Method: Array#pack
- Defined in:
- pack.c
#pack ⇒ Object
Packs the contents of arr into a binary sequence according to the directives in aTemplateString (see the table below) Directives "A," "a," and "Z" may be followed by a count, which gives the width of the resulting field. The remaining directives also may take a count, indicating the number of array elements to convert. If the count is an asterisk ("*"), all remaining array elements will be converted. Any of the directives "sSiIlL" may be followed by an underscore ("_") or exclamation mark ("!") to use the underlying platform's native size for the specified type; otherwise, they use a platform-independent size. Spaces are ignored in the template string. See also String#unpack.
a = [ "a", "b", "c" ]
n = [ 65, 66, 67 ]
a.pack("A3A3A3") #=> "a b c "
a.pack("a3a3a3") #=> "a\000\000b\000\000c\000\000"
n.pack("ccc") #=> "ABC"
Directives for pack.
Integer | Array |
Directive | Element | Meaning
---------------------------------------------------------------------------
C | Integer | 8-bit unsigned integer (unsigned char)
S | Integer | 16-bit unsigned integer, native endian (uint16_t)
L | Integer | 32-bit unsigned integer, native endian (uint32_t)
Q | Integer | 64-bit unsigned integer, native endian (uint64_t)
| |
c | Integer | 8-bit signed integer (char)
s | Integer | 16-bit signed integer, native endian (int16_t)
l | Integer | 32-bit signed integer, native endian (int32_t)
q | Integer | 64-bit signed integer, native endian (int64_t)
| |
S_, S! | Integer | unsigned short, native endian
I, I_, I! | Integer | unsigned int, native endian
L_, L! | Integer | unsigned long, native endian
| |
s_, s! | Integer | signed short, native endian
i, i_, i! | Integer | signed int, native endian
l_, l! | Integer | signed long, native endian
| |
n | Integer | 16-bit unsigned integer, network (big-endian) byte order
N | Integer | 32-bit unsigned integer, network (big-endian) byte order
v | Integer | 16-bit unsigned integer, VAX (little-endian) byte order
V | Integer | 32-bit unsigned integer, VAX (little-endian) byte order
| |
U | Integer | UTF-8 character
w | Integer | BER-compressed integer
Float | |
Directive | | Meaning
---------------------------------------------------------------------------
D, d | Float | double-precision float, native format
F, f | Float | single-precision float, native format
E | Float | double-precision float, little-endian byte order
e | Float | single-precision float, little-endian byte order
G | Float | double-precision float, network (big-endian) byte order
g | Float | single-precision float, network (big-endian) byte order
String | |
Directive | | Meaning
---------------------------------------------------------------------------
A | String | arbitrary binary string (space padded, count is width)
a | String | arbitrary binary string (null padded, count is width)
Z | String | same as ``a'', except that null is added with *
B | String | bit string (MSB first)
b | String | bit string (LSB first)
H | String | hex string (high nibble first)
h | String | hex string (low nibble first)
u | String | UU-encoded string
M | String | quoted printable, MIME encoding (see RFC2045)
m | String | base64 encoded string (see RFC 2045, count is width)
| | (if count is 0, no line feed are added, see RFC 4648)
P | String | pointer to a structure (fixed-length string)
p | String | pointer to a null-terminated string
Misc. | |
Directive | | Meaning
---------------------------------------------------------------------------
@ | --- | moves to absolute position
X | --- | back up a byte
x | --- | null byte
|
|
# File 'pack.c'
/*
* call-seq:
* arr.pack ( aTemplateString ) -> aBinaryString
*
* Packs the contents of <i>arr</i> into a binary sequence according to
* the directives in <i>aTemplateString</i> (see the table below)
* Directives ``A,'' ``a,'' and ``Z'' may be followed by a count,
* which gives the width of the resulting field. The remaining
* directives also may take a count, indicating the number of array
* elements to convert. If the count is an asterisk
* (``<code>*</code>''), all remaining array elements will be
* converted. Any of the directives ``<code>sSiIlL</code>'' may be
* followed by an underscore (``<code>_</code>'') or
* exclamation mark (``<code>!</code>'') to use the underlying
* platform's native size for the specified type; otherwise, they use a
* platform-independent size. Spaces are ignored in the template
* string. See also <code>String#unpack</code>.
