digraphs: distinguishing class for rfc-only in include

[sheet.git] / shiar.inc.txt

# common meaning of second character
        !       Grave
        "       Double acute accent
        '       Acute accent
        (       Breve
        ) +?    Inverted Breve
        ,       Cedilla
        -       Macron
        .       Dot Above
        /       Stroke
        0       Ring above
        2       Hook
        8 +?    Double Grave
        9       Horn
        9 +     Curl
        :       Diaeresis
        ;       Ogonek (+Retroflex Hook/Tail)
        <       Caron
        >       Circumflex accent
        ?       Tilde
        _       Line below
        c +     Smallcaps
        I +     Turned
        S       Superscript
        s       Subscript

        =       Cyrillic
        *       Greek
        %       Greek/Cyrillic special
        +       lc: Arabic, uc: Hebrew
        3       some Latin/Greek/Cyrillic letters
        4       Bopomofo
        5       Hiragana (also lc + a/e/i/o/u)
        6       Katakana (also uc + a/e/i/o/u)
        J +     Korean Jamo (also K)
        p +     IPA extensions

# common first character
        "       combining diacritic
        '       spacing diacritic
        R       square


# currency
#=e €  # in vim
#Eu €  # in zsh and vim
=B ฿  # more like B/, but prefer that for diacritical letter
=d ₫
=g ₴  # derived from cursive g= (soundalike h= or lookalike 2= seem bad options)
=L ₺
=N ₦
#=P ₽  # in vim
=p ₱  # =P conflicts with vim alternative for ruble
=R ₹  # conflicts with vim alternative for ruble
=t ₮
K/ ₭
Rs ₨
Sq ₪
m/ ₥

# useful characters
3: …  # opposite of ⋮ (more logical would be to swap with .3 ⋯)
.> ‣  # similar to .=
(/ ⊄  # similar to (_
)/ ⊅  # similar to )_
(+ ∉  # (- with stroke
+) ∌  # -) with stroke
0X ⊗  # *X like 0.
+0 ⊕  # 0+ already in use
0/ ⊘
0- ⊖
0* ⊛  #XXX alternatively ⍟
0: ⨸
0% ⦼  # no circled percent, but close
0< ⧀
0= ⊜
0> ⧁
0! ⦶  # no circled exclamation mark
.1 ․  # obvious location, even though ‥ and … are at inconsistent .. and 3:
** ⁑
*3 ⁂

# xorg compatibility
.= •  # previously ()
<3 ♥  # rfc has trigraph cH-
:) ☺  # easy alias to 0u
:( ☹
FU 🖕  # common abbreviation for middle finger
#88 ∞  # alias to 00
#v/ √  # alias to RT
!? ‽  # previously ?!
?! ⸘
fs ſ  # previously sl

# obvious line drawing gaps
ll ╴
rr ╶
uu ╵
dD ╷  # goddamn! stupid arabic dad got there first
LL ╸
RR ╺
UU ╹
DD ╻
Hh ╾
hH ╼
Vv ╿
vV ╽
2- ╌  # exactly like to 3 and 4
2_ ╍
2! ╎
2/ ╏
BF ╳  # FD and BD combined; FB already in use

# additional letters
HW Ƕ  # HV conflicts with vh line drawing
hw ƕ
db ȸ
qp ȹ
# old/middle english (uncommon)
WY Ƿ  # replaced by UU, later W
wy ƿ
YG Ȝ  # g-derived Y
yg ȝ
# common ipa
S1 Ʃ  # can't use SH or ES
s1 ʃ  # can't use sh; keep es for subscript
?. ʔ
?/ ʡ
# clicks
!C ǀ  # corresponding zulu letter
!Q ǃ  # idem; !. for lookalike (previously ʗ)
!X ǁ  # idem; !/ for lookalike (previously ʖ)
!A ǂ  # Alveolar; !- looks alike, != even more so but already occupied
!B ʘ  # Bilabial
!R ‼  # Retroflex (or Repeated); !! looks alike but occupied
# grave (or similar)
R! Ȑ  # no R-grave; double down
r! ȑ
S! Ș  # no S-grave; comma in use for cedilla, so misusing grave seems only fair
s! ș
T! Ț  # no T-grave; like S!
t! ț

