12#include "ruby/internal/config.h"
18#include "internal/enc.h"
19#include "internal/encoding.h"
20#include "internal/error.h"
21#include "internal/inits.h"
22#include "internal/load.h"
23#include "internal/object.h"
24#include "internal/string.h"
25#include "internal/vm.h"
29#include "ruby_assert.h"
35#define ENC_ASSERT(expr) RUBY_ASSERT_WHEN(ENC_DEBUG, expr)
36#define MUST_STRING(str) (ENC_ASSERT(RB_TYPE_P(str, T_STRING)), str)
38#undef rb_ascii8bit_encindex
39#undef rb_utf8_encindex
40#undef rb_usascii_encindex
44#if defined __GNUC__ && __GNUC__ >= 4
45#pragma GCC visibility push(default)
46int rb_enc_register(
const char *name,
rb_encoding *encoding);
47void rb_enc_set_base(
const char *name,
const char *orig);
48int rb_enc_set_dummy(
int index);
49void rb_encdb_declare(
const char *name);
50int rb_encdb_replicate(
const char *name,
const char *orig);
51int rb_encdb_dummy(
const char *name);
52int rb_encdb_alias(
const char *alias,
const char *orig);
53#pragma GCC visibility pop
59#define ENCODING_LIST_CAPA 256
60static VALUE rb_encoding_list;
78#define GLOBAL_ENC_TABLE_ENTER(enc_table) struct enc_table *enc_table = &global_enc_table; RB_VM_LOCK_ENTER()
79#define GLOBAL_ENC_TABLE_LEAVE() RB_VM_LOCK_LEAVE()
80#define GLOBAL_ENC_TABLE_EVAL(enc_table, expr) do { \
81 GLOBAL_ENC_TABLE_ENTER(enc_table); \
85 GLOBAL_ENC_TABLE_LEAVE(); \
89#define ENC_DUMMY_FLAG (1<<24)
90#define ENC_INDEX_MASK (~(~0U<<24))
92#define ENC_TO_ENCINDEX(enc) (int)((enc)->ruby_encoding_index & ENC_INDEX_MASK)
93#define ENC_DUMMY_P(enc) ((enc)->ruby_encoding_index & ENC_DUMMY_FLAG)
94#define ENC_SET_DUMMY(enc) ((enc)->ruby_encoding_index |= ENC_DUMMY_FLAG)
96#define ENCODING_COUNT ENCINDEX_BUILTIN_MAX
97#define UNSPECIFIED_ENCODING INT_MAX
99#define ENCODING_NAMELEN_MAX 63
100#define valid_encoding_name_p(name) ((name) && strlen(name) <= ENCODING_NAMELEN_MAX)
105 0, 0, RUBY_TYPED_FREE_IMMEDIATELY
108#define is_data_encoding(obj) (RTYPEDDATA_P(obj) && RTYPEDDATA_TYPE(obj) == &encoding_data_type)
109#define is_obj_encoding(obj) (RB_TYPE_P((obj), T_DATA) && is_data_encoding(obj))
112rb_data_is_encoding(
VALUE obj)
114 return is_data_encoding(obj);
131 VALUE list = rb_encoding_list;
132 if (list &&
NIL_P(rb_ary_entry(list, index))) {
134 rb_ary_store(list, index, enc_new(encoding));
139enc_list_lookup(
int idx)
143 if (idx < ENCODING_LIST_CAPA) {
144 list = rb_encoding_list;
146 enc = rb_ary_entry(list, idx);
150 rb_bug(
"rb_enc_from_encoding_index(%d): not created yet", idx);
158rb_enc_from_encoding_index(
int idx)
160 return enc_list_lookup(idx);
167 if (!encoding)
return Qnil;
168 idx = ENC_TO_ENCINDEX(encoding);
169 return rb_enc_from_encoding_index(idx);
175 return enc ? ENC_TO_ENCINDEX(enc) : 0;
181 return ENC_DUMMY_P(enc) != 0;
187 int index = rb_enc_to_index(enc);
188 if (rb_enc_from_index(index) != enc)
190 if (rb_enc_autoload_p(enc)) {
191 index = rb_enc_autoload(enc);
197enc_check_encoding(
VALUE obj)
199 if (!is_obj_encoding(obj)) {
202 return check_encoding(
RDATA(obj)->data);
205NORETURN(
static void not_encoding(
VALUE enc));
207not_encoding(
VALUE enc)
214must_encoding(
VALUE enc)
216 int index = enc_check_encoding(enc);
224must_encindex(
int index)
231 if (ENC_TO_ENCINDEX(enc) != (
