# Family names from cultures where the family name comes FIRST
# (before the given name): Chinese, Korean, Vietnamese, Japanese, Hungarian.
#
# Used by suggest_short_names() to detect that in "Kim Minsoo", "Kim" is
# the family name and "Minsoo" is the given name, so the short name
# should be "Minsoo" not "Kim".
#
# Format: one entry per line, lowercase.  Blank lines and lines starting
# with # are ignored.  Callers must .lower() the input token before
# checking membership.
#
# Maintenance
# -----------
# Add new entries as needed.  Keep sorted within each section.  Include
# common romanisation variants for the same underlying surname.
# Some entries overlap with Western given names (e.g. "lee", "kim") —
# that is intentional; false-positive handling is the caller's job.
#
# Total: ~337 unique entries across all cultures.


# =========================================================================
# Chinese — top ~100 surnames by frequency
# =========================================================================
#
# Primary source: 2019 Ministry of Public Security report on surname
# distribution (covers 1.2 billion people).
# https://en.wikipedia.org/wiki/Chinese_surname#Distribution
#
# Mandarin pinyin is the primary romanisation.  Variants include:
# - Cantonese (HK government romanisation)
# - Wade-Giles (common in Taiwan)
# - Hokkien / Teochew (common in Singapore, Malaysia, Philippines)
#
# Variant sources:
# - Wikipedia articles on individual Chinese surnames
# - "Chinese Singaporean names" https://en.wikipedia.org/wiki/Chinese_Singaporean#Names
# - Hong Kong name romanisation practices

