|
|
<?xml version="1.0" encoding="UTF-8" ?>
|
|
|
<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
|
|
|
<!--
|
|
|
Copyright © 1991-2013 Unicode, Inc.
|
|
|
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
|
|
|
For terms of use, see http://www.unicode.org/copyright.html
|
|
|
-->
|
|
|
<supplementalData>
|
|
|
<version number="$Revision$"/>
|
|
|
<transforms>
|
|
|
<transform source="es_FONIPA" target="zh" direction="forward" alias="zh-t-es-fonipa">
|
|
|
<tRule><![CDATA[
|
|
|
# Tranforms Spanish to Mandarin Chinese. The input Spanish string must be in
|
|
|
# phonemic IPA transcription (es_FONIPA); the output is in Simplified Chinese.
|
|
|
|
|
|
$word_boundary = [-\ $];
|
|
|
$vowel = [aeijouw]; # Vowels and glides
|
|
|
$not_vowel = [^$vowel];
|
|
|
|
|
|
# First pass: Collapse phonetic distinctions not preserved in Mandarin.
|
|
|
|
|
|
ð → | d;
|
|
|
ɣ → | g;
|
|
|
ŋ → | n;
|
|
|
θ → | s;
|
|
|
ɾ → | r;
|
|
|
|
|
|
ff → f ;
|
|
|
kk → k ;
|
|
|
mm → m ;
|
|
|
nn → n ;
|
|
|
pp → p ;
|
|
|
tt → t ;
|
|
|
tʧ → ʧ ;
|
|
|
|
|
|
aa → a ;
|
|
|
oi̯ → oi ;
|
|
|
oo → o ;
|
|
|
uu → u ;
|
|
|
|
|
|
[^dgktx] { ei̯ → e ;
|
|
|
[^-\ .$] { eu̯ → eu ;
|
|
|
[^-\ .$] { ou̯ → o;
|
|
|
[^j] { ui → wi ;
|
|
|
|
|
|
[^$word_boundary] { m } [bp] → n; # GB/T 17693.5-2009, 5.3.2
|
|
|
s[θs] → s; # GB/T 17693.5-2009, 5.3.4
|
|
|
[^ʧ] { jo → io; # GB/T 17693.5-2009 表 1, 注 7
|
|
|
|
|
|
::Null;
|
|
|
|
|
|
j } an $not_vowel → i ; # GB/T 17693.5-2009 表 1, 注 8
|
|
|
|
|
|
|
|
|
# GB/T 17693.5-2009 表 1, 注 8 also says that <uai> should be treated as if
|
|
|
# it was <u> plus <ai>. This is not borne out by the observed data, which
|
|
|
# suggests that <ua> plus <i> is the more appropriate choice in some
|
|
|
# situations.
|
|
|
|
|
|
[g.$] { wai̯ → wai ;
|
|
|
wai̯ → uai̯ ;
|
|
|
[g.$] { wau̯ → wau ;
|
|
|
wau̯ → uau̯ ;
|
|
|
jau̯ → iau̯ ;
|
|
|
|
|
|
# Even though "ao" is not a diphthong in Spanish, Mandarin treats it as one.
|
|
|
|
|
|
[^jw] { ao } [^n] → au̯ ;
|
|
|
[^jw] { ao } n $vowel → au̯ ;
