src/mdParser/MDParser.g

header
{

#include "antlr/CharScanner.hpp"
#include "utils/StringUtils.hpp"
#include "mdParser/FilenameObserver.hpp"
}

options
  {
  language = "Cpp";
  }
                     
class MDParser extends Parser;

options
{
        k = 3;
        exportVocab = MD;
        buildAST = true;
        codeGenMakeSwitchThreshold = 2;
        codeGenBitsetTestThreshold = 3;
        
}

tokens
{
  COMPONENT   = "component";
  MOLECULE    = "molecule";
  ZCONSTRAINT = "zconstraint";
  RESTRAINT   = "restraint";
  ATOM        = "atom";
  BOND        = "bond";
  BEND        = "bend";
  TORSION     = "torsion";
  INVERSION   = "inversion";
  RIGIDBODY   = "rigidBody";
  CUTOFFGROUP = "cutoffGroup";
  FRAGMENT    = "fragment";
  MEMBERS     = "members";
  CENTER      = "center";
  POSITION    = "position";
  ORIENTATION = "orientation";
  FLUCQ       = "flucQ";
  RNEMD       = "RNEMD";
  MINIMIZER   = "minimizer";
  ENDBLOCK;
}


mdfile  : (statement)*
        ;

statement : assignment
    | componentblock
    | moleculeblock
    | zconstraintblock
    | restraintblock
    | flucqblock
    | rnemdblock
    | minimizerblock
    ;

assignment  : ID ASSIGNEQUAL^ constant SEMICOLON!
            ;
            
constant    : intConst
                                                | floatConst
            | ID
            | StringLiteral
            ;

componentblock  : COMPONENT^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
                ;
    
zconstraintblock  : ZCONSTRAINT^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
                  ;

restraintblock  : RESTRAINT^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
                  ;

flucqblock  : FLUCQ^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
    ;

rnemdblock  : RNEMD^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
    ;

minimizerblock  : MINIMIZER^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
    ;
  
moleculeblock : MOLECULE^ LCURLY! (moleculestatement)*  RCURLY {#RCURLY->setType(ENDBLOCK);}
              ;

moleculestatement : assignment
                  | atomblock
                  | bondblock
                  | bendblock
                  | torsionblock
                  | inversionblock
                  | rigidbodyblock
                  | cutoffgroupblock
                  | fragmentblock
                  ;

atomblock : ATOM^ LBRACKET! intConst RBRACKET! LCURLY! (atomstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
          ;

atomstatement : assignment
              | POSITION^ LPAREN! doubleNumberTuple RPAREN! SEMICOLON!
              | ORIENTATION^  LPAREN! doubleNumberTuple RPAREN! SEMICOLON!
              ;

                      
bondblock : BOND^ (LBRACKET! intConst! RBRACKET!)?  LCURLY!(bondstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
          ;

bondstatement : assignment
              | MEMBERS^ LPAREN! inttuple RPAREN! SEMICOLON!
              ;

bendblock : BEND^ (LBRACKET! intConst! RBRACKET!)? LCURLY!  (bendstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
          ;

bendstatement : assignment
              | MEMBERS^ LPAREN! inttuple RPAREN! SEMICOLON!
              ;

torsionblock  : TORSION^ (LBRACKET! intConst! RBRACKET!)?  LCURLY!(torsionstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
          ;

torsionstatement  : assignment
              | MEMBERS^ LPAREN! inttuple RPAREN! SEMICOLON!
              ;

inversionblock  : INVERSION^ (LBRACKET! intConst! RBRACKET!)?  LCURLY!(inversionstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
          ;

inversionstatement  : assignment
              | CENTER^ LPAREN! intConst RPAREN! SEMICOLON!
              ;

rigidbodyblock  : RIGIDBODY^  LBRACKET! intConst RBRACKET! LCURLY!(rigidbodystatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
                ;

rigidbodystatement  : assignment
              | MEMBERS^ LPAREN!  inttuple  RPAREN! SEMICOLON!
              ;

