summary refs log tree commit diff
diff options
context:
space:
mode:
authorPeter Stephenson <pws@users.sourceforge.net>2005-08-22 09:27:57 +0000
committerPeter Stephenson <pws@users.sourceforge.net>2005-08-22 09:27:57 +0000
commit7df83c6a1c5304506c2fd7d0444ad567493da719 (patch)
tree2bda8b80221626ab28bdb108d026229f0f3e24b9
parent5b12bb382726ae2120d109fe1d55a548313ab8c0 (diff)
downloadzsh-7df83c6a1c5304506c2fd7d0444ad567493da719.tar.gz
zsh-7df83c6a1c5304506c2fd7d0444ad567493da719.tar.xz
zsh-7df83c6a1c5304506c2fd7d0444ad567493da719.zip
21676: insert-unicode-char now insert-composed-char.
Also uses RFC 1345.
-rw-r--r--ChangeLog7
-rw-r--r--Doc/Zsh/contrib.yo236
-rw-r--r--Doc/zmacros.yo1
-rw-r--r--Functions/Zle/.distfiles33
-rw-r--r--Functions/Zle/insert-composed-char407
-rw-r--r--Functions/Zle/insert-unicode-char214
6 files changed, 573 insertions, 325 deletions
diff --git a/ChangeLog b/ChangeLog
index 1aec3a17b..587c3f23b 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+2005-08-22  Peter Stephenson  <pws@csr.com>
+
+	* 21676: Doc/zmacros.yo, Doc/Zsh/contrib.yo,
+	Functions/Zle/.distfiles, Functions/Zle/insert-composed-char,
+	Functions/Zle/insert-unicode-char: insert-unicode-char is now
+	insert-composed-char and uses RFC 1345 for composing characters.
+
 2005-08-22  Geoff Wing  <gcw@zsh.org>
 
 	* unposted: Doc/Zsh/metafaq.yo, Etc/FAQ.yo: update some
diff --git a/Doc/Zsh/contrib.yo b/Doc/Zsh/contrib.yo
index 4fce28412..a2884c4c9 100644
--- a/Doc/Zsh/contrib.yo
+++ b/Doc/Zsh/contrib.yo
@@ -660,25 +660,23 @@ This works only with the new function based completion system.
 
 example(bindkey '^Xi' incremental-complete-word)
 )
-tindex(insert-files)
-item(tt(insert-files))(
-This function allows you type a file pattern, and see the results of the
-expansion at each step.  When you hit return, all expansions are inserted
-into the command line.
-
-example(bindkey '^Xf' insert-files)
-)
-tindex(insert-unicode-char)
-item(tt(insert-unicode-char))(
-This function allows you to compose Unicode characters to be inserted
-into the command line.  The command is followed by two keys (there is
-no prompt), of which the first indicates the type of accent or special
-character, and the second indicates the base character.  Both input
-characters are always from the ASCII character set.  For best results
-zsh should have been built with support for multibyte characters
-(configured with tt(--enable-multibyte)).
-
-The character is converted from Unicode into the local representation and
+tindex(insert-composed-char)
+item(tt(insert-composed-char))(
+This function allows you to compose characters that don't appear on the
+keyboard to be inserted into the command line.  The command is followed by
+two keys corresponding to ASCII characters (there is no prompt).  For
+accented characters, the two keys are a base character followed by a code
+for the accent, while for other special characters the two characters
+together form a mnemonic for the character to be inserted.  The
+two-character codes are a subset of those given by RFC 1345 (see for
+example tt(http://www.faqs.org/rfcs/rfc1345.html)).
+
+For best results zsh should have been built with support for multibyte
+characters (configured with tt(--enable-multibyte)); however, the function
+works for the limited range of characters available in single-byte
+character sets such as ISO-8859-1.
+
+The character is converted into the local representation and
 inserted into the command line at the cursor position.
 (The conversion is done within the shell, using whatever facilities
 the C library provides.)  With a numeric argument, the character and its
@@ -688,91 +686,139 @@ The function may be run outside zle in which case it prints the character
 (together with a newline) to standard output.  Input is still read from
 keystrokes.
