1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
|
# Accented characters. Inputs two keys: first the code for the accent, then
# the base character being accented. Note that all input characters are
# ASCII. For best results zsh should have been built with support for
# multibyte characters (--enable-multibyte).
#
# Outputs the character converted from Unicode into the local representation.
# (The conversion is done within the shell, using whatever facilities
# the C library provides.)
#
# When used as a zle widget, the character is inserted at the cursor
# position. With a numeric argument, preview in status line; outside zle,
# print character (and newline) to standard output.
#
# The set of accented characters is reasonably complete up to U+0180, the
# set of special characters less so. However, it mostly gives up at that
# point. Adding new Unicode characters is easy, however. Please send any
# additions to zsh-workers@sunsite.dk .
#
# Some of the accent codes are a little more obscure than others.
# Only the base character changes for upper case: A with circle is "o A".
# ` Grave
# ' Acute
# d Double acute
# ^ Circumflex
# ~ Tilde
# " Diaeresis (Umlaut)
# o Circle
# e Ligatures ending in e or E: e A gives AE, e o gives oe, etc.
# j Ligatures ending in j or J: ij or IJ
# c Cedilla
# / Stroke through character
# - Macron. (A horizonal bar over the letter.)
# u Breve. (A shallow dish shape over the letter.)
# . Dot above
# : Middle dot
# g Ogonek. (A little forward facing hook at the bottom right
# of the character. The "g" stands for "Ogonek" but another
# mnemonic is that g has a squiggle below the line.)
# v Caron. (A little v over the letter.)
# s s s = Eszett (lower case only)
# h Icelandic (or Runic) edh (h d) or thorn (h t)
# m Mathematical: not (m \), multiply (m *), divide (m /), degree (m o),
# +/- (m +), superscripts 1, 2, 3 (m 1 etc.), micro (m u), quarter (m q),
# half (m h), three quarters (m t)
# p Punctuation (and currency etc.): soft space (p _), inverted ! (p !),
# cent (p C), pound sign (p l) (think lira, librum), currency (p $),
# yen (p y), broken bar (p |), section (p s), lonely diaeresis (p "),
# copyright (p C), Spanish feminine marker (p f), left guillemet (p
# <), soft hyphen (p h), registered trade mark (p R), lonely macron (p
# -), lonely acute (p '), Pilcrow (paragraph) (p p), middle dot (p :),
# lonely cedilla (p c), Spanish masculine marker (p m), right
# guillemet (p >), inverted ? (p ?), Euro sign (p e).
#
emulate -LR zsh
setopt cbases extendedglob printeightbit
local accent basechar ochar error
if [[ -n $WIDGET ]]; then
error=(zle -M)
