disarm 0.10.0

# === Latin-1 Supplement (U+0080–U+00FF) ===
# Source: Unicode NFKD decomposition + conventional ASCII equivalents
# ~69% match NFKD; symbols/ligatures use common conventions (AE, Th, ss, GBP, JPY)

00A2	c
00A3	GBP
00A5	JPY
00A9	(c)
00AB	<<

# === Soft Hyphen (U+00AD) ===
# Source: Strip invisible formatting character

00AD	
00AE	(R)
00B0	deg
00B1	+-
00B2	2
00B3	3
00B5	u
00B7	.
00B9	1
00BB	>>
00BC	1/4
00BD	1/2
00BE	3/4
00C0	A
00C1	A
00C2	A
00C3	A
00C4	A
00C5	A
00C6	AE
00C7	C
00C8	E
00C9	E
00CA	E
00CB	E
00CC	I
00CD	I
00CE	I
00CF	I
00D0	D
00D1	N
00D2	O
00D3	O
00D4	O
00D5	O
00D6	O
00D7	x
00D8	O
00D9	U
00DA	U
00DB	U
00DC	U
00DD	Y
00DE	Th
00DF	ss
00E0	a
00E1	a
00E2	a
00E3	a
00E4	a
00E5	a
00E6	ae
00E7	c
00E8	e
00E9	e
00EA	e
00EB	e
00EC	i
00ED	i
00EE	i
00EF	i
00F0	d
00F1	n
00F2	o
00F3	o
00F4	o
00F5	o
00F6	o
00F7	/
00F8	o
00F9	u
00FA	u
00FB	u
00FC	u
00FD	y
00FE	th
00FF	y

# === Latin Extended-A (U+0100–U+017F) ===
# Source: Unicode NFKD decomposition + conventional fallbacks

0100	A
0101	a
0102	A
0103	a
0104	A
0105	a
0106	C
0107	c
0108	C
0109	c
010A	C
010B	c
010C	C
010D	c
010E	D
010F	d
0110	D
0111	d
0112	E
0113	e
0114	E
0115	e
0116	E
0117	e
0118	E
0119	e
011A	E
011B	e
011C	G
011D	g
011E	G
011F	g
0120	G
0121	g
0122	G
0123	g
0124	H
0125	h
0126	H
0127	h
0128	I
0129	i
012A	I
012B	i
012C	I
012D	i
012E	I
012F	i
0130	I
0131	i
0132	IJ
0133	ij
0134	J
0135	j
0136	K
0137	k
0138	k
0139	L
013A	l
013B	L
013C	l
013D	L
013E	l
013F	L
0140	l
0141	L
0142	l
0143	N
0144	n
0145	N
0146	n
0147	N
0148	n
0149	n
014A	N
014B	n
014C	O
014D	o
014E	O
014F	o
0150	O
0151	o
0152	OE
0153	oe
0154	R
0155	r
0156	R
0157	r
0158	R
0159	r
015A	S
015B	s
015C	S
015D	s
015E	S
015F	s
0160	S
0161	s
0162	T
0163	t
0164	T
0165	t
0166	T
0167	t
0168	U
0169	u
016A	U
016B	u
016C	U
016D	u
016E	U
016F	u
0170	U
0171	u
0172	U
0173	u
0174	W
0175	w
0176	Y
0177	y
0178	Y
0179	Z
017A	z
017B	Z
017C	z
017D	Z
017E	z
017F	s

# === Latin Extended-B (U+0180–U+024F) ===
# Source: NFKD decomposition where available; phonetic approximation for
# stroked/hooked/African letters (Ŋ→N, Ə→A, Ʃ→Sh)

0180	b
0181	B
0182	B
0183	b
0184	B
0185	b
0186	O
0187	C
0188	c
0189	D
018A	D
018B	D
018C	d
018D	d
018E	D
018F	A
0190	E
0191	F
0192	f
0193	G
0194	G
0195	hv
0196	I
0197	I
0198	K
0199	k
019A	l
019B	l
019C	M
019D	N
019E	n
019F	O
01A0	O
01A1	o
01A2	OI
01A3	oi
01A4	P
01A5	p
01A6	R
01A7	S
01A8	s
01A9	Sh
01AA	s
01AB	t
01AC	T
01AD	t
01AE	T
01AF	U
01B0	u
01B1	U
01B2	V
01B3	Y
01B4	y
01B5	Z
01B6	z
01B7	Zh
01B8	Zh
01B9	zh
01BA	zh
01BB	2
01BC	5
01BD	5
01BE	ts
01BF	w
01C0	|
01C1	||
01C2	!
01C3	!
01C4	DZ
01C5	Dz
01C6	dz
01C7	LJ
01C8	Lj
01C9	lj
01CA	NJ
01CB	Nj
01CC	nj
01CD	A
01CE	a
01CF	I
01D0	i
01D1	O
01D2	o
01D3	U
01D4	u
01D5	U
01D6	u
01D7	U
01D8	u
01D9	U
01DA	u
01DB	U
01DC	u
01DD	e
01DE	A
01DF	a
01E0	A
01E1	a
01E2	AE
01E3	ae
01E4	G
01E5	g
01E6	G
01E7	g
01E8	K
01E9	k
01EA	O
01EB	o
01EC	O
01ED	o
01EE	Zh
01EF	zh
01F0	j
01F1	DZ
01F2	Dz
01F3	dz
01F4	G
01F5	g
01F6	Hv
01F7	W
01F8	N
01F9	n
01FA	A
01FB	a
01FC	AE
01FD	ae
01FE	O
01FF	o
0200	A
0201	a
0202	A
0203	a
0204	E
0205	e
0206	E
0207	e
0208	I
0209	i
020A	I
020B	i
020C	O
020D	o
020E	O
020F	o
0210	R
0211	r
0212	R
0213	r
0214	U
0215	u
0216	U
0217	u
0218	S
0219	s
021A	T
021B	t
021C	Yh
021D	yh
021E	H
021F	h
0220	N
0221	d
0222	OU
0223	ou
0224	Z
0225	z
0226	A
0227	a
0228	E
0229	e
022A	O
022B	o
022C	O
022D	o
022E	O
022F	o
0230	O
0231	o
0232	Y
0233	y
0234	l
0235	n
0236	t
0237	j
0238	db
0239	qp
023A	A
023B	C
023C	c
023D	L
023E	T
023F	s
0240	z
0241	'
0242	'
0243	B
0244	U
0245	V
0246	E
0247	e
0248	J
0249	j
024A	Q
024B	q
024C	R
024D	r
024E	Y
024F	y

# === IPA Extensions (U+0250–U+02AF) ===
# Source: Phonetic approximation (nearest readable ASCII)
# Digraphs preferred: ʃ→sh, ʒ→zh, ɸ→ph, ʔ→'

0250	a
0251	a
0252	a
0253	b
0254	o
0255	c
0256	d
0257	d
0258	e
0259	e
025A	e
025B	e
025C	e
025D	e
025E	e
025F	j
0260	g
0261	g
0262	G
0263	g
0264	o
0265	h
0266	h
0267	h
0268	i
0269	i
026A	I
026B	l
026C	l
026D	l
026E	lz
026F	m
0270	m
0271	m
0272	n
0273	n
0274	N
0275	o
0276	OE
0277	o
0278	ph
0279	r
027A	r
027B	r
027C	r
027D	r
027E	r
027F	r
0280	R
0281	R
0282	s
0283	sh
0284	j
0285	s
0286	sh
0287	t
0288	t
0289	u
028A	u
028B	v
028C	v
028D	w
028E	y
028F	Y
0290	z
0291	z
0292	zh
0293	zh
0294	'
0295	'
0296	'
0297	!
0298	!
0299	B
029A	e
029B	G
029C	H
029D	j
029E	k
029F	L
02A0	q
02A1	'
02A2	'
02A3	dz
02A4	dz
02A5	dz
02A6	ts
02A7	tsh
02A8	tc
02A9	fn
02AA	ls
02AB	lz
02AC	w
02AD	!
02AE	h
02AF	h

# === Spacing Modifier Letters (U+02B0–U+02FF) ===
# Source: Base letter equivalents

02B0	h
02B1	h
02B2	j
02B3	r
02B4	r
02B5	r
02B6	r
02B7	w
02B8	y
02B9	'
02BA	"
02BB	'
02BC	'
02BD	'
02BE	'
02BF	'
02C0	'
02C1	'
02C2	<
02C3	>
02C4	^
02C5	v
02C6	^
02C7	v
02C8	'
02C9	-
02CA	'
02CB	`
02CC	,
02CD	_
02CE	`
02CF	'
02D0	:
02D1	:
02D2	>
02D3	<
02D4	^
02D5	v
02D6	+
02D7	-
02D8	~
02D9	.
02DA	o
02DB	,
02DC	~
02DD	"
02DE	r
02DF	x
02E0	g
02E1	l
02E2	s
02E3	x
02E4	'
02E5	|
02E6	|
02E7	|
02E8	|
02E9	|
02EA	|
02EB	|
02EC	v
02ED	=
02EE	"
02EF	v
02F0	v
02F1	v
02F2	v
02F3	o
02F4	'
02F5	"
02F6	"
02F7	~
02F8	:
02F9	!
02FA	|
02FB	|
02FC	v
02FD	=
02FE	v
02FF	'

# === Greek and Coptic (U+0370–U+03FF) ===
# Source: BGN/PCGN Greek romanization (1962, amended 1996), modern pronunciation
# Deviation: χ→Ch (BGN/PCGN uses Kh; Ch matches ISO 843)
# Coptic range (U+03E2–U+03EF) follows Coptic scholarly convention


# === Combining Diacritical Marks (U+0300–U+036F) ===
# Source: Strip to empty — combining marks are accent modifiers that
# should be silently removed during transliteration, not replaced with [?].
# The precomposed equivalents (é, ñ, etc.) are handled in the Latin blocks.

0300	
0301	
0302	
0303	
0304	
0305	
0306	
0307	
0308	
0309	
030A	
030B	
030C	
030D	
030E	
030F	
0310	
0311	
0312	
0313	
0314	
0315	
0316	
0317	
0318	
0319	
031A	
031B	
031C	
031D	
031E	
031F	
0320	
0321	
0322	
0323	
0324	
0325	
0326	
0327	
0328	
0329	
032A	
032B	
032C	
032D	
032E	
032F	
0330	
0331	
0332	
0333	
0334	
0335	
0336	
0337	
0338	
0339	
033A	
033B	
033C	
033D	
033E	
033F	
0340	
0341	
0342	
0343	
0344	
0345	
0346	
0347	
0348	
0349	
034A	
034B	
034C	
034D	
034E	
034F	
0350	
0351	
0352	
0353	
0354	
0355	
0356	
0357	
0358	
0359	
035A	
035B	
035C	
035D	
035E	
035F	
0360	
0361	
0362	
0363	
0364	
0365	
0366	
0367	
0368	
0369	
036A	
036B	
036C	
036D	
036E	
036F	
0370	H
0371	h
0372	Ss
0373	ss
0374	'
0375	,
0376	W
0377	w
037A	i
037B	s
037C	s
037D	s
037E	;
037F	J
0384	'
0385	"
0386	A
0387	.
0388	E
0389	I
038A	I
038C	O
038E	Y
038F	O
0390	i
0391	A
0392	B
0393	G
0394	D
0395	E
0396	Z
0397	I
0398	Th
0399	I
039A	K
039B	L
039C	M
039D	N
039E	X
039F	O
03A0	P
03A1	R
03A3	S
03A4	T
03A5	Y
03A6	F
03A7	Ch
03A8	Ps
03A9	O
03AA	I
03AB	Y
03AC	a
03AD	e
03AE	i
03AF	i
03B0	y
03B1	a
03B2	b
03B3	g
03B4	d
03B5	e
03B6	z
03B7	i
03B8	th
03B9	i
03BA	k
03BB	l
03BC	m
03BD	n
03BE	x
03BF	o
03C0	p
03C1	r
03C2	s
03C3	s
03C4	t
03C5	y
03C6	f
03C7	ch
03C8	ps
03C9	o
03CA	i
03CB	y
03CC	o
03CD	y
03CE	o
03CF	K
03D0	b
03D1	th
03D2	Y
03D3	Y
03D4	Y
03D5	ph
03D6	p
03D7	k
03D8	Q
03D9	q
03DA	St
03DB	st
03DC	W
03DD	w
03DE	Q
03DF	q
03E0	Ss
03E1	ss
03E2	sh
03E3	sh
03E4	f
03E5	f
03E6	kh
03E7	kh
03E8	h
03E9	h
03EA	j
03EB	j
03EC	c
03ED	c
03EE	ti
03EF	ti
03F0	k
03F1	r
03F2	s
03F3	j
03F4	Th
03F5	e
03F6	e
03F7	Sh
03F8	sh
03F9	S
03FA	S
03FB	s
03FC	r
03FD	S
03FE	S
03FF	S

# === Cyrillic (U+0400–U+04FF) ===
# Source: BGN/PCGN Russian romanization (1947, revised 1994)
# Confirmed: Ж→Zh, Х→Kh, Щ→Shch, Ц→Ts, Ю→Yu, Я→Ya
# Hard/soft signs → empty string (BGN/PCGN convention)

0400	E
0401	Yo
0402	Dj
0403	G
0404	Ye
0405	Dz
0406	I
0407	Yi
0408	J
0409	Lj
040A	Nj
040B	Tsh
040C	K
040D	I
040E	U
040F	Dzh
0410	A
0411	B
0412	V
0413	G
0414	D
0415	E
0416	Zh
0417	Z
0418	I
0419	Y
041A	K
041B	L
041C	M
041D	N
041E	O
041F	P
0420	R
0421	S
0422	T
0423	U
0424	F
0425	Kh
0426	Ts
0427	Ch
0428	Sh
0429	Shch
042A	
042B	Y
042C	
042D	E
042E	Yu
042F	Ya
0430	a
0431	b
0432	v
0433	g
0434	d
0435	e
0436	zh
0437	z
0438	i
0439	y
043A	k
043B	l
043C	m
043D	n
043E	o
043F	p
0440	r
0441	s
0442	t
0443	u
0444	f
0445	kh
0446	ts
0447	ch
0448	sh
0449	shch
044A	
044B	y
044C	
044D	e
044E	yu
044F	ya
0450	e
0451	yo
0452	dj
0453	g
0454	ye
0455	dz
0456	i
0457	yi
0458	j
0459	lj
045A	nj
045B	tsh
045C	k
045D	i
045E	u
045F	dzh
0460	O
0461	o
0462	Ye
0463	ye
0464	Ie
0465	ie
0466	E
0467	e
0468	Ie
0469	ie
046A	O
046B	o
046C	Io
046D	io
046E	Ks
046F	ks
0470	Ps
0471	ps
0472	F
0473	f
0474	Y
0475	y
0476	Y
0477	y
0478	U
0479	u
047A	O
047B	o
047C	O
047D	o
047E	Ot
047F	ot
0480	K
0481	k
048A	Y
048B	y
048C	
048D	
048E	R
048F	r
0490	G
0491	g
0492	G
0493	g
0494	G
0495	g
0496	Zh
0497	zh
0498	Z
0499	z
049A	K
049B	k
049C	K
049D	k
049E	K
049F	k
04A0	K
04A1	k
04A2	N
04A3	n
04A4	Ng
04A5	ng
04A6	P
04A7	p
04A8	Kh
04A9	kh
04AA	S
04AB	s
04AC	T
04AD	t
04AE	U
04AF	u
04B0	U
04B1	u
04B2	Kh
04B3	kh
04B4	Ts
04B5	ts
04B6	Ch
04B7	ch
04B8	Ch
04B9	ch
04BA	H
04BB	h
04BC	Ch
04BD	ch
04BE	Ch
04BF	ch
04C0	I
04C1	Zh
04C2	zh
04C3	K
04C4	k
04C5	L
04C6	l
04C7	N
04C8	n
04C9	N
04CA	n
04CB	Ch
04CC	ch
04CD	M
04CE	m
04CF	i
04D0	A
04D1	a
04D2	A
04D3	a
04D4	AE
04D5	ae
04D6	E
04D7	e
04D8	A
04D9	a
04DA	A
04DB	a
04DC	Zh
04DD	zh
04DE	Z
04DF	z
04E0	Dz
04E1	dz
04E2	I
04E3	i
04E4	I
04E5	i
04E6	O
04E7	o
04E8	O
04E9	o
04EA	O
04EB	o
04EC	E
04ED	e
04EE	U
04EF	u
04F0	U
04F1	u
04F2	U
04F3	u
04F4	Ch
04F5	ch
04F6	G
04F7	g
04F8	Y
04F9	y
04FA	G
04FB	g
04FC	Kh
04FD	kh
04FE	Kh
04FF	kh

# === Cyrillic Supplement (U+0500–U+052F) ===
# Source: BGN/PCGN conventions (extended for non-Russian Cyrillic)

0500	D
0501	d
0502	Dj
0503	dj
0504	Z
0505	z
0506	Dz
0507	dz
0508	Lj
0509	lj
050A	Nj
050B	nj
050C	Sj
050D	sj
050E	Tj
050F	tj
0510	Z
0511	z
0512	L
0513	l
0514	L
0515	l
0516	R
0517	r
0518	Ye
0519	ye
051A	Q
051B	q
051C	W
051D	w
051E	K
051F	k
0520	N
0521	n
0522	P
0523	p
0524	H
0525	h
0526	H
0527	h
0528	N
0529	n
052A	Dz
052B	dz
052C	Tch
052D	tch
052E	Kh
052F	kh

# === Armenian (U+0530–U+058F) ===
# Source: BGN/PCGN Armenian romanization (1981)
# Deviation: Aspirate apostrophes stripped for ASCII (Ch'→Ch, Ts'→Ts, P'→P, K'→K)

0531	A
0532	B
0533	G
0534	D
0535	E
0536	Z
0537	E
0538	Y
0539	T
053A	Zh
053B	I
053C	L
053D	Kh
053E	Ts
053F	K
0540	H
0541	Dz
0542	Gh
0543	Ch
0544	M
0545	Y
0546	N
0547	Sh
0548	Vo
0549	Ch
054A	P
054B	J
054C	R
054D	S
054E	V
054F	T
0550	R
0551	Ts
0552	V
0553	P
0554	K
0555	O
0556	F
0559	'
055A	'
055B	
055C	!
055D	,
055E	?
055F	
0560	a
0561	a
0562	b
0563	g
0564	d
0565	e
0566	z
0567	e
0568	y
0569	t
056A	zh
056B	i
056C	l
056D	kh
056E	ts
056F	k
0570	h
0571	dz
0572	gh
0573	ch
0574	m
0575	y
0576	n
0577	sh
0578	vo
0579	ch
057A	p
057B	j
057C	r
057D	s
057E	v
057F	t
0580	r
0581	ts
0582	v
0583	p
0584	k
0585	o
0586	f
0587	yev
0588	yi
0589	.
058A	-
058D	
058E	
058F	AMD

# === Hebrew (U+0590–U+05FF) ===
# Source: BGN/PCGN Hebrew romanization (1962/2018)
# Deviation: ח(het)→ch instead of BGN/PCGN kh (Ashkenazi/popular convention)

0591	
0592	
0593	
0594	
0595	
0596	
0597	
0598	
0599	
059A	
059B	
059C	
059D	
059E	
059F	
05A0	
05A1	
05A2	
05A3	
05A4	
05A5	
05A6	
05A7	
05A8	
05A9	
05AA	
05AB	
05AC	
05AD	
05AE	
05AF	
05B0	e
05B1	e
05B2	a
05B3	o
05B4	i
05B5	e
05B6	e
05B7	a
05B8	a
05B9	o
05BA	o
05BB	u
05BC	
05BD	
05BE	-
05BF	
05C0	
05C1	
05C2	
05C3	.
05C4	
05C5	
05C6	
05C7	o
05D0	'
05D1	v
05D2	g
05D3	d
05D4	h
05D5	v
05D6	z
05D7	ch
05D8	t
05D9	y
05DA	kh
05DB	kh
05DC	l
05DD	m
05DE	m
05DF	n
05E0	n
05E1	s
05E2	
05E3	f
05E4	f
05E5	ts
05E6	ts
05E7	q
05E8	r
05E9	sh
05EA	t
05F0	v
05F1	vy
05F2	y
05F3	'
05F4	"

