The majority of this code is either directly copied or edited from the GNU "libidn2" source code tree.
The crash is occurring in code that I added. The error message generated is "Encoding buffer allocation failed!". The system is a 24gb 2016 iMac running an up to date Catalina with >13gb free upon execution.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdarg.h>
#include <math.h>
#include "punycode.h"
#include "punycode_common.h"
#include "idn2.h"
struct punycode
{
const char *name;
size_t inlen;
uint32_t in[100];
const char *out;
int rc;
};
static const struct punycode punycode[] = {
{
"(A) Arabic (Egyptian)", 17,
{
0x0644, 0x064A, 0x0647, 0x0645, 0x0627, 0x0628, 0x062A, 0x0643,
0x0644, 0x0645, 0x0648, 0x0634, 0x0639, 0x0631, 0x0628, 0x064A,
0x061F}, "egbpdaj6bu4bxfgehfvwxn", IDN2_OK},
{
"(B) Chinese (simplified)", 9,
{
0x4ED6, 0x4EEC, 0x4E3A, 0x4EC0, 0x4E48, 0x4E0D, 0x8BF4, 0x4E2D,
0x6587}, "ihqwcrb4cv8a8dqg056pqjye", IDN2_OK},
{
"(C) Chinese (traditional)", 9,
{
0x4ED6, 0x5011, 0x7232, 0x4EC0, 0x9EBD, 0x4E0D, 0x8AAA, 0x4E2D,
0x6587}, "ihqwctvzc91f659drss3x8bo0yb", IDN2_OK},
{
"(D) Czech: Pro<ccaron>prost<ecaron>nemluv<iacute><ccaron>esky", 22,
{
0x0050, 0x0072, 0x006F, 0x010D, 0x0070, 0x0072, 0x006F, 0x0073,
0x0074, 0x011B, 0x006E, 0x0065, 0x006D, 0x006C, 0x0075, 0x0076,
0x00ED, 0x010D, 0x0065, 0x0073, 0x006B, 0x0079},
"Proprostnemluvesky-uyb24dma41a", IDN2_OK},
{
"(E) Hebrew:", 22,
{
0x05DC, 0x05DE, 0x05D4, 0x05D4, 0x05DD, 0x05E4, 0x05E9, 0x05D5,
0x05D8, 0x05DC, 0x05D0, 0x05DE, 0x05D3, 0x05D1, 0x05E8, 0x05D9,
0x05DD, 0x05E2, 0x05D1, 0x05E8, 0x05D9, 0x05EA},
"4dbcagdahymbxekheh6e0a7fei0b", IDN2_OK},
{
"(F) Hindi (Devanagari):", 30,
{
0x092F, 0x0939, 0x0932, 0x094B, 0x0917, 0x0939, 0x093F, 0x0928,
0x094D, 0x0926, 0x0940, 0x0915, 0x094D, 0x092F, 0x094B, 0x0902,
0x0928, 0x0939, 0x0940, 0x0902, 0x092C, 0x094B, 0x0932, 0x0938,
0x0915, 0x0924, 0x0947, 0x0939, 0x0948, 0x0902},
"i1baa7eci9glrd9b2ae1bj0hfcgg6iyaf8o0a1dig0cd", IDN2_OK},
{
"(G) Japanese (kanji and hiragana):", 18,
{
0x306A, 0x305C, 0x307F, 0x3093, 0x306A, 0x65E5, 0x672C, 0x8A9E,
0x3092, 0x8A71, 0x3057, 0x3066, 0x304F, 0x308C, 0x306A, 0x3044,
0x306E, 0x304B},
"n8jok5ay5dzabd5bym9f0cm5685rrjetr6pdxa", IDN2_OK},
{
"(H) Korean (Hangul syllables):", 24,
{
0xC138, 0xACC4, 0xC758, 0xBAA8, 0xB4E0, 0xC0AC, 0xB78C, 0xB4E4,
0xC774, 0xD55C, 0xAD6D, 0xC5B4, 0xB97C, 0xC774, 0xD574, 0xD55C,
0xB2E4, 0xBA74, 0xC5BC, 0xB9C8, 0xB098, 0xC88B, 0xC744, 0xAE4C},
"989aomsvi5e83db1d2a355cv1e0vak1dwrv93d5xbh15a0dt30a5jpsd879ccm6fea98c",
IDN2_OK},
{
"(I) Russian (Cyrillic):", 28,
{
0x043F, 0x043E, 0x0447, 0x0435, 0x043C, 0x0443, 0x0436, 0x0435,