# subscripts
as ₐ
#es ₑ  #TODO: move esh
@s ₔ
hs ₕ
is ᵢ
js ⱼ
ks ₖ
ls ₗ
ms ₘ
ns ₙ
os ₒ
ps ₚ
rs ᵣ
Ss ₛ  # ss is ß
#ts ₜ  # both ts and Ts in use for Ћ
us ᵤ
vs ᵥ
xs ₓ

# superscripts (modifier letters)
AS ᵃ  # alef was first for aS
bS ᵇ
CS ᶜ  # cS is ♠
dS ᵈ
eS ᵉ
#fS ᶠ  # both fS and FS in use
gS ᵍ
hS ʰ  # ipa release
iS ⁱ
jS ʲ  # ipa release
kS ᵏ
lS ˡ  # ipa release
mS ᵐ
#nS ⁿ  # already present
oS ᵒ
pS ᵖ
rS ʳ
sS ˢ
tS ᵗ
uS ᵘ
vS ᵛ
wS ʷ  # ipa release
xS ˣ
yS ʸ
zS ᶻ

# capital superscripts; avoid as most *S are in use
#AS ᴬ
##BS ᴮ
##DS ᴰ
##ES ᴱ
##GS ᴳ
##HS ᴴ
##IS ᴵ
#JS ᴶ
#KS ᴷ
#LS ᴸ
#MS ᴹ
##NS ᴺ
##OS ᴼ
#PS ᴾ
##RS ᴿ
##TS ᵀ
##US ᵁ
##VS ⱽ
#WS ᵂ

# expected but missing
A. Ȧ
a. ȧ
#A0 Ǻ  # normal A-ring already provided by AA
#a0 ǻ
H< Ȟ
h< ȟ
j. ȷ
O. Ȯ
o. ȯ
N! Ǹ
n! ǹ
Y- Ȳ  # conflicts with vim alternative for yen
y- ȳ
'i ͺ # spacing iota subscript (like "i for combining)
=v ⇓
=! ⇑
Ac ℀  # prefer common A-smallcap for ac
As ℁  # prefer common a-subscript for as
cu ℆  # co ís present though
1/ ⅟
03 ↉
17 ⅐
19 ⅑
10 ⅒

# relocate
a" ǟ  # a1 # long umlauted, very similar to double acute
A" Ǟ  # A1
jo ё  # io # consistent with ja/ju
JO Ё  # IO
ji ї  # yi # idem
JI Ї  # YI
Z1 Ʒ  # ED # doesn't make sense, put it with S1
z1 ʒ  # ed # not in vim
=Y ¥  # Ye # also Y- in vim

# bars and strokes
A/ Ⱥ
a/ ⱥ
B/ Ƀ
B- Ƃ
b- ƃ
b/ ƀ
C/ Ȼ
c/ ȼ
E/ Ɇ
e/ ɇ
F/ Ꞙ
f/ ꞙ
I/ Ɨ
i/ ɨ
J/ Ɉ
j/ ɉ
L- Ƚ
l- ƚ  # not really a macron, but wouldn't really make sense anyway otherwise
l? ɫ  # idem
L? Ɫ
P/ Ᵽ
p/ ᵽ
R/ Ɍ
r/ ɍ
U/ Ʉ
u/ ʉ
Y/ Ɏ
y/ ɏ

# middle tilde  #XXX: not tilde above
#b? ᵬ
#d? ᵭ
#f? ᵮ
#m? ᵯ
##n? ᵰ  # already a tilde above
#p? ᵱ
#r? ᵲ
#s? ᵴ
#t? ᵵ
#z? ᵶ