|
|
|
|
|
|
# Main pass: Phoneme to Hanzi conversion.
|
|
|
# This generally follows GB/T 17693.5-2009 表 1, unless otherwise noted.
|
|
|
::Null;
|
|
|
|
|
|
'.' → ;
|
|
|
ai̯ → 艾 ;
|
|
|
an } $not_vowel → 安 ;
|
|
|
au̯ → 奥 ;
|
|
|
a → 阿 ;
|
|
|
bai̯ → 拜 ;
|
|
|
ban } $not_vowel → 班 ;
|
|
|
bau̯ → 包 ;
|
|
|
ba → 巴 ;
|
|
|
ben } $not_vowel → 本 ;
|
|
|
be → 贝 ;
|
|
|
bin } $not_vowel → 宾 ;
|
|
|
bi → 比 ;
|
|
|
bja → 比亚 ;
|
|
|
bjen } $not_vowel → 比恩 ;
|
|
|
bje → 别 ;
|
|
|
bju → 比乌 ;
|
|
|
bon } $not_vowel → 邦 ;
|
|
|
bo → 博 ;
|
|
|
bun } $not_vowel → 本 ;
|
|
|
bu → 布 ;
|
|
|
bwan } $not_vowel → 布安 ;
|
|
|
bwa → 布阿 ;
|
|
|
bwen } $not_vowel → 布恩 ; # Should be be 本, per GB/T 17693.5-2009 表 1.
|
|
|
bwe → 布埃 ;
|
|
|
bwin } $not_vowel → 布因 ; # Nonstandard, but fits observed data.
|
|
|
bwi → 布伊 ;
|
|
|
bwo → 博 ;
|
|
|
b → 布 ;
|
|
|
βai̯ → 瓦伊 ;
|
|
|
βan } $not_vowel → 万 ;
|
|
|
βau̯ → 沃 ;
|
|
|
βa → 瓦 ;
|
|
|
βen } $not_vowel → 文 ;
|
|
|
βe → 韦 ;
|
|
|
βin } $not_vowel → 温 ;
|
|
|
βi → 维 ;
|
|
|
βja → 维亚 ;
|
|
|
βjen } $not_vowel → 维恩 ;
|
|
|
βje → 维耶 ;
|
|
|
βju → 维乌 ;
|
|
|
βon } $not_vowel → 翁 ;
|
|
|
βo → 沃 ;
|
|
|
βun } $not_vowel → 文 ;
|
|
|
βu → 武 ;
|
|
|
βwan } $not_vowel → 万 ;
|
|
|
βwa → 瓦 ;
|
|
|
βwen } $not_vowel → 文 ;
|
|
|
βwe → 武埃 ;
|
|
|
βwi → 维 ;
|
|
|
βwo → 沃 ;
|
|
|
β → 夫 ;
|
|
|
dai̯ → 代 ;
|
|
|
dan } $not_vowel → 丹 ;
|
|
|
dau̯ → 道 ;
|
|
|
da → 达 ;
|
|
|
dei̯ → 代 ;
|
|
|
den } $not_vowel → 登 ;
|
|
|
de → 德 ;
|
|
|
din } $not_vowel → 丁 ;
|
|
|
di → 迪 ;
|
|
|
dja → 迪亚 ;
|
|
|
djen } $not_vowel → 迪恩 ;
|
|
|
dje → 迭 ;
|
|
|
dju → 迪乌 ;
|
|
|
don } $not_vowel → 东 ;
|
|
|
do → 多 ;
|
|
|
dun } $not_vowel → 敦 ;
|
|
|
du → 杜 ;
|
|
|
dwan } $not_vowel → 端 ;
|
|
|
dwa → 杜阿 ;
|
|
|
dwen } $not_vowel → 敦 ;
|
|
|
dwe → 杜埃 ;
|
|
|
dwi → 杜伊 ;
|
|
|
dwo → 多 ;
|
|
|
d } $word_boundary → ;
|
|
|
d → 德 ;
|
|
|
ei̯ → 埃 ;
|
|
|
en } $not_vowel → 恩 ;
|
|
|
eu̯ → 欧 ;
|
|
|
e → 埃 ;
|
|
|
fai̯ → 法伊 ;
|
|
|
fan } $not_vowel → 凡 ;
|
|
|
fau̯ → 福 ;
|
|
|
fa → 法 ;
|
|
|
fe → 费 ;
|
|
|
fin } $not_vowel → 芬 ;
|
|
|
fi → 菲 ;
|
|
|
fja → 菲亚 ;
|
|
|
fjen } $not_vowel → 菲恩 ;
|
|
|
fje → 菲耶 ;
|
|
|
fju → 菲乌 ;
|
|
|
fon } $not_vowel → 丰 ;
|
|
|
fo → 福 ;
|
|
|
fun } $not_vowel → 丰 ;
|
|
|
fu → 富 ;
|
|
|
fwan } $not_vowel → 富安 ;
|
|
|
fwa → 富阿 ;
|
|
|
fwen } $not_vowel → 丰 ;
|
|
|
fwe → 富埃 ;
|
|
|
fwi → 富伊 ;
|
|
|
fwo → 福 ;
