├── doc
    ├── license.txt
    ├── TODO
    └── xorg-compose-extracts
├── examples
    ├── .gitignore
    ├── .XCompose.sample
    └── dead.xcompose
├── .gitignore
├── bin
    ├── check
    ├── checklines.py
    ├── make-dead-compose.rb
    ├── make-keysymdef.rb
    ├── scan4dups.py
    ├── treeprint.py
    ├── xcompose_parser.rb
    └── keysymdef.rb
├── README
└── xcompose


/doc/license.txt:
--------------------------------------------------------------------------------
1 | Public domain.
2 | 


--------------------------------------------------------------------------------
/examples/.gitignore:
--------------------------------------------------------------------------------
1 | !dead.xcompose
2 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | .#*
2 | #~
3 | dead.xcompose
4 | 


--------------------------------------------------------------------------------
/doc/TODO:
--------------------------------------------------------------------------------
 1 | Check automatically for invalid keysyms
 2 | 
 3 | See xcompose for more FIXMEs
 4 | 
 5 | Fix checklines.py warnings and errors
 6 | 
 7 | Evaluate scan4dups and treeprint to see if they can be removed
 8 | 
 9 | Write an overall test script
10 | 
11 | Have locale-specific sequences where necessary; check for dupes with
12 | all locales.
13 | 
14 | Eliminate spelt-out words, making sequences more language-independent.
15 | 


--------------------------------------------------------------------------------
/bin/check:
--------------------------------------------------------------------------------
 1 | #!/bin/bash
 2 | 
 3 | parser="bin/xcompose_parser.rb"
 4 | ignores="
 5 | xcompose:.*Compose:.*<Multi_key><space><comma> -> ⁣ vs. ¸
 6 | xcompose:.*Compose:.*<Multi_key><slash><slash> -> ∕ vs. \
 7 | xcompose:.*Compose.*<Multi_key><exclam><question> -> ⸘ vs. ‽
 8 | xcompose:.*Compose.*<Multi_key><plus><plus> -> ‡ vs. 
 9 | "
10 | 
11 | files="/usr/share/X11/locale/en_US.UTF-8/Compose"
12 | files+=" xcompose"
13 | 
14 | 
15 | 
16 | old_ifs="$IFS"
17 | ifs="
18 | "
19 | ignore_regexp='\\('
20 | for line in $ignores; do
21 |     ignore_regexp+="${line}\\|"
22 | done
23 | ignore_regexp+='\\)'
24 | ifs="$old_ifs"
25 | 
26 | $parser -q $files | grep -v "$ignore_regexp" 


--------------------------------------------------------------------------------
/examples/.XCompose.sample:
--------------------------------------------------------------------------------
 1 | # -*- coding: utf-8; mode: conf -*-
 2 | # vim: encoding=utf-8 ft=conf
 3 | 
 4 | # Pulls default X configurations from locale;
 5 | # e.g. /usr/share/X11/locale/en_US.UTF-8/Compose
 6 | include "%L"
 7 | 
 8 | # Brazilian users with an en_US.UTF-8 locale might want this instead
 9 | # of "include %L".
10 | #
11 | # include "/usr/share/X11/locale/pt_BR.UTF-8/Compose"
12 | 
13 | # Adjust /usr/local/share to your installation path.
14 | include "/usr/local/share/pointless-xcompose/xcompose"
15 | 
16 | # If you use a layout with X deadkeys, use bin/make-dead-compose.rb to
17 | # create this file.  See the README.
18 | include "/usr/local/share/pointless-xcompose/dead.xcompose"
19 | 


--------------------------------------------------------------------------------
/bin/checklines.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env python3
 2 | 
 3 | # From purpleposeidon!
 4 | 
 5 | from unicodedata import name
 6 | import re
 7 | import sys
 8 | 
 9 | for line in sys.stdin:
10 |   line=line.strip()
11 |   if not line or line[0]=="#":
12 |     continue
13 |   match=re.match(r'\s*(.*):\s*"(.*?)"\s*(\S*)\s*(#.*)?', line)
14 |   if not match:
15 |     print("({0})".format(line))
16 |     continue
17 |   (keystrokes, char, num, comments)=match.groups()
18 |   nummatch=re.match(r'U([0-9A-Fa-f]+)', num)
19 |   if not nummatch:
20 |     print("Number not parsed: {0}".format(line))
21 |     continue
22 |   x=int(nummatch.group(1),0x10)
23 |   c=chr(x)
24 |   try:
25 |     if c != char:
26 |       print(line)
27 |       print("\tLine's char: {0} ({1})".format(char, name(char)))
28 |       print("\tLine's number: {0:X}".format(x))
29 |       print("\tChar gives number: {0:X}".format(ord(char)))
30 |       print("\tNumber gives character: {0} ({1})".format(c, name(c)))
31 |   except Exception as e:
32 |     print("{0}\n\t{1}".format(line, e))
33 | 


--------------------------------------------------------------------------------
/examples/dead.xcompose:
--------------------------------------------------------------------------------
 1 | # Autogenerated by make-dead-compose.rb at 2009-06-13 13:38:48 GMT
 2 | 
 3 | # Starting abbrevs.xcompose.
 4 | 
 5 | # Starting arrows.xcompose.
 6 | 
 7 | # Starting bullets.xcompose.
 8 | 
 9 | # Starting cjk.xcompose.
10 | <Multi_key> <dead_tilde> <dead_tilde>: "〜" U301C # WAVE DASH
11 | 
12 | # Starting dashes-hyphens.xcompose.
13 | <Multi_key> <minus> <dead_tilde>:         "⁓" U2053 # SWUNG DASH
14 | <Multi_key> <dead_tilde> <minus>:         "⁓" U2053 # SWUNG DASH
15 | 
16 | # Starting dingbats.xcompose.
17 | 
18 | # Starting enclosed.xcompose.
19 | 
20 | # Starting fractions.xcompose.
21 | 
22 | # Starting historical.xcompose.
23 | 
24 | # Starting hyphen-macron.xcompose.
25 | 
26 | # Starting invisible.xcompose.
27 | 
28 | # Starting math.xcompose.
29 | 
30 | # Starting typographic.xcompose.
31 | <Multi_key> <dead_circumflex> <period>: "·" U00B7 # MIDDLE DOT
32 | <Multi_key> <dead_diaeresis> <parenleft>: "‟" U201F # DOUBLE HIGH-REVERSED-9
33 | <Multi_key> <parenleft> <dead_diaeresis>: "‟" U201F # DOUBLE HIGH-REVERSED-9
34 | <Multi_key> <dead_acute> <dead_acute>   : "’"   U2019 # RIGHT SINGLE QUOTATION MARK
35 | 


--------------------------------------------------------------------------------
/bin/make-dead-compose.rb:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env ruby1.9.1
 2 | require 'pp'
 3 | require File.dirname(__FILE__) + '/keysymdef.rb'
 4 | require File.dirname(__FILE__) + '/xcompose_parser.rb'
 5 | 
 6 | exit if ARGV.size == 0
 7 | files = ARGV.collect do |fname|
 8 |   if not File.readable?(fname)
 9 |     $stderr.puts("Error: Cannot read file #{fname}.")
10 |     exit 1
11 |   end
12 | end
13 | 
14 | Map = {
15 |   '<apostrophe>' => '<dead_acute>',
16 |   '<quotedbl>' => '<dead_diaeresis>',
17 |   '<asciicircum>' => '<dead_circumflex>',
18 |   '<asciitilde>' => '<dead_tilde>'
19 | }
20 | 
21 | def has_undead(str)
22 |   Map.keys.each do |undead|
23 |     return true if str.match(undead)
24 |   end
25 |   false
26 | end
27 | 
28 | def deadize(str)
29 |   out = str
30 |   Map.keys.each do |undead|
31 |     out.gsub!(undead, Map[undead])
32 |   end
33 |   out
34 | end
35 | 
36 | puts <<EOF
37 | # Autogenerated by #{File.basename $0} at #{Time.utc(*Time.now.to_a).strftime('%Y-%m-%d %H:%M:%S %Z')}
38 | EOF
39 | 
40 | buffer=[]
41 | ARGV.each do |fname|
42 |   puts "\n# Starting #{fname}."
43 |   File.open(fname, 'r') do |f|
44 |     f.each_line do |l|
45 |       next if l.match(/^#/)
46 |       if has_undead(l)
47 |         dead = deadize(l)
48 |         if not buffer.member? dead
49 |           puts dead
50 |           buffer << dead
51 |         end
52 |       end
53 |     end
54 |   end
55 | end
56 | 


--------------------------------------------------------------------------------
/bin/make-keysymdef.rb:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env ruby1.9.1
 2 | # -*- coding: utf-8 -*-
 3 | module KeysymdefParser
 4 |   DefaultHeaderPath='/usr/include/X11/keysymdef.h'
 5 |   def self.parse(input_path=nil)
 6 |     input_path ||= DefaultHeaderPath
 7 | 
 8 |     if input_path.respond_to? :read
 9 |       input = input_path
10 |     else
11 |       input = File.open(input_path, 'r')
12 |     end
13 | 
14 |     result = {}
15 |     input.each_line do |l|
16 | 
17 |       # From the file:
18 |       #
19 |       #    Where a keysym corresponds one‐to‐one to an ISO 10646 /
20 |       #    Unicode character, this is noted in a comment that provides
21 |       #    both the U+xxxx Unicode position, as well as the official
22 |       #    Unicode name of the character.
23 |       #
24 |       # The regexp below is derived from the file.
25 | 
26 |       if m=l.match(%r{^#define XK_(\w+)\s+0x[a-fA-F0-9]+\s*/\*\s*\(?U\+?([0-9A-Fa-f]+) .*\)?\*/\s*$})
27 |         result[m[1]] = [m[2].to_i(16)].pack('U')
28 |       end
29 |     end
30 |     result
31 |   end
32 | end
33 | 
34 | if __FILE__ == $0
35 |   require 'date'
36 | 
37 |   def quote(name)
38 |     '"' + name.gsub('\\','\\\\\\\\').gsub('"','\\"') + '"'
39 |   end
40 | 
41 |   hash=KeysymdefParser::parse(ARGV[0])
42 |   max_name_len = (hash.keys.map{|k| k.length}.sort)[-1]
43 | 
44 |   puts(<<EOF
45 | # -*- coding: utf-8 -*-
46 | # Autogenerated by #{$0} at #{Date::today}.
47 | # First line of input file was:
48 | # #{File.open(KeysymdefParser::DefaultHeaderPath, 'r').readline}
49 | 
50 | module Keysymdef
51 |   Keysyms = {
52 | EOF
53 |   )
54 |  
55 | 
56 |   hash.keys.sort.each do |key|
57 |     puts(format('    %*s => %s,', -max_name_len, quote(key), quote(hash[key])))
58 |   end
59 |   puts "  }"
60 |   puts "end"
61 | end
62 | 
63 | 


--------------------------------------------------------------------------------
/bin/scan4dups.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env python
 2 | 
 3 | import sys
 4 | import re
 5 | 
 6 | 
 7 | listing={}
 8 | 
 9 | try:
10 |     while True:
11 |         line=sys.stdin.next()
12 |         # print "((%s))"%line
13 |         startpos=0
14 |         name=''
15 |         dupsfound=[]
16 |         while True:
17 |             m=re.match("\s*<(\w+)>",line[startpos:])
18 |             if not m:
19 |                 break
20 |             word=m.group(1)
21 |             name+=' '+word
22 |             startpos+=m.end()
23 |         if startpos<=0:
24 |             continue
25 |         m=re.match(r'[^"]*"(.+)"',line)
26 |         if not m:
27 |             # shouldn't happen, but just in case
28 |             val='???'
29 |             print "couldn't make sense of line: "+line
30 |         else:
31 |             val=m.group(1)
32 |         if listing.has_key(name) and not re.search(r'INTENTIONAL CONFLICT', line):
33 |             if val != listing[name]:
34 |                 print "Exact conflict found: (%s )[%s][%s]"%(name, 
35 |                                                              listing[name], val)
36 |             else:   # It's easier to read if lines have different indentations
37 |                 print "\tRedundant definition: (%s )[%s]"%(name, val)
38 |         else:
39 |             listing[name]=val
40 | except StopIteration:
41 |     print "hit end"
42 | # NOW check for prefix conflicts:
43 | print "Checking prefixes."
44 | for key in listing.keys():
45 |     # print "Key: (%s)"%key
46 |     pref=''
47 |     # Careful when splitting.  The key always starts with a space.
48 |     for word in key.split(" ")[:-1]: # chop the last one; that'll always match.
49 |         # Skip the empty first entry
50 |         if not word:
51 |             continue
52 |         pref+=" "+word
53 |         # print "checking (%s)"%pref
54 |         if listing.has_key(pref):
55 |             print "Prefix conflict found: " \
56 |                 "(%s )[%s] vs (%s )[%s]"%(pref, listing[pref],
57 |                                           key, listing[key])
58 | 
59 |     
60 | 


--------------------------------------------------------------------------------
/bin/treeprint.py:
--------------------------------------------------------------------------------
  1 | #!/usr/bin/env python
  2 | 
  3 | import sys
  4 | import re
  5 | try:
  6 |     import unicodedata
  7 | except:
  8 |     pass
  9 | 
 10 | """
 11 | This program slurps in a .XCompose file on standard input (or several
 12 | concatenated together, since it won't follow includes) and outputs the
 13 | compose sequences in an S-expression-like syntax, showing the prefix tree
 14 | of sequences.  This should bring together some of the groups that use a
 15 | prefix-character, like * for the Greek alphabet and # for musical symbols.
 16 | And scatter other related things far and wide.  But it might be fun to look
 17 | at.
 18 | 
 19 | Prefix conflicts (in which you have a compose sequence that is the proper
 20 | prefix of another) and exact conflicts (in which you have a compose
 21 | sequence listed two with two different translations) cannot be handled
 22 | gracefully in this notation, and they are not handled gracefully by this
 23 | program.  The tie is not broken in a consistent or predictable fashion,
 24 | etc: this is a case of GIGO.  Deal with it.
 25 | """
 26 | 
 27 | def showdict(data, indent):
 28 |     first=True
 29 |     for key in sorted(data.keys()):
 30 |         value=data[key]
 31 |         if first:
 32 |             first=False
 33 |         else:
 34 |             print
 35 |         print " "*max(indent,0) + "("+key,
 36 |         # Sneaky trick: we don't want to go newline-indent over and
 37 |         # over for long sequences, i.e. cases where there is only
 38 |         # one possible follower.  So we skip the newlines in those
 39 |         # cases, and tell the next-lower iteration not to do the whole
 40 |         # indent thing by passing a negative indent.  We don't just
 41 |         # pass 0 or 1 because if another iteration *further down*
 42 |         # turns out not to be an only case, it will need to know
 43 |         # the right indent to pass along.  So a case like 
 44 |         # R-O-{CK|LL}, the O is unique after the R, so no linefeed,
 45 |         # but then the {C|L} are not unique after the O.
 46 |         if type(value)==dict:
 47 |             if len(value)>1:
 48 |                 print ""
 49 |                 showdict(value, abs(indent)+4),
 50 |             else:
 51 |                 showdict(value, -abs(indent+4)),
 52 |         else:
 53 |             print "    "+value.encode('utf-8'),
 54 |             if "-n" in sys.argv:
 55 |                 try:
 56 |                     print unicodedata.name(value),
 57 |                 except:
 58 |                     pass
 59 |         print ")",
 60 | 
 61 | listing={}
 62 | 
 63 | try:
 64 |     while True:
 65 |         line=sys.stdin.next().decode('utf-8')
 66 |         # print "((%s))"%line
 67 |         startpos=0
 68 |         name=[]
 69 |         dupsfound=[]
 70 |         while True:
 71 |             m=re.match("\s*<(\w+)>",line[startpos:])
 72 |             if not m:
 73 |                 break
 74 |             word=m.group(1)
 75 |             name.append(str(word)) # The keys are ordinary strings, not unicode
 76 |             startpos+=m.end()
 77 |         if startpos<=0:
 78 |             continue
 79 |         m=re.match(r'[^"]*"(.+?)"',line)
 80 |         if not m:
 81 |             # shouldn't happen, but just in case
 82 |             val='???'
 83 |             print "couldn't make sense of line: "+line
 84 |         else:
 85 |             val=m.group(1)
 86 |         cur=listing
 87 |         for elt in name[:-1]:
 88 |             if type(cur)==dict:
 89 |                 if not cur.has_key(elt):
 90 |                     cur[elt]={}
 91 |                 cur=cur[elt]        # This will fail for prefix conflicts
 92 |             else:
 93 |                 break           # prefix conflict
 94 |         # Presumably by now we're at the end, pointing to an empty dict.
 95 |         if type(cur)==dict:
 96 |             cur[name[-1]]=val
 97 |         else:
 98 |             # fail.  Prefix conflict.  Let's ignore it.
 99 |             pass
100 | except StopIteration:
101 |     # print "hit end"
102 |     pass
103 | 
104 | # Actually, you could get almost as nice a listing just by using yaml,
105 | # but now that we have special no-newlines-for-singletons handling,
106 | # showdict looks nicer.
107 | showdict(listing,0)
108 | 
109 | # #print "\n\n-=- YAML -=-"
110 | # import yaml
111 | # print yaml.dump(listing, default_style=r'"', allow_unicode=True)
112 | # # Huh.  Yaml "allow_unicode=True" still escapes non-BMP chars.
113 | 


--------------------------------------------------------------------------------
/README:
--------------------------------------------------------------------------------
  1 | All files in this distribution use UTF‐8 pointlessly.  Read them in a
  2 | font with good Unicode coverage — say, DejaVu Sans Mono or GNU unifont
  3 | (xfonts-unifont).
  4 | 
  5 | Introduction
  6 | ============
  7 | 
  8 | Unicode has lots of cool characters.  I mean lots and lots of cool
  9 | characters.  Enough characters to annoy all your friends with useless
 10 | charactery.  Your keyboard doesn’t have nearly enough keys to input
 11 | all them.
 12 | 
 13 | In X — the GUI system used in Linux, BSD, Solaris &c. — there are a
 14 | number of different ways to input these extra characters.  Some are
 15 | suitable for occasional use: search for the character online or in a
 16 | character map program by name, then copy and paste it or enter its
 17 | number or name.  Some are suitable for frequent use: use a “3rd Level
 18 | Shift” (typically AltGr), dead keys, or input methods.  XCompose is an
 19 | intermediate solution: each character is typed using a mnemonic
 20 | combination of a few keystrokes.  It’s not fast enough to use in every
 21 | word, but it’s fairly easy to remember (or rediscover) for characters
 22 | you might use once a day or once a fortnight, and much less annoying
 23 | than having to search online that often.
 24 | 
 25 | Most Compose sequences begin with the Compose key, also known as
 26 | Multi_key (typically assigned to the Windows Menu key or equivalent).
 27 | Dead keys (where you press an accent key, then a letter, and an
 28 | accented letter is typed) are implemented with Compose too.  X comes
 29 | with many builtin mappings described in
 30 | /usr/share/X11/locale/*/Compose, and you can add your own in
 31 | ~/.XCompose.  But what to add, and how?
 32 | 
 33 | Pointless‐XCompose provides a Compose file with thousands of extra
 34 | Compose mappings, compatible with the standard X US English Compose
 35 | file.  (I intend to make it compatible with *all* standard Compose
 36 | files.)
 37 | 
 38 | 
 39 | What’s included
 40 | ===============
 41 | 
 42 | I also included a few other potentially interesting Compose‐related
 43 | stuff, such as a selection of standard X mappings, a script to
 44 | generate deadkey variants of Compose files, &c.
 45 | 
 46 |  • doc/README:                 This.
 47 | 
 48 |  • xcompose:                   Abbreviations.
 49 |  • bin/make-dead-compose.rb:   You want to run this if you use a
 50 |                                keyboard layout with deadkeys.
 51 |  • examples/dead.xcompose:     Example output of make-dead-keys.rb for
 52 |                                everything in this package plus today’s
 53 |                                Xorg Compose table.
 54 | 
 55 |  • doc/xorg-compose-extracts:  Selected, annotated reading material.
 56 | 
 57 |  • bin/*.rb:                   Misc Ruby XCompose parsers and
 58 |                                validators.  Not likely to be
 59 |                                interesting to anyone at the moment.
 60 | 
 61 |  • doc/license.txt:            “Public domain.”
 62 | 
 63 | 
 64 | Installation
 65 | ============
 66 | 
 67 | 1. Copy or git-clone this directory.
 68 | 
 69 | 2. Skip to the next step if you don’t use X deadkeys.  If you do use
 70 |    them (for example, if you use an XKB layout like “us_intl”,
 71 |    “us(intl)”, or “br”), let’s create deadkey versions of the mappings
 72 |    now:
 73 | 
 74 |     pointless-xcompose$ ./bin/make-dead-compose.rb \
 75 |                         /usr/share/X11/locale/en_US.UTF-8/Compose \
 76 |                         /path/to/pointless-xcompose/xcompose \
 77 |                         > dead.xcompose
 78 | 
 79 |    In the next step, use dead.xcompose instead of xcompose.
 80 | 
 81 | 3. Symlink xcompose to ~/.XCompose:
 82 | 
 83 |     ln -s /path/to/pointless-xcompose/xcompose ~/.XCompose
 84 | 
 85 | 
 86 | 4. Check your Compose key setup: the command
 87 | 
 88 |     setxkbmap -print
 89 | 
 90 |    should mention “compose” in a line starting `xkb_symbols`, for example:
 91 | 
 92 |     xkb_symbols   { include "pc+us(altgr-intl)+gb:2+us:3+inet(evdev)+altwin(swap_alt_win)+level3(rwin_switch)+capslock(ctrl_modifier)+compose(ralt)"	};
 93 | 
 94 |    (near the end of the line; here it says Compose is the right Alt
 95 |    key).  If no Compose key is set up, you’ll need to configure one.
 96 |    Sadly, this works differently in different desktops, so I can’t
 97 |    give standard instructions.
 98 | 
 99 |    Once you have a Compose key configured, try it out: type “Compose +
100 |    -” (i.e., the Compose key, then the plus key, then the minus key)
101 |    and you should get “±”.
102 | 
103 | 5. Restart your apps (and perhaps X the first time) — XCompose
104 |    settings only apply for new windows.
105 | 
106 | 6. In GNOME (or GTK applications, if you know what that means),
107 |    XCompose configuration unfortunately won’t work by default; GTK
108 |    defines its own static, compile‐time, non-configurable compose
109 |    mechanism which overrides X.
110 | 
111 |    A workaround is to use the uim input method.  Sadly, how to install
112 |    and configure it varies from system to system.  The package is
113 |    probably called uim.  On Debian or Ubuntu, use im-config; on Fedora
114 |    or RedHat, use ImChooser.
115 | 
116 | 
117 | Usage
118 | =====
119 | 
120 | Read the included xcompose file to see what’s included.  The system’s
121 | mappings are in /usr/share/X11/locale/$LANG/Compose (if there’s no
122 | such directory for your locale, look in
123 | /usr/share/X11/locale/locale.dir; for example my locale, en_GB.UTF-8
124 | is listed there under en_US.UTF-8):
125 | 
126 |   en_US.UTF-8/XLC_LOCALE                  en_GB.UTF-8
127 | 
128 | 
129 | Adding your own Compose sequences
130 | =================================
131 | 
132 | One Compose sequence cannot be a prefix of another.  Suppose you have
133 | this sequence:
134 | 
135 |  • Compose . . =      → ·
136 |  • Compose . . . =    → …
137 | 
138 | Now when you type «Compose . .», X won’t print anything because it’s
139 | waiting for «Compose . . .» (IMHO it should print · and then change it
140 | to … should you type another period, but I digress).  That means you
141 | probably don’t want to make a Compose shortcut for U2A94 GREATER-THAN
142 | ABOVE SLANTED EQUAL ABOVE LESS-THAN ABOVE SLANTED EQUAL (⪔).
143 | 
144 | All the mappings here have been compared against X.org 1.6.2’s en_US
145 | Compose file for conflicts.  Several of my entries are present in X’s
146 | Compose as another sequence, but I prefer one that’s more mnemonic.
147 | The few entries that replace X mappings are marked “INTENTIONAL
148 | CONFLICT”.
149 | 
150 | Conventions:
151 | 
152 |  • Follow patterns in system Compose files. For example:
153 | 
154 |  • Termination convention (copied from X):
155 |    ◦ A repeated character: Compose v v → ✓
156 |    ◦ Where that would conflict, a period:
157 |      ‣ Compose - .      → − (true hypen)
158 |      ‣ Compose - - .    → – (en‐bar)
159 |      ‣ Compose - - -    → — (em‐bar)
160 |    (Side note: the difference between the above three characters is
161 |     small in monospaced fonts, but large in proportionals).
162 | 
163 |  • Where we conflict with the system files, do so only for characters
164 |    that have multiple definitions, and where multiple sequences follow
165 |    the same pattern, only conflict with one pattern, so that users can
166 |    use the remaining pattern(s) without being bothered with
167 |    exceptions.
168 | 
169 |  • Avoid spelling out names (rather, use an input method that allows
170 |    spelling out).
171 | 
172 | # vim: encoding=utf-8
173 | # Emacs:
174 | # Local Variables:
175 | # mode: text
176 | # fill-column: 70
177 | # eval: (turn-on-filladapt-mode)
178 | # coding: utf-8
179 | # End:
180 | 


--------------------------------------------------------------------------------
/bin/xcompose_parser.rb:
--------------------------------------------------------------------------------
  1 | #!/usr/bin/env ruby1.9.1
  2 | # -*- coding: utf-8 -*-
  3 | require 'rubygems'
  4 | require 'optparse'
  5 | require 'ostruct'
  6 | require 'log4r'
  7 | 
  8 | require 'pp'
  9 | include Log4r
 10 | 
 11 | require_relative 'keysymdef'
 12 | include Keysymdef
 13 | 
 14 | #require 'unprof'
 15 | 
 16 | module Enumerable
 17 |   # [1,2,3] -> [[1,2],[1,3],[2,3]]
 18 |   def each_pair()
 19 |     self.each_with_index do |item1, i|
 20 |       self[(i+1)..self.size].each do |item2|
 21 |         yield([item1, item2])
 22 |       end
 23 |     end
 24 |   end
 25 | 
 26 |   def each_prefix()
 27 |     0.upto(self.size-1-1) do |i|
 28 |       yield self[0..i]
 29 |     end
 30 |   end
 31 | 
 32 | end
 33 | 
 34 | 
 35 | # Parser for XCompose compose definitions.
 36 | #
 37 | # TODO: • includes
 38 | #       • "\nnn" description format
 39 | class XComposeParser
 40 |   attr_accessor :file, :parsed_lines, :logger
 41 | 
 42 |   # Index to speed mapping prefix checks.
 43 |   #
 44 |   # The format is mapping => [parser, lineno]
 45 |   @@map_index = {}
 46 |   def self.map_index
 47 |     @@map_index
 48 |   end
 49 | 
 50 |   class MapDuplicate < StandardError
 51 |   end
 52 |   class MapConflict < StandardError
 53 |   end
 54 |   class MapPrefixConflict < MapConflict
 55 |   end
 56 |   class ParseError < StandardError
 57 |     def initialize(file)
 58 |       super("Parse error at file #{@file.path}:#{@file.lineno}.")
 59 |     end
 60 |   end
 61 | 
 62 | 
 63 |   def initialize(file, logger=nil)
 64 | 
 65 |     if not file.respond_to? :read
 66 |       file = File.open(file.to_str, 'r')
 67 |     end
 68 |     @file = file
 69 | 
 70 |     if logger
 71 |       @logger = Logger.new(logger.fullname + '::' + \
 72 |                            "parser:#{@file.path}")
 73 |     else
 74 |       @logger = Logger.new("parser:#{@file.path}")
 75 |       @logger.outputters << Outputter.stdout
 76 |       @logger.level = DEBUG
 77 |     end
 78 |     @parsed_lines = []
 79 |   end
 80 | 
 81 | 
 82 |   # Parse the file; fill @parsed_lines, @@map_index.
 83 |   def parse
 84 |     @file.seek 0
 85 |     duplicates = []
 86 |     conflicts = []
 87 | 
 88 |     @file.each_line do |line|
 89 |       pline = nil
 90 | 
 91 |       if line.match(/^#/)
 92 |         @logger.debug("Skipped comment at line #{@file.lineno}")
 93 |       elsif line.match(/^\s*$/)
 94 |         @logger.debug("Skipped blank line at line #{@file.lineno}")
 95 |       elsif line.match(/^\s*include/)
 96 |         @logger.warn("Skipped include at line #{@file.lineno}")
 97 |       elsif line.index(':')
 98 |         pline = self.class.parse_line(line)
 99 |         if not pline
100 |           raise ParseError.new(@file)
101 |         else
102 |           @parsed_lines[@file.lineno] = pline
103 |         end
104 |       else
105 |         raise ParseError.new(@file)
106 |       end
107 | 
108 |       next if not pline
109 | 
110 |       if not (@@map_index.has_key?(pline[:map]))
111 |         @@map_index[pline[:map]] = [self, @file.lineno]
112 |       else # mapping already indexed!
113 |         dup_parser, dup_index = @@map_index[pline[:map]]
114 |         dup_pline = dup_parser.parsed_lines[dup_index]
115 |         if pline[:definition] == dup_pline[:definition]
116 |           duplicates << [@file.lineno,
117 |                          dup_parser, dup_index]
118 |         else
119 |           conflicts << [@file.lineno,
120 |                         dup_parser, dup_index]
121 |         end
122 |       end
123 |     end
124 | 
125 |     out="\n"
126 |     conflicts.each do |li, dup_parser, dup_index|
127 |       out += format("     %s:%d: conflicts with %s:%d (%s -> %s vs. %s)\n",
128 |                     @file.path, li,
129 |                     dup_parser.file.path, dup_index,
130 |                     @parsed_lines[li][:map],
131 |                     @parsed_lines[li][:definition],
132 |                     dup_parser.parsed_lines[dup_index][:definition])
133 |     end
134 |     duplicates.each do |li, dup_parser, dup_index|
135 |       out += format("     %s:%d: duplicate of %s:%d (%s -> %s)\n",
136 |                     @file.path, li,
137 |                     dup_parser.file.path, dup_index,
138 |                     @parsed_lines[li][:map],
139 |                     @parsed_lines[li][:definition])
140 |     end
141 |     if not conflicts.empty?
142 |       raise MapConflict.new(out)
143 |     elsif not duplicates.empty?
144 |       raise MapDuplicate.new(out)
145 |     end
146 |   end
147 | 
148 |   # Parse a singe XCompose line.
149 |   #
150 |   # Returns a hash with :map, :definition, :description, and :comment.
151 |   def self.parse_line(line)
152 |     map_side, definition_side = line.split ':'
153 |     definition, comment = definition_side.split '#'
154 |     defchar, defdesc = definition.split(/\s/).reject {|s| s.empty?}
155 | 
156 |     parsed = {}
157 | 
158 |     parsed[:map] = map_side.split(/\s/).reject {|s| s.empty?}.each do |s|
159 |       s.strip
160 |     end
161 | 
162 |     defin = defchar.strip.sub(/^["']/,'').sub(/["']$/,'')
163 |     # unquote definition
164 |     if defin == '\\"'
165 |       parsed[:definition] = '"'
166 |     elsif defin == '\\\\'
167 |       parsed[:definition] = '\\'
168 |     else
169 |       parsed[:definition] = defin
170 |     end
171 | 
172 |     parsed[:description] = defdesc.strip if defdesc
173 |     parsed[:comment] = comment.strip if comment
174 | 
175 |     parsed
176 |   end
177 | 
178 | 
179 |   class InvalidCodepoint < StandardError
180 |     def initialize(invcd)
181 |       super(invcd + " doesn't look like a codepoint")
182 |     end
183 |   end
184 | 
185 |   class UnknownKeysymname < StandardError
186 |     def initialize(keysymname)
187 |       super(format("Couldn't find keysym name `%s' in database", keysymname))
188 |     end
189 |   end
190 | 
191 |   class DescriptionConflict < StandardError
192 |     def initialize(parsed_line)
193 |       super(format("Description `%s' doesn't match definition `%s'",
194 |                    parsed_line[:description],
195 |                    parsed_line[:definition]))
196 | 
197 |     end
198 |   end
199 | 
200 |   # Utility function to convert a codepoint like U+nnn or Unnnn to
201 |   # UTF-8 string.
202 |   def self.codepoint_to_unichar(codepoint)
203 |     # get an integer out of codepoint
204 |     if not codepoint.kind_of? Integer
205 |       if codepoint.respond_to? :to_str
206 |         if m=codepoint.match(/^U\+?([0-9abcdef]+)$/i)
207 |           codepoint = m[1].to_i(16)
208 |         else
209 |           raise InvalidCodepoint.new(codepoint)
210 |         end
211 |       else
212 |         codepoint = codepoint.to_i
213 |       end
214 |     end
215 | 
216 |     [codepoint].pack('U')
217 |   end
218 | 
219 |   # Checks whether a parsed line's description matches its definition.
220 |   def self.validate_desc(parsed_line)
221 |     desc, defin = parsed_line[:description], parsed_line[:definition]
222 | 
223 |     return true if (not desc or not defin)
224 |     if desc.match(/^U\+?[0-9A-F]+$/i) # if unicode description
225 |       if (defin != codepoint_to_unichar(desc))
226 |         raise DescriptionConflict.new(parsed_line)
227 |       else
228 |         return true
229 |       end
230 |     else # keysymname description
231 |       keysymval = Keysyms[desc]
232 |       if not  keysymval
233 |         raise UnknownKeysymname.new(desc)
234 |       elsif defin != keysymval
235 |         raise DescriptionConflict.new(parsed_line)
236 |       else
237 |         return true
238 |       end
239 |     end
240 |   end
241 | 
242 |   def validate_descs()
243 |     valid=true
244 |     0.upto(@parsed_lines.size) do |i|
245 |       next if not @parsed_lines[i]
246 |       begin
247 |         self.class.validate_desc(@parsed_lines[i])
248 |         @logger.debug("#{i}: description valid.")
249 |       rescue UnknownKeysymname, DescriptionConflict, InvalidCodepoint => ex
250 |         @logger.error("#{i}: #{ex.message}")
251 |         valid = false
252 |       end
253 |     end
254 |     return valid
255 |   end
256 | 
257 |   def validate_mapping(li)
258 |     l = @parsed_lines[li]
259 |     return true if not l
260 |     l[:map].each_prefix do |pref|
261 |       conflict = @@map_index[pref]
262 |       if conflict
263 |         raise MapPrefixConflict.new(format("%s:%s: prefix conflict with %s:%s",
264 |                                            @file.path, li,
265 |                                            conflict[0].file.path, conflict[1]))
266 |       end
267 |     end
268 |     return true
269 |   end
270 | 
271 | end
272 | 
273 | 
274 | if __FILE__ == $0
275 |   l = Logger.new('xcompose_parser')
276 | 
277 |   options = OpenStruct.new
278 |   options.loglevel = WARN
279 | 
280 |   OptionParser.new {|op|
281 |     op.banner = "Usage: #{$0} [options] <Compose files...>"
282 |     op.on('l', '--loglevel LOG', 'Set loglevel <debug|info|warn|error>') do |l|
283 |       if l.downcase.match /debug/
284 |         options.loglevel = DEBUG
285 |       elsif l.downcase.match /info/
286 |         options.loglevel = INFO
287 |       elsif l.downcase.match /warn/
288 |         options.loglevel = WARN
289 |       elsif l.downcase.match /info/
290 |         options.loglevel = ERROR
291 |       end
292 |     end
293 |     op.on('d', '--debug', 'Equivalent to -l DEBUG') do |d|
294 |       options.loglevel = DEBUG if d
295 |     end
296 |     op.on('v', '--verbose', 'Equivalent to -l INFO') do |v|
297 |       options.loglevel = INFO if v
298 |     end
299 |     op.on('q', '--quiet', 'Equivalent to -l ERROR') do |q|
300 |       options.loglevel = ERROR if q
301 |     end
302 |   }.parse!
303 | 
304 |   exit 1 if not ARGV[0]
305 |   ARGV.each do |fpath|
306 |     if not File.readable? fpath
307 |       $stderr.puts "Cannot read file #{fpath}"
308 |       exit 1
309 |     end
310 |   end
311 | 
312 |   l.level=options.loglevel
313 |   l.outputters << Outputter.stdout
314 | 
315 | 
316 |   l.info("Checking syntax and mappings...")
317 |   parsers=[]
318 |   ARGV.each do |fpath|
319 |     p = XComposeParser.new(fpath, l)
320 |     begin
321 |       p.parse
322 |       p.logger.info("Parsed fine.")
323 |       parsers << p
324 |     rescue XComposeParser::MapDuplicate => ex
325 |       l.warn(ex.message)
326 |       parsers << p
327 |     rescue XComposeParser::MapConflict => ex
328 |       l.error(ex.message)
329 |     rescue XComposeParser::ParseError => ex
330 |       l.error(ex.message)
331 |       l.info("#{p.file.path} will be skipped")
332 |     end
333 |   end
334 | 
335 |   l.info("Checking for bad descriptions...")
336 | 
337 |   parsers.each do |p|
338 |     if p.validate_descs
339 |       p.logger.info("Descriptions ok.")
340 |     else
341 |       p.logger.error("Description errors.")
342 |     end
343 |   end
344 | 
345 |   l.info("Checking for mapping conflicts...")
346 | 
347 |   parsers.each do |p|
348 |     p.parsed_lines.each_index do |i|
349 |       begin
350 |         p.validate_mapping(i)
351 |       rescue XComposeParser::MapConflict => ex
352 |         p.logger.error(ex.message)
353 |       end
354 |     end
355 |   end
356 | end
357 | 


