dobutokO-poetry 0.16.3.0 → 0.17.0.0

raw patch · 3 files changed

+11/−221 lines, 3 filesdep −mmsyn2dep −mmsyn5PVP ok

version bump matches the API change (PVP)

Dependencies removed: mmsyn2, mmsyn5

API changes (from Hackage documentation)

Files

• ChangeLog.md +6/−0
• DobutokO/Poetry/Ukrainian/PrepareText.hs +0/−216
• dobutokO-poetry.cabal +5/−5

@@ -105,3 +105,9 @@  * Sixteenth version revised C. Fixed issues with the isConcatenated and isPreposition functions in the DobutokO.Poetry.Ukranian.PrepareText module. Some documentation  improvements.++## 0.17.0.0 -- 2020-09-07++* Seventeenth version. Moved the module DobutokO.Poetry.Ukranian.PrepareText to another new package phonetic-languages-ukrainian as a module +Languages.Phonetic.Ukrainian.PrepareText and its explicit dependencies mmsyn2 and mmsyn5 (they become, nevertheless, the implicit ones for the dobutokO-poetry+package because they are dependencies for mmsyn6ukr package). This allows to use the moved functionality with less dependencies by some other packages.

@@ -1,216 +0,0 @@--- |--- Module      :  DobutokO.Poetry.Ukrainian.PrepareText--- Copyright   :  (c) OleksandrZhabenko 2020--- License     :  MIT--- Stability   :  Experimental--- Maintainer  :  olexandr543@yahoo.com------ Helps to order the 7 or less Ukrainian words (or their concatenations) --- to obtain (to some extent) suitable for poetry or music text. --- In particular, this module can be used to prepare the Ukrainian text --- by applying the most needed grammar to avoid misunderstanding --- for the produced text. The attention is paid to the prepositions, pronouns, conjunctions --- and particles that are most commonly connected (or not) in a significant way --- with the next text. --- Uses the information from: --- https://uk.wikipedia.org/wiki/%D0%A1%D0%BF%D0%BE%D0%BB%D1%83%D1%87%D0%BD%D0%B8%D0%BA--- and --- https://uk.wikipedia.org/wiki/%D0%A7%D0%B0%D1%81%D1%82%D0%BA%D0%B0_(%D0%BC%D0%BE%D0%B2%D0%BE%D0%B7%D0%BD%D0%B0%D0%B2%D1%81%D1%82%D0%B2%D0%BE)--- --module DobutokO.Poetry.Ukrainian.PrepareText where--import CaseBi (getBFst')-import Data.List.InnToOut.Basic (mapI)-import Data.Char (isAlpha,toLower)-import qualified Data.Vector as V---- | Is used to convert a Ukrainian text into list of 'String' each of which is ready to be --- used by the functions from the other modules in the package. --- It applies minimal grammar links and connections between the most commonly used Ukrainian --- words that \"should\" be paired and not dealt with separately --- to avoid the misinterpretation and preserve maximum of the semantics for the --- \"phonetic\" language on the Ukrainian basis. -prepareText :: String -> [String]-prepareText = splitLines . map (unwords . concatenated2. auxiliary1 . complexWords . words . -        filter (\t -> isAlpha t || isSpC t)) . filter (not . null) . lines--complexWords :: [String] -> [String]-complexWords (xs:ys:zs:ts:xss) =- getBFst' (xs:complexWords (ys:zs:ts:xss),V.fromList [("\1074", -    if ys == "\1084\1110\1088\1091" && zs == "\1090\1086\1075\1086" && -    ts == "\1103\1082" then (xs ++ ys ++ zs ++ ts ++ (concat . take 1 $ xss)):-    complexWords (drop 1 xss) else (xs ++ ys):complexWords (zs:ts:xss)), -    ("\1076\1072\1088\1084\1072", if ys == "\1097\1086" -    then (xs ++ ys ++ zs):complexWords (ts:xss) -    else (xs ++ ys):complexWords (zs:ts:xss)), ("\1076\1083\1103", -    if ys == "\1090\1086\1075\1086" && zs == "\1097\1086\1073" -    then (xs ++ ys ++ zs ++ ts):complexWords xss -    else (xs ++ ys):complexWords (zs:ts:xss)), ("\1079", -      