luc14n0/glib
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/glib.git synced 2025-03-23 16:10:03 +01:00
Code Issues Packages Projects Releases Wiki Activity

Use bit hacks instead when checking a general category value against

Browse Source 
2005-11-09  Behdad Esfahbod  <behdad@gnome.org>

        * glib/guniprop.c: Use bit hacks instead when checking a general
        category value against multiple values.

        * glib/gutf8.c: Change ISO10646 to Unicode in docs.
This commit is contained in:
Behdad Esfahbod 2005-11-10 01:15:11 +00:00 committed by Behdad Esfahbod
parent 5fd0cf735c
commit 8bd94d0eb8
5 changed files with 105 additions and 56 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
ChangeLog
View File

@ -1,3 +1,10 @@
2005-11-09 Behdad Esfahbod <behdad@gnome.org>
* glib/guniprop.c: Use bit hacks instead when checking a general
category value against multiple values.
* glib/gutf8.c: Change ISO10646 to Unicode in docs.
2005-11-10 Simos Xenitellis <simos@gnome.org> 2005-11-10 Simos Xenitellis <simos@gnome.org>
* configure.in: Added tt (Tatar) to ALL_LINGUAS. * configure.in: Added tt (Tatar) to ALL_LINGUAS.

7
ChangeLog.pre-2-10
View File

@ -1,3 +1,10 @@
2005-11-09 Behdad Esfahbod <behdad@gnome.org>
* glib/guniprop.c: Use bit hacks instead when checking a general
category value against multiple values.
* glib/gutf8.c: Change ISO10646 to Unicode in docs.
2005-11-10 Simos Xenitellis <simos@gnome.org> 2005-11-10 Simos Xenitellis <simos@gnome.org>
* configure.in: Added tt (Tatar) to ALL_LINGUAS. * configure.in: Added tt (Tatar) to ALL_LINGUAS.

7
ChangeLog.pre-2-12
View File

@ -1,3 +1,10 @@
2005-11-09 Behdad Esfahbod <behdad@gnome.org>
* glib/guniprop.c: Use bit hacks instead when checking a general
category value against multiple values.
* glib/gutf8.c: Change ISO10646 to Unicode in docs.
2005-11-10 Simos Xenitellis <simos@gnome.org> 2005-11-10 Simos Xenitellis <simos@gnome.org>
* configure.in: Added tt (Tatar) to ALL_LINGUAS. * configure.in: Added tt (Tatar) to ALL_LINGUAS.