int)(index & ENC_INDEX_MASK)) {
235 if (rb_enc_autoload_p(enc) && rb_enc_autoload(enc) == -1) {
248 idx = enc_check_encoding(enc);
258 if (!(name = rb_str_to_cstr(enc))) {
261 return rb_enc_find_index(name);
265name_for_encoding(
volatile VALUE *enc)
273 if (!(n = rb_str_to_cstr(name))) {
281str_find_encindex(
VALUE enc)
283 int idx = rb_enc_find_index(name_for_encoding(&enc));
289str_to_encindex(
VALUE enc)
291 int idx = str_find_encindex(enc);
299str_to_encoding(
VALUE enc)
301 return rb_enc_from_index(str_to_encindex(enc));
307 if (enc_check_encoding(enc) >= 0)
return RDATA(enc)->data;
308 return str_to_encoding(enc);
315 if (enc_check_encoding(enc) >= 0)
return RDATA(enc)->data;
316 idx = str_find_encindex(enc);
317 if (idx < 0)
return NULL;
318 return rb_enc_from_index(idx);
324 if (newsize > ENCODING_LIST_CAPA) {
336 if (!valid_encoding_name_p(name))
return -1;
338 ent->name = name =
strdup(name);
348 *encoding = *base_encoding;
351 memset(encoding, 0,
sizeof(*ent->enc));
353 encoding->name = name;
354 encoding->ruby_encoding_index = index;
356 st_insert(
enc_table->names, (st_data_t)name, (st_data_t)index);
358 enc_list_update(index, encoding);
368 return enc_register_at(
enc_table, index, name, encoding);
371static void set_encoding_const(
const char *,
rb_encoding *);
377 if (UNLIKELY(index < 0 || enc_table->count <= (index &= ENC_INDEX_MASK))) {
384rb_enc_from_index(
int index)
386 return enc_from_index(&global_enc_table, index);
390rb_enc_register(
const char *name,
rb_encoding *encoding)
401 index = enc_register(
enc_table, name, encoding);
403 else if (rb_enc_autoload_p(oldenc) || !ENC_DUMMY_P(oldenc)) {
404 enc_register_at(
enc_table, index, name, encoding);
411 index = enc_register(
enc_table, name, encoding);
412 set_encoding_const(name, rb_enc_from_index(index));
415 GLOBAL_ENC_TABLE_LEAVE();
424 if (!name)
return -1;
426 if (st_lookup(
enc_table->names, (st_data_t)name, &idx)) {
433rb_encdb_declare(
const char *name)
437 int idx = enc_registered(
enc_table, name);
441 set_encoding_const(name, rb_enc_from_index(idx));
443 GLOBAL_ENC_TABLE_LEAVE();
449 if (enc_registered(
enc_table, name) >= 0) {
452 else if (!valid_encoding_name_p(name)) {
473rb_enc_set_base(
const char *name,
const char *orig)
477 int idx = enc_registered(
enc_table, name);
478 int origidx = enc_registered(
enc_table, orig);
479 set_base_encoding(
enc_table, idx, rb_enc_from_index(origidx));
481 GLOBAL_ENC_TABLE_LEAVE();
488rb_enc_set_dummy(
int index)
490 rb_encoding *enc = global_enc_table.list[index].enc;
501 idx = enc_register(
enc_table, name, encoding);
503 set_base_encoding(
enc_table, idx, encoding);
504 set_encoding_const(name, rb_enc_from_index(idx));
514 r = enc_replicate(
enc_table, name, encoding));
532 rb_warn_deprecated_to_remove(
"3.3",
"Encoding#replicate",
"the original encoding");
534 idx = rb_enc_replicate(name_for_encoding(&name), rb_to_encoding(encoding));
536 return rb_enc_from_encoding_index(idx);
543 idx = enc_register(
enc_table, name, origenc);
546 idx = enc_register_at(
enc_table, idx, name, origenc);
549 set_base_encoding(
enc_table, idx, origenc);
550 set_encoding_const(name, rb_enc_from_index(idx));
559rb_encdb_replicate(
const char *name,
const char *orig)