--------------------------------------------------------------------------------
/doc/xorg-compose-extracts:
--------------------------------------------------------------------------------
  1 | # -*- coding: utf-8; mode: conf -*-
  2 | # vim: encoding=utf-8 ft=conf
  3 | #
  4 | # This file is not intended for Compose inclusion; rather, it’s a
  5 | # selected extract of current (2009‒04)
  6 | # /usr/share/X11/locale/en_US.UTF-8/Compose.  There’s a lot of
  7 | # interesting mappings there, but also a lot of cruft (such as vowels
  8 | # with various permutations of piled diacritics; grep -v "WITH " and
  9 | # it gets a lot better).  I started this file for my own benefit and
 10 | # decided to include it for lazy people.  It doubles as a “X keyboard
 11 | # shortcut quick reference”.
 12 | #
 13 | # I included personal comments with ##.
 14 | #
 15 | #—leoboiko
 16 | #
 17 | 
 18 | 
 19 | ## Typography
 20 | ## ==========
 21 | 
 22 | <Multi_key> <period> <period>    	: "…"   ellipsis # HORIZONTAL ELLIPSIS
 23 | 
 24 | <Multi_key> <minus> <minus> <period> 	: "–"   U2013 # EN DASH
 25 | <Multi_key> <minus> <minus> <minus> 	: "—"   U2014 # EM DASH
 26 | ## true‐minus, true‐hyphen, and true–horizontal‐bar are absent.  see
 27 | ## my typographic.xcompose for some suggestions.
 28 | 
 29 | ## Wouldn’t <greater> <period> be more consistent with the mappings
 30 | ## for e.g. «, », –?
 31 | <Multi_key> <period> <greater>   	: "›"   U203a # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
 32 | <Multi_key> <period> <less>      	: "‹"   U2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
 33 | 
 34 | ## What’s the difference between this and the “seconds mark” ″?
 35 | <Multi_key> <quotedbl> <slash>   	: "〞"   U301e # DOUBLE PRIME QUOTATION MARK
 36 | ## And what is this one for?
 37 | <Multi_key> <quotedbl> <backslash> 	: "〝"   U301d # REVERSED DOUBLE PRIME QUOTATION MARK
 38 | 
 39 | ## These actually are fairly intuitive once you get the hang of it.
 40 | <Multi_key> <less> <less>        	: "«"   guillemotleft # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
 41 | <Multi_key> <greater> <greater>  	: "»"   guillemotright # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
 42 | <Multi_key> <less> <apostrophe>  	: "‘"   U2018 # LEFT SINGLE QUOTATION MARK
 43 | <Multi_key> <apostrophe> <less>  	: "‘"   U2018 # LEFT SINGLE QUOTATION MARK
 44 | <Multi_key> <greater> <apostrophe> 	: "’"   U2019 # RIGHT SINGLE QUOTATION MARK
 45 | <Multi_key> <apostrophe> <greater> 	: "’"   U2019 # RIGHT SINGLE QUOTATION MARK
 46 | <Multi_key> <comma> <apostrophe> 	: "‚"   U201a # SINGLE LOW-9 QUOTATION MARK
 47 | <Multi_key> <apostrophe> <comma> 	: "‚"   U201a # SINGLE LOW-9 QUOTATION MARK
 48 | <Multi_key> <less> <quotedbl>    	: "“"   U201c # LEFT DOUBLE QUOTATION MARK
 49 | <Multi_key> <quotedbl> <less>    	: "“"   U201c # LEFT DOUBLE QUOTATION MARK
 50 | <Multi_key> <greater> <quotedbl> 	: "”"   U201d # RIGHT DOUBLE QUOTATION MARK
 51 | <Multi_key> <quotedbl> <greater> 	: "”"   U201d # RIGHT DOUBLE QUOTATION MARK
 52 | <Multi_key> <comma> <quotedbl>   	: "„"   U201e # DOUBLE LOW-9 QUOTATION MARK
 53 | <Multi_key> <quotedbl> <comma>   	: "„"   U201e # DOUBLE LOW-9 QUOTATION MARK
 54 | 
 55 | ## Typography for Lawyers
 56 | <Multi_key> <s> <o>              	: "§"   section # SECTION SIGN
 57 | <Multi_key> <o> <s>              	: "§"   section # SECTION SIGN
 58 | <Multi_key> <P> <P>              	: "¶"   paragraph # PILCROW SIGN
 59 | 
 60 | ## Oldschool
 61 | 
 62 | ## This isn’t the same as English ð/Ð (dh).
 63 | <Multi_key> <minus> <d>          	: "đ"   dstroke # LATIN SMALL LETTER D WITH STROKE
 64 | <Multi_key> <minus> <D>          	: "Đ"   Dstroke # LATIN CAPITAL LETTER D WITH STROKE
 65 | 
 66 | <Multi_key> <T> <H>              	: "Þ"   THORN # LATIN CAPITAL LETTER THORN
 67 | <Multi_key> <D> <H>              	: "Ð"   ETH # LATIN CAPITAL LETTER ETH
 68 | <Multi_key> <d> <h>              	: "ð"   eth # LATIN SMALL LETTER ETH
 69 | <Multi_key> <t> <h>              	: "þ"   thorn # LATIN SMALL LETTER THORN
 70 | 
 71 | ## True Germans use essesses.
 72 | <Multi_key> <s> <s>              	: "ß"   ssharp # LATIN SMALL LETTER SHARP S
 73 | 
 74 | ## Long S is not an F dammit.  They should use <S><S> or something.
 75 | ## Well‐kown trivia: ever noticed ß is ſ+s?
 76 | <Multi_key> <f> <s>              	: "ſ"   U017f # LATIN SMALL LETTER LONG S
 77 | <Multi_key> <f> <S>              	: "ſ"   U017f # LATIN SMALL LETTER LONG S
 78 | 
 79 | <Multi_key> <o> <e>              	: "œ"   oe # LATIN SMALL LIGATURE OE
 80 | <Multi_key> <O> <E>              	: "Œ"   OE # LATIN CAPITAL LIGATURE OE
 81 | <Multi_key> <a> <e>              	: "æ"   ae # LATIN SMALL LETTER AE
 82 | <Multi_key> <A> <E>              	: "Æ"   AE # LATIN CAPITAL LETTER AE
 83 | 
 84 | 
 85 | ## Miscellaneous
 86 | ## =============
 87 | 
 88 | ## If only browsers could read this one.
 89 | <Multi_key> <space> <space>      	: " "   nobreakspace # NO-BREAK SPACE
 90 | 
 91 | <Multi_key> <space> <period>     	: " "   U2008 # PUNCTUATION SPACE
 92 | ## All the other interesting spaces are missing, and <Multi_key>
 93 | ## <space> is such a good prefix.
 94 | 
 95 | ## I prefer “( c )”, “( r )” like all other enclosed chars.
 96 | <Multi_key> <o> <c>              	: "©"   copyright # COPYRIGHT SIGN
 97 | <Multi_key> <o> <r>              	: "®"   registered # REGISTERED SIGN
 98 | 
 99 | ## These four aren’t mnemonic at all IMHO.
100 | <Multi_key> <period> <minus>    	: "·"   periodcentered # MIDDLE DOT
101 | <Multi_key> <period> <equal>    	: "•"   enfilledcircbullet # BULLET
102 | <Multi_key> <exclam> <asciicircum> 	: "¦"   brokenbar # BROKEN BAR
103 | <Multi_key> <p> <exclam>         	: "¶"   paragraph # PILCROW SIGN
104 | 
105 | <Multi_key> <exclam> <exclam>    	: "¡"   exclamdown # INVERTED EXCLAMATION MARK
106 | <Multi_key> <question> <question> 	: "¿"   questiondown # INVERTED QUESTION MARK
107 | ## …and everyone’s favourite:
108 | <Multi_key> <question> <exclam>         : "‽"   U203D # INTERROBANG
109 | <Multi_key> <exclam> <question>         : "‽"   U203D # INTERROBANG
110 | ## I want the ganborretni ⸘
111 | 
112 | <Multi_key> <plus> <minus>       	: "±"   plusminus # PLUS-MINUS SIGN
113 | 
114 | <Multi_key> <o> <o>              	: "°"   degree # DEGREE SIGN
115 | 
116 | ## Percent ÷10.
117 | <Multi_key> <percent> <o>        	: "‰"   U2030 # PER MILLE SIGN
118 | ## Obvious extension to ‱ won’n work due to XCompose substring
119 | ## conflict problem.
120 | 
121 | ## No idea how to type this sequence, but isn’t it interesting? The
122 | ## decomposed character is a negation (⫝ “non‐forking”), so the
123 | ## slashed version is an affirmative.  Both symbols are some math
124 | ## thing apparently.
125 | <Multi_key> <U2ADD> <U0338> 	: "⫝̸"   U2ADC # FORKING
126 | 
127 | ## stroking arrows! (can’t input though)
128 | <Multi_key> <slash> <leftarrow>  	: "↚"   U219A # LEFTWARDS ARROW WITH STROKE
129 | <Multi_key> <KP_Divide> <leftarrow> 	: "↚"   U219A # LEFTWARDS ARROW WITH STROKE
130 | <Multi_key> <slash> <rightarrow> 	: "↛"   U219B # RIGHTWARDS ARROW WITH STROKE
131 | <Multi_key> <KP_Divide> <rightarrow> 	: "↛"   U219B # RIGHTWARDS ARROW WITH STROKE
132 | <Multi_key> <slash> <U2194>  	: "↮"   U21AE # LEFT RIGHT ARROW WITH STROKE
133 | <Multi_key> <KP_Divide> <U2194> 	: "↮"   U21AE # LEFT RIGHT ARROW WITH STROKE
134 | 
135 | ## Super– and subscripts
136 | ## =====================
137 | 
138 | ## With keypad or not, with deadkeys or not = 4 ways to superscript
139 | <dead_circumflex> <0>            	: "⁰"   U2070 # SUPERSCRIPT ZERO
140 | <Multi_key> <asciicircum> <0>    	: "⁰"   U2070 # SUPERSCRIPT ZERO
141 | <dead_circumflex> <KP_0>         	: "⁰"   U2070 # SUPERSCRIPT ZERO
142 | <Multi_key> <asciicircum> <KP_0> 	: "⁰"   U2070 # SUPERSCRIPT ZERO
143 | ## there’s dead_circumflex and keypad variant for all sub– and superscripts.
144 | <Multi_key> <asciicircum> <1>    	: "¹"   onesuperior # SUPERSCRIPT ONE
145 | <Multi_key> <asciicircum> <2>    	: "²"   twosuperior # SUPERSCRIPT TWO
146 | ## ³,⁴, ⁵…⁰
147 | 
148 | ## Isn’t it weird how they didn’t include <Multy_key>
149 | ## <dead_circumflex>? Anyway my bin/make-dead-compose.sh fixes this.
150 | <dead_circumflex> <Multi_key> <underscore> <a> 	: "ª"   ordfeminine # FEMININE ORDINAL INDICATOR
151 | <Multi_key> <asciicircum> <underscore> <a> 	: "ª"   ordfeminine # FEMININE ORDINAL INDICATOR
152 | <dead_circumflex> <Multi_key> <underbar> <a> 	: "ª"   ordfeminine # FEMININE ORDINAL INDICATOR
153 | <Multi_key> <asciicircum> <underbar> <a> 	: "ª"   ordfeminine # FEMININE ORDINAL INDICATOR
154 | <dead_circumflex> <Multi_key> <underscore> <o> 	: "º"   masculine # MASCULINE ORDINAL INDICATOR
155 | <Multi_key> <asciicircum> <underscore> <o> 	: "º"   masculine # MASCULINE ORDINAL INDICATOR
156 | <dead_circumflex> <Multi_key> <underbar> <o> 	: "º"   masculine # MASCULINE ORDINAL INDICATOR
157 | <Multi_key> <asciicircum> <underbar> <o> 	: "º"   masculine # MASCULINE ORDINAL INDICATOR
158 | 
159 | ## <dead_circumflex> versions for all of these
160 | <Multi_key> <asciicircum> <underscore> <i> : "ⁱ"   U2071 # SUPERSCRIPT LATIN SMALL LETTER I
161 | <Multi_key> <asciicircum> <plus> 	: "⁺"   U207A # SUPERSCRIPT PLUS SIGN
162 | ## how do I u2212? (without pointless‐xcompose, I mean)
163 | <Multi_key> <asciicircum> <U2212>    	: "⁻"   U207B # SUPERSCRIPT MINUS
164 | <Multi_key> <asciicircum> <equal> 	: "⁼"   U207C # SUPERSCRIPT EQUALS SIGN
165 | <Multi_key> <asciicircum> <KP_Equal> 	: "⁼"   U207C # SUPERSCRIPT EQUALS SIGN
166 | <Multi_key> <asciicircum> <parenleft> 	: "⁽"   U207D # SUPERSCRIPT LEFT PARENTHESIS
167 | <Multi_key> <asciicircum> <parenright> 	: "⁾"   U207E # SUPERSCRIPT RIGHT PARENTHESIS
168 | 
169 | ## there’s keypad and underbar versions for all subscripts
170 | <Multi_key> <underscore> <0>     	: "₀"   U2080 # SUBSCRIPT ZERO
171 | <Multi_key> <underscore> <1>     	: "₁"   U2081 # SUBSCRIPT ONE
172 | <Multi_key> <underscore> <2>     	: "₂"   U2082 # SUBSCRIPT TWO
173 | ## ₃, ₄, ₅… ₀
174 | 
175 | <Multi_key> <underscore> <plus>  	: "₊"   U208A # SUBSCRIPT PLUS SIGN
176 | <Multi_key> <underscore> <U2212> 	: "₋"   U208B # SUBSCRIPT MINUS
177 | <Multi_key> <underscore> <equal> 	: "₌"   U208C # SUBSCRIPT EQUALS SIGN
178 | <Multi_key> <underscore> <parenleft> 	: "₍"   U208D # SUBSCRIPT LEFT PARENTHESIS
179 | <Multi_key> <underscore> <parenright> 	: "₎"   U208E # SUBSCRIPT RIGHT PARENTHESIS
180 | 
181 | ## why underscore for a superscript? a mistake?
182 | <Multi_key> <asciicircum> <underscore> <n> 	: "ⁿ"   U207F # SUPERSCRIPT LATIN SMALL LETTER N
183 | 
184 | ## <dead_circumflex> redundant? similarly for all below (ommited)
185 | <Multi_key> <S> <M>		 	: "℠"   U2120 # SERVICE MARK
186 | <dead_circumflex> <Multi_key> <S> <M> 	: "℠"   U2120 # SERVICE MARK
187 | ## they include all case permutations
188 | <Multi_key> <s> <M>		 	: "℠"   U2120 # SERVICE MARK
189 | <Multi_key> <S> <m>		 	: "℠"   U2120 # SERVICE MARK
190 | <Multi_key> <s> <m>		 	: "℠"   U2120 # SERVICE MARK
191 | 
192 | ## same variants as ℠
193 | <Multi_key> <t> <m>		 	: "™"   U2122 # TRADE MARK SIGN
194 | 
195 | 
196 | ## Circled things
197 | 
198 | <Multi_key> <parenleft> <0> <parenright> 	: "⓪"   U24EA # CIRCLED DIGIT ZERO
199 | <Multi_key> <parenleft> <1> <parenright> 	: "①"   U2460 # CIRCLED DIGIT ONE
200 | <Multi_key> <parenleft> <2> <parenright> 	: "②"   U2461 # CIRCLED DIGIT TWO
201 | ## ③, ④… ⑩, ⑪, ⑫… ⑳, ㉑… ㊿
202 | 
203 | <Multi_key> <parenleft> <A> <parenright> 	: "Ⓐ"   U24B6 # CIRCLED LATIN CAPITAL LETTER A
204 | <Multi_key> <parenleft> <B> <parenright> 	: "Ⓑ"   U24B7 # CIRCLED LATIN CAPITAL LETTER B
205 | <Multi_key> <parenleft> <C> <parenright> 	: "Ⓒ"   U24B8 # CIRCLED LATIN CAPITAL LETTER C
206 | ## …Ⓩ
207 | 
208 | <Multi_key> <parenleft> <a> <parenright> 	: "ⓐ"   U24D0 # CIRCLED LATIN SMALL LETTER A
209 | <Multi_key> <parenleft> <b> <parenright> 	: "ⓑ"   U24D1 # CIRCLED LATIN SMALL LETTER B
210 | <Multi_key> <parenleft> <c> <parenright> 	: "ⓒ"   U24D2 # CIRCLED LATIN SMALL LETTER C
211 | ## …ⓩ
212 | 
213 | ## Korean hangul
214 | <Multi_key> <parenleft> <U1100> <parenright> 	: "㉠"   U3260 # CIRCLED HANGUL KIYEOK
215 | <Multi_key> <parenleft> <U1102> <parenright> 	: "㉡"   U3261 # CIRCLED HANGUL NIEUN
216 | ## …&c.
217 | 
218 | ## Fractions
219 | ## =========
220 | ## I’d expect variants with slash.
221 | 
222 | <Multi_key> <1> <4>              	: "¼"   onequarter # VULGAR FRACTION ONE QUARTER
223 | <Multi_key> <1> <2>              	: "½"   onehalf # VULGAR FRACTION ONE HALF
224 | <Multi_key> <3> <4>              	: "¾"   threequarters # VULGAR FRACTION THREE QUARTERS
225 | <Multi_key> <1> <3>			: "⅓"	U2153 # VULGAR FRACTION ONE THIRD
226 | <Multi_key> <2> <3>			: "⅔"	U2154 # VULGAR FRACTION TWO THIRDS
227 | <Multi_key> <1> <5>			: "⅕"	U2155 # VULGAR FRACTION ONE FIFTH
228 | <Multi_key> <2> <5>			: "⅖"	U2156 # VULGAR FRACTION TWO FIFTHS
229 | <Multi_key> <3> <5>			: "⅗"	U2157 # VULGAR FRACTION THREE FIFTHS
230 | <Multi_key> <4> <5>			: "⅘"	U2158 # VULGAR FRACTION FOUR FIFTHS
231 | <Multi_key> <1> <6>			: "⅙"	U2159 # VULGAR FRACTION ONE SIXTH
232 | <Multi_key> <5> <6>			: "⅚"	U215A # VULGAR FRACTION FIVE SIXTHS
233 | <Multi_key> <1> <8>			: "⅛"	U215B # VULGAR FRACTION ONE EIGHTH
234 | <Multi_key> <3> <8>			: "⅜"	U215C # VULGAR FRACTION THREE EIGHTHS
235 | <Multi_key> <5> <8>			: "⅝"	U215D # VULGAR FRACTION FIVE EIGHTHS
236 | <Multi_key> <7> <8>			: "⅞"	U215E # VULGAR FRACTION SEVEN EIGHTHS
237 | 
238 | 
239 | ## Three ways of doing Ø… don’t confuse slashed‐O with U2205 “empty
240 | ## set” ∅, with U2300 “diameter sign” ⌀, or with the slashed zero (a
241 | ## glyph, not a character; when needed, it is represented by U0338
242 | ## “combining long solidus overlay” plus a zero (0̸).  Confused yet?
243 | <dead_stroke> <O>               	: "Ø"   Oslash # LATIN CAPITAL LETTER O WITH STROKE
244 | <Multi_key> <slash> <O>          	: "Ø"   Oslash # LATIN CAPITAL LETTER O WITH STROKE
245 | <Multi_key> <KP_Divide> <O>      	: "Ø"   Oslash # LATIN CAPITAL LETTER O WITH STROKE
246 | 
247 | 
248 | ## Music
249 | 
250 | ## Btw <numbersign> = #
251 | <Multi_key> <numbersign> <b>     	: "♭"   U266d # MUSIC FLAT SIGN
252 | <Multi_key> <numbersign> <f>     	: "♮"   U266e # MUSIC NATURAL SIGN
253 | <Multi_key> <numbersign> <numbersign> 	: "♯"   U266f # MUSIC SHARP SIGN
254 | 
255 | ## These characters somehow appear as hanzi in my system (Emacs with
256 | ## custom fontset).  In any case they appear to be unsupported by most
257 | ## fonts.
258 | <Multi_key> <U1D157> <U1D165> 	: "𝅗𝅥"   U1D15E # MUSICAL SYMBOL HALF NOTE
259 | <Multi_key> <U1D158> <U1D165> 	: "𝅘𝅥"   U1D15F # MUSICAL SYMBOL QUARTER NOTE
260 | <Multi_key> <U1D15F> <U1D16E> 	: "𝅘𝅥𝅮"   U1D160 # MUSICAL SYMBOL EIGHTH NOTE
261 | <Multi_key> <U1D15F> <U1D16F> 	: "𝅘𝅥𝅯"   U1D161 # MUSICAL SYMBOL SIXTEENTH NOTE
262 | <Multi_key> <U1D15F> <U1D170> 	: "𝅘𝅥𝅰"   U1D162 # MUSICAL SYMBOL THIRTY‐SECOND NOTE
263 | <Multi_key> <U1D15F> <U1D171> 	: "𝅘𝅥𝅱"   U1D163 # MUSICAL SYMBOL SIXTY-FOURTH NOTE
264 | <Multi_key> <U1D15F> <U1D172> 	: "𝅘𝅥𝅲"   U1D164 # MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
265 | <Multi_key> <U1D1B9> <U1D165> 	: "𝆹𝅥"   U1D1BB # MUSICAL SYMBOL MINIMA
266 | <Multi_key> <U1D1BA> <U1D165> 	: "𝆺𝅥"   U1D1BC # MUSICAL SYMBOL MINIMA BLACK
267 | <Multi_key> <U1D1BB> <U1D16E> 	: "𝆹𝅥𝅮"   U1D1BD # MUSICAL SYMBOL SEMIMINIMA WHITE
268 | <Multi_key> <U1D1BC> <U1D16E> 	: "𝆺𝅥𝅮"   U1D1BE # MUSICAL SYMBOL SEMIMINIMA BLACK
269 | <Multi_key> <U1D1BB> <U1D16F> 	: "𝆹𝅥𝅯"   U1D1BF # MUSICAL SYMBOL FUSA WHITE
270 | <Multi_key> <U1D1BC> <U1D16F> 	: "𝆺𝅥𝅯"   U1D1C0 # MUSICAL SYMBOL FUSA BLACK
271 | 
272 | ## and where’s the more common U2669–266C ♩♪♫♬?
273 | 
274 | 
275 | ## Money!
276 | ## ======
277 | ## Pay attention to case.
278 | <Multi_key> <C> <E>              	: "₠"   U20a0 # EURO-CURRENCY SIGN
279 | <Multi_key> <C> <slash>          	: "₡"   U20a1 # COLON SIGN
280 | <Multi_key> <slash> <C>          	: "₡"   U20a1 # COLON SIGN
281 | ## This is awesome! —nostalgic brazilian
282 | <Multi_key> <C> <r>              	: "₢"   U20a2 # CRUZEIRO SIGN
283 | <Multi_key> <F> <r>              	: "₣"   U20a3 # FRENCH FRANC SIGN
284 | <Multi_key> <L> <equal>          	: "₤"   U20a4 # LIRA SIGN
285 | <Multi_key> <equal> <L>          	: "₤"   U20a4 # LIRA SIGN
286 | <Multi_key> <m> <slash>          	: "₥"   U20a5 # MILL SIGN
287 | <Multi_key> <slash> <m>          	: "₥"   U20a5 # MILL SIGN
288 | <Multi_key> <N> <equal>          	: "₦"   U20a6 # NAIRA SIGN
289 | <Multi_key> <equal> <N>          	: "₦"   U20a6 # NAIRA SIGN
290 | <Multi_key> <P> <t>              	: "₧"   U20a7 # PESETA SIGN
291 | ## Zelda fans:
292 | <Multi_key> <R> <s>              	: "₨"   U20a8 # RUPEE SIGN
293 | <Multi_key> <W> <equal>          	: "₩"   U20a9 # WON SIGN
294 | <Multi_key> <equal> <W>          	: "₩"   U20a9 # WON SIGN
295 | ## ₪… heh xorg, bet you couldn’t mnemonic THIS
296 | ## On second though, perhaps “Compose [ ]”?
297 | ## On third though, I use that for ∎.
298 | # "₪" U20aa NEW SHEQEL SIGN
299 | <Multi_key> <d> <minus>          	: "₫"   U20ab # DONG SIGN
300 | ## Euro, for people with visual imagination.
301 | <Multi_key> <C> <equal>          	: "€"   EuroSign # EURO SIGN
302 | <Multi_key> <equal> <C>          	: "€"   EuroSign # EURO SIGN
303 | <Multi_key> <c> <equal>          	: "€"   EuroSign # EURO SIGN
304 | <Multi_key> <equal> <c>          	: "€"   EuroSign # EURO SIGN
305 | ## Euro, for people with verbal imagination.
306 | <Multi_key> <E> <equal>          	: "€"   EuroSign # EURO SIGN
307 | <Multi_key> <equal> <E>          	: "€"   EuroSign # EURO SIGN
308 | <Multi_key> <e> <equal>          	: "€"   EuroSign # EURO SIGN
309 | <Multi_key> <equal> <e>          	: "€"   EuroSign # EURO SIGN
310 | ## Euro, for people with, er… Cyrillic keyboards?
311 | <Multi_key> <Cyrillic_ES> <equal>	: "€"   EuroSign # EURO SIGN
312 | <Multi_key> <equal> <Cyrillic_ES>	: "€"   EuroSign # EURO SIGN
313 | <Multi_key> <Cyrillic_IE> <equal>	: "€"   EuroSign # EURO SIGN
314 | <Multi_key> <equal> <Cyrillic_IE>	: "€"   EuroSign # EURO SIGN
315 | ## Drachma? German penny? Guarani? Someone think of shorcuts for
316 | ## these, they’re great!
317 | # "₭" U20ad KIP SIGN
318 | # "₮" U20ae TUGRIK SIGN
319 | # "₯" U20af DRACHMA SIGN
320 | # "₰" U20b0 GERMAN PENNY SIGN
321 | # "₱" U20b1 PESO SIGN
322 | # "₲" U20b2 GUARANI SIGN
323 | # "₳" U20b3 AUSTRAL SIGN
324 | # "₴" U20b4 HRYVNIA SIGN
325 | # "₵" U20b5 CEDI SIGN
326 | <Multi_key> <bar> <c>            	: "¢"   cent # CENT SIGN
327 | <Multi_key> <c> <bar>            	: "¢"   cent # CENT SIGN
328 | <Multi_key> <c> <slash>          	: "¢"   cent # CENT SIGN
329 | <Multi_key> <slash> <c>          	: "¢"   cent # CENT SIGN
330 | <Multi_key> <L> <minus>          	: "£"   sterling # POUND SIGN
331 | <Multi_key> <minus> <L>          	: "£"   sterling # POUND SIGN
332 | <Multi_key> <Y> <equal>          	: "¥"   yen # YEN SIGN
333 | <Multi_key> <equal> <Y>          	: "¥"   yen # YEN SIGN
334 | 
335 | ## Generic currency!
336 | <Multi_key> <o> <x>              	: "¤"   currency # CURRENCY SIGN
337 | <Multi_key> <x> <o>              	: "¤"   currency # CURRENCY SIGN
338 | 
339 | 
340 | ## Japanese
341 | ## ========
342 | 
343 | ## How is one supposed to combine ideographs (normally inputed with an
344 | ## IM) and X compose?  In any case it’s interesting to know there are
345 | ## superscript kanji, deadkey variants and all.  I wonder how to type
346 | ## them in common IMs?
347 | 
348 | <dead_circumflex> <U4E00>    	: "㆒"   U3192 # IDEOGRAPHIC ANNOTATION ONE MARK
349 | <Multi_key> <asciicircum> <U4E00> 	: "㆒"   U3192 # IDEOGRAPHIC ANNOTATION ONE MARK
350 | <dead_circumflex> <U4E8C>    	: "㆓"   U3193 # IDEOGRAPHIC ANNOTATION TWO MARK
351 | <Multi_key> <asciicircum> <U4E8C> 	: "㆓"   U3193 # IDEOGRAPHIC ANNOTATION TWO MARK
352 | ## dead_circumflex for all the following
353 | <Multi_key> <asciicircum> <U4E09> 	: "㆔"   U3194 # IDEOGRAPHIC ANNOTATION THREE MARK
354 | <Multi_key> <asciicircum> <U56DB> 	: "㆕"   U3195 # IDEOGRAPHIC ANNOTATION FOUR MARK
355 | <Multi_key> <asciicircum> <U4E0A> 	: "㆖"   U3196 # IDEOGRAPHIC ANNOTATION TOP MARK
356 | <Multi_key> <asciicircum> <U4E2D> 	: "㆗"   U3197 # IDEOGRAPHIC ANNOTATION MIDDLE MARK
357 | <Multi_key> <asciicircum> <U4E0B> 	: "㆘"   U3198 # IDEOGRAPHIC ANNOTATION BOTTOM MARK
358 | <Multi_key> <asciicircum> <U7532> 	: "㆙"   U3199 # IDEOGRAPHIC ANNOTATION FIRST MARK
359 | <Multi_key> <asciicircum> <U4E59> 	: "㆚"   U319A # IDEOGRAPHIC ANNOTATION SECOND MARK
360 | <Multi_key> <asciicircum> <U4E19> 	: "㆛"   U319B # IDEOGRAPHIC ANNOTATION THIRD MARK
361 | <Multi_key> <asciicircum> <U4E01> 	: "㆜"   U319C # IDEOGRAPHIC ANNOTATION FOURTH MARK
362 | <Multi_key> <asciicircum> <U5929> 	: "㆝"   U319D # IDEOGRAPHIC ANNOTATION HEAVEN MARK
363 | <Multi_key> <asciicircum> <U5730> 	: "㆞"   U319E # IDEOGRAPHIC ANNOTATION EARTH MARK
364 | ## unicode sexism! why not “person mark”?
365 | <Multi_key> <asciicircum> <U4EBA> 	: "㆟"   U319F # IDEOGRAPHIC ANNOTATION MAN MARK
366 | 
367 | <Multi_key> <parenleft> <U4E00> <parenright> 	: "㊀"   U3280 # CIRCLED IDEOGRAPH ONE
368 | <Multi_key> <parenleft> <U4E8C> <parenright> 	: "㊁"   U3281 # CIRCLED IDEOGRAPH TWO
369 | <Multi_key> <parenleft> <U4E09> <parenright> 	: "㊂"   U3282 # CIRCLED IDEOGRAPH THREE
370 | ## ㊃ ㊄ ㊅ ㊆ ㊇ ㊈ ㊉ ㊊ ㊋ ㊌ ㊍ ㊎ ㊏ ㊐ ㊑ ㊒ ㊓ ㊔ ㊕ ㊖ ㊗ ㊘ ㊙
371 | ## ㊚ ㊛ ㊜ ㊝ ㊞ ㊟ ㊠ ㊡ ㊢ ㊣ ㊤ ㊥ ㊦ ㊧ ㊨ ㊩ ㊪ ㊫ ㊬ ㊭ ㊮ ㊯ ㊰
372 | 
373 | <Multi_key> <parenleft> <kana_A> <parenright> 	: "㋐"   U32D0 # CIRCLED KATAKANA A
374 | <Multi_key> <parenleft> <kana_I> <parenright> 	: "㋑"   U32D1 # CIRCLED KATAKANA I
375 | ## …㋻㋼㋽㋾. (all katakana; no hiragana?)
376 | 
377 | 
378 | ## Linguistics
379 | ## ===========
380 | <Multi_key> <e> <e>              	: "ə"   U0259 # LATIN SMALL LETTER SCHWA
381 | 
382 | ## There are order and deadkey variants for the following.  The
383 | ## <dead_circumflex> ones use Multi_key after the circumflex, not
384 | ## before as I’d expect.
385 | <Multi_key> <slash> <i>          	: "ɨ"   U0268 # LATIN SMALL LETTER I WITH STROKE
386 | <Multi_key> <slash> <U0294>  	: "ʡ"   U02A1 # LATIN LETTER GLOTTAL STOP WITH STROKE
387 | <Multi_key> <asciicircum> <underscore> <h> 	: "ʰ"   U02B0 # MODIFIER LETTER SMALL H
388 | <Multi_key> <asciicircum> <underscore> <U0266> 	: "ʱ"   U02B1 # MODIFIER LETTER SMALL H WITH HOOK
389 | <Multi_key> <asciicircum> <underscore> <j> 	: "ʲ"   U02B2 # MODIFIER LETTER SMALL J
390 | <Multi_key> <asciicircum> <underscore> <r> 	: "ʳ"   U02B3 # MODIFIER LETTER SMALL R
391 | <Multi_key> <asciicircum> <underscore> <U0279> 	: "ʴ"   U02B4 # MODIFIER LETTER SMALL TURNED R
392 | <Multi_key> <asciicircum> <underscore> <U027B> 	: "ʵ"   U02B5 # MODIFIER LETTER SMALL TURNED R WITH HOOK
393 | <Multi_key> <asciicircum> <underscore> <U0281> 	: "ʶ"   U02B6 # MODIFIER LETTER SMALL CAPITAL INVERTED R
394 | <Multi_key> <asciicircum> <underscore> <w> 	: "ʷ"   U02B7 # MODIFIER LETTER SMALL W
395 | <Multi_key> <asciicircum> <underscore> <y> 	: "ʸ"   U02B8 # MODIFIER LETTER SMALL Y
396 | <Multi_key> <asciicircum> <underscore> <U0263> 	: "ˠ"   U02E0 # MODIFIER LETTER SMALL GAMMA
397 | <Multi_key> <asciicircum> <underscore> <l> 	: "ˡ"   U02E1 # MODIFIER LETTER SMALL L
398 | <Multi_key> <asciicircum> <underscore> <s> 	: "ˢ"   U02E2 # MODIFIER LETTER SMALL S
399 | <Multi_key> <asciicircum> <underscore> <x> 	: "ˣ"   U02E3 # MODIFIER LETTER SMALL X
400 | <Multi_key> <asciicircum> <underscore> <U0295> 	: "ˤ"   U02E4 # MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
401 | 
402 | ## lots more with various modifiers, go look the file if you’re a linguist.
403 | 
404 | 
405 | 


