tests/Language/FrenchSpec.hs

   1 {-# LANGUAGE OverloadedLists #-}
   2 {-# LANGUAGE OverloadedStrings #-}
   3
   4 module Language.FrenchSpec where
   5
   6 import Data.ByteString.Builder qualified as ByteString.Builder
   7 import Data.Char qualified as Char
   8 import Data.GenValidity.Map ()
   9 import Data.GenValidity.Sequence ()
  10 import Data.GenValidity.Set ()
  11 import Data.GenValidity.Text ()
  12 import Data.List qualified as List
  13 import Data.Map.Strict qualified as Map
  14 import Data.Set qualified as Set
  15 import Data.Text qualified as Text
  16 import Data.Text.Encoding qualified as Text
  17 import Data.Text.Lazy.Encoding qualified as Text.Lazy
  18 import Data.Text.Short qualified as ShortText
  19 import Data.Validity.Map ()
  20 import Data.Validity.Set ()
  21 import Data.Validity.Text ()
  22 import Language
  23 import Language.French qualified as French
  24 import Language.Pronunciation (ExampleLiteral (..), Lexeme (..), Rule (..), RuleLexemes, after, before, begining, ending, meaning, occurence, rule, silent, word)
  25 import Language.Pronunciation qualified as Pron
  26 import Paths_worksheets qualified as Self
  27 import System.Directory qualified as IO
  28 import System.FilePath (joinPath, pathSeparator, (<.>), (</>))
  29 import System.FilePath.Posix qualified as File
  30 import System.IO qualified as IO
  31 import Test.Syd
  32 import Text.Blaze.Html5.Attributes qualified as HA
  33 import Utils.Pronunciation qualified as Pron
  34 import Utils.Tests
  35 import Wiktionary qualified
  36 import Worksheets.Utils.HTML (Html, className, classes, cm, styles, (!))
  37 import Worksheets.Utils.HTML qualified as HTML
  38 import Worksheets.Utils.IPA qualified as IPA
  39 import Worksheets.Utils.Paper qualified as Paper
  40 import Worksheets.Utils.Prelude
  41 import Worksheets.Utils.SQL qualified as SQL
  42 import Prelude (error, even, mod)
  43
  44 {-
  45 instance IsString Rule where
  46   fromString s = rule {ruleLexemes = fromString s}
  47   [ ful "de" := single "də" ["de" & occurence]
  48   , inf "'" := single "" []
  49   , inf "-" := single "" []
  50   , inf "," := single "" []
  51   , inf "?" := single "" []
  52   , inf "!" := single "" []
  53   , inf borderLeftText := single "" []
  54   , inf borderRightText := single "" []
  55
  56   , inf "demi" := single "dəmi" ["demi" & occurence]
  57   , -- , inf "amb" := single "ɑ̃b" ["amb" & occurence, "ulance"]
  58     -- , inf "amp" := single "ɑ̃p" ["amp" & occurence, "oule"]
  59     -- , inf "amph" := single "ɑ̃f" ["amph" & occurence, "ithéâtre"]
  60     -- , inf "an" := multi
  61     --    [ [PronContextBeforeBorder] := LexemePron{lexemePronunciation="ɑ̃", lexemeExample=["pl", "an" & occurence]}
  62     --    , [PronContextBeforeAnyVowel] := LexemePron{lexemePronunciation="an", lexemeExample=["an" & occurence, "imal"]}
  63     --    , [PronContextBeforeAny] := LexemePron{lexemePronunciation="ɑ̃", lexemeExample=["an" & occurence, "tilope"]}
  64     --    ]
  65   , -- , inf "coin" := single "kwɛ̃" ["coin" & occurence, "cer"]
  66
  67   , -- , inf "im"
  68     --    := multi
  69     --      [ [PronContextBeforeBorder] := LexemePron{lexemePronunciation = "", lexemeExample = }
  70     --      , [PronContextBeforeAnyVowel] := LexemePron{lexemePronunciation = "im", lexemeExample = ["im" & occurence, "ortel"]}
  71     --      , [PronContextBeforeAny] := LexemePron{lexemePronunciation = "ɛ̃", lexemeExample = ["im" & occurence, "primer"]}
  72     --      ]
  73   , -- , inf "in" := single "ɛ̃" ["merl", "in" & occurence]
  74     -- , inf "ina" := single "ina" ["ord", "ina" & occurence, "teur"]
  75     -- , inf "ine" := single "in" ["rout", "ine" & occurence]
  76     -- , inf "inent" := single "in" ["dess", "inent" & occurence]
  77     -- , inf "iner" := single "inɛʁ" ["iner" & occurence, "tie"]
  78     -- , inf "inex" := single "inɛgz" ["inex" & occurence, "istant"]
  79     -- , inf "inexp" := single "inɛksp" ["inexp" & occurence, "licable"]
  80     -- , inf "inima" := single "inima" ["inima" & occurence, "ginable"]
  81     -- , inf "inimi" := single "inimi" ["inimi" & occurence, "table"]
  82     -- , inf "inimp" := single "inimp" ["inimp" & occurence, "ortant"]
  83     -- , inf "ininf" := single "inɛ̃" ["ininf" & occurence, "lammation"]
  84     -- , inf "inint" := single "inɛ̃t" ["inint" & occurence, "éressant"]
  85     -- , inf "inn" := single "in" ["inn" & occurence, "ocent"]
  86     -- , inf "ino" := single "ino" ["ino" & occurence, "dore"]
  87     -- , inf "inu" := single "inu" ["inu" & occurence, "tile"]