565 int origidx = enc_registered(
enc_table, orig);
566 int idx = enc_registered(
enc_table, name);
569 origidx = enc_register(
enc_table, orig, 0);
571 r = enc_replicate_with_index(
enc_table, name, rb_enc_from_index(origidx), idx);
573 GLOBAL_ENC_TABLE_LEAVE();
579rb_define_dummy_encoding(
const char *name)
585 index = enc_replicate(
enc_table, name, rb_ascii8bit_encoding());
589 GLOBAL_ENC_TABLE_LEAVE();
595rb_encdb_dummy(
const char *name)
601 index = enc_replicate_with_index(
enc_table, name,
602 rb_ascii8bit_encoding(),
607 GLOBAL_ENC_TABLE_LEAVE();
626enc_dummy_p(
VALUE enc)
628 return RBOOL(ENC_DUMMY_P(must_encoding(enc)));
642enc_ascii_compatible_p(
VALUE enc)
653 return ONIGENC_IS_UNICODE(enc);
657enc_dup_name(st_data_t name)
659 return (st_data_t)
strdup((
const char *)name);
669 return st_insert2(
enc_table->names, (st_data_t)alias, (st_data_t)idx,
676 if (!valid_encoding_name_p(alias))
return -1;
677 if (!enc_alias_internal(
enc_table, alias, idx))
678 set_encoding_const(alias, enc_from_index(
enc_table, idx));
683rb_enc_alias(
const char *alias,
const char *orig)
690 if ((idx = rb_enc_find_index(orig)) < 0) {
697 GLOBAL_ENC_TABLE_LEAVE();
703rb_encdb_alias(
const char *alias,
const char *orig)
709 int idx = enc_registered(
enc_table, orig);
716 GLOBAL_ENC_TABLE_LEAVE();
724 enc_table_expand(
enc_table, ENCODING_COUNT + 1);
726 enc_table->names = st_init_strcasetable_with_size(ENCODING_LIST_CAPA);
728#define OnigEncodingASCII_8BIT OnigEncodingASCII
729#define ENC_REGISTER(enc) enc_register_at(enc_table, ENCINDEX_##enc, rb_enc_name(&OnigEncoding##enc), &OnigEncoding##enc)
730 ENC_REGISTER(ASCII_8BIT);
732 ENC_REGISTER(US_ASCII);
733 global_enc_ascii =
enc_table->list[ENCINDEX_ASCII_8BIT].enc;
734 global_enc_utf_8 =
enc_table->list[ENCINDEX_UTF_8].enc;
735 global_enc_us_ascii =
enc_table->list[ENCINDEX_US_ASCII].enc;
737#undef OnigEncodingASCII_8BIT
738#define ENCDB_REGISTER(name, enc) enc_register_at(enc_table, ENCINDEX_##enc, name, NULL)
739 ENCDB_REGISTER(
"UTF-16BE", UTF_16BE);
740 ENCDB_REGISTER(
"UTF-16LE", UTF_16LE);
741 ENCDB_REGISTER(
"UTF-32BE", UTF_32BE);
742 ENCDB_REGISTER(
"UTF-32LE", UTF_32LE);
743 ENCDB_REGISTER(
"UTF-16", UTF_16);
744 ENCDB_REGISTER(
"UTF-32", UTF_32);
745 ENCDB_REGISTER(
"UTF8-MAC", UTF8_MAC);
747 ENCDB_REGISTER(
"EUC-JP", EUC_JP);
748 ENCDB_REGISTER(
"Windows-31J", Windows_31J);
754rb_enc_get_from_index(
int index)
756 return must_encindex(index);
759int rb_require_internal_silent(
VALUE fname);
762load_encoding(
const char *name)
776 enclib = rb_fstring(enclib);
779 loaded = rb_require_internal_silent(enclib);
785 if (loaded < 0 || 1 < loaded) {
788 else if ((idx = enc_registered(
enc_table, name)) < 0) {
791 else if (rb_enc_autoload_p(
enc_table->list[idx].enc)) {
795 GLOBAL_ENC_TABLE_LEAVE();
809 }
while (
enc_table->list[i].enc != base && (++i, 1));
810 if (rb_enc_autoload_p(base)) {
811 if (rb_enc_autoload(base) < 0)
return -1;
813 i = enc->ruby_encoding_index;
837rb_enc_find_index(
const char *name)
839 int i = enc_registered(&global_enc_table, name);
843 i = load_encoding(name);
845 else if (!(enc = rb_enc_from_index(i))) {
846 if (i != UNSPECIFIED_ENCODING) {
850 else if (rb_enc_autoload_p(enc)) {
851 if (rb_enc_autoload(enc) < 0) {
