static VALUE
pack_unpack(VALUE str, VALUE fmt)
{
static const char hexdigits[] = "0123456789abcdef";
char *s, *send;
char *p, *pend;
VALUE ary;
char type;
long len, tmp_len;
int star;
int natint; /* native integer */
int block_p = rb_block_given_p();
int signed_p, integer_size, bigendian_p;
VALUE item_val = (item);\
if (block_p) {\
rb_yield(item_val);\
}\
else {\
rb_ary_push(ary, item_val);\
}\
} while (0)
StringValue(str);
StringValue(fmt);
s = RSTRING_PTR(str);
send = s + RSTRING_LEN(str);
p = RSTRING_PTR(fmt);
pend = p + RSTRING_LEN(fmt);
ary = block_p ? Qnil : rb_ary_new();
while (p < pend) {
type = *p++;
natint = 0;
if (ISSPACE(type)) continue;
if (type == '#') {
while ((p < pend) && (*p != '\n')) {
p++;
}
continue;
}
star = 0;
if (*p == '_' || *p == '!') {
static const char natstr[] = "sSiIlL";
if (strchr(natstr, type)) {
natint = 1;
p++;
}
else {
rb_raise(rb_eArgError, "'%c' allowed only after types %s", *p, natstr);
}
}
if (p >= pend)
len = 1;
else if (*p == '*') {
star = 1;
len = send - s;
p++;
}
else if (ISDIGIT(*p)) {
errno = 0;
len = STRTOUL(p, (char**)&p, 10);
if (errno) {
rb_raise(rb_eRangeError, "pack length too big");
}
}
else {
len = (type != '@');
}
switch (type) {
case '%':
rb_raise(rb_eArgError, "%% is not supported");
break;
case 'A':
if (len > send - s) len = send - s;
{
long end = len;
char *t = s + len - 1;
while (t >= s) {
if (*t != ' ' && *t != '\0') break;
t--; len--;
}
UNPACK_PUSH(infected_str_new(s, len, str));
s += end;
}
break;
case 'Z':
{
char *t = s;
if (len > send-s) len = send-s;
while (t < s+len && *t) t++;
UNPACK_PUSH(infected_str_new(s, t-s, str));
if (t < send) t++;
s = star ? t : s+len;
}
break;
case 'a':
if (len > send - s) len = send - s;
UNPACK_PUSH(infected_str_new(s, len, str));
s += len;
break;
case 'b':
{
VALUE bitstr;
char *t;
int bits;
long i;
if (p[-1] == '*' || len > (send - s) * 8)
len = (send - s) * 8;
bits = 0;
UNPACK_PUSH(bitstr = rb_str_new(0, len));
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 7) bits >>= 1;
else bits = *s++;
*t++ = (bits & 1) ? '1' : '0';
}
}
break;
case 'B':
{
VALUE bitstr;
char *t;
int bits;
long i;
if (p[-1] == '*' || len > (send - s) * 8)
len = (send - s) * 8;
bits = 0;
UNPACK_PUSH(bitstr = rb_str_new(0, len));
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 7) bits <<= 1;
else bits = *s++;
*t++ = (bits & 128) ? '1' : '0';
}
}
break;
case 'h':
{
VALUE bitstr;
char *t;
int bits;
long i;
if (p[-1] == '*' || len > (send - s) * 2)
len = (send - s) * 2;
bits = 0;
UNPACK_PUSH(bitstr = rb_str_new(0, len));
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 1)
bits >>= 4;
else
bits = *s++;
*t++ = hexdigits[bits & 15];
}
}
break;
case 'H':
{
VALUE bitstr;
char *t;
int bits;
long i;
if (p[-1] == '*' || len > (send - s) * 2)
len = (send - s) * 2;
bits = 0;
UNPACK_PUSH(bitstr = rb_str_new(0, len));
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 1)