# === Arabic (U+0600–U+06FF) ===
# Source: BGN/PCGN Arabic romanization (1956)
# Confirmed by digraphs: ث→th, خ→kh, ذ→dh, ش→sh, غ→gh
# Emphatic consonants lose underdot diacritics (ASCII constraint)

0606	
0607	
0608	
0609	%o
060A	%oo
060B	Af
060C	,
060D	/
060E	
060F	
0610	
0611	
0612	
0613	
0614	
0615	
0616	aly
0617	
0618	a
0619	u
061A	i
061B	;

# === Arabic Letter Mark (U+061C) ===
# Source: Strip invisible formatting character

061C	
061D	.
061E	...
061F	?
0620	y
0621	'
0622	a
0623	a
0624	'
0625	a
0626	'
0627	a
0628	b
0629	h
062A	t
062B	th
062C	j
062D	h
062E	kh
062F	d
0630	dh
0631	r
0632	z
0633	s
0634	sh
0635	s
0636	d
0637	t
0638	z
0639	'
063A	gh
063B	k
063C	k
063D	y
063E	y
063F	y
0640	
0641	f
0642	q
0643	k
0644	l
0645	m
0646	n
0647	h
0648	w
0649	a
064A	y
064B	an
064C	un
064D	in
064E	a
064F	u
0650	i
0651	
0652	
0653	
0654	'
0655	'
0656	a
0657	u
0658	n
0659	
065A	
065B	
065C	
065D	u
065E	a
065F	'
0660	0
0661	1
0662	2
0663	3
0664	4
0665	5
0666	6
0667	7
0668	8
0669	9
066A	%
066B	.
066C	,
066D	*
066E	b
066F	q
0670	a
0671	a
0672	a
0673	a
0674	'
0675	a
0676	w
0677	u'
0678	y
0679	t
067A	t
067B	b
067C	t
067D	t
067E	p
067F	t
0680	b
0681	h
0682	h
0683	ny
0684	dy
0685	h
0686	ch
0687	ch
0688	d
0689	d
068A	d
068B	d
068C	d
068D	d
068E	d
068F	d
0690	d
0691	r
0692	r
0693	r
0694	r
0695	r
0696	r
0697	r
0698	zh
0699	r
069A	s
069B	s
069C	s
069D	s
069E	s
069F	t
06A0	'
06A1	f
06A2	f
06A3	f
06A4	v
06A5	f
06A6	p
06A7	q
06A8	q
06A9	k
06AA	k
06AB	k
06AC	k
06AD	ng
06AE	k
06AF	g
06B0	g
06B1	ng
06B2	g
06B3	g
06B4	g
06B5	l
06B6	l
06B7	l
06B8	l
06B9	n
06BA	n
06BB	n
06BC	n
06BD	n
06BE	h
06BF	ch
06C0	h
06C1	h
06C2	h
06C3	h
06C4	w
06C5	o
06C6	o
06C7	u
06C8	yu
06C9	yu
06CA	w
06CB	v
06CC	y
06CD	y
06CE	y
06CF	w
06D0	e
06D1	y
06D2	y
06D3	y
06D4	.
06D5	a
06D6	la
06D7	la
06D8	
06D9	
06DA	
06DB	
06DC	
06DE	
06DF	
06E0	
06E1	
06E2	
06E3	
06E4	
06E5	w
06E6	y
06E7	
06E8	
06E9	
06EA	
06EB	
06EC	
06ED	
06EE	d
06EF	r
06F0	0
06F1	1
06F2	2
06F3	3
06F4	4
06F5	5
06F6	6
06F7	7
06F8	8
06F9	9
06FA	sh
06FB	d
06FC	gh
06FD	&
06FE	
06FF	h

# === Syriac (U+0700–U+074F) ===
# Source: Phonetic approximation following Arabic-like conventions

0700	.
0701	.
0702	,
0703	:
0704	:
0705	,
0706	,
0707	-
0708	+
0709	.
070A	:
070B	-
070C	.
070D	*
070F	
0710	a
0711	
0712	b
0713	g
0714	g
0715	d
0716	h
0717	w
0718	z
0719	h
071A	t
071B	t
071C	y
071D	y
071E	k
071F	k
0720	l
0721	m
0722	n
0723	s
0724	s
0725	'
0726	p
0727	p
0728	s
0729	q
072A	r
072B	sh
072C	t
072D	sh
072E	r
072F	zh
0730	a
0731	a
0732	a
0733	a
0734	a
0735	e
0736	e
0737	e
0738	e
0739	i
073A	i
073B	u
073C	u
073D	o
073E	o
073F	o
0740	ch
0741	zh
0742	g
0743	j
0744	p
0745	ch
0746	zh
0747	g
0748	j
0749	p
074A	
074D	zh
074E	k
074F	hn

# === Thaana (U+0780–U+07BF) ===
# Source: Phonetic approximation for Maldivian Thaana

0780	h
0781	sh
0782	n
0783	r
0784	b
0785	lh
0786	k
0787	'
0788	v
0789	m
078A	f
078B	dh
078C	th
078D	l
078E	g
078F	gn
0790	s
0791	d
0792	z
0793	t
0794	y
0795	p
0796	j
0797	ch
0798	tt
0799	hh
079A	kh
079B	th
079C	z
079D	sh
079E	s
079F	d
07A0	t
07A1	z
07A2	'
07A3	gh
07A4	q
07A5	w
07A6	a
07A7	aa
07A8	i
07A9	ee
07AA	u
07AB	oo
07AC	e
07AD	ey
07AE	o
07AF	oa
07B0	

# === NKo (U+07C0–U+07FF) ===
# Source: Phonetic values of N'Ko script

07C0	0
07C1	1
07C2	2
07C3	3
07C4	4
07C5	5
07C6	6
07C7	7
07C8	8
07C9	9
07CA	a
07CB	ee
07CC	i
07CD	e
07CE	u
07CF	oo
07D0	o
07D1	da
07D2	ba
07D3	ka
07D4	ja
07D5	cha
07D6	ta
07D7	nya
07D8	na
07D9	ra
07DA	rra
07DB	sa
07DC	gba
07DD	fa
07DE	ga
07DF	ha
07E0	wa
07E1	la
07E2	ya
07E3	pa
07E4	nta
07E5	ma
07E6	nya
07E7	na
07E8	nga
07E9	nka
07EA	ya2
07EB	
07EC	
07ED	
07EE	
07EF	
07F0	
07F1	
07F2	
07F3	
07F4	'
07F5	'
07F6	o
07F7	.
07F8	,
07F9	!
07FA	la

# === Devanagari (U+0900–U+097F) ===
# Source: UNGEGN/Hunterian romanization
# Diagnostic: cha/chha for palatal stops (not IAST ca/cha)
# Retroflex/dental merge to ta/tha/da/dha/na (ASCII constraint)

0900	
0901	m
0902	m
0903	h
0904	a
0905	a
0906	aa
0907	i
0908	i
0909	u
090A	u
090B	r
090C	l
090D	e
090E	e
090F	e
0910	ai
0911	o
0912	o
0913	o
0914	au
0915	ka
0916	kha
0917	ga
0918	gha
0919	nga
091A	cha
091B	chha
091C	ja
091D	jha
091E	nya
091F	ta
0920	tha
0921	da
0922	dha
0923	na
0924	ta
0925	tha
0926	da
0927	dha
0928	na
0929	na
092A	pa
092B	pha
092C	ba
092D	bha
092E	ma
092F	ya
0930	ra
0931	ra
0932	la
0933	la
0934	la
0935	va
0936	sha
0937	sha
0938	sa
0939	ha
093A	
093B	
093C	
093D	'
093E	a
093F	i
0940	i
0941	u
0942	u
0943	r
0944	r
0945	e
0946	e
0947	e
0948	ai
0949	o
094A	o
094B	o
094C	au
094D	
094E	
094F	
0950	om
0951	
0952	
0953	
0954	
0955	e
0956	u
0957	u
0958	qa
0959	kha
095A	ga
095B	za
095C	da
095D	dha
095E	fa
095F	ya
0960	r
0961	l
0962	l
0963	l
0964	.
0965	.
0966	0
0967	1
0968	2
0969	3
096A	4
096B	5
096C	6
096D	7
096E	8
096F	9
0970	.
0971	.
0972	a
0973	oe
0974	ooe
0975	aw
0976	ue
0977	uue
0978	dda
0979	zha
097A	ya
097B	gga
097C	jja
097D	'
097E	ddda
097F	bba

# === Bengali (U+0980–U+09FF) ===
# Source: UNGEGN/Hunterian romanization (mirrors Devanagari pattern)

0980	m
0981	m
0982	m
0983	h
0985	a
0986	aa
0987	i
0988	i
0989	u
098A	u
098B	r
098C	l
098F	e
0990	ai
0993	o
0994	au
0995	ka
0996	kha
0997	ga
0998	gha
0999	nga
099A	cha
099B	chha
099C	ja
099D	jha
099E	nya
099F	ta
09A0	tha
09A1	da
09A2	dha
09A3	na
09A4	ta
09A5	tha
09A6	da
09A7	dha
09A8	na
09AA	pa
09AB	pha
09AC	ba
09AD	bha
09AE	ma
09AF	ya
09B0	ra
09B2	la
09B6	sha
09B7	sha
09B8	sa
09B9	ha
09BC	
09BD	'
09BE	a
09BF	i
09C0	i
09C1	u
09C2	u
09C3	r
09C4	r
09C7	e
09C8	ai
09CB	o
09CC	au
09CD	
09CE	t
09D7	
09DC	ra
09DD	rha
09DF	ya
09E0	r
09E1	l
09E2	l
09E3	l
09E6	0
09E7	1
09E8	2
09E9	3
09EA	4
09EB	5
09EC	6
09ED	7
09EE	8
09EF	9
09F0	ra
09F1	wa
09F2	Rs
09F3	Rs
09F4	1
09F5	2
09F6	3
09F7	4
09F8	-1
09F9	16
09FA	
09FB	
09FC	m
09FD	.
09FE	

# === Gurmukhi (U+0A00–U+0A7F) ===
# Source: UNGEGN/Hunterian romanization

0A01	m
0A02	m
0A03	h
0A05	a
0A06	aa
0A07	i
0A08	i
0A09	u
0A0A	u
0A0F	e
0A10	ai
0A13	o
0A14	au
0A15	ka
0A16	kha
0A17	ga
0A18	gha
0A19	nga
0A1A	cha
0A1B	chha
0A1C	ja
0A1D	jha
0A1E	nya
0A1F	ta
0A20	tha
0A21	da
0A22	dha
0A23	na
0A24	ta
0A25	tha
0A26	da
0A27	dha
0A28	na
0A2A	pa
0A2B	pha
0A2C	ba
0A2D	bha
0A2E	ma
0A2F	ya
0A30	ra
0A32	la
0A33	la
0A35	va
0A36	sha
0A38	sa
0A39	ha
0A3C	
0A3E	a
0A3F	i
0A40	i
0A41	u
0A42	u
0A47	e
0A48	ai
0A4B	o
0A4C	au
0A4D	
0A51	
0A59	kha
0A5A	ga
0A5B	za
0A5C	ra
0A5E	fa
0A66	0
0A67	1
0A68	2
0A69	3
0A6A	4
0A6B	5
0A6C	6
0A6D	7
0A6E	8
0A6F	9
0A70	
0A71	
0A72	iri
0A73	ura
0A74	ek
0A75	
0A76	.

# === Gujarati (U+0A80–U+0AFF) ===
# Source: UNGEGN/Hunterian romanization

0A81	m
0A82	m
0A83	h
0A85	a
0A86	aa
0A87	i
0A88	i
0A89	u
0A8A	u
0A8B	r
0A8C	l
0A8D	e
0A8F	e
0A90	ai
0A91	o
0A93	o
0A94	au
0A95	ka
0A96	kha
0A97	ga
0A98	gha
0A99	nga
0A9A	cha
0A9B	chha
0A9C	ja
0A9D	jha
0A9E	nya
0A9F	ta
0AA0	tha
0AA1	da
0AA2	dha
0AA3	na
0AA4	ta
0AA5	tha
0AA6	da
0AA7	dha
0AA8	na
0AAA	pa
0AAB	pha
0AAC	ba
0AAD	bha
0AAE	ma
0AAF	ya
0AB0	ra
0AB2	la
0AB3	la
0AB5	va
0AB6	sha
0AB7	sha
0AB8	sa
0AB9	ha
0ABC	
0ABD	'
0ABE	a
0ABF	i
0AC0	i
0AC1	u
0AC2	u
0AC3	r
0AC4	r
0AC5	e
0AC7	e
0AC8	ai
0AC9	o
0ACB	o
0ACC	au
0ACD	
0AD0	om
0AE0	r
0AE1	l
0AE2	l
0AE3	l
0AE6	0
0AE7	1
0AE8	2
0AE9	3
0AEA	4
0AEB	5
0AEC	6
0AED	7
0AEE	8
0AEF	9
0AF0	.
0AF1	Rs
0AF9	zha
0AFA	
0AFB	
0AFC	
0AFD	
0AFE	
0AFF	

# === Oriya (U+0B00–U+0B7F) ===
# Source: UNGEGN/Hunterian romanization

0B01	m
0B02	m
0B03	h
0B05	a
0B06	aa
0B07	i
0B08	i
0B09	u
0B0A	u
0B0B	r
0B0C	l
0B0F	e
0B10	ai
0B13	o
0B14	au
0B15	ka
0B16	kha
0B17	ga
0B18	gha
0B19	nga
0B1A	cha
0B1B	chha
0B1C	ja
0B1D	jha
0B1E	nya
0B1F	ta
0B20	tha
0B21	da
0B22	dha
0B23	na
0B24	ta
0B25	tha
0B26	da
0B27	dha
0B28	na
0B2A	pa
0B2B	pha
0B2C	ba
0B2D	bha
0B2E	ma
0B2F	ya
0B30	ra
0B32	la
0B33	la
0B35	va
0B36	sha
0B37	sha
0B38	sa
0B39	ha
0B3C	
0B3D	'
0B3E	a
0B3F	i
0B40	i
0B41	u
0B42	u
0B43	r
0B44	r
0B47	e
0B48	ai
0B4B	o
0B4C	au
0B4D	
0B55	e
0B56	
0B57	
0B5C	da
0B5D	dha
0B5F	ya
0B60	r
0B61	l
0B62	l
0B63	l
0B66	0
0B67	1
0B68	2
0B69	3
0B6A	4
0B6B	5
0B6C	6
0B6D	7
0B6E	8
0B6F	9
0B70	
0B71	wa
0B72	1/4
0B73	1/2
0B74	3/4
0B75	1/16
0B76	1/8
0B77	3/16

# === Tamil (U+0B80–U+0BFF) ===
# Source: UNGEGN Tamil romanization
# Diagnostic: ழ→zha (UNGEGN Tamil)

0B82	m
0B83	h
0B85	a
0B86	aa
0B87	i
0B88	i
0B89	u
0B8A	u
0B8E	e
0B8F	e
0B90	ai
0B92	o
0B93	o
0B94	au
0B95	ka
0B99	nga
0B9A	cha
0B9C	ja
0B9E	nya
0B9F	ta
0BA3	na
0BA4	ta
0BA8	na
0BA9	na
0BAA	pa
0BAE	ma
0BAF	ya
0BB0	ra
0BB1	ra
0BB2	la
0BB3	la
0BB4	zha
0BB5	va
0BB6	sha
0BB7	sha
0BB8	sa
0BB9	ha
0BBE	a
0BBF	i
0BC0	i
0BC1	u
0BC2	u
0BC6	e
0BC7	e
0BC8	ai
0BCA	o
0BCB	o
0BCC	au
0BCD	
0BD0	om
0BD7	
0BE6	0
0BE7	1
0BE8	2
0BE9	3
0BEA	4
0BEB	5
0BEC	6
0BED	7
0BEE	8
0BEF	9
0BF0	10
0BF1	100
0BF2	1000
0BF3	
0BF4	
0BF5	
0BF6	
0BF7	
0BF8	
0BF9	Rs
0BFA	

# === Telugu (U+0C00–U+0C7F) ===
# Source: UNGEGN/Hunterian romanization

0C00	
0C01	m
0C02	m
0C03	h
0C04	
0C05	a
0C06	aa
0C07	i
0C08	i
0C09	u
0C0A	u
0C0B	r
0C0C	l
0C0E	e
0C0F	e
0C10	ai
0C12	o
0C13	o
0C14	au
0C15	ka
0C16	kha
0C17	ga
0C18	gha
0C19	nga
0C1A	cha
0C1B	chha
0C1C	ja
0C1D	jha
0C1E	nya
0C1F	ta
0C20	tha
0C21	da
0C22	dha
0C23	na
0C24	ta
0C25	tha
0C26	da
0C27	dha
0C28	na
0C2A	pa
0C2B	pha
0C2C	ba
0C2D	bha
0C2E	ma
0C2F	ya
0C30	ra
0C31	ra
0C32	la
0C33	la
0C34	lla
0C35	va
0C36	sha
0C37	sha
0C38	sa
0C39	ha
0C3C	
0C3D	'
0C3E	a
0C3F	i
0C40	i
0C41	u
0C42	u
0C43	r
0C44	r
0C46	e
0C47	e
0C48	ai
0C4A	o
0C4B	o
0C4C	au
0C4D	
0C55	
0C56	
0C58	tsa
0C59	dza
0C5A	rra
0C5D	n
0C60	r
0C61	l
0C62	l
0C63	l
0C66	0
0C67	1
0C68	2
0C69	3
0C6A	4
0C6B	5
0C6C	6
0C6D	7
0C6E	8
0C6F	9
0C77	
0C78	0
0C79	1
0C7A	2
0C7B	3
0C7C	1
0C7D	2
0C7E	3
0C7F	

# === Kannada (U+0C80–U+0CFF) ===
# Source: UNGEGN/Hunterian romanization

0C80	m
0C81	m
0C82	m
0C83	h
0C84	
0C85	a
0C86	aa
0C87	i
0C88	i
0C89	u
0C8A	u
0C8B	r
0C8C	l
0C8E	e
0C8F	e
0C90	ai
0C92	o
0C93	o
0C94	au
0C95	ka
0C96	kha
0C97	ga
0C98	gha
0C99	nga
0C9A	cha
0C9B	chha
0C9C	ja
0C9D	jha
0C9E	nya
0C9F	ta
0CA0	tha
0CA1	da
0CA2	dha
0CA3	na
0CA4	ta
0CA5	tha
0CA6	da
0CA7	dha
0CA8	na
0CAA	pa
0CAB	pha
0CAC	ba
0CAD	bha
0CAE	ma
0CAF	ya
0CB0	ra
0CB1	ra
0CB2	la
0CB3	la
0CB5	va
0CB6	sha
0CB7	sha
0CB8	sa
0CB9	ha
0CBC	
0CBD	'
0CBE	a
0CBF	i
0CC0	i
0CC1	u
0CC2	u
0CC3	r
0CC4	r
0CC6	e
0CC7	e
0CC8	ai
0CCA	o
0CCB	o
0CCC	au
0CCD	
0CD5	
0CD6	
0CDD	n
0CDE	fa
0CE0	r
0CE1	l
0CE2	l
0CE3	l
0CE6	0
0CE7	1
0CE8	2
0CE9	3
0CEA	4
0CEB	5
0CEC	6
0CED	7
0CEE	8
0CEF	9
0CF1	h
0CF2	h
0CF3	

