[USE] Update to the 2020-08-13 USE specification

This also uses the data files from
<78b2134fdc/USE>.
This commit is contained in:
David Corbett 2020-08-13 13:37:45 -04:00
parent e3db84a9d0
commit 06f49fc8ae
10 changed files with 946 additions and 319 deletions

View File

@ -1,25 +1,38 @@
#!/usr/bin/env python3
# flake8: noqa: F821
"""usage: ./gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt Blocks.txt
"""usage: ./gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt ArabicShaping.txt Blocks.txt IndicSyllabicCategory-Additional.txt IndicPositionalCategory-Additional.txt
Input file:
Input files:
* https://unicode.org/Public/UCD/latest/ucd/IndicSyllabicCategory.txt
* https://unicode.org/Public/UCD/latest/ucd/IndicPositionalCategory.txt
* https://unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
* https://unicode.org/Public/UCD/latest/ucd/ArabicShaping.txt
* https://unicode.org/Public/UCD/latest/ucd/Blocks.txt
* ms-use/IndicPositionalCategory-Additional.txt
* ms-use/IndicSyllabicCategory-Additional.txt
"""
import sys
if len (sys.argv) != 5:
if len (sys.argv) != 8:
sys.exit (__doc__)
BLACKLISTED_BLOCKS = ["Thai", "Lao"]
BLACKLISTED_BLOCKS = [
'Samaritan',
'Thai',
'Lao',
]
files = [open (x, encoding='utf-8') for x in sys.argv[1:]]
headers = [[f.readline () for i in range (2)] for j,f in enumerate(files) if j != 2]
for j in range(5, 7):
for line in files[j]:
line = line.rstrip()
if not line:
break
headers[j - 1].append(line)
headers.append (["UnicodeData.txt does not have a header."])
data = [{} for _ in files]
@ -42,15 +55,25 @@ for i, f in enumerate (files):
else:
end = int (uu[1], 16)
t = fields[1 if i != 2 else 2]
t = fields[1 if i not in [2, 3] else 2]
if i == 3:
t = 'jt_' + t
elif i == 5 and t == 'Consonant_Final_Modifier':
# TODO: https://github.com/MicrosoftDocs/typography-issues/issues/336
t = 'Syllable_Modifier'
elif i == 6 and t == 'NA':
t = 'Not_Applicable'
i0 = i if i < 5 else i - 5
for u in range (start, end + 1):
data[i][u] = t
values[i][t] = values[i].get (t, 0) + end - start + 1
data[i0][u] = t
values[i0][t] = values[i0].get (t, 0) + end - start + 1
defaults = ('Other', 'Not_Applicable', 'Cn', 'No_Block')
defaults = ('Other', 'Not_Applicable', 'Cn', 'jt_X', 'No_Block')
# TODO Characters that are not in Unicode Indic files, but used in USE
data[0][0x0640] = defaults[0]
data[0][0x1B61] = defaults[0]
data[0][0x1B63] = defaults[0]
data[0][0x1B64] = defaults[0]
@ -60,6 +83,29 @@ data[0][0x1B67] = defaults[0]
data[0][0x1B69] = defaults[0]
data[0][0x1B6A] = defaults[0]
data[0][0x2060] = defaults[0]
for u in range (0x07CA, 0x07EA + 1):
data[0][u] = defaults[0]
data[0][0x07FA] = defaults[0]
for u in range (0x0840, 0x0858 + 1):
data[0][u] = defaults[0]
for u in range (0x1887, 0x18A8 + 1):
data[0][u] = defaults[0]
data[0][0x18AA] = defaults[0]
for u in range (0xA840, 0xA872 + 1):
data[0][u] = defaults[0]
for u in range (0x10B80, 0x10B91 + 1):
data[0][u] = defaults[0]
for u in range (0x10BA9, 0x10BAE + 1):
data[0][u] = defaults[0]
data[0][0x10FB0] = defaults[0]
for u in range (0x10FB2, 0x10FB6 + 1):
data[0][u] = defaults[0]
for u in range (0x10FB8, 0x10FBF + 1):
data[0][u] = defaults[0]
for u in range (0x10FC1, 0x10FC4 + 1):
data[0][u] = defaults[0]
for u in range (0x10FC9, 0x10FCB + 1):
data[0][u] = defaults[0]
# TODO https://github.com/harfbuzz/harfbuzz/pull/1685
data[0][0x1B5B] = 'Consonant_Placeholder'
data[0][0x1B5C] = 'Consonant_Placeholder'
@ -83,7 +129,7 @@ for i,d in enumerate (data):
if not u in combined:
combined[u] = list (defaults)
combined[u][i] = v
combined = {k:v for k,v in combined.items() if v[3] not in BLACKLISTED_BLOCKS}
combined = {k:v for k,v in combined.items() if v[4] not in BLACKLISTED_BLOCKS}
data = combined
del combined
@ -147,6 +193,14 @@ property_names = [
'Bottom_And_Right',
'Top_And_Bottom_And_Right',
'Overstruck',
# Joining_Type
'jt_C',
'jt_D',
'jt_L',
'jt_R',
'jt_T',
'jt_U',
'jt_X',
]
class PropertyValue(object):
@ -171,83 +225,78 @@ for name in property_names:
globals().update(property_values)
def is_BASE(U, UISC, UGC):
def is_BASE(U, UISC, UGC, AJT):
return (UISC in [Number, Consonant, Consonant_Head_Letter,
#SPEC-DRAFT Consonant_Placeholder,
Tone_Letter,
Vowel_Independent #SPEC-DRAFT
Vowel_Independent,
] or
# TODO: https://github.com/MicrosoftDocs/typography-issues/issues/484
AJT in [jt_C, jt_D, jt_L, jt_R] and not is_ZWJ(U, UISC, UGC, AJT) or
(UGC == Lo and UISC in [Avagraha, Bindu, Consonant_Final, Consonant_Medial,
Consonant_Subjoined, Vowel, Vowel_Dependent]))
def is_BASE_IND(U, UISC, UGC):
#SPEC-DRAFT return (UISC in [Consonant_Dead, Modifying_Letter] or UGC == Po)
def is_BASE_IND(U, UISC, UGC, AJT):
return (UISC in [Consonant_Dead, Modifying_Letter] or
(UGC == Po and not U in [0x104B, 0x104E, 0x1B5B, 0x1B5C, 0x1B5F, 0x2022, 0x111C8, 0x11A3F, 0x11A45, 0x11C44, 0x11C45]) or
False # SPEC-DRAFT-OUTDATED! U == 0x002D
)
def is_BASE_NUM(U, UISC, UGC):
(UGC == Po and not U in [0x0F04, 0x0F05, 0x0F06, 0x104B, 0x104E, 0x1800, 0x1807, 0x180A, 0x1B5B, 0x1B5C, 0x1B5F, 0x2022, 0x111C8, 0x11A3F, 0x11A45, 0x11C44, 0x11C45]))
def is_BASE_NUM(U, UISC, UGC, AJT):
return UISC == Brahmi_Joining_Number
def is_BASE_OTHER(U, UISC, UGC):
if UISC == Consonant_Placeholder: return True #SPEC-DRAFT
#SPEC-DRAFT return U in [0x00A0, 0x00D7, 0x2015, 0x2022, 0x25CC, 0x25FB, 0x25FC, 0x25FD, 0x25FE]
def is_BASE_OTHER(U, UISC, UGC, AJT):
if UISC == Consonant_Placeholder: return True
return U in [0x2015, 0x2022, 0x25FB, 0x25FC, 0x25FD, 0x25FE]
def is_CONS_FINAL(U, UISC, UGC):
def is_CONS_FINAL(U, UISC, UGC, AJT):
return ((UISC == Consonant_Final and UGC != Lo) or
UISC == Consonant_Succeeding_Repha)
def is_CONS_FINAL_MOD(U, UISC, UGC):
#SPEC-DRAFT return UISC in [Consonant_Final_Modifier, Syllable_Modifier]
def is_CONS_FINAL_MOD(U, UISC, UGC, AJT):
return UISC == Syllable_Modifier
def is_CONS_MED(U, UISC, UGC):
def is_CONS_MED(U, UISC, UGC, AJT):
# Consonant_Initial_Postfixed is new in Unicode 11; not in the spec.
return (UISC == Consonant_Medial and UGC != Lo or
UISC == Consonant_Initial_Postfixed)
def is_CONS_MOD(U, UISC, UGC):
return UISC in [Nukta, Gemination_Mark, Consonant_Killer]
def is_CONS_SUB(U, UISC, UGC):
#SPEC-DRAFT return UISC == Consonant_Subjoined
def is_CONS_MOD(U, UISC, UGC, AJT):
return (UISC in [Nukta, Gemination_Mark, Consonant_Killer] and
not is_SYM_MOD(U, UISC, UGC, AJT))
def is_CONS_SUB(U, UISC, UGC, AJT):
return UISC == Consonant_Subjoined and UGC != Lo
def is_CONS_WITH_STACKER(U, UISC, UGC):
def is_CONS_WITH_STACKER(U, UISC, UGC, AJT):
return UISC == Consonant_With_Stacker
def is_HALANT(U, UISC, UGC):
def is_HALANT(U, UISC, UGC, AJT):
return (UISC in [Virama, Invisible_Stacker]
and not is_HALANT_OR_VOWEL_MODIFIER(U, UISC, UGC)
and not is_SAKOT(U, UISC, UGC))
def is_HALANT_OR_VOWEL_MODIFIER(U, UISC, UGC):
and not is_HALANT_OR_VOWEL_MODIFIER(U, UISC, UGC, AJT)
and not is_SAKOT(U, UISC, UGC, AJT))
def is_HALANT_OR_VOWEL_MODIFIER(U, UISC, UGC, AJT):
# https://github.com/harfbuzz/harfbuzz/issues/1102
# https://github.com/harfbuzz/harfbuzz/issues/1379
return U in [0x11046, 0x1134D]
def is_HALANT_NUM(U, UISC, UGC):
def is_HALANT_NUM(U, UISC, UGC, AJT):
return UISC == Number_Joiner
def is_ZWNJ(U, UISC, UGC):
def is_ZWNJ(U, UISC, UGC, AJT):
return UISC == Non_Joiner
def is_ZWJ(U, UISC, UGC):
def is_ZWJ(U, UISC, UGC, AJT):
return UISC == Joiner
def is_Word_Joiner(U, UISC, UGC):
def is_Word_Joiner(U, UISC, UGC, AJT):
return U == 0x2060
def is_OTHER(U, UISC, UGC):
#SPEC-OUTDATED return UGC == Zs # or any other SCRIPT_COMMON characters
def is_OTHER(U, UISC, UGC, AJT):
return (UISC == Other
and not is_SYM(U, UISC, UGC)
and not is_SYM_MOD(U, UISC, UGC)
and not is_Word_Joiner(U, UISC, UGC)
and not is_BASE(U, UISC, UGC, AJT)
and not is_SYM(U, UISC, UGC, AJT)
and not is_SYM_MOD(U, UISC, UGC, AJT)
and not is_Word_Joiner(U, UISC, UGC, AJT)
)
def is_Reserved(U, UISC, UGC):
def is_Reserved(U, UISC, UGC, AJT):
return UGC == 'Cn'
def is_REPHA(U, UISC, UGC):
def is_REPHA(U, UISC, UGC, AJT):
return UISC in [Consonant_Preceding_Repha, Consonant_Prefixed]
def is_SAKOT(U, UISC, UGC):
def is_SAKOT(U, UISC, UGC, AJT):
return U == 0x1A60
def is_SYM(U, UISC, UGC):
if U == 0x25CC: return False #SPEC-DRAFT
#SPEC-DRAFT return UGC in [So, Sc] or UISC == Symbol_Letter
return UGC in [So, Sc] and U not in [0x1B62, 0x1B68]
def is_SYM_MOD(U, UISC, UGC):
def is_SYM(U, UISC, UGC, AJT):
if U in [0x25CC, 0x1E14F]: return False
return UGC in [So, Sc] and U not in [0x0F01, 0x1B62, 0x1B68]
def is_SYM_MOD(U, UISC, UGC, AJT):
return U in [0x1B6B, 0x1B6C, 0x1B6D, 0x1B6E, 0x1B6F, 0x1B70, 0x1B71, 0x1B72, 0x1B73]
def is_VOWEL(U, UISC, UGC):
def is_VOWEL(U, UISC, UGC, AJT):
# https://github.com/harfbuzz/harfbuzz/issues/376
return (UISC == Pure_Killer or
(UGC != Lo and UISC in [Vowel, Vowel_Dependent] and U not in [0xAA29]))
def is_VOWEL_MOD(U, UISC, UGC):
def is_VOWEL_MOD(U, UISC, UGC, AJT):
# https://github.com/harfbuzz/harfbuzz/issues/376
return (UISC in [Tone_Mark, Cantillation_Mark, Register_Shifter, Visarga] or
(UGC != Lo and (UISC == Bindu or U in [0xAA29])))
@ -294,13 +343,13 @@ use_positions = {
},
'CM': {
'Abv': [Top],
'Blw': [Bottom],
'Blw': [Bottom, Overstruck],
},
'V': {
'Abv': [Top, Top_And_Bottom, Top_And_Bottom_And_Right, Top_And_Right],
'Blw': [Bottom, Overstruck, Bottom_And_Right],
'Pst': [Right, Top_And_Left, Top_And_Left_And_Right, Left_And_Right],
'Pre': [Left],
'Pst': [Right],
'Pre': [Left, Top_And_Left, Top_And_Left_And_Right, Left_And_Right],
},
'VM': {
'Abv': [Top],
@ -320,13 +369,19 @@ use_positions = {
'Blw': [Bottom],
'Pst': [Not_Applicable],
},
'R': None,
'SUB': None,
}
def map_to_use(data):
out = {}
items = use_mapping.items()
for U,(UISC,UIPC,UGC,UBlock) in data.items():
for U,(UISC,UIPC,UGC,AJT,UBlock) in data.items():
if UGC == Cn: continue
# TODO: These variation selectors are overridden to IND, but we want to ignore them
if U in range (0xFE00, 0xFE0F + 1): continue
# Resolve Indic_Syllabic_Category
@ -336,20 +391,6 @@ def map_to_use(data):
# Tibetan:
# TODO: These don't have UISC assigned in Unicode 13.0.0, but have UIPC
if 0x0F18 <= U <= 0x0F19 or 0x0F3E <= U <= 0x0F3F: UISC = Vowel_Dependent
if 0x0F86 <= U <= 0x0F87: UISC = Tone_Mark
# Overrides to allow NFC order matching syllable
# https://github.com/harfbuzz/harfbuzz/issues/1012
if UBlock == 'Tibetan' and is_VOWEL (U, UISC, UGC):
if UIPC == Top:
UIPC = Bottom
# TODO: https://github.com/harfbuzz/harfbuzz/pull/982
# also https://github.com/harfbuzz/harfbuzz/issues/1012
if UBlock == 'Chakma' and is_VOWEL (U, UISC, UGC):
if UIPC == Top:
UIPC = Bottom
elif UIPC == Bottom:
UIPC = Top
# TODO: https://github.com/harfbuzz/harfbuzz/pull/627
if 0x1BF2 <= U <= 0x1BF3: UISC = Nukta; UIPC = Bottom
@ -358,11 +399,11 @@ def map_to_use(data):
# the nasalization marks, maybe only for U+1CE9..U+1CF1.
if U == 0x1CED: UISC = Tone_Mark
# TODO: https://github.com/harfbuzz/harfbuzz/issues/1105
if U == 0x11134: UISC = Gemination_Mark
# TODO: https://github.com/microsoft/font-tools/issues/1
if U == 0xA982: UISC = Consonant_Succeeding_Repha
values = [k for k,v in items if v(U,UISC,UGC)]
assert len(values) == 1, "%s %s %s %s" % (hex(U), UISC, UGC, values)
values = [k for k,v in items if v(U,UISC,UGC,AJT)]
assert len(values) == 1, "%s %s %s %s %s" % (hex(U), UISC, UGC, AJT, values)
USE = values[0]
# Resolve Indic_Positional_Category
@ -370,9 +411,6 @@ def map_to_use(data):
# TODO: These should die, but have UIPC in Unicode 13.0.0
if U in [0x953, 0x954]: UIPC = Not_Applicable
# TODO: https://github.com/harfbuzz/harfbuzz/pull/2012
if U == 0x1C29: UIPC = Left
# TODO: These are not in USE's override list that we have, nor are they in Unicode 13.0.0
if 0xA926 <= U <= 0xA92A: UIPC = Top
# TODO: https://github.com/harfbuzz/harfbuzz/pull/1037
@ -380,14 +418,18 @@ def map_to_use(data):
if U in [0x11302, 0x11303, 0x114C1]: UIPC = Top
if 0x1CF8 <= U <= 0x1CF9: UIPC = Top
assert (UIPC in [Not_Applicable, Visual_Order_Left] or
USE == 'R' or
USE in use_positions), "%s %s %s %s %s" % (hex(U), UIPC, USE, UISC, UGC)
# TODO: https://github.com/harfbuzz/harfbuzz/pull/982
# also https://github.com/harfbuzz/harfbuzz/issues/1012
if 0x1112A <= U <= 0x1112B: UIPC = Top
if 0x11131 <= U <= 0x11132: UIPC = Top
assert (UIPC in [Not_Applicable, Visual_Order_Left] or U == 0x0F7F or
USE in use_positions), "%s %s %s %s %s %s" % (hex(U), UIPC, USE, UISC, UGC, AJT)
pos_mapping = use_positions.get(USE, None)
if pos_mapping:
values = [k for k,v in pos_mapping.items() if v and UIPC in v]
assert len(values) == 1, "%s %s %s %s %s %s" % (hex(U), UIPC, USE, UISC, UGC, values)
assert len(values) == 1, "%s %s %s %s %s %s %s" % (hex(U), UIPC, USE, UISC, UGC, AJT, values)
USE = USE + values[0]
out[U] = (USE, UBlock)
@ -400,7 +442,7 @@ print ("/* == Start of generated table == */")
print ("/*")
print (" * The following table is generated by running:")
print (" *")
print (" * ./gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt Blocks.txt")
print (" * {} IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt ArabicShaping.txt Blocks.txt IndicSyllabicCategory-Additional.txt IndicPositionalCategory-Additional.txt".format (sys.argv[0]))
print (" *")
print (" * on files with these headers:")
print (" *")