 
-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 tt(zsh-workers@sunsite.dk).
+The set of accented characters is reasonably complete up to Unicode
+character U+0180, the set of special characters less so.  However, it
+mostly gives up at that point.  Adding new characters is easy, however.
+Please send any additions to tt(zsh-workers@sunsite.dk).
 
-The codes for the first character are as follows:
+The codes for the second character when used to accent the first are as
+follows.  Note that not every character can take every accent.
 startsitem()
-sitem(tt(`))(
-Grave accent.
-)
-sitem(tt('))(
-Acute accent.
-)
-sitem(tt(d))(
-Double acute accent (only supported on a few letters).
-)
-sitem(tt(^))(
-Circumflex.
-)
-sitem(tt(~))(
-Tilde.
-)
-sitem(tt("))(
-Diaeresis (Umlaut).
-)
-sitem(tt(o))(
-Circle over the base character.
-)
-sitem(tt(e))(
-Ligatures ending in e or E: tt(e A) gives AE, tt(e o) gives oe, etc.
-)
-sitem(tt(j))(
-Ligatures ending in j or J: ij or IJ.
-)
-sitem(tt(c))(
-Cedilla.
+sitem(tt(!))(Grave.)
+sitem(tt(RQUOTE()))(Acute.)
+sitem(tt(>))(Circumflex.)
+sitem(tt(?))(Tilde.  (This is not tt(~) as RFC 1345 does not assume that
+character is present on the keyboard.))
+sitem(tt(-))(Macron.  (A horizonal bar over the base character.))
+sitem(tt(LPAR()))(Breve.  (A shallow dish shape over the base character.))
+sitem(tt(.))(Dot above the base character, or in the case of tt(i) no dot,
+or in the case of tt(L) and tt(l) a centered dot.)
+sitem(tt(:))(Diaeresis (Umlaut).)
+sitem(tt(c))(Cedilla.)
+sitem(tt(_))(Underline, however there are currently no underlined characters.)
+sitem(tt(/))(Stroke through the base character.)
+sitem(tt("))(Double acute (only supported on a few letters).)
+sitem(tt(;))(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.))
+sitem(tt(<))(Caron.  (A little v over the letter.))
+sitem(tt(0))(Circle over the base character.)
+sitem(tt(2))(Hook over the base character.)
+sitem(tt(9))(Horn over the base character.)
+endsitem()
+
+The following other two-character sequences are understood.
+
+startitem()
+item(ASCII characters)(
+These are already present on most keyboards:
+startsitem()
+sitem(tt(<LPAR()))(Left square bracket)
+sitem(tt(//))(Backslash (solidus))
+sitem(tt(RPAR()>))(Right square bracket)
+sitem(tt(LPAR()!))(Left brace (curly bracket))
+sitem(tt(!!))(Vertical bar (pipe symbol))
+sitem(tt(!RPAR()))(Right brace (curly bracket))
+sitem(tt(RQUOTE()?))(Tilde)
+endsitem()
 )
-sitem(tt(/))(
-Stroke through the base character.
+item(Special letters)(
+Characters found in various variants of the Latin alphabet:
+startsitem()
+sitem(tt(ss))(Eszett (scafes S))
+sitem(tt(D-), tt(d-))(Eth)
+sitem(tt(TH), tt(th))(Thorn)
+sitem(tt(kk))(Kra)
+sitem(tt(RQUOTE()n))(RQUOTE()n)
+sitem(tt(NG), tt(ng))(Ng)
+sitem(tt(OI), tt(oi))(Oi)
+sitem(tt(yr))(yr)
+sitem(tt(ED))(ezh)
+endsitem()
 )
-sitem(tt(-))(
-Macron.  (A horizonal bar over the base character.)
