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

Update RegExp unicode mode case folding to conform to the standard (#4004)

Browse Source 
JerryScript-DCO-1.0-Signed-off-by: Dániel Bátyai daniel.batyai@h-lab.eu
This commit is contained in:
Dániel Bátyai
2020-07-20 15:51:43 +02:00
committed by GitHub
parent 33359ac506
commit 321215fdbb
9 changed files with 284 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files
jerry-core/lit/lit-char-helpers.c
+51
View File
@@ -23,6 +23,9 @@
#if ENABLED (JERRY_UNICODE_CASE_CONVERSION)
#include "lit-unicode-conversions.inc.h"
#include "lit-unicode-conversions-sup.inc.h"
#if ENABLED (JERRY_ESNEXT)
#include "lit-unicode-folding.inc.h"
#endif /* ENABLED (JERRY_ESNEXT) */
#endif /* ENABLED (JERRY_UNICODE_CASE_CONVERSION) */
#define NUM_OF_ELEMENTS(array) (sizeof (array) / sizeof ((array)[0]))
@@ -914,3 +917,51 @@ lit_char_to_upper_case (lit_code_point_t cp, /**< code point */
return cp;
#endif /* ENABLED (JERRY_UNICODE_CASE_CONVERSION) */
} /* lit_char_to_upper_case */
#if ENABLED (JERRY_ESNEXT)
/*
* Look up whether the character should be folded to the lowercase variant.
*
* @return true, if character should be lowercased
* false, otherwise
*/
bool
lit_char_fold_to_lower (lit_code_point_t cp) /**< code point */
{
#if ENABLED (JERRY_UNICODE_CASE_CONVERSION)
return (cp > LIT_UTF16_CODE_UNIT_MAX
|| (!lit_search_char_in_interval_array ((ecma_char_t) cp,
lit_unicode_folding_skip_to_lower_interval_starts,
lit_unicode_folding_skip_to_lower_interval_lengths,
NUM_OF_ELEMENTS (lit_unicode_folding_skip_to_lower_interval_starts))
&& !lit_search_char_in_array ((ecma_char_t) cp,
lit_unicode_folding_skip_to_lower_chars,
NUM_OF_ELEMENTS (lit_unicode_folding_skip_to_lower_chars))));
#else /* !ENABLED (JERRY_UNICODE_CASE_CONVERSION) */
return true;
#endif /* ENABLED (JERRY_UNICODE_CASE_CONVERSION) */
} /* lit_char_fold_to_lower */
/*
* Look up whether the character should be folded to the uppercase variant.
*
* @return true, if character should be uppercased
* false, otherwise
*/
bool
lit_char_fold_to_upper (lit_code_point_t cp) /**< code point */
{
#if ENABLED (JERRY_UNICODE_CASE_CONVERSION)
return (cp <= LIT_UTF16_CODE_UNIT_MAX
&& (lit_search_char_in_interval_array ((ecma_char_t) cp,
lit_unicode_folding_to_upper_interval_starts,
lit_unicode_folding_to_upper_interval_lengths,
NUM_OF_ELEMENTS (lit_unicode_folding_to_upper_interval_starts))
|| lit_search_char_in_array ((ecma_char_t) cp,
lit_unicode_folding_to_upper_chars,
NUM_OF_ELEMENTS (lit_unicode_folding_to_upper_chars))));
#else /* !ENABLED (JERRY_UNICODE_CASE_CONVERSION) */
return false;
#endif /* ENABLED (JERRY_UNICODE_CASE_CONVERSION) */
} /* lit_char_fold_to_upper */
#endif /* ENABLED (JERRY_ESNEXT) */