• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# © 2016 and later: Unicode, Inc. and others.
2# License & terms of use: http://www.unicode.org/copyright.html
3# Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
4#
5# File: und_FONIPA_und_FONXSAMP.txt
6# Generated from CLDR
7#
8
9# Conversion between IPA and X-SAMPA phonetic transcription.
10#
11# See http://www.phon.ucl.ac.uk/home/sampa/x-sampa.htm for a description of
12# X-SAMPA, an ASCII encoding of the International Phonetic Alphabet.
13#
14# The following obsolete or extended IPA symbols have no X-SAMPA equivalents
15# and remain unaffected by this transform:
16#
17#   ʞ  LATIN SMALL LETTER TURNED K
18#   ʩ  LATIN SMALL LETTER FENG DIGRAPH
19#   ʪ  LATIN SMALL LETTER LS DIGRAPH
20#   ʫ  LATIN SMALL LETTER LZ DIGRAPH
21#   ʬ  LATIN LETTER BILABIAL PERCUSSIVE
22#   ʭ  LATIN LETTER BIDENTAL PERCUSSIVE
23#
24# An IPA tie bar is transformed to an X-SAMPA underscore, per the official
25# X-SAMPA guidelines.  This can result in certain ambiguities: For example, the
26# labial-velar nasal (http://en.wikipedia.org/wiki/Labial-velar_nasal) can be
27# either written as [ŋ\u0361m] or [m\u0361ŋ] in IPA.  However, neither version can be
28# represented unambiguously in X-SAMPA: IPA [ŋ\u0361m] becomes X-SAMPA [N_m], which
29# is also used to represent a hypothetical laminal (_m) velar nasal, IPA [ŋ\u033B];
30# and IPA [m\u0361ŋ] becomes X-SAMPA [m_N], which can also represent a linguolabial
31# (_N) nasal, IPA [m\u033C], which is more appropriately written [n\u033C].  To avoid
32# unintended ambiguities, it may therefore be advisable to write affricates
33# without tie bars.
34#
35$t = '_';  # X-SAMPA representation of IPA tie bar.
36::NFD(NFC);
37# 5-character X-SAMPA representations
38ʯ ↔ 'z`_w=';      # LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
39# Alternative 5-character X-SAMPA representations
40n\u031F\u030A ← 'n_+_0';
41n\u0320\u030A ← 'n_-_0';
42n\u032A\u030A ← 'n_d_0';
43n\u033A\u030A ← 'n_a_0';
44n\u033B\u030A ← 'n_m_0';
45n\u033C\u030A ← 'n_N_0';
46ɻ\u030A ← 'r\`_0';
47# 4-character X-SAMPA representations
48ǁ ↔ '|\|\';       # LATIN LETTER LATERAL CLICK
49ʄ ↔ 'J\_<';    # LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK
50ʛ ↔ 'G\_<';    # LATIN LETTER SMALL CAPITAL G WITH HOOK
51ʮ ↔ 'z_w=';       # LATIN SMALL LETTER TURNED H WITH FISHHOOK
52\u1DC4 ↔ '_H_T';  # COMBINING MACRON-ACUTE
53\u1DC5 ↔ '_B_L';  # COMBINING GRAVE-MACRON
54\u1DC8 ↔ '_R_F';  # COMBINING GRAVE-ACUTE-GRAVE
55# Alternative 4-character X-SAMPA representations
56ɭ\u030A ← 'l`_0';
57ɰ\u030A ← 'M\_0';
58ɳ\u030A ← 'n`_0';
59ɽ\u030A ← 'r`_0';
60# 3-character X-SAMPA representations
61ɓ ↔ 'b_<';     # LATIN SMALL LETTER B WITH HOOK
62ɗ ↔ 'd_<';     # LATIN SMALL LETTER D WITH HOOK
63ɠ ↔ 'g_<';     # LATIN SMALL LETTER G WITH HOOK
64ɻ ↔ 'r\`';        # LATIN SMALL LETTER TURNED R WITH HOOK
