ruby/pack.c

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

1746 строки
52 KiB
C
Исходник Обычный вид История

/**********************************************************************
pack.c -
$Author$
created at: Thu Feb 10 15:17:05 JST 1994
* encoding.c: provide basic features for M17N. * parse.y: encoding aware parsing. * parse.y (pragma_encoding): encoding specification pragma. * parse.y (rb_intern3): encoding specified symbols. * string.c (rb_str_length): length based on characters. for older behavior, bytesize method added. * string.c (rb_str_index_m): index based on characters. rindex as well. * string.c (succ_char): encoding aware succeeding string. * string.c (rb_str_reverse): reverse based on characters. * string.c (rb_str_inspect): encoding aware string description. * string.c (rb_str_upcase_bang): encoding aware case conversion. downcase, capitalize, swapcase as well. * string.c (rb_str_tr_bang): tr based on characters. delete, squeeze, tr_s, count as well. * string.c (rb_str_split_m): split based on characters. * string.c (rb_str_each_line): encoding aware each_line. * string.c (rb_str_each_char): added. iteration based on characters. * string.c (rb_str_strip_bang): encoding aware whitespace stripping. lstrip, rstrip as well. * string.c (rb_str_justify): encoding aware justifying (ljust, rjust, center). * string.c (str_encoding): get encoding attribute from a string. * re.c (rb_reg_initialize): encoding aware regular expression * sprintf.c (rb_str_format): formatting (i.e. length count) based on characters. * io.c (rb_io_getc): getc to return one-character string. for older behavior, getbyte method added. * ext/stringio/stringio.c (strio_getc): ditto. * io.c (rb_io_ungetc): allow pushing arbitrary string at the current reading point. * ext/stringio/stringio.c (strio_ungetc): ditto. * ext/strscan/strscan.c: encoding support. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@13261 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-08-25 07:29:39 +04:00
Copyright (C) 1993-2007 Yukihiro Matsumoto
**********************************************************************/
#include "ruby/internal/config.h"
#include <ctype.h>
#include <errno.h>
#include <float.h>
#include <sys/types.h>
#include "internal.h"
#include "internal/array.h"
#include "internal/bits.h"
#include "internal/string.h"
#include "internal/symbol.h"
#include "internal/variable.h"
#include "ruby/util.h"
2019-11-08 05:54:39 +03:00
#include "builtin.h"
/*
* It is intentional that the condition for natstr is HAVE_TRUE_LONG_LONG
* instead of HAVE_LONG_LONG or LONG_LONG.
* This means q! and Q! means always the standard long long type and
* causes ArgumentError for platforms which has no long long type,
* even if the platform has an implementation specific 64bit type.
* This behavior is consistent with the document of pack/unpack.
*/
#ifdef HAVE_TRUE_LONG_LONG
static const char natstr[] = "sSiIlLqQjJ";
2023-10-06 07:53:16 +03:00
# define endstr natstr
#else
static const char natstr[] = "sSiIlLjJ";
static const char endstr[] = "sSiIlLqQjJ";
2023-10-06 07:53:16 +03:00
#endif
#ifdef HAVE_TRUE_LONG_LONG
/* It is intentional to use long long instead of LONG_LONG. */
# define NATINT_LEN_Q NATINT_LEN(long long, 8)
#else
# define NATINT_LEN_Q 8
#endif
#if SIZEOF_SHORT != 2 || SIZEOF_LONG != 4 || (defined(HAVE_TRUE_LONG_LONG) && SIZEOF_LONG_LONG != 8)
# define NATINT_PACK
#endif
#ifdef DYNAMIC_ENDIAN
/* for universal binary of NEXTSTEP and MacOS X */
/* useless since autoconf 2.63? */
static int
is_bigendian(void)
{
static int init = 0;
static int endian_value;
char *p;
if (init) return endian_value;
init = 1;
p = (char*)&init;
return endian_value = p[0]?0:1;
}
# define BIGENDIAN_P() (is_bigendian())
#elif defined(WORDS_BIGENDIAN)
# define BIGENDIAN_P() 1
#else
# define BIGENDIAN_P() 0
#endif
#ifdef NATINT_PACK
# define NATINT_LEN(type,len) (natint?(int)sizeof(type):(int)(len))
#else
# define NATINT_LEN(type,len) ((int)sizeof(type))
#endif
typedef union {
float f;
uint32_t u;
char buf[4];
} FLOAT_SWAPPER;
typedef union {
double d;
uint64_t u;
char buf[8];
} DOUBLE_SWAPPER;
#define swapf(x) swap32(x)
#define swapd(x) swap64(x)
#define rb_ntohf(x) (BIGENDIAN_P()?(x):swapf(x))
#define rb_ntohd(x) (BIGENDIAN_P()?(x):swapd(x))
#define rb_htonf(x) (BIGENDIAN_P()?(x):swapf(x))
#define rb_htond(x) (BIGENDIAN_P()?(x):swapd(x))
#define rb_htovf(x) (BIGENDIAN_P()?swapf(x):(x))
#define rb_htovd(x) (BIGENDIAN_P()?swapd(x):(x))
#define rb_vtohf(x) (BIGENDIAN_P()?swapf(x):(x))
#define rb_vtohd(x) (BIGENDIAN_P()?swapd(x):(x))
#define FLOAT_CONVWITH(x) FLOAT_SWAPPER x;
#define HTONF(x) ((x).u = rb_htonf((x).u))
#define HTOVF(x) ((x).u = rb_htovf((x).u))
#define NTOHF(x) ((x).u = rb_ntohf((x).u))
#define VTOHF(x) ((x).u = rb_vtohf((x).u))
#define DOUBLE_CONVWITH(x) DOUBLE_SWAPPER x;
#define HTOND(x) ((x).u = rb_htond((x).u))
#define HTOVD(x) ((x).u = rb_htovd((x).u))
#define NTOHD(x) ((x).u = rb_ntohd((x).u))
#define VTOHD(x) ((x).u = rb_vtohd((x).u))
#define MAX_INTEGER_PACK_SIZE 8
static const char toofew[] = "too few arguments";
static void encodes(VALUE,const char*,long,int,int);
static void qpencode(VALUE,VALUE,long);
static unsigned long utf8_to_uv(const char*,long*);
static ID id_associated;
static void
str_associate(VALUE str, VALUE add)
{
/* assert(NIL_P(rb_attr_get(str, id_associated))); */
rb_ivar_set(str, id_associated, add);
}
static VALUE
str_associated(VALUE str)
{
2021-10-22 19:38:45 +03:00
VALUE associates = rb_ivar_lookup(str, id_associated, Qfalse);
if (!associates)
rb_raise(rb_eArgError, "no associated pointer");
return associates;
}
static VALUE
associated_pointer(VALUE associates, const char *t)
{
const VALUE *p = RARRAY_CONST_PTR(associates);
const VALUE *pend = p + RARRAY_LEN(associates);
for (; p < pend; p++) {
VALUE tmp = *p;
if (RB_TYPE_P(tmp, T_STRING) && RSTRING_PTR(tmp) == t) return tmp;
}
rb_raise(rb_eArgError, "non associated pointer");
UNREACHABLE_RETURN(Qnil);
}
RBIMPL_ATTR_NORETURN()
static void
unknown_directive(const char *mode, char type, VALUE fmt)
{
char unknown[5];
if (ISPRINT(type)) {
unknown[0] = type;
unknown[1] = '\0';
}
else {
snprintf(unknown, sizeof(unknown), "\\x%.2x", type & 0xff);
}
fmt = rb_str_quote_unprintable(fmt);
rb_raise(rb_eArgError, "unknown %s directive '%s' in '%"PRIsVALUE"'",
mode, unknown, fmt);
}
static float
VALUE_to_float(VALUE obj)
{
VALUE v = rb_to_float(obj);
double d = RFLOAT_VALUE(v);
if (isnan(d)) {
return NAN;
}
else if (d < -FLT_MAX) {
return -INFINITY;
}
else if (d <= FLT_MAX) {
return d;
}
else {
return INFINITY;
}
}
static VALUE
2019-11-08 05:54:39 +03:00
pack_pack(rb_execution_context_t *ec, VALUE ary, VALUE fmt, VALUE buffer)
{
static const char nul10[] = "\0\0\0\0\0\0\0\0\0\0";
static const char spc10[] = " ";
const char *p, *pend;
2019-11-08 05:54:39 +03:00
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;
* eval.c (block_pass): should not downgrade safe level. * ext/dbm/extconf.rb: allow specifying dbm-type explicitly. * ext/dbm/extconf.rb: avoid gdbm if possible, because it leaks memory, whereas gdbm.so doesn't. potential incompatibility. * string.c (rb_str_insert): new method. * parse.y (yylex): lex_state after RESCUE_MOD should be EXPR_BEG. * array.c (rb_ary_insert): new method. * array.c (rb_ary_update): new utility function. * io.c (set_outfile): should check if closed before assignment. * eval.c (rb_eval): should preserve value of ruby_errinfo. * eval.c (rb_thread_schedule): infinite sleep should not cause dead lock. * array.c (rb_ary_flatten_bang): proper recursive detection. * eval.c (yield_under): need not to prohibit at safe level 4. * pack.c (pack_pack): p/P packs nil into NULL. * pack.c (pack_unpack): p/P unpacks NULL into nil. * pack.c (pack_pack): size check for P template. * ruby.c (set_arg0): wrong predicate when new $0 value is bigger than original space. * gc.c (id2ref): should use NUM2ULONG() * object.c (rb_mod_const_get): check whether name is a class variable name. * object.c (rb_mod_const_set): ditto. * object.c (rb_mod_const_defined): ditto. * marshal.c (w_float): precision changed to "%.16g" * eval.c (rb_call0): wrong retry behavior. * numeric.c (fix_aref): a bug on long>int architecture. * eval.c (rb_eval_string_wrap): should restore ruby_wrapper. * regex.c (re_compile_pattern): char class at either edge of range should be invalid. * eval.c (handle_rescue): use === to compare exception match. * error.c (syserr_eqq): comparison between SytemCallErrors should based on their error numbers. * eval.c (safe_getter): should use INT2NUM(). * bignum.c (rb_big2long): 2**31 cannot fit in 31 bit long. * regex.c (calculate_must_string): wrong length calculation. * eval.c (rb_thread_start_0): fixed memory leak. * parse.y (none): should clear cmdarg_stack too. * io.c (rb_fopen): use setvbuf() to avoid recursive malloc() on some platforms. * file.c (rb_stat_dev): device functions should honor stat field types (except long long such as dev_t). * eval.c (rb_mod_nesting): should not push nil for nesting array. * eval.c (rb_mod_s_constants): should not search array by rb_mod_const_at() for nil (happens for singleton class). * class.c (rb_singleton_class_attached): should modify iv_tbl by itself, no longer use rb_iv_set() to avoid freeze check error. * variable.c (rb_const_get): error message "uninitialized constant Foo at Bar::Baz" instead of "uninitialized constantBar::Baz::Foo". * eval.c (rb_mod_included): new hook called from rb_mod_include(). * io.c (opt_i_set): should strdup() inplace_edit