diff options
Diffstat (limited to 'Unicode')
45 files changed, 12313 insertions, 0 deletions
diff --git a/Unicode/7bit.cp b/Unicode/7bit.cp new file mode 100644 index 0000000..5edd094 --- /dev/null +++ b/Unicode/7bit.cp @@ -0,0 +1,3 @@ +7-bit ASCII +"us-ascii", "ascii", "7bit", "7-bit", "iso-ir-6", "ANSI_X3.4", "646", "it-ascii" +# Dummy table for 7-bit terminals diff --git a/Unicode/7bitrepl.lnx b/Unicode/7bitrepl.lnx new file mode 100644 index 0000000..1378ed6 --- /dev/null +++ b/Unicode/7bitrepl.lnx @@ -0,0 +1,2232 @@ +# M.P.: unicode to ascii table. I took this file from lynx. +# lynx/src/chrtrans/def7_uni.tbl + +# Default 7bit replacements. If the MIME name is set to us-ascii, +# this will be identified with the "7 bit approximations" Display +# character set. + +#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 it 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:- +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 +U+00c4:A: +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 +U+00d6:O: +U+00d7: * +U+00d8:O/ +0x55 U+00d9-U+00db +U+00dc:U: +0x59 U+00dd +U+00de:TH +U+00df:ss +U+00e0:`a +0x61 U+00e1-U+00e3 +U+00e4:a: +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 +U+00f6:o: +U+00f7:-: +U+00f8:o/ +0x75 U+00f9-U+00fb +U+00fc:u: +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+0108 U+010a U+010c # C +# The following line is an example for mapping several accented versions +# of small letter 'c' to 'c': +0x63 U+0107 U+0109 U+010b U+010d # c +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+011c U+011e U+0120 U+0122 # G +0x67 U+011d U+011f U+0121 U+0123 # g +0x48 U+0124 +0x68 U+0125 +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 +0x4a U+0134 +0x6a U+0135 +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 +0x53 U+015a U+015c U+015e U+0160 # S +0x73 U+015b U+015d U+015f U+0161 # s +0x54 U+0162 U+0164 # T +0x74 U+0163 U+0165 # t +U+0166:T/ +U+0167:t/ +0x55 U+0168 U+016a U+016c U+016e U+0172 # U +0x75 U+0169 U+016b U+016d U+016f U+0173 # 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 +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:ed +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+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+02c9:1- +U+02cb:1! +0x3a U+02d0 +U+02d8:'( +U+02d9:'. +U+02da:'0 +U+02db:'; +U+02dc:~ +U+02dd:'" +0x7e U+0303 U+0334 +0x2e U+0322 U+0323 +U+0324:<?> +U+0325:<o> +0x2d U+0329 +0x5b U+032a +U+032b:<w> +U+0334:<H> +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+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+03f4:'% +U+03f5:j3 +# Cyrillic capital letters +U+0402:D% +U+0403:G% +U+0404:IE +U+0405:DS +U+0406:I~ +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:YO +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:SHCH +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:shch +U+044a:~ +U+044b:y +U+044c:' +U+044d:e' +U+044e:yu +U+044f:ya +U+0451:yo +# 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:i~ +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:E~ +U+0463:e~ +U+046a:O3 +U+046b:o3 +U+0472:~F +U+0473:~f +U+0474:~V +U+0475:~v +U+0480:C3 +U+0481:c3 +U+0490:G3 +U+0491:g3 + +# 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? +U+1f00:;' +U+1f01:,' +U+1f02:;! +U+1f03:,! +U+1f04:?; +U+1f05:?, +U+1f06:!: +U+1f07:?: +U+1fbf:,, +U+1fc0:?* +U+1fc1:?: +U+1fcd:,! +U+1fce:,' +U+1fcf:?, +U+1fdd:;! +U+1fde:;' +U+1fdf:?; +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+2013-U+2015 # hyphen-like +0x2d U+2011 +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 +U+2025:.. +U+2026:... + +# Dont wanna see these: +# POP DIRECTIONAL FORMATTING 202C +U+202c: +# LEFT-TO-RIGHT OVERRIDE 202D +U+202d: + +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:/ +# 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+2103:oC +U+2105:c/o +U+2109:oF +U+2111:Im +U+2116:No. +U+2117:PO +U+2118:P +U+211C:Re +U+211e:Rx +U+2120:(SM) +# TRADE MARK SIGN: +U+2122:(TM) +U+2126:Ohm +0x4b U+212A # Kelvin sign - K +U+212b:Ang. +U+212E:est. +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+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:decr. +U+2207:Nabla +U+2208:(- +U+2209:!(- +U+220b:-) +U+220f:\prod +U+2211:\sum +U+2212: - +U+2213:-/+ +U+2214:.+ +U+2217:* +U+2218:Ob +U+2219:sb +U+221a: SQRT +U+221d:0( +U+221e:infty +U+221f:-L +U+2220:-V +U+2225: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+224c:=? +U+2253:HI +U+2260:!= +U+2261:=3 +U+2264:=< +U+2265:>= +U+226a:<< +U+226b:>> +U+226e:!< +U+226f:!> +U+2282:(C +U+2283:)C +U+2282:!(C +U+2286:(_ +U+2287:)_ +U+2295:(+) +U+2297:(x) +U+2299:0. +U+229a:02 +U+22a5:-T +U+22c5:.P +U+22ee::3 +U+22ef:.3 +U+2302:Eh +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+2323::) +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:UT +U+25b3:uT +U+25b6:PR +U+25b7:Tr +U+25ba:PR +U+25bc:Dt +U+25bd:dT +U+25c0:PL +U+25c1:Tl +U+25c4:PL +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+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+301c:-? +U+3020:=T:) +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. + +# 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 ™ +# 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+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 representatiion. - FM +#U+fffd:? diff --git a/Unicode/8859_1.cp b/Unicode/8859_1.cp new file mode 100644 index 0000000..efaae2a --- /dev/null +++ b/Unicode/8859_1.cp @@ -0,0 +1,193 @@ +ISO 8859-1 (Western European) +"ISO-8859-1", "8859-1", "iso-ir-100", "latin1", "l1", "819","iso-latin1" +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x00A1 #INVERTED EXCLAMATION MARK +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x00AA #FEMININE ORDINAL INDICATOR +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x00BA #MASCULINE ORDINAL INDICATOR +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF #INVERTED QUESTION MARK +0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 #LATIN CAPITAL LETTER AE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x00D0 #LATIN CAPITAL LETTER ETH +0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x00DE #LATIN CAPITAL LETTER THORN +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 #LATIN SMALL LETTER AE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x00F0 #LATIN SMALL LETTER ETH +0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x00FE #LATIN SMALL LETTER THORN +0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS diff --git a/Unicode/8859_10.cp b/Unicode/8859_10.cp new file mode 100644 index 0000000..b589fd7 --- /dev/null +++ b/Unicode/8859_10.cp @@ -0,0 +1,305 @@ +ISO 8859-10 (Lappish, Nordic, Eskimo) +"ISO-8859-10", "8859-10" +# +# Name: ISO/IEC 8859-10:1998 to Unicode +# Unicode version: 3.0 +# Table version: 1.1 +# Table format: Format A +# Date: 1999 October 11 +# Authors: Ken Whistler <kenw@sybase.com> +# +# Copyright (c) 1999 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on optical media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-10:1998 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-10 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-10 order. +# +# Version history +# 1.0 version new. +# 1.1 corrected mistake in mapping of 0xA4 +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # <control> +0x81 0x0081 # <control> +0x82 0x0082 # <control> +0x83 0x0083 # <control> +0x84 0x0084 # <control> +0x85 0x0085 # <control> +0x86 0x0086 # <control> +0x87 0x0087 # <control> +0x88 0x0088 # <control> +0x89 0x0089 # <control> +0x8A 0x008A # <control> +0x8B 0x008B # <control> +0x8C 0x008C # <control> +0x8D 0x008D # <control> +0x8E 0x008E # <control> +0x8F 0x008F # <control> +0x90 0x0090 # <control> +0x91 0x0091 # <control> +0x92 0x0092 # <control> +0x93 0x0093 # <control> +0x94 0x0094 # <control> +0x95 0x0095 # <control> +0x96 0x0096 # <control> +0x97 0x0097 # <control> +0x98 0x0098 # <control> +0x99 0x0099 # <control> +0x9A 0x009A # <control> +0x9B 0x009B # <control> +0x9C 0x009C # <control> +0x9D 0x009D # <control> +0x9E 0x009E # <control> +0x9F 0x009F # <control> +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK +0xA2 0x0112 # LATIN CAPITAL LETTER E WITH MACRON +0xA3 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA +0xA4 0x012A # LATIN CAPITAL LETTER I WITH MACRON +0xA5 0x0128 # LATIN CAPITAL LETTER I WITH TILDE +0xA6 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA +0xA7 0x00A7 # SECTION SIGN +0xA8 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA +0xA9 0x0110 # LATIN CAPITAL LETTER D WITH STROKE +0xAA 0x0160 # LATIN CAPITAL LETTER S WITH CARON +0xAB 0x0166 # LATIN CAPITAL LETTER T WITH STROKE +0xAC 0x017D # LATIN CAPITAL LETTER Z WITH CARON +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x016A # LATIN CAPITAL LETTER U WITH MACRON +0xAF 0x014A # LATIN CAPITAL LETTER ENG +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK +0xB2 0x0113 # LATIN SMALL LETTER E WITH MACRON +0xB3 0x0123 # LATIN SMALL LETTER G WITH CEDILLA +0xB4 0x012B # LATIN SMALL LETTER I WITH MACRON +0xB5 0x0129 # LATIN SMALL LETTER I WITH TILDE +0xB6 0x0137 # LATIN SMALL LETTER K WITH CEDILLA +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x013C # LATIN SMALL LETTER L WITH CEDILLA +0xB9 0x0111 # LATIN SMALL LETTER D WITH STROKE +0xBA 0x0161 # LATIN SMALL LETTER S WITH CARON +0xBB 0x0167 # LATIN SMALL LETTER T WITH STROKE +0xBC 0x017E # LATIN SMALL LETTER Z WITH CARON +0xBD 0x2015 # HORIZONTAL BAR +0xBE 0x016B # LATIN SMALL LETTER U WITH MACRON +0xBF 0x014B # LATIN SMALL LETTER ENG +0xC0 0x0100 # LATIN CAPITAL LETTER A WITH MACRON +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 # LATIN CAPITAL LETTER AE +0xC7 0x012E # LATIN CAPITAL LETTER I WITH OGONEK +0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x00D0 # LATIN CAPITAL LETTER ETH (Icelandic) +0xD1 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA +0xD2 0x014C # LATIN CAPITAL LETTER O WITH MACRON +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x0168 # LATIN CAPITAL LETTER U WITH TILDE +0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x00DE # LATIN CAPITAL LETTER THORN (Icelandic) +0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German) +0xE0 0x0101 # LATIN SMALL LETTER A WITH MACRON +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 # LATIN SMALL LETTER AE +0xE7 0x012F # LATIN SMALL LETTER I WITH OGONEK +0xE8 0x010D # LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x00F0 # LATIN SMALL LETTER ETH (Icelandic) +0xF1 0x0146 # LATIN SMALL LETTER N WITH CEDILLA +0xF2 0x014D # LATIN SMALL LETTER O WITH MACRON +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x0169 # LATIN SMALL LETTER U WITH TILDE +0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE +0xF9 0x0173 # LATIN SMALL LETTER U WITH OGONEK +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x00FE # LATIN SMALL LETTER THORN (Icelandic) +0xFF 0x0138 # LATIN SMALL LETTER KRA diff --git a/Unicode/8859_13.cp b/Unicode/8859_13.cp new file mode 100644 index 0000000..4fb6c4e --- /dev/null +++ b/Unicode/8859_13.cp @@ -0,0 +1,134 @@ +ISO 8859-13 (Baltic) +"ISO-8859-13", "8859-13", "iso-ir-179", "latin7", "l7","iso-latin7" + +0x20-0x7e idem +# +0x80 0x0080 #PADDING CHARACTER (PAD) +0x81 0x0081 #HIGH OCTET PRESET (HOP) +0x82 0x0082 #BREAK PERMITTED HERE (BPH) +0x83 0x0083 #NO BREAK HERE (NBH) +0x84 0x0084 #INDEX (IND) +0x85 0x0085 #NEXT LINE (NEL) +0x86 0x0086 #START OF SELECTED AREA (SSA) +0x87 0x0087 #END OF SELECTED AREA (ESA) +0x88 0x0088 #CHARACTER TABULATION SET (HTS) +0x89 0x0089 #CHARACTER TABULATION WITH JUSTIFICATION (HTJ) +0x8A 0x008A #LINE TABULATION SET (VTS) +0x8B 0x008B #PARTIAL LINE FORWARD (PLD) +0x8C 0x008C #PARTIAL LINE BACKWARD (PLU) +0x8D 0x008D #REVERSE LINE FEED (RI) +0x8E 0x008E #SINGLE-SHIFT TWO (SS2) +0x8F 0x008F #SINGLE-SHIFT THREE (SS3) +0x90 0x0090 #DEVICE CONTROL STRING (DCS) +0x91 0x0091 #PRIVATE USE ONE (PU1) +0x92 0x0092 #PRIVATE USE TWO (PU2) +0x93 0x0093 #SET TRANSMIT STATE (STS) +0x94 0x0094 #CANCEL CHARACTER (CCH) +0x95 0x0095 #MESSAGE WAITING (MW) +0x96 0x0096 #START OF GUARDED AREA (SPA) +0x97 0x0097 #END OF GUARDED AREA (EPA) +0x98 0x0098 #START OF STRING (SOS) +0x99 0x0099 #SINGLE GRAPHIC CHARACTER INTRODUCER (SGCI) +0x9A 0x009A #SINGLE CHARACTER INTRODUCER (SCI) +0x9B 0x009B #CONTROL SEQUENCE INTRODUCER (CSI) +0x9C 0x009C #STRING TERMINATOR (ST) +0x9D 0x009D #OPERATING SYSTEM COMMAND (OSC) +0x9E 0x009E #PRIVACY MESSAGE (PM) +0x9F 0x009F #APPLICATION PROGRAM COMMAND (APC) +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x201D #RIGHT DOUBLE QUOTATION MARK +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x201E #DOUBLE LOW-9 QUOTATION MARK +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x0156 #LATIN CAPITAL LETTER R WITH CEDILLA +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00C6 #LATIN CAPITAL LETTER AE +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x201C #LEFT DOUBLE QUOTATION MARK +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x0157 #LATIN SMALL LETTER R WITH CEDILLA +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00E6 #LATIN SMALL LETTER AE +0xC0 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK +0xC1 0x012E #LATIN CAPITAL LETTER I WITH OGONEK +0xC2 0x0100 #LATIN CAPITAL LETTER A WITH MACRON +0xC3 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK +0xC7 0x0112 #LATIN CAPITAL LETTER E WITH MACRON +0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE +0xCB 0x0116 #LATIN CAPITAL LETTER E WITH DOT ABOVE +0xCC 0x0122 #LATIN CAPITAL LETTER G WITH CEDILLA +0xCD 0x0136 #LATIN CAPITAL LETTER K WITH CEDILLA +0xCE 0x012A #LATIN CAPITAL LETTER I WITH MACRON +0xCF 0x013B #LATIN CAPITAL LETTER L WITH CEDILLA +0xD0 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE +0xD2 0x0145 #LATIN CAPITAL LETTER N WITH CEDILLA +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x014C #LATIN CAPITAL LETTER O WITH MACRON +0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x0172 #LATIN CAPITAL LETTER U WITH OGONEK +0xD9 0x0141 #LATIN CAPITAL LETTER L WITH STROKE +0xDA 0x015A #LATIN CAPITAL LETTER S WITH ACUTE +0xDB 0x016A #LATIN CAPITAL LETTER U WITH MACRON +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xDE 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x0105 #LATIN SMALL LETTER A WITH OGONEK +0xE1 0x012F #LATIN SMALL LETTER I WITH OGONEK +0xE2 0x0101 #LATIN SMALL LETTER A WITH MACRON +0xE3 0x0107 #LATIN SMALL LETTER C WITH ACUTE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x0119 #LATIN SMALL LETTER E WITH OGONEK +0xE7 0x0113 #LATIN SMALL LETTER E WITH MACRON +0xE8 0x010D #LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x017A #LATIN SMALL LETTER Z WITH ACUTE +0xEB 0x0117 #LATIN SMALL LETTER E WITH DOT ABOVE +0xEC 0x0123 #LATIN SMALL LETTER G WITH CEDILLA +0xED 0x0137 #LATIN SMALL LETTER K WITH CEDILLA +0xEE 0x012B #LATIN SMALL LETTER I WITH MACRON +0xEF 0x013C #LATIN SMALL LETTER L WITH CEDILLA +0xF0 0x0161 #LATIN SMALL LETTER S WITH CARON +0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE +0xF2 0x0146 #LATIN SMALL LETTER N WITH CEDILLA +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x014D #LATIN SMALL LETTER O WITH MACRON +0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x0173 #LATIN SMALL LETTER U WITH OGONEK +0xF9 0x0142 #LATIN SMALL LETTER L WITH STROKE +0xFA 0x015B #LATIN SMALL LETTER S WITH ACUTE +0xFB 0x016B #LATIN SMALL LETTER U WITH MACRON +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE +0xFE 0x017E #LATIN SMALL LETTER Z WITH CARON +0xFF 0x2019 #RIGHT SINGLE QUOTATION MARK + diff --git a/Unicode/8859_14.cp b/Unicode/8859_14.cp new file mode 100644 index 0000000..96dcffb --- /dev/null +++ b/Unicode/8859_14.cp @@ -0,0 +1,303 @@ +ISO 8859-14 (Celtic) +"ISO-8859-14", "8859-14" +# +# Name: ISO/IEC 8859-14:1998 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Markus Kuhn <mkuhn@acm.org> +# Ken Whistler <kenw@sybase.com> +# +# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on optical media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-14:1998 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-14 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-14 order. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # <control> +0x81 0x0081 # <control> +0x82 0x0082 # <control> +0x83 0x0083 # <control> +0x84 0x0084 # <control> +0x85 0x0085 # <control> +0x86 0x0086 # <control> +0x87 0x0087 # <control> +0x88 0x0088 # <control> +0x89 0x0089 # <control> +0x8A 0x008A # <control> +0x8B 0x008B # <control> +0x8C 0x008C # <control> +0x8D 0x008D # <control> +0x8E 0x008E # <control> +0x8F 0x008F # <control> +0x90 0x0090 # <control> +0x91 0x0091 # <control> +0x92 0x0092 # <control> +0x93 0x0093 # <control> +0x94 0x0094 # <control> +0x95 0x0095 # <control> +0x96 0x0096 # <control> +0x97 0x0097 # <control> +0x98 0x0098 # <control> +0x99 0x0099 # <control> +0x9A 0x009A # <control> +0x9B 0x009B # <control> +0x9C 0x009C # <control> +0x9D 0x009D # <control> +0x9E 0x009E # <control> +0x9F 0x009F # <control> +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x1E02 # LATIN CAPITAL LETTER B WITH DOT ABOVE +0xA2 0x1E03 # LATIN SMALL LETTER B WITH DOT ABOVE +0xA3 0x00A3 # POUND SIGN +0xA4 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE +0xA5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE +0xA6 0x1E0A # LATIN CAPITAL LETTER D WITH DOT ABOVE +0xA7 0x00A7 # SECTION SIGN +0xA8 0x1E80 # LATIN CAPITAL LETTER W WITH GRAVE +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x1E82 # LATIN CAPITAL LETTER W WITH ACUTE +0xAB 0x1E0B # LATIN SMALL LETTER D WITH DOT ABOVE +0xAC 0x1EF2 # LATIN CAPITAL LETTER Y WITH GRAVE +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x00AE # REGISTERED SIGN +0xAF 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS +0xB0 0x1E1E # LATIN CAPITAL LETTER F WITH DOT ABOVE +0xB1 0x1E1F # LATIN SMALL LETTER F WITH DOT ABOVE +0xB2 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE +0xB3 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE +0xB4 0x1E40 # LATIN CAPITAL LETTER M WITH DOT ABOVE +0xB5 0x1E41 # LATIN SMALL LETTER M WITH DOT ABOVE +0xB6 0x00B6 # PILCROW SIGN +0xB7 0x1E56 # LATIN CAPITAL LETTER P WITH DOT ABOVE +0xB8 0x1E81 # LATIN SMALL LETTER W WITH GRAVE +0xB9 0x1E57 # LATIN SMALL LETTER P WITH DOT ABOVE +0xBA 0x1E83 # LATIN SMALL LETTER W WITH ACUTE +0xBB 0x1E60 # LATIN CAPITAL LETTER S WITH DOT ABOVE +0xBC 0x1EF3 # LATIN SMALL LETTER Y WITH GRAVE +0xBD 0x1E84 # LATIN CAPITAL LETTER W WITH DIAERESIS +0xBE 0x1E85 # LATIN SMALL LETTER W WITH DIAERESIS +0xBF 0x1E61 # LATIN SMALL LETTER S WITH DOT ABOVE +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 # LATIN CAPITAL LETTER AE +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x0174 # LATIN CAPITAL LETTER W WITH CIRCUMFLEX +0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x1E6A # LATIN CAPITAL LETTER T WITH DOT ABOVE +0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x0176 # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 # LATIN SMALL LETTER AE +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x0175 # LATIN SMALL LETTER W WITH CIRCUMFLEX +0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x1E6B # LATIN SMALL LETTER T WITH DOT ABOVE +0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x0177 # LATIN SMALL LETTER Y WITH CIRCUMFLEX +0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS + diff --git a/Unicode/8859_15.cp b/Unicode/8859_15.cp new file mode 100644 index 0000000..d16a84e --- /dev/null +++ b/Unicode/8859_15.cp @@ -0,0 +1,305 @@ +ISO 8859-15 (Western European) +"ISO-8859-15", "8859-15" +# +# Name: ISO/IEC 8859-15:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Markus Kuhn <mkuhn@acm.org> +# Ken Whistler <kenw@sybase.com> +# +# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on optical media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-15:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-15 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-15 order. +# +# Version history +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # <control> +0x81 0x0081 # <control> +0x82 0x0082 # <control> +0x83 0x0083 # <control> +0x84 0x0084 # <control> +0x85 0x0085 # <control> +0x86 0x0086 # <control> +0x87 0x0087 # <control> +0x88 0x0088 # <control> +0x89 0x0089 # <control> +0x8A 0x008A # <control> +0x8B 0x008B # <control> +0x8C 0x008C # <control> +0x8D 0x008D # <control> +0x8E 0x008E # <control> +0x8F 0x008F # <control> +0x90 0x0090 # <control> +0x91 0x0091 # <control> +0x92 0x0092 # <control> +0x93 0x0093 # <control> +0x94 0x0094 # <control> +0x95 0x0095 # <control> +0x96 0x0096 # <control> +0x97 0x0097 # <control> +0x98 0x0098 # <control> +0x99 0x0099 # <control> +0x9A 0x009A # <control> +0x9B 0x009B # <control> +0x9C 0x009C # <control> +0x9D 0x009D # <control> +0x9E 0x009E # <control> +0x9F 0x009F # <control> +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x00A1 # INVERTED EXCLAMATION MARK +0xA2 0x00A2 # CENT SIGN +0xA3 0x00A3 # POUND SIGN +0xA4 0x20AC # EURO SIGN +0xA5 0x00A5 # YEN SIGN +0xA6 0x0160 # LATIN CAPITAL LETTER S WITH CARON +0xA7 0x00A7 # SECTION SIGN +0xA8 0x0161 # LATIN SMALL LETTER S WITH CARON +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x00AA # FEMININE ORDINAL INDICATOR +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC # NOT SIGN +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x00AE # REGISTERED SIGN +0xAF 0x00AF # MACRON +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x017D # LATIN CAPITAL LETTER Z WITH CARON +0xB5 0x00B5 # MICRO SIGN +0xB6 0x00B6 # PILCROW SIGN +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x017E # LATIN SMALL LETTER Z WITH CARON +0xB9 0x00B9 # SUPERSCRIPT ONE +0xBA 0x00BA # MASCULINE ORDINAL INDICATOR +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x0152 # LATIN CAPITAL LIGATURE OE +0xBD 0x0153 # LATIN SMALL LIGATURE OE +0xBE 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS +0xBF 0x00BF # INVERTED QUESTION MARK +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 # LATIN CAPITAL LETTER AE +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x00D0 # LATIN CAPITAL LETTER ETH +0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x00DE # LATIN CAPITAL LETTER THORN +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 # LATIN SMALL LETTER AE +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x00F0 # LATIN SMALL LETTER ETH +0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x00FE # LATIN SMALL LETTER THORN +0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS + diff --git a/Unicode/8859_16.cp b/Unicode/8859_16.cp new file mode 100644 index 0000000..58781de --- /dev/null +++ b/Unicode/8859_16.cp @@ -0,0 +1,301 @@ +ISO 8859-16 (Romainian) +"ISO-8859-16", "8859-16" +# +# Name: ISO/IEC 8859-16:2001 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 2001 July 26 +# Authors: Markus Kuhn <mkuhn@acm.org> +# +# Copyright (c) 1999-2001 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on optical media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-16:2001 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-16 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-16 order. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # <control> +0x81 0x0081 # <control> +0x82 0x0082 # <control> +0x83 0x0083 # <control> +0x84 0x0084 # <control> +0x85 0x0085 # <control> +0x86 0x0086 # <control> +0x87 0x0087 # <control> +0x88 0x0088 # <control> +0x89 0x0089 # <control> +0x8A 0x008A # <control> +0x8B 0x008B # <control> +0x8C 0x008C # <control> +0x8D 0x008D # <control> +0x8E 0x008E # <control> +0x8F 0x008F # <control> +0x90 0x0090 # <control> +0x91 0x0091 # <control> +0x92 0x0092 # <control> +0x93 0x0093 # <control> +0x94 0x0094 # <control> +0x95 0x0095 # <control> +0x96 0x0096 # <control> +0x97 0x0097 # <control> +0x98 0x0098 # <control> +0x99 0x0099 # <control> +0x9A 0x009A # <control> +0x9B 0x009B # <control> +0x9C 0x009C # <control> +0x9D 0x009D # <control> +0x9E 0x009E # <control> +0x9F 0x009F # <control> +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK +0xA2 0x0105 # LATIN SMALL LETTER A WITH OGONEK +0xA3 0x0141 # LATIN CAPITAL LETTER L WITH STROKE +0xA4 0x20AC # EURO SIGN +0xA5 0x201E # DOUBLE LOW-9 QUOTATION MARK +0xA6 0x0160 # LATIN CAPITAL LETTER S WITH CARON +0xA7 0x00A7 # SECTION SIGN +0xA8 0x0161 # LATIN SMALL LETTER S WITH CARON +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x0218 # LATIN CAPITAL LETTER S WITH COMMA BELOW +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x017A # LATIN SMALL LETTER Z WITH ACUTE +0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x010C # LATIN CAPITAL LETTER C WITH CARON +0xB3 0x0142 # LATIN SMALL LETTER L WITH STROKE +0xB4 0x017D # LATIN CAPITAL LETTER Z WITH CARON +0xB5 0x201D # RIGHT DOUBLE QUOTATION MARK +0xB6 0x00B6 # PILCROW SIGN +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x017E # LATIN SMALL LETTER Z WITH CARON +0xB9 0x010D # LATIN SMALL LETTER C WITH CARON +0xBA 0x0219 # LATIN SMALL LETTER S WITH COMMA BELOW +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x0152 # LATIN CAPITAL LIGATURE OE +0xBD 0x0153 # LATIN SMALL LIGATURE OE +0xBE 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS +0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x0102 # LATIN CAPITAL LETTER A WITH BREVE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE +0xC6 0x00C6 # LATIN CAPITAL LETTER AE +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x015A # LATIN CAPITAL LETTER S WITH ACUTE +0xD8 0x0170 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK +0xDE 0x021A # LATIN CAPITAL LETTER T WITH COMMA BELOW +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0103 # LATIN SMALL LETTER A WITH BREVE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x0107 # LATIN SMALL LETTER C WITH ACUTE +0xE6 0x00E6 # LATIN SMALL LETTER AE +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE +0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x015B # LATIN SMALL LETTER S WITH ACUTE +0xF8 0x0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x0119 # LATIN SMALL LETTER E WITH OGONEK +0xFE 0x021B # LATIN SMALL LETTER T WITH COMMA BELOW +0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS diff --git a/Unicode/8859_2.cp b/Unicode/8859_2.cp new file mode 100644 index 0000000..cfb6e42 --- /dev/null +++ b/Unicode/8859_2.cp @@ -0,0 +1,193 @@ +ISO 8859-2 (Central European) +"ISO-8859-2", "8859-2", "iso-ir-101", "latin2", "l2","iso-latin2", "iso8859-2" +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK +0xA2 0x02D8 #BREVE +0xA3 0x0141 #LATIN CAPITAL LETTER L WITH STROKE +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x013D #LATIN CAPITAL LETTER L WITH CARON +0xA6 0x015A #LATIN CAPITAL LETTER S WITH ACUTE +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0xAA 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA +0xAB 0x0164 #LATIN CAPITAL LETTER T WITH CARON +0xAC 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0xAF 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x0105 #LATIN SMALL LETTER A WITH OGONEK +0xB2 0x02DB #OGONEK +0xB3 0x0142 #LATIN SMALL LETTER L WITH STROKE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x013E #LATIN SMALL LETTER L WITH CARON +0xB6 0x015B #LATIN SMALL LETTER S WITH ACUTE +0xB7 0x02C7 #CARON +0xB8 0x00B8 #CEDILLA +0xB9 0x0161 #LATIN SMALL LETTER S WITH CARON +0xBA 0x015F #LATIN SMALL LETTER S WITH CEDILLA +0xBB 0x0165 #LATIN SMALL LETTER T WITH CARON +0xBC 0x017A #LATIN SMALL LETTER Z WITH ACUTE +0xBD 0x02DD #DOUBLE ACUTE ACCENT +0xBE 0x017E #LATIN SMALL LETTER Z WITH CARON +0xBF 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE +0xC0 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE +0xC6 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x011A #LATIN CAPITAL LETTER E WITH CARON +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x010E #LATIN CAPITAL LETTER D WITH CARON +0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE +0xD2 0x0147 #LATIN CAPITAL LETTER N WITH CARON +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x0158 #LATIN CAPITAL LETTER R WITH CARON +0xD9 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x0155 #LATIN SMALL LETTER R WITH ACUTE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x013A #LATIN SMALL LETTER L WITH ACUTE +0xE6 0x0107 #LATIN SMALL LETTER C WITH ACUTE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x010D #LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x0119 #LATIN SMALL LETTER E WITH OGONEK +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x011B #LATIN SMALL LETTER E WITH CARON +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x010F #LATIN SMALL LETTER D WITH CARON +0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE +0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE +0xF2 0x0148 #LATIN SMALL LETTER N WITH CARON +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x0159 #LATIN SMALL LETTER R WITH CARON +0xF9 0x016F #LATIN SMALL LETTER U WITH RING ABOVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x0163 #LATIN SMALL LETTER T WITH CEDILLA +0xFF 0x02D9 #DOT ABOVE diff --git a/Unicode/8859_3.cp b/Unicode/8859_3.cp new file mode 100644 index 0000000..1f3ba34 --- /dev/null +++ b/Unicode/8859_3.cp @@ -0,0 +1,298 @@ +ISO 8859-3 (Esperanto, Maltese) +"ISO-8859-3", "8859-3" +# +# Name: ISO/IEC 8859-3:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> +# +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on optical media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-3:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-3 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-3 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # <control> +0x81 0x0081 # <control> +0x82 0x0082 # <control> +0x83 0x0083 # <control> +0x84 0x0084 # <control> +0x85 0x0085 # <control> +0x86 0x0086 # <control> +0x87 0x0087 # <control> +0x88 0x0088 # <control> +0x89 0x0089 # <control> +0x8A 0x008A # <control> +0x8B 0x008B # <control> +0x8C 0x008C # <control> +0x8D 0x008D # <control> +0x8E 0x008E # <control> +0x8F 0x008F # <control> +0x90 0x0090 # <control> +0x91 0x0091 # <control> +0x92 0x0092 # <control> +0x93 0x0093 # <control> +0x94 0x0094 # <control> +0x95 0x0095 # <control> +0x96 0x0096 # <control> +0x97 0x0097 # <control> +0x98 0x0098 # <control> +0x99 0x0099 # <control> +0x9A 0x009A # <control> +0x9B 0x009B # <control> +0x9C 0x009C # <control> +0x9D 0x009D # <control> +0x9E 0x009E # <control> +0x9F 0x009F # <control> +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0126 # LATIN CAPITAL LETTER H WITH STROKE +0xA2 0x02D8 # BREVE +0xA3 0x00A3 # POUND SIGN +0xA4 0x00A4 # CURRENCY SIGN +0xA6 0x0124 # LATIN CAPITAL LETTER H WITH CIRCUMFLEX +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE +0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA +0xAB 0x011E # LATIN CAPITAL LETTER G WITH BREVE +0xAC 0x0134 # LATIN CAPITAL LETTER J WITH CIRCUMFLEX +0xAD 0x00AD # SOFT HYPHEN +0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x0127 # LATIN SMALL LETTER H WITH STROKE +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x00B5 # MICRO SIGN +0xB6 0x0125 # LATIN SMALL LETTER H WITH CIRCUMFLEX +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x00B8 # CEDILLA +0xB9 0x0131 # LATIN SMALL LETTER DOTLESS I +0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA +0xBB 0x011F # LATIN SMALL LETTER G WITH BREVE +0xBC 0x0135 # LATIN SMALL LETTER J WITH CIRCUMFLEX +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE +0xC6 0x0108 # LATIN CAPITAL LETTER C WITH CIRCUMFLEX +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x011C # LATIN CAPITAL LETTER G WITH CIRCUMFLEX +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x016C # LATIN CAPITAL LETTER U WITH BREVE +0xDE 0x015C # LATIN CAPITAL LETTER S WITH CIRCUMFLEX +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE +0xE6 0x0109 # LATIN SMALL LETTER C WITH CIRCUMFLEX +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x011D # LATIN SMALL LETTER G WITH CIRCUMFLEX +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x016D # LATIN SMALL LETTER U WITH BREVE +0xFE 0x015D # LATIN SMALL LETTER S WITH CIRCUMFLEX +0xFF 0x02D9 # DOT ABOVE diff --git a/Unicode/8859_4.cp b/Unicode/8859_4.cp new file mode 100644 index 0000000..abe189f --- /dev/null +++ b/Unicode/8859_4.cp @@ -0,0 +1,133 @@ +ISO 8859-4 (Scandinavia, Baltic) +"ISO-8859-4", "8859-4", "iso-ir-110", "latin4", "l4","iso-latin4" + +0x20-0x7e idem +# +0x80 0x0080 #PADDING CHARACTER (PAD) +0x81 0x0081 #HIGH OCTET PRESET (HOP) +0x82 0x0082 #BREAK PERMITTED HERE (BPH) +0x83 0x0083 #NO BREAK HERE (NBH) +0x84 0x0084 #INDEX (IND) +0x85 0x0085 #NEXT LINE (NEL) +0x86 0x0086 #START OF SELECTED AREA (SSA) +0x87 0x0087 #END OF SELECTED AREA (ESA) +0x88 0x0088 #CHARACTER TABULATION SET (HTS) +0x89 0x0089 #CHARACTER TABULATION WITH JUSTIFICATION (HTJ) +0x8A 0x008A #LINE TABULATION SET (VTS) +0x8B 0x008B #PARTIAL LINE FORWARD (PLD) +0x8C 0x008C #PARTIAL LINE BACKWARD (PLU) +0x8D 0x008D #REVERSE LINE FEED (RI) +0x8E 0x008E #SINGLE-SHIFT TWO (SS2) +0x8F 0x008F #SINGLE-SHIFT THREE (SS3) +0x90 0x0090 #DEVICE CONTROL STRING (DCS) +0x91 0x0091 #PRIVATE USE ONE (PU1) +0x92 0x0092 #PRIVATE USE TWO (PU2) +0x93 0x0093 #SET TRANSMIT STATE (STS) +0x94 0x0094 #CANCEL CHARACTER (CCH) +0x95 0x0095 #MESSAGE WAITING (MW) +0x96 0x0096 #START OF GUARDED AREA (SPA) +0x97 0x0097 #END OF GUARDED AREA (EPA) +0x98 0x0098 #START OF STRING (SOS) +0x99 0x0099 #SINGLE GRAPHIC CHARACTER INTRODUCER (SGCI) +0x9A 0x009A #SINGLE CHARACTER INTRODUCER (SCI) +0x9B 0x009B #CONTROL SEQUENCE INTRODUCER (CSI) +0x9C 0x009C #STRING TERMINATOR (ST) +0x9D 0x009D #OPERATING SYSTEM COMMAND (OSC) +0x9E 0x009E #PRIVACY MESSAGE (PM) +0x9F 0x009F #APPLICATION PROGRAM COMMAND (APC) +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK +0xA2 0x0138 #LATIN SMALL LETTER KRA (Greenlandic) +0xA3 0x0156 #LATIN CAPITAL LETTER R WITH CEDILLA +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x0128 #LATIN CAPITAL LETTER I WITH TILDE +0xA6 0x013B #LATIN CAPITAL LETTER L WITH CEDILLA +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0xAA 0x0112 #LATIN CAPITAL LETTER E WITH MACRON +0xAB 0x0122 #LATIN CAPITAL LETTER G WITH CEDILLA +0xAC 0x0166 #LATIN CAPITAL LETTER T WITH STROKE +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x0105 #LATIN SMALL LETTER A WITH OGONEK +0xB2 0x02DB #OGONEK +0xB3 0x0157 #LATIN SMALL LETTER R WITH CEDILLA +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x0129 #LATIN SMALL LETTER I WITH TILDE +0xB6 0x013C #LATIN SMALL LETTER L WITH CEDILLA +0xB7 0x02C7 #CARON (Mandarin Chinese third tone) +0xB8 0x00B8 #CEDILLA +0xB9 0x0161 #LATIN SMALL LETTER S WITH CARON +0xBA 0x0113 #LATIN SMALL LETTER E WITH MACRON +0xBB 0x0123 #LATIN SMALL LETTER G WITH CEDILLA +0xBC 0x0167 #LATIN SMALL LETTER T WITH STROKE +0xBD 0x014A #LATIN CAPITAL LETTER ENG (Sami) +0xBE 0x017E #LATIN SMALL LETTER Z WITH CARON +0xBF 0x014B #LATIN SMALL LETTER ENG (Sami) +0xC0 0x0100 #LATIN CAPITAL LETTER A WITH MACRON +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 #LATIN CAPITAL LETTER AE +0xC7 0x012E #LATIN CAPITAL LETTER I WITH OGONEK +0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x0116 #LATIN CAPITAL LETTER E WITH DOT ABOVE +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x012A #LATIN CAPITAL LETTER I WITH MACRON +0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x0145 #LATIN CAPITAL LETTER N WITH CEDILLA +0xD2 0x014C #LATIN CAPITAL LETTER O WITH MACRON +0xD3 0x0136 #LATIN CAPITAL LETTER K WITH CEDILLA +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x0172 #LATIN CAPITAL LETTER U WITH OGONEK +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x0168 #LATIN CAPITAL LETTER U WITH TILDE +0xDE 0x016A #LATIN CAPITAL LETTER U WITH MACRON +0xDF 0x00DF #LATIN SMALL LETTER SHARP S (German) +0xE0 0x0101 #LATIN SMALL LETTER A WITH MACRON +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 #LATIN SMALL LETTER AE +0xE7 0x012F #LATIN SMALL LETTER I WITH OGONEK +0xE8 0x010D #LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x0119 #LATIN SMALL LETTER E WITH OGONEK +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x0117 #LATIN SMALL LETTER E WITH DOT ABOVE +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x012B #LATIN SMALL LETTER I WITH MACRON +0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE +0xF1 0x0146 #LATIN SMALL LETTER N WITH CEDILLA +0xF2 0x014D #LATIN SMALL LETTER O WITH MACRON +0xF3 0x0137 #LATIN SMALL LETTER K WITH CEDILLA +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xF9 0x0173 #LATIN SMALL LETTER U WITH OGONEK +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x0169 #LATIN SMALL LETTER U WITH TILDE +0xFE 0x016B #LATIN SMALL LETTER U WITH MACRON +0xFF 0x02D9 #DOT ABOVE (Mandarin Chinese light tone) diff --git a/Unicode/8859_5.cp b/Unicode/8859_5.cp new file mode 100644 index 0000000..2f13cd6 --- /dev/null +++ b/Unicode/8859_5.cp @@ -0,0 +1,305 @@ +ISO 8859-5 (Cyrillic) +"ISO-8859-5", "8859-5" +# +# Name: ISO 8859-5:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> +# +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on optical media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-5:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-5 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-5 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # <control> +0x81 0x0081 # <control> +0x82 0x0082 # <control> +0x83 0x0083 # <control> +0x84 0x0084 # <control> +0x85 0x0085 # <control> +0x86 0x0086 # <control> +0x87 0x0087 # <control> +0x88 0x0088 # <control> +0x89 0x0089 # <control> +0x8A 0x008A # <control> +0x8B 0x008B # <control> +0x8C 0x008C # <control> +0x8D 0x008D # <control> +0x8E 0x008E # <control> +0x8F 0x008F # <control> +0x90 0x0090 # <control> +0x91 0x0091 # <control> +0x92 0x0092 # <control> +0x93 0x0093 # <control> +0x94 0x0094 # <control> +0x95 0x0095 # <control> +0x96 0x0096 # <control> +0x97 0x0097 # <control> +0x98 0x0098 # <control> +0x99 0x0099 # <control> +0x9A 0x009A # <control> +0x9B 0x009B # <control> +0x9C 0x009C # <control> +0x9D 0x009D # <control> +0x9E 0x009E # <control> +0x9F 0x009F # <control> +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0401 # CYRILLIC CAPITAL LETTER IO +0xA2 0x0402 # CYRILLIC CAPITAL LETTER DJE +0xA3 0x0403 # CYRILLIC CAPITAL LETTER GJE +0xA4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xA5 0x0405 # CYRILLIC CAPITAL LETTER DZE +0xA6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0xA7 0x0407 # CYRILLIC CAPITAL LETTER YI +0xA8 0x0408 # CYRILLIC CAPITAL LETTER JE +0xA9 0x0409 # CYRILLIC CAPITAL LETTER LJE +0xAA 0x040A # CYRILLIC CAPITAL LETTER NJE +0xAB 0x040B # CYRILLIC CAPITAL LETTER TSHE +0xAC 0x040C # CYRILLIC CAPITAL LETTER KJE +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x040E # CYRILLIC CAPITAL LETTER SHORT U +0xAF 0x040F # CYRILLIC CAPITAL LETTER DZHE +0xB0 0x0410 # CYRILLIC CAPITAL LETTER A +0xB1 0x0411 # CYRILLIC CAPITAL LETTER BE +0xB2 0x0412 # CYRILLIC CAPITAL LETTER VE +0xB3 0x0413 # CYRILLIC CAPITAL LETTER GHE +0xB4 0x0414 # CYRILLIC CAPITAL LETTER DE +0xB5 0x0415 # CYRILLIC CAPITAL LETTER IE +0xB6 0x0416 # CYRILLIC CAPITAL LETTER ZHE +0xB7 0x0417 # CYRILLIC CAPITAL LETTER ZE +0xB8 0x0418 # CYRILLIC CAPITAL LETTER I +0xB9 0x0419 # CYRILLIC CAPITAL LETTER SHORT I +0xBA 0x041A # CYRILLIC CAPITAL LETTER KA +0xBB 0x041B # CYRILLIC CAPITAL LETTER EL +0xBC 0x041C # CYRILLIC CAPITAL LETTER EM +0xBD 0x041D # CYRILLIC CAPITAL LETTER EN +0xBE 0x041E # CYRILLIC CAPITAL LETTER O +0xBF 0x041F # CYRILLIC CAPITAL LETTER PE +0xC0 0x0420 # CYRILLIC CAPITAL LETTER ER +0xC1 0x0421 # CYRILLIC CAPITAL LETTER ES +0xC2 0x0422 # CYRILLIC CAPITAL LETTER TE +0xC3 0x0423 # CYRILLIC CAPITAL LETTER U +0xC4 0x0424 # CYRILLIC CAPITAL LETTER EF +0xC5 0x0425 # CYRILLIC CAPITAL LETTER HA +0xC6 0x0426 # CYRILLIC CAPITAL LETTER TSE +0xC7 0x0427 # CYRILLIC CAPITAL LETTER CHE +0xC8 0x0428 # CYRILLIC CAPITAL LETTER SHA +0xC9 0x0429 # CYRILLIC CAPITAL LETTER SHCHA +0xCA 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN +0xCB 0x042B # CYRILLIC CAPITAL LETTER YERU +0xCC 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN +0xCD 0x042D # CYRILLIC CAPITAL LETTER E +0xCE 0x042E # CYRILLIC CAPITAL LETTER YU +0xCF 0x042F # CYRILLIC CAPITAL LETTER YA +0xD0 0x0430 # CYRILLIC SMALL LETTER A +0xD1 0x0431 # CYRILLIC SMALL LETTER BE +0xD2 0x0432 # CYRILLIC SMALL LETTER VE +0xD3 0x0433 # CYRILLIC SMALL LETTER GHE +0xD4 0x0434 # CYRILLIC SMALL LETTER DE +0xD5 0x0435 # CYRILLIC SMALL LETTER IE +0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE +0xD7 0x0437 # CYRILLIC SMALL LETTER ZE +0xD8 0x0438 # CYRILLIC SMALL LETTER I +0xD9 0x0439 # CYRILLIC SMALL LETTER SHORT I +0xDA 0x043A # CYRILLIC SMALL LETTER KA +0xDB 0x043B # CYRILLIC SMALL LETTER EL +0xDC 0x043C # CYRILLIC SMALL LETTER EM +0xDD 0x043D # CYRILLIC SMALL LETTER EN +0xDE 0x043E # CYRILLIC SMALL LETTER O +0xDF 0x043F # CYRILLIC SMALL LETTER PE +0xE0 0x0440 # CYRILLIC SMALL LETTER ER +0xE1 0x0441 # CYRILLIC SMALL LETTER ES +0xE2 0x0442 # CYRILLIC SMALL LETTER TE +0xE3 0x0443 # CYRILLIC SMALL LETTER U +0xE4 0x0444 # CYRILLIC SMALL LETTER EF +0xE5 0x0445 # CYRILLIC SMALL LETTER HA +0xE6 0x0446 # CYRILLIC SMALL LETTER TSE +0xE7 0x0447 # CYRILLIC SMALL LETTER CHE +0xE8 0x0448 # CYRILLIC SMALL LETTER SHA +0xE9 0x0449 # CYRILLIC SMALL LETTER SHCHA +0xEA 0x044A # CYRILLIC SMALL LETTER HARD SIGN +0xEB 0x044B # CYRILLIC SMALL LETTER YERU +0xEC 0x044C # CYRILLIC SMALL LETTER SOFT SIGN +0xED 0x044D # CYRILLIC SMALL LETTER E +0xEE 0x044E # CYRILLIC SMALL LETTER YU +0xEF 0x044F # CYRILLIC SMALL LETTER YA +0xF0 0x2116 # NUMERO SIGN +0xF1 0x0451 # CYRILLIC SMALL LETTER IO +0xF2 0x0452 # CYRILLIC SMALL LETTER DJE +0xF3 0x0453 # CYRILLIC SMALL LETTER GJE +0xF4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE +0xF5 0x0455 # CYRILLIC SMALL LETTER DZE +0xF6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +0xF7 0x0457 # CYRILLIC SMALL LETTER YI +0xF8 0x0458 # CYRILLIC SMALL LETTER JE +0xF9 0x0459 # CYRILLIC SMALL LETTER LJE +0xFA 0x045A # CYRILLIC SMALL LETTER NJE +0xFB 0x045B # CYRILLIC SMALL LETTER TSHE +0xFC 0x045C # CYRILLIC SMALL LETTER KJE +0xFD 0x00A7 # SECTION SIGN +0xFE 0x045E # CYRILLIC SMALL LETTER SHORT U +0xFF 0x045F # CYRILLIC SMALL LETTER DZHE diff --git a/Unicode/8859_6.cp b/Unicode/8859_6.cp new file mode 100644 index 0000000..9078c08 --- /dev/null +++ b/Unicode/8859_6.cp @@ -0,0 +1,262 @@ +ISO 8859-6 (Arabic) +"ISO-8859-6", "8859-6" +# +# Name: ISO 8859-6:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> +# +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on optical media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-6:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-6 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-6 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# 0x30..0x39 remapped to the ASCII digits (U+0030..U+0039) instead +# of the Arabic digits (U+0660..U+0669). +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # <control> +0x81 0x0081 # <control> +0x82 0x0082 # <control> +0x83 0x0083 # <control> +0x84 0x0084 # <control> +0x85 0x0085 # <control> +0x86 0x0086 # <control> +0x87 0x0087 # <control> +0x88 0x0088 # <control> +0x89 0x0089 # <control> +0x8A 0x008A # <control> +0x8B 0x008B # <control> +0x8C 0x008C # <control> +0x8D 0x008D # <control> +0x8E 0x008E # <control> +0x8F 0x008F # <control> +0x90 0x0090 # <control> +0x91 0x0091 # <control> +0x92 0x0092 # <control> +0x93 0x0093 # <control> +0x94 0x0094 # <control> +0x95 0x0095 # <control> +0x96 0x0096 # <control> +0x97 0x0097 # <control> +0x98 0x0098 # <control> +0x99 0x0099 # <control> +0x9A 0x009A # <control> +0x9B 0x009B # <control> +0x9C 0x009C # <control> +0x9D 0x009D # <control> +0x9E 0x009E # <control> +0x9F 0x009F # <control> +0xA0 0x00A0 # NO-BREAK SPACE +0xA4 0x00A4 # CURRENCY SIGN +0xAC 0x060C # ARABIC COMMA +0xAD 0x00AD # SOFT HYPHEN +0xBB 0x061B # ARABIC SEMICOLON +0xBF 0x061F # ARABIC QUESTION MARK +0xC1 0x0621 # ARABIC LETTER HAMZA +0xC2 0x0622 # ARABIC LETTER ALEF WITH MADDA ABOVE +0xC3 0x0623 # ARABIC LETTER ALEF WITH HAMZA ABOVE +0xC4 0x0624 # ARABIC LETTER WAW WITH HAMZA ABOVE +0xC5 0x0625 # ARABIC LETTER ALEF WITH HAMZA BELOW +0xC6 0x0626 # ARABIC LETTER YEH WITH HAMZA ABOVE +0xC7 0x0627 # ARABIC LETTER ALEF +0xC8 0x0628 # ARABIC LETTER BEH +0xC9 0x0629 # ARABIC LETTER TEH MARBUTA +0xCA 0x062A # ARABIC LETTER TEH +0xCB 0x062B # ARABIC LETTER THEH +0xCC 0x062C # ARABIC LETTER JEEM +0xCD 0x062D # ARABIC LETTER HAH +0xCE 0x062E # ARABIC LETTER KHAH +0xCF 0x062F # ARABIC LETTER DAL +0xD0 0x0630 # ARABIC LETTER THAL +0xD1 0x0631 # ARABIC LETTER REH +0xD2 0x0632 # ARABIC LETTER ZAIN +0xD3 0x0633 # ARABIC LETTER SEEN +0xD4 0x0634 # ARABIC LETTER SHEEN +0xD5 0x0635 # ARABIC LETTER SAD +0xD6 0x0636 # ARABIC LETTER DAD +0xD7 0x0637 # ARABIC LETTER TAH +0xD8 0x0638 # ARABIC LETTER ZAH +0xD9 0x0639 # ARABIC LETTER AIN +0xDA 0x063A # ARABIC LETTER GHAIN +0xE0 0x0640 # ARABIC TATWEEL +0xE1 0x0641 # ARABIC LETTER FEH +0xE2 0x0642 # ARABIC LETTER QAF +0xE3 0x0643 # ARABIC LETTER KAF +0xE4 0x0644 # ARABIC LETTER LAM +0xE5 0x0645 # ARABIC LETTER MEEM +0xE6 0x0646 # ARABIC LETTER NOON +0xE7 0x0647 # ARABIC LETTER HEH +0xE8 0x0648 # ARABIC LETTER WAW +0xE9 0x0649 # ARABIC LETTER ALEF MAKSURA +0xEA 0x064A # ARABIC LETTER YEH +0xEB 0x064B # ARABIC FATHATAN +0xEC 0x064C # ARABIC DAMMATAN +0xED 0x064D # ARABIC KASRATAN +0xEE 0x064E # ARABIC FATHA +0xEF 0x064F # ARABIC DAMMA +0xF0 0x0650 # ARABIC KASRA +0xF1 0x0651 # ARABIC SHADDA +0xF2 0x0652 # ARABIC SUKUN diff --git a/Unicode/8859_7.cp b/Unicode/8859_7.cp new file mode 100644 index 0000000..59731a0 --- /dev/null +++ b/Unicode/8859_7.cp @@ -0,0 +1,304 @@ +ISO 8859-7 (Greek) +"ISO-8859-7", "8859-7", "iso-ir-126", "elot-928" +# +# Name: ISO 8859-7:1987 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> +# +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on optical media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO 8859-7:1987 characters map into Unicode. +# +# ISO 8859-7:1987 is equivalent to ISO-IR-126, ELOT 928, +# and ECMA 118. +# +# Format: Three tab-separated columns +# Column #1 is the ISO 8859-7 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO 8859-7 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# Remap 0xA1 to U+2018 (instead of 0x02BD) to match text of 8859-7 +# Remap 0xA2 to U+2019 (instead of 0x02BC) to match text of 8859-7 +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # <control> +0x81 0x0081 # <control> +0x82 0x0082 # <control> +0x83 0x0083 # <control> +0x84 0x0084 # <control> +0x85 0x0085 # <control> +0x86 0x0086 # <control> +0x87 0x0087 # <control> +0x88 0x0088 # <control> +0x89 0x0089 # <control> +0x8A 0x008A # <control> +0x8B 0x008B # <control> +0x8C 0x008C # <control> +0x8D 0x008D # <control> +0x8E 0x008E # <control> +0x8F 0x008F # <control> +0x90 0x0090 # <control> +0x91 0x0091 # <control> +0x92 0x0092 # <control> +0x93 0x0093 # <control> +0x94 0x0094 # <control> +0x95 0x0095 # <control> +0x96 0x0096 # <control> +0x97 0x0097 # <control> +0x98 0x0098 # <control> +0x99 0x0099 # <control> +0x9A 0x009A # <control> +0x9B 0x009B # <control> +0x9C 0x009C # <control> +0x9D 0x009D # <control> +0x9E 0x009E # <control> +0x9F 0x009F # <control> +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x2018 # LEFT SINGLE QUOTATION MARK +0xA2 0x2019 # RIGHT SINGLE QUOTATION MARK +0xA3 0x00A3 # POUND SIGN +0xA6 0x00A6 # BROKEN BAR +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x00A9 # COPYRIGHT SIGN +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC # NOT SIGN +0xAD 0x00AD # SOFT HYPHEN +0xAF 0x2015 # HORIZONTAL BAR +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x0384 # GREEK TONOS +0xB5 0x0385 # GREEK DIALYTIKA TONOS +0xB6 0x0386 # GREEK CAPITAL LETTER ALPHA WITH TONOS +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x0388 # GREEK CAPITAL LETTER EPSILON WITH TONOS +0xB9 0x0389 # GREEK CAPITAL LETTER ETA WITH TONOS +0xBA 0x038A # GREEK CAPITAL LETTER IOTA WITH TONOS +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x038C # GREEK CAPITAL LETTER OMICRON WITH TONOS +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBE 0x038E # GREEK CAPITAL LETTER UPSILON WITH TONOS +0xBF 0x038F # GREEK CAPITAL LETTER OMEGA WITH TONOS +0xC0 0x0390 # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS +0xC1 0x0391 # GREEK CAPITAL LETTER ALPHA +0xC2 0x0392 # GREEK CAPITAL LETTER BETA +0xC3 0x0393 # GREEK CAPITAL LETTER GAMMA +0xC4 0x0394 # GREEK CAPITAL LETTER DELTA +0xC5 0x0395 # GREEK CAPITAL LETTER EPSILON +0xC6 0x0396 # GREEK CAPITAL LETTER ZETA +0xC7 0x0397 # GREEK CAPITAL LETTER ETA +0xC8 0x0398 # GREEK CAPITAL LETTER THETA +0xC9 0x0399 # GREEK CAPITAL LETTER IOTA +0xCA 0x039A # GREEK CAPITAL LETTER KAPPA +0xCB 0x039B # GREEK CAPITAL LETTER LAMDA +0xCC 0x039C # GREEK CAPITAL LETTER MU +0xCD 0x039D # GREEK CAPITAL LETTER NU +0xCE 0x039E # GREEK CAPITAL LETTER XI +0xCF 0x039F # GREEK CAPITAL LETTER OMICRON +0xD0 0x03A0 # GREEK CAPITAL LETTER PI +0xD1 0x03A1 # GREEK CAPITAL LETTER RHO +0xD3 0x03A3 # GREEK CAPITAL LETTER SIGMA +0xD4 0x03A4 # GREEK CAPITAL LETTER TAU +0xD5 0x03A5 # GREEK CAPITAL LETTER UPSILON +0xD6 0x03A6 # GREEK CAPITAL LETTER PHI +0xD7 0x03A7 # GREEK CAPITAL LETTER CHI +0xD8 0x03A8 # GREEK CAPITAL LETTER PSI +0xD9 0x03A9 # GREEK CAPITAL LETTER OMEGA +0xDA 0x03AA # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA +0xDB 0x03AB # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA +0xDC 0x03AC # GREEK SMALL LETTER ALPHA WITH TONOS +0xDD 0x03AD # GREEK SMALL LETTER EPSILON WITH TONOS +0xDE 0x03AE # GREEK SMALL LETTER ETA WITH TONOS +0xDF 0x03AF # GREEK SMALL LETTER IOTA WITH TONOS +0xE0 0x03B0 # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS +0xE1 0x03B1 # GREEK SMALL LETTER ALPHA +0xE2 0x03B2 # GREEK SMALL LETTER BETA +0xE3 0x03B3 # GREEK SMALL LETTER GAMMA +0xE4 0x03B4 # GREEK SMALL LETTER DELTA +0xE5 0x03B5 # GREEK SMALL LETTER EPSILON +0xE6 0x03B6 # GREEK SMALL LETTER ZETA +0xE7 0x03B7 # GREEK SMALL LETTER ETA +0xE8 0x03B8 # GREEK SMALL LETTER THETA +0xE9 0x03B9 # GREEK SMALL LETTER IOTA +0xEA 0x03BA # GREEK SMALL LETTER KAPPA +0xEB 0x03BB # GREEK SMALL LETTER LAMDA +0xEC 0x03BC # GREEK SMALL LETTER MU +0xED 0x03BD # GREEK SMALL LETTER NU +0xEE 0x03BE # GREEK SMALL LETTER XI +0xEF 0x03BF # GREEK SMALL LETTER OMICRON +0xF0 0x03C0 # GREEK SMALL LETTER PI +0xF1 0x03C1 # GREEK SMALL LETTER RHO +0xF2 0x03C2 # GREEK SMALL LETTER FINAL SIGMA +0xF3 0x03C3 # GREEK SMALL LETTER SIGMA +0xF4 0x03C4 # GREEK SMALL LETTER TAU +0xF5 0x03C5 # GREEK SMALL LETTER UPSILON +0xF6 0x03C6 # GREEK SMALL LETTER PHI +0xF7 0x03C7 # GREEK SMALL LETTER CHI +0xF8 0x03C8 # GREEK SMALL LETTER PSI +0xF9 0x03C9 # GREEK SMALL LETTER OMEGA +0xFA 0x03CA # GREEK SMALL LETTER IOTA WITH DIALYTIKA +0xFB 0x03CB # GREEK SMALL LETTER UPSILON WITH DIALYTIKA +0xFC 0x03CC # GREEK SMALL LETTER OMICRON WITH TONOS +0xFD 0x03CD # GREEK SMALL LETTER UPSILON WITH TONOS +0xFE 0x03CE # GREEK SMALL LETTER OMEGA WITH TONOS diff --git a/Unicode/8859_8.cp b/Unicode/8859_8.cp new file mode 100644 index 0000000..887cf2b --- /dev/null +++ b/Unicode/8859_8.cp @@ -0,0 +1,272 @@ +ISO 8859-8 (Hebrew) +"ISO-8859-8", "8859-8" +# +# Name: ISO/IEC 8859-8:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.1 +# Table format: Format A +# Date: 2000-Jan-03 +# Authors: Ken Whistler <kenw@sybase.com> +# +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on optical media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-8:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-8 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-8 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# 1.1 version updates to the published 8859-8:1999, correcting +# the mapping of 0xAF and adding mappings for LRM and RLM. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # <control> +0x81 0x0081 # <control> +0x82 0x0082 # <control> +0x83 0x0083 # <control> +0x84 0x0084 # <control> +0x85 0x0085 # <control> +0x86 0x0086 # <control> +0x87 0x0087 # <control> +0x88 0x0088 # <control> +0x89 0x0089 # <control> +0x8A 0x008A # <control> +0x8B 0x008B # <control> +0x8C 0x008C # <control> +0x8D 0x008D # <control> +0x8E 0x008E # <control> +0x8F 0x008F # <control> +0x90 0x0090 # <control> +0x91 0x0091 # <control> +0x92 0x0092 # <control> +0x93 0x0093 # <control> +0x94 0x0094 # <control> +0x95 0x0095 # <control> +0x96 0x0096 # <control> +0x97 0x0097 # <control> +0x98 0x0098 # <control> +0x99 0x0099 # <control> +0x9A 0x009A # <control> +0x9B 0x009B # <control> +0x9C 0x009C # <control> +0x9D 0x009D # <control> +0x9E 0x009E # <control> +0x9F 0x009F # <control> +0xA0 0x00A0 # NO-BREAK SPACE +0xA2 0x00A2 # CENT SIGN +0xA3 0x00A3 # POUND SIGN +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x00A5 # YEN SIGN +0xA6 0x00A6 # BROKEN BAR +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x00D7 # MULTIPLICATION SIGN +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC # NOT SIGN +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x00AE # REGISTERED SIGN +0xAF 0x00AF # MACRON +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x00B5 # MICRO SIGN +0xB6 0x00B6 # PILCROW SIGN +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x00B8 # CEDILLA +0xB9 0x00B9 # SUPERSCRIPT ONE +0xBA 0x00F7 # DIVISION SIGN +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC # VULGAR FRACTION ONE QUARTER +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS +0xDF 0x2017 # DOUBLE LOW LINE +0xE0 0x05D0 # HEBREW LETTER ALEF +0xE1 0x05D1 # HEBREW LETTER BET +0xE2 0x05D2 # HEBREW LETTER GIMEL +0xE3 0x05D3 # HEBREW LETTER DALET +0xE4 0x05D4 # HEBREW LETTER HE +0xE5 0x05D5 # HEBREW LETTER VAV +0xE6 0x05D6 # HEBREW LETTER ZAYIN +0xE7 0x05D7 # HEBREW LETTER HET +0xE8 0x05D8 # HEBREW LETTER TET +0xE9 0x05D9 # HEBREW LETTER YOD +0xEA 0x05DA # HEBREW LETTER FINAL KAF +0xEB 0x05DB # HEBREW LETTER KAF +0xEC 0x05DC # HEBREW LETTER LAMED +0xED 0x05DD # HEBREW LETTER FINAL MEM +0xEE 0x05DE # HEBREW LETTER MEM +0xEF 0x05DF # HEBREW LETTER FINAL NUN +0xF0 0x05E0 # HEBREW LETTER NUN +0xF1 0x05E1 # HEBREW LETTER SAMEKH +0xF2 0x05E2 # HEBREW LETTER AYIN +0xF3 0x05E3 # HEBREW LETTER FINAL PE +0xF4 0x05E4 # HEBREW LETTER PE +0xF5 0x05E5 # HEBREW LETTER FINAL TSADI +0xF6 0x05E6 # HEBREW LETTER TSADI +0xF7 0x05E7 # HEBREW LETTER QOF +0xF8 0x05E8 # HEBREW LETTER RESH +0xF9 0x05E9 # HEBREW LETTER SHIN +0xFA 0x05EA # HEBREW LETTER TAV +0xFD 0x200E # LEFT-TO-RIGHT MARK +0xFE 0x200F # RIGHT-TO-LEFT MARK + diff --git a/Unicode/8859_9.cp b/Unicode/8859_9.cp new file mode 100644 index 0000000..290a511 --- /dev/null +++ b/Unicode/8859_9.cp @@ -0,0 +1,309 @@ +ISO 8859-9 (Turkish) +"ISO-8859-9", "8859-9" +# +# Name: ISO/IEC 8859-9:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> +# +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on magnetic media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-9:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-9 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-9 order. +# +# ISO/IEC 8859-9 is also equivalent to ISO-IR-148. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # <control> +0x81 0x0081 # <control> +0x82 0x0082 # <control> +0x83 0x0083 # <control> +0x84 0x0084 # <control> +0x85 0x0085 # <control> +0x86 0x0086 # <control> +0x87 0x0087 # <control> +0x88 0x0088 # <control> +0x89 0x0089 # <control> +0x8A 0x008A # <control> +0x8B 0x008B # <control> +0x8C 0x008C # <control> +0x8D 0x008D # <control> +0x8E 0x008E # <control> +0x8F 0x008F # <control> +0x90 0x0090 # <control> +0x91 0x0091 # <control> +0x92 0x0092 # <control> +0x93 0x0093 # <control> +0x94 0x0094 # <control> +0x95 0x0095 # <control> +0x96 0x0096 # <control> +0x97 0x0097 # <control> +0x98 0x0098 # <control> +0x99 0x0099 # <control> +0x9A 0x009A # <control> +0x9B 0x009B # <control> +0x9C 0x009C # <control> +0x9D 0x009D # <control> +0x9E 0x009E # <control> +0x9F 0x009F # <control> +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x00A1 # INVERTED EXCLAMATION MARK +0xA2 0x00A2 # CENT SIGN +0xA3 0x00A3 # POUND SIGN +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x00A5 # YEN SIGN +0xA6 0x00A6 # BROKEN BAR +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x00AA # FEMININE ORDINAL INDICATOR +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC # NOT SIGN +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x00AE # REGISTERED SIGN +0xAF 0x00AF # MACRON +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x00B5 # MICRO SIGN +0xB6 0x00B6 # PILCROW SIGN +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x00B8 # CEDILLA +0xB9 0x00B9 # SUPERSCRIPT ONE +0xBA 0x00BA # MASCULINE ORDINAL INDICATOR +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC # VULGAR FRACTION ONE QUARTER +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF # INVERTED QUESTION MARK +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 # LATIN CAPITAL LETTER AE +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x011E # LATIN CAPITAL LETTER G WITH BREVE +0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE +0xDE 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 # LATIN SMALL LETTER AE +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x011F # LATIN SMALL LETTER G WITH BREVE +0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x0131 # LATIN SMALL LETTER DOTLESS I +0xFE 0x015F # LATIN SMALL LETTER S WITH CEDILLA +0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS + + diff --git a/Unicode/cp1125.cp b/Unicode/cp1125.cp new file mode 100644 index 0000000..177e953 --- /dev/null +++ b/Unicode/cp1125.cp @@ -0,0 +1,137 @@ +CP 1125 (Ukrainian) +"x-cp866-u", "ruscii", "1125" +# +# DOS Ukrainian (RUSCII, cp1125) to UNICODE translation table +# +# Based on cp866u_uni.tbl from lynx 2.8.2 distribution +# by porokh +# +0x80 0x0410 #CYRILLIC CAPITAL LETTER A +0x81 0x0411 #CYRILLIC CAPITAL LETTER BE +0x82 0x0412 #CYRILLIC CAPITAL LETTER VE +0x83 0x0413 #CYRILLIC CAPITAL LETTER GHE +0x84 0x0414 #CYRILLIC CAPITAL LETTER DE +0x85 0x0415 #CYRILLIC CAPITAL LETTER IE +0x86 0x0416 #CYRILLIC CAPITAL LETTER ZHE +0x87 0x0417 #CYRILLIC CAPITAL LETTER ZE +0x88 0x0418 #CYRILLIC CAPITAL LETTER I +0x89 0x0419 #CYRILLIC CAPITAL LETTER SHORT I +0x8a 0x041a #CYRILLIC CAPITAL LETTER KA +0x8b 0x041b #CYRILLIC CAPITAL LETTER EL +0x8c 0x041c #CYRILLIC CAPITAL LETTER EM +0x8d 0x041d #CYRILLIC CAPITAL LETTER EN +0x8e 0x041e #CYRILLIC CAPITAL LETTER O +0x8f 0x041f #CYRILLIC CAPITAL LETTER PE +0x90 0x0420 #CYRILLIC CAPITAL LETTER ER +0x91 0x0421 #CYRILLIC CAPITAL LETTER ES +0x92 0x0422 #CYRILLIC CAPITAL LETTER TE +0x93 0x0423 #CYRILLIC CAPITAL LETTER U +0x94 0x0424 #CYRILLIC CAPITAL LETTER EF +0x95 0x0425 #CYRILLIC CAPITAL LETTER HA +0x96 0x0426 #CYRILLIC CAPITAL LETTER TSE +0x97 0x0427 #CYRILLIC CAPITAL LETTER CHE +0x98 0x0428 #CYRILLIC CAPITAL LETTER SHA +0x99 0x0429 #CYRILLIC CAPITAL LETTER SHCHA +0x9a 0x042a #CYRILLIC CAPITAL LETTER HARD SIGN +0x9b 0x042b #CYRILLIC CAPITAL LETTER YERU +0x9c 0x042c #CYRILLIC CAPITAL LETTER SOFT SIGN +0x9d 0x042d #CYRILLIC CAPITAL LETTER E +0x9e 0x042e #CYRILLIC CAPITAL LETTER YU +0x9f 0x042f #CYRILLIC CAPITAL LETTER YA +0xa0 0x0430 #CYRILLIC SMALL LETTER A +0xa1 0x0431 #CYRILLIC SMALL LETTER BE +0xa2 0x0432 #CYRILLIC SMALL LETTER VE +0xa3 0x0433 #CYRILLIC SMALL LETTER GHE +0xa4 0x0434 #CYRILLIC SMALL LETTER DE +0xa5 0x0435 #CYRILLIC SMALL LETTER IE +0xa6 0x0436 #CYRILLIC SMALL LETTER ZHE +0xa7 0x0437 #CYRILLIC SMALL LETTER ZE +0xa8 0x0438 #CYRILLIC SMALL LETTER I +0xa9 0x0439 #CYRILLIC SMALL LETTER SHORT I +0xaa 0x043a #CYRILLIC SMALL LETTER KA +0xab 0x043b #CYRILLIC SMALL LETTER EL +0xac 0x043c #CYRILLIC SMALL LETTER EM +0xad 0x043d #CYRILLIC SMALL LETTER EN +0xae 0x043e #CYRILLIC SMALL LETTER O +0xaf 0x043f #CYRILLIC SMALL LETTER PE +0xb0 0x2591 #LIGHT SHADE +0xb1 0x2592 #MEDIUM SHADE +0xb2 0x2593 #DARK SHADE +0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL +0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT +0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE +0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE +0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE +0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL +0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT +0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT +0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE +0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT +0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT +0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL +0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL +0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT +0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL +0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE +0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE +0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE +0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE +0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT +0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT +0xdb 0x2588 #FULL BLOCK +0xdc 0x2584 #LOWER HALF BLOCK +0xdd 0x258c #LEFT HALF BLOCK +0xde 0x2590 #RIGHT HALF BLOCK +0xdf 0x2580 #UPPER HALF BLOCK +0xe0 0x0440 #CYRILLIC SMALL LETTER ER +0xe1 0x0441 #CYRILLIC SMALL LETTER ES +0xe2 0x0442 #CYRILLIC SMALL LETTER TE +0xe3 0x0443 #CYRILLIC SMALL LETTER U +0xe4 0x0444 #CYRILLIC SMALL LETTER EF +0xe5 0x0445 #CYRILLIC SMALL LETTER HA +0xe6 0x0446 #CYRILLIC SMALL LETTER TSE +0xe7 0x0447 #CYRILLIC SMALL LETTER CHE +0xe8 0x0448 #CYRILLIC SMALL LETTER SHA +0xe9 0x0449 #CYRILLIC SMALL LETTER SHCHA +0xea 0x044a #CYRILLIC SMALL LETTER HARD SIGN +0xeb 0x044b #CYRILLIC SMALL LETTER YERU +0xec 0x044c #CYRILLIC SMALL LETTER SOFT SIGN +0xed 0x044d #CYRILLIC SMALL LETTER E +0xee 0x044e #CYRILLIC SMALL LETTER YU +0xef 0x044f #CYRILLIC SMALL LETTER YA +0xf0 0x0401 #CYRILLIC CAPITAL LETTER IO +0xf1 0x0451 #CYRILLIC SMALL LETTER IO +0xf2 0x0490 #CYRILLIC CAPITAL LETTER GHE WITH UPTURN +0xf3 0x0491 #CYRILLIC SMALL LETTER GHE WITH UPTURN +0xf4 0x0404 #CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xf5 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE +0xf6 0x0406 #CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0xf7 0x0456 #CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +0xf8 0x0407 #CYRILLIC CAPITAL LETTER YI +0xf9 0x0457 #CYRILLIC SMALL LETTER YI +0xfa 0x00b7 #MIDDLE DOT +0xfb 0x221a #SQUARE ROOT +0xfc 0x2116 #NUMERO SIGN +0xfd 0x00a4 #CURRENCY SIGN +0xfe 0x25a0 #BLACK SQUARE +0xff 0x00a0 #NO-BREAK SPACE + diff --git a/Unicode/cp1250.cp b/Unicode/cp1250.cp new file mode 100644 index 0000000..41f05ef --- /dev/null +++ b/Unicode/cp1250.cp @@ -0,0 +1,276 @@ +Window$ 1250 (Central European) +"windows-1250", "1250" +# +# Name: cp1250 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1250 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1250 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x20AC #EURO SIGN +0x81 0 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0 #UNDEFINED +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +#0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0 #UNDEFINED +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x015A #LATIN CAPITAL LETTER S WITH ACUTE +0x8D 0x0164 #LATIN CAPITAL LETTER T WITH CARON +0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0x8F 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE +0x90 0 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +#0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0 #UNDEFINED +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x015B #LATIN SMALL LETTER S WITH ACUTE +0x9D 0x0165 #LATIN SMALL LETTER T WITH CARON +0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON +0x9F 0x017A #LATIN SMALL LETTER Z WITH ACUTE +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x02C7 #CARON +0xA2 0x02D8 #BREVE +0xA3 0x0141 #LATIN CAPITAL LETTER L WITH STROKE +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x02DB #OGONEK +0xB3 0x0142 #LATIN SMALL LETTER L WITH STROKE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +#0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x0105 #LATIN SMALL LETTER A WITH OGONEK +0xBA 0x015F #LATIN SMALL LETTER S WITH CEDILLA +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x013D #LATIN CAPITAL LETTER L WITH CARON +0xBD 0x02DD #DOUBLE ACUTE ACCENT +0xBE 0x013E #LATIN SMALL LETTER L WITH CARON +0xBF 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE +0xC0 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE +0xC6 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x011A #LATIN CAPITAL LETTER E WITH CARON +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x010E #LATIN CAPITAL LETTER D WITH CARON +0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE +0xD2 0x0147 #LATIN CAPITAL LETTER N WITH CARON +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x0158 #LATIN CAPITAL LETTER R WITH CARON +0xD9 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x0155 #LATIN SMALL LETTER R WITH ACUTE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x013A #LATIN SMALL LETTER L WITH ACUTE +0xE6 0x0107 #LATIN SMALL LETTER C WITH ACUTE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x010D #LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x0119 #LATIN SMALL LETTER E WITH OGONEK +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x011B #LATIN SMALL LETTER E WITH CARON +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x010F #LATIN SMALL LETTER D WITH CARON +0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE +0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE +0xF2 0x0148 #LATIN SMALL LETTER N WITH CARON +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x0159 #LATIN SMALL LETTER R WITH CARON +0xF9 0x016F #LATIN SMALL LETTER U WITH RING ABOVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x0163 #LATIN SMALL LETTER T WITH CEDILLA +0xFF 0x02D9 #DOT ABOVE diff --git a/Unicode/cp1251.cp b/Unicode/cp1251.cp new file mode 100644 index 0000000..58e891b --- /dev/null +++ b/Unicode/cp1251.cp @@ -0,0 +1,225 @@ +Window$ 1251 (Cyrillic) +"windows-1251", "1251", "cp1251" + +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x80 0x0402 # CYRILLIC CAPITAL LETTER DJE +0x81 0x0403 # CYRILLIC CAPITAL LETTER GJE +0x82 0x201A # SINGLE LOW-9 QUOTATION MARK +0x83 0x0453 # CYRILLIC SMALL LETTER GJE +0x84 0x201E # DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 # HORIZONTAL ELLIPSIS +0x86 0x2020 # DAGGER +0x87 0x2021 # DOUBLE DAGGER +0x88 0x20AC # EURO SIGN +0x89 0x2030 # PER MILLE SIGN +0x8A 0x0409 # CYRILLIC CAPITAL LETTER LJE +0x8B 0x2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x040A # CYRILLIC CAPITAL LETTER NJE +0x8D 0x040C # CYRILLIC CAPITAL LETTER KJE +0x8E 0x040B # CYRILLIC CAPITAL LETTER TSHE +0x8F 0x040F # CYRILLIC CAPITAL LETTER DZHE +0x90 0x0452 # CYRILLIC SMALL LETTER DJE +0x91 0x2018 # LEFT SINGLE QUOTATION MARK +0x92 0x2019 # RIGHT SINGLE QUOTATION MARK +0x93 0x201C # LEFT DOUBLE QUOTATION MARK +0x94 0x201D # RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 # BULLET +0x96 0x2013 # EN DASH +0x97 0x2014 # EM DASH +0x99 0x2122 # TRADE MARK SIGN +0x9A 0x0459 # CYRILLIC SMALL LETTER LJE +0x9B 0x203A # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x045A # CYRILLIC SMALL LETTER NJE +0x9D 0x045C # CYRILLIC SMALL LETTER KJE +0x9E 0x045B # CYRILLIC SMALL LETTER TSHE +0x9F 0x045F # CYRILLIC SMALL LETTER DZHE +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x040E # CYRILLIC CAPITAL LETTER SHORT U +0xA2 0x045E # CYRILLIC SMALL LETTER SHORT U +0xA3 0x0408 # CYRILLIC CAPITAL LETTER JE +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x0490 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN +0xA6 0x00A6 # BROKEN BAR +0xA7 0x00A7 # SECTION SIGN +0xA8 0x0401 # CYRILLIC CAPITAL LETTER IO +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC # NOT SIGN +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x00AE # REGISTERED SIGN +0xAF 0x0407 # CYRILLIC CAPITAL LETTER YI +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0xB3 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +0xB4 0x0491 # CYRILLIC SMALL LETTER GHE WITH UPTURN +0xB5 0x00B5 # MICRO SIGN +0xB6 0x00B6 # PILCROW SIGN +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x0451 # CYRILLIC SMALL LETTER IO +0xB9 0x2116 # NUMERO SIGN +0xBA 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x0458 # CYRILLIC SMALL LETTER JE +0xBD 0x0405 # CYRILLIC CAPITAL LETTER DZE +0xBE 0x0455 # CYRILLIC SMALL LETTER DZE +0xBF 0x0457 # CYRILLIC SMALL LETTER YI +0xC0 0x0410 # CYRILLIC CAPITAL LETTER A +0xC1 0x0411 # CYRILLIC CAPITAL LETTER BE +0xC2 0x0412 # CYRILLIC CAPITAL LETTER VE +0xC3 0x0413 # CYRILLIC CAPITAL LETTER GHE +0xC4 0x0414 # CYRILLIC CAPITAL LETTER DE +0xC5 0x0415 # CYRILLIC CAPITAL LETTER IE +0xC6 0x0416 # CYRILLIC CAPITAL LETTER ZHE +0xC7 0x0417 # CYRILLIC CAPITAL LETTER ZE +0xC8 0x0418 # CYRILLIC CAPITAL LETTER I +0xC9 0x0419 # CYRILLIC CAPITAL LETTER SHORT I +0xCA 0x041A # CYRILLIC CAPITAL LETTER KA +0xCB 0x041B # CYRILLIC CAPITAL LETTER EL +0xCC 0x041C # CYRILLIC CAPITAL LETTER EM +0xCD 0x041D # CYRILLIC CAPITAL LETTER EN +0xCE 0x041E # CYRILLIC CAPITAL LETTER O +0xCF 0x041F # CYRILLIC CAPITAL LETTER PE +0xD0 0x0420 # CYRILLIC CAPITAL LETTER ER +0xD1 0x0421 # CYRILLIC CAPITAL LETTER ES +0xD2 0x0422 # CYRILLIC CAPITAL LETTER TE +0xD3 0x0423 # CYRILLIC CAPITAL LETTER U +0xD4 0x0424 # CYRILLIC CAPITAL LETTER EF +0xD5 0x0425 # CYRILLIC CAPITAL LETTER HA +0xD6 0x0426 # CYRILLIC CAPITAL LETTER TSE +0xD7 0x0427 # CYRILLIC CAPITAL LETTER CHE +0xD8 0x0428 # CYRILLIC CAPITAL LETTER SHA +0xD9 0x0429 # CYRILLIC CAPITAL LETTER SHCHA +0xDA 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN +0xDB 0x042B # CYRILLIC CAPITAL LETTER YERU +0xDC 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN +0xDD 0x042D # CYRILLIC CAPITAL LETTER E +0xDE 0x042E # CYRILLIC CAPITAL LETTER YU +0xDF 0x042F # CYRILLIC CAPITAL LETTER YA +0xE0 0x0430 # CYRILLIC SMALL LETTER A +0xE1 0x0431 # CYRILLIC SMALL LETTER BE +0xE2 0x0432 # CYRILLIC SMALL LETTER VE +0xE3 0x0433 # CYRILLIC SMALL LETTER GHE +0xE4 0x0434 # CYRILLIC SMALL LETTER DE +0xE5 0x0435 # CYRILLIC SMALL LETTER IE +0xE6 0x0436 # CYRILLIC SMALL LETTER ZHE +0xE7 0x0437 # CYRILLIC SMALL LETTER ZE +0xE8 0x0438 # CYRILLIC SMALL LETTER I +0xE9 0x0439 # CYRILLIC SMALL LETTER SHORT I +0xEA 0x043A # CYRILLIC SMALL LETTER KA +0xEB 0x043B # CYRILLIC SMALL LETTER EL +0xEC 0x043C # CYRILLIC SMALL LETTER EM +0xED 0x043D # CYRILLIC SMALL LETTER EN +0xEE 0x043E # CYRILLIC SMALL LETTER O +0xEF 0x043F # CYRILLIC SMALL LETTER PE +0xF0 0x0440 # CYRILLIC SMALL LETTER ER +0xF1 0x0441 # CYRILLIC SMALL LETTER ES +0xF2 0x0442 # CYRILLIC SMALL LETTER TE +0xF3 0x0443 # CYRILLIC SMALL LETTER U +0xF4 0x0444 # CYRILLIC SMALL LETTER EF +0xF5 0x0445 # CYRILLIC SMALL LETTER HA +0xF6 0x0446 # CYRILLIC SMALL LETTER TSE +0xF7 0x0447 # CYRILLIC SMALL LETTER CHE +0xF8 0x0448 # CYRILLIC SMALL LETTER SHA +0xF9 0x0449 # CYRILLIC SMALL LETTER SHCHA +0xFA 0x044A # CYRILLIC SMALL LETTER HARD SIGN +0xFB 0x044B # CYRILLIC SMALL LETTER YERU +0xFC 0x044C # CYRILLIC SMALL LETTER SOFT SIGN +0xFD 0x044D # CYRILLIC SMALL LETTER E +0xFE 0x044E # CYRILLIC SMALL LETTER YU +0xFF 0x044F # CYRILLIC SMALL LETTER YA diff --git a/Unicode/cp1252.cp b/Unicode/cp1252.cp new file mode 100644 index 0000000..cf8d851 --- /dev/null +++ b/Unicode/cp1252.cp @@ -0,0 +1,254 @@ +Window$ 1252 (Western European) +"windows-1252", "1252" + +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x20AC #EURO SIGN +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x0152 #LATIN CAPITAL LIGATURE OE +0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x02DC #SMALL TILDE +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x0153 #LATIN SMALL LIGATURE OE +0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON +0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x00A1 #INVERTED EXCLAMATION MARK +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x00AA #FEMININE ORDINAL INDICATOR +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x00BA #MASCULINE ORDINAL INDICATOR +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF #INVERTED QUESTION MARK +0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 #LATIN CAPITAL LIGATURE AE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x00D0 #LATIN CAPITAL LETTER ETH +0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x00DE #LATIN CAPITAL LETTER THORN +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 #LATIN SMALL LIGATURE AE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x00F0 #LATIN SMALL LETTER ETH +0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x00FE #LATIN SMALL LETTER THORN +0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS diff --git a/Unicode/cp1256.cp b/Unicode/cp1256.cp new file mode 100644 index 0000000..57333f9 --- /dev/null +++ b/Unicode/cp1256.cp @@ -0,0 +1,276 @@ +Window$ 1256 (Arabic) +"windows-1256", "1256", "cp1256" +# +# Name: cp1256 to Unicode table +# Unicode version: 2.1 +# Table version: 2.01 +# Table format: Format A +# Date: 01/5/99 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1256 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1256 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x20AC #EURO SIGN +0x81 0x067E #ARABIC LETTER PEH +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0679 #ARABIC LETTER TTEH +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x0152 #LATIN CAPITAL LIGATURE OE +0x8D 0x0686 #ARABIC LETTER TCHEH +0x8E 0x0698 #ARABIC LETTER JEH +0x8F 0x0688 #ARABIC LETTER DDAL +0x90 0x06AF #ARABIC LETTER GAF +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x06A9 #ARABIC LETTER KEHEH +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0691 #ARABIC LETTER RREH +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x0153 #LATIN SMALL LIGATURE OE +0x9D 0x200C #ZERO WIDTH NON-JOINER +0x9E 0x200D #ZERO WIDTH JOINER +0x9F 0x06BA #ARABIC LETTER NOON GHUNNA +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x060C #ARABIC COMMA +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x06BE #ARABIC LETTER HEH DOACHASHMEE +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x061B #ARABIC SEMICOLON +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x061F #ARABIC QUESTION MARK +0xC0 0x06C1 #ARABIC LETTER HEH GOAL +0xC1 0x0621 #ARABIC LETTER HAMZA +0xC2 0x0622 #ARABIC LETTER ALEF WITH MADDA ABOVE +0xC3 0x0623 #ARABIC LETTER ALEF WITH HAMZA ABOVE +0xC4 0x0624 #ARABIC LETTER WAW WITH HAMZA ABOVE +0xC5 0x0625 #ARABIC LETTER ALEF WITH HAMZA BELOW +0xC6 0x0626 #ARABIC LETTER YEH WITH HAMZA ABOVE +0xC7 0x0627 #ARABIC LETTER ALEF +0xC8 0x0628 #ARABIC LETTER BEH +0xC9 0x0629 #ARABIC LETTER TEH MARBUTA +0xCA 0x062A #ARABIC LETTER TEH +0xCB 0x062B #ARABIC LETTER THEH +0xCC 0x062C #ARABIC LETTER JEEM +0xCD 0x062D #ARABIC LETTER HAH +0xCE 0x062E #ARABIC LETTER KHAH +0xCF 0x062F #ARABIC LETTER DAL +0xD0 0x0630 #ARABIC LETTER THAL +0xD1 0x0631 #ARABIC LETTER REH +0xD2 0x0632 #ARABIC LETTER ZAIN +0xD3 0x0633 #ARABIC LETTER SEEN +0xD4 0x0634 #ARABIC LETTER SHEEN +0xD5 0x0635 #ARABIC LETTER SAD +0xD6 0x0636 #ARABIC LETTER DAD +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x0637 #ARABIC LETTER TAH +0xD9 0x0638 #ARABIC LETTER ZAH +0xDA 0x0639 #ARABIC LETTER AIN +0xDB 0x063A #ARABIC LETTER GHAIN +0xDC 0x0640 #ARABIC TATWEEL +0xDD 0x0641 #ARABIC LETTER FEH +0xDE 0x0642 #ARABIC LETTER QAF +0xDF 0x0643 #ARABIC LETTER KAF +0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0xE1 0x0644 #ARABIC LETTER LAM +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0645 #ARABIC LETTER MEEM +0xE4 0x0646 #ARABIC LETTER NOON +0xE5 0x0647 #ARABIC LETTER HEH +0xE6 0x0648 #ARABIC LETTER WAW +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x0649 #ARABIC LETTER ALEF MAKSURA +0xED 0x064A #ARABIC LETTER YEH +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x064B #ARABIC FATHATAN +0xF1 0x064C #ARABIC DAMMATAN +0xF2 0x064D #ARABIC KASRATAN +0xF3 0x064E #ARABIC FATHA +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x064F #ARABIC DAMMA +0xF6 0x0650 #ARABIC KASRA +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x0651 #ARABIC SHADDA +0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0xFA 0x0652 #ARABIC SUKUN +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x200E #LEFT-TO-RIGHT MARK +0xFE 0x200F #RIGHT-TO-LEFT MARK +0xFF 0x06D2 #ARABIC LETTER YEH BARREE diff --git a/Unicode/cp1257.cp b/Unicode/cp1257.cp new file mode 100644 index 0000000..3656f13 --- /dev/null +++ b/Unicode/cp1257.cp @@ -0,0 +1,153 @@ +Window$ 1257 (Baltic) +"windows-1257", "1257", "cp1257" +# +# Name: cp1257 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1257 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1257 order +# +################## + +0x20-0x7e idem +# +0x80 0x20AC #EURO SIGN +0x81 0 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0 #UNDEFINED +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0 #UNDEFINED +0x89 0x2030 #PER MILLE SIGN +0x8A 0 #UNDEFINED +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0 #UNDEFINED +0x8D 0x00A8 #DIAERESIS +0x8E 0x02C7 #CARON +0x8F 0x00B8 #CEDILLA +0x90 0 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0 #UNDEFINED +0x99 0x2122 #TRADE MARK SIGN +0x9A 0 #UNDEFINED +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0 #UNDEFINED +0x9D 0x00AF #MACRON +0x9E 0x02DB #OGONEK +0x9F 0 #UNDEFINED +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0 #UNDEFINED +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0 #UNDEFINED +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x0156 #LATIN CAPITAL LETTER R WITH CEDILLA +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00C6 #LATIN CAPITAL LETTER AE +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x0157 #LATIN SMALL LETTER R WITH CEDILLA +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00E6 #LATIN SMALL LETTER AE +0xC0 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK +0xC1 0x012E #LATIN CAPITAL LETTER I WITH OGONEK +0xC2 0x0100 #LATIN CAPITAL LETTER A WITH MACRON +0xC3 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK +0xC7 0x0112 #LATIN CAPITAL LETTER E WITH MACRON +0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE +0xCB 0x0116 #LATIN CAPITAL LETTER E WITH DOT ABOVE +0xCC 0x0122 #LATIN CAPITAL LETTER G WITH CEDILLA +0xCD 0x0136 #LATIN CAPITAL LETTER K WITH CEDILLA +0xCE 0x012A #LATIN CAPITAL LETTER I WITH MACRON +0xCF 0x013B #LATIN CAPITAL LETTER L WITH CEDILLA +0xD0 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE +0xD2 0x0145 #LATIN CAPITAL LETTER N WITH CEDILLA +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x014C #LATIN CAPITAL LETTER O WITH MACRON +0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x0172 #LATIN CAPITAL LETTER U WITH OGONEK +0xD9 0x0141 #LATIN CAPITAL LETTER L WITH STROKE +0xDA 0x015A #LATIN CAPITAL LETTER S WITH ACUTE +0xDB 0x016A #LATIN CAPITAL LETTER U WITH MACRON +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xDE 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x0105 #LATIN SMALL LETTER A WITH OGONEK +0xE1 0x012F #LATIN SMALL LETTER I WITH OGONEK +0xE2 0x0101 #LATIN SMALL LETTER A WITH MACRON +0xE3 0x0107 #LATIN SMALL LETTER C WITH ACUTE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x0119 #LATIN SMALL LETTER E WITH OGONEK +0xE7 0x0113 #LATIN SMALL LETTER E WITH MACRON +0xE8 0x010D #LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x017A #LATIN SMALL LETTER Z WITH ACUTE +0xEB 0x0117 #LATIN SMALL LETTER E WITH DOT ABOVE +0xEC 0x0123 #LATIN SMALL LETTER G WITH CEDILLA +0xED 0x0137 #LATIN SMALL LETTER K WITH CEDILLA +0xEE 0x012B #LATIN SMALL LETTER I WITH MACRON +0xEF 0x013C #LATIN SMALL LETTER L WITH CEDILLA +0xF0 0x0161 #LATIN SMALL LETTER S WITH CARON +0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE +0xF2 0x0146 #LATIN SMALL LETTER N WITH CEDILLA +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x014D #LATIN SMALL LETTER O WITH MACRON +0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x0173 #LATIN SMALL LETTER U WITH OGONEK +0xF9 0x0142 #LATIN SMALL LETTER L WITH STROKE +0xFA 0x015B #LATIN SMALL LETTER S WITH ACUTE +0xFB 0x016B #LATIN SMALL LETTER U WITH MACRON +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE +0xFE 0x017E #LATIN SMALL LETTER Z WITH CARON +0xFF 0x02D9 #DOT ABOVE + diff --git a/Unicode/cp437.cp b/Unicode/cp437.cp new file mode 100644 index 0000000..67b4728 --- /dev/null +++ b/Unicode/cp437.cp @@ -0,0 +1,275 @@ +CP 437 (US) +"cp437", "437" +# +# Name: cp437_DOSLatinUS to Unicode table +# Unicode version: 2.0 +# Table version: 2.00 +# Table format: Format A +# Date: 04/24/96 +# Authors: Lori Brownell <loribr@microsoft.com> +# K.D. Chang <a-kchang@microsoft.com> +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp437_DOSLatinUS code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp437_DOSLatinUS order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0a 0x000a #LINE FEED +0x0b 0x000b #VERTICAL TABULATION +0x0c 0x000c #FORM FEED +0x0d 0x000d #CARRIAGE RETURN +0x0e 0x000e #SHIFT OUT +0x0f 0x000f #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1a 0x001a #SUBSTITUTE +0x1b 0x001b #ESCAPE +0x1c 0x001c #FILE SEPARATOR +0x1d 0x001d #GROUP SEPARATOR +0x1e 0x001e #RECORD SEPARATOR +0x1f 0x001f #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2a 0x002a #ASTERISK +0x2b 0x002b #PLUS SIGN +0x2c 0x002c #COMMA +0x2d 0x002d #HYPHEN-MINUS +0x2e 0x002e #FULL STOP +0x2f 0x002f #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3a 0x003a #COLON +0x3b 0x003b #SEMICOLON +0x3c 0x003c #LESS-THAN SIGN +0x3d 0x003d #EQUALS SIGN +0x3e 0x003e #GREATER-THAN SIGN +0x3f 0x003f #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4a 0x004a #LATIN CAPITAL LETTER J +0x4b 0x004b #LATIN CAPITAL LETTER K +0x4c 0x004c #LATIN CAPITAL LETTER L +0x4d 0x004d #LATIN CAPITAL LETTER M +0x4e 0x004e #LATIN CAPITAL LETTER N +0x4f 0x004f #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5a 0x005a #LATIN CAPITAL LETTER Z +0x5b 0x005b #LEFT SQUARE BRACKET +0x5c 0x005c #REVERSE SOLIDUS +0x5d 0x005d #RIGHT SQUARE BRACKET +0x5e 0x005e #CIRCUMFLEX ACCENT +0x5f 0x005f #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6a 0x006a #LATIN SMALL LETTER J +0x6b 0x006b #LATIN SMALL LETTER K +0x6c 0x006c #LATIN SMALL LETTER L +0x6d 0x006d #LATIN SMALL LETTER M +0x6e 0x006e #LATIN SMALL LETTER N +0x6f 0x006f #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7a 0x007a #LATIN SMALL LETTER Z +0x7b 0x007b #LEFT CURLY BRACKET +0x7c 0x007c #VERTICAL LINE +0x7d 0x007d #RIGHT CURLY BRACKET +0x7e 0x007e #TILDE +0x7f 0x007f #DELETE +0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA +0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS +0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE +0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS +0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE +0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE +0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA +0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX +0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS +0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE +0x8b 0x00ef #LATIN SMALL LETTER I WITH DIAERESIS +0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX +0x8d 0x00ec #LATIN SMALL LETTER I WITH GRAVE +0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE +0x91 0x00e6 #LATIN SMALL LIGATURE AE +0x92 0x00c6 #LATIN CAPITAL LIGATURE AE +0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS +0x95 0x00f2 #LATIN SMALL LETTER O WITH GRAVE +0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX +0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE +0x98 0x00ff #LATIN SMALL LETTER Y WITH DIAERESIS +0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS +0x9b 0x00a2 #CENT SIGN +0x9c 0x00a3 #POUND SIGN +0x9d 0x00a5 #YEN SIGN +0x9e 0x20a7 #PESETA SIGN +0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK +0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE +0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE +0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE +0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE +0xa4 0x00f1 #LATIN SMALL LETTER N WITH TILDE +0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE +0xa6 0x00aa #FEMININE ORDINAL INDICATOR +0xa7 0x00ba #MASCULINE ORDINAL INDICATOR +0xa8 0x00bf #INVERTED QUESTION MARK +0xa9 0x2310 #REVERSED NOT SIGN +0xaa 0x00ac #NOT SIGN +0xab 0x00bd #VULGAR FRACTION ONE HALF +0xac 0x00bc #VULGAR FRACTION ONE QUARTER +0xad 0x00a1 #INVERTED EXCLAMATION MARK +0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xb0 0x2591 #LIGHT SHADE +0xb1 0x2592 #MEDIUM SHADE +0xb2 0x2593 #DARK SHADE +0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL +0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT +0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE +0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE +0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE +0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL +0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT +0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT +0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE +0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT +0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT +0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL +0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL +0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT +0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL +0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE +0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE +0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE +0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE +0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT +0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT +0xdb 0x2588 #FULL BLOCK +0xdc 0x2584 #LOWER HALF BLOCK +0xdd 0x258c #LEFT HALF BLOCK +0xde 0x2590 #RIGHT HALF BLOCK +0xdf 0x2580 #UPPER HALF BLOCK +0xe0 0x03b1 #GREEK SMALL LETTER ALPHA +0xe1 0x00df #LATIN SMALL LETTER SHARP S +0xe2 0x0393 #GREEK CAPITAL LETTER GAMMA +0xe3 0x03c0 #GREEK SMALL LETTER PI +0xe4 0x03a3 #GREEK CAPITAL LETTER SIGMA +0xe5 0x03c3 #GREEK SMALL LETTER SIGMA +0xe6 0x00b5 #MICRO SIGN +0xe7 0x03c4 #GREEK SMALL LETTER TAU +0xe8 0x03a6 #GREEK CAPITAL LETTER PHI +0xe9 0x0398 #GREEK CAPITAL LETTER THETA +0xea 0x03a9 #GREEK CAPITAL LETTER OMEGA +0xeb 0x03b4 #GREEK SMALL LETTER DELTA +0xec 0x221e #INFINITY +0xed 0x03c6 #GREEK SMALL LETTER PHI +0xee 0x03b5 #GREEK SMALL LETTER EPSILON +0xef 0x2229 #INTERSECTION +0xf0 0x2261 #IDENTICAL TO +0xf1 0x00b1 #PLUS-MINUS SIGN +0xf2 0x2265 #GREATER-THAN OR EQUAL TO +0xf3 0x2264 #LESS-THAN OR EQUAL TO +0xf4 0x2320 #TOP HALF INTEGRAL +0xf5 0x2321 #BOTTOM HALF INTEGRAL +0xf6 0x00f7 #DIVISION SIGN +0xf7 0x2248 #ALMOST EQUAL TO +0xf8 0x00b0 #DEGREE SIGN +0xf9 0x2219 #BULLET OPERATOR +0xfa 0x00b7 #MIDDLE DOT +0xfb 0x221a #SQUARE ROOT +0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N +0xfd 0x00b2 #SUPERSCRIPT TWO +0xfe 0x25a0 #BLACK SQUARE +0xff 0x00a0 #NO-BREAK SPACE diff --git a/Unicode/cp737.cp b/Unicode/cp737.cp new file mode 100644 index 0000000..16d3401 --- /dev/null +++ b/Unicode/cp737.cp @@ -0,0 +1,275 @@ +CP 737 (Greek) +"cp737", "737" +# +# Name: cp737_DOSGreek to Unicode table +# Unicode version: 2.0 +# Table version: 2.00 +# Table format: Format A +# Date: 04/24/96 +# Authors: Lori Brownell <loribr@microsoft.com> +# K.D. Chang <a-kchang@microsoft.com> +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp737_DOSGreek code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp737_DOSGreek order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0a 0x000a #LINE FEED +0x0b 0x000b #VERTICAL TABULATION +0x0c 0x000c #FORM FEED +0x0d 0x000d #CARRIAGE RETURN +0x0e 0x000e #SHIFT OUT +0x0f 0x000f #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1a 0x001a #SUBSTITUTE +0x1b 0x001b #ESCAPE +0x1c 0x001c #FILE SEPARATOR +0x1d 0x001d #GROUP SEPARATOR +0x1e 0x001e #RECORD SEPARATOR +0x1f 0x001f #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2a 0x002a #ASTERISK +0x2b 0x002b #PLUS SIGN +0x2c 0x002c #COMMA +0x2d 0x002d #HYPHEN-MINUS +0x2e 0x002e #FULL STOP +0x2f 0x002f #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3a 0x003a #COLON +0x3b 0x003b #SEMICOLON +0x3c 0x003c #LESS-THAN SIGN +0x3d 0x003d #EQUALS SIGN +0x3e 0x003e #GREATER-THAN SIGN +0x3f 0x003f #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4a 0x004a #LATIN CAPITAL LETTER J +0x4b 0x004b #LATIN CAPITAL LETTER K +0x4c 0x004c #LATIN CAPITAL LETTER L +0x4d 0x004d #LATIN CAPITAL LETTER M +0x4e 0x004e #LATIN CAPITAL LETTER N +0x4f 0x004f #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5a 0x005a #LATIN CAPITAL LETTER Z +0x5b 0x005b #LEFT SQUARE BRACKET +0x5c 0x005c #REVERSE SOLIDUS +0x5d 0x005d #RIGHT SQUARE BRACKET +0x5e 0x005e #CIRCUMFLEX ACCENT +0x5f 0x005f #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6a 0x006a #LATIN SMALL LETTER J +0x6b 0x006b #LATIN SMALL LETTER K +0x6c 0x006c #LATIN SMALL LETTER L +0x6d 0x006d #LATIN SMALL LETTER M +0x6e 0x006e #LATIN SMALL LETTER N +0x6f 0x006f #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7a 0x007a #LATIN SMALL LETTER Z +0x7b 0x007b #LEFT CURLY BRACKET +0x7c 0x007c #VERTICAL LINE +0x7d 0x007d #RIGHT CURLY BRACKET +0x7e 0x007e #TILDE +0x7f 0x007f #DELETE +0x80 0x0391 #GREEK CAPITAL LETTER ALPHA +0x81 0x0392 #GREEK CAPITAL LETTER BETA +0x82 0x0393 #GREEK CAPITAL LETTER GAMMA +0x83 0x0394 #GREEK CAPITAL LETTER DELTA +0x84 0x0395 #GREEK CAPITAL LETTER EPSILON +0x85 0x0396 #GREEK CAPITAL LETTER ZETA +0x86 0x0397 #GREEK CAPITAL LETTER ETA +0x87 0x0398 #GREEK CAPITAL LETTER THETA +0x88 0x0399 #GREEK