# === Malayalam (U+0D00–U+0D7F) ===
# Source: UNGEGN/Hunterian romanization

0D00	
0D01	m
0D02	m
0D03	h
0D04	a
0D05	a
0D06	aa
0D07	i
0D08	i
0D09	u
0D0A	u
0D0B	r
0D0C	l
0D0E	e
0D0F	e
0D10	ai
0D12	o
0D13	o
0D14	au
0D15	ka
0D16	kha
0D17	ga
0D18	gha
0D19	nga
0D1A	cha
0D1B	chha
0D1C	ja
0D1D	jha
0D1E	nya
0D1F	ta
0D20	tha
0D21	da
0D22	dha
0D23	na
0D24	ta
0D25	tha
0D26	da
0D27	dha
0D28	na
0D29	nna
0D2A	pa
0D2B	pha
0D2C	ba
0D2D	bha
0D2E	ma
0D2F	ya
0D30	ra
0D31	ra
0D32	la
0D33	la
0D34	zha
0D35	va
0D36	sha
0D37	sha
0D38	sa
0D39	ha
0D3A	tta
0D3B	
0D3C	
0D3D	'
0D3E	a
0D3F	i
0D40	i
0D41	u
0D42	u
0D43	r
0D44	r
0D46	e
0D47	e
0D48	ai
0D4A	o
0D4B	o
0D4C	au
0D4D	
0D4E	r
0D4F	
0D54	m
0D55	y
0D56	l
0D57	
0D58	1/160
0D59	1/40
0D5A	3/80
0D5B	1/20
0D5C	1/10
0D5D	3/20
0D5E	1/5
0D5F	ii
0D60	r
0D61	l
0D62	l
0D63	l
0D66	0
0D67	1
0D68	2
0D69	3
0D6A	4
0D6B	5
0D6C	6
0D6D	7
0D6E	8
0D6F	9
0D70	10
0D71	100
0D72	1000
0D73	1/4
0D74	1/2
0D75	3/4
0D76	1/16
0D77	1/8
0D78	3/16
0D79	
0D7A	n
0D7B	n
0D7C	r
0D7D	l
0D7E	l
0D7F	k

# === Sinhala (U+0D80–U+0DFF) ===
# Source: UNGEGN/Indic pattern with Sinhala-specific extensions
# Prenasalized stops: nnga, nndda, mba; unique vowels: ae, aae

0D81	m
0D82	m
0D83	h
0D85	a
0D86	aa
0D87	ae
0D88	aae
0D89	i
0D8A	ii
0D8B	u
0D8C	uu
0D8D	ri
0D8E	r
0D8F	rr
0D90	luu
0D91	e
0D92	ee
0D93	ai
0D94	o
0D95	oo
0D96	au
0D9A	ka
0D9B	kha
0D9C	ga
0D9D	gha
0D9E	nga
0D9F	nnga
0DA0	cha
0DA1	chha
0DA2	ja
0DA3	jha
0DA4	nya
0DA5	jnya
0DA6	nyja
0DA7	tta
0DA8	ttha
0DA9	dda
0DAA	ddha
0DAB	nna
0DAC	nndda
0DAD	ta
0DAE	tha
0DAF	da
0DB0	dha
0DB1	na
0DB3	nda
0DB4	pa
0DB5	pha
0DB6	ba
0DB7	bha
0DB8	ma
0DB9	mba
0DBA	ya
0DBB	ra
0DBD	la
0DC0	va
0DC1	sha
0DC2	sha
0DC3	sa
0DC4	ha
0DC5	lla
0DC6	fa
0DCA	
0DCF	a
0DD0	aa
0DD1	ae
0DD2	i
0DD3	ii
0DD4	u
0DD6	uu
0DD8	r
0DD9	e
0DDA	ee
0DDB	ai
0DDC	o
0DDD	oo
0DDE	au
0DDF	l
0DE6	0
0DE7	1
0DE8	2
0DE9	3
0DEA	4
0DEB	5
0DEC	6
0DED	7
0DEE	8
0DEF	9
0DF2	rr
0DF3	ll
0DF4	.

# === Thai (U+0E00–U+0E7F) ===
# Source: RTGS (Royal Thai General System)
# Exact match on all consonants and vowels

0E01	k
0E02	kh
0E03	kh
0E04	kh
0E05	kh
0E06	kh
0E07	ng
0E08	ch
0E09	ch
0E0A	ch
0E0B	s
0E0C	ch
0E0D	y
0E0E	d
0E0F	t
0E10	th
0E11	th
0E12	th
0E13	n
0E14	d
0E15	t
0E16	th
0E17	th
0E18	th
0E19	n
0E1A	b
0E1B	p
0E1C	ph
0E1D	f
0E1E	ph
0E1F	f
0E20	ph
0E21	m
0E22	y
0E23	r
0E24	rue
0E25	l
0E26	lue
0E27	w
0E28	s
0E29	s
0E2A	s
0E2B	h
0E2C	l
0E2D	o
0E2E	h
0E2F	.
0E30	a
0E31	a
0E32	a
0E33	am
0E34	i
0E35	i
0E36	ue
0E37	ue
0E38	u
0E39	u
0E3A	
0E3F	B
0E40	e
0E41	ae
0E42	o
0E43	ai
0E44	ai
0E45	a
0E46	
0E47	
0E48	
0E49	
0E4A	
0E4B	
0E4C	
0E4D	m
0E4E	
0E4F	 
0E50	0
0E51	1
0E52	2
0E53	3
0E54	4
0E55	5
0E56	6
0E57	7
0E58	8
0E59	9
0E5A	.
0E5B	.

# === Lao (U+0E80–U+0EDF) ===
# Source: BGN/PCGN Lao romanization (1966)
# Vowels ASCII-simplified (ue instead of diacritics)

0E81	k
0E82	kh
0E84	kh
0E86	gha
0E87	ng
0E88	ch
0E89	cha
0E8A	s
0E8C	jha
0E8D	ny
0E8E	nya
0E8F	tta
0E90	ttha
0E91	dda
0E92	ddha
0E93	nna
0E94	d
0E95	t
0E96	th
0E97	th
0E98	dha
0E99	n
0E9A	b
0E9B	p
0E9C	ph
0E9D	f
0E9E	ph
0E9F	f
0EA0	bha
0EA1	m
0EA2	y
0EA3	r
0EA5	l
0EA7	w
0EA8	sha
0EA9	ssa
0EAA	s
0EAB	h
0EAC	lla
0EAD	o
0EAE	h
0EAF	...
0EB0	a
0EB1	a
0EB2	a
0EB3	am
0EB4	i
0EB5	i
0EB6	ue
0EB7	ue
0EB8	u
0EB9	u
0EBA	
0EBB	o
0EBC	l
0EBD	y
0EC0	e
0EC1	ae
0EC2	o
0EC3	ai
0EC4	ai
0EC6	
0EC8	
0EC9	
0ECA	
0ECB	
0ECC	
0ECD	m
0ECE	
0ED0	0
0ED1	1
0ED2	2
0ED3	3
0ED4	4
0ED5	5
0ED6	6
0ED7	7
0ED8	8
0ED9	9
0EDC	hn
0EDD	hm
0EDE	go
0EDF	nyo

# === Tibetan (U+0F00–U+0FFF) ===
# Source: Indic-phonetic romanization (NOT Wylie)
# Diagnostic: ཅ→cha (Wylie would be ca). Uses Hunterian-style aspiration markers.

0F00	om
0F01	.
0F02	.
0F03	.
0F04	@
0F05	#
0F06	.
0F07	.
0F08	;
0F09	*
0F0A	*
0F0B	-
0F0C	
0F0D	.
0F0E	.
0F0F	.
0F10	.
0F11	.
0F12	.
0F13	.
0F14	:
0F15	
0F16	
0F17	
0F18	
0F19	
0F1A	
0F1B	
0F1C	
0F1D	
0F1E	
0F1F	
0F20	0
0F21	1
0F22	2
0F23	3
0F24	4
0F25	5
0F26	6
0F27	7
0F28	8
0F29	9
0F2A	0.0
0F2B	0.5
0F2C	1.0
0F2D	1.5
0F2E	2.0
0F2F	2.5
0F30	3.0
0F31	3.5
0F32	4.0
0F33	4.5
0F34	
0F35	
0F36	
0F37	
0F38	
0F39	
0F3A	(
0F3B	)
0F3C	(
0F3D	)
0F3E	
0F3F	
0F40	ka
0F41	kha
0F42	ga
0F43	ga
0F44	nga
0F45	cha
0F46	chha
0F47	ja
0F49	nya
0F4A	ta
0F4B	tha
0F4C	da
0F4D	da
0F4E	na
0F4F	ta
0F50	tha
0F51	da
0F52	da
0F53	na
0F54	pa
0F55	pha
0F56	ba
0F57	ba
0F58	ma
0F59	tsa
0F5A	tsha
0F5B	dza
0F5C	dza
0F5D	wa
0F5E	zha
0F5F	za
0F60	a
0F61	ya
0F62	ra
0F63	la
0F64	sha
0F65	sha
0F66	sa
0F67	ha
0F68	a
0F69	ksha
0F6A	ra
0F6B	kka
0F6C	rra
0F71	a
0F72	i
0F73	i
0F74	u
0F75	u
0F76	ri
0F77	ri
0F78	li
0F79	li
0F7A	e
0F7B	e
0F7C	o
0F7D	o
0F7E	
0F7F	
0F80	i
0F81	i
0F82	
0F83	
0F84	
0F85	.
0F86	
0F87	
0F88	
0F89	
0F8A	
0F8B	
0F8C	
0F8D	
0F8E	
0F8F	
0F90	ka
0F91	kha
0F92	ga
0F93	ga
0F94	nga
0F95	cha
0F96	chha
0F97	ja
0F99	nya
0F9A	ta
0F9B	tha
0F9C	da
0F9D	da
0F9E	na
0F9F	ta
0FA0	tha
0FA1	da
0FA2	da
0FA3	na
0FA4	pa
0FA5	pha
0FA6	ba
0FA7	ba
0FA8	ma
0FA9	tsa
0FAA	tsha
0FAB	dza
0FAC	dza
0FAD	wa
0FAE	zha
0FAF	za
0FB0	a
0FB1	ya
0FB2	ra
0FB3	la
0FB4	sha
0FB5	sha
0FB6	sa
0FB7	ha
0FB8	a
0FB9	ksha
0FBA	wa
0FBB	ya
0FBC	ra
0FBE	
0FBF	
0FC0	
0FC1	
0FC2	
0FC3	
0FC4	
0FC5	
0FC6	
0FC7	
0FC8	
0FC9	
0FCA	
0FCB	
0FCC	
0FCE	
0FCF	
0FD0	|
0FD1	|
0FD2	:
0FD3	|
0FD4	|
0FD5	
0FD6	
0FD7	
0FD8	
0FD9	|
0FDA	|

# === Myanmar (U+1000–U+109F) ===
# Source: MLC (Myanmar Language Commission) romanization
# Diagnostic: U+1006→hsa (MLC signature)

1000	ka
1001	kha
1002	ga
1003	gha
1004	nga
1005	sa
1006	hsa
1007	za
1008	zha
1009	nya
100A	nya
100B	ta
100C	tha
100D	da
100E	dha
100F	na
1010	ta
1011	tha
1012	da
1013	dha
1014	na
1015	pa
1016	pha
1017	ba
1018	bha
1019	ma
101A	ya
101B	ra
101C	la
101D	wa
101E	tha
101F	ha
1020	la
1021	a
1022	a
1023	i
1024	i
1025	u
1026	u
1027	e
1028	e
1029	o
102A	o
102B	a
102C	a
102D	i
102E	i
102F	u
1030	u
1031	e
1032	e
1033	o
1034	o
1035	e
1036	
1037	
1038	
1039	
103A	
103B	y
103C	r
103D	w
103E	h
103F	sa
1040	0
1041	1
1042	2
1043	3
1044	4
1045	5
1046	6
1047	7
1048	8
1049	9
104A	,
104B	.
104C	,
104D	.
104E	
104F	
1050	sha
1051	ssa
1052	ri
1053	ri
1054	li
1055	li
1056	ri
1057	ri
1058	li
1059	li
105A	nga
105B	jha
105C	ba
105D	be
105E	n
105F	m
1060	l
1061	sha
1062	eu
1063	
1064	
1065	tha
1066	pwa
1067	eu
1068	ue
1069	
106A	
106B	
106C	
106D	
106E	na
106F	ywa
1070	ghwa
1071	i
1072	oe
1073	u
1074	ee
1075	ka
1076	kha
1077	ga
1078	ca
1079	za
107A	nya
107B	da
107C	na
107D	pha
107E	fa
107F	ba
1080	tha
1081	ha
1082	w
1083	a
1084	e
1085	e
1086	y
1087	
1088	
1089	
108A	
108B	
108C	
108D	
108E	fa
108F	
1090	0
1091	1
1092	2
1093	3
1094	4
1095	5
1096	6
1097	7
1098	8
1099	9
109A	
109B	
109C	a
109D	ai
109E	1
109F	!

# === Georgian (U+10A0–U+10FF) ===
# Source: BGN/PCGN Georgian romanization (2009)
# Deviation: Ejective apostrophes stripped (t'→t, k'→k, p'→p, ts'→ts, ch'→ch)

10A0	A
10A1	B
10A2	G
10A3	D
10A4	E
10A5	V
10A6	Z
10A7	T
10A8	I
10A9	K
10AA	L
10AB	M
10AC	N
10AD	O
10AE	P
10AF	Zh
10B0	R
10B1	S
10B2	T
10B3	U
10B4	P
10B5	K
10B6	Gh
10B7	Q
10B8	Sh
10B9	Ch
10BA	Ts
10BB	Dz
10BC	Ts
10BD	Ch
10BE	Kh
10BF	J
10C0	H
10C1	He
10C2	Hi
10C3	W
10C4	Har
10C5	Ho
10C7	Yn
10CD	Ae
10D0	a
10D1	b
10D2	g
10D3	d
10D4	e
10D5	v
10D6	z
10D7	t
10D8	i
10D9	k
10DA	l
10DB	m
10DC	n
10DD	o
10DE	p
10DF	zh
10E0	r
10E1	s
10E2	t
10E3	u
10E4	p
10E5	k
10E6	gh
10E7	q
10E8	sh
10E9	ch
10EA	ts
10EB	dz
10EC	ts
10ED	ch
10EE	kh
10EF	j
10F0	h
10F1	he
10F2	hi
10F3	w
10F4	har
10F5	ho
10F6	f
10F7	yn
10F8	el
10F9	g
10FA	'
10FB	.
10FC	n
10FD	ae
10FE	
10FF	w

# === Hangul Jamo (U+1100–U+11FF) ===
# Source: Revised Romanization of Korean (RR, 2000)

1100	g
1101	kk
1102	n
1103	d
1104	tt
1105	r
1106	m
1107	b
1108	pp
1109	s
110A	ss
110B	
110C	j
110D	jj
110E	ch
110F	k
1110	t
1111	p
1112	h
1113	n-g
1114	nn
1115	n-d
1116	n-b
1117	dd
1118	r-n
1119	rr
111A	r-h
111B	r-
111C	mb
111D	m-
111E	b-g
111F	b-n
1120	b-d
1121	bs
1122	b-sg
1123	b-sd
1124	b-sb
1125	b-ss
1126	b-sj
1127	b-j
1128	b-ch
1129	b-t
112A	b-p
112B	b-
112C	bb-
112D	s-g
112E	s-n
112F	s-d
1130	s-r
1131	s-m
1132	s-b
1133	sb-g
1134	ss-s
1135	s-
1136	s-j
1137	s-ch
1138	s-k
1139	s-t
113A	s-p
113B	s-h
113C	ss-
113D	ss-
113E	ss-
113F	ss-
1140	z
1141	-g
1142	-d
1143	-m
1144	-b
1145	-s
1146	-z
1147	ng
1148	j-
1149	jj-
114A	j-
114B	ch-
114C	ng
114D	j
114E	ch
114F	ch
1150	ch
1151	ch-k
1152	ch-h
1153	ch-
1154	ch
1155	p-b
1156	p-
1157	h
1158	h
1159	ng
115A	g-d
115B	n-s
115C	n-j
115D	n-h
115E	d-r
115F	
1160	
1161	a
1162	ae
1163	ya
1164	yae
1165	eo
1166	e
1167	yeo
1168	ye
1169	o
116A	wa
116B	wae
116C	oe
116D	yo
116E	u
116F	wo
1170	we
1171	wi
1172	yu
1173	eu
1174	ui
1175	i
1176	a-o
1177	a-u
1178	ya-o
1179	ya-yo
117A	eo-o
117B	eo-u
117C	eo-eu
117D	yeo-o
117E	yeo-u
117F	o-eo
1180	o-e
1181	o-ye
1182	o-o
1183	o-u
1184	yo-ya
1185	yo-yae
1186	yo-yeo
1187	yo-o
1188	yo-i
1189	u-a
118A	u-ae
118B	u-eo-eu
118C	u-ye
118D	u-u
118E	yu-a
118F	yu-eo
1190	yu-e
1191	yu-yeo
1192	yu-ye
1193	yu-u
1194	yu-i
1195	eu-u
1196	eu-eu
1197	yi
1198	i-a
1199	i-ya
119A	i-o
119B	i-u
119C	i-eu
119D	i-
119E	a
119F	a-eo
11A0	a-u
11A1	a-i
11A2	a-
11A3	a-e
11A4	a-o
11A5	a-u
11A6	a-eu
11A7	i-ya-o
11A8	g
11A9	kk
11AA	gs
11AB	n
11AC	nj
11AD	nh
11AE	d
11AF	l
11B0	lg
11B1	lm
11B2	lb
11B3	ls
11B4	lt
11B5	lp
11B6	lh
11B7	m
11B8	b
11B9	bs
11BA	s
11BB	ss
11BC	ng
11BD	j
11BE	ch
11BF	k
11C0	t
11C1	p
11C2	h
11C3	g-r
11C4	g-sg
11C5	n-g
11C6	n-d
11C7	n-s
11C8	n-z
11C9	n-t
11CA	d-g
11CB	d-r
11CC	r-gs
11CD	r-n
11CE	r-d
11CF	r-dh
11D0	rr
11D1	r-mb
11D2	r-bs
11D3	r-b-s
11D4	r-b-h
11D5	r-b-
11D6	r-ss
11D7	r-z
11D8	r-k
11D9	r-
11DA	m-g
11DB	m-r
11DC	m-b
11DD	m-s
11DE	m-ss
11DF	m-z
11E0	m-ch
11E1	m-h
11E2	m-
11E3	b-r
11E4	b-ph
11E5	b-h
11E6	b-
11E7	s-g
11E8	s-d
11E9	s-r
11EA	s-b
11EB	z
11EC	ng-g
11ED	ng-gg
11EE	ng-ng
11EF	ng-k
11F0	ng
11F1	ng-s
11F2	ng-z
11F3	p-b
11F4	p-
11F5	h-n
11F6	h-r
11F7	h-m
11F8	h-b
11F9	ng
11FA	g-n
11FB	g-b
11FC	g-ch
11FD	g-k
11FE	g-h
11FF	nn

# === Ethiopic (U+1200–U+137F) ===
# Source: BGN/PCGN Amharic romanization (1967)
# Syllabic vowel order: e, u, i, a, e, ∅, o, wa