string. * eval.c (exec_under): need to push cref too. * eval.c (rb_f_missing): raise NameError for "undefined local variable or method". * error.c (Init_Exception): new exception NoMethodError. NameError moved under ScriptError again. * eval.c (rb_f_missing): use NoMethodError instead of NameError. * file.c (Init_File): should redifine "new" class method. * eval.c (PUSH_CREF): sharing cref node was problematic. maintain runtime cref list instead. * eval.c (rb_eval): copy defn node before registering. * eval.c (rb_load): clear ruby_cref before loading. * variable.c (rb_const_get): no recursion to show full class path for modules. * eval.c (rb_set_safe_level): should set safe level in curr_thread as well. * eval.c (safe_setter): ditto. * object.c (rb_obj_is_instance_of): nil belongs to false, not true. * time.c (make_time_t): proper (I hope) daylight saving time handling for both US and Europe. I HATE DST! * eval.c (rb_thread_wait_for): non blocked signal interrupt should stop the interval. * eval.c (proc_eq): class check aded. * eval.c (proc_eq): typo fixed ("return" was ommitted). * error.c (Init_Exception): move NameError under StandardError. * class.c (rb_mod_clone): should copy method bodies too. * bignum.c (bigdivrem): should trim trailing zero bdigits of remainder, even if dd == 0. * file.c (check3rdbyte): safe string check moved here. * time.c (make_time_t): remove HAVE_TM_ZONE code since it sometimes reports wrong time. * time.c (make_time_t): remove unnecessary range check for platforms where negative time_t is available. * process.c (proc_waitall): should push Process::Status instead of Finuxm status. * process.c (waitall_each): should add all entries in pid_tbl. these changes are inspired by Koji Arai. Thanks. * process.c (proc_wait): should not iterate if pid_tbl is 0. * process.c (proc_waitall): ditto. * numeric.c (flodivmod): a bug in no fmod case. * process.c (pst_wifsignaled): should apply WIFSIGNALED for status (int), not st (VALUE). * io.c (Init_IO): value of $/ and $\ are no longer restricted to strings. type checks are done on demand. * class.c (rb_include_module): module inclusion should be check taints. * ruby.h (STR2CSTR): replace to StringType() and StringTypePtr(). * ruby.h (rb_str2cstr): ditto. * eval.c (rb_load): should not copy topleve local variables. It cause variable/method ambiguity. Thanks to L. Peter Deutsch. * class.c (rb_include_module): freeze check at first. * eval.c (rb_attr): sprintf() and rb_intern() moved into conditional body. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@1356 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2001-05-02 08:22:21 +04:00
StringValue(fmt);
rb_must_asciicompat(fmt);
p = RSTRING_PTR(fmt);
pend = p + RSTRING_LEN(fmt);
2019-11-08 05:54:39 +03:00
if (NIL_P(buffer)) {
res = rb_str_buf_new(0);
}
2019-11-08 05:54:39 +03:00
else {
if (!RB_TYPE_P(buffer, T_STRING))
rb_raise(rb_eTypeError, "buffer must be String, not %s", rb_obj_classname(buffer));
rb_str_modify(buffer);
res = buffer;
2019-11-08 05:54:39 +03:00
}
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;
2022-07-21 19:23:58 +03:00
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;
}
}
2022-07-21 19:23:58 +03:00
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;
}
2022-07-21 19:23:58 +03:00
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 {
* eval.c (block_pass): should not downgrade safe level. * ext/dbm/extconf.rb: allow specifying dbm-type explicitly. * ext/dbm/extconf.rb: avoid gdbm if possible, because it leaks memory, whereas gdbm.so doesn't. potential incompatibility. * string.c (rb_str_insert): new method. * parse.y (yylex): lex_state after RESCUE_MOD should be EXPR_BEG. * array.c (rb_ary_insert): new method. * array.c (rb_ary_update): new utility function. * io.c (set_outfile): should check if closed before assignment. * eval.c (rb_eval): should preserve value of ruby_errinfo. * eval.c (rb_thread_schedule): infinite sleep should not cause dead lock. * array.c (rb_ary_flatten_bang): proper recursive detection. * eval.c (yield_under): need not to prohibit at safe level 4. * pack.c (pack_pack): p/P packs nil into NULL. * pack.c (pack_unpack): p/P unpacks NULL into nil. * pack.c (pack_pack): size check for P template. * ruby.c (set_arg0): wrong predicate when new $0 value is bigger than original space. * gc.c (id2ref): should use NUM2ULONG() * object.c (rb_mod_const_get): check whether name is a class variable name. * object.c (rb_mod_const_set): ditto. * object.c (rb_mod_const_defined): ditto. * marshal.c (w_float): precision changed to "%.16g" * eval.c (rb_call0): wrong retry behavior. * numeric.c (fix_aref): a bug on long>int architecture. * eval.c (rb_eval_string_wrap): should restore ruby_wrapper. * regex.c (re_compile_pattern): char class at either edge of range should be invalid. * eval.c (handle_rescue): use === to compare exception match. * error.c (syserr_eqq): comparison between SytemCallErrors should based on their error numbers. * eval.c (safe_getter): should use INT2NUM(). * bignum.c (rb_big2long): 2**31 cannot fit in 31 bit long. * regex.c (calculate_must_string): wrong length calculation. * eval.c (rb_thread_start_0): fixed memory leak. * parse.y (none): should clear cmdarg_stack too. * io.c (rb_fopen): use setvbuf() to avoid recursive malloc() on some platforms. * file.c (rb_stat_dev): device functions should honor stat field types (except long long such as dev_t). * eval.c (rb_mod_nesting): should not push nil for nesting array. * eval.c (rb_mod_s_constants): should not search array by rb_mod_const_at() for nil (happens for singleton class). * class.c (rb_singleton_class_attached): should modify iv_tbl by itself, no longer use rb_iv_set() to avoid freeze check error. * variable.c (rb_const_get): error message "uninitialized constant Foo at Bar::Baz" instead of "uninitialized constantBar::Baz::Foo". * eval.c (rb_mod_included): new hook called from rb_mod_include(). * io.c (opt_i_set): should strdup() inplace_edit string. * eval.c (exec_under): need to push cref too. * eval.c (rb_f_missing): raise NameError for "undefined local variable or method". * error.c (Init_Exception): new exception NoMethodError. NameError moved under ScriptError again. * eval.c (rb_f_missing): use NoMethodError instead of NameError. * file.c (Init_File): should redifine "new" class method. * eval.c (PUSH_CREF): sharing cref node was problematic. maintain runtime cref list instead. * eval.c (rb_eval): copy defn node before registering. * eval.c (rb_load): clear ruby_cref before loading. * variable.c (rb_const_get): no recursion to show full class path for modules. * eval.c (rb_set_safe_level): should set safe level in curr_thread as well. * eval.c (safe_setter): ditto. * object.c (rb_obj_is_instance_of): nil belongs to false, not true. * time.c (make_time_t): proper (I hope) daylight saving time handling for both US and Europe. I HATE DST! * eval.c (rb_thread_wait_for): non blocked signal interrupt should stop the interval. * eval.c (proc_eq): class check aded. * eval.c (proc_eq): typo fixed ("return" was ommitted). * error.c (Init_Exception): move NameError under StandardError. * class.c (rb_mod_clone): should copy method bodies too. * bignum.c (bigdivrem): should trim trailing zero bdigits of remainder, even if dd == 0. * file.c (check3rdbyte): safe string check moved here. * time.c (make_time_t): remove HAVE_TM_ZONE code since it sometimes reports wrong time. * time.c (make_time_t): remove unnecessary range check for platforms where negative time_t is available. * process.c (proc_waitall): should push Process::Status instead of Finuxm status. * process.c (waitall_each): should add all entries in pid_tbl. these changes are inspired by Koji Arai. Thanks. * process.c (proc_wait): should not iterate if pid_tbl is 0. * process.c (proc_waitall): ditto. * numeric.c (flodivmod): a bug in no fmod case. * process.c (pst_wifsignaled): should apply WIFSIGNALED for status (int), not st (VALUE). * io.c (Init_IO): value of $/ and $\ are no longer restricted to strings. type checks are done on demand. * class.c (rb_include_module): module inclusion should be check taints. * ruby.h (STR2CSTR): replace to StringType() and StringTypePtr(). * ruby.h (rb_str2cstr): ditto. * eval.c (rb_load): should not copy topleve local variables. It cause variable/method ambiguity. Thanks to L. Peter Deutsch. * class.c (rb_include_module): freeze check at first. * eval.c (rb_attr): sprintf() and rb_intern() moved into conditional body. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@1356 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2001-05-02 08:22:21 +04:00
StringValue(from);
ptr = RSTRING_PTR(from);
plen = RSTRING_LEN(from);
}
2022-07-21 19:23:58 +03:00
if (p[-1] == '*')
len = plen;
2022-07-21 19:23:58 +03:00
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;
2022-07-21 19:23:58 +03:00
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;
2022-07-21 19:23:58 +03:00
case 'B': /* bit string (descending) */
{
int byte = 0;
long i, j = 0;
2022-07-21 19:23:58 +03:00
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;
2022-07-21 19:23:58 +03:00
case 'h': /* hex string (low nibble first) */
{
int byte = 0;
long i, j = 0;
2022-07-21 19:23:58 +03:00
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;
2022-07-21 19:23:58 +03:00
case 'H': /* hex string (high nibble first) */
{
int byte = 0;
long i, j = 0;
2022-07-21 19:23:58 +03:00
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;
2022-07-21 19:23:58 +03:00