--------------------------------------------------------------------------------
/bin/keysymdef.rb:
--------------------------------------------------------------------------------
   1 | # -*- coding: utf-8 -*-
   2 | # Autogenerated by ./make-keysymdef.rb at 2009-05-15.
   3 | # First line of input file was:
   4 | # /* $Xorg: keysymdef.h,v 1.4 2001/02/09 02:03:23 $ */
   5 | 
   6 | 
   7 | module Keysymdef
   8 |   Keysyms = {
   9 |     "0"                         => "0",
  10 |     "1"                         => "1",
  11 |     "2"                         => "2",
  12 |     "3"                         => "3",
  13 |     "4"                         => "4",
  14 |     "5"                         => "5",
  15 |     "6"                         => "6",
  16 |     "7"                         => "7",
  17 |     "8"                         => "8",
  18 |     "9"                         => "9",
  19 |     "A"                         => "A",
  20 |     "AE"                        => "Æ",
  21 |     "Aacute"                    => "Á",
  22 |     "Abelowdot"                 => "Ạ",
  23 |     "Abreve"                    => "Ă",
  24 |     "Abreveacute"               => "Ắ",
  25 |     "Abrevebelowdot"            => "Ặ",
  26 |     "Abrevegrave"               => "Ằ",
  27 |     "Abrevehook"                => "Ẳ",
  28 |     "Abrevetilde"               => "Ẵ",
  29 |     "Acircumflex"               => "Â",
  30 |     "Acircumflexacute"          => "Ấ",
  31 |     "Acircumflexbelowdot"       => "Ậ",
  32 |     "Acircumflexgrave"          => "Ầ",
  33 |     "Acircumflexhook"           => "Ẩ",
  34 |     "Acircumflextilde"          => "Ẫ",
  35 |     "Adiaeresis"                => "Ä",
  36 |     "Agrave"                    => "À",
  37 |     "Ahook"                     => "Ả",
  38 |     "Amacron"                   => "Ā",
  39 |     "Aogonek"                   => "Ą",
  40 |     "Arabic_0"                  => "٠",
  41 |     "Arabic_1"                  => "١",
  42 |     "Arabic_2"                  => "٢",
  43 |     "Arabic_3"                  => "٣",
  44 |     "Arabic_4"                  => "٤",
  45 |     "Arabic_5"                  => "٥",
  46 |     "Arabic_6"                  => "٦",
  47 |     "Arabic_7"                  => "٧",
  48 |     "Arabic_8"                  => "٨",
  49 |     "Arabic_9"                  => "٩",
  50 |     "Arabic_ain"                => "ع",
  51 |     "Arabic_alef"               => "ا",
  52 |     "Arabic_alefmaksura"        => "ى",
  53 |     "Arabic_beh"                => "ب",
  54 |     "Arabic_comma"              => "،",
  55 |     "Arabic_dad"                => "ض",
  56 |     "Arabic_dal"                => "د",
  57 |     "Arabic_damma"              => "ُ",
  58 |     "Arabic_dammatan"           => "ٌ",
  59 |     "Arabic_ddal"               => "ڈ",
  60 |     "Arabic_farsi_yeh"          => "ی",
  61 |     "Arabic_fatha"              => "َ",
  62 |     "Arabic_fathatan"           => "ً",
  63 |     "Arabic_feh"                => "ف",
  64 |     "Arabic_fullstop"           => "۔",
  65 |     "Arabic_gaf"                => "گ",
  66 |     "Arabic_ghain"              => "غ",
  67 |     "Arabic_ha"                 => "ه",
  68 |     "Arabic_hah"                => "ح",
  69 |     "Arabic_hamza"              => "ء",
  70 |     "Arabic_hamza_above"        => "ٔ",
  71 |     "Arabic_hamza_below"        => "ٕ",
  72 |     "Arabic_hamzaonalef"        => "أ",
  73 |     "Arabic_hamzaonwaw"         => "ؤ",
  74 |     "Arabic_hamzaonyeh"         => "ئ",
  75 |     "Arabic_hamzaunderalef"     => "إ",
  76 |     "Arabic_heh_doachashmee"    => "ھ",
  77 |     "Arabic_heh_goal"           => "ہ",
  78 |     "Arabic_jeem"               => "ج",
  79 |     "Arabic_jeh"                => "ژ",
  80 |     "Arabic_kaf"                => "ك",
  81 |     "Arabic_kasra"              => "ِ",
  82 |     "Arabic_kasratan"           => "ٍ",
  83 |     "Arabic_keheh"              => "ک",
  84 |     "Arabic_khah"               => "خ",
  85 |     "Arabic_lam"                => "ل",
  86 |     "Arabic_madda_above"        => "ٓ",
  87 |     "Arabic_maddaonalef"        => "آ",
  88 |     "Arabic_meem"               => "م",
  89 |     "Arabic_noon"               => "ن",
  90 |     "Arabic_noon_ghunna"        => "ں",
  91 |     "Arabic_peh"                => "پ",
  92 |     "Arabic_percent"            => "٪",
  93 |     "Arabic_qaf"                => "ق",
  94 |     "Arabic_question_mark"      => "؟",
  95 |     "Arabic_ra"                 => "ر",
  96 |     "Arabic_rreh"               => "ڑ",
  97 |     "Arabic_sad"                => "ص",
  98 |     "Arabic_seen"               => "س",
  99 |     "Arabic_semicolon"          => "؛",
 100 |     "Arabic_shadda"             => "ّ",
 101 |     "Arabic_sheen"              => "ش",
 102 |     "Arabic_sukun"              => "ْ",
 103 |     "Arabic_superscript_alef"   => "ٰ",
 104 |     "Arabic_tah"                => "ط",
 105 |     "Arabic_tatweel"            => "ـ",
 106 |     "Arabic_tcheh"              => "چ",
 107 |     "Arabic_teh"                => "ت",
 108 |     "Arabic_tehmarbuta"         => "ة",
 109 |     "Arabic_thal"               => "ذ",
 110 |     "Arabic_theh"               => "ث",
 111 |     "Arabic_tteh"               => "ٹ",
 112 |     "Arabic_veh"                => "ڤ",
 113 |     "Arabic_waw"                => "و",
 114 |     "Arabic_yeh"                => "ي",
 115 |     "Arabic_yeh_baree"          => "ے",
 116 |     "Arabic_zah"                => "ظ",
 117 |     "Arabic_zain"               => "ز",
 118 |     "Aring"                     => "Å",
 119 |     "Armenian_AT"               => "Ը",
 120 |     "Armenian_AYB"              => "Ա",
 121 |     "Armenian_BEN"              => "Բ",
 122 |     "Armenian_CHA"              => "Չ",
 123 |     "Armenian_DA"               => "Դ",
 124 |     "Armenian_DZA"              => "Ձ",
 125 |     "Armenian_E"                => "Է",
 126 |     "Armenian_FE"               => "Ֆ",
 127 |     "Armenian_GHAT"             => "Ղ",
 128 |     "Armenian_GIM"              => "Գ",
 129 |     "Armenian_HI"               => "Յ",
 130 |     "Armenian_HO"               => "Հ",
 131 |     "Armenian_INI"              => "Ի",
 132 |     "Armenian_JE"               => "Ջ",
 133 |     "Armenian_KE"               => "Ք",
 134 |     "Armenian_KEN"              => "Կ",
 135 |     "Armenian_KHE"              => "Խ",
 136 |     "Armenian_LYUN"             => "Լ",
 137 |     "Armenian_MEN"              => "Մ",
 138 |     "Armenian_NU"               => "Ն",
 139 |     "Armenian_O"                => "Օ",
 140 |     "Armenian_PE"               => "Պ",
 141 |     "Armenian_PYUR"             => "Փ",
 142 |     "Armenian_RA"               => "Ռ",
 143 |     "Armenian_RE"               => "Ր",
 144 |     "Armenian_SE"               => "Ս",
 145 |     "Armenian_SHA"              => "Շ",
 146 |     "Armenian_TCHE"             => "Ճ",
 147 |     "Armenian_TO"               => "Թ",
 148 |     "Armenian_TSA"              => "Ծ",
 149 |     "Armenian_TSO"              => "Ց",
 150 |     "Armenian_TYUN"             => "Տ",
 151 |     "Armenian_VEV"              => "Վ",
 152 |     "Armenian_VO"               => "Ո",
 153 |     "Armenian_VYUN"             => "Ւ",
 154 |     "Armenian_YECH"             => "Ե",
 155 |     "Armenian_ZA"               => "Զ",
 156 |     "Armenian_ZHE"              => "Ժ",
 157 |     "Armenian_accent"           => "՛",
 158 |     "Armenian_amanak"           => "՜",
 159 |     "Armenian_apostrophe"       => "՚",
 160 |     "Armenian_at"               => "ը",
 161 |     "Armenian_ayb"              => "ա",
 162 |     "Armenian_ben"              => "բ",
 163 |     "Armenian_but"              => "՝",
 164 |     "Armenian_cha"              => "չ",
 165 |     "Armenian_da"               => "դ",
 166 |     "Armenian_dza"              => "ձ",
 167 |     "Armenian_e"                => "է",
 168 |     "Armenian_exclam"           => "՜",
 169 |     "Armenian_fe"               => "ֆ",
 170 |     "Armenian_full_stop"        => "։",
 171 |     "Armenian_ghat"             => "ղ",
 172 |     "Armenian_gim"              => "գ",
 173 |     "Armenian_hi"               => "յ",
 174 |     "Armenian_ho"               => "հ",
 175 |     "Armenian_hyphen"           => "֊",
 176 |     "Armenian_ini"              => "ի",
 177 |     "Armenian_je"               => "ջ",
 178 |     "Armenian_ke"               => "ք",
 179 |     "Armenian_ken"              => "կ",
 180 |     "Armenian_khe"              => "խ",
 181 |     "Armenian_ligature_ew"      => "և",
 182 |     "Armenian_lyun"             => "լ",
 183 |     "Armenian_men"              => "մ",
 184 |     "Armenian_nu"               => "ն",
 185 |     "Armenian_o"                => "օ",
 186 |     "Armenian_paruyk"           => "՞",
 187 |     "Armenian_pe"               => "պ",
 188 |     "Armenian_pyur"             => "փ",
 189 |     "Armenian_question"         => "՞",
 190 |     "Armenian_ra"               => "ռ",
 191 |     "Armenian_re"               => "ր",
 192 |     "Armenian_se"               => "ս",
 193 |     "Armenian_separation_mark"  => "՝",
 194 |     "Armenian_sha"              => "շ",
 195 |     "Armenian_shesht"           => "՛",
 196 |     "Armenian_tche"             => "ճ",
 197 |     "Armenian_to"               => "թ",
 198 |     "Armenian_tsa"              => "ծ",
 199 |     "Armenian_tso"              => "ց",
 200 |     "Armenian_tyun"             => "տ",
 201 |     "Armenian_verjaket"         => "։",
 202 |     "Armenian_vev"              => "վ",
 203 |     "Armenian_vo"               => "ո",
 204 |     "Armenian_vyun"             => "ւ",
 205 |     "Armenian_yech"             => "ե",
 206 |     "Armenian_yentamna"         => "֊",
 207 |     "Armenian_za"               => "զ",
 208 |     "Armenian_zhe"              => "ժ",
 209 |     "Atilde"                    => "Ã",
 210 |     "B"                         => "B",
 211 |     "Babovedot"                 => "Ḃ",
 212 |     "Byelorussian_SHORTU"       => "Ў",
 213 |     "Byelorussian_shortu"       => "ў",
 214 |     "C"                         => "C",
 215 |     "Cabovedot"                 => "Ċ",
 216 |     "Cacute"                    => "Ć",
 217 |     "Ccaron"                    => "Č",
 218 |     "Ccedilla"                  => "Ç",
 219 |     "Ccircumflex"               => "Ĉ",
 220 |     "ColonSign"                 => "₡",
 221 |     "CruzeiroSign"              => "₢",
 222 |     "Cyrillic_A"                => "А",
 223 |     "Cyrillic_BE"               => "Б",
 224 |     "Cyrillic_CHE"              => "Ч",
 225 |     "Cyrillic_CHE_descender"    => "Ҷ",
 226 |     "Cyrillic_CHE_vertstroke"   => "Ҹ",
 227 |     "Cyrillic_DE"               => "Д",
 228 |     "Cyrillic_DZHE"             => "Џ",
 229 |     "Cyrillic_E"                => "Э",
 230 |     "Cyrillic_EF"               => "Ф",
 231 |     "Cyrillic_EL"               => "Л",
 232 |     "Cyrillic_EM"               => "М",
 233 |     "Cyrillic_EN"               => "Н",
 234 |     "Cyrillic_EN_descender"     => "Ң",
 235 |     "Cyrillic_ER"               => "Р",
 236 |     "Cyrillic_ES"               => "С",
 237 |     "Cyrillic_GHE"              => "Г",
 238 |     "Cyrillic_GHE_bar"          => "Ғ",
 239 |     "Cyrillic_HA"               => "Х",
 240 |     "Cyrillic_HARDSIGN"         => "Ъ",
 241 |     "Cyrillic_HA_descender"     => "Ҳ",
 242 |     "Cyrillic_I"                => "И",
 243 |     "Cyrillic_IE"               => "Е",
 244 |     "Cyrillic_IO"               => "Ё",
 245 |     "Cyrillic_I_macron"         => "Ӣ",
 246 |     "Cyrillic_JE"               => "Ј",
 247 |     "Cyrillic_KA"               => "К",
 248 |     "Cyrillic_KA_descender"     => "Қ",
 249 |     "Cyrillic_KA_vertstroke"    => "Ҝ",
 250 |     "Cyrillic_LJE"              => "Љ",
 251 |     "Cyrillic_NJE"              => "Њ",
 252 |     "Cyrillic_O"                => "О",
 253 |     "Cyrillic_O_bar"            => "Ө",
 254 |     "Cyrillic_PE"               => "П",
 255 |     "Cyrillic_SCHWA"            => "Ә",
 256 |     "Cyrillic_SHA"              => "Ш",
 257 |     "Cyrillic_SHCHA"            => "Щ",
 258 |     "Cyrillic_SHHA"             => "Һ",
 259 |     "Cyrillic_SHORTI"           => "Й",
 260 |     "Cyrillic_SOFTSIGN"         => "Ь",
 261 |     "Cyrillic_TE"               => "Т",
 262 |     "Cyrillic_TSE"              => "Ц",
 263 |     "Cyrillic_U"                => "У",
 264 |     "Cyrillic_U_macron"         => "Ӯ",
 265 |     "Cyrillic_U_straight"       => "Ү",
 266 |     "Cyrillic_U_straight_bar"   => "Ұ",
 267 |     "Cyrillic_VE"               => "В",
 268 |     "Cyrillic_YA"               => "Я",
 269 |     "Cyrillic_YERU"             => "Ы",
 270 |     "Cyrillic_YU"               => "Ю",
 271 |     "Cyrillic_ZE"               => "З",
 272 |     "Cyrillic_ZHE"              => "Ж",
 273 |     "Cyrillic_ZHE_descender"    => "Җ",
 274 |     "Cyrillic_a"                => "а",
 275 |     "Cyrillic_be"               => "б",
 276 |     "Cyrillic_che"              => "ч",
 277 |     "Cyrillic_che_descender"    => "ҷ",
 278 |     "Cyrillic_che_vertstroke"   => "ҹ",
 279 |     "Cyrillic_de"               => "д",
 280 |     "Cyrillic_dzhe"             => "џ",
 281 |     "Cyrillic_e"                => "э",
 282 |     "Cyrillic_ef"               => "ф",
 283 |     "Cyrillic_el"               => "л",
 284 |     "Cyrillic_em"               => "м",
 285 |     "Cyrillic_en"               => "н",
 286 |     "Cyrillic_en_descender"     => "ң",
 287 |     "Cyrillic_er"               => "р",
 288 |     "Cyrillic_es"               => "с",
 289 |     "Cyrillic_ghe"              => "г",
 290 |     "Cyrillic_ghe_bar"          => "ғ",
 291 |     "Cyrillic_ha"               => "х",
 292 |     "Cyrillic_ha_descender"     => "ҳ",
 293 |     "Cyrillic_hardsign"         => "ъ",
 294 |     "Cyrillic_i"                => "и",
 295 |     "Cyrillic_i_macron"         => "ӣ",
 296 |     "Cyrillic_ie"               => "е",
 297 |     "Cyrillic_io"               => "ё",
 298 |     "Cyrillic_je"               => "ј",
 299 |     "Cyrillic_ka"               => "к",
 300 |     "Cyrillic_ka_descender"     => "қ",
 301 |     "Cyrillic_ka_vertstroke"    => "ҝ",
 302 |     "Cyrillic_lje"              => "љ",
 303 |     "Cyrillic_nje"              => "њ",
 304 |     "Cyrillic_o"                => "о",
 305 |     "Cyrillic_o_bar"            => "ө",
 306 |     "Cyrillic_pe"               => "п",
 307 |     "Cyrillic_schwa"            => "ә",
 308 |     "Cyrillic_sha"              => "ш",
 309 |     "Cyrillic_shcha"            => "щ",
 310 |     "Cyrillic_shha"             => "һ",
 311 |     "Cyrillic_shorti"           => "й",
 312 |     "Cyrillic_softsign"         => "ь",
 313 |     "Cyrillic_te"               => "т",
 314 |     "Cyrillic_tse"              => "ц",
 315 |     "Cyrillic_u"                => "у",
 316 |     "Cyrillic_u_macron"         => "ӯ",
 317 |     "Cyrillic_u_straight"       => "ү",
 318 |     "Cyrillic_u_straight_bar"   => "ұ",
 319 |     "Cyrillic_ve"               => "в",
 320 |     "Cyrillic_ya"               => "я",
 321 |     "Cyrillic_yeru"             => "ы",
 322 |     "Cyrillic_yu"               => "ю",
 323 |     "Cyrillic_ze"               => "з",
 324 |     "Cyrillic_zhe"              => "ж",
 325 |     "Cyrillic_zhe_descender"    => "җ",
 326 |     "D"                         => "D",
 327 |     "Dabovedot"                 => "Ḋ",
 328 |     "Dcaron"                    => "Ď",
 329 |     "DongSign"                  => "₫",
 330 |     "Dstroke"                   => "Đ",
 331 |     "E"                         => "E",
 332 |     "ENG"                       => "Ŋ",
 333 |     "ETH"                       => "Ð",
 334 |     "Eabovedot"                 => "Ė",
 335 |     "Eacute"                    => "É",
 336 |     "Ebelowdot"                 => "Ẹ",
 337 |     "Ecaron"                    => "Ě",
 338 |     "Ecircumflex"               => "Ê",
 339 |     "Ecircumflexacute"          => "Ế",
 340 |     "Ecircumflexbelowdot"       => "Ệ",
 341 |     "Ecircumflexgrave"          => "Ề",
 342 |     "Ecircumflexhook"           => "Ể",
 343 |     "Ecircumflextilde"          => "Ễ",
 344 |     "EcuSign"                   => "₠",
 345 |     "Ediaeresis"                => "Ë",
 346 |     "Egrave"                    => "È",
 347 |     "Ehook"                     => "Ẻ",
 348 |     "Emacron"                   => "Ē",
 349 |     "Eogonek"                   => "Ę",
 350 |     "Etilde"                    => "Ẽ",
 351 |     "EuroSign"                  => "€",
 352 |     "F"                         => "F",
 353 |     "FFrancSign"                => "₣",
 354 |     "Fabovedot"                 => "Ḟ",
 355 |     "Farsi_0"                   => "۰",
 356 |     "Farsi_1"                   => "۱",
 357 |     "Farsi_2"                   => "۲",
 358 |     "Farsi_3"                   => "۳",
 359 |     "Farsi_4"                   => "۴",
 360 |     "Farsi_5"                   => "۵",
 361 |     "Farsi_6"                   => "۶",
 362 |     "Farsi_7"                   => "۷",
 363 |     "Farsi_8"                   => "۸",
 364 |     "Farsi_9"                   => "۹",
 365 |     "Farsi_yeh"                 => "ی",
 366 |     "G"                         => "G",
 367 |     "Gabovedot"                 => "Ġ",
 368 |     "Gbreve"                    => "Ğ",
 369 |     "Gcaron"                    => "Ǧ",
 370 |     "Gcedilla"                  => "Ģ",
 371 |     "Gcircumflex"               => "Ĝ",
 372 |     "Georgian_an"               => "ა",
 373 |     "Georgian_ban"              => "ბ",
 374 |     "Georgian_can"              => "ც",
 375 |     "Georgian_char"             => "ჭ",
 376 |     "Georgian_chin"             => "ჩ",
 377 |     "Georgian_cil"              => "წ",
 378 |     "Georgian_don"              => "დ",
 379 |     "Georgian_en"               => "ე",
 380 |     "Georgian_fi"               => "ჶ",
 381 |     "Georgian_gan"              => "გ",
 382 |     "Georgian_ghan"             => "ღ",
 383 |     "Georgian_hae"              => "ჰ",
 384 |     "Georgian_har"              => "ჴ",
 385 |     "Georgian_he"               => "ჱ",
 386 |     "Georgian_hie"              => "ჲ",
 387 |     "Georgian_hoe"              => "ჵ",
 388 |     "Georgian_in"               => "ი",
 389 |     "Georgian_jhan"             => "ჯ",
 390 |     "Georgian_jil"              => "ძ",
 391 |     "Georgian_kan"              => "კ",
 392 |     "Georgian_khar"             => "ქ",
 393 |     "Georgian_las"              => "ლ",
 394 |     "Georgian_man"              => "მ",
 395 |     "Georgian_nar"              => "ნ",
 396 |     "Georgian_on"               => "ო",
 397 |     "Georgian_par"              => "პ",
 398 |     "Georgian_phar"             => "ფ",
 399 |     "Georgian_qar"              => "ყ",
 400 |     "Georgian_rae"              => "რ",
 401 |     "Georgian_san"              => "ს",
 402 |     "Georgian_shin"             => "შ",
 403 |     "Georgian_tan"              => "თ",
 404 |     "Georgian_tar"              => "ტ",
 405 |     "Georgian_un"               => "უ",
 406 |     "Georgian_vin"              => "ვ",
 407 |     "Georgian_we"               => "ჳ",
 408 |     "Georgian_xan"              => "ხ",
 409 |     "Georgian_zen"              => "ზ",
 410 |     "Georgian_zhar"             => "ჟ",
 411 |     "Greek_ALPHA"               => "Α",
 412 |     "Greek_ALPHAaccent"         => "Ά",
 413 |     "Greek_BETA"                => "Β",
 414 |     "Greek_CHI"                 => "Χ",
 415 |     "Greek_DELTA"               => "Δ",
 416 |     "Greek_EPSILON"             => "Ε",
 417 |     "Greek_EPSILONaccent"       => "Έ",
 418 |     "Greek_ETA"                 => "Η",
 419 |     "Greek_ETAaccent"           => "Ή",
 420 |     "Greek_GAMMA"               => "Γ",
 421 |     "Greek_IOTA"                => "Ι",
 422 |     "Greek_IOTAaccent"          => "Ί",
 423 |     "Greek_IOTAdieresis"        => "Ϊ",
 424 |     "Greek_KAPPA"               => "Κ",
 425 |     "Greek_LAMBDA"              => "Λ",
 426 |     "Greek_LAMDA"               => "Λ",
 427 |     "Greek_MU"                  => "Μ",
 428 |     "Greek_NU"                  => "Ν",
 429 |     "Greek_OMEGA"               => "Ω",
 430 |     "Greek_OMEGAaccent"         => "Ώ",
 431 |     "Greek_OMICRON"             => "Ο",
 432 |     "Greek_OMICRONaccent"       => "Ό",
 433 |     "Greek_PHI"                 => "Φ",
 434 |     "Greek_PI"                  => "Π",
 435 |     "Greek_PSI"                 => "Ψ",
 436 |     "Greek_RHO"                 => "Ρ",
 437 |     "Greek_SIGMA"               => "Σ",
 438 |     "Greek_TAU"                 => "Τ",
 439 |     "Greek_THETA"               => "Θ",
 440 |     "Greek_UPSILON"             => "Υ",
 441 |     "Greek_UPSILONaccent"       => "Ύ",
 442 |     "Greek_UPSILONdieresis"     => "Ϋ",
 443 |     "Greek_XI"                  => "Ξ",
 444 |     "Greek_ZETA"                => "Ζ",
 445 |     "Greek_accentdieresis"      => "΅",
 446 |     "Greek_alpha"               => "α",
 447 |     "Greek_alphaaccent"         => "ά",
 448 |     "Greek_beta"                => "β",
 449 |     "Greek_chi"                 => "χ",
 450 |     "Greek_delta"               => "δ",
 451 |     "Greek_epsilon"             => "ε",
 452 |     "Greek_epsilonaccent"       => "έ",
 453 |     "Greek_eta"                 => "η",
 454 |     "Greek_etaaccent"           => "ή",
 455 |     "Greek_finalsmallsigma"     => "ς",
 456 |     "Greek_gamma"               => "γ",
 457 |     "Greek_horizbar"            => "―",
 458 |     "Greek_iota"                => "ι",
 459 |     "Greek_iotaaccent"          => "ί",
 460 |     "Greek_iotaaccentdieresis"  => "ΐ",
 461 |     "Greek_iotadieresis"        => "ϊ",
 462 |     "Greek_kappa"               => "κ",
 463 |     "Greek_lambda"              => "λ",
 464 |     "Greek_lamda"               => "λ",
 465 |     "Greek_mu"                  => "μ",
 466 |     "Greek_nu"                  => "ν",
 467 |     "Greek_omega"               => "ω",
 468 |     "Greek_omegaaccent"         => "ώ",
 469 |     "Greek_omicron"             => "ο",
 470 |     "Greek_omicronaccent"       => "ό",
 471 |     "Greek_phi"                 => "φ",
 472 |     "Greek_pi"                  => "π",
 473 |     "Greek_psi"                 => "ψ",
 474 |     "Greek_rho"                 => "ρ",
 475 |     "Greek_sigma"               => "σ",
 476 |     "Greek_tau"                 => "τ",
 477 |     "Greek_theta"               => "θ",
 478 |     "Greek_upsilon"             => "υ",
 479 |     "Greek_upsilonaccent"       => "ύ",
 480 |     "Greek_upsilonaccentdieresis" => "ΰ",
 481 |     "Greek_upsilondieresis"     => "ϋ",
 482 |     "Greek_xi"                  => "ξ",
 483 |     "Greek_zeta"                => "ζ",
 484 |     "H"                         => "H",
 485 |     "Hcircumflex"               => "Ĥ",
 486 |     "Hstroke"                   => "Ħ",
 487 |     "I"                         => "I",
 488 |     "Iabovedot"                 => "İ",
 489 |     "Iacute"                    => "Í",
 490 |     "Ibelowdot"                 => "Ị",
 491 |     "Ibreve"                    => "Ĭ",
 492 |     "Icircumflex"               => "Î",
 493 |     "Idiaeresis"                => "Ï",
 494 |     "Igrave"                    => "Ì",
 495 |     "Ihook"                     => "Ỉ",
 496 |     "Imacron"                   => "Ī",
 497 |     "Iogonek"                   => "Į",
 498 |     "Itilde"                    => "Ĩ",
 499 |     "J"                         => "J",
 500 |     "Jcircumflex"               => "Ĵ",
 501 |     "K"                         => "K",
 502 |     "Kcedilla"                  => "Ķ",
 503 |     "Korean_Won"                => "₩",
 504 |     "L"                         => "L",
 505 |     "Lacute"                    => "Ĺ",
 506 |     "Lbelowdot"                 => "Ḷ",
 507 |     "Lcaron"                    => "Ľ",
 508 |     "Lcedilla"                  => "Ļ",
 509 |     "LiraSign"                  => "₤",
 510 |     "Lstroke"                   => "Ł",
 511 |     "M"                         => "M",
 512 |     "Mabovedot"                 => "Ṁ",
 513 |     "Macedonia_DSE"             => "Ѕ",
 514 |     "Macedonia_GJE"             => "Ѓ",
 515 |     "Macedonia_KJE"             => "Ќ",
 516 |     "Macedonia_dse"             => "ѕ",
 517 |     "Macedonia_gje"             => "ѓ",
 518 |     "Macedonia_kje"             => "ќ",
 519 |     "MillSign"                  => "₥",
 520 |     "N"                         => "N",
 521 |     "Nacute"                    => "Ń",
 522 |     "NairaSign"                 => "₦",
 523 |     "Ncaron"                    => "Ň",
 524 |     "Ncedilla"                  => "Ņ",
 525 |     "NewSheqelSign"             => "₪",
 526 |     "Ntilde"                    => "Ñ",
 527 |     "O"                         => "O",
 528 |     "OE"                        => "Œ",
 529 |     "Oacute"                    => "Ó",
 530 |     "Obarred"                   => "Ɵ",
 531 |     "Obelowdot"                 => "Ọ",
 532 |     "Ocaron"                    => "ǒ",
 533 |     "Ocircumflex"               => "Ô",
 534 |     "Ocircumflexacute"          => "Ố",
 535 |     "Ocircumflexbelowdot"       => "Ộ",
 536 |     "Ocircumflexgrave"          => "Ồ",
 537 |     "Ocircumflexhook"           => "Ổ",
 538 |     "Ocircumflextilde"          => "Ỗ",
 539 |     "Odiaeresis"                => "Ö",
 540 |     "Odoubleacute"              => "Ő",
 541 |     "Ograve"                    => "Ò",
 542 |     "Ohook"                     => "Ỏ",
 543 |     "Ohorn"                     => "Ơ",
 544 |     "Ohornacute"                => "Ớ",
 545 |     "Ohornbelowdot"             => "Ợ",
 546 |     "Ohorngrave"                => "Ờ",
 547 |     "Ohornhook"                 => "Ở",
 548 |     "Ohorntilde"                => "Ỡ",
 549 |     "Omacron"                   => "Ō",
 550 |     "Ooblique"                  => "Ø",
 551 |     "Oslash"                    => "Ø",
 552 |     "Otilde"                    => "Õ",
 553 |     "P"                         => "P",
 554 |     "Pabovedot"                 => "Ṗ",
 555 |     "PesetaSign"                => "₧",
 556 |     "Q"                         => "Q",
 557 |     "R"                         => "R",
 558 |     "Racute"                    => "Ŕ",
 559 |     "Rcaron"                    => "Ř",
 560 |     "Rcedilla"                  => "Ŗ",
 561 |     "RupeeSign"                 => "₨",
 562 |     "S"                         => "S",
 563 |     "SCHWA"                     => "Ə",
 564 |     "Sabovedot"                 => "Ṡ",
 565 |     "Sacute"                    => "Ś",
 566 |     "Scaron"                    => "Š",
 567 |     "Scedilla"                  => "Ş",
 568 |     "Scircumflex"               => "Ŝ",
 569 |     "Serbian_DJE"               => "Ђ",
 570 |     "Serbian_TSHE"              => "Ћ",
 571 |     "Serbian_dje"               => "ђ",
 572 |     "Serbian_tshe"              => "ћ",
 573 |     "T"                         => "T",
 574 |     "THORN"                     => "Þ",
 575 |     "Tabovedot"                 => "Ṫ",
 576 |     "Tcaron"                    => "Ť",
 577 |     "Tcedilla"                  => "Ţ",
 578 |     "Thai_baht"                 => "฿",
 579 |     "Thai_bobaimai"             => "บ",
 580 |     "Thai_chochan"              => "จ",
 581 |     "Thai_chochang"             => "ช",
 582 |     "Thai_choching"             => "ฉ",
 583 |     "Thai_chochoe"              => "ฌ",
 584 |     "Thai_dochada"              => "ฎ",
 585 |     "Thai_dodek"                => "ด",
 586 |     "Thai_fofa"                 => "ฝ",
 587 |     "Thai_fofan"                => "ฟ",
 588 |     "Thai_hohip"                => "ห",
 589 |     "Thai_honokhuk"             => "ฮ",
 590 |     "Thai_khokhai"              => "ข",
 591 |     "Thai_khokhon"              => "ฅ",
 592 |     "Thai_khokhuat"             => "ฃ",
 593 |     "Thai_khokhwai"             => "ค",
 594 |     "Thai_khorakhang"           => "ฆ",
 595 |     "Thai_kokai"                => "ก",
 596 |     "Thai_lakkhangyao"          => "ๅ",
 597 |     "Thai_lekchet"              => "๗",
 598 |     "Thai_lekha"                => "๕",
 599 |     "Thai_lekhok"               => "๖",
 600 |     "Thai_lekkao"               => "๙",
 601 |     "Thai_leknung"              => "๑",
 602 |     "Thai_lekpaet"              => "๘",
 603 |     "Thai_leksam"               => "๓",
 604 |     "Thai_leksi"                => "๔",
 605 |     "Thai_leksong"              => "๒",
 606 |     "Thai_leksun"               => "๐",
 607 |     "Thai_lochula"              => "ฬ",
 608 |     "Thai_loling"               => "ล",
 609 |     "Thai_lu"                   => "ฦ",
 610 |     "Thai_maichattawa"          => "๋",
 611 |     "Thai_maiek"                => "่",
 612 |     "Thai_maihanakat"           => "ั",
 613 |     "Thai_maitaikhu"            => "็",
 614 |     "Thai_maitho"               => "้",
 615 |     "Thai_maitri"               => "๊",
 616 |     "Thai_maiyamok"             => "ๆ",
 617 |     "Thai_moma"                 => "ม",
 618 |     "Thai_ngongu"               => "ง",
 619 |     "Thai_nikhahit"             => "ํ",
 620 |     "Thai_nonen"                => "ณ",
 621 |     "Thai_nonu"                 => "น",
 622 |     "Thai_oang"                 => "อ",
 623 |     "Thai_paiyannoi"            => "ฯ",
 624 |     "Thai_phinthu"              => "ฺ",
 625 |     "Thai_phophan"              => "พ",
 626 |     "Thai_phophung"             => "ผ",
 627 |     "Thai_phosamphao"           => "ภ",
 628 |     "Thai_popla"                => "ป",
 629 |     "Thai_rorua"                => "ร",
 630 |     "Thai_ru"                   => "ฤ",
 631 |     "Thai_saraa"                => "ะ",
 632 |     "Thai_saraaa"               => "า",
 633 |     "Thai_saraae"               => "แ",
 634 |     "Thai_saraaimaimalai"       => "ไ",
 635 |     "Thai_saraaimaimuan"        => "ใ",
 636 |     "Thai_saraam"               => "ำ",
 637 |     "Thai_sarae"                => "เ",
 638 |     "Thai_sarai"                => "ิ",
 639 |     "Thai_saraii"               => "ี",
 640 |     "Thai_sarao"                => "โ",
 641 |     "Thai_sarau"                => "ุ",
 642 |     "Thai_saraue"               => "ึ",
 643 |     "Thai_sarauee"              => "ื",
 644 |     "Thai_sarauu"               => "ู",
 645 |     "Thai_sorusi"               => "ษ",
 646 |     "Thai_sosala"               => "ศ",
 647 |     "Thai_soso"                 => "ซ",
 648 |     "Thai_sosua"                => "ส",
 649 |     "Thai_thanthakhat"          => "์",
 650 |     "Thai_thonangmontho"        => "ฑ",
 651 |     "Thai_thophuthao"           => "ฒ",
 652 |     "Thai_thothahan"            => "ท",
 653 |     "Thai_thothan"              => "ฐ",
 654 |     "Thai_thothong"             => "ธ",
 655 |     "Thai_thothung"             => "ถ",
 656 |     "Thai_topatak"              => "ฏ",
 657 |     "Thai_totao"                => "ต",
 658 |     "Thai_wowaen"               => "ว",
 659 |     "Thai_yoyak"                => "ย",
 660 |     "Thai_yoying"               => "ญ",
 661 |     "Tslash"                    => "Ŧ",
 662 |     "U"                         => "U",
 663 |     "Uacute"                    => "Ú",
 664 |     "Ubelowdot"                 => "Ụ",
 665 |     "Ubreve"                    => "Ŭ",
 666 |     "Ucircumflex"               => "Û",
 667 |     "Udiaeresis"                => "Ü",
 668 |     "Udoubleacute"              => "Ű",
 669 |     "Ugrave"                    => "Ù",
 670 |     "Uhook"                     => "Ủ",
 671 |     "Uhorn"                     => "Ư",
 672 |     "Uhornacute"                => "Ứ",
 673 |     "Uhornbelowdot"             => "Ự",
 674 |     "Uhorngrave"                => "Ừ",
 675 |     "Uhornhook"                 => "Ử",
 676 |     "Uhorntilde"                => "Ữ",
 677 |     "Ukrainian_GHE_WITH_UPTURN" => "Ґ",
 678 |     "Ukrainian_I"               => "І",
 679 |     "Ukrainian_IE"              => "Є",
 680 |     "Ukrainian_YI"              => "Ї",
 681 |     "Ukrainian_ghe_with_upturn" => "ґ",
 682 |     "Ukrainian_i"               => "і",
 683 |     "Ukrainian_ie"              => "є",
 684 |     "Ukrainian_yi"              => "ї",
 685 |     "Umacron"                   => "Ū",
 686 |     "Uogonek"                   => "Ų",
 687 |     "Uring"                     => "Ů",
 688 |     "Utilde"                    => "Ũ",
 689 |     "V"                         => "V",
 690 |     "W"                         => "W",
 691 |     "Wacute"                    => "Ẃ",
 692 |     "Wcircumflex"               => "Ŵ",
 693 |     "Wdiaeresis"                => "Ẅ",
 694 |     "Wgrave"                    => "Ẁ",
 695 |     "WonSign"                   => "₩",
 696 |     "X"                         => "X",
 697 |     "Xabovedot"                 => "Ẋ",
 698 |     "Y"                         => "Y",
 699 |     "Yacute"                    => "Ý",
 700 |     "Ybelowdot"                 => "Ỵ",
 701 |     "Ycircumflex"               => "Ŷ",
 702 |     "Ydiaeresis"                => "Ÿ",
 703 |     "Ygrave"                    => "Ỳ",
 704 |     "Yhook"                     => "Ỷ",
 705 |     "Ytilde"                    => "Ỹ",
 706 |     "Z"                         => "Z",
 707 |     "Zabovedot"                 => "Ż",
 708 |     "Zacute"                    => "Ź",
 709 |     "Zcaron"                    => "Ž",
 710 |     "Zstroke"                   => "Ƶ",
 711 |     "a"                         => "a",
 712 |     "aacute"                    => "á",
 713 |     "abelowdot"                 => "ạ",
 714 |     "abovedot"                  => "˙",
 715 |     "abreve"                    => "ă",
 716 |     "abreveacute"               => "ắ",
 717 |     "abrevebelowdot"            => "ặ",
 718 |     "abrevegrave"               => "ằ",
 719 |     "abrevehook"                => "ẳ",
 720 |     "abrevetilde"               => "ẵ",
 721 |     "acircumflex"               => "â",
 722 |     "acircumflexacute"          => "ấ",
 723 |     "acircumflexbelowdot"       => "ậ",
 724 |     "acircumflexgrave"          => "ầ",
 725 |     "acircumflexhook"           => "ẩ",
 726 |     "acircumflextilde"          => "ẫ",
 727 |     "acute"                     => "´",
 728 |     "adiaeresis"                => "ä",
 729 |     "ae"                        => "æ",
 730 |     "agrave"                    => "à",
 731 |     "ahook"                     => "ả",
 732 |     "amacron"                   => "ā",
 733 |     "ampersand"                 => "&",
 734 |     "aogonek"                   => "ą",
 735 |     "apostrophe"                => "'",
 736 |     "approxeq"                  => "≅",
 737 |     "approximate"               => "∼",
 738 |     "aring"                     => "å",
 739 |     "asciicircum"               => "^",
 740 |     "asciitilde"                => "~",
 741 |     "asterisk"                  => "*",
 742 |     "at"                        => "@",
 743 |     "atilde"                    => "ã",
 744 |     "b"                         => "b",
 745 |     "babovedot"                 => "ḃ",
 746 |     "backslash"                 => "\\",
 747 |     "ballotcross"               => "✗",
 748 |     "bar"                       => "|",
 749 |     "because"                   => "∵",
 750 |     "botintegral"               => "⌡",
 751 |     "botleftparens"             => "⎝",
 752 |     "botleftsqbracket"          => "⎣",
 753 |     "botrightparens"            => "⎠",
 754 |     "botrightsqbracket"         => "⎦",