1200	he
1201	hu
1202	hi
1203	ha
1204	he
1205	h
1206	ho
1207	hwa
1208	le
1209	lu
120A	li
120B	la
120C	le
120D	l
120E	lo
120F	lwa
1210	hhe
1211	hhu
1212	hhi
1213	hha
1214	hhe
1215	hh
1216	hho
1217	hhwa
1218	me
1219	mu
121A	mi
121B	ma
121C	me
121D	m
121E	mo
121F	mwa
1220	se
1221	su
1222	si
1223	sa
1224	se
1225	s
1226	so
1227	swa
1228	re
1229	ru
122A	ri
122B	ra
122C	re
122D	r
122E	ro
122F	rwa
1230	se
1231	su
1232	si
1233	sa
1234	se
1235	s
1236	so
1237	swa
1238	she
1239	shu
123A	shi
123B	sha
123C	she
123D	sh
123E	sho
123F	shwa
1240	qe
1241	qu
1242	qi
1243	qa
1244	qe
1245	q
1246	qo
1247	qwa
1248	qwa
124A	qwi
124B	qwa
124C	qwe
124D	qw
1250	qhe
1251	qhu
1252	qhi
1253	qha
1254	qhe
1255	qh
1256	qho
1258	qhwa
125A	qhwi
125B	qhwa
125C	qhwe
125D	qhw
1260	be
1261	bu
1262	bi
1263	ba
1264	be
1265	b
1266	bo
1267	bwa
1268	ve
1269	vu
126A	vi
126B	va
126C	ve
126D	v
126E	vo
126F	vwa
1270	te
1271	tu
1272	ti
1273	ta
1274	te
1275	t
1276	to
1277	twa
1278	che
1279	chu
127A	chi
127B	cha
127C	che
127D	ch
127E	cho
127F	chwa
1280	he
1281	hu
1282	hi
1283	ha
1284	he
1285	h
1286	ho
1287	hwa
1288	hwa
128A	hwi
128B	hwa
128C	hwe
128D	hw
1290	ne
1291	nu
1292	ni
1293	na
1294	ne
1295	n
1296	no
1297	nwa
1298	nye
1299	nyu
129A	nyi
129B	nya
129C	nye
129D	ny
129E	nyo
129F	nywa
12A0	e
12A1	u
12A2	i
12A3	a
12A4	e
12A5	e
12A6	o
12A7	wa
12A8	ke
12A9	ku
12AA	ki
12AB	ka
12AC	ke
12AD	k
12AE	ko
12AF	kwa
12B0	kwa
12B2	kwi
12B3	kwa
12B4	kwe
12B5	kw
12B8	khe
12B9	khu
12BA	khi
12BB	kha
12BC	khe
12BD	kh
12BE	kho
12C0	khwa
12C2	khwi
12C3	khwa
12C4	khwe
12C5	khw
12C8	we
12C9	wu
12CA	wi
12CB	wa
12CC	we
12CD	w
12CE	wo
12CF	wwa
12D0	e
12D1	u
12D2	i
12D3	a
12D4	e
12D5	e
12D6	o
12D8	ze
12D9	zu
12DA	zi
12DB	za
12DC	ze
12DD	z
12DE	zo
12DF	zwa
12E0	zhe
12E1	zhu
12E2	zhi
12E3	zha
12E4	zhe
12E5	zh
12E6	zho
12E7	zhwa
12E8	ye
12E9	yu
12EA	yi
12EB	ya
12EC	ye
12ED	y
12EE	yo
12EF	ywa
12F0	de
12F1	du
12F2	di
12F3	da
12F4	de
12F5	d
12F6	do
12F7	dwa
12F8	dde
12F9	ddu
12FA	ddi
12FB	dda
12FC	dde
12FD	dd
12FE	ddo
12FF	ddwa
1300	je
1301	ju
1302	ji
1303	ja
1304	je
1305	j
1306	jo
1307	jwa
1308	ge
1309	gu
130A	gi
130B	ga
130C	ge
130D	g
130E	go
130F	gwa
1310	gwa
1312	gwi
1313	gwa
1314	gwe
1315	gw
1318	gge
1319	ggu
131A	ggi
131B	gga
131C	gge
131D	gg
131E	ggo
131F	ggwa
1320	te
1321	tu
1322	ti
1323	ta
1324	te
1325	t
1326	to
1327	twa
1328	che
1329	chu
132A	chi
132B	cha
132C	che
132D	ch
132E	cho
132F	chwa
1330	pe
1331	pu
1332	pi
1333	pa
1334	pe
1335	p
1336	po
1337	pwa
1338	tse
1339	tsu
133A	tsi
133B	tsa
133C	tse
133D	ts
133E	tso
133F	tswa
1340	tse
1341	tsu
1342	tsi
1343	tsa
1344	tse
1345	ts
1346	tso
1347	tswa
1348	fe
1349	fu
134A	fi
134B	fa
134C	fe
134D	f
134E	fo
134F	fwa
1350	pe
1351	pu
1352	pi
1353	pa
1354	pe
1355	p
1356	po
1357	pwa
1358	rya
1359	mya
135A	fya
135D	
135E	
135F	
1360	 
1361	:
1362	.
1363	,
1364	;
1365	:
1366	:
1367	?
1368	//
1369	1
136A	2
136B	3
136C	4
136D	5
136E	6
136F	7
1370	8
1371	9
1372	10
1373	20
1374	30
1375	40
1376	50
1377	60
1378	70
1379	80
137A	90
137B	100
137C	10000

# === Ethiopic Supplement (U+1380–U+139F) ===
# Source: BGN/PCGN Amharic conventions (extended)

1380	mwa
1381	mwi
1382	mwe
1383	mwe
1384	bwa
1385	bwi
1386	bwe
1387	bwe
1388	fwa
1389	fwi
138A	fwe
138B	fwe
138C	pwa
138D	pwi
138E	pwe
138F	pwe
1390	
1391	
1392	
1393	
1394	
1395	
1396	
1397	
1398	
1399	

# === Cherokee (U+13A0–U+13FF) ===
# Source: Syllabary phonetic values

13A0	a
13A1	e
13A2	i
13A3	o
13A4	u
13A5	v
13A6	ga
13A7	ka
13A8	ge
13A9	gi
13AA	go
13AB	gu
13AC	gv
13AD	ha
13AE	he
13AF	hi
13B0	ho
13B1	hu
13B2	hv
13B3	la
13B4	le
13B5	li
13B6	lo
13B7	lu
13B8	lv
13B9	ma
13BA	me
13BB	mi
13BC	mo
13BD	mu
13BE	na
13BF	hna
13C0	nah
13C1	ne
13C2	ni
13C3	no
13C4	nu
13C5	nv
13C6	qua
13C7	que
13C8	qui
13C9	quo
13CA	quu
13CB	quv
13CC	sa
13CD	s
13CE	se
13CF	si
13D0	so
13D1	su
13D2	sv
13D3	da
13D4	ta
13D5	de
13D6	te
13D7	di
13D8	ti
13D9	do
13DA	du
13DB	dv
13DC	dla
13DD	tla
13DE	tle
13DF	tli
13E0	tlo
13E1	tlu
13E2	tlv
13E3	tsa
13E4	tse
13E5	tsi
13E6	tso
13E7	tsu
13E8	tsv
13E9	wa
13EA	we
13EB	wi
13EC	wo
13ED	wu
13EE	wv
13EF	ya
13F0	ye
13F1	yi
13F2	yo
13F3	yu
13F4	yv
13F5	mv
13F8	ye
13F9	yi
13FA	yo
13FB	yu
13FC	yv
13FD	mv

# === Unified Canadian Aboriginal Syllabics (U+1400–U+167F) ===
# Source: Phonetic decomposition of syllabics (consonant+vowel)
# No single published standard; reflects inherent syllabary structure

1400	.
1401	e
1402	aai
1403	i
1404	ii
1405	o
1406	oo
1407	a
1408	aa
1409	cari
140A	we
140B	waai
140C	wi
140D	wii
140E	wo
140F	woo
1410	wa
1411	waa
1412	w
1413	weswo
1414	woo
1415	weswo
1416	naswo
1417	wa
1418	weswa
1419	waa
141A	weswa
141B	naswa
141C	ai
141D	y-cw
141E	glost
141F	ac
1420	gr
1421	bo
1422	to
1423	ri
1425	do
1427	.
1428	sh
1429	pl
142A	do
142B	en
142C	in
142D	on
142E	an
142F	pe
1430	paai
1431	pe
1432	paai
1433	pi
1434	pii
1435	po
1436	poo
1437	pa
1438	paa
1439	pwe
143A	pwi
143B	pwii
143C	pwo
143D	pwoo
143E	pwa
143F	pwaa
1440	p
1441	wespw
1442	pwoo
1443	wespw
1444	pwa
1445	wespw
1446	te
1447	taai
1448	ti
1449	tii
144A	to
144B	too
144C	ta
144D	taa
144E	twe
144F	twi
1450	twii
1451	two
1452	twoo
1453	twa
1454	twaa
1455	t
1456	taa
1457	twe
1458	westw
1459	twi
145A	westw
145B	twii
145C	westw
145D	two
145E	westw
145F	twoo
1460	westw
1461	twa
1462	westw
1463	twaa
1464	westw
1465	nastw
1466	t
1467	tte
1468	tti
1469	tto
146A	tta
146B	ke
146C	kaai
146D	ki
146E	kii
146F	ko
1470	koo
1471	y-cko
1472	ke
1473	kaai
1474	ki
1475	kii
1476	ko
1477	koo
1478	ka
1479	kaa
147A	kwe
147B	kwi
147C	kwii
147D	kwo
147E	kwoo
147F	kwa
1480	kwaa
1481	k
1482	naskw
1483	k
1484	kw
1485	souke
1486	souki
1487	souko
1488	souka
1489	ce
148A	caai
148B	ce
148C	caai
148D	ci
148E	cii
148F	co
1490	coo
1491	ca
1492	caa
1493	cwe
1494	cwi
1495	cwii
1496	cwo
1497	cwoo
1498	cwa
1499	cwaa
149A	c
149B	wescw
149C	cwa
149D	wescw
149E	cwaa
149F	wescw
14A0	nascw
14A1	me
14A2	maai
14A3	mi
14A4	mii
14A5	mo
14A6	moo
14A7	ma
14A8	maa
14A9	mwe
14AA	mwi
14AB	mwii
14AC	mwo
14AD	mwoo
14AE	mwa
14AF	mwaa
14B0	m
14B1	wesmw
14B2	mwo
14B3	wesmw
14B4	mwoo
14B5	wesmw
14B6	mwa
14B7	wesmw
14B8	mwaa
14B9	wesmw
14BA	nasmw
14BB	m
14BC	wesm
14BD	mh
14BE	athm
14BF	saym
14C0	ne
14C1	naai
14C2	ni
14C3	nii
14C4	no
14C5	noo
14C6	na
14C7	naa
14C8	nwe
14C9	nwi
14CA	nwii
14CB	nwo
14CC	nwoo
14CD	nwa
14CE	nwaa
14CF	n
14D0	le
14D1	laai
14D2	li
14D3	lii
14D4	lo
14D5	loo
14D6	la
14D7	laa
14D8	l
14D9	y-clo
14DA	la
14DB	laa
14DC	lwe
14DD	weslw
14DE	lwi
14DF	weslw
14E0	lwii
14E1	weslw
14E2	lwo
14E3	weslw
14E4	lwoo
14E5	weslw
14E6	lwa
14E7	weslw
14E8	lwaa
14E9	weslw
14EA	se
14EB	saai
14EC	si
14ED	sii
14EE	so
14EF	soo
14F0	sa
14F1	saa
14F2	swe
14F3	swi
14F4	swii
14F5	swo
14F6	swoo
14F7	swa
14F8	swaa
14F9	s
14FA	swii
14FB	wessw
14FC	swo
14FD	wessw
14FE	swoo
14FF	wessw
1500	swa
1501	wessw
1502	swaa
1503	wessw
1504	nassw
1505	s
1506	aths
1507	sw
1508	blas
1509	moosk
150A	nassk
150B	nass-
150C	nassp
150D	nasst
150E	nassk
150F	nassc
1510	she
1511	shi
1512	shii
1513	sho
1514	shoo
1515	sha
1516	shaa
1517	shwe
1518	shwi
1519	shwii
151A	shwo
151B	shwoo
151C	shwa
151D	shwaa
151E	sh
151F	shwoo
1520	wessh
1521	shwa
1522	wessh
1523	shwaa
1524	wessh
1525	sh
1526	ye
1527	yaai
1528	yi
1529	yii
152A	yo
152B	yoo
152C	y-cyo
152D	ya
152E	ye
152F	yaai
1530	yi
1531	yii
1532	yo
1533	yoo
1534	ya
1535	yaa
1536	ywe
1537	ywi
1538	ywii
1539	ywo
153A	ywoo
153B	ywa
153C	ywaa
153D	y
153E	y
153F	biby
1540	wesy
1541	sayyi
1542	re
1543	r-cre
1544	wesle
1545	raai
1546	ri
1547	rii
1548	re
1549	raai
154A	ri
154B	rii
154C	ro
154D	roo
154E	ra
154F	raa
1550	r
1551	wesr
1552	medr
1553	fe
1554	faai
1555	fi
1556	fii
1557	fo
1558	foo
1559	fa
155A	faa
155B	fwaa
155C	wesfw
155D	f
155E	the
155F	thi
1560	thii
1561	tho
1562	thoo
1563	tha
1564	thaa
1565	th
1566	tha
1567	thaa
1568	thwaa
1569	westh
156A	th
156B	tthe
156C	tthi
156D	ttho
156E	ttha
156F	tth
1570	tye
1571	he
1572	hi
1573	hii
1574	ho
1575	hoo
1576	ha
1577	haa
1578	h
1579	nunha
157A	nunha
157B	nunh
157C	nunh
157D	hk
157E	qaai
157F	qi
1580	qii
1581	qo
1582	qoo
1583	qa
1584	qaa
1585	q
1586	tlhe
1587	tlhi
1588	tlho
1589	tlha
158A	wesre
158B	wesri
158C	wesro
158D	wesra
158E	ngaai
158F	ngi
1590	ngii
1591	ngo
1592	ngoo
1593	nga
1594	ngaa
1595	ng
1596	nng
1597	saysh
1598	saysh
1599	saysh
159A	saysh
159B	wooth
159C	wooth
159D	wooth
159E	wooth
159F	wooth
15A0	lhi
15A1	lhii
15A2	lho
15A3	lhoo
15A4	lha
15A5	lhaa
15A6	lh
15A7	th-th
15A8	th-th
15A9	th-th
15AA	th-th
15AB	th-th
15AC	th-th
15AD	th-th
15AE	th-th
15AF	aivb
15B0	blae
15B1	blai
15B2	blao
15B3	blaa
15B4	blawe
15B5	blawi
15B6	blawo
15B7	blawa
15B8	blane
15B9	blani
15BA	blano
15BB	blana
15BC	blake
15BD	blaki
15BE	blako
15BF	blaka
15C0	sayhe
15C1	sayhi
15C2	sayho
15C3	sayha
15C4	cargh
15C5	cargh
15C6	cargh
15C7	cargh
15C8	cargh
15C9	cargh
15CA	carru
15CB	carro
15CC	carre
15CD	carre
15CE	carri
15CF	carra
15D0	carwu
15D1	carwo
15D2	carwe
15D3	carwe
15D4	carwi
15D5	carwa
15D6	carhw
15D7	carhw
15D8	carhw
15D9	carhw
15DA	carhw
15DB	carhw
15DC	carth
15DD	carth
15DE	carth
15DF	carth
15E0	carth
15E1	carth
15E2	cartt
15E3	cartt
15E4	cartt
15E5	cartt
15E6	cartt
15E7	cartt
15E8	carpu
15E9	carpo
15EA	carpe
15EB	carpe
15EC	carpi
15ED	carpa
15EE	carp
15EF	cargu
15F0	cargo
15F1	carge
15F2	carge
15F3	cargi
15F4	carga
15F5	carkh
15F6	carkh
15F7	carkh
15F8	carkh
15F9	carkh
15FA	carkh
15FB	carkk
15FC	carkk
15FD	carkk
15FE	carkk
15FF	carkk
1600	carkk
1601	carkk
1602	carnu
1603	carno
1604	carne
1605	carne
1606	carni
1607	carna
1608	carmu
1609	carmo
160A	carme
160B	carme
160C	carmi
160D	carma
160E	caryu
160F	caryo
1610	carye
1611	carye
1612	caryi
1613	carya
1614	carju
1615	sayju
1616	carjo
1617	carje
1618	carje
1619	carji
161A	sayji
161B	carja
161C	carjj
161D	carjj
161E	carjj
161F	carjj
1620	carjj
1621	carjj
1622	carlu
1623	carlo
1624	carle
1625	carle
1626	carli
1627	carla
1628	cardl
1629	cardl
162A	cardl
162B	cardl
162C	cardl
162D	cardl
162E	carlh
162F	carlh
1630	carlh
1631	carlh
1632	carlh
1633	carlh
1634	cartl
1635	cartl
1636	cartl
1637	cartl
1638	cartl
1639	cartl
163A	cartl
163B	cartl
163C	cartl
163D	cartl
163E	cartl
163F	cartl
1640	carzu
1641	carzo
1642	carze
1643	carze
1644	carzi
1645	carza
1646	carz
1647	carin
1648	cardz
1649	cardz
164A	cardz
164B	cardz
164C	cardz
164D	cardz
164E	carsu
164F	carso
1650	carse
1651	carse
1652	carsi
1653	carsa
1654	carsh
1655	carsh
1656	carsh
1657	carsh
1658	carsh
1659	carsh
165A	carsh
165B	carts
165C	carts
165D	carts
165E	carts
165F	carts
1660	carts
1661	carch
1662	carch
1663	carch
1664	carch
1665	carch
1666	carch
1667	cartt
1668	cartt
1669	cartt
166A	cartt
166B	cartt
166C	cartt
166D	chisi
166E	fulst
166F	qai
1670	ngai
1671	nngi
1672	nngii
1673	nngo
1674	nngoo
1675	nnga
1676	nngaa
1677	wooth
1678	wooth
1679	wooth
167A	wooth
167B	wooth
167C	wooth
167D	wooth
167E	woofi
167F	blaw

# === Ogham (U+1680–U+169F) ===
# Source: Standard scholarly Ogham transliteration (Book of Ballymote)

1680	 
1681	b
1682	l
1683	f
1684	s
1685	n
1686	h
1687	d
1688	t
1689	c
168A	q
168B	m
168C	g
168D	ng
168E	st
168F	r
1690	a
1691	o
1692	u
1693	e
1694	i
1695	ea
1696	oi
1697	ui
1698	p
1699	x
169A	p
169B	>
169C	<

# === Runic (U+16A0–U+16FF) ===
# Source: Phonetic values per scholarly consensus
# Mixed Elder/Younger Futhark and Anglo-Saxon traditions

16A0	f
16A1	v
16A2	u
16A3	y
16A4	y
16A5	w
16A6	th
16A7	dh
16A8	a
16A9	o
16AA	a
16AB	ae
16AC	o
16AD	o
16AE	o
16AF	oe
16B0	o
16B1	r
16B2	k
16B3	c
16B4	k
16B5	g
16B6	ng
16B7	g
16B8	g
16B9	w
16BA	h
16BB	h
16BC	h
16BD	h
16BE	n
16BF	n
16C0	n
16C1	i
16C2	e
16C3	j
16C4	j
16C5	ae
16C6	a
16C7	ei
16C8	p
16C9	z
16CA	s
16CB	s
16CC	s
16CD	c
16CE	z
16CF	t
16D0	t
16D1	d
16D2	b
16D3	b
16D4	p
16D5	p
16D6	e
16D7	m
16D8	m
16D9	m
16DA	l
16DB	l
16DC	ng
16DD	ng
16DE	d
16DF	o
16E0	ea
16E1	io
16E2	q
16E3	k
16E4	k
16E5	st
16E6	y
16E7	y
16E8	y
16E9	q
16EA	x
16EB	.
16EC	:
16ED	+
16EE	17
16EF	18
16F0	19
16F1	k
16F2	sh
16F3	oo
16F4	o
16F5	i
16F6	e
16F7	m
16F8	ae

# === Philippine Scripts: Tagalog, Hanunoo, Buhid, Tagbanwa (U+1700–U+177F) ===
# Source: Phonetic values following Indic abugida pattern

1700	a
1701	i
1702	u
1703	ka
1704	ga
1705	nga
1706	ta
1707	da
1708	na
1709	pa
170A	ba
170B	ma
170C	ya
170D	ra
170E	la
170F	wa
1710	sa
1711	ha
1712	i
1713	u
1714	
1715	
171F	ra
1720	a
1721	i
1722	u
1723	ka
1724	ga
1725	nga
1726	ta
1727	da
1728	na
1729	pa
172A	ba
172B	ma
172C	ya
172D	ra
172E	la
172F	wa
1730	sa
1731	ha
1732	i
1733	u
1734	
1735	.
1736	.
1740	a
1741	i
1742	u
1743	ka
1744	ga
1745	nga
1746	ta
1747	da
1748	na
1749	pa
174A	ba
174B	ma
174C	ya
174D	ra
174E	la
174F	wa
1750	sa
1751	ha
1752	i
1753	u
1760	a
1761	i
1762	u
1763	ka
1764	ga
1765	nga
1766	ta
1767	da
1768	na
1769	pa
176A	ba
176B	ma
176C	ya
176E	la
176F	wa
1770	sa
1772	i
1773	u

# === Khmer (U+1780–U+17FF) ===
# Source: UNGEGN Khmer romanization (simplified)
# Two-series consonants collapse to same romanization (ASCII constraint)