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 */
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 */
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 */
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 */
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)
2023-01-19 18:20:27 +03:00
rb_bug("unexpected integer 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 = VALUE_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_CONVWITH(tmp);
from = NEXTFROM;
tmp.f = VALUE_to_float(from);
HTOVF(tmp);
rb_str_buf_cat(res, tmp.buf, sizeof(float));
}
break;
2022-07-21 19:23:58 +03:00
case 'E': /* double precision float in VAX byte-order */
while (len-- > 0) {
DOUBLE_CONVWITH(tmp);
from = NEXTFROM;
tmp.d = RFLOAT_VALUE(rb_to_float(from));
HTOVD(tmp);
rb_str_buf_cat(res, tmp.buf, sizeof(double));
}
break;
2022-07-21 19:23:58 +03:00
case 'd': /* double precision float in native format */
case 'D': /* ditto */
while (len-- > 0) {
double d;
2022-07-21 19:23:58 +03:00
from = NEXTFROM;
d = RFLOAT_VALUE(rb_to_float(from));
rb_str_buf_cat(res, (char*)&d, sizeof(double));
}
break;
2022-07-21 19:23:58 +03:00
case 'g': /* single precision float in network byte-order */
while (len-- > 0) {
FLOAT_CONVWITH(tmp);
from = NEXTFROM;
tmp.f = VALUE_to_float(from);
HTONF(tmp);
rb_str_buf_cat(res, tmp.buf, sizeof(float));
}
break;
2022-07-21 19:23:58 +03:00
case 'G': /* double precision float in network byte-order */
while (len-- > 0) {
DOUBLE_CONVWITH(tmp);
2022-07-21 19:23:58 +03:00
from = NEXTFROM;
tmp.d = RFLOAT_VALUE(rb_to_float(from));
HTOND(tmp);
rb_str_buf_cat(res, tmp.buf, sizeof(double));
}
break;
2022-07-21 19:23:58 +03:00
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;
2022-07-21 19:23:58 +03:00
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;
2022-07-21 19:23:58 +03:00
case '@': /* null fill to absolute position */
len -= RSTRING_LEN(res);
if (len > 0) goto grow;
len = -len;
if (len > 0) goto shrink;
break;
2022-07-21 19:23:58 +03:00
case '%':
rb_raise(rb_eArgError, "%% is not supported");
break;
2022-07-21 19:23:58 +03:00
case 'U': /* Unicode character */
while (len-- > 0) {
SIGNED_VALUE l;
char buf[8];
int le;
2022-07-21 19:23:58 +03:00
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;
2022-07-21 19:23:58 +03:00
case 'u': /* uuencoded string */
case 'm': /* base64 encoded string */
* eval.c (block_pass): should not downgrade safe level. * ext/dbm/extconf.rb: allow specifying dbm-type explicitly. * ext/dbm/extconf.rb: avoid gdbm if possible, because it leaks memory, whereas gdbm.so doesn't. potential incompatibility. * string.c (rb_str_insert): new method. * parse.y (yylex): lex_state after RESCUE_MOD should be EXPR_BEG. * array.c (rb_ary_insert): new method. * array.c (rb_ary_update): new utility function. * io.c (set_outfile): should check if closed before assignment. * eval.c (rb_eval): should preserve value of ruby_errinfo. * eval.c (rb_thread_schedule): infinite sleep should not cause dead lock. * array.c (rb_ary_flatten_bang): proper recursive detection. * eval.c (yield_under): need not to prohibit at safe level 4. * pack.c (pack_pack): p/P packs nil into NULL. * pack.c (pack_unpack): p/P unpacks NULL into nil. * pack.c (pack_pack): size check for P template. * ruby.c (set_arg0): wrong predicate when new $0 value is bigger than original space. * gc.c (id2ref): should use NUM2ULONG() * object.c (rb_mod_const_get): check whether name is a class variable name. * object.c (rb_mod_const_set): ditto. * object.c (rb_mod_const_defined): ditto. * marshal.c (w_float): precision changed to "%.16g" * eval.c (rb_call0): wrong retry behavior. * numeric.c (fix_aref): a bug on long>int architecture. * eval.c (rb_eval_string_wrap): should restore ruby_wrapper. * regex.c (re_compile_pattern): char class at either edge of range should be invalid. * eval.c (handle_rescue): use === to compare exception match. * error.c (syserr_eqq): comparison between SytemCallErrors should based on their error numbers. * eval.c (safe_getter): should use INT2NUM(). * bignum.c (rb_big2long): 2**31 cannot fit in 31 bit long. * regex.c (calculate_must_string): wrong length calculation. * eval.c (rb_thread_start_0): fixed memory leak. * parse.y (none): should clear cmdarg_stack too. * io.c (rb_fopen): use setvbuf() to avoid recursive malloc() on some platforms. * file.c (rb_stat_dev): device functions should honor stat field types (except long long such as dev_t). * eval.c (rb_mod_nesting): should not push nil for nesting array. * eval.c (rb_mod_s_constants): should not search array by rb_mod_const_at() for nil (happens for singleton class). * class.c (rb_singleton_class_attached): should modify iv_tbl by itself, no longer use rb_iv_set() to avoid freeze check error. * variable.c (rb_const_get): error message "uninitialized constant Foo at Bar::Baz" instead of "uninitialized constantBar::Baz::Foo". * eval.c (rb_mod_included): new hook called from rb_mod_include(). * io.c (opt_i_set): should strdup() inplace_edit string. * eval.c (exec_under): need to push cref too. * eval.c (rb_f_missing): raise NameError for "undefined local variable or method". * error.c (Init_Exception): new exception NoMethodError. NameError moved under ScriptError again. * eval.c (rb_f_missing): use NoMethodError instead of NameError. * file.c (Init_File): should redifine "new" class method. * eval.c (PUSH_CREF): sharing cref node was problematic. maintain runtime cref list instead. * eval.c (rb_eval): copy defn node before registering. * eval.c (rb_load): clear ruby_cref before loading. * variable.c (rb_const_get): no recursion to show full class path for modules. * eval.c (rb_set_safe_level): should set safe level in curr_thread as well. * eval.c (safe_setter): ditto. * object.c (rb_obj_is_instance_of): nil belongs to false, not true. * time.c (make_time_t): proper (I hope) daylight saving time handling for both US and Europe. I HATE DST! * eval.c (rb_thread_wait_for): non blocked signal interrupt should stop the interval. * eval.c (proc_eq): class check aded. * eval.c (proc_eq): typo fixed ("return" was ommitted). * error.c (Init_Exception): move NameError under StandardError. * class.c (rb_mod_clone): should copy method bodies too. * bignum.c (bigdivrem): should trim trailing zero bdigits of remainder, even if dd == 0. * file.c (check3rdbyte): safe string check moved here. * time.c (make_time_t): remove HAVE_TM_ZONE code since it sometimes reports wrong time. * time.c (make_time_t): remove unnecessary range check for platforms where negative time_t is available. * process.c (proc_waitall): should push Process::Status instead of Finuxm status. * process.c (waitall_each): should add all entries in pid_tbl. these changes are inspired by Koji Arai. Thanks. * process.c (proc_wait): should not iterate if pid_tbl is 0. * process.c (proc_waitall): ditto. * numeric.c (flodivmod): a bug in no fmod case. * process.c (pst_wifsignaled): should apply WIFSIGNALED for status (int), not st (VALUE). * io.c (Init_IO): value of $/ and $\ are no longer restricted to strings. type checks are done on demand. * class.c (rb_include_module): module inclusion should be check taints. * ruby.h (STR2CSTR): replace to StringType() and StringTypePtr(). * ruby.h (rb_str2cstr): ditto. * eval.c (rb_load): should not copy topleve local variables. It cause variable/method ambiguity. Thanks to L. Peter Deutsch. * class.c (rb_include_module): freeze check at first. * eval.c (rb_attr): sprintf() and rb_intern() moved into conditional body. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@1356 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2001-05-02 08:22:21 +04:00
from = NEXTFROM;
StringValue(from);
ptr = RSTRING_PTR(from);
plen = RSTRING_LEN(from);
2022-07-21 19:23:58 +03:00
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;
2022-07-21 19:23:58 +03:00
if (plen > len)
todo = len;
else
todo = plen;
encodes(res, ptr, todo, type, 1);
plen -= todo;
ptr += todo;
}
break;
2022-07-21 19:23:58 +03:00
case 'M': /* quoted-printable encoded string */
from = rb_obj_as_string(NEXTFROM);
if (len <= 1)
len = 72;
qpencode(res, from, len);
break;
2022-07-21 19:23:58 +03:00
case 'P': /* pointer to packed byte string */
