2813e3049a
Test stats remain unchanged, except for Malayalam, which we investigate: BENGALI: 353725 out of 354188 tests passed. 463 failed (0.130722%) DEVANAGARI: 707307 out of 707394 tests passed. 87 failed (0.0122987%) GUJARATI: 366349 out of 366457 tests passed. 108 failed (0.0294714%) GURMUKHI: 60732 out of 60747 tests passed. 15 failed (0.0246926%) KANNADA: 951190 out of 951913 tests passed. 723 failed (0.0759523%) KHMER: 299070 out of 299124 tests passed. 54 failed (0.0180527%) MALAYALAM: 1047584 out of 1048334 tests passed. 750 failed (0.0715421%) ORIYA: 42320 out of 42329 tests passed. 9 failed (0.021262%) SINHALA: 271662 out of 271847 tests passed. 185 failed (0.068053%) TAMIL: 1091753 out of 1091754 tests passed. 1 failed (9.15957e-05%) TELUGU: 970555 out of 970573 tests passed. 18 failed (0.00185457%) Myanmar, compared to Windows 10 mmrtext.ttf: MYANMAR: 1123865 out of 1123883 tests passed. 18 failed (0.00160159%)
191 lines
6.7 KiB
C++
191 lines
6.7 KiB
C++
/*
|
|
* Copyright © 2012 Google, Inc.
|
|
*
|
|
* 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
|
|
*/
|
|
|
|
#ifndef HB_OT_SHAPE_COMPLEX_INDIC_PRIVATE_HH
|
|
#define HB_OT_SHAPE_COMPLEX_INDIC_PRIVATE_HH
|
|
|
|
#include "hb-private.hh"
|
|
|
|
|
|
#include "hb-ot-shape-complex-private.hh"
|
|
#include "hb-ot-shape-private.hh" /* XXX Remove */
|
|
|
|
|
|
#define INDIC_TABLE_ELEMENT_TYPE uint16_t
|
|
|
|
/* Cateories used in the OpenType spec:
|
|
* https://www.microsoft.com/typography/otfntdev/devanot/shaping.aspx
|
|
*/
|
|
/* Note: This enum is duplicated in the -machine.rl source file.
|
|
* Not sure how to avoid duplication. */
|
|
enum indic_category_t {
|
|
OT_X = 0,
|
|
OT_C = 1,
|
|
OT_V = 2,
|
|
OT_N = 3,
|
|
OT_H = 4,
|
|
OT_ZWNJ = 5,
|
|
OT_ZWJ = 6,
|
|
OT_M = 7,
|
|
OT_SM = 8,
|
|
OT_VD = 9,
|
|
OT_A = 10,
|
|
OT_PLACEHOLDER = 11,
|
|
OT_DOTTEDCIRCLE = 12,
|
|
OT_RS = 13, /* Register Shifter, used in Khmer OT spec. */
|
|
OT_Coeng = 14, /* Khmer-style Virama. */
|
|
OT_Repha = 15, /* Atomically-encoded logical or visual repha. */
|
|
OT_Ra = 16,
|
|
OT_CM = 17, /* Consonant-Medial. */
|
|
OT_Symbol = 18, /* Avagraha, etc that take marks (SM,A,VD). */
|
|
OT_CM2 = 31 /* Consonant-Medial, second slot. */
|
|
};
|
|
|
|
#define MEDIAL_FLAGS (FLAG (OT_CM) | FLAG (OT_CM2))
|
|
|
|
/* Note:
|
|
*
|
|
* We treat Vowels and placeholders as if they were consonants. This is safe because Vowels
|
|