1780	ka
1781	kha
1782	ka
1783	kha
1784	nga
1785	cha
1786	chha
1787	cha
1788	chha
1789	nya
178A	da
178B	ttha
178C	da
178D	ttha
178E	na
178F	ta
1790	tha
1791	ta
1792	tha
1793	na
1794	ba
1795	pha
1796	pa
1797	pha
1798	ma
1799	ya
179A	ra
179B	la
179C	va
179D	sha
179E	sha
179F	sa
17A0	ha
17A1	la
17A2	a
17A3	a
17A4	a
17A5	e
17A6	e
17A7	u
17A8	uk
17A9	u
17AA	u
17AB	ry
17AC	ry
17AD	ly
17AE	ly
17AF	e
17B0	ai
17B1	o
17B2	o
17B3	au
17B4	
17B5	
17B6	a
17B7	e
17B8	e
17B9	o
17BA	o
17BB	u
17BC	u
17BD	ua
17BE	ae
17BF	e
17C0	e
17C1	e
17C2	ae
17C3	ai
17C4	o
17C5	au
17C6	m
17C7	h
17C8	'
17C9	
17CA	
17CB	
17CC	r
17CD	
17CE	
17CF	
17D0	
17D1	
17D2	
17D3	
17D4	.
17D5	.
17D6	:
17D7	
17D8	...
17D9	.
17DA	.
17DB	KHR
17DC	'
17DD	
17E0	0
17E1	1
17E2	2
17E3	3
17E4	4
17E5	5
17E6	6
17E7	7
17E8	8
17E9	9
17F0	0
17F1	1
17F2	2
17F3	3
17F4	4
17F5	5
17F6	6
17F7	7
17F8	8
17F9	9

# === Mongolian (U+1800–U+18AF) ===
# Source: Phonetic approximation

1800	.
1801	.
1802	,
1803	:
1804	...
1805	:
1806	-
1807	.
1808	,
1809	.
180A	-
180B	
180C	
180D	
180E	
1810	0
1811	1
1812	2
1813	3
1814	4
1815	5
1816	6
1817	7
1818	8
1819	9
1820	a
1821	e
1822	i
1823	o
1824	u
1825	oe
1826	ue
1827	ee
1828	n
1829	ng
182A	b
182B	p
182C	q
182D	g
182E	m
182F	l
1830	s
1831	sh
1832	t
1833	d
1834	ch
1835	j
1836	y
1837	r
1838	w
1839	f
183A	k
183B	kh
183C	ts
183D	z
183E	h
183F	zr
1840	lh
1841	zh
1842	ch
1843	
1844	e
1845	i
1846	o
1847	u
1848	oe
1849	ue
184A	ang
184B	b
184C	p
184D	q
184E	g
184F	m
1850	t
1851	d
1852	ch
1853	j
1854	ts
1855	y
1856	w
1857	k
1858	g
1859	h
185A	j
185B	n
185C	dz
185D	e
185E	i
185F	iy
1860	ue
1861	u
1862	ang
1863	k
1864	g
1865	h
1866	p
1867	sh
1868	t
1869	d
186A	j
186B	f
186C	g
186D	h
186E	ts
186F	z
1870	r
1871	ch
1872	zh
1873	i
1874	k
1875	r
1876	f
1877	zh
1878	ch
1880	m
1881	h
1882	d
1883	u
1884	u
1885	
1886	
1887	a
1888	i
1889	ka
188A	nga
188B	ca
188C	ta
188D	tha
188E	da
188F	na
1890	ta
1891	da
1892	pa
1893	pha
1894	sha
1895	zha
1896	za
1897	ah
1898	ta
1899	zha
189A	gha
189B	nga
189C	ca
189D	jha
189E	ta
189F	dha
18A0	ta
18A1	dha
18A2	sha
18A3	cya
18A4	zha
18A5	za
18A6	u
18A7	y
18A8	bha
18A9	
18AA	lha

# === Tai Le (U+1950–U+197F) ===
# Source: Phonetic approximation

1950	ka
1951	kha
1952	ga
1953	nga
1954	tsa
1955	sa
1956	ya
1957	ta
1958	tha
1959	la
195A	pa
195B	pha
195C	ma
195D	fa
195E	va
195F	ha
1960	qa
1961	kha
1962	na
1963	a
1964	aa
1965	i
1966	e
1967	eh
1968	u
1969	aw
196A	ue
196B	o
196C	au
196D	ai
1970	
1971	
1972	
1973	
1974	

# === New Tai Lue (U+1980–U+19DF) ===
# Source: Phonetic approximation

1980	ka
1981	kha
1982	kha
1983	kha
1984	nga
1985	tsa
1986	sa
1987	sa
1988	nya
1989	ta
198A	tha
198B	tha
198C	na
198D	ba
198E	pha
198F	pha
1990	pha
1991	ma
1992	ya
1993	ra
1994	la
1995	va
1996	ha
1997	da
1998	ba
1999	a
199A	ka
199B	kha
199C	kha
199D	kha
199E	nga
199F	tsa
19A0	sa
19A1	sa
19A2	nya
19A3	ta
19A4	tha
19A5	tha
19A6	na
19A7	ba
19A8	pha
19A9	ma
19B0	aa
19B1	aa
19B2	i
19B3	i
19B4	i
19B5	ue
19B6	ue
19B7	ue
19B8	u
19B9	u
19BA	o
19BB	o
19BC	o
19BD	ai
19BE	ai
19BF	ai
19C0	ai
19C1	k
19C2	ng
19C3	n
19C4	t
19C5	p
19C6	m
19C7	y
19C8	
19C9	
19D0	0
19D1	1
19D2	2
19D3	3
19D4	4
19D5	5
19D6	6
19D7	7
19D8	8
19D9	9
19DA	1
19DE	.
19DF	.

# === Buginese/Lontara (U+1A00–U+1A1F) ===
# Source: Phonetic values of Lontara syllabary

1A00	ka
1A01	ga
1A02	nga
1A03	ngka
1A04	pa
1A05	ba
1A06	ma
1A07	mpa
1A08	ta
1A09	da
1A0A	na
1A0B	nra
1A0C	ca
1A0D	ja
1A0E	nya
1A0F	nyca
1A10	ya
1A11	ra
1A12	la
1A13	wa
1A14	sa
1A15	a
1A16	ha
1A17	i
1A18	u
1A19	e
1A1A	o
1A1B	e
1A1E	.
1A1F	.

# === Tai Tham (U+1A20–U+1AAF) ===
# Source: Phonetic approximation

1A20	ka
1A21	kha
1A22	kha
1A23	ga
1A24	gha
1A25	nga
1A26	ca
1A27	sa
1A28	cha
1A29	ja
1A2A	ha
1A2B	nya
1A2C	da
1A2D	na
1A2E	da
1A2F	tha
1A30	tha
1A31	da
1A32	dha
1A33	na
1A34	ba
1A35	pa
1A36	pha
1A37	fa
1A38	pha
1A39	ba
1A3A	bha
1A3B	ma
1A3C	ya
1A3D	ra
1A3E	la
1A3F	wa
1A40	sa
1A41	ha
1A42	la
1A43	a
1A44	ha
1A45	a
1A46	sa
1A47	sa
1A48	ha
1A49	ha
1A4A	la
1A4B	a
1A4C	a
1A4D	ka
1A4E	kha
1A4F	kha
1A50	ga
1A51	nga
1A52	ca
1A53	sa
1A54	i
1A55	a
1A56	a
1A57	
1A58	
1A59	
1A5A	
1A5B	
1A5C	
1A5D	
1A5E	
1A60	
1A61	i
1A62	i
1A63	aa
1A64	aa
1A65	i
1A66	ii
1A67	u
1A68	uu
1A69	u
1A6A	uu
1A6B	o
1A6C	oa
1A6D	oy
1A6E	e
1A6F	ae
1A70	o
1A71	ai
1A72	ao
1A73	
1A74	
1A75	
1A76	
1A77	
1A78	
1A79	
1A7A	
1A7B	
1A7C	
1A7F	
1A80	0
1A81	1
1A82	2
1A83	3
1A84	4
1A85	5
1A86	6
1A87	7
1A88	8
1A89	9
1A90	0
1A91	1
1A92	2
1A93	3
1A94	4
1A95	5
1A96	6
1A97	7
1A98	8
1A99	9
1AA0	.
1AA1	.
1AA2	.
1AA3	.
1AA4	.
1AA5	.
1AA6	
1AA7	
1AA8	.
1AA9	.
1AAA	.
1AAB	.
1AAC	
1AAD	

# === Balinese (U+1B00–U+1B7F) ===
# Source: Phonetic values following Indic abugida pattern


# === Combining Diacritical Marks Extended (U+1AB0–U+1AFF) ===
# Source: Strip combining marks (same rationale as U+0300–U+036F)

1AB0	
1AB1	
1AB2	
1AB3	
1AB4	
1AB5	
1AB6	
1AB7	
1AB8	
1AB9	
1ABA	
1ABB	
1ABC	
1ABD	
1ABE	
1ABF	
1AC0	
1AC1	
1AC2	
1AC3	
1AC4	
1AC5	
1AC6	
1AC7	
1AC8	
1AC9	
1ACA	
1ACB	
1ACC	
1ACD	
1ACE	
1B00	
1B01	
1B02	
1B03	
1B04	
1B05	a
1B06	aa
1B07	i
1B08	ii
1B09	u
1B0A	uu
1B0B	r
1B0C	r
1B0D	l
1B0E	l
1B0F	e
1B10	ai
1B11	o
1B12	au
1B13	ka
1B14	kha
1B15	ga
1B16	gha
1B17	nga
1B18	cha
1B19	chha
1B1A	ja
1B1B	jha
1B1C	nya
1B1D	tta
1B1E	ttha
1B1F	dda
1B20	ddha
1B21	nna
1B22	ta
1B23	tha
1B24	da
1B25	dha
1B26	na
1B27	pa
1B28	pha
1B29	ba
1B2A	bha
1B2B	ma
1B2C	ya
1B2D	ra
1B2E	la
1B2F	wa
1B30	sha
1B31	ssa
1B32	sa
1B33	ha
1B35	aa
1B36	i
1B37	ii
1B38	u
1B39	uu
1B3A	r
1B3B	r
1B3C	l
1B3D	l
1B3E	e
1B3F	ai
1B40	o
1B41	au
1B42	
1B43	
1B44	
1B45	ka
1B46	sa
1B47	ta
1B48	na
1B49	pa
1B4A	da
1B4B	ra
1B50	0
1B51	1
1B52	2
1B53	3
1B54	4
1B55	5
1B56	6
1B57	7
1B58	8
1B59	9
1B5A	.
1B5B	.
1B5C	.
1B5D	,
1B5E	.
1B5F	.
1B60	
1B61	0
1B62	1
1B63	2
1B64	3
1B65	4
1B66	5
1B67	6
1B68	7
1B69	8
1B6A	9
1B6B	
1B6C	
1B6D	
1B6E	
1B6F	
1B70	
1B71	
1B72	
1B73	
1B74	
1B75	
1B76	
1B77	
1B78	
1B79	
1B7A	
1B7B	
1B7C	

# === Sundanese (U+1B80–U+1BBF) ===
# Source: Phonetic values following Indic abugida pattern

1B80	
1B81	
1B82	
1B83	a
1B84	i
1B85	u
1B86	ae
1B87	o
1B88	e
1B89	eu
1B8A	ka
1B8B	qa
1B8C	ga
1B8D	nga
1B8E	ca
1B8F	ja
1B90	za
1B91	nya
1B92	ta
1B93	da
1B94	na
1B95	pa
1B96	fa
1B97	ba
1B98	ma
1B99	ya
1B9A	ra
1B9B	la
1B9C	wa
1B9D	sa
1B9E	ha
1B9F	sa
1BA0	xa
1BA1	i
1BA2	u
1BA3	eu
1BA4	i
1BA5	u
1BA6	e
1BA7	o
1BA8	
1BA9	
1BAA	r
1BAB	
1BAC	
1BAD	
1BB0	0
1BB1	1
1BB2	2
1BB3	3
1BB4	4
1BB5	5
1BB6	6
1BB7	7
1BB8	8
1BB9	9
1BBA	
1BBB	
1BBC	
1BBD	
1BBE	
1BBF	

# === Batak (U+1BC0–U+1BFF) ===
# Source: Phonetic values following Indic abugida pattern

1BC0	a
1BC1	ha
1BC2	ha
1BC3	ba
1BC4	ba
1BC5	pa
1BC6	pa
1BC7	na
1BC8	na
1BC9	na
1BCA	wa
1BCB	wa
1BCC	ga
1BCD	ga
1BCE	ja
1BCF	da
1BD0	da
1BD1	ra
1BD2	ra
1BD3	ma
1BD4	ma
1BD5	ta
1BD6	ta
1BD7	sa
1BD8	sa
1BD9	sa
1BDA	ya
1BDB	ya
1BDC	nga
1BDD	nga
1BDE	la
1BDF	la
1BE0	la
1BE1	la
1BE2	ca
1BE3	ca
1BE4	i
1BE5	u
1BE6	
1BE7	e
1BE8	i
1BE9	i
1BEA	u
1BEB	u
1BEC	u
1BED	o
1BEE	e
1BEF	
1BF0	
1BF1	
1BF2	
1BF3	
1BFC	.
1BFD	.
1BFE	.
1BFF	.

# === Ol Chiki (U+1C50–U+1C7F) ===
# Source: Santali phonetic values

1C50	0
1C51	1
1C52	2
1C53	3
1C54	4
1C55	5
1C56	6
1C57	7
1C58	8
1C59	9
1C5A	la
1C5B	at
1C5C	ag
1C5D	ang
1C5E	al
1C5F	laa
1C60	aak
1C61	aaj
1C62	aam
1C63	aaw
1C64	li
1C65	is
1C66	ih
1C67	iny
1C68	ir
1C69	lu
1C6A	uc
1C6B	ud
1C6C	unn
1C6D	unny
1C6E	le
1C6F	ep
1C70	edd
1C71	en
1C72	err
1C73	lo
1C74	ott
1C75	ob
1C76	ov
1C77	oh
1C78	
1C79	
1C7A	
1C7B	
1C7C	
1C7D	ah
1C7E	.
1C7F	.

# === Georgian Extended (U+1C90–U+1CBF) ===
# Source: BGN/PCGN Georgian (Mtavruli uppercase forms)

1C90	A
1C91	B
1C92	G
1C93	D
1C94	E
1C95	V
1C96	Z
1C97	T
1C98	I
1C99	K
1C9A	L
1C9B	M
1C9C	N
1C9D	O
1C9E	P
1C9F	Zh
1CA0	R
1CA1	S
1CA2	T
1CA3	U
1CA4	P
1CA5	K
1CA6	Gh
1CA7	Q
1CA8	Sh
1CA9	Ch
1CAA	Ts
1CAB	Dz
1CAC	Ts
1CAD	Ch
1CAE	Kh
1CAF	J
1CB0	H

# === Latin Extended Additional (U+1E00–U+1EFF) ===
# Source: Unicode NFKD decomposition (99.6% match)
# Exception: U+1E9E CAPITAL SHARP S → SS (no NFKD exists)


# === Combining Diacritical Marks Supplement (U+1DC0–U+1DFF) ===
# Source: Strip combining marks (same rationale as U+0300–U+036F)

1DC0	
1DC1	
1DC2	
1DC3	
1DC4	
1DC5	
1DC6	
1DC7	
1DC8	
1DC9	
1DCA	
1DCB	
1DCC	
1DCD	
1DCE	
1DCF	
1DD0	
1DD1	
1DD2	
1DD3	
1DD4	
1DD5	
1DD6	
1DD7	
1DD8	
1DD9	
1DDA	
1DDB	
1DDC	
1DDD	
1DDE	
1DDF	
1DE0	
1DE1	
1DE2	
1DE3	
1DE4	
1DE5	
1DE6	
1DE7	
1DE8	
1DE9	
1DEA	
1DEB	
1DEC	
1DED	
1DEE	
1DEF	
1DF0	
1DF1	
1DF2	
1DF3	
1DF4	
1DF5	
1DF6	
1DF7	
1DF8	
1DF9	
1DFA	
1DFB	
1DFC	
1DFD	
1DFE	
1DFF	
1E00	A
1E01	a
1E02	B
1E03	b
1E04	B
1E05	b
1E06	B
1E07	b
1E08	C
1E09	c
1E0A	D
1E0B	d
1E0C	D
1E0D	d
1E0E	D
1E0F	d
1E10	D
1E11	d
1E12	D
1E13	d
1E14	E
1E15	e
1E16	E
1E17	e
1E18	E
1E19	e
1E1A	E
1E1B	e
1E1C	E
1E1D	e
1E1E	F
1E1F	f
1E20	G
1E21	g
1E22	H
1E23	h
1E24	H
1E25	h
1E26	H
1E27	h
1E28	H
1E29	h
1E2A	H
1E2B	h
1E2C	I
1E2D	i
1E2E	I
1E2F	i
1E30	K
1E31	k
1E32	K
1E33	k
1E34	K
1E35	k
1E36	L
1E37	l
1E38	L
1E39	l
1E3A	L
1E3B	l
1E3C	L
1E3D	l
1E3E	M
1E3F	m
1E40	M
1E41	m
1E42	M
1E43	m
1E44	N
1E45	n
1E46	N
1E47	n
1E48	N
1E49	n
1E4A	N
1E4B	n
1E4C	O
1E4D	o
1E4E	O
1E4F	o
1E50	O
1E51	o
1E52	O
1E53	o
1E54	P
1E55	p
1E56	P
1E57	p
1E58	R
1E59	r
1E5A	R
1E5B	r
1E5C	R
1E5D	r
1E5E	R
1E5F	r
1E60	S
1E61	s
1E62	S
1E63	s
1E64	S
1E65	s
1E66	S
1E67	s
1E68	S
1E69	s
1E6A	T
1E6B	t
1E6C	T
1E6D	t
1E6E	T
1E6F	t
1E70	T
1E71	t
1E72	U
1E73	u
1E74	U
1E75	u
1E76	U
1E77	u
1E78	U
1E79	u
1E7A	U
1E7B	u
1E7C	V
1E7D	v
1E7E	V
1E7F	v
1E80	W
1E81	w
1E82	W
1E83	w
1E84	W
1E85	w
1E86	W
1E87	w
1E88	W
1E89	w
1E8A	X
1E8B	x
1E8C	X
1E8D	x
1E8E	Y
1E8F	y
1E90	Z
1E91	z
1E92	Z
1E93	z
1E94	Z
1E95	z
1E96	h
1E97	t
1E98	w
1E99	y
1E9A	a
1E9B	s
1E9E	SS
1EA0	A
1EA1	a
1EA2	A
1EA3	a
1EA4	A
1EA5	a
1EA6	A
1EA7	a
1EA8	A
1EA9	a
1EAA	A
1EAB	a
1EAC	A
1EAD	a
1EAE	A
1EAF	a
1EB0	A
1EB1	a
1EB2	A
1EB3	a
1EB4	A
1EB5	a
1EB6	A
1EB7	a
1EB8	E
1EB9	e
1EBA	E
1EBB	e
1EBC	E
1EBD	e
1EBE	E
1EBF	e
1EC0	E
1EC1	e
1EC2	E
1EC3	e
1EC4	E
1EC5	e
1EC6	E
1EC7	e
1EC8	I
1EC9	i
1ECA	I
1ECB	i
1ECC	O
1ECD	o
1ECE	O
1ECF	o
1ED0	O
1ED1	o
1ED2	O
1ED3	o
1ED4	O
1ED5	o
1ED6	O
1ED7	o
1ED8	O
1ED9	o
1EDA	O
1EDB	o
1EDC	O
1EDD	o
1EDE	O
1EDF	o
1EE0	O
1EE1	o
1EE2	O
1EE3	o
1EE4	U
1EE5	u
1EE6	U
1EE7	u
1EE8	U
1EE9	u
1EEA	U
1EEB	u
1EEC	U
1EED	u
1EEE	U
1EEF	u
1EF0	U
1EF1	u
1EF2	Y
1EF3	y
1EF4	Y
1EF5	y
1EF6	Y
1EF7	y
1EF8	Y
1EF9	y