|
|
|
|
|
|
|
|
|
# The choice of 弗 vs. 夫 sounds simple according to the GB/T standard, but the
|
|
|
# data suggest otherwise. Ideally, 弗 should occur at the beginning of a
|
|
|
# morpheme (e.g. in "villafranca" 比利亚弗兰卡) and 夫 everywhere else. Since
|
|
|
# we don't have morpheme boundaries, we'll fudge it by writing 夫 at the end of
|
|
|
# a word and 弗 everywhere else.
|
|
|
|
|
|
f } $word_boundary → 夫 ;
|
|
|
f → 弗 ;
|
|
|
|
|
|
gai̯ → 盖 ;
|
|
|
gan } $not_vowel → 甘 ;
|
|
|
gau̯ → 高 ;
|
|
|
ga → 加 ;
|
|
|
gei̯ → 盖 ;
|
|
|
gen } $not_vowel → 根 ;
|
|
|
ge → 格 ;
|
|
|
gin } $not_vowel → 金 ;
|
|
|
gi → 吉 ;
|
|
|
gja → 吉亚 ;
|
|
|
gjen } $not_vowel → 吉恩 ;
|
|
|
gje → 吉耶 ;
|
|
|
gju → 吉乌 ;
|
|
|
gon } $not_vowel → 贡 ;
|
|
|
go → 戈 ;
|
|
|
gun } $not_vowel → 贡 ;
|
|
|
gu → 古 ;
|
|
|
gwan } [$] → 古安 ; # Nonstandard, but fits observed data.
|
|
|
gwan } $not_vowel → 关 ;
|
|
|
gwa → 瓜 ;
|
|
|
gwen } $not_vowel → 古恩 ;
|
|
|
gwe → 圭 ;
|
|
|
gwi → 圭 ;
|
|
|
gwo → 果 ;
|
|
|
g → 格 ;
|
|
|
in } $not_vowel → 因 ;
|
|
|
i → 伊 ;
|
|
|
ʝai̯ → 亚伊 ;
|
|
|
ʝan } $not_vowel → 扬 ;
|
|
|
ʝau̯ → 尧 ;
|
|
|
ʝa → 亚 ;
|
|
|
ʝen } $not_vowel → 延 ;
|
|
|
ʝe → 耶 ;
|
|
|
ʝin } $not_vowel → 因 ;
|
|
|
ʝi → 伊 ;
|
|
|
ʝon } $not_vowel → 永 ;
|
|
|
ʝo → 约 ;
|
|
|
ʝun } $not_vowel → 云 ;
|
|
|
ʝu → 尤 ;
|
|
|
ʝwan } $not_vowel → 元 ;
|
|
|
ʝwa → 尤阿 ;
|
|
|
ʝwen } $not_vowel → 云 ;
|
|
|
ʝwe → 尤埃 ;
|
|
|
ʝwi → 尤伊 ;
|
|
|
ʝwo → 约 ;
|
|
|
ʝ → 伊 ;
|
|
|
kai̯ → 凯 ;
|
|
|
kan } $not_vowel → 坎 ;
|
|
|
kau̯ → 考 ;
|
|
|
ka → 卡 ;
|
|
|
kei̯ → 凯 ;
|
|
|
ken } $not_vowel → 肯 ;
|
|
|
ke → 克 ;
|
|
|
kin } $not_vowel → 金 ;
|
|
|
ki → 基 ;
|
|
|
kja → 基亚 ;
|
|
|
kjen } $not_vowel → 基恩 ;
|