+item(Currency symbols)(
+startsitem()
+sitem(tt(Ct))(Cent)
+sitem(tt(Pd))(Pound sterling (also lira and others))
+sitem(tt(Cu))(Currency)
+sitem(tt(Ye))(Yen)
+sitem(tt(Eu))(Euro (N.B. not in RFC 1345))
+endsitem()
 )
-sitem(tt(u))(
-Breve.  (A shallow dish shape over the base character.)
+item(Punctuation characters)(
+References to "right" quotes indicate the shape (like a 9 rather than 6)
+rather than their grammatical use.  (For example, a "right" low double
+quote is used to open quotations in German.)
+startsitem()
+sitem(tt(!I))(Inverted exclamation mark)
+sitem(tt(BB))(Broken vertical bar)
+sitem(tt(SE))(Section)
+sitem(tt(Co))(Copyright)
+sitem(tt(-a))(Spanish feminine ordinal indicator)
+sitem(tt(<<))(Left guillemet)
+sitem(tt(--))(Soft hyphen)
+sitem(tt(Rg))(Registered trade mark)
+sitem(tt(PI))(Pilcrow (paragraph))
+sitem(tt(-o))(Spanish masculine ordinal indicator)
+sitem(tt(>>))(Right guillemet)
+sitem(tt(?I))(Inverted question mark)
+sitem(tt(RQUOTE()6))(Left single quote)
+sitem(tt(RQUOTE()9))(Right single quote)
+sitem(tt(.9))("Right" low quote)
+sitem(tt(9+RQUOTE()))(Reversed "right" quote)
+sitem(tt("6))(Left double quote)
+sitem(tt("9))(Right double quote)
+sitem(tt(:9))("Right" low double quote)
+sitem(tt(9"))(Reversed "right" double quote)
+sitem(tt(/-))(Dagger)
+sitem(tt(/=))(Double dagger)
+endsitem()
 )
-sitem(tt(.))(
-Dot above the base character
+item(Mathematical symbols)(
+startsitem()
+sitem(tt(DG))(Degree)
+sitem(tt(+-))(+/- sign)
+sitem(tt(2S))(Superscript 2)
+sitem(tt(3S))(Superscript 3)
+sitem(tt(1S))(Superscript 1)
+sitem(tt(My))(Micro)
+sitem(tt(.M))(Middle dot)
+sitem(tt(14))(Quarter)
+sitem(tt(12))(Half)
+sitem(tt(34))(Three quarters)
+sitem(tt(*X))(Multiplication)
+sitem(tt(-:))(Division)
+endsitem()
 )
-sitem(tt(:))(
-A dot in the middle plane of the base character
+item(Accents on their own)(
+startsitem()
+sitem(tt(RQUOTE()>))(Circumflex (same as caret, tt(^)))
+sitem(tt(RQUOTE()!))(Grave (same as backtick, tt(`)))
+sitem(tt(RQUOTE(),))(Cedilla)
+sitem(tt(RQUOTE():))(Diaeresis (Umlaut))
+sitem(tt(RQUOTE()m))(Macron)
+sitem(tt(RQUOTE()RQUOTE()))(Acute)
+endsitem()
 )
-sitem(tt(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.)
-)
-sitem(tt(v))(
-Caron.  (A little v over the letter.)
-)
-sitem(tt(s))(
-Used only as tt(s s), a german Eszett or "scharfes S" ligature.
-)
-sitem(tt(h))(
-Icelandic (or Runic) edh (tt(h d)) or thorn (tt(h t)).
-)
-sitem(tt(m))(
-Various mathematical characters: not (tt(m \)), multiply (tt(m *)), divide
-(tt(m /)), degree (tt(m o)), +/- (tt(m +)), superscripts 1, 2, 3 (tt(m 1),
-etc.), micro (tt(m u)), quarter (tt(m q)), half (tt(m h)), three quarters
-(tt(m t)).