124
glib/guniprop.c
View File

@ -56,20 +56,37 @@
: G_UNICODE_UNASSIGNED)) : G_UNICODE_UNASSIGNED))
#define ISDIGIT(Type) ((Type) == G_UNICODE_DECIMAL_NUMBER \ #define IS(Type, Class) (((guint)1 << (Type)) & (Class))
|| (Type) == G_UNICODE_LETTER_NUMBER \ #define OR(Type, Rest) (((guint)1 << (Type)) | (Rest))
|| (Type) == G_UNICODE_OTHER_NUMBER)
#define ISALPHA(Type) ((Type) == G_UNICODE_LOWERCASE_LETTER \
|| (Type) == G_UNICODE_UPPERCASE_LETTER \
|| (Type) == G_UNICODE_TITLECASE_LETTER \
|| (Type) == G_UNICODE_MODIFIER_LETTER \
|| (Type) == G_UNICODE_OTHER_LETTER)
#define ISMARK(Type) ((Type) == G_UNICODE_NON_SPACING_MARK || \
(Type) == G_UNICODE_COMBINING_MARK || \
(Type) == G_UNICODE_ENCLOSING_MARK)
#define ISDIGIT(Type) IS ((Type), \
OR (G_UNICODE_DECIMAL_NUMBER, \
OR (G_UNICODE_LETTER_NUMBER, \
OR (G_UNICODE_OTHER_NUMBER, 0))))
#define ISALPHA(Type) IS ((Type), \
OR (G_UNICODE_LOWERCASE_LETTER, \
OR (G_UNICODE_UPPERCASE_LETTER, \
OR (G_UNICODE_TITLECASE_LETTER, \
OR (G_UNICODE_MODIFIER_LETTER, \
OR (G_UNICODE_OTHER_LETTER, 0))))))
#define ISALDIGIT(Type) IS ((Type), \
OR (G_UNICODE_DECIMAL_NUMBER, \
OR (G_UNICODE_LETTER_NUMBER, \
OR (G_UNICODE_OTHER_NUMBER, \
OR (G_UNICODE_LOWERCASE_LETTER, \
OR (G_UNICODE_UPPERCASE_LETTER, \
OR (G_UNICODE_TITLECASE_LETTER, \
OR (G_UNICODE_MODIFIER_LETTER, \
OR (G_UNICODE_OTHER_LETTER, 0)))))))))
#define ISMARK(Type) IS ((Type), \
OR (G_UNICODE_NON_SPACING_MARK, \
OR (G_UNICODE_COMBINING_MARK, \
OR (G_UNICODE_ENCLOSING_MARK, 0))))
/** /**
* g_unichar_isalnum: * g_unichar_isalnum:
@ -84,8 +101,7 @@
gboolean gboolean
g_unichar_isalnum (gunichar c) g_unichar_isalnum (gunichar c)
{ {
int t = TYPE (c); return ISALDIGIT (TYPE (c)) ? TRUE : FALSE;
return ISDIGIT (t) || ISALPHA (t);
} }
/** /**
@ -101,8 +117,7 @@ g_unichar_isalnum (gunichar c)
gboolean gboolean
g_unichar_isalpha (gunichar c) g_unichar_isalpha (gunichar c)
{ {
int t = TYPE (c); return ISALPHA (TYPE (c)) ? TRUE : FALSE;
return ISALPHA (t);
} }
@ -154,13 +169,14 @@ g_unichar_isdigit (gunichar c)
gboolean gboolean
g_unichar_isgraph (gunichar c) g_unichar_isgraph (gunichar c)
{ {
int t = TYPE (c); return !IS (TYPE(c),
return (t != G_UNICODE_CONTROL OR (G_UNICODE_CONTROL,
&& t != G_UNICODE_FORMAT OR (G_UNICODE_FORMAT,
&& t != G_UNICODE_UNASSIGNED OR (G_UNICODE_UNASSIGNED,
&& t != G_UNICODE_PRIVATE_USE OR (G_UNICODE_PRIVATE_USE,
&& t != G_UNICODE_SURROGATE OR (G_UNICODE_SURROGATE,
&& t != G_UNICODE_SPACE_SEPARATOR); OR (G_UNICODE_SPACE_SEPARATOR,
0)))))));
} }
/** /**
@ -194,12 +210,13 @@ g_unichar_islower (gunichar c)
gboolean gboolean
g_unichar_isprint (gunichar c) g_unichar_isprint (gunichar c)
{ {
int t = TYPE (c); return !IS (TYPE(c),
return (t != G_UNICODE_CONTROL OR (G_UNICODE_CONTROL,
&& t != G_UNICODE_FORMAT OR (G_UNICODE_FORMAT,
&& t != G_UNICODE_UNASSIGNED OR (G_UNICODE_UNASSIGNED,
&& t != G_UNICODE_PRIVATE_USE OR (G_UNICODE_PRIVATE_USE,
&& t != G_UNICODE_SURROGATE); OR (G_UNICODE_SURROGATE,
0))))));
} }
/** /**
@ -215,13 +232,19 @@ g_unichar_isprint (gunichar c)
gboolean gboolean
g_unichar_ispunct (gunichar c) g_unichar_ispunct (gunichar c)
{ {
int t = TYPE (c); return IS (TYPE(c),
return (t == G_UNICODE_CONNECT_PUNCTUATION || t == G_UNICODE_DASH_PUNCTUATION OR (G_UNICODE_CONNECT_PUNCTUATION,
|| t == G_UNICODE_CLOSE_PUNCTUATION || t == G_UNICODE_FINAL_PUNCTUATION OR (G_UNICODE_DASH_PUNCTUATION,
|| t == G_UNICODE_INITIAL_PUNCTUATION || t == G_UNICODE_OTHER_PUNCTUATION OR (G_UNICODE_CLOSE_PUNCTUATION,
|| t == G_UNICODE_OPEN_PUNCTUATION || t == G_UNICODE_CURRENCY_SYMBOL OR (G_UNICODE_FINAL_PUNCTUATION,