|
|
kje → 基耶 ;
|
|
|
kju → 基乌 ;
|
|
|
kon } $not_vowel → 孔 ;
|
|
|
ko → 科 ;
|
|
|
kun } $not_vowel → 昆 ;
|
|
|
ku → 库 ;
|
|
|
kwan } $not_vowel → 宽 ;
|
|
|
kwa → 夸 ;
|
|
|
kwen } $not_vowel → 昆 ;
|
|
|
kwe → 库埃 ;
|
|
|
kwin } $not_vowel → 昆 ;
|
|
|
kwi → 奎 ;
|
|
|
kwo → 阔 ;
|
|
|
k → 克 ;
|
|
|
lae } [^n] → 莱 ;
|
|
|
lai̯ → 莱 ;
|
|
|
lan } $not_vowel → 兰 ;
|
|
|
lau̯ → 劳 ;
|
|
|
la → 拉 ;
|
|
|
len } $not_vowel → 伦 ;
|
|
|
le → 莱 ;
|
|
|
lin } $not_vowel → 林 ;
|
|
|
li → 利 ;
|
|
|
lja → 利亚 ;
|
|
|
ljen } $not_vowel → 连 ;
|
|
|
lje → 列 ;
|
|
|
lju → 柳 ;
|
|
|
lon } $not_vowel → 隆 ;
|
|
|
lo → 洛 ;
|
|
|
lun } $not_vowel → 伦 ;
|
|
|
lu → 卢 ;
|
|
|
lwan } $not_vowel → 卢安 ;
|
|
|
lwa → 卢阿 ;
|
|
|
lwen } $not_vowel → 伦 ;
|
|
|
lwe → 卢埃 ;
|
|
|
lwi → 卢伊 ;
|
|
|
lwo → 洛 ;
|
|
|
l → 尔 ;
|
|
|
ʎan } $not_vowel → 良 ;
|
|
|
ʎau̯ → 廖 ;
|
|
|
ʎa → 利亚 ;
|
|
|
ʎen } $not_vowel → 连 ;
|
|
|
ʎe → 列 ;
|
|
|
ʎin } $not_vowel → 林 ;
|
|
|
ʎi → 利 ;
|
|
|
ʎon } $not_vowel → 利翁 ;
|
|
|
ʎo → 略 ;
|
|
|
ʎu → 柳 ;
|
|
|
ʎwan } $not_vowel → 柳安 ;
|
|
|
ʎwa → 柳阿 ;
|
|
|
ʎwen } $not_vowel → 柳恩 ;
|
|
|
ʎwe → 柳埃 ;
|
|
|
ʎwi → 柳伊 ;
|
|
|
ʎwo → 略 ;
|
|
|
ʎ → 尔 ;
|
|
|
mai̯ → 迈 ;
|
|
|
man } $not_vowel → 曼 ;
|
|
|
martin → 马丁 ;
|
|
|
mau̯ → 毛 ;
|
|
|
ma → 马 ;
|
|
|
men } $not_vowel → 门 ;
|
|
|
me → 梅 ;
|
|
|
min } $not_vowel → 明 ;
|
|
|
mi → 米 ;
|
|
|
mja → 米亚 ;
|
|
|
mjen } $not_vowel → 缅 ;
|
|
|
mje → 米耶 ;
|
|
|
mju → 缪 ;
|
|
|
mon } $not_vowel → 蒙 ;
|
|
|
mo → 莫 ;
|
|
|
mun } $not_vowel → 蒙 ;
|
|
|
mu → 穆 ;
|
|
|
mwan } $not_vowel → 穆安 ;
|
|
|
mwa → 穆阿 ;
|
|
|
mwen } $not_vowel → 门 ;
|
|
|
mwe → 穆埃 ;
|
|
|
mwin } $not_vowel → 穆因 ; # Nonstandard, but fits observed data.