  88     -- , inf "ix" := single "iks" ["phén", "ix" & occurence]
  89     -- , inf "gine" := single "ʒin" ["an", "gine" & occurence]
  90   -- , inf "era" := single "əʁa" ["s", "era" & occurence]
  91   -- , inf "erai" := single "əʁɛ" ["s", "erai" & occurence]
  92   , inf "era" :=
  93       multi
  94         [ [PronContextBeforeAnyVowel] := LexemePron{lexemePronunciation = "əʁ", lexemeExample = ["mer" & occurence, "ingue"]}
  95         , [PronContextBeforeAny] := LexemePron{lexemePronunciation = "ɛʁ", lexemeExample = ["mer" & occurence, "le"]}
  96         ]
  97   , inf "erin" := single "əʁɛ̃" ["m", "erin" & occurence, "gue"]
  98   , inf "s" :=
  99       multi
 100         [ [PronContextBeforeAnyVowel] := LexemePron{lexemePronunciation = "z", lexemeExample = ["ti", "s" & occurence, "ane"]}
 101         , [PronContextBeforeAnySemiVowel] := LexemePron{lexemePronunciation = "z", lexemeExample = ["pari", "s" & occurence, "ienne"]}
 102         , [PronContextBeforeAny] := LexemePron{lexemePronunciation = "s", lexemeExample = ["s", "a" & occurence]}
 103         ]
 104   , -- , inf "shirt" := single "ʃœʁt" ["shirt" & occurence]
 105   , -- , inf "teau" := single "to" ["teau" & occurence]
 106     -- , inf "ti" := single "ti" ["ti" & occurence, "gre"]
 107   , pre "ukulele" := single "jukulele" ["ukulele" & occurence]
 108   , -- , inf "ui" := single "ɥi" ["ling", "ui" & occurence, "stique"]
 109   , pre "abrivent" := single "abʁivɑ̃" ["abrivent" & occurence]
 110   , pre "adjuvent" := single "adʒyvɑ̃" ["adjuvent" & occurence]
 111   , pre "antivent" := single "ɑ̃tivɑ̃" ["antivent" & occurence]
 112   , pre "auvent" := single "ovɑ̃" ["auvent" & occurence]
 113   , pre "avent" := single "avɑ̃" ["avent" & occurence]
 114   , pre "aï" := single "ai" ["c", "aï" & occurence, "man"]
 115   , pre "bavent" := single "bavɑ̃" ["bavent" & occurence]
 116   , pre "boutavent" := single "butavɑ̃" ["boutavent" & occurence]
 117   , pre "bouvent" := single "buvɑ̃" ["bouvent" & occurence]
 118   , pre "bénévent" := single "benevɑ̃" ["bénévent" & occurence]
 119   , pre "connivent" := single "konivɑ̃" ["connivenr" & occurence]
 120   , pre "contrevent" := single "kɔ̃tʁəvɑ̃" ["contrevent" & occurence]
 121   , pre "convent" := single "kɔ̃vɑ̃" ["convent" & occurence]
 122   , pre "couvent" := single "kuvɑ̃" ["couvent" & occurence]
 123   , pre "couvents" := single "kuvɑ̃" ["couvents" & occurence]
 124   , pre "engoulevent" := single "ɑ̃gulvɑ̃" ["engoulevent" & occurence]
 125   , pre "fervent" := single "fɛʁvɑ̃" ["fervent" & occurence]
 126   , pre "frévent" := single "fʁevɑ̃" ["frévent" & occurence]
 127   , pre "heurtevent" := single "œʁtəvɑ̃" ["heurtevent" & occurence]
 128   , pre "her" := single "ɛʁ" ["her" & occurence, "be"]
 129   , pre "hi" := single "i" ["hi" & occurence, "ver"]
 130   , pre "ill" := single "il" ["ill" & occurence, "étrisme"]
 131   , pre "jack" := single "dʒak" ["jack" & occurence]
 132   , pre "jazz" := single "dʒaz" ["jazz" & occurence]
 133   , pre "montsurvent" := single "mɔ̃syʁvɑ̃" ["montsurvent" & occurence]
 134   , -- , pre "ni" := single "ni" ["ni" & occurence, "ais"]
 135     pre "niai" := single "njɛ" ["niai" & occurence, "s"]
 136   , pre "paravent" := single "paʁavɑ̃" ["paravent" & occurence]
 137   , pre "sen" :=
 138       multi
 139         [ [PronContextBeforeAny] := LexemePron{lexemePronunciation = "sɑ̃", lexemeExample = ["sen" & occurence, "t"]}
 140         , [PronContextBeforeAnyVowel] := LexemePron{lexemePronunciation = "sen", lexemeExample = ["sen" & occurence, "a"]}
 141         -- , inf "a" := LexemePron{lexemePronunciation="sen", lexemeExample=["sen" & occurence, "a"]}
 142         -- , inf "e" := LexemePron{lexemePronunciation="sən", lexemeExample=["sen" & occurence, "estre"]}
 143         -- , inf "i" := LexemePron{lexemePronunciation="sen", lexemeExample=["sen" & occurence, "ior"]}
 144         -- , inf "o" := LexemePron{lexemePronunciation="sen", lexemeExample=["Sen" & occurence, "oueix"]}
 145         -- , inf "u" := LexemePron{lexemePronunciation="sen", lexemeExample=[]}
 146         ]
 147   , pre "souvent" := single "suvɑ̃" ["souvent" & occurence]
 148   , pre "taillevent" := single "tɑjvɑ̃" ["taillevent" & occurence]
 149   , pre "tournevent" := single "tuʁnəvɑ̃" ["tournevent" & occurence]
 150   , pre "vent" := single "vɑ̃" ["vent" & occurence]
 151   , pre "virevent" := single "viʁvɑ̃" ["virevent" & occurence]
 152   , pre "volvent" := single "vɔlvɑ̃" ["volvent" & occurence]
 153   , pre "évent" := single "evɑ̃" ["évent" & occurence]
