // Whitespace -- ignored WS : ( ' ' | '\t' | '\f' // handle newlines | ( options {generateAmbigWarnings=false;} : "\r\n" // Evil DOS | '\r' // Macintosh | '\n' // Unix (the right way) ) { newline(); } )+ { _ttype = Token.SKIP; } ; // Single-line comments SL_COMMENT : "//" (~('\n'|'\r'))* ('\n'|'\r'('\n')?) {$setType(Token.SKIP); newline();} ; // multiple-line comments ML_COMMENT : "/*" ( /* '\r' '\n' can be matched in one alternative or by matching '\r' in one iteration and '\n' in another. I am trying to handle any flavor of newline that comes in, but the language that allows both "\r\n" and "\r" and "\n" to all be valid newline is ambiguous. Consequently, the resulting grammar must be ambiguous. I'm shutting this warning off. */ options { generateAmbigWarnings=false; } : { LA(2)!='/' }? '*' | '\r' '\n' {newline();} | '\r' {newline();} | '\n' {newline();} | ~('*'|'\n'|'\r') )* "*/" {$setType(Token.SKIP);} ; // character literals CHAR_LITERAL : '\'' ( ESC | ~'\'' ) '\'' ; // string literals STRING_LITERAL : '"' (ESC|~('"'|'\\'))* '"' ; // escape sequence -- note that this is protected; it can only be called // from another lexer rule -- it will not ever directly return a token to // the parser // There are various ambiguities hushed in this rule. The optional // '0'...'9' digit matches should be matched here rather than letting // them go back to STRING_LITERAL to be matched. ANTLR does the // right thing by matching immediately; hence, it's ok to shut off // the FOLLOW ambig warnings. protected ESC : '\\' ( 'n' | 'r' | 't' | 'b' | 'f' | '"' | '\'' | '\\' | ('u')+ HEX_DIGIT HEX_DIGIT HEX_DIGIT HEX_DIGIT | '0'..'3' ( options { warnWhenFollowAmbig = false; } : '0'..'7' ( options { warnWhenFollowAmbig = false; } : '0'..'7' )? )? | '4'..'7' ( options { warnWhenFollowAmbig = false; } : '0'..'7' )? ) ; // hexadecimal digit (again, note it's protected!) protected HEX_DIGIT : ('0'..'9'|'A'..'F'|'a'..'f') ; // a dummy rule to force vocabulary to be all characters (except special // ones that ANTLR uses internally (0 to 2) protected VOCAB : '\3'..'\377' ; // a numeric literal NUM_INT options {testLiterals=true;} // needed to match "." as an IDENT {boolean isDecimal=false; Token t=null;} : '.' {_ttype = DOT;} ( ( ('0'..'9')+ (EXPONENT)? (f1:FLOAT_SUFFIX {t=f1;})? { if (t != null && t.getText().toUpperCase().indexOf('F')>=0) { _ttype = NUM_FLOAT; } else { _ttype = NUM_DOUBLE; // assume double } } )? | ('a'..'z'|'A'..'Z'|'_'|'$') ('a'..'z'|'A'..'Z'|'_'|'0'..'9'|'$')* { _ttype=IDENT;} // "." ==> IDENT ) | ( '0' {isDecimal = true;} // special case for just '0' ( ('x'|'X') ( // hex // the 'e'|'E' and float suffix stuff look // like hex digits, hence the (...)+ doesn't // know when to stop: ambig. ANTLR resolves // it correctly by matching immediately. It // is therefor ok to hush warning. options { warnWhenFollowAmbig=false; } : HEX_DIGIT )+ | ('0'..'7')+ // octal )? | ('1'..'9') ('0'..'9')* {isDecimal=true;} // non-zero decimal ) ( ('l'|'L') { _ttype = NUM_LONG; } // only check to see if it's a float if looks like decimal so far | {isDecimal}? ( '.' ('0'..'9')* (EXPONENT)? (f2:FLOAT_SUFFIX {t=f2;})? | EXPONENT (f3:FLOAT_SUFFIX {t=f3;})? | f4:FLOAT_SUFFIX {t=f4;} ) { if (t != null && t.getText().toUpperCase() .indexOf('F') >= 0) { _ttype = NUM_FLOAT; } else { _ttype = NUM_DOUBLE; // assume double } } )? ; // a couple protected methods to assist in matching floating point numbers protected EXPONENT : ('e'|'E') ('+'|'-')? ('0'..'9')+ ; protected FLOAT_SUFFIX : 'f'|'F'|'d'|'D' ;