CAPITAL LETTER IOTA +0x89 0x039a #GREEK CAPITAL LETTER KAPPA +0x8a 0x039b #GREEK CAPITAL LETTER LAMDA +0x8b 0x039c #GREEK CAPITAL LETTER MU +0x8c 0x039d #GREEK CAPITAL LETTER NU +0x8d 0x039e #GREEK CAPITAL LETTER XI +0x8e 0x039f #GREEK CAPITAL LETTER OMICRON +0x8f 0x03a0 #GREEK CAPITAL LETTER PI +0x90 0x03a1 #GREEK CAPITAL LETTER RHO +0x91 0x03a3 #GREEK CAPITAL LETTER SIGMA +0x92 0x03a4 #GREEK CAPITAL LETTER TAU +0x93 0x03a5 #GREEK CAPITAL LETTER UPSILON +0x94 0x03a6 #GREEK CAPITAL LETTER PHI +0x95 0x03a7 #GREEK CAPITAL LETTER CHI +0x96 0x03a8 #GREEK CAPITAL LETTER PSI +0x97 0x03a9 #GREEK CAPITAL LETTER OMEGA +0x98 0x03b1 #GREEK SMALL LETTER ALPHA +0x99 0x03b2 #GREEK SMALL LETTER BETA +0x9a 0x03b3 #GREEK SMALL LETTER GAMMA +0x9b 0x03b4 #GREEK SMALL LETTER DELTA +0x9c 0x03b5 #GREEK SMALL LETTER EPSILON +0x9d 0x03b6 #GREEK SMALL LETTER ZETA +0x9e 0x03b7 #GREEK SMALL LETTER ETA +0x9f 0x03b8 #GREEK SMALL LETTER THETA +0xa0 0x03b9 #GREEK SMALL LETTER IOTA +0xa1 0x03ba #GREEK SMALL LETTER KAPPA +0xa2 0x03bb #GREEK SMALL LETTER LAMDA +0xa3 0x03bc #GREEK SMALL LETTER MU +0xa4 0x03bd #GREEK SMALL LETTER NU +0xa5 0x03be #GREEK SMALL LETTER XI +0xa6 0x03bf #GREEK SMALL LETTER OMICRON +0xa7 0x03c0 #GREEK SMALL LETTER PI +0xa8 0x03c1 #GREEK SMALL LETTER RHO +0xa9 0x03c3 #GREEK SMALL LETTER SIGMA +0xaa 0x03c2 #GREEK SMALL LETTER FINAL SIGMA +0xab 0x03c4 #GREEK SMALL LETTER TAU +0xac 0x03c5 #GREEK SMALL LETTER UPSILON +0xad 0x03c6 #GREEK SMALL LETTER PHI +0xae 0x03c7 #GREEK SMALL LETTER CHI +0xaf 0x03c8 #GREEK SMALL LETTER PSI +0xb0 0x2591 #LIGHT SHADE +0xb1 0x2592 #MEDIUM SHADE +0xb2 0x2593 #DARK SHADE +0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL +0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT +0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE +0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE +0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE +0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL +0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT +0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT +0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE +0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT +0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT +0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL +0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL +0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT +0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL +0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE +0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE +0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE +0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE +0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT +0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT +0xdb 0x2588 #FULL BLOCK +0xdc 0x2584 #LOWER HALF BLOCK +0xdd 0x258c #LEFT HALF BLOCK +0xde 0x2590 #RIGHT HALF BLOCK +0xdf 0x2580 #UPPER HALF BLOCK +0xe0 0x03c9 #GREEK SMALL LETTER OMEGA +0xe1 0x03ac #GREEK SMALL LETTER ALPHA WITH TONOS +0xe2 0x03ad #GREEK SMALL LETTER EPSILON WITH TONOS +0xe3 0x03ae #GREEK SMALL LETTER ETA WITH TONOS +0xe4 0x03ca #GREEK SMALL LETTER IOTA WITH DIALYTIKA +0xe5 0x03af #GREEK SMALL LETTER IOTA WITH TONOS +0xe6 0x03cc #GREEK SMALL LETTER OMICRON WITH TONOS +0xe7 0x03cd #GREEK SMALL LETTER UPSILON WITH TONOS +0xe8 0x03cb #GREEK SMALL LETTER UPSILON WITH DIALYTIKA +0xe9 0x03ce #GREEK SMALL LETTER OMEGA WITH TONOS +0xea 0x0386 #GREEK CAPITAL LETTER ALPHA WITH TONOS +0xeb 0x0388 #GREEK CAPITAL LETTER EPSILON WITH TONOS +0xec 0x0389 #GREEK CAPITAL LETTER ETA WITH TONOS +0xed 0x038a #GREEK CAPITAL LETTER IOTA WITH TONOS +0xee 0x038c #GREEK CAPITAL LETTER OMICRON WITH TONOS +0xef 0x038e #GREEK CAPITAL LETTER UPSILON WITH TONOS +0xf0 0x038f #GREEK CAPITAL LETTER OMEGA WITH TONOS +0xf1 0x00b1 #PLUS-MINUS SIGN +0xf2 0x2265 #GREATER-THAN OR EQUAL TO +0xf3 0x2264 #LESS-THAN OR EQUAL TO +0xf4 0x03aa #GREEK CAPITAL LETTER IOTA WITH DIALYTIKA +0xf5 0x03ab #GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA +0xf6 0x00f7 #DIVISION SIGN +0xf7 0x2248 #ALMOST EQUAL TO +0xf8 0x00b0 #DEGREE SIGN +0xf9 0x2219 #BULLET OPERATOR +0xfa 0x00b7 #MIDDLE DOT +0xfb 0x221a #SQUARE ROOT +0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N +0xfd 0x00b2 #SUPERSCRIPT TWO +0xfe 0x25a0 #BLACK SQUARE +0xff 0x00a0 #NO-BREAK SPACE diff --git a/Unicode/cp850.cp b/Unicode/cp850.cp new file mode 100644 index 0000000..cf0eba6 --- /dev/null +++ b/Unicode/cp850.cp @@ -0,0 +1,275 @@ +CP 850 (Western European) +"cp850", "850" +# +# Name: cp850_DOSLatin1 to Unicode table +# Unicode version: 2.0 +# Table version: 2.00 +# Table format: Format A +# Date: 04/24/96 +# Authors: Lori Brownell <loribr@microsoft.com> +# K.D. Chang <a-kchang@microsoft.com> +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp850_DOSLatin1 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp850_DOSLatin1 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0a 0x000a #LINE FEED +0x0b 0x000b #VERTICAL TABULATION +0x0c 0x000c #FORM FEED +0x0d 0x000d #CARRIAGE RETURN +0x0e 0x000e #SHIFT OUT +0x0f 0x000f #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1a 0x001a #SUBSTITUTE +0x1b 0x001b #ESCAPE +0x1c 0x001c #FILE SEPARATOR +0x1d 0x001d #GROUP SEPARATOR +0x1e 0x001e #RECORD SEPARATOR +0x1f 0x001f #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2a 0x002a #ASTERISK +0x2b 0x002b #PLUS SIGN +0x2c 0x002c #COMMA +0x2d 0x002d #HYPHEN-MINUS +0x2e 0x002e #FULL STOP +0x2f 0x002f #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3a 0x003a #COLON +0x3b 0x003b #SEMICOLON +0x3c 0x003c #LESS-THAN SIGN +0x3d 0x003d #EQUALS SIGN +0x3e 0x003e #GREATER-THAN SIGN +0x3f 0x003f #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4a 0x004a #LATIN CAPITAL LETTER J +0x4b 0x004b #LATIN CAPITAL LETTER K +0x4c 0x004c #LATIN CAPITAL LETTER L +0x4d 0x004d #LATIN CAPITAL LETTER M +0x4e 0x004e #LATIN CAPITAL LETTER N +0x4f 0x004f #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5a 0x005a #LATIN CAPITAL LETTER Z +0x5b 0x005b #LEFT SQUARE BRACKET +0x5c 0x005c #REVERSE SOLIDUS +0x5d 0x005d #RIGHT SQUARE BRACKET +0x5e 0x005e #CIRCUMFLEX ACCENT +0x5f 0x005f #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6a 0x006a #LATIN SMALL LETTER J +0x6b 0x006b #LATIN SMALL LETTER K +0x6c 0x006c #LATIN SMALL LETTER L +0x6d 0x006d #LATIN SMALL LETTER M +0x6e 0x006e #LATIN SMALL LETTER N +0x6f 0x006f #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7a 0x007a #LATIN SMALL LETTER Z +0x7b 0x007b #LEFT CURLY BRACKET +0x7c 0x007c #VERTICAL LINE +0x7d 0x007d #RIGHT CURLY BRACKET +0x7e 0x007e #TILDE +0x7f 0x007f #DELETE +0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA +0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS +0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE +0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS +0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE +0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE +0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA +0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX +0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS +0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE +0x8b 0x00ef #LATIN SMALL LETTER I WITH DIAERESIS +0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX +0x8d 0x00ec #LATIN SMALL LETTER I WITH GRAVE +0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE +0x91 0x00e6 #LATIN SMALL LIGATURE AE +0x92 0x00c6 #LATIN CAPITAL LIGATURE AE +0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS +0x95 0x00f2 #LATIN SMALL LETTER O WITH GRAVE +0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX +0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE +0x98 0x00ff #LATIN SMALL LETTER Y WITH DIAERESIS +0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS +0x9b 0x00f8 #LATIN SMALL LETTER O WITH STROKE +0x9c 0x00a3 #POUND SIGN +0x9d 0x00d8 #LATIN CAPITAL LETTER O WITH STROKE +0x9e 0x00d7 #MULTIPLICATION SIGN +0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK +0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE +0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE +0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE +0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE +0xa4 0x00f1 #LATIN SMALL LETTER N WITH TILDE +0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE +0xa6 0x00aa #FEMININE ORDINAL INDICATOR +0xa7 0x00ba #MASCULINE ORDINAL INDICATOR +0xa8 0x00bf #INVERTED QUESTION MARK +0xa9 0x00ae #REGISTERED SIGN +0xaa 0x00ac #NOT SIGN +0xab 0x00bd #VULGAR FRACTION ONE HALF +0xac 0x00bc #VULGAR FRACTION ONE QUARTER +0xad 0x00a1 #INVERTED EXCLAMATION MARK +0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xb0 0x2591 #LIGHT SHADE +0xb1 0x2592 #MEDIUM SHADE +0xb2 0x2593 #DARK SHADE +0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL +0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT +0xb5 0x00c1 #LATIN CAPITAL LETTER A WITH ACUTE +0xb6 0x00c2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xb7 0x00c0 #LATIN CAPITAL LETTER A WITH GRAVE +0xb8 0x00a9 #COPYRIGHT SIGN +0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL +0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT +0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT +0xbd 0x00a2 #CENT SIGN +0xbe 0x00a5 #YEN SIGN +0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT +0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT +0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL +0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL +0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0xc6 0x00e3 #LATIN SMALL LETTER A WITH TILDE +0xc7 0x00c3 #LATIN CAPITAL LETTER A WITH TILDE +0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT +0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL +0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xcf 0x00a4 #CURRENCY SIGN +0xd0 0x00f0 #LATIN SMALL LETTER ETH +0xd1 0x00d0 #LATIN CAPITAL LETTER ETH +0xd2 0x00ca #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xd3 0x00cb #LATIN CAPITAL LETTER E WITH DIAERESIS +0xd4 0x00c8 #LATIN CAPITAL LETTER E WITH GRAVE +0xd5 0x0131 #LATIN SMALL LETTER DOTLESS I +0xd6 0x00cd #LATIN CAPITAL LETTER I WITH ACUTE +0xd7 0x00ce #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xd8 0x00cf #LATIN CAPITAL LETTER I WITH DIAERESIS +0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT +0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT +0xdb 0x2588 #FULL BLOCK +0xdc 0x2584 #LOWER HALF BLOCK +0xdd 0x00a6 #BROKEN BAR +0xde 0x00cc #LATIN CAPITAL LETTER I WITH GRAVE +0xdf 0x2580 #UPPER HALF BLOCK +0xe0 0x00d3 #LATIN CAPITAL LETTER O WITH ACUTE +0xe1 0x00df #LATIN SMALL LETTER SHARP S +0xe2 0x00d4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xe3 0x00d2 #LATIN CAPITAL LETTER O WITH GRAVE +0xe4 0x00f5 #LATIN SMALL LETTER O WITH TILDE +0xe5 0x00d5 #LATIN CAPITAL LETTER O WITH TILDE +0xe6 0x00b5 #MICRO SIGN +0xe7 0x00fe #LATIN SMALL LETTER THORN +0xe8 0x00de #LATIN CAPITAL LETTER THORN +0xe9 0x00da #LATIN CAPITAL LETTER U WITH ACUTE +0xea 0x00db #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xeb 0x00d9 #LATIN CAPITAL LETTER U WITH GRAVE +0xec 0x00fd #LATIN SMALL LETTER Y WITH ACUTE +0xed 0x00dd #LATIN CAPITAL LETTER Y WITH ACUTE +0xee 0x00af #MACRON +0xef 0x00b4 #ACUTE ACCENT +0xf0 0x00ad #SOFT HYPHEN +0xf1 0x00b1 #PLUS-MINUS SIGN +0xf2 0x2017 #DOUBLE LOW LINE +0xf3 0x00be #VULGAR FRACTION THREE QUARTERS +0xf4 0x00b6 #PILCROW SIGN +0xf5 0x00a7 #SECTION SIGN +0xf6 0x00f7 #DIVISION SIGN +0xf7 0x00b8 #CEDILLA +0xf8 0x00b0 #DEGREE SIGN +0xf9 0x00a8 #DIAERESIS +0xfa 0x00b7 #MIDDLE DOT +0xfb 0x00b9 #SUPERSCRIPT ONE +0xfc 0x00b3 #SUPERSCRIPT THREE +0xfd 0x00b2 #SUPERSCRIPT TWO +0xfe 0x25a0 #BLACK SQUARE +0xff 0x00a0 #NO-BREAK SPACE diff --git a/Unicode/cp852.cp b/Unicode/cp852.cp new file mode 100644 index 0000000..5f0fc2c --- /dev/null +++ b/Unicode/cp852.cp @@ -0,0 +1,275 @@ +CP 852 (Central European) +"cp852", "852" +# +# Name: cp852_DOSLatin2 to Unicode table +# Unicode version: 2.0 +# Table version: 2.00 +# Table format: Format A +# Date: 04/24/96 +# Authors: Lori Brownell <loribr@microsoft.com> +# K.D. Chang <a-kchang@microsoft.com> +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp852_DOSLatin2 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp852_DOSLatin2 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0a 0x000a #LINE FEED +0x0b 0x000b #VERTICAL TABULATION +0x0c 0x000c #FORM FEED +0x0d 0x000d #CARRIAGE RETURN +0x0e 0x000e #SHIFT OUT +0x0f 0x000f #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1a 0x001a #SUBSTITUTE +0x1b 0x001b #ESCAPE +0x1c 0x001c #FILE SEPARATOR +0x1d 0x001d #GROUP SEPARATOR +0x1e 0x001e #RECORD SEPARATOR +0x1f 0x001f #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2a 0x002a #ASTERISK +0x2b 0x002b #PLUS SIGN +0x2c 0x002c #COMMA +0x2d 0x002d #HYPHEN-MINUS +0x2e 0x002e #FULL STOP +0x2f 0x002f #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3a 0x003a #COLON +0x3b 0x003b #SEMICOLON +0x3c 0x003c #LESS-THAN SIGN +0x3d 0x003d #EQUALS SIGN +0x3e 0x003e #GREATER-THAN SIGN +0x3f 0x003f #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4a 0x004a #LATIN CAPITAL LETTER J +0x4b 0x004b #LATIN CAPITAL LETTER K +0x4c 0x004c #LATIN CAPITAL LETTER L +0x4d 0x004d #LATIN CAPITAL LETTER M +0x4e 0x004e #LATIN CAPITAL LETTER N +0x4f 0x004f #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5a 0x005a #LATIN CAPITAL LETTER Z +0x5b 0x005b #LEFT SQUARE BRACKET +0x5c 0x005c #REVERSE SOLIDUS +0x5d 0x005d #RIGHT SQUARE BRACKET +0x5e 0x005e #CIRCUMFLEX ACCENT +0x5f 0x005f #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6a 0x006a #LATIN SMALL LETTER J +0x6b 0x006b #LATIN SMALL LETTER K +0x6c 0x006c #LATIN SMALL LETTER L +0x6d 0x006d #LATIN SMALL LETTER M +0x6e 0x006e #LATIN SMALL LETTER N +0x6f 0x006f #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7a 0x007a #LATIN SMALL LETTER Z +0x7b 0x007b #LEFT CURLY BRACKET +0x7c 0x007c #VERTICAL LINE +0x7d 0x007d #RIGHT CURLY BRACKET +0x7e 0x007e #TILDE +0x7f 0x007f #DELETE +0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA +0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS +0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE +0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS +0x85 0x016f #LATIN SMALL LETTER U WITH RING ABOVE +0x86 0x0107 #LATIN SMALL LETTER C WITH ACUTE +0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA +0x88 0x0142 #LATIN SMALL LETTER L WITH STROKE +0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS +0x8a 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0x8b 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE +0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX +0x8d 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE +0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0x8f 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE +0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE +0x91 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE +0x92 0x013a #LATIN SMALL LETTER L WITH ACUTE +0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS +0x95 0x013d #LATIN CAPITAL LETTER L WITH CARON +0x96 0x013e #LATIN SMALL LETTER L WITH CARON +0x97 0x015a #LATIN CAPITAL LETTER S WITH ACUTE +0x98 0x015b #LATIN SMALL LETTER S WITH ACUTE +0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS +0x9b 0x0164 #LATIN CAPITAL LETTER T WITH CARON +0x9c 0x0165 #LATIN SMALL LETTER T WITH CARON +0x9d 0x0141 #LATIN CAPITAL LETTER L WITH STROKE +0x9e 0x00d7 #MULTIPLICATION SIGN +0x9f 0x010d #LATIN SMALL LETTER C WITH CARON +0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE +0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE +0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE +0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE +0xa4 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK +0xa5 0x0105 #LATIN SMALL LETTER A WITH OGONEK +0xa6 0x017d #LATIN CAPITAL LETTER Z WITH CARON +0xa7 0x017e #LATIN SMALL LETTER Z WITH CARON +0xa8 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK +0xa9 0x0119 #LATIN SMALL LETTER E WITH OGONEK +0xaa 0x00ac #NOT SIGN +0xab 0x017a #LATIN SMALL LETTER Z WITH ACUTE +0xac 0x010c #LATIN CAPITAL LETTER C WITH CARON +0xad 0x015f #LATIN SMALL LETTER S WITH CEDILLA +0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xb0 0x2591 #LIGHT SHADE +0xb1 0x2592 #MEDIUM SHADE +0xb2 0x2593 #DARK SHADE +0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL +0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT +0xb5 0x00c1 #LATIN CAPITAL LETTER A WITH ACUTE +0xb6 0x00c2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xb7 0x011a #LATIN CAPITAL LETTER E WITH CARON +0xb8 0x015e #LATIN CAPITAL LETTER S WITH CEDILLA +0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL +0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT +0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT +0xbd 0x017b #LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xbe 0x017c #LATIN SMALL LETTER Z WITH DOT ABOVE +0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT +0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT +0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL +0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL +0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0xc6 0x0102 #LATIN CAPITAL LETTER A WITH BREVE +0xc7 0x0103 #LATIN SMALL LETTER A WITH BREVE +0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT +0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL +0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xcf 0x00a4 #CURRENCY SIGN +0xd0 0x0111 #LATIN SMALL LETTER D WITH STROKE +0xd1 0x0110 #LATIN CAPITAL LETTER D WITH STROKE +0xd2 0x010e #LATIN CAPITAL LETTER D WITH CARON +0xd3 0x00cb #LATIN CAPITAL LETTER E WITH DIAERESIS +0xd4 0x010f #LATIN SMALL LETTER D WITH CARON +0xd5 0x0147 #LATIN CAPITAL LETTER N WITH CARON +0xd6 0x00cd #LATIN CAPITAL LETTER I WITH ACUTE +0xd7 0x00ce #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xd8 0x011b #LATIN SMALL LETTER E WITH CARON +0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT +0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT +0xdb 0x2588 #FULL BLOCK +0xdc 0x2584 #LOWER HALF BLOCK +0xdd 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA +0xde 0x016e #LATIN CAPITAL LETTER U WITH RING ABOVE +0xdf 0x2580 #UPPER HALF BLOCK +0xe0 0x00d3 #LATIN CAPITAL LETTER O WITH ACUTE +0xe1 0x00df #LATIN SMALL LETTER SHARP S +0xe2 0x00d4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xe3 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE +0xe4 0x0144 #LATIN SMALL LETTER N WITH ACUTE +0xe5 0x0148 #LATIN SMALL LETTER N WITH CARON +0xe6 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0xe7 0x0161 #LATIN SMALL LETTER S WITH CARON +0xe8 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE +0xe9 0x00da #LATIN CAPITAL LETTER U WITH ACUTE +0xea 0x0155 #LATIN SMALL LETTER R WITH ACUTE +0xeb 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0xec 0x00fd #LATIN SMALL LETTER Y WITH ACUTE +0xed 0x00dd #LATIN CAPITAL LETTER Y WITH ACUTE +0xee 0x0163 #LATIN SMALL LETTER T WITH CEDILLA +0xef 0x00b4 #ACUTE ACCENT +0xf0 0x00ad #SOFT HYPHEN +0xf1 0x02dd #DOUBLE ACUTE ACCENT +0xf2 0x02db #OGONEK +0xf3 0x02c7 #CARON +0xf4 0x02d8 #BREVE +0xf5 0x00a7 #SECTION SIGN +0xf6 0x00f7 #DIVISION SIGN +0xf7 0x00b8 #CEDILLA +0xf8 0x00b0 #DEGREE SIGN +0xf9 0x00a8 #DIAERESIS +0xfa 0x02d9 #DOT ABOVE +0xfb 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE +0xfc 0x0158 #LATIN CAPITAL LETTER R WITH CARON +0xfd 0x0159 #LATIN SMALL LETTER R WITH CARON +0xfe 0x25a0 #BLACK SQUARE +0xff 0x00a0 #NO-BREAK SPACE diff --git a/Unicode/cp866.cp b/Unicode/cp866.cp new file mode 100644 index 0000000..a78df1b --- /dev/null +++ b/Unicode/cp866.cp @@ -0,0 +1,276 @@ +CP 866 (Cyrillic) +"cp866", "866" +# +# Name: cp866_DOSCyrillicRussian to Unicode table +# Unicode version: 2.0 +# Table version: 2.00 +# Table format: Format A +# Date: 04/24/96 +# Authors: Lori Brownell <loribr@microsoft.com> +# K.D. Chang <a-kchang@microsoft.com> +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp866_DOSCyrillicRussian code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp866_DOSCyrillicRussian order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0a 0x000a #LINE FEED +0x0b 0x000b #VERTICAL TABULATION +0x0c 0x000c #FORM FEED +0x0d 0x000d #CARRIAGE RETURN +0x0e 0x000e #SHIFT OUT +0x0f 0x000f #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1a 0x001a #SUBSTITUTE +0x1b 0x001b #ESCAPE +0x1c 0x001c #FILE SEPARATOR +0x1d 0x001d #GROUP SEPARATOR +0x1e 0x001e #RECORD SEPARATOR +0x1f 0x001f #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2a 0x002a #ASTERISK +0x2b 0x002b #PLUS SIGN +0x2c 0x002c #COMMA +0x2d 0x002d #HYPHEN-MINUS +0x2e 0x002e #FULL STOP +0x2f 0x002f #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3a 0x003a #COLON +0x3b 0x003b #SEMICOLON +0x3c 0x003c #LESS-THAN SIGN +0x3d 0x003d #EQUALS SIGN +0x3e 0x003e #GREATER-THAN SIGN +0x3f 0x003f #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4a 0x004a #LATIN CAPITAL LETTER J +0x4b 0x004b #LATIN CAPITAL LETTER K +0x4c 0x004c #LATIN CAPITAL LETTER L +0x4d 0x004d #LATIN CAPITAL LETTER M +0x4e 0x004e #LATIN CAPITAL LETTER N +0x4f 0x004f #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5a 0x005a #LATIN CAPITAL LETTER Z +0x5b 0x005b #LEFT SQUARE BRACKET +0x5c 0x005c #REVERSE SOLIDUS +0x5d 0x005d #RIGHT SQUARE BRACKET +0x5e 0x005e #CIRCUMFLEX ACCENT +0x5f 0x005f #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6a 0x006a #LATIN SMALL LETTER J +0x6b 0x006b #LATIN SMALL LETTER K +0x6c 0x006c #LATIN SMALL LETTER L +0x6d 0x006d #LATIN SMALL LETTER M +0x6e 0x006e #LATIN SMALL LETTER N +0x6f 0x006f #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7a 0x007a #LATIN SMALL LETTER Z +0x7b 0x007b #LEFT CURLY BRACKET +0x7c 0x007c #VERTICAL LINE +0x7d 0x007d #RIGHT CURLY BRACKET +0x7e 0x007e #TILDE +0x7f 0x007f #DELETE +0x80 0x0410 #CYRILLIC CAPITAL LETTER A +0x81 0x0411 #CYRILLIC CAPITAL LETTER BE +0x82 0x0412 #CYRILLIC CAPITAL LETTER VE +0x83 0x0413 #CYRILLIC CAPITAL LETTER GHE +0x84 0x0414 #CYRILLIC CAPITAL LETTER DE +0x85 0x0415 #CYRILLIC CAPITAL LETTER IE +0x86 0x0416 #CYRILLIC CAPITAL LETTER ZHE +0x87 0x0417 #CYRILLIC CAPITAL LETTER ZE +0x88 0x0418 #CYRILLIC CAPITAL LETTER I +0x89 0x0419 #CYRILLIC CAPITAL LETTER SHORT I +0x8a 0x041a #CYRILLIC CAPITAL LETTER KA +0x8b 0x041b #CYRILLIC CAPITAL LETTER EL +0x8c 0x041c #CYRILLIC CAPITAL LETTER EM +0x8d 0x041d #CYRILLIC CAPITAL LETTER EN +0x8e 0x041e #CYRILLIC CAPITAL LETTER O +0x8f 0x041f #CYRILLIC CAPITAL LETTER PE +0x90 0x0420 #CYRILLIC CAPITAL LETTER ER +0x91 0x0421 #CYRILLIC CAPITAL LETTER ES +0x92 0x0422 #CYRILLIC CAPITAL LETTER TE +0x93 0x0423 #CYRILLIC CAPITAL LETTER U +0x94 0x0424 #CYRILLIC CAPITAL LETTER EF +0x95 0x0425 #CYRILLIC CAPITAL LETTER HA +0x96 0x0426 #CYRILLIC CAPITAL LETTER TSE +0x97 0x0427 #CYRILLIC CAPITAL LETTER CHE +0x98 0x0428 #CYRILLIC CAPITAL LETTER SHA +0x99 0x0429 #CYRILLIC CAPITAL LETTER SHCHA +0x9a 0x042a #CYRILLIC CAPITAL LETTER HARD SIGN +0x9b 0x042b #CYRILLIC CAPITAL LETTER YERU +0x9c 0x042c #CYRILLIC CAPITAL LETTER SOFT SIGN +0x9d 0x042d #CYRILLIC CAPITAL LETTER E +0x9e 0x042e #CYRILLIC CAPITAL LETTER YU +0x9f 0x042f #CYRILLIC CAPITAL LETTER YA +0xa0 0x0430 #CYRILLIC SMALL LETTER A +0xa1 0x0431 #CYRILLIC SMALL LETTER BE +0xa2 0x0432 #CYRILLIC SMALL LETTER VE +0xa3 0x0433 #CYRILLIC SMALL LETTER GHE +0xa4 0x0434 #CYRILLIC SMALL LETTER DE +0xa5 0x0435 #CYRILLIC SMALL LETTER IE +0xa6 0x0436 #CYRILLIC SMALL LETTER ZHE +0xa7 0x0437 #CYRILLIC SMALL LETTER ZE +0xa8 0x0438 #CYRILLIC SMALL LETTER I +0xa9 0x0439 #CYRILLIC SMALL LETTER SHORT I +0xaa 0x043a #CYRILLIC SMALL LETTER KA +0xab 0x043b #CYRILLIC SMALL LETTER EL +0xac 0x043c #CYRILLIC SMALL LETTER EM +0xad 0x043d #CYRILLIC SMALL LETTER EN +0xae 0x043e #CYRILLIC SMALL LETTER O +0xaf 0x043f #CYRILLIC SMALL LETTER PE +0xb0 0x2591 #LIGHT SHADE +0xb1 0x2592 #MEDIUM SHADE +0xb2 0x2593 #DARK SHADE +0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL +0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT +0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE +0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE +0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE +0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL +0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT +0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT +0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE +0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT +0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT +0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL +0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL +0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT +0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL +0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE +0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE +0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE +0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE +0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT +0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT +0xdb 0x2588 #FULL BLOCK +0xdc 0x2584 #LOWER HALF BLOCK +0xdd 0x258c #LEFT HALF BLOCK +0xde 0x2590 #RIGHT HALF BLOCK +0xdf 0x2580 #UPPER HALF BLOCK +0xe0 0x0440 #CYRILLIC SMALL LETTER ER +0xe1 0x0441 #CYRILLIC SMALL LETTER ES +0xe2 0x0442 #CYRILLIC SMALL LETTER TE +0xe3 0x0443 #CYRILLIC SMALL LETTER U +0xe4 0x0444 #CYRILLIC SMALL LETTER EF +0xe5 0x0445 #CYRILLIC SMALL LETTER HA +0xe6 0x0446 #CYRILLIC SMALL LETTER TSE +0xe7 0x0447 #CYRILLIC SMALL LETTER CHE +0xe8 0x0448 #CYRILLIC SMALL LETTER SHA +0xe9 0x0449 #CYRILLIC SMALL LETTER SHCHA +0xea 0x044a #CYRILLIC SMALL LETTER HARD SIGN +0xeb 0x044b #CYRILLIC SMALL LETTER YERU +0xec 0x044c #CYRILLIC SMALL LETTER SOFT SIGN +0xed 0x044d #CYRILLIC SMALL LETTER E +0xee 0x044e #CYRILLIC SMALL LETTER YU +0xef 0x044f #CYRILLIC SMALL LETTER YA +0xf0 0x0401 #CYRILLIC CAPITAL LETTER IO +0xf1 0x0451 #CYRILLIC SMALL LETTER IO +0xf2 0x0404 #CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xf3 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE +0xf4 0x0407 #CYRILLIC CAPITAL LETTER YI +0xf5 0x0457 #CYRILLIC SMALL LETTER YI +0xf6 0x040e #CYRILLIC CAPITAL LETTER SHORT U +0xf7 0x045e #CYRILLIC SMALL LETTER SHORT U +0xf8 0x00b0 #DEGREE SIGN +0xf9 0x2219 #BULLET OPERATOR +0xfa 0x00b7 #MIDDLE DOT +0xfb 0x221a #SQUARE ROOT +0xfc 0x2116 #NUMERO SIGN +0xfd 0x00a4 #CURRENCY SIGN +0xfe 0x25a0 #BLACK SQUARE +0xff 0x00a0 #NO-BREAK SPACE + diff --git a/Unicode/entities.lnx b/Unicode/entities.lnx new file mode 100644 index 0000000..ea233d1 --- /dev/null +++ b/Unicode/entities.lnx @@ -0,0 +1,1100 @@ +/* +# M.P.: entity to unicode table. I took this file from lynx. +# lynx/WWW/Library/Implementation/entities.h +*/ + +/* Entity Names to Unicode table +** ----------------------------- +** +* +* Whole entities[] thing (and much more) now present +* in this kind of structure. The structured streams to which +* the SGML modules sends its output could then easily have access +* to both entity names and unicode values for each (special) +* character. Probably the whole translation to display characters +* should be done at that later stage (e.g. in HTML.c). +* What's missing is a way for the later stage to return info +* to SGML whether the entity could be displayed or not. +* (like between SGML_character() and handle_entity() via FoundEntity.) +* Well, trying to do that now. +* Why keep two structures for entities? Backward compatibility.. +*/ + +#ifndef ENTITIES_H +#define ENTITIES_H 1 + +#include <HTUtils.h> +#include <SGML.h> + +/* UC_entity_info structure is defined in SGML.h. + This has to be sorted alphabetically (case-sensitive), + bear this in mind when you add some more entities.. */ + +/* + +This table available from ftp://ftp.unicode.org/ +original comment follows: + + +# Author: John Cowan <cowan@ccil.org> +# Date: 25 July 1997 +# +# The following table maps SGML character entities from various +# public sets (namely, ISOamsa, ISOamsb, ISOamsc, ISOamsn, ISOamso, +# ISOamsr, ISObox, ISOcyr1, ISOcyr2, ISOdia, ISOgrk1, ISOgrk2, +# ISOgrk3, ISOgrk4, ISOlat1, ISOlat2, ISOnum, ISOpub, ISOtech, +# HTMLspecial, HTMLsymbol) to corresponding Unicode characters. +# +# The table has four tab-separated columns: +# Column 1: SGML character entity name +# Column 2: SGML public entity set +# Column 3: Unicode 2.0 character code +# Column 4: Unicode 2.0 character name (UPPER CASE) +# Entries which don't have Unicode equivalents have "0x????" +# in Column 3 and a lower case description (from the public entity +# set DTD) in Column 4. The mapping is not reversible, because many +# distinctions are unified away in Unicode, particularly between +# mathematical symbols. +# +# The table is sorted case-blind by SGML character entity name. +# +# The contents of this table are drawn from various sources, and +# are in the public domain. +# +######################## + + We just sort it and move column 2 away (line too long, sorry; + look at sgml.html in test/ directory for details). + Also we add a few (obsolete) synonyms: + "brkbar" for "brvbar" 0x00A6 + "emdash" for "mdash" 0x2014 + "endash" for "ndash" 0x2013 + "hibar" for "macr" 0x00AF + for exact compatibility with entities[] and previous bevavior. + BTW, lots of synonyms found in this table, we shouldn't worry about... +*/ + +static CONST UC_entity_info unicode_entities[] = { + {"AElig", 0x00C6}, /* LATIN CAPITAL LETTER AE */ + {"Aacgr", 0x0386}, /* GREEK CAPITAL LETTER ALPHA WITH TONOS */ + {"Aacute", 0x00C1}, /* LATIN CAPITAL LETTER A WITH ACUTE */ + {"Abreve", 0x0102}, /* LATIN CAPITAL LETTER A WITH BREVE */ + {"Acirc", 0x00C2}, /* LATIN CAPITAL LETTER A WITH CIRCUMFLEX */ + {"Acy", 0x0410}, /* CYRILLIC