aniani/elinks
1
0
Fork 0
mirror of https://github.com/rkd77/elinks.git synced 2024-10-29 08:17:18 -04:00
Code
a685470da9
elinks/Unicode/7bitrepl.lnx
Petr Baudis 0f6d4310ad Initial commit of the HEAD branch of the ELinks CVS repository, as of 
Thu Sep 15 15:57:07 CEST 2005. The previous history can be added to this
by grafting.
2005-09-15 15:58:31 +02:00

2402 lines
29 KiB
Plaintext
Raw Blame History

# Default 7bit replacements.
#
# Default 7bit replacements. If the MIME name is set to us-ascii,
# this will be identified with the "7 bit approximations" Display
# character set.
#
# This table is very important and should not be excluded from the distribution
# since this is a default fallback for any 8bit user's "display character set"
# which (nearly) of 256 chars and could not map a rich Unicode repertoire.
#
# M.P.: unicode to ascii table. I took this file from lynx.
# lynx/src/chrtrans/def7_uni.tbl
#The MIME name of this charset.
Mus-ascii
# Shall this become the "default" translation table? YES!
# There has to be exactly one table marked as "default".
D1
# us-ascii characters should not normally pass here,
# they are always processed directly but let declare them here:
0x20-0x7e idem
# NO-BREAK SPACE,
# should not happen (processed in the code):
#U+00a0:NS
U+00a1:!
U+00a2:-c-
U+00a3:-L-
U+00a4:CUR
U+00a5:YEN
U+00a6:|
U+00a7:S:
U+00a8:"
# COPYRIGHT SIGN:
U+00a9:(c)
U+00aa:-a
U+00ab:<<
U+00ac:NOT
# SOFT HYPHEN,
# should not happen (processed in the code):
#U+00ad:-
# XXX: The following is missing in original lynx, not sure if we should do
# anything about it...? --pasky
U+00ad:
# REGISTERED SIGN:
U+00ae:(R)
U+00af:-
U+00b0:DEG
U+00b1:+-
U+00b2:^2
U+00b3:^3
U+00b4:'
# My -> u
U+00b5:u
U+00b6:P:
U+00b7:.
U+00b8:,
U+00b9:^1
U+00ba:-o
U+00bb:>>
U+00bc: 1/4
U+00bd: 1/2
U+00be: 3/4
U+00bf:?
0x41 U+00c0-U+00c3
# &Auml;, not the best choice for some languages.
U+00c4:Ae
U+00c5:AA
U+00c6:AE
U+00c7:C,
0x45 U+00c8-U+00cb
0x49 U+00cc-U+00cf
U+00d0:D-
0x4e U+00d1
0x4f U+00d2-U+00d5
# &Ouml;, not the best choice for some languages.
U+00d6:Oe
U+00d7: *
U+00d8:O/
0x55 U+00d9-U+00db
# &Uuml;, not the best choice for some languages.
U+00dc:Ue
0x59 U+00dd
U+00de:TH
U+00df:ss
U+00e0:`a
0x61 U+00e1-U+00e3
# &auml;, not the best choice for some languages.
U+00e4:ae
U+00e5:aa
U+00e6:ae
U+00e7:c,
0x65 U+00e8-U+00eb
U+00ec:`i
0x69 U+00ed-U+00ef
U+00f0:d-
0x6e U+00f1
0x6f U+00f2-U+00f5
# &ouml;, not the best choice for some languages.
U+00f6:oe
U+00f7:-:
U+00f8:o/
0x75 U+00f9-U+00fb
# &uuml;, not the best choice for some languages.
U+00fc:ue
0x79 U+00fd
U+00fe:th
0x79 U+00ff
# end of latin-1 repertoire
0x41 U+0100 U+0102 U+0104 # A
0x61 U+0101 U+0103 U+0105 # a
0x43 U+0106 U+010a U+010c # C
# "Fundamento de Esperanto"
U+0108:CH
# The following line is an example for mapping several accented versions
# of small letter 'c' to 'c':
0x63 U+0107 U+010b U+010d # c
# "Fundamento de Esperanto"
U+0109:ch
0x44 U+010e
0x64 U+010f
U+0110:D/
U+0111:d/
0x45 U+0112 U+0114 U+0116 U+0118 U+011a # E
0x65 U+0113 U+0115 U+0117 U+0119 U+011b # e
0x47 U+011e U+0120 U+0122 # G
# "Fundamento de Esperanto"
U+011c:GH
0x67 U+011f U+0121 U+0123 # g
U+011d:gh
U+0124:HH
U+0125:hh
U+0126:H/
0x48 U+0127 # LATIN SMALL LETTER H BAR -> H
0x49 U+0128 U+012a U+012c U+012e U+0130 # I
0x69 U+0129 U+012b U+012d U+012f U+0131 # i
U+0132:IJ
U+0133:ij
# "Fundamento de Esperanto"
U+0134:JH
U+0135:jh
0x4b U+0136
0x6b U+0137
U+0138:kk
0x4c U+0139 U+013b U+013d # L
0x6c U+013a U+013c U+013e # l
U+013f:L.
U+0140:l.
U+0141:L/
U+0142:l/
0x4e U+0143 U+0145 U+0147 # N
0x6e U+0144 U+0146 U+0148 # n
U+0149:'n
U+014a:NG
0x4e U+014B # LATIN SMALL LETTER ENG -> N
0x4f U+014c U+014e # O
0x6f U+014d U+014f # o
U+0150:O"
U+0151:o"
U+0152:OE
U+0153:oe
0x52 U+0154 U+0156 U+0158 # R
0x72 U+0155 U+0157 U+0159 # r
# "Fundamento de Esperanto"
0x53 U+015a U+015e U+0160 # S
U+015c:SH
0x73 U+015b U+015f U+0161 # s
U+015d:sh
0x54 U+0162 U+0164 # T
0x74 U+0163 U+0165 # t
U+0166:T/
U+0167:t/
0x55 U+0168 U+016a U+016e U+0172 # U
# "Fundamento"
U+016c:U
0x75 U+0169 U+016b U+016f U+0173 # u
# "Fundamento"
U+016d:u
U+0170:U"
U+0171:u"
0x57 U+0174
0x77 U+0175
0x59 U+0176 U+0178
0x79 U+0177
0x5a U+0179 U+017b U+017d U+021d
0x7a U+017a U+017c U+017e
U+017f:s1
U+0187:C2
U+0188:c2
U+0191:F2
U+0192: f
U+0198:K2
U+0199:k2
U+01a0:O9
U+01a1:o9
U+01a2:OI
U+01a3:oi
U+01a6:yr
U+01af:U9
U+01b0:u9
U+01b5:Z/
U+01b6:z/
U+01b7:ED
0x41 U+01cd
0x61 U+01ce
0x49 U+01cf
0x69 U+01d0
0x4f U+01d1
0x6f U+01d2
0x55 U+01d3
0x75 U+01d4
U+01d5:U:-
U+01d6:u:-
U+01d7:U:'
U+01d8:u:'
U+01d9:U:<
U+01da:u:<
U+01db:U:!
U+01dc:u:!
