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/parser/regexp/re-compiler.c
+6 -6
View File
@@ -272,7 +272,7 @@ re_parse_char_class (re_compiler_ctx_t *re_ctx_p, /**< number of classes */
const bool is_char_class = (re_ctx_p->current_token.type == RE_TOK_START_CHAR_CLASS
|| re_ctx_p->current_token.type == RE_TOK_START_INV_CHAR_CLASS);
const ecma_char_t prev_char = lit_utf8_peek_prev (parser_ctx_p->input_curr_p);
const ecma_char_t prev_char = lit_cesu8_peek_prev (parser_ctx_p->input_curr_p);
if (prev_char != LIT_CHAR_LEFT_SQUARE && prev_char != LIT_CHAR_CIRCUMFLEX)
{
lit_utf8_decr (&parser_ctx_p->input_curr_p);
@@ -286,7 +286,7 @@ re_parse_char_class (re_compiler_ctx_t *re_ctx_p, /**< number of classes */
return ecma_raise_syntax_error (ECMA_ERR_MSG ("invalid character class, end of string"));
}
lit_code_point_t ch = lit_utf8_read_next (&parser_ctx_p->input_curr_p);
lit_code_point_t ch = lit_cesu8_read_next (&parser_ctx_p->input_curr_p);
if (ch == LIT_CHAR_RIGHT_SQUARE)
{
@@ -318,7 +318,7 @@ re_parse_char_class (re_compiler_ctx_t *re_ctx_p, /**< number of classes */
return ecma_raise_syntax_error (ECMA_ERR_MSG ("invalid character class, end of string after '\\'"));
}
ch = lit_utf8_read_next (&parser_ctx_p->input_curr_p);
ch = lit_cesu8_read_next (&parser_ctx_p->input_curr_p);
if (ch == LIT_CHAR_LOWERCASE_B)
{
@@ -376,7 +376,7 @@ re_parse_char_class (re_compiler_ctx_t *re_ctx_p, /**< number of classes */
parser_ctx_p->input_curr_p += 2;
if (parser_ctx_p->input_curr_p < parser_ctx_p->input_end_p
&& is_range == false
&& lit_utf8_peek_next (parser_ctx_p->input_curr_p) == LIT_CHAR_MINUS)
&& lit_cesu8_peek_next (parser_ctx_p->input_curr_p) == LIT_CHAR_MINUS)
{
start = code_unit;
continue;
@@ -396,7 +396,7 @@ re_parse_char_class (re_compiler_ctx_t *re_ctx_p, /**< number of classes */
parser_ctx_p->input_curr_p += 4;
if (parser_ctx_p->input_curr_p < parser_ctx_p->input_end_p
&& is_range == false
&& lit_utf8_peek_next (parser_ctx_p->input_curr_p) == LIT_CHAR_MINUS)
&& lit_cesu8_peek_next (parser_ctx_p->input_curr_p) == LIT_CHAR_MINUS)
{
start = code_unit;
continue;
@@ -481,7 +481,7 @@ re_parse_char_class (re_compiler_ctx_t *re_ctx_p, /**< number of classes */
&& lit_is_code_point_utf16_high_surrogate (ch)
&& parser_ctx_p->input_curr_p < parser_ctx_p->input_end_p)
{
const ecma_char_t next_ch = lit_utf8_peek_next (parser_ctx_p->input_curr_p);
const ecma_char_t next_ch = lit_cesu8_peek_next (parser_ctx_p->input_curr_p);
if (lit_is_code_point_utf16_low_surrogate (next_ch))
{
ch = lit_convert_surrogate_pair_to_code_point ((ecma_char_t) ch, next_ch);
jerry-core/parser/regexp/re-parser.c
+2 -2
View File
@@ -315,7 +315,7 @@ re_parse_next_token (re_parser_ctx_t *parser_ctx_p, /**< RegExp parser context *
return ret_value;
}
ecma_char_t ch = lit_utf8_read_next (&parser_ctx_p->input_curr_p);
ecma_char_t ch = lit_cesu8_read_next (&parser_ctx_p->input_curr_p);
switch (ch)
{
@@ -348,7 +348,7 @@ re_parse_next_token (re_parser_ctx_t *parser_ctx_p, /**< RegExp parser context *
}
out_token_p->type = RE_TOK_CHAR;
ch = lit_utf8_read_next (&parser_ctx_p->input_curr_p);
ch = lit_cesu8_read_next (&parser_ctx_p->input_curr_p);
if (ch == LIT_CHAR_LOWERCASE_B)
{