bits <<= 4;
else
bits = *s++;
*t++ = hexdigits[(bits >> 4) & 15];
}
}
break;
case 'c':
PACK_LENGTH_ADJUST_SIZE(sizeof(char));
while (len-- > 0) {
int c = *s++;
if (c > (char)127) c-=256;
UNPACK_PUSH(INT2FIX(c));
}
PACK_ITEM_ADJUST();
break;
case 'C':
PACK_LENGTH_ADJUST_SIZE(sizeof(unsigned char));
while (len-- > 0) {
unsigned char c = *s++;
UNPACK_PUSH(INT2FIX(c));
}
PACK_ITEM_ADJUST();
break;
case 's':
signed_p = 1;
integer_size = NATINT_LEN(short, 2);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'S':
signed_p = 0;
integer_size = NATINT_LEN(short, 2);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'i':
signed_p = 1;
integer_size = (int)sizeof(int);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'I':
signed_p = 0;
integer_size = (int)sizeof(int);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'l':
signed_p = 1;
integer_size = NATINT_LEN(long, 4);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'L':
signed_p = 0;
integer_size = NATINT_LEN(long, 4);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'q':
signed_p = 1;
integer_size = QUAD_SIZE;
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'Q':
signed_p = 0;
integer_size = QUAD_SIZE;
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
case 'n':
signed_p = 0;
integer_size = 2;
bigendian_p = 1;
goto unpack_integer;
case 'N':
signed_p = 0;
integer_size = 4;
bigendian_p = 1;
goto unpack_integer;
case 'v':
signed_p = 0;
integer_size = 2;
bigendian_p = 0;
goto unpack_integer;
case 'V':
signed_p = 0;
integer_size = 4;
bigendian_p = 0;
goto unpack_integer;
unpack_integer:
switch (integer_size) {
case SIZEOF_INT16_T:
if (signed_p) {
PACK_LENGTH_ADJUST_SIZE(sizeof(int16_t));
while (len-- > 0) {
union {
int16_t i;
char a[sizeof(int16_t)];
} v;
memcpy(v.a, s, sizeof(int16_t));
if (bigendian_p != BIGENDIAN_P()) v.i = swap16(v.i);
s += sizeof(int16_t);
UNPACK_PUSH(INT2FIX(v.i));
}
PACK_ITEM_ADJUST();
}
else {
PACK_LENGTH_ADJUST_SIZE(sizeof(uint16_t));
while (len-- > 0) {
union {
uint16_t i;
char a[sizeof(uint16_t)];
} v;
memcpy(v.a, s, sizeof(uint16_t));
if (bigendian_p != BIGENDIAN_P()) v.i = swap16(v.i);
s += sizeof(uint16_t);
UNPACK_PUSH(INT2FIX(v.i));
}
PACK_ITEM_ADJUST();
}
break;
case SIZEOF_INT32_T:
if (signed_p) {
PACK_LENGTH_ADJUST_SIZE(sizeof(int32_t));
while (len-- > 0) {
union {
int32_t i;
char a[sizeof(int32_t)];
} v;
memcpy(v.a, s, sizeof(int32_t));
if (bigendian_p != BIGENDIAN_P()) v.i = swap32(v.i);
s += sizeof(int32_t);
UNPACK_PUSH(INT2NUM(v.i));
}
PACK_ITEM_ADJUST();
}
else {
PACK_LENGTH_ADJUST_SIZE(sizeof(uint32_t));
while (len-- > 0) {
union {
uint32_t i;
char a[sizeof(uint32_t)];
} v;
memcpy(v.a, s, sizeof(uint32_t));
if (bigendian_p != BIGENDIAN_P()) v.i = swap32(v.i);
s += sizeof(uint32_t);
UNPACK_PUSH(UINT2NUM(v.i));
}
PACK_ITEM_ADJUST();
}
break;
case SIZEOF_INT64_T:
if (signed_p) {
PACK_LENGTH_ADJUST_SIZE(sizeof(int64_t));
while (len-- > 0) {
