js.c 33.4 KB
Newer Older
1
/*
2 3
 *	 $Id$
 *
4 5 6 7 8 9 10 11 12 13
 *	 Copyright (c) 2003, Darren Hiebert
 *
 *	 This source code is released for free distribution under the terms of the
 *	 GNU General Public License.
 *
 *	 This module contains functions for generating tags for JavaScript language
 *	 files.
 *
 *	 This is a good reference for different forms of the function statement:
 *		 http://www.permadi.com/tutorial/jsFunc/
14 15
 *   Another good reference:
 *       http://developer.mozilla.org/en/docs/Core_JavaScript_1.5_Guide
16 17 18 19 20 21 22 23
 */

/*
 *	 INCLUDE FILES
 */
#include "general.h"	/* must always come first */
#include <ctype.h>	/* to define isalpha () */
#include <setjmp.h>
24
#include <mio/mio.h>
25 26 27 28 29 30 31
#ifdef DEBUG
#include <stdio.h>
#endif

#include "keyword.h"
#include "parse.h"
#include "read.h"
32
#include "main.h"
33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58
#include "vstring.h"

/*
 *	 MACROS
 */
#define isType(token,t)		(boolean) ((token)->type == (t))
#define isKeyword(token,k)	(boolean) ((token)->keyword == (k))

/*
 *	 DATA DECLARATIONS
 */

typedef enum eException { ExceptionNone, ExceptionEOF } exception_t;

/*
 * Tracks class and function names already created
 */
static stringList *ClassNames;
static stringList *FunctionNames;

/*	Used to specify type of keyword.
*/
typedef enum eKeywordId {
	KEYWORD_NONE = -1,
	KEYWORD_function,
	KEYWORD_capital_function,
59 60
	KEYWORD_object,
	KEYWORD_capital_object,
61 62 63 64 65 66 67 68 69
	KEYWORD_prototype,
	KEYWORD_var,
	KEYWORD_new,
	KEYWORD_this,
	KEYWORD_for,
	KEYWORD_while,
	KEYWORD_do,
	KEYWORD_if,
	KEYWORD_else,
70 71 72 73
	KEYWORD_switch,
	KEYWORD_try,
	KEYWORD_catch,
	KEYWORD_finally
74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99
} keywordId;

/*	Used to determine whether keyword is valid for the token language and
 *	what its ID is.
 */
typedef struct sKeywordDesc {
	const char *name;
	keywordId id;
} keywordDesc;

typedef enum eTokenType {
	TOKEN_UNDEFINED,
	TOKEN_CHARACTER,
	TOKEN_CLOSE_PAREN,
	TOKEN_SEMICOLON,
	TOKEN_COLON,
	TOKEN_COMMA,
	TOKEN_KEYWORD,
	TOKEN_OPEN_PAREN,
	TOKEN_OPERATOR,
	TOKEN_IDENTIFIER,
	TOKEN_STRING,
	TOKEN_PERIOD,
	TOKEN_OPEN_CURLY,
	TOKEN_CLOSE_CURLY,
	TOKEN_EQUAL_SIGN,
100 101 102
	TOKEN_FORWARD_SLASH,
	TOKEN_OPEN_SQUARE,
	TOKEN_CLOSE_SQUARE
103 104 105
} tokenType;

typedef struct sTokenInfo {
106 107 108 109 110
	tokenType		type;
	keywordId		keyword;
	vString *		string;
	vString *		scope;
	unsigned long 	lineNumber;
111
	MIOPos			filePosition;
112 113
	int				nestLevel;
	boolean			ignoreTag;
114 115 116 117 118 119 120 121 122 123 124 125 126 127
} tokenInfo;

/*
 *	DATA DEFINITIONS
 */

static langType Lang_js;

static jmp_buf Exception;

typedef enum {
	JSTAG_FUNCTION,
	JSTAG_CLASS,
	JSTAG_METHOD,
128
	JSTAG_PROPERTY,
129 130 131 132 133
	JSTAG_VARIABLE,
	JSTAG_COUNT
} jsKind;

static kindOption JsKinds [] = {
134
	{ TRUE,  'f', "function",	  "functions"		   },
135 136
	{ TRUE,  'c', "class",		  "classes"			   },
	{ TRUE,  'm', "method",		  "methods"			   },
137
	{ TRUE,  'p', "member",		  "properties"		   },
138
	{ TRUE,  'v', "variable",	  "global variables"   }
139 140 141 142 143 144
};

static const keywordDesc JsKeywordTable [] = {
	/* keyword		keyword ID */
	{ "function",	KEYWORD_function			},
	{ "Function",	KEYWORD_capital_function	},
145 146
	{ "object",		KEYWORD_object				},
	{ "Object",		KEYWORD_capital_object		},
147 148 149 150 151 152 153 154 155
	{ "prototype",	KEYWORD_prototype			},
	{ "var",		KEYWORD_var					},
	{ "new",		KEYWORD_new					},
	{ "this",		KEYWORD_this				},
	{ "for",		KEYWORD_for					},
	{ "while",		KEYWORD_while				},
	{ "do",			KEYWORD_do					},
	{ "if",			KEYWORD_if					},
	{ "else",		KEYWORD_else				},
156 157 158 159
	{ "switch",		KEYWORD_switch				},
	{ "try",		KEYWORD_try					},
	{ "catch",		KEYWORD_catch				},
	{ "finally",	KEYWORD_finally				}
160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198
};