852 rb_warn(
"failed to load encoding (%s); use ASCII-8BIT instead",
861rb_enc_find_index2(
const char *name,
long len)
863 char buf[ENCODING_NAMELEN_MAX+1];
865 if (len > ENCODING_NAMELEN_MAX)
return -1;
866 memcpy(buf, name, len);
868 return rb_enc_find_index(buf);
872rb_enc_find(
const char *name)
874 int idx = rb_enc_find_index(name);
875 if (idx < 0) idx = 0;
876 return rb_enc_from_index(idx);
880enc_capable(
VALUE obj)
890 if (is_data_encoding(obj))
return TRUE;
899 return enc_capable(obj);
910enc_get_index_str(
VALUE str)
946 i = enc_get_index_str(obj);
949 tmp = rb_funcallv(obj,
rb_intern(
"internal_encoding"), 0, 0);
951 tmp = rb_funcallv(obj,
rb_intern(
"external_encoding"), 0, 0);
953 if (is_obj_encoding(tmp)) {
954 i = enc_check_encoding(tmp);
958 if (is_data_encoding(obj)) {
959 i = enc_check_encoding(obj);
969enc_set_index(
VALUE obj,
int idx)
971 if (!enc_capable(obj)) {
988 enc_set_index(obj, idx);
992rb_enc_associate_index(
VALUE obj,
int idx)
995 int oldidx, oldtermlen, termlen;
999 oldidx = rb_enc_get_index(obj);
1005 enc = must_encindex(idx);
1013 rb_str_change_terminator_length(obj, oldtermlen, termlen);
1015 enc_set_index(obj, idx);
1022 return rb_enc_associate_index(obj, rb_enc_to_index(enc));
1028 return rb_enc_from_index(rb_enc_get_index(obj));
1046 rb_encoding *enc = enc_compatible_str(MUST_STRING(str1), MUST_STRING(str2));
1047 return rb_encoding_check(enc, str1, str2);
1054 return rb_encoding_check(enc, str1, str2);
1058enc_compatible_latter(
VALUE str1,
VALUE str2,
int idx1,
int idx2)
1075 if (!isstr2 && idx2 == ENCINDEX_US_ASCII)
1077 if (!isstr1 && idx1 == ENCINDEX_US_ASCII)
1115 int idx1 = enc_get_index_str(str1);
1116 int idx2 = enc_get_index_str(str2);
1118 if (idx1 < 0 || idx2 < 0)
1122 return rb_enc_from_index(idx1);
1125 return enc_compatible_latter(str1, str2, idx1, idx2);
1132 int idx1 = rb_enc_get_index(str1);
1133 int idx2 = rb_enc_get_index(str2);
1135 if (idx1 < 0 || idx2 < 0)
1139 return rb_enc_from_index(idx1);
1142 return enc_compatible_latter(str1, str2, idx1, idx2);
1148 rb_enc_associate_index(obj1, rb_enc_get_index(obj2));
1162 int idx = rb_enc_get_index(obj);
1166 return rb_enc_from_encoding_index(idx & ENC_INDEX_MASK);
1172 return ONIGENC_MBC_ENC_LEN(enc, (UChar*)p, (UChar*)e);
1178 int n = ONIGENC_PRECISE_MBC_ENC_LEN(enc, (UChar*)p, (UChar*)e);
1183 return min <= e-p ? min : (int)(e-p);
1192 return ONIGENC_CONSTRUCT_MBCLEN_NEEDMORE(1);
1193 n = ONIGENC_PRECISE_MBC_ENC_LEN(enc, (UChar*)p, (UChar*)e);
1195 return ONIGENC_CONSTRUCT_MBCLEN_NEEDMORE(n-(
int)(e-p));
1200rb_enc_ascget(
const char *p,
const char *e,
int *len,
rb_encoding *enc)
1207 c = (
unsigned char)*p;
1213 l = rb_enc_precise_mbclen(p, e, enc);
1224rb_enc_codepoint_len(
const char *p,
const char *e,
int *len_p,
rb_encoding *enc)
1229 r = rb_enc_precise_mbclen(p, e, enc);
1240 int n = ONIGENC_CODE_TO_MBCLEN(enc,c);
1250 return (ONIGENC_IS_ASCII_CODE(c)?ONIGENC_ASCII_CODE_TO_UPPER_CASE(c):(c));
1256 return (ONIGENC_IS_ASCII_CODE(c)?ONIGENC_ASCII_CODE_TO_LOWER_CASE(c):(c));
1269enc_inspect(
VALUE self)
1273 if (!is_data_encoding(self)) {
1276 if (!(enc =
DATA_PTR(self)) || rb_enc_from_index(rb_enc_to_index(enc)) != enc) {
1282 (ENC_DUMMY_P(enc) ?