# === Greek Extended (U+1F00–U+1FFF) ===
# Source: NFKD decomposition to base Greek + default Greek table mappings

1F00	a
1F01	a
1F02	a
1F03	a
1F04	a
1F05	a
1F06	a
1F07	a
1F08	A
1F09	A
1F0A	A
1F0B	A
1F0C	A
1F0D	A
1F0E	A
1F0F	A
1F10	e
1F11	e
1F12	e
1F13	e
1F14	e
1F15	e
1F18	E
1F19	E
1F1A	E
1F1B	E
1F1C	E
1F1D	E
1F20	i
1F21	i
1F22	i
1F23	i
1F24	i
1F25	i
1F26	i
1F27	i
1F28	I
1F29	I
1F2A	I
1F2B	I
1F2C	I
1F2D	I
1F2E	I
1F2F	I
1F30	i
1F31	i
1F32	i
1F33	i
1F34	i
1F35	i
1F36	i
1F37	i
1F38	I
1F39	I
1F3A	I
1F3B	I
1F3C	I
1F3D	I
1F3E	I
1F3F	I
1F40	o
1F41	o
1F42	o
1F43	o
1F44	o
1F45	o
1F48	O
1F49	O
1F4A	O
1F4B	O
1F4C	O
1F4D	O
1F50	y
1F51	y
1F52	y
1F53	y
1F54	y
1F55	y
1F56	y
1F57	y
1F59	Y
1F5B	Y
1F5D	Y
1F5F	Y
1F60	o
1F61	o
1F62	o
1F63	o
1F64	o
1F65	o
1F66	o
1F67	o
1F68	O
1F69	O
1F6A	O
1F6B	O
1F6C	O
1F6D	O
1F6E	O
1F6F	O
1F70	a
1F71	a
1F72	e
1F73	e
1F74	i
1F75	i
1F76	i
1F77	i
1F78	o
1F79	o
1F7A	y
1F7B	y
1F7C	o
1F7D	o
1F80	ai
1F81	ai
1F82	ai
1F83	ai
1F84	ai
1F85	ai
1F86	ai
1F87	ai
1F88	Ai
1F89	Ai
1F8A	Ai
1F8B	Ai
1F8C	Ai
1F8D	Ai
1F8E	Ai
1F8F	Ai
1F90	ii
1F91	ii
1F92	ii
1F93	ii
1F94	ii
1F95	ii
1F96	ii
1F97	ii
1F98	Ii
1F99	Ii
1F9A	Ii
1F9B	Ii
1F9C	Ii
1F9D	Ii
1F9E	Ii
1F9F	Ii
1FA0	oi
1FA1	oi
1FA2	oi
1FA3	oi
1FA4	oi
1FA5	oi
1FA6	oi
1FA7	oi
1FA8	Oi
1FA9	Oi
1FAA	Oi
1FAB	Oi
1FAC	Oi
1FAD	Oi
1FAE	Oi
1FAF	Oi
1FB0	a
1FB1	a
1FB2	ai
1FB3	ai
1FB4	ai
1FB6	a
1FB7	ai
1FB8	A
1FB9	A
1FBA	A
1FBB	A
1FBC	Ai
1FBF	ps
1FC2	ii
1FC3	ii
1FC4	ii
1FC6	i
1FC7	ii
1FC8	E
1FC9	E
1FCA	I
1FCB	I
1FCC	Ii
1FCD	ps
1FCE	x
1FCF	ps
1FD0	i
1FD1	i
1FD2	i
1FD3	i
1FD6	i
1FD7	i
1FD8	I
1FD9	I
1FDA	I
1FDB	I
1FDE	x
1FE0	y
1FE1	y
1FE2	y
1FE3	y
1FE4	r
1FE5	r
1FE6	y
1FE7	y
1FE8	Y
1FE9	Y
1FEA	Y
1FEB	Y
1FEC	R
1FEE	x
1FF2	oi
1FF3	oi
1FF4	oi
1FF6	o
1FF7	oi
1FF8	O
1FF9	O
1FFA	O
1FFB	O
1FFC	Oi
1FFD	x

# === General Punctuation (U+2000–U+206F) ===
# Source: Functional ASCII equivalents


# === Zero-width and invisible formatting (U+200B–U+200F, U+2028–U+202E, U+2060–U+2069) ===
# Source: Strip invisible characters — zero-width spaces, joiners,
# directional marks, and line/paragraph separators

200B	
200C	
200D	
200E	
200F	
2013	-
2014	-
2015	-
2018	'
2019	'
201A	,
201B	'
201C	\"
201D	\"
201E	\"
2020	+
2021	++
2022	*
2026	...
2027	.
2028	
2029	
202A	
202B	
202C	
202D	
202E	
2030	o/oo
2039	<
203A	>
2044	/

# === Superscripts and Subscripts (U+2070–U+209F) ===
# Source: Base digit/letter extraction

2060	
2061	
2062	
2063	
2064	
2066	
2067	
2068	
2069	
2070	0
2071	i
2074	4
2075	5
2076	6
2077	7
2078	8
2079	9
207A	+
207B	-
207C	=
207D	(
207E	)
207F	n
2080	0
2081	1
2082	2
2083	3
2084	4
2085	5
2086	6
2087	7
2088	8
2089	9
208A	+
208B	-
208C	=
208D	(
208E	)

# === Currency Symbols (U+20A0–U+20CF) ===
# Source: ISO 4217 codes or conventional abbreviations

20A3	Fr
20A4	L
20A7	Pts
20A8	Rs
20A9	W
20AB	d
20AC	EUR
20B1	P
20B4	UAH
20B9	Rs
20BA	TL
20BD	RUB
20BF	BTC

# === Letterlike Symbols (U+2100–U+214F) ===
# Source: Conventional expansion


# === Combining Diacritical Marks for Symbols (U+20D0–U+20F0) ===
# Source: Strip combining marks on symbols

20D0	
20D1	
20D2	
20D3	
20D4	
20D5	
20D6	
20D7	
20D8	
20D9	
20DA	
20DB	
20DC	
20DD	
20DE	
20DF	
20E0	
20E1	
20E2	
20E3	
20E4	
20E5	
20E6	
20E7	
20E8	
20E9	
20EA	
20EB	
20EC	
20ED	
20EE	
20EF	
20F0	
2122	TM

# === Number Forms (U+2150–U+218F) ===
# Source: Numeric expansion (fractions, Roman numerals)

2150	1/7
2151	1/9
2152	1/10
2153	1/3
2154	2/3
2155	1/5
2156	2/5
2157	3/5
2158	4/5
2159	1/6
215A	5/6
215B	1/8
215C	3/8
215D	5/8
215E	7/8
2160	I
2161	II
2162	III
2163	IV
2164	V
2165	VI
2166	VII
2167	VIII
2168	IX
2169	X
216A	XI
216B	XII
216C	L
216D	C
216E	D
216F	M
2170	i
2171	ii
2172	iii
2173	iv
2174	v
2175	vi
2176	vii
2177	viii
2178	ix
2179	x
217A	xi
217B	xii
217C	l
217D	c
217E	d
217F	m
2180	1000
2181	5000
2182	10000
2183	C
2184	c
2185	6
2186	50
2187	50000
2188	100000

# === Enclosed Alphanumerics (U+2460–U+24FF) ===
# Source: Enclosed digit/letter extraction

2460	1
2461	2
2462	3
2463	4
2464	5
2465	6
2466	7
2467	8
2468	9
2469	10
246A	11
246B	12
246C	13
246D	14
246E	15
246F	16
2470	17
2471	18
2472	19
2473	20
2474	(1)
2475	(2)
2476	(3)
2477	(4)
2478	(5)
2479	(6)
247A	(7)
247B	(8)
247C	(9)
247D	(10)
247E	(11)
247F	(12)
2480	(13)
2481	(14)
2482	(15)
2483	(16)
2484	(17)
2485	(18)
2486	(19)
2487	(20)
2488	1.
2489	2.
248A	3.
248B	4.
248C	5.
248D	6.
248E	7.
248F	8.
2490	9.
2491	10.
2492	11.
2493	12.
2494	13.
2495	14.
2496	15.
2497	16.
2498	17.
2499	18.
249A	19.
249B	20.
24B6	A
24B7	B
24B8	C
24B9	D
24BA	E
24BB	F
24BC	G
24BD	H
24BE	I
24BF	J
24C0	K
24C1	L
24C2	M
24C3	N
24C4	O
24C5	P
24C6	Q
24C7	R
24C8	S
24C9	T
24CA	U
24CB	V
24CC	W
24CD	X
24CE	Y
24CF	Z
24D0	a
24D1	b
24D2	c
24D3	d
24D4	e
24D5	f
24D6	g
24D7	h
24D8	i
24D9	j
24DA	k
24DB	l
24DC	m
24DD	n
24DE	o
24DF	p
24E0	q
24E1	r
24E2	s
24E3	t
24E4	u
24E5	v
24E6	w
24E7	x
24E8	y
24E9	z
24EA	0
24EB	11
24EC	12
24ED	13
24EE	14
24EF	15
24F0	16
24F1	17
24F2	18
24F3	19
24F4	20
24F5	1
24F6	2
24F7	3
24F8	4
24F9	5
24FA	6
24FB	7
24FC	8
24FD	9
24FE	10
24FF	0

# === Coptic (U+2C80–U+2CFF) ===
# Source: Coptic scholarly convention

2C80	a
2C81	a
2C82	b
2C83	b
2C84	g
2C85	g
2C86	d
2C87	d
2C88	e
2C89	e
2C8A	so
2C8B	so
2C8C	z
2C8D	z
2C8E	e
2C8F	e
2C90	th
2C91	th
2C92	i
2C93	i
2C94	k
2C95	k
2C96	l
2C97	l
2C98	m
2C99	m
2C9A	n
2C9B	n
2C9C	ks
2C9D	ks
2C9E	o
2C9F	o
2CA0	p
2CA1	p
2CA2	r
2CA3	r
2CA4	s
2CA5	s
2CA6	t
2CA7	t
2CA8	u
2CA9	u
2CAA	ph
2CAB	ph
2CAC	kh
2CAD	kh
2CAE	ps
2CAF	ps
2CB0	o
2CB1	o
2CB2	sh
2CB3	sh
2CB4	f
2CB5	f
2CB6	h
2CB7	h
2CB8	j
2CB9	j
2CBA	c
2CBB	c
2CBC	ti
2CBD	ti
2CBE	
2CBF	
2CC0	sh
2CC1	sh
2CC2	f
2CC3	f
2CC4	kh
2CC5	kh
2CC6	h
2CC7	h
2CC8	j
2CC9	j
2CCA	c
2CCB	c
2CCC	ti
2CCD	ti
2CCE	k
2CCF	k
2CD0	g
2CD1	g
2CD2	s
2CD3	s
2CD4	t
2CD5	t
2CD6	sh
2CD7	sh
2CD8	ch
2CD9	ch
2CDA	a
2CDB	a
2CDC	i
2CDD	i
2CDE	kh
2CDF	kh
2CE0	sh
2CE1	sh
2CE2	r
2CE3	r
2CE4	
2CE5	
2CE6	
2CE7	
2CE8	
2CE9	
2CEA	
2CEB	j
2CEC	j
2CED	sh
2CEE	sh
2CEF	
2CF0	
2CF1	
2CF2	
2CF3	

# === Georgian Supplement (U+2D00–U+2D2F) ===
# Source: BGN/PCGN Georgian (Nuskhuri lowercase forms)

2D00	a
2D01	b
2D02	g
2D03	d
2D04	e
2D05	v
2D06	z
2D07	t
2D08	i
2D09	k
2D0A	l
2D0B	m
2D0C	n
2D0D	o
2D0E	p
2D0F	zh
2D10	r
2D11	s
2D12	t
2D13	u
2D14	p
2D15	k
2D16	gh
2D17	q
2D18	sh
2D19	ch
2D1A	ts
2D1B	dz
2D1C	ts
2D1D	ch
2D1E	kh
2D1F	j
2D20	h
2D21	he
2D22	hi
2D23	w
2D24	har
2D25	ho
2D27	yn
2D2D	ae

# === Tifinagh (U+2D30–U+2D7F) ===
# Source: IRCAM phonetic values for Neo-Tifinagh

2D30	a
2D31	b
2D32	bh
2D33	g
2D34	ghh
2D35	j
2D36	j
2D37	d
2D38	dh
2D39	dd
2D3A	ddh
2D3B	ey
2D3C	f
2D3D	k
2D3E	k
2D3F	khh
2D40	h
2D41	h
2D42	h
2D43	hh
2D44	a
2D45	kh
2D46	kh
2D47	q
2D48	q
2D49	i
2D4A	zh
2D4B	zh
2D4C	zh
2D4D	l
2D4E	m
2D4F	n
2D50	gn
2D51	ng
2D52	p
2D53	u
2D54	r
2D55	rr
2D56	gh
2D57	gh
2D58	gh
2D59	s
2D5A	ss
2D5B	sh
2D5C	t
2D5D	th
2D5E	ch
2D5F	tt
2D60	v
2D61	w
2D62	y
2D63	z
2D64	z
2D65	zz
2D66	e
2D67	o
2D6F	+
2D70	.
2D7F	

# === Ethiopic Supplement (U+2D80–U+2DDF) ===
# Source: BGN/PCGN Amharic conventions (extended)

2D80	loa
2D81	moa
2D82	roa
2D83	soa
2D84	shoa
2D85	boa
2D86	toa
2D87	choa
2D88	noa
2D89	nyoa
2D8A	oa
2D8B	zoa
2D8C	doa
2D8D	ddoa
2D8E	joa
2D8F	toa
2D90	choa
2D91	poa
2D92	poa
2D93	ggwa
2D94	ggwi
2D95	ggwe
2D96	ggwe
2DA0	sse
2DA1	ssu
2DA2	ssi
2DA3	ssa
2DA4	sse
2DA5	ss
2DA6	sso
2DA8	che
2DA9	chu
2DAA	chi
2DAB	cha
2DAC	che
2DAD	ch
2DAE	cho
2DB0	zze
2DB1	zzu
2DB2	zzi
2DB3	zza
2DB4	zze
2DB5	zz
2DB6	zzo
2DB8	chche
2DB9	chchu
2DBA	chchi
2DBB	chcha
2DBC	chche
2DBD	chch
2DBE	chcho
2DC0	qye
2DC1	qyu
2DC2	qyi
2DC3	qya
2DC4	qye
2DC5	qy
2DC6	qyo
2DC8	kye
2DC9	kyu
2DCA	kyi
2DCB	kya
2DCC	kye
2DCD	ky
2DCE	kyo
2DD0	xye
2DD1	xyu
2DD2	xyi
2DD3	xya
2DD4	xye
2DD5	xy
2DD6	xyo
2DD8	gye
2DD9	gyu
2DDA	gyi
2DDB	gya
2DDC	gye
2DDD	gy
2DDE	gyo

# === Kangxi Radicals (U+2F00–U+2FDF) ===
# Source: Unicode Unihan kMandarin (radical-to-ideograph mapping)

2F00	yi
2F01	gun
2F02	zhu
2F03	pie
2F04	yi
2F05	jue
2F06	er
2F07	tou
2F08	ren
2F09	er
2F0A	ru
2F0B	ba
2F0C	jiong
2F0D	mi
2F0E	bing
2F0F	ji
2F10	qian
2F11	dao
2F12	li
2F13	bao
2F14	bi
2F15	fang
2F16	xi
2F17	shi
2F18	bo
2F19	jie
2F1A	chang
2F1B	si
2F1C	you
2F1D	kou
2F1E	wei
2F1F	tu
2F20	shi
2F21	zhi
2F22	sui
2F23	xi
2F24	da
2F25	nu
2F26	zi
2F27	mian
2F28	cun
2F29	xiao
2F2A	wang
2F2B	shi
2F2C	che
2F2D	shan
2F2E	chuan
2F2F	gong
2F30	ji
2F31	jin
2F32	gan
2F33	yao
2F34	guang
2F35	yin
2F36	gong
2F37	yi
2F38	gong
2F39	ji
2F3A	shan
2F3B	chi
2F3C	xin
2F3D	ge
2F3E	hu
2F3F	shou
2F40	zhi
2F41	pu
2F42	wen
2F43	dou
2F44	jin
2F45	fang
2F46	wu
2F47	ri
2F48	yue
2F49	yue
2F4A	mu
2F4B	qian
2F4C	zhi
2F4D	dai
2F4E	shu
2F4F	wu
2F50	bi
2F51	mao
2F52	shi
2F53	qi
2F54	shui
2F55	huo
2F56	zhao
2F57	fu
2F58	yao
2F59	pan
2F5A	pian
2F5B	ya
2F5C	niu
2F5D	quan
2F5E	xuan
2F5F	yu
2F60	gua
2F61	wa
2F62	gan
2F63	sheng
2F64	yong
2F65	tian
2F66	pi
2F67	ne
2F68	bo
2F69	bai
2F6A	pi
2F6B	min
2F6C	mu
2F6D	mao
2F6E	shi
2F6F	shi
2F70	shi
2F71	rou
2F72	he
2F73	xue
2F74	li
2F75	zhu
2F76	mi
2F77	mi
2F78	fou
2F79	wang
2F7A	yang
2F7B	yu
2F7C	lao
2F7D	er
2F7E	lei
2F7F	er
2F80	yu
2F81	rou
2F82	chen
2F83	zi
2F84	zhi
2F85	jiu
2F86	she
2F87	chuan
2F88	zhou
2F89	gen
2F8A	se
2F8B	cao
2F8C	hu
2F8D	chong
2F8E	xue
2F8F	xing
2F90	yi
2F91	ya
2F92	jian
2F93	jiao
2F94	yan
2F95	gu
2F96	dou
2F97	shi
2F98	zhi
2F99	bei
2F9A	chi
2F9B	zou
2F9C	zu
2F9D	shen
2F9E	che
2F9F	xin
2FA0	chen
2FA1	chuo
2FA2	yi
2FA3	you
2FA4	bian
2FA5	li
2FA6	jin
2FA7	zhang
2FA8	men
2FA9	fu
2FAA	li
2FAB	zhui
2FAC	yu
2FAD	qing
2FAE	fei
2FAF	mian
2FB0	ge
2FB1	wei
2FB2	jiu
2FB3	yin
2FB4	ye
2FB5	feng
2FB6	fei
2FB7	shi
2FB8	shou
2FB9	xiang
2FBA	ma
2FBB	gu
2FBC	gao
2FBD	biao
2FBE	dou
2FBF	chang
2FC0	ge
2FC1	gui
2FC2	yu
2FC3	niao
2FC4	lu
2FC5	lu
2FC6	mai
2FC7	ma
2FC8	huang
2FC9	shu
2FCA	hei
2FCB	zhi
2FCC	mian
2FCD	ding
2FCE	gu
2FCF	shu
2FD0	bi
2FD1	qi
2FD2	chi
2FD3	long
2FD4	gui
2FD5	yue

# === Hiragana (U+3040–U+309F) ===
# Source: Modified Hepburn romanization

3041	a
3042	a
3043	i
3044	i
3045	u
3046	u
3047	e
3048	e
3049	o
304A	o
304B	ka
304C	ga
304D	ki
304E	gi
304F	ku
3050	gu
3051	ke
3052	ge
3053	ko
3054	go
3055	sa
3056	za
3057	shi
3058	ji
3059	su
305A	zu
305B	se
305C	ze
305D	so
305E	zo
305F	ta
3060	da
3061	chi
3062	di
3063	tsu
3064	tsu
3065	du
3066	te
3067	de
3068	to
3069	do
306A	na
306B	ni
306C	nu
306D	ne
306E	no
306F	ha
3070	ba
3071	pa
3072	hi
3073	bi
3074	pi
3075	fu
3076	bu
3077	pu
3078	he
3079	be
307A	pe
307B	ho
307C	bo
307D	po
307E	ma
307F	mi
3080	mu
3081	me
3082	mo
3083	ya
3084	ya
3085	yu
3086	yu
3087	yo
3088	yo
3089	ra
308A	ri
308B	ru
308C	re
308D	ro
308E	wa
308F	wa
3090	wi
3091	we
3092	wo
3093	n
3094	vu
3095	ka
3096	ke
3099	
309A	
309B	
309C	
309D	
309E	
309F	yori

# === Katakana (U+30A0–U+30FF) ===
# Source: Modified Hepburn romanization

30A0	=
30A1	a
30A2	a
30A3	i
30A4	i
30A5	u
30A6	u
30A7	e
30A8	e
30A9	o
30AA	o
30AB	ka
30AC	ga
30AD	ki
30AE	gi
30AF	ku
30B0	gu
30B1	ke
30B2	ge
30B3	ko
30B4	go
30B5	sa
30B6	za
30B7	shi
30B8	ji
30B9	su
30BA	zu
30BB	se
30BC	ze
30BD	so
30BE	zo
30BF	ta
30C0	da
30C1	chi
30C2	di
30C3	tsu
30C4	tsu
30C5	du
30C6	te
30C7	de
30C8	to
30C9	do
30CA	na
30CB	ni
30CC	nu
30CD	ne
30CE	no
30CF	ha
30D0	ba
30D1	pa
30D2	hi
30D3	bi
30D4	pi
30D5	fu
30D6	bu
30D7	pu
30D8	he
30D9	be
30DA	pe
30DB	ho
30DC	bo
30DD	po
30DE	ma
30DF	mi
30E0	mu
30E1	me
30E2	mo
30E3	ya
30E4	ya
30E5	yu
30E6	yu
30E7	yo
30E8	yo
30E9	ra
30EA	ri
30EB	ru
30EC	re
30ED	ro
30EE	wa
30EF	wa
30F0	wi
30F1	we
30F2	wo
30F3	n
30F4	vu
30F5	ka
30F6	ke
30F7	va
30F8	vi
30F9	ve
30FA	vo
30FB	 
30FC	-
30FD	
30FE	
30FF	koto

# === Lisu (U+A4D0–U+A4FF) ===
# Source: Phonetic values of Fraser script

A4D0	ba
A4D1	pa
A4D2	pha
A4D3	da
A4D4	ta
A4D5	tha
A4D6	ga
A4D7	ka
A4D8	kha
A4D9	ja
A4DA	ca
A4DB	cha
A4DC	dza
A4DD	tsa
A4DE	tsha
A4DF	ma
A4E0	na
A4E1	la
A4E2	sa
A4E3	zha
A4E4	za
A4E5	nga
A4E6	ha
A4E7	xa
A4E8	hha
A4E9	fa
A4EA	wa
A4EB	sha
A4EC	ya
A4ED	gha
A4EE	a
A4EF	ae
A4F0	e
A4F1	eu
A4F2	i
A4F3	o
A4F4	u
A4F5	ue
A4F6	uh
A4F7	oe
A4F8	.
A4F9	-
A4FA	:
A4FB	.
A4FC	.
A4FD	.
A4FE	.
A4FF	.