cutoffgroupblock  : CUTOFFGROUP^ (LBRACKET! intConst! RBRACKET!)? LCURLY! (cutoffgroupstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
                  ;

cutoffgroupstatement  : assignment
              | MEMBERS^ LPAREN! inttuple RPAREN! SEMICOLON!
              ;

fragmentblock : FRAGMENT^ LBRACKET! intConst RBRACKET! LCURLY! (fragmentstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
              ;

fragmentstatement : assignment
              ;


doubleNumberTuple   : doubleNumber (COMMA! doubleNumber)* 
              ;
                          
inttuple      : intConst (COMMA! intConst)*
              ;
              
protected
intConst
        :  NUM_INT | NUM_LONG
        ;

protected
doubleNumber  :  
                (intConst | floatConst)
              ;
              
protected
floatConst
        : 
          NUM_FLOAT | NUM_DOUBLE
        ;


class MDLexer extends Lexer;

options
  {
  k = 3;
  exportVocab = MD;
  testLiterals = false;
  }

tokens {
    DOT;
}

{


        int deferredLineCount;
        FilenameObserver* observer;
        
  public:
        void setObserver(FilenameObserver* osv) {observer = osv;}
  void initDeferredLineCount() { deferredLineCount = 0;}
  void deferredNewline() { 
        deferredLineCount++;
  }

        
  virtual void newline() { 
                for (;deferredLineCount>0;deferredLineCount--) {
                        CharScanner::newline();
                }
    CharScanner::newline();
  }
    
}


// Operators:

ASSIGNEQUAL     : '=' ;
COLON           : ':' ;
COMMA           : ',' ;
QUESTIONMARK    : '?' ;
SEMICOLON       : ';' ;

LPAREN          : '(' ;
RPAREN          : ')' ;
LBRACKET        : '[' ;
RBRACKET        : ']' ;
LCURLY          : '{' ;
RCURLY          : '}' ;

Whitespace  
  : 
    ( // whitespace ignored
      (' ' |'\t' | '\f')
    | // handle newlines
      ( '\r' '\n' // MS
      | '\r'    // Mac
      | '\n'    // Unix 
      ) { newline(); }
    | // handle continuation lines
      ( '\\' '\r' '\n'  // MS
      | '\\' '\r'   // Mac
      | '\\' '\n'   // Unix 
      ) {printf("CPP_parser.g continuation line detected\n");
        deferredNewline();}
    ) 
    {_ttype = ANTLR_USE_NAMESPACE(antlr)Token::SKIP;}
  ;

Comment  
  : 
    "/*"   
    ( {LA(2) != '/'}? '*'
    | EndOfLine {deferredNewline();}
    | ~('*'| '\r' | '\n')
    )*
    "*/" {_ttype = ANTLR_USE_NAMESPACE(antlr)Token::SKIP;}
  ;

CPPComment
  : 
    "//" (~('\n' | '\r'))* EndOfLine
    {_ttype = ANTLR_USE_NAMESPACE(antlr)Token::SKIP; newline();}                     
  ;

PREPROC_DIRECTIVE
  options{paraphrase = "a line directive";}
  : 
    '#' LineDirective
    {_ttype = ANTLR_USE_NAMESPACE(antlr)Token::SKIP; newline();} 
  ;

protected 
LineDirective
  :
  {
   deferredLineCount = 0;
  }
    ("line")?  // this would be for if the directive started "#line"
    (Space)+
    n:Decimal { setLine(OpenMD::lexi_cast<int>(n->getText()) - 1); } 
    (Space)+
    (sl:StringLiteral) {std::string filename = sl->getText().substr(1,sl->getText().length()-2); observer->notify(filename);} 
    ((Space)+ Decimal)* // To support cpp flags (GNU)
    EndOfLine
  ;

protected  
Space
  : 
    (' '|'\t'|'\f')
  ;


// Literals:

/*
 * Note that we do NOT handle tri-graphs nor multi-byte sequences.
 */

/*
 * Note that we can't have empty character constants (even though we
 * can have empty strings :-).
 */
CharLiteral
  : 
    '\'' (Escape | ~('\'')) '\''
  ;

