| Index: source/data/translit/und_FONIPA_und_FONXSAMP.txt
|
| diff --git a/source/data/translit/und_FONIPA_und_FONXSAMP.txt b/source/data/translit/und_FONIPA_und_FONXSAMP.txt
|
| new file mode 100644
|
| index 0000000000000000000000000000000000000000..b86314682a2af2cc213bf0b131e2f690f23b4c93
|
| --- /dev/null
|
| +++ b/source/data/translit/und_FONIPA_und_FONXSAMP.txt
|
| @@ -0,0 +1,234 @@
|
| +# © 2016 and later: Unicode, Inc. and others.
|
| +# License & terms of use: http://www.unicode.org/copyright.html#License
|
| +#
|
| +# File: und_FONIPA_und_FONXSAMP.txt
|
| +# Generated from CLDR
|
| +#
|
| +
|
| +# Conversion between IPA and X-SAMPA phonetic transcription.
|
| +#
|
| +# See http://www.phon.ucl.ac.uk/home/sampa/x-sampa.htm for a description of
|
| +# X-SAMPA, an ASCII encoding of the International Phonetic Alphabet.
|
| +#
|
| +# The following obsolete or extended IPA symbols have no X-SAMPA equivalents
|
| +# and remain unaffected by this transform:
|
| +#
|
| +# ʞ LATIN SMALL LETTER TURNED K
|
| +# ʩ LATIN SMALL LETTER FENG DIGRAPH
|
| +# ʪ LATIN SMALL LETTER LS DIGRAPH
|
| +# ʫ LATIN SMALL LETTER LZ DIGRAPH
|
| +# ʬ LATIN LETTER BILABIAL PERCUSSIVE
|
| +# ʭ LATIN LETTER BIDENTAL PERCUSSIVE
|
| +#
|
| +# An IPA tie bar is transformed to an X-SAMPA underscore, per the official
|
| +# X-SAMPA guidelines. This can result in certain ambiguities: For example, the
|
| +# labial-velar nasal (http://en.wikipedia.org/wiki/Labial-velar_nasal) can be
|
| +# either written as [ŋ\u0361m] or [m\u0361ŋ] in IPA. However, neither version can be
|
| +# represented unambiguously in X-SAMPA: IPA [ŋ\u0361m] becomes X-SAMPA [N_m], which
|
| +# is also used to represent a hypothetical laminal (_m) velar nasal, IPA [ŋ\u033B];
|
| +# and IPA [m\u0361ŋ] becomes X-SAMPA [m_N], which can also represent a linguolabial
|
| +# (_N) nasal, IPA [m\u033C], which is more appropriately written [n\u033C]. To avoid
|
| +# unintended ambiguities, it may therefore be advisable to write affricates
|
| +# without tie bars.
|
| +#
|
| +$t = '_'; # X-SAMPA representation of IPA tie bar.