case ys of-        "\1090\1080\1084" -> if zs == "\1097\1086\1073"-          then (xs ++ ys ++ zs):complexWords (ts:xss)-          else (xs ++ ys):complexWords (zs:ts:xss)-        "\1090\1086\1075\1086" -> if zs == "\1095\1072\1089\1091" && ts == "\1103\1082"-          then (xs ++ ys ++ zs ++ "\1081\1072\1082" ++ -          (concat . take 1 $ xss)):complexWords (drop 1 xss)-          else (xs ++ ys):complexWords (zs:ts:xss)-        _ -> (xs ++ ys):complexWords (zs:ts:xss)), ("\1079\1072\1084\1110\1089\1090\1100", -    if ys == "\1090\1086\1075\1086" && zs == "\1097\1086\1073" -    then (xs ++ ys ++ zs ++ ts):complexWords xss-    else (xs ++ ys):complexWords (zs:ts:xss)), ("\1087\1086\1087\1088\1080", -    if ys == "\1090\1077" && zs == "\1097\1086" then (xs ++ ys ++ zs ++ ts):complexWords xss-    else (xs ++ ys):complexWords (zs:ts:xss)), ("\1087\1088\1080", -    if ys == "\1094\1100\1086\1084\1091" then (xs ++ ys ++ zs):complexWords (ts:xss) -    else (xs ++ ys):complexWords (zs:ts:xss)), ("\1087\1110\1089\1083\1103", -    if ys == "\1090\1086\1075\1086" && zs == "\1103\1082" then (xs ++ ys ++ zs ++ ts):complexWords xss-    else (xs ++ ys):complexWords (zs:ts:xss)), ("\1090\1072\1082", if ys == "\1097\1086" -    then (xs ++ ys ++ zs):complexWords (ts:xss) else (xs ++ ys):complexWords (zs:ts:xss)), -    ("\1090\1080\1084\1095\1072\1089\1086\1084", if ys == "\1103\1082" -    then (xs ++ ys ++ zs):complexWords (ts:xss) else (xs ++ ys):complexWords (zs:ts:xss)), -    ("\1090\1086\1084\1091", if ys == "\1103\1082" then (xs ++ "\1081\1072\1082" ++ zs):complexWords (ts:xss) -    else (xs ++ ys):complexWords (zs:ts:xss)), ("\1091", if ys == "\1084\1110\1088\1091" && -    zs == "\1090\1086\1075\1086" && ts == "\1103\1082" then (xs ++ ys ++ zs ++ ts ++ -    (concat . take 1 $ xss)):complexWords (drop 1 xss) else (xs ++ ys):complexWords (zs:ts:xss)), -    ("\1093\1086\1095", if ys == "\1073\1080" then (xs ++ ys ++ zs):complexWords (ts:xss) -    else (xs ++ ys):complexWords (zs:ts:xss)), ("\1093\1086\1095", if ys == "\1073\1080" -    then (xs ++ ys ++ zs):complexWords (ts:xss) else (xs ++ ys):complexWords (zs:ts:xss)), -    ("\1095\1077\1088\1077\1079", if ys == "\1090\1077" && zs == "\1097\1086" -    then (xs ++ ys ++ zs ++ ts):complexWords xss else (xs ++ ys):complexWords (zs:ts:xss))]) xs-complexWords (xs:ys:zs:_) =- getBFst' ([xs,ys,zs],V.fromList [ -    ("\1076\1072\1088\1084\1072", if ys == "\1097\1086" -    then [xs ++ ys ++ zs]-    else [xs ++ ys,zs]), ("\1079", -      case ys of-        "\1090\1080\1084" -> if zs == "\1097\1086\1073"-          then [xs ++ ys ++ zs]-          else [xs ++ ys,zs]-        _ -> [xs ++ ys,zs]), ("\1087\1088\1080", -    if ys == "\1094\1100\1086\1084\1091" then [xs ++ ys ++ zs]-    else [xs ++ ys,zs]), ("\1090\1072\1082", if ys == "\1097\1086" -    then [xs ++ ys ++ zs] else [xs ++ ys,zs]),     ("\1090\1080\1084\1095\1072\1089\1086\1084", -    if ys == "\1103\1082" then [xs ++ ys ++ zs] else [xs ++ ys, zs]), -    ("\1090\1086\1084\1091", if ys == "\1103\1082" then [xs ++ "\1081\1072\1082" ++ zs]-    else [xs ++ ys,zs]), ("\1093\1086\1095", if ys == "\1073\1080" then [xs ++ ys ++ zs] -    else [xs ++ ys,zs]), ("\1093\1086\1095", if ys == "\1073\1080" -    then [xs ++ ys ++ zs] else [xs ++ ys,zs])]) xs-complexWords xss = xss--splitLines :: [String] -> [String]-splitLines xss - | null xss = []- | otherwise = mapI (\xs -> compare (length . words $ xs) 7 == GT) (\xs -> -     (\(t,z) -> [t, z]) . splitAt (length xs `quot` 2) $ xs) xss--auxiliary1 :: [String] -> [String]-auxiliary1 (xs:ys:zs:xss) -  | isConcatenated ys || isPreposition ys = -      auxiliary1 (xs:auxiliary1 ((ys ++ (drop 1 . jottedConv $ ' ':zs)):xss))-  | isConcatenated xs || isPreposition xs = auxiliary1 ((xs ++ (drop 1 . jottedConv $ ' ':ys)):zs:xss)-  | otherwise = xs:auxiliary1 (ys:zs:xss)-auxiliary1 x@(xs:ys:xss) -  | isConcatenated xs || isPreposition xs = auxiliary1 ((xs ++ (drop 1 . jottedConv $ ' ':ys)):xss)-  | otherwise = x-auxiliary1 xss = xss--isPreposition :: String -> Bool-isPreposition ts = -  getBFst' (False, V.fromList . -   zip ["\1030\1079", "\1041\1077\1079", "\1041\1110\1083\1103", "\1042", -    "\1042\1110\1076", "\1044\1083\1103", "\1044\1086", "\1047", -     "\1047\1072", "\1047\1072\1088\1072\1076\1080", "\1047\1110", -      "\1050", "\1050\1086\1083\1086", "\1050\1088\1110\1079\1100", -       "\1050\1088\1110\1084", "\1052\1077\1078", "\1052\1077\1078\1080", -        "\1052\1110\1078", "\1053\1072", "\1053\1072\1076", "\1054", -         "\1054\1073", "\1054\1076", "\1054\1082\1088\1110\1084", -          "\1055\1077\1088\1077\1076", "\1055\1086", "\1055\1088\1080", -           "\1055\1088\1086", "\1055\1088\1086\1090\1080", -            "\1055\1110\1076", "\1055\1110\1089\1083\1103", -             "\1057\1077\1088\1077\1076", "\1057\1077\1088\1077\1076\1080", -              "\1059", "\1063\1077\1088\1077\1079", "\1073\1077\1079", -               "\1073\1110\1083\1103", "\1074", "\1074\1110\1076", -                "\1076\1083\1103", "\1076\1086", "\1079", "\1079\1072", -                 "\1079\1072\1088\1072\1076\1080", "\1079\1110", -                  "\1082", "\1082\1086\1083\1086", "\1082\1088\1110\1079\1100", -                   "\1082\1088\1110\1084", "\1084\1077\1078", "\1084\1077\1078\1080", -                    "\1084\1110\1078", "\1085\1072", "\1085\1072\1076", "\1086", -                     "\1086\1073", "\1086\1076", "\1086\1082\1088\1110\1084", -                      "\1087\1077\1088\1077\1076", "\1087\1086", "\1087\1088\1080", -                       "\1087\1088\1086", "\1087\1088\1086\1090\1080", "\1087\1110\1076", -                        "\1087\1110\1089\1083\1103", "\1089\1077\1088\1077\1076", -                         "\1089\1077\1088\1077\1076\1080", "\1091", -                          "\1095\1077\1088\1077\1079", "\1110\1079"] $ -                           replicate 100 True) ts -{-# INLINE isPreposition #-}---- | Since the dobutokO-poetry version 0.16.3.0 the (||) operator has been changed to the (&&). --- The idea is that these words are the ones that are pronouns and they \"should\" be treated --- (by the author's understanding) as independent words.-isConcatenated :: String -> Bool-isConcatenated ts - | null ts = False- | otherwise = compare (length ts) 2 /= GT && getBFst' (True, V.fromList . -     zip ["\1028", "\1042\1080", "\1052\1080", "\1058\1080", "\1058\1110", -       "\1062\1110", "\1071", "\1074\1080", "\1084\1080", "\1090\1080", "\1090\1110", -         "\1094\1110", "\1103", "\1108"] $ replicate 14 False) ts && -           (head ts `notElem` "\1031\1111")-{-# INLINE isConcatenated #-}--concatenated2 :: [String] -> [String]-concatenated2 (xs:ys:xss) = - getBFst' (xs:concatenated2 (ys:xss), V.fromList . zip ["\1040\1073\1086","\1040\1076\1078\1077",- "\1040\1083\1077","\1040\1085\1110\1078","\1041\1086\1076\1072\1081",- "\1041\1091\1094\1110\1084\1090\1086","\1042\1078\1077","\1042\1080\1082\1083\1102\1095\1085\1086",- "\1042\1083\1072\1089\1085\1077","\1042\1090\1110\1084","\1044\1072\1074\1072\1081",- "\1047\1072\1090\1077","\1050\1086\1083\1080","\1051\1077\1076\1074\1077","\1051\1080\1096\1077",- "\1052\1072\1081\1078\1077","\1052\1086\1074","\1052\1086\1074\1073\1080",- "\1052\1086\1074\1073\1080\1090\1086","\1053\1072\1074\1110\1090\1100",- "\1053\1072\1089\1082\1110\1083\1100\1082\1080","\1053\1072\1095\1077","\1053\1072\1095\1077\1073",- "\1053\1072\1095\1077\1073\1090\1086","\1053\1077\1074\1078\1077","\1053\1077\1084\1086\1074",- "\1053\1077\1084\1086\1074\1073\1080","\1053\1077\1084\1086\1074\1073\1080\1090\1086",- "\1053\1077\1085\1072\1095\1077","\1053\1077\1085\1072\1095\1077\1073\1090\1086",- "\1053\1077\1093\1072\1081","\1053\1090\1078\1077","\1053\1110\1073\1080",- "\1053\1110\1073\1080\1090\1086","\1053\1110\1078","\1054\1090\1086\1078",- "\1055\1088\1080\1090\1086\1084\1091","\1055\1088\1080\1090\1110\1084",- "\1055\1088\1080\1095\1086\1084\1091","\1055\1088\1080\1095\1110\1084",- "\1055\1088\1086\1090\1077","\1057\1072\1084\1077","\1057\1077\1073\1090\1086",- "\1058\1072\1082\1080","\1058\1086\1073\1090\1086","\1058\1110\1083\1100\1082\1080",- "\1061\1072\1081","\1061\1086\1095","\1061\1110\1073\1072","\1062\1077\1073\1090\1086",- "\1065\1086\1073","\1071\1082\1073\1080","\1071\1082\1088\1072\1079","\1071\1082\1097\1086",- "\1072\1073\1086","\1072\1076\1078\1077","\1072\1083\1077","\1072\1085\1110\1078",- "\1073\1086\1076\1072\1081","\1073\1091\1094\1110\1084\1090\1086","\1074\1078\1077",- "\1074\1080\1082\1083\1102\1095\1085\1086","\1074\1083\1072\1089\1085\1077",- "\1074\1090\1110\1084","\1076\1072\1074\1072\1081","\1079\1072\1090\1077","\1082\1086\1083\1080",- "\1083\1077\1076\1074\1077","\1083\1080\1096\1077","\1084\1072\1081\1078\1077","\1084\1086\1074",- "\1084\1086\1074\1073\1080","\1084\1086\1074\1073\1080\1090\1086","\1085\1072\1074\1110\1090\1100",- "\1085\1072\1089\1082\1110\1083\1100\1082\1080","\1085\1072\1095\1077","\1085\1072\1095\1077\1073",- "\1085\1072\1095\1077\1073\1090\1086","\1085\1077\1074\1078\1077","\1085\1077\1084\1086\1074",- "\1085\1077\1084\1086\1074\1073\1080","\1085\1077\1084\1086\1074\1073\1080\1090\1086",- "\1085\1077\1085\1072\1095\1077","\1085\1077\1085\1072\1095\1077\1073\1090\1086",- "\1085\1077\1093\1072\1081","\1085\1110\1073\1080","\1085\1110\1073\1080\1090\1086",- "\1085\1110\1078","\1086\1090\1078\1077","\1086\1090\1086\1078","\1087\1088\1080\1090\1086\1084\1091",- "\1087\1088\1080\1090\1110\1084","\1087\1088\1080\1095\1086\1084\1091","\1087\1088\1080\1095\1110\1084",- "\1087\1088\1086\1090\1077","\1089\1072\1084\1077","\1089\1077\1073\1090\1086","\1090\1072\1082\1080",- "\1090\1086\1073\1090\1086","\1090\1110\1083\1100\1082\1080","\1093\1072\1081","\1093\1086\1095",- "\1093\1110\1073\1072","\1094\1077\1073\1090\1086","\1097\1086\1073","\1103\1082\1073\1080",- "\1103\1082\1088\1072\1079","\1103\1082\1097\1086"] $ replicate 100 ((xs ++ (drop 1 . jottedConv $ ' ':ys)):concatenated2 xss)) xs-concatenated2 xss = xss --isSpC :: Char -> Bool-isSpC x = x == '\'' || x == ' ' || x == '\x2019' || x == '\x02BC' || x == '-'-{-# INLINE isSpC #-}--jottedConv :: String -> String-jottedConv (x:y:xs) -  | isSpC x = x:(getBFst' (jottedConv (y:xs), V.fromList -     [('\1028', '\1049':'\1077':jottedConv xs),-      ('\1031', '\1049':'\1110':jottedConv xs),-      ('\1070', '\1049':'\1091':jottedConv xs),-      ('\1071', '\1049':'\1072':jottedConv xs),-      ('\1102', '\1081':'\1091':jottedConv xs),-      ('\1103', '\1081':'\1072':jottedConv xs),-      ('\1108', '\1081':'\1077':jottedConv xs),-      ('\1111', '\1081':'\1110':jottedConv xs)]) y)-  | otherwise = x:jottedConv (y:xs)-jottedConv xs = xs