U+01de:A1
U+01df:a1
U+01e0:A7
U+01e1:a7
U+01e2:A3
U+01e3:a3
U+01e4:G/
U+01e5:g/
0x47 U+01e6
0x67 U+01e7
0x4b U+01e8
0x6b U+01e9
0x4f U+01ea
0x6f U+01eb
U+01ec:O1
U+01ed:o1
U+01ee:EZ
U+01ef:ez
0x6a U+01f0
0x47 U+01f4
0x67 U+01f5
U+01fa:AA'
U+01fb:aa'
U+01fc:AE'
U+01fd:ae'
U+01fe:O/'
U+01ff:o/'
U+0200:A!!
U+0201:a!!
U+0202:A)
U+0203:a)
U+0204:E!!
U+0205:e!!
U+0206:E)
U+0207:e)
U+0208:I!!
U+0209:i!!
U+020a:I)
U+020b:i)
U+020c:O!!
U+020d:o!!
U+020e:O)
U+020f:o)
U+0210:R!!
U+0211:r!!
U+0212:R)
U+0213:r)
U+0214:U!!
U+0215:u!!
U+0216:U)
U+0217:u)
# IPA symbols, from
# Linkname: FAQ: Representing IPA Phonetics in ASCII
# URL: http://www.hpl.hp.com/personal/Evan_Kirshenbaum/IPA/faq.html
# (corrected in Russian Cyrillic area).
# (corrected in Greek area).
#
0x41 U+0251 # LATIN SMALL LETTER SCRIPT A -> A
U+0252:A.
U+0253:b`
0x4f U+0254 # LATIN SMALL LETTER OPEN O -> O
U+0256:d.
U+0257:d`
U+0258:@<umd>
0x40 U+0259 # LATIN SMALL LETTER SCHWA -> @
0x52 U+025A # LATIN SMALL LETTER SCHWA HOOK -> R
0x45 U+025B # LATIN SMALL LETTER EPSILON -> E
U+025c:V"
U+025d:R<umd>
U+025e:O"
0x4a U+025F # LATIN SMALL LETTER DOTLESS J BAR -> J
U+0260:g`
0x67 U+0261 # LATIN SMALL LETTER SCRIPT G
0x47 U+0262 # LATIN LETTER SMALL CAPITAL G
0x51 U+0263 # LATIN SMALL LETTER GAMMA -> Q
U+0264:o-
U+0265:j<rnd>
U+0266:h<?>
U+0268:i"
0x49 U+026A U+0269 # LATIN LETTER SMALL CAPITAL I, LATIN SMALL LETTER IOTA
0x4c U+026B # LATIN SMALL LETTER L WITH MIDDLE TILDE
0x4c U+026C # LATIN SMALL LETTER L BELT
U+026d:l.
U+026e:z<lat>
U+026f:u-
U+0270:j<vel>
0x4d U+0271 # LATIN SMALL LETTER M HOOK
U+0273:n.
U+0274:n"
U+0275:@.
U+0276:&.
0x55 U+0277 # LATIN SMALL LETTER CLOSED OMEGA -> U
0x72 U+0279 # LATIN SMALL LETTER TURNED R -> r
U+027a:*<lat>
U+027b:r.
U+027d:*.
0x2a U+027E # LATIN SMALL LETTER FISHHOOK R -> *
U+0280:r"
0x52 U+0280 # LATIN LETTER SMALL CAPITAL R -> R
U+0281:g"
U+0282:s.
0x53 U+0283 # LATIN SMALL LETTER ESH -> S
U+0284:J`
U+0287:t!
U+0288:t.
U+0289:u"
0x55 U+028A # LATIN SMALL LETTER UPSILON -> U
U+028b:r<lbd>
0x56 U+028C # LATIN SMALL LETTER TURNED V -> V
U+028d:w<vls>
U+028e:l^
U+028f:I.
U+0290:z.
U+0292:Z
0x3f U+0294 # LATIN SMALL LETTER GLOTTAL STOP -> ?
U+0295:H<vcd>
U+0296:l!
U+0297:c!
U+0298:p!
U+0299:b<trl>
U+029b:G`
0x6a U+029d # LATIN SMALL LETTER CROSSED-TAIL J
U+029e:k!
0x4c U+029F # LATIN LETTER SMALL CAPITAL L
U+02a0:q`
U+02a4:d3
U+02a6:ts
U+02a7:tS
U+02b0:<h>
U+02b1:<?>
0x3b U+02b2 U+0321
U+02b3:<r>
U+02b7:<w>
U+02bb:;S
0x60 U+02bc
U+02c6:^
U+02c7:'<
U+02c8:|
U+02c9:1-
U+02cb:1!
0x3a U+02d0
U+02d1::\\
0x2b U+02d6
0x2d U+02d7
U+02d8:'(
U+02d9:'.
U+02da:'0
U+02db:';
U+02dc:~
U+02dd:'"
U+02e5:_T
U+02e6:_H
U+02e7:_M
U+02e8:_L
U+02e9:_B
U+02ec:_v
U+02ee:''
0x60 U+0300
0x27 U+0301
0x5e U+0302
0x7e U+0303 U+0334
U+030b:''
0x7c U+030d
U+030e:||
U+030f:``
0x2e U+0322 U+0323
U+0324:<?>
U+0325:<o>
0x2c U+0326 U+0327
0x2d U+0329
0x5b U+032a
U+032b:<w>
U+0334:<H>
0x2f U+0337 U+0338
U+0340:`
U+0341:'
U+0342:~
U+0344:'%
U+0345:j3
U+0347:=
U+0360:~~
U+0374:'
U+0375:,
U+037a:j3
U+037e:?%
U+0384:'*
U+0385:'%
# Greek letters
U+0386:A'
U+0387:.*
U+0388:E'
U+0389:Y%
U+038a:I'
U+038c:O'
U+038e:U%
U+038f:W%
U+0390:i3
U+0391:A
U+0392:B
U+0393:G
U+0394:D
U+0395:E
U+0396:Z
U+0397:Y
U+0398:TH
U+0399:I
U+039a:K
U+039b:L
U+039c:M
U+039d:N
U+039e:C
U+039f:O
U+03a0:P
U+03a1:R
U+03a3:S
U+03a4:T
U+03a5:U
U+03a6:F
U+03a7:X
U+03a8:Q
U+03a9:W*
U+03aa:J
U+03ab:V*
U+03ac:a'
U+03ad:e'
U+03ae:y%
U+03af:i'
U+03b0:u3
U+03b1:a
U+03b2:b
U+03b3:g
U+03b4:d
U+03b5:e
U+03b6:z
U+03b7:y
U+03b8:th
U+03b9:i
U+03ba:k
U+03bb:l
U+03bc:m
U+03bd:n
U+03be:c
U+03bf:o
U+03c0:p
U+03c1:r
U+03c2:*s
U+03c3:s
U+03c4:t
U+03c5:u
U+03c6:f
U+03c7:x
U+03c8:q
U+03c9:w
U+03ca:j
U+03cb:v*
U+03cc:o'
U+03cd:u%
U+03ce:w%
# Greek symbols
U+03d0:beta
U+03d1:theta
U+03d2:upsi
U+03d5:phi
U+03d6:pi
U+03d7:k.
