File: ro-ro_FONIPA.xml

package info (click to toggle)
python-babel 2.6.0%2Bdfsg.1-1%2Bdeb10u1
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 164,640 kB
  • sloc: xml: 1,848,178; python: 11,849; makefile: 213; sh: 44
file content (147 lines) | stat: -rw-r--r-- 2,433 bytes parent folder | download | duplicates (3)
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
147
<?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: 12813 $"/>
	<transforms>
		<transform source="ro" target="ro_FONIPA" direction="forward" alias="ro-fonipa-t-ro">
			<tRule><![CDATA[
# Romanian orthography to phonemic transcription.
# http://en.wikipedia.org/wiki/Romanian_phonology
#
# TODO: Currently this transform does not palatalize consonants.

$VowelEI = [e i î];
$VowelAOU = [a â ă o u];
$Vowel = [$VowelEI $VowelAOU];
$Boundary =  [^[:L:][:M:][:N:]];

:: NFC () ;
:: Lower () ;

# Special cases.
eoai → eo̯aj ;  # eg. leoaică → /leo̯ajkə/, not /le̯o̯aikə/

# Triphthongs.
eai → e̯aj ;
eau → e̯aw ;
eoa → e̯o̯a ;
i\-ai → jaj ;
ia\-i → jaj ;
iau → jaw ;
iei → jej ;
ieu → jew ;
$Boundary {eu} → jew ;
ioa → jo̯a ;
ioi → joj ;
i\-oi → joj ;
iou → jow ;
oai → o̯aj ;
uai → waj ;
uau → waw ;
uăi → wəj ;

# Diphthongs.
ai → aj ;
âi → ɨj ;
ăi → əj ;
au} r → au ;
au → aw ;
âu → ɨw ;
ău → əw ;
ea → e̯a ;
ei → ej ;
eo → e̯o ;
e\-o → e̯o ;
eu → ew ;
e\-u → e̯u ;
ia → ja ;
i\-a → ja ;
ie → je ;
ii → ij ;
io → jo ;
iu} [$Vowel $Boundary] → iw ;
iu → ju ;
oa → o̯a ;
oi → oj ;
ou → ow ;
ua → wa ;
uâ → wɨ ;
uă → wə ;
ue → we ;
ui → uj ;
uu → uw ;

a → a ;
â → ɨ ;
ă → ə ;
b → b ;
ch → k ;
{c} [ei] → t͡ʃ ;
c → k ;
d → d ;
e → e ;
f → f ;
gh → ɡ ;
{g} [ei] → d͡ʒ ;
g → ɡ ;
h → h ;
i → i ;
î → ɨ ;
j → ʒ ;
k → k ;
l → l ;
m → m ;
ng → ŋ ;
n → n ;
o → o ;
p → p ;
q → k ;
r → r ;
s → s ;
ş → ʃ ;
ș → ʃ ;
t → t ;
ţ → t͡s ;
ț → t͡s ;
u → u ;
v → v ;
x → ks ;
y → i ;
z → z ;
[:P:]+ → ' ';

# Romanian does not have any gemination.
# https://en.wikipedia.org/wiki/Gemination#Latin_and_Romance_languages
::null;
pp+ → p;
bb+ → b;
tt+ → t;
dd+ → d;
kk+ → k;
dd+ → d;
ɡɡ+ → ɡ;

ff+ → f;
vv+ → v;
hh+ → h;

ss+ → s;
zz+ → z;
ʃʃ+ → ʃ;
ʒʒ+ → ʒ;

rr+ → r;
ll+ → l;

jj+ → j;
ww+ → w;

			]]></tRule>
		</transform>
	</transforms>
</supplementalData>