union {
int64_t i;
char a[sizeof(int64_t)];
} v;
memcpy(v.a, s, sizeof(int64_t));
if (bigendian_p != BIGENDIAN_P()) v.i = swap64(v.i);
s += sizeof(int64_t);
UNPACK_PUSH(INT64toNUM(v.i));
}
PACK_ITEM_ADJUST();
}
else {
PACK_LENGTH_ADJUST_SIZE(sizeof(uint64_t));
while (len-- > 0) {
union {
uint64_t i;
char a[sizeof(uint64_t)];
} v;
memcpy(v.a, s, sizeof(uint64_t));
if (bigendian_p != BIGENDIAN_P()) v.i = swap64(v.i);
s += sizeof(uint64_t);
UNPACK_PUSH(UINT64toNUM(v.i));
}
PACK_ITEM_ADJUST();
}
break;
default:
if (integer_size > MAX_INTEGER_PACK_SIZE)
rb_bug("unexpected intger size for pack: %d", integer_size);
PACK_LENGTH_ADJUST_SIZE(integer_size);
while (len-- > 0) {
union {
unsigned long i[(MAX_INTEGER_PACK_SIZE+SIZEOF_LONG)/SIZEOF_LONG];
char a[(MAX_INTEGER_PACK_SIZE+SIZEOF_LONG)/SIZEOF_LONG*SIZEOF_LONG];
} v;
int num_longs = (integer_size+SIZEOF_LONG)/SIZEOF_LONG;
int i;
if (signed_p && (signed char)s[bigendian_p ? 0 : (integer_size-1)] < 0)
memset(v.a, 0xff, sizeof(long)*num_longs);
else
memset(v.a, 0, sizeof(long)*num_longs);
if (bigendian_p)
memcpy(v.a + sizeof(long)*num_longs - integer_size, s, integer_size);
else
memcpy(v.a, s, integer_size);
if (bigendian_p) {
for (i = 0; i < num_longs/2; i++) {
unsigned long t = v.i[i];
v.i[i] = v.i[num_longs-1-i];
v.i[num_longs-1-i] = t;
}
}
if (bigendian_p != BIGENDIAN_P()) {
for (i = 0; i < num_longs; i++)
v.i[i] = swapl(v.i[i]);
}
s += integer_size;
UNPACK_PUSH(rb_big_unpack(v.i, num_longs));
}
PACK_ITEM_ADJUST();
break;
}
break;
case 'f':
case 'F':
PACK_LENGTH_ADJUST_SIZE(sizeof(float));
while (len-- > 0) {
float tmp;
memcpy(&tmp, s, sizeof(float));
s += sizeof(float);
UNPACK_PUSH(DBL2NUM((double)tmp));
}
PACK_ITEM_ADJUST();
break;
case 'e':
PACK_LENGTH_ADJUST_SIZE(sizeof(float));
while (len-- > 0) {
float tmp;
FLOAT_CONVWITH(ftmp);
memcpy(&tmp, s, sizeof(float));
s += sizeof(float);
tmp = VTOHF(tmp,ftmp);
UNPACK_PUSH(DBL2NUM((double)tmp));
}
PACK_ITEM_ADJUST();
break;
case 'E':
PACK_LENGTH_ADJUST_SIZE(sizeof(double));
while (len-- > 0) {
double tmp;
DOUBLE_CONVWITH(dtmp);
memcpy(&tmp, s, sizeof(double));
s += sizeof(double);
tmp = VTOHD(tmp,dtmp);
UNPACK_PUSH(DBL2NUM(tmp));
}
PACK_ITEM_ADJUST();
break;
case 'D':
case 'd':
PACK_LENGTH_ADJUST_SIZE(sizeof(double));
while (len-- > 0) {
double tmp;
memcpy(&tmp, s, sizeof(double));
s += sizeof(double);
UNPACK_PUSH(DBL2NUM(tmp));
}
PACK_ITEM_ADJUST();
break;
case 'g':
PACK_LENGTH_ADJUST_SIZE(sizeof(float));
while (len-- > 0) {
float tmp;
FLOAT_CONVWITH(ftmp;)
memcpy(&tmp, s, sizeof(float));
s += sizeof(float);
tmp = NTOHF(tmp,ftmp);
UNPACK_PUSH(DBL2NUM((double)tmp));
}
PACK_ITEM_ADJUST();
break;
case 'G':
PACK_LENGTH_ADJUST_SIZE(sizeof(double));
while (len-- > 0) {
double tmp;
DOUBLE_CONVWITH(dtmp);
memcpy(&tmp, s, sizeof(double));
s += sizeof(double);
tmp = NTOHD(tmp,dtmp);
UNPACK_PUSH(DBL2NUM(tmp));
}
PACK_ITEM_ADJUST();
break;
case 'U':