# 1 王 Wáng — Cantonese: Wong; Hokkien: Ong, Heng
ong
wang
wong

# 2 李 Lǐ — common variant: Lee
lee
li

# 3 张/張 Zhāng — Wade-Giles: Chang; Cantonese: Cheung; Hokkien: Teo
chang
cheung
teo
zhang

# 4 刘/劉 Liú — Cantonese: Lau; Hokkien: Lew, Liew
lau
lew
liew
liu

# 5 陈/陳 Chén — Cantonese: Chan; Hokkien: Tan; Wade-Giles: Chin
chan
chen
chin
tan

# 6 杨/楊 Yáng — Cantonese: Yeung; Hokkien: Yeo
yang
yeo
yeung

# 7 黄/黃 Huáng — Cantonese: Wong (same as 王); Hokkien: Ooi, Wee, Ng
huang
hwang
ng
ooi
wee

# 8 赵/趙 Zhào — Cantonese: Chiu; Wade-Giles: Chao
chao
chiu
zhao

# 9 吴/吳 Wú — Hokkien: Goh, Go; Cantonese: Ng (same as 黄)
go
goh
wu

# 10 周 Zhōu — Cantonese: Chow; Wade-Giles: Chou; Hokkien: Chew
chew
chou
chow
zhou

# 11 徐 Xú — Wade-Giles: Hsu; Cantonese: Tsui, Chui
chui
hsu
tsui
xu

# 12 孙/孫 Sūn — Cantonese: Suen
suen
sun

# 13 马/馬 Mǎ — Cantonese: Mah
ma
mah

# 14 朱 Zhū — Cantonese: Chu
chu
zhu

# 15 胡 Hú — Cantonese: Woo; Hokkien: Aw
aw
hu
woo

# 16 郭 Guō — Cantonese: Kwok; Wade-Giles: Kuo; Hokkien: Quek, Kuok
guo
kuok
kuo
kwok
quek

# 17 何 Hé — Cantonese: Ho
he
ho

# 18 高 Gāo — Cantonese: Ko; Wade-Giles: Kao
gao
kao
ko

# 19 林 Lín — Cantonese: Lam; Hokkien: Lim
lam
lim
lin

# 20 罗/羅 Luó — Cantonese: Lo; variant: Law
law
lo
luo

# 21 郑/鄭 Zhèng — Cantonese: Cheng; Hokkien: Tay, Teh
cheng
tay
teh
zheng

# 22 梁 Liáng — Cantonese: Leung, Leong; Hokkien: Neo
leong
leung
liang
neo

# 23 谢/謝 Xiè — Cantonese: Tse; Wade-Giles: Hsieh; Hokkien: Chia, Cheah, Sia
cheah
chia
hsieh
sia
tse
xie

# 24 宋 Sòng — variant: Sung
song
sung

# 25 唐 Táng — Cantonese: Tong
tang
tong

# 26 韩/韓 Hán
han

# 27 冯/馮 Féng — Cantonese: Fung; Hokkien: Png
feng
fung
png

# 28 于/於 Yú
yu

# 29 董 Dǒng — Cantonese: Tung
dong
tung

# 30 魏 Wèi — Cantonese: Ngai
ngai
wei

# 31 萧/蕭/肖 Xiāo — Wade-Giles: Hsiao; Cantonese: Siu; Hokkien: Siew, Seow
hsiao
seow
siew
siu
xiao

# 32 曹 Cáo — Wade-Giles: Tso
cao
tso

# 33 袁 Yuán — Cantonese: Yuen
yuan
yuen

# 34 邓/鄧 Dèng
deng

# 35 彭 Péng — Cantonese: Pang; Hokkien: Phang
pang
peng
phang

# 36 曾 Zēng — Cantonese: Tsang; Wade-Giles: Tseng
tsang
tseng
zeng

# 37 潘 Pān — Cantonese: Poon; Hokkien: Phua
pan
phua
poon

# 38 蔡 Cài — Wade-Giles: Tsai; Cantonese: Choi, Choy; Hokkien: Chua
cai
choi
choy
chua
tsai

# 39 田 Tián — Cantonese: Tin
tian
tin

# 40 苏/蘇 Sū — Cantonese: So; variant: Soo
so
soo
su

# 41 吕/呂 Lǚ — romanised as Lv, Lu; Cantonese: Lui
lu
lui
lv

# 42 蒋/蔣 Jiǎng — Wade-Giles: Chiang; Cantonese: Cheong
cheong
chiang
jiang

# 43 杜 Dù — Hokkien: Toh
du
toh

# 44 丁 Dīng — Hokkien: Teng
ding
teng

# 45 沈 Shěn — Cantonese: Shum; Hokkien: Sim
shen
shum
sim

# 46 任 Rèn — Cantonese: Yam
ren
yam

# 47 姚 Yáo — Cantonese: Yiu
yao
yiu

# 48 范/範 Fàn
fan

# 49 廖 Liào
liao

# 50 石 Shí — Cantonese: Shek; Hokkien: Seah
seah
shek
shi

# 51 金 Jīn — Cantonese: Kam
jin
kam

# 52 贾/賈 Jiǎ
jia

# 53 夏 Xià — Korean/Cantonese: Ha
ha
xia

# 54 付/傅 Fù — variant: Foo
foo
fu

# 55 方 Fāng — Cantonese: Fong
fang
fong

# 56 邹/鄒 Zōu
zou

# 57 熊 Xióng — Cantonese: Hung
hung
xiong

# 58 白 Bái — Cantonese: Pak; Hokkien: Peh
bai
pak
peh

# 59 孟 Mèng
meng

# 60 秦 Qín
qin

# 61 邱/丘 Qiū — Cantonese: Yau; Hokkien: Khoo, Hew
hew
khoo
qiu
yau

