CORD CORD_cat(CORD x, CORD y)
{
size_t result_len;
int depth;
size_t lenx;
if (x == CORD_EMPTY) return(y);
if (y == CORD_EMPTY) return(x);
if (CORD_IS_STRING(y)) {
return(CORD_cat_char_star(x, y, strlen(y)));
} else if (CORD_IS_STRING(x)) {
lenx = strlen(x);
depth = DEPTH(y) + 1;
} else {
int depthy = DEPTH(y);
lenx = LEN(x);
depth = DEPTH(x) + 1;
if (depthy >= depth) depth = depthy + 1;
}
result_len = lenx + LEN(y);
{
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(CORD x, CORD y)
{
register size_t result_len;
register int depth;
register size_t lenx;
if (x == CORD_EMPTY) return(y);
if (y == CORD_EMPTY) return(x);
if (CORD_IS_STRING(y)) {
return(CORD_cat_char_star(x, y, strlen(y)));
} else if (CORD_IS_STRING(x)) {
lenx = strlen(x);
depth = DEPTH(y) + 1;
} else {
register int depthy = DEPTH(y);
lenx = LEN(x);
depth = DEPTH(x) + 1;
if (depthy >= depth) depth = depthy + 1;
}
result_len = lenx + LEN(y);
{
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);
}
}
}
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)));
}
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);
}
}
}
void test_basics(void)
{
CORD x = CORD_from_char_star("ab");
register int i;
char c;
CORD y;
CORD_pos p;
x = CORD_cat(x,x);
if (x == CORD_EMPTY) ABORT("CORD_cat(x,x) returned empty cord");
if (!CORD_IS_STRING(x)) ABORT("short cord should usually be a string");
if (strcmp(x, "abab") != 0) ABORT("bad CORD_cat result");
for (i = 1; i < 16; i++) {
x = CORD_cat(x,x);
}
x = CORD_cat(x,"c");
if (CORD_len(x) != 128*1024+1) ABORT("bad length");
count = 0;
if (CORD_iter5(x, 64*1024-1, test_fn, CORD_NO_FN, (void *)13) == 0) {
ABORT("CORD_iter5 failed");
}
if (count != 64*1024 + 2) ABORT("CORD_iter5 failed");
count = 0;
CORD_set_pos(p, x, 64*1024-1);
while(CORD_pos_valid(p)) {
(void) test_fn(CORD_pos_fetch(p), (void *)13);
CORD_next(p);
}
if (count != 64*1024 + 2) ABORT("Position based iteration failed");
y = CORD_substr(x, 1023, 5);
if (!y) ABORT("CORD_substr returned NULL");
if (!CORD_IS_STRING(y)) ABORT("short cord should usually be a string");
if (strcmp(y, "babab") != 0) ABORT("bad CORD_substr result");
y = CORD_substr(x, 1024, 8);
if (!y) ABORT("CORD_substr returned NULL");
if (!CORD_IS_STRING(y)) ABORT("short cord should usually be a string");
if (strcmp(y, "abababab") != 0) ABORT("bad CORD_substr result");
y = CORD_substr(x, 128*1024-1, 8);
if (!y) ABORT("CORD_substr returned NULL");
if (!CORD_IS_STRING(y)) ABORT("short cord should usually be a string");
if (strcmp(y, "bc") != 0) ABORT("bad CORD_substr result");
x = CORD_balance(x);
if (CORD_len(x) != 128*1024+1) ABORT("bad length");
count = 0;
if (CORD_iter5(x, 64*1024-1, test_fn, CORD_NO_FN, (void *)13) == 0) {
ABORT("CORD_iter5 failed");
}
if (count != 64*1024 + 2) ABORT("CORD_iter5 failed");
y = CORD_substr(x, 1023, 5);
if (!y) ABORT("CORD_substr returned NULL");
if (!CORD_IS_STRING(y)) ABORT("short cord should usually be a string");
if (strcmp(y, "babab") != 0) ABORT("bad CORD_substr result");
y = CORD_from_fn(id_cord_fn, 0, 13);
i = 0;
CORD_set_pos(p, y, i);