View File

@ -40,36 +40,34 @@ static const unsigned char _use_syllable_machine_trans_keys[] = {
12u, 48u, 1u, 15u, 1u, 1u, 12u, 48u, 1u, 1u, 0u, 48u, 11u, 48u, 11u, 48u,
1u, 15u, 1u, 1u, 22u, 48u, 23u, 48u, 24u, 47u, 25u, 47u, 26u, 47u, 45u, 46u,
46u, 46u, 24u, 48u, 24u, 48u, 24u, 48u, 1u, 1u, 24u, 48u, 23u, 48u, 23u, 48u,
23u, 48u, 22u, 48u, 22u, 48u, 22u, 48u, 22u, 48u, 11u, 48u, 1u, 48u, 13u, 13u,
4u, 4u, 11u, 48u, 41u, 42u, 42u, 42u, 11u, 48u, 22u, 48u, 23u, 48u, 24u, 47u,
25u, 47u, 26u, 47u, 45u, 46u, 46u, 46u, 24u, 48u, 24u, 48u, 24u, 48u, 24u, 48u,
23u, 48u, 23u, 48u, 23u, 48u, 22u, 48u, 22u, 48u, 22u, 48u, 22u, 48u, 11u, 48u,
1u, 48u, 1u, 15u, 4u, 4u, 13u, 13u, 12u, 48u, 1u, 48u, 11u, 48u, 41u, 42u,
42u, 42u, 1u, 5u, 0
23u, 48u, 22u, 48u, 22u, 48u, 22u, 48u, 11u, 48u, 1u, 48u, 13u, 13u, 4u, 4u,
11u, 48u, 41u, 42u, 42u, 42u, 11u, 48u, 22u, 48u, 23u, 48u, 24u, 47u, 25u, 47u,
26u, 47u, 45u, 46u, 46u, 46u, 24u, 48u, 24u, 48u, 24u, 48u, 24u, 48u, 23u, 48u,
23u, 48u, 23u, 48u, 22u, 48u, 22u, 48u, 22u, 48u, 11u, 48u, 1u, 48u, 1u, 15u,
4u, 4u, 13u, 13u, 12u, 48u, 1u, 48u, 11u, 48u, 41u, 42u, 42u, 42u, 1u, 5u,
0
};
static const char _use_syllable_machine_key_spans[] = {
37, 15, 1, 37, 1, 49, 38, 38,
15, 1, 27, 26, 24, 23, 22, 2,
1, 25, 25, 25, 1, 25, 26, 26,
26, 27, 27, 27, 27, 38, 48, 1,
1, 38, 2, 1, 38, 27, 26, 24,
23, 22, 2, 1, 25, 25, 25, 25,
26, 26, 26, 27, 27, 27, 27, 38,
48, 15, 1, 1, 37, 48, 38, 2,
1, 5
26, 27, 27, 27, 38, 48, 1, 1,
38, 2, 1, 38, 27, 26, 24, 23,
22, 2, 1, 25, 25, 25, 25, 26,
26, 26, 27, 27, 27, 38, 48, 15,
1, 1, 37, 48, 38, 2, 1, 5
};
static const short _use_syllable_machine_index_offsets[] = {
0, 38, 54, 56, 94, 96, 146, 185,
224, 240, 242, 270, 297, 322, 346, 369,
372, 374, 400, 426, 452, 454, 480, 507,
534, 561, 589, 617, 645, 673, 712, 761,
763, 765, 804, 807, 809, 848, 876, 903,
928, 952, 975, 978, 980, 1006, 1032, 1058,
1084, 1111, 1138, 1165, 1193, 1221, 1249, 1277,
1316, 1365, 1381, 1383, 1385, 1423, 1472, 1511,
1514, 1516
534, 561, 589, 617, 645, 684, 733, 735,
737, 776, 779, 781, 820, 848, 875, 900,
924, 947, 950, 952, 978, 1004, 1030, 1056,
1083, 1110, 1137, 1165, 1193, 1221, 1260, 1309,
1325, 1327, 1329, 1367, 1416, 1455, 1458, 1460
};
static const char _use_syllable_machine_indicies[] = {
@ -147,136 +145,129 @@ static const char _use_syllable_machine_indicies[] = {
44, 41, 41, 41, 53, 54, 55, 41,
56, 57, 58, 41, 41, 41, 41, 45,
60, 61, 62, 65, 41, 44, 45, 46,
47, 48, 41, 68, 44, 41, 41, 41,
47, 48, 41, 41, 44, 41, 41, 41,
53, 54, 55, 41, 56, 57, 58, 41,
41, 41, 41, 45, 60, 61, 62, 65,
41, 44, 45, 46, 47, 48, 41, 41,
41, 44, 45, 46, 47, 48, 49, 50,
44, 41, 41, 41, 53, 54, 55, 41,
56, 57, 58, 41, 41, 41, 41, 45,
60, 61, 62, 65, 41, 44, 45, 46,
47, 48, 49, 50, 44, 41, 41, 41,
53, 54, 55, 41, 56, 57, 58, 41,
41, 41, 41, 45, 60, 61, 62, 65,
41, 42, 1, 41, 41, 43, 41, 41,
41, 41, 41, 41, 44, 45, 46, 47,
48, 49, 50, 44, 51, 41, 52, 53,
54, 55, 41, 56, 57, 58, 41, 41,
41, 41, 59, 60, 61, 62, 1, 41,
42, 63, 63, 63, 63, 63, 63, 63,
63, 63, 63, 63, 63, 63, 64, 63,
63, 63, 63, 63, 63, 63, 45, 46,
47, 48, 63, 63, 63, 63, 63, 63,
63, 63, 63, 63, 56, 57, 58, 63,
63, 63, 63, 63, 60, 61, 62, 65,
63, 70, 69, 11, 71, 42, 1, 41,
60, 61, 62, 65, 41, 42, 1, 41,
41, 43, 41, 41, 41, 41, 41, 41,
44, 45, 46, 47, 48, 49, 50, 44,
51, 9, 52, 53, 54, 55, 41, 56,
57, 58, 41, 17, 72, 41, 59, 60,
61, 62, 1, 41, 17, 72, 73, 72,
73, 3, 6, 74, 74, 75, 74, 74,
74, 74, 74, 74, 18, 19, 20, 21,
22, 23, 24, 18, 25, 27, 27, 28,
29, 30, 74, 31, 32, 33, 74, 74,
74, 74, 37, 38, 39, 40, 6, 74,
18, 19, 20, 21, 22, 74, 74, 74,
74, 74, 74, 28, 29, 30, 74, 31,
32, 33, 74, 74, 74, 74, 19, 38,
39, 40, 76, 74, 19, 20, 21, 22,
74, 74, 74, 74, 74, 74, 74, 74,
74, 74, 31, 32, 33, 74, 74, 74,
74, 74, 38, 39, 40, 76, 74, 20,
21, 22, 74, 74, 74, 74, 74, 74,
74, 74, 74, 74, 74, 74, 74, 74,
74, 74, 74, 74, 38, 39, 40, 74,
21, 22, 74, 74, 74, 74, 74, 74,
74, 74, 74, 74, 74, 74, 74, 74,
74, 74, 74, 74, 38, 39, 40, 74,
22, 74, 74, 74, 74, 74, 74, 74,
74, 74, 74, 74, 74, 74, 74, 74,
74, 74, 74, 38, 39, 40, 74, 38,
39, 74, 39, 74, 20, 21, 22, 74,
74, 74, 74, 74, 74, 74, 74, 74,
74, 31, 32, 33, 74, 74, 74, 74,
74, 38, 39, 40, 76, 74, 20, 21,
22, 74, 74, 74, 74, 74, 74, 74,
74, 74, 74, 74, 32, 33, 74, 74,
74, 74, 74, 38, 39, 40, 76, 74,
20, 21, 22, 74, 74, 74, 74, 74,
74, 74, 74, 74, 74, 74, 74, 33,
74, 74, 74, 74, 74, 38, 39, 40,
76, 74, 20, 21, 22, 74, 74, 74,
74, 74, 74, 74, 74, 74, 74, 74,
74, 74, 74, 74, 74, 74, 74, 38,
39, 40, 76, 74, 19, 20, 21, 22,
74, 74, 74, 74, 74, 74, 28, 29,
30, 74, 31, 32, 33, 74, 74, 74,
74, 19, 38, 39, 40, 76, 74, 19,
20, 21, 22, 74, 74, 74, 74, 74,
74, 74, 29, 30, 74, 31, 32, 33,
74, 74, 74, 74, 19, 38, 39, 40,
76, 74, 19, 20, 21, 22, 74, 74,
74, 74, 74, 74, 74, 74, 30, 74,
31, 32, 33, 74, 74, 74, 74, 19,
38, 39, 40, 76, 74, 18, 19, 20,
21, 22, 74, 24, 18, 74, 74, 74,
28, 29, 30, 74, 31, 32, 33, 74,
74, 74, 74, 19, 38, 39, 40, 76,
74, 18, 19, 20, 21, 22, 74, 77,
18, 74, 74, 74, 28, 29, 30, 74,
31, 32, 33, 74, 74, 74, 74, 19,
38, 39, 40, 76, 74, 18, 19, 20,
21, 22, 74, 74, 18, 74, 74, 74,
28, 29, 30, 74, 31, 32, 33, 74,
74, 74, 74, 19, 38, 39, 40, 76,
74, 18, 19, 20, 21, 22, 23, 24,
18, 74, 74, 74, 28, 29, 30, 74,
31, 32, 33, 74, 74, 74, 74, 19,
38, 39, 40, 76, 74, 3, 6, 74,
74, 75, 74, 74, 74, 74, 74, 74,
51, 41, 52, 53, 54, 55, 41, 56,
57, 58, 41, 41, 41, 41, 59, 60,
61, 62, 1, 41, 42, 63, 63, 63,
63, 63, 63, 63, 63, 63, 63, 63,
63, 63, 64, 63, 63, 63, 63, 63,
63, 63, 45, 46, 47, 48, 63, 63,
63, 63, 63, 63, 63, 63, 63, 63,
56, 57, 58, 63, 63, 63, 63, 63,
60, 61, 62, 65, 63, 69, 68, 11,
70, 42, 1, 41, 41, 43, 41, 41,
41, 41, 41, 41, 44, 45, 46, 47,
48, 49, 50, 44, 51, 9, 52, 53,
54, 55, 41, 56, 57, 58, 41, 17,
71, 41, 59, 60, 61, 62, 1, 41,
17, 71, 72, 71, 72, 3, 6, 73,
73, 74, 73, 73, 73, 73, 73, 73,
18, 19, 20, 21, 22, 23, 24, 18,
25, 74, 27, 28, 29, 30, 74, 31,
32, 33, 74, 74, 74, 74, 37, 38,
39, 40, 6, 74, 3, 74, 74, 74,
74, 74, 74, 74, 74, 74, 74, 74,
74, 74, 4, 74, 74, 74, 74, 74,
74, 74, 19, 20, 21, 22, 74, 74,
74, 74, 74, 74, 74, 74, 74, 74,
31, 32, 33, 74, 74, 74, 74, 74,
38, 39, 40, 76, 74, 3, 78, 78,
78, 78, 78, 78, 78, 78, 78, 78,
78, 78, 78, 4, 78, 79, 74, 14,
74, 6, 78, 78, 78, 78, 78, 78,
78, 78, 78, 78, 78, 78, 78, 78,
78, 78, 78, 78, 78, 78, 78, 78,
78, 78, 78, 78, 78, 78, 78, 78,
78, 6, 78, 78, 78, 6, 78, 9,
74, 74, 74, 9, 74, 74, 74, 74,
74, 3, 6, 14, 74, 75, 74, 74,
74, 74, 74, 74, 18, 19, 20, 21,
25, 27, 27, 28, 29, 30, 73, 31,
32, 33, 73, 73, 73, 73, 37, 38,
39, 40, 6, 73, 18, 19, 20, 21,
22, 73, 73, 73, 73, 73, 73, 28,
29, 30, 73, 31, 32, 33, 73, 73,
73, 73, 19, 38, 39, 40, 75, 73,
19, 20, 21, 22, 73, 73, 73, 73,
73, 73, 73, 73, 73, 73, 31, 32,
33, 73, 73, 73, 73, 73, 38, 39,
40, 75, 73, 20, 21, 22, 73, 73,
73, 73, 73, 73, 73, 73, 73, 73,
73, 73, 73, 73, 73, 73, 73, 73,
38, 39, 40, 73, 21, 22, 73, 73,
73, 73, 73, 73, 73, 73, 73, 73,
73, 73, 73, 73, 73, 73, 73, 73,
38, 39, 40, 73, 22, 73, 73, 73,
73, 73, 73, 73, 73, 73, 73, 73,
73, 73, 73, 73, 73, 73, 73, 38,
39, 40, 73, 38, 39, 73, 39, 73,
20, 21, 22, 73, 73, 73, 73, 73,
73, 73, 73, 73, 73, 31, 32, 33,
73, 73, 73, 73, 73, 38, 39, 40,
75, 73, 20, 21, 22, 73, 73, 73,
73, 73, 73, 73, 73, 73, 73, 73,
32, 33, 73, 73, 73, 73, 73, 38,
39, 40, 75, 73, 20, 21, 22, 73,
73, 73, 73, 73, 73, 73, 73, 73,
73, 73, 73, 33, 73, 73, 73, 73,
73, 38, 39, 40, 75, 73, 20, 21,
22, 73, 73, 73, 73, 73, 73, 73,
73, 73, 73, 73, 73, 73, 73, 73,
73, 73, 73, 38, 39, 40, 75, 73,
19, 20, 21, 22, 73, 73, 73, 73,
73, 73, 28, 29, 30, 73, 31, 32,
33, 73, 73, 73, 73, 19, 38, 39,
40, 75, 73, 19, 20, 21, 22, 73,
73, 73, 73, 73, 73, 73, 29, 30,