 154   , pre "œ" := single "œ" ["œ" & occurence, "uf"]
 155   , pre "fier" := single "fjɛʁ" ["fier" & occurence]
 156   , pre "tier" := single "tjɛʁ" ["tier" & occurence]
 157
 158   ]
 159     & list
 160     & foldMap (\(ks, v) -> [(k, v) | k <- ks])
 161     & mapFromListCheckingDuplicates
 162   where
 163     single pron exs =
 164       Map.singleton PronContextBeforeAny $ LexemePron{lexemePronunciation = pron, lexemeExample = exs}
 165     multi l =
 166       l
 167         & list
 168         & foldMap (\(ks, v) -> [(k, v) | k <- ks])
 169         & mapFromListCheckingDuplicates
 170 -}
 171
 172 spec :: HasCallStack => Spec
 173 spec = do
 174   -- Pron.lexerRender $ French.pronunciationDict
 175   describe "pronunciation" do
 176     -- describe "decomposition" do
 177     --  forM_ sentences \sentence ->
 178     --    Pron.pronunciationDecompositionTest French.pronunciationDict $ sentence & Text.unpack
 179     -- describe "result" do
 180     --  forM_ sentences \sentence ->
 181     --    Pron.pronunciationResultTest French.pronunciationDict $ sentence & Text.unpack
 182     describe "parser" do
 183       Pron.pronunciationParserTest pronunciationRules sentences
 184
 185 {-
 186 withoutRetries do
 187   withoutTimeout do
 188     around (\k -> SQL.withConnection "data/langs/français/kaikki/wiktionary=fr.lang=fr.sqlite3" k) do
 189       outDB <- goldenPath "wiktionary" "sqlite"
 190       outDBExists <- IO.doesFileExist outDB & liftIO
 191       when (outDBExists) do
 192         IO.removeFile outDB & liftIO
 193       aroundWith
 194         ( \k wiktConn -> do
 195             SQL.withConnection outDB \outConn ->
 196               k (wiktConn, outConn)
 197         )
 198         do
 199           it "check-against-wiktionary" \(wiktConn, outConn) -> do
 200             SQL.execute_ outConn $ "PRAGMA journal_mode = OFF"
 201             SQL.execute_ outConn $ "PRAGMA synchronous = OFF"
 202             SQL.execute_ outConn $ "CREATE TABLE IF NOT EXISTS results (exprLit TEXT NON NULL, wiktBroad TEXT NON NULL, wiktBroadSegments TEXT NON NULL, synthBroad TEXT NON NULL, synthExplain TEXT NON NULL)"
 203             SQL.execute_ outConn $ "CREATE INDEX results__exprLit ON results (exprLit);"
 204             SQL.execute_ outConn $ "CREATE INDEX results__wiktBroad ON results (wiktBroad);"
 205             SQL.execute_ outConn $ "CREATE INDEX results__synthBroad ON results (synthBroad);"
 206             SQL.execute_ outConn $ "CREATE TABLE IF NOT EXISTS errors (exprId INTEGER NON NULL, exprLit TEXT NON NULL, error TEXT NON NULL)"
 207             SQL.fold
 208               wiktConn
 209               "SELECT id,word,sounds FROM wiktionary WHERE lang_code='fr' LIMIT 1000"
 210               ()
 211               (1 :: Int)
 212               \ !i
 213                 ( exprId :: Int
 214                   , maybeWord :: Maybe Text
 215                   , sounds :: [Wiktionary.Sound]
 216                   ) -> do
 217                   case maybeWord of
 218                     Nothing -> return ()
 219                     Just exprLit ->
 220                       case exprLit & Pron.run French.pronunciationRules of
 221                         Left err -> do
 222                           SQL.execute
 223                             outConn
 224                             "INSERT INTO errors (exprId, exprLit, error) VALUES (?,?,?)"
 225                             ( exprId
 226                             , exprLit
 227                             , err & pShowNoColor
 228                             )
 229                         Right lexemes -> do
 230                           let synthExplain = lexemes <&> (\Pron.Pron{pronInput, pronRule} -> Pron.chars pronInput <> " → " <> show (Pron.rulePron pronRule)) & List.intercalate "; "
 231                           let synthBroad = lexemes & foldMap (Pron.pronRule >>> Pron.rulePron >>> Pron.pronunciationText)
 232                           forM_ sounds \Wiktionary.Sound{..} -> do
 233                             -- IO.hPrint IO.stderr (i, ident::Int, maybeWord)
 234                             case sound_ipa of
 235                               Just (IPA.IPAPhons exprIPAs) -> do
 236                                 forM_ exprIPAs \case
 237                                   IPA.IPAPhonemic exprBroad -> do
 238                                     when (i `mod` 5000 == 0) do
 239                                       IO.hPrint IO.stderr (i, exprLit, exprBroad)
 240                                     SQL.execute
 241                                       outConn