/*
 * Can't have raw imbedded newlines in string constants.  Strict reading of
 * the standard gives odd dichotomy between newlines & carriage returns.
 * Go figure.
 */
StringLiteral
  : 
    '"'
    ( Escape
    | 
      ( "\\\r\n"   // MS 
      | "\\\r"     // MAC
      | "\\\n"     // Unix
      ) {deferredNewline();}
    | 
      ~('"'|'\r'|'\n'|'\\')
    )*
    '"'
  ;

protected
EndOfLine
  : 
    ( options{generateAmbigWarnings = false;}:
      "\r\n"  // MS
    | '\r'    // Mac
    | '\n'    // Unix
    )
  ;

/*
 * Handle the various escape sequences.
 *
 * Note carefully that these numeric escape *sequences* are *not* of the
 * same form as the C language numeric *constants*.
 *
 * There is no such thing as a binary numeric escape sequence.
 *
 * Octal escape sequences are either 1, 2, or 3 octal digits exactly.
 *
 * There is no such thing as a decimal escape sequence.
 *
 * Hexadecimal escape sequences are begun with a leading \x and continue
 * until a non-hexadecimal character is found.
 *
 * No real handling of tri-graph sequences, yet.
 */

protected
Escape  
  : 
    '\\'
    ( options{warnWhenFollowAmbig=false;}:
      'a'
    | 'b'
    | 'f'
    | 'n'
    | 'r'
    | 't'
    | 'v'
    | '"'
    | '\''
    | '\\'
    | '?'
    | ('0'..'3') (options{warnWhenFollowAmbig=false;}: Digit (options{warnWhenFollowAmbig=false;}: Digit)? )?
    | ('4'..'7') (options{warnWhenFollowAmbig=false;}: Digit)?
    | 'x' (options{warnWhenFollowAmbig=false;}: Digit | 'a'..'f' | 'A'..'F')+
    )
  ;


protected
Vocabulary
  : 
    '\3'..'\377'
  ;


ID
  options {testLiterals = true;}
  : 
    ('a'..'z'|'A'..'Z'|'_')
    ('a'..'z'|'A'..'Z'|'_'|'0'..'9')*
  ;


protected
Digit
  : 
    '0'..'9'
  ;

protected
Decimal
  : 
    ('0'..'9')+
  ;

// hexadecimal digit (again, note it's protected!)
protected
HEX_DIGIT
        :       ('0'..'9'|'A'..'F'|'a'..'f')
        ;


// a numeric literal
NUM_INT
        {
                bool isDecimal = false;
                ANTLR_USE_NAMESPACE(antlr)RefToken t = ANTLR_USE_NAMESPACE(antlr)nullToken;
        }
    : ('+' | '-')?
    (
      '.' {_ttype = DOT;}
            (   ('0'..'9')+ (EXPONENT)? (f1:FLOAT_SUFFIX {t=f1;})?
            {
                                        if ( t &&
                                                  (t->getText().find('f') != ANTLR_USE_NAMESPACE(std)string::npos ||
                                                        t->getText().find('F') != ANTLR_USE_NAMESPACE(std)string::npos ) ) {
                                                _ttype = NUM_FLOAT;
                                        }
                                        else {
                                                _ttype = NUM_DOUBLE; // assume double
                                        }
                                }
            )?

        |       (       '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
                                )+
                        |       //float or double with leading zero
                                (('0'..'9')+ ('.'|EXPONENT|FLOAT_SUFFIX)) => ('0'..'9')+
                        |       ('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 &&
                                                  (t->getText().find('f') != ANTLR_USE_NAMESPACE(std)string::npos ||
                                                        t->getText().find('F') != ANTLR_USE_NAMESPACE(std)string::npos ) ) {
                                                _ttype = NUM_FLOAT;
                                        }
                                        else {
                                                _ttype = NUM_DOUBLE; // assume double
                                        }
                                }
        )?
  )
        ;