73, 31, 32, 33, 73, 73, 73, 73,
19, 38, 39, 40, 75, 73, 19, 20,
21, 22, 73, 73, 73, 73, 73, 73,
73, 73, 30, 73, 31, 32, 33, 73,
73, 73, 73, 19, 38, 39, 40, 75,
73, 18, 19, 20, 21, 22, 73, 24,
18, 73, 73, 73, 28, 29, 30, 73,
31, 32, 33, 73, 73, 73, 73, 19,
38, 39, 40, 75, 73, 18, 19, 20,
21, 22, 73, 73, 18, 73, 73, 73,
28, 29, 30, 73, 31, 32, 33, 73,
73, 73, 73, 19, 38, 39, 40, 75,
73, 18, 19, 20, 21, 22, 23, 24,
18, 73, 73, 73, 28, 29, 30, 73,
31, 32, 33, 73, 73, 73, 73, 19,
38, 39, 40, 75, 73, 3, 6, 73,
73, 74, 73, 73, 73, 73, 73, 73,
18, 19, 20, 21, 22, 23, 24, 18,
25, 73, 27, 28, 29, 30, 73, 31,
32, 33, 73, 73, 73, 73, 37, 38,
39, 40, 6, 73, 3, 73, 73, 73,
73, 73, 73, 73, 73, 73, 73, 73,
73, 73, 4, 73, 73, 73, 73, 73,
73, 73, 19, 20, 21, 22, 73, 73,
73, 73, 73, 73, 73, 73, 73, 73,
31, 32, 33, 73, 73, 73, 73, 73,
38, 39, 40, 75, 73, 3, 76, 76,
76, 76, 76, 76, 76, 76, 76, 76,
76, 76, 76, 4, 76, 77, 73, 14,
73, 6, 76, 76, 76, 76, 76, 76,
76, 76, 76, 76, 76, 76, 76, 76,
76, 76, 76, 76, 76, 76, 76, 76,
76, 76, 76, 76, 76, 76, 76, 76,
76, 6, 76, 76, 76, 6, 76, 9,
73, 73, 73, 9, 73, 73, 73, 73,
73, 3, 6, 14, 73, 74, 73, 73,
73, 73, 73, 73, 18, 19, 20, 21,
22, 23, 24, 18, 25, 26, 27, 28,
29, 30, 74, 31, 32, 33, 74, 34,
35, 74, 37, 38, 39, 40, 6, 74,
3, 6, 74, 74, 75, 74, 74, 74,
74, 74, 74, 18, 19, 20, 21, 22,
29, 30, 73, 31, 32, 33, 73, 34,
35, 73, 37, 38, 39, 40, 6, 73,
3, 6, 73, 73, 74, 73, 73, 73,
73, 73, 73, 18, 19, 20, 21, 22,
23, 24, 18, 25, 26, 27, 28, 29,
30, 74, 31, 32, 33, 74, 74, 74,
74, 37, 38, 39, 40, 6, 74, 34,
35, 74, 35, 74, 9, 78, 78, 78,
9, 78, 0
30, 73, 31, 32, 33, 73, 73, 73,
73, 37, 38, 39, 40, 6, 73, 34,
35, 73, 35, 73, 9, 76, 76, 76,
9, 76, 0
};
static const char _use_syllable_machine_trans_targs[] = {
5, 8, 5, 36, 2, 5, 1, 47,
5, 6, 5, 31, 33, 57, 58, 60,
61, 34, 37, 38, 39, 40, 41, 51,
52, 54, 62, 55, 48, 49, 50, 44,
45, 46, 63, 64, 65, 56, 42, 43,
5, 8, 5, 35, 2, 5, 1, 46,
5, 6, 5, 30, 32, 55, 56, 58,
59, 33, 36, 37, 38, 39, 40, 50,
51, 52, 60, 53, 47, 48, 49, 43,
44, 45, 61, 62, 63, 54, 41, 42,
5, 5, 7, 0, 10, 11, 12, 13,
14, 25, 26, 28, 29, 22, 23, 24,
17, 18, 19, 30, 15, 16, 5, 5,
9, 20, 5, 21, 27, 5, 32, 5,
35, 5, 5, 3, 4, 53, 5, 59
14, 25, 26, 27, 28, 22, 23, 24,
17, 18, 19, 29, 15, 16, 5, 5,
9, 20, 5, 21, 5, 31, 5, 34,
5, 5, 3, 4, 5, 57
};
static const char _use_syllable_machine_trans_actions[] = {
@ -288,8 +279,8 @@ static const char _use_syllable_machine_trans_actions[] = {
11, 12, 5, 0, 0, 0, 0, 0,
0, 0, 0, 0, 5, 0, 0, 0,
0, 0, 0, 0, 0, 0, 13, 14,
0, 0, 15, 0, 0, 16, 0, 17,
0, 18, 19, 0, 0, 5, 20, 0
0, 0, 15, 0, 16, 0, 17, 0,
18, 19, 0, 0, 20, 0
};
static const char _use_syllable_machine_to_state_actions[] = {
@ -300,8 +291,7 @@ static const char _use_syllable_machine_to_state_actions[] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0
0, 0, 0, 0, 0, 0, 0, 0
};
static const char _use_syllable_machine_from_state_actions[] = {
@ -312,20 +302,18 @@ static const char _use_syllable_machine_from_state_actions[] = {
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0,
0, 0
0, 0, 0, 0, 0, 0, 0, 0
};
static const short _use_syllable_machine_eof_trans[] = {
1, 3, 3, 6, 6, 0, 42, 42,
64, 64, 42, 42, 42, 42, 42, 42,
42, 42, 42, 42, 67, 42, 42, 42,
42, 42, 42, 42, 42, 42, 64, 70,
72, 42, 74, 74, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 75, 75, 75, 75, 75, 75, 75,
75, 79, 75, 75, 79, 75, 75, 75,
75, 79
42, 42, 42, 42, 42, 64, 69, 71,
42, 73, 73, 74, 74, 74, 74, 74,
74, 74, 74, 74, 74, 74, 74, 74,
74, 74, 74, 74, 74, 74, 74, 77,
74, 74, 77, 74, 74, 74, 74, 77
};
static const int use_syllable_machine_start = 5;
@ -339,7 +327,7 @@ static const int use_syllable_machine_en_main = 5;
#line 161 "hb-ot-shape-complex-use-machine.rl"
#line 160 "hb-ot-shape-complex-use-machine.rl"
#define found_syllable(syllable_type) \
@ -381,7 +369,7 @@ find_syllables_use (hb_buffer_t *buffer)
unsigned int act;
int cs;
#line 385 "hb-ot-shape-complex-use-machine.hh"
#line 373 "hb-ot-shape-complex-use-machine.hh"
{
cs = use_syllable_machine_start;
ts = 0;
@ -389,12 +377,12 @@ find_syllables_use (hb_buffer_t *buffer)
act = 0;
}
#line 204 "hb-ot-shape-complex-use-machine.rl"
#line 203 "hb-ot-shape-complex-use-machine.rl"
unsigned int syllable_serial = 1;
#line 398 "hb-ot-shape-complex-use-machine.hh"
#line 386 "hb-ot-shape-complex-use-machine.hh"
{
int _slen;
int _trans;
@ -408,7 +396,7 @@ _resume:
#line 1 "NONE"
{ts = p;}
break;
#line 412 "hb-ot-shape-complex-use-machine.hh"
#line 400 "hb-ot-shape-complex-use-machine.hh"
}
_keys = _use_syllable_machine_trans_keys + (cs<<1);
@ -431,59 +419,59 @@ _eof_trans:
{te = p+1;}
break;
case 8:
#line 149 "hb-ot-shape-complex-use-machine.rl"
#line 148 "hb-ot-shape-complex-use-machine.rl"
{te = p+1;{ found_syllable (independent_cluster); }}
break;
case 13:
#line 152 "hb-ot-shape-complex-use-machine.rl"
#line 151 "hb-ot-shape-complex-use-machine.rl"
{te = p+1;{ found_syllable (standard_cluster); }}
break;
case 11:
#line 156 "hb-ot-shape-complex-use-machine.rl"
#line 155 "hb-ot-shape-complex-use-machine.rl"
{te = p+1;{ found_syllable (broken_cluster); }}
break;
case 9:
#line 157 "hb-ot-shape-complex-use-machine.rl"
#line 156 "hb-ot-shape-complex-use-machine.rl"
{te = p+1;{ found_syllable (non_cluster); }}
break;
case 14:
#line 150 "hb-ot-shape-complex-use-machine.rl"
#line 149 "hb-ot-shape-complex-use-machine.rl"
{te = p;p--;{ found_syllable (virama_terminated_cluster); }}
break;
case 15:
#line 151 "hb-ot-shape-complex-use-machine.rl"
#line 150 "hb-ot-shape-complex-use-machine.rl"
{te = p;p--;{ found_syllable (sakot_terminated_cluster); }}
break;
case 12:
#line 152 "hb-ot-shape-complex-use-machine.rl"
#line 151 "hb-ot-shape-complex-use-machine.rl"
{te = p;p--;{ found_syllable (standard_cluster); }}
break;
case 17:
#line 153 "hb-ot-shape-complex-use-machine.rl"
#line 152 "hb-ot-shape-complex-use-machine.rl"
{te = p;p--;{ found_syllable (number_joiner_terminated_cluster); }}
break;
case 16:
#line 154 "hb-ot-shape-complex-use-machine.rl"
#line 153 "hb-ot-shape-complex-use-machine.rl"
{te = p;p--;{ found_syllable (numeral_cluster); }}
break;
case 18:
#line 155 "hb-ot-shape-complex-use-machine.rl"
#line 154 "hb-ot-shape-complex-use-machine.rl"
{te = p;p--;{ found_syllable (symbol_cluster); }}
break;
case 19:
#line 156 "hb-ot-shape-complex-use-machine.rl"
#line 155 "hb-ot-shape-complex-use-machine.rl"
{te = p;p--;{ found_syllable (broken_cluster); }}
break;
case 20:
#line 157 "hb-ot-shape-complex-use-machine.rl"
#line 156 "hb-ot-shape-complex-use-machine.rl"
{te = p;p--;{ found_syllable (non_cluster); }}
break;
case 1:
#line 152 "hb-ot-shape-complex-use-machine.rl"
#line 151 "hb-ot-shape-complex-use-machine.rl"
{{p = ((te))-1;}{ found_syllable (standard_cluster); }}
break;
case 4:
#line 156 "hb-ot-shape-complex-use-machine.rl"
#line 155 "hb-ot-shape-complex-use-machine.rl"
{{p = ((te))-1;}{ found_syllable (broken_cluster); }}
break;
case 2:
@ -501,16 +489,16 @@ _eof_trans:
case 3:
#line 1 "NONE"
{te = p+1;}
#line 156 "hb-ot-shape-complex-use-machine.rl"
#line 155 "hb-ot-shape-complex-use-machine.rl"
{act = 8;}
break;
case 10:
#line 1 "NONE"
{te = p+1;}
#line 157 "hb-ot-shape-complex-use-machine.rl"
#line 156 "hb-ot-shape-complex-use-machine.rl"
{act = 9;}
break;
#line 514 "hb-ot-shape-complex-use-machine.hh"
#line 502 "hb-ot-shape-complex-use-machine.hh"
}
_again:
@ -519,7 +507,7 @@ _again:
#line 1 "NONE"
{ts = 0;}
break;
#line 523 "hb-ot-shape-complex-use-machine.hh"
#line 511 "hb-ot-shape-complex-use-machine.hh"
}
if ( ++p != pe )
@ -535,7 +523,7 @@ _again:
}
#line 209 "hb-ot-shape-complex-use-machine.rl"
#line 208 "hb-ot-shape-complex-use-machine.rl"
}