CAPITAL LETTER A */ + {"Agr", 0x0391}, /* GREEK CAPITAL LETTER ALPHA */ + {"Agrave", 0x00C0}, /* LATIN CAPITAL LETTER A WITH GRAVE */ + {"Alpha", 0x0391}, /* GREEK CAPITAL LETTER ALPHA */ + {"Amacr", 0x0100}, /* LATIN CAPITAL LETTER A WITH MACRON */ + {"Aogon", 0x0104}, /* LATIN CAPITAL LETTER A WITH OGONEK */ + {"Aring", 0x00C5}, /* LATIN CAPITAL LETTER A WITH RING ABOVE */ + {"Atilde", 0x00C3}, /* LATIN CAPITAL LETTER A WITH TILDE */ + {"Auml", 0x00C4}, /* LATIN CAPITAL LETTER A WITH DIAERESIS */ + {"Barwed", 0x2306}, /* PERSPECTIVE */ + {"Bcy", 0x0411}, /* CYRILLIC CAPITAL LETTER BE */ + {"Beta", 0x0392}, /* GREEK CAPITAL LETTER BETA */ + {"Bgr", 0x0392}, /* GREEK CAPITAL LETTER BETA */ + {"CHcy", 0x0427}, /* CYRILLIC CAPITAL LETTER CHE */ + {"Cacute", 0x0106}, /* LATIN CAPITAL LETTER C WITH ACUTE */ + {"Cap", 0x22D2}, /* DOUBLE INTERSECTION */ + {"Ccaron", 0x010C}, /* LATIN CAPITAL LETTER C WITH CARON */ + {"Ccedil", 0x00C7}, /* LATIN CAPITAL LETTER C WITH CEDILLA */ + {"Ccirc", 0x0108}, /* LATIN CAPITAL LETTER C WITH CIRCUMFLEX */ + {"Cdot", 0x010A}, /* LATIN CAPITAL LETTER C WITH DOT ABOVE */ + {"Chi", 0x03A7}, /* GREEK CAPITAL LETTER CHI */ + {"Cup", 0x22D3}, /* DOUBLE UNION */ + {"DJcy", 0x0402}, /* CYRILLIC CAPITAL LETTER DJE */ + {"DScy", 0x0405}, /* CYRILLIC CAPITAL LETTER DZE */ + {"DZcy", 0x040F}, /* CYRILLIC CAPITAL LETTER DZHE */ + {"Dagger", 0x2021}, /* DOUBLE DAGGER */ + {"Dcaron", 0x010E}, /* LATIN CAPITAL LETTER D WITH CARON */ + {"Dcy", 0x0414}, /* CYRILLIC CAPITAL LETTER DE */ + {"Delta", 0x0394}, /* GREEK CAPITAL LETTER DELTA */ + {"Dgr", 0x0394}, /* GREEK CAPITAL LETTER DELTA */ + {"Dot", 0x00A8}, /* DIAERESIS */ + {"DotDot", 0x20DC}, /* COMBINING FOUR DOTS ABOVE */ + {"Dstrok", 0x0110}, /* LATIN CAPITAL LETTER D WITH STROKE */ + {"EEacgr", 0x0389}, /* GREEK CAPITAL LETTER ETA WITH TONOS */ + {"EEgr", 0x0397}, /* GREEK CAPITAL LETTER ETA */ + {"ENG", 0x014A}, /* LATIN CAPITAL LETTER ENG */ + {"ETH", 0x00D0}, /* LATIN CAPITAL LETTER ETH */ + {"Eacgr", 0x0388}, /* GREEK CAPITAL LETTER EPSILON WITH TONOS */ + {"Eacute", 0x00C9}, /* LATIN CAPITAL LETTER E WITH ACUTE */ + {"Ecaron", 0x011A}, /* LATIN CAPITAL LETTER E WITH CARON */ + {"Ecirc", 0x00CA}, /* LATIN CAPITAL LETTER E WITH CIRCUMFLEX */ + {"Ecy", 0x042D}, /* CYRILLIC CAPITAL LETTER E */ + {"Edot", 0x0116}, /* LATIN CAPITAL LETTER E WITH DOT ABOVE */ + {"Egr", 0x0395}, /* GREEK CAPITAL LETTER EPSILON */ + {"Egrave", 0x00C8}, /* LATIN CAPITAL LETTER E WITH GRAVE */ + {"Emacr", 0x0112}, /* LATIN CAPITAL LETTER E WITH MACRON */ + {"Eogon", 0x0118}, /* LATIN CAPITAL LETTER E WITH OGONEK */ + {"Epsilon", 0x0395}, /* GREEK CAPITAL LETTER EPSILON */ + {"Eta", 0x0397}, /* GREEK CAPITAL LETTER ETA */ + {"Euml", 0x00CB}, /* LATIN CAPITAL LETTER E WITH DIAERESIS */ + {"Euro", 0x20AC}, /* EURO SYMBOL */ + {"Fcy", 0x0424}, /* CYRILLIC CAPITAL LETTER EF */ + {"GJcy", 0x0403}, /* CYRILLIC CAPITAL LETTER GJE */ + {"Gamma", 0x0393}, /* GREEK CAPITAL LETTER GAMMA */ + {"Gbreve", 0x011E}, /* LATIN CAPITAL LETTER G WITH BREVE */ + {"Gcedil", 0x0122}, /* LATIN CAPITAL LETTER G WITH CEDILLA */ + {"Gcirc", 0x011C}, /* LATIN CAPITAL LETTER G WITH CIRCUMFLEX */ + {"Gcy", 0x0413}, /* CYRILLIC CAPITAL LETTER GHE */ + {"Gdot", 0x0120}, /* LATIN CAPITAL LETTER G WITH DOT ABOVE */ + {"Gg", 0x22D9}, /* VERY MUCH GREATER-THAN */ + {"Ggr", 0x0393}, /* GREEK CAPITAL LETTER GAMMA */ + {"Gt", 0x226B}, /* MUCH GREATER-THAN */ + {"HARDcy", 0x042A}, /* CYRILLIC CAPITAL LETTER HARD SIGN */ + {"Hcirc", 0x0124}, /* LATIN CAPITAL LETTER H WITH CIRCUMFLEX */ + {"Hstrok", 0x0126}, /* LATIN CAPITAL LETTER H WITH STROKE */ + {"IEcy", 0x0415}, /* CYRILLIC CAPITAL LETTER IE */ + {"IJlig", 0x0132}, /* LATIN CAPITAL LIGATURE IJ */ + {"IOcy", 0x0401}, /* CYRILLIC CAPITAL LETTER IO */ + {"Iacgr", 0x038A}, /* GREEK CAPITAL LETTER IOTA WITH TONOS */ + {"Iacute", 0x00CD}, /* LATIN CAPITAL LETTER I WITH ACUTE */ + {"Icirc", 0x00CE}, /* LATIN CAPITAL LETTER I WITH CIRCUMFLEX */ + {"Icy", 0x0418}, /* CYRILLIC CAPITAL LETTER I */ + {"Idigr", 0x03AA}, /* GREEK CAPITAL LETTER IOTA WITH DIALYTIKA */ + {"Idot", 0x0130}, /* LATIN CAPITAL LETTER I WITH DOT ABOVE */ + {"Igr", 0x0399}, /* GREEK CAPITAL LETTER IOTA */ + {"Igrave", 0x00CC}, /* LATIN CAPITAL LETTER I WITH GRAVE */ + {"Imacr", 0x012A}, /* LATIN CAPITAL LETTER I WITH MACRON */ + {"Iogon", 0x012E}, /* LATIN CAPITAL LETTER I WITH OGONEK */ + {"Iota", 0x0399}, /* GREEK CAPITAL LETTER IOTA */ + {"Itilde", 0x0128}, /* LATIN CAPITAL LETTER I WITH TILDE */ + {"Iukcy", 0x0406}, /* CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN*/ + {"Iuml", 0x00CF}, /* LATIN CAPITAL LETTER I WITH DIAERESIS */ + {"Jcirc", 0x0134}, /* LATIN CAPITAL LETTER J WITH CIRCUMFLEX */ + {"Jcy", 0x0419}, /* CYRILLIC CAPITAL LETTER SHORT I */ + {"Jsercy", 0x0408}, /* CYRILLIC CAPITAL LETTER JE */ + {"Jukcy", 0x0404}, /* CYRILLIC CAPITAL LETTER UKRAINIAN IE */ + {"KHcy", 0x0425}, /* CYRILLIC CAPITAL LETTER HA */ + {"KHgr", 0x03A7}, /* GREEK CAPITAL LETTER CHI */ + {"KJcy", 0x040C}, /* CYRILLIC CAPITAL LETTER KJE */ + {"Kappa", 0x039A}, /* GREEK CAPITAL LETTER KAPPA */ + {"Kcedil", 0x0136}, /* LATIN CAPITAL LETTER K WITH CEDILLA */ + {"Kcy", 0x041A}, /* CYRILLIC CAPITAL LETTER KA */ + {"Kgr", 0x039A}, /* GREEK CAPITAL LETTER KAPPA */ + {"LJcy", 0x0409}, /* CYRILLIC CAPITAL LETTER LJE */ + {"Lacute", 0x0139}, /* LATIN CAPITAL LETTER L WITH ACUTE */ + {"Lambda", 0x039B}, /* GREEK CAPITAL LETTER LAMDA */ + {"Larr", 0x219E}, /* LEFTWARDS TWO HEADED ARROW */ + {"Lcaron", 0x013D}, /* LATIN CAPITAL LETTER L WITH CARON */ + {"Lcedil", 0x013B}, /* LATIN CAPITAL LETTER L WITH CEDILLA */ + {"Lcy", 0x041B}, /* CYRILLIC CAPITAL LETTER EL */ + {"Lgr", 0x039B}, /* GREEK CAPITAL LETTER LAMDA */ + {"Ll", 0x22D8}, /* VERY MUCH LESS-THAN */ + {"Lmidot", 0x013F}, /* LATIN CAPITAL LETTER L WITH MIDDLE DOT */ + {"Lstrok", 0x0141}, /* LATIN CAPITAL LETTER L WITH STROKE */ + {"Lt", 0x226A}, /* MUCH LESS-THAN */ + {"Mcy", 0x041C}, /* CYRILLIC CAPITAL LETTER EM */ + {"Mgr", 0x039C}, /* GREEK CAPITAL LETTER MU */ + {"Mu", 0x039C}, /* GREEK CAPITAL LETTER MU */ + {"NJcy", 0x040A}, /* CYRILLIC CAPITAL LETTER NJE */ + {"Nacute", 0x0143}, /* LATIN CAPITAL LETTER N WITH ACUTE */ + {"Ncaron", 0x0147}, /* LATIN CAPITAL LETTER N WITH CARON */ + {"Ncedil", 0x0145}, /* LATIN CAPITAL LETTER N WITH CEDILLA */ + {"Ncy", 0x041D}, /* CYRILLIC CAPITAL LETTER EN */ + {"Ngr", 0x039D}, /* GREEK CAPITAL LETTER NU */ + {"Ntilde", 0x00D1}, /* LATIN CAPITAL LETTER N WITH TILDE */ + {"Nu", 0x039D}, /* GREEK CAPITAL LETTER NU */ + {"OElig", 0x0152}, /* LATIN CAPITAL LIGATURE OE */ + {"OHacgr", 0x038F}, /* GREEK CAPITAL LETTER OMEGA WITH TONOS */ + {"OHgr", 0x03A9}, /* GREEK CAPITAL LETTER OMEGA */ + {"Oacgr", 0x038C}, /* GREEK CAPITAL LETTER OMICRON WITH TONOS */ + {"Oacute", 0x00D3}, /* LATIN CAPITAL LETTER O WITH ACUTE */ + {"Ocirc", 0x00D4}, /* LATIN CAPITAL LETTER O WITH CIRCUMFLEX */ + {"Ocy", 0x041E}, /* CYRILLIC CAPITAL LETTER O */ + {"Odblac", 0x0150}, /* LATIN CAPITAL LETTER O WITH DOUBLE ACUTE */ + {"Ogr", 0x039F}, /* GREEK CAPITAL LETTER OMICRON */ + {"Ograve", 0x00D2}, /* LATIN CAPITAL LETTER O WITH GRAVE */ + {"Omacr", 0x014C}, /* LATIN CAPITAL LETTER O WITH MACRON */ + {"Omega", 0x03A9}, /* GREEK CAPITAL LETTER OMEGA */ + {"Omicron", 0x039F}, /* GREEK CAPITAL LETTER OMICRON */ + {"Oslash", 0x00D8}, /* LATIN CAPITAL LETTER O WITH STROKE */ + {"Otilde", 0x00D5}, /* LATIN CAPITAL LETTER O WITH TILDE */ + {"Ouml", 0x00D6}, /* LATIN CAPITAL LETTER O WITH DIAERESIS */ + {"PHgr", 0x03A6}, /* GREEK CAPITAL LETTER PHI */ + {"PSgr", 0x03A8}, /* GREEK CAPITAL LETTER PSI */ + {"Pcy", 0x041F}, /* CYRILLIC CAPITAL LETTER PE */ + {"Pgr", 0x03A0}, /* GREEK CAPITAL LETTER PI */ + {"Phi", 0x03A6}, /* GREEK CAPITAL LETTER PHI */ + {"Pi", 0x03A0}, /* GREEK CAPITAL LETTER PI */ + {"Prime", 0x2033}, /* DOUBLE PRIME */ + {"Psi", 0x03A8}, /* GREEK CAPITAL LETTER PSI */ + {"Racute", 0x0154}, /* LATIN CAPITAL LETTER R WITH ACUTE */ + {"Rarr", 0x21A0}, /* RIGHTWARDS TWO HEADED ARROW */ + {"Rcaron", 0x0158}, /* LATIN CAPITAL LETTER R WITH CARON */ + {"Rcedil", 0x0156}, /* LATIN CAPITAL LETTER R WITH CEDILLA */ + {"Rcy", 0x0420}, /* CYRILLIC CAPITAL LETTER ER */ + {"Rgr", 0x03A1}, /* GREEK CAPITAL LETTER RHO */ + {"Rho", 0x03A1}, /* GREEK CAPITAL LETTER RHO */ + {"SHCHcy", 0x0429}, /* CYRILLIC CAPITAL LETTER SHCHA */ + {"SHcy", 0x0428}, /* CYRILLIC CAPITAL LETTER SHA */ + {"SOFTcy", 0x042C}, /* CYRILLIC CAPITAL LETTER SOFT SIGN */ + {"Sacute", 0x015A}, /* LATIN CAPITAL LETTER S WITH ACUTE */ + {"Scaron", 0x0160}, /* LATIN CAPITAL LETTER S WITH CARON */ + {"Scedil", 0x015E}, /* LATIN CAPITAL LETTER S WITH CEDILLA */ + {"Scirc", 0x015C}, /* LATIN CAPITAL LETTER S WITH CIRCUMFLEX */ + {"Scy", 0x0421}, /* CYRILLIC CAPITAL LETTER ES */ + {"Sgr", 0x03A3}, /* GREEK CAPITAL LETTER SIGMA */ + {"Sigma", 0x03A3}, /* GREEK CAPITAL LETTER SIGMA */ + {"Sub", 0x22D0}, /* DOUBLE SUBSET */ + {"Sup", 0x22D1}, /* DOUBLE SUPERSET */ + {"THORN", 0x00DE}, /* LATIN CAPITAL LETTER THORN */ + {"THgr", 0x0398}, /* GREEK CAPITAL LETTER THETA */ + {"TSHcy", 0x040B}, /* CYRILLIC CAPITAL LETTER TSHE */ + {"TScy", 0x0426}, /* CYRILLIC CAPITAL LETTER TSE */ + {"Tau", 0x03A4}, /* GREEK CAPITAL LETTER TAU */ + {"Tcaron", 0x0164}, /* LATIN CAPITAL LETTER T WITH CARON */ + {"Tcedil", 0x0162}, /* LATIN CAPITAL LETTER T WITH CEDILLA */ + {"Tcy", 0x0422}, /* CYRILLIC CAPITAL LETTER TE */ + {"Tgr", 0x03A4}, /* GREEK CAPITAL LETTER TAU */ + {"Theta", 0x0398}, /* GREEK CAPITAL LETTER THETA */ + {"Tstrok", 0x0166}, /* LATIN CAPITAL LETTER T WITH STROKE */ + {"Uacgr", 0x038E}, /* GREEK CAPITAL LETTER UPSILON WITH TONOS */ + {"Uacute", 0x00DA}, /* LATIN CAPITAL LETTER U WITH ACUTE */ + {"Ubrcy", 0x040E}, /* CYRILLIC CAPITAL LETTER SHORT U */ + {"Ubreve", 0x016C}, /* LATIN CAPITAL LETTER U WITH BREVE */ + {"Ucirc", 0x00DB}, /* LATIN CAPITAL LETTER U WITH CIRCUMFLEX */ + {"Ucy", 0x0423}, /* CYRILLIC CAPITAL LETTER U */ + {"Udblac", 0x0170}, /* LATIN CAPITAL LETTER U WITH DOUBLE ACUTE */ + {"Udigr", 0x03AB}, /* GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA */ + {"Ugr", 0x03A5}, /* GREEK CAPITAL LETTER UPSILON */ + {"Ugrave", 0x00D9}, /* LATIN CAPITAL LETTER U WITH GRAVE */ + {"Umacr", 0x016A}, /* LATIN CAPITAL LETTER U WITH MACRON */ + {"Uogon", 0x0172}, /* LATIN CAPITAL LETTER U WITH OGONEK */ + {"Upsi", 0x03A5}, /* GREEK CAPITAL LETTER UPSILON */ + {"Upsilon", 0x03A5}, /* GREEK CAPITAL LETTER UPSILON */ + {"Uring", 0x016E}, /* LATIN CAPITAL LETTER U WITH RING ABOVE */ + {"Utilde", 0x0168}, /* LATIN CAPITAL LETTER U WITH TILDE */ + {"Uuml", 0x00DC}, /* LATIN CAPITAL LETTER U WITH DIAERESIS */ + {"Vcy", 0x0412}, /* CYRILLIC CAPITAL LETTER VE */ + {"Vdash", 0x22A9}, /* FORCES */ + {"Verbar", 0x2016}, /* DOUBLE VERTICAL LINE */ + {"Vvdash", 0x22AA}, /* TRIPLE VERTICAL BAR RIGHT TURNSTILE */ + {"Wcirc", 0x0174}, /* LATIN CAPITAL LETTER W WITH CIRCUMFLEX */ + {"Xgr", 0x039E}, /* GREEK CAPITAL LETTER XI */ + {"Xi", 0x039E}, /* GREEK CAPITAL LETTER XI */ + {"YAcy", 0x042F}, /* CYRILLIC CAPITAL LETTER YA */ + {"YIcy", 0x0407}, /* CYRILLIC CAPITAL LETTER YI */ + {"YUcy", 0x042E}, /* CYRILLIC CAPITAL LETTER YU */ + {"Yacute", 0x00DD}, /* LATIN CAPITAL LETTER Y WITH ACUTE */ + {"Ycirc", 0x0176}, /* LATIN CAPITAL LETTER Y WITH CIRCUMFLEX */ + {"Ycy", 0x042B}, /* CYRILLIC CAPITAL LETTER YERU */ + {"Yuml", 0x0178}, /* LATIN CAPITAL LETTER Y WITH DIAERESIS */ + {"ZHcy", 0x0416}, /* CYRILLIC CAPITAL LETTER ZHE */ + {"Zacute", 0x0179}, /* LATIN CAPITAL LETTER Z WITH ACUTE */ + {"Zcaron", 0x017D}, /* LATIN CAPITAL LETTER Z WITH CARON */ + {"Zcy", 0x0417}, /* CYRILLIC CAPITAL LETTER ZE */ + {"Zdot", 0x017B}, /* LATIN CAPITAL LETTER Z WITH DOT ABOVE */ + {"Zeta", 0x0396}, /* GREEK CAPITAL LETTER ZETA */ + {"Zgr", 0x0396}, /* GREEK CAPITAL LETTER ZETA */ + {"aacgr", 0x03AC}, /* GREEK SMALL LETTER ALPHA WITH TONOS */ + {"aacute", 0x00E1}, /* LATIN SMALL LETTER A WITH ACUTE */ + {"abreve", 0x0103}, /* LATIN SMALL LETTER A WITH BREVE */ + {"acirc", 0x00E2}, /* LATIN SMALL LETTER A WITH CIRCUMFLEX */ + {"acute", 0x00B4}, /* ACUTE ACCENT */ + {"acy", 0x0430}, /* CYRILLIC SMALL LETTER A */ + {"aelig", 0x00E6}, /* LATIN SMALL LETTER AE */ + {"agr", 0x03B1}, /* GREEK SMALL LETTER ALPHA */ + {"agrave", 0x00E0}, /* LATIN SMALL LETTER A WITH GRAVE */ + {"alefsym", 0x2135}, /* ALEF SYMBOL */ + {"aleph", 0x2135}, /* ALEF SYMBOL */ + {"alpha", 0x03B1}, /* GREEK SMALL LETTER ALPHA */ + {"amacr", 0x0101}, /* LATIN SMALL LETTER A WITH MACRON */ + {"amalg", 0x2210}, /* N-ARY COPRODUCT */ + {"amp", 0x0026}, /* AMPERSAND */ + {"and", 0x2227}, /* LOGICAL AND */ + {"ang", 0x2220}, /* ANGLE */ + {"ang90", 0x221F}, /* RIGHT ANGLE */ + {"angmsd", 0x2221}, /* MEASURED ANGLE */ + {"angsph", 0x2222}, /* SPHERICAL ANGLE */ + {"angst", 0x212B}, /* ANGSTROM SIGN */ + {"aogon", 0x0105}, /* LATIN SMALL LETTER A WITH OGONEK */ + {"ap", 0x2248}, /* ALMOST EQUAL TO */ + {"ape", 0x224A}, /* ALMOST EQUAL OR EQUAL TO */ + {"apos", 0x02BC}, /* MODIFIER LETTER APOSTROPHE */ + {"aring", 0x00E5}, /* LATIN SMALL LETTER A WITH RING ABOVE */ + {"ast", 0x002A}, /* ASTERISK */ + {"asymp", 0x2248}, /* ALMOST EQUAL TO */ + {"atilde", 0x00E3}, /* LATIN SMALL LETTER A WITH TILDE */ + {"auml", 0x00E4}, /* LATIN SMALL LETTER A WITH DIAERESIS */ + {"b.Delta", 0x0394}, /* GREEK CAPITAL LETTER DELTA */ + {"b.Gamma", 0x0393}, /* GREEK CAPITAL LETTER GAMMA */ + {"b.Lambda", 0x039B}, /* GREEK CAPITAL LETTER LAMDA */ + {"b.Omega", 0x03A9}, /* GREEK CAPITAL LETTER OMEGA */ + {"b.Phi", 0x03A6}, /* GREEK CAPITAL LETTER PHI */ + {"b.Pi", 0x03A0}, /* GREEK CAPITAL LETTER PI */ + {"b.Psi", 0x03A8}, /* GREEK CAPITAL LETTER PSI */ + {"b.Sigma", 0x03A3}, /* GREEK CAPITAL LETTER SIGMA */ + {"b.Theta", 0x0398}, /* GREEK CAPITAL LETTER THETA */ + {"b.Upsi", 0x03A5}, /* GREEK CAPITAL LETTER UPSILON */ + {"b.Xi", 0x039E}, /* GREEK CAPITAL LETTER XI */ + {"b.alpha", 0x03B1}, /* GREEK SMALL LETTER ALPHA */ + {"b.beta", 0x03B2}, /* GREEK SMALL LETTER BETA */ + {"b.chi", 0x03C7}, /* GREEK SMALL LETTER CHI */ + {"b.delta", 0x03B3}, /* GREEK SMALL LETTER GAMMA */ + {"b.epsi", 0x03B5}, /* GREEK SMALL LETTER EPSILON */ + {"b.epsis", 0x03B5}, /* GREEK SMALL LETTER EPSILON */ + {"b.epsiv", 0x03B5}, /* GREEK SMALL LETTER EPSILON */ + {"b.eta", 0x03B7}, /* GREEK SMALL LETTER ETA */ + {"b.gamma", 0x03B3}, /* GREEK SMALL LETTER GAMMA */ + {"b.gammad", 0x03DC}, /* GREEK LETTER DIGAMMA */ + {"b.iota", 0x03B9}, /* GREEK SMALL LETTER IOTA */ + {"b.kappa", 0x03BA}, /* GREEK SMALL LETTER KAPPA */ + {"b.kappav", 0x03F0}, /* GREEK KAPPA SYMBOL */ + {"b.lambda", 0x03BB}, /* GREEK SMALL LETTER LAMDA */ + {"b.mu", 0x03BC}, /* GREEK SMALL LETTER MU */ + {"b.nu", 0x03BD}, /* GREEK SMALL LETTER NU */ + {"b.omega", 0x03CE}, /* GREEK SMALL LETTER OMEGA WITH TONOS */ + {"b.phis", 0x03C6}, /* GREEK SMALL LETTER PHI */ + {"b.phiv", 0x03D5}, /* GREEK PHI SYMBOL */ + {"b.pi", 0x03C0}, /* GREEK SMALL LETTER PI */ + {"b.piv", 0x03D6}, /* GREEK PI SYMBOL */ + {"b.psi", 0x03C8}, /* GREEK SMALL LETTER PSI */ + {"b.rho", 0x03C1}, /* GREEK SMALL LETTER RHO */ + {"b.rhov", 0x03F1}, /* GREEK RHO SYMBOL */ + {"b.sigma", 0x03C3}, /* GREEK SMALL LETTER SIGMA */ + {"b.sigmav", 0x03C2}, /* GREEK SMALL LETTER FINAL SIGMA */ + {"b.tau", 0x03C4}, /* GREEK SMALL LETTER TAU */ + {"b.thetas", 0x03B8}, /* GREEK SMALL LETTER THETA */ + {"b.thetav", 0x03D1}, /* GREEK THETA SYMBOL */ + {"b.upsi", 0x03C5}, /* GREEK SMALL LETTER UPSILON */ + {"b.xi", 0x03BE}, /* GREEK SMALL LETTER XI */ + {"b.zeta", 0x03B6}, /* GREEK SMALL LETTER ZETA */ + {"barwed", 0x22BC}, /* NAND */ + {"bcong", 0x224C}, /* ALL EQUAL TO */ + {"bcy", 0x0431}, /* CYRILLIC SMALL LETTER BE */ + {"bdquo", 0x201E}, /* DOUBLE LOW-9 QUOTATION MARK */ + {"becaus", 0x2235}, /* BECAUSE */ + {"bepsi", 0x220D}, /* SMALL CONTAINS AS MEMBER */ + {"bernou", 0x212C}, /* SCRIPT CAPITAL B */ + {"beta", 0x03B2}, /* GREEK SMALL LETTER BETA */ + {"beth", 0x2136}, /* BET SYMBOL */ + {"bgr", 0x03B2}, /* GREEK SMALL LETTER BETA */ + {"blank", 0x2423}, /* OPEN BOX */ + {"blk12", 0x2592}, /* MEDIUM SHADE */ + {"blk14", 0x2591}, /* LIGHT SHADE */ + {"blk34", 0x2593}, /* DARK SHADE */ + {"block", 0x2588}, /* FULL BLOCK */ + {"bottom", 0x22A5}, /* UP TACK */ + {"bowtie", 0x22C8}, /* BOWTIE */ + {"boxDL", 0x2557}, /* BOX DRAWINGS DOUBLE DOWN AND LEFT */ + {"boxDR", 0x2554}, /* BOX DRAWINGS DOUBLE DOWN AND RIGHT */ + {"boxDl", 0x2556}, /* BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE */ + {"boxDr", 0x2553}, /* BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE */ + {"boxH", 0x2550}, /* BOX DRAWINGS DOUBLE HORIZONTAL */ + {"boxHD", 0x2566}, /* BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL */ + {"boxHU", 0x2569}, /* BOX DRAWINGS DOUBLE UP AND HORIZONTAL */ + {"boxHd", 0x2564}, /* BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE*/ + {"boxHu", 0x2567}, /* BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE */ + {"boxUL", 0x255D}, /* BOX DRAWINGS DOUBLE UP AND LEFT */ + {"boxUR", 0x255A}, /* BOX DRAWINGS DOUBLE UP AND RIGHT */ + {"boxUl", 0x255C}, /* BOX DRAWINGS UP DOUBLE AND LEFT SINGLE */ + {"boxUr", 0x2559}, /* BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE */ + {"boxV", 0x2551}, /* BOX DRAWINGS DOUBLE VERTICAL */ + {"boxVH", 0x256C}, /* BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL */ + {"boxVL", 0x2563}, /* BOX DRAWINGS DOUBLE VERTICAL AND LEFT */ + {"boxVR", 0x2560}, /* BOX DRAWINGS DOUBLE VERTICAL AND RIGHT */ + {"boxVh", 0x256B}, /* BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SI*/ + {"boxVl", 0x2562}, /* BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE */ + {"boxVr", 0x255F}, /* BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE */ + {"boxdL", 0x2555}, /* BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE */ + {"boxdR", 0x2552}, /* BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE */ + {"boxdl", 0x2510}, /* BOX DRAWINGS LIGHT DOWN AND LEFT */ + {"boxdr", 0x250C}, /* BOX DRAWINGS LIGHT DOWN AND RIGHT */ + {"boxh", 0x2500}, /* BOX DRAWINGS LIGHT HORIZONTAL */ + {"boxhD", 0x2565}, /* BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE*/ + {"boxhU", 0x2568}, /* BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE */ + {"boxhd", 0x252C}, /* BOX DRAWINGS LIGHT DOWN AND HORIZONTAL */ + {"boxhu", 0x2534}, /* BOX DRAWINGS LIGHT UP AND HORIZONTAL */ + {"boxuL", 0x255B}, /* BOX DRAWINGS UP SINGLE AND LEFT DOUBLE */ + {"boxuR", 0x2558}, /* BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE */ + {"boxul", 0x2518}, /* BOX DRAWINGS LIGHT UP AND LEFT */ + {"boxur", 0x2514}, /* BOX DRAWINGS LIGHT UP AND RIGHT */ + {"boxv", 0x2502}, /* BOX DRAWINGS LIGHT VERTICAL */ + {"boxvH", 0x256A}, /* BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DO*/ + {"boxvL", 0x2561}, /* BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE */ + {"boxvR", 0x255E}, /* BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE */ + {"boxvh", 0x253C}, /* BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL */ + {"boxvl", 0x2524}, /* BOX DRAWINGS LIGHT VERTICAL AND LEFT */ + {"boxvr", 0x251C}, /* BOX DRAWINGS LIGHT VERTICAL AND RIGHT */ + {"bprime", 0x2035}, /* REVERSED PRIME */ + {"breve", 0x02D8}, /* BREVE */ + {"brkbar", 0x00A6}, /* obsolete synonym for "brvbar" 0x00A6 */ + {"brvbar", 0x00A6}, /* BROKEN BAR */ + {"bsim", 0x223D}, /* REVERSED TILDE */ + {"bsime", 0x22CD}, /* REVERSED TILDE EQUALS */ + {"bsol", 0x005C}, /* REVERSE SOLIDUS */ + {"bull", 0x2022}, /* BULLET */ + {"bump", 0x224E}, /* GEOMETRICALLY EQUIVALENT TO */ + {"bumpe", 0x224F}, /* DIFFERENCE BETWEEN */ + {"cacute", 0x0107}, /* LATIN SMALL LETTER C WITH ACUTE */ + {"cap", 0x2229}, /* INTERSECTION */ + {"caret", 0x2041}, /* CARET INSERTION POINT */ + {"caron", 0x02C7}, /* CARON */ + {"ccaron", 0x010D}, /* LATIN SMALL LETTER C WITH CARON */ + {"ccedil", 0x00E7}, /* LATIN SMALL LETTER C WITH CEDILLA */ + {"ccirc", 0x0109}, /* LATIN SMALL LETTER C WITH CIRCUMFLEX */ + {"cdot", 0x010B}, /* LATIN SMALL LETTER C WITH DOT ABOVE */ + {"cedil", 0x00B8}, /* CEDILLA */ + {"cent", 0x00A2}, /* CENT SIGN */ + {"chcy", 0x0447}, /* CYRILLIC SMALL LETTER CHE */ + {"check", 0x2713}, /* CHECK MARK */ + {"chi", 0x03C7}, /* GREEK SMALL LETTER CHI */ + {"cir", 0x25CB}, /* WHITE CIRCLE */ + {"circ", 0x02C6}, /* MODIFIER LETTER CIRCUMFLEX ACCENT */ + {"cire", 0x2257}, /* RING EQUAL TO */ + {"clubs", 0x2663}, /* BLACK CLUB SUIT */ + {"colon", 0x003A}, /* COLON */ + {"colone", 0x2254}, /* COLON EQUALS */ + {"comma", 0x002C}, /* COMMA */ + {"commat", 0x0040}, /* COMMERCIAL AT */ + {"comp", 0x2201}, /* COMPLEMENT */ + {"compfn", 0x2218}, /* RING OPERATOR */ + {"cong", 0x2245}, /* APPROXIMATELY EQUAL TO */ + {"conint", 0x222E}, /* CONTOUR INTEGRAL */ + {"coprod", 0x2210}, /* N-ARY COPRODUCT */ + {"copy", 0x00A9}, /* COPYRIGHT SIGN */ + {"copysr", 0x2117}, /* SOUND RECORDING COPYRIGHT */ + {"crarr", 0x21B5}, /* DOWNWARDS ARROW WITH CORNER LEFTWARDS */ + {"cross", 0x2717}, /* BALLOT X */ + {"cuepr", 0x22DE}, /* EQUAL TO OR PRECEDES */ + {"cuesc", 0x22DF}, /* EQUAL TO OR SUCCEEDS */ + {"cularr", 0x21B6}, /* ANTICLOCKWISE TOP SEMICIRCLE ARROW */ + {"cup", 0x222A}, /* UNION */ + {"cupre", 0x227C}, /* PRECEDES OR EQUAL TO */ + {"curarr", 0x21B7}, /* CLOCKWISE TOP SEMICIRCLE ARROW */ + {"curren", 0x00A4}, /* CURRENCY SIGN */ + {"cuvee", 0x22CE}, /* CURLY LOGICAL OR */ + {"cuwed", 0x22CF}, /* CURLY LOGICAL AND */ + {"dArr", 0x21D3}, /* DOWNWARDS DOUBLE ARROW */ + {"dagger", 0x2020}, /* DAGGER */ + {"daleth", 0x2138}, /* DALET SYMBOL */ + {"darr", 0x2193}, /* DOWNWARDS ARROW */ + {"darr2", 0x21CA}, /* DOWNWARDS PAIRED ARROWS */ + {"dash", 0x2010}, /* HYPHEN */ + {"dashv", 0x22A3}, /* LEFT TACK */ + {"dblac", 0x02DD}, /* DOUBLE ACUTE ACCENT */ + {"dcaron", 0x010F}, /* LATIN SMALL LETTER D WITH CARON */ + {"dcy", 0x0434}, /* CYRILLIC SMALL LETTER DE */ + {"deg", 0x00B0}, /* DEGREE SIGN */ + {"delta", 0x03B4}, /* GREEK SMALL LETTER DELTA */ + {"dgr", 0x03B4}, /* GREEK SMALL LETTER DELTA */ + {"dharl", 0x21C3}, /* DOWNWARDS HARPOON WITH BARB LEFTWARDS */ + {"dharr", 0x21C2}, /* DOWNWARDS HARPOON WITH BARB RIGHTWARDS */ + {"diam", 0x22C4}, /* DIAMOND OPERATOR */ + {"diams", 0x2666}, /* BLACK DIAMOND SUIT */ + {"die", 0x00A8}, /* DIAERESIS */ + {"divide", 0x00F7}, /* DIVISION SIGN */ + {"divonx", 0x22C7}, /* DIVISION TIMES */ + {"djcy", 0x0452}, /* CYRILLIC SMALL LETTER DJE */ + {"dlarr", 0x2199}, /* SOUTH WEST ARROW */ + {"dlcorn", 0x231E}, /* BOTTOM LEFT CORNER */ + {"dlcrop", 0x230D}, /* BOTTOM LEFT CROP */ + {"dollar", 0x0024}, /* DOLLAR SIGN */ + {"dot", 0x02D9}, /* DOT ABOVE */ + {"drarr", 0x2198}, /* SOUTH EAST ARROW */ + {"drcorn", 0x231F}, /* BOTTOM RIGHT CORNER */ + {"drcrop", 0x230C}, /* BOTTOM RIGHT CROP */ + {"dscy", 0x0455}, /* CYRILLIC SMALL LETTER DZE */ + {"dstrok", 0x0111}, /* LATIN SMALL LETTER D WITH STROKE */ + {"dtri", 0x25BF}, /* WHITE DOWN-POINTING SMALL TRIANGLE */ + {"dtrif", 0x25BE}, /* BLACK DOWN-POINTING SMALL TRIANGLE */ + {"dzcy", 0x045F}, /* CYRILLIC SMALL LETTER DZHE */ + {"eDot", 0x2251}, /* GEOMETRICALLY EQUAL TO */ + {"eacgr", 0x03AD}, /* GREEK SMALL LETTER EPSILON WITH TONOS */ + {"eacute", 0x00E9}, /* LATIN SMALL LETTER E WITH ACUTE */ + {"ecaron", 0x011B}, /* LATIN SMALL LETTER E WITH CARON */ + {"ecir", 0x2256}, /* RING IN EQUAL TO */ + {"ecirc", 0x00EA}, /* LATIN SMALL LETTER E WITH CIRCUMFLEX */ + {"ecolon", 0x2255}, /* EQUALS COLON */ + {"ecy", 0x044D}, /* CYRILLIC SMALL LETTER E */ + {"edot", 0x0117}, /* LATIN SMALL LETTER E WITH DOT ABOVE */ + {"eeacgr", 0x03AE}, /* GREEK SMALL LETTER ETA WITH TONOS */ + {"eegr", 0x03B7}, /* GREEK SMALL LETTER ETA */ + {"efDot", 0x2252}, /* APPROXIMATELY EQUAL TO OR THE IMAGE OF */ + {"egr", 0x03B5}, /* GREEK SMALL LETTER EPSILON */ + {"egrave", 0x00E8}, /* LATIN SMALL LETTER E WITH GRAVE */ + {"egs", 0x22DD}, /* EQUAL TO OR GREATER-THAN */ + {"ell", 0x2113}, /* SCRIPT SMALL L */ + {"els", 0x22DC}, /* EQUAL TO OR LESS-THAN */ + {"emacr", 0x0113}, /* LATIN SMALL LETTER E WITH MACRON */ + {"emdash", 0x2014}, /* obsolete synonym for "mdash" 0x2014 */ + {"empty", 0x2205}, /* EMPTY SET */ + {"emsp", 0x2003}, /* EM SPACE */ + {"emsp13", 0x2004}, /* THREE-PER-EM SPACE */ + {"emsp14", 0x2005}, /* FOUR-PER-EM SPACE */ + {"endash", 0x2013}, /* obsolete synonym for "ndash" 0x2013 */ + {"eng", 0x014B}, /* LATIN SMALL LETTER ENG */ + {"ensp", 0x2002}, /* EN SPACE */ + {"eogon", 0x0119}, /* LATIN SMALL LETTER E WITH OGONEK */ + {"epsi", 0x03B5}, /* GREEK SMALL LETTER EPSILON */ + {"epsilon", 0x03B5}, /* GREEK SMALL LETTER EPSILON */ + {"epsis", 0x220A}, /* SMALL ELEMENT OF */ + {"equals", 0x003D}, /* EQUALS SIGN */ + {"equiv", 0x2261}, /* IDENTICAL TO */ + {"erDot", 0x2253}, /* IMAGE OF OR APPROXIMATELY EQUAL TO */ + {"esdot", 0x2250}, /* APPROACHES THE LIMIT */ + {"eta", 0x03B7}, /* GREEK SMALL LETTER ETA */ + {"eth", 0x00F0}, /* LATIN SMALL LETTER ETH */ + {"euml", 0x00EB}, /* LATIN SMALL LETTER E WITH DIAERESIS */ + {"euro", 0x20AC}, /* EURO SYMBOL */ + {"excl", 0x0021}, /* EXCLAMATION MARK */ + {"exist", 0x2203}, /* THERE EXISTS */ + {"fcy", 0x0444}, /* CYRILLIC SMALL LETTER EF */ + {"female", 0x2640}, /* FEMALE SIGN */ + {"ffilig", 0xFB03}, /* LATIN SMALL LIGATURE FFI */ + {"fflig", 0xFB00}, /* LATIN SMALL LIGATURE FF */ + {"ffllig", 0xFB04}, /* LATIN SMALL LIGATURE FFL */ + {"filig", 0xFB01}, /* LATIN SMALL LIGATURE FI */ + {"flat", 0x266D}, /* MUSIC FLAT SIGN */ + {"fllig", 0xFB02}, /* LATIN SMALL LIGATURE FL */ + {"fnof", 0x0192}, /* LATIN SMALL LETTER F WITH HOOK */ + {"forall", 0x2200}, /* FOR ALL */ + {"fork", 0x22D4}, /* PITCHFORK */ + {"frac12", 0x00BD}, /* VULGAR FRACTION ONE HALF */ + {"frac13", 0x2153}, /* VULGAR FRACTION ONE THIRD */ + {"frac14", 0x00BC}, /* VULGAR FRACTION ONE QUARTER */ + {"frac15", 0x2155}, /* VULGAR FRACTION ONE FIFTH */ + {"frac16", 0x2159}, /* VULGAR FRACTION ONE SIXTH */ + {"frac18", 0x215B}, /* VULGAR FRACTION ONE EIGHTH */ + {"frac23", 0x2154}, /* VULGAR FRACTION TWO THIRDS */ + {"frac25", 0x2156}, /* VULGAR FRACTION TWO FIFTHS */ + {"frac34", 0x00BE}, /* VULGAR FRACTION THREE QUARTERS */ + {"frac35", 0x2157}, /* VULGAR FRACTION THREE FIFTHS */ + {"frac38", 0x215C}, /* VULGAR FRACTION THREE EIGHTHS */ + {"frac45", 0x2158}, /* VULGAR FRACTION FOUR FIFTHS */ + {"frac56", 0x215A}, /* VULGAR FRACTION FIVE SIXTHS */ + {"frac58", 0x215D}, /* VULGAR FRACTION FIVE EIGHTHS */ + {"frac78", 0x215E}, /* VULGAR FRACTION SEVEN EIGHTHS */ + {"frasl", 0x2044}, /* FRACTION SLASH */ + {"frown", 0x2322}, /* FROWN */ + {"gE", 0x2267}, /* GREATER-THAN OVER EQUAL TO */ + {"gacute", 0x01F5}, /* LATIN SMALL LETTER G WITH ACUTE */ + {"gamma", 0x03B3}, /* GREEK SMALL LETTER GAMMA */ + {"gammad", 0x03DC}, /* GREEK LETTER DIGAMMA */ + {"gbreve", 0x011F}, /* LATIN SMALL LETTER G WITH BREVE */ + {"gcedil", 0x0123}, /* LATIN SMALL LETTER G WITH CEDILLA */ + {"gcirc", 0x011D}, /* LATIN SMALL LETTER G WITH CIRCUMFLEX */ + {"gcy", 0x0433}, /* CYRILLIC SMALL LETTER GHE */ + {"gdot", 0x0121}, /* LATIN SMALL LETTER G WITH DOT ABOVE */ + {"ge", 0x2265}, /* GREATER-THAN OR EQUAL TO */ + {"gel", 0x22DB}, /* GREATER-THAN EQUAL TO OR LESS-THAN */ + {"ges", 0x2265}, /* GREATER-THAN OR EQUAL TO */ + {"ggr", 0x03B3}, /* GREEK SMALL LETTER GAMMA */ + {"gimel", 0x2137}, /* GIMEL SYMBOL */ + {"gjcy", 0x0453}, /* CYRILLIC SMALL LETTER GJE */ + {"gl", 0x2277}, /* GREATER-THAN OR LESS-THAN */ + {"gnE", 0x2269}, /* GREATER-THAN BUT NOT EQUAL TO */ + {"gne", 0x2269}, /* GREATER-THAN BUT NOT EQUAL TO */ + {"gnsim", 0x22E7}, /* GREATER-THAN BUT NOT EQUIVALENT TO */ + {"grave", 0x0060}, /* GRAVE ACCENT */ + {"gsdot", 0x22D7}, /* GREATER-THAN WITH DOT */ + {"gsim", 0x2273}, /* GREATER-THAN OR EQUIVALENT TO */ + {"gt", 0x003E}, /* GREATER-THAN SIGN */ + {"gvnE", 0x2269}, /* GREATER-THAN BUT NOT EQUAL TO */ + {"hArr", 0x21D4}, /* LEFT RIGHT DOUBLE ARROW */ + {"hairsp", 0x200A}, /* HAIR SPACE */ + {"half", 0x00BD}, /* VULGAR FRACTION ONE HALF */ + {"hamilt", 0x210B}, /* SCRIPT CAPITAL H */ + {"hardcy", 0x044A}, /* CYRILLIC SMALL LETTER HARD SIGN */ + {"harr", 0x2194}, /* LEFT RIGHT ARROW */ + {"harrw", 0x21AD}, /* LEFT RIGHT WAVE ARROW */ + {"hcirc", 0x0125}, /* LATIN SMALL LETTER H WITH CIRCUMFLEX */ + {"hearts", 0x2665}, /* BLACK HEART SUIT */ + {"hellip", 0x2026}, /* HORIZONTAL ELLIPSIS */ + {"hibar", 0x00AF}, /* obsolete synonym for "macr" 0x00AF */ + {"horbar", 0x2015}, /* HORIZONTAL BAR */ + {"hstrok", 0x0127}, /* LATIN SMALL LETTER H WITH STROKE */ + {"hybull", 0x2043}, /* HYPHEN BULLET */ + {"hyphen", 0x002D}, /* HYPHEN-MINUS */ + {"iacgr", 0x03AF}, /* GREEK SMALL LETTER IOTA WITH TONOS */ + {"iacute", 0x00ED}, /* LATIN SMALL LETTER I WITH ACUTE */ + {"icirc", 0x00EE}, /* LATIN SMALL LETTER I WITH CIRCUMFLEX */ + {"icy", 0x0438}, /* CYRILLIC SMALL LETTER I */ + {"idiagr", 0x0390}, /* GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TON*/ + {"idigr", 0x03CA}, /* GREEK SMALL LETTER IOTA WITH DIALYTIKA */ + {"iecy", 0x0435}, /* CYRILLIC SMALL LETTER IE */ + {"iexcl", 0x00A1}, /* INVERTED EXCLAMATION MARK */ + {"iff", 0x21D4}, /* LEFT RIGHT DOUBLE ARROW */ + {"igr", 0x03B9}, /* GREEK SMALL LETTER IOTA */ + {"igrave", 0x00EC}, /* LATIN SMALL LETTER I WITH GRAVE */ + {"ijlig", 0x0133}, /* LATIN SMALL LIGATURE IJ */ + {"imacr", 0x012B}, /* LATIN SMALL LETTER I WITH MACRON */ + {"image", 0x2111}, /* BLACK-LETTER CAPITAL I */ + {"incare", 0x2105}, /* CARE OF */ + {"infin", 0x221E}, /* INFINITY */ + {"inodot", 0x0131}, /* LATIN SMALL LETTER DOTLESS I */ + {"int", 0x222B}, /* INTEGRAL */ + {"intcal", 0x22BA}, /* INTERCALATE */ + {"iocy", 0x0451}, /* CYRILLIC SMALL LETTER IO */ + {"iogon", 0x012F}, /* LATIN SMALL LETTER I WITH OGONEK */ + {"iota", 0x03B9}, /* GREEK SMALL LETTER IOTA */ + {"iquest", 0x00BF}, /* INVERTED QUESTION MARK */ + {"isin", 0x2208}, /* ELEMENT OF */ + {"itilde", 0x0129}, /* LATIN SMALL LETTER I WITH TILDE */ + {"iukcy", 