while(CORD_pos_valid(p)) {
c = CORD_pos_fetch(p);
if(c != i) ABORT("Traversal of function node failed");
CORD_next(p); i++;
}
if (i != 13) ABORT("Bad apparent length for function node");
}
void test_extras(void)
{
# define FNAME1 "cordtst1.tmp" /* short name (8+3) for portability */
# define FNAME2 "cordtst2.tmp"
register int i;
CORD y = "abcdefghijklmnopqrstuvwxyz0123456789";
CORD x = "{}";
CORD w, z;
FILE *f;
FILE *f1a, *f1b, *f2;
w = CORD_cat(CORD_cat(y,y),y);
z = CORD_catn(3,y,y,y);
if (CORD_cmp(w,z) != 0) ABORT("CORD_catn comparison wrong");
for (i = 1; i < 100; i++) {
x = CORD_cat(x, y);
}
z = CORD_balance(x);
if (CORD_cmp(x,z) != 0) ABORT("balanced string comparison wrong");
if (CORD_cmp(x,CORD_cat(z, CORD_nul(13))) >= 0) ABORT("comparison 2");
if (CORD_cmp(CORD_cat(x, CORD_nul(13)), z) <= 0) ABORT("comparison 3");
if (CORD_cmp(x,CORD_cat(z, "13")) >= 0) ABORT("comparison 4");
if ((f = fopen(FNAME1, "w")) == 0) ABORT("open failed");
if (CORD_put(z,f) == EOF) ABORT("CORD_put failed");
if (fclose(f) == EOF) ABORT("fclose failed");
f1a = fopen(FNAME1, "rb");
if (!f1a) ABORT("Unable to open " FNAME1);
w = CORD_from_file(f1a);
if (CORD_len(w) != CORD_len(z)) ABORT("file length wrong");
if (CORD_cmp(w,z) != 0) ABORT("file comparison wrong");
if (CORD_cmp(CORD_substr(w, 50*36+2, 36), y) != 0)
ABORT("file substr wrong");
f1b = fopen(FNAME1, "rb");
if (!f1b) ABORT("2nd open failed: " FNAME1);
z = CORD_from_file_lazy(f1b);
if (CORD_cmp(w,z) != 0) ABORT("File conversions differ");
if (CORD_chr(w, 0, '9') != 37) ABORT("CORD_chr failed 1");
if (CORD_chr(w, 3, 'a') != 38) ABORT("CORD_chr failed 2");
if (CORD_rchr(w, CORD_len(w) - 1, '}') != 1) ABORT("CORD_rchr failed");
x = y;
for (i = 1; i < 14; i++) {
x = CORD_cat(x,x);
}
if ((f = fopen(FNAME2, "w")) == 0) ABORT("2nd open failed");
# ifdef __DJGPP__
/* FIXME: DJGPP workaround. Why does this help? */
if (fflush(f) != 0) ABORT("fflush failed");
# endif
if (CORD_put(x,f) == EOF) ABORT("CORD_put failed");
if (fclose(f) == EOF) ABORT("fclose failed");
f2 = fopen(FNAME2, "rb");
if (!f2) ABORT("Unable to open " FNAME2);
w = CORD_from_file(f2);
if (CORD_len(w) != CORD_len(x)) ABORT("file length wrong");
if (CORD_cmp(w,x) != 0) ABORT("file comparison wrong");
if (CORD_cmp(CORD_substr(w, 1000*36, 36), y) != 0)
ABORT("file substr wrong");
if (strcmp(CORD_to_char_star(CORD_substr(w, 1000*36, 36)), y) != 0)
ABORT("char * file substr wrong");
if (strcmp(CORD_substr(w, 1000*36, 2), "ab") != 0)
ABORT("short file substr wrong");
if (CORD_str(x,1,"9a") != 35) ABORT("CORD_str failed 1");
if (CORD_str(x,0,"9abcdefghijk") != 35) ABORT("CORD_str failed 2");
if (CORD_str(x,0,"9abcdefghijx") != CORD_NOT_FOUND)
ABORT("CORD_str failed 3");
if (CORD_str(x,0,"9>") != CORD_NOT_FOUND) ABORT("CORD_str failed 4");
if (remove(FNAME1) != 0) {
/* On some systems, e.g. OS2, this may fail if f1 is still open. */
if ((fclose(f1a) == EOF) & (fclose(f1b) == EOF))
ABORT("fclose(f1) failed");
if (remove(FNAME1) != 0) ABORT("remove 1 failed");
}
if (remove(FNAME2) != 0) {
if (fclose(f2) == EOF) ABORT("fclose(f2) failed");