View File

@ -96,8 +96,7 @@ h = H | HVM | Sk;
# Override: Adhoc ZWJ placement. https://github.com/harfbuzz/harfbuzz/issues/542#issuecomment-353169729
consonant_modifiers = CMAbv* CMBlw* ((ZWJ?.h.ZWJ? B | SUB) CMAbv? CMBlw*)*;
# Override: Allow two MBlw. https://github.com/harfbuzz/harfbuzz/issues/376
medial_consonants = MPre? MAbv? MBlw?.MBlw? MPst?;
medial_consonants = MPre? MAbv? MBlw? MPst?;
dependent_vowels = VPre* VAbv* VBlw* VPst*;
vowel_modifiers = HVM? VMPre* VMAbv* VMBlw* VMPst*;
final_consonants = FAbv* FBlw* FPst*;

View File

@ -2,7 +2,7 @@
/*
* The following table is generated by running:
*
* ./gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt Blocks.txt
* ./gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt ArabicShaping.txt Blocks.txt IndicSyllabicCategory-Additional.txt IndicPositionalCategory-Additional.txt
*
* on files with these headers:
*
@ -10,8 +10,24 @@
* # Date: 2019-07-22, 19:55:00 GMT [KW, RP]
* # IndicPositionalCategory-13.0.0.txt
* # Date: 2019-07-23, 00:01:00 GMT [KW, RP]
* # ArabicShaping-13.0.0.txt
* # Date: 2020-01-31, 23:55:00 GMT [KW, RP]
* # Blocks-13.0.0.txt
* # Date: 2019-07-10, 19:06:00 GMT [KW]
* # Override values For Indic_Syllabic_Category
* # Not derivable
* # Initial version based on Unicode 7.0 by Andrew Glass 2014-03-17
* # Updated for Unicode 10.0 by Andrew Glass 2017-07-25
* # Updated for Unicode 12.1 by Andrew Glass 2019-05-24
* # Updated for Unicode 13.0 by Andrew Glass 2020-07-28
* # Override values For Indic_Positional_Category
* # Not derivable
* # Initial version based on Unicode 7.0 by Andrew Glass 2014-03-17
* # Updated for Unicode 10.0 by Andrew Glass 2017-07-25
* # Ammended for Unicode 10.0 by Andrew Glass 2018-09-21
* # Updated for L2/19-083 by Andrew Glass 2019-05-06
* # Updated for Unicode 12.1 by Andrew Glass 2019-05-30
* # Updated for Unicode 13.0 by Andrew Glass 2020-07-28
* UnicodeData.txt does not have a header.
*/
@ -84,7 +100,31 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 00C0 */ O, O, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
/* 00D0 */ O, O, O, O, O, O, O, GB,
#define use_offset_0x0900u 80
#define use_offset_0x0640u 80
/* Arabic */
/* 0640 */ B, O, O, O, O, O, O, O,
#define use_offset_0x07c8u 88
/* NKo */
O, O, B, B, B, B, B, B,
/* 07D0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 07E0 */ B, B, B, B, B, B, B, B, B, B, B, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv,
/* 07F0 */ VMAbv, VMAbv, VMAbv, VMAbv, O, O, O, O, O, O, B, O, O, VMAbv, O, O,
#define use_offset_0x0840u 144
/* Mandaic */
/* 0840 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 0850 */ B, B, B, B, B, B, B, B, B, CMBlw, CMBlw, CMBlw, O, O, O, O,
#define use_offset_0x0900u 176
/* Devanagari */
@ -104,7 +144,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 0990 */ B, O, O, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 09A0 */ B, B, B, B, B, B, B, B, B, O, B, B, B, B, B, B,
/* 09B0 */ B, O, B, O, O, O, B, B, B, B, O, O, CMBlw, B, VPst, VPre,
/* 09C0 */ VPst, VBlw, VBlw, VBlw, VBlw, O, O, VPre, VPre, O, O, VPst, VPst, H, IND, O,
/* 09C0 */ VPst, VBlw, VBlw, VBlw, VBlw, O, O, VPre, VPre, O, O, VPre, VPre, H, IND, O,
/* 09D0 */ O, O, O, O, O, O, O, VPst, O, O, O, O, B, B, O, B,
/* 09E0 */ B, B, VBlw, VBlw, O, O, B, B, B, B, B, B, B, B, B, B,
/* 09F0 */ B, B, O, O, O, O, O, O, O, O, O, O, B, O, FMAbv, O,
@ -137,7 +177,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 0B10 */ B, O, O, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 0B20 */ B, B, B, B, B, B, B, B, B, O, B, B, B, B, B, B,
/* 0B30 */ B, O, B, B, O, B, B, B, B, B, O, O, CMBlw, B, VPst, VAbv,
/* 0B40 */ VPst, VBlw, VBlw, VBlw, VBlw, O, O, VPre, VPst, O, O, VPst, VPst, H, O, O,
/* 0B40 */ VPst, VBlw, VBlw, VBlw, VBlw, O, O, VPre, VPre, O, O, VPre, VPre, H, O, O,
/* 0B50 */ O, O, O, O, O, VAbv, VAbv, VAbv, O, O, O, O, B, B, O, B,
/* 0B60 */ B, B, VBlw, VBlw, O, O, B, B, B, B, B, B, B, B, B, B,
/* 0B70 */ O, B, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
@ -148,7 +188,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 0B90 */ B, O, B, B, B, B, O, O, O, B, B, O, B, O, B, B,
/* 0BA0 */ O, O, O, B, B, O, O, O, B, B, B, O, O, O, B, B,
/* 0BB0 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, VPst, VPst,
/* 0BC0 */ VAbv, VPst, VPst, O, O, O, VPre, VPre, VPre, O, VPst, VPst, VPst, H, O, O,
/* 0BC0 */ VAbv, VPst, VPst, O, O, O, VPre, VPre, VPre, O, VPre, VPre, VPre, H, O, O,
/* 0BD0 */ O, O, O, O, O, O, O, VPst, O, O, O, O, O, O, O, O,
/* 0BE0 */ O, O, O, O, O, O, B, B, B, B, B, B, B, B, B, B,
/* 0BF0 */ O, O, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
@ -181,7 +221,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 0D10 */ B, O, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 0D20 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 0D30 */ B, B, B, B, B, B, B, B, B, B, B, VAbv, VAbv, B, VPst, VPst,
/* 0D40 */ VPst, VPst, VPst, VBlw, VBlw, O, VPre, VPre, VPre, O, VPst, VPst, VPst, H, R, O,
/* 0D40 */ VPst, VPst, VPst, VBlw, VBlw, O, VPre, VPre, VPre, O, VPre, VPre, VPre, H, R, O,
/* 0D50 */ O, O, O, O, IND, IND, IND, VPst, O, O, O, O, O, O, O, B,
/* 0D60 */ B, B, VBlw, VBlw, O, O, B, B, B, B, B, B, B, B, B, B,
/* 0D70 */ O, O, O, O, O, O, O, O, O, O, IND, IND, IND, IND, IND, IND,
@ -193,28 +233,30 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 0DA0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 0DB0 */ B, B, O, B, B, B, B, B, B, B, B, B, O, B, O, O,
/* 0DC0 */ B, B, B, B, B, B, B, O, O, O, H, O, O, O, O, VPst,
/* 0DD0 */ VPst, VPst, VAbv, VAbv, VBlw, O, VBlw, O, VPst, VPre, VPst, VPre, VPst, VPst, VPst, VPst,
/* 0DD0 */ VPst, VPst, VAbv, VAbv, VBlw, O, VBlw, O, VPst, VPre, VPre, VPre, VPre, VPre, VPre, VPst,
/* 0DE0 */ O, O, O, O, O, O, B, B, B, B, B, B, B, B, B, B,
/* 0DF0 */ O, O, VPst, VPst, O, O, O, O,
#define use_offset_0x0f18u 1352
#define use_offset_0x0f00u 1448
/* Tibetan */
VBlw, VBlw, O, O, O, O, O, O,
/* 0F00 */ B, B, O, O, B, B, B, O, O, O, O, O, O, O, O, O,
/* 0F10 */ O, O, O, O, O, O, O, O, VBlw, VBlw, O, O, O, O, O, O,
/* 0F20 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 0F30 */ B, B, B, B, O, FMBlw, O, FMBlw, O, CMAbv, O, O, O, O, VPst, VPre,
/* 0F30 */ B, B, B, B, O, FBlw, O, FBlw, O, CMAbv, O, O, O, O, VPst, VPre,
/* 0F40 */ B, B, B, B, B, B, B, B, O, B, B, B, B, B, B, B,
/* 0F50 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 0F60 */ B, B, B, B, B, B, B, B, B, B, B, B, B, O, O, O,
/* 0F70 */ O, VBlw, VBlw, VAbv, VBlw, VBlw, VAbv, VAbv, VAbv, VAbv, VBlw, VBlw, VBlw, VBlw, VMAbv, VMPst,
/* 0F70 */ O, CMBlw, VBlw, VAbv, VAbv, VBlw, VAbv, VAbv, VAbv, VAbv, VBlw, VBlw, VBlw, VBlw, VMAbv, IND,
/* 0F80 */ VBlw, VAbv, VMAbv, VMAbv, VBlw, IND, VMAbv, VMAbv, B, B, B, B, B, SUB, SUB, SUB,
/* 0F90 */ SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, O, SUB, SUB, SUB, SUB, SUB, SUB, SUB,
/* 0FA0 */ SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB,
/* 0FB0 */ SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, O, O, O,
/* 0FC0 */ O, O, O, O, O, O, FMBlw, O,
/* 0FC0 */ O, O, O, O, O, O, FBlw, O,
#define use_offset_0x1000u 1528
#define use_offset_0x1000u 1648
/* Myanmar */
@ -230,7 +272,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 1080 */ B, B, MBlw, VPst, VPre, VAbv, VAbv, VMPst, VMPst, VMPst, VMPst, VMPst, VMPst, VMBlw, B, VMPst,
/* 1090 */ B, B, B, B, B, B, B, B, B, B, VMPst, VMPst, VPst, VAbv, O, O,
#define use_offset_0x1700u 1688
#define use_offset_0x1700u 1808
/* Tagalog */
@ -258,12 +300,27 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 1780 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1790 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 17A0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 17B0 */ B, B, B, B, O, O, VPst, VAbv, VAbv, VAbv, VAbv, VBlw, VBlw, VBlw, VPst, VPst,
/* 17C0 */ VPst, VPre, VPre, VPre, VPst, VPst, VMAbv, VMPst, VPst, VMAbv, VMAbv, FMAbv, FAbv, CMAbv, FMAbv, FMAbv,
/* 17B0 */ B, B, B, B, O, O, VPst, VAbv, VAbv, VAbv, VAbv, VBlw, VBlw, VBlw, VPre, VPre,
/* 17C0 */ VPre, VPre, VPre, VPre, VPre, VPre, VMAbv, VMPst, VPst, VMAbv, VMAbv, FMAbv, FAbv, CMAbv, FMAbv, VMAbv,
/* 17D0 */ FMAbv, VAbv, H, FMAbv, O, O, O, O, O, O, O, O, B, FMAbv, O, O,
/* 17E0 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
/* 17F0 */ O, O, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
#define use_offset_0x1900u 1928
/* Mongolian */
/* 1800 */ B, O, O, O, O, O, O, B, O, O, B, O, O, O, O, O,
/* 1810 */ O, O, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
/* 1820 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1830 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1840 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1850 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1860 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1870 */ B, B, B, B, B, B, B, B, B, O, O, O, O, O, O, O,
/* 1880 */ GB, GB, GB, GB, GB, CMAbv, CMAbv, B, B, B, B, B, B, B, B, B,
/* 1890 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18A0 */ B, B, B, B, B, B, B, B, B, CMBlw, B, O, O, O, O, O,
#define use_offset_0x1900u 2240
/* Limbu */
@ -271,7 +328,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 1900 */ GB, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1910 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, O,
/* 1920 */ VAbv, VAbv, VBlw, VPst, VPst, VAbv, VAbv, VAbv, VAbv, SUB, SUB, SUB, O, O, O, O,
/* 1930 */ FPst, FPst, VMBlw, FPst, FPst, FPst, FPst, FPst, FPst, FBlw, VAbv, FMBlw, O, O, O, O,
/* 1930 */ FPst, FPst, VMBlw, FPst, FPst, FPst, FPst, FPst, FPst, FBlw, VMAbv, FMBlw, O, O, O, O,
/* 1940 */ O, O, O, O, O, O, B, B, B, B, B, B, B, B, B, B,
/* Tai Le */
@ -294,7 +351,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* Buginese */
/* 1A00 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1A10 */ B, B, B, B, B, B, B, VAbv, VBlw, VPre, VPst, VAbv, O, O, O, O,
/* 1A10 */ B, B, B, B, B, B, B, VAbv, VAbv, VPre, VPst, VAbv, O, O, O, O,
/* Tai Tham */
@ -303,11 +360,11 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 1A40 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1A50 */ B, B, B, B, B, MPre, MBlw, SUB, FAbv, FAbv, MAbv, SUB, SUB, SUB, SUB, O,
/* 1A60 */ Sk, VPst, VAbv, VPst, VPst, VAbv, VAbv, VAbv, VAbv, VBlw, VBlw, VAbv, VBlw, VPst, VPre, VPre,
/* 1A70 */ VPre, VPre, VPre, VAbv, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, VAbv, FMAbv, FMAbv, O, O, FMBlw,
/* 1A70 */ VPre, VPre, VPre, VAbv, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, VAbv, VMAbv, VMAbv, O, O, VMBlw,
/* 1A80 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
/* 1A90 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
#define use_offset_0x1b00u 2344
#define use_offset_0x1b00u 2656
/* Balinese */
@ -316,7 +373,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 1B10 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1B20 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1B30 */ B, B, B, B, CMAbv, VPst, VAbv, VAbv, VBlw, VBlw, VBlw, VBlw, VAbv, VAbv, VPre, VPre,
/* 1B40 */ VPst, VPst, VAbv, VAbv, H, B, B, B, B, B, B, B, O, O, O, O,
/* 1B40 */ VPre, VPre, VAbv, VAbv, H, B, B, B, B, B, B, B, O, O, O, O,
