# © 2016 and later: Unicode, Inc. and others. # License & terms of use: http://www.unicode.org/copyright.html#License # # File: Latin_NumericPinyin.txt # Generated from CLDR # # According to the pinyin definitions I've been able to find: # 'a', 'e' are the preferred bases # otherwise 'o' # otherwise last vowel # The trailing form of syllables are the following: # "a", "ai", "ao", "an", "ang", # "o", "ou", "ong", # "e", "ei", "er", "en", "eng", # "i", "ia", "iao", "ie", "iu", "ian", "in", "iang", "ing", "iong", # "u", "ua", "uo", "uai", "ui", "uan", "un", "uang", "ueng", # "ü", "üe", "üan", "ün" # so the letters the tone will 'hop' are: ::NFD (NFC); $tone = [\u0304\u0301\u030C\u0300\u0306] ; # Move the tone to the end of a syllable, and convert to number e {($tone) r} → r &Pinyin-NumericPinyin($1); ($tone) ( [i o n u {o n} {n g}]) → $2 &Pinyin-NumericPinyin($1); ($tone) → &Pinyin-NumericPinyin($1); # The following backs up until it finds the right vowel, then deposits the tone $vowel = [aAeEiIoOuU {u\u0308} {U\u0308} vV]; $consonant = [[a-z A-Z] - [$vowel]]; $digit = [1-5]; $1 &NumericPinyin-Pinyin($3) $2 ← ([aAeE]) ($vowel* $consonant*) ($digit); $1 &NumericPinyin-Pinyin($3) $2 ← ([oO]) ([$vowel-[aeAE]]* $consonant*) ($digit); $1 &NumericPinyin-Pinyin($3) $2 ← ($vowel) ($consonant*) ($digit); &NumericPinyin-Pinyin($1) ← [:letter:] {($digit)}; ::NFC (NFD);