" (dummy)" :
""),
1283 rb_enc_autoload_p(enc) ?
" (autoload)" :
"");
1302enc_names_i(st_data_t name, st_data_t idx, st_data_t args)
1306 if ((
int)idx == (int)arg[0]) {
1307 VALUE str = rb_fstring_cstr((
char *)name);
1308 rb_ary_push(arg[1], str);
1322enc_names(
VALUE self)
1326 args[0] = (
VALUE)rb_to_encoding_index(self);
1328 st_foreach(global_enc_table.names, enc_names_i, (st_data_t)args);
1351enc_list(
VALUE klass)
1354 rb_ary_replace(ary, rb_encoding_list);
1384 if (is_obj_encoding(enc))
1386 idx = str_to_encindex(enc);
1387 if (idx == UNSPECIFIED_ENCODING)
return Qnil;
1388 return rb_enc_from_encoding_index(idx);
1420 if (!enc_capable(str1))
return Qnil;
1421 if (!enc_capable(str2))
return Qnil;
1422 enc = rb_enc_compatible(str1, str2);
1423 if (!enc)
return Qnil;
1424 return rb_enc_from_encoding(enc);
1427NORETURN(
static VALUE enc_s_alloc(
VALUE klass));
1430enc_s_alloc(
VALUE klass)
1432 rb_undefined_alloc(klass);
1441 return enc_name(self);
1455 return enc_find(klass, str);
1459rb_ascii8bit_encoding(
void)
1461 return global_enc_ascii;
1465rb_ascii8bit_encindex(
void)
1467 return ENCINDEX_ASCII_8BIT;
1471rb_utf8_encoding(
void)
1473 return global_enc_utf_8;
1477rb_utf8_encindex(
void)
1479 return ENCINDEX_UTF_8;
1483rb_usascii_encoding(
void)
1485 return global_enc_us_ascii;
1489rb_usascii_encindex(
void)
1491 return ENCINDEX_US_ASCII;
1494int rb_locale_charmap_index(
void);
1497rb_locale_encindex(
void)
1499 int idx = rb_locale_charmap_index();
1501 if (idx < 0) idx = ENCINDEX_UTF_8;
1503 if (enc_registered(&global_enc_table,
"locale") < 0) {
1505 void Init_w32_codepage(
void);
1506 Init_w32_codepage();
1510 enc_alias_internal(
enc_table,
"locale", idx);
1512 GLOBAL_ENC_TABLE_LEAVE();
1519rb_locale_encoding(
void)
1521 return rb_enc_from_index(rb_locale_encindex());
1525rb_filesystem_encindex(
void)
1527 int idx = enc_registered(&global_enc_table,
"filesystem");
1528 if (idx < 0) idx = ENCINDEX_ASCII_8BIT;
1533rb_filesystem_encoding(
void)
1535 return rb_enc_from_index(rb_filesystem_encindex());
1548 int overridden = FALSE;
1550 if (def->index != -2)
1556 if (
NIL_P(encoding)) {
1560 (st_data_t)UNSPECIFIED_ENCODING);
1563 def->index = rb_enc_to_index(rb_to_encoding(encoding));
1565 enc_alias_internal(
enc_table, name, def->index);
1568 if (def == &default_external) {
1569 enc_alias_internal(
enc_table,
"filesystem", Init_enc_set_filesystem_encoding());
1572 GLOBAL_ENC_TABLE_LEAVE();
1578rb_default_external_encoding(
void)
1580 if (default_external.enc)
return default_external.enc;
1582 if (default_external.index >= 0) {
1583 default_external.enc = rb_enc_from_index(default_external.index);
1584 return default_external.enc;
1587 return rb_locale_encoding();
1592rb_enc_default_external(
void)
1594 return rb_enc_from_encoding(rb_default_external_encoding());
1626get_default_external(
VALUE klass)
1628 return rb_enc_default_external();
1632rb_enc_set_default_external(
VALUE encoding)
1634 if (
NIL_P(encoding)) {
