/* indentation level n. */
void CORD_dump_inner(CORD x, unsigned n)
{
size_t i;
for (i = 0; i < (size_t)n; i++) {
fputs(" ", stdout);
}
if (x == 0) {
fputs("NIL\n", stdout);
} else if (CORD_IS_STRING(x)) {
for (i = 0; i <= SHORT_LIMIT; i++) {
if (x[i] == '\0') break;
putchar(x[i]);
}
if (x[i] != '\0') fputs("...", stdout);
putchar('\n');
} else if (IS_CONCATENATION(x)) {
struct Concatenation * conc = &(((CordRep *)x) -> concatenation);
printf("Concatenation: %p (len: %d, depth: %d)\n",
(void *)x, (int)(conc -> len), (int)(conc -> depth));
CORD_dump_inner(conc -> left, n+1);
CORD_dump_inner(conc -> right, n+1);
} else /* function */ {
struct Function * func = &(((CordRep *)x) -> function);
if (IS_SUBSTR(x)) printf("(Substring) ");
printf("Function: %p (len: %d): ", (void *)x, (int)(func -> len));
for (i = 0; i < 20 && i < func -> len; i++) {
putchar((*(func -> fn))(i, func -> client_data));
}
if (i < func -> len) fputs("...", stdout);
putchar('\n');
}
}
/* See cord.h for definition. We assume i is in range. */
int CORD_iter5(CORD x, size_t i, CORD_iter_fn f1,
CORD_batched_iter_fn f2, void * client_data)
{
if (x == 0) return(0);
if (CORD_IS_STRING(x)) {
register const char *p = x+i;
if (*p == '\0') ABORT("2nd arg to CORD_iter5 too big");
if (f2 != CORD_NO_FN) {
return((*f2)(p, client_data));
} else {
while (*p) {
if ((*f1)(*p, client_data)) return(1);
p++;
}
return(0);
}
} else if (IS_CONCATENATION(x)) {
register struct Concatenation * conc
= &(((CordRep *)x) -> concatenation);
if (i > 0) {
register size_t left_len = LEFT_LEN(conc);
if (i >= left_len) {
return(CORD_iter5(conc -> right, i - left_len, f1, f2,
client_data));
}
}
if (CORD_iter5(conc -> left, i, f1, f2, client_data)) {
return(1);
}
return(CORD_iter5(conc -> right, 0, f1, f2, client_data));
} else /* function */ {
register struct Function * f = &(((CordRep *)x) -> function);
register size_t j;
register size_t lim = f -> len;
for (j = i; j < lim; j++) {
if ((*f1)((*(f -> fn))(j, f -> client_data), client_data)) {
return(1);
}
}
return(0);
}
}
/* of the final tree. */
void CORD_balance_insert(CORD x, size_t len, ForestElement * forest)
{
int depth;
if (CORD_IS_STRING(x)) {
CORD_add_forest(forest, x, len);
} else if (IS_CONCATENATION(x)
&& ((depth = DEPTH(x)) >= MAX_DEPTH
|| len < min_len[depth])) {
struct Concatenation * conc = &(((CordRep *)x) -> concatenation);
size_t left_len = LEFT_LEN(conc);
CORD_balance_insert(conc -> left, left_len, forest);
CORD_balance_insert(conc -> right, len - left_len, forest);
} else /* function or balanced */ {
CORD_add_forest(forest, x, len);
}
}
int CORD_riter4(CORD x, size_t i, CORD_iter_fn f1, void * client_data)
{
if (x == 0) return(0);
if (CORD_IS_STRING(x)) {
register const char *p = x + i;
register char c;
for(;;) {
c = *p;
if (c == '\0') ABORT("2nd arg to CORD_riter4 too big");
if ((*f1)(c, client_data)) return(1);
if (p == x) break;
p--;
}
return(0);
} else if (IS_CONCATENATION(x)) {
register struct Concatenation * conc
= &(((CordRep *)x) -> concatenation);
register CORD left_part = conc -> left;
register size_t left_len;
left_len = LEFT_LEN(conc);
if (i >= left_len) {
if (CORD_riter4(conc -> right, i - left_len, f1, client_data)) {
return(1);
}
return(CORD_riter4(left_part, left_len - 1, f1, client_data));
} else {
return(CORD_riter4(left_part, i, f1, client_data));
}
} else /* function */ {
register struct Function * f = &(((CordRep *)x) -> function);
register size_t j;
for (j = i; ; j--) {
if ((*f1)((*(f -> fn))(j, f -> client_data), client_data)) {
return(1);
}
if (j == 0) return(0);
}
}
}
/* Return 0 if past the end of cord, 1 o.w. */
void CORD__extend_path(register CORD_pos p)