U+03da:T3
U+03db:t3
U+03dc:M3
U+03dd:m3
U+03de:K3
U+03df:k3
U+03e0:P3
U+03e1:p3
U+03f0:kappa
U+03f1:rho
U+03f3:J
U+03f4:'%
U+03f5:j3
# Cyrillic capital letters
U+0402:D%
U+0403:G%
U+0404:IE
U+0405:DS
U+0406:II
U+0407:YI
U+0408:J%
U+0409:LJ
U+040a:NJ
U+040b:Ts
U+040c:KJ
U+040e:V%
U+040f:DZ
# Russian Cyrillic letters, transliterated
U+0401:IO
U+0410:A
U+0411:B
U+0412:V
U+0413:G
U+0414:D
U+0415:E
U+0416:ZH
U+0417:Z
U+0418:I
U+0419:J
U+041a:K
U+041b:L
U+041c:M
U+041d:N
U+041e:O
U+041f:P
U+0420:R
U+0421:S
U+0422:T
U+0423:U
U+0424:F
U+0425:H
U+0426:C
U+0427:CH
U+0428:SH
U+0429:SCH
U+042a:"
U+042b:Y
U+042c:'
U+042d:`E
U+042e:YU
U+042f:YA
U+0430:a
U+0431:b
U+0432:v
U+0433:g
U+0434:d
U+0435:e
U+0436:zh
U+0437:z
U+0438:i
U+0439:j
U+043a:k
U+043b:l
U+043c:m
U+043d:n
U+043e:o
U+043f:p
U+0440:r
U+0441:s
U+0442:t
U+0443:u
U+0444:f
U+0445:h
U+0446:c
U+0447:ch
U+0448:sh
U+0449:sch
U+044a:"
U+044b:y
U+044c:'
U+044d:`e
U+044e:yu
U+044f:ya
U+0451:io
# end of Russian Cyrillic letters.
# Cyrillic small letters (and some archaic)
U+0452:d%
U+0453:g%
U+0454:ie
U+0455:ds
U+0456:ii
U+0457:yi
U+0458:j%
U+0459:lj
U+045a:nj
U+045b:ts
U+045c:kj
U+045e:v%
U+045f:dz
U+0462:Y3
U+0463:y3
U+046a:O3
U+046b:o3
U+0472:F3
U+0473:f3
U+0474:V3
U+0475:v3
U+0480:C3
U+0481:c3
U+0490:G3
U+0491:g3
U+04d4:AE
U+04d5:ae
# These may make Yiddish slightly more readable, until we have
# something better.
0x69 U+05b4 # i
0x61 U+05b7 # a
0x6f U+05b8 # o
0x75 U+05bc # u
0x68 U+05bf # h
0x3a U+05c2 # :
0x76 U+05f0 # v
U+05f1:oy
U+05f2:ey
# U+05d0:A+
0x23 U+05d0 # '#'
U+05d1:B+
U+05d2:G+
U+05d3:D+
U+05d4:H+
U+05d5:W+
U+05d6:Z+
U+05d7:X+
U+05d8:Tj
U+05d9:J+
U+05da:K%
U+05db:K+
U+05dc:L+
U+05dd:M%
U+05de:M+
U+05df:N%
U+05e0:N+
U+05e1:S+
U+05e2:E+
U+05e3:P%
U+05e4:P+
U+05e5:Zj
U+05e6:ZJ
U+05e7:Q+
U+05e8:R+
U+05e9:Sh
U+05ea:T+
U+060c:,+
U+061b:;+
U+061f:?+
U+0621:H'
U+0622:aM
U+0623:aH
U+0624:wH
U+0625:ah
U+0626:yH
U+0627:a+
U+0628:b+
U+0629:tm
U+062a:t+
U+062b:tk
U+062c:g+
U+062d:hk
U+062e:x+
U+062f:d+
U+0630:dk
U+0631:r+
U+0632:z+
U+0633:s+
U+0634:sn
U+0635:c+
U+0636:dd
U+0637:tj
U+0638:zH
U+0639:e+
U+063a:i+
U+0640:++
U+0641:f+
U+0642:q+
U+0643:k+
U+0644:l+
U+0645:m+
U+0646:n+
U+0647:h+
U+0648:w+
U+0649:j+
U+064a:y+
U+064b::+
U+064c:"+
U+064d:=+
U+064e:/+
U+064f:'+
U+0650:1+
U+0651:3+
U+0652:0+
U+0660:0a
U+0661:1a
U+0662:2a
U+0663:3a
U+0664:4a
U+0665:5a
U+0666:6a
U+0667:7a
U+0668:8a
U+0669:9a
U+0670:aS
U+067e:p+
U+0681:hH
U+0686:tc
U+0698:zj
U+06a4:v+
U+06af:gf
U+06f0:0a
U+06f1:1a
U+06f2:2a
U+06f3:3a
U+06f4:4a
U+06f5:5a
U+06f6:6a
U+06f7:7a
U+06f8:8a
U+06f9:9a
# Replacement strings for Ethiopic characters
U+1200:he
U+1201:hu
U+1202:hi
U+1203:ha
U+1204:hE
0x68 U+1205 #:h
U+1206:ho
U+1208:le
U+1209:lu
U+120A:li
U+120B:la
U+120C:lE
0x6c U+120D #:l
U+120E:lo
U+120F:lWa
U+1210:He
U+1211:Hu
U+1212:Hi
U+1213:Ha
U+1214:HE
0x48 U+1215 #:H
U+1216:Ho
U+1217:HWa
U+1218:me
U+1219:mu
U+121A:mi
U+121B:ma
U+121C:mE
0x6d U+121D #:m
U+121E:mo
U+121F:mWa
U+1220:`se
U+1221:`su
U+1222:`si
U+1223:`sa
U+1224:`sE
U+1225:`s
U+1226:`so
U+1227:`sWa
U+1228:re
U+1229:ru
U+122A:ri
U+122B:ra
U+122C:rE
0x72 U+122D #:r
U+122E:ro
U+122F:rWa
U+1230:se
U+1231:su
U+1232:si
U+1233:sa
U+1234:sE
0x73 U+1235 #:s
U+1236:so
U+1237:sWa
U+1238:xe
U+1239:xu
U+123A:xi
U+123B:xa
U+123C:xE
U+123D:xa
U+123E:xo
U+123F:xWa
U+1240:qe
U+1241:qu
U+1242:qi
U+1243:qa
U+1244:qE
0x71 U+1245 #:q
U+1246:qo
U+1248:qWe
U+124A:qWi
U+124B:qWa
U+124C:qWE
U+124D:qW
U+1250:Qe
U+1251:Qu
U+1252:Qi
U+1253:Qa
U+1254:QE
0x51 U+1255 #:Q
U+1256:Qo
U+1258:QWe
U+125A:QWi
U+125B:QWa
U+125C:QWE
U+125D:QW
U+1260:be
U+1261:bu
U+1262:bi
U+1263:ba
U+1264:bE
0x62 U+1265 #:b