-)
-sitem(tt(p))(
-Various punctuation and currency characters (any non-mathematical symbol
-that is not part of a word):  soft space (tt(p _)), inverted ! (tt(p !)),
-cent (tt(p %)), pound sign (tt(p l)) (think lira, librum), currency (tt(p
-$)), yen (tt(p y)), broken bar (tt(p |)), section sign (tt(p s)), lonely
-diaeresis (tt(p ")), copyright sign (tt(p C)), Spanish feminine marker
-(tt(p f)), left guillemet (tt(p <)), soft hyphen (tt(p h)), registered
-trade mark (tt(p R)), lonely macron (tt(p -)), lonely acute (tt(p ')),
-Pilcrow (paragraph) sign (tt(p p)), middle dot (tt(p :)),
-lonely cedilla (tt(p c)), Spanish masculine marker (tt(p m)), right
-guillemet (tt(p >)), inverted ? (tt(p ?)), Euro sign (tt(p e)).
+enditem()
 )
-endsitem()
+tindex(insert-files)
+item(tt(insert-files))(
+This function allows you type a file pattern, and see the results of the
+expansion at each step.  When you hit return, all expansions are inserted
+into the command line.
+
+example(bindkey '^Xf' insert-files)
 )
 tindex(narrow-to-region)
 tindex(narrow-to-region-invisible)
diff --git a/Doc/zmacros.yo b/Doc/zmacros.yo
index 882abf41a..1c3319059 100644
--- a/Doc/zmacros.yo
+++ b/Doc/zmacros.yo
@@ -17,6 +17,7 @@ DEFINEMACRO(redef)(3)(\
   DEFINEMACRO(ARG1)(ARG2)(ARG3)\
 )
 
+DEFINEMACRO(RQUOTE)(0)(CHAR(39))
 DEFINEMACRO(LPAR)(0)(CHAR(40))
 DEFINEMACRO(RPAR)(0)(CHAR(41))
 DEFINEMACRO(PLUS)(0)(CHAR(43))
diff --git a/Functions/Zle/.distfiles b/Functions/Zle/.distfiles
index 499f33b6f..c6852732f 100644
--- a/Functions/Zle/.distfiles
+++ b/Functions/Zle/.distfiles
@@ -1,19 +1,20 @@
 DISTFILES_SRC='
 .distfiles
-cycle-completion-positions  incarg                      predict-on
-edit-command-line           incremental-complete-word   smart-insert-last-word
-history-search-end          insert-files
-copy-earlier-word
-down-line-or-beginning-search
-up-line-or-beginning-search
-narrow-to-region narrow-to-region-invisible
-read-from-minibuffer replace-string
-backward-kill-word-match backward-word-match capitalize-word-match
-down-case-word-match forward-word-match kill-word-match
-match-words-by-style select-word-style transpose-words-match
-up-case-word-match
-delete-whole-word-match quote-and-complete-word url-quote-magic
-zed-set-file-name history-pattern-search
-keeper
-which-command
+backward-kill-word-match       backward-word-match
+capitalize-word-match          copy-earlier-word
+cycle-completion-positions     delete-whole-word-match
+down-case-word-match           down-line-or-beginning-search
+edit-command-line              forward-word-match
+history-pattern-search         history-search-end
+incarg                         incremental-complete-word
+insert-composed-char           insert-files
+keeper                         kill-word-match
+match-words-by-style           narrow-to-region
+narrow-to-region-invisible     predict-on
+quote-and-complete-word        read-from-minibuffer
+replace-string                 select-word-style
+smart-insert-last-word         transpose-words-match
+up-case-word-match             up-line-or-beginning-search
+url-quote-magic                which-command
+zed-set-file-name
 '
diff --git a/Functions/Zle/insert-composed-char b/Functions/Zle/insert-composed-char
new file mode 100644
index 000000000..60a42e089
--- /dev/null
+++ b/Functions/Zle/insert-composed-char
@@ -0,0 +1,407 @@
+# Accented characters.  Inputs two keys.  There are two types: those
+# with a base character followed by an accent (see below for codes for
+# accents), and those with a two-character mnemonic for the composed
+# character.  These are (with the exception of the Euro) the codes
+# given by RFC 1345.  Note that some codes in RFC 1345 require three
+# characters to be input; none of these are handled.
