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

Improvements related to lexer

Browse Source 
Improvements related to lexer:

* duplicated clone elimination
* magic numbers are replaced with constants
* functions are moved form util to lit-char-helpers

JerryScript-DCO-1.0-Signed-off-by: István Kádár ikadar@inf.u-szeged.hu
This commit is contained in:
Istvan Kadar
2016-04-14 10:26:36 +02:00
committed by Akos Kiss
parent c7dcce4fc7
commit ecfd478df0
9 changed files with 424 additions and 388 deletions
Download Patch File Download Diff File Expand all files Collapse all files
jerry-core/parser/js/common.c
-127
View File
@@ -16,7 +16,6 @@
#include "common.h"
#include "ecma-helpers.h"
#include "lit-char-helpers.h"
/** \addtogroup parser Parser
* @{
@@ -28,132 +27,6 @@
* @{
*/
/**
* Checks whether the next UTF8 character is a valid identifier start.
*
* @return non-zero if it is.
*/
int
util_is_identifier_start (const uint8_t *src_p) /* pointer to a vaild UTF8 character */
{
if (*src_p <= 127)
{
return util_is_identifier_start_character (*src_p);
}
return util_is_identifier_start_character (lit_utf8_peek_next (src_p));
} /* util_is_identifier_start */
/**
* Checks whether the next UTF8 character is a valid identifier part.
*
* @return non-zero if it is.
*/
int
util_is_identifier_part (const uint8_t *src_p) /* pointer to a vaild UTF8 character */
{
if (*src_p <= 127)
{
return util_is_identifier_part_character (*src_p);
}
return util_is_identifier_part_character (lit_utf8_peek_next (src_p));
} /* util_is_identifier_part */
/**
* Checks whether the character is a valid identifier start.
*
* @return non-zero if it is.
*/
int
util_is_identifier_start_character (uint16_t chr) /**< EcmaScript character */
{
if (chr <= 127)
{
return (((chr | 0x20) >= LIT_CHAR_LOWERCASE_A && (chr | 0x20) <= LIT_CHAR_LOWERCASE_Z)
|| chr == LIT_CHAR_DOLLAR_SIGN
|| chr == LIT_CHAR_UNDERSCORE);
}
return lit_char_is_unicode_letter (chr);
} /* util_is_identifier_start_character */
/**
* Checks whether the character is a valid identifier part.
*
* @return non-zero if it is.
*/
int
util_is_identifier_part_character (uint16_t chr) /**< EcmaScript character */
{
if (chr <= 127)
{
return (((chr | 0x20) >= LIT_CHAR_LOWERCASE_A && (chr | 0x20) <= LIT_CHAR_LOWERCASE_Z)
|| (chr >= LIT_CHAR_0 && chr <= LIT_CHAR_9)
|| chr == LIT_CHAR_DOLLAR_SIGN
|| chr == LIT_CHAR_UNDERSCORE);
}
return (lit_char_is_unicode_letter (chr)
|| lit_char_is_unicode_non_letter_ident_part (chr));
} /* util_is_identifier_part_character */
/**
* Converts a character to UTF8 bytes.
*
* @return length of the UTF8 representation.
*/
size_t
util_to_utf8_bytes (uint8_t *dst_p, /**< destination buffer */
uint16_t chr) /**< EcmaScript character */
{
if (!(chr & ~0x007f))
{
/* 00000000 0xxxxxxx -> 0xxxxxxx */
*dst_p = (uint8_t) chr;
return 1;
}
if (!(chr & ~0x07ff))
{
/* 00000yyy yyxxxxxx -> 110yyyyy 10xxxxxx */
*(dst_p++) = (uint8_t) (0xc0 | ((chr >> 6) & 0x1f));
*dst_p = (uint8_t) (0x80 | (chr & 0x3f));
return 2;
}
/* zzzzyyyy yyxxxxxx -> 1110zzzz 10yyyyyy 10xxxxxx */
*(dst_p++) = (uint8_t) (0xe0 | ((chr >> 12) & 0x0f));
*(dst_p++) = (uint8_t) (0x80 | ((chr >> 6) & 0x3f));
*dst_p = (uint8_t) (0x80 | (chr & 0x3f));
return 3;
} /* util_to_utf8_bytes */
/**
* Returns the length of the UTF8 representation of a character.
*
* @return length of the UTF8 representation.
*/
size_t
util_get_utf8_length (uint16_t chr) /**< EcmaScript character */
{
if (!(chr & ~0x007f))
{
/* 00000000 0xxxxxxx */
return 1;
}
if (!(chr & ~0x07ff))
{
/* 00000yyy yyxxxxxx */
return 2;
}
/* zzzzyyyy yyxxxxxx */
return 3;
} /* util_get_utf8_length */
/**
* Free literal.
*/