#define HB_UNICODE_PRIVATE_HH
#include "hb-private.hh"
-
-#include "hb-unicode.h"
#include "hb-object-private.hh"
}
- unsigned int
+ inline unsigned int
modified_combining_class (hb_codepoint_t unicode)
{
+ /* XXX This hack belongs to the Myanmar shaper. */
+ if (unlikely (unicode == 0x1037u)) unicode = 0x103Au;
+
+ /* XXX This hack belongs to the SEA shaper (for Tai Tham):
+ * Reorder SAKOT to ensure it comes after any tone marks. */
+ if (unlikely (unicode == 0x1A60u)) return 254;
+
+ /* XXX This hack belongs to the Tibetan shaper:
+ * Reorder PADMA to ensure it comes after any vowel marks. */
+ if (unlikely (unicode == 0x0FC6u)) return 254;
+
return _hb_modified_combining_class[combining_class (unicode)];
}
- inline hb_bool_t
+ static inline hb_bool_t
is_variation_selector (hb_codepoint_t unicode)
{
- return unlikely (hb_in_ranges<hb_codepoint_t> (unicode,
- 0x180B, 0x180D, /* MONGOLIAN FREE VARIATION SELECTOR ONE..THREE */
- 0xFE00, 0xFE0F, /* VARIATION SELECTOR-1..16 */
- 0xE0100, 0xE01EF)); /* VARIATION SELECTOR-17..256 */
+ /* U+180B..180D MONGOLIAN FREE VARIATION SELECTORs are handled in the
+ * Arabic shaper. No need to match them here. */
+ return unlikely (hb_in_ranges (unicode,
+ 0xFE00u, 0xFE0Fu, /* VARIATION SELECTOR-1..16 */
+ 0xE0100u, 0xE01EFu)); /* VARIATION SELECTOR-17..256 */
}
/* Default_Ignorable codepoints:
*
- * Note that as of Oct 2012 (Unicode 6.2), U+180E MONGOLIAN VOWEL SEPARATOR
- * is NOT Default_Ignorable, but it really behaves in a way that it should
- * be. That has been reported to the Unicode Technical Committee for
- * consideration. As such, we include it here, since Uniscribe removes it.
- *
- * Gathered from:
- * http://unicode.org/cldr/utility/list-unicodeset.jsp?a=[:DI:]&abb=on&ucd=on&esc=on
- *
- * Last updated to the page with the following versions:
- * Version 3.6; ICU version: 50.0.1.0; Unicode version: 6.1.0.0
- *
- * 4,167 Code Points
- *
- * [\u00AD\u034F\u115F\u1160\u17B4\u17B5\u180B-\u180D\u200B-\u200F\u202A-\u202E\u2060-\u206F\u3164\uFE00-\uFE0F\uFEFF\uFFA0\uFFF0-\uFFF8\U0001D173-\U0001D17A\U000E0000-\U000E0FFF]
+ * Note: While U+115F, U+1160, U+3164 and U+FFA0 are Default_Ignorable,
+ * we do NOT want to hide them, as the way Uniscribe has implemented them
+ * is with regular spacing glyphs, and that's the way fonts are made to work.
+ * As such, we make exceptions for those four.