 755 |     "bott"                      => "┴",
 756 |     "braceleft"                 => "{",
 757 |     "braceright"                => "}",
 758 |     "bracketleft"               => "[",
 759 |     "bracketright"              => "]",
 760 |     "braille_blank"             => "⠀",
 761 |     "braille_dots_1"            => "⠁",
 762 |     "braille_dots_12"           => "⠃",
 763 |     "braille_dots_123"          => "⠇",
 764 |     "braille_dots_1234"         => "⠏",
 765 |     "braille_dots_12345"        => "⠟",
 766 |     "braille_dots_123456"       => "⠿",
 767 |     "braille_dots_1234567"      => "⡿",
 768 |     "braille_dots_12345678"     => "⣿",
 769 |     "braille_dots_1234568"      => "⢿",
 770 |     "braille_dots_123457"       => "⡟",
 771 |     "braille_dots_1234578"      => "⣟",
 772 |     "braille_dots_123458"       => "⢟",
 773 |     "braille_dots_12346"        => "⠯",
 774 |     "braille_dots_123467"       => "⡯",
 775 |     "braille_dots_1234678"      => "⣯",
 776 |     "braille_dots_123468"       => "⢯",
 777 |     "braille_dots_12347"        => "⡏",
 778 |     "braille_dots_123478"       => "⣏",
 779 |     "braille_dots_12348"        => "⢏",
 780 |     "braille_dots_1235"         => "⠗",
 781 |     "braille_dots_12356"        => "⠷",
 782 |     "braille_dots_123567"       => "⡷",
 783 |     "braille_dots_1235678"      => "⣷",
 784 |     "braille_dots_123568"       => "⢷",
 785 |     "braille_dots_12357"        => "⡗",
 786 |     "braille_dots_123578"       => "⣗",
 787 |     "braille_dots_12358"        => "⢗",
 788 |     "braille_dots_1236"         => "⠧",
 789 |     "braille_dots_12367"        => "⡧",
 790 |     "braille_dots_123678"       => "⣧",
 791 |     "braille_dots_12368"        => "⢧",
 792 |     "braille_dots_1237"         => "⡇",
 793 |     "braille_dots_12378"        => "⣇",
 794 |     "braille_dots_1238"         => "⢇",
 795 |     "braille_dots_124"          => "⠋",
 796 |     "braille_dots_1245"         => "⠛",
 797 |     "braille_dots_12456"        => "⠻",
 798 |     "braille_dots_124567"       => "⡻",
 799 |     "braille_dots_1245678"      => "⣻",
 800 |     "braille_dots_124568"       => "⢻",
 801 |     "braille_dots_12457"        => "⡛",
 802 |     "braille_dots_124578"       => "⣛",
 803 |     "braille_dots_12458"        => "⢛",
 804 |     "braille_dots_1246"         => "⠫",
 805 |     "braille_dots_12467"        => "⡫",
 806 |     "braille_dots_124678"       => "⣫",
 807 |     "braille_dots_12468"        => "⢫",
 808 |     "braille_dots_1247"         => "⡋",
 809 |     "braille_dots_12478"        => "⣋",
 810 |     "braille_dots_1248"         => "⢋",
 811 |     "braille_dots_125"          => "⠓",
 812 |     "braille_dots_1256"         => "⠳",
 813 |     "braille_dots_12567"        => "⡳",
 814 |     "braille_dots_125678"       => "⣳",
 815 |     "braille_dots_12568"        => "⢳",
 816 |     "braille_dots_1257"         => "⡓",
 817 |     "braille_dots_12578"        => "⣓",
 818 |     "braille_dots_1258"         => "⢓",
 819 |     "braille_dots_126"          => "⠣",
 820 |     "braille_dots_1267"         => "⡣",
 821 |     "braille_dots_12678"        => "⣣",
 822 |     "braille_dots_1268"         => "⢣",
 823 |     "braille_dots_127"          => "⡃",
 824 |     "braille_dots_1278"         => "⣃",
 825 |     "braille_dots_128"          => "⢃",
 826 |     "braille_dots_13"           => "⠅",
 827 |     "braille_dots_134"          => "⠍",
 828 |     "braille_dots_1345"         => "⠝",
 829 |     "braille_dots_13456"        => "⠽",
 830 |     "braille_dots_134567"       => "⡽",
 831 |     "braille_dots_1345678"      => "⣽",
 832 |     "braille_dots_134568"       => "⢽",
 833 |     "braille_dots_13457"        => "⡝",
 834 |     "braille_dots_134578"       => "⣝",
 835 |     "braille_dots_13458"        => "⢝",
 836 |     "braille_dots_1346"         => "⠭",
 837 |     "braille_dots_13467"        => "⡭",
 838 |     "braille_dots_134678"       => "⣭",
 839 |     "braille_dots_13468"        => "⢭",
 840 |     "braille_dots_1347"         => "⡍",
 841 |     "braille_dots_13478"        => "⣍",
 842 |     "braille_dots_1348"         => "⢍",
 843 |     "braille_dots_135"          => "⠕",
 844 |     "braille_dots_1356"         => "⠵",
 845 |     "braille_dots_13567"        => "⡵",
 846 |     "braille_dots_135678"       => "⣵",
 847 |     "braille_dots_13568"        => "⢵",
 848 |     "braille_dots_1357"         => "⡕",
 849 |     "braille_dots_13578"        => "⣕",
 850 |     "braille_dots_1358"         => "⢕",
 851 |     "braille_dots_136"          => "⠥",
 852 |     "braille_dots_1367"         => "⡥",
 853 |     "braille_dots_13678"        => "⣥",
 854 |     "braille_dots_1368"         => "⢥",
 855 |     "braille_dots_137"          => "⡅",
 856 |     "braille_dots_1378"         => "⣅",
 857 |     "braille_dots_138"          => "⢅",
 858 |     "braille_dots_14"           => "⠉",
 859 |     "braille_dots_145"          => "⠙",
 860 |     "braille_dots_1456"         => "⠹",
 861 |     "braille_dots_14567"        => "⡹",
 862 |     "braille_dots_145678"       => "⣹",
 863 |     "braille_dots_14568"        => "⢹",
 864 |     "braille_dots_1457"         => "⡙",
 865 |     "braille_dots_14578"        => "⣙",
 866 |     "braille_dots_1458"         => "⢙",
 867 |     "braille_dots_146"          => "⠩",
 868 |     "braille_dots_1467"         => "⡩",
 869 |     "braille_dots_14678"        => "⣩",
 870 |     "braille_dots_1468"         => "⢩",
 871 |     "braille_dots_147"          => "⡉",
 872 |     "braille_dots_1478"         => "⣉",
 873 |     "braille_dots_148"          => "⢉",
 874 |     "braille_dots_15"           => "⠑",
 875 |     "braille_dots_156"          => "⠱",
 876 |     "braille_dots_1567"         => "⡱",
 877 |     "braille_dots_15678"        => "⣱",
 878 |     "braille_dots_1568"         => "⢱",
 879 |     "braille_dots_157"          => "⡑",
 880 |     "braille_dots_1578"         => "⣑",
 881 |     "braille_dots_158"          => "⢑",
 882 |     "braille_dots_16"           => "⠡",
 883 |     "braille_dots_167"          => "⡡",
 884 |     "braille_dots_1678"         => "⣡",
 885 |     "braille_dots_168"          => "⢡",
 886 |     "braille_dots_17"           => "⡁",
 887 |     "braille_dots_178"          => "⣁",
 888 |     "braille_dots_18"           => "⢁",
 889 |     "braille_dots_2"            => "⠂",
 890 |     "braille_dots_23"           => "⠆",
 891 |     "braille_dots_234"          => "⠎",
 892 |     "braille_dots_2345"         => "⠞",
 893 |     "braille_dots_23456"        => "⠾",
 894 |     "braille_dots_234567"       => "⡾",
 895 |     "braille_dots_2345678"      => "⣾",
 896 |     "braille_dots_234568"       => "⢾",
 897 |     "braille_dots_23457"        => "⡞",
 898 |     "braille_dots_234578"       => "⣞",
 899 |     "braille_dots_23458"        => "⢞",
 900 |     "braille_dots_2346"         => "⠮",
 901 |     "braille_dots_23467"        => "⡮",
 902 |     "braille_dots_234678"       => "⣮",
 903 |     "braille_dots_23468"        => "⢮",
 904 |     "braille_dots_2347"         => "⡎",
 905 |     "braille_dots_23478"        => "⣎",
 906 |     "braille_dots_2348"         => "⢎",
 907 |     "braille_dots_235"          => "⠖",
 908 |     "braille_dots_2356"         => "⠶",
 909 |     "braille_dots_23567"        => "⡶",
 910 |     "braille_dots_235678"       => "⣶",
 911 |     "braille_dots_23568"        => "⢶",
 912 |     "braille_dots_2357"         => "⡖",
 913 |     "braille_dots_23578"        => "⣖",
 914 |     "braille_dots_2358"         => "⢖",
 915 |     "braille_dots_236"          => "⠦",
 916 |     "braille_dots_2367"         => "⡦",
 917 |     "braille_dots_23678"        => "⣦",
 918 |     "braille_dots_2368"         => "⢦",
 919 |     "braille_dots_237"          => "⡆",
 920 |     "braille_dots_2378"         => "⣆",
 921 |     "braille_dots_238"          => "⢆",
 922 |     "braille_dots_24"           => "⠊",
 923 |     "braille_dots_245"          => "⠚",
 924 |     "braille_dots_2456"         => "⠺",
 925 |     "braille_dots_24567"        => "⡺",
 926 |     "braille_dots_245678"       => "⣺",
 927 |     "braille_dots_24568"        => "⢺",
 928 |     "braille_dots_2457"         => "⡚",
 929 |     "braille_dots_24578"        => "⣚",
 930 |     "braille_dots_2458"         => "⢚",
 931 |     "braille_dots_246"          => "⠪",
 932 |     "braille_dots_2467"         => "⡪",
 933 |     "braille_dots_24678"        => "⣪",
 934 |     "braille_dots_2468"         => "⢪",
 935 |     "braille_dots_247"          => "⡊",
 936 |     "braille_dots_2478"         => "⣊",
 937 |     "braille_dots_248"          => "⢊",
 938 |     "braille_dots_25"           => "⠒",
 939 |     "braille_dots_256"          => "⠲",
 940 |     "braille_dots_2567"         => "⡲",
 941 |     "braille_dots_25678"        => "⣲",
 942 |     "braille_dots_2568"         => "⢲",
 943 |     "braille_dots_257"          => "⡒",
 944 |     "braille_dots_2578"         => "⣒",
 945 |     "braille_dots_258"          => "⢒",
 946 |     "braille_dots_26"           => "⠢",
 947 |     "braille_dots_267"          => "⡢",
 948 |     "braille_dots_2678"         => "⣢",
 949 |     "braille_dots_268"          => "⢢",
 950 |     "braille_dots_27"           => "⡂",
 951 |     "braille_dots_278"          => "⣂",
 952 |     "braille_dots_28"           => "⢂",
 953 |     "braille_dots_3"            => "⠄",
 954 |     "braille_dots_34"           => "⠌",
 955 |     "braille_dots_345"          => "⠜",
 956 |     "braille_dots_3456"         => "⠼",
 957 |     "braille_dots_34567"        => "⡼",
 958 |     "braille_dots_345678"       => "⣼",
 959 |     "braille_dots_34568"        => "⢼",
 960 |     "braille_dots_3457"         => "⡜",
 961 |     "braille_dots_34578"        => "⣜",
 962 |     "braille_dots_3458"         => "⢜",
 963 |     "braille_dots_346"          => "⠬",
 964 |     "braille_dots_3467"         => "⡬",
 965 |     "braille_dots_34678"        => "⣬",
 966 |     "braille_dots_3468"         => "⢬",
 967 |     "braille_dots_347"          => "⡌",
 968 |     "braille_dots_3478"         => "⣌",
 969 |     "braille_dots_348"          => "⢌",
 970 |     "braille_dots_35"           => "⠔",
 971 |     "braille_dots_356"          => "⠴",
 972 |     "braille_dots_3567"         => "⡴",
 973 |     "braille_dots_35678"        => "⣴",
 974 |     "braille_dots_3568"         => "⢴",
 975 |     "braille_dots_357"          => "⡔",
 976 |     "braille_dots_3578"         => "⣔",
 977 |     "braille_dots_358"          => "⢔",
 978 |     "braille_dots_36"           => "⠤",
 979 |     "braille_dots_367"          => "⡤",
 980 |     "braille_dots_3678"         => "⣤",
 981 |     "braille_dots_368"          => "⢤",
 982 |     "braille_dots_37"           => "⡄",
 983 |     "braille_dots_378"          => "⣄",
 984 |     "braille_dots_38"           => "⢄",
 985 |     "braille_dots_4"            => "⠈",
 986 |     "braille_dots_45"           => "⠘",
 987 |     "braille_dots_456"          => "⠸",
 988 |     "braille_dots_4567"         => "⡸",
 989 |     "braille_dots_45678"        => "⣸",
 990 |     "braille_dots_4568"         => "⢸",
 991 |     "braille_dots_457"          => "⡘",
 992 |     "braille_dots_4578"         => "⣘",
 993 |     "braille_dots_458"          => "⢘",
 994 |     "braille_dots_46"           => "⠨",
 995 |     "braille_dots_467"          => "⡨",
 996 |     "braille_dots_4678"         => "⣨",
 997 |     "braille_dots_468"          => "⢨",
 998 |     "braille_dots_47"           => "⡈",
 999 |     "braille_dots_478"          => "⣈",
1000 |     "braille_dots_48"           => "⢈",
1001 |     "braille_dots_5"            => "⠐",
1002 |     "braille_dots_56"           => "⠰",
1003 |     "braille_dots_567"          => "⡰",
1004 |     "braille_dots_5678"         => "⣰",
1005 |     "braille_dots_568"          => "⢰",
1006 |     "braille_dots_57"           => "⡐",
1007 |     "braille_dots_578"          => "⣐",
1008 |     "braille_dots_58"           => "⢐",
1009 |     "braille_dots_6"            => "⠠",
1010 |     "braille_dots_67"           => "⡠",
1011 |     "braille_dots_678"          => "⣠",
1012 |     "braille_dots_68"           => "⢠",
1013 |     "braille_dots_7"            => "⡀",
1014 |     "braille_dots_78"           => "⣀",
1015 |     "braille_dots_8"            => "⢀",
1016 |     "breve"                     => "˘",
1017 |     "brokenbar"                 => "¦",
1018 |     "c"                         => "c",
1019 |     "cabovedot"                 => "ċ",
1020 |     "cacute"                    => "ć",
1021 |     "careof"                    => "℅",
1022 |     "caret"                     => "‸",
1023 |     "caron"                     => "ˇ",
1024 |     "ccaron"                    => "č",
1025 |     "ccedilla"                  => "ç",
1026 |     "ccircumflex"               => "ĉ",
1027 |     "cedilla"                   => "¸",
1028 |     "cent"                      => "¢",
1029 |     "checkerboard"              => "▒",
1030 |     "checkmark"                 => "✓",
1031 |     "circle"                    => "○",
1032 |     "club"                      => "♣",
1033 |     "colon"                     => ":",
1034 |     "comma"                     => ",",
1035 |     "containsas"                => "∋",
1036 |     "copyright"                 => "©",
1037 |     "cr"                        => "␍",
1038 |     "crossinglines"             => "┼",
1039 |     "cuberoot"                  => "∛",
1040 |     "currency"                  => "¤",
1041 |     "d"                         => "d",
1042 |     "dabovedot"                 => "ḋ",
1043 |     "dagger"                    => "†",
1044 |     "dcaron"                    => "ď",
1045 |     "decimalpoint"              => ".",
1046 |     "degree"                    => "°",
1047 |     "diaeresis"                 => "¨",
1048 |     "diamond"                   => "♦",
1049 |     "digitspace"                => " ",
1050 |     "dintegral"                 => "∬",
1051 |     "division"                  => "÷",
1052 |     "dollar"                    => "$",
1053 |     "doubbaselinedot"           => "‥",
1054 |     "doubleacute"               => "˝",
1055 |     "doubledagger"              => "‡",
1056 |     "doublelowquotemark"        => "„",
1057 |     "downarrow"                 => "↓",
1058 |     "downcaret"                 => "∨",
1059 |     "downshoe"                  => "∪",
1060 |     "downstile"                 => "⌊",
1061 |     "downtack"                  => "⊤",
1062 |     "dstroke"                   => "đ",
1063 |     "e"                         => "e",
1064 |     "eabovedot"                 => "ė",
1065 |     "eacute"                    => "é",
1066 |     "ebelowdot"                 => "ẹ",
1067 |     "ecaron"                    => "ě",
1068 |     "ecircumflex"               => "ê",
1069 |     "ecircumflexacute"          => "ế",
1070 |     "ecircumflexbelowdot"       => "ệ",
1071 |     "ecircumflexgrave"          => "ề",
1072 |     "ecircumflexhook"           => "ể",
1073 |     "ecircumflextilde"          => "ễ",
1074 |     "ediaeresis"                => "ë",
1075 |     "egrave"                    => "è",
1076 |     "ehook"                     => "ẻ",
1077 |     "eightsubscript"            => "₈",
1078 |     "eightsuperior"             => "⁸",
1079 |     "elementof"                 => "∈",
1080 |     "ellipsis"                  => "…",
1081 |     "em3space"                  => " ",
1082 |     "em4space"                  => " ",
1083 |     "emacron"                   => "ē",
1084 |     "emdash"                    => "—",
1085 |     "emfilledcircle"            => "●",
1086 |     "emfilledrect"              => "▮",
1087 |     "emopencircle"              => "○",
1088 |     "emopenrectangle"           => "▯",
1089 |     "emptyset"                  => "∅",
1090 |     "emspace"                   => " ",
1091 |     "endash"                    => "–",
1092 |     "enfilledcircbullet"        => "•",
1093 |     "enfilledsqbullet"          => "▪",
1094 |     "eng"                       => "ŋ",
1095 |     "enopencircbullet"          => "◦",
1096 |     "enopensquarebullet"        => "▫",
1097 |     "enspace"                   => " ",
1098 |     "eogonek"                   => "ę",
1099 |     "equal"                     => "=",
1100 |     "eth"                       => "ð",
1101 |     "etilde"                    => "ẽ",
1102 |     "exclam"                    => "!",
1103 |     "exclamdown"                => "¡",
1104 |     "f"                         => "f",
1105 |     "fabovedot"                 => "ḟ",
1106 |     "femalesymbol"              => "♀",
1107 |     "ff"                        => "␌",
1108 |     "figdash"                   => "‒",
1109 |     "filledlefttribullet"       => "◀",
1110 |     "filledrectbullet"          => "▬",
1111 |     "filledrighttribullet"      => "▶",
1112 |     "filledtribulletdown"       => "▼",
1113 |     "filledtribulletup"         => "▲",
1114 |     "fiveeighths"               => "⅝",
1115 |     "fivesixths"                => "⅚",
1116 |     "fivesubscript"             => "₅",
1117 |     "fivesuperior"              => "⁵",
1118 |     "fourfifths"                => "⅘",
1119 |     "foursubscript"             => "₄",
1120 |     "foursuperior"              => "⁴",
1121 |     "fourthroot"                => "∜",
1122 |     "function"                  => "ƒ",
1123 |     "g"                         => "g",
1124 |     "gabovedot"                 => "ġ",
1125 |     "gbreve"                    => "ğ",
1126 |     "gcaron"                    => "ǧ",
1127 |     "gcedilla"                  => "ģ",
1128 |     "gcircumflex"               => "ĝ",
1129 |     "grave"                     => "`",
1130 |     "greater"                   => ">",
1131 |     "greaterthanequal"          => "≥",
1132 |     "guillemotleft"             => "«",
1133 |     "guillemotright"            => "»",
1134 |     "h"                         => "h",
1135 |     "hairspace"                 => " ",
1136 |     "hcircumflex"               => "ĥ",
1137 |     "heart"                     => "♥",
1138 |     "hebrew_aleph"              => "א",
1139 |     "hebrew_ayin"               => "ע",
1140 |     "hebrew_bet"                => "ב",
1141 |     "hebrew_chet"               => "ח",
1142 |     "hebrew_dalet"              => "ד",
1143 |     "hebrew_doublelowline"      => "‗",
1144 |     "hebrew_finalkaph"          => "ך",
1145 |     "hebrew_finalmem"           => "ם",
1146 |     "hebrew_finalnun"           => "ן",
1147 |     "hebrew_finalpe"            => "ף",
1148 |     "hebrew_finalzade"          => "ץ",
1149 |     "hebrew_gimel"              => "ג",
1150 |     "hebrew_he"                 => "ה",
1151 |     "hebrew_kaph"               => "כ",
1152 |     "hebrew_lamed"              => "ל",
1153 |     "hebrew_mem"                => "מ",
1154 |     "hebrew_nun"                => "נ",
1155 |     "hebrew_pe"                 => "פ",
1156 |     "hebrew_qoph"               => "ק",
1157 |     "hebrew_resh"               => "ר",
1158 |     "hebrew_samech"             => "ס",
1159 |     "hebrew_shin"               => "ש",
1160 |     "hebrew_taw"                => "ת",
1161 |     "hebrew_tet"                => "ט",
1162 |     "hebrew_waw"                => "ו",
1163 |     "hebrew_yod"                => "י",
1164 |     "hebrew_zade"               => "צ",
1165 |     "hebrew_zain"               => "ז",
1166 |     "horizconnector"            => "─",
1167 |     "horizlinescan1"            => "⎺",
1168 |     "horizlinescan3"            => "⎻",
1169 |     "horizlinescan5"            => "─",
1170 |     "horizlinescan7"            => "⎼",
1171 |     "horizlinescan9"            => "⎽",
1172 |     "hstroke"                   => "ħ",
1173 |     "ht"                        => "␉",
1174 |     "hyphen"                    => "­",
1175 |     "i"                         => "i",
1176 |     "iacute"                    => "í",
1177 |     "ibelowdot"                 => "ị",
1178 |     "ibreve"                    => "ĭ",
1179 |     "icircumflex"               => "î",
1180 |     "identical"                 => "≡",
1181 |     "idiaeresis"                => "ï",
1182 |     "idotless"                  => "ı",
1183 |     "ifonlyif"                  => "⇔",
1184 |     "igrave"                    => "ì",
1185 |     "ihook"                     => "ỉ",
1186 |     "imacron"                   => "ī",
1187 |     "implies"                   => "⇒",
1188 |     "includedin"                => "⊂",
1189 |     "includes"                  => "⊃",
1190 |     "infinity"                  => "∞",
1191 |     "integral"                  => "∫",
1192 |     "intersection"              => "∩",
1193 |     "iogonek"                   => "į",
1194 |     "itilde"                    => "ĩ",
1195 |     "j"                         => "j",
1196 |     "jcircumflex"               => "ĵ",
1197 |     "jot"                       => "∘",
1198 |     "k"                         => "k",
1199 |     "kana_A"                    => "ア",
1200 |     "kana_CHI"                  => "チ",
1201 |     "kana_E"                    => "エ",
1202 |     "kana_FU"                   => "フ",
1203 |     "kana_HA"                   => "ハ",
1204 |     "kana_HE"                   => "ヘ",
1205 |     "kana_HI"                   => "ヒ",
1206 |     "kana_HO"                   => "ホ",
1207 |     "kana_I"                    => "イ",
1208 |     "kana_KA"                   => "カ",
1209 |     "kana_KE"                   => "ケ",
1210 |     "kana_KI"                   => "キ",
1211 |     "kana_KO"                   => "コ",
1212 |     "kana_KU"                   => "ク",
1213 |     "kana_MA"                   => "マ",
1214 |     "kana_ME"                   => "メ",
1215 |     "kana_MI"                   => "ミ",
1216 |     "kana_MO"                   => "モ",
1217 |     "kana_MU"                   => "ム",
1218 |     "kana_N"                    => "ン",
1219 |     "kana_NA"                   => "ナ",
1220 |     "kana_NE"                   => "ネ",
1221 |     "kana_NI"                   => "ニ",
1222 |     "kana_NO"                   => "ノ",
1223 |     "kana_NU"                   => "ヌ",
1224 |     "kana_O"                    => "オ",
1225 |     "kana_RA"                   => "ラ",
1226 |     "kana_RE"                   => "レ",
1227 |     "kana_RI"                   => "リ",
1228 |     "kana_RO"                   => "ロ",
1229 |     "kana_RU"                   => "ル",
1230 |     "kana_SA"                   => "サ",
1231 |     "kana_SE"                   => "セ",
1232 |     "kana_SHI"                  => "シ",
1233 |     "kana_SO"                   => "ソ",
1234 |     "kana_SU"                   => "ス",
1235 |     "kana_TA"                   => "タ",
1236 |     "kana_TE"                   => "テ",
1237 |     "kana_TO"                   => "ト",
1238 |     "kana_TSU"                  => "ツ",
1239 |     "kana_U"                    => "ウ",
1240 |     "kana_WA"                   => "ワ",
1241 |     "kana_WO"                   => "ヲ",
1242 |     "kana_YA"                   => "ヤ",
1243 |     "kana_YO"                   => "ヨ",
1244 |     "kana_YU"                   => "ユ",
1245 |     "kana_a"                    => "ァ",
1246 |     "kana_closingbracket"       => "」",
1247 |     "kana_comma"                => "、",
1248 |     "kana_conjunctive"          => "・",
1249 |     "kana_e"                    => "ェ",
1250 |     "kana_fullstop"             => "。",
1251 |     "kana_i"                    => "ィ",
1252 |     "kana_o"                    => "ォ",
1253 |     "kana_openingbracket"       => "「",
1254 |     "kana_tsu"                  => "ッ",
1255 |     "kana_u"                    => "ゥ",
1256 |     "kana_ya"                   => "ャ",
1257 |     "kana_yo"                   => "ョ",
1258 |     "kana_yu"                   => "ュ",
1259 |     "kcedilla"                  => "ķ",
1260 |     "kra"                       => "ĸ",
1261 |     "l"                         => "l",
1262 |     "lacute"                    => "ĺ",
1263 |     "latincross"                => "✝",
1264 |     "lbelowdot"                 => "ḷ",
1265 |     "lcaron"                    => "ľ",
1266 |     "lcedilla"                  => "ļ",
1267 |     "leftanglebracket"          => "⟨",
1268 |     "leftarrow"                 => "←",
1269 |     "leftcaret"                 => "<",
1270 |     "leftdoublequotemark"       => "“",
1271 |     "leftmiddlecurlybrace"      => "⎨",
1272 |     "leftopentriangle"          => "◁",
1273 |     "leftpointer"               => "☜",
1274 |     "leftradical"               => "⎷",
1275 |     "leftshoe"                  => "⊂",
1276 |     "leftsinglequotemark"       => "‘",
1277 |     "leftt"                     => "├",
1278 |     "lefttack"                  => "⊣",
1279 |     "less"                      => "<",
1280 |     "lessthanequal"             => "≤",
1281 |     "lf"                        => "␊",
1282 |     "logicaland"                => "∧",
1283 |     "logicalor"                 => "∨",
1284 |     "lowleftcorner"             => "└",
1285 |     "lowrightcorner"            => "┘",
1286 |     "lstroke"                   => "ł",
1287 |     "m"                         => "m",
1288 |     "mabovedot"                 => "ṁ",
1289 |     "macron"                    => "¯",
1290 |     "malesymbol"                => "♂",
1291 |     "maltesecross"              => "✠",
1292 |     "masculine"                 => "º",
1293 |     "minus"                     => "-",
1294 |     "minutes"                   => "′",
1295 |     "mu"                        => "µ",
1296 |     "multiply"                  => "×",
1297 |     "musicalflat"               => "♭",
1298 |     "musicalsharp"              => "♯",
1299 |     "n"                         => "n",
1300 |     "nabla"                     => "∇",
1301 |     "nacute"                    => "ń",
1302 |     "ncaron"                    => "ň",
1303 |     "ncedilla"                  => "ņ",
1304 |     "ninesubscript"             => "₉",
1305 |     "ninesuperior"              => "⁹",
1306 |     "nl"                        => "␤",
1307 |     "nobreakspace"              => " ",
1308 |     "notapproxeq"               => "≇",
1309 |     "notelementof"              => "∉",
1310 |     "notequal"                  => "≠",
1311 |     "notidentical"              => "≢",
1312 |     "notsign"                   => "¬",
1313 |     "ntilde"                    => "ñ",
1314 |     "numbersign"                => "#",
1315 |     "numerosign"                => "№",
1316 |     "o"                         => "o",
1317 |     "oacute"                    => "ó",
1318 |     "obarred"                   => "ɵ",
1319 |     "obelowdot"                 => "ọ",
1320 |     "ocaron"                    => "ǒ",
1321 |     "ocircumflex"               => "ô",
1322 |     "ocircumflexacute"          => "ố",
1323 |     "ocircumflexbelowdot"       => "ộ",
1324 |     "ocircumflexgrave"          => "ồ",
1325 |     "ocircumflexhook"           => "ổ",
1326 |     "ocircumflextilde"          => "ỗ",
1327 |     "odiaeresis"                => "ö",
1328 |     "odoubleacute"              => "ő",
1329 |     "oe"                        => "œ",
1330 |     "ogonek"                    => "˛",
1331 |     "ograve"                    => "ò",
1332 |     "ohook"                     => "ỏ",
1333 |     "ohorn"                     => "ơ",
1334 |     "ohornacute"                => "ớ",
1335 |     "ohornbelowdot"             => "ợ",
1336 |     "ohorngrave"                => "ờ",
1337 |     "ohornhook"                 => "ở",
1338 |     "ohorntilde"                => "ỡ",
1339 |     "omacron"                   => "ō",
1340 |     "oneeighth"                 => "⅛",
1341 |     "onefifth"                  => "⅕",
1342 |     "onehalf"                   => "½",
1343 |     "onequarter"                => "¼",
1344 |     "onesixth"                  => "⅙",
1345 |     "onesubscript"              => "₁",
1346 |     "onesuperior"               => "¹",
1347 |     "onethird"                  => "⅓",
1348 |     "ooblique"                  => "ø",
1349 |     "openrectbullet"            => "▭",
1350 |     "openstar"                  => "☆",
1351 |     "opentribulletdown"         => "▽",
1352 |     "opentribulletup"           => "△",
1353 |     "ordfeminine"               => "ª",
1354 |     "oslash"                    => "ø",
1355 |     "otilde"                    => "õ",
1356 |     "overbar"                   => "¯",
1357 |     "overline"                  => "‾",
1358 |     "p"                         => "p",
1359 |     "pabovedot"                 => "ṗ",
1360 |     "paragraph"                 => "¶",
1361 |     "parenleft"                 => "(",
1362 |     "parenright"                => ")",
1363 |     "partdifferential"          => "∂",
1364 |     "partialderivative"         => "∂",
1365 |     "percent"                   => "%",
1366 |     "period"                    => ".",
1367 |     "periodcentered"            => "·",
1368 |     "phonographcopyright"       => "℗",
1369 |     "plus"                      => "+",
1370 |     "plusminus"                 => "±",
1371 |     "prescription"              => "℞",
1372 |     "prolongedsound"            => "ー",
1373 |     "punctspace"                => " ",
1374 |     "q"                         => "q",
1375 |     "quad"                      => "⎕",
1376 |     "question"                  => "?",
1377 |     "questiondown"              => "¿",
1378 |     "quotedbl"                  => "\"",
1379 |     "r"                         => "r",
1380 |     "racute"                    => "ŕ",
1381 |     "radical"                   => "√",
1382 |     "rcaron"                    => "ř",
1383 |     "rcedilla"                  => "ŗ",
1384 |     "registered"                => "®",
1385 |     "rightanglebracket"         => "⟩",
1386 |     "rightarrow"                => "→",
1387 |     "rightcaret"                => ">",
1388 |     "rightdoublequotemark"      => "”",
1389 |     "rightmiddlecurlybrace"     => "⎬",
1390 |     "rightopentriangle"         => "▷",
1391 |     "rightpointer"              => "☞",
1392 |     "rightshoe"                 => "⊃",
1393 |     "rightsinglequotemark"      => "’",
1394 |     "rightt"                    => "┤",
1395 |     "righttack"                 => "⊢",
1396 |     "s"                         => "s",
1397 |     "sabovedot"                 => "ṡ",
1398 |     "sacute"                    => "ś",
1399 |     "scaron"                    => "š",
1400 |     "scedilla"                  => "ş",
1401 |     "schwa"                     => "ə",
1402 |     "scircumflex"               => "ŝ",
1403 |     "seconds"                   => "″",
1404 |     "section"                   => "§",
1405 |     "semicolon"                 => ";",
1406 |     "semivoicedsound"           => "゜",
1407 |     "seveneighths"              => "⅞",
1408 |     "sevensubscript"            => "₇",
1409 |     "sevensuperior"             => "⁷",
1410 |     "signaturemark"             => "☓",
1411 |     "signifblank"               => "␣",
1412 |     "similarequal"              => "≃",
1413 |     "singlelowquotemark"        => "‚",
1414 |     "sixsubscript"              => "₆",
1415 |     "sixsuperior"               => "⁶",
1416 |     "slash"                     => "/",
1417 |     "soliddiamond"              => "◆",
1418 |     "space"                     => " ",
1419 |     "squareroot"                => "√",
1420 |     "ssharp"                    => "ß",
1421 |     "sterling"                  => "£",
1422 |     "stricteq"                  => "≣",
1423 |     "t"                         => "t",
1424 |     "tabovedot"                 => "ṫ",
1425 |     "tcaron"                    => "ť",
1426 |     "tcedilla"                  => "ţ",
1427 |     "telephone"                 => "☎",
1428 |     "telephonerecorder"         => "⌕",
1429 |     "therefore"                 => "∴",
1430 |     "thinspace"                 => " ",
1431 |     "thorn"                     => "þ",
1432 |     "threeeighths"              => "⅜",
1433 |     "threefifths"               => "⅗",
1434 |     "threequarters"             => "¾",
1435 |     "threesubscript"            => "₃",
1436 |     "threesuperior"             => "³",
1437 |     "tintegral"                 => "∭",
1438 |     "topintegral"               => "⌠",
1439 |     "topleftparens"             => "⎛",
1440 |     "topleftradical"            => "┌",
1441 |     "topleftsqbracket"          => "⎡",
1442 |     "toprightparens"            => "⎞",
1443 |     "toprightsqbracket"         => "⎤",
1444 |     "topt"                      => "┬",
1445 |     "trademark"                 => "™",
1446 |     "tslash"                    => "ŧ",
1447 |     "twofifths"                 => "⅖",
1448 |     "twosubscript"              => "₂",
1449 |     "twosuperior"               => "²",
1450 |     "twothirds"                 => "⅔",
1451 |     "u"                         => "u",
1452 |     "uacute"                    => "ú",
1453 |     "ubelowdot"                 => "ụ",
1454 |     "ubreve"                    => "ŭ",
1455 |     "ucircumflex"               => "û",
1456 |     "udiaeresis"                => "ü",
1457 |     "udoubleacute"              => "ű",
1458 |     "ugrave"                    => "ù",
1459 |     "uhook"                     => "ủ",
1460 |     "uhorn"                     => "ư",
1461 |     "uhornacute"                => "ứ",
1462 |     "uhornbelowdot"             => "ự",
1463 |     "uhorngrave"                => "ừ",
1464 |     "uhornhook"                 => "ử",
1465 |     "uhorntilde"                => "ữ",
1466 |     "umacron"                   => "ū",
1467 |     "underbar"                  => "_",
1468 |     "underscore"                => "_",
1469 |     "union"                     => "∪",
1470 |     "uogonek"                   => "ų",
1471 |     "uparrow"                   => "↑",
1472 |     "upcaret"                   => "∧",
1473 |     "upleftcorner"              => "┌",
1474 |     "uprightcorner"             => "┐",
1475 |     "upshoe"                    => "∩",
1476 |     "upstile"                   => "⌈",
1477 |     "uptack"                    => "⊥",
1478 |     "uring"                     => "ů",
1479 |     "utilde"                    => "ũ",
1480 |     "v"                         => "v",
1481 |     "variation"                 => "∝",
1482 |     "vertbar"                   => "│",
1483 |     "vertconnector"             => "│",
1484 |     "voicedsound"               => "゛",
1485 |     "vt"                        => "␋",
1486 |     "w"                         => "w",
1487 |     "wacute"                    => "ẃ",
1488 |     "wcircumflex"               => "ŵ",
1489 |     "wdiaeresis"                => "ẅ",
1490 |     "wgrave"                    => "ẁ",
1491 |     "x"                         => "x",
1492 |     "xabovedot"                 => "ẋ",
1493 |     "y"                         => "y",
1494 |     "yacute"                    => "ý",
1495 |     "ybelowdot"                 => "ỵ",
1496 |     "ycircumflex"               => "ŷ",
1497 |     "ydiaeresis"                => "ÿ",
1498 |     "yen"                       => "¥",
1499 |     "ygrave"                    => "ỳ",
1500 |     "yhook"                     => "ỷ",
1501 |     "ytilde"                    => "ỹ",
1502 |     "z"                         => "z",
1503 |     "zabovedot"                 => "ż",
1504 |     "zacute"                    => "ź",
1505 |     "zcaron"                    => "ž",
1506 |     "zerosubscript"             => "₀",
1507 |     "zerosuperior"              => "⁰",
1508 |     "zstroke"                   => "ƶ",
1509 |   }
1510 | end
1511 | 


