diff options
| author | John J. Camilleri <john@digitalgrammars.com> | 2021-07-07 09:40:41 +0200 |
|---|---|---|
| committer | John J. Camilleri <john@digitalgrammars.com> | 2021-07-07 09:40:41 +0200 |
| commit | f2e52d6f2c2bc90febceebdea0268b40ea37476c (patch) | |
| tree | 710619761319d65c5d997ec008f57f9253eae5dd /src/compiler/GF/Text/Transliterations.hs | |
| parent | a2b23d5897b4c04b50cd222ce8f215e45a3b6e40 (diff) | |
Replace tabs for whitespace in source code
Diffstat (limited to 'src/compiler/GF/Text/Transliterations.hs')
| -rw-r--r-- | src/compiler/GF/Text/Transliterations.hs | 132 |
1 files changed, 65 insertions, 67 deletions
diff --git a/src/compiler/GF/Text/Transliterations.hs b/src/compiler/GF/Text/Transliterations.hs index 9b1b6e151..8dbc02823 100644 --- a/src/compiler/GF/Text/Transliterations.hs +++ b/src/compiler/GF/Text/Transliterations.hs @@ -17,7 +17,7 @@ import qualified Data.Map as Map -- to add a new one: define the Unicode range and the corresponding ASCII strings, -- which may be one or more characters long --- conventions to be followed: +-- conventions to be followed: -- each character is either [letter] or [letter+nonletters] -- when using a sparse range of unicodes, mark missing codes as "-" in transliterations -- characters can be invisible: ignored in translation to unicode @@ -33,7 +33,7 @@ transliterateWithFile name src isFrom = (if isFrom then appTransFromUnicode else appTransToUnicode) (getTransliterationFile name src) transliteration :: String -> Maybe Transliteration -transliteration s = Map.lookup s allTransliterations +transliteration s = Map.lookup s allTransliterations allTransliterations = Map.fromList [ ("amharic",transAmharic), @@ -67,25 +67,25 @@ data Transliteration = Trans { } appTransToUnicode :: Transliteration -> String -> String -appTransToUnicode trans = +appTransToUnicode trans = concat . map (\c -> maybe c (return . toEnum) $ Map.lookup c (trans_to_unicode trans) - ) . - filter (flip notElem (invisible_chars trans)) . + ) . + filter (flip notElem (invisible_chars trans)) . unchar appTransFromUnicode :: Transliteration -> String -> String -appTransFromUnicode trans = +appTransFromUnicode trans = concat . - map (\c -> maybe [toEnum c] id $ + map (\c -> maybe [toEnum c] id $ Map.lookup c (trans_from_unicode trans) - ) . + ) . map fromEnum mkTransliteration :: String -> [String] -> [Int] -> Transliteration -mkTransliteration name ts us = +mkTransliteration name ts us = Trans (Map.fromList (tzip ts us)) (Map.fromList (uzip us ts)) [] name where tzip ts us = [(t,u) | (t,u) <- zip ts us, t /= "-"] @@ -102,7 +102,7 @@ getTransliterationFile name = uncurry (mkTransliteration name) . codes unchar :: String -> [String] unchar s = case s of - c:d:cs + c:d:cs | isAlpha d -> [c] : unchar (d:cs) | isSpace d -> [c]:[d]: unchar cs | otherwise -> let (ds,cs2) = break (\x -> isAlpha x || isSpace x) cs in @@ -122,8 +122,8 @@ transThai = mkTransliteration "Thai" allTrans allCodes where allCodes = [0x0e00 .. 0x0e7f] transDevanagari :: Transliteration -transDevanagari = - (mkTransliteration "Devanagari" +transDevanagari = + (mkTransliteration "Devanagari" allTransUrduHindi allCodes){invisible_chars = ["a"]} where allCodes = [0x0900 .. 0x095f] ++ [0x0966 .. 0x096f] @@ -136,13 +136,13 @@ allTransUrduHindi = words $ "- - - - - - - - q x g. z R R' f - " ++ "N0 N1 N2 N3 N4 N5 N6 N7 N8 N9 " -