U+1266:bo
U+1267:bWa
U+1268:ve
U+1269:vu
U+126A:vi
U+126B:va
U+126C:vE
0x76 U+126D #:v
U+126E:vo
U+126F:vWa
U+1270:te
U+1271:tu
U+1272:ti
U+1273:ta
U+1274:tE
0x74 U+1275 #:t
U+1276:to
U+1277:tWa
U+1278:ce
U+1279:cu
U+127A:ci
U+127B:ca
U+127C:cE
0x63 U+127D #:c
U+127E:co
U+127F:cWa
U+1280:`he
U+1281:`hu
U+1282:`hi
U+1283:`ha
U+1284:`hE
U+1285:`h
U+1286:`ho
U+1288:hWe
U+128A:hWi
U+128B:hWa
U+128C:hWE
U+128D:hW
U+1290:na
U+1291:nu
U+1292:ni
U+1293:na
U+1294:nE
0x6e U+1295 #:n
U+1296:no
U+1297:nWa
U+1298:Ne
U+1299:Nu
U+129A:Ni
U+129B:Na
U+129C:NE
0x4e U+129D #:N
U+129E:No
U+129F:NWa
0x65 U+12A0 #:e
0x75 U+12A1 #:u
0x69 U+12A2 #:i
0x61 U+12A3 #:a
0x45 U+12A4 #:E
0x49 U+12A5 #:I
0x6f U+12A6 #:o
U+12A7:e3
U+12A8:ke
U+12A9:ku
U+12AA:ki
U+12AB:ka
U+12AC:kE
0x6b U+12AD #:k
U+12AE:ko
U+12B0:kWe
U+12B2:kWi
U+12B3:kWa
U+12B4:kWE
U+12B5:kW
U+12B8:Ke
U+12B9:Ku
U+12BA:Ki
U+12BB:Ka
U+12BC:KE
0x4b U+12BD #:K
U+12BE:Ko
U+12C0:KWe
U+12C2:KWi
U+12C3:KWa
U+12C4:KWE
U+12C5:KW
U+12C8:we
U+12C9:wu
U+12CA:wi
U+12CB:wa
U+12CC:wE
0x77 U+12CD #:w
U+12CE:wo
U+12D0:`e
U+12D1:`u
U+12D2:`i
U+12D3:`a
U+12D4:`E
U+12D5:`I
U+12D6:`o
U+12D8:ze
U+12D9:zu
U+12DA:zi
U+12DB:za
U+12DC:zE
0x7a U+12DD #:z
U+12DE:zo
U+12DF:zWa
U+12E0:Ze
U+12E1:Zu
U+12E2:Zi
U+12E3:Za
U+12E4:ZE
0x5a U+12E5 #:Z
U+12E6:Zo
U+12E7:ZWa
U+12E8:ye
U+12E9:yu
U+12EA:yi
U+12EB:ya
U+12EC:yE
0x79 U+12ED #:y
U+12EE:yo
U+12EF:yWa
U+12F0:de
U+12F1:du
U+12F2:di
U+12F3:da
U+12F4:dE
0x64 U+12F5 #:d
U+12F6:do
U+12F7:dWa
U+12F8:De
U+12F9:Du
U+12FA:Di
U+12FB:Da
U+12FC:DE
0x44 U+12FD #:D
U+12FE:Do
U+12FF:DWa
U+1300:je
U+1301:ju
U+1302:ji
U+1303:ja
U+1304:jE
0x6a U+1305 #:j
U+1306:jo
U+1307:jWa
U+1308:ga
U+1309:gu
U+130A:gi
U+130B:ga
U+130C:gE
0x67 U+130D #:g
U+130E:go
U+1310:gWu
U+1312:gWi
U+1313:gWa
U+1314:gWE
U+1315:gW
U+1318:Ge
U+1319:Gu
U+131A:Gi
U+131B:Ga
U+131C:GE
0x47 U+131D #:G
U+131E:Go
U+131F:GWa
U+1320:Te
U+1321:Tu
U+1322:Ti
U+1323:Ta
U+1324:TE
0x54 U+1325 #:T
U+1326:To
U+1327:TWa
U+1328:Ce
U+1329:Ca
U+132A:Cu
U+132B:Ca
U+132C:CE
0x43 U+132D #:C
U+132E:Co
U+132F:CWa
U+1330:Pe
U+1331:Pu
U+1332:Pi
U+1333:Pa
U+1334:PE
0x50 U+1335 #:P
U+1336:Po
U+1337:PWa
U+1338:SWe
U+1339:SWu
U+133A:SWi
U+133B:SWa
U+133C:SWE
U+133D:SW
U+133E:SWo
U+133F:SWa
U+1340:`Sa
U+1341:`Su
U+1342:`Si
U+1343:`Sa
U+1344:`SE
U+1345:`S
U+1346:`So
U+1348:fa
U+1349:fu
U+134A:fi
U+134B:fa
U+134C:fE
0x6f U+134D #:f
U+134E:fo
U+134F:fWa
U+1350:pe
U+1351:pu
U+1352:pi
U+1353:pa
U+1354:pE
0x70 U+1355 #:p
U+1356:po
U+1357:pWa
U+1358:mYa
U+1359:rYa
U+135A:fYa
# ETHIOPIC SPACE U+1360 mapped to ASCII space
0x20 U+1360
0x3a U+1361 #::
U+1362:::
0x2c U+1363 #:,
U+1364:;
U+1365:-:
U+1366::-
U+1367:`?
U+1368::|:
U+1369:`1
U+136A:`2
U+136B:`3
U+136C:`4
U+136D:`5
U+136E:`6
U+136F:`7
U+1370:`8
U+1371:`9
U+1372:`10
U+1373:`20
U+1374:`30
U+1375:`40
U+1376:`50
U+1377:`60
U+1378:`70
U+1379:`80
U+137A:`90
U+137B:`100
U+137C:`10000
U+1e00:A-0
U+1e01:a-0
U+1e02:B.
U+1e03:b.
U+1e04:B-.
U+1e05:b-.
U+1e06:B_
U+1e07:b_
U+1e08:C,'
U+1e09:c,'
U+1e0a:D.
U+1e0b:d.
U+1e0c:D-.
U+1e0d:d-.
U+1e0e:D_
U+1e0f:d_
U+1e10:D,
U+1e11:d,
U+1e12:D->
U+1e13:d->
U+1e14:E-!
U+1e15:e-!
U+1e16:E-'
U+1e17:e-'
U+1e18:E->
U+1e19:e->
U+1e1a:E-?
U+1e1b:e-?
U+1e1c:E,(
U+1e1d:e,(
U+1e1e:F.
U+1e1f:f.
U+1e20:G-
U+1e21:g-
U+1e22:H.
U+1e23:h.
U+1e24:H-.
U+1e25:h-.
U+1e26:H:
U+1e27:h:
U+1e28:H,
U+1e29:h,
U+1e2a:H-(
U+1e2b:h-(
U+1e2c:I-?
U+1e2d:i-?
U+1e2e:I:'
U+1e2f:i:'
U+1e30:K'
U+1e31:k'
U+1e32:K-.
U+1e33:k-.
U+1e34:K_
U+1e35:k_
U+1e36:L-.
U+1e37:l-.
U+1e38:L--.
U+1e39:l--.
U+1e3a:L_
U+1e3b:l_
U+1e3c:L->
U+1e3d:l->
U+1e3e:M'
U+1e3f:m'
U+1e40:M.
U+1e41:m.
U+1e42:M-.
U+1e43:m-.
U+1e44:N.
U+1e45:n.