--------------------------------------------------------------------------------
/xcompose:
--------------------------------------------------------------------------------
   1 | # -*- coding: utf-8; mode: conf -*-
   2 | include "%L"
   3 | 
   4 | # See also http://bleah.co.uk/~simon/stuff/XCompose
   5 | # and http://dotfiles.org/~inky/.XCompose
   6 | # and http://paste.lisp.org/display/73094
   7 | # and https://tools.ietf.org/html/rfc1345
   8 | 
   9 | # scan4dups.py will ignore conflicts marked INTENTIONAL CONFLICT
  10 | 
  11 | # Arrows
  12 | # ======
  13 | <Multi_key> <less> <greater>: "↔" U2194 # INTENTIONAL CONFLICT
  14 | <Multi_key> <asciicircum> <bar>: "↑" U2191
  15 | <Multi_key> <bar> <asciicircum>: "↑" U2191
  16 | <Multi_key> <v> <bar>: "↓" U2193
  17 | <Multi_key> <bar> <v>: "↓" U2193
  18 | 
  19 | <Multi_key> <bar> <less> <minus>      : "↚"   U219A # LEFTWARDS ARROW WITH STROKE
  20 | <Multi_key> <bar> <minus> <greater>   : "↛"   U219B # RIGHTWARDS ARROW WITH STROKE
  21 | <Multi_key> <bar> <less> <greater>    : "↮"   U21AE # LEFT RIGHT ARROW WITH STROKE
  22 | 
  23 | <Multi_key> <less> <v>		      : "↵"	U21B5		# DOWNWARDS ARROW WITH CORNER LEFTWARDS
  24 | 
  25 | <Multi_key> <minus> <less>		: "←"	leftarrow	# LEFTWARDS ARROW
  26 | <Multi_key> <minus> <asciicircum>	: "↑"	uparrow		# UPWARDS ARROW (INTENTIONAL CONFLICT)
  27 | <Multi_key> <minus> <v>			: "↓"	downarrow	# DOWNWARDS ARROW
  28 | 
  29 | <Multi_key> <asciicircum> <v>		: "↕"	U2195           # UP DOWN ARROW (kragen's)
  30 | <Multi_key> <asciicircum> <ampersand> <v>: "⇵"	U21F5		# DOWNWARDS ARROW LEFTWARDS OF UPWARDS ARROW
  31 | <Multi_key> <less> <o>			: "⟲"	U27F2		# ANTICLOCKWISE GAPPED CIRCLE ARROW
  32 | <Multi_key> <greater> <o>		: "⟳"	U27F3		# CLOCKWISE GAPPED CIRCLE ARROW (INTENTIONAL CONFLICT)
  33 | # FIXME: conflict
  34 | #<Multi_key> <less> <c>			: "↺"	U21BA		# ANTICLOCKWISE OPEN CIRCLE ARROW
  35 | <Multi_key> <greater> <c>		: "↻"	U21BB		# CLOCKWISE OPEN CIRCLE ARROW
  36 | <Multi_key> <less> <asciitilde>		: "⇜"	U21DC		# LEFTWARDS SQUIGGLE ARROW
  37 | <Multi_key> <greater> <asciitilde>	: "⇝"	U21DD		# RIGHTWARDS SQUIGGLE ARROW
  38 | <Multi_key> <less> <bar>                : "⇤"	U21E4		# LEFTWARDS ARROW TO BAR
  39 | <Multi_key> <greater> <bar>             : "⇥"	U21E5		# RIGHTWARDS ARROW TO BAR
  40 | <Multi_key> <brokenbar> <less>          : "⇠"	U21E0		# LEFTWARDS DASHED ARROW
  41 | <Multi_key> <brokenbar> <asciicircum>   : "⇡"	U21E1		# UPWARDS DASHED ARROW (INTENTIONAL CONFLICT)
  42 | <Multi_key> <brokenbar> <greater>       : "⇢"	U21E2		# RIGHTWARDS DASHED ARROW
  43 | <Multi_key> <brokenbar> <v>             : "⇣"	U21E3		# DOWNWARDS DASHED ARROW
  44 | 
  45 | # Doubled arrows
  46 | # ==============
  47 | <Multi_key> <equal> <greater>		: "⇒"	U21D2	# RIGHTWARDS DOUBLE ARROW
  48 | <Multi_key> <equal> <less>		: "⇐"	U21D0	# LEFTWARDS DOUBLE ARROW
  49 | # FIXME: a very useful character, but "iff" does not match other sequences; all combinations of <=> conflict
  50 | <Multi_key> <i> <f> <f>	: "⇔"	U21D4	# LEFT RIGHT DOUBLE ARROW
  51 | <Multi_key> <equal> <asciicircum> <asciicircum>: "⇑"	U21D1	# UPWARDS DOUBLE ARROW
  52 | <Multi_key> <equal> <v> <v>		: "⇓"	U21D3	# DOWNWARDS DOUBLE ARROW
  53 | <Multi_key> <equal> <asciicircum> <v>	: "⇕"	U21D5	# UP DOWN DOUBLE ARROW
  54 | <Multi_key> <equal> <v> <less>		: "⏎"	U23CE	# RETURN SYMBOL
  55 | 
  56 | 
  57 | # Asterisk is commonly used for bullets in ASCII.
  58 | <Multi_key> <asterisk> <asterisk>: "•" U2022 # BULLET
  59 | <Multi_key> <asterisk> <o>: "◦" U25E6 # WHITE BULLET
  60 | <Multi_key> <asterisk> <greater>: "‣" U2023 # TRIANGULAR BULLET
  61 | <Multi_key> <asterisk> <minus>: "⁃" U2043 # HYPHEN BULLET
  62 | <Multi_key> <asterisk> <parenleft>: "⁌" U204C # LEFTWARDS BULLET
  63 | <Multi_key> <asterisk> <parenright>: "⁍" U204D # RIGHTWARDS BULLET
  64 | <Multi_key> <exclam> <asterisk>: "◘" U25D8 # INVERSE BULLET
  65 | # Japanese tainome
  66 | <Multi_key> <asterisk> <at>: "◉" U25C9 # FISHEYE
  67 | 
  68 | 
  69 | # perhaps CJK input is better handled by CJK input methods.  we try to
  70 | # list here only characters that are not typically avaiable in those
  71 | # (at least in my experience with Japanese IMs).
  72 | 
  73 | # “nyoro” on JIMs
  74 | # <Multi_key> <asciitilde> <>: "〜" U301C # WAVE DASH
  75 | <Multi_key> <asciitilde> <minus>: "〰" U3030 # WAVY DASH (~~ is ≈)
  76 | 
  77 | # FIXME: conflicts
  78 | #<Multi_key> <minus> <equal>: "゠" U30A0 # KATAKANA DOUBLE HYPHEN
  79 | #<Multi_key> <equal> <minus>: "゠" U30A0 # KATAKANA DOUBLE HYPHEN
  80 | 
  81 | # “kome” IM.
  82 | #
  83 | # <Multi_key> <colon> <x>: "※" U203B # REFERENCE MARK
  84 | 
  85 | # VERTICAL FORMS
  86 | # ==============
  87 | # correct vertical text uses font glyph substitution; the characters
  88 | # below are deprecated.  since almost no one supports vertical text
  89 | # (not even XeTeX!), these my come in handy.
  90 | 
  91 | # «<exclam> <exclam>», «<exclam> <question>» &c. taken
  92 | <Multi_key> <2> <exclam>: "‼" U203C # DOUBLE EXCLAMATION MARK
  93 | <Multi_key> <2> <question>: "⁇" U2047 # DOUBLE QUESTION MARK
  94 | # ⁈
  95 | # ⁉
  96 | 
  97 | 
  98 | # A quick recap on hyphens and dashes:
  99 | #
 100 | # • U002D «-» is the ASCII hyphen‐minus.  It is overloaded as hyphen,
 101 | #   dash, and minus sign at the command‐line, programming languages,
 102 | #   and in software that can’t handle Unicode well.
 103 | # • U2010 «‐» is the true hyphen.  Use it as the grammatical hyphen
 104 | #   when you feel typographical.
 105 | # • U2011 «‑» is the non‐breaking hyphen.  It is visually identical
 106 | #   to the true hyphen, but tells software they shouldn’t break a line
 107 | #   at this point.  This is useful whenever you feel like an
 108 | #   hyphenated word musn’t be separated in different lines — for
 109 | #   example, when a broken hyphenated word could be mistaken by a
 110 | #   non‐hyphenated word (e.g. “re‑creation”, if broken, could be taken
 111 | #   as “recreation”).
 112 | # • U2012 «‒» is the figure dash.  “Figure” here refers to numbers,
 113 | #   and this dash is guaranteed to be the same width as a digit (in
 114 | #   fonts with equal‐width digits) so they line up.  This dash
 115 | #   therefore is to be used with digits, as in telephone numbers or
 116 | #   postal codes.  Don’t use it for mathematical operations (for which
 117 | #   there is the minus sign) or ranges (for which the en‐dash is
 118 | #   best).  See also U2007, the figure space.
 119 | # • U2013 «–» is the en‐dash — that is, a dash with roughly the
 120 | #   width of an uppercase N.  It’s kind of a softer (and smaller)
 121 | #   version of the em‐dash.  Its main uses are ranges (“2–10”,
 122 | #   “Jan–Mar”) and as a further separator for hyphenated words
 123 | #   (“un‐american–like”).  In a pinch, some people use two ASCII
 124 | #   hyphen‐minuses to substitute it.
 125 | # • U2014 «—» is the em‐dash — the dash that is roughly the width of
 126 | #   an uppercase M, which is usually the maximum type width.  This is
 127 | #   the one used to make parenthetical remarks — like this — or
 128 | #   dangling clauses — like this.  Use it a lot if you’re a beatnik.
 129 | #   In a pinch, many people use two or three ASCII hyphen‐minuses to
 130 | #   substitute it.  Traditionally the em‐dash is used without
 131 | #   spaces—like this—but this looks bad in monospace fonts (only).
 132 | # • U2015 «―» is the horizontal bar.  It’s the official character to
 133 | #   use in dialogues.  It’s identical to the em‐dash in most fonts, so
 134 | #   many just use the em‐dash instead.
 135 | # • U2212 «−» is the true minus sign.  It is more visible and
 136 | #   better‐spaced than the ASCII hyphen‐minus, particularly with
 137 | #   proportional fonts (generally its size and positioning will match
 138 | #   +, × and other mathematical operators).
 139 | #
 140 | # All of the above look basically the same in most monospaced fonts.
 141 | # Their true typographical beauty shows up in real texts, not in
 142 | # conffiles.
 143 | #
 144 | # • U00AD «­» is the soft hyphen.  This is an invisible control
 145 | #   character in Unicode; its purpose is to mark what points of a word
 146 | #   can be broken for hyphenation and aid in automatic text layout.
 147 | #   However, it was visible in ISO-8859-1, where it served to mark
 148 | #   points where words _were_ broken by algorithms; thus some software
 149 | #   still render it as a regular hyphen.  See
 150 | #   http://www.cs.tut.fi/~jkorpela/shy.html .
 151 | # • U2053 «⁓» is the swung dash (not a tilde like «~» ascii tilde or
 152 | #   « ̃» combining tilde).  A swung dash is often used to substitute
 153 | #   words, as in dictionaries.  It overlaps with CJK wave dash U301C
 154 | #   «〜» and wavy dash U3030 «〰», which are probably better for
 155 | #   full-width contexts (see cjk.xcompose).  Other CJK dashes are «゠»
 156 | #   and «－».
 157 | # • U2027 «‧» is the hyphenation point.  Also commonly seen in
 158 | #   dictionaries (dic‧tion‧ar‧ies).  Not to be confused with the
 159 | #   middle dot U00B7 · nor the katakana middle dot (・).
 160 | 
 161 | 
 162 | # Notice the X name <minus> refer to the ASCII hyphen‐minus, not the
 163 | # true minus.
 164 | <Multi_key> <minus> <period>            : "‐" U2010 # hyhpen
 165 | 
 166 | # Literally counter‐intuitive? Press Return when you don’t want line breaks.
 167 | <Multi_key> <minus> <Return>                : "‑" U2011 # non‐breaking hyphen
 168 | <Multi_key> <minus> <numbersign>            : "‒" U2012 # figure dash
 169 | <Multi_key> <minus> <minus> <underscore>    : "―" U2015 # horizontal bar
 170 | 
 171 | <Multi_key> <bar> <bar>                     : "‖" U2016 # DOUBLE VERTICAL LINE
 172 | 
 173 | <Multi_key> <minus> <asciitilde>:         "⁓" U2053 # SWUNG DASH
 174 | # <Multi_key>  <>: "‧" U2027 # HYPHENATION POINT
 175 | ## <Multi_key> <period> <minus>    	: "·"   periodcentered # MIDDLE DOT
 176 | 
 177 | 
 178 | <Multi_key> <V> <V> : "✓" U2713 # CHECK MARK
 179 | <Multi_key> <X> <X> : "✗" U2717 # BALLOT X — <x> <x> taken by Xorg for multiply
 180 | <Multi_key> <V> <underscore> : "✔" U2714 # HEAVY CHECK MARK
 181 | <Multi_key> <X> <underscore> : "✘" U2718 # HEAVY BALLOT X
 182 | 
 183 | 
 184 | # X already includes mappings of the form:
 185 | ## <Multi_key> <parenleft> <0> <parenright>     : "⓪"   U24EA # CIRCLED DIGIT ZERO
 186 | 
 187 | # Since X uses () for circled, we use [] for parenthesised…is this a good solution?
 188 | #
 189 | <Multi_key> <bracketleft> <1> <bracketright>  : "⑴" U2474 # PARENTHESIZED DIGIT ONE
 190 | <Multi_key> <bracketleft> <2> <bracketright>  : "⑵" U2475 # PARENTHESIZED DIGIT TWO
 191 | <Multi_key> <bracketleft> <3> <bracketright>  : "⑶" U2476 # PARENTHESIZED DIGIT THREE
 192 | <Multi_key> <bracketleft> <4> <bracketright>  : "⑷" U2477 # ⋮
 193 | <Multi_key> <bracketleft> <5> <bracketright>  : "⑸" U2478
 194 | <Multi_key> <bracketleft> <6> <bracketright>  : "⑹" U2479
 195 | <Multi_key> <bracketleft> <7> <bracketright>  : "⑺" U247A
 196 | <Multi_key> <bracketleft> <8> <bracketright>  : "⑻" U247B
 197 | <Multi_key> <bracketleft> <9> <bracketright>  : "⑼" U247C
 198 | <Multi_key> <bracketleft> <1> <0> <bracketright> : "⑽" U247D
 199 | <Multi_key> <bracketleft> <1> <1> <bracketright> : "⑾" U247E
 200 | <Multi_key> <bracketleft> <1> <2> <bracketright> : "⑿" U247F
 201 | <Multi_key> <bracketleft> <1> <3> <bracketright> : "⒀" U2480
 202 | <Multi_key> <bracketleft> <1> <4> <bracketright> : "⒁" U2481
 203 | <Multi_key> <bracketleft> <1> <5> <bracketright> : "⒂" U2482
 204 | <Multi_key> <bracketleft> <1> <6> <bracketright> : "⒃" U2483
 205 | <Multi_key> <bracketleft> <1> <7> <bracketright> : "⒄" U2484
 206 | <Multi_key> <bracketleft> <1> <8> <bracketright> : "⒅" U2485
 207 | <Multi_key> <bracketleft> <1> <9> <bracketright> : "⒆" U2486
 208 | <Multi_key> <bracketleft> <2> <0> <bracketright> : "⒇" U2487
 209 | 
 210 | <Multi_key> <bracketleft> <a> <bracketright>  : "⒜" U249C # PARENTHESIZED LATIN SMALL LETTER A
 211 | <Multi_key> <bracketleft> <b> <bracketright>  : "⒝" U249D # PARENTHESIZED LATIN SMALL LETTER B
 212 | <Multi_key> <bracketleft> <c> <bracketright>  : "⒞" U249E # ⋮
 213 | <Multi_key> <bracketleft> <d> <bracketright>  : "⒟" U249F
 214 | <Multi_key> <bracketleft> <e> <bracketright>  : "⒠" U24A0
 215 | <Multi_key> <bracketleft> <f> <bracketright>  : "⒡" U24A1
 216 | <Multi_key> <bracketleft> <g> <bracketright>  : "⒢" U24A2
 217 | <Multi_key> <bracketleft> <h> <bracketright>  : "⒣" U24A3
 218 | <Multi_key> <bracketleft> <i> <bracketright>  : "⒤" U24A4
 219 | <Multi_key> <bracketleft> <j> <bracketright>  : "⒥" U24A5
 220 | <Multi_key> <bracketleft> <k> <bracketright>  : "⒦" U24A6
 221 | <Multi_key> <bracketleft> <l> <bracketright>  : "⒧" U24A7
 222 | <Multi_key> <bracketleft> <m> <bracketright>  : "⒨" U24A8
 223 | <Multi_key> <bracketleft> <n> <bracketright>  : "⒩" U24A9
 224 | <Multi_key> <bracketleft> <o> <bracketright>  : "⒪" U24AA
 225 | <Multi_key> <bracketleft> <p> <bracketright>  : "⒫" U24AB
 226 | <Multi_key> <bracketleft> <q> <bracketright>  : "⒬" U24AC
 227 | <Multi_key> <bracketleft> <r> <bracketright>  : "⒭" U24AD
 228 | <Multi_key> <bracketleft> <s> <bracketright>  : "⒮" U24AE
 229 | <Multi_key> <bracketleft> <t> <bracketright>  : "⒯" U24AF
 230 | <Multi_key> <bracketleft> <u> <bracketright>  : "⒰" U24B0
 231 | <Multi_key> <bracketleft> <v> <bracketright>  : "⒱" U24B1
 232 | <Multi_key> <bracketleft> <w> <bracketright>  : "⒲" U24B2
 233 | <Multi_key> <bracketleft> <x> <bracketright>  : "⒳" U24B3
 234 | <Multi_key> <bracketleft> <y> <bracketright>  : "⒴" U24B4
 235 | <Multi_key> <bracketleft> <z> <bracketright>  : "⒵" U24B5
 236 | 
 237 | <Multi_key> <1> <period>   : "⒈" U2488 # DIGIT ONE FULL STOP
 238 | <Multi_key> <2> <period>   : "⒉" U2489 # DIGIT TWO FULL STOP
 239 | <Multi_key> <3> <period>   : "⒊" U248A # ⋮
 240 | <Multi_key> <4> <period>   : "⒋" U248B
 241 | <Multi_key> <5> <period>   : "⒌" U248C
 242 | <Multi_key> <6> <period>   : "⒍" U248D
 243 | <Multi_key> <7> <period>   : "⒎" U248E
 244 | <Multi_key> <8> <period>   : "⒏" U248F
 245 | <Multi_key> <9> <period>   : "⒐" U2490
 246 | <Multi_key> <1> <0> <period>  : "⒑" U2491
 247 | # Various of those two‐digit period forms have prefix‐conflicts with X
 248 | # sequences for fractions.
 249 | # <Multi_key> <1> <1> <period>  : "⒒" U2492
 250 | # <Multi_key> <1> <2> <period>  : "⒓" U2493
 251 | # <Multi_key> <1> <3> <period>  : "⒔" U2494
 252 | # <Multi_key> <1> <4> <period>  : "⒕" U2495
 253 | # <Multi_key> <1> <5> <period>  : "⒖" U2496
 254 | # <Multi_key> <1> <6> <period>  : "⒗" U2497
 255 | # <Multi_key> <1> <7> <period>  : "⒘" U2498
 256 | # <Multi_key> <1> <8> <period>  : "⒙" U2499
 257 | # <Multi_key> <1> <9> <period>  : "⒚" U249A
 258 | # <Multi_key> <2> <0> <period>  : "⒛" U249B
 259 | 
 260 | 
 261 | # The idea here is that “!” = “not” = inverted.  Despite being called
 262 | # “negative” they are not negative numbers, so no minus sign.
 263 | #
 264 | # Unicode only has negative numbers for 0 and 11–20; 1–10 are dingbats.
 265 | <Multi_key> <exclam> <parenleft> <0> <parenright> : "⓿" U24FF # NEGATIVE CIRCLED DIGIT ZERO
 266 | <Multi_key> <exclam> <parenleft> <1> <parenright> : "❶" U2776 # DINGBAT NEGATIVE CIRCLED DIGIT ONE
 267 | <Multi_key> <exclam> <parenleft> <2> <parenright> : "❷" U2777 # DINGBAT NEGATIVE CIRCLED DIGIT TWO
 268 | <Multi_key> <exclam> <parenleft> <3> <parenright> : "❸" U2778 # ⋮
 269 | <Multi_key> <exclam> <parenleft> <4> <parenright> : "❹" U2779
 270 | <Multi_key> <exclam> <parenleft> <5> <parenright> : "❺" U277A
 271 | <Multi_key> <exclam> <parenleft> <6> <parenright> : "❻" U277B
 272 | <Multi_key> <exclam> <parenleft> <7> <parenright> : "❼" U277C
 273 | <Multi_key> <exclam> <parenleft> <8> <parenright> : "❽" U277D
 274 | <Multi_key> <exclam> <parenleft> <9> <parenright> : "❾" U277E
 275 | <Multi_key> <exclam> <parenleft> <1> <0> <parenright> : "❿" U277F # DINGBAT NEGATIVE CIRCLED NUMBER TEN
 276 | <Multi_key> <exclam> <parenleft> <1> <1> <parenright> : "⓫" U24EB # NEGATIVE CIRCLED NUMBER ELEVEN
 277 | <Multi_key> <exclam> <parenleft> <1> <2> <parenright> : "⓬" U24EC # ⋮
 278 | <Multi_key> <exclam> <parenleft> <1> <3> <parenright> : "⓭" U24ED
 279 | <Multi_key> <exclam> <parenleft> <1> <4> <parenright> : "⓮" U24EE
 280 | <Multi_key> <exclam> <parenleft> <1> <5> <parenright> : "⓯" U24EF
 281 | <Multi_key> <exclam> <parenleft> <1> <6> <parenright> : "⓰" U24F0
 282 | <Multi_key> <exclam> <parenleft> <1> <7> <parenright> : "⓱" U24F1
 283 | <Multi_key> <exclam> <parenleft> <1> <8> <parenright> : "⓲" U24F2
 284 | <Multi_key> <exclam> <parenleft> <1> <9> <parenright> : "⓳" U24F3
 285 | <Multi_key> <exclam> <parenleft> <2> <0> <parenright> : "⓴" U24F4
 286 | 
 287 | 
 288 | # X has all these without slash.
 289 | 
 290 | <Multi_key> <1> <slash> <4>: "¼"   onequarter # VULGAR FRACTION ONE QUARTER
 291 | <Multi_key> <1> <slash> <2>: "½"   onehalf # VULGAR FRACTION ONE HALF
 292 | <Multi_key> <3> <slash> <4>: "¾"   threequarters # VULGAR FRACTION THREE QUARTERS
 293 | <Multi_key> <1> <slash> <3>: "⅓"   U2153 # VULGAR FRACTION ONE THIRD
 294 | <Multi_key> <2> <slash> <3>: "⅔"   U2154 # VULGAR FRACTION TWO THIRDS
 295 | <Multi_key> <1> <slash> <5>: "⅕"   U2155 # VULGAR FRACTION ONE FIFTH
 296 | <Multi_key> <2> <slash> <5>: "⅖"   U2156 # VULGAR FRACTION TWO FIFTHS
 297 | <Multi_key> <3> <slash> <5>: "⅗"   U2157 # VULGAR FRACTION THREE FIFTHS
 298 | <Multi_key> <4> <slash> <5>: "⅘"   U2158 # VULGAR FRACTION FOUR FIFTHS
 299 | <Multi_key> <1> <slash> <6>: "⅙"   U2159 # VULGAR FRACTION ONE SIXTH
 300 | <Multi_key> <5> <slash> <6>: "⅚"   U215A # VULGAR FRACTION FIVE SIXTHS
 301 | <Multi_key> <1> <slash> <8>: "⅛"   U215B # VULGAR FRACTION ONE EIGHTH
 302 | <Multi_key> <3> <slash> <8>: "⅜"   U215C # VULGAR FRACTION THREE EIGHTHS
 303 | <Multi_key> <5> <slash> <8>: "⅝"   U215D # VULGAR FRACTION FIVE EIGHTHS
 304 | <Multi_key> <7> <slash> <8>: "⅞"   U215E # VULGAR FRACTION SEVEN EIGHTHS
 305 | 
 306 | 
 307 | # these two are the latin letters, not the runic wynn ᚹ U16B9
 308 | <Multi_key> <W> <W>: "Ƿ" U01F7 # Wynn
 309 | <Multi_key> <w> <w>: "ƿ" U01BF # wynn
 310 | 
 311 | <Multi_key> <Y> <Y>: "Ȝ" U021C # Yogh
 312 | <Multi_key> <y> <y>: "ȝ" U021D # yogh
 313 | 
 314 | 
 315 | # Macrons are more convenient with (shift‐less) hyphen than X default
 316 | # (shift‐full) underscore.  Notice the <minus> X name refers to the
 317 | # ASCII hyphen‐minus, not to the true minus character.
 318 | #
 319 | # It would be cool if we could do this using <Multi_key> <minus> :
 320 | # dead_macron, but doesn’t work due to conflict.
 321 | #
 322 | 
 323 | # FIXME: The following fixes https://bugs.freedesktop.org/show_bug.cgi?id=74116
 324 | <Multi_key> <minus> <a>    : "ā" U0101 # LATIN SMALL LETTER A WITH MACRON (INTENTIONAL CONFLICT)
 325 | <Multi_key> <a> <minus>    : "ā" U0101 # LATIN SMALL LETTER A WITH MACRON (INTENTIONAL CONFLICT)
 326 | 
 327 | # FIXME: Submit the following to freedesktop.org, as they're consistent with existing shortcuts
 328 | <Multi_key> <minus> <AE>                : "Ǣ"   U01E2 # LATIN CAPITAL LETTER AE WITH MACRON
 329 | <Multi_key> <minus> <ae>                : "ǣ"   U01E3 # LATIN SMALL LETTER AE WITH MACRON
 330 | <Multi_key> <minus> <Y>                       : "Ȳ"   U0232 # LATIN CAPITAL LETTER Y WITH MACRON (INTENTIONAL CONFLICT)
 331 | <Multi_key> <minus> <y>                       : "ȳ"   U0233 # LATIN SMALL LETTER Y WITH MACRON (INTENTIONAL CONFLICT)
 332 | <Multi_key> <minus> <G>                       : "Ḡ"   U1E20 # LATIN CAPITAL LETTER G WITH MACRON
 333 | <Multi_key> <minus> <g>                       : "ḡ"   U1E21 # LATIN SMALL LETTER G WITH MACRON
 334 | 
 335 | <Multi_key> <minus> <Greek_alpha>       : "ᾱ"   U1FB1 # GREEK SMALL LETTER ALPHA WITH MACRON
 336 | <Multi_key> <minus> <Greek_ALPHA>       : "Ᾱ"   U1FB9 # GREEK CAPITAL LETTER ALPHA WITH MACRON
 337 | <Multi_key> <minus> <Greek_iota>        : "ῑ"   U1FD1 # GREEK SMALL LETTER IOTA WITH MACRON
 338 | <Multi_key> <minus> <Greek_IOTA>        : "Ῑ"   U1FD9 # GREEK CAPITAL LETTER IOTA WITH MACRON
 339 | <Multi_key> <minus> <Greek_upsilon>     : "ῡ"   U1FE1 # GREEK SMALL LETTER UPSILON WITH MACRON
 340 | <Multi_key> <minus> <Greek_UPSILON>     : "Ῡ"   U1FE9 # GREEK CAPITAL LETTER UPSILON WITH MACRON
 341 | 
