yudit-common 2.9.6-7 / usr / share / yudit / src / SAMPA.kmap

// SAMPA.kmap
// Gaspar Sinai <gsinai@yudit.org>
// Tokyo 2002-12-06 
// (Mikulás napja)
// Typed in by hand from:
// http://www.phon.ucl.ac.uk/home/sampa/home.htm
//
// Version 1.1: g,v added and ligatures broken down.
//
// SAMPA (Speech Assessment Methods Phonetic Alphabet) 
// is a machine-readable phonetic alphabet. It was originally 
// developed under the ESPRIT project 1541, SAM (Speech Assessment Methods)
// in 1987-89 by an international group of phoneticians, and was applied 
// in the first instance to the European Communities languages 
//  Danish, Dutch, English, French, German, and Italian (by 1989); 
// later to Norwegian and Swedish (by 1992); and subsequently to Greek, 
// Portuguese, and Spanish (1993). Under the BABEL project, 
// it has now been extended to Bulgarian, Estonian, Hungarian, Polish, 
// and Romanian (1996). 
//
//-------------------------------------------------------------------------
// SAMPA
// http://www.phon.ucl.ac.uk/home/sampa/home.htm
//-------------------------------------------------------------------------
// regex:
// :'a,'es/\(^.\)^I[01234567899]*[^0]*\(0[ABCDEF0123456789]*\)\, [01234567899]*^I\(.*\)/"\1 = 0x\2", \/\/\3
//
// Vowels
//
"A = 0x0251", // ɑ open back unrounded, Cardinal 5, Eng. start
"{ = 0x00E6", // æ - near-open front unrounded, Eng. trap
"0x36 = 0x0250", // ɐ open schwa, Ger. besser       
"Q = 0x0252", // ɒ open back rounded, Eng. lot   
"E = 0x025B", // ɛ open-mid front unrounded, C3, Fr. même    
"@ =0x0259", // ə schwa, Eng. banana 
"0x33 = 0x025C", // ɜ long mid central, Eng. nurse
"I = 0x026A", // ɪ lax close front unrounded, Eng. kit
"O = 0x0254", // ɔ open-mid back rounded, Eng. thought  
"0x32 = 0x00F8", // ø close-mid front rounded, Fr. deux   
"0x39 = 0x0153", // œ open-mid front rounded, Fr. neuf 
"& = 0x0276", // ɶ open front rounded
"U = 0x028A", // ʊ lax close back rounded, Eng. foot
"} = 0x0289", // ʉ close central rounded, Swedish sju
"V = 0x028C", // ʌ open-mid back unrounded, Eng. strut
"Y = 0x028F", // ʏ lax [y], Ger. hübsch
//
// Consonants
//
"B = 0x03B2", // β voiced bilabial fricative, Sp. cabo
"C = 0x00E7", // ç voiceless palatal fricative, Ger. ich
"D = 0x00F0", // ð voiced dental fricative, Eng. then
"G = 0x0263", // ɣ voiced velar fricative, Sp. fuego
"L = 0x028E", // ʎ palatal lateral, It. famiglia 
"J = 0x0272", // ɲ palatal nasal, Sp. año 
"N = 0x014B", // ŋ velar nasal, Eng. thing  
"R = 0x0281", // ʁ vd. uvular fric. or trill, Fr. roi
"S = 0x0283", // ʃ voiceless palatoalveolar fricative, Eng. ship
"T = 0x03B8", // θ voiceless dental fricative, Eng. thin
"H = 0x0265", // ɥ labial-palatal semivowel, Fr. huit
"Z = 0x0292", // ʒ vd. palatoalveolar fric., Eng. measure
"? = 0x0294", // ʔ glottal stop, Ger. Verein, also Danish stød
//
// Length, stress and tone marks