@@ -2,7 +2,7 @@ -- documentation, see http://haskell.org/cabal/users-guide/  name:                dobutokO-poetry-version:             0.16.3.0+version:             0.17.0.0 synopsis:            Helps to order the 7 or less Ukrainian words to obtain somewhat suitable for poetry or music text description:         Helps to order the 7 or less Ukrainian words (or their concatenations) to obtain somewhat suitable for poetry or music text. Can be also used as a research instrument with generalized functions. @@ -18,17 +18,17 @@ cabal-version:       >=1.10  library-  exposed-modules:     DobutokO.Poetry.UniquenessPeriodsG, Main, DobutokO.Poetry.General, DobutokO.Poetry.General.Debug, DobutokO.Poetry.Ukrainian.PrepareText+  exposed-modules:     DobutokO.Poetry.UniquenessPeriodsG, Main, DobutokO.Poetry.General, DobutokO.Poetry.General.Debug   -- other-modules:   other-extensions:    CPP-  build-depends:       base >=4.7 && <4.15, vector >=0.11 && <0.14, mmsyn3 >=0.1.5 && <1, mmsyn7s >=0.8 && <1, mmsyn6ukr >=0.8 && <1, uniqueness-periods >=0.2 && <1, dobutokO-poetry-general >=0.1 && <1, mmsyn2 >=0.1.8 && <1, mmsyn5 >=0.4.4 && <1+  build-depends:       base >=4.7 && <4.15, vector >=0.11 && <0.14, mmsyn3 >=0.1.5 && <1, mmsyn7s >=0.8 && <1, mmsyn6ukr >=0.8 && <1, uniqueness-periods >=0.2 && <1, dobutokO-poetry-general >=0.1 && <1   -- hs-source-dirs:   default-language:    Haskell2010  executable dobutokO-poetry   main-is:             Main.hs-  other-modules:       DobutokO.Poetry.UniquenessPeriodsG, DobutokO.Poetry.General, DobutokO.Poetry.General.Debug, DobutokO.Poetry.Ukrainian.PrepareText+  other-modules:       DobutokO.Poetry.UniquenessPeriodsG, DobutokO.Poetry.General, DobutokO.Poetry.General.Debug   other-extensions:    CPP-  build-depends:       base >=4.7 && <4.15, vector >=0.11 && <0.14, mmsyn3 >=0.1.5 && <1, mmsyn7s >=0.8 && <1, mmsyn6ukr >=0.8 && <1, uniqueness-periods >=0.2 && <1, dobutokO-poetry-general >=0.1 && <1, mmsyn2 >=0.1.8 && <1, mmsyn5 >=0.4.4 && <1+  build-depends:       base >=4.7 && <4.15, vector >=0.11 && <0.14, mmsyn3 >=0.1.5 && <1, mmsyn7s >=0.8 && <1, mmsyn6ukr >=0.8 && <1, uniqueness-periods >=0.2 && <1, dobutokO-poetry-general >=0.1 && <1   -- hs-source-dirs:   default-language:    Haskell2010