 342 | <Multi_key> <minus> <Cyrillic_I>              : "Ӣ"   U04E2 # CYRILLIC CAPITAL LETTER I WITH MACRON
 343 | <Multi_key> <minus> <Cyrillic_i>              : "ӣ"   U04E3 # CYRILLIC SMALL LETTER I WITH MACRON
 344 | <Multi_key> <minus> <Cyrillic_U>              : "Ӯ"   U04EE # CYRILLIC CAPITAL LETTER U WITH MACRON
 345 | <Multi_key> <minus> <Cyrillic_u>              : "ӯ"   U04EF # CYRILLIC SMALL LETTER U WITH MACRON
 346 | 
 347 | 
 348 | # Spaces
 349 | # ======
 350 | 
 351 | # Used like the regular space, except it tells layout software not to
 352 | # break lines at its position.  Also the preferred character to
 353 | # display combining marks in isolation (example:  ̧́)
 354 | ## <Multi_key> <space> <space>: " "   nobreakspace # NO-BREAK SPACE
 355 | # common abbreviation
 356 | <Multi_key> <n> <b> <s> <p>: " "   nobreakspace # NO-BREAK SPACE
 357 | 
 358 | # The following are used for manual spacing, for example in math.
 359 | 
 360 | # Nut; the width of capital N (half an em‐space)
 361 | <Multi_key> <space> <n>: " " U2002   # EN SPACE
 362 | # Mutton; the width of capital M ≅ type width
 363 | <Multi_key> <space> <m>: " " U2003   # EM SPACE
 364 | # aka thick space
 365 | <Multi_key> <space> <3>: " " U2004 # THREE-PER-EM SPACE
 366 | # aka mid space
 367 | <Multi_key> <space> <4>: " " U2005 # FOUR-PER-EM SPACE
 368 | <Multi_key> <space> <6>: " " U2006 # SIX-PER-EM SPACE
 369 | 
 370 | # 4/18 of an em
 371 | # <Multi_key> <space> <>: " " U205F # MEDIUM MATHEMATICAL SPACE
 372 | 
 373 | # tabular space = the width of a digit if font is fixed‐digit
 374 | <Multi_key> <space> <numbersign>: " " U2007 # FIGURE SPACE
 375 | 
 376 | <Multi_key> <space> <t>: " " U2009 # THIN SPACE
 377 | <Multi_key> <space> <h>: " " U200A # HAIR SPACE
 378 | # bar = a strand of hair?
 379 | <Multi_key> <space> <bar>: " " U200A # HAIR SPACE
 380 | 
 381 | 
 382 | # Control
 383 | # =======
 384 | 
 385 | # A space so thin, it’s invisible.  Used to separate words in scripts
 386 | # that don’t separate words such as Thai, Kmer, and Japanese.  Since
 387 | # it’s invisible, ZWSP is actually not a space at all; but it might
 388 | # get expanded in automatic paragraph justification.
 389 | <Multi_key> <space> <0>: "​" U200B # ZERO WIDTH SPACE
 390 | # common abbreviation
 391 | <Multi_key> <space> <N> <J>		: "‌"	U200C	# ZERO WIDTH NON-JOINER
 392 | <Multi_key> <space> <W> <J>		: "‍"	U200D	# ZERO WIDTH JOINER
 393 | 
 394 | # The proper zero‐width no‐break space.
 395 | <Multi_key> <w> <j>: "⁠" U2060 # WORD JOINER
 396 | 
 397 | # The following fine‐tune the bidirectional algorithm.  In fact they
 398 | # might mess up the display of this file =) The sequences are the
 399 | # official abbreviations and widely used.
 400 | #
 401 | # The “marks” are useful for overriding the default behavior of the
 402 | # bidi algorithm, that considers a paragraph to be in the direction of
 403 | # the first strongly‐directed letter.
 404 | <Multi_key> <l> <r> <m>: "‎" U200E # LEFT TO RIGHT MARK
 405 | <Multi_key> <r> <l> <m>: "‏" U200F # RIGHT TO LEFT MARK
 406 | <Multi_key> <l> <r> <e>: "‪" U202A # LEFT TO RIGHT EMBEDDING
 407 | <Multi_key> <r> <l> <e>: "‫" U202B # RIGHT TO LEFT EMBEDDING
 408 | <Multi_key> <p> <d> <f>: "‬" U202C # POP DIRECTIONAL FORMATTING
 409 | # The overrides will force bidi to treat _any_ character as one of
 410 | # that directionality.
 411 | <Multi_key> <l> <r> <o>: "‭" U202D # LEFT TO RIGHT OVERRIDE
 412 | <Multi_key> <r> <l> <o>: "‮" U202E # RIGHT TO LEFT OVERRIDE
 413 | 
 414 | # a free pop just to be sure: ‬
 415 | 
 416 | 
 417 | ## Arithmetic operators
 418 | # Notice the “<minus>” X name refers to the ASCII hyphen‐minus, not to
 419 | # the true minus character.
 420 | 
 421 | <Multi_key> <m> <m>                : "−" U2212 # MINUS SIGN
 422 | <Multi_key> <minus> <KP_Subtract>  : "−" U2212 #  MINUS SIGN
 423 | 
 424 | # 2215 is different from both the ASCII slash (which Unicode
 425 | # confusingly call “solidus”) and the U2044 fraction slash ⁄, which
 426 | # everyone _except_ unicode call “solidus”. Use U2215 as a math
 427 | # operator, U2044 for fractions.
 428 | 
 429 | # slash:                   "/" U002F # ASCII SLASH
 430 | <Multi_key> <slash> <slash>: "∕" U2215 # DIVISION SLASH (INTENTIONAL CONFLICT)
 431 | <Multi_key> <slash> <period>: "⁄" U2044 # FRACTION SLASH
 432 | 
 433 | ## Comparison
 434 | # The order here is more intuitive for programmers than the X
 435 | # versions.
 436 | <Multi_key> <exclam> <equal>   : "≠" U2260 # NOT EQUAL TO
 437 | <Multi_key> <asciitilde> <equal> : "≅" U2245 # APPROXIMATELY EQUAL TO
 438 | <Multi_key> <slash> <less>    : "≮" U226E # NOT LESS THAN (INTENTIONAL CONFLICT)
 439 | <Multi_key> <slash> <greater> : "≯" U226F # NOT GREATER THAN
 440 | <Multi_key> <asciitilde> <asciitilde>        : "≈"  U2248           # ALMOST EQUAL TO
 441 | 
 442 | 
 443 | ## Set operators
 444 | <Multi_key> <E> <E>			: "∈"	U2208		# ELEMENT OF
 445 | <Multi_key> <slash> <E> <E>		: "∉"	U2209		# NOT AN ELEMENT OF
 446 | <Multi_key> <braceleft> <parenleft>	: "⊂"	U2282		# SUBSET OF
 447 | <Multi_key> <braceleft>	<parenright>	: "⊃"	U2283		# SUPERSET OF
 448 | <Multi_key> <exclam> <braceleft> <parenleft> : "⊄" U2284        # NOT A SUBSET OF
 449 | <Multi_key> <braceleft> <equal> <parenleft> : "⊆" U2286		# SUBSET OF OR EQUAL TO
 450 | <Multi_key> <braceleft> <equal> <parenright> : "⊇" U2287	# SUPERSET OF OR EQUAL TO
 451 | <Multi_key> <braceleft> <asciicircum>	: "∩"	U2229		# INTERSECTION
 452 | <Multi_key> <braceleft> <U>		: "∪"	U222A		# UNION
 453 | 
 454 | <Multi_key> <bracketleft> <bracketright>: "∎" # END OF PROOF (INTENTIONAL CONFLICT)
 455 | 
 456 | # % ÷ 100; can’t extend with <o> <o> due to XCompose substring issue
 457 | # (<%> <o> already used for per-mille)
 458 | <Multi_key> <percent> <O>: "‱"   U2031 # PER MYRIAD SIGN
 459 | 
 460 | # Tell that adjacent symbols form a list, without a visible comma.
 461 | <Multi_key> <space> <comma>: "⁣" U2063 # INVISIBLE COMMA (INTENTIONAL CONFLICT)
 462 | 
 463 | <Multi_key> <H> <less>: "❮" U276E # HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT
 464 | <Multi_key> <H> <greater>: "❯" U276F # HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT
 465 | 
 466 | # v = ↓ = vertical
 467 | <Multi_key> <v> <period> <period>: "⋮" U22EE # VERTICAL ELLIPSIS
 468 | # FIXME: prefix conflict
 469 | #<Multi_key> <c> <period> <period>	: "⋯"	U22EF		# MIDLINE HORIZONTAL ELLIPSIS
 470 | <Multi_key> <period> <slash> <period>	: "⋰"	U22F0		# UP RIGHT DIAGONAL ELLIPSIS
 471 | # To avoid conflict with \. for combining dot
 472 | <Multi_key> <period> <backslash> <period> : "⋱" U22F1		# DOWN RIGHT DIAGONAL ELLIPSIS
 473 | 
 474 | # See also the other files (e.g. invisible.xcompose for spaces, &c.)
 475 | 
 476 | # FIXME: 2. is ⒉
 477 | #<Multi_key> <2> <period>                  : "‥"	U2025		# TWO DOT LEADER
 478 | # This should not be needed.
 479 | #<Multi_key> <1> <period>                 : "․"	U2024		# ONE DOT LEADER
 480 | # FIXME: ./. = ⋰
 481 | #<Multi_key> <period> <slash> <period>	: "⁒"	U2052		# COMMERCIAL MINUS SIGN
 482 | # Printable sign for space.  But is \<space> too useful a key combo to use
 483 | # for this?
 484 | <Multi_key> <backslash> <space>		: "␣"	U2423		# OPEN BOX
 485 | 
 486 | # Mnemonics
 487 | # =========
 488 | 
 489 | <Multi_key> <colon> <colon>: "⸪" U2E2A # TWO DOTS OVER ONE DOT
 490 | #FIXME: conflicts
 491 | # <Multi_key> <period> <colon>: "⸫" U2E2B # ONE DOT OVER TWO DOTS
 492 | # <Multi_key> <colon> <colon>:  "⸬" U2E2C # TWO DOTS OVER TWO DOTS
 493 | <Multi_key> <colon> <plus>: "⸭" U2E2D # FIVE DOTS MARK
 494 | <Multi_key> <plus> <colon>: "⸭" U2E2D # FIVE DOTS MARK
 495 | 
 496 | <Multi_key> <plus> <bar> : "†" U2020 # DAGGER
 497 | <Multi_key> <plus> <plus> : "‡" U2021 # DOUBLE DAGGER (INTENTIONAL CONFLICT)
 498 | 
 499 | <Multi_key> <asterisk> <3>: "⁂" U2042 # ASTERISM
 500 | 
 501 | # One missing for Greek
 502 | <Multi_key> <quotedbl> <parenleft>: "‟" U201F # DOUBLE HIGH-REVERSED-9
 503 | <Multi_key> <parenleft> <quotedbl>: "‟" U201F # DOUBLE HIGH-REVERSED-9
 504 | 
 505 | # In the Asian section, but it's general-purpose punctuation
 506 | <Multi_key> <quotedbl> <quotedbl>       : "〃"	U3003		# DITTO MARK (INTENTIONAL CONFLICT)
 507 | 
 508 | # These versions make more sense with other mappings.
 509 | <Multi_key> <greater> <period>          : "›"   U203a # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
 510 | <Multi_key> <less> <period>             : "‹"   U2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
 511 | 
 512 | <Multi_key> <equal> <period> <equal>	: "⸎"	U2E0E		# EDITORIAL CORONIS
 513 | 
 514 | # Alternative, convenient sequence for apostrophe (so common in English).
 515 | #
 516 | # The right single quotation mark is the official apostrophe in Unicode.
 517 | <Multi_key> <apostrophe> <apostrophe>   : "’"   U2019 # RIGHT SINGLE QUOTATION MARK (INTENTIONAL CONFLICT)
 518 | 
 519 | # Some quotation styles around the world:
 520 | # “American English.” “British English”.
 521 | # “Dutch, English, Italian, Portuguese, Spanish, Turkish”
 522 | # ”Danish, Finnish, Norwegian, Swedish” (but »Swedish books»)
 523 | # „Czech, German, Slovak“ (opening low-9 is Gänsefüßchen „little goose feet“)
 524 | # „Hungarian, Polish”
 525 | # « French » # no-break space or 3∕M or (3∕M+WJ) better than regular
 526 | #              spaces
 527 | # «Greek, Russian»
 528 | # ‟Greek, second level” (opening high-reversed-9)
 529 | # »Slovenian«
 530 | # 〝ＣＪＫ〞, 「ＣＪＫ」, 『ＣＪＫ』,【ＣＪＫ】,《ＣＪＫ》,〔ＣＪＫ〕 &c. &c.
 531 | 
 532 | # Spelled out
 533 | # ===========
 534 | <Multi_key> <s> <c>:      "§" U00A7	# SECTION SIGN
 535 | <Multi_key> <m> <i> <n> : "′"
 536 | # ≠ prime quotation mark above
 537 | <Multi_key> <s> <e> <c> : "″"
 538 | <Multi_key> <i> <n> <f> : "∞"
 539 | 
 540 | # Not a dingbat —“General Punctuation”, used as separator.
 541 | <Multi_key> <p> <a> <l> <m>: "⸙" U2E19 # PALM BRANCH
 542 | 
 543 | # Used in Indic scripts.
 544 | # FIXME: conflict
 545 | #<Multi_key> <p> <h> <u> <l>: "⁕" U2055 # FLOWER PUNCTUATION MARK
 546 | 
 547 | <Multi_key> <F> <less>			: "☚"	U261A		# BLACK LEFT POINTING INDEX
 548 | <Multi_key> <F> <greater>		: "☛"	U261B		# BLACK RIGHT POINTING INDEX
 549 | <Multi_key> <f> <less>			: "☜"	U261C		# WHITE LEFT POINTING INDEX
 550 | <Multi_key> <f> <asciicircum>		: "☝"	U261D		# WHITE UP POINTING INDEX
 551 | <Multi_key> <f> <greater>		: "☞"	U261E		# WHITE RIGHT POINTING INDEX
 552 | <Multi_key> <f> <v>			: "☟"	U261F		# WHITE DOWN POINTING INDEX
 553 | # FIXME: f v is WHITE DOWN POINTING INDEX
 554 | #<Multi_key> <f> <v>   			: "✌"   U270C   	# VICTORY HAND
 555 | <Multi_key> <f> <w>   			: "✍"   U270D   	# WRITING HAND
 556 | <Multi_key> <f> <p> <v>			: "✎"   U270E   	# LOWER RIGHT PENCIL
 557 | <Multi_key> <f> <p> <greater>		: "✏"   U270F   	# PENCIL
 558 | <Multi_key> <f> <p> <asciicircum>	: "✐"   U2710   	# UPPER RIGHT PENCIL
 559 | 
 560 | 
 561 | ## Ligatures
 562 | <Multi_key> <s> <t>		: "st"  UFB06 # LATIN SMALL LIGATURE ST
 563 | <Multi_key> <f> <t>		: "ſt"  UFB05 # LATIN SMALL LIGATURE LONG S T
 564 | 
 565 | 
 566 | ## Latin Extended-B
 567 | <Multi_key> <E> <less>	 	 : "Ǝ"	    U018E # LATIN CAPITAL LETTER REVERSED E (INTENTIONAL CONFLICT)
 568 | 
 569 | 
 570 | ## IPA Extensions
 571 | <Multi_key> <e> <less>		 : "ɘ"	    U0258 # LATIN SMALL LETTER REVERSED E (INTENTIONAL CONFLICT)
 572 | 
 573 | 
 574 | ## Latin-D
 575 | <Multi_key> <o> <ampersand> <o>	: "ꝏ"	UA74F	# LATIN SMALL LETTER OO
 576 | <Multi_key> <O> <ampersand> <O> : "Ꝏ"	UA74E	# LATIN CAPITAL LETTER OO
 577 | # FIXME: fill in the following
 578 | # <Multi_key> <ampersand>:"Ꜳ" UA7 # LATIN LETTER
 579 | # <Multi_key> <ampersand>:"ꜳ" UA7 # LATIN LETTER
 580 | # <Multi_key> <ampersand>:"Ꜵ" UA7 # LATIN LETTER
 581 | # <Multi_key> <ampersand>:"ꜵ" UA7 # LATIN LETTER
 582 | # <Multi_key> <ampersand>:"Ꜷ" UA7 # LATIN LETTER
 583 | # <Multi_key> <ampersand>:"ꜷ" UA7 # LATIN LETTER
 584 | # <Multi_key> <ampersand>:"Ꜹ" UA7 # LATIN LETTER
 585 | # <Multi_key> <ampersand>:"ꜹ" UA7 # LATIN LETTER
 586 | # <Multi_key> <ampersand>:"Ꜽ" UA7 # LATIN LETTER
 587 | # <Multi_key> <ampersand>:"ꜽ" UA7 # LATIN LETTER
 588 | # <Multi_key> <ampersand>:"Ꝓ" UA7 # LATIN LETTER
 589 | # <Multi_key> <ampersand>:"ꝓ" UA7 # LATIN LETTER
 590 | # <Multi_key> <ampersand>:"Ꝕ" UA7 # LATIN LETTER
 591 | # <Multi_key> <ampersand>:"ꝕ" UA7 # LATIN LETTER
 592 | # <Multi_key> <ampersand>:"Ꝛ" UA7 # LATIN LETTER
 593 | # <Multi_key> <ampersand>:"ꝛ" UA7 # LATIN LETTER
 594 | # <Multi_key> <ampersand>:"Ꝝ" UA7 # LATIN LETTER
 595 | # <Multi_key> <ampersand>:"ꝝ" UA7 # LATIN LETTER
 596 | # <Multi_key> <ampersand>:"Ꝡ" UA7 # LATIN LETTER
 597 | # <Multi_key> <ampersand>:"ꝡ" UA7 # LATIN LETTER
 598 | # <Multi_key> <ampersand>:"ꝸ" UA7 # LATIN LETTER
 599 | <Multi_key> <E> <ampersand> <T>: "Ꝫ" UA76A # LATIN CAPITAL LETTER ET
 600 | <Multi_key> <e> <ampersand> <t>: "ꝫ" UA76B # LATIN SMALL LETTER ET
 601 | 
 602 | # Ancient Roman epigraphic letters
 603 | # FIXME: conflict
 604 | #<Multi_key> <F> <less>		: "ꟻ"	UA7FB	# LATIN EPIGRAPHIC LETTER REVERSED F
 605 | <Multi_key> <P> <less>		: "ꟼ"	UA7FC	# LATIN EPIGRAPHIC LETTER REVERSED P
 606 | <Multi_key> <M> <W>		: "ꟽ"	UA7FD	# LATIN EPIGRAPHIC LETTER INVERTED M
 607 | <Multi_key> <I> <bar>		: "ꟾ"	UA7FE	# LATIN EPIGRAPHIC LETTER I LONGA
 608 | <Multi_key> <M> <slash>		: "ꟿ"	UA7FF	# LATIN EPIGRAPHIC LETTER ARCHAIC M
 609 | 
 610 | 
 611 | # Custom additions: Mathematical symbols
 612 | <Multi_key> <less> <exclam> <greater>   : "≸"  U2278		# NEITHER LESS-THAN NOR GREATER-THAN
 613 | <Multi_key> <plus> <less>        	: "≪"  U226A		# MUCH LESS-THAN
 614 | <Multi_key> <plus> <greater> 		: "≫"  U226B		# MUCH GREATER-THAN
 615 | # Avoid conflict with the standard plus plus → #
 616 | <Multi_key> <3> <greater> 		: "⋙"  U22D9		# VERY MUCH GREATER-THAN
 617 | <Multi_key> <3> <less>			: "⋘"  U22D8		# VERY MUCH LESS-THAN
 618 | <Multi_key> <n> <i>			: "∋"  U220B		# CONTAINS AS MEMBER  (I hope this doesn't conflict)
 619 | <Multi_key> <slash> <n> <i>		: "∌"  U220C		# DOES NOT CONTAIN AS MEMBER
 620 | # <exclam><n><i> would conflict, with <exclam> <n> for N WITH DOT BELOW, etc.
 621 | <Multi_key> <equal> <question>		: "≟"  U225f		# QUESTIONED EQUAL TO
 622 | # FIXME: conflict
 623 | #<Multi_key> <equal> <d> <e> <f>		: "≝"  U225D		# EQUAL TO BY DEFINITION
 624 | <Multi_key> <equal> <equal>		: "≡"  U2261		# IDENTICAL TO
 625 | <Multi_key> <colon> <equal> 		: "≔"  U2254		# COLON EQUALS
 626 | <Multi_key> <equal> <colon> 		: "≕"  U2255		# EQUALS COLON
 627 | # Using <slash> would conflict
 628 | <Multi_key> <equal> <bar> <equal>	: "≢"  U2262		# NOT IDENTICAL TO
 629 | # We already have ±
 630 | <Multi_key> <minus> <plus>		: "∓"  U2213		# MINUS OR PLUS SIGN (INTENTIONAL CONFLICT)
 631 | <Multi_key> <s> <q>			: "√"  U221A		# SQUARE ROOT
 632 | <Multi_key> <3> <s> <q>			: "∛"  U221B	        # CUBE ROOT
 633 | <Multi_key> <4> <s> <q>			: "∜"  U221C		# FOURTH ROOT
 634 | <Multi_key> <slash> <backslash>		: "∧"  U2227            # LOGICAL AND
 635 | <Multi_key> <backslash> <slash>		: "∨"  U2228            # LOGICAL OR
 636 | <Multi_key> <backslash> <underscore> <slash>: "⊻"  U22BB        # XOR
 637 | # FIXME: conflict
 638 | #<Multi_key> <asterisk> <o>		: "∘"  U2218            # RING OPERATOR (function composition)
 639 | <Multi_key> <asterisk> <x>		: "⨯"  U2A2F            # CROSS PRODUCT
 640 | <Multi_key> <asterisk> <period>		: "⋅"  U22C5            # DOT OPERATOR (dot product)
 641 | <Multi_key> <0> <slash>                 : "∅"  U2205            # EMPTY SET
 642 | <Multi_key> <slash> <0>                 : "∅"  U2205            # EMPTY SET
 643 | <Multi_key> <less> <E>                  : "∃"  U2203         # THERE EXISTS (INTENTIONAL CONFLICT)
 644 | <Multi_key> <exclam> <less> <E> <E>     : "∄"  U2204            # THERE DOES NOT EXIST
 645 | <Multi_key> <A> <A>                     : "∀"  U2200            # FOR ALL (INTENTIONAL CONFLICT)
 646 | <Multi_key> <Q> <E> <D>     : "∎"  U220E            # END OF PROOF
 647 | <Multi_key> <a> <l> <e> <f> : "ℵ" U2135	       # ALEF SYMBOL
 648 | <Multi_key> <KP_Multiply> <KP_Multiply>    : "∗"   U2217 # ASTERISK OPERATOR
 649 | <Multi_key> <parenleft> <plus> <parenright>     : "⊕"  U2295    # CIRCLED PLUS
 650 | # FIXME: prefix conflict
 651 | #<Multi_key> <parenleft> <minus> <parenright>    : "⊖"  U2296    # CIRCLED MINUS
 652 | <Multi_key> <parenleft> <x> <x> <parenright>    : "⊗"  U2297    # CIRCLED TIMES
 653 | <Multi_key> <parenleft> <slash> <parenright>    : "⊘"  U2298    # CIRCLED DIVISION SLASH
 654 | # FIXME: conflict
 655 | #<Multi_key> <parenleft> <asterisk> <parenright> : "⊛"  U229B    # CIRCLED ASTERISK OPERATOR
 656 | # )- conflicts with system for }.
 657 | <Multi_key> <parenright> <underscore>    : "⟌"   	U27CC		# LONG DIVISION
 658 | <Multi_key> <period> <quotedbl>	   	: "∴"	U2234  		# THEREFORE
 659 | <Multi_key> <quotedbl> <period>	   	: "∵"	U2235  		# BECAUSE
 660 | # Ordinal indicators, for feminine and masculine, used in Romance languages
 661 | <Multi_key> <a> <minus>	      	  	: "ª"   U00AA		# FEMININE ORDINAL INDICATOR (INTENTIONAL CONFLICT)
 662 | <Multi_key> <o> <minus>			: "º"	U00BA		# MASCULINE ORDINAL INDICATOR (INTENTIONAL CONFLICT)
 663 | 
 664 | <Multi_key> <s> <u> <m>	: "∑"	U2211		# N-ARY SUMMATION
 665 | <Multi_key> <i> <n> <t>	: "∫"	U222B		# INTEGRAL
 666 | <Multi_key> <u> <i> <n> <t>	: "⨛"	U2A1B		# UPPER INTEGRAL
 667 | <Multi_key> <l> <i> <n> <t>	: "⨜"	U2A1C		# LOWER INTEGRAL
 668 | <Multi_key> <i> <i> <n> <t>	: "∬"	U222C		# DOUBLE INTEGRAL
 669 | <Multi_key> <i> <i> <i> <n> <t>	: "∭"	U222D		# TRIPLE INTEGRAL
 670 | #<Multi_key> <i> <i> <i> <i> <n> <t>	: "⨌"	U2A0C		# QUADRUPLE INTEGRAL
 671 | <Multi_key> <o> <i> <n> <t>	: "∮"	U222E		# CONTOUR INTEGRAL
 672 | <Multi_key> <p> <i> <n> <t>	: "⨕"	U2a15		# SEMICIRCULAR POLE INTEGRAL
 673 | <Multi_key> <c> <P> <i> <n> <t>	: "⨓"	U2A13		# INTEGRAL AROUND POINT
 674 | <Multi_key> <o> <i> <i> <n> <t>	: "∯"	U222F		# SURFACE INTEGRAL
 675 | #<Multi_key> <o> <i> <i> <i> <n> <t>	: "∰"	U2230		# VOLUME INTEGRAL
 676 | <Multi_key> <g> <i> <n> <t>	: "⨘"	U2A18		# GEOMETRIC INTEGRAL
 677 | <Multi_key> <s> <i> <n> <t>	: "⨋"	U2A0B		# SUM/INTEGRAL
 678 | <Multi_key> <d> <e> <l>	: "∇"	U2207	        # NABLA
 679 | <Multi_key> <p> <a> <r> <t>   : "∂" U2202		# PARTIAL DIFFERENTIAL
 680 | # FIXME: prefix <asterisk> <period> is already used
 681 | #<Multi_key> <asterisk> <period> <period> <d>   : "∂" U2202	# PARTIAL DIFFERENTIAL
 682 | # Would we prefer 20D1 COMBINING RIGHT HARPOON ABOVE?
 683 | <Multi_key> <asciicircum> <greater>     : "⃗"   U20D7           # COMBINING RIGHT ARROW ABOVE (vector)
 684 | # TODO: There's a whole passel of these guys starting at U+1D538 but I have no fonts for those.
 685 | <Multi_key> <bar> <C>                   : "ℂ"   U2102           # DOUBLE-STRUCK CAPITAL C (set of complex numbers) (INTENTIONAL CONFLICT)
 686 | <Multi_key> <bar> <N>                   : "ℕ"   U2115           # DOUBLE-STRUCK CAPITAL N (natural number)
 687 | <Multi_key> <bar> <P>                   : "ℙ"   U2119           # DOUBLE-STRUCK CAPITAL P 
 688 | <Multi_key> <bar> <Q>                   : "ℚ"   U211A           # DOUBLE-STRUCK CAPITAL Q (set of rational numbers)
 689 | <Multi_key> <bar> <R>                   : "ℝ"   U211D           # DOUBLE-STRUCK CAPITAL R (set of real numbers)
 690 | <Multi_key> <bar> <Z>                   : "ℤ"   U2124           # DOUBLE-STRUCK CAPITAL Z (set of integers)
 691 | <Multi_key> <bar> <H>		: "ℍ" U210D	# DOUBLE-STRUCK CAPITAL H
 692 | <Multi_key> <bar> <e>		: "ⅇ" U2147	# DOUBLE-STRUCK ITALIC SMALL E
 693 | <Multi_key> <bar> <i>		: "ⅈ" U2148	# DOUBLE-STRUCK ITALIC SMALL I
 694 | <Multi_key> <bar> <j>		: "ⅉ" U2149	# DOUBLE-STRUCK ITALIC SMALL J
 695 | <Multi_key> <bar> <asterisk> <p> : "ℼ" U213C	# DOUBLE-STRUCK SMALL PI
 696 | <Multi_key> <bar> <Greek_pi> 	 : "ℼ" U213C	# DOUBLE-STRUCK SMALL PI
 697 | <Multi_key> <bar> <asterisk> <P> : "ℿ" U213F	# DOUBLE-STRUCK CAPITAL PI
 698 | <Multi_key> <bar> <Greek_PI> 	 : "ℿ" U213F	# DOUBLE-STRUCK CAPITAL PI
 699 | <Multi_key> <bar> <asterisk> <S> : "⅀" U2140	# DOUBLE-STRUCK N-ARY SUMMATION
 700 | <Multi_key> <bar> <Greek_SIGMA>  : "⅀" U2140	# DOUBLE-STRUCK N-ARY SUMMATION
 701 | 
 702 | ## Brackets
 703 | # TODO: There are lots more brackets to consider: 
 704 | # ⦅⦆ ⦇⦈ ⦉⦊ ⟪⟫ ⟬⟭ ⟮⟯ ⦑⦒ ⦓⦔ ⦕⦖ ⦗⦘ ⧼⧽ ⧘⧙ ⧚⧛ 「」 『』
 705 | # Consider <7> <less>/<greater> for ⸂⸃ maybe? <S> and <slash> for ⸉⸊⸌⸍ ...?