if (len > send - s) len = send - s;
while (len > 0 && s < send) {
long alen = send - s;
unsigned long l;
l = utf8_to_uv(s, &alen);
s += alen; len--;
UNPACK_PUSH(ULONG2NUM(l));
}
break;
case 'u':
{
VALUE buf = infected_str_new(0, (send - s)*3/4, str);
char *ptr = RSTRING_PTR(buf);
long total = 0;
while (s < send && *s > ' ' && *s < 'a') {
long a,b,c,d;
char hunk[4];
hunk[3] = '\0';
len = (*s++ - ' ') & 077;
total += len;
if (total > RSTRING_LEN(buf)) {
len -= total - RSTRING_LEN(buf);
total = RSTRING_LEN(buf);
}
while (len > 0) {
long mlen = len > 3 ? 3 : len;
if (s < send && *s >= ' ')
a = (*s++ - ' ') & 077;
else
a = 0;
if (s < send && *s >= ' ')
b = (*s++ - ' ') & 077;
else
b = 0;
if (s < send && *s >= ' ')
c = (*s++ - ' ') & 077;
else
c = 0;
if (s < send && *s >= ' ')
d = (*s++ - ' ') & 077;
else
d = 0;
hunk[0] = (char)(a << 2 | b >> 4);
hunk[1] = (char)(b << 4 | c >> 2);
hunk[2] = (char)(c << 6 | d);
memcpy(ptr, hunk, mlen);
ptr += mlen;
len -= mlen;
}
if (*s == '\r') s++;
if (*s == '\n') s++;
else if (s < send && (s+1 == send || s[1] == '\n'))
s += 2; /* possible checksum byte */
}
rb_str_set_len(buf, total);
UNPACK_PUSH(buf);
}
break;
case 'm':
{
VALUE buf = infected_str_new(0, (send - s)*3/4, str);
char *ptr = RSTRING_PTR(buf);
int a = -1,b = -1,c = 0,d = 0;
static signed char b64_xtable[256];
if (b64_xtable['/'] <= 0) {
int i;
for (i = 0; i < 256; i++) {
b64_xtable[i] = -1;
}
for (i = 0; i < 64; i++) {
b64_xtable[(unsigned char)b64_table[i]] = i;
}
}
if (len == 0) {
while (s < send) {
a = b = c = d = -1;
a = b64_xtable[(unsigned char)*s++];
if (s >= send || a == -1) rb_raise(rb_eArgError, "invalid base64");
b = b64_xtable[(unsigned char)*s++];
if (s >= send || b == -1) rb_raise(rb_eArgError, "invalid base64");
if (*s == '=') {
if (s + 2 == send && *(s + 1) == '=') break;
rb_raise(rb_eArgError, "invalid base64");
}
c = b64_xtable[(unsigned char)*s++];
if (s >= send || c == -1) rb_raise(rb_eArgError, "invalid base64");
if (s + 1 == send && *s == '=') break;
d = b64_xtable[(unsigned char)*s++];
if (d == -1) rb_raise(rb_eArgError, "invalid base64");
*ptr++ = a << 2 | b >> 4;
*ptr++ = b << 4 | c >> 2;
*ptr++ = c << 6 | d;
}
if (c == -1) {
*ptr++ = a << 2 | b >> 4;
if (b & 0xf) rb_raise(rb_eArgError, "invalid base64");
}
else if (d == -1) {
*ptr++ = a << 2 | b >> 4;
*ptr++ = b << 4 | c >> 2;
if (c & 0x3) rb_raise(rb_eArgError, "invalid base64");
}
}
else {
while (s < send) {
a = b = c = d = -1;
while ((a = b64_xtable[(unsigned char)*s]) == -1 && s < send) {s++;}
if (s >= send) break;
s++;
while ((b = b64_xtable[(unsigned char)*s]) == -1 && s < send) {s++;}
if (s >= send) break;
s++;
while ((c = b64_xtable[(unsigned char)*s]) == -1 && s < send) {if (*s == '=') break; s++;}
if (*s == '=' || s >= send) break;
s++;
while ((d = b64_xtable[(unsigned char)*s]) == -1 && s < send) {if (*s == '=') break; s++;}
if (*s == '=' || s >= send) break;
s++;