+ transUrdu :: Transliteration -transUrdu = +transUrdu = (mkTransliteration "Urdu" allTrans allCodes) where - allCodes = [0x0622 .. 0x062f] ++ [0x0630 .. 0x063a] ++ [0x0641,0x0642] ++ [0x06A9] ++ [0x0644 .. 0x0648] ++ + allCodes = [0x0622 .. 0x062f] ++ [0x0630 .. 0x063a] ++ [0x0641,0x0642] ++ [0x06A9] ++ [0x0644 .. 0x0648] ++ [0x0654,0x0658,0x0679,0x067e,0x0686,0x0688,0x0691,0x0698,0x06af,0x06c1,0x06c3,0x06cc,0x06ba,0x06be,0x06d2] ++ - [0x06f0 .. 0x06f9] ++ [0x061f,0x06D4] + [0x06f0 .. 0x06f9] ++ [0x061f,0x06D4] allTrans = words $ "A - w^ - y^ a b - t C j H K d " ++ -- 0622 - 062f "Z r z s X S Z- t- z- e G " ++ -- 0630 - 063a @@ -151,22 +151,22 @@ transUrdu = "N0 N1 N2 N3 N4 N5 N6 N7 N8 N9 " ++ "? ." transSindhi :: Transliteration -transSindhi = +transSindhi = (mkTransliteration "Sindhi" allTrans allCodes) where allCodes = [0x062e] ++ [0x0627 .. 0x062f] ++ [0x0630 .. 0x063a] ++ [0x0641 .. 0x0648] ++ [0x067a,0x067b,0x067d,0x067e,0x067f] ++ [0x0680 .. 0x068f] ++ [0x0699,0x0918,0x06a6,0x061d,0x06a9,0x06af,0x06b3,0x06bb,0x06be,0x06f6,0x064a,0x06b1, 0x06aa, 0x06fd, 0x06fe] ++ - [0x06f0 .. 0x06f9] ++ [0x061f,0x06D4] + [0x06f0 .. 0x06f9] ++ [0x061f,0x06D4] allTrans = words $ "K a b - t C j H - d " ++ -- 0626 - 062f "Z r z s X S Z- t- z- e G " ++ -- 0630 - 063a "f q - L m n - W " ++ -- 0641 - 0648 "T! B T p T' " ++ -- 067a,067b,067d,067e,067f "B' - - Y' J' - c c' - - d! - d' D - D' " ++ -- 0680 - 068f - "R - F' - k' g G' t' h' e' y c! k A M " ++ -- 0699, 0918, 06a6, 061d, 06a9,06af,06b3,06bb,06be,06f6,06cc,06b1 + "R - F' - k' g G' t' h' e' y c! k A M " ++ -- 0699, 0918, 06a6, 061d, 06a9,06af,06b3,06bb,06be,06f6,06cc,06b1 "N0 N1 N2 N3 N4 N5 N6 N7 N8 N9 " ++ "? ." - + transArabic :: Transliteration transArabic = mkTransliteration "Arabic" allTrans allCodes where @@ -175,8 +175,8 @@ transArabic = mkTransliteration "Arabic" allTrans allCodes where "W r z s C S D T Z c G " ++ -- 0630 - 063a " f q k l m n h w y. y a. u. i. a u " ++ -- 0641 - 064f "i v2 o a: V+ V- i: a+ " ++ -- 0650 - 0657 - "A* q?" -- 0671 (used by AED) - allCodes = [0x0621..0x062f] ++ [0x0630..0x063a] ++ + "A* q?" -- 0671 (used by AED) + allCodes = [0x0621..0x062f] ++ [0x0630..0x063a] ++ [0x0641..0x064f] ++ [0x0650..0x0657] ++ [0x0671,0x061f] @@ -193,16 +193,16 @@ transPersian = (mkTransliteration "Persian/Farsi" allTrans allCodes) " V A: A? w? A- y? A b t. t t- j H K d " ++ -- 0621 - 062f "W r z s C S D T Z c G " ++ -- 0630 - 063a " f q - l m n h v - y. a. u. i. a u " ++ -- 0640 - 064f - "i v2 o a: V+ V- i: a+ " ++ -- 0650 - 0657 + "i v2 o a: V+ V- i: a+ " ++ -- 0650 - 0657 "p c^ J k g y q? Z0" - allCodes = [0x0621..0x062f] ++ [0x0630..0x063a] ++ - [0x0641..0x064f] ++ [0x0650..0x0657] ++ + allCodes = [0x0621..0x062f] ++ [0x0630..0x063a] ++ + [0x0641..0x064f] ++ [0x0650..0x0657] ++ [0x067e,0x0686,0x0698,0x06a9,0x06af,0x06cc,0x061f,0x200c] transNepali :: Transliteration transNepali = mkTransliteration "Nepali" allTrans allCodes where allTrans = words $ - "z+ z= " ++ + "z+ z= " ++ "- V M h: - H A i: I: f F Z - - - e: " ++ "E: - - O W k K g G n: C c j J Y q " ++ "Q x X N t T d D n - p P b B m y " ++ @@ -241,7 +241,7 @@ transGreek = mkTransliteration "modern Greek" allTrans allCodes where "i= A B G D E Z H V I K L M N X O " ++ "P R - S T Y F C Q W I- Y- a' e' h' i' " ++ "y= a b g d e z h v i k l m n x o " ++ - "p r s* s t y f c q w i- y- o' y' w' - " + "p r s* s t y f c q w i- y- o' y' w' - " allCodes = [0x0380 .. 0x03cf] transAncientGreek :: Transliteration @@ -261,32 +261,32 @@ transAncientGreek = mkTransliteration "ancient Greek" allTrans allCodes where "y) y( y)` y(` y)' y(' y)~ y(~ - Y( - Y(` - Y(' - Y(~ " ++ "w) w( w)` w(` w)' w(' w)~ w(~ W) W( W)` W(` W)' W(' W)~ W(~ " ++ "a` a' e` e' h` h' i` i' o` o' y` y' w` w' - - " ++ - "a|) a|( a|)` a|(` a|)' a|(' a|)~ a|(~ - - - - - - - - " ++ -- 1f80- - "h|) h|( h|)` h|(` h|)' h|(' h|)~ h|(~ - - - - - - - - " ++ -- 1f90- - "w|) w|( w|)` w|(` w|)' w|(' w|)~ w|(~ - - - - - - - - " ++ -- 1fa0- + "a|) a|( a|)` a|(` a|)' a|(' a|)~ a|(~ - - - - - - - - " ++ -- 1f80- + "h|) h|( h|)` h|(` h|)' h|(' h|)~ h|(~ - - - - - - - - " ++ -- 1f90- + "w|) w|( w|)` w|(` w|)' w|(' w|)~ w|(~ - - - - - - - - " ++ -- 1fa0- "a. a_ a|` a| a|' - a~ a|~ - - - - - - - - " ++ -- 1fb0- "- - h|` h| h|' - h~ h|~ - - - - - - - - " ++ -- 1fc0- "i. i_ i=` i=' - - i~ i=~ - - - - - - - - " ++ -- 1fd0- - "y. y_ y=` y=' r) r( y~ y=~ - - - - - - - - " ++ -- 1fe0- + "y. y_ y=` y=' r) r( y~ y=~ - - - - - - - - " ++ -- 1fe0- "- - w|` w| w|' - w~ w|~ - - - - - - - - " ++ -- 1ff0- -- HL, Private Use Area Code Points (New Athena Unicode, Cardo, ALPHABETUM, Antioch) -- see: http://apagreekkeys.org/technicalDetails.html -- GreekKeys Support by Donald Mastronarde - "- - - - - - - - - e. o. R) Y) Y)` Y)' Y)~ " ++ -- e1a0-e1af + "- - - - - - - - - e. o. R) Y) Y)` Y)' Y)~ " ++ -- e1a0-e1af "e~ e)~ e(~ e_ e_' e_` e_) e_( e_)` e_(` e_)' e_(' E)~ E(~ E_ E. " ++ -- e1b0-e1bf "o~ o)~ o(~ o_ o_' o_` o_) o_( o_)` o_(` o_)' o_(' O)~ O(~ O_ O. " ++ -- e1c0-e1cf - "a_` - a_~ a_)` a_(` a_)~ a_(~ - a.` a.) a.)` a.(' a.(` - - - " ++ -- eaf0-eaff - "a_' - - - a_) a_( - a_)' - a_(' a.' a.( a.)' - - - " ++ -- eb00-eb0f + "a_` - a_~ a_)` a_(` a_)~ a_(~ - a.` a.) a.)` a.(' a.(` - - - " ++ -- eaf0-eaff + "a_' - - - a_) a_( - a_)' - a_(' a.' a.( a.)' - - - " ++ -- eb00-eb0f "e_)~ e_(~ - - - - - e_~ - - - - - - - - " ++ -- eb20-eb2f - "- - - - - - i_~ - i_` i_' - - i_) i_)' i_( i_(' " ++ -- eb30-eb3f + "- - - - - - i_~ - i_` i_' - - i_) i_)' i_( i_(' " ++ -- eb30-eb3f "i.' i.) i.)' i.( i.` i.)` - i.(' i.(` - - - - - - - " ++ -- eb40-eb4f "- - - - i_)` i_(` - i_)~ i_(~ - o_~ o_)~ o_(~ - - - " ++ -- eb50-eb5f "y_` " ++ -- eb6f "y_~ y_)` - - - y_(` - y_)~ y_(~ - y_' - - y_) y_( y_)' " ++ -- eb70-eb7f "y_(' y.' y.