/* 1B50 */ B, B, B, B, B, B, B, B, B, B, O, GB, GB, O, O, GB,
/* 1B60 */ O, S, GB, S, S, S, S, S, GB, S, S, SMAbv, SMBlw, SMAbv, SMAbv, SMAbv,
/* 1B70 */ SMAbv, SMAbv, SMAbv, SMAbv, O, O, O, O, O, O, O, O, O, O, O, O,
@ -343,7 +400,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 1C30 */ FAbv, FAbv, FAbv, FAbv, VMPre, VMPre, FMAbv, CMBlw, O, O, O, O, O, O, O, O,
/* 1C40 */ B, B, B, B, B, B, B, B, B, B, O, O, O, B, B, B,
#define use_offset_0x1cd0u 2680
#define use_offset_0x1cd0u 2992
/* Vedic Extensions */
@ -352,20 +409,20 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 1CE0 */ VMAbv, VMPst, VMBlw, VMBlw, VMBlw, VMBlw, VMBlw, VMBlw, VMBlw, O, O, O, O, VMBlw, O, O,
/* 1CF0 */ O, O, IND, IND, VMAbv, CS, CS, VMPst, VMAbv, VMAbv, GB, O, O, O, O, O,
#define use_offset_0x1df8u 2728
#define use_offset_0x1df8u 3040
/* Combining Diacritical Marks Supplement */
O, O, O, FMAbv, O, O, O, O,
#define use_offset_0x2008u 2736
#define use_offset_0x2008u 3048
/* General Punctuation */
O, O, O, O, ZWNJ, ZWJ, O, O,
/* 2010 */ GB, GB, GB, GB, GB, O, O, O,
#define use_offset_0x2060u 2752
#define use_offset_0x2060u 3064
/* 2060 */ WJ, O, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
@ -374,20 +431,31 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 2070 */ O, O, O, O, FMPst, O, O, O, O, O, O, O, O, O, O, O,
/* 2080 */ O, O, FMPst, FMPst, FMPst, O, O, O,
#define use_offset_0x20f0u 2792
#define use_offset_0x20f0u 3104
/* Combining Diacritical Marks for Symbols */
/* 20F0 */ VMAbv, O, O, O, O, O, O, O,
#define use_offset_0x25c8u 2800
#define use_offset_0x25c8u 3112
/* Geometric Shapes */
O, O, O, O, GB, O, O, O,
O, O, O, O, B, O, O, O,
#define use_offset_0xa800u 2808
#define use_offset_0x2d30u 3120
/* Tifinagh */
/* 2D30 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 2D40 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 2D50 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 2D60 */ B, B, B, B, B, B, B, B, O, O, O, O, O, O, O, B,
/* 2D70 */ O, O, O, O, O, O, O, O, O, O, O, O, O, O, O, H,
#define use_offset_0xa800u 3200
/* Syloti Nagri */
@ -437,7 +505,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* A980 */ VMAbv, VMAbv, FAbv, VMPst, B, B, B, B, B, B, B, B, B, B, B, B,
/* A990 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* A9A0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* A9B0 */ B, B, B, CMAbv, VPst, VPst, VAbv, VAbv, VBlw, VBlw, VPre, VPre, VAbv, MBlw, MBlw, MBlw,
/* A9B0 */ B, B, B, CMAbv, VPst, VPst, VAbv, VAbv, VBlw, VBlw, VPre, VPre, VAbv, MBlw, MPst, MBlw,
/* A9C0 */ H, O, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
/* A9D0 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
@ -451,7 +519,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* AA00 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* AA10 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* AA20 */ B, B, B, B, B, B, B, B, B, VMAbv, VAbv, VAbv, VAbv, VBlw, VAbv, VPre,
/* AA30 */ VPre, VAbv, VBlw, MPst, MPre, MBlw, MBlw, O, O, O, O, O, O, O, O, O,
/* AA30 */ VPre, VAbv, VBlw, MPst, MPre, MAbv, MBlw, O, O, O, O, O, O, O, O, O,
/* AA40 */ B, B, B, FAbv, B, B, B, B, B, B, B, B, FAbv, FPst, O, O,
/* AA50 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
@ -474,7 +542,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* AAE0 */ B, B, B, B, B, B, B, B, B, B, B, VPre, VBlw, VAbv, VPre, VPst,
/* AAF0 */ O, O, O, O, O, VMPst, H, O,
#define use_offset_0xabc0u 3568
#define use_offset_0xabc0u 3960
/* Meetei Mayek */
@ -484,20 +552,75 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* ABE0 */ B, B, B, VPst, VPst, VAbv, VPst, VPst, VBlw, VPst, VPst, O, VMPst, VBlw, O, O,
/* ABF0 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
#define use_offset_0x10a00u 3632
#define use_offset_0x10a00u 4024
/* Kharoshthi */
/* 10A00 */ B, VBlw, VBlw, VBlw, O, VAbv, VBlw, O, O, O, O, O, VBlw, VBlw, VMBlw, VMAbv,
/* 10A00 */ B, VBlw, VBlw, VBlw, O, VAbv, VBlw, O, O, O, O, O, VPst, VMBlw, VMBlw, VMAbv,
/* 10A10 */ B, B, B, B, O, B, B, B, O, B, B, B, B, B, B, B,
/* 10A20 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 10A30 */ B, B, B, B, B, B, O, O, CMAbv, CMBlw, CMBlw, O, O, O, O, H,
/* 10A40 */ B, B, B, B, B, B, B, B, B, O, O, O, O, O, O, O,
#define use_offset_0x11000u 3712
#define use_offset_0x10ac0u 4104
/* Manichaean */
/* 10AC0 */ B, B, B, B, B, B, B, B, O, B, B, B, B, B, B, B,
/* 10AD0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 10AE0 */ B, B, B, B, B, CMBlw, CMBlw, O,
#define use_offset_0x10b80u 4144
/* Psalter Pahlavi */
/* 10B80 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 10B90 */ B, B, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
/* 10BA0 */ O, O, O, O, O, O, O, O, O, B, B, B, B, B, B, O,
#define use_offset_0x10d00u 4192
/* Hanifi Rohingya */
/* 10D00 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 10D10 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 10D20 */ B, B, B, B, VMAbv, VMAbv, VMAbv, CMAbv, O, O, O, O, O, O, O, O,
/* 10D30 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
#define use_offset_0x10e80u 4256
/* Yezidi */
/* 10E80 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 10E90 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 10EA0 */ B, B, B, B, B, B, B, B, B, B, O, VAbv, VAbv, O, O, O,
/* 10EB0 */ B, B, O, O, O, O, O, O,
#define use_offset_0x10f30u 4312
/* Sogdian */
/* 10F30 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 10F40 */ B, B, B, B, B, B, VMBlw, VMBlw, VMBlw, VMBlw, VMBlw, VMBlw, VMBlw, VMBlw, VMBlw, VMBlw,
/* 10F50 */ VMBlw, B, B, B, B, O, O, O,
#define use_offset_0x10fb0u 4352
/* Chorasmian */
/* 10FB0 */ B, O, B, B, B, B, B, O, B, B, B, B, B, B, B, B,
/* 10FC0 */ O, B, B, B, B, O, O, O, O, B, B, B, O, O, O, O,
/* 10FD0 */ O, O, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
/* 10FE0 */ O, O, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
/* 10FF0 */ O, O, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
/* Brahmi */
/* 11000 */ VMPst, VMAbv, VMPst, CS, CS, B, B, B, B, B, B, B, B, B, B, B,
@ -516,7 +639,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 110A0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 110B0 */ VPst, VPre, VPst, VBlw, VBlw, VAbv, VAbv, VPst, VPst, H, CMBlw, O, O, O, O, O,
#define use_offset_0x11100u 3904
#define use_offset_0x11100u 4624
/* Chakma */
@ -524,7 +647,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11100 */ VMAbv, VMAbv, VMAbv, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 11110 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 11120 */ B, B, B, B, B, B, B, VBlw, VBlw, VBlw, VAbv, VAbv, VPre, VBlw, VAbv, VAbv,
/* 11130 */ VBlw, VAbv, VAbv, H, CMBlw, O, B, B, B, B, B, B, B, B, B, B,
/* 11130 */ VBlw, VAbv, VAbv, H, CMAbv, O, B, B, B, B, B, B, B, B, B, B,
/* 11140 */ O, O, O, O, B, VPst, VPst, B, O, O, O, O, O, O, O, O,
/* Mahajani */
@ -540,7 +663,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 111A0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 111B0 */ B, B, B, VPst, VPre, VPst, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VAbv, VAbv, VAbv, VAbv,
/* 111C0 */ H, B, R, R, O, O, O, O, GB, FMBlw, CMBlw, VAbv, VBlw, O, VPre, VMAbv,
/* 111D0 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
/* 111D0 */ B, B, B, B, B, B, B, B, B, B, B, O, O, O, O, O,
/* Sinhala Archaic Numbers */
@ -554,7 +677,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11220 */ B, B, B, B, B, B, B, B, B, B, B, B, VPst, VPst, VPst, VBlw,
/* 11230 */ VAbv, VAbv, VAbv, VAbv, VMAbv, H, CMAbv, CMAbv, O, O, O, O, O, O, VMAbv, O,
#define use_offset_0x11280u 4224
#define use_offset_0x11280u 4944
/* Multani */
@ -577,12 +700,12 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11310 */ B, O, O, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 11320 */ B, B, B, B, B, B, B, B, B, O, B, B, B, B, B, B,
/* 11330 */ B, O, B, B, O, B, B, B, B, B, O, CMBlw, CMBlw, B, VPst, VPst,
/* 11340 */ VAbv, VPst, VPst, VPst, VPst, O, O, VPre, VPre, O, O, VPst, VPst, HVM, O, O,
/* 11340 */ VAbv, VPst, VPst, VPst, VPst, O, O, VPre, VPre, O, O, VPre, VPre, HVM, O, O,
/* 11350 */ O, O, O, O, O, O, O, VPst, O, O, O, O, O, O, B, B,
/* 11360 */ B, B, VPst, VPst, O, O, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, O, O, O,
/* 11370 */ VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, O, O, O,
#define use_offset_0x11400u 4472
#define use_offset_0x11400u 5192
/* Newa */
@ -601,11 +724,11 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11480 */ O, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 11490 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 114A0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 114B0 */ VPst, VPre, VPst, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VPre, VAbv, VPst, VPst, VPst, VPst, VMAbv,
/* 114B0 */ VPst, VPre, VPst, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VPre, VAbv, VPre, VPre, VPst, VPre, VMAbv,
/* 114C0 */ VMAbv, VMAbv, H, CMBlw, B, O, O, O, O, O, O, O, O, O, O, O,
/* 114D0 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
#define use_offset_0x11580u 4696
#define use_offset_0x11580u 5416
/* Siddham */
@ -613,7 +736,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11580 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 11590 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 115A0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, VPst,
/* 115B0 */ VPre, VPst, VBlw, VBlw, VBlw, VBlw, O, O, VPre, VPst, VPst, VPst, VMAbv, VMAbv, VMPst, H,
/* 115B0 */ VPre, VPst, VBlw, VBlw, VBlw, VBlw, O, O, VPre, VPre, VPre, VPre, VMAbv, VMAbv, VMPst, H,
/* 115C0 */ CMBlw, O, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
/* 115D0 */ O, O, O, O, O, O, O, O, B, B, B, B, VBlw, VBlw, O, O,
/* 115E0 */ O, O, O, O, O, O, O, O, O, O, O, O, O, O, O, O,
@ -645,10 +768,10 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11700 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 11710 */ B, B, B, B, B, B, B, B, B, B, B, O, O, MBlw, MPre, MAbv,
/* 11720 */ VPst, VPst, VAbv, VAbv, VBlw, VBlw, VPre, VAbv, VBlw, VAbv, VAbv, VAbv, O, O, O, O,
/* 11720 */ VPst, VPst, VAbv, VAbv, VBlw, VBlw, VPre, VAbv, VBlw, VAbv, VAbv, VMAbv, O, O, O, O,
/* 11730 */ B, B, B, B, B, B, B, B, B, B, B, B, O, O, O, O,
#define use_offset_0x11800u 5144
#define use_offset_0x11800u 5864
/* Dogra */
@ -658,7 +781,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11820 */ B, B, B, B, B, B, B, B, B, B, B, B, VPst, VPre, VPst, VBlw,
/* 11830 */ VBlw, VBlw, VBlw, VAbv, VAbv, VAbv, VAbv, VMAbv, VMPst, H, CMBlw, O, O, O, O, O,
#define use_offset_0x11900u 5208
#define use_offset_0x11900u 5928
/* Dives Akuru */
@ -666,11 +789,11 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11900 */ B, B, B, B, B, B, B, O, O, B, O, O, B, B, B, B,
/* 11910 */ B, B, B, B, O, B, B, O, B, B, B, B, B, B, B, B,
/* 11920 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 11930 */ VPst, VPst, VPst, VPst, VPst, VPre, O, VPre, VPst, O, O, VMAbv, VMAbv, VPst, H, R,
/* 11940 */ MPst, R, MBlw, CMBlw, O, O, O, O, O, O, O, O, O, O, O, O,
/* 11930 */ VPst, VPst, VPst, VPst, VPst, VPre, O, VPre, VPre, O, O, VMAbv, VMAbv, VPst, H, R,