// a couple protected methods to assist in matching floating point numbers
protected
EXPONENT
        :       ('e'|'E'|'d'|'D') ('+'|'-')? ('0'..'9')+
        ;

protected
FLOAT_SUFFIX
        :       'f'|'F'|'d'|'D'
        ;
Revision:	1746
Committed:	Wed Jun 6 02:18:54 2012 UTC (12 years, 11 months ago) by gezelter
File size:	11111 byte(s)
Log Message:	added a minimizer parsing block
#	User	Rev	Content
1	tim	770	header
2			{
3
4			#include "antlr/CharScanner.hpp"
5			#include "utils/StringUtils.hpp"
6			#include "mdParser/FilenameObserver.hpp"
7			}
8
9			options
10			{
11			language = "Cpp";
12			}
13
14			class MDParser extends Parser;
15
16			options
17			{
18			k = 3;
19			exportVocab = MD;
20			buildAST = true;
21			codeGenMakeSwitchThreshold = 2;
22			codeGenBitsetTestThreshold = 3;
23
24			}
25
26			tokens
27			{
28			COMPONENT = "component";
29			MOLECULE = "molecule";
30			ZCONSTRAINT = "zconstraint";
31	cli2	1360	RESTRAINT = "restraint";
32	tim	770	ATOM = "atom";
33			BOND = "bond";
34			BEND = "bend";
35			TORSION = "torsion";
36	cli2	1275	INVERSION = "inversion";
37	tim	770	RIGIDBODY = "rigidBody";
38			CUTOFFGROUP = "cutoffGroup";
39			FRAGMENT = "fragment";
40			MEMBERS = "members";
41	cli2	1275	CENTER = "center";
42	tim	770	POSITION = "position";
43			ORIENTATION = "orientation";
44	gezelter	1731	FLUCQ = "flucQ";
45			RNEMD = "RNEMD";
46	gezelter	1746	MINIMIZER = "minimizer";
47	tim	770	ENDBLOCK;
48			}
49
50
51			mdfile : (statement)*
52			;
53
54			statement : assignment
55	gezelter	1731	\| componentblock
56			\| moleculeblock
57			\| zconstraintblock
58			\| restraintblock
59			\| flucqblock
60			\| rnemdblock
61	gezelter	1746	\| minimizerblock
62	gezelter	1731	;
63
64	tim	770	assignment : ID ASSIGNEQUAL^ constant SEMICOLON!
65			;
66
67	tim	814	constant : intConst
68			\| floatConst
69	tim	770	\| ID
70			\| StringLiteral
71			;
72
73			componentblock : COMPONENT^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
74			;
75
76			zconstraintblock : ZCONSTRAINT^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
77			;
78	cli2	1360
79			restraintblock : RESTRAINT^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
80			;
81	gezelter	1731
82			flucqblock : FLUCQ^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
83			;
84
85			rnemdblock : RNEMD^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
86			;
87	gezelter	1746
88			minimizerblock : MINIMIZER^ LCURLY! (assignment)* RCURLY {#RCURLY->setType(ENDBLOCK);}
89			;
90	tim	770
91			moleculeblock : MOLECULE^ LCURLY! (moleculestatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
92			;
93
94			moleculestatement : assignment
95			\| atomblock
96			\| bondblock
97			\| bendblock
98			\| torsionblock
99	gezelter	1277	\| inversionblock
100	tim	770	\| rigidbodyblock
101			\| cutoffgroupblock
102			\| fragmentblock
103			;
104
105			atomblock : ATOM^ LBRACKET! intConst RBRACKET! LCURLY! (atomstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
106			;
107
108			atomstatement : assignment
109	tim	814	\| POSITION^ LPAREN! doubleNumberTuple RPAREN! SEMICOLON!
110			\| ORIENTATION^ LPAREN! doubleNumberTuple RPAREN! SEMICOLON!