*
* a = [ "a", "b", "c" ]
* n = [ 65, 66, 67 ]
* a.pack("A3A3A3") #=> "a b c "
* a.pack("a3a3a3") #=> "a\000\000b\000\000c\000\000"
* n.pack("ccc") #=> "ABC"
*
* Directives for +pack+.
*
* Integer | Array |
* Directive | Element | Meaning
* ---------------------------------------------------------------------------
* C | Integer | 8-bit unsigned integer (unsigned char)
* S | Integer | 16-bit unsigned integer, native endian (uint16_t)
* L | Integer | 32-bit unsigned integer, native endian (uint32_t)
* Q | Integer | 64-bit unsigned integer, native endian (uint64_t)
* | |
* c | Integer | 8-bit signed integer (char)
* s | Integer | 16-bit signed integer, native endian (int16_t)
* l | Integer | 32-bit signed integer, native endian (int32_t)
* q | Integer | 64-bit signed integer, native endian (int64_t)
* | |
* S_, S! | Integer | unsigned short, native endian
* I, I_, I! | Integer | unsigned int, native endian
* L_, L! | Integer | unsigned long, native endian
* | |
* s_, s! | Integer | signed short, native endian
* i, i_, i! | Integer | signed int, native endian
* l_, l! | Integer | signed long, native endian
* | |
* n | Integer | 16-bit unsigned integer, network (big-endian) byte order
* N | Integer | 32-bit unsigned integer, network (big-endian) byte order
* v | Integer | 16-bit unsigned integer, VAX (little-endian) byte order
* V | Integer | 32-bit unsigned integer, VAX (little-endian) byte order
* | |
* U | Integer | UTF-8 character
* w | Integer | BER-compressed integer
*
* Float | |
* Directive | | Meaning
* ---------------------------------------------------------------------------
* D, d | Float | double-precision float, native format
* F, f | Float | single-precision float, native format
* E | Float | double-precision float, little-endian byte order
* e | Float | single-precision float, little-endian byte order
* G | Float | double-precision float, network (big-endian) byte order
* g | Float | single-precision float, network (big-endian) byte order
*
* String | |
* Directive | | Meaning
* ---------------------------------------------------------------------------
* A | String | arbitrary binary string (space padded, count is width)
* a | String | arbitrary binary string (null padded, count is width)
* Z | String | same as ``a'', except that null is added with *
* B | String | bit string (MSB first)
* b | String | bit string (LSB first)
* H | String | hex string (high nibble first)
* h | String | hex string (low nibble first)
* u | String | UU-encoded string
* M | String | quoted printable, MIME encoding (see RFC2045)
* m | String | base64 encoded string (see RFC 2045, count is width)
* | | (if count is 0, no line feed are added, see RFC 4648)
* P | String | pointer to a structure (fixed-length string)
* p | String | pointer to a null-terminated string
*
* Misc. | |
* Directive | | Meaning
* ---------------------------------------------------------------------------
* @ | --- | moves to absolute position
* X | --- | back up a byte