 242                                       "INSERT INTO results(exprLit, wiktBroad, wiktBroadSegments, synthBroad, synthExplain) VALUES(?,?,?,?,?);"
 243                                       ( exprLit
 244                                       , exprBroad & IPA.ipaWordsToText Nothing
 245                                       , exprBroad & IPA.dropSupraSegmentalFeatures & IPA.ipaWordsToText Nothing
 246                                       , synthBroad
 247                                       , synthExplain
 248                                       ) -- & traceShowId
 249                                   IPA.IPAPhonError (_errMsg, _err) -> return ()
 250                                   _ -> return ()
 251                               _ -> return ()
 252                   return (i + 1)
 253             return @IO ()
 254 -}
 255
 256 {-
 257 mangleSupraSegmentalFeatures :: [IPA.Syllable []] -> [[IPA.Segment]]
 258 mangleSupraSegmentalFeatures = \case
 259   [] -> []
 260   IPA.Syllable syl : ts -> syl : mangleSupraSegmentalFeatures ts
 261   IPA.WithSuprasegmentalFeature IPA.Linking syl : ts ->
 262     case mangleSupraSegmentalFeatures ts of
 263       [] -> [dropSupraSegmentalFeatures syl]
 264       x : xs -> (dropSupraSegmentalFeatures syl <> x) : xs
 265   IPA.WithSuprasegmentalFeature _feat syl : xs ->
 266     mangleSupraSegmentalFeatures (syl : xs)
 267 -}
 268
 269 -- cardsHtml "syllabes" $ French.syllablesTable & French.syllablesTableToHTML
 270
 271 sentences :: Map Pron.InputLexemes Pron.Pronunciation
 272 sentences =
 273   [ -- [ ["aiguille"]
 274     -- , ["ail"]
 275     -- , ["aimer"]
 276     -- , ["ampoules"]
 277     -- , ["couvent"{exampleLiteralMeaning = "couver"}]
 278     -- , ["couvent"{exampleLiteralMeaning = "monastère"}]
 279     -- , ["papillon"]
 280     -- ] :: [[]]
 281     pronunciationRules
 282       & Pron.examples
 283   ]
 284     & list
 285     & Map.unionsWith (curry errorShow)
 286 pronunciationRules :: Pron.Table
 287 pronunciationRules =
 288   [ "Escherichia" := Rule{rulePron = ["E" := "ɛ", "sche" := "ʃe", "ri" := "ʁi", "chia" := "ʃja"], ruleExamples = ["Escherichia" := "ɛ.ʃe.ʁi.ʃja"]}
 289   , "Maël" := Rule{rulePron = ["ma" := "ma", "ël" := "ɛl"], ruleExamples = ["Maël" := "ma.ɛl"]}
 290   , "a" := Rule{rulePron = ["a" := "a"], ruleExamples = ["allume" := "a.lym"]}
 291   , "ancrage" := Rule{rulePron = ["an" := "ɑ̃", "crage" := "kʁaʒ"], ruleExamples = ["ancrage" := "ɑ̃.kʁaʒ"]}
 292   , "ancre" := Rule{rulePron = ["ancre" := "ɑ̃kʁ"], ruleExamples = ["ancre" := "ɑ̃kʁ"]}
 293   , "ba" := Rule{rulePron = ["ba" := "ba"], ruleExamples = ["bateau" := "ba.to"]}
 294   , "bain" := Rule{rulePron = ["bain" := "bɛ̃"], ruleExamples = ["bain" := "bɛ̃"]}
 295   , "bile" := Rule{rulePron = ["bile" := "bil"], ruleExamples = ["immobile" := "i.mɔ.bil"]}
 296   , "bo" := Rule{rulePron = ["bo" := "bɔ"], ruleExamples = ["bobo" := "bɔ.bo"]}
 297   , "boi" := Rule{rulePron = ["boi" := "bwa"], ruleExamples = ["boit" := "bwa"]}
 298   , "boué" := Rule{rulePron = ["boué" := "bwe"], ruleExamples = ["boué" := "bwe"]}
 299   , "bri" := Rule{rulePron = ["bri" := "bʁi"], ruleExamples = ["sabrina" := "sa.bʁi.na"]}
 300   , "brou" := Rule{rulePron = ["brou" := "bʁu"], ruleExamples = ["brouette" := "bʁu.ɛt"]}
 301   , "ca" := Rule{rulePron = ["ca" := "ka"], ruleExamples = ["calla" := "ka.la"]}
 302   , "cha" := Rule{rulePron = ["cha" := "ʃa"], ruleExamples = ["chamotté" := "ʃa.mɔ.te"]}
 303   , "cham" <> [LexemeConsonant] := Rule{rulePron = ["cham" := "ʃɑ̃"], ruleExamples = ["champignon" := "ʃɑ̃.pi.ɲɔ̃"]}
 304   , "chon" := Rule{rulePron = ["chon" := "ʃɔ̃"], ruleExamples = ["cochon" := "kɔ.ʃɔ̃"]}
 305   , "chry" := Rule{rulePron = ["chry" := "kʁi"], ruleExamples = ["chrysanthème" := "kʁi.zɑ̃.tɛm"]}
 306   , "ci" := Rule{rulePron = ["ci" := "si"], ruleExamples = ["mucidule" := "my.si.dyl"]}
 307   , "cinthe" := Rule{rulePron = ["cinthe" := "sɛ̃t"], ruleExamples = ["jacinthe" := "ʒa.sɛ̃t"]}
 308   , "co" := Rule{rulePron = ["co" := "kɔ"], ruleExamples = ["cochon" := "kɔ.ʃɔ̃"]}
 309   , "de" := Rule{rulePron = ["de" := "də"], ruleExamples = ["demi" := "də.mi"]}
 310   , "de" := Rule{rulePron = ["de" := "də"], ruleExamples = ["demi" := "də.mi"]}
 311   , "deau" := Rule{rulePron = ["deau" := "do"], ruleExamples = ["rideau" := "ʁi.do"]}
 312   , "dent" := Rule{rulePron = ["dent" := "dɑ̃"], ruleExamples = ["dent" := "dɑ̃"]}
 313   , "deuil" := Rule{rulePron = ["deuil" := "dœj"], ruleExamples = ["deuil" := "dœj"]}
 314   , "do" := Rule{rulePron = ["do" := "dɔ"], ruleExamples = ["doré" := "dɔ.ʁe"]}