111	tim	770	;
112
113
114			bondblock : BOND^ (LBRACKET! intConst! RBRACKET!)? LCURLY!(bondstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
115			;
116
117			bondstatement : assignment
118			\| MEMBERS^ LPAREN! inttuple RPAREN! SEMICOLON!
119			;
120
121			bendblock : BEND^ (LBRACKET! intConst! RBRACKET!)? LCURLY! (bendstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
122			;
123
124			bendstatement : assignment
125			\| MEMBERS^ LPAREN! inttuple RPAREN! SEMICOLON!
126			;
127
128			torsionblock : TORSION^ (LBRACKET! intConst! RBRACKET!)? LCURLY!(torsionstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
129			;
130
131			torsionstatement : assignment
132			\| MEMBERS^ LPAREN! inttuple RPAREN! SEMICOLON!
133			;
134
135	cli2	1275	inversionblock : INVERSION^ (LBRACKET! intConst! RBRACKET!)? LCURLY!(inversionstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
136			;
137
138			inversionstatement : assignment
139			\| CENTER^ LPAREN! intConst RPAREN! SEMICOLON!
140			;
141
142	tim	770	rigidbodyblock : RIGIDBODY^ LBRACKET! intConst RBRACKET! LCURLY!(rigidbodystatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
143			;
144
145			rigidbodystatement : assignment
146			\| MEMBERS^ LPAREN! inttuple RPAREN! SEMICOLON!
147			;
148
149			cutoffgroupblock : CUTOFFGROUP^ (LBRACKET! intConst! RBRACKET!)? LCURLY! (cutoffgroupstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
150			;
151
152			cutoffgroupstatement : assignment
153			\| MEMBERS^ LPAREN! inttuple RPAREN! SEMICOLON!
154			;
155
156			fragmentblock : FRAGMENT^ LBRACKET! intConst RBRACKET! LCURLY! (fragmentstatement)* RCURLY {#RCURLY->setType(ENDBLOCK);}
157			;
158
159			fragmentstatement : assignment
160			;
161
162
163
164	tim	814	doubleNumberTuple : doubleNumber (COMMA! doubleNumber)*
165	tim	770	;
166
167			inttuple : intConst (COMMA! intConst)*
168			;
169
170			protected
171			intConst
172	tim	814	: NUM_INT \| NUM_LONG
173	tim	770	;
174
175			protected
176	tim	814	doubleNumber :
177	tim	770	(intConst \| floatConst)
178			;
179
180			protected
181			floatConst
182			:
183	tim	814	NUM_FLOAT \| NUM_DOUBLE
184	tim	770	;
185
186
187
188			class MDLexer extends Lexer;
189
190			options
191			{
192			k = 3;
193			exportVocab = MD;
194			testLiterals = false;
195			}
196
197			tokens {
198			DOT;
199			}
200
201			{
202
203
204			int deferredLineCount;
205			FilenameObserver* observer;
206
207			public:
208			void setObserver(FilenameObserver* osv) {observer = osv;}
209			void initDeferredLineCount() { deferredLineCount = 0;}
210			void deferredNewline() {
211			deferredLineCount++;
212			}
213
214
215			virtual void newline() {
216			for (;deferredLineCount>0;deferredLineCount--) {
217			CharScanner::newline();
218			}
219			CharScanner::newline();
220			}
221
222			}
223
224
225			// Operators:
226
227			ASSIGNEQUAL : '=' ;
228			COLON : ':' ;
229			COMMA : ',' ;
230			QUESTIONMARK : '?' ;
231			SEMICOLON : ';' ;
232
233			LPAREN : '(' ;
234			RPAREN : ')' ;
235			LBRACKET : '[' ;
236			RBRACKET : ']' ;
237			LCURLY : '{' ;
238			RCURLY : '}' ;
239
240			Whitespace
241			:
242			( // whitespace ignored
