diff options
Diffstat (limited to 'generic/regguts.h')
| -rw-r--r-- | generic/regguts.h | 84 |
1 files changed, 52 insertions, 32 deletions
diff --git a/generic/regguts.h b/generic/regguts.h index ac625d5..de760b0 100644 --- a/generic/regguts.h +++ b/generic/regguts.h @@ -39,15 +39,6 @@ * Things that regcustom.h might override. */ -/* standard header files (NULL is a reasonable indicator for them) */ -#ifndef NULL -#include <stdio.h> -#include <stdlib.h> -#include <ctype.h> -#include <limits.h> -#include <string.h> -#endif - /* assertions */ #ifndef assert #ifndef REG_DEBUG @@ -75,11 +66,6 @@ #define NOPARMS void /* for empty parm lists */ #endif -/* const */ -#ifndef CONST -#define CONST const /* for old compilers, might be empty */ -#endif - /* function-pointer declarator */ #ifndef FUNCPTR #if __STDC__ >= 1 @@ -101,9 +87,6 @@ #endif /* want size of a char in bits, and max value in bounded quantifiers */ -#ifndef CHAR_BIT -#include <limits.h> -#endif #ifndef _POSIX2_RE_DUP_MAX #define _POSIX2_RE_DUP_MAX 255 /* normally from <limits.h> */ #endif @@ -203,7 +186,14 @@ struct colordesc { union tree *block; /* block of solid color, if any */ }; -/* the color map itself */ +/* + * The color map itself + * + * Much of the data in the colormap struct is only used at compile time. + * However, the bulk of the space usage is in the "tree" structure, so it's + * not clear that there's much point in converting the rest to a more compact + * form when compilation is finished. + */ struct colormap { int magic; #define CMMAGIC 0x876 @@ -259,15 +249,14 @@ struct cvec { struct state; struct arc { - int type; -#define ARCFREE '\0' + int type; /* 0 if free, else an NFA arc type code */ color co; struct state *from; /* where it's from (and contained within) */ struct state *to; /* where it's to */ - struct arc *outchain; /* *from's outs chain or free chain */ + struct arc *outchain; /* link in *from's outs chain or free chain */ #define freechain outchain - struct arc *inchain; /* *to's ins chain */ - struct arc *colorchain; /* color's arc chain */ + struct arc *inchain; /* link in *to's ins chain */ + struct arc *colorchain; /* link in color's arc chain */ struct arc *colorchainRev; /* back-link in color's arc chain */ }; @@ -314,11 +303,22 @@ struct nfa { /* * definitions for compacted NFA + * + * The main space savings in a compacted NFA is from making the arcs as small + * as possible. We store only the transition color and next-state number for + * each arc. The list of out arcs for each state is an array beginning at + * cnfa.states[statenumber], and terminated by a dummy carc struct with + * co == COLORLESS. + * + * The non-dummy carc structs are of two types: plain arcs and LACON arcs. + * Plain arcs just store the transition color number as "co". LACON arcs + * store the lookahead constraint number plus cnfa.ncolors as "co". LACON + * arcs can be distinguished from plain by testing for co >= cnfa.ncolors. */ struct carc { color co; /* COLORLESS is list terminator */ - int to; /* state number */ + int to; /* next-state number */ }; struct cnfa { @@ -330,7 +330,10 @@ struct cnfa { int post; /* teardown state number */ color bos[2]; /* colors, if any, assigned to BOS and BOL */ color eos[2]; /* colors, if any, assigned to EOS and EOL */ + char *stflags; /* vector of per-state flags bytes */ +#define CNFA_NOPROGRESS 01 /* flag bit for a no-progress state */ struct carc **states; /* vector of pointers to outarc lists */ + /* states[n] are pointers into a single malloc'd array of arcs */ struct carc *arcs; /* the area for the lists */ }; #define ZAPCNFA(cnfa) ((cnfa).nstates = 0) @@ -346,11 +349,28 @@ struct cnfa { /* * subexpression tree + * + * "op" is one of: + * '=' plain regex without interesting substructure (implemented as DFA) + * 'b' back-reference (has no substructure either) + * '(' capture node: captures the match of its single child + * '.' concatenation: matches a match for left, then a match for right + * '|' alternation: matches a match for left or a match for right + * '*' iteration: matches some number of matches of its single child + * + * Note: the right child of an alternation must be another alternation or + * NULL; hence, an N-way branch requires N alternation nodes, not N-1 as you + * might expect. This could stand to be changed. Actually I'd rather see + * a single alternation node with N children, but that will take revising + * the representation of struct subre. + * + * Note: when a backref is directly quantified, we stick the min/max counts + * into the backref rather than plastering an iteration node on top. This is + * for efficiency: there is no need to search for possible division points. */ struct subre { - char op; /* '|', '.' (concat), 'b' (backref), '(', - * '=' */ + char op; /* see type codes above */ char flags; #define LONGER 01 /* prefers longer match */ #define SHORTER 02 /* prefers shorter match */ @@ -366,10 +386,10 @@ struct subre { #define PREF(f) ((f)&NOPROP) #define PREF2(f1, f2) ((PREF(f1) != 0) ? PREF(f1) : PREF(f2)) #define COMBINE(f1, f2) (UP((f1)|(f2)) | PREF2(f1, f2)) - short retry; /* index into retry memory */ + short id; /* ID of subre (1..ntree-1) */ int subno; /* subexpression number (for 'b' and '(') */ - short min; /* min repetitions, for backref only */ - short max; /* max repetitions, for backref only */ + short min; /* min repetitions for iteration or backref */ + short max; /* max repetitions for iteration or backref */ struct subre *left; /* left child, if any (also freelist chain) */ struct subre *right; /* right child, if any */ struct state *begin; /* outarcs from here... */ @@ -384,7 +404,7 @@ struct subre { */ struct fns { - VOID FUNCPTR(free, (regex_t *)); + void FUNCPTR(free, (regex_t *)); }; /* @@ -399,9 +419,9 @@ struct guts { size_t nsub; /* copy of re_nsub */ struct subre *tree; struct cnfa search; /* for fast preliminary search */ - int ntree; + int ntree; /* number of subre's, plus one */ struct colormap cmap; - int FUNCPTR(compare, (CONST chr *, CONST chr *, size_t)); + int FUNCPTR(compare, (const chr *, const chr *, size_t)); struct subre *lacons; /* lookahead-constraint vector */ int nlacons; /* size of lacons */ }; |