cordxtra.c

Boost provides free peer-reviewed portable C++ source libraries. We emphasize libraries that work

{
    register chr_data * d = (chr_data *)client_data;
    register char * occ = strchr(s, d -> target);
    
    if (occ == 0) {
      	d -> pos += strlen(s);
      	return(0);
    } else {
    	d -> pos += occ - s;
    	return(1);
    }
}

size_t CORD_chr(CORD x, size_t i, int c)
{
    chr_data d;
    
    d.pos = i;
    d.target = c;
    if (CORD_iter5(x, i, CORD_chr_proc, CORD_batched_chr_proc, &d)) {
        return(d.pos);
    } else {
    	return(CORD_NOT_FOUND);
    }
}

size_t CORD_rchr(CORD x, size_t i, int c)
{
    chr_data d;
    
    d.pos = i;
    d.target = c;
    if (CORD_riter4(x, i, CORD_rchr_proc, &d)) {
        return(d.pos);
    } else {
    	return(CORD_NOT_FOUND);
    }
}

/* Find the first occurrence of s in x at position start or later.	*/
/* This uses an asymptotically poor algorithm, which should typically 	*/
/* perform acceptably.  We compare the first few characters directly,	*/
/* and call CORD_ncmp whenever there is a partial match.		*/
/* This has the advantage that we allocate very little, or not at all.	*/
/* It's very fast if there are few close misses.			*/
size_t CORD_str(CORD x, size_t start, CORD s)
{
    CORD_pos xpos;
    size_t xlen = CORD_len(x);
    size_t slen;
    register size_t start_len;
    const char * s_start;
    unsigned long s_buf = 0;	/* The first few characters of s	*/
    unsigned long x_buf = 0;	/* Start of candidate substring.	*/
    				/* Initialized only to make compilers	*/
    				/* happy.				*/
    unsigned long mask = 0;
    register size_t i;
    register size_t match_pos;
    
    if (s == CORD_EMPTY) return(start);
    if (CORD_IS_STRING(s)) {
        s_start = s;
        slen = strlen(s);
    } else {
        s_start = CORD_to_char_star(CORD_substr(s, 0, sizeof(unsigned long)));
        slen = CORD_len(s);
    }
    if (xlen < start || xlen - start < slen) return(CORD_NOT_FOUND);
    start_len = slen;
    if (start_len > sizeof(unsigned long)) start_len = sizeof(unsigned long);
    CORD_set_pos(xpos, x, start);
    for (i = 0; i < start_len; i++) {
        mask <<= 8;
        mask |= 0xff;
        s_buf <<= 8;
        s_buf |= (unsigned char)s_start[i];
        x_buf <<= 8;
        x_buf |= (unsigned char)CORD_pos_fetch(xpos);
        CORD_next(xpos);
    }
    for (match_pos = start; ; match_pos++) {
    	if ((x_buf & mask) == s_buf) {
    	    if (slen == start_len ||
    	     	CORD_ncmp(x, match_pos + start_len,
    	     	 	  s, start_len, slen - start_len) == 0) {
    	        return(match_pos);
    	    }
    	}
	if ( match_pos == xlen - slen ) {
	    return(CORD_NOT_FOUND);
	}
    	x_buf <<= 8;
        x_buf |= (unsigned char)CORD_pos_fetch(xpos);
        CORD_next(xpos);
    }
}

void CORD_ec_flush_buf(CORD_ec x)
{
    register size_t len = x[0].ec_bufptr - x[0].ec_buf;
    char * s;

    if (len == 0) return;
    s = GC_MALLOC_ATOMIC(len+1);
    memcpy(s, x[0].ec_buf, len);
    s[len] = '\0';
    x[0].ec_cord = CORD_cat_char_star(x[0].ec_cord, s, len);
    x[0].ec_bufptr = x[0].ec_buf;
}

void CORD_ec_append_cord(CORD_ec x, CORD s)
{
    CORD_ec_flush_buf(x);
    x[0].ec_cord = CORD_cat(x[0].ec_cord, s);
}

/*ARGSUSED*/
char CORD_nul_func(size_t i, void * client_data)
{
    return((char)(unsigned long)client_data);
}


CORD CORD_chars(char c, size_t i)
{
    return(CORD_from_fn(CORD_nul_func, (void *)(unsigned long)c, i));
}

CORD CORD_from_file_eager(FILE * f)
{
    register int c;
    CORD_ec ecord;
    
    CORD_ec_init(ecord);
    for(;;) {
        c = getc(f);
        if (c == 0) {
          /* Append the right number of NULs	*/
          /* Note that any string of NULs is rpresented in 4 words,	*/
          /* independent of its length.					*/
            register size_t count = 1;
            
            CORD_ec_flush_buf(ecord);
            while ((c = getc(f)) == 0) count++;
            ecord[0].ec_cord = CORD_cat(ecord[0].ec_cord, CORD_nul(count));
        }
        if (c == EOF) break;
        CORD_ec_append(ecord, c);
    }
    (void) fclose(f);
    return(CORD_balance(CORD_ec_to_cord(ecord)));
}

/* The state maintained for a lazily read file consists primarily	*/
/* of a large direct-mapped cache of previously read values.		*/
/* We could rely more on stdio buffering.  That would have 2		*/
/* disadvantages:							*/
/*  	1) Empirically, not all fseek implementations preserve the	*/
/*	   buffer whenever they could.					*/
/*	2) It would fail if 2 different sections of a long cord		*/
/*	   were being read alternately.					*/
/* We do use the stdio buffer for read ahead.				*/
/* To guarantee thread safety in the presence of atomic pointer		*/
/* writes, cache lines are always replaced, and never modified in	*/
/* place.								*/