65↗ ↔ '<R>';  # NORTH EAST ARROW
66↘ ↔ '<F>';  # SOUTH EAST ARROW
67# Alternative 3-character X-SAMPA representations
68j\u030A ← 'j_0';
69ŋ\u030A ← 'N_0';
70ɥ\u030A ← 'H_0';
71ɱ\u030A ← 'F_0';
72ɲ\u030A ← 'J_0';
73# 2-character X-SAMPA representations
74ħ ↔ 'X\';      # LATIN SMALL LETTER H WITH STROKE
75ǀ ↔ '|\';      # LATIN LETTER DENTAL CLICK
76ǂ ↔ '=\';      # LATIN LETTER ALVEOLAR CLICK
77ǃ ↔ '!\';      # LATIN LETTER RETROFLEX CLICK
78ɕ ↔ 's\';      # LATIN SMALL LETTER C WITH CURL
79ɖ ↔ 'd`';      # LATIN SMALL LETTER D WITH TAIL
80ɘ ↔ '@\';      # LATIN SMALL LETTER REVERSED E
81ɚ ↔ '@`';      # LATIN SMALL LETTER SCHWA WITH HOOK
82ɝ ↔ '3`';      # LATIN SMALL LETTER REVERSED OPEN E WITH HOOK
83ɞ ↔ '3\';      # LATIN SMALL LETTER CLOSED REVERSED OPEN E
84ɟ ↔ 'J\';      # LATIN SMALL LETTER DOTLESS J WITH STROKE
85ɢ ↔ 'G\';      # LATIN LETTER SMALL CAPITAL G
86ɦ ↔ 'h\';      # LATIN SMALL LETTER H WITH HOOK
87ɧ ↔ 'x\';      # LATIN SMALL LETTER HENG WITH HOOK
88ɭ ↔ 'l`';      # LATIN SMALL LETTER L WITH RETROFLEX HOOK
89ɮ ↔ 'K\';      # LATIN SMALL LETTER LEZH
90ɰ ↔ 'M\';      # LATIN SMALL LETTER TURNED M WITH LONG LEG
91ɳ ↔ 'n`';      # LATIN SMALL LETTER N WITH RETROFLEX HOOK
92ɴ ↔ 'N\';      # LATIN LETTER SMALL CAPITAL N
93ɸ ↔ 'p\';      # LATIN SMALL LETTER PHI
94ɹ ↔ 'r\';      # LATIN SMALL LETTER TURNED R
95ɺ ↔ 'l\';      # LATIN SMALL LETTER TURNED R WITH LONG LEG
96ɽ ↔ 'r`';      # LATIN SMALL LETTER R WITH TAIL
97ʀ ↔ 'R\';      # LATIN LETTER SMALL CAPITAL R
98ʂ ↔ 's`';      # LATIN SMALL LETTER S WITH HOOK
99ʈ ↔ 't`';      # LATIN SMALL LETTER T WITH RETROFLEX HOOK
100ʐ ↔ 'z`';      # LATIN SMALL LETTER Z WITH RETROFLEX HOOK
101ʑ ↔ 'z\';      # LATIN SMALL LETTER Z WITH CURL
102ʕ ↔ '?\';      # LATIN LETTER PHARYNGEAL VOICED FRICATIVE
103ʘ ↔ 'O\';      # LATIN LETTER BILABIAL CLICK
104ʙ ↔ 'B\';      # LATIN LETTER SMALL CAPITAL B
105ʜ ↔ 'H\';      # LATIN LETTER SMALL CAPITAL H
106ʝ ↔ 'j\';      # LATIN SMALL LETTER J WITH CROSSED-TAIL
107ʟ ↔ 'L\';      # LATIN LETTER SMALL CAPITAL L
108ʡ ↔ '>\';      # LATIN LETTER GLOTTAL STOP WITH STROKE
109ʢ ↔ '<\';      # LATIN LETTER REVERSED GLOTTAL STOP WITH STROKE
110ʰ ↔ '_h';      # MODIFIER LETTER SMALL H
111ʷ ↔ '_w';      # MODIFIER LETTER SMALL W
112ʼ ↔ '_>';      # MODIFIER LETTER APOSTROPHE
113ˆ ↔ '_\';      # MODIFIER LETTER CIRCUMFLEX ACCENT
114ˇ ↔ '_/';      # CARON
115ˑ ↔ ':\';      # MODIFIER LETTER HALF TRIANGULAR COLON
116ˠ ↔ '_G';      # MODIFIER LETTER SMALL GAMMA
117ˡ ↔ '_l';      # MODIFIER LETTER SMALL L
118ˤ ↔ '_?\';     # MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
119\u0300 ↔ '_L';    # COMBINING GRAVE ACCENT
120\u0301 ↔ '_H';    # COMBINING ACUTE ACCENT
121\u0302 ↔ '_F';    # COMBINING CIRCUMFLEX ACCENT
122\u0304 ↔ '_M';    # COMBINING MACRON
123\u0306 ↔ '_X';    # COMBINING BREVE