U+1e46:N-.
U+1e47:n-.
U+1e48:N_
U+1e49:n_
U+1e4a:N->
U+1e4b:n->
U+1e4c:O?'
U+1e4d:o?'
U+1e4e:O?:
U+1e4f:o?:
U+1e50:O-!
U+1e51:o-!
U+1e52:O-'
U+1e53:o-'
U+1e54:P'
U+1e55:p'
U+1e56:P.
U+1e57:p.
U+1e58:R.
U+1e59:r.
U+1e5a:R-.
U+1e5b:r-.
U+1e5c:R--.
U+1e5d:r--.
U+1e5e:R_
U+1e5f:r_
U+1e60:S.
U+1e61:s.
U+1e62:S-.
U+1e63:s-.
U+1e64:S'.
U+1e65:s'.
U+1e66:S<.
U+1e67:s<.
U+1e68:S.-.
U+1e69:s.-.
U+1e6a:T.
U+1e6b:t.
U+1e6c:T-.
U+1e6d:t-.
U+1e6e:T_
U+1e6f:t_
U+1e70:T->
U+1e71:t->
U+1e72:U--:
U+1e73:u--:
U+1e74:U-?
U+1e75:u-?
U+1e76:U->
U+1e77:u->
U+1e78:U?'
U+1e79:u?'
U+1e7a:U-:
U+1e7b:u-:
U+1e7c:V?
U+1e7d:v?
U+1e7e:V-.
U+1e7f:v-.
U+1e80:W!
U+1e81:w!
U+1e82:W'
U+1e83:w'
U+1e84:W:
U+1e85:w:
U+1e86:W.
U+1e87:w.
U+1e88:W-.
U+1e89:w-.
U+1e8a:X.
U+1e8b:x.
U+1e8c:X:
U+1e8d:x:
U+1e8e:Y.
U+1e8f:y.
U+1e90:Z>
U+1e91:z>
U+1e92:Z-.
U+1e93:z-.
U+1e94:Z_
U+1e95:z_
U+1e96:h_
U+1e97:t:
U+1e98:w0
U+1e99:y0
U+1ea0:A-.
U+1ea1:a-.
U+1ea2:A2
U+1ea3:a2
U+1ea4:A>'
U+1ea5:a>'
U+1ea6:A>!
U+1ea7:a>!
U+1ea8:A>2
U+1ea9:a>2
U+1eaa:A>?
U+1eab:a>?
U+1eac:A>-.
U+1ead:a>-.
U+1eae:A('
U+1eaf:a('
U+1eb0:A(!
U+1eb1:a(!
U+1eb2:A(2
U+1eb3:a(2
U+1eb4:A(?
U+1eb5:a(?
U+1eb6:A(-.
U+1eb7:a(-.
U+1eb8:E-.
U+1eb9:e-.
U+1eba:E2
U+1ebb:e2
U+1ebc:E?
U+1ebd:e?
U+1ebe:E>'
U+1ebf:e>'
U+1ec0:E>!
U+1ec1:e>!
U+1ec2:E>2
U+1ec3:e>2
U+1ec4:E>?
U+1ec5:e>?
U+1ec6:E>-.
U+1ec7:e>-.
U+1ec8:I2
U+1ec9:i2
U+1eca:I-.
U+1ecb:i-.
U+1ecc:O-.
U+1ecd:o-.
U+1ece:O2
U+1ecf:o2
U+1ed0:O>'
U+1ed1:o>'
U+1ed2:O>!
U+1ed3:o>!
U+1ed4:O>2
U+1ed5:o>2
U+1ed6:O>?
U+1ed7:o>?
U+1ed8:O>-.
U+1ed9:o>-.
U+1eda:O9'
U+1edb:o9'
U+1edc:O9!
U+1edd:o9!
U+1ede:O92
U+1edf:o92
U+1ee0:O9?
U+1ee1:o9?
U+1ee2:O9-.
U+1ee3:o9-.
U+1ee4:U-.
U+1ee5:u-.
U+1ee6:U2
U+1ee7:u2
U+1ee8:U9'
U+1ee9:u9'
U+1eea:U9!
U+1eeb:u9!
U+1eec:U92
U+1eed:u92
U+1eee:U9?
U+1eef:u9?
U+1ef0:U9-.
U+1ef1:u9-.
U+1ef2:Y!
U+1ef3:y!
U+1ef4:Y-.
U+1ef5:y-.
U+1ef6:Y2
U+1ef7:y2
U+1ef8:Y?
U+1ef9:y?
0x61 U+1f00
U+1f01:ha
U+1f02:`a
U+1f03:h`a
U+1f04:a'
U+1f05:ha'
U+1f06:a~
U+1f07:ha~
0x41 U+1f08
U+1f09:hA
U+1f0a:`A
U+1f0b:h`A
U+1f0c:A'
U+1f0d:hA'
U+1f0e:A~
U+1f0f:hA~
U+1f11:he
U+1f19:hE
U+1f31:hi
U+1f39:hI
U+1f41:ho
U+1f49:hO
U+1f51:hu
U+1f59:hU
U+1fbf:,,
U+1fc0:?*
U+1fc1:?:
U+1fcd:,!
U+1fce:,'
U+1fcf:?,
U+1fdd:;!
U+1fde:;'
U+1fdf:?;
U+1fe5:rh
U+1fec:Rh
U+1fed:!:
U+1fef:!*
U+1ffe:;;
# General punctuation:
0x20 U+2000 U+2002 U+2004-U+2009 # spaces
U+2001:
U+2003:
U+200e:(->)
U+200f:(<-)
U+200a:
0x2d U+2010 U+2011 U+2013 U+2015 # hyphen-like
U+2014:--
U+2016:||
U+2017:=2
0x60 U+2018 # left single quotation mark <`>
0x27 U+2019-U+201b # various single quotation marks <'>
0x22 U+201c-U+201f # various double quotation marks <">
U+2020:/-
U+2021:/=
U+2022: o
0x2e U+2024
U+2025:..
U+2026:...
U+2027:.
U+2028:\015
U+2029:\015\012
# Dont wanna see these:
# POP DIRECTIONAL FORMATTING 202C
U+202c:
# LEFT-TO-RIGHT OVERRIDE 202D
U+202d:
U+202f:
U+2030: 0/00
U+2032:'
U+2033:''
U+2034:'''
U+2035:`
U+2036:``
U+2037:```
U+2038:Ca
U+2039:<
U+203a:>
U+203b::X
U+203c:!!
U+203e:'-
0x2d U+2043 # HYPHEN BULLET ?
U+2044:/
U+2048:?!
U+2049:!?
# end of General punctuation.
U+2070:^0
U+2074:^4
U+2075:^5
U+2076:^6
U+2077:^7
U+2078:^8
U+2079:^9
U+207a:^+
U+207b:^-
U+207c:^=
U+207d:^(
U+207e:^)
U+207f:^n
U+2080:_0
U+2081:_1
U+2082:_2
U+2083:_3
U+2084:_4
U+2085:_5
U+2086:_6
U+2087:_7
U+2088:_8
U+2089:_9
U+208a:_+
U+208b:_-
U+208c:_=
U+208d:(
U+208e:)
# Old euro currency sign glyph:
#U+20A0:CE
U+20a3:Ff
U+20a4:Li
U+20a7:Pt
U+20a9:W=
# New euro currency sign glyph:
U+20AC:EUR
U+2100:a/c
U+2101:a/s
U+2103:oC
U+2105:c/o
U+2106:c/u
U+2109:oF
0x67 U+210a
0x68 U+210e
U+210f:"hbar
U+2111:Im
U+2113:l
U+2116:No.