|
|
|
mwi → 穆伊 ;
|
|
|
mwo → 莫 ;
|
|
|
m → 姆 ;
|
|
|
nai̯ → 奈 ;
|
|
|
nan } $not_vowel → 南 ;
|
|
|
nau̯ → 瑙 ;
|
|
|
na → 纳 ;
|
|
|
nen } $not_vowel → 嫩 ;
|
|
|
ne → 内 ;
|
|
|
nin } $not_vowel → 宁 ;
|
|
|
ni → 尼 ;
|
|
|
nja → 尼亚 ;
|
|
|
njen } $not_vowel → 年 ;
|
|
|
nje → 涅 ;
|
|
|
nju → 纽 ;
|
|
|
non } $not_vowel → 农 ;
|
|
|
no → 诺 ;
|
|
|
nun } $not_vowel → 嫩 ;
|
|
|
nu → 努 ;
|
|
|
nwan } $not_vowel → 努安 ;
|
|
|
nwa → 努阿 ;
|
|
|
nwen } $not_vowel → 农 ;
|
|
|
nwe → 努埃 ;
|
|
|
nwi → 努伊 ;
|
|
|
nwo → 诺 ;
|
|
|
n → 恩 ;
|
|
|
ɲan } $not_vowel → 尼扬 ;
|
|
|
ɲau̯ → 尼奥 ;
|
|
|
ɲa → 尼亚 ;
|
|
|
ɲen } $not_vowel → 年 ;
|
|
|
ɲe → 涅 ;
|
|
|
ɲin } $not_vowel → 宁 ;
|
|
|
ɲi → 尼 ;
|
|
|
ɲon } $not_vowel → 尼翁 ;
|
|
|
ɲo → 尼奥 ;
|
|
|
ɲu → 纽 ;
|
|
|
ɲwan } $not_vowel → 纽安 ;
|
|
|
ɲwa → 纽阿 ;
|
|
|
ɲwen } $not_vowel → 纽恩 ;
|
|
|
ɲwe → 纽埃 ;
|
|
|
ɲwi → 纽伊 ;
|
|
|
ɲwo → 尼奥 ;
|
|
|
on } $not_vowel → 翁 ;
|
|
|
ou̯ → 欧 ;
|
|
|
o → 奥 ;
|
|
|
pai̯ → 派 ;
|
|
|
pan } $not_vowel → 潘 ;
|
|
|
pau̯ → 保 ;
|
|
|
pa → 帕 ;
|
|
|
pen } $not_vowel → 彭 ;
|
|
|
pe → 佩 ;
|
|
|
pin } $not_vowel → 平 ;
|
|
|
pi → 皮 ;
|
|
|
pja → 皮亚 ;
|
|
|
pjen } $not_vowel → 皮恩 ;
|
|
|
pje → 彼 ;
|
|
|
pju → 皮乌 ;
|
|
|
pon } $not_vowel → 蓬 ;
|
|
|
po → 波 ;
|
|
|
pun } $not_vowel → 蓬 ;
|
|
|
pu → 普 ;
|
|
|
pwan } $not_vowel → 普安 ;
|
|
|
pwa → 普阿 ;
|
|
|
pwen } $not_vowel → 蓬 ;
|
|
|
pwe → 普埃 ;
|
|
|
pwi → 普伊 ;
|
|
|
pwo → 波 ;
|
|
|
p → 普 ;
|
|
|
rai̯ → 赖 ;
|
|
|
ran } $not_vowel → 兰 ;
|
|
|
rau̯ → 劳 ;
|
|
|
ra → 拉 ;
|
|
|
ren } $not_vowel → 伦 ;
|
|
|
re → 雷 ;
|
|
|
rin } $not_vowel → 林 ;
|
|
|
ri → 里 ;
|
|
|
rja → 里亚 ;
|
|
|
rjen } $not_vowel → 连 ;
|
|
|
rje → 列 ;
|
|
|
rju → 留 ;
|
|
|
ron } $not_vowel → 龙 ;
|
|
|
ro → 罗 ;
|
|
|
run } $not_vowel → 伦 ;
|
|
|
ru → 鲁 ;
|
|
|
rwan } $not_vowel → 鲁安 ;
|
|
|
rwa → 鲁阿 ;
|
|
|
rwen } $not_vowel → 伦 ;
|
|
|