124\u0308 ↔ '_"';    # COMBINING DIAERESIS
125\u030B ↔ '_T';    # COMBINING DOUBLE ACUTE ACCENT
126\u030C ↔ '_R';    # COMBINING CARON
127\u030F ↔ '_B';    # COMBINING DOUBLE GRAVE ACCENT
128\u0318 ↔ '_A';    # COMBINING LEFT TACK BELOW
129\u0319 ↔ '_q';    # COMBINING RIGHT TACK BELOW
130\u031A ↔ '_}';    # COMBINING LEFT ANGLE ABOVE
131\u031C ↔ '_c';    # COMBINING LEFT HALF RING BELOW
132\u031D ↔ '_r';    # COMBINING UP TACK BELOW
133\u031E ↔ '_o';    # COMBINING DOWN TACK BELOW
134\u031F ↔ '_+';    # COMBINING PLUS SIGN BELOW
135\u0320 ↔ '_-';    # COMBINING MINUS SIGN BELOW
136\u0324 ↔ '_t';    # COMBINING DIAERESIS BELOW
137\u0325 ↔ '_0';    # COMBINING RING BELOW
138\u032A ↔ '_d';    # COMBINING BRIDGE BELOW
139\u032C ↔ '_v';    # COMBINING CARON BELOW
140\u032F ↔ '_^';    # COMBINING INVERTED BREVE BELOW
141\u0330 ↔ '_k';    # COMBINING TILDE BELOW
142\u0334 ↔ '_e';    # COMBINING TILDE OVERLAY
143\u0339 ↔ '_O';    # COMBINING RIGHT HALF RING BELOW
144\u033A ↔ '_a';    # COMBINING INVERTED BRIDGE BELOW
145\u033B ↔ '_m';    # COMBINING SQUARE BELOW
146\u033C ↔ '_N';    # COMBINING SEAGULL BELOW
147\u033D ↔ '_x';    # COMBINING X ABOVE
148ᵻ ↔ 'I\';      # LATIN SMALL CAPITAL LETTER I WITH STROKE
149ᵿ ↔ 'U\';      # LATIN SMALL CAPITAL LETTER U WITH STROKE
150ⁿ ↔ '_n';      # MODIFIER LETTER LATIN SMALL LETTER N
151# Alternative 2-character X-SAMPA representations
152ʋ ← 'v\';         # LATIN SMALL LETTER V WITH HOOK
153ʲ ← '_j';         # MODIFIER LETTER SMALL J
154\u0303 ← '_~';    # COMBINING TILDE
155\u0329 ← '_=';    # COMBINING VERTICAL LINE BELOW
156# 1-character X-SAMPA representations
157c\u0327 ↔ C;      # LATIN SMALL LETTER C WITH CEDILLA (decomposed)
158æ ↔ '{';          # LATIN SMALL LETTER AE
159ð ↔ D;            # LATIN SMALL LETTER ETH
160ø ↔ 2;            # LATIN SMALL LETTER O WITH STROKE
161ŋ ↔ N;            # LATIN SMALL LETTER ENG
162œ ↔ 9;            # LATIN SMALL LIGATURE OE
163ɐ ↔ 6;            # LATIN SMALL LETTER TURNED A
164ɑ ↔ A;            # LATIN SMALL LETTER ALPHA
165ɒ ↔ Q;            # LATIN SMALL LETTER TURNED ALPHA
166ɔ ↔ O;            # LATIN SMALL LETTER OPEN O
167ə ↔ '@';          # LATIN SMALL LETTER SCHWA
168ɛ ↔ E;            # LATIN SMALL LETTER OPEN E
169ɜ ↔ 3;            # LATIN SMALL LETTER REVERSED OPEN E
170ɡ ↔ g;            # LATIN SMALL LETTER SCRIPT G
171ɣ ↔ G;            # LATIN SMALL LETTER GAMMA
172ɤ ↔ 7;            # LATIN SMALL LETTER RAMS HORN
173ɥ ↔ H;            # LATIN SMALL LETTER TURNED H
174ɨ ↔ 1;            # LATIN SMALL LETTER I WITH STROKE
175ɪ ↔ I;            # LATIN LETTER SMALL CAPITAL I
176ɫ ↔ 5;            # LATIN SMALL LETTER L WITH MIDDLE TILDE
177ɬ ↔ K;            # LATIN SMALL LETTER L WITH BELT
178ɯ ↔ M;            # LATIN SMALL LETTER TURNED M
179ɱ ↔ F;            # LATIN SMALL LETTER M WITH HOOK
180ɲ ↔ J;            # LATIN SMALL LETTER N WITH LEFT HOOK
