2011-07-08 04:35:17 +02:00
|
|
|
/*
|
2012-08-12 00:34:13 +02:00
|
|
|
* Copyright © 2010,2012 Google, Inc.
|
2011-07-08 04:35:17 +02:00
|
|
|
*
|
|
|
|
* This is part of HarfBuzz, a text shaping library.
|
|
|
|
*
|
|
|
|
* Permission is hereby granted, without written agreement and without
|
|
|
|
* license or royalty fees, to use, copy, modify, and distribute this
|
|
|
|
* software and its documentation for any purpose, provided that the
|
|
|
|
* above copyright notice and the following two paragraphs appear in
|
|
|
|
* all copies of this software.
|
|
|
|
*
|
|
|
|
* IN NO EVENT SHALL THE COPYRIGHT HOLDER BE LIABLE TO ANY PARTY FOR
|
|
|
|
* DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES
|
|
|
|
* ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS DOCUMENTATION, EVEN
|
|
|
|
* IF THE COPYRIGHT HOLDER HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
|
|
|
|
* DAMAGE.
|
|
|
|
*
|
|
|
|
* THE COPYRIGHT HOLDER SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING,
|
|
|
|
* BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
|
|
|
|
* FITNESS FOR A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS
|
|
|
|
* ON AN "AS IS" BASIS, AND THE COPYRIGHT HOLDER HAS NO OBLIGATION TO
|
|
|
|
* PROVIDE MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS.
|
|
|
|
*
|
|
|
|
* Google Author(s): Behdad Esfahbod
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "hb-ot-shape-complex-private.hh"
|
|
|
|
|
|
|
|
|
2012-04-10 16:52:07 +02:00
|
|
|
/* TODO Add kana, and other small shapers here */
|
2011-07-08 04:35:17 +02:00
|
|
|
|
2012-07-17 02:26:57 +02:00
|
|
|
|
2012-07-18 22:34:10 +02:00
|
|
|
/* The default shaper *only* adds additional per-script features.*/
|
2012-04-10 16:52:07 +02:00
|
|
|
|
2012-04-12 04:00:46 +02:00
|
|
|
static const hb_tag_t hangul_features[] =
|
|
|
|
{
|
|
|
|
HB_TAG('l','j','m','o'),
|
|
|
|
HB_TAG('v','j','m','o'),
|
|
|
|
HB_TAG('t','j','m','o'),
|
2012-07-18 22:34:10 +02:00
|
|
|
HB_TAG_NONE
|
|
|
|
};
|
|
|
|
|
|
|
|
static const hb_tag_t tibetan_features[] =
|
|
|
|
{
|
|
|
|
HB_TAG('a','b','v','s'),
|
|
|
|
HB_TAG('b','l','w','s'),
|
|
|
|
HB_TAG('a','b','v','m'),
|
|
|
|
HB_TAG('b','l','w','m'),
|
|
|
|
HB_TAG_NONE
|
2012-04-12 04:00:46 +02:00
|
|
|
};
|
|
|
|
|
2012-07-31 03:08:51 +02:00
|
|
|
static void
|
2012-08-02 15:38:28 +02:00
|
|
|
collect_features_default (hb_ot_shape_planner_t *plan)
|
2012-04-07 21:06:55 +02:00
|
|
|
{
|
2012-07-18 22:34:10 +02:00
|
|
|
const hb_tag_t *script_features = NULL;
|
|
|
|
|
2012-08-02 15:38:28 +02:00
|
|
|
switch ((hb_tag_t) plan->props.script)
|
2012-07-18 22:34:10 +02:00
|
|
|
{
|
|
|
|
/* Unicode-1.1 additions */
|
|
|
|
case HB_SCRIPT_HANGUL:
|
|
|
|
script_features = hangul_features;
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* Unicode-2.0 additions */
|
|
|
|
case HB_SCRIPT_TIBETAN:
|
|
|
|
script_features = tibetan_features;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (; script_features && *script_features; script_features++)
|
2012-08-02 15:38:28 +02:00
|
|
|
plan->map.add_bool_feature (*script_features);
|
2012-04-07 21:06:55 +02:00
|
|
|
}
|
|
|
|
|
2012-07-31 03:08:51 +02:00
|
|
|
static hb_ot_shape_normalization_mode_t
|
2012-11-13 21:35:35 +01:00
|
|
|
normalization_preference_default (const hb_segment_properties_t *props)
|
2012-04-07 21:06:55 +02:00
|
|
|
{
|
2012-11-13 21:35:35 +01:00
|
|
|
switch ((hb_tag_t) props->script)
|
2012-07-30 20:53:41 +02:00
|
|
|
{
|
|
|
|
/* Unicode-1.1 additions */
|
|
|
|
case HB_SCRIPT_HANGUL:
|
|
|
|
return HB_OT_SHAPE_NORMALIZATION_MODE_COMPOSED_FULL;
|
|
|
|
}
|
2012-07-18 22:34:10 +02:00
|
|
|
return HB_OT_SHAPE_NORMALIZATION_MODE_COMPOSED_DIACRITICS;
|
2012-04-07 21:06:55 +02:00
|
|
|
}
|
|
|
|
|
2012-11-16 21:39:23 +01:00
|
|
|
static bool
|
|
|
|
compose_default (const hb_ot_shape_normalize_context_t *c,
|
2012-11-13 21:35:35 +01:00
|
|
|
hb_codepoint_t a,
|
|
|
|
hb_codepoint_t b,
|
|
|
|
hb_codepoint_t *ab)
|
|
|
|
{
|
|
|
|
/* Hebrew presentation-form shaping.