* eval.c (block_pass): should not downgrade safe level. * ext/dbm/extconf.rb: allow specifying dbm-type explicitly. * ext/dbm/extconf.rb: avoid gdbm if possible, because it leaks memory, whereas gdbm.so doesn't. potential incompatibility. * string.c (rb_str_insert): new method. * parse.y (yylex): lex_state after RESCUE_MOD should be EXPR_BEG. * array.c (rb_ary_insert): new method. * array.c (rb_ary_update): new utility function. * io.c (set_outfile): should check if closed before assignment. * eval.c (rb_eval): should preserve value of ruby_errinfo. * eval.c (rb_thread_schedule): infinite sleep should not cause dead lock. * array.c (rb_ary_flatten_bang): proper recursive detection. * eval.c (yield_under): need not to prohibit at safe level 4. * pack.c (pack_pack): p/P packs nil into NULL. * pack.c (pack_unpack): p/P unpacks NULL into nil. * pack.c (pack_pack): size check for P template. * ruby.c (set_arg0): wrong predicate when new $0 value is bigger than original space. * gc.c (id2ref): should use NUM2ULONG() * object.c (rb_mod_const_get): check whether name is a class variable name. * object.c (rb_mod_const_set): ditto. * object.c (rb_mod_const_defined): ditto. * marshal.c (w_float): precision changed to "%.16g" * eval.c (rb_call0): wrong retry behavior. * numeric.c (fix_aref): a bug on long>int architecture. * eval.c (rb_eval_string_wrap): should restore ruby_wrapper. * regex.c (re_compile_pattern): char class at either edge of range should be invalid. * eval.c (handle_rescue): use === to compare exception match. * error.c (syserr_eqq): comparison between SytemCallErrors should based on their error numbers. * eval.c (safe_getter): should use INT2NUM(). * bignum.c (rb_big2long): 2**31 cannot fit in 31 bit long. * regex.c (calculate_must_string): wrong length calculation. * eval.c (rb_thread_start_0): fixed memory leak. * parse.y (none): should clear cmdarg_stack too. * io.c (rb_fopen): use setvbuf() to avoid recursive malloc() on some platforms. * file.c (rb_stat_dev): device functions should honor stat field types (except long long such as dev_t). * eval.c (rb_mod_nesting): should not push nil for nesting array. * eval.c (rb_mod_s_constants): should not search array by rb_mod_const_at() for nil (happens for singleton class). * class.c (rb_singleton_class_attached): should modify iv_tbl by itself, no longer use rb_iv_set() to avoid freeze check error. * variable.c (rb_const_get): error message "uninitialized constant Foo at Bar::Baz" instead of "uninitialized constantBar::Baz::Foo". * eval.c (rb_mod_included): new hook called from rb_mod_include(). * io.c (opt_i_set): should strdup() inplace_edit string. * eval.c (exec_under): need to push cref too. * eval.c (rb_f_missing): raise NameError for "undefined local variable or method". * error.c (Init_Exception): new exception NoMethodError. NameError moved under ScriptError again. * eval.c (rb_f_missing): use NoMethodError instead of NameError. * file.c (Init_File): should redifine "new" class method. * eval.c (PUSH_CREF): sharing cref node was problematic. maintain runtime cref list instead. * eval.c (rb_eval): copy defn node before registering. * eval.c (rb_load): clear ruby_cref before loading. * variable.c (rb_const_get): no recursion to show full class path for modules. * eval.c (rb_set_safe_level): should set safe level in curr_thread as well. * eval.c (safe_setter): ditto. * object.c (rb_obj_is_instance_of): nil belongs to false, not true. * time.c (make_time_t): proper (I hope) daylight saving time handling for both US and Europe. I HATE DST! * eval.c (rb_thread_wait_for): non blocked signal interrupt should stop the interval. * eval.c (proc_eq): class check aded. * eval.c (proc_eq): typo fixed ("return" was ommitted). * error.c (Init_Exception): move NameError under StandardError. * class.c (rb_mod_clone): should copy method bodies too. * bignum.c (bigdivrem): should trim trailing zero bdigits of remainder, even if dd == 0. * file.c (check3rdbyte): safe string check moved here. * time.c (make_time_t): remove HAVE_TM_ZONE code since it sometimes reports wrong time. * time.c (make_time_t): remove unnecessary range check for platforms where negative time_t is available. * process.c (proc_waitall): should push Process::Status instead of Finuxm status. * process.c (waitall_each): should add all entries in pid_tbl. these changes are inspired by Koji Arai. Thanks. * process.c (proc_wait): should not iterate if pid_tbl is 0. * process.c (proc_waitall): ditto. * numeric.c (flodivmod): a bug in no fmod case. * process.c (pst_wifsignaled): should apply WIFSIGNALED for status (int), not st (VALUE). * io.c (Init_IO): value of $/ and $\ are no longer restricted to strings. type checks are done on demand. * class.c (rb_include_module): module inclusion should be check taints. * ruby.h (STR2CSTR): replace to StringType() and StringTypePtr(). * ruby.h (rb_str2cstr): ditto. * eval.c (rb_load): should not copy topleve local variables. It cause variable/method ambiguity. Thanks to L. Peter Deutsch. * class.c (rb_include_module): freeze check at first. * eval.c (rb_attr): sprintf() and rb_intern() moved into conditional body. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@1356 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2001-05-02 08:22:21 +04:00
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);
* eval.c (block_pass): should not downgrade safe level. * ext/dbm/extconf.rb: allow specifying dbm-type explicitly. * ext/dbm/extconf.rb: avoid gdbm if possible, because it leaks memory, whereas gdbm.so doesn't. potential incompatibility. * string.c (rb_str_insert): new method. * parse.y (yylex): lex_state after RESCUE_MOD should be EXPR_BEG. * array.c (rb_ary_insert): new method. * array.c (rb_ary_update): new utility function. * io.c (set_outfile): should check if closed before assignment. * eval.c (rb_eval): should preserve value of ruby_errinfo. * eval.c (rb_thread_schedule): infinite sleep should not cause dead lock. * array.c (rb_ary_flatten_bang): proper recursive detection. * eval.c (yield_under): need not to prohibit at safe level 4. * pack.c (pack_pack): p/P packs nil into NULL. * pack.c (pack_unpack): p/P unpacks NULL into nil. * pack.c (pack_pack): size check for P template. * ruby.c (set_arg0): wrong predicate when new $0 value is bigger than original space. * gc.c (id2ref): should use NUM2ULONG() * object.c (rb_mod_const_get): check whether name is a class variable name. * object.c (rb_mod_const_set): ditto. * object.c (rb_mod_const_defined): ditto. * marshal.c (w_float): precision changed to "%.16g" * eval.c (rb_call0): wrong retry behavior. * numeric.c (fix_aref): a bug on long>int architecture. * eval.c (rb_eval_string_wrap): should restore ruby_wrapper. * regex.c (re_compile_pattern): char class at either edge of range should be invalid. * eval.c (handle_rescue): use === to compare exception match. * error.c (syserr_eqq): comparison between SytemCallErrors should based on their error numbers. * eval.c (safe_getter): should use INT2NUM(). * bignum.c (rb_big2long): 2**31 cannot fit in 31 bit long. * regex.c (calculate_must_string): wrong length calculation. * eval.c (rb_thread_start_0): fixed memory leak. * parse.y (none): should clear cmdarg_stack too. * io.c (rb_fopen): use setvbuf() to avoid recursive malloc() on some platforms. * file.c (rb_stat_dev): device functions should honor stat field types (except long long such as dev_t). * eval.c (rb_mod_nesting): should not push nil for nesting array. * eval.c (rb_mod_s_constants): should not search array by rb_mod_const_at() for nil (happens for singleton class). * class.c (rb_singleton_class_attached): should modify iv_tbl by itself, no longer use rb_iv_set() to avoid freeze check error. * variable.c (rb_const_get): error message "uninitialized constant Foo at Bar::Baz" instead of "uninitialized constantBar::Baz::Foo". * eval.c (rb_mod_included): new hook called from rb_mod_include(). * io.c (opt_i_set): should strdup() inplace_edit string. * eval.c (exec_under): need to push cref too. * eval.c (rb_f_missing): raise NameError for "undefined local variable or method". * error.c (Init_Exception): new exception NoMethodError. NameError moved under ScriptError again. * eval.c (rb_f_missing): use NoMethodError instead of NameError. * file.c (Init_File): should redifine "new" class method. * eval.c (PUSH_CREF): sharing cref node was problematic. maintain runtime cref list instead. * eval.c (rb_eval): copy defn node before registering. * eval.c (rb_load): clear ruby_cref before loading. * variable.c (rb_const_get): no recursion to show full class path for modules. * eval.c (rb_set_safe_level): should set safe level in curr_thread as well. * eval.c (safe_setter): ditto. * object.c (rb_obj_is_instance_of): nil belongs to false, not true. * time.c (make_time_t): proper (I hope) daylight saving time handling for both US and Europe. I HATE DST! * eval.c (rb_thread_wait_for): non blocked signal interrupt should stop the interval. * eval.c (proc_eq): class check aded. * eval.c (proc_eq): typo fixed ("return" was ommitted). * error.c (Init_Exception): move NameError under StandardError. * class.c (rb_mod_clone): should copy method bodies too. * bignum.c (bigdivrem): should trim trailing zero bdigits of remainder, even if dd == 0. * file.c (check3rdbyte): safe string check moved here. * time.c (make_time_t): remove HAVE_TM_ZONE code since it sometimes reports wrong time. * time.c (make_time_t): remove unnecessary range check for platforms where negative time_t is available. * process.c (proc_waitall): should push Process::Status instead of Finuxm status. * process.c (waitall_each): should add all entries in pid_tbl. these changes are inspired by Koji Arai. Thanks. * process.c (proc_wait): should not iterate if pid_tbl is 0. * process.c (proc_waitall): ditto. * numeric.c (flodivmod): a bug in no fmod case. * process.c (pst_wifsignaled): should apply WIFSIGNALED for status (int), not st (VALUE). * io.c (Init_IO): value of $/ and $\ are no longer restricted to strings. type checks are done on demand. * class.c (rb_include_module): module inclusion should be check taints. * ruby.h (STR2CSTR): replace to StringType() and StringTypePtr(). * ruby.h (rb_str2cstr): ditto. * eval.c (rb_load): should not copy topleve local variables. It cause variable/method ambiguity. Thanks to L. Peter Deutsch. * class.c (rb_include_module): freeze check at first. * eval.c (rb_attr): sprintf() and rb_intern() moved into conditional body. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@1356 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2001-05-02 08:22:21 +04:00
}
}
len = 1;
/* FALL THROUGH */
case 'p': /* pointer to string */
while (len-- > 0) {
char *t;
from = NEXTFROM;
if (NIL_P(from)) {