1637 enc_set_default_encoding(&default_external, encoding,
1655set_default_external(
VALUE klass,
VALUE encoding)
1657 rb_warning(
"setting Encoding.default_external");
1658 rb_enc_set_default_external(encoding);
1665rb_default_internal_encoding(
void)
1667 if (!default_internal.enc && default_internal.index >= 0) {
1668 default_internal.enc = rb_enc_from_index(default_internal.index);
1670 return default_internal.enc;
1674rb_enc_default_internal(
void)
1677 return rb_enc_from_encoding(rb_default_internal_encoding());
1709get_default_internal(
VALUE klass)
1711 return rb_enc_default_internal();
1715rb_enc_set_default_internal(
VALUE encoding)
1717 enc_set_default_encoding(&default_internal, encoding,
1735set_default_internal(
VALUE klass,
VALUE encoding)
1737 rb_warning(
"setting Encoding.default_internal");
1738 rb_enc_set_default_internal(encoding);
1743set_encoding_const(
const char *name,
rb_encoding *enc)
1745 VALUE encoding = rb_enc_from_encoding(enc);
1746 char *s = (
char *)name;
1747 int haslower = 0, hasupper = 0, valid = 0;
1752 while (*++s && (
ISALNUM(*s) || *s ==
'_')) {
1753 if (
ISLOWER(*s)) haslower = 1;
1757 if (s - name > ENCODING_NAMELEN_MAX)
return;
1761 if (!valid || haslower) {
1762 size_t len = s - name;
1763 if (len > ENCODING_NAMELEN_MAX)
return;
1764 if (!haslower || !hasupper) {
1766 if (
ISLOWER(*s)) haslower = 1;
1767 if (
ISUPPER(*s)) hasupper = 1;
1768 }
while (*++s && (!haslower || !hasupper));
1772 if (len++ > ENCODING_NAMELEN_MAX)
return;
1776 if (
ISLOWER(*s)) *s = ONIGENC_ASCII_CODE_TO_UPPER_CASE((
int)*s);
1785 for (s = (
char *)name; *s; ++s) {
1786 if (
ISLOWER(*s)) *s = ONIGENC_ASCII_CODE_TO_UPPER_CASE((
int)*s);
1794rb_enc_name_list_i(st_data_t name, st_data_t idx, st_data_t arg)
1797 VALUE str = rb_fstring_cstr((
char *)name);
1798 rb_ary_push(ary, str);
1817rb_enc_name_list(
VALUE klass)
1820 st_foreach(global_enc_table.names, rb_enc_name_list_i, (st_data_t)ary);
1825rb_enc_aliases_enc_i(st_data_t name, st_data_t orig, st_data_t arg)
1828 VALUE aliases = p[0], ary = p[1];
1829 int idx = (int)orig;
1830 VALUE key, str = rb_ary_entry(ary, idx);
1835 if (!enc)
return ST_CONTINUE;
1840 rb_ary_store(ary, idx, str);
1842 key = rb_fstring_cstr((
char *)name);
1843 rb_hash_aset(aliases, key, str);
1860rb_enc_aliases(
VALUE klass)
1863 aliases[0] = rb_hash_new();
1864 aliases[1] = rb_ary_new();
1866 st_foreach(global_enc_table.names, rb_enc_aliases_enc_i, (st_data_t)aliases);
1935 list = rb_encoding_list =
rb_ary_new2(ENCODING_LIST_CAPA);
1936 RBASIC_CLEAR_CLASS(list);
1937 rb_gc_register_mark_object(list);
1939 for (i = 0; i <
enc_table->count; ++i) {
1940 rb_ary_push(list, enc_new(
enc_table->list[i].enc));
1949 rb_enc_init(&global_enc_table);
1955rb_enc_foreach_name(
int (*func)(st_data_t name, st_data_t idx, st_data_t arg), st_data_t arg)
1957 st_foreach(global_enc_table.names, func, arg);
#define RUBY_ASSERT(expr)
Asserts that the given expression is truthy if and only if RUBY_DEBUG is truthy.