( y.` y.) y.)' - - y.)` y.(' y.(` - - - - - " -- eb80-eb8f - allCodes = -- [0x00B0 .. 0x00Bf] - [0x0380 .. 0x03cf] ++ [0x1f00 .. 0x1fff] - ++ [0xe1a0 .. 0xe1af] + allCodes = -- [0x00B0 .. 0x00Bf] + [0x0380 .. 0x03cf] ++ [0x1f00 .. 0x1fff] + ++ [0xe1a0 .. 0xe1af] ++ [0xe1b0 .. 0xe1bf] ++ [0xe1c0 .. 0xe1cf] ++ [0xeaf0 .. 0xeaff] @@ -297,36 +297,34 @@ transAncientGreek = mkTransliteration "ancient Greek" allTrans allCodes where ++ [0xeb50 .. 0xeb5f] ++ [0xeb6f] ++ [0xeb70 .. 0xeb7f] ++ [0xeb80 .. 0xeb8f] -
-transAmharic :: Transliteration
+ +transAmharic :: Transliteration transAmharic = mkTransliteration "Amharic" allTrans allCodes where -
-allTrans = words $ -
- " h. h- h' h( h) h h? h* l. l- l' l( l) l l? l* "++
- " H. H- H' H( H) H H? H* m. m- m' m( m) m m? m* "++
- " s. s- s' s( s) s s? s* r. r- r' r( r) r r? r* "++
- " - - - - - - - - x. x- x' x( x) x x? x* "++
- " q. q- q' q( q) q q? q* - - - - - - - - "++
- " - - - - - - - - - - - - - - - - "++
- " b. b- b' b( b) b b? b* v. v- v' v( v) v v? v* "++
- " t. t- t' t( t) t t? t* c. c- c' c( c) c c? c* "++
- " X. X- X' X( X) X X? - - - - X* - - - - "++
- " n. n- n' n( n) n n? n* N. N- N' N( N) N N? N* "++
- " a u i A E e o e* k. k- k' k( k) k k? - "++
- " - - - k* - - - - - - - - - - - - "++
- " - - - - - - - - w. w- w' w( w) w w? w* "++
- " - - - - - - - - z. z- z' z( z) z z? z* "++
- " Z. Z- Z' Z( Z) Z Z? Z* y. y- y' y( y) y y? y* "++
- " d. d- d' d( d) d d? d* - - - - - - - - "++
- " j. j- j' j( j) j j? j* g. g- g' g( g) g g? - "++
- " - - - g* - - - - - - - - - - - - "++
- " T. T- T' T( T) T T? T* C. C- C' C( C) C C? C* "++
- " P. P- P' P( P) P P? P* S. S- S' S( S) S S? S* "++
- " - - - - - - - - f. f- f' f( f) f f? f*"++
- " p. p- p' p( p) p p? p*"
-allCodes = [0x1200..0x1357] - + allTrans = words $ + " h. h- h' h( h) h h? h* l. l- l' l( l) l l? l* "++ + " H. H- H' H( H) H H? H* m. m- m' m( m) m m? m* "++ + " s. s- s' s( s) s s? s* r. r- r' r( r) r r? r* "++ + " - - - - - - - - x. x- x' x( x) x x? x* "++ + " q. q- q' q( q) q q? q* - - - - - - - - "++ + " - - - - - - - - - - - - - - - - "++ + " b. b- b' b( b) b b? b* v. v- v' v( v) v v? v* "++ + " t. t- t' t( t) t t? t* c. c- c' c( c) c c? c* "++ + " X. X- X' X( X) X X? - - - - X* - - - - "++ + " n. n- n' n( n) n n? n* N. N- N' N( N) N N? N* "++ + " a u i A E e o e* k. k- k' k( k) k k? - "++ + " - - - k* - - - - - - - - - - - - "++ + " - - - - - - - - w. w- w' w( w) w w? w* "++ + " - - - - - - - - z. z- z' z( z) z z? z* "++ + " Z. Z- Z' Z( Z) Z Z? Z* y. y- y' y( y) y y? y* "++ + " d. d- d' d( d) d d? d* - - - - - - - - "++ + " j. j- j' j( j) j j? j* g. g- g' g( g) g g? - "++ + " - - - g* - - - - - - - - - - - - "++ + " T. T- T' T( T) T T? T* C. C- C' C( C) C C? C* "++ + " P. P- P' P( P) P P? P* S. S- S' S( S) S S? S* "++ + " - - - - - - - - f. f- f' f( f) f f? f*"++ + " p. p- p' p( p) p p? p*" + allCodes = [0x1200..0x1357] + -- by Prasad 31/5/2013 transSanskrit :: Transliteration transSanskrit = (mkTransliteration "Sanskrit" allTrans allCodes) {invisible_chars = ["a"]} where |