0x0456}, /* CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I*/ + {"iuml", 0x00EF}, /* LATIN SMALL LETTER I WITH DIAERESIS */ + {"jcirc", 0x0135}, /* LATIN SMALL LETTER J WITH CIRCUMFLEX */ + {"jcy", 0x0439}, /* CYRILLIC SMALL LETTER SHORT I */ + {"jsercy", 0x0458}, /* CYRILLIC SMALL LETTER JE */ + {"jukcy", 0x0454}, /* CYRILLIC SMALL LETTER UKRAINIAN IE */ + {"kappa", 0x03BA}, /* GREEK SMALL LETTER KAPPA */ + {"kappav", 0x03F0}, /* GREEK KAPPA SYMBOL */ + {"kcedil", 0x0137}, /* LATIN SMALL LETTER K WITH CEDILLA */ + {"kcy", 0x043A}, /* CYRILLIC SMALL LETTER KA */ + {"kgr", 0x03BA}, /* GREEK SMALL LETTER KAPPA */ + {"kgreen", 0x0138}, /* LATIN SMALL LETTER KRA */ + {"khcy", 0x0445}, /* CYRILLIC SMALL LETTER HA */ + {"khgr", 0x03C7}, /* GREEK SMALL LETTER CHI */ + {"kjcy", 0x045C}, /* CYRILLIC SMALL LETTER KJE */ + {"lAarr", 0x21DA}, /* LEFTWARDS TRIPLE ARROW */ + {"lArr", 0x21D0}, /* LEFTWARDS DOUBLE ARROW */ + {"lE", 0x2266}, /* LESS-THAN OVER EQUAL TO */ + {"lacute", 0x013A}, /* LATIN SMALL LETTER L WITH ACUTE */ + {"lagran", 0x2112}, /* SCRIPT CAPITAL L */ + {"lambda", 0x03BB}, /* GREEK SMALL LETTER LAMDA */ + {"lang", 0x2329}, /* LEFT-POINTING ANGLE BRACKET */ + {"laquo", 0x00AB}, /* LEFT-POINTING DOUBLE ANGLE QUOTATION MARK */ + {"larr", 0x2190}, /* LEFTWARDS ARROW */ + {"larr2", 0x21C7}, /* LEFTWARDS PAIRED ARROWS */ + {"larrhk", 0x21A9}, /* LEFTWARDS ARROW WITH HOOK */ + {"larrlp", 0x21AB}, /* LEFTWARDS ARROW WITH LOOP */ + {"larrtl", 0x21A2}, /* LEFTWARDS ARROW WITH TAIL */ + {"lcaron", 0x013E}, /* LATIN SMALL LETTER L WITH CARON */ + {"lcedil", 0x013C}, /* LATIN SMALL LETTER L WITH CEDILLA */ + {"lceil", 0x2308}, /* LEFT CEILING */ + {"lcub", 0x007B}, /* LEFT CURLY BRACKET */ + {"lcy", 0x043B}, /* CYRILLIC SMALL LETTER EL */ + {"ldot", 0x22D6}, /* LESS-THAN WITH DOT */ + {"ldquo", 0x201C}, /* LEFT DOUBLE QUOTATION MARK */ + {"ldquor", 0x201E}, /* DOUBLE LOW-9 QUOTATION MARK */ + {"le", 0x2264}, /* LESS-THAN OR EQUAL TO */ + {"leg", 0x22DA}, /* LESS-THAN EQUAL TO OR GREATER-THAN */ + {"les", 0x2264}, /* LESS-THAN OR EQUAL TO */ + {"lfloor", 0x230A}, /* LEFT FLOOR */ + {"lg", 0x2276}, /* LESS-THAN OR GREATER-THAN */ + {"lgr", 0x03BB}, /* GREEK SMALL LETTER LAMDA */ + {"lhard", 0x21BD}, /* LEFTWARDS HARPOON WITH BARB DOWNWARDS */ + {"lharu", 0x21BC}, /* LEFTWARDS HARPOON WITH BARB UPWARDS */ + {"lhblk", 0x2584}, /* LOWER HALF BLOCK */ + {"ljcy", 0x0459}, /* CYRILLIC SMALL LETTER LJE */ + {"lmidot", 0x0140}, /* LATIN SMALL LETTER L WITH MIDDLE DOT */ + {"lnE", 0x2268}, /* LESS-THAN BUT NOT EQUAL TO */ + {"lne", 0x2268}, /* LESS-THAN BUT NOT EQUAL TO */ + {"lnsim", 0x22E6}, /* LESS-THAN BUT NOT EQUIVALENT TO */ + {"lowast", 0x2217}, /* ASTERISK OPERATOR */ + {"lowbar", 0x005F}, /* LOW LINE */ + {"loz", 0x25CA}, /* LOZENGE */ + {"loz", 0x2727}, /* WHITE FOUR POINTED STAR */ + {"lozf", 0x2726}, /* BLACK FOUR POINTED STAR */ + {"lpar", 0x0028}, /* LEFT PARENTHESIS */ + {"lrarr2", 0x21C6}, /* LEFTWARDS ARROW OVER RIGHTWARDS ARROW */ + {"lrhar2", 0x21CB}, /* LEFTWARDS HARPOON OVER RIGHTWARDS HARPOON */ + {"lrm", 0x200E}, /* LEFT-TO-RIGHT MARK */ + {"lsaquo", 0x2039}, /* SINGLE LEFT-POINTING ANGLE QUOTATION MARK */ + {"lsh", 0x21B0}, /* UPWARDS ARROW WITH TIP LEFTWARDS */ + {"lsim", 0x2272}, /* LESS-THAN OR EQUIVALENT TO */ + {"lsqb", 0x005B}, /* LEFT SQUARE BRACKET */ + {"lsquo", 0x2018}, /* LEFT SINGLE QUOTATION MARK */ + {"lsquor", 0x201A}, /* SINGLE LOW-9 QUOTATION MARK */ + {"lstrok", 0x0142}, /* LATIN SMALL LETTER L WITH STROKE */ + {"lt", 0x003C}, /* LESS-THAN SIGN */ + {"lthree", 0x22CB}, /* LEFT SEMIDIRECT PRODUCT */ + {"ltimes", 0x22C9}, /* LEFT NORMAL FACTOR SEMIDIRECT PRODUCT */ + {"ltri", 0x25C3}, /* WHITE LEFT-POINTING SMALL TRIANGLE */ + {"ltrie", 0x22B4}, /* NORMAL SUBGROUP OF OR EQUAL TO */ + {"ltrif", 0x25C2}, /* BLACK LEFT-POINTING SMALL TRIANGLE */ + {"lvnE", 0x2268}, /* LESS-THAN BUT NOT EQUAL TO */ + {"macr", 0x00AF}, /* MACRON */ + {"male", 0x2642}, /* MALE SIGN */ + {"malt", 0x2720}, /* MALTESE CROSS */ + {"map", 0x21A6}, /* RIGHTWARDS ARROW FROM BAR */ + {"marker", 0x25AE}, /* BLACK VERTICAL RECTANGLE */ + {"mcy", 0x043C}, /* CYRILLIC SMALL LETTER EM */ + {"mdash", 0x2014}, /* EM DASH */ + {"mgr", 0x03BC}, /* GREEK SMALL LETTER MU */ + {"micro", 0x00B5}, /* MICRO SIGN */ + {"mid", 0x2223}, /* DIVIDES */ + {"middot", 0x00B7}, /* MIDDLE DOT */ + {"minus", 0x2212}, /* MINUS SIGN */ + {"minusb", 0x229F}, /* SQUARED MINUS */ + {"mldr", 0x2026}, /* HORIZONTAL ELLIPSIS */ + {"mnplus", 0x2213}, /* MINUS-OR-PLUS SIGN */ + {"models", 0x22A7}, /* MODELS */ + {"mu", 0x03BC}, /* GREEK SMALL LETTER MU */ + {"mumap", 0x22B8}, /* MULTIMAP */ + {"nVDash", 0x22AF}, /* NEGATED DOUBLE VERTICAL BAR DOUBLE RIGHT TURNS*/ + {"nVdash", 0x22AE}, /* DOES NOT FORCE */ + {"nabla", 0x2207}, /* NABLA */ + {"nacute", 0x0144}, /* LATIN SMALL LETTER N WITH ACUTE */ + {"nap", 0x2249}, /* NOT ALMOST EQUAL TO */ + {"napos", 0x0149}, /* LATIN SMALL LETTER N PRECEDED BY APOSTROPHE */ + {"natur", 0x266E}, /* MUSIC NATURAL SIGN */ + {"nbsp", 0x00A0}, /* NO-BREAK SPACE */ + {"ncaron", 0x0148}, /* LATIN SMALL LETTER N WITH CARON */ + {"ncedil", 0x0146}, /* LATIN SMALL LETTER N WITH CEDILLA */ + {"ncong", 0x2247}, /* NEITHER APPROXIMATELY NOR ACTUALLY EQUAL TO */ + {"ncy", 0x043D}, /* CYRILLIC SMALL LETTER EN */ + {"ndash", 0x2013}, /* EN DASH */ + {"ne", 0x2260}, /* NOT EQUAL TO */ + {"nearr", 0x2197}, /* NORTH EAST ARROW */ + {"nequiv", 0x2262}, /* NOT IDENTICAL TO */ + {"nexist", 0x2204}, /* THERE DOES NOT EXIST */ + {"nge", 0x2271}, /* NEITHER GREATER-THAN NOR EQUAL TO */ + {"nges", 0x2271}, /* NEITHER GREATER-THAN NOR EQUAL TO */ + {"ngr", 0x03BD}, /* GREEK SMALL LETTER NU */ + {"ngt", 0x226F}, /* NOT GREATER-THAN */ + {"nhArr", 0x21CE}, /* LEFT RIGHT DOUBLE ARROW WITH STROKE */ + {"nharr", 0x21AE}, /* LEFT RIGHT ARROW WITH STROKE */ + {"ni", 0x220B}, /* CONTAINS AS MEMBER */ + {"njcy", 0x045A}, /* CYRILLIC SMALL LETTER NJE */ + {"nlArr", 0x21CD}, /* LEFTWARDS DOUBLE ARROW WITH STROKE */ + {"nlarr", 0x219A}, /* LEFTWARDS ARROW WITH STROKE */ + {"nldr", 0x2025}, /* TWO DOT LEADER */ + {"nle", 0x2270}, /* NEITHER LESS-THAN NOR EQUAL TO */ + {"nles", 0x2270}, /* NEITHER LESS-THAN NOR EQUAL TO */ + {"nlt", 0x226E}, /* NOT LESS-THAN */ + {"nltri", 0x22EA}, /* NOT NORMAL SUBGROUP OF */ + {"nltrie", 0x22EC}, /* NOT NORMAL SUBGROUP OF OR EQUAL TO */ + {"nmid", 0x2224}, /* DOES NOT DIVIDE */ + {"not", 0x00AC}, /* NOT SIGN */ + {"notin", 0x2209}, /* NOT AN ELEMENT OF */ + {"npar", 0x2226}, /* NOT PARALLEL TO */ + {"npr", 0x2280}, /* DOES NOT PRECEDE */ + {"npre", 0x22E0}, /* DOES NOT PRECEDE OR EQUAL */ + {"nrArr", 0x21CF}, /* RIGHTWARDS DOUBLE ARROW WITH STROKE */ + {"nrarr", 0x219B}, /* RIGHTWARDS ARROW WITH STROKE */ + {"nrtri", 0x22EB}, /* DOES NOT CONTAIN AS NORMAL SUBGROUP */ + {"nrtrie", 0x22ED}, /* DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL */ + {"nsc", 0x2281}, /* DOES NOT SUCCEED */ + {"nsce", 0x22E1}, /* DOES NOT SUCCEED OR EQUAL */ + {"nsim", 0x2241}, /* NOT TILDE */ + {"nsime", 0x2244}, /* NOT ASYMPTOTICALLY EQUAL TO */ + {"nspar", 0x2226}, /* NOT PARALLEL TO */ + {"nsub", 0x2284}, /* NOT A SUBSET OF */ + {"nsubE", 0x2288}, /* NEITHER A SUBSET OF NOR EQUAL TO */ + {"nsube", 0x2288}, /* NEITHER A SUBSET OF NOR EQUAL TO */ + {"nsup", 0x2285}, /* NOT A SUPERSET OF */ + {"nsupE", 0x2289}, /* NEITHER A SUPERSET OF NOR EQUAL TO */ + {"nsupe", 0x2289}, /* NEITHER A SUPERSET OF NOR EQUAL TO */ + {"ntilde", 0x00F1}, /* LATIN SMALL LETTER N WITH TILDE */ + {"nu", 0x03BD}, /* GREEK SMALL LETTER NU */ + {"num", 0x0023}, /* NUMBER SIGN */ + {"numero", 0x2116}, /* NUMERO SIGN */ + {"numsp", 0x2007}, /* FIGURE SPACE */ + {"nvDash", 0x22AD}, /* NOT TRUE */ + {"nvdash", 0x22AC}, /* DOES NOT PROVE */ + {"nwarr", 0x2196}, /* NORTH WEST ARROW */ + {"oS", 0x24C8}, /* CIRCLED LATIN CAPITAL LETTER S */ + {"oacgr", 0x03CC}, /* GREEK SMALL LETTER OMICRON WITH TONOS */ + {"oacute", 0x00F3}, /* LATIN SMALL LETTER O WITH ACUTE */ + {"oast", 0x229B}, /* CIRCLED ASTERISK OPERATOR */ + {"ocir", 0x229A}, /* CIRCLED RING OPERATOR */ + {"ocirc", 0x00F4}, /* LATIN SMALL LETTER O WITH CIRCUMFLEX */ + {"ocy", 0x043E}, /* CYRILLIC SMALL LETTER O */ + {"odash", 0x229D}, /* CIRCLED DASH */ + {"odblac", 0x0151}, /* LATIN SMALL LETTER O WITH DOUBLE ACUTE */ + {"odot", 0x2299}, /* CIRCLED DOT OPERATOR */ + {"oelig", 0x0153}, /* LATIN SMALL LIGATURE OE */ + {"ogon", 0x02DB}, /* OGONEK */ + {"ogr", 0x03BF}, /* GREEK SMALL LETTER OMICRON */ + {"ograve", 0x00F2}, /* LATIN SMALL LETTER O WITH GRAVE */ + {"ohacgr", 0x03CE}, /* GREEK SMALL LETTER OMEGA WITH TONOS */ + {"ohgr", 0x03C9}, /* GREEK SMALL LETTER OMEGA */ + {"ohm", 0x2126}, /* OHM SIGN */ + {"olarr", 0x21BA}, /* ANTICLOCKWISE OPEN CIRCLE ARROW */ + {"oline", 0x203E}, /* OVERLINE */ + {"omacr", 0x014D}, /* LATIN SMALL LETTER O WITH MACRON */ + {"omega", 0x03C9}, /* GREEK SMALL LETTER OMEGA */ + {"omicron", 0x03BF}, /* GREEK SMALL LETTER OMICRON */ + {"ominus", 0x2296}, /* CIRCLED MINUS */ + {"oplus", 0x2295}, /* CIRCLED PLUS */ + {"or", 0x2228}, /* LOGICAL OR */ + {"orarr", 0x21BB}, /* CLOCKWISE OPEN CIRCLE ARROW */ + {"order", 0x2134}, /* SCRIPT SMALL O */ + {"ordf", 0x00AA}, /* FEMININE ORDINAL INDICATOR */ + {"ordm", 0x00BA}, /* MASCULINE ORDINAL INDICATOR */ + {"oslash", 0x00F8}, /* LATIN SMALL LETTER O WITH STROKE */ + {"osol", 0x2298}, /* CIRCLED DIVISION SLASH */ + {"otilde", 0x00F5}, /* LATIN SMALL LETTER O WITH TILDE */ + {"otimes", 0x2297}, /* CIRCLED TIMES */ + {"ouml", 0x00F6}, /* LATIN SMALL LETTER O WITH DIAERESIS */ + {"par", 0x2225}, /* PARALLEL TO */ + {"para", 0x00B6}, /* PILCROW SIGN */ + {"part", 0x2202}, /* PARTIAL DIFFERENTIAL */ + {"pcy", 0x043F}, /* CYRILLIC SMALL LETTER PE */ + {"percnt", 0x0025}, /* PERCENT SIGN */ + {"period", 0x002E}, /* FULL STOP */ + {"permil", 0x2030}, /* PER MILLE SIGN */ + {"perp", 0x22A5}, /* UP TACK */ + {"pgr", 0x03C0}, /* GREEK SMALL LETTER PI */ + {"phgr", 0x03C6}, /* GREEK SMALL LETTER PHI */ + {"phi", 0x03C6}, /* GREEK SMALL LETTER PHI */ + {"phis", 0x03C6}, /* GREEK SMALL LETTER PHI */ + {"phiv", 0x03D5}, /* GREEK PHI SYMBOL */ + {"phmmat", 0x2133}, /* SCRIPT CAPITAL M */ + {"phone", 0x260E}, /* BLACK TELEPHONE */ + {"pi", 0x03C0}, /* GREEK SMALL LETTER PI */ + {"piv", 0x03D6}, /* GREEK PI SYMBOL */ + {"planck", 0x210F}, /* PLANCK CONSTANT OVER TWO PI */ + {"plus", 0x002B}, /* PLUS SIGN */ + {"plusb", 0x229E}, /* SQUARED PLUS */ + {"plusdo", 0x2214}, /* DOT PLUS */ + {"plusmn", 0x00B1}, /* PLUS-MINUS SIGN */ + {"pound", 0x00A3}, /* POUND SIGN */ + {"pr", 0x227A}, /* PRECEDES */ + {"pre", 0x227C}, /* PRECEDES OR EQUAL TO */ + {"prime", 0x2032}, /* PRIME */ + {"prnsim", 0x22E8}, /* PRECEDES BUT NOT EQUIVALENT TO */ + {"prod", 0x220F}, /* N-ARY PRODUCT */ + {"prop", 0x221D}, /* PROPORTIONAL TO */ + {"prsim", 0x227E}, /* PRECEDES OR EQUIVALENT TO */ + {"psgr", 0x03C8}, /* GREEK SMALL LETTER PSI */ + {"psi", 0x03C8}, /* GREEK SMALL LETTER PSI */ + {"puncsp", 0x2008}, /* PUNCTUATION SPACE */ + {"quest", 0x003F}, /* QUESTION MARK */ + {"quot", 0x0022}, /* QUOTATION MARK */ + {"quote", 0x0022}, /* QUOTATION MARK */ + {"rAarr", 0x21DB}, /* RIGHTWARDS TRIPLE ARROW */ + {"rArr", 0x21D2}, /* RIGHTWARDS DOUBLE ARROW */ + {"racute", 0x0155}, /* LATIN SMALL LETTER R WITH ACUTE */ + {"radic", 0x221A}, /* SQUARE ROOT */ + {"rang", 0x232A}, /* RIGHT-POINTING ANGLE BRACKET */ + {"raquo", 0x00BB}, /* RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK */ + {"rarr", 0x2192}, /* RIGHTWARDS ARROW */ + {"rarr2", 0x21C9}, /* RIGHTWARDS PAIRED ARROWS */ + {"rarrhk", 0x21AA}, /* RIGHTWARDS ARROW WITH HOOK */ + {"rarrlp", 0x21AC}, /* RIGHTWARDS ARROW WITH LOOP */ + {"rarrtl", 0x21A3}, /* RIGHTWARDS ARROW WITH TAIL */ + {"rarrw", 0x219D}, /* RIGHTWARDS WAVE ARROW */ + {"rcaron", 0x0159}, /* LATIN SMALL LETTER R WITH CARON */ + {"rcedil", 0x0157}, /* LATIN SMALL LETTER R WITH CEDILLA */ + {"rceil", 0x2309}, /* RIGHT CEILING */ + {"rcub", 0x007D}, /* RIGHT CURLY BRACKET */ + {"rcy", 0x0440}, /* CYRILLIC SMALL LETTER ER */ + {"rdquo", 0x201D}, /* RIGHT DOUBLE QUOTATION MARK */ + {"rdquor", 0x201C}, /* LEFT DOUBLE QUOTATION MARK */ + {"real", 0x211C}, /* BLACK-LETTER CAPITAL R */ + {"rect", 0x25AD}, /* WHITE RECTANGLE */ + {"reg", 0x00AE}, /* REGISTERED SIGN */ + {"rfloor", 0x230B}, /* RIGHT FLOOR */ + {"rgr", 0x03C1}, /* GREEK SMALL LETTER RHO */ + {"rhard", 0x21C1}, /* RIGHTWARDS HARPOON WITH BARB DOWNWARDS */ + {"rharu", 0x21C0}, /* RIGHTWARDS HARPOON WITH BARB UPWARDS */ + {"rho", 0x03C1}, /* GREEK SMALL LETTER RHO */ + {"rhov", 0x03F1}, /* GREEK RHO SYMBOL */ + {"ring", 0x02DA}, /* RING ABOVE */ + {"rlarr2", 0x21C4}, /* RIGHTWARDS ARROW OVER LEFTWARDS ARROW */ + {"rlhar2", 0x21CC}, /* RIGHTWARDS HARPOON OVER LEFTWARDS HARPOON */ + {"rlm", 0x200F}, /* RIGHT-TO-LEFT MARK */ + {"rpar", 0x0029}, /* RIGHT PARENTHESIS */ + {"rsaquo", 0x203A}, /* SINGLE RIGHT-POINTING ANGLE QUOTATION MARK */ + {"rsh", 0x21B1}, /* UPWARDS ARROW WITH TIP RIGHTWARDS */ + {"rsqb", 0x005D}, /* RIGHT SQUARE BRACKET */ + {"rsquo", 0x2019}, /* RIGHT SINGLE QUOTATION MARK */ + {"rsquor", 0x2018}, /* LEFT SINGLE QUOTATION MARK */ + {"rthree", 0x22CC}, /* RIGHT SEMIDIRECT PRODUCT */ + {"rtimes", 0x22CA}, /* RIGHT NORMAL FACTOR SEMIDIRECT PRODUCT */ + {"rtri", 0x25B9}, /* WHITE RIGHT-POINTING SMALL TRIANGLE */ + {"rtrie", 0x22B5}, /* CONTAINS AS NORMAL SUBGROUP OR EQUAL TO */ + {"rtrif", 0x25B8}, /* BLACK RIGHT-POINTING SMALL TRIANGLE */ + {"rx", 0x211E}, /* PRESCRIPTION TAKE */ + {"sacute", 0x015B}, /* LATIN SMALL LETTER S WITH ACUTE */ + {"samalg", 0x2210}, /* N-ARY COPRODUCT */ + {"sbquo", 0x201A}, /* SINGLE LOW-9 QUOTATION MARK */ + {"sbsol", 0x005C}, /* REVERSE SOLIDUS */ + {"sc", 0x227B}, /* SUCCEEDS */ + {"scaron", 0x0161}, /* LATIN SMALL LETTER S WITH CARON */ + {"sccue", 0x227D}, /* SUCCEEDS OR EQUAL TO */ + {"sce", 0x227D}, /* SUCCEEDS OR EQUAL TO */ + {"scedil", 0x015F}, /* LATIN SMALL LETTER S WITH CEDILLA */ + {"scirc", 0x015D}, /* LATIN SMALL LETTER S WITH CIRCUMFLEX */ + {"scnsim", 0x22E9}, /* SUCCEEDS BUT NOT EQUIVALENT TO */ + {"scsim", 0x227F}, /* SUCCEEDS OR EQUIVALENT TO */ + {"scy", 0x0441}, /* CYRILLIC SMALL LETTER ES */ + {"sdot", 0x22C5}, /* DOT OPERATOR */ + {"sdotb", 0x22A1}, /* SQUARED DOT OPERATOR */ + {"sect", 0x00A7}, /* SECTION SIGN */ + {"semi", 0x003B}, /* SEMICOLON */ + {"setmn", 0x2216}, /* SET MINUS */ + {"sext", 0x2736}, /* SIX POINTED BLACK STAR */ + {"sfgr", 0x03C2}, /* GREEK SMALL LETTER FINAL SIGMA */ + {"sfrown", 0x2322}, /* FROWN */ + {"sgr", 0x03C3}, /* GREEK SMALL LETTER SIGMA */ + {"sharp", 0x266F}, /* MUSIC SHARP SIGN */ + {"shchcy", 0x0449}, /* CYRILLIC SMALL LETTER SHCHA */ + {"shcy", 0x0448}, /* CYRILLIC SMALL LETTER SHA */ + {"shy", 0x00AD}, /* SOFT HYPHEN */ + {"sigma", 0x03C3}, /* GREEK SMALL LETTER SIGMA */ + {"sigmaf", 0x03C2}, /* GREEK SMALL LETTER FINAL SIGMA */ + {"sigmav", 0x03C2}, /* GREEK SMALL LETTER FINAL SIGMA */ + {"sim", 0x223C}, /* TILDE OPERATOR */ + {"sime", 0x2243}, /* ASYMPTOTICALLY EQUAL TO */ + {"smile", 0x2323}, /* SMILE */ + {"softcy", 0x044C}, /* CYRILLIC SMALL LETTER SOFT SIGN */ + {"sol", 0x002F}, /* SOLIDUS */ + {"spades", 0x2660}, /* BLACK SPADE SUIT */ + {"spar", 0x2225}, /* PARALLEL TO */ + {"sqcap", 0x2293}, /* SQUARE CAP */ + {"sqcup", 0x2294}, /* SQUARE CUP */ + {"sqsub", 0x228F}, /* SQUARE IMAGE OF */ + {"sqsube", 0x2291}, /* SQUARE IMAGE OF OR EQUAL TO */ + {"sqsup", 0x2290}, /* SQUARE ORIGINAL OF */ + {"sqsupe", 0x2292}, /* SQUARE ORIGINAL OF OR EQUAL TO */ + {"squ", 0x25A1}, /* WHITE SQUARE */ + {"square", 0x25A1}, /* WHITE SQUARE */ + {"squf", 0x25AA}, /* BLACK SMALL SQUARE */ + {"ssetmn", 0x2216}, /* SET MINUS */ + {"ssmile", 0x2323}, /* SMILE */ + {"sstarf", 0x22C6}, /* STAR OPERATOR */ + {"star", 0x2606}, /* WHITE STAR */ + {"starf", 0x2605}, /* BLACK STAR */ + {"sub", 0x2282}, /* SUBSET OF */ + {"subE", 0x2286}, /* SUBSET OF OR EQUAL TO */ + {"sube", 0x2286}, /* SUBSET OF OR EQUAL TO */ + {"subnE", 0x228A}, /* SUBSET OF WITH NOT EQUAL TO */ + {"subne", 0x228A}, /* SUBSET OF WITH NOT EQUAL TO */ + {"sum", 0x2211}, /* N-ARY SUMMATION */ + {"sung", 0x266A}, /* EIGHTH NOTE */ + {"sup", 0x2283}, /* SUPERSET OF */ + {"sup1", 0x00B9}, /* SUPERSCRIPT ONE */ + {"sup2", 0x00B2}, /* SUPERSCRIPT TWO */ + {"sup3", 0x00B3}, /* SUPERSCRIPT THREE */ + {"supE", 0x2287}, /* SUPERSET OF OR EQUAL TO */ + {"supe", 0x2287}, /* SUPERSET OF OR EQUAL TO */ + {"supnE", 0x228B}, /* SUPERSET OF WITH NOT EQUAL TO */ + {"supne", 0x228B}, /* SUPERSET OF WITH NOT EQUAL TO */ + {"szlig", 0x00DF}, /* LATIN SMALL LETTER SHARP S */ + {"target", 0x2316}, /* POSITION INDICATOR */ + {"tau", 0x03C4}, /* GREEK SMALL LETTER TAU */ + {"tcaron", 0x0165}, /* LATIN SMALL LETTER T WITH CARON */ + {"tcedil", 0x0163}, /* LATIN SMALL LETTER T WITH CEDILLA */ + {"tcy", 0x0442}, /* CYRILLIC SMALL LETTER TE */ + {"tdot", 0x20DB}, /* COMBINING THREE DOTS ABOVE */ + {"telrec", 0x2315}, /* TELEPHONE RECORDER */ + {"tgr", 0x03C4}, /* GREEK SMALL LETTER TAU */ + {"there4", 0x2234}, /* THEREFORE */ + {"theta", 0x03B8}, /* GREEK SMALL LETTER THETA */ + {"thetas", 0x03B8}, /* GREEK SMALL LETTER THETA */ + {"thetasym", 0x03D1}, /* GREEK THETA SYMBOL */ + {"thetav", 0x03D1}, /* GREEK THETA SYMBOL */ + {"thgr", 0x03B8}, /* GREEK SMALL LETTER THETA */ + {"thinsp", 0x2009}, /* THIN SPACE */ + {"thkap", 0x2248}, /* ALMOST EQUAL TO */ + {"thksim", 0x223C}, /* TILDE OPERATOR */ + {"thorn", 0x00FE}, /* LATIN SMALL LETTER THORN */ + {"tilde", 0x02DC}, /* SMALL TILDE */ + {"times", 0x00D7}, /* MULTIPLICATION SIGN */ + {"timesb", 0x22A0}, /* SQUARED TIMES */ + {"top", 0x22A4}, /* DOWN TACK */ + {"tprime", 0x2034}, /* TRIPLE PRIME */ + {"trade", 0x2122}, /* TRADE MARK SIGN */ + {"trie", 0x225C}, /* DELTA EQUAL TO */ + {"tscy", 0x0446}, /* CYRILLIC SMALL LETTER TSE */ + {"tshcy", 0x045B}, /* CYRILLIC SMALL LETTER TSHE */ + {"tstrok", 0x0167}, /* LATIN SMALL LETTER T WITH STROKE */ + {"twixt", 0x226C}, /* BETWEEN */ + {"uArr", 0x21D1}, /* UPWARDS DOUBLE ARROW */ + {"uacgr", 0x03CD}, /* GREEK SMALL LETTER UPSILON WITH TONOS */ + {"uacute", 0x00FA}, /* LATIN SMALL LETTER U WITH ACUTE */ + {"uarr", 0x2191}, /* UPWARDS ARROW */ + {"uarr2", 0x21C8}, /* UPWARDS PAIRED ARROWS */ + {"ubrcy", 0x045E}, /* CYRILLIC SMALL LETTER SHORT U */ + {"ubreve", 0x016D}, /* LATIN SMALL LETTER U WITH BREVE */ + {"ucirc", 0x00FB}, /* LATIN SMALL LETTER U WITH CIRCUMFLEX */ + {"ucy", 0x0443}, /* CYRILLIC SMALL LETTER U */ + {"udblac", 0x0171}, /* LATIN SMALL LETTER U WITH DOUBLE ACUTE */ + {"udiagr", 0x03B0}, /* GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND */ + {"udigr", 0x03CB}, /* GREEK SMALL LETTER UPSILON WITH DIALYTIKA */ + {"ugr", 0x03C5}, /* GREEK SMALL LETTER UPSILON */ + {"ugrave", 0x00F9}, /* LATIN SMALL LETTER U WITH GRAVE */ + {"uharl", 0x21BF}, /* UPWARDS HARPOON WITH BARB LEFTWARDS */ + {"uharr", 0x21BE}, /* UPWARDS HARPOON WITH BARB RIGHTWARDS */ + {"uhblk", 0x2580}, /* UPPER HALF BLOCK */ + {"ulcorn", 0x231C}, /* TOP LEFT CORNER */ + {"ulcrop", 0x230F}, /* TOP LEFT CROP */ + {"umacr", 0x016B}, /* LATIN SMALL LETTER U WITH MACRON */ + {"uml", 0x00A8}, /* DIAERESIS */ + {"uogon", 0x0173}, /* LATIN SMALL LETTER U WITH OGONEK */ + {"uplus", 0x228E}, /* MULTISET UNION */ + {"upsi", 0x03C5}, /* GREEK SMALL LETTER UPSILON */ + {"upsih", 0x03D2}, /* GREEK UPSILON WITH HOOK SYMBOL */ + {"upsilon", 0x03C5}, /* GREEK SMALL LETTER UPSILON */ + {"urcorn", 0x231D}, /* TOP RIGHT CORNER */ + {"urcrop", 0x230E}, /* TOP RIGHT CROP */ + {"uring", 0x016F}, /* LATIN SMALL LETTER U WITH RING ABOVE */ + {"utilde", 0x0169}, /* LATIN SMALL LETTER U WITH TILDE */ + {"utri", 0x25B5}, /* WHITE UP-POINTING SMALL TRIANGLE */ + {"utrif", 0x25B4}, /* BLACK UP-POINTING SMALL TRIANGLE */ + {"uuml", 0x00FC}, /* LATIN SMALL LETTER U WITH DIAERESIS */ + {"vArr", 0x21D5}, /* UP DOWN DOUBLE ARROW */ + {"vDash", 0x22A8}, /* TRUE */ + {"varr", 0x2195}, /* UP DOWN ARROW */ + {"vcy", 0x0432}, /* CYRILLIC SMALL LETTER VE */ + {"vdash", 0x22A2}, /* RIGHT TACK */ + {"veebar", 0x22BB}, /* XOR */ + {"vellip", 0x22EE}, /* VERTICAL ELLIPSIS */ + {"verbar", 0x007C}, /* VERTICAL LINE */ + {"vltri", 0x22B2}, /* NORMAL SUBGROUP OF */ + {"vprime", 0x2032}, /* PRIME */ + {"vprop", 0x221D}, /* PROPORTIONAL TO */ + {"vrtri", 0x22B3}, /* CONTAINS AS NORMAL SUBGROUP */ + {"vsubnE", 0x228A}, /* SUBSET OF WITH NOT EQUAL TO */ + {"vsubne", 0x228A}, /* SUBSET OF WITH NOT EQUAL TO */ + {"vsupnE", 0x228B}, /* SUPERSET OF WITH NOT EQUAL TO */ + {"vsupne", 0x228B}, /* SUPERSET OF WITH NOT EQUAL TO */ + {"wcirc", 0x0175}, /* LATIN SMALL LETTER W WITH CIRCUMFLEX */ + {"wedgeq", 0x2259}, /* ESTIMATES */ + {"weierp", 0x2118}, /* SCRIPT CAPITAL P */ + {"wreath", 0x2240}, /* WREATH PRODUCT */ + {"xcirc", 0x25CB}, /* WHITE CIRCLE */ + {"xdtri", 0x25BD}, /* WHITE DOWN-POINTING TRIANGLE */ + {"xgr", 0x03BE}, /* GREEK SMALL LETTER XI */ + {"xhArr", 0x2194}, /* LEFT RIGHT ARROW */ + {"xharr", 0x2194}, /* LEFT RIGHT ARROW */ + {"xi", 0x03BE}, /* GREEK SMALL LETTER XI */ + {"xlArr", 0x21D0}, /* LEFTWARDS DOUBLE ARROW */ + {"xrArr", 0x21D2}, /* RIGHTWARDS DOUBLE ARROW */ + {"xutri", 0x25B3}, /* WHITE UP-POINTING TRIANGLE */ + {"yacute", 0x00FD}, /* LATIN SMALL LETTER Y WITH ACUTE */ + {"yacy", 0x044F}, /* CYRILLIC SMALL LETTER YA */ + {"ycirc", 0x0177}, /* LATIN SMALL LETTER Y WITH CIRCUMFLEX */ + {"ycy", 0x044B}, /* CYRILLIC SMALL LETTER YERU */ + {"yen", 0x00A5}, /* YEN SIGN */ + {"yicy", 0x0457}, /* CYRILLIC SMALL LETTER YI */ + {"yucy", 0x044E}, /* CYRILLIC SMALL LETTER YU */ + {"yuml", 0x00FF}, /* LATIN SMALL LETTER Y WITH DIAERESIS */ + {"zacute", 0x017A}, /* LATIN SMALL LETTER Z WITH ACUTE */ + {"zcaron", 0x017E}, /* LATIN SMALL LETTER Z WITH CARON */ + {"zcy", 0x0437}, /* CYRILLIC SMALL LETTER ZE */ + {"zdot", 0x017C}, /* LATIN SMALL LETTER Z WITH DOT ABOVE */ + {"zeta", 0x03B6}, /* GREEK SMALL LETTER ZETA */ + {"zgr", 0x03B6}, /* GREEK SMALL LETTER ZETA */ + {"zhcy", 0x0436}, /* CYRILLIC SMALL LETTER ZHE */ + {"zwj", 0x200D}, /* ZERO WIDTH JOINER */ + {"zwnj", 0x200C}, /* ZERO WIDTH NON-JOINER */ +/* {"epsiv", 0x????}, variant epsilon # ISOgrk3 */ +/* {"fjlig", 0x????}, fj ligature # ISOpub */ +/* {"gEl", 0x????}, greater-than, double equals, less-than # ISOamsr */ +/* {"gap", 0x????}, greater-than, approximately equal to # ISOamsr */ +/* {"gnap", 0x????}, greater-than, not approximately equal t# ISOamsn */ +/* {"jnodot", 0x????}, latin small letter dotless j # ISOamso */ +/* {"lEg", 0x????}, less-than, double equals, greater-than # ISOamsr */ +/* {"lap", 0x????}, less-than, approximately equal to # ISOamsr */ +/* {"lnap", 0x????}, less-than, not approximately equal to # ISOamsn */ +/* {"lpargt", 0x????}, left parenthesis, greater-than # ISOamsc */ +/* {"ngE", 0x????}, not greater-than, double equals # ISOamsn */ +/* {"nlE", 0x????}, not less-than, double equals # ISOamsn */ +/* {"nsmid", 0x????}, nshortmid # ISOamsn */ +/* {"prap", 0x????}, precedes, approximately equal to # ISOamsr */ +/* {"prnE", 0x????}, precedes, not double equal # ISOamsn */ +/* {"prnap", 0x????}, precedes, not approximately equal to # ISOamsn */ +/* {"rpargt", 0x????}, right parenthesis, greater-than # ISOamsc */ +/* {"scap", 0x????}, succeeds, approximately equal to # ISOamsr */ +/* {"scnE", 0x????}, succeeds, not double equals # ISOamsn */ +/* {"scnap", 0x????}, succeeds, not approximately equal to # ISOamsn */ +/* {"smid", 0x????}, shortmid # ISOamsr */ +}; + +#endif /* ENTITIES_H */ diff --git a/Unicode/gen b/Unicode/gen new file mode 100755 index 0000000..41bf33d --- /dev/null +++ b/Unicode/gen @@ -0,0 +1,5 @@ +#!/bin/sh +./gen-cp +./gen-7b +./gen-ent +./gen-upc diff --git a/Unicode/gen-7b b/Unicode/gen-7b new file mode 100755 index 0000000..a879fc9 --- /dev/null +++ b/Unicode/gen-7b @@ -0,0 +1,20 @@ +#!/bin/sh +LC_ALL=C +export LC_ALL +echo +echo Generating Unicode2ascii translation table. +( +cat 7bitrepl.lnx | awk -f tr7bit.awk >tmp +N=`cat tmp | wc -l` +echo '/* Automatically generated by gen-7b */' +echo +echo 'static struct { int x; unsigned char *s; } unicode_7b ['`expr $N + 1`'] = {' +sort tmp | sed 's/"/\\"/g' | sed 's/^/ { /' | sed 's/:/, "/' | sed 's/$/" },/' +echo ' { -1, NULL }' +echo '};' +echo +echo '#define N_UNICODE_7B' $N +)>../uni_7b.inc +rm -f tmp +echo Done. +echo diff --git a/Unicode/gen-cp b/Unicode/gen-cp new file mode 100755 index 0000000..628c0e3 --- /dev/null +++ b/Unicode/gen-cp @@ -0,0 +1,34 @@ +#!/bin/sh +LC_ALL=C +export LC_ALL +echo +echo Generating code page translation tables. +codepages=`cat index.txt|sed 's/
//g'` +if [ -n "$codepages" ]; then +( +n=0 +echo '/* Automatically generated by gen-cp */' +for i in $codepages; do + echo -n $i' ' 1>&2 + echo + echo 'static struct table_entry table_'$i' [] = {' + tail -n +3 $i.cp | sed 's/#.*$//' | grep '^0x[89a-zA-Z]' | sed 's/[ ][ ]*/ /g' | sed 's/[ ]*$/ },/' | sed 's/ /, /' | sed 's/^[ ]*/ { /' | grep '.*,.*,' + echo ' { 0, 0 }' + echo '};' + echo + echo 'static unsigned char *aliases_'$i' [] = {'`head -2 $i.cp | tail -n +2`', NULL };' + n=`expr $n + 1` +done +echo +echo 'static struct codepage_desc codepages [] = {' +for i in $codepages; do + echo ' { "'`head -1 $i.cp`'", aliases_'$i', table_'$i' },' +done +echo ' { NULL, NULL, NULL }' +echo '};' +echo '#define N_CODEPAGES '$n | sed 's/
//g' > ../codepage.h +) | sed 's/
//g' > ../codepage.inc +echo +echo Done. +fi +echo diff --git a/Unicode/gen-ent b/Unicode/gen-ent new file mode 100755 index 0000000..7f43f7c --- /dev/null +++ b/Unicode/gen-ent @@ -0,0 +1,20 @@ +#!/bin/sh +LC_ALL=c +export LC_ALL +echo +echo Generating entity table. +( +cat entities.lnx | sed 's/