* x | --- | null byte
*/
static VALUE
pack_pack(VALUE ary, VALUE fmt)
{
static const char nul10[] = "\0\0\0\0\0\0\0\0\0\0";
static const char spc10[] = " ";
const char *p, *pend;
VALUE res, from, associates = 0;
char type;
long items, len, idx, plen;
const char *ptr;
int enc_info = 1; /* 0 - BINARY, 1 - US-ASCII, 2 - UTF-8 */
#ifdef NATINT_PACK
int natint; /* native integer */
#endif
int signed_p, integer_size, bigendian_p;
StringValue(fmt);
p = RSTRING_PTR(fmt);
pend = p + RSTRING_LEN(fmt);
res = rb_str_buf_new(0);
items = RARRAY_LEN(ary);
idx = 0;
#define TOO_FEW (rb_raise(rb_eArgError, toofew), 0)
#define THISFROM (items > 0 ? RARRAY_PTR(ary)[idx] : TOO_FEW)
#define NEXTFROM (items-- > 0 ? RARRAY_PTR(ary)[idx++] : TOO_FEW)
while (p < pend) {
if (RSTRING_PTR(fmt) + RSTRING_LEN(fmt) != pend) {
rb_raise(rb_eRuntimeError, "format string modified");
}
type = *p++; /* get data type */
#ifdef NATINT_PACK
natint = 0;
#endif
if (ISSPACE(type)) continue;
if (type == '#') {
while ((p < pend) && (*p != '\n')) {
p++;
}
continue;
}
if (*p == '_' || *p == '!') {
static const char natstr[] = "sSiIlL";
if (strchr(natstr, type)) {
#ifdef NATINT_PACK
natint = 1;
#endif
p++;
}
else {
rb_raise(rb_eArgError, "'%c' allowed only after types %s", *p, natstr);
}
}
if (*p == '*') { /* set data length */
len = strchr("@Xxu", type) ? 0
: strchr("PMm", type) ? 1
: items;
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 = 1;
}
switch (type) {
case 'U':
/* if encoding is US-ASCII, upgrade to UTF-8 */
if (enc_info == 1) enc_info = 2;
break;
case 'm': case 'M': case 'u':
/* keep US-ASCII (do nothing) */
break;
default:
/* fall back to BINARY */
enc_info = 0;
break;
}
switch (type) {
case 'A': case 'a': case 'Z':
case 'B': case 'b':
case 'H': case 'h':
from = NEXTFROM;
if (NIL_P(from)) {
ptr = "";
plen = 0;
}
else {
StringValue(from);
ptr = RSTRING_PTR(from);
plen = RSTRING_LEN(from);
OBJ_INFECT(res, from);
}
if (p[-1] == '*')
len = plen;
switch (type) {
case 'a': /* arbitrary binary string (null padded) */
case 'A': /* arbitrary binary string (ASCII space padded) */
case 'Z': /* null terminated string */
if (plen >= len) {
rb_str_buf_cat(res, ptr, len);
if (p[-1] == '*' && type == 'Z')
rb_str_buf_cat(res, nul10, 1);
}
else {
rb_str_buf_cat(res, ptr, plen);
len -= plen;
while (len >= 10) {
rb_str_buf_cat(res, (type == 'A')?spc10:nul10, 10);
len -= 10;
}
rb_str_buf_cat(res, (type == 'A')?spc10:nul10, len);
}
break;
case 'b': /* bit string (ascending) */
{
int byte = 0;
long i, j = 0;
if (len > plen) {
j = (len - plen + 1)/2;
len = plen;
}
for (i=0; i++ < len; ptr++) {
if (*ptr & 1)
byte |= 128;
if (i & 7)
byte >>= 1;
else {
char c = byte & 0xff;
rb_str_buf_cat(res, &c, 1);
byte = 0;
}
}
if (len & 7) {
char c;
byte >>= 7 - (len & 7);
c = byte & 0xff;
rb_str_buf_cat(res, &c, 1);
}
len = j;
goto grow;
}
break;
case 'B': /* bit string (descending) */
{
int byte = 0;
long i, j = 0;
if (len > plen) {
j = (len - plen + 1)/2;
len = plen;
}
for (i=0; i++ < len; ptr++) {
byte |= *ptr & 1;