# inverted breves
        # not used all that much, better leave x) free
#")
#')
#A) Ȃ
#a) ȃ
#E) Ȇ
#e) ȇ
#I) Ȋ  # )I exists, but should not confuse
#i) ȋ
#O) Ȏ
#o) ȏ
#R) Ȓ
#r) ȓ
#U) Ȗ  # )U exists
#u) ȗ

# double grave
        # usage is similar to inverted breve, just as rare
#"8
#'8
#A8 Ȁ
#a8 ȁ
#E8 Ȅ
#e8 ȅ
#I8 Ȉ
#i8 ȉ
#O8 Ȍ
#o8 ȍ
#R8 Ȑ
#r8 ȑ
#U8 Ȕ
#u8 ȕ

# hooks
#"2
#'2
B2 Ɓ
b2 ɓ
C2 Ƈ
c2 ƈ
#D2 Ɗ  # in use by control char
d2 ɗ  # hook
d; ɖ  # R (tail)
D; Ɖ
E, Ȩ
e, ȩ
F, Ƒ  # described as hook, but similar to cedilla
f, ƒ  # replaces more specialised f( and Fl, unified nowadays
G2 Ɠ
g2 ɠ
H2 Ɦ  # different hook from lowercase
h2 ɦ
HG Ꜧ  # similar to NG, distinct from ꞕ ḩ ⱨ
hg ꜧ
K2 Ƙ
k2 ƙ
l; ɭ  # R
MG Ɱ  # M2 in use
mg ɱ  # similar to ng
N2 Ɲ  # left hook
n2 ɲ
n; ɳ  # R
#P2 Ƥ  # in use by control char
p2 ƥ
Q; Ɋ  # hook tail
q; ɋ  # hook tail
q2 ʠ  # hook
R; Ɽ  # R (tail)
r; ɽ
s; ʂ  # R
T2 Ƭ  # hook
t2 ƭ
T; Ʈ  # R
t; ʈ
V2 Ʋ
v2 ʋ
v; ⱱ
W; Ⱳ
w; ⱳ
Y; Ƴ  # not a hook below, but Y2 hook above is already present
y; ƴ
Z, Ȥ  # prefer cedilla similarity like F,
z, ȥ
z; ʐ  # R

# curls (9 is mostly free because horns are so rare)
c9 ɕ
d9 ȡ
j9 ʝ  # crossed-tail actually
l9 ȴ
n9 ȵ
t9 ȶ
v9 ⱴ
z9 ʑ
#S9 ʆ
#Z9 ʓ

# tone letters
#2/ ƻ  # rarely used, and double dash is far more logical
%2 Ƨ
2% ƨ
%6 Ƅ
6% ƅ
%5 Ƽ
5% ƽ

# turned/inverted (trailing I is uncommon for lowercase, and already used thusly for !I, ?I and NI)
AI Ɐ
aI ɐ
cI ɔ  # open o
#EI Ǝ  # would be confusing, as it's not uppercase schwa eI
eI ə  # schwa, not turned E (latter is very uncommon)
FI Ⅎ  # not a letter
fI ⅎ  # idem
gI ᵷ
hI ɥ
iI ᴉ
KI Ʞ
kI ʞ
LI Ꞁ
lI ꞁ
MI Ɯ
mI ɯ
#nI ᴎ  # reversed capital N, but NI already in use
rI ɹ
#RI ᴚ  # conflicts with RI control char
TI Ʇ
tI ʇ
VI Ʌ
vI ʌ
wI ʍ
yI ʎ

# open/ipa vowels
oE ɶ  # Oe also available, but E looks capital
ap ɑ  #XXX ao
Ap ɒ  #XXX Ao? (AO in use)
ep ɛ  #XXX eo
 # Ɛ  #XXX Eo or EO
3p ɜ  #XXX 3o
up ʊ  #XXX uo
 # Ʊ  #XXX Uo or UO

# ipa (*p)
#:> ː  # :p
#:< ˑ  # .p -p
8p ɞ
Ep ɘ
op ɵ
Op ɤ  #XXX oy would look alike
?p ʕ
ww ʬ
gp ɡ
#lp ɬ  #XXX: lb for 'belt'
jp ɟ
lz ɮ  #XXX
r2 ɾ  #XXX: fishhook
Jp ʄ
Gp ɣ
rl ɼ
rL ɺ
rp ɻ
Rp ʁ
mL ɰ  # like rL (XXX mp?)