/* 11940 */ MPst, R, MPst, CMBlw, O, O, O, O, O, O, O, O, O, O, O, O,
/* 11950 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
#define use_offset_0x119a0u 5304
#define use_offset_0x119a0u 6024
/* Nandinagari */
@ -698,7 +821,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11A80 */ B, B, B, B, R, R, R, R, R, R, FBlw, FBlw, FBlw, FBlw, FBlw, FBlw,
/* 11A90 */ FBlw, FBlw, FBlw, FBlw, FBlw, FBlw, VMAbv, VMPst, CMAbv, H, O, O, O, B, O, O,
#define use_offset_0x11c00u 5560
#define use_offset_0x11c00u 6280
/* Bhaiksuki */
@ -719,7 +842,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11CA0 */ SUB, SUB, SUB, SUB, SUB, SUB, SUB, SUB, O, SUB, SUB, SUB, SUB, SUB, SUB, SUB,
/* 11CB0 */ VBlw, VPre, VBlw, VAbv, VPst, VMAbv, VMAbv, O,
#define use_offset_0x11d00u 5744
#define use_offset_0x11d00u 6464
/* Masaram Gondi */
@ -739,7 +862,7 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11D90 */ VAbv, VAbv, O, VPst, VPst, VMAbv, VMPst, H, O, O, O, O, O, O, O, O,
/* 11DA0 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
#define use_offset_0x11ee0u 5920
#define use_offset_0x11ee0u 6640
/* Makasar */
@ -747,7 +870,132 @@ static const USE_TABLE_ELEMENT_TYPE use_table[] = {
/* 11EE0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 11EF0 */ B, B, GB, VAbv, VBlw, VPre, VPst, O,
}; /* Table items: 5944; occupancy: 74% */
#define use_offset_0x13430u 6664
/* Egyptian Hieroglyph Format Controls */
/* 13430 */ H, H, H, H, H, H, H, O,
#define use_offset_0x16b00u 6672
/* Pahawh Hmong */
/* 16B00 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 16B10 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 16B20 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 16B30 */ VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, O,
#define use_offset_0x16f00u 6728
/* Miao */
/* 16F00 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 16F10 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 16F20 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 16F30 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 16F40 */ B, B, B, B, B, B, B, B, B, B, B, O, O, O, O, CMBlw,
/* 16F50 */ IND, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw,
/* 16F60 */ VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw,
/* 16F70 */ VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw,
/* 16F80 */ VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, VBlw, O, O, O, O, O, O, O, VMBlw,
/* 16F90 */ VMBlw, VMBlw, VMBlw, O, O, O, O, O,
#define use_offset_0x16fe0u 6880
/* Ideographic Symbols and Punctuation */
/* 16FE0 */ O, O, O, O, B, O, O, O,
#define use_offset_0x18b00u 6888
/* Khitan Small Script */
/* 18B00 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18B10 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18B20 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18B30 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18B40 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18B50 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18B60 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18B70 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18B80 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18B90 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18BA0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18BB0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18BC0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18BD0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18BE0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18BF0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18C00 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18C10 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18C20 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18C30 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18C40 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18C50 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18C60 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18C70 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18C80 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18C90 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18CA0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18CB0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18CC0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 18CD0 */ B, B, B, B, B, B, O, O,
#define use_offset_0x1bc00u 7360
/* Duployan */
/* 1BC00 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1BC10 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1BC20 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1BC30 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1BC40 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1BC50 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1BC60 */ B, B, B, B, B, B, B, B, B, B, B, O, O, O, O, O,
/* 1BC70 */ B, B, B, B, B, B, B, B, B, B, B, B, B, O, O, O,
/* 1BC80 */ B, B, B, B, B, B, B, B, B, O, O, O, O, O, O, O,
/* 1BC90 */ B, B, B, B, B, B, B, B, B, B, O, O, O, CMBlw, CMBlw, O,
#define use_offset_0x1e100u 7520
/* Nyiakeng Puachue Hmong */
/* 1E100 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1E110 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1E120 */ B, B, B, B, B, B, B, B, B, B, B, B, B, O, O, O,
/* 1E130 */ VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, VMAbv, B, B, B, B, B, B, B, O, O,
/* 1E140 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, B, B,
#define use_offset_0x1e2c0u 7600
/* Wancho */
/* 1E2C0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1E2D0 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1E2E0 */ B, B, B, B, B, B, B, B, B, B, B, B, VMAbv, VMAbv, VMAbv, VMAbv,
/* 1E2F0 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
#define use_offset_0x1e900u 7664
/* Adlam */
/* 1E900 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1E910 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1E920 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1E930 */ B, B, B, B, B, B, B, B, B, B, B, B, B, B, B, B,
/* 1E940 */ B, B, B, B, CMAbv, CMAbv, CMAbv, CMAbv, CMAbv, CMAbv, CMAbv, B, O, O, O, O,
/* 1E950 */ B, B, B, B, B, B, B, B, B, B, O, O, O, O, O, O,
}; /* Table items: 7760; occupancy: 76% */
USE_TABLE_ELEMENT_TYPE
hb_use_get_category (hb_codepoint_t u)
@ -757,13 +1005,16 @@ hb_use_get_category (hb_codepoint_t u)
case 0x0u:
if (hb_in_range<hb_codepoint_t> (u, 0x0028u, 0x003Fu)) return use_table[u - 0x0028u + use_offset_0x0028u];
if (hb_in_range<hb_codepoint_t> (u, 0x00A0u, 0x00D7u)) return use_table[u - 0x00A0u + use_offset_0x00a0u];
if (hb_in_range<hb_codepoint_t> (u, 0x0640u, 0x0647u)) return use_table[u - 0x0640u + use_offset_0x0640u];
if (hb_in_range<hb_codepoint_t> (u, 0x07C8u, 0x07FFu)) return use_table[u - 0x07C8u + use_offset_0x07c8u];
if (hb_in_range<hb_codepoint_t> (u, 0x0840u, 0x085Fu)) return use_table[u - 0x0840u + use_offset_0x0840u];
if (hb_in_range<hb_codepoint_t> (u, 0x0900u, 0x0DF7u)) return use_table[u - 0x0900u + use_offset_0x0900u];
if (hb_in_range<hb_codepoint_t> (u, 0x0F18u, 0x0FC7u)) return use_table[u - 0x0F18u + use_offset_0x0f18u];
if (hb_in_range<hb_codepoint_t> (u, 0x0F00u, 0x0FC7u)) return use_table[u - 0x0F00u + use_offset_0x0f00u];
break;
case 0x1u:
if (hb_in_range<hb_codepoint_t> (u, 0x1000u, 0x109Fu)) return use_table[u - 0x1000u + use_offset_0x1000u];
if (hb_in_range<hb_codepoint_t> (u, 0x1700u, 0x17EFu)) return use_table[u - 0x1700u + use_offset_0x1700u];
if (hb_in_range<hb_codepoint_t> (u, 0x1700u, 0x18AFu)) return use_table[u - 0x1700u + use_offset_0x1700u];
if (hb_in_range<hb_codepoint_t> (u, 0x1900u, 0x1A9Fu)) return use_table[u - 0x1900u + use_offset_0x1900u];
if (hb_in_range<hb_codepoint_t> (u, 0x1B00u, 0x1C4Fu)) return use_table[u - 0x1B00u + use_offset_0x1b00u];
if (hb_in_range<hb_codepoint_t> (u, 0x1CD0u, 0x1CFFu)) return use_table[u - 0x1CD0u + use_offset_0x1cd0u];
@ -775,6 +1026,7 @@ hb_use_get_category (hb_codepoint_t u)
if (hb_in_range<hb_codepoint_t> (u, 0x2060u, 0x2087u)) return use_table[u - 0x2060u + use_offset_0x2060u];
if (hb_in_range<hb_codepoint_t> (u, 0x20F0u, 0x20F7u)) return use_table[u - 0x20F0u + use_offset_0x20f0u];
if (hb_in_range<hb_codepoint_t> (u, 0x25C8u, 0x25CFu)) return use_table[u - 0x25C8u + use_offset_0x25c8u];
if (hb_in_range<hb_codepoint_t> (u, 0x2D30u, 0x2D7Fu)) return use_table[u - 0x2D30u + use_offset_0x2d30u];
break;
case 0xAu:
@ -784,10 +1036,16 @@ hb_use_get_category (hb_codepoint_t u)
case 0x10u:
if (hb_in_range<hb_codepoint_t> (u, 0x10A00u, 0x10A4Fu)) return use_table[u - 0x10A00u + use_offset_0x10a00u];
if (hb_in_range<hb_codepoint_t> (u, 0x10AC0u, 0x10AE7u)) return use_table[u - 0x10AC0u + use_offset_0x10ac0u];
if (hb_in_range<hb_codepoint_t> (u, 0x10B80u, 0x10BAFu)) return use_table[u - 0x10B80u + use_offset_0x10b80u];
if (hb_in_range<hb_codepoint_t> (u, 0x10D00u, 0x10D3Fu)) return use_table[u - 0x10D00u + use_offset_0x10d00u];
if (hb_in_range<hb_codepoint_t> (u, 0x10E80u, 0x10EB7u)) return use_table[u - 0x10E80u + use_offset_0x10e80u];
if (hb_in_range<hb_codepoint_t> (u, 0x10F30u, 0x10F57u)) return use_table[u - 0x10F30u + use_offset_0x10f30u];
if (hb_in_range<hb_codepoint_t> (u, 0x10FB0u, 0x110BFu)) return use_table[u - 0x10FB0u + use_offset_0x10fb0u];
break;
case 0x11u:
if (hb_in_range<hb_codepoint_t> (u, 0x11000u, 0x110BFu)) return use_table[u - 0x11000u + use_offset_0x11000u];
if (hb_in_range<hb_codepoint_t> (u, 0x10FB0u, 0x110BFu)) return use_table[u - 0x10FB0u + use_offset_0x10fb0u];
if (hb_in_range<hb_codepoint_t> (u, 0x11100u, 0x1123Fu)) return use_table[u - 0x11100u + use_offset_0x11100u];
if (hb_in_range<hb_codepoint_t> (u, 0x11280u, 0x11377u)) return use_table[u - 0x11280u + use_offset_0x11280u];
if (hb_in_range<hb_codepoint_t> (u, 0x11400u, 0x114DFu)) return use_table[u - 0x11400u + use_offset_0x11400u];
@ -800,6 +1058,30 @@ hb_use_get_category (hb_codepoint_t u)
if (hb_in_range<hb_codepoint_t> (u, 0x11EE0u, 0x11EF7u)) return use_table[u - 0x11EE0u + use_offset_0x11ee0u];
break;
case 0x13u:
if (hb_in_range<hb_codepoint_t> (u, 0x13430u, 0x13437u)) return use_table[u - 0x13430u + use_offset_0x13430u];
break;
case 0x16u:
if (hb_in_range<hb_codepoint_t> (u, 0x16B00u, 0x16B37u)) return use_table[u - 0x16B00u + use_offset_0x16b00u];
if (hb_in_range<hb_codepoint_t> (u, 0x16F00u, 0x16F97u)) return use_table[u - 0x16F00u + use_offset_0x16f00u];
if (hb_in_range<hb_codepoint_t> (u, 0x16FE0u, 0x16FE7u)) return use_table[u - 0x16FE0u + use_offset_0x16fe0u];
break;
case 0x18u:
if (hb_in_range<hb_codepoint_t> (u, 0x18B00u, 0x18CD7u)) return use_table[u - 0x18B00u + use_offset_0x18b00u];
break;
case 0x1Bu:
if (hb_in_range<hb_codepoint_t> (u, 0x1BC00u, 0x1BC9Fu)) return use_table[u - 0x1BC00u + use_offset_0x1bc00u];
break;
case 0x1Eu:
if (hb_in_range<hb_codepoint_t> (u, 0x1E100u, 0x1E14Fu)) return use_table[u - 0x1E100u + use_offset_0x1e100u];
if (hb_in_range<hb_codepoint_t> (u, 0x1E2C0u, 0x1E2FFu)) return use_table[u - 0x1E2C0u + use_offset_0x1e2c0u];
if (hb_in_range<hb_codepoint_t> (u, 0x1E900u, 0x1E95Fu)) return use_table[u - 0x1E900u + use_offset_0x1e900u];
break;
default:
break;
}

