[p5sagit/p5-mst-13.2.git] / regcomp.h

/* $Header: regcomp.h,v 3.0.1.1 90/08/09 05:06:49 lwall Locked $
 *
 * $Log:	regcomp.h,v $
 * Revision 3.0.1.1  90/08/09  05:06:49  lwall
 * patch19: sped up {m,n} on simple items
 * 
 * Revision 3.0  89/10/18  15:22:39  lwall
 * 3.0 baseline
 * 
 */

/*
 * The "internal use only" fields in regexp.h are present to pass info from
 * compile to execute that permits the execute phase to run lots faster on
 * simple cases.  They are:
 *
 * regstart	str that must begin a match; Nullch if none obvious
 * reganch	is the match anchored (at beginning-of-line only)?
 * regmust	string (pointer into program) that match must include, or NULL
 *  [regmust changed to STR* for bminstr()--law]
 * regmlen	length of regmust string
 *  [regmlen not used currently]
 *
 * Regstart and reganch permit very fast decisions on suitable starting points
 * for a match, cutting down the work a lot.  Regmust permits fast rejection
 * of lines that cannot possibly match.  The regmust tests are costly enough
 * that regcomp() supplies a regmust only if the r.e. contains something
 * potentially expensive (at present, the only such thing detected is * or +
 * at the start of the r.e., which can involve a lot of backup).  Regmlen is
 * supplied because the test in regexec() needs it and regcomp() is computing
 * it anyway.
 * [regmust is now supplied always.  The tests that use regmust have a
 * heuristic that disables the test if it usually matches.]
 *
 * [In fact, we now use regmust in many cases to locate where the search
 * starts in the string, so if regback is >= 0, the regmust search is never
 * wasted effort.  The regback variable says how many characters back from
 * where regmust matched is the earliest possible start of the match.
 * For instance, /[a-z].foo/ has a regmust of 'foo' and a regback of 2.]
 */

/*
 * Structure for regexp "program".  This is essentially a linear encoding
 * of a nondeterministic finite-state machine (aka syntax charts or
 * "railroad normal form" in parsing technology).  Each node is an opcode
 * plus a "next" pointer, possibly plus an operand.  "Next" pointers of
 * all nodes except BRANCH implement concatenation; a "next" pointer with
 * a BRANCH on both ends of it is connecting two alternatives.  (Here we
 * have one of the subtle syntax dependencies:  an individual BRANCH (as
 * opposed to a collection of them) is never concatenated with anything
 * because of operator precedence.)  The operand of some types of node is
 * a literal string; for others, it is a node leading into a sub-FSM.  In
 * particular, the operand of a BRANCH node is the first node of the branch.
 * (NB this is *not* a tree structure:  the tail of the branch connects
 * to the thing following the set of BRANCHes.)  The opcodes are:
 */

/* definition	number	opnd?	meaning */
#define	END	0	/* no	End of program. */
#define	BOL	1	/* no	Match "" at beginning of line. */
#define	EOL	2	/* no	Match "" at end of line. */
#define	ANY	3	/* no	Match any one character. */
#define	ANYOF	4	/* str	Match character in (or not in) this class. */
#define	CURLY	5	/* str	Match this simple thing {n,m} times. */
#define	BRANCH	6	/* node	Match this alternative, or the next... */
#define	BACK	7	/* no	Match "", "next" ptr points backward. */
#define	EXACTLY	8	/* str	Match this string (preceded by length). */
#define	NOTHING	9	/* no	Match empty string. */
#define	STAR	10	/* node	Match this (simple) thing 0 or more times. */
#define	PLUS	11	/* node	Match this (simple) thing 1 or more times. */
#define ALNUM	12	/* no	Match any alphanumeric character */
#define NALNUM	13	/* no	Match any non-alphanumeric character */
#define BOUND	14	/* no	Match "" at any word boundary */
#define NBOUND	15	/* no	Match "" at any word non-boundary */
#define SPACE	16	/* no	Match any whitespace character */
#define NSPACE	17	/* no	Match any non-whitespace character */
#define DIGIT	18	/* no	Match any numeric character */
#define NDIGIT	19	/* no	Match any non-numeric character */
#define REF	20	/* no	Match some already matched string */
#define	OPEN	30	/* no	Mark this point in input as start of #n. */
			/*	OPEN+1 is number 1, etc. */
#define	CLOSE	40	/* no	Analogous to OPEN. */
/* CLOSE must be last one! see regmust finder */