#define rb_define_method(klass, mid, func, arity)
Defines klass#mid.
#define rb_define_singleton_method(klass, mid, func, arity)
Defines klass.mid.
static bool rb_enc_isascii(OnigCodePoint c, rb_encoding *enc)
Identical to rb_isascii(), except it additionally takes an encoding.
VALUE rb_enc_sprintf(rb_encoding *enc, const char *fmt,...)
Identical to rb_sprintf(), except it additionally takes an encoding.
@ RUBY_FL_SHAREABLE
This flag has something to do with Ractor.
VALUE rb_define_class(const char *name, VALUE super)
Defines a top-level class.
void rb_undef_method(VALUE klass, const char *name)
Defines an undef of a method.
#define ENCODING_SET_INLINED(obj, i)
Old name of RB_ENCODING_SET_INLINED.
#define ENC_CODERANGE_7BIT
Old name of RUBY_ENC_CODERANGE_7BIT.
#define T_FILE
Old name of RUBY_T_FILE.
#define T_STRING
Old name of RUBY_T_STRING.
#define ISUPPER
Old name of rb_isupper.
#define SPECIAL_CONST_P
Old name of RB_SPECIAL_CONST_P.
#define UNREACHABLE_RETURN
Old name of RBIMPL_UNREACHABLE_RETURN.
#define T_DATA
Old name of RUBY_T_DATA.
#define CLASS_OF
Old name of rb_class_of.
#define xmalloc
Old name of ruby_xmalloc.
#define ISDIGIT
Old name of rb_isdigit.
#define ISLOWER
Old name of rb_islower.
#define ASSUME
Old name of RBIMPL_ASSUME.
#define MBCLEN_CHARFOUND_LEN(ret)
Old name of ONIGENC_MBCLEN_CHARFOUND_LEN.
#define ENCODING_INLINE_MAX
Old name of RUBY_ENCODING_INLINE_MAX.
#define STRCASECMP
Old name of st_locale_insensitive_strcasecmp.
#define ISASCII
Old name of rb_isascii.
#define TOLOWER
Old name of rb_tolower.
#define NUM2INT
Old name of RB_NUM2INT.
#define INT2NUM
Old name of RB_INT2NUM.
#define Qnil
Old name of RUBY_Qnil.
#define Qfalse
Old name of RUBY_Qfalse.
#define NIL_P
Old name of RB_NIL_P.
#define MBCLEN_CHARFOUND_P(ret)
Old name of ONIGENC_MBCLEN_CHARFOUND_P.
#define T_SYMBOL
Old name of RUBY_T_SYMBOL.
#define ENC_CODERANGE_ASCIIONLY(obj)
Old name of RB_ENC_CODERANGE_ASCIIONLY.
#define BUILTIN_TYPE
Old name of RB_BUILTIN_TYPE.
#define ENCODING_GET_INLINED(obj)
Old name of RB_ENCODING_GET_INLINED.
#define ENC_CODERANGE_CLEAR(obj)
Old name of RB_ENC_CODERANGE_CLEAR.
#define CONST_ID
Old name of RUBY_CONST_ID.
#define rb_ary_new2
Old name of rb_ary_new_capa.
#define ISALNUM
Old name of rb_isalnum.
#define FL_SET_RAW
Old name of RB_FL_SET_RAW.
#define SYMBOL_P
Old name of RB_SYMBOL_P.
#define T_REGEXP
Old name of RUBY_T_REGEXP.
#define ruby_debug
This variable controls whether the interpreter is in debug mode.
void rb_raise(VALUE exc, const char *fmt,...)
Exception entry point.
void rb_bug(const char *fmt,...)