|| t == G_UNICODE_MODIFIER_SYMBOL || t == G_UNICODE_MATH_SYMBOL OR (G_UNICODE_INITIAL_PUNCTUATION,
|| t == G_UNICODE_OTHER_SYMBOL); OR (G_UNICODE_OTHER_PUNCTUATION,
OR (G_UNICODE_OPEN_PUNCTUATION,
OR (G_UNICODE_CURRENCY_SYMBOL,
OR (G_UNICODE_MODIFIER_SYMBOL,
OR (G_UNICODE_MATH_SYMBOL,
OR (G_UNICODE_OTHER_SYMBOL,
0)))))))))))) ? TRUE : FALSE;
} }
/** /**
@ -236,7 +259,7 @@ g_unichar_ispunct (gunichar c)
* Pango or equivalent to get word breaking right, the algorithm * Pango or equivalent to get word breaking right, the algorithm
* is fairly complex.) * is fairly complex.)
* *
* Return value: %TRUE if @c is a punctuation character * Return value: %TRUE if @c is a space character
**/ **/
gboolean gboolean
g_unichar_isspace (gunichar c) g_unichar_isspace (gunichar c)
@ -253,9 +276,11 @@ g_unichar_isspace (gunichar c)
default: default:
{ {
int t = TYPE (c); return IS (TYPE(c),
return (t == G_UNICODE_SPACE_SEPARATOR || t == G_UNICODE_LINE_SEPARATOR OR (G_UNICODE_SPACE_SEPARATOR,
|| t == G_UNICODE_PARAGRAPH_SEPARATOR); OR (G_UNICODE_LINE_SEPARATOR,
OR (G_UNICODE_PARAGRAPH_SEPARATOR,
0)))) ? TRUE : FALSE;
} }
break; break;
} }
@ -309,10 +334,9 @@ g_unichar_istitle (gunichar c)
gboolean gboolean
g_unichar_isxdigit (gunichar c) g_unichar_isxdigit (gunichar c)
{ {
int t = TYPE (c);
return ((c >= 'a' && c <= 'f') return ((c >= 'a' && c <= 'f')
|| (c >= 'A' && c <= 'F') || (c >= 'A' && c <= 'F')
|| ISDIGIT (t)); || ISDIGIT (TYPE (c)));
} }
/** /**
@ -327,8 +351,7 @@ g_unichar_isxdigit (gunichar c)
gboolean gboolean
g_unichar_isdefined (gunichar c) g_unichar_isdefined (gunichar c)
{ {
int t = TYPE (c); return TYPE (c) != G_UNICODE_UNASSIGNED;
return t != G_UNICODE_UNASSIGNED;
} }
/** /**
@ -567,9 +590,8 @@ output_marks (const char **p_inout,
while (*p) while (*p)
{ {
gunichar c = g_utf8_get_char (p); gunichar c = g_utf8_get_char (p);
int t = TYPE(c);
if (ISMARK(t)) if (ISMARK (TYPE (c)))
{ {
if (!remove_dot || c != 0x307 /* COMBINING DOT ABOVE */) if (!remove_dot || c != 0x307 /* COMBINING DOT ABOVE */)
len += g_unichar_to_utf8 (c, out_buffer ? out_buffer + len : NULL); len += g_unichar_to_utf8 (c, out_buffer ? out_buffer + len : NULL);
@ -673,7 +695,10 @@ real_toupper (const gchar *str,
/* And output as GREEK CAPITAL LETTER IOTA */ /* And output as GREEK CAPITAL LETTER IOTA */
len += g_unichar_to_utf8 (0x399, out_buffer ? out_buffer + len : NULL); len += g_unichar_to_utf8 (0x399, out_buffer ? out_buffer + len : NULL);
} }
else if (t == G_UNICODE_LOWERCASE_LETTER || t == G_UNICODE_TITLECASE_LETTER) else if (IS (t,
OR (G_UNICODE_LOWERCASE_LETTER,
OR (G_UNICODE_TITLECASE_LETTER,
0))))
{ {
val = ATTTABLE (c >> 8, c & 0xff); val = ATTTABLE (c >> 8, c & 0xff);
@ -855,7 +880,10 @@ real_tolower (const gchar *str,
len += g_unichar_to_utf8 (val, out_buffer ? out_buffer + len : NULL); len += g_unichar_to_utf8 (val, out_buffer ? out_buffer + len : NULL);
} }
else if (t == G_UNICODE_UPPERCASE_LETTER || t == G_UNICODE_TITLECASE_LETTER) else if (IS (t,
OR (G_UNICODE_UPPERCASE_LETTER,
OR (G_UNICODE_TITLECASE_LETTER,
0))))
{ {
val = ATTTABLE (c >> 8, c & 0xff); val = ATTTABLE (c >> 8, c & 0xff);
@ -998,7 +1026,7 @@ g_utf8_casefold (const gchar *str,
/** /**
* g_unichar_get_mirror_char: * g_unichar_get_mirror_char:
* @ch: a unicode character * @ch: a Unicode character
* @mirrored_ch: location to store the mirrored character * @mirrored_ch: location to store the mirrored character
* *
* In Unicode, some characters are <firstterm>mirrored</firstterm>. This * In Unicode, some characters are <firstterm>mirrored</firstterm>. This