243			(' ' \|'\t' \| '\f')
244			\| // handle newlines
245			( '\r' '\n' // MS
246			\| '\r' // Mac
247			\| '\n' // Unix
248			) { newline(); }
249			\| // handle continuation lines
250			( '\\' '\r' '\n' // MS
251			\| '\\' '\r' // Mac
252			\| '\\' '\n' // Unix
253			) {printf("CPP_parser.g continuation line detected\n");
254			deferredNewline();}
255			)
256			{_ttype = ANTLR_USE_NAMESPACE(antlr)Token::SKIP;}
257			;
258
259			Comment
260			:
261			"/*"
262			( {LA(2) != '/'}? '*'
263			\| EndOfLine {deferredNewline();}
264			\| ~('*'\| '\r' \| '\n')
265			)*
266			"*/" {_ttype = ANTLR_USE_NAMESPACE(antlr)Token::SKIP;}
267			;
268
269			CPPComment
270			:
271			"//" (~('\n' \| '\r'))* EndOfLine
272			{_ttype = ANTLR_USE_NAMESPACE(antlr)Token::SKIP; newline();}
273			;
274
275			PREPROC_DIRECTIVE
276			options{paraphrase = "a line directive";}
277			:
278			'#' LineDirective
279			{_ttype = ANTLR_USE_NAMESPACE(antlr)Token::SKIP; newline();}
280			;
281
282			protected
283			LineDirective
284			:
285			{
286			deferredLineCount = 0;
287			}
288			("line")? // this would be for if the directive started "#line"
289			(Space)+
290	gezelter	1390	n:Decimal { setLine(OpenMD::lexi_cast<int>(n->getText()) - 1); }
291	tim	770	(Space)+
292			(sl:StringLiteral) {std::string filename = sl->getText().substr(1,sl->getText().length()-2); observer->notify(filename);}
293			((Space)+ Decimal)* // To support cpp flags (GNU)
294			EndOfLine
295			;
296
297			protected
298			Space
299			:
300			(' '\|'\t'\|'\f')
301			;
302
303
304			// Literals:
305
306			/*
307			* Note that we do NOT handle tri-graphs nor multi-byte sequences.
308			*/
309
310			/*
311			* Note that we can't have empty character constants (even though we
312			* can have empty strings :-).
313			*/
314			CharLiteral
315			:
316			'\'' (Escape \| ~('\'')) '\''
317			;
318
319			/*
320			* Can't have raw imbedded newlines in string constants. Strict reading of
321			* the standard gives odd dichotomy between newlines & carriage returns.
322			* Go figure.
323			*/
324			StringLiteral
325			:
326			'"'
327			( Escape
328			\|
329			( "\\\r\n" // MS
330			\| "\\\r" // MAC
331			\| "\\\n" // Unix
332			) {deferredNewline();}
333			\|
334			~('"'\|'\r'\|'\n'\|'\\')
335			)*
336			'"'
337			;
338
339			protected
340			EndOfLine
341			:
342			( options{generateAmbigWarnings = false;}:
343			"\r\n" // MS
344			\| '\r' // Mac
345			\| '\n' // Unix
346			)
347			;
348
349			/*
350			* Handle the various escape sequences.
351			*
352			* Note carefully that these numeric escape sequences are not of the
353			* same form as the C language numeric constants.
354			*
355			* There is no such thing as a binary numeric escape sequence.
356			*
357			* Octal escape sequences are either 1, 2, or 3 octal digits exactly.
358			*
359			* There is no such thing as a decimal escape sequence.
360			*
361			* Hexadecimal escape sequences are begun with a leading \x and continue
362			* until a non-hexadecimal character is found.
363			*
364			* No real handling of tri-graph sequences, yet.
365			*/
366
367			protected
368			Escape
369			:
370			'\\'