/*
 * Opcode notes:
 *
 * BRANCH	The set of branches constituting a single choice are hooked
 *		together with their "next" pointers, since precedence prevents
 *		anything being concatenated to any individual branch.  The
 *		"next" pointer of the last BRANCH in a choice points to the
 *		thing following the whole choice.  This is also where the
 *		final "next" pointer of each individual branch points; each
 *		branch starts with the operand node of a BRANCH node.
 *
 * BACK		Normal "next" pointers all implicitly point forward; BACK
 *		exists to make loop structures possible.
 *
 * STAR,PLUS	'?', and complex '*' and '+', are implemented as circular
 *		BRANCH structures using BACK.  Simple cases (one character
 *		per match) are implemented with STAR and PLUS for speed
 *		and to minimize recursive plunges.
 *
 * OPEN,CLOSE	...are numbered at compile time.
 */

/* The following have no fixed length. */
#ifndef DOINIT
extern char varies[];
#else
char varies[] = {BRANCH,BACK,STAR,PLUS,CURLY,
	REF+1,REF+2,REF+3,REF+4,REF+5,REF+6,REF+7,REF+8,REF+9,0};
#endif

/* The following always have a length of 1. */
#ifndef DOINIT
extern char simple[];
#else
char simple[] = {ANY,ANYOF,ALNUM,NALNUM,SPACE,NSPACE,DIGIT,NDIGIT,0};
#endif

EXT char regdummy;

/*
 * A node is one char of opcode followed by two chars of "next" pointer.
 * "Next" pointers are stored as two 8-bit pieces, high order first.  The
 * value is a positive offset from the opcode of the node containing it.
 * An operand, if any, simply follows the node.  (Note that much of the
 * code generation knows about this implicit relationship.)
 *
 * Using two bytes for the "next" pointer is vast overkill for most things,
 * but allows patterns to get big without disasters.
 *
 * [If REGALIGN is defined, the "next" pointer is always aligned on an even
 * boundary, and reads the offset directly as a short.  Also, there is no
 * special test to reverse the sign of BACK pointers since the offset is
 * stored negative.]
 */

#ifndef gould
#ifndef cray
#define REGALIGN
#endif
#endif

#define	OP(p)	(*(p))

#ifndef lint
#ifdef REGALIGN
#define NEXT(p) (*(short*)(p+1))
#define ARG1(p) (*(unsigned short*)(p+3))
#define ARG2(p) (*(unsigned short*)(p+5))
#else
#define	NEXT(p)	(((*((p)+1)&0377)<<8) + (*((p)+2)&0377))
#define	ARG1(p)	(((*((p)+3)&0377)<<8) + (*((p)+4)&0377))
#define	ARG2(p)	(((*((p)+5)&0377)<<8) + (*((p)+6)&0377))
#endif
#else /* lint */
#define NEXT(p) 0
#endif /* lint */

#define	OPERAND(p)	((p) + 3)

#ifdef REGALIGN
#define	NEXTOPER(p)	((p) + 4)
#else
#define	NEXTOPER(p)	((p) + 3)
#endif

#define MAGIC 0234

/*
 * Utility definitions.
 */
#ifndef lint
#ifndef CHARBITS
#define	UCHARAT(p)	((int)*(unsigned char *)(p))
#else
#define	UCHARAT(p)	((int)*(p)&CHARBITS)
#endif
#else /* lint */
#define UCHARAT(p)	regdummy
#endif /* lint */

#define	FAIL(m)	fatal("/%s/: %s",regprecomp,m)