+#
+# For best results zsh should have been built with support for
+# multibyte characters (--enable-multibyte), but single character sets
+# also work.
+#
+# 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.
+#  !   Grave
+#  '   Acute
+#  >   Circumflex
+#  ?   Tilde
+#  -   Macron.  (A horizonal bar over the letter.)
+#  (   Breve.  (A shallow dish shape over the letter.)
+#  .   Dot above, or no dot with lower case i, or dot in the middle of L or l.
+#  :   Diaeresis (Umlaut)
+#  ,   Cedilla
+#  _   Underline (none of these currently)
+#  /   Stroke through character
+#  "   Double acute
+#  ;   Ogonek.  (A little forward facing hook at the bottom right
+#      of the character.)
+#  <   Caron.  (A little v over the letter.)
+#  0   Circle
+#  2   Hook
+#  9   Horn
+# Hence A! is upper case A with a grave, c, is lower case c with cedilla.
+#
+# Some other composed charaters:
+# Various ligatures:
+#  AE ae OE oe IJ ij
+#
+# ASCII characters not on all keyboards:
+#  <(           [
+#  //           \
+#  )>           ]
+#  (!           {
+#  !!           |
+#  !)           }
+#  '?           ~
+#
+# Special letters:
+#  ss		Eszett (schafes S)
+#  D- d- TH th  Eth and thorn
+#  kk           kra
+#  'n           'n
+#  NG ng        ng
+#  OI oi        OI
+#  yr           yr
+#  ED           ezh
+#
+# Currency symbols:
+#  Ct           Cent
+#  Pd           Pound sterling
+#  Cu           Currency
+#  Ye           Yen
+#  Eu           Euro (not in RFC 1345 but logical)
+#
+# Punctuation
+#  !I           Inverted !
+#  BB           Broken vertical bar
+#  SE           Section
+#  Co           Copyright
+#  -a           Spanish feminine ordinal indicator
+#  <<           Left guillemet
+#  --           Soft hyphen
+#  Rg           Registered trade mark
+#  PI           Pilcrow (paragraph)
+#  -o           Spanish masculine ordinal indicator
+#  >>           Right guillemet
+#  ?I           Inverted question mark
+#  '6           Left single quote
+#  '9           Right single quote
+#  .9           "Right" low quote
+#  9'           Reversed "right" quote
+#  "6           Left double quote
+#  "9           Right double quote
+#  :9           "Right" low double quote
+#  9"           Reversed "right" double quote
+#  /-           Dagger
+#  /=           Double dagger
+#
+# Mathematical
+#  DG           Degree
+#  +-           +/-
+#  2S           Superscript 2
+#  3S           Superscript 3
+#  My           Micro
+#  .M           Middle dot
+#  1S           Superscript 1
+#  14           Quarter
+#  12           Half
+#  34           Three quarters
+#  *X           Multiplication
+#  -:           Division
+#
+# Accents with no base character
+# '>            Circumflex (caret)
+# '!            Grave (backtick)
+# ',            Cedilla
+# ':            Diaeresis (Umlaut)
+# 'm            Macron
+# ''            Acute
+
+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[$accent]="\
+A C1 E C9 I CD O D3 U DA Y DD a E1 e E9 i EC o F3 u FA y FD C 106 c 107 \
+L 139 l 13A N 143 n 144 R 154 r 155 S 15A s 15B Z 179 z 17A \
+"
+  # circumflex
+  accent=\>
+  zsh_accented_chars[$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[$accent]="\
+A C3 E CB N D1 O D5 a E3 n F1 o F5 I 128 i 129 U 168 u 169 \
+"
+  # macron (d-, D- give eth)
+  accent=-
+  zsh_accented_chars[$accent]="\
+A 100 a 101 d F0 D D0 E 112 e 113 I 12a i 12b O 14C o 14D U 16A u 16B \
+"
+  # breve
+  accent=\(
+  zsh_accented_chars[$accent]="\
+A 102 a 103 E 114 e 115 G 11E g 11F I 12C i 12D O 14E o 14F U 16C u 16D \
+"
+  # dot above, small i with no dot, or l with middle dot
+  accent=.