/*
 *	 FUNCTION DEFINITIONS
 */

/* Recursive functions */
static void parseFunction (tokenInfo *const token);
static boolean parseBlock (tokenInfo *const token, tokenInfo *const parent);
static boolean parseLine (tokenInfo *const token, boolean is_inside_class);

static boolean isIdentChar (const int c)
{
	return (boolean)
		(isalpha (c) || isdigit (c) || c == '$' ||
		 c == '@' || c == '_' || c == '#');
}

static void buildJsKeywordHash (void)
{
	const size_t count = sizeof (JsKeywordTable) /
		sizeof (JsKeywordTable [0]);
	size_t i;
	for (i = 0	;  i < count  ;  ++i)
	{
		const keywordDesc* const p = &JsKeywordTable [i];
		addKeyword (p->name, Lang_js, (int) p->id);
	}
}

static tokenInfo *newToken (void)
{
	tokenInfo *const token = xMalloc (1, tokenInfo);

	token->type			= TOKEN_UNDEFINED;
	token->keyword		= KEYWORD_NONE;
	token->string		= vStringNew ();
	token->scope		= vStringNew ();
	token->nestLevel	= 0;
199 200
	token->ignoreTag	= FALSE;
	token->lineNumber   = getSourceLineNumber ();
201
	token->filePosition = getInputFilePosition ();
202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218

	return token;
}

static void deleteToken (tokenInfo *const token)
{
	vStringDelete (token->string);
	vStringDelete (token->scope);
	eFree (token);
}

/*
 *	 Tag generation functions
 */

static void makeConstTag (tokenInfo *const token, const jsKind kind)
{
219
	if (JsKinds [kind].enabled && ! token->ignoreTag )
220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237
	{
		const char *const name = vStringValue (token->string);
		tagEntryInfo e;
		initTagEntry (&e, name);

		e.lineNumber   = token->lineNumber;
		e.filePosition = token->filePosition;
		e.kindName	   = JsKinds [kind].name;
		e.kind		   = JsKinds [kind].letter;

		makeTagEntry (&e);
	}
}

static void makeJsTag (tokenInfo *const token, const jsKind kind)
{
	vString *	fulltag;

238
	if (JsKinds [kind].enabled && ! token->ignoreTag )
239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259
	{
		/*
		 * If a scope has been added to the token, change the token
		 * string to include the scope when making the tag.
		 */
		if ( vStringLength(token->scope) > 0 )
		{
			fulltag = vStringNew ();
			vStringCopy(fulltag, token->scope);
			vStringCatS (fulltag, ".");
			vStringCatS (fulltag, vStringValue(token->string));
			vStringTerminate(fulltag);
			vStringCopy(token->string, fulltag);
			vStringDelete (fulltag);
		}
		makeConstTag (token, kind);
	}
}

static void makeClassTag (tokenInfo *const token)
{
260
	if ( ! token->ignoreTag )
261
	{
262 263 264 265 266
		if ( ! stringListHas(ClassNames, vStringValue (token->string)) )
		{
			stringListAdd (ClassNames, vStringNewCopy (token->string));
			makeJsTag (token, JSTAG_CLASS);
		}
267 268 269 270 271
	}
}

static void makeFunctionTag (tokenInfo *const token)
{
272
	if ( ! token->ignoreTag )
273
	{
274 275 276 277 278
		if ( ! stringListHas(FunctionNames, vStringValue (token->string)) )
		{
			stringListAdd (FunctionNames, vStringNewCopy (token->string));
			makeJsTag (token, JSTAG_FUNCTION);
		}
279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300
	}
}

/*
 *	 Parsing functions
 */

static int skipToCharacter (const int c)
{
	int d;
	do
	{
		d = fileGetc ();
	} while (d != EOF  &&  d != c);
	return d;
}

static void parseString (vString *const string, const int delimiter)
{
	boolean end = FALSE;
	while (! end)
	{
301
		int c = fileGetc ();
302 303
		if (c == EOF)
			end = TRUE;
304 305 306 307 308
		else if (c == '\\')
		{
			c = fileGetc(); /* This maybe a ' or ". */
			vStringPut(string, c);
		}
309 310 311 312 313 314 315 316 317 318 319 320 321 322
		else if (c == delimiter)
			end = TRUE;
		else
			vStringPut (string, c);
	}
	vStringTerminate (string);
}

/*	Read a C identifier beginning with "firstChar" and places it into
 *	"name".
 */
static void parseIdentifier (vString *const string, const int firstChar)
{
	int c = firstChar;
323
	Assert (isIdentChar (c));
324 325 326 327 328 329 330 331 332 333 334 335
	do
	{
		vStringPut (string, c);
		c = fileGetc ();
	} while (isIdentChar (c));
	vStringTerminate (string);
	if (!isspace (c))
		fileUngetc (c);		/* unget non-identifier character */
}

static keywordId analyzeToken (vString *const name)
{
336 337
	vString *keyword = vStringNew ();
	keywordId result;
338
	vStringCopyToLower (keyword, name);
339 340 341
	result = (keywordId) lookupKeyword (vStringValue (keyword), Lang_js);
	vStringDelete (keyword);
	return result;
342 343 344 345 346 347 348 349 350 351 352 353 354 355
}

static void readToken (tokenInfo *const token)
{
	int c;