# 62 侯 Hóu — Cantonese: Hau
hau
hou

# 63 尹 Yǐn
yin

# 64 薛 Xuē
xue

# 65 闫/閻 Yán — Cantonese: Yim
yan
yim

# 66 段 Duàn
duan

# 67 雷 Léi
lei

# 68 龙/龍 Lóng — Cantonese: Lung
long
lung

# 69 黎 Lí — Cantonese: Lai
lai

# 70 陶 Táo
tao

# 71 毛 Máo
mao

# 72 莫 Mò — Cantonese: Mok
mo
mok

# 73 郝 Hǎo
hao

# 74 顾/顧 Gù — Cantonese: Ku
gu
ku

# 75 龚/龔 Gōng — Cantonese: Kung
gong
kung

# 76 邵 Shào
shao

# 77 万/萬 Wàn
wan

# 78 戴 Dài — variant: Tai
dai
tai

# 79 孔 Kǒng
kong

# 80 向 Xiàng — Cantonese: Heung
heung
xiang

# 81 欧/歐 Ōu — Cantonese: Au
au
ou

# 82 汤/湯 Tāng (same romanisation as 唐, already listed)

# 83 文 Wén — Cantonese: Man
man
wen

# 84 钟/鍾 Zhōng — Cantonese: Chung
chung
zhong

# 85 康 Kāng
kang

# 86 赖/賴 Lài (Cantonese: Lai — already listed under 黎)

# 87 叶/葉 Yè — Cantonese: Yip, Ip; Wade-Giles: Yeh
ip
ye
yeh
yip

# 88 关/關 Guān — Cantonese: Kwan
kwan

# 89 谭/譚 Tán — Cantonese: Tam
tam

# 90 麦/麥 Mài — Cantonese: Mak
mai
mak

# 91 骆/駱 Luò — Cantonese: Lok
lok

# 92 邝/鄺 Kuàng — Cantonese: Kwong
kwong


# =========================================================================
# Korean — top ~30 surnames by frequency
# =========================================================================
#
# Primary source: 2015 South Korean census (Statistics Korea).
# https://en.wikipedia.org/wiki/List_of_Korean_surnames
#
# Romanisation follows Revised Romanisation (primary) with
# McCune-Reischauer and ad-hoc variants common in English-language use.

# 1 김 Kim
gim
kim

# 2 이 Lee/Yi/Rhee/Ri (Lee is by far the most common English spelling)
# "lee" already in Chinese section — shared entry
rhee
ri
yi

# 3 박 Park/Pak/Bak
bak
park

# 4 최 Choi/Choe (Choi already in Chinese 蔡 section — shared entry)
choe

# 5 정 Jung/Jeong/Chung (Chung already in Chinese 钟 section)
jeong
jung

# 6 강 Kang/Gang (Kang already in Chinese 康 section)
gang

# 7 조 Cho/Jo
cho
jo

# 8 윤 Yoon/Yun
yoon
yun

# 9 장 Jang (Chang already in Chinese 张 section)
jang

# 10 임 Im/Lim (Lim already in Chinese 林 section)
im

# 11 한 Han (already in Chinese 韩 section)

# 12 오 Oh
oh

# 13 서 Seo/Suh
seo
suh

# 14 신 Shin
shin

# 15 권 Kwon/Gwon
gwon
kwon

# 16 황 Hwang (already in Chinese 黄 section)

# 17 안 Ahn/An
ahn
an

# 18 송 Song (already in Chinese 宋 section)

# 19 유 Ryu/Yoo/You
ryu
yoo
you

# 20 홍 Hong
hong

# 21 전 Jeon
jeon

# 22 고 Ko (already in Chinese 高 section)

# 23 문 Moon/Mun
moon
mun

# 24 양 Yang (already in Chinese 杨 section)

# 25 손 Son
son

# 26 배 Bae
bae

# 27 백 Baek/Paek
baek
paek

# 28 허 Heo/Huh/Hur
heo
huh
hur

# 29 남 Nam
nam

# 30 심 Shim (Sim already in Chinese 沈 section)
shim

# 31 노 Noh/Roh
noh
roh

# 32 하 Ha (already in Chinese 夏 section)

# 33 곽 Kwak/Gwak
gwak
kwak


# =========================================================================
# Vietnamese — top ~20 surnames by frequency
# =========================================================================
#
# Primary source: Vietnamese census data and Wikipedia.
# https://en.wikipedia.org/wiki/Vietnamese_name#Family_name
#
# Nguyễn alone accounts for ~38% of the Vietnamese population.
# Romanisation is standard Vietnamese without diacritics (as commonly
# used in English-language contexts).

