From 36d22d82aa202bb199967e9512281e9a53db42c9 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 7 Apr 2024 21:33:14 +0200 Subject: Adding upstream version 115.7.0esr. Signed-off-by: Daniel Baumann --- .../source/data/translit/Latin_NumericPinyin.txt | 36 ++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 intl/icu/source/data/translit/Latin_NumericPinyin.txt (limited to 'intl/icu/source/data/translit/Latin_NumericPinyin.txt') diff --git a/intl/icu/source/data/translit/Latin_NumericPinyin.txt b/intl/icu/source/data/translit/Latin_NumericPinyin.txt new file mode 100644 index 0000000000..9f832fcad4 --- /dev/null +++ b/intl/icu/source/data/translit/Latin_NumericPinyin.txt @@ -0,0 +1,36 @@ +# © 2016 and later: Unicode, Inc. and others. +# License & terms of use: http://www.unicode.org/copyright.html +# Generated using tools/cldr/cldr-to-icu/build-icu-data.xml +# +# 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); + -- cgit v1.2.3