10
glib/gutf8.c
View File

@ -523,7 +523,7 @@ g_get_charset (G_CONST_RETURN char **charset)
/** /**
* g_unichar_to_utf8: * g_unichar_to_utf8:
* @c: a ISO10646 character code * @c: a Unicode character code
* @outbuf: output buffer, must have at least 6 bytes of space. * @outbuf: output buffer, must have at least 6 bytes of space.
* If %NULL, the length will be computed and returned * If %NULL, the length will be computed and returned
* and nothing will be written to @outbuf. * and nothing will be written to @outbuf.
@ -589,9 +589,9 @@ g_unichar_to_utf8 (gunichar c,
* g_utf8_strchr: * g_utf8_strchr:
* @p: a nul-terminated UTF-8 encoded string * @p: a nul-terminated UTF-8 encoded string
* @len: the maximum length of @p * @len: the maximum length of @p
* @c: a ISO10646 character * @c: a Unicode character
* *
* Finds the leftmost occurrence of the given ISO10646 character * Finds the leftmost occurrence of the given Unicode character
* in a UTF-8 encoded string, while limiting the search to @len bytes. * in a UTF-8 encoded string, while limiting the search to @len bytes.
* If @len is -1, allow unbounded search. * If @len is -1, allow unbounded search.
* *
@ -617,9 +617,9 @@ g_utf8_strchr (const char *p,
* g_utf8_strrchr: * g_utf8_strrchr:
* @p: a nul-terminated UTF-8 encoded string * @p: a nul-terminated UTF-8 encoded string
* @len: the maximum length of @p * @len: the maximum length of @p
* @c: a ISO10646 character * @c: a Unicode character
* *
* Find the rightmost occurrence of the given ISO10646 character * Find the rightmost occurrence of the given Unicode character
* in a UTF-8 encoded string, while limiting the search to @len bytes. * in a UTF-8 encoded string, while limiting the search to @len bytes.
* If @len is -1, allow unbounded search. * If @len is -1, allow unbounded search.
* *