 315   , "drai" := Rule{rulePron = ["drai" := "dʁɛ"], ruleExamples = ["draisienne" := "dʁɛ.zjɛn"]}
 316   , "du" := Rule{rulePron = ["du" := "dy"], ruleExamples = ["du" := "dy"]}
 317   , "dule" := Rule{rulePron = ["dule" := "dyl"], ruleExamples = ["mucidule" := "my.si.dyl"]}
 318   , "en" := Rule{rulePron = ["en" := "ɑ̃"], ruleExamples = ["en" := "ɑ̃"]}
 319   , "ette" := Rule{rulePron = ["ette" := "ɛt"], ruleExamples = ["brouette" := "bʁu.ɛt"]}
 320   , "fait" := Rule{rulePron = ["fait" := "fɛ"], ruleExamples = ["fait" := "fɛ"]}
 321   , "feu" := Rule{rulePron = ["feu" := "fø"], ruleExamples = ["feu" := "fø"]}
 322   , "feuille" := Rule{rulePron = ["feuille" := "fœj"], ruleExamples = ["feuille" := "fœj"]}
 323   , "font" := Rule{rulePron = ["font" := "fɔ̃"], ruleExamples = ["font" := "fɔ̃"]}
 324   , "fraise" := Rule{rulePron = ["fraise" := "fʁɛz"], ruleExamples = ["fraise" := "fʁɛz"]}
 325   , "ga" := Rule{rulePron = ["ga" := "ga"], ruleExamples = ["alligator" := "a.li.ga.tɔʁ"]}
 326   , "ge" := Rule{rulePron = ["ge" := "ʒə"], ruleExamples = ["gelée" := "ʒə.le"]}
 327   , "geoir" := Rule{rulePron = ["geoir" := "ʒwaʁ"], ruleExamples = ["plongeoir" := "plɔ̃.ʒwaʁ"]}
 328   , "geur" := Rule{rulePron = ["geur" := "ʒœʁ"], ruleExamples = ["nageur" := "na.ʒœʁ"]}
 329   , "geuse" := Rule{rulePron = ["geuse" := "ʒøz"], ruleExamples = ["nageuse" := "na.ʒøz"]}
 330   , "gi" <> [LexemeConsonant] := Rule{rulePron = ["gi" := "ʒi"], ruleExamples = ["gilet" := "ʒi.lɛ"]}
 331   , "glace" := Rule{rulePron = ["glace" := "glas"], ruleExamples = ["glace" := "glas"]}
 332   , "gnon" := Rule{rulePron = ["gnon" := "ɲɔ̃"], ruleExamples = ["champignon" := "ʃɑ̃.pi.ɲɔ̃"]}
 333   , "gou" := Rule{rulePron = ["gou" := "gu"], ruleExamples = ["gouttière" := "gu.tjɛʁ"]}
 334   , "gue" := Rule{rulePron = ["gue" := "gə"], ruleExamples = ["marguerite" := "maʁ.gə.ʁit"]}
 335   , "gâ" := Rule{rulePron = ["gâ" := "ga"], ruleExamples = ["gâté" := "ga.te"]}
 336   , "gée" := Rule{rulePron = ["gée" := "ʒe"], ruleExamples = ["orangée" := "ɔ.ʁɑ̃.ʒe"]}
 337   , "hi" := Rule{rulePron = ["hi" := "i"], ruleExamples = ["hippopotame" := "i.pɔ.pɔ.tam"]}
 338   , "ppo" := Rule{rulePron = ["ppo" := "pɔ"], ruleExamples = ["hippopotame" := "i.pɔ.pɔ.tam"]}
 339   , "tame" := Rule{rulePron = ["tame" := "tam"], ruleExamples = ["hippopotame" := "i.pɔ.pɔ.tam"]}
 340   , "ho" := Rule{rulePron = ["ho" := "o"], ruleExamples = ["homo" := "o.mo"]}
 341   , "hêtre" := Rule{rulePron = ["hêtre" := "ɛtʁ"], ruleExamples = ["hêtre" := "ɛtʁ"]}
 342   , "i" := Rule{rulePron = ["i" := "i"], ruleExamples = ["ibis" := "i.bis"]}
 343   , "illet" := Rule{rulePron = ["illet" := "jɛ"], ruleExamples = ["œillet" := "œ.jɛ"]}
 344   , "illo" := Rule{rulePron = ["illo" := "jo"], ruleExamples = ["maillot" := "ma.jo"]}
 345   , "ja" := Rule{rulePron = ["ja" := "ʒa"], ruleExamples = ["jacinthe" := "ʒa.sɛ̃t"]}
 346   , "jas" := Rule{rulePron = ["jas" := "ʒas"], ruleExamples = ["jasmin" := "ʒas.mɛ̃"]}
 347   , "je" := Rule{rulePron = ["je" := "ʒə"], ruleExamples = ["jetée" := "ʒə.te"]}
 348   , "jon" <> [LexemeConsonant] := Rule{rulePron = ["jon" := "ʒɔ̃"], ruleExamples = ["jonquille" := "ʒɔ̃.kij"]}
 349   , "ju" := Rule{rulePron = ["ju" := "ʒy"], ruleExamples = ["judo" := "ʒy.do"]}
 350   , "kan" := Rule{rulePron = ["kan" := "kɑ̃"], ruleExamples = ["kangourou" := "kɑ̃.gu.ʁu"]}
 351   , "gou" := Rule{rulePron = ["gou" := "gu"], ruleExamples = ["kangourou" := "kɑ̃.gu.ʁu"]}
 352   , "rou" := Rule{rulePron = ["rou" := "ʁu"], ruleExamples = ["kangourou" := "kɑ̃.gu.ʁu"]}
 353   , "la" := Rule{rulePron = ["la" := "la"], ruleExamples = ["la" := "la"]}
 354   , "langue" := Rule{rulePron = ["langue" := "lɑ̃g"], ruleExamples = ["langue" := "lɑ̃g"]}
 355   , "le" := Rule{rulePron = ["le" := "lə"], ruleExamples = ["le" := "lə"]}
 356   , "li" := Rule{rulePron = ["li" := "li"], ruleExamples = ["pissenlit" := "pi.sɑ̃.li"]}
 357   , "lier" := Rule{rulePron = ["lier" := "lje"], ruleExamples = ["voilier" := "vwa.lje"]}
 358   , "lin" <> [LexemeBorder] := Rule{rulePron = ["lin" := "lɛ̃"], ruleExamples = ["merlin" := "mɛʁ.lɛ̃"]}
 359   , "lion" := Rule{rulePron = ["lion" := "ljɔ̃"], ruleExamples = ["lion" := "ljɔ̃"]}
 360   , "lla" := Rule{rulePron = ["lla" := "la"], ruleExamples = ["calla" := "ka.la"]}
 361   , "lli" := Rule{rulePron = ["lli" := "li"], ruleExamples = ["alligator" := "a.li.ga.tɔʁ"]}
 362   , "llon" := Rule{rulePron = ["llon" := "jɔ̃"], ruleExamples = ["papillon" := "pa.pi.jɔ̃"]}
 363   , "llume" := Rule{rulePron = ["llume" := "lym"], ruleExamples = ["allume" := "a.lym", "allume-feu" := "a.lym.fø"]}