|
| +::NFD(NFC);
|
| +# 5-character X-SAMPA representations
|
| +ʯ ↔ 'z`_w='; # LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
|
| +# Alternative 5-character X-SAMPA representations
|
| +n\u031F\u030A ← 'n_+_0';
|
| +n\u0320\u030A ← 'n_-_0';
|
| +n\u032A\u030A ← 'n_d_0';
|
| +n\u033A\u030A ← 'n_a_0';
|
| +n\u033B\u030A ← 'n_m_0';
|
| +n\u033C\u030A ← 'n_N_0';
|
| +ɻ\u030A ← 'r\`_0';
|
| +# 4-character X-SAMPA representations
|
| +ǁ ↔ '|\|\'; # LATIN LETTER LATERAL CLICK
|
| +ʄ ↔ 'J\_<'; # LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK
|
| +ʛ ↔ 'G\_<'; # LATIN LETTER SMALL CAPITAL G WITH HOOK
|
| +ʮ ↔ 'z_w='; # LATIN SMALL LETTER TURNED H WITH FISHHOOK
|
| +\u1DC4 ↔ '_H_T'; # COMBINING MACRON-ACUTE
|
| +\u1DC5 ↔ '_B_L'; # COMBINING GRAVE-MACRON
|
| +\u1DC8 ↔ '_R_F'; # COMBINING GRAVE-ACUTE-GRAVE
|
| +# Alternative 4-character X-SAMPA representations
|
| +ɭ\u030A ← 'l`_0';
|
| +ɰ\u030A ← 'M\_0';
|
| +ɳ\u030A ← 'n`_0';
|
| +ɽ\u030A ← 'r`_0';
|
| +# 3-character X-SAMPA representations
|
| +ɓ ↔ 'b_<'; # LATIN SMALL LETTER B WITH HOOK
|
| +ɗ ↔ 'd_<'; # LATIN SMALL LETTER D WITH HOOK
|
| +ɠ ↔ 'g_<'; # LATIN SMALL LETTER G WITH HOOK
|
| +ɻ ↔ 'r\`'; # LATIN SMALL LETTER TURNED R WITH HOOK
|
| +↗ ↔ '<R>'; # NORTH EAST ARROW
|
| +↘ ↔ '<F>'; # SOUTH EAST ARROW
|
| +# Alternative 3-character X-SAMPA representations
|
| +j\u030A ← 'j_0';
|
| +ŋ\u030A ← 'N_0';
|
| +ɥ\u030A ← 'H_0';
|
| +ɱ\u030A ← 'F_0';
|
| +ɲ\u030A ← 'J_0';
|
| +# 2-character X-SAMPA representations
|
| +ħ ↔ 'X\'; # LATIN SMALL LETTER H WITH STROKE
|
| +ǀ ↔ '|\'; # LATIN LETTER DENTAL CLICK
|
| +ǂ ↔ '=\'; # LATIN LETTER ALVEOLAR CLICK
|
| +ǃ ↔ '!\'; # LATIN LETTER RETROFLEX CLICK
|
| +ɕ ↔ 's\'; # LATIN SMALL LETTER C WITH CURL
|
| +ɖ ↔ 'd`'; # LATIN SMALL LETTER D WITH TAIL
|
| +ɘ ↔ '@\'; # LATIN SMALL LETTER REVERSED E
|
| +ɚ ↔ '@`'; # LATIN SMALL LETTER SCHWA WITH HOOK
|
| +ɝ ↔ '3`'; # LATIN SMALL LETTER REVERSED OPEN E WITH HOOK
|
| +ɞ ↔ '3\'; # LATIN SMALL LETTER CLOSED REVERSED OPEN E
|
| +ɟ ↔ 'J\'; # LATIN SMALL LETTER DOTLESS J WITH STROKE
|
| +ɢ ↔ 'G\'; # LATIN LETTER SMALL CAPITAL G
|
| +ɦ ↔ 'h\'; # LATIN SMALL LETTER H WITH HOOK
|
| +ɧ ↔ 'x\'; # LATIN SMALL LETTER HENG WITH HOOK
|
| +ɭ ↔ 'l`'; # LATIN SMALL LETTER L WITH RETROFLEX HOOK
|