{
register struct CORD_pe * current_pe = &(p[0].path[p[0].path_len]);
register CORD top = current_pe -> pe_cord;
register size_t pos = p[0].cur_pos;
register size_t top_pos = current_pe -> pe_start_pos;
register size_t top_len = GEN_LEN(top);
/* Fill in the rest of the path. */
while(!CORD_IS_STRING(top) && IS_CONCATENATION(top)) {
register struct Concatenation * conc =
&(((CordRep *)top) -> concatenation);
register size_t left_len;
left_len = LEFT_LEN(conc);
current_pe++;
if (pos >= top_pos + left_len) {
current_pe -> pe_cord = top = conc -> right;
current_pe -> pe_start_pos = top_pos = top_pos + left_len;
top_len -= left_len;
} else {
current_pe -> pe_cord = top = conc -> left;
current_pe -> pe_start_pos = top_pos;
top_len = left_len;
}
p[0].path_len++;
}
/* Fill in leaf description for fast access. */
if (CORD_IS_STRING(top)) {
p[0].cur_leaf = top;
p[0].cur_start = top_pos;
p[0].cur_end = top_pos + top_len;
} else {
p[0].cur_end = 0;
}
if (pos >= top_pos + top_len) p[0].path_len = CORD_POS_INVALID;
}
/* A version of CORD_substr that assumes i >= 0, n > 0, and i + n < length(x).*/
CORD CORD_substr_checked(CORD x, size_t i, size_t n)
{
if (CORD_IS_STRING(x)) {
if (n > SUBSTR_LIMIT) {
return(CORD_substr_closure(x, i, n, CORD_index_access_fn));
} else {
char * result = (char *)GC_MALLOC_ATOMIC(n + 1);
if (result == 0) OUT_OF_MEMORY;
strncpy(result, x+i, n);
result[n] = '\0';
return(result);
}
} else if (IS_CONCATENATION(x)) {
struct Concatenation * conc = &(((CordRep *)x) -> concatenation);
size_t left_len = LEFT_LEN(conc);
size_t right_len = conc -> len - left_len;
if (i >= left_len) {
if (n == right_len) return(conc -> right);
return(CORD_substr_checked(conc -> right, i - left_len, n));
} else if (i+n <= left_len) {
if (n == left_len) return(conc -> left);
return(CORD_substr_checked(conc -> left, i, n));
} else {
/* Need at least one character from each side. */
CORD left_part;
CORD right_part;
size_t left_part_len = left_len - i;
if (i == 0) {
left_part = conc -> left;
} else {
left_part = CORD_substr_checked(conc -> left, i, left_part_len);
}
if (i + n == right_len + left_len) {
right_part = conc -> right;
} else {
right_part = CORD_substr_checked(conc -> right, 0,
n - left_part_len);
}
return(CORD_cat(left_part, right_part));
}
} else /* function */ {
if (n > SUBSTR_LIMIT) {
if (IS_SUBSTR(x)) {
/* Avoid nesting substring nodes. */
struct Function * f = &(((CordRep *)x) -> function);
struct substr_args *descr =
(struct substr_args *)(f -> client_data);
return(CORD_substr_closure((CORD)descr->sa_cord,
i + descr->sa_index,
n, f -> fn));
} else {
return(CORD_substr_closure(x, i, n, CORD_apply_access_fn));
}
} else {
char * result;
struct Function * f = &(((CordRep *)x) -> function);
char buf[SUBSTR_LIMIT+1];
char * p = buf;
size_t j;
size_t lim = i + n;
for (j = i; j < lim; j++) {
char c = (*(f -> fn))(j, f -> client_data);
if (c == '\0') {
return(CORD_substr_closure(x, i, n, CORD_apply_access_fn));
}
*p++ = c;
}
result = (char *)GC_MALLOC_ATOMIC(n + 1);
if (result == 0) OUT_OF_MEMORY;
memcpy(result, buf, n);
result[n] = '\0';
return(result);
}
}
}
CORD CORD_cat_char_star(CORD x, const char * y, size_t leny)
{
size_t result_len;
size_t lenx;
int depth;
if (x == CORD_EMPTY) return(y);
if (leny == 0) return(x);
if (CORD_IS_STRING(x)) {
lenx = strlen(x);
result_len = lenx + leny;
if (result_len <= SHORT_LIMIT) {
char * result = (char *)GC_MALLOC_ATOMIC(result_len + 1);
if (result == 0) OUT_OF_MEMORY;
# ifdef LINT2
memcpy(result, x, lenx + 1);
# else
memcpy(result, x, lenx);
/* No need to copy the terminating zero */
/* as result[lenx] is written below. */