# define LOG_CACHE_SZ 14
# define CACHE_SZ (1 << LOG_CACHE_SZ)
# define LOG_LINE_SZ 9
# define LINE_SZ (1 << LOG_LINE_SZ)

typedef struct {
    size_t tag;
    char data[LINE_SZ];
    	/* data[i%LINE_SZ] = ith char in file if tag = i/LINE_SZ	*/
} cache_line;

typedef struct {
    FILE * lf_file;
    size_t lf_current;	/* Current file pointer value */
    cache_line * volatile lf_cache[CACHE_SZ/LINE_SZ];
} lf_state;

# define MOD_CACHE_SZ(n) ((n) & (CACHE_SZ - 1))
# define DIV_CACHE_SZ(n) ((n) >> LOG_CACHE_SZ)
# define MOD_LINE_SZ(n) ((n) & (LINE_SZ - 1))
# define DIV_LINE_SZ(n) ((n) >> LOG_LINE_SZ)
# define LINE_START(n) ((n) & ~(LINE_SZ - 1))

typedef struct {
    lf_state * state;
    size_t file_pos;	/* Position of needed character. */
    cache_line * new_cache;
} refill_data;

/* Executed with allocation lock. */
static char refill_cache(client_data)
refill_data * client_data;
{
    register lf_state * state = client_data -> state;
    register size_t file_pos = client_data -> file_pos;
    FILE *f = state -> lf_file;
    size_t line_start = LINE_START(file_pos);
    size_t line_no = DIV_LINE_SZ(MOD_CACHE_SZ(file_pos));
    cache_line * new_cache = client_data -> new_cache;
    
    if (line_start != state -> lf_current
        && fseek(f, line_start, SEEK_SET) != 0) {
    	    ABORT("fseek failed");
    }
    if (fread(new_cache -> data, sizeof(char), LINE_SZ, f)
    	<= file_pos - line_start) {
    	ABORT("fread failed");
    }
    new_cache -> tag = DIV_LINE_SZ(file_pos);
    /* Store barrier goes here. */
    ATOMIC_WRITE(state -> lf_cache[line_no], new_cache);
    state -> lf_current = line_start + LINE_SZ;
    return(new_cache->data[MOD_LINE_SZ(file_pos)]);
}

char CORD_lf_func(size_t i, void * client_data)
{
    register lf_state * state = (lf_state *)client_data;
    register cache_line * volatile * cl_addr =
		&(state -> lf_cache[DIV_LINE_SZ(MOD_CACHE_SZ(i))]);
    register cache_line * cl = (cache_line *)ATOMIC_READ(cl_addr);
    
    if (cl == 0 || cl -> tag != DIV_LINE_SZ(i)) {
    	/* Cache miss */
    	refill_data rd;
    	
        rd.state = state;
        rd.file_pos =  i;
        rd.new_cache = GC_NEW_ATOMIC(cache_line);
        if (rd.new_cache == 0) OUT_OF_MEMORY;
        return((char)(GC_word)
        	  GC_call_with_alloc_lock((GC_fn_type) refill_cache, &rd));
    }
    return(cl -> data[MOD_LINE_SZ(i)]);
}    

/*ARGSUSED*/
void CORD_lf_close_proc(void * obj, void * client_data)  
{
    if (fclose(((lf_state *)obj) -> lf_file) != 0) {
    	ABORT("CORD_lf_close_proc: fclose failed");
    }
}			

CORD CORD_from_file_lazy_inner(FILE * f, size_t len)
{
    register lf_state * state = GC_NEW(lf_state);
    register int i;
    
    if (state == 0) OUT_OF_MEMORY;
    if (len != 0) {
	/* Dummy read to force buffer allocation.  	*/
	/* This greatly increases the probability	*/
	/* of avoiding deadlock if buffer allocation	*/
	/* is redirected to GC_malloc and the		*/
	/* world is multithreaded.			*/
	char buf[1];

	(void) fread(buf, 1, 1, f); 
	rewind(f);
    }
    state -> lf_file = f;
    for (i = 0; i < CACHE_SZ/LINE_SZ; i++) {
        state -> lf_cache[i] = 0;
    }
    state -> lf_current = 0;
    GC_REGISTER_FINALIZER(state, CORD_lf_close_proc, 0, 0, 0);
    return(CORD_from_fn(CORD_lf_func, state, len));
}

CORD CORD_from_file_lazy(FILE * f)
{
    register long len;
    
    if (fseek(f, 0l, SEEK_END) != 0) {
        ABORT("Bad fd argument - fseek failed");
    }
    if ((len = ftell(f)) < 0) {
        ABORT("Bad fd argument - ftell failed");
    }
    rewind(f);
    return(CORD_from_file_lazy_inner(f, (size_t)len));
}

# define LAZY_THRESHOLD (128*1024 + 1)

CORD CORD_from_file(FILE * f)
{
    register long len;
    
    if (fseek(f, 0l, SEEK_END) != 0) {
        ABORT("Bad fd argument - fseek failed");
    }
    if ((len = ftell(f)) < 0) {
        ABORT("Bad fd argument - ftell failed");
    }
    rewind(f);
    if (len < LAZY_THRESHOLD) {
        return(CORD_from_file_eager(f));
    } else {
        return(CORD_from_file_lazy_inner(f, (size_t)len));
    }
}