 364   , "lu" := Rule{rulePron = ["lu" := "ly"], ruleExamples = ["révolution" := "ʁe.vɔ.ly.sjɔ̃"]}
 365   , "ly" := Rule{rulePron = ["ly" := "li"], ruleExamples = ["polypore" := "pɔ.li.pɔʁ"]}
 366   , "lé" := Rule{rulePron = ["lé" := "le"], ruleExamples = ["gelé" := "ʒə.le"]}
 367   , "ma" := Rule{rulePron = ["ma" := "ma"], ruleExamples = ["ma" := "ma"]}
 368   , "mar" <> [LexemeConsonant] := Rule{rulePron = ["mar" <> [LexemeConsonant] := "maʁ"], ruleExamples = ["marguerite" := "maʁ.gə.ʁit"]}
 369   , "masque" := Rule{rulePron = ["masque" := "mask"], ruleExamples = ["masque" := "mask"]}
 370   , "mer" <> [LexemeConsonant] := Rule{rulePron = ["mer" <> [LexemeConsonant] := "mɛʁ"], ruleExamples = ["merlin" := "mɛʁ.lɛ̃"]}
 371   , "mi" := Rule{rulePron = ["mi" := "mi"], ruleExamples = ["demi" := "də.mi"]}
 372   , "mmo" := Rule{rulePron = ["mmo" := "mɔ"], ruleExamples = ["immobile" := "i.mɔ.bil"]}
 373   , "mo" := Rule{rulePron = ["mo" := "mɔ"], ruleExamples = ["moto" := "mɔ.to"]}
 374   , "mu" := Rule{rulePron = ["mu" := "my"], ruleExamples = ["mucidule" := "my.si.dyl"]}
 375   , "mène" := Rule{rulePron = ["mène" := "mɛn"], ruleExamples = ["promène" := "pʁɔ.mɛn"]}
 376   , "mènent" := Rule{rulePron = ["mènent" := "mɛn"], ruleExamples = ["promènent" := "pʁɔ.mɛn"]}
 377   , "na" := Rule{rulePron = ["na" := "na"], ruleExamples = ["na" := "na"]}
 378   , "nette" := Rule{rulePron = ["nette" := "nɛt"], ruleExamples = ["lunette" := "ly.nɛt", "lunettes" := "ly.nɛt"]}
 379   , "niche" := Rule{rulePron = ["niche" := "niʃ"], ruleExamples = ["péniche" := "pe.niʃ"]}
 380   , "nnet" := Rule{rulePron = ["nnet" := "nɛ"], ruleExamples = ["bonnet" := "bɔ.nɛ"]}
 381   , "noc" := Rule{rulePron = ["noc" := "nɔk"], ruleExamples = ["nocturne" := "nɔk.tyʁn"]}
 382   , "nou" := Rule{rulePron = ["nou" := "nu"], ruleExamples = ["nourrit" := "nu.ʁi"]}
 383   , "o" := Rule{rulePron = ["o" := "ɔ"], ruleExamples = ["orange" := "ɔ.ʁɑ̃ʒ"]}
 384   , "ou" := Rule{rulePron = ["ou" := "u"], ruleExamples = ["ou" := "u"]}
 385   , "pa" := Rule{rulePron = ["pa" := "pa"], ruleExamples = ["papillon" := "pa.pi.jɔ̃"]}
 386   , "paque" := Rule{rulePron = ["paque" := "pak"], ruleExamples = ["paquebot" := "pak.bo"]}
 387   , "passe" := Rule{rulePron = ["passe" := "pas"], ruleExamples = ["passerelle" := "pas.ʁɛl"]}
 388   , "pi" := Rule{rulePron = ["pi" := "pi"], ruleExamples = ["papillon" := "pa.pi.jɔ̃"]}
 389   , "pi" := Rule{rulePron = ["pi" := "pi"], ruleExamples = ["pissenlit" := "pi.sɑ̃.li"]}
 390   , "plon" := Rule{rulePron = ["plon" := "plɔ̃"], ruleExamples = ["plongeoir" := "plɔ̃.ʒwaʁ"]}
 391   , "pneu" := Rule{rulePron = ["pneu" := "pnø"], ruleExamples = ["pneumatique" := "pnø.ma.tik"]}
 392   , "po" := Rule{rulePron = ["po" := "pɔ"], ruleExamples = ["polypore" := "pɔ.li.pɔʁ"]}
 393   , "pore" := Rule{rulePron = ["pore" := "pɔʁ"], ruleExamples = ["polypore" := "pɔ.li.pɔʁ"]}
 394   , "porte" := Rule{rulePron = ["porte" := "pɔʁt"], ruleExamples = ["porte" := "pɔʁt"]}
 395   , "pro" := Rule{rulePron = ["pro" := "pʁɔ"], ruleExamples = ["promène" := "pʁɔ.mɛn"]}
 396   , "pâ" := Rule{rulePron = ["pâ" := "pa"], ruleExamples = ["pâquerette" := "pa.kʁɛt"]} -- ɑ
 397   , "pé" := Rule{rulePron = ["pé" := "pe"], ruleExamples = ["péniche" := "pe.niʃ"]}
 398   , "que" := Rule{rulePron = ["que" := "kə"], ruleExamples = ["querelle" := "kə.ʁɛl"]}
 399   , "querette" := Rule{rulePron = ["querette" := "kʁɛt"], ruleExamples = ["pâquerette" := "pa.kʁɛt"]}
 400   , "queuse" := Rule{rulePron = ["queuse" := "køz"], ruleExamples = ["visqueuse" := "vis.køz"]}
 401   , "quille" := Rule{rulePron = ["quille" := "kij"], ruleExamples = ["jonquille" := "ʒɔ̃.kij"]}
 402   , "quipe" := Rule{rulePron = ["quipe" := "kip"], ruleExamples = ["équipe" := "e.kip"]}
 403   , "range" := Rule{rulePron = ["range" := "ʁɑ̃ʒ"], ruleExamples = ["orange" := "ɔ.ʁɑ̃ʒ"]}
 404   , "relle" := Rule{rulePron = ["relle" := "ʁɛl"], ruleExamples = ["passerelle" := "pas.ʁɛl"]}
 405   , "ri" := Rule{rulePron = ["ri" := "ʁi"], ruleExamples = ["rideau" := "ʁi.do"]}
 406   , "rine" := Rule{rulePron = ["rine" := "ʁin"], ruleExamples = ["marine" := "ma.ʁin"]}
 407   , "rite" := Rule{rulePron = ["rite" := "ʁit"], ruleExamples = ["marguerite" := "maʁ.gə.ʁit"]}
 408   , "ro" := Rule{rulePron = ["ro" := "rɔ"], ruleExamples = ["robot" := "rɔ.bo"]}
 409   , "rou" := Rule{rulePron = ["rou" := "ʁu"], ruleExamples = ["rouler" := "ʁu.le"]}
 410   , "rouge" := Rule{rulePron = ["rouge" := "ʁuʒ"], ruleExamples = ["rouge" := "ʁuʒ"]}
 411   , "rri" := Rule{rulePron = ["rri" := "ʁi"], ruleExamples = ["nourrit" := "nu.ʁi"]}
 412   , "ré" := Rule{rulePron = ["ré" := "ʁe"], ruleExamples = ["révolution" := "ʁe.vɔ.ly.sjɔ̃"]}