181ɵ ↔ 8;            # LATIN SMALL LETTER BARRED O
182ɶ ↔ '&';          # LATIN LETTER SMALL CAPITAL OE
183ɾ ↔ 4;            # LATIN SMALL LETTER R WITH FISHHOOK
184ʁ ↔ R;            # LATIN LETTER SMALL CAPITAL INVERTED R
185ʃ ↔ S;            # LATIN SMALL LETTER ESH
186ʉ ↔ '}';          # LATIN SMALL LETTER U BAR
187ʊ ↔ U;            # LATIN SMALL LETTER UPSILON
188ʋ ↔ P;            # LATIN SMALL LETTER V WITH HOOK
189ʌ ↔ V;            # LATIN SMALL LETTER TURNED V
190ʍ ↔ W;            # LATIN SMALL LETTER TURNED W
191ʎ ↔ L;            # LATIN SMALL LETTER TURNED Y
192ʏ ↔ Y;            # LATIN LETTER SMALL CAPITAL Y
193ʒ ↔ Z;            # LATIN SMALL LETTER EZH
194ʔ ↔ '?';          # LATIN LETTER GLOTTAL STOP
195ʲ ↔ \';           # MODIFIER LETTER SMALL J
196ˈ ↔ '"';          # MODIFIER LETTER VERTICAL LINE
197ˌ ↔ '%';          # MODIFIER LETTER LOW VERTICAL LINE
198ː ↔ ':';          # MODIFIER LETTER TRIANGULAR COLON
199˞ ↔ '`';          # MODIFIER LETTER RHOTIC HOOK
200\u0303 ↔ '~';     # COMBINING TILDE
201\u0329 ↔ '=';     # COMBINING VERTICAL LINE BELOW
202\u0361 ↔ $t;      # COMBINING DOUBLE INVERTED BREVE
203β ↔ B;            # GREEK SMALL LETTER BETA
204θ ↔ T;            # GREEK SMALL LETTER THETA
205χ ↔ X;            # GREEK SMALL LETTER CHI
206↑ ↔ '^';          # UPWARDS ARROW
207↓ ↔ '!';          # DOWNWARDS ARROW
208# Compatibility rules for variant or obsolete IPA symbols
209g → g;            # LATIN SMALL LETTER G (redundant, for additional clarity)
210ȵ → J;            # LATIN SMALL LETTER N WITH CURL
211ɩ → I;            # LATIN SMALL LETTER IOTA
212ɷ → U;            # LATIN SMALL LETTER CLOSED OMEGA
213ɼ → 'r_r';        # LATIN SMALL LETTER R WITH LONG LEG
214ɿ → 'z=';         # LATIN SMALL LETTER REVERSED R WITH FISHHOOK
215ʅ → 'z`=';        # LATIN SMALL LETTER SQUAT REVERSED ESH
216ʆ → S\';          # LATIN SMALL LETTER ESH WITH CURL
217ʇ → '|\' ;        # LATIN SMALL LETTER TURNED T
218ʓ → Z\';          # LATIN SMALL LETTER EZH WITH CURL
219ʖ → '|\|\';       # LATIN LETTER INVERTED GLOTTAL STOP
220ʗ → '!\';         # LATIN LETTER STRETCHED C
221ʚ → '3\';         # LATIN SMALL LETTER CLOSED OPEN E
222ʠ → 'G\_<_0';  # LATIN SMALL LETTER Q WITH HOOK
223ʣ → d $t z;       # LATIN SMALL LETTER DZ DIGRAPH
224ʤ → d $t Z;       # LATIN SMALL LETTER DEZH DIGRAPH
225ʥ → d $t 'z\';    # LATIN SMALL LETTER DZ DIGRAPH WITH CURL
226ʦ → t $t s;       # LATIN SMALL LETTER TS DIGRAPH
227ʧ → t $t S;       # LATIN SMALL LETTER TESH DIGRAPH
228ʨ → t $t 's\';    # LATIN SMALL LETTER TC DIGRAPH WITH CURL
229˔ → '_r';         # MODIFIER LETTER UP TACK
230˕ → '_o';         # MODIFIER LETTER DOWN TACK
231\u030A → '_0';    # COMBINING RING ABOVE
232φ → 'p\';         # GREEK SMALL LETTER PHI
233ꞎ → 'K`';         # LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
234::NFC(NFD);
235
236