* cannot happen in a consonant syllable. The plus side however is, we can call the
|
|
* consonant syllable logic from the vowel syllable function and get it all right! */
|
|
#define CONSONANT_FLAGS (FLAG (OT_C) | FLAG (OT_Ra) | MEDIAL_FLAGS | FLAG (OT_V) | FLAG (OT_PLACEHOLDER) | FLAG (OT_DOTTEDCIRCLE))
|
|
#define JOINER_FLAGS (FLAG (OT_ZWJ) | FLAG (OT_ZWNJ))
|
|
#define HALANT_OR_COENG_FLAGS (FLAG (OT_H) | FLAG (OT_Coeng))
|
|
|
|
|
|
/* Visual positions in a syllable from left to right. */
|
|
enum indic_position_t {
|
|
POS_START,
|
|
|
|
POS_RA_TO_BECOME_REPH,
|
|
POS_PRE_M,
|
|
POS_PRE_C,
|
|
|
|
POS_BASE_C,
|
|
POS_AFTER_MAIN,
|
|
|
|
POS_ABOVE_C,
|
|
|
|
POS_BEFORE_SUB,
|
|
POS_BELOW_C,
|
|
POS_AFTER_SUB,
|
|
|
|
POS_BEFORE_POST,
|
|
POS_POST_C,
|
|
POS_AFTER_POST,
|
|
|
|
POS_FINAL_C,
|
|
POS_SMVD,
|
|
|
|
POS_END
|
|
};
|
|
|
|
/* Categories used in IndicSyllabicCategory.txt from UCD. */
|
|
enum indic_syllabic_category_t {
|
|
INDIC_SYLLABIC_CATEGORY_OTHER = OT_X,
|
|
|
|
INDIC_SYLLABIC_CATEGORY_AVAGRAHA = OT_Symbol,
|
|
INDIC_SYLLABIC_CATEGORY_BINDU = OT_SM,
|
|
INDIC_SYLLABIC_CATEGORY_BRAHMI_JOINING_NUMBER = OT_PLACEHOLDER, /* Don't care. */
|
|
INDIC_SYLLABIC_CATEGORY_CANTILLATION_MARK = OT_A,
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT = OT_C,
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT_DEAD = OT_C,
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT_FINAL = OT_CM,
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT_HEAD_LETTER = OT_C,
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT_KILLER = OT_M, /* U+17CD only. */
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT_MEDIAL = OT_CM,
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT_PLACEHOLDER = OT_PLACEHOLDER,
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT_PRECEDING_REPHA = OT_Repha,
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT_PREFIXED = OT_X, /* Don't care. */
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT_SUBJOINED = OT_CM,
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT_SUCCEEDING_REPHA = OT_N,
|
|
INDIC_SYLLABIC_CATEGORY_CONSONANT_WITH_STACKER = OT_Repha, /* TODO */
|
|
INDIC_SYLLABIC_CATEGORY_GEMINATION_MARK = OT_SM,
|
|
INDIC_SYLLABIC_CATEGORY_INVISIBLE_STACKER = OT_Coeng,
|
|
INDIC_SYLLABIC_CATEGORY_JOINER = OT_ZWJ,
|
|
INDIC_SYLLABIC_CATEGORY_MODIFYING_LETTER = OT_X,
|
|
INDIC_SYLLABIC_CATEGORY_NON_JOINER = OT_ZWNJ,
|
|
INDIC_SYLLABIC_CATEGORY_NUKTA = OT_N,
|