 413   , "sa" := Rule{rulePron = ["sa" := "sa"], ruleExamples = ["satellite" := "sa.te.lit"]}
 414   , "sauve" := Rule{rulePron = ["sauve" := "sov"], ruleExamples = ["sauvetage" := "sov.taʒ"]}
 415   , "scine" := Rule{rulePron = ["scine" := "sin"], ruleExamples = ["piscine" := "pi.sin"]}
 416   , "short" := Rule{rulePron = ["short" := "ʃɔʁt"], ruleExamples = ["short" := "ʃɔʁt"]}
 417   , "ssen" := Rule{rulePron = ["ssen" := "sɑ̃"], ruleExamples = ["pissenlit" := "pi.sɑ̃.li"]}
 418   , "sur" := Rule{rulePron = ["sur" := "syʁ"], ruleExamples = ["sur" := "syʁ"]}
 419   , "ta" := Rule{rulePron = ["ta" := "ta"], ruleExamples = ["ta" := "ta"]}
 420   , "tage" := Rule{rulePron = ["tage" := "taʒ"], ruleExamples = ["sauvetage" := "sov.taʒ"]}
 421   , "tan" <> [LexemeConsonant] := Rule{rulePron = ["tan" <> [LexemeConsonant] := "tɑ̃"], ruleExamples = ["tan" := "tɑ̃"]}
 422   , "tellite" := Rule{rulePron = ["te" <> [LexemeDoubleConsonant] := "te", "llite" := "lit"], ruleExamples = ["satellite" := "sa.te.lit"]}
 423   , "terie" := Rule{rulePron = ["terie" := "tʁi"], ruleExamples = ["poterie" := "pɔ.tʁi"]}
 424   , "thème" := Rule{rulePron = ["thème" := "tɛm"], ruleExamples = ["chrysanthème" := "kʁi.zɑ̃.tɛm"]}
 425   , "tient" := Rule{rulePron = ["tient" := "tjɛ̃"], ruleExamples = ["tient" := "tjɛ̃"]}
 426   , "tier" := Rule{rulePron = ["tier" := "tje"], ruleExamples = ["chalutier" := "ʃa.ly.tje"]}
 427   , "tion" := Rule{rulePron = ["tion" := "sjɔ̃"], ruleExamples = ["révolution" := "ʁe.vɔ.ly.sjɔ̃"]}
 428   , "tique" := Rule{rulePron = ["tique" := "tik"], ruleExamples = ["pneumatique" := "pnø.ma.tik"]}
 429   , "tire" := Rule{rulePron = ["tire" := "tiʁ"], ruleExamples = ["tire" := "tiʁ"]}
 430   , "tor" := Rule{rulePron = ["tor" := "tɔʁ"], ruleExamples = ["alligator" := "a.li.ga.tɔʁ"]}
 431   , "touche" := Rule{rulePron = ["touche" := "tuʃ"], ruleExamples = ["touche" := "tuʃ"]}
 432   , "tris" <> [LexemeConsonant] := Rule{rulePron = ["tris" := "tʁis"], ruleExamples = ["ma" := "ma"]}
 433   , "truffe" := Rule{rulePron = ["truffe" := "tʁyf"], ruleExamples = ["Truffe" := "tʁyf"]}
 434   , "trône" := Rule{rulePron = ["trône" := "tʁon"], ruleExamples = ["trône" := "tʁon"]}
 435   , "ttière" := Rule{rulePron = ["ttière" := "tjɛʁ"], ruleExamples = ["gouttière" := "gu.tjɛʁ"]}
 436   , "tu" := Rule{rulePron = ["tu" := "ty"], ruleExamples = ["tuba" := "ty.ba"]}
 437   , "turne" := Rule{rulePron = ["turne" := "tyʁn"], ruleExamples = ["nocturne" := "nɔk.tyʁn"]}
 438   , "té" := Rule{rulePron = ["té" := "te"], ruleExamples = ["gâté" := "ga.te"]}
 439   , "vache" := Rule{rulePron = ["vache" := "vaʃ"], ruleExamples = ["vache" := "vaʃ"]}
 440   , "vec" := Rule{rulePron = ["vec" := "vɛk"], ruleExamples = ["avec" := "a.vɛk"]}
 441   , "vis" := Rule{rulePron = ["vis" := "vis"], ruleExamples = ["visqueuse" := "vis.køz"]}
 442   , "vo" := Rule{rulePron = ["vo" := "vɔ"], ruleExamples = ["révolution" := "ʁe.vɔ.ly.sjɔ̃"]}
 443   , "voi" := Rule{rulePron = ["voi" := "vwa"], ruleExamples = ["voilier" := "vwa.lje"]}
 444   , "vé" := Rule{rulePron = ["vé" := "ve"], ruleExamples = ["vélo" := "ve.lo"]}
 445   , "yo" := Rule{rulePron = ["yo" := "jo"], ruleExamples = ["Yohan" := "jo.an"]}
 446   , "é" := Rule{rulePron = ["é" := "e"], ruleExamples = ["équipe" := "e.kip"]}
 447   , "œ" := Rule{rulePron = ["œ" := "œ"], ruleExamples = ["œillet" := "œ.jɛ"]}
 448   , [LexemeVowel] <> "san" <> [LexemeConsonant] := Rule{rulePron = [[LexemeVowel] <> "san" <> [LexemeConsonant] := "zɑ̃"], ruleExamples = ["chrysanthème" := "kʁi.zɑ̃.tɛm"]}
 449   , [LexemeVowel] <> "sienne" := Rule{rulePron = [[LexemeVowel] <> "sienne" := "zjɛn"], ruleExamples = ["draisienne" := "dʁɛ.zjɛn"]}
 450   , [LexemeVowel] <> "ya" := Rule{rulePron = [[LexemeVowel] <> "ya" := "ja"], ruleExamples = ["ya" := "ja"]}
 451   , begining "absent" := Rule{rulePron = [begining "ab" := "ab", "sent" := "sɑ̃"], ruleExamples = ["absent" := "ab.sɑ̃", "absents" := "ab.sɑ̃"]}
 452   , begining "exer" := Rule{rulePron = ["e" := "ɛ", "x" := "g.z", "er" := "ɛʁ"], ruleExamples = ["exercice" := "ɛg.zɛʁ.sis"]}
 453   , begining "ya" := Rule{rulePron = [begining "ya" := "ja"], ruleExamples = ["ya" := "ja"]}
 454   , begining "yacht" := Rule{rulePron = ["yacht" := "jɔt"], ruleExamples = ["yacht" := "jɔt"]}
 455   , ending "bis" := Rule{rulePron = [ending "bis" := "bis"], ruleExamples = ["ibis" := "i.bis"]}
 456   , ending "bo" := Rule{rulePron = [ending "bo" := "bo"], ruleExamples = ["bobo" := "bɔ.bo"]}
 457   , ending "bot" := Rule{rulePron = [ending "bot" := "bo"], ruleExamples = ["robot" := "rɔ.bo"]}
