Method: Array#pack
- Defined in:
- pack.c
#pack(fmt) ⇒ 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 (unsigned char)
S | Integer | 16-bit unsigned, native endian (uint16_t)
L | Integer | 32-bit unsigned, native endian (uint32_t)
Q | Integer | 64-bit unsigned, native endian (uint64_t)
J | Integer | pointer width unsigned, native endian (uintptr_t)
| | (J is available since Ruby 2.3.)
| |
c | Integer | 8-bit signed (signed char)
s | Integer | 16-bit signed, native endian (int16_t)
l | Integer | 32-bit signed, native endian (int32_t)
q | Integer | 64-bit signed, native endian (int64_t)
j | Integer | pointer width signed, native endian (intptr_t)
| | (j is available since Ruby 2.3.)
| |
S_, S! | Integer | unsigned short, native endian
I, I_, I! | Integer | unsigned int, native endian
L_, L! | Integer | unsigned long, native endian
Q_, Q! | Integer | unsigned long long, native endian (ArgumentError
| | if the platform has no long long type.)
| | (Q_ and Q! is available since Ruby 2.1.)
J! | Integer | uintptr_t, native endian (same with J)
| | (J! is available since Ruby 2.3.)
| |
s_, s! | Integer | signed short, native endian
i, i_, i! | Integer | signed int, native endian
l_, l! | Integer | signed long, native endian
q_, q! | Integer | signed long long, native endian (ArgumentError
| | if the platform has no long long type.)
| | (q_ and q! is available since Ruby 2.1.)
j! | Integer | intptr_t, native endian (same with j)
| | (j! is available since Ruby 2.3.)
| |
S> L> Q> | Integer | same as the directives without ">" except
J> s> l> | | big endian
q> j> | | (available since Ruby 1.9.3)
S!> I!> | | "S>" is same as "n"
L!> Q!> | | "L>" is same as "N"
J!> s!> | |
i!> l!> | |
q!> j!> | |
| |
S< L< Q< | Integer | same as the directives without "<" except
J< s< l< | | little endian
q< j< | | (available since Ruby 1.9.3)
S!< I!< | | "S<" is same as "v"
L!< Q!< | | "L<" is same as "V"
J!< s!< | |
i!< l!< | |
q!< j!< | |
| |
n | Integer | 16-bit unsigned, network (big-endian) byte order
N | Integer | 32-bit unsigned, network (big-endian) byte order
v | Integer | 16-bit unsigned, VAX (little-endian) byte order
V | Integer | 32-bit unsigned, VAX (little-endian) byte order
| |
U | Integer | UTF-8 character
w | Integer | BER-compressed integer
Float | |
Directive | | Meaning
---------------------------------------------------------------------------
D, d | Float | double-precision, native format
F, f | Float | single-precision, native format
E | Float | double-precision, little-endian byte order
e | Float | single-precision, little-endian byte order
G | Float | double-precision, network (big-endian) byte order
g | Float | single-precision, 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
356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 |
# File 'pack.c', line 356
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 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 integer_size, bigendian_p;
StringValue(fmt);
p = RSTRING_PTR(fmt);
pend = p + RSTRING_LEN(fmt);
res = rb_str_buf_new(0);
idx = 0;
#define TOO_FEW (rb_raise(rb_eArgError, toofew), 0)
#define MORE_ITEM (idx < RARRAY_LEN(ary))
#define THISFROM (MORE_ITEM ? RARRAY_AREF(ary, idx) : TOO_FEW)
#define NEXTFROM (MORE_ITEM ? RARRAY_AREF(ary, idx++) : TOO_FEW)
while (p < pend) {
int explicit_endian = 0;
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;
}
{
modifiers:
switch (*p) {
case '_':
case '!':
if (strchr(natstr, type)) {
#ifdef NATINT_PACK
natint = 1;
#endif
p++;
}
else {
rb_raise(rb_eArgError, "'%c' allowed only after types %s", *p, natstr);
}
goto modifiers;
case '<':
case '>':
if (!strchr(endstr, type)) {
rb_raise(rb_eArgError, "'%c' allowed only after types %s", *p, endstr);
}
if (explicit_endian) {
rb_raise(rb_eRangeError, "Can't use both '<' and '>'");
}
explicit_endian = *p++;
goto modifiers;
}
}
if (*p == '*') { /* set data length */
len = strchr("@Xxu", type) ? 0
: strchr("PMm", type) ? 1
: RARRAY_LEN(ary) - idx;
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;
#define castchar(from) (char)((from) & 0xff)
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 = castchar(byte);
rb_str_buf_cat(res, &c, 1);
byte = 0;
}
}
if (len & 7) {