if (i & 7)
byte <<= 1;
else {
char c = byte & 0xff;
rb_str_buf_cat(res, &c, 1);
byte = 0;
}
}
if (len & 7) {
char c;
byte <<= 7 - (len & 7);
c = byte & 0xff;
rb_str_buf_cat(res, &c, 1);
}
len = j;
goto grow;
}
break;
case 'h': /* hex string (low nibble first) */
{
int byte = 0;
long i, j = 0;
if (len > plen) {
j = (len + 1) / 2 - (plen + 1) / 2;
len = plen;
}
for (i=0; i++ < len; ptr++) {
if (ISALPHA(*ptr))
byte |= (((*ptr & 15) + 9) & 15) << 4;
else
byte |= (*ptr & 15) << 4;
if (i & 1)
byte >>= 4;
else {
char c = byte & 0xff;
rb_str_buf_cat(res, &c, 1);
byte = 0;
}
}
if (len & 1) {
char c = byte & 0xff;
rb_str_buf_cat(res, &c, 1);
}
len = j;
goto grow;
}
break;
case 'H': /* hex string (high nibble first) */
{
int byte = 0;
long i, j = 0;
if (len > plen) {
j = (len + 1) / 2 - (plen + 1) / 2;
len = plen;
}
for (i=0; i++ < len; ptr++) {
if (ISALPHA(*ptr))
byte |= ((*ptr & 15) + 9) & 15;
else
byte |= *ptr & 15;
if (i & 1)
byte <<= 4;
else {
char c = byte & 0xff;
rb_str_buf_cat(res, &c, 1);
byte = 0;
}
}
if (len & 1) {
char c = byte & 0xff;
rb_str_buf_cat(res, &c, 1);
}
len = j;
goto grow;
}
break;
}
break;
case 'c': /* signed char */
case 'C': /* unsigned char */
while (len-- > 0) {
char c;
from = NEXTFROM;
c = (char)num2i32(from);
rb_str_buf_cat(res, &c, sizeof(char));
}
break;
case 's': /* signed short */
signed_p = 1;
integer_size = NATINT_LEN(short, 2);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'S': /* unsigned short */
signed_p = 0;
integer_size = NATINT_LEN(short, 2);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'i': /* signed int */
signed_p = 1;
integer_size = (int)sizeof(int);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'I': /* unsigned int */
signed_p = 0;
integer_size = (int)sizeof(int);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'l': /* signed long */
signed_p = 1;
integer_size = NATINT_LEN(long, 4);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'L': /* unsigned long */
signed_p = 0;
integer_size = NATINT_LEN(long, 4);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'q': /* signed quad (64bit) int */
signed_p = 1;
integer_size = 8;
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'Q': /* unsigned quad (64bit) int */
signed_p = 0;
integer_size = 8;
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'n': /* unsigned short (network byte-order) */
signed_p = 0;
integer_size = 2;
bigendian_p = 1;
goto pack_integer;
case 'N': /* unsigned long (network byte-order) */
signed_p = 0;
integer_size = 4;
bigendian_p = 1;
goto pack_integer;
case 'v': /* unsigned short (VAX byte-order) */
signed_p = 0;
integer_size = 2;
bigendian_p = 0;
goto pack_integer;
case 'V': /* unsigned long (VAX byte-order) */
signed_p = 0;
integer_size = 4;
bigendian_p = 0;
goto pack_integer;
pack_integer:
switch (integer_size) {
#if defined(HAVE_INT16_T) && !defined(FORCE_BIG_PACK)
case SIZEOF_INT16_T:
while (len-- > 0) {
union {
int16_t i;
char a[sizeof(int16_t)];
} v;
from = NEXTFROM;
v.i = (int16_t)num2i32(from);
