icu4c/source/data/translit/ch_ch_FONIPA.txt

# © 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: ch_ch_FONIPA.txt
# Generated from CLDR
#

# Transformation from Chamorro (ch) to its IPA transcription (ch_FONIPA).
#
# http://en.wikipedia.org/wiki/Chamorro_language#Orthography
# http://www.omniglot.com/writing/chamorro.htm
# http://guampedia.com/chamorro-orthography-rules/
# http://finochamoru.blogspot.com/2009/04/leksion-chamoru-pronunsiasion.html
#
# Recorded sound samples: http://www.chamorro.com/fino/fino.html
#
# http://guampedia.com/chamorro-orthography-rules/ lists in section 3.b)
# graphemes that would be used for loanwords/proper names. Most examples
# are Spanish. Our rules thus generate the Spanish sounds [θ], [x], [β]
# and [w] even though these sounds are not used by the Chamorro language.
::Lower;
::NFC;
\' → ʔ;
’ → ʔ;
# The IPA chart from Omniglot appears to be mixing up [æ] and [ɑ] when
# explaining how to pronounce ‹a› and ‹å›. The language course on
# finochamoru.blogspot.com copies the pronunciation chart from Omniglot,
# but then explains that ‹å› gets prounounced like in English ‹father›,
# which would be [ɑ]. Also, the sound samples on www.chamorro.com pronounce
# ‹a› as [æ] and ‹å› as [ɑ].
a → æ;
å → ɑ;
b → b;
ch → t\u0361s;
{c} [eéií] → θ; # loanwords
c → k; # loanwords
d → d;
e → e;
f → f;
gu → ɡʷ;
g → ɡ;
h → h;
i → i;
j → x ; # loanwords
k → k;
l → l;
m → m;
ng → ŋ;
ñ → ɲ;
n → n;
o → o;
p → p;
{qu} [eéiíy] → k; # loanwords
q → k; # loanwords
rr → r;
r → ɾ;
s → s;
t → t;
u → u;
v → β; # loanwords
w → w; # loanwords
{x} h?[aáåeéiíoóuú$] → ks; # loanwords
{x} [^aáåeéiíoóuú$] → s; # loanwords
x → ks ; # loanwords
# Wikipedia [http://en.wikipedia.org/wiki/Chamorro_language#Orthography]
# writes that ‹y› gets pronounced as [d\u0361z], while Omniglot says [d\u0361ʒ].
y → d\u0361z;
\- → \.; # hyphen is a syllable boundary, eg ‹sena-ta›
# Handle geminated consonants.
::Null;
bb → bː;
dd → dː;
ff → fː;
ɡɡ → ɡː;
hh → hː;
kk → kː;
ll → lː;
mm → mː;
nn → nː;
pp → pː;
rr → rː;
ss → sː;
tt → tː;
::NFC;