# original source for character list: http://www.gov.cn/gzdt/att/att/site1/20130819/tygfhzb.pdf (通用规范汉字表)
# text version taken from http://xh.5156edu.com/page/z6211m4474j19255.html with manual fixed between chars 3649-3668, this was made into table.txt

# original source for pronunciation data: ftp://ftp.cuhk.hk/pub/chinese/ifcss/software/data/Uni2Pinyin.gz
# converted with: for lines in {1..6500..100}; do echo $lines-$((lines+99))/6500 1>&2; for code in $(unicode --max 100 --brief "$(sed -n "$lines,$((lines+99))p" < table.txt | tr -d '\n')" | g 2 | cut -d+ -f2); do pinyin="$(grep ^$code Uni2Pinyin)"; if [ $? -ne 0 ]; then echo $'\t?'; else echo "$pinyin"; fi ;done | cut -d$'\t' -f2-; done > pinyin-table.txt

# manual fixes for pronunciation data:

# tone change rules, 变调
一,+yi4,+yi2
不,+bu2,+bu5
# common tone change in for ex. 想一想，试一试
一,+yi5
# common pronunciation was missing
么,+me5
几,+ji3
识,+shi2,shi4
传,+chuan2
陆,+lu4
鲜,+xian3
强,+jiang4
迹,+ji4
绩,+ji4
还,+huan2
脏,+zang1
盖,+gai4
仔,+zai3
构,+gou4
# uncommon characters, source pronunciations from https://zidian.911cha.com/ -- cross referenced with zh.wiktionary.org
㧐,?=>song3
䏝,?=>chun2,zhuan3
㤘,?=>chu4,cu4,zhou4
𠳐,?=>bang1
䓖,?=>qiong2
𥻗,?=>cha2
㸆,?=>kao4
# uncommon character, previous source doesn't have it, source https://baike.baidu.com/
䦃,?=>zhuo1
# style of writing pinyin changed
嗯,eng4:eng2:eng3 (was ng, made eng)
# fixed mistaken pronunciation
触,hong2=>chu4