if (bigendian_p != BIGENDIAN_P()) v.i = swap16(v.i);
rb_str_buf_cat(res, v.a, sizeof(int16_t));
}
break;
#endif
#if defined(HAVE_INT32_T) && !defined(FORCE_BIG_PACK)
case SIZEOF_INT32_T:
while (len-- > 0) {
union {
int32_t i;
char a[sizeof(int32_t)];
} v;
from = NEXTFROM;
v.i = (int32_t)num2i32(from);
if (bigendian_p != BIGENDIAN_P()) v.i = swap32(v.i);
rb_str_buf_cat(res, v.a, sizeof(int32_t));
}
break;
#endif
#if defined(HAVE_INT64_T) && SIZEOF_LONG == SIZEOF_INT64_T && !defined(FORCE_BIG_PACK)
case SIZEOF_INT64_T:
while (len-- > 0) {
union {
int64_t i;
char a[sizeof(int64_t)];
} v;
from = NEXTFROM;
v.i = num2i32(from); /* can return 64bit value if SIZEOF_LONG == SIZEOF_INT64_T */
if (bigendian_p != BIGENDIAN_P()) v.i = swap64(v.i);
rb_str_buf_cat(res, v.a, sizeof(int64_t));
}
break;
#endif
default:
if (integer_size > MAX_INTEGER_PACK_SIZE)
rb_bug("unexpected intger size for pack: %d", integer_size);
while (len-- > 0) {
union {
unsigned long i[(MAX_INTEGER_PACK_SIZE+SIZEOF_LONG-1)/SIZEOF_LONG];
char a[(MAX_INTEGER_PACK_SIZE+SIZEOF_LONG-1)/SIZEOF_LONG*SIZEOF_LONG];
} v;
int num_longs = (integer_size+SIZEOF_LONG-1)/SIZEOF_LONG;
int i;
from = NEXTFROM;
rb_big_pack(from, v.i, num_longs);
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]);
}
rb_str_buf_cat(res,
bigendian_p ?
v.a + sizeof(long)*num_longs - integer_size :
v.a,
integer_size);
}
break;
}
break;
case 'f': /* single precision float in native format */
case 'F': /* ditto */
while (len-- > 0) {
float f;
from = NEXTFROM;
f = (float)RFLOAT_VALUE(rb_to_float(from));
rb_str_buf_cat(res, (char*)&f, sizeof(float));
}
break;
case 'e': /* single precision float in VAX byte-order */
while (len-- > 0) {
float f;
FLOAT_CONVWITH(ftmp);
from = NEXTFROM;
f = (float)RFLOAT_VALUE(rb_to_float(from));
f = HTOVF(f,ftmp);
rb_str_buf_cat(res, (char*)&f, sizeof(float));
}
break;
case 'E': /* double precision float in VAX byte-order */
while (len-- > 0) {
double d;
DOUBLE_CONVWITH(dtmp);
from = NEXTFROM;
d = RFLOAT_VALUE(rb_to_float(from));
d = HTOVD(d,dtmp);
rb_str_buf_cat(res, (char*)&d, sizeof(double));
}
break;
case 'd': /* double precision float in native format */
case 'D': /* ditto */
while (len-- > 0) {
double d;
from = NEXTFROM;
d = RFLOAT_VALUE(rb_to_float(from));
rb_str_buf_cat(res, (char*)&d, sizeof(double));
}
break;
case 'g': /* single precision float in network byte-order */
while (len-- > 0) {
float f;
FLOAT_CONVWITH(ftmp);
from = NEXTFROM;
f = (float)RFLOAT_VALUE(rb_to_float(from));
f = HTONF(f,ftmp);
rb_str_buf_cat(res, (char*)&f, sizeof(float));
}
break;
case 'G': /* double precision float in network byte-order */
while (len-- > 0) {
double d;
DOUBLE_CONVWITH(dtmp);
from = NEXTFROM;
d = RFLOAT_VALUE(rb_to_float(from));
d = HTOND(d,dtmp);
rb_str_buf_cat(res, (char*)&d, sizeof(double));
}
break;
case 'x': /* null byte */
grow:
while (len >= 10) {
rb_str_buf_cat(res, nul10, 10);
len -= 10;
}
rb_str_buf_cat(res, nul10, len);
break;
case 'X': /* back up byte */
shrink:
plen = RSTRING_LEN(res);
if (plen < len)