|
INDIC_SYLLABIC_CATEGORY_NUMBER = OT_PLACEHOLDER,
|
|
INDIC_SYLLABIC_CATEGORY_NUMBER_JOINER = OT_PLACEHOLDER, /* Don't care. */
|
|
INDIC_SYLLABIC_CATEGORY_PURE_KILLER = OT_M, /* Is like a vowel matra. */
|
|
INDIC_SYLLABIC_CATEGORY_REGISTER_SHIFTER = OT_RS,
|
|
INDIC_SYLLABIC_CATEGORY_SYLLABLE_MODIFIER = OT_M, /* Misc Khmer signs. */
|
|
INDIC_SYLLABIC_CATEGORY_TONE_LETTER = OT_X,
|
|
INDIC_SYLLABIC_CATEGORY_TONE_MARK = OT_N,
|
|
INDIC_SYLLABIC_CATEGORY_VIRAMA = OT_H,
|
|
INDIC_SYLLABIC_CATEGORY_VISARGA = OT_SM,
|
|
INDIC_SYLLABIC_CATEGORY_VOWEL = OT_V,
|
|
INDIC_SYLLABIC_CATEGORY_VOWEL_DEPENDENT = OT_M,
|
|
INDIC_SYLLABIC_CATEGORY_VOWEL_INDEPENDENT = OT_V
|
|
};
|
|
|
|
/* Categories used in IndicSMatraCategory.txt from UCD */
|
|
enum indic_matra_category_t {
|
|
INDIC_MATRA_CATEGORY_NOT_APPLICABLE = POS_END,
|
|
|
|
INDIC_MATRA_CATEGORY_LEFT = POS_PRE_C,
|
|
INDIC_MATRA_CATEGORY_TOP = POS_ABOVE_C,
|
|
INDIC_MATRA_CATEGORY_BOTTOM = POS_BELOW_C,
|
|
INDIC_MATRA_CATEGORY_RIGHT = POS_POST_C,
|
|
|
|
/* These should resolve to the position of the last part of the split sequence. */
|
|
INDIC_MATRA_CATEGORY_BOTTOM_AND_RIGHT = INDIC_MATRA_CATEGORY_RIGHT,
|
|
INDIC_MATRA_CATEGORY_LEFT_AND_RIGHT = INDIC_MATRA_CATEGORY_RIGHT,
|
|
INDIC_MATRA_CATEGORY_TOP_AND_BOTTOM = INDIC_MATRA_CATEGORY_BOTTOM,
|
|
INDIC_MATRA_CATEGORY_TOP_AND_BOTTOM_AND_RIGHT = INDIC_MATRA_CATEGORY_RIGHT,
|
|
INDIC_MATRA_CATEGORY_TOP_AND_LEFT = INDIC_MATRA_CATEGORY_TOP,
|
|
INDIC_MATRA_CATEGORY_TOP_AND_LEFT_AND_RIGHT = INDIC_MATRA_CATEGORY_RIGHT,
|
|
INDIC_MATRA_CATEGORY_TOP_AND_RIGHT = INDIC_MATRA_CATEGORY_RIGHT,
|
|
|
|
INDIC_MATRA_CATEGORY_OVERSTRUCK = POS_AFTER_MAIN,
|
|
INDIC_MATRA_CATEGORY_VISUAL_ORDER_LEFT = POS_PRE_M
|
|
};
|
|
|
|
#define INDIC_COMBINE_CATEGORIES(S,M) \
|
|
( \
|
|
ASSERT_STATIC_EXPR_ZERO (S < 255 && M < 255) + \
|
|
( S | \
|
|
( \
|
|
( \
|
|
S == INDIC_SYLLABIC_CATEGORY_CONSONANT_MEDIAL || \
|
|
S == INDIC_SYLLABIC_CATEGORY_GEMINATION_MARK || \
|
|
S == INDIC_SYLLABIC_CATEGORY_REGISTER_SHIFTER || \
|
|
S == INDIC_SYLLABIC_CATEGORY_CONSONANT_SUCCEEDING_REPHA || \
|
|
S == INDIC_SYLLABIC_CATEGORY_VIRAMA || \
|
|
S == INDIC_SYLLABIC_CATEGORY_VOWEL_DEPENDENT || \
|
|
false \
|
|
? M : INDIC_MATRA_CATEGORY_NOT_APPLICABLE \
|
|
) << 8 \
|
|
) \
|
|
) \
|
|
)
|
|
|
|
HB_INTERNAL INDIC_TABLE_ELEMENT_TYPE
|
|
hb_indic_get_categories (hb_codepoint_t u);
|
|
|
|
#endif /* HB_OT_SHAPE_COMPLEX_INDIC_PRIVATE_HH */
|