| +ɮ ↔ 'K\'; # LATIN SMALL LETTER LEZH
|
| +ɰ ↔ 'M\'; # LATIN SMALL LETTER TURNED M WITH LONG LEG
|
| +ɳ ↔ 'n`'; # LATIN SMALL LETTER N WITH RETROFLEX HOOK
|
| +ɴ ↔ 'N\'; # LATIN LETTER SMALL CAPITAL N
|
| +ɸ ↔ 'p\'; # LATIN SMALL LETTER PHI
|
| +ɹ ↔ 'r\'; # LATIN SMALL LETTER TURNED R
|
| +ɺ ↔ 'l\'; # LATIN SMALL LETTER TURNED R WITH LONG LEG
|
| +ɽ ↔ 'r`'; # LATIN SMALL LETTER R WITH TAIL
|
| +ʀ ↔ 'R\'; # LATIN LETTER SMALL CAPITAL R
|
| +ʂ ↔ 's`'; # LATIN SMALL LETTER S WITH HOOK
|
| +ʈ ↔ 't`'; # LATIN SMALL LETTER T WITH RETROFLEX HOOK
|
| +ʐ ↔ 'z`'; # LATIN SMALL LETTER Z WITH RETROFLEX HOOK
|
| +ʑ ↔ 'z\'; # LATIN SMALL LETTER Z WITH CURL
|
| +ʕ ↔ '?\'; # LATIN LETTER PHARYNGEAL VOICED FRICATIVE
|
| +ʘ ↔ 'O\'; # LATIN LETTER BILABIAL CLICK
|
| +ʙ ↔ 'B\'; # LATIN LETTER SMALL CAPITAL B
|
| +ʜ ↔ 'H\'; # LATIN LETTER SMALL CAPITAL H
|
| +ʝ ↔ 'j\'; # LATIN SMALL LETTER J WITH CROSSED-TAIL
|
| +ʟ ↔ 'L\'; # LATIN LETTER SMALL CAPITAL L
|
| +ʡ ↔ '>\'; # LATIN LETTER GLOTTAL STOP WITH STROKE
|
| +ʢ ↔ '<\'; # LATIN LETTER REVERSED GLOTTAL STOP WITH STROKE
|
| +ʰ ↔ '_h'; # MODIFIER LETTER SMALL H
|
| +ʷ ↔ '_w'; # MODIFIER LETTER SMALL W
|
| +ʼ ↔ '_>'; # MODIFIER LETTER APOSTROPHE
|
| +ˆ ↔ '_\'; # MODIFIER LETTER CIRCUMFLEX ACCENT
|
| +ˇ ↔ '_/'; # CARON
|
| +ˑ ↔ ':\'; # MODIFIER LETTER HALF TRIANGULAR COLON
|
| +ˠ ↔ '_G'; # MODIFIER LETTER SMALL GAMMA
|
| +ˡ ↔ '_l'; # MODIFIER LETTER SMALL L
|
| +ˤ ↔ '_?\'; # MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
|
| +\u0300 ↔ '_L'; # COMBINING GRAVE ACCENT
|
| +\u0301 ↔ '_H'; # COMBINING ACUTE ACCENT
|
| +\u0302 ↔ '_F'; # COMBINING CIRCUMFLEX ACCENT
|
| +\u0304 ↔ '_M'; # COMBINING MACRON
|
| +\u0306 ↔ '_X'; # COMBINING BREVE
|
| +\u0308 ↔ '_"'; # COMBINING DIAERESIS
|
| +\u030B ↔ '_T'; # COMBINING DOUBLE ACUTE ACCENT
|
| +\u030C ↔ '_R'; # COMBINING CARON
|
| +\u030F ↔ '_B'; # COMBINING DOUBLE GRAVE ACCENT
|
| +\u0318 ↔ '_A'; # COMBINING LEFT TACK BELOW
|
| +\u0319 ↔ '_q'; # COMBINING RIGHT TACK BELOW
|
| +\u031A ↔ '_}'; # COMBINING LEFT ANGLE ABOVE
|
| +\u031C ↔ '_c'; # COMBINING LEFT HALF RING BELOW
|
| +\u031D ↔ '_r'; # COMBINING UP TACK BELOW
|
| +\u031E ↔ '_o'; # COMBINING DOWN TACK BELOW
|
| +\u031F ↔ '_+'; # COMBINING PLUS SIGN BELOW
|
| +\u0320 ↔ '_-'; # COMBINING MINUS SIGN BELOW
|