else
error=print
fi
if (( ${+zsh_accented_chars} == 0 )); then
# The associative array zsh_accent_chars is indexed by the
# accent. The values are sets of character / Unicode pairs for
# the character with the given accent. The Unicode value is
# a hex index with no base discriminator; essentially a UCS-4 index
# with the leading zeroes suppressed.
typeset -gA zsh_accented_chars
# grave
accent=\`
zsh_accented_chars[$accent]="\
A C0 E C8 I CC O D2 U D9 a E0 e E8 i EC o F2 u F9 N 1F8 n 1F9 \
"
# acute
accent=\'
zsh_accented_chars[$accent]="\
A C1 E C9 I CD O D3 U DA Y DD a E1 e E9 i EC o F3 u FA y FD C 106 c 107 \
L 139 l 13A N 143 n 144 R 154 r 155 S 15A s 15B Z 179 z 17A \
"
# double acute
accent=d
zsh_accented_chars[$accent]="\
O 150 o 151 U 170 u 171\
"
# circumflex
accent=\^
zsh_accented_chars[$accent]="\
A C2 E CA I CE O D4 U DB a E2 e EA i EE o F4 u FB C 108 c 109 G 11C g 11d \
H 124 h 125 J 134 j 135 S 15C s 15D W 174 w 175 Y 176 y 177 \
"
# tilde
accent=\~
zsh_accented_chars[$accent]="\
A C3 E CB N D1 O D5 a E3 n F1 o F5 I 128 i 129 U 168 u 169 \
"
# diaeresis / Umlaut
accent=\"
zsh_accented_chars[$accent]="\
A C4 I CF O D6 U DC a E4 e EB i EF o F6 u FC y FF Y 178 \
"
# ring above
accent=o
zsh_accented_chars[$accent]="\
A C5 a E5 U 16E u 16F \
"
# ligature with e or E
accent=e
zsh_accented_chars[$accent]="\
A C6 a E6 O 152 o 153 \
"
# ligature with j or J
accent=j
zsh_accented_chars[$accent]="\
I 132 i 133\
"
# cedilla
accent=c
zsh_accented_chars[$accent]="\
C C7 c E7 G 122 g 123 K 136 k 137 L 13B l 13C N 145 n 146 R 156 r 157 \
S 15E s 15F T 162 t 163 \
"
# stroke through
accent=/
zsh_accented_chars[$accent]="\
O D8 o F8 D 110 d 111 H 126 h 127 L 141 l 142 T 166 t 167 b 180 \
"
# macron
accent=-
zsh_accented_chars[$accent]="\
A 100 a 101 E 112 e 113 I 12a i 12b O 14C o 14D U 16A u 16B \
"
# breve
accent=u
zsh_accented_chars[$accent]="\
A 102 a 103 E 114 e 115 G 11E g 11F I 12C i 12D O 14E o 14F U 16C u 16D \
"
# dot above
accent=.
zsh_accented_chars[$accent]="\
C 10A c 10b E 116 e 117 G 120 g 121 I 130 i 131 Z 17B z 17C \
"
# middle dot
accent=:
zsh_accented_chars[$accent]="\
L 13F l 140 \
"
# ogonek
accent=g
zsh_accented_chars[$accent]="\
A 104 a 105 E 118 e 119 I 12E i 12F U 172 u 173 \
"
# caron
accent=v
zsh_accented_chars[$accent]="\
C 10C c 10D D 10E d 10F E 11A e 11B L 13D l 13E N 147 n 148 R 158 r 159 \
S 160 s 161 T 164 t 165 Z 17D z 17E \
"
# eszett
accent=s
zsh_accented_chars[$accent]="\
s DF \
"
# edh or thorn
accent=h
zsh_accented_chars[$accent]="\
D D0 d F0 t FE \
"
# mathematical
accent=m
zsh_accented_chars[$accent]="\
\\ AC o B0 * D7 / F7 + B1 2 B2 3 B3 u B5 1 B9 q BC h BD t BE\
"
# punctuation and currency
accent=p
zsh_accented_chars[$accent]="\
_ A0 ! A1 C A2 l A3 $ A4 y A5 | A6 s A7 \" A8 C A9 f AA < AB \
h AD R AE - AF ' B4 p B6 : B7 c B8 m BA > BB ? BF e 20AC \
"
fi
read -k accent || return 1
if [[ -z $zsh_accented_chars[$accent] ]]; then
$error "No accented characters with accent: $accent"
return 1
fi
local -A charmap
charmap=(${=zsh_accented_chars[$accent]})
read -k basechar
if [[ -z $charmap[$basechar] ]]; then
$error "Accent $accent not available with character $basechar"
return 1
fi
if [[ -z $WIDGET ]]; then
[[ -t 1 ]] && print
print "\U${(l.8..0.)charmap[$basechar]}"
else
ochar="$(print -n "\U${(l.8..0.)charmap[$basechar]}")"
if (( ${+NUMERIC} )); then
$error "Character ${(l.8..0.)charmap[$basechar]}: $ochar"
else
LBUFFER+=$ochar
fi
fi
|
