YourWishes/jerryscript
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Implement \u{hex} support. (#3447)

Browse Source 
A large rework because surrogate pairs must be combined.

Currently only the 0x10C80..0x10CF2 is accepted as valid identifier character from the non-basic plane.

JerryScript-DCO-1.0-Signed-off-by: Zoltan Herczeg zherczeg.u-szeged@partner.samsung.com
This commit is contained in:
Zoltan Herczeg
2019-12-16 11:26:02 +01:00
committed by Dániel Bátyai
parent 1db16c3a1c
commit 40d930d62c
22 changed files with 765 additions and 370 deletions
Download Patch File Download Diff File Expand all files Collapse all files
jerry-core/ecma/base/ecma-helpers-string.c
+5 -12
View File
@@ -461,16 +461,9 @@ ecma_new_ecma_string_from_utf8_converted_to_cesu8 (const lit_utf8_byte_t *string
if ((string_p[pos] & LIT_UTF8_4_BYTE_MASK) == LIT_UTF8_4_BYTE_MARKER)
{
/* Processing 4 byte unicode sequence. Always converted to two 3 byte long sequence. */
uint32_t character = ((((uint32_t) string_p[pos++]) & 0x7) << 18);
character |= ((((uint32_t) string_p[pos++]) & LIT_UTF8_LAST_6_BITS_MASK) << 12);
character |= ((((uint32_t) string_p[pos++]) & LIT_UTF8_LAST_6_BITS_MASK) << 6);
character |= (((uint32_t) string_p[pos++]) & LIT_UTF8_LAST_6_BITS_MASK);
JERRY_ASSERT (character >= 0x10000);
character -= 0x10000;
data_p += lit_char_to_utf8_bytes (data_p, (ecma_char_t) (0xd800 | (character >> 10)));
data_p += lit_char_to_utf8_bytes (data_p, (ecma_char_t) (0xdc00 | (character & LIT_UTF16_LAST_10_BITS_MASK)));
lit_four_byte_utf8_char_to_cesu8 (data_p, string_p + pos);
data_p += 3 * 2;
pos += 4;
}
else
{
@@ -2683,10 +2676,10 @@ void
ecma_stringbuilder_append_char (ecma_stringbuilder_t *builder_p, /**< string builder */
const ecma_char_t c) /**< ecma char */
{
const lit_utf8_size_t size = (lit_utf8_size_t) lit_char_get_utf8_length (c);
const lit_utf8_size_t size = (lit_utf8_size_t) lit_code_point_get_cesu8_length (c);
lit_utf8_byte_t *dest_p = ecma_stringbuilder_grow (builder_p, size);
lit_char_to_utf8_bytes (dest_p, c);
lit_code_point_to_cesu8_bytes (dest_p, c);
} /* ecma_stringbuilder_append_char */
/**