| +\u0324 ↔ '_t'; # COMBINING DIAERESIS BELOW
|
| +\u0325 ↔ '_0'; # COMBINING RING BELOW
|
| +\u032A ↔ '_d'; # COMBINING BRIDGE BELOW
|
| +\u032C ↔ '_v'; # COMBINING CARON BELOW
|
| +\u032F ↔ '_^'; # COMBINING INVERTED BREVE BELOW
|
| +\u0330 ↔ '_k'; # COMBINING TILDE BELOW
|
| +\u0334 ↔ '_e'; # COMBINING TILDE OVERLAY
|
| +\u0339 ↔ '_O'; # COMBINING RIGHT HALF RING BELOW
|
| +\u033A ↔ '_a'; # COMBINING INVERTED BRIDGE BELOW
|
| +\u033B ↔ '_m'; # COMBINING SQUARE BELOW
|
| +\u033C ↔ '_N'; # COMBINING SEAGULL BELOW
|
| +\u033D ↔ '_x'; # COMBINING X ABOVE
|
| +ᵻ ↔ 'I\'; # LATIN SMALL CAPITAL LETTER I WITH STROKE
|
| +ᵿ ↔ 'U\'; # LATIN SMALL CAPITAL LETTER U WITH STROKE
|
| +ⁿ ↔ '_n'; # MODIFIER LETTER LATIN SMALL LETTER N
|
| +# Alternative 2-character X-SAMPA representations
|
| +ʋ ← 'v\'; # LATIN SMALL LETTER V WITH HOOK
|
| +ʲ ← '_j'; # MODIFIER LETTER SMALL J
|
| +\u0303 ← '_~'; # COMBINING TILDE
|
| +\u0329 ← '_='; # COMBINING VERTICAL LINE BELOW
|
| +# 1-character X-SAMPA representations
|
| +c\u0327 ↔ C; # LATIN SMALL LETTER C WITH CEDILLA (decomposed)
|
| +æ ↔ '{'; # LATIN SMALL LETTER AE
|
| +ð ↔ D; # LATIN SMALL LETTER ETH
|
| +ø ↔ 2; # LATIN SMALL LETTER O WITH STROKE
|
| +ŋ ↔ N; # LATIN SMALL LETTER ENG
|
| +œ ↔ 9; # LATIN SMALL LIGATURE OE
|
| +ɐ ↔ 6; # LATIN SMALL LETTER TURNED A
|
| +ɑ ↔ A; # LATIN SMALL LETTER ALPHA
|
| +ɒ ↔ Q; # LATIN SMALL LETTER TURNED ALPHA
|
| +ɔ ↔ O; # LATIN SMALL LETTER OPEN O
|
| +ə ↔ '@'; # LATIN SMALL LETTER SCHWA
|
| +ɛ ↔ E; # LATIN SMALL LETTER OPEN E
|
| +ɜ ↔ 3; # LATIN SMALL LETTER REVERSED OPEN E
|
| +ɡ ↔ g; # LATIN SMALL LETTER SCRIPT G
|
| +ɣ ↔ G; # LATIN SMALL LETTER GAMMA
|
| +ɤ ↔ 7; # LATIN SMALL LETTER RAMS HORN
|
| +ɥ ↔ H; # LATIN SMALL LETTER TURNED H
|
| +ɨ ↔ 1; # LATIN SMALL LETTER I WITH STROKE
|
| +ɪ ↔ I; # LATIN LETTER SMALL CAPITAL I
|
| +ɫ ↔ 5; # LATIN SMALL LETTER L WITH MIDDLE TILDE
|
| +ɬ ↔ K; # LATIN SMALL LETTER L WITH BELT
|
| +ɯ ↔ M; # LATIN SMALL LETTER TURNED M
|
| +ɱ ↔ F; # LATIN SMALL LETTER M WITH HOOK
|
| +ɲ ↔ J; # LATIN SMALL LETTER N WITH LEFT HOOK
|
| +ɵ ↔ 8; # LATIN SMALL LETTER BARRED O
|
| +ɶ ↔ '&'; # LATIN LETTER SMALL CAPITAL OE
|
| +ɾ ↔ 4; # LATIN SMALL LETTER R WITH FISHHOOK
|
| +ʁ ↔ R; # LATIN LETTER SMALL CAPITAL INVERTED R
|
| +ʃ ↔ S; # LATIN SMALL LETTER ESH
|