if (remove(FNAME2) != 0) ABORT("remove 2 failed");
}
}
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);
}
}
}
void test_extras()
{
# if defined(__OS2__)
# define FNAME1 "tmp1"
# define FNAME2 "tmp2"
# elif defined(AMIGA)
# define FNAME1 "T:tmp1"
# define FNAME2 "T:tmp2"
# else
# define FNAME1 "/tmp/cord_test"
# define FNAME2 "/tmp/cord_test2"
# endif
register int i;
CORD y = "abcdefghijklmnopqrstuvwxyz0123456789";
CORD x = "{}";
CORD w, z;
FILE *f;
FILE *f1a, *f1b, *f2;
w = CORD_cat(CORD_cat(y,y),y);
z = CORD_catn(3,y,y,y);
if (CORD_cmp(w,z) != 0) ABORT("CORD_catn comparison wrong");
for (i = 1; i < 100; i++) {
x = CORD_cat(x, y);
}
z = CORD_balance(x);
if (CORD_cmp(x,z) != 0) ABORT("balanced string comparison wrong");
if (CORD_cmp(x,CORD_cat(z, CORD_nul(13))) >= 0) ABORT("comparison 2");
if (CORD_cmp(CORD_cat(x, CORD_nul(13)), z) <= 0) ABORT("comparison 3");
if (CORD_cmp(x,CORD_cat(z, "13")) >= 0) ABORT("comparison 4");
if ((f = fopen(FNAME1, "w")) == 0) ABORT("open failed");
if (CORD_put(z,f) == EOF) ABORT("CORD_put failed");
if (fclose(f) == EOF) ABORT("fclose failed");
w = CORD_from_file(f1a = fopen(FNAME1, "rb"));
if (CORD_len(w) != CORD_len(z)) ABORT("file length wrong");
if (CORD_cmp(w,z) != 0) ABORT("file comparison wrong");
if (CORD_cmp(CORD_substr(w, 50*36+2, 36), y) != 0)
ABORT("file substr wrong");
z = CORD_from_file_lazy(f1b = fopen(FNAME1, "rb"));
if (CORD_cmp(w,z) != 0) ABORT("File conversions differ");
if (CORD_chr(w, 0, '9') != 37) ABORT("CORD_chr failed 1");
if (CORD_chr(w, 3, 'a') != 38) ABORT("CORD_chr failed 2");
if (CORD_rchr(w, CORD_len(w) - 1, '}') != 1) ABORT("CORD_rchr failed");
x = y;
for (i = 1; i < 14; i++) {
x = CORD_cat(x,x);
}
if ((f = fopen(FNAME2, "w")) == 0) ABORT("2nd open failed");
if (CORD_put(x,f) == EOF) ABORT("CORD_put failed");
if (fclose(f) == EOF) ABORT("fclose failed");
w = CORD_from_file(f2 = fopen(FNAME2, "rb"));
if (CORD_len(w) != CORD_len(x)) ABORT("file length wrong");
if (CORD_cmp(w,x) != 0) ABORT("file comparison wrong");
if (CORD_cmp(CORD_substr(w, 1000*36, 36), y) != 0)
ABORT("file substr wrong");
if (strcmp(CORD_to_char_star(CORD_substr(w, 1000*36, 36)), y) != 0)
ABORT("char * file substr wrong");
if (strcmp(CORD_substr(w, 1000*36, 2), "ab") != 0)
ABORT("short file substr wrong");
if (CORD_str(x,1,"9a") != 35) ABORT("CORD_str failed 1");
if (CORD_str(x,0,"9abcdefghijk") != 35) ABORT("CORD_str failed 2");
if (CORD_str(x,0,"9abcdefghijx") != CORD_NOT_FOUND)
ABORT("CORD_str failed 3");
if (CORD_str(x,0,"9>") != CORD_NOT_FOUND) ABORT("CORD_str failed 4");
if (remove(FNAME1) != 0) {
/* On some systems, e.g. OS2, this may fail if f1 is still open. */
if ((fclose(f1a) == EOF) & (fclose(f1b) == EOF))
ABORT("fclose(f1) failed");
if (remove(FNAME1) != 0) ABORT("remove 1 failed");
}
if (remove(FNAME2) != 0) {
if (fclose(f2) == EOF) ABORT("fclose(f2) failed");
if (remove(FNAME2) != 0) ABORT("remove 2 failed");
}
}
void test_extras(void)
{
# define FNAME1 "cordtst1.tmp" /* short name (8+3) for portability */
# define FNAME2 "cordtst2.tmp"
register int i;