*ptr++ = a << 2 | b >> 4;
*ptr++ = b << 4 | c >> 2;
*ptr++ = c << 6 | d;
}
if (a != -1 && b != -1) {
if (c == -1 && *s == '=')
*ptr++ = a << 2 | b >> 4;
else if (c != -1 && *s == '=') {
*ptr++ = a << 2 | b >> 4;
*ptr++ = b << 4 | c >> 2;
}
}
}
rb_str_set_len(buf, ptr - RSTRING_PTR(buf));
UNPACK_PUSH(buf);
}
break;
case 'M':
{
VALUE buf = infected_str_new(0, send - s, str);
char *ptr = RSTRING_PTR(buf);
int c1, c2;
while (s < send) {
if (*s == '=') {
if (++s == send) break;
if (s+1 < send && *s == '\r' && *(s+1) == '\n')
s++;
if (*s != '\n') {
if ((c1 = hex2num(*s)) == -1) break;
if (++s == send) break;
if ((c2 = hex2num(*s)) == -1) break;
*ptr++ = c1 << 4 | c2;
}
}
else {
*ptr++ = *s;
}
s++;
}
rb_str_set_len(buf, ptr - RSTRING_PTR(buf));
ENCODING_CODERANGE_SET(buf, rb_usascii_encindex(), ENC_CODERANGE_7BIT);
UNPACK_PUSH(buf);
}
break;
case '@':
if (len > RSTRING_LEN(str))
rb_raise(rb_eArgError, "@ outside of string");
s = RSTRING_PTR(str) + len;
break;
case 'X':
if (len > s - RSTRING_PTR(str))
rb_raise(rb_eArgError, "X outside of string");
s -= len;
break;
case 'x':
if (len > send - s)
rb_raise(rb_eArgError, "x outside of string");
s += len;
break;
case 'P':
if (sizeof(char *) <= (size_t)(send - s)) {
VALUE tmp = Qnil;
char *t;
memcpy(&t, s, sizeof(char *));
s += sizeof(char *);
if (t) {
VALUE a, *p, *pend;
if (!(a = rb_str_associated(str))) {
rb_raise(rb_eArgError, "no associated pointer");
}
p = RARRAY_PTR(a);
pend = p + RARRAY_LEN(a);
while (p < pend) {
if (TYPE(*p) == T_STRING && RSTRING_PTR(*p) == t) {
if (len < RSTRING_LEN(*p)) {
tmp = rb_tainted_str_new(t, len);
rb_str_associate(tmp, a);
}
else {
tmp = *p;
}
break;
}
p++;
}
if (p == pend) {
rb_raise(rb_eArgError, "non associated pointer");
}
}
UNPACK_PUSH(tmp);
}
break;
case 'p':
if (len > (long)((send - s) / sizeof(char *)))
len = (send - s) / sizeof(char *);
while (len-- > 0) {
if ((size_t)(send - s) < sizeof(char *))
break;
else {
VALUE tmp = Qnil;
char *t;
memcpy(&t, s, sizeof(char *));
s += sizeof(char *);
if (t) {
VALUE a, *p, *pend;
if (!(a = rb_str_associated(str))) {
rb_raise(rb_eArgError, "no associated pointer");
}
p = RARRAY_PTR(a);
pend = p + RARRAY_LEN(a);
while (p < pend) {
if (TYPE(*p) == T_STRING && RSTRING_PTR(*p) == t) {
tmp = *p;
break;
}
p++;
}
if (p == pend) {
rb_raise(rb_eArgError, "non associated pointer");
}
}
UNPACK_PUSH(tmp);
}
}
break;
case 'w':
{
unsigned long ul = 0;
unsigned long ulmask = 0xfeUL << ((sizeof(unsigned long) - 1) * 8);
while (len > 0 && s < send) {
ul <<= 7;
ul |= (*s & 0x7f);
if (!(*s++ & 0x80)) {
UNPACK_PUSH(ULONG2NUM(ul));
len--;
ul = 0;
}
else if (ul & ulmask) {
VALUE big = rb_uint2big(ul);
VALUE big128 = rb_uint2big(128);
while (s < send) {
big = rb_big_mul(big, big128);
big = rb_big_plus(big, rb_uint2big(*s & 0x7f));
if (!(*s++ & 0x80)) {
UNPACK_PUSH(big);
len--;
ul = 0;
break;
}
}
}
}
}
break;
default:
break;
}
}
return ary;
}