| +ʉ ↔ '}'; # LATIN SMALL LETTER U BAR
|
| +ʊ ↔ U; # LATIN SMALL LETTER UPSILON
|
| +ʋ ↔ P; # LATIN SMALL LETTER V WITH HOOK
|
| +ʌ ↔ V; # LATIN SMALL LETTER TURNED V
|
| +ʍ ↔ W; # LATIN SMALL LETTER TURNED W
|
| +ʎ ↔ L; # LATIN SMALL LETTER TURNED Y
|
| +ʏ ↔ Y; # LATIN LETTER SMALL CAPITAL Y
|
| +ʒ ↔ Z; # LATIN SMALL LETTER EZH
|
| +ʔ ↔ '?'; # LATIN LETTER GLOTTAL STOP
|
| +ʲ ↔ \'; # MODIFIER LETTER SMALL J
|
| +ˈ ↔ '"'; # MODIFIER LETTER VERTICAL LINE
|
| +ˌ ↔ '%'; # MODIFIER LETTER LOW VERTICAL LINE
|
| +ː ↔ ':'; # MODIFIER LETTER TRIANGULAR COLON
|
| +˞ ↔ '`'; # MODIFIER LETTER RHOTIC HOOK
|
| +\u0303 ↔ '~'; # COMBINING TILDE
|
| +\u0329 ↔ '='; # COMBINING VERTICAL LINE BELOW
|
| +\u0361 ↔ $t; # COMBINING DOUBLE INVERTED BREVE
|
| +β ↔ B; # GREEK SMALL LETTER BETA
|
| +θ ↔ T; # GREEK SMALL LETTER THETA
|
| +χ ↔ X; # GREEK SMALL LETTER CHI
|
| +↑ ↔ '^'; # UPWARDS ARROW
|
| +↓ ↔ '!'; # DOWNWARDS ARROW
|
| +# Compatibility rules for variant or obsolete IPA symbols
|
| +g → g; # LATIN SMALL LETTER G (redundant, for additional clarity)
|
| +ȵ → J; # LATIN SMALL LETTER N WITH CURL
|
| +ɩ → I; # LATIN SMALL LETTER IOTA
|
| +ɷ → U; # LATIN SMALL LETTER CLOSED OMEGA
|
| +ɼ → 'r_r'; # LATIN SMALL LETTER R WITH LONG LEG
|
| +ɿ → 'z='; # LATIN SMALL LETTER REVERSED R WITH FISHHOOK
|
| +ʅ → 'z`='; # LATIN SMALL LETTER SQUAT REVERSED ESH
|
| +ʆ → S\'; # LATIN SMALL LETTER ESH WITH CURL
|
| +ʇ → '|\' ; # LATIN SMALL LETTER TURNED T
|
| +ʓ → Z\'; # LATIN SMALL LETTER EZH WITH CURL
|
| +ʖ → '|\|\'; # LATIN LETTER INVERTED GLOTTAL STOP
|
| +ʗ → '!\'; # LATIN LETTER STRETCHED C
|
| +ʚ → '3\'; # LATIN SMALL LETTER CLOSED OPEN E
|
| +ʠ → 'G\_<_0'; # LATIN SMALL LETTER Q WITH HOOK
|
| +ʣ → d $t z; # LATIN SMALL LETTER DZ DIGRAPH
|
| +ʤ → d $t Z; # LATIN SMALL LETTER DEZH DIGRAPH
|
| +ʥ → d $t 'z\'; # LATIN SMALL LETTER DZ DIGRAPH WITH CURL
|
| +ʦ → t $t s; # LATIN SMALL LETTER TS DIGRAPH
|
| +ʧ → t $t S; # LATIN SMALL LETTER TESH DIGRAPH
|
| +ʨ → t $t 's\'; # LATIN SMALL LETTER TC DIGRAPH WITH CURL
|
| +˔ → '_r'; # MODIFIER LETTER UP TACK
|
| +˕ → '_o'; # MODIFIER LETTER DOWN TACK
|
| +\u030A → '_0'; # COMBINING RING ABOVE
|
| +φ → 'p\'; # GREEK SMALL LETTER PHI
|
| +ꞎ → 'K`'; # LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
|
| +::NFC(NFD);
|
| +
|
|
|