371			( options{warnWhenFollowAmbig=false;}:
372			'a'
373			\| 'b'
374			\| 'f'
375			\| 'n'
376			\| 'r'
377			\| 't'
378			\| 'v'
379			\| '"'
380			\| '\''
381			\| '\\'
382			\| '?'
383			\| ('0'..'3') (options{warnWhenFollowAmbig=false;}: Digit (options{warnWhenFollowAmbig=false;}: Digit)? )?
384			\| ('4'..'7') (options{warnWhenFollowAmbig=false;}: Digit)?
385			\| 'x' (options{warnWhenFollowAmbig=false;}: Digit \| 'a'..'f' \| 'A'..'F')+
386			)
387			;
388
389
390			protected
391	tim	814	Vocabulary
392			:
393			'\3'..'\377'
394			;
395
396
397			ID
398			options {testLiterals = true;}
399			:
400			('a'..'z'\|'A'..'Z'\|'_')
401			('a'..'z'\|'A'..'Z'\|'_'\|'0'..'9')*
402			;
403
404
405			protected
406	tim	770	Digit
407			:
408			'0'..'9'
409			;
410
411			protected
412			Decimal
413			:
414			('0'..'9')+
415			;
416
417	tim	814	// hexadecimal digit (again, note it's protected!)
418	tim	770	protected
419	tim	814	HEX_DIGIT
420			: ('0'..'9'\|'A'..'F'\|'a'..'f')
421			;
422	tim	770
423
424	tim	814	// a numeric literal
425			NUM_INT
426			{
427			bool isDecimal = false;
428			ANTLR_USE_NAMESPACE(antlr)RefToken t = ANTLR_USE_NAMESPACE(antlr)nullToken;
429			}
430			: ('+' \| '-')?
431			(
432			'.' {_ttype = DOT;}
433			( ('0'..'9')+ (EXPONENT)? (f1:FLOAT_SUFFIX {t=f1;})?
434			{
435			if ( t &&
436			(t->getText().find('f') != ANTLR_USE_NAMESPACE(std)string::npos \|\|
437			t->getText().find('F') != ANTLR_USE_NAMESPACE(std)string::npos ) ) {
438			_ttype = NUM_FLOAT;
439			}
440			else {
441			_ttype = NUM_DOUBLE; // assume double
442			}
443			}
444			)?
445	tim	770
446	tim	814	\| ( '0' {isDecimal = true;} // special case for just '0'
447			( ('x'\|'X')
448			( // hex
449			// the 'e'\|'E' and float suffix stuff look
450			// like hex digits, hence the (...)+ doesn't
451			// know when to stop: ambig. ANTLR resolves
452			// it correctly by matching immediately. It
453			// is therefor ok to hush warning.
454			options {
455			warnWhenFollowAmbig=false;
456			}
457			: HEX_DIGIT
458			)+
459			\| //float or double with leading zero
460			(('0'..'9')+ ('.'\|EXPONENT\|FLOAT_SUFFIX)) => ('0'..'9')+
461			\| ('0'..'7')+ // octal
462			)?
463			\| ('1'..'9') ('0'..'9')* {isDecimal=true;} // non-zero decimal
464			)
465			( ('l'\|'L') { _ttype = NUM_LONG; }
466
467			// only check to see if it's a float if looks like decimal so far
468			\| {isDecimal}?
469			( '.' ('0'..'9')* (EXPONENT)? (f2:FLOAT_SUFFIX {t=f2;})?
470			\| EXPONENT (f3:FLOAT_SUFFIX {t=f3;})?
471			\| f4:FLOAT_SUFFIX {t=f4;}
472			)
473			{
474			if ( t &&
475			(t->getText().find('f') != ANTLR_USE_NAMESPACE(std)string::npos \|\|
476			t->getText().find('F') != ANTLR_USE_NAMESPACE(std)string::npos ) ) {
477			_ttype = NUM_FLOAT;
478			}
479			else {
480			_ttype = NUM_DOUBLE; // assume double
481			}
482			}
483			)?
484			)
485			;
486
487			// a couple protected methods to assist in matching floating point numbers
488	tim	770	protected
489	tim	814	EXPONENT
490	gezelter	848	: ('e'\|'E'\|'d'\|'D') ('+'\|'-')? ('0'..'9')+
491	tim	814	;
492	tim	770
493			protected
494	tim	814	FLOAT_SUFFIX
495			: 'f'\|'F'\|'d'\|'D'
496			;