	token->type			= TOKEN_UNDEFINED;
	token->keyword		= KEYWORD_NONE;
	vStringClear (token->string);

getNextChar:
	do
	{
		c = fileGetc ();
356
		token->lineNumber   = getSourceLineNumber ();
357 358
		token->filePosition = getInputFilePosition ();
	}
359 360 361 362 363
	while (c == '\t'  ||  c == ' ' ||  c == '\n');

	switch (c)
	{
		case EOF: longjmp (Exception, (int)ExceptionEOF);	break;
364 365 366 367
		case '(': token->type = TOKEN_OPEN_PAREN;			break;
		case ')': token->type = TOKEN_CLOSE_PAREN;			break;
		case ';': token->type = TOKEN_SEMICOLON;			break;
		case ',': token->type = TOKEN_COMMA;				break;
368
		case '.': token->type = TOKEN_PERIOD;				break;
369 370 371
		case ':': token->type = TOKEN_COLON;				break;
		case '{': token->type = TOKEN_OPEN_CURLY;			break;
		case '}': token->type = TOKEN_CLOSE_CURLY;			break;
372
		case '=': token->type = TOKEN_EQUAL_SIGN;			break;
373 374
		case '[': token->type = TOKEN_OPEN_SQUARE;			break;
		case ']': token->type = TOKEN_CLOSE_SQUARE;			break;
375 376 377 378 379 380

		case '\'':
		case '"':
				  token->type = TOKEN_STRING;
				  parseString (token->string, c);
				  token->lineNumber = getSourceLineNumber ();
381
				  token->filePosition = getInputFilePosition ();
382 383
				  break;

384 385 386 387 388 389
		case '\\':
				  c = fileGetc ();
				  if (c != '\\'  && c != '"'  &&  !isspace (c))
					  fileUngetc (c);
				  token->type = TOKEN_CHARACTER;
				  token->lineNumber = getSourceLineNumber ();
390
				  token->filePosition = getInputFilePosition ();
391 392
				  break;

393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426
		case '/':
				  {
					  int d = fileGetc ();
					  if ( (d != '*') &&		/* is this the start of a comment? */
							  (d != '/') )		/* is a one line comment? */
					  {
						  token->type = TOKEN_FORWARD_SLASH;
						  fileUngetc (d);
					  }
					  else
					  {
						  if (d == '*')
						  {
							  do
							  {
								  skipToCharacter ('*');
								  c = fileGetc ();
								  if (c == '/')
									  break;
								  else
									  fileUngetc (c);
							  } while (c != EOF && c != '\0');
							  goto getNextChar;
						  }
						  else if (d == '/')	/* is this the start of a comment?  */
						  {
							  skipToCharacter ('\n');
							  goto getNextChar;
						  }
					  }
					  break;
				  }

		default:
427
				  if (! isIdentChar (c))
428 429 430 431 432
					  token->type = TOKEN_UNDEFINED;
				  else
				  {
					  parseIdentifier (token->string, c);
					  token->lineNumber = getSourceLineNumber ();
433
					  token->filePosition = getInputFilePosition ();
434 435 436 437 438 439 440 441 442 443 444 445 446 447
					  token->keyword = analyzeToken (token->string);
					  if (isKeyword (token, KEYWORD_NONE))
						  token->type = TOKEN_IDENTIFIER;
					  else
						  token->type = TOKEN_KEYWORD;
				  }
				  break;
	}
}

static void copyToken (tokenInfo *const dest, tokenInfo *const src)
{
	dest->nestLevel = src->nestLevel;
	dest->lineNumber = src->lineNumber;
448
	dest->filePosition = src->filePosition;
449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491
	dest->type = src->type;
	dest->keyword = src->keyword;
	vStringCopy(dest->string, src->string);
	vStringCopy(dest->scope, src->scope);
}

/*
 *	 Token parsing functions
 */

static void skipArgumentList (tokenInfo *const token)
{
	int nest_level = 0;

	/*
	 * Other databases can have arguments with fully declared
	 * datatypes:
	 *	 (	name varchar(30), text binary(10)  )
	 * So we must check for nested open and closing parantheses
	 */

	if (isType (token, TOKEN_OPEN_PAREN))	/* arguments? */
	{
		nest_level++;
		while (! (isType (token, TOKEN_CLOSE_PAREN) && (nest_level == 0)))
		{
			readToken (token);
			if (isType (token, TOKEN_OPEN_PAREN))
			{
				nest_level++;
			}
			if (isType (token, TOKEN_CLOSE_PAREN))
			{
				if (nest_level > 0)
				{
					nest_level--;
				}
			}
		}
		readToken (token);
	}
}

492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523
static void skipArrayList (tokenInfo *const token)
{
	int nest_level = 0;

	/*
	 * Handle square brackets
	 *	 var name[1]
	 * So we must check for nested open and closing square brackets
	 */

	if (isType (token, TOKEN_OPEN_SQUARE))	/* arguments? */
	{
		nest_level++;
		while (! (isType (token, TOKEN_CLOSE_SQUARE) && (nest_level == 0)))
		{
			readToken (token);
			if (isType (token, TOKEN_OPEN_SQUARE))
			{
				nest_level++;
			}
			if (isType (token, TOKEN_CLOSE_SQUARE))
			{
				if (nest_level > 0)
				{
					nest_level--;
				}
			}
		}
		readToken (token);
	}
}