CORD y = "abcdefghijklmnopqrstuvwxyz0123456789";
CORD x = "{}";
CORD w, z;
FILE *f;
FILE *f1a, *f1b, *f2;
w = CORD_cat(CORD_cat(y,y),y);
z = CORD_catn(3,y,y,y);
if (CORD_cmp(w,z) != 0) ABORT("CORD_catn comparison wrong");
for (i = 1; i < 100; i++) {
x = CORD_cat(x, y);
}
z = CORD_balance(x);
if (CORD_cmp(x,z) != 0) ABORT("balanced string comparison wrong");
if (CORD_cmp(x,CORD_cat(z, CORD_nul(13))) >= 0) ABORT("comparison 2");
if (CORD_cmp(CORD_cat(x, CORD_nul(13)), z) <= 0) ABORT("comparison 3");
if (CORD_cmp(x,CORD_cat(z, "13")) >= 0) ABORT("comparison 4");
if ((f = fopen(FNAME1, "w")) == 0) ABORT("open failed");
if (CORD_put(z,f) == EOF) ABORT("CORD_put failed");
if (fclose(f) == EOF) ABORT("fclose failed");
f1a = fopen(FNAME1, "rb");
if (!f1a) ABORT("Unable to open " FNAME1);
w = CORD_from_file(f1a);
if (CORD_len(w) != CORD_len(z)) ABORT("file length wrong");
if (CORD_cmp(w,z) != 0) ABORT("file comparison wrong");
if (CORD_cmp(CORD_substr(w, 50*36+2, 36), y) != 0)
ABORT("file substr wrong");
f1b = fopen(FNAME1, "rb");
if (!f1b) ABORT("2nd open failed: " FNAME1);
z = CORD_from_file_lazy(f1b);
if (CORD_cmp(w,z) != 0) ABORT("File conversions differ");
if (CORD_chr(w, 0, '9') != 37) ABORT("CORD_chr failed 1");
if (CORD_chr(w, 3, 'a') != 38) ABORT("CORD_chr failed 2");
if (CORD_rchr(w, CORD_len(w) - 1, '}') != 1) ABORT("CORD_rchr failed");
x = y;
for (i = 1; i < 14; i++) {
x = CORD_cat(x,x);
}
if ((f = fopen(FNAME2, "w")) == 0) ABORT("2nd open failed");
# ifdef __DJGPP__
/* FIXME: DJGPP workaround. Why does this help? */
if (fflush(f) != 0) ABORT("fflush failed");
# endif
if (CORD_put(x,f) == EOF) ABORT("CORD_put failed");
if (fclose(f) == EOF) ABORT("fclose failed");
f2 = fopen(FNAME2, "rb");
if (!f2) ABORT("Unable to open " FNAME2);
w = CORD_from_file(f2);
if (CORD_len(w) != CORD_len(x)) ABORT("file length wrong");
if (CORD_cmp(w,x) != 0) ABORT("file comparison wrong");
if (CORD_cmp(CORD_substr(w, 1000*36, 36), y) != 0)
ABORT("file substr wrong");
if (strcmp(CORD_to_char_star(CORD_substr(w, 1000*36, 36)), y) != 0)
ABORT("char * file substr wrong");
if (strcmp(CORD_substr(w, 1000*36, 2), "ab") != 0)
ABORT("short file substr wrong");
if (CORD_str(x,1,"9a") != 35) ABORT("CORD_str failed 1");
if (CORD_str(x,0,"9abcdefghijk") != 35) ABORT("CORD_str failed 2");
if (CORD_str(x,0,"9abcdefghijx") != CORD_NOT_FOUND)
ABORT("CORD_str failed 3");
if (CORD_str(x,0,"9>") != CORD_NOT_FOUND) ABORT("CORD_str failed 4");
/* Note: f1a, f1b, f2 handles are closed lazily by CORD library. */
/* TODO: Propose and use CORD_fclose. */
*(CORD volatile *)&w = CORD_EMPTY;
*(CORD volatile *)&z = CORD_EMPTY;
GC_gcollect();
GC_invoke_finalizers();
/* Of course, this does not guarantee the files are closed. */
if (remove(FNAME1) != 0) {
/* On some systems, e.g. OS2, this may fail if f1 is still open. */
/* But we cannot call fclose as it might lead to double close. */
fprintf(stderr, "WARNING: remove(FNAME1) failed\n");
}
if (remove(FNAME2) != 0) {
fprintf(stderr, "WARNING: remove(FNAME2) failed\n");
}
}