# === Vai (U+A500–U+A62B) ===
# Source: Phonetic values of Vai syllabary

A500	ee
A501	een
A502	hee
A503	wee
A504	ween
A505	pee
A506	bhee
A507	bee
A508	mbee
A509	kpee
A50A	mgbee
A50B	gbee
A50C	fee
A50D	vee
A50E	tee
A50F	thee
A510	dhee
A511	dhhee
A512	lee
A513	ree
A514	dee
A515	ndee
A516	see
A517	shee
A518	zee
A519	zhee
A51A	cee
A51B	jee
A51C	njee
A51D	yee
A51E	kee
A51F	nggee
A520	gee
A521	mee
A522	nee
A523	nyee
A524	i
A525	in
A526	hi
A527	hin
A528	wi
A529	win
A52A	pi
A52B	bhi
A52C	bi
A52D	mbi
A52E	kpi
A52F	mgbi
A530	gbi
A531	fi
A532	vi
A533	ti
A534	thi
A535	dhi
A536	dhhi
A537	li
A538	ri
A539	di
A53A	ndi
A53B	si
A53C	shi
A53D	zi
A53E	zhi
A53F	ci
A540	ji
A541	nji
A542	yi
A543	ki
A544	nggi
A545	gi
A546	mi
A547	ni
A548	nyi
A549	a
A54A	an
A54B	ngan
A54C	ha
A54D	han
A54E	wa
A54F	wan
A550	pa
A551	bha
A552	ba
A553	mba
A554	kpa
A555	kpan
A556	mgba
A557	gba
A558	fa
A559	va
A55A	ta
A55B	tha
A55C	dha
A55D	dhha
A55E	la
A55F	ra
A560	da
A561	nda
A562	sa
A563	sha
A564	za
A565	zha
A566	ca
A567	ja
A568	nja
A569	ya
A56A	ka
A56B	kan
A56C	ngga
A56D	ga
A56E	ma
A56F	na
A570	nya
A571	oo
A572	oon
A573	hoo
A574	woo
A575	woon
A576	poo
A577	bhoo
A578	boo
A579	mboo
A57A	kpoo
A57B	mgboo
A57C	gboo
A57D	foo
A57E	voo
A57F	too
A580	thoo
A581	dhoo
A582	dhhoo
A583	loo
A584	roo
A585	doo
A586	ndoo
A587	soo
A588	shoo
A589	zoo
A58A	zhoo
A58B	coo
A58C	joo
A58D	njoo
A58E	yoo
A58F	koo
A590	nggoo
A591	goo
A592	moo
A593	noo
A594	nyoo
A595	u
A596	un
A597	hu
A598	hun
A599	wu
A59A	wun
A59B	pu
A59C	bhu
A59D	bu
A59E	mbu
A59F	kpu
A5A0	mgbu
A5A1	gbu
A5A2	fu
A5A3	vu
A5A4	tu
A5A5	thu
A5A6	dhu
A5A7	dhhu
A5A8	lu
A5A9	ru
A5AA	du
A5AB	ndu
A5AC	su
A5AD	shu
A5AE	zu
A5AF	zhu
A5B0	cu
A5B1	ju
A5B2	nju
A5B3	yu
A5B4	ku
A5B5	nggu
A5B6	gu
A5B7	mu
A5B8	nu
A5B9	nyu
A5BA	o
A5BB	on
A5BC	ngon
A5BD	ho
A5BE	hon
A5BF	wo
A5C0	won
A5C1	po
A5C2	bho
A5C3	bo
A5C4	mbo
A5C5	kpo
A5C6	mgbo
A5C7	gbo
A5C8	gbon
A5C9	fo
A5CA	vo
A5CB	to
A5CC	tho
A5CD	dho
A5CE	dhho
A5CF	lo
A5D0	ro
A5D1	do
A5D2	ndo
A5D3	so
A5D4	sho
A5D5	zo
A5D6	zho
A5D7	co
A5D8	jo
A5D9	njo
A5DA	yo
A5DB	ko
A5DC	nggo
A5DD	go
A5DE	mo
A5DF	no
A5E0	nyo
A5E1	e
A5E2	en
A5E3	ngen
A5E4	he
A5E5	hen
A5E6	we
A5E7	wen
A5E8	pe
A5E9	bhe
A5EA	be
A5EB	mbe
A5EC	kpe
A5ED	kpen
A5EE	mgbe
A5EF	gbe
A5F0	gben
A5F1	fe
A5F2	ve
A5F3	te
A5F4	the
A5F5	dhe
A5F6	dhhe
A5F7	le
A5F8	re
A5F9	de
A5FA	nde
A5FB	se
A5FC	she
A5FD	ze
A5FE	zhe
A5FF	ce
A600	je
A601	nje
A602	ye
A603	ke
A604	ngge
A605	nggen
A606	ge
A607	gen
A608	me
A609	ne
A60A	nye
A60B	ng
A60C	lengthener
A60D	,
A60E	.
A610	ndolefa
A611	ndoleka
A612	ndolesoo
A620	0
A621	1
A622	2
A623	3
A624	4
A625	5
A626	6
A627	7
A628	8
A629	9
A62A	ndolema
A62B	ndoledo

# === Bamum (U+A6A0–U+A6FF) ===
# Source: Phonetic values of Bamum syllabary

A6A0	a
A6A1	ka
A6A2	u
A6A3	ku
A6A4	ee
A6A5	ree
A6A6	tae
A6A7	o
A6A8	nyi
A6A9	i
A6AA	la
A6AB	pa
A6AC	rii
A6AD	riee
A6AE	leeee
A6AF	meeee
A6B0	taa
A6B1	ndaa
A6B2	njaem
A6B3	m
A6B4	suu
A6B5	mu
A6B6	shii
A6B7	si
A6B8	sheux
A6B9	seux
A6BA	kyee
A6BB	ket
A6BC	nuae
A6BD	nu
A6BE	njuae
A6BF	yoq
A6C0	shu
A6C1	yuq
A6C2	ya
A6C3	nsha
A6C4	keux
A6C5	peux
A6C6	njee
A6C7	ntee
A6C8	pue
A6C9	wue
A6CA	pee
A6CB	fee
A6CC	ru
A6CD	lu
A6CE	mi
A6CF	ni
A6D0	reux
A6D1	rae
A6D2	ken
A6D4	ngga
A6D5	nga
A6D6	sho
A6D7	puae
A6D8	fu
A6D9	fom
A6DA	wa
A6DB	na
A6DC	li
A6DD	pi
A6DE	loq
A6DF	ko
A6E0	mben
A6E1	ren
A6E2	men
A6E3	ma
A6E4	ti
A6E5	ki
A6E6	mo
A6E7	mbaa
A6E8	tet
A6E9	kpa
A6EA	ten
A6EB	ntuu
A6EC	samba
A6ED	faamae
A6EE	kovuu
A6EF	koghom
A6F3	.
A6F4	:
A6F5	,
A6F6	;
A6F7	?

# === Javanese (U+A980–U+A9DF) ===
# Source: Phonetic values following Indic abugida pattern

A980	
A981	
A982	
A983	
A984	a
A985	aa
A986	i
A987	ii
A988	u
A989	uu
A98A	e
A98B	ai
A98C	o
A98D	au
A98E	e
A98F	o
A990	ka
A991	kha
A992	ga
A993	gha
A994	nga
A995	cha
A996	chha
A997	ja
A998	jha
A999	nya
A99A	tta
A99B	ttha
A99C	dda
A99D	ddha
A99E	nna
A99F	ta
A9A0	tha
A9A1	da
A9A2	dha
A9A3	na
A9A4	pa
A9A5	pha
A9A6	ba
A9A7	bha
A9A8	ma
A9A9	ya
A9AA	ra
A9AB	la
A9AC	wa
A9AD	sha
A9AE	ssa
A9AF	sa
A9B0	ha
A9B1	ra
A9B2	la
A9B4	aa
A9B5	aa
A9B6	i
A9B7	ii
A9B8	u
A9B9	uu
A9BA	e
A9BB	ai
A9BC	o
A9BD	ya
A9BE	ra
A9BF	la
A9C0	
A9C1	,
A9C2	.
A9C3	:
A9C4	.
A9C5	.
A9C6	.
A9D0	0
A9D1	1
A9D2	2
A9D3	3
A9D4	4
A9D5	5
A9D6	6
A9D7	7
A9D8	8
A9D9	9

# === Cham (U+AA00–U+AA5F) ===
# Source: Phonetic values following Indic abugida pattern

AA00	ka
AA01	kha
AA02	ga
AA03	gha
AA04	ngha
AA05	nga
AA06	cha
AA07	chha
AA08	ja
AA09	jha
AA0A	nhja
AA0B	nha
AA0C	nhra
AA0D	a
AA0E	ta
AA0F	tha
AA10	da
AA11	dha
AA12	nra
AA13	na
AA14	dda
AA15	pa
AA16	ppa
AA17	pha
AA18	ba
AA19	bha
AA1A	mba
AA1B	ma
AA1C	bba
AA1D	ya
AA1E	ra
AA1F	la
AA20	va
AA21	sha
AA22	sa
AA23	ha
AA24	la
AA25	wa
AA26	a
AA27	a
AA28	a
AA29	i
AA2A	i
AA2B	ei
AA2C	u
AA2D	oe
AA2E	o
AA2F	ai
AA30	au
AA31	e
AA32	o
AA33	ya
AA34	ra
AA35	
AA36	
AA40	la
AA41	la
AA42	la
AA43	
AA44	la
AA45	la
AA46	la
AA47	la
AA48	la
AA49	la
AA4A	la
AA4B	la
AA4C	
AA4D	
AA50	0
AA51	1
AA52	2
AA53	3
AA54	4
AA55	5
AA56	6
AA57	7
AA58	8
AA59	9
AA5C	.
AA5D	.
AA5E	.
AA5F	.

# === Meetei Mayek Extensions (U+AAE0–U+AAFF) ===
# Source: Phonetic values of Meitei script

AAE0	e
AAE1	o
AAE2	a
AAE3	a
AAE4	a
AAE5	a
AAE6	a
AAE7	a
AAE8	a
AAE9	a
AAEA	a
AAEB	i
AAEC	u
AAED	e
AAEE	o
AAEF	ou
AAF0	.
AAF1	.
AAF2	a
AAF3	
AAF4	
AAF5	
AAF6	

# === Cherokee Supplement (U+AB70–U+ABBF) ===
# Source: Syllabary phonetic values (lowercase forms)

AB70	a
AB71	e
AB72	i
AB73	o
AB74	u
AB75	v
AB76	ga
AB77	ka
AB78	ge
AB79	gi
AB7A	go
AB7B	gu
AB7C	gv
AB7D	ha
AB7E	he
AB7F	hi
AB80	ho
AB81	hu
AB82	hv
AB83	la
AB84	le
AB85	li
AB86	lo
AB87	lu
AB88	lv
AB89	ma
AB8A	me
AB8B	mi
AB8C	mo
AB8D	mu
AB8E	na
AB8F	hna
AB90	nah
AB91	ne
AB92	ni
AB93	no
AB94	nu
AB95	nv
AB96	qua
AB97	que
AB98	qui
AB99	quo
AB9A	quu
AB9B	quv
AB9C	sa
AB9D	s
AB9E	se
AB9F	si
ABA0	so
ABA1	su
ABA2	sv
ABA3	da
ABA4	ta
ABA5	de
ABA6	te
ABA7	di
ABA8	ti
ABA9	do
ABAA	du
ABAB	dv
ABAC	dla
ABAD	tla
ABAE	tle
ABAF	tli
ABB0	tlo
ABB1	tlu
ABB2	tlv
ABB3	tsa
ABB4	tse
ABB5	tsi
ABB6	tso
ABB7	tsu
ABB8	tsv
ABB9	wa
ABBA	we
ABBB	wi
ABBC	wo
ABBD	wu
ABBE	wv
ABBF	ya

# === Meetei Mayek (U+ABC0–U+ABFF) ===
# Source: Phonetic values of Meitei script

ABC0	ka
ABC1	kha
ABC2	ga
ABC3	gha
ABC4	nga
ABC5	cha
ABC6	chha
ABC7	ja
ABC8	jha
ABC9	nya
ABCA	ta
ABCB	tha
ABCC	da
ABCD	dha
ABCE	na
ABCF	ta
ABD0	tha
ABD1	da
ABD2	dha
ABD3	na
ABD4	pa
ABD5	pha
ABD6	ba
ABD7	bha
ABD8	ma
ABD9	ya
ABDA	ra
ABDB	la
ABDC	wa
ABDD	sha
ABDE	sa
ABDF	ha
ABE0	kha
ABE1	sa
ABE2	sa
ABE3	aa
ABE4	ei
ABE5	i
ABE6	oo
ABE7	ou
ABE8	u
ABE9	ei
ABEA	ou
ABEB	.
ABEC	
ABED	
ABF0	0
ABF1	1
ABF2	2
ABF3	3
ABF4	4
ABF5	5
ABF6	6
ABF7	7
ABF8	8
ABF9	9

# === CJK Compatibility Ideographs (U+F900–U+FAFF) ===
# Source: Unicode Unihan kMandarin (toneless pinyin)

F900	qi
F901	geng
F902	che
F903	jia
F904	hua
F905	chuan
F906	ju
F907	gui
F908	gui
F909	qi
F90A	jin
F90B	la
F90C	nai
F90D	lan
F90E	lai
F90F	luo
F910	luo
F911	luo
F912	luo
F913	luo
F914	le
F915	luo
F916	lao
F917	luo
F918	luo
F919	lao
F91A	luo
F91B	luan
F91C	luan
F91D	lan
F91E	lan
F91F	lan
F920	luan
F921	lan
F922	lan
F923	lan
F924	lan
F925	la
F926	la
F927	la
F928	lang
F929	lang
F92A	lang
F92B	lang
F92C	lang
F92D	lai
F92E	leng
F92F	lao
F930	lu
F931	lu
F932	lu
F933	lu
F934	lao
F935	lu
F936	lu
F937	lu
F938	lu
F939	lu
F93A	lu
F93B	lu
F93C	lu
F93D	lu
F93E	lu
F93F	lu
F940	lu
F941	lun
F942	long
F943	nong
F944	long
F945	long
F946	lao
F947	lei
F948	lu
F949	lei
F94A	lei
F94B	lu
F94C	lou
F94D	lei
F94E	lou
F94F	lei
F950	lu
F951	lou
F952	lei
F953	lei
F954	lin
F955	ling
F956	leng
F957	ling
F958	ling
F959	ling
F95A	du
F95B	na
F95C	le
F95D	nuo
F95E	dan
F95F	ning
F960	nu
F961	lu
F962	yi
F963	bei
F964	pan
F965	bian
F966	fu
F967	bu
F968	mi
F969	shu
F96A	suo
F96B	can
F96C	sai
F96D	sheng
F96E	ye
F96F	shuo
F970	sha
F971	chen
F972	shen
F973	shi
F974	ruo
F975	lue
F976	lue
F977	liang
F978	liang
F979	liang
F97A	liang
F97B	liang
F97C	liang
F97D	liang
F97E	liang
F97F	li
F980	lu
F981	nu
F982	lu
F983	lu
F984	lu
F985	li
F986	lu
F987	li
F988	li
F989	li
F98A	li
F98B	li
F98C	li
F98D	li
F98E	nian
F98F	lian
F990	lian
F991	nian
F992	lian
F993	lian
F994	lian
F995	nian
F996	lian
F997	lian
F998	nian
F999	lian
F99A	lian
F99B	lian
F99C	lie
F99D	lie
F99E	yan
F99F	lie
F9A0	lie
F9A1	shuo
F9A2	lian
F9A3	nian
F9A4	nian
F9A5	lian
F9A6	lian
F9A7	lie
F9A8	ling
F9A9	ling
F9AA	ning
F9AB	ling
F9AC	lian
F9AD	ling
F9AE	ying
F9AF	ling
F9B0	ling
F9B1	ling
F9B2	ling
F9B3	ling
F9B4	ling
F9B5	li
F9B6	li
F9B7	li
F9B8	li
F9B9	e
F9BA	le
F9BB	liao
F9BC	liao
F9BD	niao
F9BE	liao
F9BF	le
F9C0	liao
F9C1	liao
F9C2	liao
F9C3	liao
F9C4	long
F9C5	yun
F9C6	ruan
F9C7	liu
F9C8	chou
F9C9	liu
F9CA	liu
F9CB	liu
F9CC	liu
F9CD	liu
F9CE	liu
F9CF	niu
F9D0	lei
F9D1	liu
F9D2	lu
F9D3	lu
F9D4	lun
F9D5	lun
F9D6	lun
F9D7	lun
F9D8	lu
F9D9	li
F9DA	li
F9DB	lu
F9DC	long
F9DD	li
F9DE	li
F9DF	lu
F9E0	yi
F9E1	li
F9E2	li
F9E3	ni
F9E4	li
F9E5	li
F9E6	li
F9E7	li
F9E8	li
F9E9	li
F9EA	li
F9EB	ni
F9EC	ni
F9ED	lin
F9EE	lin
F9EF	lin
F9F0	lin
F9F1	lin
F9F2	lin
F9F3	lin
F9F4	lin
F9F5	lin
F9F6	lin
F9F7	li
F9F8	li
F9F9	li
F9FA	zhuang
F9FB	zhi
F9FC	shi
F9FD	shen
F9FE	cha
F9FF	ci
FA00	qie
FA01	du
FA02	ta
FA03	tang
FA04	zhai
FA05	dong
FA06	bao
FA07	fu
FA08	xing
FA09	jiang
FA0A	jian
FA0B	kuo
FA0C	wu
FA0D	hu
FA10	zhong
FA12	qing
FA15	xi
FA16	zhu
FA17	yi
FA18	li
FA19	shen
FA1A	xiang
FA1B	fu
FA1C	jing
FA1D	jing
FA1E	yu
FA20	qiu
FA22	zhu
FA25	yi
FA26	dou
FA2A	fan
FA2B	si
FA2C	guan
FA2D	he
FA2E	lang
FA2F	li
FA30	wu
FA31	seng
FA32	mian
FA33	mian
FA34	qin
FA35	bei
FA36	he
FA37	tan
FA38	qi
FA39	ping
FA3A	mo
FA3B	ceng
FA3C	che
FA3D	hui
FA3E	kai
FA3F	zeng
FA40	cheng
FA41	min
FA42	ji
FA43	shu
FA44	mei
FA45	hai
FA46	zhu
FA47	han
FA48	zhu
FA49	zhao
FA4A	zuo
FA4B	bei
FA4C	she
FA4D	zhi
FA4E	qi
FA4F	you
FA50	zu
FA51	zhu
FA52	huo
FA53	zhen
FA54	gu
FA55	tu
FA56	jie
FA57	lian
FA58	jin
FA59	fan
FA5A	shu
FA5B	zhe
FA5C	chou
FA5D	cao
FA5E	cao
FA5F	zhu
FA60	he
FA61	shi
FA62	ye
FA63	jin
FA64	bin
FA65	zeng
FA66	chuo
FA67	yi
FA68	nan
FA69	xiang
FA6A	pin
FA6B	hui
FA6D	guan
FA70	bing
FA71	kuang
FA72	quan
FA73	xing
FA74	chong
FA75	ji
FA76	yong
FA77	shao
FA78	he
FA79	tao
FA7A	hui
FA7B	wa
FA7C	zhong
FA7D	fen
FA7E	yan
FA7F	ben
FA80	bi
FA81	ci
FA82	ao
FA83	yi
FA84	cai
FA85	yao
FA86	wang
FA87	shen
FA88	yu
FA89	zeng
FA8A	ao
FA8B	cheng
FA8C	dai
FA8D	yu
FA8E	sou
FA8F	bing
FA90	ao
FA91	qing
FA92	lang
FA93	wang
FA94	zhang
FA95	dai
FA96	sha
FA97	liu
FA98	yin
FA99	zi
FA9A	han
FA9B	jing
FA9C	zhu
FA9D	qiao
FA9E	jue
FA9F	fan
FAA0	zhu
FAA1	tian
FAA2	ci
FAA3	hua
FAA4	guan
FAA5	wen
FAA6	yi
FAA7	sheng
FAA8	zhi
FAA9	juan
FAAA	zhe
FAAB	tian
FAAC	tiao
FAAD	jie
FAAE	lei
FAAF	tao
FAB0	lian
FAB1	ping
FAB2	zhe
FAB3	huang
FAB4	hua
FAB5	yun
FAB6	qiang
FAB7	fu
FAB8	shi
FAB9	diao
FABA	zhu
FABB	qing
FABC	ye
FABD	nuo
FABE	yu
FABF	jin
FAC0	bian
FAC1	zeng
FAC2	shu
FAC3	chi
FAC4	sou
FAC5	xing
FAC6	zhu
FAC7	nan
FAC8	jing
FAC9	bai
FACA	xiang
FACB	e
FACC	pin
FACD	zhen
FACE	gui
FAD8	e
FAD9	pang