char c;
byte >>= 7 - (len & 7);
c = castchar(byte);
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 = castchar(byte);
rb_str_buf_cat(res, &c, 1);
byte = 0;
}
}
if (len & 7) {
char c;
byte <<= 7 - (len & 7);
c = castchar(byte);
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 = castchar(byte);
rb_str_buf_cat(res, &c, 1);
byte = 0;
}
}
if (len & 1) {
char c = castchar(byte);
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 = castchar(byte);
rb_str_buf_cat(res, &c, 1);
byte = 0;
}
}
if (len & 1) {
char c = castchar(byte);
rb_str_buf_cat(res, &c, 1);
}
len = j;
goto grow;
}
break;
}
break;
case 'c': /* signed char */
case 'C': /* unsigned char */
integer_size = 1;
bigendian_p = BIGENDIAN_P(); /* not effective */
goto pack_integer;
case 's': /* s for int16_t, s! for signed short */
integer_size = NATINT_LEN(short, 2);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'S': /* S for uint16_t, S! for unsigned short */
integer_size = NATINT_LEN(short, 2);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'i': /* i and i! for signed int */
integer_size = (int)sizeof(int);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'I': /* I and I! for unsigned int */
integer_size = (int)sizeof(int);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'l': /* l for int32_t, l! for signed long */
integer_size = NATINT_LEN(long, 4);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'L': /* L for uint32_t, L! for unsigned long */
integer_size = NATINT_LEN(long, 4);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'q': /* q for int64_t, q! for signed long long */
integer_size = NATINT_LEN_Q;
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'Q': /* Q for uint64_t, Q! for unsigned long long */
integer_size = NATINT_LEN_Q;
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'j': /* j for intptr_t */
integer_size = sizeof(intptr_t);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'J': /* J for uintptr_t */
integer_size = sizeof(uintptr_t);
bigendian_p = BIGENDIAN_P();
goto pack_integer;
case 'n': /* 16 bit (2 bytes) integer (network byte-order) */
integer_size = 2;
bigendian_p = 1;
goto pack_integer;
case 'N': /* 32 bit (4 bytes) integer (network byte-order) */
integer_size = 4;
bigendian_p = 1;
goto pack_integer;
case 'v': /* 16 bit (2 bytes) integer (VAX byte-order) */
integer_size = 2;
bigendian_p = 0;
goto pack_integer;
case 'V': /* 32 bit (4 bytes) integer (VAX byte-order) */
integer_size = 4;
bigendian_p = 0;
goto pack_integer;
pack_integer:
if (explicit_endian) {
bigendian_p = explicit_endian == '>';
}
if (integer_size > MAX_INTEGER_PACK_SIZE)
rb_bug("unexpected intger size for pack: %d", integer_size);
while (len-- > 0) {
char intbuf[MAX_INTEGER_PACK_SIZE];
from = NEXTFROM;
rb_integer_pack(from, intbuf, integer_size, 1, 0,
INTEGER_PACK_2COMP |
(bigendian_p ? INTEGER_PACK_BIG_ENDIAN : INTEGER_PACK_LITTLE_ENDIAN));
rb_str_buf_cat(res, intbuf, integer_size);
}
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 if (len > 63 && type == 'u')
len = 63;
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);
rb_obj_taint(from);
}
if (!associates) {
associates = rb_ary_new();
}
rb_ary_push(associates, from);
rb_str_buf_cat(res, (char*)&t, sizeof(char*));
}
break;
case 'w': /* BER compressed integer */
while (len-- > 0) {
VALUE buf = rb_str_new(0, 0);
size_t numbytes;
int sign;
char *cp;
from = NEXTFROM;
from = rb_to_int(from);
numbytes = rb_absint_numwords(from, 7, NULL);
if (numbytes == 0)
numbytes = 1;
buf = rb_str_new(NULL, numbytes);
sign = rb_integer_pack(from, RSTRING_PTR(buf), RSTRING_LEN(buf), 1, 1, INTEGER_PACK_BIG_ENDIAN);
if (sign < 0)
rb_raise(rb_eArgError, "can't compress negative numbers");
if (sign == 2)
rb_bug("buffer size problem?");
cp = RSTRING_PTR(buf);
while (1 < numbytes) {
*cp |= 0x80;
cp++;
numbytes--;
}
rb_str_buf_cat(res, RSTRING_PTR(buf), RSTRING_LEN(buf));
}
break;
default: {
char unknown[5];
if (ISPRINT(type)) {
unknown[0] = type;
unknown[1] = '\0';
}
else {
snprintf(unknown, sizeof(unknown), "\\x%.2x", type & 0xff);
}
rb_warning("unknown pack directive '%s' in '% "PRIsVALUE"'",
unknown, fmt);
break;
}
}
}
if (associates) {
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;
}
|