Interpreter panic switch.
void rb_set_errinfo(VALUE err)
Sets the current exception ($!) to the given value.
VALUE rb_eTypeError
TypeError exception.
VALUE rb_eEncCompatError
Encoding::CompatibilityError exception.
void rb_warn(const char *fmt,...)
Identical to rb_warning(), except it reports always regardless of runtime -W flag.
VALUE rb_eArgError
ArgumentError exception.
void rb_loaderror(const char *fmt,...)
Raises an instance of rb_eLoadError.
VALUE rb_errinfo(void)
This is the same as $! in Ruby.
VALUE rb_eEncodingError
EncodingError exception.
void rb_warning(const char *fmt,...)
Issues a warning.
VALUE rb_obj_class(VALUE obj)
Queries the class of an object.
VALUE rb_cEncoding
Encoding class.
VALUE rb_obj_freeze(VALUE obj)
Just calls rb_obj_freeze_inline() inside.
static const char * rb_enc_name(rb_encoding *enc)
Queries the (canonical) name of the passed encoding.
VALUE rb_locale_charmap(VALUE klass)
Returns a platform-depended "charmap" of the current locale.
static bool rb_enc_asciicompat(rb_encoding *enc)
Queries if the passed encoding is in some sense compatible with ASCII.
static OnigCodePoint rb_enc_mbc_to_codepoint(const char *p, const char *e, rb_encoding *enc)
Identical to rb_enc_codepoint(), except it assumes the passed character is not broken.
static int rb_enc_mbminlen(rb_encoding *enc)
Queries the minimum number of bytes that the passed encoding needs to represent a character.
int rb_enc_str_coderange(VALUE str)
Scans the passed string to collect its code range.
int rb_enc_str_asciionly_p(VALUE str)
Queries if the passed string is "ASCII only".
#define rb_check_frozen
Just another name of rb_check_frozen.
static int rb_check_arity(int argc, int min, int max)
Ensures that the passed integer is in the passed range.
VALUE rb_check_string_type(VALUE obj)
Try converting an object to its stringised representation using its to_str method,...
VALUE rb_attr_get(VALUE obj, ID name)
Identical to rb_ivar_get()
VALUE rb_ivar_set(VALUE obj, ID name, VALUE val)
Identical to rb_iv_set(), except it accepts the name as an ID instead of a C string.
VALUE rb_ivar_get(VALUE obj, ID name)
Identical to rb_iv_get(), except it accepts the name as an ID instead of a C string.
void rb_define_alloc_func(VALUE klass, rb_alloc_func_t func)
Sets the allocator function of a class.
ID rb_intern(const char *name)
Finds or creates a symbol of the given name.
VALUE rb_sym2str(VALUE id)
Identical to rb_id2str(), except it takes an instance of rb_cSymbol rather than an ID.
void rb_define_const(VALUE klass, const char *name, VALUE val)
Defines a Ruby level constant under a namespace.
#define strdup(s)
Just another name of ruby_strdup.
VALUE rb_sprintf(const char *fmt,...)
Ruby's extended sprintf(3).
void rb_marshal_define_compat(VALUE newclass, VALUE oldclass, VALUE(*dumper)(VALUE), VALUE(*loader)(VALUE, VALUE))
Marshal format compatibility layer.
#define MEMCPY(p1, p2, type, n)
Handy macro to call memcpy.
#define ALLOCA_N(type, n)
#define RB_GC_GUARD(v)
Prevents premature destruction of local objects.
#define DATA_PTR(obj)
Convenient getter macro.
#define RDATA(obj)
Convenient casting macro.
#define StringValue(v)
Ensures that the parameter object is a String.
static char * RSTRING_END(VALUE str)
Queries the end of the contents pointer of the string.
static long RSTRING_LEN(VALUE str)
Queries the length of the string.
static char * RSTRING_PTR(VALUE str)
Queries the contents pointer of the string.
#define TypedData_Wrap_Struct(klass, data_type, sval)
Converts sval, a pointer to your struct, into a Ruby object.
This is the struct that holds necessary info for a struct.
uintptr_t ID
Type that represents a Ruby identifier such as a variable name.
uintptr_t VALUE
Type that represents a Ruby object.
static bool RB_TYPE_P(VALUE obj, enum ruby_value_type t)
Queries if the given object is of given type.