char *regnext();
#ifdef DEBUGGING
void regdump();
char *regprop();
#endif
Commit	Line	Data
00bf170e	1	/* $Header: regcomp.h,v 3.0.1.1 90/08/09 05:06:49 lwall Locked $
a687059c	2	*
a687059c	3	* $Log: regcomp.h,v $
00bf170e	4	* Revision 3.0.1.1 90/08/09 05:06:49 lwall
	5	* patch19: sped up {m,n} on simple items
	6	*
a687059c	7	* Revision 3.0 89/10/18 15:22:39 lwall
	8	* 3.0 baseline
	9	*
	10	*/
	11
	12	/*
	13	* The "internal use only" fields in regexp.h are present to pass info from
	14	* compile to execute that permits the execute phase to run lots faster on
	15	* simple cases. They are:
	16	*
	17	* regstart str that must begin a match; Nullch if none obvious
	18	* reganch is the match anchored (at beginning-of-line only)?
	19	* regmust string (pointer into program) that match must include, or NULL
	20	* [regmust changed to STR* for bminstr()--law]
	21	* regmlen length of regmust string
	22	* [regmlen not used currently]
	23	*
	24	* Regstart and reganch permit very fast decisions on suitable starting points
	25	* for a match, cutting down the work a lot. Regmust permits fast rejection
	26	* of lines that cannot possibly match. The regmust tests are costly enough
	27	* that regcomp() supplies a regmust only if the r.e. contains something
	28	* potentially expensive (at present, the only such thing detected is * or +
	29	* at the start of the r.e., which can involve a lot of backup). Regmlen is
	30	* supplied because the test in regexec() needs it and regcomp() is computing
	31	* it anyway.
	32	* [regmust is now supplied always. The tests that use regmust have a
	33	* heuristic that disables the test if it usually matches.]
	34	*
	35	* [In fact, we now use regmust in many cases to locate where the search
	36	* starts in the string, so if regback is >= 0, the regmust search is never
	37	* wasted effort. The regback variable says how many characters back from
	38	* where regmust matched is the earliest possible start of the match.
	39	* For instance, /[a-z].foo/ has a regmust of 'foo' and a regback of 2.]
	40	*/
	41
	42	/*
	43	* Structure for regexp "program". This is essentially a linear encoding
	44	* of a nondeterministic finite-state machine (aka syntax charts or
	45	* "railroad normal form" in parsing technology). Each node is an opcode
	46	* plus a "next" pointer, possibly plus an operand. "Next" pointers of
	47	* all nodes except BRANCH implement concatenation; a "next" pointer with
	48	* a BRANCH on both ends of it is connecting two alternatives. (Here we
	49	* have one of the subtle syntax dependencies: an individual BRANCH (as
	50	* opposed to a collection of them) is never concatenated with anything
	51	* because of operator precedence.) The operand of some types of node is
	52	* a literal string; for others, it is a node leading into a sub-FSM. In
	53	* particular, the operand of a BRANCH node is the first node of the branch.
	54	* (NB this is not a tree structure: the tail of the branch connects
	55	* to the thing following the set of BRANCHes.) The opcodes are:
	56	*/
	57
	58	/* definition number opnd? meaning */
	59	#define END 0 /* no End of program. */
	60	#define BOL 1 /* no Match "" at beginning of line. */
	61	#define EOL 2 /* no Match "" at end of line. */
	62	#define ANY 3 /* no Match any one character. */
00bf170e	63	#define ANYOF 4 /* str Match character in (or not in) this class. */
00bf170e	64	#define CURLY 5 /* str Match this simple thing {n,m} times. */
a687059c	65	#define BRANCH 6 /* node Match this alternative, or the next... */
	66	#define BACK 7 /* no Match "", "next" ptr points backward. */
	67	#define EXACTLY 8 /* str Match this string (preceded by length). */
	68	#define NOTHING 9 /* no Match empty string. */
	69	#define STAR 10 /* node Match this (simple) thing 0 or more times. */
	70	#define PLUS 11 /* node Match this (simple) thing 1 or more times. */
	71	#define ALNUM 12 /* no Match any alphanumeric character */
	72	#define NALNUM 13 /* no Match any non-alphanumeric character */
	73	#define BOUND 14 /* no Match "" at any word boundary */