View File

@ -320,7 +320,7 @@ _hb_preprocess_text_vowel_constraints (const hb_ot_shape_plan_t *plan HB_UNUSED,
switch (buffer->cur (1).codepoint)
{
case 0x0DCAu: case 0x0DD9u: case 0x0DDAu: case 0x0DDCu:
case 0x0DDDu:
case 0x0DDDu: case 0x0DDEu:
matched = true;
break;
}

View File

@ -341,6 +341,7 @@ hb_ot_shape_complex_categorize (const hb_ot_shape_planner_t *planner)
/* Unicode-6.1 additions */
case HB_SCRIPT_CHAKMA:
case HB_SCRIPT_MIAO:
case HB_SCRIPT_SHARADA:
case HB_SCRIPT_TAKRI:
@ -359,6 +360,7 @@ hb_ot_shape_complex_categorize (const hb_ot_shape_planner_t *planner)
/* Unicode-8.0 additions */
case HB_SCRIPT_AHOM:
case HB_SCRIPT_MULTANI:
/* Unicode-9.0 additions */
//case HB_SCRIPT_ADLAM:
@ -376,10 +378,15 @@ hb_ot_shape_complex_categorize (const hb_ot_shape_planner_t *planner)
case HB_SCRIPT_GUNJALA_GONDI:
//case HB_SCRIPT_HANIFI_ROHINGYA:
case HB_SCRIPT_MAKASAR:
case HB_SCRIPT_MEDEFAIDRIN:
case HB_SCRIPT_OLD_SOGDIAN:
//case HB_SCRIPT_SOGDIAN:
/* Unicode-12.0 additions */
case HB_SCRIPT_ELYMAIC:
case HB_SCRIPT_NANDINAGARI:
case HB_SCRIPT_NYIAKENG_PUACHUE_HMONG:
case HB_SCRIPT_WANCHO:
/* Unicode-13.0 additions */
case HB_SCRIPT_CHORASMIAN:

View File

@ -0,0 +1,102 @@
# Override values For Indic_Positional_Category
# Not derivable
# Initial version based on Unicode 7.0 by Andrew Glass 2014-03-17
# Updated for Unicode 10.0 by Andrew Glass 2017-07-25
# Ammended for Unicode 10.0 by Andrew Glass 2018-09-21
# Updated for L2/19-083 by Andrew Glass 2019-05-06
# Updated for Unicode 12.1 by Andrew Glass 2019-05-30
# Updated for Unicode 13.0 by Andrew Glass 2020-07-28
# ================================================
# ================================================
# OVERRIDES TO ASSIGNED VALUES
# ================================================
# ================================================
# Indic_Positional_Category=Bottom
0F72 ; Bottom # Mn TIBETAN VOWEL SIGN I # Not really below, but need to override to fit into Universal model
0F7A..0F7D ; Bottom # Mn [4] TIBETAN VOWEL SIGN E..TIBETAN VOWEL SIGN OO # Not really below, but need to override to fit into Universal model
0F80 ; Bottom # Mn TIBETAN VOWEL SIGN REVERSED I # Not really below, but need to override to fit into Universal model
A9BF ; Bottom # Mc JAVANESE CONSONANT SIGN CAKRA
11127..11129; Bottom # Mn [3] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN II
1112D ; Bottom # Mn CHAKMA VOWEL SIGN AI
11130 ; Bottom # Mn CHAKMA VOWEL SIGN OI
# ================================================
# Indic_Positional_Category=Left
1C29 ; Left # Mc LEPCHA VOWEL SIGN OO # Reduced from Top_And_Left
# ================================================
# Indic_Positional_Category=Right
A9BE ; Right # Mc JAVANESE CONSONANT SIGN PENGKAL # Reduced from Bottom_And_Right
10A0C ; Right # Mn KHAROSHTHI VOWEL LENGTH MARK # Follows vowels and precedes vowel modifiers
11942 ; Right # Mc DIVES AKURU MEDIAL RA # Reduced from Bottom_And_Right
# ================================================
# Indic_Positional_Category=Top
0F74 ; Top # Mn TIBETAN VOWEL SIGN U # Not really above, but need to override to fit into Universal model
1A18 ; Top # Mn BUGINESE VOWEL SIGN U # Workaround to allow below to occur before above by treating all below marks as above
AA35   ; Top # Mn       CHAM CONSONANT SIGN
# ================================================
# Indic_Positional_Category=Top_And_Right
0E33 ; Top_And_Right # Lo THAI CHARACTER SARA AM # IMC has Right, which seems to be a mistake.
0EB3 ; Top_And_Right # Lo LAO VOWEL SIGN AM # IMC has Right, which seems to be a mistake.
# ================================================
# ================================================
# VALUES NOT ASSIGNED IN Indic_Positional_Category
# ================================================
# ================================================
# Indic_Positional_Category=Bottom
0859..085B ; Bottom # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
18A9 ; Bottom # Mn MONGOLIAN LETTER ALI GALI DAGALGA
10AE5 ; Bottom # Mn MANICHAEAN ABBREVIATION MARK ABOVE # Not really bottom, but here for ccc to control
10AE6 ; Bottom # Mn MANICHAEAN ABBREVIATION MARK BELOW
10F46..10F47 ; Bottom # Mn [2] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING TWO DOTS BELOW
10F48..10F4A ; Bottom # Mn [3] SOGDIAN COMBINING DOT ABOVE..SOGDIAN COMBINING CURVE ABOVE # Overriden to below because ccc-based Normalization controls order
10F4B ; Bottom # Mn SOGDIAN COMBINING CURVE BELOW
10F4C ; Bottom # Mn SOGDIAN COMBINING HOOK ABOVE # Overriden to below because ccc-based Normalization controls order
10F4D..10F50 ; Bottom # Mn [4] SOGDIAN COMBINING HOOK BELOW..SOGDIAN COMBINING STROKE BELOW
16F4F ; Bottom # Mn MIAO SIGN CONSONANT MODIFIER BAR
16F51..16F87 ; Bottom # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
16F8F..16F92 ; Bottom # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
# ================================================
# Indic_Positional_Category=Left
103C ; Left # Mc MYANMAR CONSONANT SIGN MEDIAL RA
# ================================================
# Indic_Positional_Category=Top
07EB..07F3 ; Top # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
07FD ; Top # Mn NKO DANTAYALAN # Not really top, but assigned here to allow ccc to control mark order
1885..1886 ; Top # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
10EAB..10EAC ; Top # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
1E944..1E94A ; Top # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
10D24..10D27 ; Top # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
16B30..16B36 ; Top # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
1E130..1E136 ; Top # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
1E2EC..1E2EF ; Top # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
# ================================================
# Indic_Positional_Category=Overstruck
1BC9D..1BC9E ; Overstruck # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK
# ================================================
# ================================================
# Deliberately suppressed
# ================================================
# ================================================
# Indic_Positional_Category=NA
180B..180D ; NA # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
2D7F ; NA # Mn TIFINAGH CONSONANT JOINER