524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561
static void addContext (tokenInfo* const parent, const tokenInfo* const child)
{
	if (vStringLength (parent->string) > 0)
	{
		vStringCatS (parent->string, ".");
	}
	vStringCatS (parent->string, vStringValue(child->string));
	vStringTerminate(parent->string);
}

static void addToScope (tokenInfo* const token, vString* const extra)
{
	if (vStringLength (token->scope) > 0)
	{
		vStringCatS (token->scope, ".");
	}
	vStringCatS (token->scope, vStringValue(extra));
	vStringTerminate(token->scope);
}

/*
 *	 Scanning functions
 */

static void findCmdTerm (tokenInfo *const token)
{
	/*
	 * Read until we find either a semicolon or closing brace.
	 * Any nested braces will be handled within.
	 */
	while (! ( isType (token, TOKEN_SEMICOLON) ||
				isType (token, TOKEN_CLOSE_CURLY) ) )
	{
		/* Handle nested blocks */
		if ( isType (token, TOKEN_OPEN_CURLY))
		{
			parseBlock (token, token);
		}
562 563 564 565
		else if ( isType (token, TOKEN_OPEN_PAREN) )
		{
			skipArgumentList(token);
		}
566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699
		else
		{
			readToken (token);
		}
	}
}

static void parseSwitch (tokenInfo *const token)
{
	/*
	 * switch (expression){
	 * case value1:
	 *	   statement;
	 *	   break;
	 * case value2:
	 *	   statement;
	 *	   break;
	 * default : statement;
	 * }
	 */

	readToken (token);

	if (isType (token, TOKEN_OPEN_PAREN))
	{
		/*
		 * Handle nameless functions, these will only
		 * be considered methods.
		 */
		skipArgumentList(token);
	}

	if (isType (token, TOKEN_OPEN_CURLY))
	{
		/*
		 * This will be either a function or a class.
		 * We can only determine this by checking the body
		 * of the function.  If we find a "this." we know
		 * it is a class, otherwise it is a function.
		 */
		parseBlock (token, token);
	}

}

static void parseLoop (tokenInfo *const token)
{
	/*
	 * Handles these statements
	 *	   for (x=0; x<3; x++)
	 *		   document.write("This text is repeated three times<br>");
	 *
	 *	   for (x=0; x<3; x++)
	 *	   {
	 *		   document.write("This text is repeated three times<br>");
	 *	   }
	 *
	 *	   while (number<5){
	 *		   document.write(number+"<br>");
	 *		   number++;
	 *	   }
	 *
	 *	   do{
	 *		   document.write(number+"<br>");
	 *		   number++;
	 *	   }
	 *	   while (number<5);
	 */

	if (isKeyword (token, KEYWORD_for) || isKeyword (token, KEYWORD_while))
	{
		readToken(token);

		if (isType (token, TOKEN_OPEN_PAREN))
		{
			/*
			 * Handle nameless functions, these will only
			 * be considered methods.
			 */
			skipArgumentList(token);
		}

		if (isType (token, TOKEN_OPEN_CURLY))
		{
			/*
			 * This will be either a function or a class.
			 * We can only determine this by checking the body
			 * of the function.  If we find a "this." we know
			 * it is a class, otherwise it is a function.
			 */
			parseBlock (token, token);
		}
		else
		{
			parseLine(token, FALSE);
		}
	}
	else if (isKeyword (token, KEYWORD_do))
	{
		readToken(token);

		if (isType (token, TOKEN_OPEN_CURLY))
		{
			/*
			 * This will be either a function or a class.
			 * We can only determine this by checking the body
			 * of the function.  If we find a "this." we know
			 * it is a class, otherwise it is a function.
			 */
			parseBlock (token, token);
		}
		else
		{
			parseLine(token, FALSE);
		}

		readToken(token);

		if (isKeyword (token, KEYWORD_while))
		{
			readToken(token);

			if (isType (token, TOKEN_OPEN_PAREN))
			{
				/*
				 * Handle nameless functions, these will only
				 * be considered methods.
				 */
				skipArgumentList(token);
			}
		}
	}
}

700
static boolean parseIf (tokenInfo *const token)
701
{
702
	boolean read_next_token = TRUE;
703 704 705 706 707
	/*
	 * If statements have two forms
	 *	   if ( ... )
	 *		   one line;
	 *
708 709 710 711 712
	 *	   if ( ... )
	 *		  statement;
	 *	   else
	 *		  statement
	 *
713 714 715 716 717
	 *	   if ( ... ) {
	 *		  multiple;
	 *		  statements;
	 *	   }
	 *
718
	 *
719 720 721
	 *	   if ( ... ) {
	 *		  return elem
	 *	   }
722 723 724 725 726 727 728 729 730 731 732
	 *
	 *     This example if correctly written, but the
	 *     else contains only 1 statement without a terminator
	 *     since the function finishes with the closing brace.
	 *
     *     function a(flag){
     *         if(flag)
     *             test(1);
     *         else
     *             test(2)
     *     }
733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766
	 *
	 * TODO:  Deal with statements that can optional end
	 *		  without a semi-colon.  Currently this messes up
	 *		  the parsing of blocks.
	 *		  Need to somehow detect this has happened, and either
	 *		  backup a token, or skip reading the next token if
	 *		  that is possible from all code locations.
	 *
	 */

	readToken (token);

	if (isType (token, TOKEN_OPEN_PAREN))
	{
		/*
		 * Handle nameless functions, these will only
		 * be considered methods.
		 */
		skipArgumentList(token);
	}

	if (isType (token, TOKEN_OPEN_CURLY))
	{
		/*
		 * This will be either a function or a class.
		 * We can only determine this by checking the body
		 * of the function.  If we find a "this." we know
		 * it is a class, otherwise it is a function.
		 */
		parseBlock (token, token);
	}
	else
	{
		findCmdTerm (token);
767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797