	74	#define NBOUND 15 /* no Match "" at any word non-boundary */
	75	#define SPACE 16 /* no Match any whitespace character */
	76	#define NSPACE 17 /* no Match any non-whitespace character */
	77	#define DIGIT 18 /* no Match any numeric character */
	78	#define NDIGIT 19 /* no Match any non-numeric character */
	79	#define REF 20 /* no Match some already matched string */
	80	#define OPEN 30 /* no Mark this point in input as start of #n. */
	81	/* OPEN+1 is number 1, etc. */
	82	#define CLOSE 40 /* no Analogous to OPEN. */
	83	/* CLOSE must be last one! see regmust finder */
	84
	85	/*
	86	* Opcode notes:
	87	*
	88	* BRANCH The set of branches constituting a single choice are hooked
	89	* together with their "next" pointers, since precedence prevents
	90	* anything being concatenated to any individual branch. The
	91	* "next" pointer of the last BRANCH in a choice points to the
	92	* thing following the whole choice. This is also where the
	93	* final "next" pointer of each individual branch points; each
	94	* branch starts with the operand node of a BRANCH node.
	95	*
	96	* BACK Normal "next" pointers all implicitly point forward; BACK
	97	* exists to make loop structures possible.
	98	*
	99	* STAR,PLUS '?', and complex '*' and '+', are implemented as circular
	100	* BRANCH structures using BACK. Simple cases (one character
	101	* per match) are implemented with STAR and PLUS for speed
	102	* and to minimize recursive plunges.
	103	*
	104	* OPEN,CLOSE ...are numbered at compile time.
	105	*/
	106
	107	/* The following have no fixed length. */
	108	#ifndef DOINIT
	109	extern char varies[];
	110	#else
00bf170e	111	char varies[] = {BRANCH,BACK,STAR,PLUS,CURLY,
a687059c	112	REF+1,REF+2,REF+3,REF+4,REF+5,REF+6,REF+7,REF+8,REF+9,0};
	113	#endif
	114
	115	/* The following always have a length of 1. */
	116	#ifndef DOINIT
	117	extern char simple[];
	118	#else
00bf170e	119	char simple[] = {ANY,ANYOF,ALNUM,NALNUM,SPACE,NSPACE,DIGIT,NDIGIT,0};
a687059c	120	#endif
	121
	122	EXT char regdummy;
	123
	124	/*
	125	* A node is one char of opcode followed by two chars of "next" pointer.
	126	* "Next" pointers are stored as two 8-bit pieces, high order first. The
	127	* value is a positive offset from the opcode of the node containing it.
	128	* An operand, if any, simply follows the node. (Note that much of the
	129	* code generation knows about this implicit relationship.)
	130	*
	131	* Using two bytes for the "next" pointer is vast overkill for most things,
	132	* but allows patterns to get big without disasters.
	133	*
	134	* [If REGALIGN is defined, the "next" pointer is always aligned on an even
	135	* boundary, and reads the offset directly as a short. Also, there is no
	136	* special test to reverse the sign of BACK pointers since the offset is
	137	* stored negative.]
	138	*/
	139
	140	#ifndef gould
	141	#ifndef cray
	142	#define REGALIGN
	143	#endif
	144	#endif
	145
	146	#define OP(p) (*(p))
	147
	148	#ifndef lint
	149	#ifdef REGALIGN
	150	#define NEXT(p) ((short)(p+1))
00bf170e	151	#define ARG1(p) ((unsigned short)(p+3))
00bf170e	152	#define ARG2(p) ((unsigned short)(p+5))
a687059c	153	#else
a687059c	154	#define NEXT(p) (((((p)+1)&0377)<<8) + (((p)+2)&0377))
00bf170e	155	#define ARG1(p) (((((p)+3)&0377)<<8) + (((p)+4)&0377))
00bf170e	156	#define ARG2(p) (((((p)+5)&0377)<<8) + (((p)+6)&0377))
a687059c	157	#endif
	158	#else /* lint */
	159	#define NEXT(p) 0
	160	#endif /* lint */
	161
	162	#define OPERAND(p) ((p) + 3)
	163
	164	#ifdef REGALIGN
	165	#define NEXTOPER(p) ((p) + 4)
	166	#else
	167	#define NEXTOPER(p) ((p) + 3)
	168	#endif
	169
	170	#define MAGIC 0234
	171
	172	/*
	173	* Utility definitions.
	174	*/
	175	#ifndef lint
	176	#ifndef CHARBITS
	177	#define UCHARAT(p) ((int)(unsigned char )(p))
	178	#else
	179	#define UCHARAT(p) ((int)*(p)&CHARBITS)
	180	#endif
	181	#else /* lint */
	182	#define UCHARAT(p) regdummy
	183	#endif /* lint */
	184
	185	#define FAIL(m) fatal("/%s/: %s",regprecomp,m)
	186
	187	char *regnext();
	188	#ifdef DEBUGGING
	189	void regdump();
	190	char *regprop();
	191	#endif
	192