//
": = 0x02D0", // ː length mark    
"\" = 0x02C8", // ˈ primary stress 
"% = 0x02CC", // ˌ secondary stress             
// These SAMPA tone mark recommendations were based on the IPA
// as it was up to 1989-90. Since then, however, the IPA has
// changed its symbols for falling and rising tones. These SAMPA
// tone marks may now be considered obsolete, having in practice
// been superseded by the SAMPROSA proposals:
// http://www.phon.ucl.ac.uk/home/sampa/samprosa.htm
//
"` = 0x02E5 0x02E9", // ˥˩ falling tone                 
"' = 0x02E9 0x02E5", // ˩˥ rising tone                  
// I need to type Hungarian. This is from:
// http://www.phon.ucl.ac.uk/home/wells/ipa-unicode.htm
"aa = 0x0252", // ɒ Hungarian a
"d' = 0x025F", // ɟ Hungarian gy
"t' = 0x0063", // c Hungarian ty
// The latest IPA does not like ligature representation
// I just put a dot between words to show that
"t.S = 0x02A7", // ʧ Hungarian cs
"d.z = 0x02A3", // ʣ Hungarian dz
"d.Z = 0x02A4", // ʤ Hungarian dz
"t.s = 0x02A6", // ʦ Hungarian c
"dZ = 0x0064 0x0361 0x0292", // d͡ʒ Hungarian dzs
"tS = 0x0074 0x0361 0x0283", // t͡ʃ Hungarian cs
"dz = 0x0064 0x0361 0x007A", // d͡z Hungarian dz
"ts = 0x0074 0x0361 0x0073", // t͡s Hungarian c
"P = 0x028B", // ʋ 
"g = 0x0261", // ɡ 
// 
// Diacritics 
"0x3D n = 0x0329", // =n inferior stroke
"O ~ = 0x303", //  superior tilde
//-------------------------------------------------------------------------
// X-SAMPA
//-------------------------------------------------------------------------
// http://www.phon.ucl.ac.uk/home/sampa/x-sampa.htm
// 
// regex:
// :'a,'es/^\([^^I]*\)[^I ]*\([^^I ]*\)[^0]*\([0123456789ABCDEF]*\).*/"\2 = 0x\3",\/\/ \1/
//
"t` = 0x0288", // ʈ retroflex plosive, voiceless
"d` = 0x0256", // ɖ retroflex plosive, voiced
"F = 0x0271", // ɱ labiodental nasal
"n` = 0x0273", // ɳ retroflex nasal
"J = 0x0272", // ɲ palatal nasal
"N = 0x014B", // ŋ velar nasal
"N\\ = 0x0274", // ɴ uvular nasal
"B\\ = 0x0299", // ʙ bilabial trill
"R\\ = 0x0280", // ʀ uvular trill
"0x34 = 0x027E", // ɾ alveolar tap
"r` = 0x027D", // ɽ retroflex flap
"p\\ = 0x0278", // ɸ bilabial fricative, voiceless
"B = 0x03B2", // β bilabial fricative, voiced
"T = 0x03B8", // θ dental fricative, voiceless
"D = 0x00F0", // ð dental fricative, voiced
"S = 0x0283", // ʃ postalveolar fricative, voiceless
"Z = 0x0292", // ʒ postalveolar fricative, voiced
"s` = 0x0282", // ʂ retroflex fricative, voiceless
"z` = 0x0290", // ʐ retroflex fricative, voiced
"C = 0x00E7", // ç palatal fricative, voiceless
"j\\ = 0x029D", // ʝ palatal fricative, voiced
"G = 0x0263", // ɣ velar fricative, voiced
"X = 0x03C7", // χ uvular fricative, voiceless
"R = 0x0281", // ʁ uvular fricative, voiced
"X\\ = 0x0127", // ħ pharyngeal fricative, voiceless
"?\\ = 0x0295", // ʕ pharyngeal fricative, voiced
"h\\ = 0x0266", // ɦ glottal fricative, voiced
//