rb_raise(rb_eArgError, "X outside of string");
rb_str_set_len(res, plen - len);
break;
case '@': /* null fill to absolute position */
len -= RSTRING_LEN(res);
if (len > 0) goto grow;
len = -len;
if (len > 0) goto shrink;
break;
case '%':
rb_raise(rb_eArgError, "%% is not supported");
break;
case 'U': /* Unicode character */
while (len-- > 0) {
SIGNED_VALUE l;
char buf[8];
int le;
from = NEXTFROM;
from = rb_to_int(from);
l = NUM2LONG(from);
if (l < 0) {
rb_raise(rb_eRangeError, "pack(U): value out of range");
}
le = rb_uv_to_utf8(buf, l);
rb_str_buf_cat(res, (char*)buf, le);
}
break;
case 'u': /* uuencoded string */
case 'm': /* base64 encoded string */
from = NEXTFROM;
StringValue(from);
ptr = RSTRING_PTR(from);
plen = RSTRING_LEN(from);
if (len == 0 && type == 'm') {
encodes(res, ptr, plen, type, 0);
ptr += plen;
break;
}
if (len <= 2)
len = 45;
else
len = len / 3 * 3;
while (plen > 0) {
long todo;
if (plen > len)
todo = len;
else
todo = plen;
encodes(res, ptr, todo, type, 1);
plen -= todo;
ptr += todo;
}
break;
case 'M': /* quoted-printable encoded string */
from = rb_obj_as_string(NEXTFROM);
if (len <= 1)
len = 72;
qpencode(res, from, len);
break;
case 'P': /* pointer to packed byte string */
from = THISFROM;
if (!NIL_P(from)) {
StringValue(from);
if (RSTRING_LEN(from) < len) {
rb_raise(rb_eArgError, "too short buffer for P(%ld for %ld)",
RSTRING_LEN(from), len);
}
}
len = 1;
/* FALL THROUGH */
case 'p': /* pointer to string */
while (len-- > 0) {
char *t;
from = NEXTFROM;
if (NIL_P(from)) {
t = 0;
}
else {
t = StringValuePtr(from);
}
if (!associates) {
associates = rb_ary_new();
}
rb_ary_push(associates, from);
rb_obj_taint(from);
rb_str_buf_cat(res, (char*)&t, sizeof(char*));
}
break;
case 'w': /* BER compressed integer */
while (len-- > 0) {
unsigned long ul;
VALUE buf = rb_str_new(0, 0);
char c, *bufs, *bufe;
from = NEXTFROM;
if (TYPE(from) == T_BIGNUM) {
VALUE big128 = rb_uint2big(128);
while (TYPE(from) == T_BIGNUM) {
from = rb_big_divmod(from, big128);
c = NUM2INT(RARRAY_PTR(from)[1]) | 0x80; /* mod */
rb_str_buf_cat(buf, &c, sizeof(char));
from = RARRAY_PTR(from)[0]; /* div */
}
}
{
long l = NUM2LONG(from);
if (l < 0) {
rb_raise(rb_eArgError, "can't compress negative numbers");
}
ul = l;
}
while (ul) {
c = (char)(ul & 0x7f) | 0x80;
rb_str_buf_cat(buf, &c, sizeof(char));
ul >>= 7;
}
if (RSTRING_LEN(buf)) {
bufs = RSTRING_PTR(buf);
bufe = bufs + RSTRING_LEN(buf) - 1;
*bufs &= 0x7f; /* clear continue bit */
while (bufs < bufe) { /* reverse */
c = *bufs;
*bufs++ = *bufe;
*bufe-- = c;
}
rb_str_buf_cat(res, RSTRING_PTR(buf), RSTRING_LEN(buf));
}
else {
c = 0;
rb_str_buf_cat(res, &c, sizeof(char));
}
}
break;
default:
break;
}
}
if (associates) {
rb_str_associate(res, associates);
}
OBJ_INFECT(res, fmt);
switch (enc_info) {
case 1:
ENCODING_CODERANGE_SET(res, rb_usascii_encindex(), ENC_CODERANGE_7BIT);
break;
case 2:
rb_enc_set_index(res, rb_utf8_encindex());
break;
default:
/* do nothing, keep ASCII-8BIT */
break;
}
return res;
}
|