diff options
| author | aarne <aarne@cs.chalmers.se> | 2008-06-15 15:55:49 +0000 |
|---|---|---|
| committer | aarne <aarne@cs.chalmers.se> | 2008-06-15 15:55:49 +0000 |
| commit | 72b4ba963971f4a815f434b55a5fea0d82c2d4e3 (patch) | |
| tree | 47a02262f04a5af3fe2eb90ca308685785e70fee | |
| parent | c2bbdc8a162adb6e50c66a681b7df1c8fbed3f1e (diff) | |
converted Hindi to the revised encoding
| -rw-r--r-- | src-3.0/GF/Text/Transliterations.hs | 11 |
1 files changed, 7 insertions, 4 deletions
diff --git a/src-3.0/GF/Text/Transliterations.hs b/src-3.0/GF/Text/Transliterations.hs index 28f653dcf..05e10dc98 100644 --- a/src-3.0/GF/Text/Transliterations.hs +++ b/src-3.0/GF/Text/Transliterations.hs @@ -23,7 +23,8 @@ characterTable = unlines . map prOne . Map.assocs . trans_from_unicode where data Transliteration = Trans { trans_to_unicode :: Map.Map String Int, - trans_from_unicode :: Map.Map Int String + trans_from_unicode :: Map.Map Int String, + invisible_chars :: [String] } appTransToUnicode :: Transliteration -> String -> String @@ -32,6 +33,7 @@ appTransToUnicode trans = map (\c -> maybe c (return . toEnum) $ Map.lookup c (trans_to_unicode trans) ) . + filter (flip notElem (invisible_chars trans)) . unchar appTransFromUnicode :: Transliteration -> String -> String @@ -46,9 +48,10 @@ appTransFromUnicode trans = -- conventions: -- each character is either [letter] or [letter+nonletter] -- when using a sparse range of unicodes, mark missing codes as "-" in transliterations +-- characters can be invisible: ignored in translation to unicode mkTransliteration :: [String] -> [Int] -> Transliteration -mkTransliteration ts us = Trans (Map.fromList (tzip ts us)) (Map.fromList (uzip us ts)) +mkTransliteration ts us = Trans (Map.fromList (tzip ts us)) (Map.fromList (uzip us ts)) [] where tzip ts us = [(t,u) | (t,u) <- zip ts us, t /= "-"] uzip us ts = [(u,t) | (u,t) <- zip us ts, t /= "-"] @@ -75,9 +78,9 @@ transThai = mkTransliteration allTrans allCodes where allCodes = [0x0e00 .. 0x0e7f] transDevanagari :: Transliteration -transDevanagari = mkTransliteration allTrans allCodes where +transDevanagari = (mkTransliteration allTrans allCodes){invisible_chars = ["a"]} where allTrans = words $ - "~ * - - " ++ + "M N - - " ++ "a- A- i- I- u- U- R- - - - e- E- - - o- O- " ++ "k K g G N: c C j J n: t. T. d. D. n. t " ++ "T d D n - p P b B m y r - l - - v " ++ |