U+2117:PO
U+2118:P
U+211C:Re
U+211e:Rx
U+2120:(SM)
U+2121:TEL
# TRADE MARK SIGN:
U+2122:(TM)
U+2126:Ohm
0x4b U+212A # Kelvin sign - K
U+212b:Ang.
U+212E:est.
0x6f U+2134
U+2135:Aleph
U+2136:Bet
U+2137:Gimel
U+2138:Dalet
U+2153: 1/3
U+2154: 2/3
U+2155: 1/5
U+2156: 2/5
U+2157: 3/5
U+2158: 4/5
U+2159: 1/6
U+215a: 5/6
U+215b: 1/8
U+215c: 3/8
U+215d: 5/8
U+215e: 7/8
U+215f: 1/
U+2160:I
U+2161:II
U+2162:III
U+2163:IV
U+2164:V
U+2165:VI
U+2166:VII
U+2167:VIII
U+2168:IX
U+2169:X
U+216a:XI
U+216b:XII
U+216c:L
U+216d:C
U+216e:D
U+216f:M
U+2170:i
U+2171:ii
U+2172:iii
U+2173:iv
U+2174:v
U+2175:vi
U+2176:vii
U+2177:viii
U+2178:ix
U+2179:x
U+217a:xi
U+217b:xii
U+217c:l
U+217d:c
U+217e:d
U+217f:m
U+2180:1000RCD
U+2181:5000R
U+2182:10000R
U+2190:<-
U+2191:-^
U+2192:->
U+2193:-v
U+2194:<->
U+2195:UD
U+2196:<!!
U+2197://>
U+2198:!!>
U+2199:<//
U+21a8:UD-
U+21B5:RET
U+21c0:>V
U+21d0:<=
U+21d1:^^
U+21d2:=>
U+21d3:vv
U+21d4:<=>
U+2200:FA
U+2202:\partial
U+2203:TE
U+2205:{}
U+2206:Delta
U+2207:Nabla
U+2208:(-
U+2209:!(-
U+220a:(-
U+220b:-)
U+220c:!-)
U+220d:-)
U+220e: qed
U+220f:\prod
U+2211:\sum
U+2212: -
U+2213:-/+
U+2214:.+
0x2f U+2215
U+2216: -
U+2217:*
U+2218:Ob
U+2219:sb
U+221a: SQRT
U+221b: ROOT3
U+221c: ROOT4
U+221d:0(
U+221e:infty
U+221f:-L
U+2220:-V
U+2225:PP
U+2226: !PP
U+2227:AND
U+2228:OR
U+2229:(U
U+222a:)U
U+222b:"int
U+222c:DI
U+222e:Io
U+2234:.:
U+2235::.
U+2236::R
U+2237:::
U+223c:?1
U+223e:CG
U+2243:?-
U+2245:?=
# ALMOST EQUAL TO:
U+2248:~=
U+2249: !~=
U+224c:=?
U+2253:HI
U+2254::=
U+2255:=:
U+2260:!=
U+2261:=3
U+2262: !=3
U+2264:=<
U+2265:>=
U+2266:.LE.
U+2267:.GE.
U+2268:.LT.NOT.EQ.
U+2269:.GT.NOT.EQ.
U+226a:<<
U+226b:>>
U+226e:!<
U+226f:!>
U+2276: <>
U+2277: ><
U+2282:(C
U+2283:)C
U+2284: !(C
U+2285: !)C
U+2286:(_
U+2287:)_
U+2295:(+)
U+2296:(-)
U+2297:(x)
U+2298:(/)
U+2299:(.)
U+229A:(o)
U+229B:(*)
U+229C:(=)
U+229D:(-)
U+229E:[+]
U+229F:[-]
U+22A0:[x]
U+22A1:[.]
U+22a5:-T
U+22A7: MODELS
U+22A8: TRUE
U+22A9: FORCES
U+22AC: !PROVES
U+22AD: NOT TRUE
U+22AE: !FORCES
U+22B2: NORMAL SUBGROUP OF
U+22B3: CONTAINS AS NORMAL SUBGROUP
U+22B4: NORMAL SUBGROUP OF OR EQUAL TO
U+22B5: CONTAINS AS NORMAL SUBGROUP OR EQUAL TO
U+22B8: MULTIMAP
U+22BA: INTERCALATE
U+22BB: XOR
U+22BC: NAND
U+22C5: DOT
U+22d6:<.
U+22d7:>.
U+22d8:<<<
U+22d9:>>>
U+22ee::3
U+22ef:.3
U+2302:Eh
U+2307:~~
U+2308:<7
U+2309:>7
U+230a:7<
U+230b:7>
U+2310:NI
U+2312:(A
U+2315:TR
U+2318:88
U+2320:Iu
U+2321:Il
U+2322::(
U+2323::)
U+2324:|^|
U+2327:[X]
U+2329:</
U+232a:/>
U+2423:Vs
U+2440:1h
U+2441:3h
U+2442:2h
U+2443:4h
U+2446:1j
U+2447:2j
U+2448:3j
U+2449:4j
U+2460:1-o
U+2461:2-o
U+2462:3-o
U+2463:4-o
U+2464:5-o
U+2465:6-o
U+2466:7-o
U+2467:8-o
U+2468:9-o
U+2469:10-o
U+246a:11-o
U+246b:12-o
U+246c:13-o
U+246d:14-o
U+246e:15-o
U+246f:16-o
U+2470:17-o
U+2471:18-o
U+2472:19-o
U+2473:20-o
U+2474:(1)
U+2475:(2)
U+2476:(3)
U+2477:(4)
U+2478:(5)
U+2479:(6)
U+247a:(7)
U+247b:(8)
U+247c:(9)
U+247d:(10)
U+247e:(11)
U+247f:(12)
U+2480:(13)
U+2481:(14)
U+2482:(15)
U+2483:(16)
U+2484:(17)
U+2485:(18)
U+2486:(19)
U+2487:(20)
U+2488:1.
U+2489:2.
U+248a:3.
U+248b:4.
U+248c:5.
U+248d:6.
U+248e:7.
U+248f:8.
U+2490:9.
U+2491:10.
U+2492:11.
U+2493:12.
U+2494:13.
U+2495:14.
U+2496:15.
U+2497:16.
U+2498:17.
U+2499:18.
U+249a:19.
U+249b:20.