+  zsh_accented_chars[$accent]="\
+C 10A c 10b E 116 e 117 G 120 g 121 I 130 i 131 L 13F l 140 Z 17B z 17C \
+"
+  # diaeresis / Umlaut
+  accent=:
+  zsh_accented_chars[$accent]="\
+A C4 I CF O D6 U DC a E4 e EB i EF o F6 u FC y FF Y 178 \
+"
+  # cedilla
+  accent=,
+  zsh_accented_chars[$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 \
+"
+  # underline (_) would go here
+  # stroke through
+  accent=/
+  zsh_accented_chars[$accent]="\
+O D8 o F8 D 110 d 111 H 126 h 127 L 141 l 142 T 166 t 167 b 180 \
+"
+  # double acute
+  accent=\"
+  zsh_accented_chars[$accent]="\
+O 150 o 151 U 170 u 171\
+"
+  # ogonek
+  accent=\;
+  zsh_accented_chars[$accent]="\
+A 104 a 105 E 118 e 119 I 12E i 12F U 172 u 173 \
+"
+  # caron
+  accent=\<
+  zsh_accented_chars[$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 \
+"
+  # ring above
+  accent=0
+  zsh_accented_chars[$accent]="\
+A C5 a E5 U 16E u 16F \
+"
+  # hook above
+  accent=2
+  zsh_accented_chars[$accent]="\
+A 1EA2 a 1EA3 E 1EBA e 1EBA \
+"
+  # horn, also right quotation marks
+  accent=9
+  zsh_accented_chars[$accent]="\
+O 1A0 o 1A1 U 1Af u 1b0 ' 2019 . 201A \" 201D : 201E \
+"
+  # left quotation marks
+  accent=6
+  zsh_accented_chars[$accent]="\
+' 2018 \" 201C \
+"
+  # reversed quotation marks for convenience
+  accent=\'
+  zsh_accented_chars[$accent]+=" \
+9 201B \
+"
+  accent=\"
+  zsh_accented_chars[$accent]+=" \
+9 201F \
+"
+
+  # ligature with E
+  accent=e
+  zsh_accented_chars[$accent]="\
+A C6 O 152 \
+"
+  # ligature with e
+  accent=e
+  zsh_accented_chars[$accent]="\
+a E6 o 153 \
+"
+  # ligature with J
+  accent=J
+  zsh_accented_chars[$accent]="\
+I 132 \
+"
+  # ligature with j
+  accent=j
+  zsh_accented_chars[$accent]="\
+i 133 \
+"
+  # eszett
+  accent=s
+  zsh_accented_chars[$accent]="\
+s DF \
+"
+  # upper case thorn
+  accent=H
+  zsh_accented_chars[$accent]="\
+T DE \
+"
+  # lower case thorn
+  accent=h
+  zsh_accented_chars[$accent]="\
+t FE \
+"
+
+  # Remaining characters are handled as separate pairs.
+  # We need to remember that the assoc array is keyed by the second character.
+  # Left square bracket
+  accent=\(
+  zsh_accented_chars[$accent]+=" < 5B"
+  # Reverse solidus (backslash to you and me).
+  accent=/
+  zsh_accented_chars[$accent]+=" / 5C"
+  # Right square bracket, circumflex
+  accent=\>
+  zsh_accented_chars[$accent]+=" ) 5D ' 5E"
+  # Grave accent
+  accent=\!
+  zsh_accented_chars[$accent]+=" ' 60"
+  # diglyphys for (usually) standard characters {, |, }, ~
+  accent=\!
+  zsh_accented_chars[$accent]+=" ( 7B"
+  zsh_accented_chars[$accent]+=" ! 7C"
+  accent=\)
+  zsh_accented_chars[$accent]+=" ! 7D"
+  accent=\?