View File

@ -80,7 +80,7 @@
0D91 0DDA ; # SINHALA LETTER EYANNA, SINHALA VOWEL SIGN DIGA KOMBUVA
0D91 0DDC ; # SINHALA LETTER EYANNA, SINHALA VOWEL SIGN KOMBUVA HAA AELA-PILLA
0D91 0DDD ; # SINHALA LETTER EYANNA, SINHALA VOWEL SIGN KOMBUVA HAA DIGA AELA-PILLA
0D91 0DDD ; # SINHALA LETTER EYANNA, SINHALA VOWEL SIGN KOMBUVA HAA DIGA AELA-PILLA
0D91 0DDE ; # SINHALA LETTER EYANNA, SINHALA VOWEL SIGN KOMBUVA HAA GAYANUKITTA
0D94 0DDF ; # SINHALA LETTER OYANNA, SINHALA VOWEL SIGN GAYANUKITTA
11005 11038 ; # BRAHMI LETTER A, BRAHMI VOWEL SIGN AA
1100B 1103E ; # BRAHMI LETTER VOCALIC R, BRAHMI VOWEL SIGN VOCALIC R

View File

@ -0,0 +1,207 @@
# Override values For Indic_Syllabic_Category
# Not derivable
# Initial version based on Unicode 7.0 by Andrew Glass 2014-03-17
# Updated for Unicode 10.0 by Andrew Glass 2017-07-25
# Updated for Unicode 12.1 by Andrew Glass 2019-05-24
# Updated for Unicode 13.0 by Andrew Glass 2020-07-28
# ================================================
# OVERRIDES TO ASSIGNED VALUES
# ================================================
# Indic_Syllabic_Category=Bindu
193A ; Bindu # Mn LIMBU SIGN KEMPHRENG
AA29 ; Bindu # Mn  CHAM VOWEL SIGN AA
10A0D ; Bindu # Mn KHAROSHTHI SIGN DOUBLE RING BELOW
1172B ; Bindu # Mn AHOM SIGN KILLER
# ================================================
# Indic_Syllabic_Category=Consonant
0840..0858 ; Consonant # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
0F00..0F01 ; Consonant # Lo [2] TIBETAN SYLLABLE OM..TIBETAN MARK GTER YIG MGO TRUNCATED
0F04..0F06 ; Consonant # Po TIBETAN MARK INITIAL YIG MGO MDUN MA..TIBETAN MARK CARET YIG MGO PHUR SHAD MA
19C1..19C7 ; Consonant # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B # Reassigned to avoid clustering with a base consonant
25CC ; Consonant # So DOTTED CIRCLE
# ================================================
# Indic_Syllabic_Category=Consonant_Dead
0F7F ; Consonant_Dead # Mc TIBETAN SIGN RNAM BCAD # reassigned so that visarga will form an independent cluster
# ================================================
# Indic_Syllabic_Category=Consonant_Final
0F35 ; Consonant_Final # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
0F37 ; Consonant_Final # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS
0FC6 ; Consonant_Final # Mn TIBETAN SYMBOL PADMA GDAN
# ================================================
# Indic_Syllabic_Category=Consonant_Final_Modifier
1C36 ; Consonant_Final_Modifier # Mn LEPCHA SIGN RAN
# ================================================
# Indic_Syllabic_Category=Gemination_Mark
11134 ; Gemination_Mark # Mc CHAKMA MAAYYAA
# ================================================
# Indic_Syllabic_Category=Nukta
0F71 ; Nukta # Mn TIBETAN VOWEL SIGN AA # Reassigned to get this before an above vowel
10A38..10A3A ; Nukta # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
# ================================================
# Indic_Syllabic_Category=Tone_Mark
A982 ; Tone_Mark # Mn JAVANESE SIGN LAYAR# Not a repha, because it does not reorder to front of cluster
1A7B..1A7C ; Tone_Mark # Mn [2] TAI THAM SIGN MAI SAM..TAI THAM SIGN KHUEN-LUE KARAN
1A7F ; Tone_Mark # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT
# ================================================
# Indic_Syllabic_Category=Vowel_Independent
AAB1 ; Vowel_Independent # Lo TAI VIET VOWEL AA
AABA ; Vowel_Independent # Lo TAI VIET VOWEL UA
AABD ; Vowel_Independent # Lo TAI VIET VOWEL AN
# ================================================
# ================================================
# VALUES NOT ASSIGNED IN Indic_Syllabic_Category
# ================================================
# ================================================
# Indic_Syllabic_Category=Consonant
0800..0815 ; Consonant # Lo [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF
1800 ; Consonant # Po MONGOLIAN BIRGA # Reassigned so that legacy Birga + MFVS sequences still work
1807 ; Consonant # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER
180A ; Consonant # Po MONGOLIAN NIRUGU
1820..1878 ; Consonant # Lo [88] MONGOLIAN LETTER A..MONGOLIAN LETTER CHA WITH TWO DOTS
1843 ; Consonant # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN
2D30..2D67 ; Consonant # Lo [56] TIFINAGH LETTER YA..TIFINAGH LETTER YO
2D6F ; Consonant # Lm TIFINAGH MODIFIER LETTER LABIALIZATION MARK
10AC0..10AC7 ; Consonant # Lo [8] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER WAW
10AC9..10AE4 ; Consonant # Lo [28] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER TAW
10D00..10D23 ; Consonant # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA
10E80..10EA9 ; Consonant # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET
10EB0..10EB1 ; Consonant # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
10F30..10F45 ; Consonant # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN
111DA ; Consonant # Lo SHARADA EKAM
#HIEROGLYPHS moved to new category
#13000..1342E ; Consonant # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
#For the Begin and End segment to be handled fully correctly, the cluster model needs to be modified.
#13437..13438 ; Consonant # Lo [2] EGYPTIAN HIEROGLYPH BEGIN SEGMENT..EGYPTIAN HIEROGLYPH END SEGMENT
16B00..16B2F ; Consonant # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU
16F00..16F4A ; Consonant # Lo [75] MIAO LETTER PA..MIAO LETTER RTE
16FE4 ; Consonant # Mn KHITAN SMALL SCRIPT FILLER
18B00..18CD5 ; Consonant # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5
1BC00..1BC99 ; Consonant # Lo [139] DUPLOYAN LETTER H..DUPLOYAN AFFIX LOW ARROW
1E100..1E12C ; Consonant # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
1E137..1E13D ; Consonant # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
1E14E ; Consonant # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
1E14F ; Consonant # So NYIAKENG PUACHUE HMONG CIRCLED CA
1E2C0..1E2EB ; Consonant # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH
1E900..1E921 ; Consonant # Lu [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA
1E922..1E943 ; Consonant # Ll [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA
1E94B ; Consonant # Lm ADLAM NASALIZATION MARK
# ================================================
# Indic_Syllabic_Category=Consonant_Placeholder
1880..1884 ; Consonant_Placeholder # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA
# ================================================
# Indic_Syllabic_Category=Gemination_Mark
10D27 ; Gemination_Mark # Mn HANIFI ROHINGYA SIGN TASSI
# ================================================
# Indic_Syllabic_Category=Modifying_Letter
FE00..FE0F ; Modifying_Letter # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16# Need to treat them as isolated bases so they don't merge with a cluster in invalid scenarios
16F50 ; Modifying_Letter # Lo MIAO LETTER NASALIZATION
# ================================================
# Indic_Syllabic_Category=Nukta
0859..085B ; Nukta # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK
0F39 ; Nukta # Mn TIBETAN MARK TSA -PHRU # NOW IN UNICODE 10.0
1885..1886 ; Nukta # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA
18A9 ; Nukta # Mn MONGOLIAN LETTER ALI GALI DAGALGA
1B6B..1B73 ; Nukta # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG
10AE5..10AE6 ; Nukta # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
16F4F ; Nukta # Mn MIAO SIGN CONSONANT MODIFIER BAR
1BC9D..1BC9E ; Nukta # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK
1E944..1E94A ; Nukta # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
# ================================================
# Indic_Syllabic_Category=Number
10D30..10D39 ; Number # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE
10F51..10F54 ; Number # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED
1E140..1E149 ; Number # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE
1E2F0..1E2F9 ; Number # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE
1E950..1E959 ; Number # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
# ================================================
# Indic_Syllabic_Category=Tone_Mark
07EB..07F3 ; Tone_Mark # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
07FD ; Tone_Mark # Mn NKO DANTAYALAN
0F86..0F87 ; Tone_Mark # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS
17CF ; Tone_Mark # Mn KHMER SIGN AHSDA
10D24..10D26 ; Tone_Mark # Mn [3] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TANA
10F46..10F50 ; Tone_Mark # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
16B30..16B36 ; Tone_Mark # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
16F8F..16F92 ; Tone_Mark # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW
1E130..1E136 ; Tone_Mark # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
1E2EC..1E2EF ; Tone_Mark # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI
# ================================================
# Indic_Syllabic_Category=Virama
2D7F ; Virama # Mn TIFINAGH CONSONANT JOINER
13430..13436 ; Virama # Cf [7] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH OVERLAY MIDDLE
# ================================================
# Indic_Syllabic_Category=Vowel_Independent
AAB1 ; Vowel_Independent # Lo TAI VIET VOWEL AA
AABA ; Vowel_Independent # Lo TAI VIET VOWEL UA
AABD ; Vowel_Independent # Lo TAI VIET VOWEL AN
# ================================================
# Indic_Syllabic_Category=Vowel_Dependent
0B55 ; Vowel_Dependent # Mn ORIYA SIGN OVERLINE
10EAB..10EAC ; Vowel_Dependent # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
16F51..16F87 ; Vowel_Dependent # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
# ================================================
# ================================================
# PROPERTIES NOT ASSIGNED IN Indic_Syllabic_Category
# ================================================
# ================================================
# USE_Syllabic_Category=Hieroglyph
# 13000..1342E ; Hieroglyph # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
# ================================================
# USE_Syllabic_Category=Hieroglyph_Joiner
# 13430..13436 ; Hieroglyph_Joiner # Cf EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH OVERLAY MIDDLE
# ================================================
# USE_Syllabic_Category= Hieroglyph_Segment_Begin
# 13437 ; Hieroglyph_Segment_Begin # Cf EGYPTIAN HIEROGLYPH BEGIN SEGMENT
# ================================================
# USE_Syllabic_Category= Hieroglyph_Segment_End
# 13438 ; Hieroglyph_Segment_End # Cf EGYPTIAN HIEROGLYPH END SEGMENT
# ================================================
# eof

View File

@ -21,7 +21,7 @@ hb-ot-tag-table.hh: gen-tag-table.py languagetags language-subtag-registry
./$^ > $@ || ($(RM) $@; false)
hb-ucd-table.hh: gen-ucd-table.py ucd.nounihan.grouped.zip hb-common.h
./$^ > $@ || ($(RM) $@; false)
hb-ot-shape-complex-use-table.cc: gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt Blocks.txt
hb-ot-shape-complex-use-table.cc: gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt ArabicShaping.txt Blocks.txt ms-use/IndicSyllabicCategory-Additional.txt ms-use/IndicPositionalCategory-Additional.txt
./$^ > $@ || ($(RM) $@; false)
hb-ot-shape-complex-vowel-constraints.cc: gen-vowel-constraints.py ms-use/IndicShapingInvalidCluster.txt Scripts.txt
./$^ > $@ || ($(RM) $@; false)