U+249c:(a)
U+249d:(b)
U+249e:(c)
U+249f:(d)
U+24a0:(e)
U+24a1:(f)
U+24a2:(g)
U+24a3:(h)
U+24a4:(i)
U+24a5:(j)
U+24a6:(k)
U+24a7:(l)
U+24a8:(m)
U+24a9:(n)
U+24aa:(o)
U+24ab:(p)
U+24ac:(q)
U+24ad:(r)
U+24ae:(s)
U+24af:(t)
U+24b0:(u)
U+24b1:(v)
U+24b2:(w)
U+24b3:(x)
U+24b4:(y)
U+24b5:(z)
U+24b6:A-o
U+24b7:B-o
U+24b8:C-o
U+24b9:D-o
U+24ba:E-o
U+24bb:F-o
U+24bc:G-o
U+24bd:H-o
U+24be:I-o
U+24bf:J-o
U+24c0:K-o
U+24c1:L-o
U+24c2:M-o
U+24c3:N-o
U+24c4:O-o
U+24c5:P-o
U+24c6:Q-o
U+24c7:R-o
U+24c8:S-o
U+24c9:T-o
U+24ca:U-o
U+24cb:V-o
U+24cc:W-o
U+24cd:X-o
U+24ce:Y-o
U+24cf:Z-o
U+24d0:a-o
U+24d1:b-o
U+24d2:c-o
U+24d3:d-o
U+24d4:e-o
U+24d5:f-o
U+24d6:g-o
U+24d7:h-o
U+24d8:i-o
U+24d9:j-o
U+24da:k-o
U+24db:l-o
U+24dc:m-o
U+24dd:n-o
U+24de:o-o
U+24df:p-o
U+24e0:q-o
U+24e1:r-o
U+24e2:s-o
U+24e3:t-o
U+24e4:u-o
U+24e5:v-o
U+24e6:w-o
U+24e7:x-o
U+24e8:y-o
U+24e9:z-o
U+24ea:0-o
U+2500:-
U+2501:=
U+2502:|
U+2503:|
U+2504:-
U+2505:=
U+2506:|
U+2507:|
U+2508:-
U+2509:=
U+250a:|
U+250b:|
0x2b U+250c-U+256c # box drawings, use +
U+2571:/
U+2572:\
U+2580:TB
U+2584:LB
U+2588:FB
U+258c:lB
U+2590:RB
U+2591:.S
U+2592::S
U+2593:?S
U+25a0:fS
U+25a1:OS
U+25a2:RO
U+25a3:Rr
U+25a4:RF
U+25a5:RY
U+25a6:RH
U+25a7:RZ
U+25a8:RK
U+25a9:RX
U+25aa:sB
U+25ac:SR
U+25ad:Or
U+25b2:^
U+25b3:uT
U+25b6:|>
U+25b7:Tr
U+25ba:|>
U+25bc:v
U+25bd:dT
U+25c0:<|
U+25c1:Tl
U+25c4:<|
U+25c6:Db
U+25c7:Dw
U+25ca:LZ
U+25cb:0m
U+25ce:0o
U+25cf:0M
U+25d0:0L
U+25d1:0R
U+25d8:Sn
U+25d9:Ic
U+25e2:Fd
U+25e3:Bd
U+25ef:Ci
U+2605:*2
U+2606:*1
U+260e:TEL
U+260f:tel
U+261c:<--
U+261e:-->
U+2621:CAUTION
U+2627:XP
U+2639::-(
U+263a::-)
U+263b:(-:
U+263c:SU
U+2640:f.
U+2642:m.
U+2660:cS
U+2661:cH
U+2662:cD
U+2663:cC
U+2664:cS-
U+2665:cH-
U+2666:cD-
U+2667:cC-
U+2669:Md
U+266a:M8
U+266b:M2
U+266c:M16
U+266d:b
U+266e:Mx
U+266f:#
0x58 U+2713 U+2717 # check marks -> x
U+2720:-X
# CJK area:
0x20 U+3000 # ideographic space
U+3001:,_
U+3002:._
U+3003:+"
U+3004:JIS
U+3005:*_
U+3006:;_
U+3007:0_
U+300a:<+
U+300b:>+
U+300c:<'
U+300d:>'
U+300e:<"
U+300f:>"
U+3010:("
U+3011:)"
U+3012:=T
U+3013:=_
U+3014:('
U+3015:)'
U+3016:(I
U+3017:)I
U+301a:[[
U+301b:]]
U+301c:-?
U+3020:=T:)
0x20 U+303f
U+3041:A5
U+3042:a5
U+3043:I5
U+3044:i5
U+3045:U5
U+3046:u5
U+3047:E5
U+3048:e5
U+3049:O5
U+304a:o5
U+304b:ka
U+304c:ga
U+304d:ki
U+304e:gi
U+304f:ku
U+3050:gu
U+3051:ke
U+3052:ge
U+3053:ko
U+3054:go
U+3055:sa
U+3056:za
U+3057:si
U+3058:zi
U+3059:su
U+305a:zu
U+305b:se
U+305c:ze
U+305d:so
U+305e:zo
U+305f:ta
U+3060:da
U+3061:ti
U+3062:di
U+3063:tU
U+3064:tu
U+3065:du
U+3066:te
U+3067:de
U+3068:to
U+3069:do
U+306a:na
U+306b:ni
U+306c:nu
U+306d:ne
U+306e:no
U+306f:ha
U+3070:ba
U+3071:pa
U+3072:hi
U+3073:bi
U+3074:pi
U+3075:hu
U+3076:bu
U+3077:pu
U+3078:he
U+3079:be
U+307a:pe
U+307b:ho
U+307c:bo
U+307d:po
U+307e:ma
U+307f:mi
U+3080:mu
U+3081:me
U+3082:mo
U+3083:yA
U+3084:ya
U+3085:yU
U+3086:yu
U+3087:yO
U+3088:yo
U+3089:ra
U+308a:ri
U+308b:ru
U+308c:re
U+308d:ro
U+308e:wA
U+308f:wa
U+3090:wi
U+3091:we
U+3092:wo
U+3093:n5
U+3094:vu
U+309b:"5
U+309c:05
U+309d:*5
U+309e:+5
U+30a1:a6
U+30a2:A6
U+30a3:i6
U+30a4:I6
U+30a5:u6
U+30a6:U6
U+30a7:e6
U+30a8:E6
U+30a9:o6
U+30aa:O6
U+30ab:Ka
U+30ac:Ga
U+30ad:Ki
U+30ae:Gi
U+30af:Ku
U+30b0:Gu
U+30b1:Ke
U+30b2:Ge
U+30b3:Ko
U+30b4:Go
U+30b5:Sa
U+30b6:Za
U+30b7:Si
U+30b8:Zi
U+30b9:Su
U+30ba:Zu
U+30bb:Se
U+30bc:Ze
U+30bd:So
U+30be:Zo
U+30bf:Ta
U+30c0:Da
U+30c1:Ti
U+30c2:Di
U+30c3:TU
U+30c4:Tu
U+30c5:Du
U+30c6:Te
U+30c7:De
U+30c8:To
U+30c9:Do
U+30ca:Na
U+30cb:Ni
U+30cc:Nu
U+30cd:Ne
U+30ce:No
U+30cf:Ha
U+30d0:Ba
U+30d1:Pa
U+30d2:Hi
U+30d3:Bi
U+30d4:Pi
U+30d5:Hu
U+30d6:Bu
U+30d7:Pu
U+30d8:He
U+30d9:Be
U+30da:Pe
U+30db:Ho
U+30dc:Bo
U+30dd:Po
U+30de:Ma
U+30df:Mi
U+30e0:Mu
U+30e1:Me
U+30e2:Mo
U+30e3:YA
U+30e4:Ya
U+30e5:YU
U+30e6:Yu
U+30e7:YO
U+30e8:Yo
U+30e9:Ra
U+30ea:Ri
