Latin_NumericPinyin.txt (1484B)
1 # © 2016 and later: Unicode, Inc. and others. 2 # License & terms of use: http://www.unicode.org/copyright.html 3 # Generated using tools/cldr/cldr-to-icu/ 4 # 5 # File: Latin_NumericPinyin.txt 6 # Generated from CLDR 7 # 8 9 # According to the pinyin definitions I've been able to find: 10 # 'a', 'e' are the preferred bases 11 # otherwise 'o' 12 # otherwise last vowel 13 # The trailing form of syllables are the following: 14 # "a", "ai", "ao", "an", "ang", 15 # "o", "ou", "ong", 16 # "e", "ei", "er", "en", "eng", 17 # "i", "ia", "iao", "ie", "iu", "ian", "in", "iang", "ing", "iong", 18 # "u", "ua", "uo", "uai", "ui", "uan", "un", "uang", "ueng", 19 # "ü", "üe", "üan", "ün" 20 # so the letters the tone will 'hop' are: 21 ::NFD (NFC); 22 $tone = [\u0304\u0301\u030C\u0300\u0306] ; 23 # Move the tone to the end of a syllable, and convert to number 24 e {($tone) r} → r &Pinyin-NumericPinyin($1); 25 ($tone) ( [i o n u {o n} {n g}]) → $2 &Pinyin-NumericPinyin($1); 26 ($tone) → &Pinyin-NumericPinyin($1); 27 # The following backs up until it finds the right vowel, then deposits the tone 28 $vowel = [aAeEiIoOuU {u\u0308} {U\u0308} vV]; 29 $consonant = [[a-z A-Z] - [$vowel]]; 30 $digit = [1-5]; 31 $1 &NumericPinyin-Pinyin($3) $2 ← ([aAeE]) ($vowel* $consonant*) ($digit); 32 $1 &NumericPinyin-Pinyin($3) $2 ← ([oO]) ([$vowel-[aeAE]]* $consonant*) ($digit); 33 $1 &NumericPinyin-Pinyin($3) $2 ← ($vowel) ($consonant*) ($digit); 34 &NumericPinyin-Pinyin($1) ← [:Letter:] {($digit)}; 35 ::NFC (NFD);