* eval.c (block_pass): should not downgrade safe level. * ext/dbm/extconf.rb: allow specifying dbm-type explicitly. * ext/dbm/extconf.rb: avoid gdbm if possible, because it leaks memory, whereas gdbm.so doesn't. potential incompatibility. * string.c (rb_str_insert): new method. * parse.y (yylex): lex_state after RESCUE_MOD should be EXPR_BEG. * array.c (rb_ary_insert): new method. * array.c (rb_ary_update): new utility function. * io.c (set_outfile): should check if closed before assignment. * eval.c (rb_eval): should preserve value of ruby_errinfo. * eval.c (rb_thread_schedule): infinite sleep should not cause dead lock. * array.c (rb_ary_flatten_bang): proper recursive detection. * eval.c (yield_under): need not to prohibit at safe level 4. * pack.c (pack_pack): p/P packs nil into NULL. * pack.c (pack_unpack): p/P unpacks NULL into nil. * pack.c (pack_pack): size check for P template. * ruby.c (set_arg0): wrong predicate when new $0 value is bigger than original space. * gc.c (id2ref): should use NUM2ULONG() * object.c (rb_mod_const_get): check whether name is a class variable name. * object.c (rb_mod_const_set): ditto. * object.c (rb_mod_const_defined): ditto. * marshal.c (w_float): precision changed to "%.16g" * eval.c (rb_call0): wrong retry behavior. * numeric.c (fix_aref): a bug on long>int architecture. * eval.c (rb_eval_string_wrap): should restore ruby_wrapper. * regex.c (re_compile_pattern): char class at either edge of range should be invalid. * eval.c (handle_rescue): use === to compare exception match. * error.c (syserr_eqq): comparison between SytemCallErrors should based on their error numbers. * eval.c (safe_getter): should use INT2NUM(). * bignum.c (rb_big2long): 2**31 cannot fit in 31 bit long. * regex.c (calculate_must_string): wrong length calculation. * eval.c (rb_thread_start_0): fixed memory leak. * parse.y (none): should clear cmdarg_stack too. * io.c (rb_fopen): use setvbuf() to avoid recursive malloc() on some platforms. * file.c (rb_stat_dev): device functions should honor stat field types (except long long such as dev_t). * eval.c (rb_mod_nesting): should not push nil for nesting array. * eval.c (rb_mod_s_constants): should not search array by rb_mod_const_at() for nil (happens for singleton class). * class.c (rb_singleton_class_attached): should modify iv_tbl by itself, no longer use rb_iv_set() to avoid freeze check error. * variable.c (rb_const_get): error message "uninitialized constant Foo at Bar::Baz" instead of "uninitialized constantBar::Baz::Foo". * eval.c (rb_mod_included): new hook called from rb_mod_include(). * io.c (opt_i_set): should strdup() inplace_edit string. * eval.c (exec_under): need to push cref too. * eval.c (rb_f_missing): raise NameError for "undefined local variable or method". * error.c (Init_Exception): new exception NoMethodError. NameError moved under ScriptError again. * eval.c (rb_f_missing): use NoMethodError instead of NameError. * file.c (Init_File): should redifine "new" class method. * eval.c (PUSH_CREF): sharing cref node was problematic. maintain runtime cref list instead. * eval.c (rb_eval): copy defn node before registering. * eval.c (rb_load): clear ruby_cref before loading. * variable.c (rb_const_get): no recursion to show full class path for modules. * eval.c (rb_set_safe_level): should set safe level in curr_thread as well. * eval.c (safe_setter): ditto. * object.c (rb_obj_is_instance_of): nil belongs to false, not true. * time.c (make_time_t): proper (I hope) daylight saving time handling for both US and Europe. I HATE DST! * eval.c (rb_thread_wait_for): non blocked signal interrupt should stop the interval. * eval.c (proc_eq): class check aded. * eval.c (proc_eq): typo fixed ("return" was ommitted). * error.c (Init_Exception): move NameError under StandardError. * class.c (rb_mod_clone): should copy method bodies too. * bignum.c (bigdivrem): should trim trailing zero bdigits of remainder, even if dd == 0. * file.c (check3rdbyte): safe string check moved here. * time.c (make_time_t): remove HAVE_TM_ZONE code since it sometimes reports wrong time. * time.c (make_time_t): remove unnecessary range check for platforms where negative time_t is available. * process.c (proc_waitall): should push Process::Status instead of Finuxm status. * process.c (waitall_each): should add all entries in pid_tbl. these changes are inspired by Koji Arai. Thanks. * process.c (proc_wait): should not iterate if pid_tbl is 0. * process.c (proc_waitall): ditto. * numeric.c (flodivmod): a bug in no fmod case. * process.c (pst_wifsignaled): should apply WIFSIGNALED for status (int), not st (VALUE). * io.c (Init_IO): value of $/ and $\ are no longer restricted to strings. type checks are done on demand. * class.c (rb_include_module): module inclusion should be check taints. * ruby.h (STR2CSTR): replace to StringType() and StringTypePtr(). * ruby.h (rb_str2cstr): ditto. * eval.c (rb_load): should not copy topleve local variables. It cause variable/method ambiguity. Thanks to L. Peter Deutsch. * class.c (rb_include_module): freeze check at first. * eval.c (rb_attr): sprintf() and rb_intern() moved into conditional body. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@1356 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2001-05-02 08:22:21 +04:00
t = 0;
}
else {
t = StringValuePtr(from);
}
if (!associates) {
associates = rb_ary_new();
}
rb_ary_push(associates, from);
rb_str_buf_cat(res, (char*)&t, sizeof(char*));
}
break;
2022-07-21 19:23:58 +03:00
case 'w': /* BER compressed integer */
while (len-- > 0) {
VALUE buf = rb_str_new(0, 0);
size_t numbytes;
int sign;
char *cp;
from = NEXTFROM;
from = rb_to_int(from);
numbytes = rb_absint_numwords(from, 7, NULL);
if (numbytes == 0)
numbytes = 1;
buf = rb_str_new(NULL, numbytes);
sign = rb_integer_pack(from, RSTRING_PTR(buf), RSTRING_LEN(buf), 1, 1, INTEGER_PACK_BIG_ENDIAN);
if (sign < 0)
rb_raise(rb_eArgError, "can't compress negative numbers");
if (sign == 2)
rb_bug("buffer size problem?");
cp = RSTRING_PTR(buf);
while (1 < numbytes) {
*cp |= 0x80;
cp++;
numbytes--;
}
rb_str_buf_cat(res, RSTRING_PTR(buf), RSTRING_LEN(buf));
}
break;
default: {
unknown_directive("pack", type, fmt);
break;
}
}
}
if (associates) {
str_associate(res, associates);
}
switch (enc_info) {
case 1:
ENCODING_CODERANGE_SET(res, rb_usascii_encindex(), ENC_CODERANGE_7BIT);
break;
case 2:
rb_enc_set_index(res, rb_utf8_encindex());
break;
default:
/* do nothing, keep ASCII-8BIT */
break;
}
return res;
}
VALUE
rb_ec_pack_ary(rb_execution_context_t *ec, VALUE ary, VALUE fmt, VALUE buffer)
{
return pack_pack(ec, ary, fmt, buffer);
}
static const char uu_table[] =
"`!\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_";
static const char b64_table[] =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
static void
encodes(VALUE str, const char *s0, long len, int type, int tail_lf)
{
enum {buff_size = 4096, encoded_unit = 4, input_unit = 3};
char buff[buff_size + 1]; /* +1 for tail_lf */
long i = 0;
const char *const trans = type == 'u' ? uu_table : b64_table;
char padding;
const unsigned char *s = (const unsigned char *)s0;
if (type == 'u') {
buff[i++] = (char)len + ' ';
padding = '`';
}
else {
padding = '=';
}
while (len >= input_unit) {
while (len >= input_unit && buff_size-i >= encoded_unit) {
buff[i++] = trans[077 & (*s >> 2)];
buff[i++] = trans[077 & (((*s << 4) & 060) | ((s[1] >> 4) & 017))];
buff[i++] = trans[077 & (((s[1] << 2) & 074) | ((s[2] >> 6) & 03))];
buff[i++] = trans[077 & s[2]];
s += input_unit;
len -= input_unit;
}
if (buff_size-i < encoded_unit) {
rb_str_buf_cat(str, buff, i);
i = 0;
}
}
if (len == 2) {
buff[i++] = trans[077 & (*s >> 2)];
buff[i++] = trans[077 & (((*s << 4) & 060) | ((s[1] >> 4) & 017))];
buff[i++] = trans[077 & (((s[1] << 2) & 074) | (('\0' >> 6) & 03))];
buff[i++] = padding;
}
else if (len == 1) {
buff[i++] = trans[077 & (*s >> 2)];
buff[i++] = trans[077 & (((*s << 4) & 060) | (('\0' >> 4) & 017))];
buff[i++] = padding;
buff[i++] = padding;
}
if (tail_lf) buff[i++] = '\n';
rb_str_buf_cat(str, buff, i);
if ((size_t)i > sizeof(buff)) rb_bug("encodes() buffer overrun");
}
static const char hex_table[] = "0123456789ABCDEF";
static void
qpencode(VALUE str, VALUE from, long len)
{
char buff[1024];
long i = 0, n = 0, prev = EOF;
unsigned char *s = (unsigned char*)RSTRING_PTR(from);
unsigned char *send = s + RSTRING_LEN(from);
while (s < send) {
if ((*s > 126) ||
(*s < 32 && *s != '\n' && *s != '\t') ||
(*s == '=')) {
buff[i++] = '=';
buff[i++] = hex_table[*s >> 4];
buff[i++] = hex_table[*s & 0x0f];
n += 3;
prev = EOF;
}
else if (*s == '\n') {
if (prev == ' ' || prev == '\t') {
buff[i++] = '=';
buff[i++] = *s;
}
buff[i++] = *s;
n = 0;
prev = *s;
}
else {
buff[i++] = *s;
n++;
prev = *s;
}
if (n > len) {
buff[i++] = '=';
buff[i++] = '\n';
n = 0;
prev = '\n';
}
if (i > 1024 - 5) {
rb_str_buf_cat(str, buff, i);
i = 0;
}
s++;
}
if (n > 0) {
buff[i++] = '=';
buff[i++] = '\n';
}
if (i > 0) {
rb_str_buf_cat(str, buff, i);
}
}
static inline int
hex2num(char c)
{
int n;
n = ruby_digit36_to_number_table[(unsigned char)c];
if (16 <= n)
n = -1;
return n;
}
#define PACK_LENGTH_ADJUST_SIZE(sz) do { \
tmp_len = 0; \
if (len > (long)((send-s)/(sz))) { \
if (!star) { \
tmp_len = len-(send-s)/(sz); \
} \
len = (send-s)/(sz); \
} \
} while (0)
#define PACK_ITEM_ADJUST() do { \
if (tmp_len > 0 && mode == UNPACK_ARRAY) \
rb_ary_store(ary, RARRAY_LEN(ary)+tmp_len-1, Qnil); \
} while (0)
/* Workaround for Oracle Developer Studio (Oracle Solaris Studio)
* 12.4/12.5/12.6 C compiler optimization bug
* with "-xO4" optimization option.