|
2012-11-17 03:49:54 +01:00
|
|
|
* https://bugzilla.mozilla.org/show_bug.cgi?id=728866
|
|
|
|
* Hebrew presentation forms with dagesh, for characters 0x05D0..0x05EA;
|
|
|
|
* Note that some letters do not have a dagesh presForm encoded.
|
|
|
|
*/
|
2012-11-13 21:35:35 +01:00
|
|
|
static const hb_codepoint_t sDageshForms[0x05EA - 0x05D0 + 1] = {
|
2012-11-17 03:49:54 +01:00
|
|
|
0xFB30, /* ALEF */
|
|
|
|
0xFB31, /* BET */
|
|
|
|
0xFB32, /* GIMEL */
|
|
|
|
0xFB33, /* DALET */
|
|
|
|
0xFB34, /* HE */
|
|
|
|
0xFB35, /* VAV */
|
|
|
|
0xFB36, /* ZAYIN */
|
|
|
|
0x0000, /* HET */
|
|
|
|
0xFB38, /* TET */
|
|
|
|
0xFB39, /* YOD */
|
|
|
|
0xFB3A, /* FINAL KAF */
|
|
|
|
0xFB3B, /* KAF */
|
|
|
|
0xFB3C, /* LAMED */
|
|
|
|
0x0000, /* FINAL MEM */
|
|
|
|
0xFB3E, /* MEM */
|
|
|
|
0x0000, /* FINAL NUN */
|
|
|
|
0xFB40, /* NUN */
|
|
|
|
0xFB41, /* SAMEKH */
|
|
|
|
0x0000, /* AYIN */
|
|
|
|
0xFB43, /* FINAL PE */
|
|
|
|
0xFB44, /* PE */
|
|
|
|
0x0000, /* FINAL TSADI */
|
|
|
|
0xFB46, /* TSADI */
|
|
|
|
0xFB47, /* QOF */
|
|
|
|
0xFB48, /* RESH */
|
|
|
|
0xFB49, /* SHIN */
|
|
|
|
0xFB4A /* TAV */
|
2012-11-13 21:35:35 +01:00
|
|
|
};
|
|
|
|
|
2012-11-16 21:39:23 +01:00
|
|
|
bool found = c->unicode->compose (a, b, ab);
|
2012-11-13 21:35:35 +01:00
|
|
|
|
|
|
|
if (!found && (b & ~0x7F) == 0x0580) {
|
2012-11-17 03:49:54 +01:00
|
|
|
/* Special-case Hebrew presentation forms that are excluded from
|
|
|
|
* standard normalization, but wanted for old fonts. */
|
2012-11-13 21:35:35 +01:00
|
|
|
switch (b) {
|
2012-11-17 03:49:54 +01:00
|
|
|
case 0x05B4: /* HIRIQ */
|
|
|
|
if (a == 0x05D9) { /* YOD */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB1D;
|
|
|
|
found = true;
|
|
|
|
}
|
|
|
|
break;
|
2012-11-17 03:49:54 +01:00
|
|
|
case 0x05B7: /* patah */
|
|
|
|
if (a == 0x05F2) { /* YIDDISH YOD YOD */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB1F;
|
|
|
|
found = true;
|
2012-11-17 03:49:54 +01:00
|
|
|
} else if (a == 0x05D0) { /* ALEF */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB2E;
|
|
|
|
found = true;
|
|
|
|
}
|
|
|
|
break;
|
2012-11-17 03:49:54 +01:00
|
|
|
case 0x05B8: /* QAMATS */
|
|
|
|
if (a == 0x05D0) { /* ALEF */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB2F;
|
|
|
|
found = true;
|
|
|
|
}
|
|
|
|
break;
|
2012-11-17 03:49:54 +01:00
|
|
|
case 0x05B9: /* HOLAM */
|
|
|
|
if (a == 0x05D5) { /* VAV */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB4B;
|
|
|
|
found = true;
|
|
|
|
}
|
|
|
|
break;
|
2012-11-17 03:49:54 +01:00
|
|
|
case 0x05BC: /* DAGESH */
|
2012-11-13 21:35:35 +01:00
|
|
|
if (a >= 0x05D0 && a <= 0x05EA) {
|
|
|
|
*ab = sDageshForms[a - 0x05D0];
|
|
|
|
found = (*ab != 0);
|
2012-11-17 03:49:54 +01:00
|
|
|
} else if (a == 0xFB2A) { /* SHIN WITH SHIN DOT */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB2C;
|
|
|
|
found = true;
|
2012-11-17 03:49:54 +01:00
|
|
|
} else if (a == 0xFB2B) { /* SHIN WITH SIN DOT */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB2D;
|
|
|
|
found = true;
|
|