$//' | grep '^[ ]*{"' | sort >tmp +N=`cat tmp | wc -l` +echo '/* Automatically generated by gen-ent */' +echo +echo 'static struct { unsigned char *s; int c; } entities ['`expr $N + 1`'] = {' +cat tmp +echo ' {NULL, 0}' +echo '};' +echo +echo '#define N_ENTITIES' $N +) > ../entity.inc +rm -f tmp +echo Done. +echo diff --git a/Unicode/gen-upc b/Unicode/gen-upc new file mode 100755 index 0000000..724e6ff --- /dev/null +++ b/Unicode/gen-upc @@ -0,0 +1,14 @@ +#!/bin/sh +LC_ALL=C +export LC_ALL +echo +echo Generating Unicode upcase table. +( +echo '/* Automatically generated by gen-upc */' +echo +echo 'static struct { unsigned lo; unsigned up; } unicode_upcase [] = {' +(echo ' 160 32';cat upcase.uni) | sed 's/^[ ]*//' | sed 's/[ ]*$//' | sed 's/ */, /' | sort -n | sed 's/^/ { /' | sed 's/$/ },/' +echo '};' +) > ../upcase.inc +echo Done. +echo diff --git a/Unicode/index.txt b/Unicode/index.txt new file mode 100644 index 0000000..07b0606 --- /dev/null +++ b/Unicode/index.txt @@ -0,0 +1,35 @@ +7bit +8859_1 +8859_2 +8859_3 +8859_4 +8859_5 +8859_6 +8859_7 +8859_8 +8859_9 +8859_10 +8859_13 +8859_14 +8859_15 +8859_16 +cp1250 +cp1251 +cp1252 +cp1256 +cp1257 +cp437 +cp737 +cp850 +cp852 +cp866 +cp1125 +macroman +mac_lat2 +kamen +koi8_r +koi8_u +koi8_ru +tcvn5712 +viscii +utf_8 diff --git a/Unicode/kamen.cp b/Unicode/kamen.cp new file mode 100644 index 0000000..860d330 --- /dev/null +++ b/Unicode/kamen.cp @@ -0,0 +1,263 @@ +Kamenicky Brothers +"x-kam-cs", "kam", "867", "869" + +# Kamenicky Brothers Charset File +# Czech characters extracted from CStoCS "kam.enc" and others copied from +# IBM charset by Martin Mares <mj@atrey.karlin.mff.cuni.cz> + +0x00 0x0000 #<control> +0x01 0x263A #WHITE SMILING FACE +0x02 0x263B #BLACK SMILING FACE +0x03 0x2665 #BLACK HEART SUIT +0x04 0x2666 #BLACK DIAMOND SUIT +0x05 0x2663 #BLACK CLUB SUIT +0x06 0x2660 #BLACK SPADE SUIT +0x07 0x2022 #BULLET +0x08 0x25D8 #INVERSE BULLET +0x09 0x25CB #WHITE CIRCLE +0x0A 0x25D9 #INVERSE WHITE CIRCLE +0x0B 0x2642 #MALE SIGN +0x0C 0x2640 #FEMALE SIGN +0x0D 0x266A #EIGHTH NOTE +0x0E 0x266B #BEAMED EIGHTH NOTES +0x0F 0x263C #WHITE SUN WITH RAYS +0x10 0x25B6 #BLACK RIGHT-POINTING TRIANGLE +0x11 0x25C0 #BLACK LEFT-POINTING TRIANGLE +0x12 0x2195 #UP DOWN ARROW +0x13 0x203C #DOUBLE EXCLAMATION MARK +0x14 0x00B6 #PILCROW SIGN +0x15 0x00A7 #SECTION SIGN +0x16 0x25AC #BLACK RECTANGLE +0x17 0x21A8 #UP DOWN ARROW WITH BASE +0x18 0x2191 #UPWARDS ARROW +0x19 0x2193 #DOWNWARDS ARROW +0x1A 0x2192 #RIGHTWARDS ARROW +0x1B 0x2190 #LEFTWARDS ARROW +0x1C 0x221F #RIGHT ANGLE +0x1D 0x2194 #LEFT RIGHT ARROW +0x1E 0x25B2 #BLACK UP-POINTING TRIANGLE +0x1F 0x25BC #BLACK DOWN-POINTING TRIANGLE +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x2302 #HOUSE +0x80 0x010C #LATIN CAPITAL LETTER C WITH CARON +0x81 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0x82 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0x83 0x010F #LATIN SMALL LETTER D WITH CARON +0x84 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0x85 0x010E #LATIN CAPITAL LETTER D WITH CARON +0x86 0x0164 #LATIN CAPITAL LETTER T WITH CARON +0x87 0x010D #LATIN SMALL LETTER C WITH CARON +0x88 0x011B #LATIN SMALL LETTER E WITH CARON +0x89 0x011A #LATIN CAPITAL LETTER E WITH CARON +0x8A 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE +0x8B 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0x8C 0x013E #LATIN SMALL LETTER L WITH CARON +0x8D 0x013A #LATIN SMALL LETTER L WITH ACUTE +0x8E 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0x8F 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0x90 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0x91 0x017E #LATIN SMALL LETTER Z WITH CARON +0x92 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0x93 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0x94 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0x95 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0x96 0x016F #LATIN SMALL LETTER U WITH RING ABOVE +0x97 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0x98 0x00FD #LATIN SMALL LETTER Y WITH ACUTE +0x99 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0x9A 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0x9B 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0x9C 0x013D #LATIN CAPITAL LETTER L WITH CARON +0x9D 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE +0x9E 0x0158 #LATIN CAPITAL LETTER R WITH CARON +0x9F 0x0165 #LATIN SMALL LETTER T WITH CARON +0xA0 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xA1 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xA2 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xA3 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xA4 0x0148 #LATIN SMALL LETTER N WITH CARON +0xA5 0x0147 #LATIN CAPITAL LETTER N WITH CARON +0xA6 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE +0xA7 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xA8 0x0161 #LATIN SMALL LETTER S WITH CARON +0xA9 0x0159 #LATIN SMALL LETTER R WITH CARON +0xAA 0x0155 #LATIN SMALL LETTER R WITH ACUTE +0xAB 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE +0xAC 0x00BC #VULGAR FRACTION ONE QUARTER +0xAD 0x00A7 #SECTION SIGN +0xAE 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAF 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xB0 0x2591 #LIGHT SHADE +0xB1 0x2592 #MEDIUM SHADE +0xB2 0x2593 #DARK SHADE +0xB3 0x2502 #BOX DRAWINGS LIGHT VERTICAL +0xB4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT +0xB5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xB6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE +0xB7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE +0xB8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE +0xB9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xBA 0x2551 #BOX DRAWINGS DOUBLE VERTICAL +0xBB 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT +0xBC 0x255D #BOX DRAWINGS DOUBLE UP AND LEFT +0xBD 0x255C #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE +0xBE 0x255B #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xBF 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT +0xC0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT +0xC1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL +0xC2 0x252C #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0xC3 0x251C #BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0xC4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL +0xC5 0x253C #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0xC6 0x255E #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xC7 0x255F #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xC8 0x255A #BOX DRAWINGS DOUBLE UP AND RIGHT +0xC9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xCA 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xCB 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xCC 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xCD 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL +0xCE 0x256C #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xCF 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xD0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xD1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE +0xD2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE +0xD3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xD4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xD5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xD6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE +0xD7 0x256B #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE +0xD8 0x256A #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xD9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT +0xDA 0x250C #BOX DRAWINGS LIGHT DOWN AND RIGHT +0xDB 0x2588 #FULL BLOCK +0xDC 0x2584 #LOWER HALF BLOCK +0xDD 0x258C #LEFT HALF BLOCK +0xDE 0x2590 #RIGHT HALF BLOCK +0xDF 0x2580 #UPPER HALF BLOCK +0xE0 0x03B1 #GREEK SMALL LETTER ALPHA +0xE1 0x03B2 #GREEK SMALL LETTER BETA +0xE2 0x0194 #LATIN CAPITAL LETTER GAMMA +0xE3 0x03C0 #GREEK SMALL LETTER PI +0xE4 0x03A3 #GREEK CAPITAL LETTER SIGMA +0xE5 0x03C3 #GREEK SMALL LETTER SIGMA +0xE6 0x03BC #GREEK SMALL LETTER MU +0xE7 0x03C4 #GREEK SMALL LETTER TAU +0xE8 0x03A6 #GREEK CAPITAL LETTER PHI +0xE9 0x0398 #GREEK CAPITAL LETTER THETA +0xEA 0x03A9 #GREEK CAPITAL LETTER OMEGA +0xEB 0x03B4 #GREEK SMALL LETTER DELTA +0xEC 0x221E #INFINITY +0xED 0x03C6 #GREEK SMALL LETTER PHI +0xEE 0x2208 #ELEMENT OF +0xEF 0x2229 #INTERSECTION +0xF0 0x224D #EQUIVALENT TO +0xF1 0x00B1 #PLUS-MINUS SIGN +0xF2 0x2265 #GREATER-THAN OR EQUAL TO +0xF3 0x2264 #LESS-THAN OR EQUAL TO +0xF4 0x2320 #TOP HALF INTEGRAL +0xF5 0x2321 #BOTTOM HALF INTEGRAL +0xF6 0x00F7 #DIVISION SIGN +0xF7 0x2248 #ALMOST EQUAL TO +0xF8 0x00B0 #DEGREE SIGN +0xF9 0x2219 #BULLET OPERATOR +0xFA 0x00B7 #MIDDLE DOT +0xFB 0x221A #SQUARE ROOT +0xFC 0x207F #SUPERSCRIPT LATIN SMALL LETTER N +0xFD 0x00B2 #SUPERSCRIPT TWO +0xFE 0x25A0 #BLACK SQUARE +0xFF 0x00A0 #NO-BREAK SPACE diff --git a/Unicode/koi8_r.cp b/Unicode/koi8_r.cp new file mode 100644 index 0000000..2f3f416 --- /dev/null +++ b/Unicode/koi8_r.cp @@ -0,0 +1,226 @@ +KOI8-R +"koi8-r" + +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x80 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL +0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL +0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT +0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT +0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT +0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT +0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT +0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL +0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0x8B 0x2580 # UPPER HALF BLOCK +0x8C 0x2584 # LOWER HALF BLOCK +0x8D 0x2588 # FULL BLOCK +0x8E 0x258C # LEFT HALF BLOCK +0x8F 0x2590 # RIGHT HALF BLOCK +0x90 0x2591 # LIGHT SHADE +0x91 0x2592 # MEDIUM SHADE +0x92 0x2593 # DARK SHADE +0x93 0x2320 # TOP HALF INTEGRAL +0x94 0x25A0 # BLACK SQUARE +0x95 0x2022 # BULLET +0x96 0x221A # SQUARE ROOT +0x97 0x2248 # ALMOST EQUAL TO +0x98 0x2264 # LESS-THAN OR EQUAL TO +0x99 0x2265 # GREATER-THAN OR EQUAL TO +0x9A 0x00A0 # NO-BREAK SPACE +0x9B 0x2321 # BOTTOM HALF INTEGRAL +0x9C 0x00B0 # DEGREE SIGN +0x9D 0x00B2 # SUPERSCRIPT TWO +0x9E 0x00B7 # MIDDLE DOT +0x9F 0x00F7 # DIVISION SIGN +0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL +0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL +0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xA3 0x0451 # CYRILLIC SMALL LETTER IO +0xA4 0x2553 # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE +0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xA6 0x2555 # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE +0xA7 0x2556 # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE +0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT +0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT +0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xAD 0x255C # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE +0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT +0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO +0xB4 0x2562 # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE +0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xB6 0x2564 # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE +0xB7 0x2565 # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE +0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xBD 0x256B # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE +0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xBF 0x00A9 # COPYRIGHT SIGN +0xC0 0x044E # CYRILLIC SMALL LETTER YU +0xC1 0x0430 # CYRILLIC SMALL LETTER A +0xC2 0x0431 # CYRILLIC SMALL LETTER BE +0xC3 0x0446 # CYRILLIC SMALL LETTER TSE +0xC4 0x0434 # CYRILLIC SMALL LETTER DE +0xC5 0x0435 # CYRILLIC SMALL LETTER IE +0xC6 0x0444 # CYRILLIC SMALL LETTER EF +0xC7 0x0433 # CYRILLIC SMALL LETTER GHE +0xC8 0x0445 # CYRILLIC SMALL LETTER HA +0xC9 0x0438 # CYRILLIC SMALL LETTER I +0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I +0xCB 0x043A # CYRILLIC SMALL LETTER KA +0xCC 0x043B # CYRILLIC SMALL LETTER EL +0xCD 0x043C # CYRILLIC SMALL LETTER EM +0xCE 0x043D # CYRILLIC SMALL LETTER EN +0xCF 0x043E # CYRILLIC SMALL LETTER O +0xD0 0x043F # CYRILLIC SMALL LETTER PE +0xD1 0x044F # CYRILLIC SMALL LETTER YA +0xD2 0x0440 # CYRILLIC SMALL LETTER ER +0xD3 0x0441 # CYRILLIC SMALL LETTER ES +0xD4 0x0442 # CYRILLIC SMALL LETTER TE +0xD5 0x0443 # CYRILLIC SMALL LETTER U +0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE +0xD7 0x0432 # CYRILLIC SMALL LETTER VE +0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN +0xD9 0x044B # CYRILLIC SMALL LETTER YERU +0xDA 0x0437 # CYRILLIC SMALL LETTER ZE +0xDB 0x0448 # CYRILLIC SMALL LETTER SHA +0xDC 0x044D # CYRILLIC SMALL LETTER E +0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA +0xDE 0x0447 # CYRILLIC SMALL LETTER CHE +0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN +0xE0 0x042E # CYRILLIC CAPITAL LETTER YU +0xE1 0x0410 # CYRILLIC CAPITAL LETTER A +0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE +0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE +0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE +0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE +0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF +0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE +0xE8 0x0425 # CYRILLIC CAPITAL LETTER HA +0xE9 0x0418 # CYRILLIC CAPITAL LETTER I +0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I +0xEB 0x041A # CYRILLIC CAPITAL LETTER KA +0xEC 0x041B # CYRILLIC CAPITAL LETTER EL +0xED 0x041C # CYRILLIC CAPITAL LETTER EM +0xEE 0x041D # CYRILLIC CAPITAL LETTER EN +0xEF 0x041E # CYRILLIC CAPITAL LETTER O +0xF0 0x041F # CYRILLIC CAPITAL LETTER PE +0xF1 0x042F # CYRILLIC CAPITAL LETTER YA +0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER +0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES +0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE +0xF5 0x0423 # CYRILLIC CAPITAL LETTER U +0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE +0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE +0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN +0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU +0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE +0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA +0xFC 0x042D # CYRILLIC CAPITAL LETTER E +0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA +0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE +0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN diff --git a/Unicode/koi8_ru.cp b/Unicode/koi8_ru.cp new file mode 100644 index 0000000..2e363bc --- /dev/null +++ b/Unicode/koi8_ru.cp @@ -0,0 +1,137 @@ +KOI8-RU +"koi8-ru" +# +# UNIX Belarusian and Ukrainian (koi8-u) to UNICODE translation table +# +# Based on koi8u_uni.tbl from lynx 2.8.2 distribution +# by porokh +# Belarusian language support by Yevgeny Gromov <yevgeny@tut.by> +# +0x80 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL +0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL +0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT +0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT +0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT +0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT +0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT +0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL +0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0x8B 0x2580 # UPPER HALF BLOCK +0x8C 0x2584 # LOWER HALF BLOCK +0x8D 0x2588 # FULL BLOCK +0x8E 0x258C # LEFT HALF BLOCK +0x8F 0x2590 # RIGHT HALF BLOCK +0x90 0x2591 # LIGHT SHADE +0x91 0x2592 # MEDIUM SHADE +0x92 0x2593 # DARK SHADE +0x93 0x2320 # TOP HALF INTEGRAL +0x94 0x25A0 # BLACK SQUARE +0x95 0x2219 # BULLET OPERATOR +0x96 0x221A # SQUARE ROOT +0x97 0x2248 # ALMOST EQUAL TO +0x98 0x2264 # LESS THAN OR EQUAL TO +0x99 0x2265 # GREATER THAN OR EQUAL TO +0x9A 0x00A0 # NO-BREAK SPACE +0x9B 0x2321 # BOTTOM HALF INTEGRAL +0x9C 0x00B0 # DEGREE SIGN +0x9D 0x00B2 # SUPERSCRIPT TWO +0x9E 0x00B7 # MIDDLE DOT +0x9F 0x00F7 # DIVISION SIGN +0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL +0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL +0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xA3 0x0451 # CYRILLIC SMALL LETTER IO +0xA4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE +0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xA6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +0xA7 0x0457 # CYRILLIC SMALL LETTER YI (UKRAINIAN) +0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT +0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT +0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xAD 0x0491 # CYRILLIC SMALL LETTER GHE WITH UPTURN +0xAE 0x045E # CYRILLIC SMALL LETTER SHORT U +0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO +0xB4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xB6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0xB7 0x0407 # CYRILLIC CAPITAL LETTER YI (UKRAINIAN) +0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xBD 0x0490 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN +0xBE 0x040E # CYRILLIC CAPITAL LETTER SHORT U +0xBF 0x00A9 # COPYRIGHT SIGN +0xC0 0x044E # CYRILLIC SMALL LETTER YU +0xC1 0x0430 # CYRILLIC SMALL LETTER A +0xC2 0x0431 # CYRILLIC SMALL LETTER BE +0xC3 0x0446 # CYRILLIC SMALL LETTER TSE +0xC4 0x0434 # CYRILLIC SMALL LETTER DE +0xC5 0x0435 # CYRILLIC SMALL LETTER IE +0xC6 0x0444 # CYRILLIC SMALL LETTER EF +0xC7 0x0433 # CYRILLIC SMALL LETTER GHE +0xC8 0x0445 # CYRILLIC SMALL LETTER KHA +0xC9 0x0438 # CYRILLIC SMALL LETTER I +0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I +0xCB 0x043A # CYRILLIC SMALL LETTER KA +0xCC 0x043B # CYRILLIC SMALL LETTER EL +0xCD 0x043C # CYRILLIC SMALL LETTER EM +0xCE 0x043D # CYRILLIC SMALL LETTER EN +0xCF 0x043E # CYRILLIC SMALL LETTER O +0xD0 0x043F # CYRILLIC SMALL LETTER PE +0xD1 0x044F # CYRILLIC SMALL LETTER YA +0xD2 0x0440 # CYRILLIC SMALL LETTER ER +0xD3 0x0441 # CYRILLIC SMALL LETTER ES +0xD4 0x0442 # CYRILLIC SMALL LETTER TE +0xD5 0x0443 # CYRILLIC SMALL LETTER U +0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE +0xD7 0x0432 # CYRILLIC SMALL LETTER VE +0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN +0xD9 0x044B # CYRILLIC SMALL LETTER YERU +0xDA 0x0437 # CYRILLIC SMALL LETTER ZE +0xDB 0x0448 # CYRILLIC SMALL LETTER SHA +0xDC 0x044D # CYRILLIC SMALL LETTER E +0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA +0xDE 0x0447 # CYRILLIC SMALL LETTER CHE +0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN +0xE0 0x042E # CYRILLIC CAPITAL LETTER YU +0xE1 0x0410 # CYRILLIC CAPITAL LETTER A +0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE +0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE +0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE +0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE +0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF +0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE +0xE8 0x0425 # CYRILLIC CAPITAL LETTER KHA +0xE9 0x0418 # CYRILLIC CAPITAL LETTER I +0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I +0xEB 0x041A # CYRILLIC CAPITAL LETTER KA +0xEC 0x041B # CYRILLIC CAPITAL LETTER EL +0xED 0x041C # CYRILLIC CAPITAL LETTER EM +0xEE 0x041D # CYRILLIC CAPITAL LETTER EN +0xEF 0x041E # CYRILLIC CAPITAL LETTER O +0xF0 0x041F # CYRILLIC CAPITAL LETTER PE +0xF1 0x042F # CYRILLIC CAPITAL LETTER YA +0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER +0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES +0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE +0xF5 0x0423 # CYRILLIC CAPITAL LETTER U +0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE +0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE +0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN +0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU +0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE +0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA +0xFC 0x042D # CYRILLIC CAPITAL LETTER E +0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA +0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE +0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN diff --git a/Unicode/koi8_u.cp b/Unicode/koi8_u.cp new file mode 100644 index 0000000..ecff9ee --- /dev/null +++ b/Unicode/koi8_u.cp @@ -0,0 +1,136 @@ +KOI8-U +"koi8-u" +# +# UNIX Ukrainian (koi8-u) to UNICODE translation table +# +# Based on koi8u_uni.tbl from lynx 2.8.2 distribution +# by porokh +# +0x80 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL +0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL +0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT +0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT +0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT +0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT +0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT +0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL +0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0x8B 0x2580 # UPPER HALF BLOCK +0x8C 0x2584 # LOWER HALF BLOCK +0x8D 0x2588 # FULL BLOCK +0x8E 0x258C # LEFT HALF BLOCK +0x8F 0x2590 # RIGHT HALF BLOCK +0x90 0x2591 # LIGHT SHADE +0x91 0x2592 # MEDIUM SHADE +0x92 0x2593 # DARK SHADE +0x93 0x2320 # TOP HALF INTEGRAL +0x94 0x25A0 # BLACK SQUARE +0x95 0x2219 # BULLET OPERATOR +0x96 0x221A # SQUARE ROOT +0x97 0x2248 # ALMOST EQUAL TO +0x98 0x2264 # LESS THAN OR EQUAL TO +0x99 0x2265 # GREATER THAN OR EQUAL TO +0x9A 0x00A0 # NO-BREAK SPACE +0x9B 0x2321 # BOTTOM HALF INTEGRAL +0x9C 0x00B0 # DEGREE SIGN +0x9D 0x00B2 # SUPERSCRIPT TWO +0x9E 0x00B7 # MIDDLE DOT +0x9F 0x00F7 # DIVISION SIGN +0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL +0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL +0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xA3 0x0451 # CYRILLIC SMALL LETTER IO +0xA4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE +0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xA6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +0xA7 0x0457 # CYRILLIC SMALL LETTER YI (UKRAINIAN) +0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT +0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT +0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xAD 0x0491 # CYRILLIC SMALL LETTER GHE WITH UPTURN +0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT +0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO +0xB4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xB6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0xB7 0x0407 # CYRILLIC CAPITAL LETTER YI (UKRAINIAN) +0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xBD 0x0490 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN +0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xBF 0x00A9 # COPYRIGHT SIGN +0xC0 0x044E # CYRILLIC SMALL LETTER YU +0xC1 0x0430 # CYRILLIC SMALL LETTER A +0xC2 0x0431 # CYRILLIC SMALL LETTER BE +0xC3 0x0446 # CYRILLIC SMALL LETTER TSE +0xC4 0x0434 # CYRILLIC SMALL LETTER DE +0xC5 0x0435 # CYRILLIC SMALL LETTER IE +0xC6 0x0444 # CYRILLIC SMALL LETTER EF +0xC7 0x0433 # CYRILLIC SMALL LETTER GHE +0xC8 0x0445 # CYRILLIC SMALL LETTER KHA +0xC9 0x0438 # CYRILLIC SMALL LETTER I +0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I +0xCB 0x043A # CYRILLIC SMALL LETTER KA +0xCC 0x043B # CYRILLIC SMALL LETTER EL +0xCD 0x043C # CYRILLIC SMALL LETTER EM +0xCE 0x043D # CYRILLIC SMALL LETTER EN +0xCF 0x043E # CYRILLIC SMALL LETTER O +0xD0 0x043F # CYRILLIC SMALL LETTER PE +0xD1 0x044F # CYRILLIC SMALL LETTER YA +0xD2 0x0440 # CYRILLIC SMALL LETTER ER +0xD3 0x0441 # CYRILLIC SMALL LETTER ES +0xD4 0x0442 # CYRILLIC SMALL LETTER TE +0xD5 0x0443 # CYRILLIC SMALL LETTER U +0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE +0xD7 0x0432 # CYRILLIC SMALL LETTER VE +0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN +0xD9 0x044B # CYRILLIC SMALL LETTER YERU +0xDA 0x0437 # CYRILLIC SMALL LETTER ZE +0xDB 0x0448 # CYRILLIC SMALL LETTER SHA +0xDC 0x044D # CYRILLIC SMALL LETTER E +0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA +0xDE 0x0447 # CYRILLIC SMALL LETTER CHE +0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN +0xE0 0x042E # CYRILLIC CAPITAL LETTER YU +0xE1 0x0410 # CYRILLIC CAPITAL LETTER A +0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE +0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE +0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE +0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE +0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF +0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE +0xE8 0x0425 # CYRILLIC CAPITAL LETTER KHA +0xE9 0x0418 # CYRILLIC CAPITAL LETTER I +0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I +0xEB 0x041A # CYRILLIC CAPITAL LETTER KA +0xEC 0x041B # CYRILLIC CAPITAL LETTER EL +0xED 0x041C # CYRILLIC CAPITAL LETTER EM +0xEE 0x041D # CYRILLIC CAPITAL LETTER EN +0xEF 0x041E # CYRILLIC CAPITAL LETTER O +0xF0 0x041F # CYRILLIC CAPITAL LETTER PE +0xF1 0x042F # CYRILLIC CAPITAL LETTER YA +0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER +0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES +0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE +0xF5 0x0423 # CYRILLIC CAPITAL LETTER U +0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE +0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE +0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN +0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU +0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE +0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA +0xFC 0x042D # CYRILLIC CAPITAL LETTER E +0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA +0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE +0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN diff --git a/Unicode/mac_lat2.cp b/Unicode/mac_lat2.cp new file mode 100644 index 0000000..f8b791c --- /dev/null +++ b/Unicode/mac_lat2.cp @@ -0,0 +1,276 @@ +Mac latin 2 +"x-mac-ce", "mac-ce", "maclatin2", "10029" +# +# Name: cp10029_MacLatin2 to Unicode table +# Unicode version: 2.0 +# Table version: 2.00 +# Table format: Format A +# Date: 04/24/96 +# Authors: Lori Brownell <loribr@microsoft.com> +# K.D. Chang <a-kchang@microsoft.com> +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp10029_MacLatin2 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp10029_MacLatin2 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0x81 0x0100 #LATIN CAPITAL LETTER A WITH MACRON +0x82 0x0101 #LATIN SMALL LETTER A WITH MACRON +0x83 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0x84 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK +0x85 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0x86 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0x87 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0x88 0x0105 #LATIN SMALL LETTER A WITH OGONEK +0x89 0x010C #LATIN CAPITAL LETTER C WITH CARON +0x8A 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0x8B 0x010D #LATIN SMALL LETTER C WITH CARON +0x8C 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE +0x8D 0x0107 #LATIN SMALL LETTER C WITH ACUTE +0x8E 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0x8F 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE +0x90 0x017A #LATIN SMALL LETTER Z WITH ACUTE +0x91 0x010E #LATIN CAPITAL LETTER D WITH CARON +0x92 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0x93 0x010F #LATIN SMALL LETTER D WITH CARON +0x94 0x0112 #LATIN CAPITAL LETTER E WITH MACRON +0x95 0x0113 #LATIN SMALL LETTER E WITH MACRON +0x96 0x0116 #LATIN CAPITAL LETTER E WITH DOT ABOVE +0x97 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0x98 0x0117 #LATIN SMALL LETTER E WITH DOT ABOVE +0x99 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0x9A 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0x9B 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0x9C 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0x9D 0x011A #LATIN CAPITAL LETTER E WITH CARON +0x9E 0x011B #LATIN SMALL LETTER E WITH CARON +0x9F 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xA0 0x2020 #DAGGER +0xA1 0x00B0 #DEGREE SIGN +0xA2 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A7 #SECTION SIGN +0xA5 0x2022 #BULLET +0xA6 0x00B6 #PILCROW SIGN +0xA7 0x00DF #LATIN SMALL LETTER SHARP S +0xA8 0x00AE #REGISTERED SIGN +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x2122 #TRADE MARK SIGN +0xAB 0x0119 #LATIN SMALL LETTER E WITH OGONEK +0xAC 0x00A8 #DIAERESIS +0xAD 0x2260 #NOT EQUAL TO +0xAE 0x0123 #LATIN SMALL LETTER G WITH CEDILLA +0xAF 0x012E #LATIN CAPITAL LETTER I WITH OGONEK +0xB0 0x012F #LATIN SMALL LETTER I WITH OGONEK +0xB1 0x012A #LATIN CAPITAL LETTER I WITH MACRON +0xB2 0x2264 #LESS-THAN OR EQUAL TO +0xB3 0x2265 #GREATER-THAN OR EQUAL TO +0xB4 0x012B #LATIN SMALL LETTER I WITH MACRON +0xB5 0x0136 #LATIN CAPITAL LETTER K WITH CEDILLA +0xB6 0x2202 #PARTIAL DIFFERENTIAL +0xB7 0x2211 #N-ARY SUMMATION +0xB8 0x0142 #LATIN SMALL LETTER L WITH STROKE +0xB9 0x013B #LATIN CAPITAL LETTER L WITH CEDILLA +0xBA 0x013C #LATIN SMALL LETTER L WITH CEDILLA +0xBB 0x013D #LATIN CAPITAL LETTER L WITH CARON +0xBC 0x013E #LATIN SMALL LETTER L WITH CARON +0xBD 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE +0xBE 0x013A #LATIN SMALL LETTER L WITH ACUTE +0xBF 0x0145 #LATIN CAPITAL LETTER N WITH CEDILLA +0xC0 0x0146 #LATIN SMALL LETTER N WITH CEDILLA +0xC1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE +0xC2 0x00AC #NOT SIGN +0xC3 0x221A #SQUARE ROOT +0xC4 0x0144 #LATIN SMALL LETTER N WITH ACUTE +0xC5 0x0147 #LATIN CAPITAL LETTER N WITH CARON +0xC6 0x2206 #INCREMENT +0xC7 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xC8 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xC9 0x2026 #HORIZONTAL ELLIPSIS +0xCA 0x00A0 #NO-BREAK SPACE +0xCB 0x0148 #LATIN SMALL LETTER N WITH CARON +0xCC 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0xCD 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xCE 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE +0xCF 0x014C #LATIN CAPITAL LETTER O WITH MACRON +0xD0 0x2013 #EN DASH +0xD1 0x2014 #EM DASH +0xD2 0x201C #LEFT DOUBLE QUOTATION MARK +0xD3 0x201D #RIGHT DOUBLE QUOTATION MARK +0xD4 0x2018 #LEFT SINGLE QUOTATION MARK +0xD5 0x2019 #RIGHT SINGLE QUOTATION MARK +0xD6 0x00F7 #DIVISION SIGN +0xD7 0x25CA #LOZENGE +0xD8 0x014D #LATIN SMALL LETTER O WITH MACRON +0xD9 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE +0xDA 0x0155 #LATIN SMALL LETTER R WITH ACUTE +0xDB 0x0158 #LATIN CAPITAL LETTER R WITH CARON +0xDC 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0xDD 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0xDE 0x0159 #LATIN SMALL LETTER R WITH CARON +0xDF 0x0156 #LATIN CAPITAL LETTER R WITH CEDILLA +0xE0 0x0157 #LATIN SMALL LETTER R WITH CEDILLA +0xE1 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0xE2 0x201A #SINGLE LOW-9 QUOTATION MARK +0xE3 0x201E #DOUBLE LOW-9 QUOTATION MARK +0xE4 0x0161 #LATIN SMALL LETTER S WITH CARON +0xE5 0x015A #LATIN CAPITAL LETTER S WITH ACUTE +0xE6 0x015B #LATIN SMALL LETTER S WITH ACUTE +0xE7 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xE8 0x0164 #LATIN CAPITAL LETTER T WITH CARON +0xE9 0x0165 #LATIN SMALL LETTER T WITH CARON +0xEA 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xEB 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0xEC 0x017E #LATIN SMALL LETTER Z WITH CARON +0xED 0x016A #LATIN CAPITAL LETTER U WITH MACRON +0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xEF 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xF0 0x016B #LATIN SMALL LETTER U WITH MACRON +0xF1 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE +0xF2 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xF3 0x016F #LATIN SMALL LETTER U WITH RING ABOVE +0xF4 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0xF5 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE +0xF6 0x0172 #LATIN CAPITAL LETTER U WITH OGONEK +0xF7 0x0173 #LATIN SMALL LETTER U WITH OGONEK +0xF8 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE +0xF9 0x00FD #LATIN SMALL LETTER Y WITH ACUTE +0xFA 0x0137 #LATIN SMALL LETTER K WITH CEDILLA +0xFB 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xFC 0x0141 #LATIN CAPITAL LETTER L WITH STROKE +0xFD 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE +0xFE 0x0122 #LATIN CAPITAL LETTER G WITH CEDILLA +0xFF 0x02C7 #CARON + diff --git a/Unicode/macroman.cp b/Unicode/macroman.cp new file mode 100644 index 0000000..d544587 --- /dev/null +++ b/Unicode/macroman.cp @@ -0,0 +1,258 @@ +MacRoman 2000 +"x-mac", "mac", "macroman" +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0x81 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0x82 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0x83 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0x84 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE +0x85 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0x86 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0x87 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0x88 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0x89 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0x8A 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0x8B 0x00E3 #LATIN SMALL LETTER A WITH TILDE +0x8C 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0x8D 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0x8E 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0x8F 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0x90 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0x91 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0x92 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0x93 0x00EC #LATIN SMALL LETTER I WITH GRAVE +0x94 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0x95 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0x96 0x00F1 #LATIN SMALL LETTER N WITH TILDE +0x97 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0x98 0x00F2 #LATIN SMALL LETTER O WITH GRAVE +0x99 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0x9A 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0x9B 