*/
#if defined(__SUNPRO_C) && 0x5130 <= __SUNPRO_C && __SUNPRO_C <= 0x5150
# define AVOID_CC_BUG volatile
#else
# define AVOID_CC_BUG
#endif
2022-11-22 08:20:45 +03:00
enum unpack_mode {
UNPACK_ARRAY,
UNPACK_BLOCK,
UNPACK_1
};
static VALUE
2022-11-22 08:20:45 +03:00
pack_unpack_internal(VALUE str, VALUE fmt, enum unpack_mode mode, long offset)
{
#define hexdigits ruby_hexdigits
char *s, *send;
char *p, *pend;
2021-10-22 19:38:45 +03:00
VALUE ary, associates = Qfalse;
char type;
long len;
AVOID_CC_BUG long tmp_len;
int star;
#ifdef NATINT_PACK
int natint; /* native integer */
#endif
int signed_p, integer_size, bigendian_p;
#define UNPACK_PUSH(item) do {\
VALUE item_val = (item);\
if ((mode) == UNPACK_BLOCK) {\
rb_yield(item_val);\
}\
else if ((mode) == UNPACK_ARRAY) {\
rb_ary_push(ary, item_val);\
}\
else /* if ((mode) == UNPACK_1) { */ {\
return item_val; \
}\
} while (0)
* eval.c (block_pass): should not downgrade safe level. * ext/dbm/extconf.rb: allow specifying dbm-type explicitly. * ext/dbm/extconf.rb: avoid gdbm if possible, because it leaks memory, whereas gdbm.so doesn't. potential incompatibility. * string.c (rb_str_insert): new method. * parse.y (yylex): lex_state after RESCUE_MOD should be EXPR_BEG. * array.c (rb_ary_insert): new method. * array.c (rb_ary_update): new utility function. * io.c (set_outfile): should check if closed before assignment. * eval.c (rb_eval): should preserve value of ruby_errinfo. * eval.c (rb_thread_schedule): infinite sleep should not cause dead lock. * array.c (rb_ary_flatten_bang): proper recursive detection. * eval.c (yield_under): need not to prohibit at safe level 4. * pack.c (pack_pack): p/P packs nil into NULL. * pack.c (pack_unpack): p/P unpacks NULL into nil. * pack.c (pack_pack): size check for P template. * ruby.c (set_arg0): wrong predicate when new $0 value is bigger than original space. * gc.c (id2ref): should use NUM2ULONG() * object.c (rb_mod_const_get): check whether name is a class variable name. * object.c (rb_mod_const_set): ditto. * object.c (rb_mod_const_defined): ditto. * marshal.c (w_float): precision changed to "%.16g" * eval.c (rb_call0): wrong retry behavior. * numeric.c (fix_aref): a bug on long>int architecture. * eval.c (rb_eval_string_wrap): should restore ruby_wrapper. * regex.c (re_compile_pattern): char class at either edge of range should be invalid. * eval.c (handle_rescue): use === to compare exception match. * error.c (syserr_eqq): comparison between SytemCallErrors should based on their error numbers. * eval.c (safe_getter): should use INT2NUM(). * bignum.c (rb_big2long): 2**31 cannot fit in 31 bit long. * regex.c (calculate_must_string): wrong length calculation. * eval.c (rb_thread_start_0): fixed memory leak. * parse.y (none): should clear cmdarg_stack too. * io.c (rb_fopen): use setvbuf() to avoid recursive malloc() on some platforms. * file.c (rb_stat_dev): device functions should honor stat field types (except long long such as dev_t). * eval.c (rb_mod_nesting): should not push nil for nesting array. * eval.c (rb_mod_s_constants): should not search array by rb_mod_const_at() for nil (happens for singleton class). * class.c (rb_singleton_class_attached): should modify iv_tbl by itself, no longer use rb_iv_set() to avoid freeze check error. * variable.c (rb_const_get): error message "uninitialized constant Foo at Bar::Baz" instead of "uninitialized constantBar::Baz::Foo". * eval.c (rb_mod_included): new hook called from rb_mod_include(). * io.c (opt_i_set): should strdup() inplace_edit string. * eval.c (exec_under): need to push cref too. * eval.c (rb_f_missing): raise NameError for "undefined local variable or method". * error.c (Init_Exception): new exception NoMethodError. NameError moved under ScriptError again. * eval.c (rb_f_missing): use NoMethodError instead of NameError. * file.c (Init_File): should redifine "new" class method. * eval.c (PUSH_CREF): sharing cref node was problematic. maintain runtime cref list instead. * eval.c (rb_eval): copy defn node before registering. * eval.c (rb_load): clear ruby_cref before loading. * variable.c (rb_const_get): no recursion to show full class path for modules. * eval.c (rb_set_safe_level): should set safe level in curr_thread as well. * eval.c (safe_setter): ditto. * object.c (rb_obj_is_instance_of): nil belongs to false, not true. * time.c (make_time_t): proper (I hope) daylight saving time handling for both US and Europe. I HATE DST! * eval.c (rb_thread_wait_for): non blocked signal interrupt should stop the interval. * eval.c (proc_eq): class check aded. * eval.c (proc_eq): typo fixed ("return" was ommitted). * error.c (Init_Exception): move NameError under StandardError. * class.c (rb_mod_clone): should copy method bodies too. * bignum.c (bigdivrem): should trim trailing zero bdigits of remainder, even if dd == 0. * file.c (check3rdbyte): safe string check moved here. * time.c (make_time_t): remove HAVE_TM_ZONE code since it sometimes reports wrong time. * time.c (make_time_t): remove unnecessary range check for platforms where negative time_t is available. * process.c (proc_waitall): should push Process::Status instead of Finuxm status. * process.c (waitall_each): should add all entries in pid_tbl. these changes are inspired by Koji Arai. Thanks. * process.c (proc_wait): should not iterate if pid_tbl is 0. * process.c (proc_waitall): ditto. * numeric.c (flodivmod): a bug in no fmod case. * process.c (pst_wifsignaled): should apply WIFSIGNALED for status (int), not st (VALUE). * io.c (Init_IO): value of $/ and $\ are no longer restricted to strings. type checks are done on demand. * class.c (rb_include_module): module inclusion should be check taints. * ruby.h (STR2CSTR): replace to StringType() and StringTypePtr(). * ruby.h (rb_str2cstr): ditto. * eval.c (rb_load): should not copy topleve local variables. It cause variable/method ambiguity. Thanks to L. Peter Deutsch. * class.c (rb_include_module): freeze check at first. * eval.c (rb_attr): sprintf() and rb_intern() moved into conditional body. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@1356 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2001-05-02 08:22:21 +04:00
StringValue(str);
StringValue(fmt);
rb_must_asciicompat(fmt);
if (offset < 0) rb_raise(rb_eArgError, "offset can't be negative");
len = RSTRING_LEN(str);
if (offset > len) rb_raise(rb_eArgError, "offset outside of string");
s = RSTRING_PTR(str);
send = s + len;
s += offset;
p = RSTRING_PTR(fmt);
pend = p + RSTRING_LEN(fmt);
2021-10-21 15:52:17 +03:00
#define UNPACK_FETCH(var, type) (memcpy((var), s, sizeof(type)), s += sizeof(type))
ary = mode == UNPACK_ARRAY ? rb_ary_new() : Qnil;
while (p < pend) {
int explicit_endian = 0;
type = *p++;
#ifdef NATINT_PACK
natint = 0;
#endif
if (ISSPACE(type)) continue;
if (type == '#') {
while ((p < pend) && (*p != '\n')) {
p++;
}
continue;
}
star = 0;
{
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;
2022-07-21 19:23:58 +03:00
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;
}
}
2022-07-21 19:23:58 +03:00
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 (len < 0 || errno) {
rb_raise(rb_eRangeError, "pack length too big");
}
}
else {
len = (type != '@');
}
2022-07-21 19:23:58 +03:00
switch (type) {
case '%':
rb_raise(rb_eArgError, "%% is not supported");
break;
2022-07-21 19:23:58 +03:00
case 'A':
if (len > send - s) len = send - s;
{
long end = len;
char *t = s + len - 1;
2022-07-21 19:23:58 +03:00
while (t >= s) {
if (*t != ' ' && *t != '\0') break;
t--; len--;
}