 706 | # FIXME: <asterisk> <parenright> is a conflict
 707 | #<Multi_key> <asterisk> <parenleft>      : "﴾"   UFD3E           # ORNATE LEFT PARENTHESIS
 708 | #<Multi_key> <asterisk> <parenright>     : "﴿"   UFD3F           # ORNATE RIGHT PARENTHESIS
 709 | # The following *look* double-struck.
 710 | <Multi_key> <bar> <braceleft>	 : "⦃" U2983	# LEFT WHITE CURLY BRACKET
 711 | <Multi_key> <bar> <braceright>	 : "⦄" U2984	# RIGHT WHITE CURLY BRACKET 
 712 | <Multi_key> <S> <parenleft>  	: "⟅" U27C5 	# LEFT S-SHAPED BAG DELIMITER
 713 | <Multi_key> <S> <parenright>			: "⟆" U27C6 # RIGHT S-SHAPED BAG DELIMITER
 714 | # FIXME: Are the Mathematical versions ⟨⟩ preferable? And there are more at 3008 and 3009
 715 | <Multi_key> <less> <parenleft>			: "〈" U2329 # LEFT-POINTING ANGLE BRACKET
 716 | <Multi_key> <greater> <parenright>		: "〉" U232A # RIGHT-POINTING ANGLE BRACKET
 717 | <Multi_key> <parenleft> <ampersand> <parenleft>	: "⸨"  U2E28 # LEFT DOUBLE PARENTHESIS
 718 | <Multi_key> <parenright> <ampersand> <parenright>: "⸩" U2E29 # RIGHT DOUBLE PARENTHESIS
 719 | <Multi_key> <2> <parenleft>			: "⸨"  U2E28 # LEFT DOUBLE PARENTHESIS
 720 | <Multi_key> <2> <parenright>			: "⸩"  U2E29 # RIGHT DOUBLE PARENTHESIS
 721 | <Multi_key> <Z> <parenleft>			: "༼"  U0F3C # TIBETAN MARK ANG KHANG GYON
 722 | <Multi_key> <Z> <parenright>			: "༽"  U0F3D # TIBETAN MARK ANG KHANG GYAS
 723 | <Multi_key> <L> <bracketleft>			: "⌊"  U230A # LEFT FLOOR
 724 | <Multi_key> <L> <bracketright>			: "⌋"  U230B # RIGHT FLOOR
 725 | <Multi_key> <7> <bracketleft>			: "⌈"  U2308 # LEFT CEILING
 726 | <Multi_key> <7> <bracketright>			: "⌉"  U2309 # RIGHT CEILING
 727 | # The following use the pattern from FLOOR/CEILING
 728 | <Multi_key> <7> <asciicircum> <bracketleft>	: "⸢"  U2E22 # TOP LEFT HALF BRACKET
 729 | <Multi_key> <7> <asciicircum> <bracketright>	: "⸣"  U2E23 # TOP RIGHT HALF BRACKET
 730 | <Multi_key> <L> <underscore> <bracketleft>	: "⸤"  U2E24 # BOTTOM LEFT HALF BRACKET
 731 | <Multi_key> <L> <underscore> <bracketright>	: "⸥"  U2E25 # BOTTOM RIGHT HALF BRACKET
 732 | 
 733 | 
 734 | <Multi_key> <bracketleft> <bracketleft> 	: "⊏"  U228F # SQUARE IMAGE OF
 735 | <Multi_key> <bracketleft> <equal>       	: "⊑"  U2291 # SQUARE IMAGE OF OR EQUAL TO
 736 | <Multi_key> <bracketleft> <underscore>  	: "⊑"  U2291 # SQUARE IMAGE OF OR EQUAL TO
 737 | <Multi_key> <bracketright> <bracketright>	: "⊐"  U2290 # SQUARE ORIGINAL OF
 738 | <Multi_key> <bracketright> <equal>      	: "⊒"  U2292 # SQUARE ORIGINAL OF OR EQUAL TO
 739 | <Multi_key> <bracketright> <underscore> 	: "⊒"  U2292 # SQUARE ORIGINAL OF OR EQUAL TO
 740 | 
 741 | <Multi_key> <l> <l>				: "ℓ"  U2113 # SCRIPT SMALL L
 742 | <Multi_key> <underscore> <bar> <underscore>	: "⊥"  U22A5 # UP TACK (bottom) or should we use U27C2 PERPENDICULAR?
 743 | 
 744 | 
 745 | ## Subscript letters
 746 | <Multi_key> <underscore> <i>  	       :  "ᵢ"  U1D62   	  # LATIN SUBSCRIPT SMALL LETTER I (INTENTIONAL CONFLICT)
 747 | <Multi_key> <underscore> <u>           :  "ᵤ"  U1D64      # LATIN SUBSCRIPT SMALL LETTER U (INTENTIONAL CONFLICT)
 748 | <Multi_key> <underscore> <o>	       :  "ₒ"  U2092	  # LATIN SUBSCRIPT SMALL LETTER O (INTENTIONAL CONFLICT)
 749 | <Multi_key> <underscore> <x>	       :  "ₓ"  U2093	  # LATIN SUBSCRIPT SMALL LETTER X
 750 | <Multi_key> <underscore> <j>	       :  "ⱼ"  U2C7C	  # LATIN SUBSCRIPT SMALL LETTER J
 751 | <Multi_key> <underscore> <k>           :  "ₖ"  U2096	  # LATIN SUBSCRIPT SMALL LETTER K
 752 | <Multi_key> <underscore> <m>	       :  "ₘ"  U2098	  # LATIN SUBSCRIPT SMALL LETTER M
 753 | <Multi_key> <underscore> <n>	       :  "ₙ"  U2099	  # LATIN SUBSCRIPT SMALL LETTER N
 754 | <Multi_key> <underscore> <minus>       : "₋"   U208B	  # SUBSCRIPT MINUS
 755 | 
 756 | # Some archaic Greek.  (For modern Greek, use a Greek keyboard layout.)
 757 | # FIXME: <asterisk> <period> is already used
 758 | # # "period" will indicate a sort of variant of some kind; asterisk is still the "greek" marker
 759 | # <Multi_key> <asterisk> <period> <p>	: "ϖ"	U03D6		# GREEK PI SYMBOL
 760 | # # Reserving .f in case we want PHI SYMBOL.  Digamma was "w" sound anyway.
 761 | # <Multi_key> <asterisk> <period> <w>	: "ϝ"	U03DD		# GREEK SMALL LETTER DIGAMMA
 762 | # <Multi_key> <asterisk> <period> <W>	: "Ϝ"	U03DC		# GREEK CAPITAL LETTER DIGAMMA
 763 | # <Multi_key> <asterisk> <Q>	: "Ϟ"	U03DE	# GREEK LETTER QOPPA
 764 | # <Multi_key> <asterisk> <q>	: "ϟ"	U03DF	# GREEK SMALL LETTER QOPPA
 765 | # <Multi_key> <asterisk> <period> <Q>	: "Ϙ"	U03D8	# GREEK LETTER ARCHAIC QOPPA
 766 | # <Multi_key> <asterisk> <period> <q>	: "ϙ"	U03D9	# GREEK SMALL LETTER ARCHAIC QOPPA
 767 | # <Multi_key> <asterisk> <ampersand>	: "ϗ"	U03D7	# GREEK KAI SYMBOL
 768 | # <Multi_key> <asterisk> <period> <Z>	: "Ϡ"	U03E0	# GREEK LETTER SAMPI
 769 | # <Multi_key> <asterisk> <period> <z>	: "ϡ"	U03E1	# GREEK SMALL LETTER SAMPI
 770 | # <Multi_key> <asterisk> <period> <period> <Z> : "Ͳ"  U0372  # GREEK CAPITAL LETTER ARCHAIC SAMPI
 771 | # <Multi_key> <asterisk> <period> <period> <z> : "ͳ"  U0373  # GREEK SMALL LETTER ARCHAIC SAMPI
 772 | # # Sorry, couldn't think of better ones for these.  Might want .s for SAN.
 773 | # <Multi_key> <asterisk> <question>      : "Ϛ"	U03DA	# GREEK LETTER STIGMA
 774 | # <Multi_key> <asterisk> <slash>	       : "ϛ"	U03DB	# GREEK SMALL LETTER STIGMA
 775 | # <Multi_key> <asterisk> <apostrophe> <apostrophe>    : "ʹ"	U02B9	# MODIFIER LETTER PRIME, canonically equivalent to U0374 GREEK NUMERAL SIGN
 776 | # # While we're at it...
 777 | # <Multi_key> <asterisk> <period> <apostrophe>	: "′"	U2032	# PRIME
 778 | # <Multi_key> <asterisk> <period> <quotedbl>      : "″"	U2033	# DOUBLE PRIME
 779 | # <Multi_key> <asterisk> <comma>	       : "͵"	U0375	# GREEK LOWER NUMERAL SIGN (for thousands)
 780 | # # Do we want BETA SYMBOL, RHO SYMBOL, KAPPA SYMBOL, PHI SYMBOL, THETA SYMBOL?
 781 | # # The format makes them obvious enough I guess.  PI SYMBOL is different enough
 782 | # # that there's no question, and it is separate from these.
 783 | # <Multi_key> <asterisk> <period> <b>    : "ϐ"	U03D0	# GREEK BETA SYMBOL
 784 | # <Multi_key> <asterisk> <period> <u>    : "ϑ"	U03D1	# GREEK THETA SYMBOL
 785 | # <Multi_key> <asterisk> <period> <Y>    : "ϒ"	U03D2	# GREEK UPSILON WITH HOOK SYMBOL
 786 | # <Multi_key> <asterisk> <period> <f>    : "ϕ"	U03D5	# GREEK PHI SYMBOL
 787 | # <Multi_key> <asterisk> <period> <k>    : "ϰ"	U03F0	# GREEK KAPPA SYMBOL
 788 | # <Multi_key> <asterisk> <period> <r>    : "ϱ"	U03F1	# GREEK RHO SYMBOL
 789 | # <Multi_key> <asterisk> <period> <U>    : "ϴ"	U03F4	# GREEK CAPITAL THETA SYMBOL
 790 | # <Multi_key> <asterisk> <period> <e>    : "ϵ"	U03F5	# GREEK LUNATE EPSILON SYMBOL
 791 | # # TODO: Lunate sigmas and dotted versions thereof...  What about SAN, which is at least a letter?
 792 | 
 793 | # Roman numerals
 794 | # Percent for numerical mnemonic
 795 | <Multi_key> <percent> <1>		: "ⅰ"	U2170		# SMALL ROMAN NUMERAL ONE
 796 | <Multi_key> <percent> <2>		: "ⅱ"	U2171		# SMALL ROMAN NUMERAL TWO
 797 | <Multi_key> <percent> <3>		: "ⅲ"	U2172		# SMALL ROMAN NUMERAL THREE
 798 | <Multi_key> <percent> <4>		: "ⅳ"	U2173		# SMALL ROMAN NUMERAL FOUR
 799 | <Multi_key> <percent> <5>		: "ⅴ"	U2174		# SMALL ROMAN NUMERAL FIVE
 800 | <Multi_key> <percent> <6>		: "ⅵ"	U2175		# SMALL ROMAN NUMERAL SIX
 801 | <Multi_key> <percent> <7>		: "ⅶ"	U2176		# SMALL ROMAN NUMERAL SEVEN
 802 | <Multi_key> <percent> <8>		: "ⅷ"	U2177		# SMALL ROMAN NUMERAL EIGHT
 803 | <Multi_key> <percent> <9>		: "ⅸ"	U2178		# SMALL ROMAN NUMERAL NINE
 804 | <Multi_key> <percent> <x>		: "ⅹ"	U2179		# SMALL ROMAN NUMERAL TEN
 805 | <Multi_key> <percent> <underscore> <1>	: "ⅺ"	U217A		# SMALL ROMAN NUMERAL ELEVEN
 806 | <Multi_key> <percent> <underscore> <2>	: "ⅻ"	U217B		# SMALL ROMAN NUMERAL TWELVE
 807 | <Multi_key> <percent> <l>		: "ⅼ"	U217C		# SMALL ROMAN NUMERAL FIFTY
 808 | <Multi_key> <percent> <c>		: "ⅽ"	U217D		# SMALL ROMAN NUMERAL ONE HUNDRED
 809 | <Multi_key> <percent> <d>		: "ⅾ"	U217E		# SMALL ROMAN NUMERAL FIVE HUNDRED
 810 | <Multi_key> <percent> <m>		: "ⅿ"	U217F		# SMALL ROMAN NUMERAL ONE THOUSAND
 811 | <Multi_key> <percent> <0> <1>		: "Ⅰ"	U2160		# ROMAN NUMERAL ONE
 812 | <Multi_key> <percent> <0> <2>		: "Ⅱ"	U2161		# ROMAN NUMERAL TWO
 813 | <Multi_key> <percent> <0> <3>		: "Ⅲ"	U2162		# ROMAN NUMERAL THREE
 814 | <Multi_key> <percent> <0> <4>		: "Ⅳ"	U2163		# ROMAN NUMERAL FOUR
 815 | <Multi_key> <percent> <0> <5>		: "Ⅴ"	U2164		# ROMAN NUMERAL FIVE
 816 | <Multi_key> <percent> <0> <6>		: "Ⅵ"	U2165		# ROMAN NUMERAL SIX
 817 | <Multi_key> <percent> <0> <7>		: "Ⅶ"	U2166		# ROMAN NUMERAL SEVEN
 818 | <Multi_key> <percent> <0> <8>		: "Ⅷ"	U2167		# ROMAN NUMERAL EIGHT
 819 | <Multi_key> <percent> <0> <9>		: "Ⅸ"	U2168		# ROMAN NUMERAL NINE
 820 | <Multi_key> <percent> <0> <x>		: "Ⅹ"	U2169		# ROMAN NUMERAL TEN
 821 | <Multi_key> <percent> <underscore> <0> <1>	: "Ⅺ"	U216A	# ROMAN NUMERAL ELEVEL
 822 | <Multi_key> <percent> <underscore> <0> <2>	: "Ⅻ"	U216B	# ROMAN NUMERAL TWELVE
 823 | <Multi_key> <percent> <0> <l>		: "Ⅼ"	U216C		# ROMAN NUMERAL FIFTY
 824 | <Multi_key> <percent> <0> <c>		: "Ⅽ"	U216D		# ROMAN NUMERAL ONE HUNDRED
 825 | <Multi_key> <percent> <0> <d>		: "Ⅾ"	U216E		# ROMAN NUMERAL FIVE HUNDRED
 826 | <Multi_key> <percent> <0> <m>		: "Ⅿ"	U216F		# ROMAN NUMERAL ONE THOUSAND
 827 | <Multi_key> <percent> <X>		: "Ⅹ"	U2169		# ROMAN NUMERAL TEN
 828 | <Multi_key> <percent> <L>		: "Ⅼ"	U216C		# ROMAN NUMERAL FIFTY
 829 | <Multi_key> <percent> <C>		: "Ⅽ"	U216D		# ROMAN NUMERAL ONE HUNDRED
 830 | <Multi_key> <percent> <D>		: "Ⅾ"	U216E		# ROMAN NUMERAL FIVE HUNDRED
 831 | <Multi_key> <percent> <M>		: "Ⅿ"	U216F		# ROMAN NUMERAL ONE THOUSAND
 832 | 
 833 | # Custom additions: for chat (kragen)
 834 | <Multi_key> <parenleft> <colon>         : "☻"   U263B           # BLACK SMILING FACE
 835 | <Multi_key> <colon> <asciitilde>	: "⍨"   U2368		# APL FUNCTIONAL SYMBOL TILDE DIAERESIS
 836 | <Multi_key> <colon> <bar>		: "⸚"   U2E1A		# HYPHEN WITH DIAERESIS
 837 | # Those are archaic Cyrillic letters... but look so _perfect_ for use
 838 | # in chat. And about the last, the "multiocular O"... Well, I don't
 839 | # know what it can be used for, but given the description, how could I
 840 | # leave it out‽
 841 | # (I guess using U+1F440 EYES would be more straightforward, but not as funny?)
 842 | <Multi_key> <O> <period> <O>		: "Ꙭ"	UA66C		# CYRILLIC CAPITAL LETTER DOUBLE MONOCULAR O * used in the dual of words based on the root for 'eye'
 843 | <Multi_key> <o> <period> <o>		: "ꙭ"  UA66D		# CYRILLIC SMALL LETTER DOUBLE MONOCULAR O
 844 | <Multi_key> <O> <colon>	 		: "Ꙫ"  UA66A		# CYRILLIC CAPITAL LETTER BINOCULAR O * used in the dual of words based on the root for 'eye'
 845 | <Multi_key> <o> <colon> 		: "ꙫ"  UA66B 		# CYRILLIC SMALL LETTER BINOCULAR O
 846 | <Multi_key> <o> <plus>			: "ꙮ"  UA66E		# CYRILLIC LETTER MULTIOCULAR O * used in the epithet 'many-eyed'
 847 | # While we're doing stacks of circles with dots.
 848 | <Multi_key> <o> <3>			: "߷"	U07F7		# NKO SYMBOL GBAKURUNEN
 849 | <Multi_key> <question> <less>	      : "⸮"	  U2E2E		# REVERSED QUESTION MARK
 850 | <Multi_key> <question> <ampersand> <exclam>	  : "⁈"	 U2048	# QUESTION EXCLAMATION MARK
 851 | <Multi_key> <exclam> <ampersand> <question>	  : "⁉"	 U2049	# EXCLAMATION QUESTION MARK
 852 | <Multi_key> <2> <colon>		  : "∷"	 U2237	# PROPORTION -- not strictly 2 times COLON
 853 | <Multi_key> <semicolon> <less>	 		  : "⁏"	 U204F	# REVERSED SEMICOLON
 854 | # Keep looking into big hunks of Latin Extended-D, A720- et seq.
 855 | <Multi_key> <3> <3>			: "♣" U2663		# BLACK CLUB SUIT
 856 | <Multi_key> <D> <greater>		: "♢" U2662		# WHITE DIAMOND SUIT (<> is ↔)
 857 | <Multi_key> <3> <minus>		: "♠" U2660		# BLACK SPADE SUIT
 858 | <Multi_key> <E> <greater>		: "♡" U2661		# WHITE HEART SUIT (INTENTIONAL CONFLICT)
 859 | # "shamrock" is too long; there IS a limit to these!
 860 | # FIXME: conflict
 861 | #<Multi_key> <s> <h> <m> <r> <c> <k>		: "☘" U2618   # SHAMROCK
 862 | <Multi_key> <p> <c>         : "☮"   U262E           # PEACE SYMBOL
 863 | # FIXME: conflict
 864 | #<Multi_key> <y> <y>		: "☯" U262F		# YIN YANG
 865 | # And now that we are into hearts...
 866 | # FIXME: clash with system Compose file
 867 | #<Multi_key> <less> <less> <3>           : "❥"  U2765            # ROTATED HEAVY BLACK HEART BULLET
 868 | <Multi_key> <exclam> <less> <3>         : "❣"  U2763            # HEAVY HEART EXCLAMATION MARK ORNAMENT
 869 | <Multi_key> <less> <f> <3>              : "❦"  U2766            # FLORAL HEART
 870 | <Multi_key> <less> <f> <less> <3>       : "❧"  U2767            # ROTATED FLORAL HEART BULLET
 871 | <Multi_key> <greater> <f> <less> <3>    : "☙"  U2619            # REVERSED ROTATED FLORAL HEART BULLET
 872 | # For some reason, I don't really like these word-based mnemonics.  But until we have something better... -clsn
 873 | # are the ampersand versions better? -kragen
 874 | <Multi_key> <t> <e> <l>			: "☎" 	U260E		# BLACK TELEPHONE
 875 | <Multi_key> <t> <e> <a>		: "☕"	U2615		# HOT BEVERAGE
 876 | # These last two bother me less, though they can still be improved.
 877 | # Other possibly useful symbols:
 878 | # 2668 HOT SPRINGS (for chat, for running off to shower?)
 879 | # I want 2713-2714 and 2717-2718
 880 | # We need a Dingbats prefix, for ❛❜❝❞❢
 881 | <Multi_key> <bracketleft> <space> <bracketright> :	"☐"	U2610	# BALLOT BOX
 882 | # FIXME: Better keystrokes anyone?  This one breaks the pattern. [c]? [v]? [y]? [/]?
 883 | #<Multi_key> <bracketleft> <slash> <bracketright>     :	 "☑"  U2611		# BALLOT BOX WITH CHECK
 884 | # FIXME: conflict
 885 | #<Multi_key> <bracketleft> <x> <bracketright>  :	 "☒"  U2612		# BALLOT BOX WITH X
 886 | # How about dice?
 887 | # FIXME: conflicts
 888 | # <Multi_key> <bracketleft> <1> <bracketright>  :  "⚀"  U2680	# DIE FACE-1
 889 | # <Multi_key> <bracketleft> <2> <bracketright>  :  "⚁"  U2681	# DIE FACE-2
 890 | # <Multi_key> <bracketleft> <3> <bracketright>  :  "⚂"  U2682	# DIE FACE-3
 891 | # <Multi_key> <bracketleft> <4> <bracketright>  :  "⚃"  U2683	# DIE FACE-4
 892 | # <Multi_key> <bracketleft> <5> <bracketright>  :  "⚄"  U2684	# DIE FACE-5
 893 | # <Multi_key> <bracketleft> <6> <bracketright>  :  "⚅"  U2685	# DIE FACE-6
 894 | # 267B BLACK UNIVERSAL RECYCLING SYMBOL
 895 | 
 896 | # Keystrokes okay?
 897 | <Multi_key> <f> <d> <l>   	        : "⚜"	U269C	  # FLEUR-DE-LIS
 898 | <Multi_key> <a> <t> <o> <m>	        : "⚛"	U269B		# ATOM SYMBOL
 899 | <Multi_key> <slash> <exclam> <backslash> : "⚠"  U26A0           # WARNING SIGN
 900 | <Multi_key> <exclam> <asciicircum>	: "⚠"	U26A0		# WARNING SIGN  (INTENTIONAL CONFLICT)
 901 | <Multi_key> <z> <a> <p>	  		: "⚡"	U26A1		# HIGH VOLTAGE SIGN 
 902 | # Shouldn't use just <r><a> because it's too likely to be a prefix for
 903 | # a useful word.
 904 | <Multi_key> <r> <a> <d>	: "☢"	U2622		# RADIOACTIVE SIGN
 905 | <Multi_key> <b> <h>		: "☣"	U2623		# BIOHAZARD SIGN
 906 | # Changing this from ⚝
 907 | # FIXME: conflict
 908 | #<Multi_key> <A> <A> <A> <A> <A>	:	"⛤" U26E4 # PENTAGRAM (pentalpha, get it?)
 909 | <Multi_key> <p> <l> <a> <n> <e>	: "✈"   U2708	  # AIRPLANE
 910 | <Multi_key> <m> <a> <i> <l>		: "✉"	U2709	  # ENVELOPE
 911 | <Multi_key> <w> <h> <l> <c> <h>	: "♿"	U267F	  # WHEELCHAIR SYMBOL
 912 | <Multi_key> <m> <e> <d> 		: "☤"	U2624	  # CADEUCEUS
 913 | # Something different for STAFF OF AESCULAPIUS?
 914 | <Multi_key> <1> <m> <e> <d>		: "⚕"	U2695	# STAFF OF AESCULAPIUS
 915 | # Maybe something different that isn't lousy.
 916 | # 26B0 COFFIN ?
 917 | # One of the SNOWFLAKEs?
 918 | # SNOWMAN? COMET? ANCHOR?
 919 | # Maybe if we go with having a "word" symbol and spelling out lots and 
 920 | # lots of whole words, we can have all the planets.
 921 | #    "Word Symbol" Notion:
 922 | #    Have a semi-reserved symbol reserved for this.  Probably ampersand.
 923 | #    Something that isn't already used for much.  Then you can happily make
 924 | #    all the &-j-u-p-i-t-e-r and &-a-r-i-e-s combos you want without worrying
 925 | #    that you'll run into a combination already used, like "ca"=ǎ or something.
 926 | #    (unless you have whole words that are prefixes).  Worth doing?
 927 | #    I think so. -Kragen
 928 | #
 929 | # I already have STAR OF DAVID on another map.
 930 | # 231A, 231B -- WATCH and HOURGLASS -- one should be &-w-a-i-t
 931 | # 23D4 METRICAL LONG OVER TWO SHORTS a.k.a. METRICAL BOOBS
 932 | # 0950 DEVANAGARI OM?
 933 | # 214C PER SIGN?
 934 | # 212E ESTIMATED SYMBOL?
 935 | # 2324 UP ARROWHEAD BETWEEN TWO HORIZONTAL BARS a.k.a. NOT AMUSED
 936 | 
 937 | # FIXME: prefix conflict
 938 | # <Multi_key> <O> <minus> <plus>		: "♀"	U2640		# FEMALE SIGN
 939 | # <Multi_key> <O> <minus> <greater>	: "♂"	U2642		# MALE SIGN
 940 | #<Multi_key> <g> <a> <y>                 :   "⚣"     U26A3   # DOUBLED MALE SIGN
 941 | #<Multi_key> <l> <e> <s> <b> <i> <a> <n> :   "⚢"     U26A2   # DOUBLED FEMALE SIGN
 942 | #<Multi_key> <h> <e> <t> <e> <r> <o>     :   "⚤"     U26A4   # INTERLOCKED FEMALE AND MALE SIGN
 943 | #<Multi_key> <t> <r> <a> <n> <s>         :   "⚥"     U26A5   # MALE AND FEMALE SIGN
 944 | #<Multi_key> <g> <e> <n> <d> <e> <r> <q> :   "⚧"     U26A7   # MALE WITH STROKE AND MALE AND FEMALE SIGN
 945 | 
 946 | 
 947 | <Multi_key> <O> <X>: 			"☠" U2620 # SKULL AND CROSSBONES (INTENTIONAL CONFLICT)
 948 | <Multi_key> <k> <b> <d> :	"⌨"	  U2328	    # KEYBOARD
 949 | # Can we get better keycodes for these?
 950 | <Multi_key> <equal> <minus>	: "☞" U261E # WHITE RIGHT POINTING INDEX
 951 | <Multi_key> <minus> <equal>	: "☜" U261C # WHITE LEFT POINTING INDEX
 952 | # FIXME: conflict
 953 | #<Multi_key> <asterisk> <asterisk>	:"★" U2605 # BLACK STAR
 954 | <Multi_key> <asterisk> <0>	:"☆" U2606 # WHITE STAR (INTENTIONAL CONFLICT)
 955 | # FIXME: conflict
 956 | #<Multi_key> <asterisk> <minus>	:"✪" U272A # CIRCLED WHITE STAR
 957 | <Multi_key> <2> <asterisk>	:"⁑" U2051 # TWO ASTERISKS ALIGNED VERTICALLY
 958 | <Multi_key> <asterisk> <4>      :"✢"  U2722  # FOUR TEARDROP-SPOKED ASTERISK
 959 | <Multi_key> <asterisk> <6>	:"✡" U2721 # STAR OF DAVID
 960 | <Multi_key> <asterisk> <numbersign>	:"✯" U272F # PINWHEEL STAR
 961 | <Multi_key> <asterisk> <exclam>	:"✱" U2731 # HEAVY ASTERISK
 962 | <Multi_key> <at> <numbersign>	: "⌘" U2318	# PLACE OF INTEREST SIGN
 963 | # Using backslash-minus-slash etc. conflicts with combining accents(? or APL, in US layout).
 964 | <Multi_key> <grave> <minus> <apostrophe>	 : "⚞"	U269E  # THREE LINES CONVERGING RIGHT
 965 | <Multi_key> <apostrophe> <minus> <grave>	 : "⚟"	U269F  # THREE LINES CONVERGING LEFT
 966 | # FIXME: prefix conflict
 967 | #<Multi_key> <b> <e> <l> <l>		: "⍾" U237E  # BELL SYMBOL (or ALIENS LANDING) -- &-a-l-i-e-n ?
 968 | # Other monstery characters... ѪꙚ (alien abductions?) 
 969 | # ඏൠഋ & others from Kannada et al...? 
 970 | # Can't use -^- for this; conflicts with -^ for ↑, and getting those arrows
 971 | # workable was complicated enough.  How about this?
 972 | # FIXME: prefix conflict
 973 | #<Multi_key> <underscore> <asciicircum> <underscore>	: "⌤" U2324  # UP ARROWHEAD BETWEEN TWO HORIZONTAL BARS; aka ENTER KEY, aka NOT AMUSED.
 974 | <Multi_key> <w> <a> <i> <t>		: "⌛" U231B   # HOURGLASS
 975 | <Multi_key> <t> <i> <m> <e>		: "⌚" U231A   # WATCH
 976 | <Multi_key> <parenleft> <parenright>: "◌" U25CC # DOTTED CIRCLE
 977 | # FIXME: conflict
 978 | #<Multi_key> <bracketleft> <bracketright>: "⬚" U2B1A # DOTTED SQUARE
 979 | <Multi_key> <k> <s>                     : "ʘ"   U0298           # LATIN LETTER BILABIAL CLICK (kiss sound)
 980 | 
 981 | #SUPERSCRIPTS:
 982 | #To avoid namespace clashes, <asciicircum> is doubled (will I regret that?)
 983 | <Multi_key> <asciicircum> <asciicircum> <i>       : "ⁱ"   U2071           # SUPERSCRIPT I
 984 | <Multi_key> <asciicircum> <asciicircum> <n>       : "ⁿ"   U207F           # SUPERSCRIPT N
 985 | #Maybe add: ˀˁ˃˂  Need to be able to talk about ʔˁ...
 986 | <Multi_key> <asciicircum> <question> <period>	: "ˀ"	U02C0	# MODIFIER LETTER GLOTTAL STOP
 987 | <Multi_key> <asciicircum> <question> <parenleft> : "ˁ"	U02C1	# MODIFIER LETTER REVERSED GLOTTAL STOP
 988 | 
 989 | <Multi_key> <s> <h>			: "ʃ"	U0283		# LATIN SMALL LETTER ESH
 990 | <Multi_key> <z> <h>			: "ʒ"	U0292		# LATIN SMALL LETTER EZH
 991 | <Multi_key> <l> <h>    			: "ɬ"	U026C		# LATIN SMALL LETTER L WITH BELT
 992 | <Multi_key> <l> <3>			: "ɮ"	U026E		# LATIN SMALL LETTER LEZH