0x043E, 0x043D, 0x0438, 0x043D, 0x0435, 0x0433, 0x043E, 0x0432,
0x043E, 0x0440, 0x044F, 0x0442, 0x043F, 0x043E, 0x0440, 0x0443,
0x0441, 0x0441, 0x043A, 0x0438},
"b1abfaaepdrnnbgefbadotcwatmq2g4l", IDN2_OK},
{
"(J) Spanish: Porqu<eacute>nopuedensimplementehablarenEspa<ntilde>ol", 40,
{
0x0050, 0x006F, 0x0072, 0x0071, 0x0075, 0x00E9, 0x006E, 0x006F,
0x0070, 0x0075, 0x0065, 0x0064, 0x0065, 0x006E, 0x0073, 0x0069,
0x006D, 0x0070, 0x006C, 0x0065, 0x006D, 0x0065, 0x006E, 0x0074,
0x0065, 0x0068, 0x0061, 0x0062, 0x006C, 0x0061, 0x0072, 0x0065,
0x006E, 0x0045, 0x0073, 0x0070, 0x0061, 0x00F1, 0x006F, 0x006C},
"PorqunopuedensimplementehablarenEspaol-fmd56a", IDN2_OK},
{
"(K) Vietnamese:", 31,
{
0x0054, 0x1EA1, 0x0069, 0x0073, 0x0061, 0x006F, 0x0068, 0x1ECD,
0x006B, 0x0068, 0x00F4, 0x006E, 0x0067, 0x0074, 0x0068, 0x1EC3,
0x0063, 0x0068, 0x1EC9, 0x006E, 0x00F3, 0x0069, 0x0074, 0x0069,
0x1EBF, 0x006E, 0x0067, 0x0056, 0x0069, 0x1EC7, 0x0074},
"TisaohkhngthchnitingVit-kjcr8268qyxafd2f1b9g", IDN2_OK},
{
"(L) 3<nen>B<gumi><kinpachi><sensei>", 8,
{
0x0033, 0x5E74, 0x0042, 0x7D44, 0x91D1, 0x516B, 0x5148, 0x751F},
"3B-ww4c5e180e575a65lsy2b", IDN2_OK},
{
"(M) <amuro><namie>-with-SUPER-MONKEYS", 24,
{
0x5B89, 0x5BA4, 0x5948, 0x7F8E, 0x6075, 0x002D, 0x0077, 0x0069,
0x0074, 0x0068, 0x002D, 0x0053, 0x0055, 0x0050, 0x0045, 0x0052,
0x002D, 0x004D, 0x004F, 0x004E, 0x004B, 0x0045, 0x0059, 0x0053},
"-with-SUPER-MONKEYS-pc58ag80a8qai00g7n9n", IDN2_OK},
{
"(N) Hello-Another-Way-<sorezore><no><basho>", 25,
{
0x0048, 0x0065, 0x006C, 0x006C, 0x006F, 0x002D, 0x0041, 0x006E,
0x006F, 0x0074, 0x0068, 0x0065, 0x0072, 0x002D, 0x0057, 0x0061,
0x0079, 0x002D, 0x305D, 0x308C, 0x305E, 0x308C, 0x306E, 0x5834,
0x6240},
"Hello-Another-Way--fc4qua05auwb3674vfr0b", IDN2_OK},
{
"(O) <hitotsu><yane><no><shita>2", 8,
{
0x3072, 0x3068, 0x3064, 0x5C4B, 0x6839, 0x306E, 0x4E0B, 0x0032},
"2-u9tlzr9756bt3uc0v", IDN2_OK},
{
"(P) Maji<de>Koi<suru>5<byou><mae>", 13,
{
0x004D, 0x0061, 0x006A, 0x0069, 0x3067, 0x004B, 0x006F, 0x0069,
0x3059, 0x308B, 0x0035, 0x79D2, 0x524D},
"MajiKoi5-783gue6qz075azm5e", IDN2_OK},
{
"(Q) <pafii>de<runba>", 9,
{
0x30D1, 0x30D5, 0x30A3, 0x30FC, 0x0064, 0x0065, 0x30EB, 0x30F3, 0x30D0},
"de-jg4avhby1noc0d", IDN2_OK},
{
"(R) <sono><supiido><de>", 7,
{
0x305D, 0x306E, 0x30B9, 0x30D4, 0x30FC, 0x30C9, 0x3067},
"d9juau41awczczp", IDN2_OK},
{
"(S) -> $1.00 <-", 11,
{
0x002D, 0x003E, 0x0020, 0x0024, 0x0031, 0x002E, 0x0030, 0x0030,
0x0020, 0x003C, 0x002D}, "-> $1.00 <--", IDN2_OK}
};
static int error_count = 0;
static int break_on_error = 0;
static void
fail (const char *format, ...)
