minix/usr.bin/mdocml/dist/chars.c

244 lines
4.8 KiB
C
Raw Normal View History

/* $Vendor-Id: chars.c,v 1.31 2011/01/02 10:10:57 kristaps Exp $ */
2010-06-26 04:20:06 +02:00
/*
* Copyright (c) 2009, 2010 Kristaps Dzonsons <kristaps@bsd.lv>
2010-06-26 04:20:06 +02:00
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include <assert.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "mandoc.h"
#include "chars.h"
#define PRINT_HI 126
#define PRINT_LO 32
struct ln {
struct ln *next;
const char *code;
const char *ascii;
int unicode;
2010-06-26 04:20:06 +02:00
int type;
#define CHARS_CHAR (1 << 0)
#define CHARS_STRING (1 << 1)
#define CHARS_BOTH (CHARS_CHAR | CHARS_STRING)
};
#define LINES_MAX 351
2010-06-26 04:20:06 +02:00
#define CHAR(in, ch, code) \
{ NULL, (in), (ch), (code), CHARS_CHAR },
#define STRING(in, ch, code) \
{ NULL, (in), (ch), (code), CHARS_STRING },
#define BOTH(in, ch, code) \
{ NULL, (in), (ch), (code), CHARS_BOTH },
2010-06-26 04:20:06 +02:00
#define CHAR_TBL_START static struct ln lines[LINES_MAX] = {
#define CHAR_TBL_END };
#include "chars.in"
struct ctab {
2010-06-26 04:20:06 +02:00
enum chars type;
struct ln **htab;
};
static inline int match(const struct ln *,
const char *, size_t, int);
static const struct ln *find(struct ctab *, const char *, size_t, int);
2010-06-26 04:20:06 +02:00
void
chars_free(void *arg)
{
struct ctab *tab;
2010-06-26 04:20:06 +02:00
tab = (struct ctab *)arg;
2010-06-26 04:20:06 +02:00
free(tab->htab);
free(tab);
}
void *
chars_init(enum chars type)
{
struct ctab *tab;
2010-06-26 04:20:06 +02:00
struct ln **htab;
struct ln *pp;
int i, hash;
/*
* Constructs a very basic chaining hashtable. The hash routine
* is simply the integral value of the first character.
* Subsequent entries are chained in the order they're processed
* (they're in-line re-ordered during lookup).
*/
tab = malloc(sizeof(struct ctab));
2010-06-26 04:20:06 +02:00
if (NULL == tab) {
perror(NULL);
exit((int)MANDOCLEVEL_SYSERR);
2010-06-26 04:20:06 +02:00
}
htab = calloc(PRINT_HI - PRINT_LO + 1, sizeof(struct ln **));
if (NULL == htab) {
perror(NULL);
exit((int)MANDOCLEVEL_SYSERR);
2010-06-26 04:20:06 +02:00
}
for (i = 0; i < LINES_MAX; i++) {
hash = (int)lines[i].code[0] - PRINT_LO;
if (NULL == (pp = htab[hash])) {
htab[hash] = &lines[i];
continue;
}
for ( ; pp->next; pp = pp->next)
/* Scan ahead. */ ;
pp->next = &lines[i];
}
tab->htab = htab;
tab->type = type;
return(tab);
}
/*
* Special character to Unicode codepoint.
*/
int
chars_spec2cp(void *arg, const char *p, size_t sz)
{
const struct ln *ln;
ln = find((struct ctab *)arg, p, sz, CHARS_CHAR);
if (NULL == ln)
return(-1);
return(ln->unicode);
}
/*
* Reserved word to Unicode codepoint.
*/
int
chars_res2cp(void *arg, const char *p, size_t sz)
{
const struct ln *ln;
ln = find((struct ctab *)arg, p, sz, CHARS_STRING);
if (NULL == ln)
return(-1);
return(ln->unicode);
}
/*
* Special character to string array.
*/
2010-06-26 04:20:06 +02:00
const char *
chars_spec2str(void *arg, const char *p, size_t sz, size_t *rsz)
2010-06-26 04:20:06 +02:00
{
const struct ln *ln;
ln = find((struct ctab *)arg, p, sz, CHARS_CHAR);
if (NULL == ln)
return(NULL);
2010-06-26 04:20:06 +02:00
*rsz = strlen(ln->ascii);
return(ln->ascii);
2010-06-26 04:20:06 +02:00
}
/*
* Reserved word to string array.
*/
2010-06-26 04:20:06 +02:00
const char *
chars_res2str(void *arg, const char *p, size_t sz, size_t *rsz)
2010-06-26 04:20:06 +02:00
{
const struct ln *ln;
ln = find((struct ctab *)arg, p, sz, CHARS_STRING);
if (NULL == ln)
return(NULL);
2010-06-26 04:20:06 +02:00
*rsz = strlen(ln->ascii);
return(ln->ascii);
2010-06-26 04:20:06 +02:00
}
static const struct ln *
find(struct ctab *tab, const char *p, size_t sz, int type)
2010-06-26 04:20:06 +02:00
{
struct ln *pp, *prev;
struct ln **htab;
int hash;
assert(p);
if (0 == sz)
return(NULL);
2010-06-26 04:20:06 +02:00
if (p[0] < PRINT_LO || p[0] > PRINT_HI)
return(NULL);
/*
* Lookup the symbol in the symbol hash. See ascii2htab for the
* hashtable specs. This dynamically re-orders the hash chain
* to optimise for repeat hits.
*/
hash = (int)p[0] - PRINT_LO;
htab = tab->htab;
if (NULL == (pp = htab[hash]))
return(NULL);
for (prev = NULL; pp; pp = pp->next) {
if ( ! match(pp, p, sz, type)) {
prev = pp;
continue;
}
if (prev) {
prev->next = pp->next;
pp->next = htab[hash];
htab[hash] = pp;
}
return(pp);
2010-06-26 04:20:06 +02:00
}
return(NULL);
}
static inline int
match(const struct ln *ln, const char *p, size_t sz, int type)
{
if ( ! (ln->type & type))
return(0);
if (strncmp(ln->code, p, sz))
2010-06-26 04:20:06 +02:00
return(0);
return('\0' == ln->code[(int)sz]);
2010-06-26 04:20:06 +02:00
}