summaryrefslogtreecommitdiffstats
path: root/intl/icu/source/data/translit/es_es_FONIPA.txt
blob: 4114f9ec927bd6a61a08fbddb008b1d6a2af2048 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
# © 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: es_es_FONIPA.txt
# Generated from CLDR
#

# Transformation from Spanish to Spanish in IPA transcription (es_FONIPA).
# Not fully phonemic, since we mark up allophonic variants of voiced stops,
# e.g. we break down /b/ into [b] and [β].
#
# See e.g. "Ortografía de la lengua española" by Real Academia Española,
# available in PDF format on the web (non-stable URL).
#
# Definitions.
$bow = [-\ $] ;  # Beginning of word.
$consonant = [bβdðfgɣʝklʎmnŋɲθprɾstʧx] ;
$syll = '.' ;    # Syllable boundary.
#
#
#
#
::NFC;
::Lower;
#
#
#
#
#
# Word-initial cluster simplification.
#
$bow { ct → | t ;  # ctónico (?)
$bow { cz → | z ;  # czar
$bow { gn → | n ;  # gnomo
$bow { mn → | n ;  # mnemotécnico
$bow { ps → | s ;  # psicología
$bow { pt → | t ;  # pterodáctilo
$bow { x  → | s ;  # xilófono
#
#
#
# Vowels and glides.
#
$bow       { i                 → i ;
$consonant { i } [ aáeé  oóuú] → j ;
[aeo]      { i } [^aáeé  oóuú] → i\u032F ;
i } [ aáeé  oóuú] → ʝ ;
i                 → i ;
#
#
[aeo]      { y } [^aáeéiíoóuú] → i\u032F ;
y } [ aáeéiíoóuú] → ʝ ;
y                 → i ;
#
#
[aeo]      { u } [^aáeéiíoó  ] → u\u032F ;
u } [ aáeéiíoó  ] → w ;
ü } [   eéií    ] → w ;
u                 → u ;
ü                 → u ;  # Should not be needed, but just in case.
#
#
[aá] → a ;
[eé] → e ;
í    → i ;
[oó] → o ;
ú    → u ;
#
#
#
# Consonants.
#
b → β ;
cch → ʧ ;
ch → ʧ ;
cc } [^eéií] → k ;
c } [eéií] → θ ;
c → k ;
d → ð ;
f → f;
gu } [eéiíy] → ɣ ;
g } [eéiíy] → x ;
g → ɣ ;
hi } [aáeéoóuú] → ʝ ;
h → $syll ;
j → x ;
k → k ;
ll → ʎ ;
l → l ;
m → m ;
n → n ;
ñ → ɲ ;
p → p ;
qu } [eéiíy] → k ;
q → k ;
[-\ lns$] { r → r ;
rr → r ;
r → ɾ ;
ss → s ;
s → s ;
tx → ʧ ;  # for loanwords from Basque, Catalan
t → t ;
v → β ;
w → $syll w ;
x } h?[aáeéiíoóuú$] → ks ;
x } [^aáeéiíoóuú$] → s ;
x → ks ;
z → θ ;
#
#
#
# Second pass: phoneme-to-phone rules. Differentiation of /β/ into [b] and [β],
# place assimilation of [n], etc.
#
::Null;
#
#
[-\ ] → ;
#
#
[mnɲŋ  $] { β → b ;
[mnɲŋlʎ$] { ð → d ;
[mnɲŋ  $] { ɣ → g ;
#
#
n } [gɣk] → ŋ ;
#
#
# Optional: Place assimilation of n before labial consonants.
#
# n } [bβpfm] → m ;
#
# Optional: Voicing of [s].
#
# s } [bβdð] → z ;
# s } [gɣ][^ei] → z ;
# s } [mnɲŋlʎrɾ] → z ;
#
# Optional: Lenition of [k] before [θ].
#
# k } θ → ɣ ;
#
#
::NFC;