*
- * 00AD ;SOFT HYPHEN
- * 034F ;COMBINING GRAPHEME JOINER
- * 115F ;HANGUL CHOSEONG FILLER
- * 1160 ;HANGUL JUNGSEONG FILLER
- * 17B4 ;KHMER VOWEL INHERENT AQ
- * 17B5 ;KHMER VOWEL INHERENT AA
- * 180B..180D ;MONGOLIAN FREE VARIATION SELECTOR THREE
- * 200B..200F ;RIGHT-TO-LEFT MARK
- * 202A..202E ;RIGHT-TO-LEFT OVERRIDE
- * 2060..206F ;NOMINAL DIGIT SHAPES
- * 3164 ;HANGUL FILLER
- * FE00..FE0F ;VARIATION SELECTOR-16
- * FEFF ;ZERO WIDTH NO-BREAK SPACE
- * FFA0 ;HALFWIDTH HANGUL FILLER
- * FFF0..FFF8 ;<unassigned-FFF8>
- * 1D173..1D17A ;MUSICAL SYMBOL END PHRASE
- * E0000..E0FFF ;<unassigned-E0FFF>
+ * Unicode 7.0:
+ * $ grep '; Default_Ignorable_Code_Point ' DerivedCoreProperties.txt | sed 's/;.*#/#/'
+ * 00AD # Cf SOFT HYPHEN
+ * 034F # Mn COMBINING GRAPHEME JOINER
+ * 061C # Cf ARABIC LETTER MARK
+ * 115F..1160 # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
+ * 17B4..17B5 # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
+ * 180B..180D # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
+ * 180E # Cf MONGOLIAN VOWEL SEPARATOR
+ * 200B..200F # Cf [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK
+ * 202A..202E # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
+ * 2060..2064 # Cf [5] WORD JOINER..INVISIBLE PLUS
+ * 2065 # Cn <reserved-2065>
+ * 2066..206F # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
+ * 3164 # Lo HANGUL FILLER
+ * FE00..FE0F # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
+ * FEFF # Cf ZERO WIDTH NO-BREAK SPACE
+ * FFA0 # Lo HALFWIDTH HANGUL FILLER
+ * FFF0..FFF8 # Cn [9] <reserved-FFF0>..<reserved-FFF8>
+ * 1BCA0..1BCA3 # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
+ * 1D173..1D17A # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
+ * E0000 # Cn <reserved-E0000>
+ * E0001 # Cf LANGUAGE TAG
+ * E0002..E001F # Cn [30] <reserved-E0002>..<reserved-E001F>
+ * E0020..E007F # Cf [96] TAG SPACE..CANCEL TAG
+ * E0080..E00FF # Cn [128] <reserved-E0080>..<reserved-E00FF>
+ * E0100..E01EF # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
+ * E01F0..E0FFF # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
*/
- inline hb_bool_t
+ static inline hb_bool_t
is_default_ignorable (hb_codepoint_t ch)
{
hb_codepoint_t plane = ch >> 16;
/* BMP */
hb_codepoint_t page = ch >> 8;
switch (page) {
- case 0x00: return unlikely (ch == 0x00AD);
- case 0x03: return unlikely (ch == 0x034F);
- case 0x11: return hb_in_range<hb_codepoint_t> (ch, 0x115F, 0x1160);
- case 0x17: return hb_in_range<hb_codepoint_t> (ch, 0x17B4, 0x17B5);
- case 0x18: return hb_in_range<hb_codepoint_t> (ch, 0x180B, 0x180E);
- case 0x20: return hb_in_ranges<hb_codepoint_t> (ch, 0x200B, 0x200F,
- 0x202A, 0x202E,
- 0x2060, 0x206F);
- case 0x31: return unlikely (ch == 0x3164);
- case 0xFE: return hb_in_range<hb_codepoint_t> (ch, 0xFE00, 0xFE0F) || ch == 0xFEFF;
- case 0xFF: return hb_in_range<hb_codepoint_t> (ch, 0xFFF0, 0xFFF8) || ch == 0xFFA0;
+ case 0x00: return unlikely (ch == 0x00ADu);
+ case 0x03: return unlikely (ch == 0x034Fu);
+ case 0x06: return unlikely (ch == 0x061Cu);
+ case 0x17: return hb_in_range (ch, 0x17B4u, 0x17B5u);
+ case 0x18: return hb_in_range (ch, 0x180Bu, 0x180Eu);
+ case 0x20: return hb_in_ranges (ch, 0x200Bu, 0x200Fu,
+ 0x202Au, 0x202Eu,
+ 0x2060u, 0x206Fu);
+ case 0xFE: return hb_in_range (ch, 0xFE00u, 0xFE0Fu) || ch == 0xFEFFu;
+ case 0xFF: return hb_in_range (ch, 0xFFF0u, 0xFFF8u);
default: return false;
}
}
{
/* Other planes */
switch (plane) {
- case 0x01: return hb_in_range<hb_codepoint_t> (ch, 0x0001D173, 0x0001D17A);
- case 0x0E: return hb_in_range<hb_codepoint_t> (ch, 0x000E0000, 0x000E0FFF);
+ case 0x01: return hb_in_ranges (ch, 0x1BCA0u, 0x1BCA3u,
+ 0x1D173u, 0x1D17Au);
+ case 0x0E: return hb_in_range (ch, 0xE0000u, 0xE0FFFu);
default: return false;
}
}
projects / platform / upstream / harfbuzz.git / blobdiff