# === Alphabetic Presentation Forms (U+FB00–U+FB4F) ===
# Source: Latin ligatures (fi→fi, fl→fl) and Armenian ligatures

FB13	mn
FB14	me
FB15	mi
FB16	vn
FB17	mkh
FB1D	i
FB1E	
FB1F	y
FB20	a
FB21	a
FB22	d
FB23	h
FB24	kh
FB25	l
FB26	m
FB27	r
FB28	t
FB29	+
FB2A	sh
FB2B	s
FB2C	sh
FB2D	s
FB2E	a
FB2F	a
FB30	a
FB31	b
FB32	g
FB33	d
FB34	h
FB35	u
FB36	z
FB38	t
FB39	y
FB3A	k
FB3B	k
FB3C	l
FB3E	m
FB40	n
FB41	s
FB43	p
FB44	p
FB46	ts
FB47	q
FB48	r
FB49	sh
FB4A	t
FB4B	o
FB4C	v
FB4D	kh
FB4E	f
FB4F	al

# === Arabic Presentation Forms-A (U+FB50–U+FDFF) ===
# Source: Derived from base Arabic (BGN/PCGN) mappings

FB50	a
FB51	a
FB56	p
FB57	p
FB58	p
FB59	p
FB66	t
FB67	t
FB68	t
FB69	t
FB6A	v
FB6B	v
FB6C	v
FB6D	v
FB7A	ch
FB7B	ch
FB7C	ch
FB7D	ch
FB88	d
FB89	d
FB8A	zh
FB8B	zh
FB8C	r
FB8D	r
FB8E	k
FB8F	k
FB90	k
FB91	k
FB92	g
FB93	g
FB94	g
FB95	g
FB9E	n
FB9F	n
FBA4	h
FBA5	h
FBA6	h
FBA7	h
FBA8	h
FBA9	h
FBAA	h
FBAB	h
FBAC	h
FBAD	h
FBAE	y
FBAF	y
FBB0	y
FBB1	y
FBD3	ng
FBD4	ng
FBD5	ng
FBD6	ng
FBE4	e
FBE5	e
FBE6	e
FBE7	e
FBEA	y'a
FBEB	y'a
FBEE	y'w
FBEF	y'w
FBF6	y'e
FBF7	y'e
FBF8	y'e
FBF9	y'a
FBFA	y'a
FBFB	y'a
FBFC	y
FBFD	y
FBFE	y
FBFF	y
FC00	y'j
FC01	y'h
FC02	y'm
FC03	y'a
FC04	y'y
FC05	bj
FC06	bh
FC07	bkh
FC08	bm
FC09	ba
FC0A	by
FC0B	tj
FC0C	th
FC0D	tkh
FC0E	tm
FC0F	ta
FC10	ty
FC11	thj
FC12	thm
FC13	tha
FC14	thy
FC15	jh
FC16	jm
FC17	hj
FC18	hm
FC19	khj
FC1A	khh
FC1B	khm
FC1C	sj
FC1D	sh
FC1E	skh
FC1F	sm
FC20	sh
FC21	sm
FC22	dj
FC23	dh
FC24	dkh
FC25	dm
FC26	th
FC27	tm
FC28	zm
FC29	'j
FC2A	'm
FC2B	ghj
FC2C	ghm
FC2D	fj
FC2E	fh
FC2F	fkh
FC30	fm
FC31	fa
FC32	fy
FC33	qh
FC34	qm
FC35	qa
FC36	qy
FC37	ka
FC38	kj
FC39	kh
FC3A	kkh
FC3B	kl
FC3C	km
FC3D	ka
FC3E	ky
FC3F	lj
FC40	lh
FC41	lkh
FC42	lm
FC43	la
FC44	ly
FC45	mj
FC46	mh
FC47	mkh
FC48	mm
FC49	ma
FC4A	my
FC4B	nj
FC4C	nh
FC4D	nkh
FC4E	nm
FC4F	na
FC50	ny
FC51	hj
FC52	hm
FC53	ha
FC54	hy
FC55	yj
FC56	yh
FC57	ykh
FC58	ym
FC59	ya
FC5A	yy
FC5B	dha
FC5C	ra
FC5D	aa
FC5E	un
FC5F	in
FC60	a
FC61	u
FC62	i
FC63	
FC64	y'r
FC65	y'z
FC66	y'm
FC67	y'n
FC68	y'a
FC69	y'y
FC6A	br
FC6B	bz
FC6C	bm
FC6D	bn
FC6E	ba
FC6F	by
FC70	tr
FC71	tz
FC72	tm
FC73	tn
FC74	ta
FC75	ty
FC76	thr
FC77	thz
FC78	thm
FC79	thn
FC7A	tha
FC7B	thy
FC7C	fa
FC7D	fy
FC7E	qa
FC7F	qy
FC80	ka
FC81	kl
FC82	km
FC83	ka
FC84	ky
FC85	lm
FC86	la
FC87	ly
FC88	ma
FC89	mm
FC8A	nr
FC8B	nz
FC8C	nm
FC8D	nn
FC8E	na
FC8F	ny
FC90	aa
FC91	yr
FC92	yz
FC93	ym
FC94	yn
FC95	ya
FC96	yy
FC97	y'j
FC98	y'h
FC99	y'kh
FC9A	y'm
FC9B	y'h
FC9C	bj
FC9D	bh
FC9E	bkh
FC9F	bm
FCA0	bh
FCA1	tj
FCA2	th
FCA3	tkh
FCA4	tm
FCA5	th
FCA6	thm
FCA7	jh
FCA8	jm
FCA9	hj
FCAA	hm
FCAB	khj
FCAC	khm
FCAD	sj
FCAE	sh
FCAF	skh
FCB0	sm
FCB1	sh
FCB2	skh
FCB3	sm
FCB4	dj
FCB5	dh
FCB6	dkh
FCB7	dm
FCB8	th
FCB9	zm
FCBA	'j
FCBB	'm
FCBC	ghj
FCBD	ghm
FCBE	fj
FCBF	fh
FCC0	fkh
FCC1	fm
FCC2	qh
FCC3	qm
FCC4	kj
FCC5	kh
FCC6	kkh
FCC7	kl
FCC8	km
FCC9	lj
FCCA	lh
FCCB	lkh
FCCC	lm
FCCD	lh
FCCE	mj
FCCF	mh
FCD0	mkh
FCD1	mm
FCD2	nj
FCD3	nh
FCD4	nkh
FCD5	nm
FCD6	nh
FCD7	hj
FCD8	hm
FCD9	ha
FCDA	yj
FCDB	yh
FCDC	ykh
FCDD	ym
FCDE	yh
FCDF	y'm
FCE0	y'h
FCE1	bm
FCE2	bh
FCE3	tm
FCE4	th
FCE5	thm
FCE6	thh
FCE7	sm
FCE8	sh
FCE9	shm
FCEA	shh
FCEB	kl
FCEC	km
FCED	lm
FCEE	nm
FCEF	nh
FCF0	ym
FCF1	yh
FCF2	a
FCF3	u
FCF4	i
FCF5	ta
FCF6	ty
FCF7	'a
FCF8	'y
FCF9	gha
FCFA	ghy
FCFB	sa
FCFC	sy
FCFD	sha
FCFE	shy
FCFF	ha
FD00	hy
FD01	ja
FD02	jy
FD03	kha
FD04	khy
FD05	sa
FD06	sy
FD07	da
FD08	dy
FD09	shj
FD0A	shh
FD0B	shkh
FD0C	shm
FD0D	shr
FD0E	sr
FD0F	sr
FD10	dr
FD11	ta
FD12	ty
FD13	'a
FD14	'y
FD15	gha
FD16	ghy
FD17	sa
FD18	sy
FD19	sha
FD1A	shy
FD1B	ha
FD1C	hy
FD1D	ja
FD1E	jy
FD1F	kha
FD20	khy
FD21	sa
FD22	sy
FD23	da
FD24	dy
FD25	shj
FD26	shh
FD27	shkh
FD28	shm
FD29	shr
FD2A	sr
FD2B	sr
FD2C	dr
FD2D	shj
FD2E	shh
FD2F	shkh
FD30	shm
FD31	sh
FD32	shh
FD33	tm
FD34	sj
FD35	sh
FD36	skh
FD37	shj
FD38	shh
FD39	shkh
FD3A	tm
FD3B	zm
FD3C	an
FD3D	an
FD4C	l
FD50	tjm
FD51	thj
FD52	thj
FD53	thm
FD54	tkhm
FD55	tmj
FD56	tmh
FD57	tmkh
FD58	jmh
FD59	jmh
FD5A	hmy
FD5B	hma
FD5C	shj
FD5D	sjh
FD5E	sja
FD5F	smh
FD60	smh
FD61	smj
FD62	smm
FD63	smm
FD64	shh
FD65	shh
FD66	smm
FD67	shhm
FD68	shhm
FD69	shjy
FD6A	shmkh
FD6B	shmkh
FD6C	shmm
FD6D	shmm
FD6E	dha
FD6F	dkhm
FD70	dkhm
FD71	tmh
FD72	tmh
FD73	tmm
FD74	tmy
FD75	'jm
FD76	'mm
FD77	'mm
FD78	'ma
FD79	ghmm
FD7A	ghmy
FD7B	ghma
FD7C	fkhm
FD7D	fkhm
FD7E	qmh
FD7F	qmm
FD80	lhm
FD81	lhy
FD82	lha
FD83	ljj
FD84	ljj
FD85	lkhm
FD86	lkhm
FD87	lmh
FD88	lmh
FD89	mhj
FD8A	mhm
FD8B	mhy
FD8C	mjh
FD8D	mjm
FD8E	mkhj
FD8F	mkhm
FD92	mjkh
FD93	hmj
FD94	hmm
FD95	nhm
FD96	nha
FD97	njm
FD98	njm
FD99	nja
FD9A	nmy
FD9B	nma
FD9C	ymm
FD9D	ymm
FD9E	bkhy
FD9F	tjy
FDA0	tja
FDA1	tkhy
FDA2	tkha
FDA3	tmy
FDA4	tma
FDA5	jmy
FDA6	jha
FDA7	jma
FDA8	skha
FDA9	shy
FDAA	shhy
FDAB	dhy
FDAC	ljy
FDAD	lmy
FDAE	yhy
FDAF	yjy
FDB0	ymy
FDB1	mmy
FDB2	qmy
FDB3	nhy
FDB4	qmh
FDB5	lhm
FDB6	'my
FDB7	kmy
FDB8	njh
FDB9	mkhy
FDBA	ljm
FDBB	kmm
FDBC	ljm
FDBD	njh
FDBE	jhy
FDBF	hjy
FDC0	mjy
FDC1	fmy
FDC2	bhy
FDC3	kmm
FDC4	'jm
FDC5	smm
FDC6	skhy
FDC7	njy
FDF5	l
FDF8	l
FDFA	l

# === Arabic Presentation Forms-B (U+FE70–U+FEFF) ===
# Source: Derived from base Arabic (BGN/PCGN) mappings


# === Combining Half Marks (U+FE20–U+FE2F) ===
# Source: Strip combining marks

FE20	
FE21	
FE22	
FE23	
FE24	
FE25	
FE26	
FE27	
FE28	
FE29	
FE2A	
FE2B	
FE2C	
FE2D	
FE2E	
FE2F	
FE70	an
FE71	an
FE72	un
FE74	in
FE76	a
FE77	a
FE78	u
FE79	u
FE7A	i
FE7B	i
FE7C	
FE7D	
FE7E	
FE7F	
FE80	'
FE81	a
FE82	a
FE83	a
FE84	a
FE85	'
FE86	'
FE87	a
FE88	a
FE89	'
FE8A	'
FE8B	'
FE8C	'
FE8D	a
FE8E	a
FE8F	b
FE90	b
FE91	b
FE92	b
FE93	h
FE94	h
FE95	t
FE96	t
FE97	t
FE98	t
FE99	th
FE9A	th
FE9B	th
FE9C	th
FE9D	j
FE9E	j
FE9F	j
FEA0	j
FEA1	h
FEA2	h
FEA3	h
FEA4	h
FEA5	kh
FEA6	kh
FEA7	kh
FEA8	kh
FEA9	d
FEAA	d
FEAB	dh
FEAC	dh
FEAD	r
FEAE	r
FEAF	z
FEB0	z
FEB1	s
FEB2	s
FEB3	s
FEB4	s
FEB5	sh
FEB6	sh
FEB7	sh
FEB8	sh
FEB9	s
FEBA	s
FEBB	s
FEBC	s
FEBD	d
FEBE	d
FEBF	d
FEC0	d
FEC1	t
FEC2	t
FEC3	t
FEC4	t
FEC5	z
FEC6	z
FEC7	z
FEC8	z
FEC9	'
FECA	'
FECB	'
FECC	'
FECD	gh
FECE	gh
FECF	gh
FED0	gh
FED1	f
FED2	f
FED3	f
FED4	f
FED5	q
FED6	q
FED7	q
FED8	q
FED9	k
FEDA	k
FEDB	k
FEDC	k
FEDD	l
FEDE	l
FEDF	l
FEE0	l
FEE1	m
FEE2	m
FEE3	m
FEE4	m
FEE5	n
FEE6	n
FEE7	n
FEE8	n
FEE9	h
FEEA	h
FEEB	h
FEEC	h
FEED	w
FEEE	w
FEEF	a
FEF0	a
FEF1	y
FEF2	y
FEF3	y
FEF4	y
FEF5	la
FEF6	la
FEF7	la
FEF8	la
FEF9	la
FEFA	la
FEFB	la
FEFC	la

# === Halfwidth and Fullwidth Forms (U+FF00–U+FFEF) ===
# Source: NFKD to base character (fullwidth→ASCII, halfwidth kana→Hepburn)


# === BOM / Zero Width No-Break Space (U+FEFF) ===
# Source: Strip invisible character

FEFF	
FF01	!
FF02	"
FF03	#
FF04	$
FF05	%
FF06	&
FF07	'
FF08	(
FF09	)
FF0A	*
FF0B	+
FF0C	,
FF0D	-
FF0E	.
FF0F	/
FF10	0
FF11	1
FF12	2
FF13	3
FF14	4
FF15	5
FF16	6
FF17	7
FF18	8
FF19	9
FF1A	:
FF1B	;
FF1C	<
FF1D	=
FF1E	>
FF1F	?
FF20	@
FF21	A
FF22	B
FF23	C
FF24	D
FF25	E
FF26	F
FF27	G
FF28	H
FF29	I
FF2A	J
FF2B	K
FF2C	L
FF2D	M
FF2E	N
FF2F	O
FF30	P
FF31	Q
FF32	R
FF33	S
FF34	T
FF35	U
FF36	V
FF37	W
FF38	X
FF39	Y
FF3A	Z
FF3B	[
FF3C	\
FF3D	]
FF3E	^
FF3F	_
FF40	`
FF41	a
FF42	b
FF43	c
FF44	d
FF45	e
FF46	f
FF47	g
FF48	h
FF49	i
FF4A	j
FF4B	k
FF4C	l
FF4D	m
FF4E	n
FF4F	o
FF50	p
FF51	q
FF52	r
FF53	s
FF54	t
FF55	u
FF56	v
FF57	w
FF58	x
FF59	y
FF5A	z
FF5B	{
FF5C	|
FF5D	}
FF5E	~
FF65	 
FF66	wo
FF67	a
FF68	i
FF69	u
FF6A	e
FF6B	o
FF6C	ya
FF6D	yu
FF6E	yo
FF6F	tsu
FF70	-
FF71	a
FF72	i
FF73	u
FF74	e
FF75	o
FF76	ka
FF77	ki
FF78	ku
FF79	ke
FF7A	ko
FF7B	sa
FF7C	shi
FF7D	su
FF7E	se
FF7F	so
FF80	ta
FF81	chi
FF82	tsu
FF83	te
FF84	to
FF85	na
FF86	ni
FF87	nu
FF88	ne
FF89	no
FF8A	ha
FF8B	hi
FF8C	fu
FF8D	he
FF8E	ho
FF8F	ma
FF90	mi
FF91	mu
FF92	me
FF93	mo
FF94	ya
FF95	yu
FF96	yo
FF97	ra
FF98	ri
FF99	ru
FF9A	re
FF9B	ro
FF9C	wa
FF9D	n
FF9E	
FF9F	
FFA0	
FFA1	g
FFA2	kk
FFA3	gs
FFA4	n
FFA5	nj
FFA6	nh
FFA7	d
FFA8	tt
FFA9	r
FFAA	lg
FFAB	lm
FFAC	lb
FFAD	ls
FFAE	lt
FFAF	lp
FFB0	lh
FFB1	m
FFB2	b
FFB3	pp
FFB4	bs
FFB5	s
FFB6	ss
FFB7	
FFB8	j
FFB9	jj
FFBA	ch
FFBB	k
FFBC	t
FFBD	p
FFBE	h
FFC2	a
FFC3	ae
FFC4	ya
FFC5	yae
FFC6	eo
FFC7	e
FFCA	yeo
FFCB	ye
FFCC	o
FFCD	wa
FFCE	wae
FFCF	oe
FFD2	yo
FFD3	u
FFD4	wo
FFD5	we
FFD6	wi
FFD7	yu
FFDA	eu
FFDB	ui
FFDC	i
FFE0	c
FFE1	GBP
FFE2	-
FFE3	-
FFE4	|
FFE5	JPY
FFE6	KRW
FFE8	|
FFE9	<-
FFEA	^
FFEB	->
FFEC	v
FFED	#
FFEE	o

# === Interlinear Annotation (U+FFF9–U+FFFB) ===
# Source: Strip invisible annotation characters

FFF9	
FFFA	
FFFB