{
va_list arg_ptr;
va_start (arg_ptr, format);
vfprintf (stderr, format, arg_ptr);
va_end (arg_ptr);
error_count++;
if (break_on_error)
exit (EXIT_FAILURE);
}
static void
ucs4print (const uint32_t * str, size_t len)
{
size_t i;
printf ("\t;; ");
for (i = 0; i < len; i++)
{
printf ("U+%04x ", str[i]);
if ((i + 1) % 4 == 0)
printf (" ");
if ((i + 1) % 8 == 0 && i + 1 < len)
printf ("\n\t;; ");
}
puts ("");
}
void adaptinput(char *inp, uint32_t *buffer) {
int ndx = 0;
for (int ctr = 0; ctr < strlen(inp); ctr++) {
buffer[ndx] = inp[ctr];
ndx += sizeof(uint32_t);
}
}
int main(int argc, char **argv) {
unsigned includeConstantTests = 1;
if (argc >= 2) {
for (int ctr1 = 1; ctr1 < argc; ctr1++) {
if (strcmp(argv[ctr1], "--skip")) {
includeConstantTests = 0;
for (int ctr2 = argc - 2; ctr2 > ctr1 && ctr2 < argc - 1; ctr2--) {
argv[ctr2 - 1] = argv[ctr2];
}
argc = argc - 1;
}
if (includeConstantTests != 0)
{
char *p;
uint32_t *q;
int rc;
size_t i, outlen;
p = (char *) malloc (sizeof (*p) * BUFSIZ);
if (p == NULL)
fail ("malloc() returned NULL\n");
q = (uint32_t *) malloc (sizeof (*q) * BUFSIZ);
if (q == NULL)
fail ("malloc() returned NULL\n");
for (i = 0; i < sizeof (punycode) / sizeof (punycode[0]); i++)
{
printf ("PUNYCODE entry %d: %s\n", (int) i, punycode[i].name);
printf ("in:\n");
ucs4print (punycode[i].in, punycode[i].inlen);
outlen = BUFSIZ;
rc = punycode_encode(punycode[i].inlen, punycode[i].in, &outlen, p);
if (rc != punycode[i].rc)
{
fail ("punycode_encode() entry %d failed: %d\n", (int) i, rc);
printf ("FATAL\n");
continue;
}
if (rc == IDN2_OK)
p[outlen] = '\0';
if (rc == IDN2_OK)
{
printf ("computed out: %s\n", p);
printf ("expected out: %s\n", punycode[i].out);
}
else
printf ("returned %d expected %d\n", rc, punycode[i].rc);
if (rc == IDN2_OK)
{
if (strlen (punycode[i].out) != strlen (p) ||
memcmp (punycode[i].out, p, strlen (p)) != 0)
{
fail ("punycode() entry %d failed\n", (int) i);
printf ("ERROR\n");
}
else
printf ("OK\n\n");
}
else
printf ("OK\n\n");
printf ("in: %s\n", punycode[i].out);
outlen = BUFSIZ;
rc = punycode_decode(strlen (punycode[i].out), punycode[i].out, &outlen, q);
if (rc != punycode[i].rc)
{
fail ("punycode() entry %d failed: %d\n", (int) i, rc);
printf ("FATAL\n");
continue;
}
if (rc == IDN2_OK)
{
printf ("computed out:\n");
ucs4print (q, outlen);
printf ("expected out:\n");
ucs4print (punycode[i].in, punycode[i].inlen);
}
else
printf ("returned %d expected %d\n", rc, punycode[i].rc);
if (rc == IDN2_OK)
{
if (punycode[i].inlen != outlen ||
memcmp (punycode[i].in, q, outlen) != 0)
{
fail ("punycode_decode() entry %d failed\n", (int) i);
printf ("ERROR\n");
}
else
printf ("OK\n\n");
}
else
printf ("OK\n\n");
}
free (q);
free (p);
}
size_t insize = sizeof(argv[ctr1]) * sizeof(uint32_t);
void *inbuffer = malloc(insize);
if (inbuffer != NULL) {
adaptinput(argv[ctr1], inbuffer);
unsigned mbs = 256;
size_t bufsize = pow(2,20) * mbs;
void *encbuffer = malloc(bufsize);
if (encbuffer != NULL) {
size_t encsize = bufsize;
int rc = punycode_encode(insize, inbuffer, &encsize, encbuffer);
if (rc == IDN2_OK) {
void *decbuffer = malloc(pow(2, 10) * mbs);
if (decbuffer != NULL) {
rc = punycode_decode(bufsize, decbuffer, &insize, encbuffer);
if (rc == IDN2_OK) {
printf("%s ",argv[ctr1]);
if (strcmp(inbuffer, argv[ctr1])) {
printf("MATCHED!");
} else {
printf("Did NOT Match");
}
printf("\n");
}
} else {
printf("Decoding buffer allocation failed!\n");
printf("size of uint32_t is %lu", sizeof(uint32_t));
return -3;
}
} else {
printf("Encoding buffer allocation failed!\n");
printf("size of uint32_t is %lu", sizeof(uint32_t));
return -2;
}
}
} else {
printf("Input buffer allocation failed!\n");
return -1;
}
}
}
}