		/*
		 * The IF could be followed by an ELSE statement.
		 * This too could have two formats, a curly braced
		 * multiline section, or another single line.
		 */

		if (isType (token, TOKEN_CLOSE_CURLY))
		{
			/*
			 * This statement did not have a line terminator.
			 */
			read_next_token = FALSE;
		}
		else
		{
			readToken (token);

			if (isType (token, TOKEN_CLOSE_CURLY))
			{
				/*
				* This statement did not have a line terminator.
				*/
				read_next_token = FALSE;
			}
			else
			{
				if (isKeyword (token, KEYWORD_else))
					read_next_token = parseIf (token);
			}
		}
798
	}
799
	return read_next_token;
800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873
}

static void parseFunction (tokenInfo *const token)
{
	tokenInfo *const name = newToken ();
	boolean is_class = FALSE;

	/*
	 * This deals with these formats
	 *	   function validFunctionTwo(a,b) {}
	 */

	readToken (name);
	/* Add scope in case this is an INNER function */
	addToScope(name, token->scope);

	readToken (token);
	if (isType (token, TOKEN_PERIOD))
	{
		do
		{
			readToken (token);
			if ( isKeyword(token, KEYWORD_NONE) )
			{
				addContext (name, token);
				readToken (token);
			}
		} while (isType (token, TOKEN_PERIOD));
	}

	if ( isType (token, TOKEN_OPEN_PAREN) )
		skipArgumentList(token);

	if ( isType (token, TOKEN_OPEN_CURLY) )
	{
		is_class = parseBlock (token, name);
		if ( is_class )
			makeClassTag (name);
		else
			makeFunctionTag (name);
	}

	findCmdTerm (token);

	deleteToken (name);
}

static boolean parseBlock (tokenInfo *const token, tokenInfo *const parent)
{
	boolean is_class = FALSE;
	boolean read_next_token = TRUE;
	vString * saveScope = vStringNew ();

	token->nestLevel++;
	/*
	 * Make this routine a bit more forgiving.
	 * If called on an open_curly advance it
	 */
	if ( isType (token, TOKEN_OPEN_CURLY) &&
			isKeyword(token, KEYWORD_NONE) )
		readToken(token);

	if (! isType (token, TOKEN_CLOSE_CURLY))
	{
		/*
		 * Read until we find the closing brace,
		 * any nested braces will be handled within
		 */
		do
		{
			read_next_token = TRUE;
			if (isKeyword (token, KEYWORD_this))
			{
				/*
874
				 * Means we are inside a class and have found
875 876 877 878 879 880
				 * a class, not a function
				 */
				is_class = TRUE;
				vStringCopy(saveScope, token->scope);
				addToScope (token, parent->string);

881 882 883 884
				/*
				 * Ignore the remainder of the line
				 * findCmdTerm(token);
				 */
885
				parseLine (token, is_class);
886

887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948
				vStringCopy(token->scope, saveScope);
			}
			else if (isKeyword (token, KEYWORD_var))
			{
				/*
				 * Potentially we have found an inner function.
				 * Set something to indicate the scope
				 */
				vStringCopy(saveScope, token->scope);
				addToScope (token, parent->string);
				parseLine (token, is_class);
				vStringCopy(token->scope, saveScope);
			}
			else if (isKeyword (token, KEYWORD_function))
			{
				vStringCopy(saveScope, token->scope);
				addToScope (token, parent->string);
				parseFunction (token);
				vStringCopy(token->scope, saveScope);
			}
			else if (isType (token, TOKEN_OPEN_CURLY))
			{
				/* Handle nested blocks */
				parseBlock (token, parent);
			}
			else
			{
				/*
				 * It is possible for a line to have no terminator
				 * if the following line is a closing brace.
				 * parseLine will detect this case and indicate
				 * whether we should read an additional token.
				 */
				read_next_token = parseLine (token, is_class);
			}

			/*
			 * Always read a new token unless we find a statement without
			 * a ending terminator
			 */
			if( read_next_token )
				readToken(token);

			/*
			 * If we find a statement without a terminator consider the
			 * block finished, otherwise the stack will be off by one.
			 */
		} while (! isType (token, TOKEN_CLOSE_CURLY) && read_next_token );
	}

	vStringDelete(saveScope);
	token->nestLevel--;

	return is_class;
}

static void parseMethods (tokenInfo *const token, tokenInfo *const class)
{
	tokenInfo *const name = newToken ();

	/*
	 * This deals with these formats
949 950 951
	 *	   validProperty  : 2,
	 *	   validMethod    : function(a,b) {}
	 *	   'validMethod2' : function(a,b) {}
952 953 954 955 956
	 */

	do
	{
		readToken (token);
957
		if (isType (token, TOKEN_STRING) || isKeyword(token, KEYWORD_NONE))
958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980
		{
			copyToken(name, token);

			readToken (token);
			if ( isType (token, TOKEN_COLON) )
			{
				readToken (token);
				if ( isKeyword (token, KEYWORD_function) )
				{
					readToken (token);
					if ( isType (token, TOKEN_OPEN_PAREN) )
					{
						skipArgumentList(token);
					}

					if (isType (token, TOKEN_OPEN_CURLY))
					{
						addToScope (name, class->string);
						makeJsTag (name, JSTAG_METHOD);
						parseBlock (token, name);