|
|
}
|
|
|
|
break;
|
2012-11-17 03:49:54 +01:00
|
|
|
case 0x05BF: /* RAFE */
|
2012-11-13 21:35:35 +01:00
|
|
|
switch (a) {
|
2012-11-17 03:49:54 +01:00
|
|
|
case 0x05D1: /* BET */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB4C;
|
|
|
|
found = true;
|
|
|
|
break;
|
2012-11-17 03:49:54 +01:00
|
|
|
case 0x05DB: /* KAF */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB4D;
|
|
|
|
found = true;
|
|
|
|
break;
|
2012-11-17 03:49:54 +01:00
|
|
|
case 0x05E4: /* PE */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB4E;
|
|
|
|
found = true;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
break;
|
2012-11-17 03:49:54 +01:00
|
|
|
case 0x05C1: /* SHIN DOT */
|
|
|
|
if (a == 0x05E9) { /* SHIN */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB2A;
|
|
|
|
found = true;
|
2012-11-17 03:49:54 +01:00
|
|
|
} else if (a == 0xFB49) { /* SHIN WITH DAGESH */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB2C;
|
|
|
|
found = true;
|
|
|
|
}
|
|
|
|
break;
|
2012-11-17 03:49:54 +01:00
|
|
|
case 0x05C2: /* SIN DOT */
|
|
|
|
if (a == 0x05E9) { /* SHIN */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB2B;
|
|
|
|
found = true;
|
2012-11-17 03:49:54 +01:00
|
|
|
} else if (a == 0xFB49) { /* SHIN WITH DAGESH */
|
2012-11-13 21:35:35 +01:00
|
|
|
*ab = 0xFB2D;
|
|
|
|
found = true;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return found;
|
|
|
|
}
|
|
|
|
|
2012-07-31 03:08:51 +02:00
|
|
|
const hb_ot_complex_shaper_t _hb_ot_complex_shaper_default =
|
2012-04-07 21:06:55 +02:00
|
|
|
{
|
2012-07-31 03:08:51 +02:00
|
|
|
"default",
|
|
|
|
collect_features_default,
|
|
|
|
NULL, /* override_features */
|
2012-08-02 16:46:34 +02:00
|
|
|
NULL, /* data_create */
|
|
|
|
NULL, /* data_destroy */
|
2012-08-12 00:34:13 +02:00
|
|
|
NULL, /* preprocess_text */
|
2012-07-31 03:08:51 +02:00
|
|
|
normalization_preference_default,
|
2012-11-13 21:35:35 +01:00
|
|
|
NULL, /* decompose */
|
|
|
|
compose_default,
|
2012-07-31 03:08:51 +02:00
|
|
|
NULL, /* setup_masks */
|
Adjust mark advance-width zeroing logic for Myanmar
Before, we were zeroing advance width of attached marks for
non-Indic scripts, and not doing it for Indic.
We have now three different behaviors, which seem to better
reflect what Uniscribe is doing:
- For Indic, no explicit zeroing happens whatsoever, which
is the same as before,
- For Myanmar, zero advance width of glyphs marked as marks
*in GDEF*, and do that *before* applying GPOS. This seems
to be what the new Win8 Myanmar shaper does,
- For everything else, zero advance width of glyphs that are
from General_Category=Mn Unicode characters, and do so
before applying GPOS. This seems to be what Uniscribe does
for Latin at least.
With these changes, positioning of all tests matches for Myanmar,
except for the glitch in Uniscribe not applying 'mark'. See preivous
commit.
2013-02-12 15:44:57 +01:00
|
|
|
HB_OT_SHAPE_ZERO_WIDTH_MARKS_BY_UNICODE,
|
2012-11-14 22:48:26 +01:00
|
|
|
true, /* fallback_position */
|
2012-07-31 03:08:51 +02:00
|
|
|
};
|