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0x9C 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0x9D 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0x9E 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +0x9F 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xA0 0x2020 #DAGGER +0xA1 0x00B0 #DEGREE SIGN +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A7 #SECTION SIGN +0xA5 0x2022 #PUCE +0xA6 0x00B6 #PILCROW SIGN +0xA7 0x00DF #LATIN SMALL LETTER SHARP S (GERMAN) +0xA8 0x00AE #REGISTERED SIGN +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x2122 #TRADE MARK SIGN +0xAB 0x00B4 #ACUTE ACCENT +0xAC 0x00A8 #DIAERESIS +0xAD 0x2260 #NOT EQUAL TO +0xAE 0x00C6 #LATIN CAPITAL LETTER AE +0xAF 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xB0 0x221E #INFINITY +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x2264 #LESS-THAN OR EQUAL TO +0xB3 0x2265 #GREATER-THAN OR EQUAL TO +0xB4 0x00A5 #YEN SIGN +0xB5 0x00B5 #MICRO SIGN +0xB6 0x2202 #PARTIAL DIFFERENTIAL +0xB7 0x2211 #N-ARY SUMMATION +0xB8 0x220F #N-ARY PRODUCT +0xB9 0x03C0 #GREEK SMALL LETTER PI +0xBA 0x222B #INTEGRAL +0xBB 0x00AA #FEMININE ORDINAL INDICATOR +0xBC 0x00BA #MASCULINE ORDINAL INDICATOR +0xBD 0x03A9 #GREEK CAPITAL LETTER OMEGA +0xBE 0x00E6 #LATIN SMALL LETTER AE +0xBF 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xC0 0x00BF #INVERTED QUESTION MARK +0xC1 0x00A1 #INVERTED EXCLAMATION MARK +0xC2 0x00AC #NOT SIGN +0xC3 0x221A #SQUARE ROOT +0xC4 0x0192 #LETTRE MINUSCULE LATINE F CEDILLE +0xC5 0x2248 #ALMOST EQUAL TO +0xC6 0x0394 #GREEK CAPITAL LETTER DELTA +0xC7 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xC8 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xC9 0x2026 #MIDLINE HORIZONTAL ELLIPSIS +0xCA 0x00A0 #NO-BREAK SPACE +0xCB 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE +0xCC 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE +0xCD 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xCE 0x0152 #LATIN CAPITAL LIGATURE OE +0xCF 0x0153 #LATIN SMALL LIGATURE OE +0xD0 0x2013 #EN DASH +0xD1 0x2014 #EM DASH +0xD2 0x201C #LEFT DOUBLE QUOTATION MARK +0xD3 0x201D #RIGHT DOUBLE QUOTATION MARK +0xD4 0x2018 #LEFT SINGLE QUOTATION MARK +0xD5 0x2019 #RIGHT SINGLE QUOTATION MARK +0xD6 0x00F7 #DIVISION SIGN +0xD7 0x25CA #LOZENGE +0xD8 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS +0xD9 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS +0xDA 0x2044 #FRACTION SLASH +0xDB 0x20AC #SYMBOLE EURO +0xDC 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0xDD 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0xDE 0xFB01 #LATIN SMALL LIGATURE FI +0xDF 0xFB02 #LATIN SMALL LIGATURE FL +0xE0 0x2021 #DOUBLE DAGGER +0xE1 0x00B7 #MIDDLE DOT +0xE2 0x201A #SINGLE LOW-9 QUOTATION MARK +0xE3 0x201E #DOUBLE LOW-9 QUOTATION MARK +0xE4 0x2030 #PER MILLE SIGN +0xE5 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xE6 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xE7 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xE8 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xE9 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE +0xEA 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xEB 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xEC 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS +0xED 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE +0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xEF 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xF0 0xF8FF #Mac Logo (in Private Use Area) +0xF1 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE +0xF2 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xF3 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xF4 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE +0xF5 0x0131 #LATIN SMALL LETTER I DOTLESS +0xF6 0x02C6 #LETTRE MODIFICATIVE ACCENT CIRCONFLEXE +0xF7 0x02DC #PETIT TILDE +0xF8 0x00AF #MACRON +0xF9 0x02D8 #BREVE +0xFA 0x02D9 #DOT ABOVE +0xFB 0x02DA #RING ABOVE +0xFC 0x00B8 #CEDILLA +0xFD 0x02DD #DOUBLE ACUTE ACCENT +0xFE 0x02DB #OGONEK +0xFF 0x02C7 #CARON diff --git a/Unicode/tcvn5712.cp b/Unicode/tcvn5712.cp new file mode 100644 index 0000000..f6b0f03 --- /dev/null +++ b/Unicode/tcvn5712.cp @@ -0,0 +1,264 @@ +TCVN-5712 (Vietnamese) +"TCVN-5712", "TCVN", "TCVN-0", "TCVN-1" +0x00 0x0000 # NUL +0x00 0x0000 # NULL (NUL) +0x01 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0x02 0x1EE4 # LATIN CAPITAL LETTER U WITH DOT BELOW +0x03 0x0003 # END OF TEXT (ETX) +0x04 0x1EEA # LATIN CAPITAL LETTER U WITH HORN AND GRAVE +0x05 0x1EEC # LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE +0x06 0x1EEE # LATIN CAPITAL LETTER U WITH HORN AND TILDE +0x07 0x0007 # BELL (BEL) +0x08 0x0008 # BACKSPACE (BS) +0x09 0x0009 # CHARACTER TABULATION (HT) +0x0A 0x000A # LINE FEED (LF) +0x0B 0x000B # LINE TABULATION (VT) +0x0C 0x000C # FORM FEED (FF) +0x0D 0x000D # CARRIAGE RETURN (CR) +0x0E 0x000E # SHIFT OUT (SO) +0x0F 0x000F # SHIFT IN (SI) +0x10 0x0010 # DATALINK ESCAPE (DLE) +0x11 0x1EE8 # LATIN CAPITAL LETTER U WITH HORN AND ACUTE +0x12 0x1EF0 # LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW +0x13 0x1EF2 # LATIN CAPITAL LETTER Y WITH GRAVE +0x14 0x1EF6 # LATIN CAPITAL LETTER Y WITH HOOK ABOVE +0x15 0x1EF8 # LATIN CAPITAL LETTER Y WITH TILDE +0x16 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE +0x17 0x1EF4 # LATIN CAPITAL LETTER Y WITH DOT BELOW +0x18 0x0018 # CANCEL (CAN) +0x19 0x0019 # END OF MEDIUM (EM) +0x1A 0x001A # SUBSTITUTE (SUB) +0x1B 0x001B # ESCAPE (ESC) +0x1C 0x001C # FILE SEPARATOR (IS4) +0x1D 0x001D # GROUP SEPARATOR (IS3) +0x1E 0x001E # RECORD SEPARATOR (IS2) +0x1F 0x001F # UNIT SEPARATOR (IS1) +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE (DEL) +0x80 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0x81 0x1EA2 # LATIN CAPITAL LETTER A WITH HOOK ABOVE +0x82 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0x83 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0x84 0x1EA0 # LATIN CAPITAL LETTER A WITH DOT BELOW +0x85 0x1EB6 # LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW +0x86 0x1EAC # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW +0x87 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0x88 0x1EBA # LATIN CAPITAL LETTER E WITH HOOK ABOVE +0x89 0x1EBC # LATIN CAPITAL LETTER E WITH TILDE +0x8A 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0x8B 0x1EB8 # LATIN CAPITAL LETTER E WITH DOT BELOW +0x8C 0x1EC6 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW +0x8D 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0x8E 0x1EC8 # LATIN CAPITAL LETTER I WITH HOOK ABOVE +0x8F 0x0128 # LATIN CAPITAL LETTER I WITH TILDE +0x90 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0x91 0x1ECA # LATIN CAPITAL LETTER I WITH DOT BELOW +0x92 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0x93 0x1ECE # LATIN CAPITAL LETTER O WITH HOOK ABOVE +0x94 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0x95 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0x96 0x1ECC # LATIN CAPITAL LETTER O WITH DOT BELOW +0x97 0x1ED8 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW +0x98 0x1EDC # LATIN CAPITAL LETTER O WITH HORN AND GRAVE +0x99 0x1EDE # LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE +0x9A 0x1EE0 # LATIN CAPITAL LETTER O WITH HORN AND TILDE +0x9B 0x1EDA # LATIN CAPITAL LETTER O WITH HORN AND ACUTE +0x9C 0x1EE2 # LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW +0x9D 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0x9E 0x1EE6 # LATIN CAPITAL LETTER U WITH HOOK ABOVE +0x9F 0x0168 # LATIN CAPITAL LETTER U WITH TILDE +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0102 # LATIN CAPITAL LETTER A WITH BREVE +0xA2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xA3 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xA4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xA5 0x01A0 # LATIN CAPITAL LETTER O WITH HOOK +0xA6 0x01AF # LATIN CAPITAL LETTER U WITH HORN +0xA7 0x0110 # LATIN CAPITAL LETTER D WITH STROKE +0xA8 0x0103 # LATIN SMALL LETTER A WITH BREVE +0xA9 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xAA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xAB 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xAC 0x01A1 # LATIN SMALL LETTER O WITH HOOK +0xAD 0x01B0 # LATIN SMALL LETTER U WITH HORN +0xAE 0x0111 # LATIN SMALL LETTER D WITH STROKE +0xAF 0x1EB0 # LATIN CAPITAL LETTER A WITH BREVE AND GRAVE +0xB0 0x0300 # COMBINING GRAVE ACCENT +0xB1 0x0309 # COMBINING HOOK ABOVE +0xB2 0x0303 # COMBINING TILDE +0xB3 0x0301 # COMBINING ACUTE ACCENT +0xB4 0x0323 # COMBINING DOT BELOW +0xB5 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xB6 0x1EA3 # LATIN SMALL LETTER A WITH HOOK ABOVE +0xB7 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xB8 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xB9 0x1EA1 # LATIN SMALL LETTER A WITH DOT BELOW +0xBA 0x1EB2 # LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE +0xBB 0x1EB1 # LATIN SMALL LETTER A WITH BREVE AND GRAVE +0xBC 0x1EB3 # LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE +0xBD 0x1EB5 # LATIN SMALL LETTER A WITH BREVE AND TILDE +0xBE 0x1EAF # LATIN SMALL LETTER A WITH BREVE AND ACUTE +0xBF 0x1EB4 # LATIN CAPITAL LETTER A WITH BREVE AND TILDE +0xC0 0x1EAE # LATIN CAPITAL LETTER A WITH BREVE AND ACUTE +0xC1 0x1EA6 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE +0xC2 0x1EA8 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE +0xC3 0x1EAA # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE +0xC4 0x1EA4 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE +0xC5 0x1EC0 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE +0xC6 0x1EB7 # LATIN SMALL LETTER A WITH BREVE AND DOT BELOW +0xC7 0x1EA7 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE +0xC8 0x1EA9 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE +0xC9 0x1EAB # LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE +0xCA 0x1EA5 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE +0xCB 0x1EAD # LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW +0xCC 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xCD 0x1EC2 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE +0xCE 0x1EBB # LATIN SMALL LETTER E WITH HOOK ABOVE +0xCF 0x1EBD # LATIN SMALL LETTER E WITH TILDE +0xD0 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xD1 0x1EB9 # LATIN SMALL LETTER E WITH DOT BELOW +0xD2 0x1EC1 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE +0xD3 0x1EC3 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE +0xD4 0x1EC5 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE +0xD5 0x1EBF # LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE +0xD6 0x1EC7 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW +0xD7 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xD8 0x1EC9 # LATIN SMALL LETTER I WITH HOOK ABOVE +0xD9 0x1EC4 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE +0xDA 0x1EBE # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE +0xDB 0x1ED2 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE +0xDC 0x0129 # LATIN SMALL LETTER I WITH TILDE +0xDD 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xDE 0x1ECB # LATIN SMALL LETTER I WITH DOT BELOW +0xDF 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xE0 0x1ED4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +0xE1 0x1ECF # LATIN SMALL LETTER O WITH HOOK ABOVE +0xE2 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xE3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xE4 0x1ECD # LATIN SMALL LETTER O WITH DOT BELOW +0xE5 0x1ED3 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE +0xE6 0x1ED5 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +0xE7 0x1ED7 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE +0xE8 0x1ED1 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE +0xE9 0x1ED9 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW +0xEA 0x1EDD # LATIN SMALL LETTER O WITH HORN AND GRAVE +0xEB 0x1EDF # LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE +0xEC 0x1EE1 # LATIN SMALL LETTER O WITH HORN AND TILDE +0xED 0x1EDB # LATIN SMALL LETTER O WITH HORN AND ACUTE +0xEE 0x1EE3 # LATIN SMALL LETTER O WITH HORN AND DOT BELOW +0xEF 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xF0 0x1ED6 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE +0xF1 0x1EE7 # LATIN SMALL LETTER U WITH HOOK ABOVE +0xF2 0x0169 # LATIN SMALL LETTER U WITH TILDE +0xF3 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xF4 0x1EE5 # LATIN SMALL LETTER U WITH DOT BELOW +0xF5 0x1EEB # LATIN SMALL LETTER U WITH HORN AND GRAVE +0xF6 0x1EED # LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE +0xF7 0x1EEF # LATIN SMALL LETTER U WITH HORN AND TILDE +0xF8 0x1EE9 # LATIN SMALL LETTER U WITH HORN AND ACUTE +0xF9 0x1EF1 # LATIN SMALL LETTER U WITH HORN AND DOT BELOW +0xFA 0x1EF3 # LATIN SMALL LETTER Y WITH GRAVE +0xFB 0x1EF7 # LATIN SMALL LETTER Y WITH HOOK ABOVE +0xFC 0x1EF9 # LATIN SMALL LETTER Y WITH TILDE +0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x1EF5 # LATIN SMALL LETTER Y WITH DOT BELOW +0xFF 0x1ED0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE + +# compatibility +0xA7 0x00D0 # letter ETH +0xAE 0x00F0 + diff --git a/Unicode/tr7bit.awk b/Unicode/tr7bit.awk new file mode 100755 index 0000000..dc2256a --- /dev/null +++ b/Unicode/tr7bit.awk @@ -0,0 +1,35 @@ +#!/bin/awk -f +function hex2dec(xx) { + nn = 0; + while (xx != "") { + aa = substr(xx, 1, 1); + ii = index("0123456789ABCDEF", aa); + if (!ii) ii = index("0123456789abcdef", aa); + if (!ii) return -1; + nn = nn * 16 + ii - 1; + xx = substr(xx, 2); + } + return nn; +} + +/^U/{ + gsub("\\\\", "\\\\"); + printf("0x%s\n", substr($0, 3)); +} +/^0x[0-9a-fA-F]*[ ]/{ + c = hex2dec(substr($1, 3)); + for (i = 2; i <= NF; i++) { + if (substr($i, 1, 1) == "#") break; + if (p = index($i, "-")) { + p1 = hex2dec(substr($i, 3, p - 3)); + p2 = hex2dec(substr($i, p + 3)); + } else { + p1 = hex2dec(substr($i, 3)); + p2 = p1; + } + for (p = p1; p <= p2; p++) printf("0x%04x:%c\n", p, c); + } +} +BEGIN{ + printf("0x00a0:\\001\n0x00ad:\n"); +} diff --git a/Unicode/upcase.uni b/Unicode/upcase.uni new file mode 100644 index 0000000..22d2565 --- /dev/null +++ b/Unicode/upcase.uni @@ -0,0 +1,674 @@ + 97 65 + 98 66 + 99 67 + 100 68 + 101 69 + 102 70 + 103 71 + 104 72 + 105 73 + 106 74 + 107 75 + 108 76 + 109 77 + 110 78 + 111 79 + 112 80 + 113 81 + 114 82 + 115 83 + 116 84 + 117 85 + 118 86 + 119 87 + 120 88 + 121 89 + 122 90 + 181 924 + 224 192 + 225 193 + 226 194 + 227 195 + 228 196 + 229 197 + 230 198 + 231 199 + 232 200 + 233 201 + 234 202 + 235 203 + 236 204 + 237 205 + 238 206 + 239 207 + 240 208 + 241 209 + 242 210 + 243 211 + 244 212 + 245 213 + 246 214 + 248 216 + 249 217 + 250 218 + 251 219 + 252 220 + 253 221 + 254 222 + 255 376 + 257 256 + 259 258 + 261 260 + 263 262 + 265 264 + 267 266 + 269 268 + 271 270 + 273 272 + 275 274 + 277 276 + 279 278 + 281 280 + 283 282 + 285 284 + 287 286 + 289 288 + 291 290 + 293 292 + 295 294 + 297 296 + 299 298 + 301 300 + 303 302 + 305 73 + 307 306 + 309 308 + 311 310 + 314 313 + 316 315 + 318 317 + 320 319 + 322 321 + 324 323 + 326 325 + 328 327 + 331 330 + 333 332 + 335 334 + 337 336 + 339 338 + 341 340 + 343 342 + 345 344 + 347 346 + 349 348 + 351 350 + 353 352 + 355 354 + 357 356 + 359 358 + 361 360 + 363 362 + 365 364 + 367 366 + 369 368 + 371 370 + 373 372 + 375 374 + 378 377 + 380 379 + 382 381 + 383 83 + 387 386 + 389 388 + 392 391 + 396 395 + 402 401 + 405 502 + 409 408 + 414 544 + 417 416 + 419 418 + 421 420 + 424 423 + 429 428 + 432 431 + 436 435 + 438 437 + 441 440 + 445 444 + 447 503 + 454 452 + 457 455 + 460 458 + 462 461 + 464 463 + 466 465 + 468 467 + 470 469 + 472 471 + 474 473 + 476 475 + 477 398 + 479 478 + 481 480 + 483 482 + 485 484 + 487 486 + 489 488 + 491 490 + 493 492 + 495 494 + 499 497 + 501 500 + 505 504 + 507 506 + 509 508 + 511 510 + 513 512 + 515 514 + 517 516 + 519 518 + 521 520 + 523 522 + 525 524 + 527 526 + 529 528 + 531 530 + 533 532 + 535 534 + 537 536 + 539 538 + 541 540 + 543 542 + 547 546 + 549 548 + 551 550 + 553 552 + 555 554 + 557 556 + 559 558 + 561 560 + 563 562 + 595 385 + 596 390 + 598 393 + 599 394 + 601 399 + 603 400 + 608 403 + 611 404 + 616 407 + 617 406 + 623 412 + 626 413 + 629 415 + 640 422 + 643 425 + 648 430 + 650 433 + 651 434 + 658 439 + 940 902 + 941 904 + 942 905 + 943 906 + 945 913 + 946 914 + 947 915 + 948 916 + 949 917 + 950 918 + 951 919 + 952 920 + 953 921 + 954 922 + 955 923 + 956 924 + 957 925 + 958 926 + 959 927 + 960 928 + 961 929 + 962 931 + 963 931 + 964 932 + 965 933 + 966 934 + 967 935 + 968 936 + 969 937 + 970 938 + 971 939 + 972 908 + 973 910 + 974 911 + 976 914 + 977 920 + 981 934 + 982 928 + 985 984 + 987 986 + 989 988 + 991 990 + 993 992 + 995 994 + 997 996 + 999 998 + 1001 1000 + 1003 1002 + 1005 1004 + 1007 1006 + 1008 922 + 1009 929 + 1010 931 + 1013 917 + 1072 1040 + 1073 1041 + 1074 1042 + 1075 1043 + 1076 1044 + 1077 1045 + 1078 1046 + 1079 1047 + 1080 1048 + 1081 1049 + 1082 1050 + 1083 1051 + 1084 1052 + 1085 1053 + 1086 1054 + 1087 1055 + 1088 1056 + 1089 1057 + 1090 1058 + 1091 1059 + 1092 1060 + 1093 1061 + 1094 1062 + 1095 1063 + 1096 1064 + 1097 1065 + 1098 1066 + 1099 1067 + 1100 1068 + 1101 1069 + 1102 1070 + 1103 1071 + 1104 1024 + 1105 1025 + 1106 1026 + 1107 1027 + 1108 1028 + 1109 1029 + 1110 1030 + 1111 1031 + 1112 1032 + 1113 1033 + 1114 1034 + 1115 1035 + 1116 1036 + 1117 1037 + 1118 1038 + 1119 1039 + 1121 1120 + 1123 1122 + 1125 1124 + 1127 1126 + 1129 1128 + 1131 1130 + 1133 1132 + 1135 1134 + 1137 1136 + 1139 1138 + 1141 1140 + 1143 1142 + 1145 1144 + 1147 1146 + 1149 1148 + 1151 1150 + 1153 1152 + 1163 1162 + 1165 1164 + 1167 1166 + 1169 1168 + 1171 1170 + 1173 1172 + 1175 1174 + 1177 1176 + 1179 1178 + 1181 1180 + 1183 1182 + 1185 1184 + 1187 1186 + 1189 1188 + 1191 1190 + 1193 1192 + 1195 1194 + 1197 1196 + 1199 1198 + 1201 1200 + 1203 1202 + 1205 1204 + 1207 1206 + 1209 1208 + 1211 1210 + 1213 1212 + 1215 1214 + 1218 1217 + 1220 1219 + 1222 1221 + 1224 1223 + 1226 1225 + 1228 1227 + 1230 1229 + 1233 1232 + 1235 1234 + 1237 1236 + 1239 1238 + 1241 1240 + 1243 1242 + 1245 1244 + 1247 1246 + 1249 1248 + 1251 1250 + 1253 1252 + 1255 1254 + 1257 1256 + 1259 1258 + 1261 1260 + 1263 1262 + 1265 1264 + 1267 1266 + 1269 1268 + 1273 1272 + 1281 1280 + 1283 1282 + 1285 1284 + 1287 1286 + 1289 1288 + 1291 1290 + 1293 1292 + 1295 1294 + 1377 1329 + 1378 1330 + 1379 1331 + 1380 1332 + 1381 1333 + 1382 1334 + 1383 1335 + 1384 1336 + 1385 1337 + 1386 1338 + 1387 1339 + 1388 1340 + 1389 1341 + 1390 1342 + 1391 1343 + 1392 1344 + 1393 1345 + 1394 1346 + 1395 1347 + 1396 1348 + 1397 1349 + 1398 1350 + 1399 1351 + 1400 1352 + 1401 1353 + 1402 1354 + 1403 1355 + 1404 1356 + 1405 1357 + 1406 1358 + 1407 1359 + 1408 1360 + 1409 1361 + 1410 1362 + 1411 1363 + 1412 1364 + 1413 1365 + 1414 1366 + 7681 7680 + 7683 7682 + 7685 7684 + 7687 7686 + 7689 7688 + 7691 7690 + 7693 7692 + 7695 7694 + 7697 7696 + 7699 7698 + 7701 7700 + 7703 7702 + 7705 7704 + 7707 7706 + 7709 7708 + 7711 7710 + 7713 7712 + 7715 7714 + 7717 7716 + 7719 7718 + 7721 7720 + 7723 7722 + 7725 7724 + 7727 7726 + 7729 7728 + 7731 7730 + 7733 7732 + 7735 7734 + 7737 7736 + 7739 7738 + 7741 7740 + 7743 7742 + 7745 7744 + 7747 7746 + 7749 7748 + 7751 7750 + 7753 7752 + 7755 7754 + 7757 7756 + 7759 7758 + 7761 7760 + 7763 7762 + 7765 7764 + 7767 7766 + 7769 7768 + 7771 7770 + 7773 7772 + 7775 7774 + 7777 7776 + 7779 7778 + 7781 7780 + 7783 7782 + 7785 7784 + 7787 7786 + 7789 7788 + 7791 7790 + 7793 7792 + 7795 7794 + 7797 7796 + 7799 7798 + 7801 7800 + 7803 7802 + 7805 7804 + 7807 7806 + 7809 7808 + 7811 7810 + 7813 7812 + 7815 7814 + 7817 7816 + 7819 7818 + 7821 7820 + 7823 7822 + 7825 7824 + 7827 7826 + 7829 7828 + 7835 7776 + 7841 7840 + 7843 7842 + 7845 7844 + 7847 7846 + 7849 7848 + 7851 7850 + 7853 7852 + 7855 7854 + 7857 7856 + 7859 7858 + 7861 7860 + 7863 7862 + 7865 7864 + 7867 7866 + 7869 7868 + 7871 7870 + 7873 7872 + 7875 7874 + 7877 7876 + 7879 7878 + 7881 7880 + 7883 7882 + 7885 7884 + 7887 7886 + 7889 7888 + 7891 7890 + 7893 7892 + 7895 7894 + 7897 7896 + 7899 7898 + 7901 7900 + 7903 7902 + 7905 7904 + 7907 7906 + 7909 7908 + 7911 7910 + 7913 7912 + 7915 7914 + 7917 7916 + 7919 7918 + 7921 7920 + 7923 7922 + 7925 7924 + 7927 7926 + 7929 7928 + 7936 7944 + 7937 7945 + 7938 7946 + 7939 7947 + 7940 7948 + 7941 7949 + 7942 7950 + 7943 7951 + 7952 7960 + 7953 7961 + 7954 7962 + 7955 7963 + 7956 7964 + 7957 7965 + 7968 7976 + 7969 7977 + 7970 7978 + 7971 7979 + 7972 7980 + 7973 7981 + 7974 7982 + 7975 7983 + 7984 7992 + 7985 7993 + 7986 7994 + 7987 7995 + 7988 7996 + 7989 7997 + 7990 7998 + 7991 7999 + 8000 8008 + 8001 8009 + 8002 8010 + 8003 8011 + 8004 8012 + 8005 8013 + 8017 8025 + 8019 8027 + 8021 8029 + 8023 8031 + 8032 8040 + 8033 8041 + 8034 8042 + 8035 8043 + 8036 8044 + 8037 8045 + 8038 8046 + 8039 8047 + 8048 8122 + 8049 8123 + 8050 8136 + 8051 8137 + 8052 8138 + 8053 8139 + 8054 8154 + 8055 8155 + 8056 8184 + 8057 8185 + 8058 8170 + 8059 8171 + 8060 8186 + 8061 8187 + 8064 8072 + 8065 8073 + 8066 8074 + 8067 8075 + 8068 8076 + 8069 8077 + 8070 8078 + 8071 8079 + 8080 8088 + 8081 8089 + 8082 8090 + 8083 8091 + 8084 8092 + 8085 8093 + 8086 8094 + 8087 8095 + 8096 8104 + 8097 8105 + 8098 8106 + 8099 8107 + 8100 8108 + 8101 8109 + 8102 8110 + 8103 8111 + 8112 8120 + 8113 8121 + 8115 8124 + 8126 921 + 8131 8140 + 8144 8152 + 8145 8153 + 8160 8168 + 8161 8169 + 8165 8172 + 8179 8188 + 65345 65313 + 65346 65314 + 65347 65315 + 65348 65316 + 65349 65317 + 65350 65318 + 65351 65319 + 65352 65320 + 65353 65321 + 65354 65322 + 65355 65323 + 65356 65324 + 65357 65325 + 65358 65326 + 65359 65327 + 65360 65328 + 65361 65329 + 65362 65330 + 65363 65331 + 65364 65332 + 65365 65333 + 65366 65334 + 65367 65335 + 65368 65336 + 65369 65337 + 65370 65338 diff --git a/Unicode/utf_8.cp b/Unicode/utf_8.cp new file mode 100644 index 0000000..01c5536 --- /dev/null +++ b/Unicode/utf_8.cp @@ -0,0 +1,3 @@ +Unicode UTF-8 +"utf-8", "utf8" +# Handled specially in charsets.c diff --git a/Unicode/viscii.cp b/Unicode/viscii.cp new file mode 100644 index 0000000..2761629 --- /dev/null +++ b/Unicode/viscii.cp @@ -0,0 +1,264 @@ +VISCII +"VISCII", "VISCII-1", "VISCII 1.1", "VISCII-1.1", "VISCII1.1-1" +0x00 0x0000 # NUL +0x00 0x0000 # NULL (NUL) +0x01 0x0001 # START OF HEADING (SOH) +0x02 0x1EB2 # LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE +0x03 0x0003 # END OF TEXT (ETX) +0x04 0x0004 # END OF TRANSMISSION (EOT) +0x05 0x1EB4 # LATIN CAPITAL LETTER A WITH BREVE AND TILDE +0x06 0x1EAA # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE +0x07 0x0007 # BELL (BEL) +0x08 0x0008 # BACKSPACE (BS) +0x09 0x0009 # CHARACTER TABULATION (HT) +0x0A 0x000A # LINE FEED (LF) +0x0B 0x000B # LINE TABULATION (VT) +0x0C 0x000C # FORM FEED (FF) +0x0D 0x000D # CARRIAGE RETURN (CR) +0x0E 0x000E # SHIFT OUT (SO) +0x0F 0x000F # SHIFT IN (SI) +0x10 0x0010 # DATALINK ESCAPE (DLE) +0x11 0x0011 # DEVICE CONTROL ONE (DC1) +0x12 0x0012 # DEVICE CONTROL TWO (DC2) +0x13 0x0013 # DEVICE CONTROL THREE (DC3) +0x14 0x1EF6 # LATIN CAPITAL LETTER Y WITH HOOK ABOVE +0x15 0x0015 # NEGATIVE ACKNOWLEDGE (NAK) +0x16 0x0016 # SYNCHRONOUS IDLE (SYN) +0x17 0x0017 # END OF TRANSMISSION BLOCK (ETB) +0x18 0x0018 # CANCEL (CAN) +0x19 0x1EF8 # LATIN CAPITAL LETTER Y WITH TILDE +0x1A 0x001A # SUBSTITUTE (SUB) +0x1B 0x001B # ESCAPE (ESC) +0x1C 0x001C # FILE SEPARATOR (IS4) +0x1D 0x001D # GROUP SEPARATOR (IS3) +0x1E 0x1EF4 # LATIN CAPITAL LETTER Y WITH DOT BELOW +0x1F 0x001F # UNIT SEPARATOR (IS1) +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE (DEL) +0x80 0x1EA0 # LATIN CAPITAL LETTER A WITH DOT BELOW +0x81 0x1EAE # LATIN CAPITAL LETTER A WITH BREVE AND ACUTE +0x82 0x1EB0 # LATIN CAPITAL LETTER A WITH BREVE AND GRAVE +0x83 0x1EB6 # LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW +0x84 0x1EA4 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE +0x85 0x1EA6 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE +0x86 0x1EA8 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE +0x87 0x1EAC # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW +0x88 0x1EBC # LATIN CAPITAL LETTER E WITH TILDE +0x89 0x1EB8 # LATIN CAPITAL LETTER E WITH DOT BELOW +0x8A 0x1EBE # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE +0x8B 0x1EC0 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE +0x8C 0x1EC2 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE +0x8D 0x1EC4 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE +0x8E 0x1EC6 # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW +0x8F 0x1ED0 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE +0x90 0x1ED2 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE +0x91 0x1ED4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +0x92 0x1ED6 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE +0x93 0x1ED8 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW +0x94 0x1EE2 # LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW +0x95 0x1EDA # LATIN CAPITAL LETTER O WITH HORN AND ACUTE +0x96 0x1EDC # LATIN CAPITAL LETTER O WITH HORN AND GRAVE +0x97 0x1EDE # LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE +0x98 0x1ECA # LATIN CAPITAL LETTER I WITH DOT BELOW +0x99 0x1ECE # LATIN CAPITAL LETTER O WITH HOOK ABOVE +0x9A 0x1ECC # LATIN CAPITAL LETTER O WITH DOT BELOW +0x9B 0x1EC8 # LATIN CAPITAL LETTER I WITH HOOK ABOVE +0x9C 0x1EE6 # LATIN CAPITAL LETTER U WITH HOOK ABOVE +0x9D 0x0168 # LATIN CAPITAL LETTER U WITH TILDE +0x9E 0x1EE4 # LATIN CAPITAL LETTER U WITH DOT BELOW +0x9F 0x1EF2 # LATIN CAPITAL LETTER Y WITH GRAVE +0xA0 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xA1 0x1EAF # LATIN SMALL LETTER A WITH BREVE AND ACUTE +0xA2 0x1EB1 # LATIN SMALL LETTER A WITH BREVE AND GRAVE +0xA3 0x1EB7 # LATIN SMALL LETTER A WITH BREVE AND DOT BELOW +0xA4 0x1EA5 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE +0xA5 0x1EA7 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE +0xA6 0x1EA9 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE +0xA7 0x1EAD # LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW +0xA8 0x1EBD # LATIN SMALL LETTER E WITH TILDE +0xA9 0x1EB9 # LATIN SMALL LETTER E WITH DOT BELOW +0xAA 0x1EBF # LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE +0xAB 0x1EC1 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE +0xAC 0x1EC3 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE +0xAD 0x1EC5 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE +0xAE 0x1EC7 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW +0xAF 0x1ED1 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE +0xB0 0x1ED3 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE +0xB1 0x1ED5 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +0xB2 0x1ED7 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE +0xB3 0x1EE0 # LATIN CAPITAL LETTER O WITH HOOK AND TILDE +0xB4 0x01A0 # LATIN CAPITAL LETTER O WITH HOOK +0xB5 0x1ED9 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW +0xB6 0x1EDD # LATIN SMALL LETTER O WITH HORN AND GRAVE +0xB7 0x1EDF # LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE +0xB8 0x1ECB # LATIN SMALL LETTER I WITH DOT BELOW +0xB9 0x1EF0 # LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW +0xBA 0x1EE8 # LATIN CAPITAL LETTER U WITH HORN AND ACUTE +0xBB 0x1EEA # LATIN CAPITAL LETTER U WITH HORN AND GRAVE +0xBC 0x1EEC # LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE +0xBD 0x01A1 # LATIN SMALL LETTER O WITH HORN +0xBE 0x1EDB # LATIN SMALL LETTER O WITH HORN AND ACUTE +0xBF 0x01AF # LATIN CAPITAL LETTER U WITH HORN +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x1EA2 # LATIN CAPITAL LETTER A WITH HOOK ABOVE +0xC5 0x0102 # LATIN CAPITAL LETTER A WITH BREVE +0xC6 0x1EB3 # LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE +0xC7 0x1EB5 # LATIN SMALL LETTER A WITH BREVE AND TILDE +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x1EBA # LATIN CAPITAL LETTER E WITH HOOK ABOVE +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x0128 # LATIN CAPITAL LETTER I WITH TILDE +0xCF 0x1EF3 # LATIN SMALL LETTER Y WITH GRAVE +0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x1EE9 # LATIN SMALL LETTER U WITH HORN AND ACUTE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x1EA1 # LATIN SMALL LETTER A WITH DOT BELOW +0xD6 0x1EF7 # LATIN SMALL LETTER Y WITH HOOK ABOVE +0xD7 0x1EEB # LATIN SMALL LETTER U WITH HORN AND GRAVE +0xD8 0x1EED # LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x1EF9 # LATIN SMALL LETTER Y WITH TILDE +0xDC 0x1EF5 # LATIN SMALL LETTER Y WITH DOT BELOW +0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x1EE1 # LATIN SMALL LETTER O WITH HORN AND TILDE +0xDF 0x01B0 # LATIN SMALL LETTER U WITH HORN +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xE4 0x1EA3 # LATIN SMALL LETTER A WITH HOOK ABOVE +0xE5 0x0103 # LATIN SMALL LETTER A WITH BREVE +0xE6 0x1EEF # LATIN SMALL LETTER U WITH HORN AND TILDE +0xE7 0x1EAB # LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x1EBB # LATIN SMALL LETTER E WITH HOOK ABOVE +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x0129 # LATIN SMALL LETTER I WITH TILDE +0xEF 0x1EC9 # LATIN SMALL LETTER I WITH HOOK ABOVE +0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE +0xF1 0x1EF1 # LATIN SMALL LETTER U WITH HORN AND DOT BELOW +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xF6 0x1ECF # LATIN SMALL LETTER O WITH HOOK ABOVE +0xF7 0x1ECD # LATIN SMALL LETTER O WITH DOT BELOW +0xF8 0x1EE5 # LATIN SMALL LETTER U WITH DOT BELOW +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x0169 # LATIN SMALL LETTER U WITH TILDE +0xFC 0x1EE7 # LATIN SMALL LETTER U WITH HOOK ABOVE +0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x1EE3 # LATIN SMALL LETTER O WITH HORN AND DOT BELOW +0xFF 0x1EEE # LATIN CAPITAL LETTER U WITH HORN AND TILDE + +# compatibility +0xD0 0x00D0 # letter ETH +0xF0 0x00F0 + |