Give names to Unicode code points in C code

* src/character.h (NO_BREAK_SPACE, SOFT_HYPHEN)
(ZERO_WIDTH_NON_JOINER, ZERO_WIDTH_JOINER, HYPHEN)
(NON_BREAKING_HYPHEN, LEFT_SINGLE_QUOTATION_MARK)
(RIGHT_SINGLE_QUOTATION_MARK, PARAGRAPH_SEPARATOR)
(LEFT_POINTING_ANGLE_BRACKET, RIGHT_POINTING_ANGLE_BRACKET)
(LEFT_ANGLE_BRACKET, RIGHT_ANGLE_BRACKET)
(OBJECT_REPLACEMENT_CHARACTER):
New named constants for Unicode code points.
* src/bidi.c (bidi_fetch_char, CANONICAL_EQU):
* src/composite.c (char_composable_p):
* src/lread.c (readevalloop, read1):
* src/xdisp.c (get_next_display_element):
Use them.
* src/doc.c (LEFT_SINGLE_QUOTATION_POINT):
Remove; now in character.h.
This commit is contained in:
Paul Eggert 2015-08-11 15:53:18 -07:00
parent 85f7e5115f
commit d6640d6e4c
6 changed files with 31 additions and 12 deletions

View file

@ -1313,13 +1313,13 @@ bidi_fetch_char (ptrdiff_t charpos, ptrdiff_t bytepos, ptrdiff_t *disp_pos,
/* `(space ...)' display specs are handled as paragraph
separators for the purposes of the reordering; see UAX#9
section 3 and clause HL1 in section 4.3 there. */
ch = 0x2029;
ch = PARAGRAPH_SEPARATOR;
}
else
{
/* All other display specs are handled as the Unicode Object
Replacement Character. */
ch = 0xFFFC;
ch = OBJECT_REPLACEMENT_CHARACTER;
}
disp_end_pos = compute_display_string_end (*disp_pos, string);
if (disp_end_pos < 0)
@ -2482,8 +2482,8 @@ typedef struct bpa_stack_entry {
#define CANONICAL_EQU(c) \
( ASCII_CHAR_P (c) ? c \
: (c) == 0x2329 ? 0x3008 \
: (c) == 0x232a ? 0x3009 \
: (c) == LEFT_POINTING_ANGLE_BRACKET ? LEFT_ANGLE_BRACKET \
: (c) == RIGHT_POINTING_ANGLE_BRACKET ? RIGHT_ANGLE_BRACKET \
: c )
#ifdef ENABLE_CHECKING

View file

@ -59,6 +59,25 @@ INLINE_HEADER_BEGIN
/* Maximum leading code of multibyte characters. */
#define MAX_MULTIBYTE_LEADING_CODE 0xF8
/* Unicode character values. */
enum
{
NO_BREAK_SPACE = 0x00A0,
SOFT_HYPHEN = 0x00AD,
ZERO_WIDTH_NON_JOINER = 0x200C,
ZERO_WIDTH_JOINER = 0x200D,
HYPHEN = 0x2010,
NON_BREAKING_HYPHEN = 0x2011,
LEFT_SINGLE_QUOTATION_MARK = 0x2018,
RIGHT_SINGLE_QUOTATION_MARK = 0x2019,
PARAGRAPH_SEPARATOR = 0x2029,
LEFT_POINTING_ANGLE_BRACKET = 0x2329,
RIGHT_POINTING_ANGLE_BRACKET = 0x232A,
LEFT_ANGLE_BRACKET = 0x3008,
RIGHT_ANGLE_BRACKET = 0x3009,
OBJECT_REPLACEMENT_CHARACTER = 0xFFFC,
};
/* Nonzero iff C is a character that corresponds to a raw 8-bit
byte. */
#define CHAR_BYTE8_P(c) ((c) > MAX_5_BYTE_CHAR)

View file

@ -927,7 +927,7 @@ char_composable_p (int c)
{
Lisp_Object val;
return (c > ' '
&& (c == 0x200C || c == 0x200D
&& (c == ZERO_WIDTH_NON_JOINER || c == ZERO_WIDTH_JOINER
|| (val = CHAR_TABLE_REF (Vunicode_category_table, c),
(INTEGERP (val) && (XINT (val) <= UNICODE_CATEGORY_So)))));
}

View file

@ -689,7 +689,6 @@ the same file name is found in the `doc-directory'. */)
"\xE2\x80\x98" and "\xE2\x80\x99", respectively. */
enum
{
LEFT_SINGLE_QUOTATION_MARK = 0x2018,
uLSQM0 = 0xE2, uLSQM1 = 0x80, uLSQM2 = 0x98,
uRSQM0 = 0xE2, uRSQM1 = 0x80, uRSQM2 = 0x99,
};

View file

@ -1885,7 +1885,7 @@ readevalloop (Lisp_Object readcharfun,
/* Ignore whitespace here, so we can detect eof. */
if (c == ' ' || c == '\t' || c == '\n' || c == '\f' || c == '\r'
|| c == 0xa0) /* NBSP */
|| c == NO_BREAK_SPACE)
goto read_next;
if (!NILP (Vpurify_flag) && c == '(')
@ -2793,7 +2793,7 @@ read1 (Lisp_Object readcharfun, int *pch, bool first_in_list)
uninterned_symbol = 1;
c = READCHAR;
if (!(c > 040
&& c != 0xa0 /* NBSP */
&& c != NO_BREAK_SPACE
&& (c >= 0200
|| strchr ("\"';()[]#`,", c) == NULL)))
{
@ -3127,7 +3127,7 @@ read1 (Lisp_Object readcharfun, int *pch, bool first_in_list)
default:
default_label:
if (c <= 040) goto retry;
if (c == 0xa0) /* NBSP */
if (c == NO_BREAK_SPACE)
goto retry;
read_symbol:
@ -3167,7 +3167,7 @@ read1 (Lisp_Object readcharfun, int *pch, bool first_in_list)
c = READCHAR;
}
while (c > 040
&& c != 0xa0 /* NBSP */
&& c != NO_BREAK_SPACE
&& (c >= 0200
|| strchr ("\"';()[]#`,", c) == NULL));

View file

@ -6890,9 +6890,10 @@ get_next_display_element (struct it *it)
non-ASCII spaces and hyphens specially. */
if (! ASCII_CHAR_P (c) && ! NILP (Vnobreak_char_display))
{
if (c == 0xA0)
if (c == NO_BREAK_SPACE)
nonascii_space_p = true;
else if (c == 0xAD || c == 0x2010 || c == 0x2011)
else if (c == SOFT_HYPHEN || c == HYPHEN
|| c == NON_BREAKING_HYPHEN)
nonascii_hyphen_p = true;
}