rwe → 鲁埃 ;
|
|
|
rwi → 鲁伊 ;
|
|
|
rwo → 罗 ;
|
|
|
r → R ;
|
|
|
sai̯ → 赛 ;
|
|
|
san } $not_vowel → 桑 ;
|
|
|
sau̯ → 绍 ;
|
|
|
sa → 萨 ;
|
|
|
sen } $not_vowel → 森 ;
|
|
|
se → 塞 ;
|
|
|
sin } $not_vowel → 辛 ;
|
|
|
si → 西 ;
|
|
|
sja → 西亚 ;
|
|
|
sjen } $not_vowel → 先 ;
|
|
|
sje → 谢 ;
|
|
|
sju → 休 ;
|
|
|
son } $not_vowel → 松 ;
|
|
|
so → 索 ;
|
|
|
sun } $not_vowel → 孙 ;
|
|
|
su → 苏 ;
|
|
|
swan } $not_vowel → 苏安 ;
|
|
|
swa → 苏阿 ;
|
|
|
swen } $not_vowel → 孙 ;
|
|
|
swe → 苏埃 ;
|
|
|
swi → 绥 ;
|
|
|
swo → 索 ;
|
|
|
s → 斯 ;
|
|
|
tai̯ → 泰 ;
|
|
|
tan } $not_vowel → 坦 ;
|
|
|
tau̯ → 陶 ;
|
|
|
ta → 塔 ;
|
|
|
tei̯ → 泰 ;
|
|
|
ten } $not_vowel → 滕 ;
|
|
|
te → 特 ;
|
|
|
tin } $not_vowel → 廷 ;
|
|
|
ti → 蒂 ;
|
|
|
tja → 蒂亚 ;
|
|
|
tjen } $not_vowel → 蒂恩 ;
|
|
|
tje → 铁 ;
|
|
|
tju → 蒂乌 ;
|
|
|
ton } $not_vowel → 通 ;
|
|
|
to → 托 ;
|
|
|
|
|
|
# The rules for /ts/ (tz in the orthography) are nonstandard and derived
|
|
|
# entirely from the observed data. They apply mostly to native toponyms
|
|
|
# in Mexico.
|
|
|
|
|
|
tsa → 察 ;
|
|
|
tsen } $not_vowel → 岑 ;
|
|
|
tse → 采 ;
|
|
|
tsin } $not_vowel → 钦 ;
|
|
|
tsi → 齐 ;
|
|
|
tso → 措 ;
|
|
|
tsun } $not_vowel → 聪 ;
|
|
|
tsu → 楚 ;
|
|
|
ts → 茨 ;
|
|
|
|
|
|
tun } $not_vowel → 通 ;
|
|
|
tu → 图 ;
|
|
|
twan } $not_vowel → 图安 ;
|
|
|
twa → 图阿 ;
|
|
|
twen } $not_vowel → 通 ;
|
|
|
twe → 图埃 ;
|
|
|
twi → 图伊 ;
|
|
|
two → 托 ;
|
|
|
t → 特 ;
|
|
|
ʧai̯ → 柴 ;
|
|
|
ʧan } $not_vowel → 钱 ;
|
|
|
ʧau̯ → 乔 ;
|
|
|
ʧa → 查 ;
|
|
|
ʧen } $not_vowel → 琴 ;
|
|
|
ʧe → 切 ;
|
|
|
ʧin } $not_vowel → 钦 ;
|
|
|
ʧi → 奇 ;
|
|
|
ʧjan } $not_vowel → 钱 ;
|
|
|
ʧja → 恰 ;
|
|
|
ʧjen } $not_vowel → 钱 ;
|
|
|
ʧje → 切 ;
|
|
|
ʧjon } $not_vowel → 琼 ;
|
|
|
ʧju → 丘 ;
|
|
|
ʧon } $not_vowel → 琼 ;
|
|
|
ʧo → 乔 ;
|
|
|
ʧun } $not_vowel → 琼 ; # Should be 春, per GB/T 17693.5-2009 表 1.