UNPACK_PUSH(rb_str_new(s, len));
s += end;
}
break;
case 'Z':
{
char *t = s;
if (len > send-s) len = send-s;
while (t < s+len && *t) t++;
UNPACK_PUSH(rb_str_new(s, t-s));
if (t < send) t++;
s = star ? t : s+len;
}
break;
case 'a':
if (len > send - s) len = send - s;
UNPACK_PUSH(rb_str_new(s, len));
s += len;
break;
2022-07-21 19:23:58 +03:00
case 'b':
{
VALUE bitstr;
char *t;
int bits;
long i;
2022-07-21 19:23:58 +03:00
if (p[-1] == '*' || len > (send - s) * 8)
len = (send - s) * 8;
bits = 0;
bitstr = rb_usascii_str_new(0, len);
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 7) bits >>= 1;
else bits = (unsigned char)*s++;
*t++ = (bits & 1) ? '1' : '0';
}
UNPACK_PUSH(bitstr);
}
break;
2022-07-21 19:23:58 +03:00
case 'B':
{
VALUE bitstr;
char *t;
int bits;
long i;
2022-07-21 19:23:58 +03:00
if (p[-1] == '*' || len > (send - s) * 8)
len = (send - s) * 8;
bits = 0;
bitstr = rb_usascii_str_new(0, len);
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 7) bits <<= 1;
else bits = (unsigned char)*s++;
*t++ = (bits & 128) ? '1' : '0';
}
UNPACK_PUSH(bitstr);
}
break;
2022-07-21 19:23:58 +03:00
case 'h':
{
VALUE bitstr;
char *t;
int bits;
long i;
2022-07-21 19:23:58 +03:00
if (p[-1] == '*' || len > (send - s) * 2)
len = (send - s) * 2;
bits = 0;
bitstr = rb_usascii_str_new(0, len);
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 1)
bits >>= 4;
else
bits = (unsigned char)*s++;
*t++ = hexdigits[bits & 15];
}
UNPACK_PUSH(bitstr);
}
break;
2022-07-21 19:23:58 +03:00
case 'H':
{
VALUE bitstr;
char *t;
int bits;
long i;
2022-07-21 19:23:58 +03:00
if (p[-1] == '*' || len > (send - s) * 2)
len = (send - s) * 2;
bits = 0;
bitstr = rb_usascii_str_new(0, len);
t = RSTRING_PTR(bitstr);
for (i=0; i<len; i++) {
if (i & 1)
bits <<= 4;
else
bits = (unsigned char)*s++;
*t++ = hexdigits[(bits >> 4) & 15];
}
UNPACK_PUSH(bitstr);
}
break;
2022-07-21 19:23:58 +03:00
case 'c':
signed_p = 1;
integer_size = 1;
bigendian_p = BIGENDIAN_P(); /* not effective */
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'C':
signed_p = 0;
integer_size = 1;
bigendian_p = BIGENDIAN_P(); /* not effective */
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 's':
signed_p = 1;
integer_size = NATINT_LEN(short, 2);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'S':
signed_p = 0;
integer_size = NATINT_LEN(short, 2);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'i':
signed_p = 1;
integer_size = (int)sizeof(int);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'I':
signed_p = 0;
integer_size = (int)sizeof(int);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'l':
signed_p = 1;
integer_size = NATINT_LEN(long, 4);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'L':
signed_p = 0;
integer_size = NATINT_LEN(long, 4);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'q':
signed_p = 1;
integer_size = NATINT_LEN_Q;
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'Q':
signed_p = 0;
integer_size = NATINT_LEN_Q;
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'j':
signed_p = 1;
integer_size = sizeof(intptr_t);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'J':
signed_p = 0;
integer_size = sizeof(uintptr_t);
bigendian_p = BIGENDIAN_P();
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'n':
signed_p = 0;
integer_size = 2;
bigendian_p = 1;
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'N':
signed_p = 0;
integer_size = 4;
bigendian_p = 1;
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'v':
signed_p = 0;
integer_size = 2;
bigendian_p = 0;
goto unpack_integer;
2022-07-21 19:23:58 +03:00
case 'V':
signed_p = 0;
integer_size = 4;
bigendian_p = 0;
goto unpack_integer;
2022-07-21 19:23:58 +03:00
unpack_integer:
if (explicit_endian) {
bigendian_p = explicit_endian == '>';
}
PACK_LENGTH_ADJUST_SIZE(integer_size);
while (len-- > 0) {
int flags = bigendian_p ? INTEGER_PACK_BIG_ENDIAN : INTEGER_PACK_LITTLE_ENDIAN;
VALUE val;
if (signed_p)
flags |= INTEGER_PACK_2COMP;
val = rb_integer_unpack(s, integer_size, 1, 0, flags);
UNPACK_PUSH(val);
s += integer_size;
}
PACK_ITEM_ADJUST();
break;
case 'f':
case 'F':
PACK_LENGTH_ADJUST_SIZE(sizeof(float));
while (len-- > 0) {
float tmp;
2021-10-21 15:52:17 +03:00
UNPACK_FETCH(&tmp, float);
UNPACK_PUSH(DBL2NUM((double)tmp));
}
PACK_ITEM_ADJUST();
break;
2022-07-21 19:23:58 +03:00
case 'e':
PACK_LENGTH_ADJUST_SIZE(sizeof(float));
while (len-- > 0) {
FLOAT_CONVWITH(tmp);
2021-10-21 15:52:17 +03:00
UNPACK_FETCH(tmp.buf, float);
VTOHF(tmp);
UNPACK_PUSH(DBL2NUM(tmp.f));
}
PACK_ITEM_ADJUST();
break;
2022-07-21 19:23:58 +03:00
case 'E':
PACK_LENGTH_ADJUST_SIZE(sizeof(double));
while (len-- > 0) {
DOUBLE_CONVWITH(tmp);
2021-10-21 15:52:17 +03:00
UNPACK_FETCH(tmp.buf, double);
VTOHD(tmp);
UNPACK_PUSH(DBL2NUM(tmp.d));
}
PACK_ITEM_ADJUST();
break;
2022-07-21 19:23:58 +03:00
case 'D':
case 'd':
PACK_LENGTH_ADJUST_SIZE(sizeof(double));
while (len-- > 0) {
double tmp;
2021-10-21 15:52:17 +03:00
UNPACK_FETCH(&tmp, double);
UNPACK_PUSH(DBL2NUM(tmp));
}
PACK_ITEM_ADJUST();
break;
2022-07-21 19:23:58 +03:00
case 'g':
PACK_LENGTH_ADJUST_SIZE(sizeof(float));
while (len-- > 0) {
FLOAT_CONVWITH(tmp);
2021-10-21 15:52:17 +03:00
UNPACK_FETCH(tmp.buf, float);
NTOHF(tmp);
UNPACK_PUSH(DBL2NUM(tmp.f));
}
PACK_ITEM_ADJUST();
break;
2022-07-21 19:23:58 +03:00
case 'G':
PACK_LENGTH_ADJUST_SIZE(sizeof(double));
while (len-- > 0) {
DOUBLE_CONVWITH(tmp);
2021-10-21 15:52:17 +03:00
UNPACK_FETCH(tmp.buf, double);
NTOHD(tmp);
UNPACK_PUSH(DBL2NUM(tmp.d));
}
PACK_ITEM_ADJUST();
break;
2022-07-21 19:23:58 +03:00
case 'U':
if (len > send - s) len = send - s;
while (len > 0 && s < send) {
long alen = send - s;
unsigned long l;
2022-07-21 19:23:58 +03:00
l = utf8_to_uv(s, &alen);
s += alen; len--;
UNPACK_PUSH(ULONG2NUM(l));
}
break;
2022-07-21 19:23:58 +03:00
case 'u':
{
VALUE buf = rb_str_new(0, (send - s)*3/4);
char *ptr = RSTRING_PTR(buf);
long total = 0;
2022-07-21 19:23:58 +03:00
while (s < send && (unsigned char)*s > ' ' && (unsigned char)*s < 'a') {
long a,b,c,d;
char hunk[3];
2022-07-21 19:23:58 +03:00
len = ((unsigned char)*s++ - ' ') & 077;
2022-07-21 19:23:58 +03:00
total += len;
if (total > RSTRING_LEN(buf)) {
len -= total - RSTRING_LEN(buf);
total = RSTRING_LEN(buf);
}
2022-07-21 19:23:58 +03:00
while (len > 0) {
long mlen = len > 3 ? 3 : len;
2022-07-21 19:23:58 +03:00
if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
a = ((unsigned char)*s++ - ' ') & 077;
else
a = 0;
if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
b = ((unsigned char)*s++ - ' ') & 077;
else
b = 0;
if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
c = ((unsigned char)*s++ - ' ') & 077;
else
c = 0;
if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
d = ((unsigned char)*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 < send && (unsigned char)*s != '\r' && *s != '\n')
s++; /* possible checksum byte */
if (s < send && *s == '\r') s++;
if (s < send && *s == '\n') s++;
}
2022-07-21 19:23:58 +03:00
rb_str_set_len(buf, total);
UNPACK_PUSH(buf);
}
break;
2022-07-21 19:23:58 +03:00
case 'm':
{
VALUE buf = rb_str_new(0, (send - s + 3)*3/4); /* +3 is for skipping paddings */
char *ptr = RSTRING_PTR(buf);
int a = -1,b = -1,c = 0,d = 0;
static signed char b64_xtable[256];
2022-07-21 19:23:58 +03:00
if (b64_xtable['/'] <= 0) {
int i;
2022-07-21 19:23:58 +03:00
for (i = 0; i < 256; i++) {
b64_xtable[i] = -1;
}
for (i = 0; i < 64; i++) {
b64_xtable[(unsigned char)b64_table[i]] = (char)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++ = castchar(a << 2 | b >> 4);
*ptr++ = castchar(b << 4 | c >> 2);