+  zsh_accented_chars[$accent]+=" ' 7E"
+  # non-breaking space
+  zsh_accented_chars[S]+=" N A0"
+  # inverted exclamation mark
+  zsh_accented_chars[I]+=" ! A1"
+  # cent
+  zsh_accented_chars[t]+=" C A2"
+  # pound sterling
+  zsh_accented_chars[d]+=" P A3"
+  # currency
+  zsh_accented_chars[u]+=" C A4"
+  # yen
+  zsh_accented_chars[e]+=" Y A5"
+  # broken bar
+  zsh_accented_chars[B]+=" B A6"
+  # section
+  zsh_accented_chars[E]+=" S A7"
+  # lonely diaeresis
+  zsh_accented_chars[:]+=" ' A8"
+  # copyright
+  zsh_accented_chars[o]+=" C A9"
+  # spanish feminine ordinal
+  zsh_accented_chars[a]+=" - AA"
+  # left guillemet
+  accent=\<
+  zsh_accented_chars[$accent]+=" < AB"
+  zsh_accented_chars[O]+=" N AC"
+  # soft hyphen
+  zsh_accented_chars[-]+=" - AD"
+  # registered
+  zsh_accented_chars[g]+=" R AE"
+  # lonely macron
+  zsh_accented_chars[m]+=" ' AF"
+  # degree
+  zsh_accented_chars[G]+=" D B0"
+  # +/-
+  zsh_accented_chars[-]+=" + B1"
+  # superscripts
+  zsh_accented_chars[S]+=" 2 B2 3 B3"
+  # lonely acute
+  accent=\'
+  zsh_accented_chars[$accent]+=" ' B4"
+  # micro
+  zsh_accented_chars[y]+=" M B5"
+  # pilcrow (paragraph)
+  zsh_accented_chars[I]+=" P B6"
+  # Middle dot
+  zsh_accented_chars[M]+=" . B7"
+  # Lonely cedilla
+  zsh_accented_chars[,]+=" ' B8"
+  # Superscript one
+  zsh_accented_chars[S]+=" 1 B9"
+  # spanish masculine ordinal
+  zsh_accented_chars[o]+=" - BA"
+  # right guillemet
+  accent=\>
+  zsh_accented_chars[$accent]+=" > BB"
+  # fractions
+  zsh_accented_chars[4]+=" 1 BC 3 BE"
+  zsh_accented_chars[2]+=" 1 BD"
+  # inverted question mark
+  zsh_accented_chars[I]+=" ? BF"
+  # multiplication
+  zsh_accented_chars[X]+=" * D7"
+  # division
+  zsh_accented_chars[:]+=" - F7"
+  # kra
+  zsh_accented_chars[k]+=" k 138"
+  # apostrophe n
+  zsh_accented_chars[n]+=" ' 149"
+  # Lappish ng
+  zsh_accented_chars[G]+=" N 14A"
+  zsh_accented_chars[g]+=" n 14B"
+  # OI
+  zsh_accented_chars[I]+=" O 1A2"
+  zsh_accented_chars[i]+=" o 1A3"
+  # yr
+  zsh_accented_chars[r]+=" y 1A6"
+  # ezh
+  zsh_accented_chars[D]+=" E 1B7"
+  # euro (I invented this but it's logical)
+  zsh_accented_chars[u]+=" E 20AC"
+  # dagger and double dagger
+  zsh_accented_chars[-]+=" / 2020"
+  zsh_accented_chars[=]+=" / 2021"
+fi
+
+read -k basechar || return 1
+read -k accent || return 1
+
+local -A charmap
+charmap=(${=zsh_accented_chars[$accent]})
+
+if [[ ${#charmap} -eq 0 || -z $charmap[$basechar] ]]; then
+  $error "Combination ${basechar}${accent} is not available."
+  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
diff --git a/Functions/Zle/insert-unicode-char b/Functions/Zle/insert-unicode-char
deleted file mode 100644
index f8767fdd2..000000000
--- a/Functions/Zle/insert-unicode-char
+++ /dev/null
@@ -1,214 +0,0 @@
-# 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