U+30eb:Ru
U+30ec:Re
U+30ed:Ro
U+30ee:WA
U+30ef:Wa
U+30f0:Wi
U+30f1:We
U+30f2:Wo
U+30f3:N6
U+30f4:Vu
U+30f5:KA
U+30f6:KE
U+30f7:Va
U+30f8:Vi
U+30f9:Ve
U+30fa:Vo
U+30fb:.6
U+30fc:-6
U+30fd:*6
U+30fe:+6
U+3105:b4
U+3106:p4
U+3107:m4
U+3108:f4
U+3109:d4
U+310a:t4
U+310b:n4
U+310c:l4
U+310d:g4
U+310e:k4
U+310f:h4
U+3110:j4
U+3111:q4
U+3112:x4
U+3113:zh
U+3114:ch
U+3115:sh
U+3116:r4
U+3117:z4
U+3118:c4
U+3119:s4
U+311a:a4
U+311b:o4
U+311c:e4
U+311d:eh4
U+311e:ai
U+311f:ei
U+3120:au
U+3121:ou
U+3122:an
U+3123:en
U+3124:aN
U+3125:eN
U+3126:er
U+3127:i4
U+3128:u4
U+3129:iu
U+312a:v4
U+312b:nG
U+312c:gn
U+321c:(JU)
U+3220:1c
U+3221:2c
U+3222:3c
U+3223:4c
U+3224:5c
U+3225:6c
U+3226:7c
U+3227:8c
U+3228:9c
U+3229:10c
U+327f:KSC
U+33c2:am
U+33d8:pm
#
#
#There are four special ranges of characters that are represented only by
#their start and end characters <...>
#
# The CJK Ideographs Area (U+4E00 - U+9FFF)
# The Hangul Syllables Area (U+AC00 - U+D7A3)
# The Surrogates Area (U+D800 - U+DFFF)
# The Private Use Area (U+E000 - U+F8FF)
#
#
U+fb00:ff
U+fb01:fi
U+fb02:fl
U+fb03:ffi
U+fb04:ffl
U+fb05:St
U+fb06:st
U+fe7d:3+;
U+fe82:aM.
U+fe84:aH.
U+fe88:ah.
U+fe8d:a+-
U+fe8e:a+.
U+fe8f:b+-
U+fe90:b+.
U+fe91:b+,
U+fe92:b+;
U+fe93:tm-
U+fe94:tm.
U+fe95:t+-
U+fe96:t+.
U+fe97:t+,
U+fe98:t+;
U+fe99:tk-
U+fe9a:tk.
U+fe9b:tk,
U+fe9c:tk;
U+fe9d:g+-
U+fe9e:g+.
U+fe9f:g+,
U+fea0:g+;
U+fea1:hk-
U+fea2:hk.
U+fea3:hk,
U+fea4:hk;
U+fea5:x+-
U+fea6:x+.
U+fea7:x+,
U+fea8:x+;
U+fea9:d+-
U+feaa:d+.
U+feab:dk-
U+feac:dk.
U+fead:r+-
U+feae:r+.
U+feaf:z+-
U+feb0:z+.
U+feb1:s+-
U+feb2:s+.
U+feb3:s+,
U+feb4:s+;
U+feb5:sn-
U+feb6:sn.
U+feb7:sn,
U+feb8:sn;
U+feb9:c+-
U+feba:c+.
U+febb:c+,
U+febc:c+;
U+febd:dd-
U+febe:dd.
U+febf:dd,
U+fec0:dd;
U+fec1:tj-
U+fec2:tj.
U+fec3:tj,
U+fec4:tj;
U+fec5:zH-
U+fec6:zH.
U+fec7:zH,
U+fec8:zH;
U+fec9:e+-
U+feca:e+.
U+fecb:e+,
U+fecc:e+;
U+fecd:i+-
U+fece:i+.
U+fecf:i+,
U+fed0:i+;
U+fed1:f+-
U+fed2:f+.
U+fed3:f+,
U+fed4:f+;
U+fed5:q+-
U+fed6:q+.
U+fed7:q+,
U+fed8:q+;
U+fed9:k+-
U+feda:k+.
U+fedb:k+,
U+fedc:k+;
U+fedd:l+-
U+fede:l+.
U+fedf:l+,
U+fee0:l+;
U+fee1:m+-
U+fee2:m+.
U+fee3:m+,
U+fee4:m+;
U+fee5:n+-
U+fee6:n+.
U+fee7:n+,
U+fee8:n+;
U+fee9:h+-
U+feea:h+.
U+feeb:h+,
U+feec:h+;
U+feed:w+-
U+feee:w+.
U+feef:j+-
U+fef0:j+.
U+fef1:y+-
U+fef2:y+.
U+fef3:y+,
U+fef4:y+;
U+fef5:lM-
U+fef6:lM.
U+fef7:lH-
U+fef8:lH.
U+fef9:lh-
U+fefa:lh.
U+fefb:la-
U+fefc:la.
# the reverse byte-order-mark: zero-width non-break space
U+feff:
0x21-0x7e U+ff01-U+ff5e
0x2e U+ff61
0x22 U+ff62 U+ff63
0x2c U+ff64
# Symbols for C0 and C1 control characters, in case they get through...
U+0000:NUL
U+0001:SH
U+0002:SX
U+0003:EX
U+0004:ET
U+0005:ENQ
U+0006:AK
U+0007:BL
U+0008:BS
U+0009:HT
U+000a:LF
U+000b:VT
U+000c:FF
U+000d:CR
U+000e:SO
U+000f:SI
U+0010:DL
U+0011:DC1
U+0012:DC2
U+0013:DC3
U+0014:DC4
U+0015:NAK
U+0016:SYN
U+0017:EB
U+0018:CN
U+0019:EM
U+001a:SB
U+001b:ESC
U+001c:FS
U+001d:GS
U+001e:RS
U+001f:US
U+007f:DT
# Most of these characters (80-9F) may be inflicted on us
# by MS FrontPages which uses Unicode notation such as &#153;
# but there are no assigned letters in Unicode 128-159 range.
# It is assumed in the code that those codepoints are from windows-1252.
#U+0080:PA
#U+0081:HO
#U+0082:BH
#U+0083:NH
#U+0084:IN
#U+0085:NL
U+0085:\012
#U+0086:SA
#U+0087:ES
#U+0088:HS
#U+0089:HJ
#U+008a:VS
#U+008b:PD
#U+008c:PU
#U+008d:RI
#U+008e:SS2
#U+008f:SS3
#U+0090:DCS
#U+0091:P1
#U+0092:P2
#U+0093:TS
#U+0094:CC
#U+0095:MW
#U+0096:SG
#U+0097:EG
#U+0098:SS
#U+0099:GC
#U+009a:SC
#U+009b:CSI
#U+009c:ST
#U+009d:OC
#U+009e:PM
#U+009f:AC
# Let's try to show a question mark for character that cannot
# be shown. U+fffd is used for invalid characters.
# It works, but let's stick with UHHH representation. - FM
#U+fffd "?"
View Git Blame Copy Permalink