						/*
						 * Read to the closing curly, check next
981
						 * token, if a comma, we must loop again
982 983 984 985
						 */
						readToken (token);
					}
				}
986 987 988 989 990 991 992 993 994 995 996
				else
				{
						addToScope (name, class->string);
						makeJsTag (name, JSTAG_PROPERTY);

						/*
						 * Read the next token, if a comma
						 * we must loop again
						 */
						readToken (token);
				}
997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013
			}
		}
	} while ( isType(token, TOKEN_COMMA) );

	findCmdTerm (token);

	deleteToken (name);
}

static boolean parseStatement (tokenInfo *const token, boolean is_inside_class)
{
	tokenInfo *const name = newToken ();
	tokenInfo *const secondary_name = newToken ();
	vString * saveScope = vStringNew ();
	boolean is_class = FALSE;
	boolean is_terminated = TRUE;
	boolean is_global = FALSE;
1014
	boolean is_prototype = FALSE;
1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035

	vStringClear(saveScope);
	/*
	 * Functions can be named or unnamed.
	 * This deals with these formats:
	 * Function
	 *	   validFunctionOne = function(a,b) {}
	 *	   testlib.validFunctionFive = function(a,b) {}
	 *	   var innerThree = function(a,b) {}
	 *	   var innerFour = (a,b) {}
	 *	   var D2 = secondary_fcn_name(a,b) {}
	 *	   var D3 = new Function("a", "b", "return a+b;");
	 * Class
	 *	   testlib.extras.ValidClassOne = function(a,b) {
	 *		   this.a = a;
	 *	   }
	 * Class Methods
	 *	   testlib.extras.ValidClassOne.prototype = {
	 *		   'validMethodOne' : function(a,b) {},
	 *		   'validMethodTwo' : function(a,b) {}
	 *	   }
1036 1037 1038 1039 1040 1041 1042
     *     ValidClassTwo = function ()
     *     {
     *         this.validMethodThree = function() {}
     *         // unnamed method
     *         this.validMethodFour = () {}
     *     }
	 *	   Database.prototype.validMethodThree = Database_getTodaysDate;
1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061
	 */

	if ( is_inside_class )
		is_class = TRUE;
	/*
	 * var can preceed an inner function
	 */
	if ( isKeyword(token, KEYWORD_var) )
	{
		/*
		 * Only create variables for global scope
		 */
		if ( token->nestLevel == 0 )
		{
			is_global = TRUE;
		}
		readToken(token);
	}

1062 1063 1064 1065 1066 1067 1068 1069 1070
	if ( isKeyword(token, KEYWORD_this) )
	{
		readToken(token);
		if (isType (token, TOKEN_PERIOD))
		{
			readToken(token);
		}
	}

1071 1072
	copyToken(name, token);

1073 1074 1075
	while (! isType (token, TOKEN_CLOSE_CURLY) &&
	       ! isType (token, TOKEN_SEMICOLON)   &&
	       ! isType (token, TOKEN_EQUAL_SIGN)  )
1076
	{
1077 1078 1079
		/* Potentially the name of the function */
		readToken (token);
		if (isType (token, TOKEN_PERIOD))
1080
		{
1081 1082 1083 1084 1085
			/*
			 * Cannot be a global variable is it has dot references in the name
			 */
			is_global = FALSE;
			do
1086
			{
1087 1088
				readToken (token);
				if ( isKeyword(token, KEYWORD_NONE) )
1089
				{
1090 1091 1092 1093 1094 1095 1096
					if ( is_class )
					{
						vStringCopy(saveScope, token->scope);
						addToScope(token, name->string);
					}
					else
						addContext (name, token);
1097
				}
1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231
				else if ( isKeyword(token, KEYWORD_prototype) )
				{
					/*
					 * When we reach the "prototype" tag, we infer:
					 *     "BindAgent" is a class
					 *     "build"     is a method
					 *
					 * function BindAgent( repeatableIdName, newParentIdName ) {
					 * }
					 *
					 * CASE 1
					 * Specified function name: "build"
					 *     BindAgent.prototype.build = function( mode ) {
					 *     	  ignore everything within this function
					 *     }
					 *
					 * CASE 2
					 * Prototype listing
					 *     ValidClassOne.prototype = {
					 *         'validMethodOne' : function(a,b) {},
					 *         'validMethodTwo' : function(a,b) {}
					 *     }
					 *
					 */
					makeClassTag (name);
					is_class = TRUE;
					is_prototype = TRUE;