*ptr++ = castchar(c << 6 | d);
}
if (c == -1) {
*ptr++ = castchar(a << 2 | b >> 4);
if (b & 0xf) rb_raise(rb_eArgError, "invalid base64");
}
else if (d == -1) {
*ptr++ = castchar(a << 2 | b >> 4);
*ptr++ = castchar(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++ = castchar(a << 2 | b >> 4);
*ptr++ = castchar(b << 4 | c >> 2);
*ptr++ = castchar(c << 6 | d);
a = -1;
}
if (a != -1 && b != -1) {
if (c == -1)
*ptr++ = castchar(a << 2 | b >> 4);
else {
*ptr++ = castchar(a << 2 | b >> 4);
*ptr++ = castchar(b << 4 | c >> 2);
}
}
}
rb_str_set_len(buf, ptr - RSTRING_PTR(buf));
UNPACK_PUSH(buf);
}
break;
2022-07-21 19:23:58 +03:00
case 'M':
{
VALUE buf = rb_str_new(0, send - s);
char *ptr = RSTRING_PTR(buf), *ss = s;
int csum = 0;
int c1, c2;
2022-07-21 19:23:58 +03:00
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;
csum |= *ptr++ = castchar(c1 << 4 | c2);
}
}
else {
csum |= *ptr++ = *s;
}
s++;
ss = s;
}
rb_str_set_len(buf, ptr - RSTRING_PTR(buf));
rb_str_buf_cat(buf, ss, send-ss);
csum = ISASCII(csum) ? ENC_CODERANGE_7BIT : ENC_CODERANGE_VALID;
ENCODING_CODERANGE_SET(buf, rb_ascii8bit_encindex(), csum);
UNPACK_PUSH(buf);
}
break;
2022-07-21 19:23:58 +03:00
case '@':
if (len > RSTRING_LEN(str))
rb_raise(rb_eArgError, "@ outside of string");
s = RSTRING_PTR(str) + len;
break;
2022-07-21 19:23:58 +03:00
case 'X':
if (len > s - RSTRING_PTR(str))
rb_raise(rb_eArgError, "X outside of string");
s -= len;
break;
2022-07-21 19:23:58 +03:00
case 'x':
if (len > send - s)
rb_raise(rb_eArgError, "x outside of string");
s += len;
break;
2022-07-21 19:23:58 +03:00
case 'P':
if (sizeof(char *) <= (size_t)(send - s)) {
VALUE tmp = Qnil;
char *t;
2022-07-21 19:23:58 +03:00
2021-10-21 15:52:17 +03:00
UNPACK_FETCH(&t, char *);
if (t) {
2021-10-22 19:38:45 +03:00
if (!associates) associates = str_associated(str);
tmp = associated_pointer(associates, t);
if (len < RSTRING_LEN(tmp)) {
tmp = rb_str_new(t, len);
str_associate(tmp, associates);
}
}
UNPACK_PUSH(tmp);
}
break;
2022-07-21 19:23:58 +03:00
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;
2022-07-21 19:23:58 +03:00
2021-10-21 15:52:17 +03:00
UNPACK_FETCH(&t, char *);
if (t) {
2021-10-22 19:38:45 +03:00
if (!associates) associates = str_associated(str);
tmp = associated_pointer(associates, t);
}
UNPACK_PUSH(tmp);
}
}
break;
2022-07-21 19:23:58 +03:00
case 'w':
{
char *s0 = s;
while (len > 0 && s < send) {
if (*s & 0x80) {
s++;
}
else {
s++;
UNPACK_PUSH(rb_integer_unpack(s0, s-s0, 1, 1, INTEGER_PACK_BIG_ENDIAN));
len--;
s0 = s;
}
}
}
break;
default:
unknown_directive("unpack", type, fmt);
break;
}
}
return ary;
}
static VALUE
pack_unpack(rb_execution_context_t *ec, VALUE str, VALUE fmt, VALUE offset)
{
2022-11-22 08:20:45 +03:00
enum unpack_mode mode = rb_block_given_p() ? UNPACK_BLOCK : UNPACK_ARRAY;
return pack_unpack_internal(str, fmt, mode, RB_NUM2LONG(offset));
}
static VALUE
pack_unpack1(rb_execution_context_t *ec, VALUE str, VALUE fmt, VALUE offset)
{
return pack_unpack_internal(str, fmt, UNPACK_1, RB_NUM2LONG(offset));
}
int
rb_uv_to_utf8(char buf[6], unsigned long uv)
{
if (uv <= 0x7f) {
buf[0] = (char)uv;
return 1;
}
if (uv <= 0x7ff) {
buf[0] = castchar(((uv>>6)&0xff)|0xc0);
buf[1] = castchar((uv&0x3f)|0x80);
return 2;
}
if (uv <= 0xffff) {
buf[0] = castchar(((uv>>12)&0xff)|0xe0);
buf[1] = castchar(((uv>>6)&0x3f)|0x80);
buf[2] = castchar((uv&0x3f)|0x80);
return 3;
}
if (uv <= 0x1fffff) {
buf[0] = castchar(((uv>>18)&0xff)|0xf0);
buf[1] = castchar(((uv>>12)&0x3f)|0x80);
buf[2] = castchar(((uv>>6)&0x3f)|0x80);
buf[3] = castchar((uv&0x3f)|0x80);
return 4;
}
if (uv <= 0x3ffffff) {
buf[0] = castchar(((uv>>24)&0xff)|0xf8);
buf[1] = castchar(((uv>>18)&0x3f)|0x80);
buf[2] = castchar(((uv>>12)&0x3f)|0x80);
buf[3] = castchar(((uv>>6)&0x3f)|0x80);
buf[4] = castchar((uv&0x3f)|0x80);
return 5;
}
if (uv <= 0x7fffffff) {
buf[0] = castchar(((uv>>30)&0xff)|0xfc);
buf[1] = castchar(((uv>>24)&0x3f)|0x80);
buf[2] = castchar(((uv>>18)&0x3f)|0x80);
buf[3] = castchar(((uv>>12)&0x3f)|0x80);
buf[4] = castchar(((uv>>6)&0x3f)|0x80);
buf[5] = castchar((uv&0x3f)|0x80);
return 6;
}
rb_raise(rb_eRangeError, "pack(U): value out of range");
* encoding.c (rb_enc_codepoint_len): Use UNREACHABLE to avoid "control reaches end of non-void function" warnings. [ruby-trunk - Bug #6066] * re.c (name_to_backref_number): ditto. * object.c (rb_Float): ditto. * io.c (io_readpartial): ditto. * io.c (io_read_nonblock): ditto. * pack.c (rb_uv_to_utf8): ditto. * proc.c (rb_method_entry_arity): ditto. * vm_method.c (rb_f_notimplement): ditto. * struct.c (rb_struct_aset_id): ditto. * class.c (rb_scan_args): ditto. * process.c (rlimit_resource_type): ditto. * process.c (rlimit_resource_value): ditto. * process.c (p_uid_switch): ditto. * process.c (p_gid_switch): ditto. * ext/digest/digest.c (rb_digest_instance_update): ditto. * ext/digest/digest.c (rb_digest_instance_finish): ditto. * ext/digest/digest.c (rb_digest_instance_reset): ditto. * ext/digest/digest.c (rb_digest_instance_block_length): ditto. * ext/bigdecimal/bigdecimal.c (BigDecimalCmp): ditto. * ext/dl/handle.c (rb_dlhandle_close): ditto. * ext/tk/tcltklib.c (pending_exception_check0): ditto. * ext/tk/tcltklib.c (pending_exception_check1): ditto. * ext/tk/tcltklib.c (ip_cancel_eval_core): ditto. * ext/tk/tcltklib.c (lib_get_reltype_name): ditto. * ext/tk/tcltklib.c (create_dummy_encoding_for_tk_core): ditto. * ext/tk/tkutil/tkutil.c (tk_hash_kv): ditto. * ext/openssl/ossl_ssl.c (ossl_ssl_session_reused): ditto. * ext/openssl/ossl_pkey_ec.c (ossl_ec_key_dsa_verify_asn1): ditto. * ext/openssl/ossl_pkey_ec.c (ossl_ec_point_is_at_infinit): ditto. * ext/openssl/ossl_pkey_ec.c (ossl_ec_point_is_on_curve): ditto. * ext/fiddle/conversions.c (generic_to_value): ditto. * ext/socket/raddrinfo.c (rsock_io_socket_addrinfo): ditto. * ext/socket/socket.c (sock_s_getnameinfo): ditto. * ext/ripper/eventids2.c (ripper_token2eventid): ditto. * cont.c (return_fiber): ditto. * dmydln.c (dln_load): ditto. * vm_insnhelper.c (vm_search_normal_superclass): ditto. * bignum.c (big_fdiv): ditto. * marshal.c (r_symlink): ditto. * marshal.c (r_symbol): ditto. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@35321 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2012-04-14 03:45:37 +04:00
UNREACHABLE_RETURN(Qnil);
}
static const unsigned long utf8_limits[] = {
0x0, /* 1 */
0x80, /* 2 */
0x800, /* 3 */
0x10000, /* 4 */
0x200000, /* 5 */
0x4000000, /* 6 */
0x80000000, /* 7 */
};
static unsigned long
utf8_to_uv(const char *p, long *lenp)
{
int c = *p++ & 0xff;
unsigned long uv = c;
long n;
if (!(uv & 0x80)) {
*lenp = 1;
return uv;
}
if (!(uv & 0x40)) {
*lenp = 1;
rb_raise(rb_eArgError, "malformed UTF-8 character");
}
if (!(uv & 0x20)) { n = 2; uv &= 0x1f; }
else if (!(uv & 0x10)) { n = 3; uv &= 0x0f; }
else if (!(uv & 0x08)) { n = 4; uv &= 0x07; }
else if (!(uv & 0x04)) { n = 5; uv &= 0x03; }
else if (!(uv & 0x02)) { n = 6; uv &= 0x01; }
else {
*lenp = 1;
rb_raise(rb_eArgError, "malformed UTF-8 character");
}
if (n > *lenp) {
rb_raise(rb_eArgError, "malformed UTF-8 character (expected %ld bytes, given %ld bytes)",
n, *lenp);
}
*lenp = n--;
if (n != 0) {
while (n--) {
c = *p++ & 0xff;
if ((c & 0xc0) != 0x80) {
*lenp -= n + 1;
rb_raise(rb_eArgError, "malformed UTF-8 character");
}
else {
c &= 0x3f;
uv = uv << 6 | c;
}
}
}
n = *lenp - 1;
if (uv < utf8_limits[n]) {
rb_raise(rb_eArgError, "redundant UTF-8 sequence");
}
return uv;
}
2019-11-08 05:54:39 +03:00
#include "pack.rbinc"
void
Init_pack(void)
{
id_associated = rb_make_internal_id();
}