 993 | <Multi_key> <question> <period>		: "ʔ"	U0294		# LATIN LETTER GLOTTAL STOP
 994 | <Multi_key> <question> <parenleft>	: "ʕ"	U0295		# LATIN LETTER PHARYNGEAL VOICED FRICATIVE
 995 | # Not great keystrokes...
 996 | <Multi_key> <question> <v>		: "ʖ"	U0296		# LATIN LETTER INVERTED GLOTTAL STOP
 997 | <Multi_key> <question> <minus>		: "ʡ"	U02A1		# LATIN LETTER GLOTTAL STOP WITH STROKE
 998 | <Multi_key> <question> <braceleft>	: "ʢ"	U02A2		# LATIN LETTER REVERSED GLOTTAL STOP WITH STROKE
 999 | # How about ɸ? φ isn’t the IPA glyph.
1000 | <Multi_key> <p> <h>			: "ɸ"	U0278		# LATIN SMALL LETTER PHI
1001 | <Multi_key> <i> <h>    			: "ɪ"	U026A		# LATIN LETTER SMALL CAPITAL I
1002 | <Multi_key> <u> <h>			: "ʊ"	U028A		# LATIN SMALL LETTER UPSILON
1003 | <Multi_key> <a> <h>			: "ɑ"	U0251		# LATIN SMALL LETTER ALPHA
1004 | <Multi_key> <e> <r>			: "ɚ"	U025A		# LATIN SMALL LETTER SCHWA WITH HOOK
1005 | <Multi_key> <o> <parenright>		:"ɔ" 	U0254 		# LATIN SMALL LETTER OPEN O
1006 | <Multi_key> <O> <parenright>		:"Ɔ" 	U0186 		# LATIN CAPITAL LETTER OPEN O
1007 | <Multi_key> <e> <h>   	    	    	: "ɛ"   U025B		# LATIN SMALL LETTER OPEN E
1008 | # Have to put the <less> at the beginning for these.
1009 | # FIXME: prefix conflicts
1010 | #<Multi_key> <less> <e> <h>		: "ɜ"	U025C		# LATIN SMALL LETTER REVERSED OPEN E
1011 | #<Multi_key> <less> <e> <r>		: "ɝ"	U025D		# LATIN SMALL LETTER REVERSED OPEN E WITH HOOK
1012 | # How are these keystrokes?
1013 | <Multi_key> <bar> <apostrophe>		: "ˈ"	U02C8		# MODIFIER LETTER VERTICAL LINE
1014 | <Multi_key> <bar> <comma>		: "ˌ"	U02CC		# MODIFIER LETTER LOW VERTICAL LINE
1015 | <Multi_key> <bar> <underscore>		: "̩"	U0329		# COMBINING VERTICAL LINE BELOW
1016 | # Harmonize with other combiners.
1017 | <Multi_key> <backslash> <underscore> <bar>	: "̩"	U0329		# COMBINING VERTICAL LINE BELOW
1018 | <Multi_key> <r> <r>                     : "ɹ"   U0279           # LATIN SMALL LETTER TURNED R: voiced alveolar approximant (American English (at least) R)
1019 | <Multi_key> <r> <d>                     : "ɾ"   U027E           # LATIN SMALL LETTER R WITH FISHHOOK: voiced alveolar flap or tap (American English intervocalic allophone of d, or Spanish r)
1020 | # FIXME: conflicts
1021 | #<Multi_key> <v> <v>                     : "ʌ"   U028C           # LATIN SMALL LETTER TURNED V
1022 | #<Multi_key> <u> <i>			: "ɯ"	U026F		# LATIN SMALL LETTER TURNED M
1023 | # doubling a letter seems to be mostly used for turning
1024 | # FIXME: conflict
1025 | # <Multi_key> <w> <w>			: "ʍ"	U028D		# LATIN SMALL LETTER TURNED W
1026 | <Multi_key> <a> <a>			: "ɐ"	U0250		# LATIN SMALL LETTER TURNED A (INTENTIONAL CONFLICT)
1027 | # I'll use capitals for a different double
1028 | # FIXME: conflict
1029 | #<Multi_key> <W> <W>			: "ʬ"	U02AC		# LATIN LETTER BILABIAL PERCUSSIVE
1030 | # FIXME: conflict
1031 | #<Multi_key> <colon> <plus>  	      	: "ː"	U02D0		# MODIFIER LETTER TRIANGULAR COLON
1032 | # Also handy for writing urls: http://ʬw.omniglot.com/
1033 | # ɣ? ᴥ?  Important enough to add? ᴥ is cool just as a "latin" letter.
1034 | <Multi_key> <g> <h>	     	    : "ɣ"   U0263     # LATIN SMALL LETTER GAMMA
1035 | <Multi_key> <a> <i> <n>		    : "ᴥ"   U1D25     # LATIN LETTER AIN
1036 | # Sometimes it's a "tail", sometimes a "hook", and sometimes a "retroflex hook"
1037 | # These conflict with system definitions for letters with cedilla, but those can be obtained by typing the comma first
1038 | <Multi_key> <d> <comma>		    : "ɖ"   U0256     # LATIN SMALL LETTER D WITH TAIL (INTENTIONAL CONFLICT)
1039 | <Multi_key> <l> <comma>		    : "ɭ"   U026D     # LATIN SMALL LETTER L WITH RETROFLEX HOOK (INTENTIONAL CONFLICT)
1040 | <Multi_key> <n> <comma>		    : "ɳ"   U0273     # LATIN SMALL LETTER N WITH RETROFLEX HOOK (INTENTIONAL CONFLICT)
1041 | <Multi_key> <s> <comma>		    : "ʂ"   U0282     # LATIN SMALL LETTER S WITH HOOK (INTENTIONAL CONFLICT)
1042 | <Multi_key> <t> <comma>		    : "ʈ"   U0288     # LATIN SMALL LETTER T WITH RETROFLEX HOOK (INTENTIONAL CONFLICT)
1043 | <Multi_key> <z> <comma>		    : "ʐ"   U0290     # LATIN SMALL LETTER Z WITH RETROFLEX HOOK
1044 | # This is used for functions, folders, etc.  Yeah, the hook's facing wrong.
1045 | <Multi_key> <f> <comma>		    : "ƒ"   U0192     # LATIN SMALL LETTER F WITH HOOK
1046 | # Sigh, might as well do implosives.  Which is also sometimes a hook.
1047 | <Multi_key> <b> <apostrophe>	    : "ɓ"   U0253     # LATIN SMALL LETTER B WITH HOOK
1048 | <Multi_key> <d> <apostrophe>	    : "ɗ"   U0257     # LATIN SMALL LETTER D WITH HOOK
1049 | <Multi_key> <g> <apostrophe>	    : "ɠ"   U0260     # LATIN SMALL LETTER G WITH HOOK
1050 | <Multi_key> <g> <g>		    : "ɡ"   U0261     # LATIN SMALL LETTER SCRIPT G
1051 | # The h looks the same...
1052 | <Multi_key> <h> <apostrophe>	    : "ɦ"   U0266     # LATIN SMALL LETTER H WITH HOOK
1053 | <Multi_key> <G> <apostrophe>	    : "ʛ"   U029B     # LATIN LETTER SMALL CAPITAL G WITH HOOK
1054 | <Multi_key> <R> <x>			: "℞"	U211E		# PRESCRIPTION TAKE
1055 | <Multi_key> <o> <z> <period>		: "℥"	U2125		# OUNCE SIGN
1056 | # FIXME: conflict
1057 | #<Multi_key> <s> <c> <r> <period>	: "℈"	U2108		# SCRUPLE
1058 | # There are all kinds of awesome combining characters in the U+0300 page.
1059 | # There are a bunch of other awesome combining characters like U+20E0
1060 | # FIXME: conflict
1061 | #<Multi_key> <asterisk> <period> <period> <period> : "๛" U0E5B   # THAI CHARACTER KHOMUT (end of chapter)
1062 | 
1063 | 
1064 | ## Music.  # is the music mnemonic.
1065 | <Multi_key> <numbersign> <G>              : "𝄞"  U0001d11e # MUSICAL SYMBOL G CLEF
1066 | <Multi_key> <numbersign> <F>              : "𝄢"  U0001d122 # MUSICAL SYMBOL F CLEF
1067 | <Multi_key> <numbersign> <C>              : "𝄡" U0001d121 # MUSICAL SYMBOL C CLEF
1068 | <Multi_key> <numbersign> <b>              : "♭" U266D # MUSIC FLAT SIGN
1069 | <Multi_key> <numbersign> <numbersign>     : "♯" U266F # MUSIC SHARP SIGN
1070 | 
1071 | 
1072 | ## Astrological signs
1073 | 
1074 | # Planets
1075 | #FIXME: Improve these
1076 | # <Multi_key> <s> <u> <n>	: "☉"	U2609	# SUN (Sunday)
1077 | # <Multi_key> <m> <o> <o> <n>	: "☽"	U263D	# FIRST QUARTER MOON (Monday)
1078 | # <Multi_key> <m> <e> <r> <c> <u> <r> <y> : "☿" U263F	# MERCURY (Wednesday)
1079 | # <Multi_key> <v> <e> <n> <u> <s>  : "♀" U2640    # FEMALE SIGN
1080 | # <Multi_key> <j> <u> <p> <i> <t> <e> <r> : "♃" U2643	# JUPITER (Thursday)
1081 | # <Multi_key> <s> <a> <t> <u> <r> <n>     : "♄" U2644	# SATURN (Saturday)
1082 | # <Multi_key> <u> <r> <a> <n> <u> <s>	    : "♅" U2645	# URANUS (FIXME: or ⛢ U26E2?)
1083 | # <Multi_key> <n> <e> <p> <t> <u> <n> <e> : "♆" U2646	# NEPTUNE
1084 | # <Multi_key> <p> <l> <u> <t> <o> 	    : "♇" U2647	# PLUTO (ok, it isn't a planet anymore, but we still love it.)
1085 | 
1086 | # Minor planets
1087 | #FIXME: Improve these
1088 | # <Multi_key> <c> <e> <r> <e> <s>	: "⚳"	U26B3	# CERES
1089 | # <Multi_key> <p> <a> <l> <l> <a> <s>	: "⚴"	U26B4	# PALLAS
1090 | # <Multi_key> <j> <u> <n> <o>     	: "⚵"	U26B5	# JUNO
1091 | # <Multi_key> <v> <e> <s> <t> <a>    	: "⚶"	U26B6	# VESTA
1092 | # <Multi_key> <c> <h> <i> <r> <o> <n>	: "⚷"	U26B7	# CHIRON
1093 | # <Multi_key> <l> <i> <l> <i> <t> <h>	: "⚸"	U26B8	# BLACK MOON LILITH
1094 | 
1095 | # Zodiac signs
1096 | #FIXME: Improve these
1097 | # <Multi_key> <a> <r> <i> <e> <s>	: "♈"	U2648	# ARIES
1098 | # <Multi_key> <t> <a> <u> <r> <u> <s>	: "♉"	U2649	# TAURUS
1099 | # <Multi_key> <g> <e> <m> <i> <n> <i>	: "♊"	U264A	# GEMINI
1100 | # <Multi_key> <c> <a> <n> <c> <e> <r>	: "♋"	U264B	# CANCER
1101 | # <Multi_key> <l> <e> <o> 		: "♌"	U264C	# LEO
1102 | # <Multi_key> <v> <i> <r> <g> <o>	: "♍"	U264D	# VIRGO
1103 | # <Multi_key> <l> <i> <b> <r> <a>	: "♎"	U264E	# LIBRA
1104 | # <Multi_key> <s> <c> <o> <r> <p>	: "♏"	U264F	# SCORPIUS
1105 | # <Multi_key> <s> <a> <g> <i> <t>	: "♐"	U2650	# SAGITTARIUS
1106 | # <Multi_key> <c> <a> <p> <r> <i> <c>	: "♑"	U2651	# CAPRICORN
1107 | # <Multi_key> <a> <q> <u> <a> <r>	: "♒"	U2652	# AQUARIUS
1108 | # <Multi_key> <p> <i> <s> <c> <e> <s>	: "♓"	U2653	# PISCES
1109 | # # Really, this should be SERPENTARIUS.  All the other signs are in Latin.
1110 | # <Multi_key> <o> <p> <h> <i> <u> <c> : "⛎"	U26CE	# OPHIUCHUS
1111 | 
1112 | 
1113 | ## Games
1114 | 
1115 | # Playing Cards
1116 | # The convention is more or less established, except for the Knight.  I'm
1117 | # using N for that, like in Chess, since K would conflict with King of course.
1118 | <Multi_key> <bracketleft> <A> <S> <bracketright>  : "🂡"	U1F0A1	# PLAYING CARD ACE OF SPADES
1119 | <Multi_key> <bracketleft> <2> <S> <bracketright>  : "🂢"	U1F0A2	# PLAYING CARD TWO OF SPADES
1120 | <Multi_key> <bracketleft> <3> <S> <bracketright>  : "🂣"	U1F0A3	# PLAYING CARD THREE OF SPADES
1121 | <Multi_key> <bracketleft> <4> <S> <bracketright>  : "🂤"	U1F0A4	# PLAYING CARD FOUR OF SPADES
1122 | <Multi_key> <bracketleft> <5> <S> <bracketright>  : "🂥"	U1F0A5	# PLAYING CARD FIVE OF SPADES
1123 | <Multi_key> <bracketleft> <6> <S> <bracketright>  : "🂦"	U1F0A6	# PLAYING CARD SIX OF SPADES
1124 | <Multi_key> <bracketleft> <7> <S> <bracketright>  : "🂧"	U1F0A7	# PLAYING CARD SEVEN OF SPADES
1125 | <Multi_key> <bracketleft> <8> <S> <bracketright>  : "🂨"	U1F0A8	# PLAYING CARD EIGHT OF SPADES
1126 | <Multi_key> <bracketleft> <9> <S> <bracketright>  : "🂩"	U1F0A9	# PLAYING CARD NINE OF SPADES
1127 | <Multi_key> <bracketleft> <T> <S> <bracketright>  : "🂪"	U1F0AA	# PLAYING CARD TEN OF SPADES
1128 | <Multi_key> <bracketleft> <J> <S> <bracketright>  : "🂫"	U1F0AB	# PLAYING CARD JACK OF SPADES
1129 | <Multi_key> <bracketleft> <N> <S> <bracketright>  : "🂬"	U1F0AC	# PLAYING CARD KNIGHT OF SPADES
1130 | <Multi_key> <bracketleft> <Q> <S> <bracketright>  : "🂭"	U1F0AD	# PLAYING CARD QUEEN OF SPADES
1131 | <Multi_key> <bracketleft> <K> <S> <bracketright>  : "🂮"	U1F0AE	# PLAYING CARD KING OF SPADES
1132 | 
1133 | <Multi_key> <bracketleft> <A> <H> <bracketright>  : "🂱"	U1F0B1	# PLAYING CARD ACE OF HEARTS
1134 | <Multi_key> <bracketleft> <2> <H> <bracketright>  : "🂲"	U1F0B2	# PLAYING CARD TWO OF HEARTS
1135 | <Multi_key> <bracketleft> <3> <H> <bracketright>  : "🂳"	U1F0B3	# PLAYING CARD THREE OF HEARTS
1136 | <Multi_key> <bracketleft> <4> <H> <bracketright>  : "🂴"	U1F0B4	# PLAYING CARD FOUR OF HEARTS
1137 | <Multi_key> <bracketleft> <5> <H> <bracketright>  : "🂵"	U1F0B5	# PLAYING CARD FIVE OF HEARTS
1138 | <Multi_key> <bracketleft> <6> <H> <bracketright>  : "🂶"	U1F0B6	# PLAYING CARD SIX OF HEARTS
1139 | <Multi_key> <bracketleft> <7> <H> <bracketright>  : "🂷"	U1F0B7	# PLAYING CARD SEVEN OF HEARTS
1140 | <Multi_key> <bracketleft> <8> <H> <bracketright>  : "🂸"	U1F0B8	# PLAYING CARD EIGHT OF HEARTS
1141 | <Multi_key> <bracketleft> <9> <H> <bracketright>  : "🂹"	U1F0B9	# PLAYING CARD NINE OF HEARTS
1142 | <Multi_key> <bracketleft> <T> <H> <bracketright>  : "🂺"	U1F0BA	# PLAYING CARD TEN OF HEARTS
1143 | <Multi_key> <bracketleft> <J> <H> <bracketright>  : "🂻"	U1F0BB	# PLAYING CARD JACK OF HEARTS
1144 | <Multi_key> <bracketleft> <N> <H> <bracketright>  : "🂼"	U1F0BC	# PLAYING CARD KNIGHT OF HEARTS
1145 | <Multi_key> <bracketleft> <Q> <H> <bracketright>  : "🂽"	U1F0BD	# PLAYING CARD QUEEN OF HEARTS
1146 | <Multi_key> <bracketleft> <K> <H> <bracketright>  : "🂾"	U1F0BE	# PLAYING CARD KING OF HEARTS
1147 | 
1148 | <Multi_key> <bracketleft> <A> <D> <bracketright>  : "🃁"	U1F0C1	# PLAYING CARD ACE OF DIAMONDS
1149 | <Multi_key> <bracketleft> <2> <D> <bracketright>  : "🃂"	U1F0C2	# PLAYING CARD TWO OF DIAMONDS
1150 | <Multi_key> <bracketleft> <3> <D> <bracketright>  : "🃃"	U1F0C3	# PLAYING CARD THREE OF DIAMONDS
1151 | <Multi_key> <bracketleft> <4> <D> <bracketright>  : "🃄"	U1F0C4	# PLAYING CARD FOUR OF DIAMONDS
1152 | <Multi_key> <bracketleft> <5> <D> <bracketright>  : "🃅"	U1F0C5	# PLAYING CARD FIVE OF DIAMONDS
1153 | <Multi_key> <bracketleft> <6> <D> <bracketright>  : "🃆"	U1F0C6	# PLAYING CARD SIX OF DIAMONDS
1154 | <Multi_key> <bracketleft> <7> <D> <bracketright>  : "🃇"	U1F0C7	# PLAYING CARD SEVEN OF DIAMONDS
1155 | <Multi_key> <bracketleft> <8> <D> <bracketright>  : "🃈"	U1F0C8	# PLAYING CARD EIGHT OF DIAMONDS
1156 | <Multi_key> <bracketleft> <9> <D> <bracketright>  : "🃉"	U1F0C9	# PLAYING CARD NINE OF DIAMONDS
1157 | <Multi_key> <bracketleft> <T> <D> <bracketright>  : "🃊"	U1F0CA	# PLAYING CARD TEN OF DIAMONDS
1158 | <Multi_key> <bracketleft> <J> <D> <bracketright>  : "🃋"	U1F0CB	# PLAYING CARD JACK OF DIAMONDS
1159 | <Multi_key> <bracketleft> <N> <D> <bracketright>  : "🃌"	U1F0CC	# PLAYING CARD KNIGHT OF DIAMONDS
1160 | <Multi_key> <bracketleft> <Q> <D> <bracketright>  : "🃍"	U1F0CD	# PLAYING CARD QUEEN OF DIAMONDS
1161 | <Multi_key> <bracketleft> <K> <D> <bracketright>  : "🃎"	U1F0CE	# PLAYING CARD KING OF DIAMONDS
1162 | 
1163 | <Multi_key> <bracketleft> <A> <C> <bracketright>  : "🃑"	U1F0D1	# PLAYING CARD ACE OF CLUBS
1164 | <Multi_key> <bracketleft> <2> <C> <bracketright>  : "🃒"	U1F0D2	# PLAYING CARD TWO OF CLUBS
1165 | <Multi_key> <bracketleft> <3> <C> <bracketright>  : "🃓"	U1F0D3	# PLAYING CARD THREE OF CLUBS
1166 | <Multi_key> <bracketleft> <4> <C> <bracketright>  : "🃔"	U1F0D4	# PLAYING CARD FOUR OF CLUBS
1167 | <Multi_key> <bracketleft> <5> <C> <bracketright>  : "🃕"	U1F0D5	# PLAYING CARD FIVE OF CLUBS
1168 | <Multi_key> <bracketleft> <6> <C> <bracketright>  : "🃖"	U1F0D6	# PLAYING CARD SIX OF CLUBS
1169 | <Multi_key> <bracketleft> <7> <C> <bracketright>  : "🃗"	U1F0D7	# PLAYING CARD SEVEN OF CLUBS
1170 | <Multi_key> <bracketleft> <8> <C> <bracketright>  : "🃘"	U1F0D8	# PLAYING CARD EIGHT OF CLUBS
1171 | <Multi_key> <bracketleft> <9> <C> <bracketright>  : "🃙"	U1F0D9	# PLAYING CARD NINE OF CLUBS
1172 | <Multi_key> <bracketleft> <T> <C> <bracketright>  : "🃚"	U1F0DA	# PLAYING CARD TEN OF CLUBS
1173 | <Multi_key> <bracketleft> <J> <C> <bracketright>  : "🃛"	U1F0DB	# PLAYING CARD JACK OF CLUBS
1174 | <Multi_key> <bracketleft> <N> <C> <bracketright>  : "🃜"	U1F0DC	# PLAYING CARD KNIGHT OF CLUBS
1175 | <Multi_key> <bracketleft> <Q> <C> <bracketright>  : "🃝"	U1F0DD	# PLAYING CARD QUEEN OF CLUBS
1176 | <Multi_key> <bracketleft> <K> <C> <bracketright>  : "🃞"	U1F0DE	# PLAYING CARD KING OF CLUBS
1177 | 
1178 | <Multi_key> <bracketleft> <C> <B> <bracketright>  : "🂠"	U1F0A0	# PLAYING CARD BACK
1179 | <Multi_key> <bracketleft> <B> <J> <bracketright>  : "🃏"	U1F0CF	# PLAYING CARD BLACK JOKER
1180 | <Multi_key> <bracketleft> <W> <J> <bracketright>  : "🃟"	U1F0DF	# PLAYING CARD WHITE JOKER
1181 | 
1182 | # TODO: Dominoes
1183 | # I'm thinking [ 1 1 ], etc, maybe use ] 1 1 [ for vertical
1184 | 
1185 | # Chess
1186 | # FIXME: <bar> will be an issue when we want double-struck W or B... replace with <equal>?
1187 | <Multi_key> <bar> <W> <K>	 : "♔" U2654	# WHITE CHESS KING
1188 | <Multi_key> <bar> <W> <Q>	 : "♕" U2655	# WHITE CHESS QUEEN
1189 | <Multi_key> <bar> <W> <R>	 : "♖" U2656	# WHITE CHESS ROOK
1190 | <Multi_key> <bar> <W> <B>	 : "♗" U2657	# WHITE CHESS BISHOP
1191 | <Multi_key> <bar> <W> <N>	 : "♘" U2658	# WHITE CHESS KNIGHT
1192 | <Multi_key> <bar> <W> <P>	 : "♙" U2659	# WHITE CHESS PAWN
1193 | <Multi_key> <bar> <B> <K>	 : "♚" U265A	# BLACK CHESS KING
1194 | <Multi_key> <bar> <B> <Q>	 : "♛" U265B	# BLACK CHESS QUEEN
1195 | <Multi_key> <bar> <B> <R>	 : "♜" U265C	# BLACK CHESS ROOK
1196 | <Multi_key> <bar> <B> <B>	 : "♝" U265D	# BLACK CHESS BISHOP
1197 | <Multi_key> <bar> <B> <N>	 : "♞" U265E	# BLACK CHESS KNIGHT
1198 | <Multi_key> <bar> <B> <P>	 : "♟" U265F	# BLACK CHESS PAWN
1199 | 
1200 | # Checkers/Draughts
1201 | <Multi_key> <bar> <W> <D> <M>	 : "⛀" U26C0	# WHITE DRAUGHTS MAN
1202 | <Multi_key> <bar> <W> <D> <K>	 : "⛁" U26C1	# WHITE DRAUGHTS KING
1203 | <Multi_key> <bar> <B> <D> <M>	 : "⛂" U26C2	# BLACK DRAUGHTS MAN
1204 | <Multi_key> <bar> <B> <D> <K>	 : "⛃" U26C3	# BLACK DRAUGHTS KING
1205 | 
1206 | # Shogi
1207 | <Multi_key> <bar> <W> <S>	 : "☖" U2616	# WHITE SHOGI PIECE
1208 | <Multi_key> <bar> <B> <S>	 : "☗" U2617	# BLACK SHOGI PIECE
1209 | <Multi_key> <bar> <less> <W> <S> : "⛉" U26C9	# TURNED WHITE SHOGI PIECE
1210 | <Multi_key> <bar> <less> <B> <S> : "⛊" U26CA	# TURNED BLACK SHOGI PIECE
1211 | 
1212 | 
1213 | ## Temperature
1214 | <Multi_key> <d> <e> <g> <C> 		: "℃"   U2103 	# DEGREE CELSIUS
1215 | <Multi_key> <d> <e> <g> <F> 		: "℉"   U2109   # DEGREE FAHRENHEIT
1216 | 
1217 | 
1218 | ## Emoji
1219 | <Multi_key> <i> <d> <e> <a>		: "💡"    U1F4A1 # ELECTRIC LIGHT BULB
1220 | <Multi_key> <a> <n> <g> <e> <r>		: "💢"    U1F4A2 # ANGER SYMBOL
1221 | # FIXME: conflict
1222 | # <Multi_key> <b> <o> <m> <b>		: "💣"    U1F4A3 # BOMB
1223 | <Multi_key> <z> <z> <z>			: "💤"    U1F4A4 # SLEEPING SYMBOL
1224 | <Multi_key> <p> <o> <w>			: "💥"    U1F4A5 # COLLISION SYMBOL
1225 | <Multi_key> <s> <w> <e> <a> <t>		: "💦"    U1F4A6 # SPLASHING SWEAT SYMBOL
1226 | <Multi_key> <d> <r> <o> <p>		: "💧"    U1F4A7 # DROPLET
1227 | <Multi_key> <z> <i> <p>			: "💨"    U1F4A8 # DASH SYMBOL
1228 | <Multi_key> <p> <o> <o>			: "💩"    U1F4A9 # PILE OF POO
1229 | # FIXME: prefix conflict
1230 | #<Multi_key> <d> <i> <z> <z> <y>		: "💫"    U1F4AB # DIZZY SYMBOL
1231 | <Multi_key> <dollar> <b> <a> <g>	: "💰"    U1F4B0 # MONEY BAG
1232 | # FIXME: prefix conflict
1233 | #<Multi_key> <c> <a> <k> <e>		: "🍰"    U1F370 # SHORTCAKE
1234 | <Multi_key> <b> <d> <a> <y>		: "🎂"    U1F382 # BIRTHDAY CAKE
1235 | <Multi_key> <A> <O> <K>			: "👌"    U1F44C # OK HAND SIGN
1236 | # FIXME: Next is conflict, second needs to be fixed in the same way
1237 | #<Multi_key> <t> <h> <m> <u> <p>		: "👍"    U1F44D # THUMBS UP SIGN
1238 | #<Multi_key> <t> <h> <m> <d> <n>		: "👎"    U1F44E # THUMBS DOWN SIGN
1239 | <Multi_key> <k> <i> <s> <s>		: "💋"    U1F48B # KISS MARK
1240 | 
1241 | 
1242 | ## Clock faces
1243 | # <Multi_key> <parenleft> <1> <colon> <0> <0> <parenright> : "🕐" U1F550 # CLOCK FACE ONE OCLOCK
1244 | # <Multi_key> <parenleft> <2> <colon> <0> <0> <parenright> : "🕑" U1F551 # CLOCK FACE TWO OCLOCK
1245 | # <Multi_key> <parenleft> <3> <colon> <0> <0> <parenright> : "🕒" U1F552 # CLOCK FACE THREE OCLOCK
1246 | # <Multi_key> <parenleft> <4> <colon> <0> <0> <parenright> : "🕓" U1F553 # CLOCK FACE FOUR OCLOCK
1247 | # <Multi_key> <parenleft> <5> <colon> <0> <0> <parenright> : "🕔" U1F554 # CLOCK FACE FIVE OCLOCK
1248 | # <Multi_key> <parenleft> <6> <colon> <0> <0> <parenright> : "🕕" U1F555 # CLOCK FACE SIX OCLOCK
1249 | # <Multi_key> <parenleft> <7> <colon> <0> <0> <parenright> : "🕖" U1F556 # CLOCK FACE SEVEN OCLOCK
1250 | # <Multi_key> <parenleft> <8> <colon> <0> <0> <parenright> : "🕗" U1F557 # CLOCK FACE EIGHT OCLOCK
1251 | # <Multi_key> <parenleft> <9> <colon> <0> <0> <parenright> : "🕘" U1F558 # CLOCK FACE NINE OCLOCK
1252 | # <Multi_key> <parenleft> <1> <0> <colon> <0> <0> <parenright> : "🕙" U1F559 # CLOCK FACE TEN OCLOCK
1253 | # <Multi_key> <parenleft> <1> <1> <colon> <0> <0> <parenright> : "🕚" U1F55A # CLOCK FACE ELEVEN OCLOCK
1254 | # <Multi_key> <parenleft> <1> <2> <colon> <0> <0> <parenright> : "🕛" U1F55B # CLOCK FACE TWELVE OCLOCK
1255 | 
1256 | # <Multi_key> <parenleft> <1> <colon> <3> <0> <parenright>     : "🕜" U1F55C # CLOCK FACE ONE-THIRTY
1257 | # <Multi_key> <parenleft> <2> <colon> <3> <0> <parenright>     : "🕝" U1F55D # CLOCK FACE TWO-THIRTY
1258 | # <Multi_key> <parenleft> <3> <colon> <3> <0> <parenright>     : "🕞" U1F55E # CLOCK FACE THREE-THIRTY
1259 | # <Multi_key> <parenleft> <4> <colon> <3> <0> <parenright>     : "🕟" U1F55F # CLOCK FACE FOUR-THIRTY
1260 | # <Multi_key> <parenleft> <5> <colon> <3> <0> <parenright>     : "🕠" U1F560 # CLOCK FACE FIVE-THIRTY
1261 | # <Multi_key> <parenleft> <6> <colon> <3> <0> <parenright>     : "🕡" U1F561 # CLOCK FACE SIX-THIRTY
1262 | # <Multi_key> <parenleft> <7> <colon> <3> <0> <parenright>     : "🕢" U1F562 # CLOCK FACE SEVEN-THIRTY
1263 | # <Multi_key> <parenleft> <8> <colon> <3> <0> <parenright>     : "🕣" U1F563 # CLOCK FACE EIGHT-THIRTY
1264 | # <Multi_key> <parenleft> <9> <colon> <3> <0> <parenright>     : "🕤" U1F564 # CLOCK FACE NINE-THIRTY
1265 | # <Multi_key> <parenleft> <1> <0> <colon> <3> <0> <parenright>     : "🕥" U1F565 # CLOCK FACE TEN-THIRTY
1266 | # <Multi_key> <parenleft> <1> <1> <colon> <3> <0> <parenright>     : "🕦" U1F566 # CLOCK FACE ELEVEN-THIRTY
1267 | # <Multi_key> <parenleft> <1> <2> <colon> <3> <0> <parenright>     : "🕧" U1F567 # CLOCK FACE TWELVE-THIRTY
1268 | 
1269 | 
1270 | ## TODO: Emoticons (U+1F600 et seq)
1271 | 
1272 | # Lozenge (for Pollen http://pollenpub.com)
1273 | <Multi_key> <greater> <less>: "◊" U25ca # INTENTIONAL CONFLICT
1274 | 


--------------------------------------------------------------------------------