					/*
					 * There should a ".function_name" next.
					 */
					readToken (token);
					if (isType (token, TOKEN_PERIOD))
					{
						/*
						 * Handle CASE 1
						 */
						readToken (token);
						if ( isKeyword(token, KEYWORD_NONE) )
						{
							vStringCopy(saveScope, token->scope);
							addToScope(token, name->string);

							makeJsTag (token, JSTAG_METHOD);
							/*
							 * We can read until the end of the block / statement.
							 * We need to correctly parse any nested blocks, but
							 * we do NOT want to create any tags based on what is
							 * within the blocks.
							 */
							token->ignoreTag = TRUE;
							/*
							 * Find to the end of the statement
							 */
							findCmdTerm (token);
							token->ignoreTag = FALSE;
							is_terminated = TRUE;
							goto cleanUp;
						}
					}
					else if (isType (token, TOKEN_EQUAL_SIGN))
					{
						readToken (token);
						if (isType (token, TOKEN_OPEN_CURLY))
						{
							/*
							 * Handle CASE 2
							 *
							 * Creates tags for each of these class methods
							 *     ValidClassOne.prototype = {
							 *         'validMethodOne' : function(a,b) {},
							 *         'validMethodTwo' : function(a,b) {}
							 *     }
							 */
							parseMethods(token, name);
							/*
							 * Find to the end of the statement
							 */
							findCmdTerm (token);
							token->ignoreTag = FALSE;
							is_terminated = TRUE;
							goto cleanUp;
						}
					}
				}
				readToken (token);
			} while (isType (token, TOKEN_PERIOD));
		}

		if ( isType (token, TOKEN_OPEN_PAREN) )
			skipArgumentList(token);

		if ( isType (token, TOKEN_OPEN_SQUARE) )
			skipArrayList(token);

		/*
		if ( isType (token, TOKEN_OPEN_CURLY) )
		{
			is_class = parseBlock (token, name);
		}
		*/
	}

	if ( isType (token, TOKEN_CLOSE_CURLY) )
	{
		/*
		 * Reaching this section without having
		 * processed an open curly brace indicates
		 * the statement is most likely not terminated.
		 */
		is_terminated = FALSE;
		goto cleanUp;
	}

	if ( isType (token, TOKEN_SEMICOLON) )
	{
		/*
		 * Only create variables for global scope
		 */
		if ( token->nestLevel == 0 && is_global )
		{
			/*
			 * Handles this syntax:
			 *	   var g_var2;
			 */
			if (isType (token, TOKEN_SEMICOLON))
				makeJsTag (name, JSTAG_VARIABLE);
		}
		/*
		 * Statement has ended.
		 * This deals with calls to functions, like:
		 *     alert(..);
		 */
		goto cleanUp;
1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246
	}

	if ( isType (token, TOKEN_EQUAL_SIGN) )
	{
		readToken (token);

		if ( isKeyword (token, KEYWORD_function) )
		{
			readToken (token);

			if ( isKeyword (token, KEYWORD_NONE) &&
					! isType (token, TOKEN_OPEN_PAREN) )
			{
				/*
				 * Functions of this format:
1247
				 *	   var D2A = function theAdd(a, b)
1248 1249 1250
				 *	   {
				 *		  return a+b;
				 *	   }
1251
				 * Are really two separate defined functions and
1252
				 * can be referenced in two ways:
1253 1254
				 *	   alert( D2A(1,2) );			  // produces 3
				 *	   alert( theAdd(1,2) );		  // also produces 3
1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293
				 * So it must have two tags:
				 *	   D2A
				 *	   theAdd
				 * Save the reference to the name for later use, once
				 * we have established this is a valid function we will
				 * create the secondary reference to it.
				 */
				copyToken(secondary_name, token);
				readToken (token);
			}

			if ( isType (token, TOKEN_OPEN_PAREN) )
				skipArgumentList(token);

			if (isType (token, TOKEN_OPEN_CURLY))
			{
				/*
				 * This will be either a function or a class.
				 * We can only determine this by checking the body
				 * of the function.  If we find a "this." we know
				 * it is a class, otherwise it is a function.
				 */
				if ( is_inside_class )
				{
					makeJsTag (name, JSTAG_METHOD);
					if ( vStringLength(secondary_name->string) > 0 )
						makeFunctionTag (secondary_name);
					parseBlock (token, name);
				}
				else
				{
					is_class = parseBlock (token, name);
					if ( is_class )
						makeClassTag (name);
					else
						makeFunctionTag (name);

					if ( vStringLength(secondary_name->string) > 0 )
						makeFunctionTag (secondary_name);
1294 1295 1296 1297 1298

					/*
					 * Find to the end of the statement
					 */
					goto cleanUp;
1299 1300 1301 1302 1303 1304
				}
			}
		}
		else if (isType (token, TOKEN_OPEN_PAREN))
		{
			/*
1305 1306
			 * Handle nameless functions
			 *     this.method_name = () {}
1307 1308 1309 1310 1311 1312
			 */
			skipArgumentList(token);

			if (isType (token, TOKEN_OPEN_CURLY))
			{
				/*
1313
				 * Nameless functions are only setup as methods.
1314 1315 1316 1317 1318 1319 1320
				 */
				makeJsTag (name, JSTAG_METHOD);
				parseBlock (token, name);
			}
		}
		else if (isType (token, TOKEN_OPEN_CURLY))
		{
1321 1322 1323 1324 1325 1326 1327
			/*
			 * Creates tags for each of these class methods
			 *     ValidClassOne.prototype = {
			 *         'validMethodOne' : function(a,b) {},
			 *         'validMethodTwo' : function(a,b) {}
			 *     }
			 */
1328 1329 1330 1331 1332 1333
			parseMethods(token, name);
		}
		else if (isKeyword (token, KEYWORD_new))
		{
			readToken (token);
			if ( isKeyword (token, KEYWORD_function) ||
1334 1335 1336
					isKeyword (token, KEYWORD_capital_function) ||
					isKeyword (token, KEYWORD_object) ||
					isKeyword (token, KEYWORD_capital_object) )
1337
			{
1338 1339 1340 1341
				if ( isKeyword (token, KEYWORD_object) ||
						isKeyword (token, KEYWORD_capital_object) )
					is_class = TRUE;

