zsh/Functions/Zle/insert-composed-char

# 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@zsh.org .
#
# 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
#  -1           Hyphen
#  -N           en dash
#  -M           em dash
#  -3           horizontal bar
#  :3           vertical ellipsis
#  .3           horizontal midline ellipsis
#  !2           double vertical line
#  =2           double low line
#  '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
#  %0           Per mille
#
# Accents with no base character
# '>            Circumflex (caret)
# '!            Grave (backtick)
# ',            Cedilla
# ':            Diaeresis (Umlaut)
# 'm            Macron
# ''            Acute

emulate -L 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
  # Save quite a lot of memory by running and then erasing
  # the function that defines the characters.
  autoload -U define-composed-chars
  define-composed-chars
  unfunction define-composed-chars
fi

if (( $# )); then
  basechar=${1[1]}
  if [[ $1 = ? ]]; then
    shift
  else
    1=${1[2,-1]}
  fi
else
  read -k basechar || return 1
fi

if (( $# )); then
  accent=${1[1]}
else
  read -k accent || return 1
fi

local -A charmap
# just in case someone is monkeying with IFS...
charmap=(${(s. .)zsh_accented_chars[$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