|
|
|
ʧu → 丘 ;
|
|
|
ʧwan } $not_vowel → 丘安 ;
|
|
|
ʧwa → 丘阿 ;
|
|
|
ʧwen } $not_vowel → 琼 ;
|
|
|
ʧwe → 丘埃 ;
|
|
|
ʧwi → 崔 ;
|
|
|
ʧwo → 乔 ;
|
|
|
ʧ → 奇 ;
|
|
|
un } $not_vowel → 温 ;
|
|
|
u → 乌 ;
|
|
|
wan } $not_vowel → 万 ;
|
|
|
wa → 瓦 ;
|
|
|
wen } $not_vowel → 温 ;
|
|
|
we → 韦 ;
|
|
|
win } $not_vowel → 温 ;
|
|
|
wi → 维 ;
|
|
|
won } $not_vowel → 翁 ; # Unseen.
|
|
|
wo → 沃 ;
|
|
|
xai̯ → 海 ;
|
|
|
xan } $not_vowel → 汉 ;
|
|
|
xau̯ → 豪 ;
|
|
|
xa → 哈 ;
|
|
|
xei̯ → 黑 ;
|
|
|
xen } $not_vowel → 亨 ;
|
|
|
xe → 赫 ;
|
|
|
xin } $not_vowel → 欣 ;
|
|
|
xi → 希 ;
|
|
|
xja → 希亚 ;
|
|
|
xjen } $not_vowel → 希恩 ;
|
|
|
xje → 希耶 ;
|
|
|
xju → 休 ;
|
|
|
xon } $not_vowel → 洪 ;
|
|
|
xo → 霍 ;
|
|
|
xun } $not_vowel → 洪 ;
|
|
|
xu → 胡 ;
|
|
|
xwan } $not_vowel → 胡安 ;
|
|
|
xwa → 华 ;
|
|
|
xwen } $not_vowel → 洪 ;
|
|
|
xwe → 胡埃 ;
|
|
|
xwi → 惠 ;
|
|
|
xwo → 霍 ;
|
|
|
x → 赫 ;
|
|
|
|
|
|
# 尔 simplification pass. The idea is to drop most occurences of 尔
|
|
|
# corresponding to <r> (not to <l> or <ll>) from a word if there is another /l/
|
|
|
# sound nearby. There is a vague pattern like this in the data, but the details
|
|
|
# remain to be determined. At the moment, this does nothing, it just puts 尔 in
|
|
|
# for every <r> in a syllable coda.
|
|
|
|
|
|
::Null;
|
|
|
$r = [R利拉];
|
|
|
#
|
|
|
#
|
|
|
# R } . $r → ;
|
|
|
# R } .. $r → ;
|
|
|
# R } ... $r → ;
|
|
|
# R } .... $r → ;
|
|
|
|
|
|
R → 尔 ;
|
|
|
|
|
|
# Dong-nan-xi-hai pass. Per GB/T 17693.5-2009 表 1, 注 4, replace confusing
|
|
|
# characters at the beginning and end of a word.
|
|
|
|
|
|
::Null;
|
|
|
$word_boundary { 东 → 栋 ;
|
|
|
$word_boundary { 南 → 楠 ;
|
|
|
$word_boundary { 西 → 锡 ;
|
|
|
海 } $word_boundary → 亥 ;
|
|
|
|
|
|
::NFC;
|
|
|
]]></tRule>
|
|
|
</transform>
|
|
|
</transforms>
|
|
|
</supplementalData>
|
