return {
vNums = { -- Numbers prefixed by 'an'
'1[18]',
'1[18]..', -- Assumes it's a year
'1[18]...',
'1[18]......',
'1[18].........',
'1[18]............',
'8.*',
},
cvWords = { -- Words beginning with a consonant letter but prefixed by 'an'
'f',
'h',
'haute.*',
'heir.*',
'hombres?',
'honest.*',
'honou?r.*',
'hour.*',
'l',
'm',
'mb[aeiou].+',
'n',
'nd[aeiou].+',
'ng[aeiou].+',
'nth',
'r',
's',
'x',
'xbox',
'y[^aehioru].*',
},
cvWordsUS = { -- Words prefixed by 'an' only in American English
-- 'Herbivore', 'herbivorous', etc. vary but pronunciations with /h/
-- seem to be more--or at least equally--common.
'herbs?',
'herbal.*',
},
cvAcronyms = { -- Acronyms beginning with F/H/L/M/N/R/S/X but prefixed by 'a'
'FAT',
'FEMA',
'FIBA',
'FIDE',
'FIFA',
'FTSE',
'FORTRAN',
'FYROM',
'HANS',
'HEPA',
'LAN',
'LASIK',
'LISP',
'MAC',
'MERS',
'MIDI',
'MIME',
'MOOC',
'NAFTA',
'NASA',
'NASCAR',
'NASDAQ',
'NATO',
'NIMBY',
'NOW',
'RAID',
'RAM',
'RISC',
'ROM',
'SAGE',
'SARS',
'SCOTUS',
'SIM',
'STEM',
'SWAT',
},
vvAcronyms = { -- Acronyms not beginning with F/H/L/M/N/R/S/X but prefixed by 'an'
'UNRWA',
'USDAW',
},
vcWords = { -- Words beginning with A/E/I/O/U but prefixed by 'a'
'e[uw].*',
'oaxaca.*',
'onc?er?s?',
'oneness',
'oneself',
'oua.*',
'oui.*',
'u',
'uakaris?',
'ubi.+',
'udall',
'udo[mn].+',
'ufolog.*',
'uganda',
'ugandans?',
'u[iy]gh?urs?',
'uint.*',
'ukases?',
'ukes?',
'uk[eu]leles?',
'ukrain.*',
'ulo[bt].*',
'ulysses',
'unabombers?',
'unanimity',
'unanimous.*',
'unary',
'uni.*',
'upas',
'upases',
'ur[aeio].*',
'uruguay.*',
'us[aeiou].*',
'ustinov',
'ut[aeiou].*',
'utd',
'uther',
'utrecht',
'utri.*',
'uv[aeiou].*',
},
vvWords = { -- Exceptions to the above
'euler',
'eupen',
'euxton',
'uniced',
'unideaed',
'unideal.*',
'unidentif.*',
'unideologic.*',
'unidiomatic.*',
'unignorab.*',
'unill.*',
'uni[mn][^aeiou].*',
'unimagin.*',
'unimitabl.*',
'uninaugurated',
'uninitiat.*',
'uninoculat.*',
'uniron.*',
'unirr.*',
'unissu.*',
},
}