# 1 Nguyễn (~38%)
nguyen

# 2 Trần (~11%)
tran

# 3 Lê (~9.5%)
le

# 4 Phạm (~7%)
pham

# 5 Hoàng/Huỳnh (~5%) — Hoang (northern), Huynh (southern)
hoang
huynh

# 6 Phan
phan

# 7 Vũ/Võ — Vu (northern), Vo (southern)
vo
vu

# 8 Đặng
dang

# 9 Bùi
bui

# 10 Đỗ
do

# 11 Hồ (Ho already in Chinese 何 section)

# 12 Ngô
ngo

# 13 Dương
duong

# 14 Lý
ly

# 15 Đinh
dinh

# 16 Đào
dao

# 17 Trịnh
trinh

# 18 Đoàn
doan

# 19 Lâm (Lam already in Chinese 林 section)

# 20 Lương
luong


# =========================================================================
# Japanese — top ~30 surnames by frequency
# =========================================================================
#
# Primary source: Meiji Yasuda Life Insurance surname survey and
# Wikipedia "Japanese surname".
# https://en.wikipedia.org/wiki/Japanese_surname
#
# Romanisation is modified Hepburn (standard).  Long-vowel variants
# (-oh, -ou) included where common in passports and English-language use.

# 1 佐藤 Satō
sato
satoh
satou

# 2 鈴木 Suzuki
suzuki

# 3 高橋 Takahashi
takahashi

# 4 田中 Tanaka
tanaka

# 5 渡辺 Watanabe
watanabe

# 6 伊藤 Itō
ito
itoh
itou

# 7 山本 Yamamoto
yamamoto

# 8 中村 Nakamura
nakamura

# 9 小林 Kobayashi
kobayashi

# 10 加藤 Katō
kato
katoh
katou

# 11 吉田 Yoshida
yoshida

# 12 山田 Yamada
yamada

# 13 佐々木 Sasaki
sasaki

# 14 山口 Yamaguchi
yamaguchi

# 15 松本 Matsumoto
matsumoto

# 16 斎藤 Saitō
saito
saitoh
saitou

# 17 井上 Inoue
inoue

# 18 木村 Kimura
kimura

# 19 林 Hayashi (Lin already in Chinese section — different kanji)
hayashi

# 20 清水 Shimizu
shimizu

# 21 山崎 Yamazaki
yamazaki

# 22 池田 Ikeda
ikeda

# 23 阿部 Abe
abe

# 24 橋本 Hashimoto
hashimoto

# 25 山下 Yamashita
yamashita

# 26 森 Mori
mori

# 27 石川 Ishikawa
ishikawa

# 28 中島 Nakajima/Nakashima
nakajima
nakashima

# 29 前田 Maeda
maeda

# 30 藤田 Fujita
fujita


# =========================================================================
# Hungarian — top ~20 surnames by frequency
# =========================================================================
#
# Primary source: Hungarian Central Statistical Office (KSH) and
# Wikipedia "List of most common surnames in Europe".
# https://en.wikipedia.org/wiki/List_of_most_common_surnames_in_Europe#Hungary
#
# Both accented (proper Hungarian) and unaccented (common in
# English-language text) forms are included.

# 1 Nagy
nagy

# 2 Kovács
kovacs
kovács

# 3 Tóth
toth
tóth

# 4 Szabó
szabo
szabó

# 5 Horváth
horvath
horváth

# 6 Varga
varga

# 7 Kiss
kiss

# 8 Molnár
molnar
molnár

# 9 Németh
nemeth
németh

# 10 Farkas
farkas

# 11 Balogh
balogh

# 12 Juhász
juhasz
juhász

# 13 Lakatos
lakatos

# 14 Oláh
olah
oláh

# 15 Mészáros
meszaros
mészáros

# 16 Fekete
fekete

# 17 Szilágyi
szilagyi
szilágyi

# 18 Török
torok
török

# 19 Papp
papp

# 20 Takács
takacs
takács