# endif
memcpy(result + lenx, y, leny);
result[result_len] = '\0';
return((CORD) result);
} else {
depth = 1;
}
} else {
CORD right;
CORD left;
char * new_right;
lenx = LEN(x);
if (leny <= SHORT_LIMIT/2
&& IS_CONCATENATION(x)
&& CORD_IS_STRING(right = ((CordRep *)x) -> concatenation.right)) {
size_t right_len;
/* Merge y into right part of x. */
if (!CORD_IS_STRING(left = ((CordRep *)x) -> concatenation.left)) {
right_len = lenx - LEN(left);
} else if (((CordRep *)x) -> concatenation.left_len != 0) {
right_len = lenx - ((CordRep *)x) -> concatenation.left_len;
} else {
right_len = strlen(right);
}
result_len = right_len + leny; /* length of new_right */
if (result_len <= SHORT_LIMIT) {
new_right = (char *)GC_MALLOC_ATOMIC(result_len + 1);
if (new_right == 0) OUT_OF_MEMORY;
memcpy(new_right, right, right_len);
memcpy(new_right + right_len, y, leny);
new_right[result_len] = '\0';
y = new_right;
leny = result_len;
x = left;
lenx -= right_len;
/* Now fall through to concatenate the two pieces: */
}
if (CORD_IS_STRING(x)) {
depth = 1;
} else {
depth = DEPTH(x) + 1;
}
} else {
depth = DEPTH(x) + 1;
}
result_len = lenx + leny;
}
{
/* The general case; lenx, result_len is known: */
struct Concatenation * result = GC_NEW(struct Concatenation);
if (NULL == result) OUT_OF_MEMORY;
result->header = CONCAT_HDR;
result->depth = (char)depth;
if (lenx <= MAX_LEFT_LEN)
result->left_len = (unsigned char)lenx;
result->len = (word)result_len;
result->left = x;
GC_PTR_STORE_AND_DIRTY((void *)&result->right, y);
GC_reachable_here(x);
if (depth >= MAX_DEPTH) {
return(CORD_balance((CORD)result));
} else {
return((CORD) result);
}
}
}
CORD CORD_cat_char_star(CORD x, const char * y, size_t leny)
{
register size_t result_len;
register size_t lenx;
register int depth;
if (x == CORD_EMPTY) return(y);
if (leny == 0) return(x);
if (CORD_IS_STRING(x)) {
lenx = strlen(x);
result_len = lenx + leny;
if (result_len <= SHORT_LIMIT) {
register char * result = MK_GC_MALLOC_ATOMIC(result_len+1);
if (result == 0) OUT_OF_MEMORY;
memcpy(result, x, lenx);
memcpy(result + lenx, y, leny);
result[result_len] = '\0';
return((CORD) result);
} else {
depth = 1;
}
} else {
register CORD right;
register CORD left;
register char * new_right;
register size_t right_len;
lenx = LEN(x);
if (leny <= SHORT_LIMIT/2
&& IS_CONCATENATION(x)
&& CORD_IS_STRING(right = ((CordRep *)x) -> concatenation.right)) {
/* Merge y into right part of x. */
if (!CORD_IS_STRING(left = ((CordRep *)x) -> concatenation.left)) {
right_len = lenx - LEN(left);
} else if (((CordRep *)x) -> concatenation.left_len != 0) {
right_len = lenx - ((CordRep *)x) -> concatenation.left_len;
} else {
right_len = strlen(right);
}
result_len = right_len + leny; /* length of new_right */
if (result_len <= SHORT_LIMIT) {
new_right = MK_GC_MALLOC_ATOMIC(result_len + 1);
if (new_right == 0) OUT_OF_MEMORY;
memcpy(new_right, right, right_len);
memcpy(new_right + right_len, y, leny);
new_right[result_len] = '\0';
y = new_right;
leny = result_len;
x = left;
lenx -= right_len;
/* Now fall through to concatenate the two pieces: */
}
if (CORD_IS_STRING(x)) {
depth = 1;
} else {
depth = DEPTH(x) + 1;
}
} else {
depth = DEPTH(x) + 1;
}
result_len = lenx + leny;
}
{
/* The general case; lenx, result_len is known: */
register struct Concatenation * result;
result = MK_GC_NEW(struct Concatenation);
if (result == 0) OUT_OF_MEMORY;
result->header = CONCAT_HDR;
result->depth = depth;
if (lenx <= MAX_LEFT_LEN) result->left_len = lenx;
result->len = result_len;
result->left = x;
result->right = y;
if (depth >= MAX_DEPTH) {
return(CORD_balance((CORD)result));
} else {
return((CORD) result);
}
}
}