 458   , ending "cice" := Rule{rulePron = [ending "cice" := ["sis"]], ruleExamples = ["exercice" := "ɛg.zɛʁ.sis"]}
 459   , ending "cices" := Rule{rulePron = [ending "cices" := ["sis"]], ruleExamples = ["exercices" := "ɛg.zɛʁ.sis"]}
 460   , ending "co" := Rule{rulePron = ["co" := "ko"], ruleExamples = ["cocorico" := "kɔ.kɔ.ʁi.ko"]}
 461   , ending "do" := Rule{rulePron = [ending "do" := "do"], ruleExamples = ["judo" := "ʒy.do"]}
 462   , ending "e" := Rule{rulePron = [ending "e" := [""]], ruleExamples = ["gelée" := "ʒə.le"]}
 463   , ending "han" := Rule{rulePron = [ending "han" := "an"], ruleExamples = ["Yohan" := "jo.an"]}
 464   , ending "ler" := Rule{rulePron = [ending "ler" := "le"], ruleExamples = ["rouler" := "ʁu.le"]}
 465   , ending "let" := Rule{rulePron = [ending "let" := "lɛ"], ruleExamples = ["gilet" := "ʒi.lɛ"]}
 466   , ending "lo" := Rule{rulePron = [ending "lo" := "lo"], ruleExamples = ["vélo" := "ve.lo"]}
 467   , ending "min" := Rule{rulePron = [ending "min" := "mɛ̃"], ruleExamples = ["jasmin" := "ʒas.mɛ̃"]}
 468   , ending "mmo" := Rule{rulePron = [ending "mmo" := "mo"], ruleExamples = ["immo" := "i.mo"]}
 469   , ending "mo" := Rule{rulePron = [ending "mo" := "mo"], ruleExamples = ["homo" := "o.mo"]}
 470   , ending "mot" := Rule{rulePron = [ending "mot" := "mo"], ruleExamples = ["mot" := "mo"]}
 471   , ending "not" := Rule{rulePron = [ending "not" := "no"], ruleExamples = ["canot" := "ka.no"]}
 472   , ending "s" := Rule{rulePron = [ending "s" := [""]], ruleExamples = []}
 473   , ending "t" := Rule{rulePron = [ending "t" := [""]], ruleExamples = []}
 474   , ending "tan" := Rule{rulePron = [ending "tan" := "tɑ̃"], ruleExamples = ["tan" := "tɑ̃"]}
 475   , ending "teau" := Rule{rulePron = [ending "teau" := "to"], ruleExamples = ["bateau" := "ba.to"]}
 476   , ending "to" := Rule{rulePron = [ending "to" := "to"], ruleExamples = ["moto" := "mɔ.to"]}
 477   , ending "ts" := Rule{rulePron = [ending "ts" := [""]], ruleExamples = ["maillots" := "ma.jo"]}
 478   , word "dans" := Rule{rulePron = [word "dans" := "dɑ̃"], ruleExamples = ["dans" := "dɑ̃"]}
 479   , word "et" := Rule{rulePron = [word "et" := "e"], ruleExamples = ["et" := "e"]}
 480   , word "les" := Rule{rulePron = [word "les" := "le"], ruleExamples = ["les" := "le"]}
 481   , word "sous" := Rule{rulePron = [word "sous" := "su"], ruleExamples = ["sous" := "su"]}
 482   , word "un" := Rule{rulePron = [word "un" := "œ̃"], ruleExamples = ["un" := "œ̃"]}
 483   , word "une" := Rule{rulePron = [word "une" := "yn"], ruleExamples = ["une" := "yn"]}
 484   , "coli" := Rule{rulePron = ["co" := "kɔ", "li" := "li"], ruleExamples = ["Escherichia coli" := "ɛ.ʃe.ʁi.ʃja.kɔ.li"]}
 485   ]
 486     & Pron.withCapital
 487     & fromList
 488
 489 {-
 490 , word "mer" :=
 491     Rule
 492       { rulePron =
 493           [ "mer" := ["mɛʁ"]
 494           ]
 495       , ruleExamples = [["mer" & occurence]]
 496       }
 497 , begining "mer" <> [LexemeConsonant] :=
 498     Rule
 499       { rulePron = [ "mer" := ["mɛʁ"] ]
 500       , ruleExamples = [["mer" & occurence, "le"]]
 501       }
 502 , begining "Mer" <> [LexemeConsonant] :=
 503     Rule
 504       { rulePron = [ "Mer" := ["mɛʁ"] ]
 505       , ruleExamples = [["Mer" & occurence, "lin"]]
 506       }
 507 , begining "Mer" <> [LexemeConsonant] :=
 508     Rule
 509       { rulePron = [ "Mer" := ["mɛʁ"] ]
 510       , ruleExamples = [["Mer" & occurence, "lin"]]
 511       }
 512 , "abstrait" :=
 513     Rule
 514       { rulePron =
 515           [ "ab" := ["ap"] -- sic
 516           , "strait" := ["stʁɛ"]
 517           ]
 518       , ruleExamples = [["abstrait" & occurence]]
 519       }
 520 , "ab" :=
 521     Rule
 522       { rulePron = ["ab" := ["ab"]]
 523       , ruleExamples = [["ab" & occurence, "solu"]]
 524       }
 525 , "so" :=
 526     Rule
 527       { rulePron = ["so" := ["sɔ"]]
 528       , ruleExamples = [["ab", "so" & occurence, "lu"]]
 529       }
 530 , "lu" :=
 531     Rule
 532       { rulePron = ["lu" := ["ly"]]
 533       , ruleExamples = [["lu" & occurence], ["abso", "lu" & occurence]]
 534       }
 535 , "a" :=
 536     Rule
 537       { rulePron = ["a" := ["a"]]
 538       , ruleExamples = [["a" & occurence]]
 539       }
 540 , "llume" :=
 541     Rule
 542       { rulePron = ["llume" := ["lym"]]
 543       , ruleExamples = [["a", "llume" & occurence]]
 544       }
 545 , "cice" :=
 546     Rule
 547       { rulePron =
 548           [ "cice" := ["sis"]
 549           ]
 550       , ruleExamples = [["exer", "cice" & occurence]]
 551       }
 552 -}