1342 1343 1344 1345 1346
				readToken (token);
				if ( isType (token, TOKEN_OPEN_PAREN) )
					skipArgumentList(token);

				if (isType (token, TOKEN_SEMICOLON))
1347 1348 1349 1350 1351 1352 1353 1354
				{
					if ( is_class )
					{
						makeClassTag (name);
					} else {
						makeFunctionTag (name);
					}
				}
1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379
			}
		}
		else if (isKeyword (token, KEYWORD_NONE))
		{
			/*
			 * Only create variables for global scope
			 */
			if ( token->nestLevel == 0 && is_global )
			{
				/*
				 * A pointer can be created to the function.
				 * If we recognize the function/class name ignore the variable.
				 * This format looks identical to a variable definition.
				 * A variable defined outside of a block is considered
				 * a global variable:
				 *	   var g_var1 = 1;
				 *	   var g_var2;
				 * This is not a global variable:
				 *	   var g_var = function;
				 * This is a global variable:
				 *	   var g_var = different_var_name;
				 */
				if ( ! stringListHas(FunctionNames, vStringValue (token->string)) &&
						! stringListHas(ClassNames, vStringValue (token->string)) )
				{
1380
					findCmdTerm (token);
1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437
					if (isType (token, TOKEN_SEMICOLON))
						makeJsTag (name, JSTAG_VARIABLE);
				}
			}
		}
	}
	findCmdTerm (token);

	/*
	 * Statements can be optionally terminated in the case of
	 * statement prior to a close curly brace as in the
	 * document.write line below:
	 *
	 * function checkForUpdate() {
	 *	   if( 1==1 ) {
	 *		   document.write("hello from checkForUpdate<br>")
	 *	   }
	 *	   return 1;
	 * }
	 */
	if (isType (token, TOKEN_CLOSE_CURLY))
		is_terminated = FALSE;


cleanUp:
	vStringCopy(token->scope, saveScope);
	deleteToken (name);
	deleteToken (secondary_name);
	vStringDelete(saveScope);

	return is_terminated;
}

static boolean parseLine (tokenInfo *const token, boolean is_inside_class)
{
	boolean is_terminated = TRUE;
	/*
	 * Detect the common statements, if, while, for, do, ...
	 * This is necessary since the last statement within a block "{}"
	 * can be optionally terminated.
	 *
	 * If the statement is not terminated, we need to tell
	 * the calling routine to prevent reading an additional token
	 * looking for the end of the statement.
	 */

	if (isType(token, TOKEN_KEYWORD))
	{
		switch (token->keyword)
		{
			case KEYWORD_for:
			case KEYWORD_while:
			case KEYWORD_do:
				parseLoop (token);
				break;
			case KEYWORD_if:
			case KEYWORD_else:
1438 1439 1440 1441 1442
			case KEYWORD_try:
			case KEYWORD_catch:
			case KEYWORD_finally:
				/* Common semantics */
				is_terminated = parseIf (token);
1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455
				break;
			case KEYWORD_switch:
				parseSwitch (token);
				break;
			default:
				parseStatement (token, is_inside_class);
				break;
		}
	}
	else
	{
		/*
		 * Special case where single line statements may not be
1456
		 * SEMICOLON terminated.  parseBlock needs to know this
1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494
		 * so that it does not read the next token.
		 */
		is_terminated = parseStatement (token, is_inside_class);
	}
	return is_terminated;
}

static void parseJsFile (tokenInfo *const token)
{
	do
	{
		readToken (token);

		if (isType(token, TOKEN_KEYWORD))
		{
			switch (token->keyword)
			{
				case KEYWORD_function:	parseFunction (token); break;
				default:				parseLine (token, FALSE); break;
			}
		}
		else
		{
			parseLine (token, FALSE);
		}
	} while (TRUE);
}

static void initialize (const langType language)
{
	Assert (sizeof (JsKinds) / sizeof (JsKinds [0]) == JSTAG_COUNT);
	Lang_js = language;
	buildJsKeywordHash ();
}

static void findJsTags (void)
{
	tokenInfo *const token = newToken ();
1495 1496
	exception_t exception;

1497 1498 1499
	ClassNames = stringListNew ();
	FunctionNames = stringListNew ();

1500
	exception = (exception_t) (setjmp (Exception));
1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514
	while (exception == ExceptionNone)
		parseJsFile (token);

	stringListDelete (ClassNames);
	stringListDelete (FunctionNames);
	ClassNames = NULL;
	FunctionNames = NULL;
	deleteToken (token);
}

/* Create parser definition stucture */
extern parserDefinition* JavaScriptParser (void)
{
	static const char *const extensions [] = { "js", NULL };
1515
	parserDefinition *const def = parserNew ("JavaScript");
1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527
	def->extensions = extensions;
	/*
	 * New definitions for parsing instead of regex
	 */
	def->kinds		= JsKinds;
	def->kindCount	= KIND_COUNT (JsKinds);
	def->parser		= findJsTags;
	def->initialize = initialize;

	return def;
}
/* vi:set tabstop=4 shiftwidth=4 noexpandtab: */