# small caps (also possible at *s)
bc ʙ
gc ɢ
hc ʜ
ic ɪ
lc ʟ
nc ɴ
rc ʀ
yc ʏ
# more from phonetics extensions
ac ᴀ
cc ᴄ
dc ᴅ
ec ᴇ
fc ꜰ
jc ᴊ
kc ᴋ
mc ᴍ
oc ᴏ
pc ᴘ
tc ᴛ
sC ꜱ  # sc/Sc/SC in use
uc ᴜ
vc ᴠ
wc ᴡ
zc ᴢ

# hangeul jamo consonants at *J
gJ ㄱ
GJ ㄲ
xJ ㄳ
nJ ㄴ
dJ ㄷ
DJ ㄸ
rJ ㄹ
mJ ㅁ
bJ ㅂ
BJ ㅃ
sJ ㅅ
SJ ㅆ
0J ㅇ
jJ ㅈ
JJ ㅉ
cJ ㅊ
kJ ㅋ
tJ ㅌ
pJ ㅍ
hJ ㅎ

# hangeul jamo vowels at *J
aJ ㅏ
AJ ㅐ
eJ ㅓ
EJ ㅔ
oJ ㅗ
OJ ㅚ
uJ ㅜ
UJ ㅝ
iJ ㅣ
vJ ㅝ
VJ ㅞ
wJ ㅘ
WJ ㅙ
yJ ㅑ
YJ ㅒ
-J ㅡ  # qJ?
+J ㅢ  # QJ?

# hangeul jamo iotized vowels at *K (for Korean)
uK ㅠ
UK ㆌ
oK ㅛ
eK ㅕ
EK ㅖ

# common formatting control
ZS ​  # ZWSP; capitals like other Cc
ZN ‌  # ZWNJ;                           less obvious alt: 'Z
ZW ‍  # ZWJ; ZJ somewhy used for tsadi; less obvious alt: "Z
LR ‎  # LRM
RL ‏  # RLM; keep rl for ɼ

###
# under development or temporary

# incompatible
$PR ► # current PR should be TR
$PL ◄ # current PL should be TL
$'> ˆ # where to put ^?
$'? ˜ # where to put ~?
$?' ΄ # tonos
$?" ΅ # tonos+dialytika
$!: ῏ # psili+peris
$?, ῞ # dasia+oxia
$,! ῝ # dasia+varia
$,' ῾ # dasia
$;! ῍ # psili+varia
$;' ᾿ # psili
$?: ῟ # dasia+peris
$?; ῎ # psili+oxia

# undecided
$!D ‼ # !! in use
$<> ♦
$ud ↨ # UD with base
$FS   # figure space
$!o ϕ # Ph?
$D= ₯
$vv װ
$vy ױ
$yy ײ
$g1 ׳
$g2 ״

# rfc (incorrectly?) maps double to heavy
$vL ╡
$Vl ╢
$Dl ╖
$dL ╕
$VL ╣
$VV ║
$DL ╗
$UL ╝
$Ul ╜
$uL ╛
$vR ╞
$Vr ╟
$UR ╚
$DR ╔
$UH ╩
$DH ╦
$VR ╠
$HH ═
$VH ╬
$uH ╧
$Uh ╨
$dH ╤
$Dh ╥
$Ur ╙
$uR ╘
$dR ╒
$Dr ╓
$Vh ╫
$vH ╪