diff --git a/README b/README --- a/README +++ b/README @@ -110,7 +110,36 @@ It is possible to pass the flags also too [cabal-install]. +### Installing with ICU support +Sorting Unicode strings containing non ASCII characters is not +supported by the standard Haskell libraries and requires the +installation of the ICU libraries, available here: + + + http://site.icu-project.org/ + + +It is then necessary to install the Haskell bindings to these +libraries. These bindings are available here: + + + http://hackage.haskell.org/package/text-icu + + +You then need to configure the citeproc-hs package with the +appropriate cabal flag: + + + runhaskell Setup.lhs configure -funicode_collation + + +and then build as usual. + +It is possible to pass the flags also too [cabal-install]. In this +case the installation of the ICU libraries is the only prerequisite. + + Using citeproc-hs with Pandoc ----------------------------- @@ -225,7 +254,7 @@ [citeproc-hs] at the present time. Specifically the [display] attribute has not been implemented yet. -The [citeproc-hs]-0.3.5 release passes 504 out of 693 tests of the +The [citeproc-hs]-0.3.9 release passes 586 out of 757 tests of the [citeproc-test] suite. The test-suite has been developed along with [citeproc-js], and the failure of some of those tests is not meaningful for [citeproc-hs]. diff --git a/citeproc-hs.cabal b/citeproc-hs.cabal --- a/citeproc-hs.cabal +++ b/citeproc-hs.cabal @@ -1,5 +1,5 @@ name: citeproc-hs -version: 0.3.8 +version: 0.3.9 homepage: http://gorgias.mine.nu/repos/citeproc-hs/ synopsis: A Citation Style Language implementation in Haskell @@ -40,6 +40,7 @@ locales/locales-fr-CA.xml locales/locales-fr-FR.xml locales/locales-he-IL.xml + locales/locales-hr-HR.xml locales/locales-hu-HU.xml locales/locales-is-IS.xml locales/locales-it-IT.xml @@ -47,6 +48,7 @@ locales/locales-km-KH.xml locales/locales-ko-KR.xml locales/locales-lt-LT.xml + locales/locales-lv-LV.xml locales/locales-mn-MN.xml locales/locales-nb-NO.xml locales/locales-nl-NL.xml @@ -86,6 +88,10 @@ description: Embed locale files into the library (needed for windows packaging) default: False +flag unicode_collation + description: Use Haskell bindings to the International Components for Unicode (ICU) libraries + default: False + library exposed-modules: Text.CSL Text.CSL.Eval @@ -111,7 +117,7 @@ ghc-prof-options: -prof -auto-all hs-source-dirs: src build-depends: containers, directory, mtl, json, utf8-string, - bytestring, filepath, pandoc-types >= 1.8 && < 1.11 + bytestring, filepath, pandoc-types >= 1.8 && < 1.13 if flag(bibutils) build-depends: hs-bibutils >= 0.3 @@ -135,6 +141,11 @@ build-depends: template-haskell, file-embed extensions: CPP cpp-options: -DEMBED_DATA_FILES + + if flag(unicode_collation) + build-depends: text, text-icu + extensions: CPP + cpp-options: -DUNICODE_COLLATION if impl(ghc >= 6.10) build-depends: base >= 4, syb, parsec, old-locale, time diff --git a/locales/locales-ca-AD.xml b/locales/locales-ca-AD.xml --- a/locales/locales-ca-AD.xml +++ b/locales/locales-ca-AD.xml @@ -22,7 +22,7 @@ anònim anòn. a - available at + disponible a per circa c. @@ -54,8 +54,8 @@ ref. recuperat - scale - version + escala + versió dC @@ -66,7 +66,7 @@ » “ ” - – + - a @@ -203,8 +203,8 @@ editors - illustrator - illustrators + il·lustrador + il·lustradors traductor @@ -218,7 +218,7 @@ dir. - dirs. + dir. ed. @@ -229,8 +229,8 @@ ed. - ill. - ills. + il·lust. + il·lust. trad. @@ -242,13 +242,13 @@ - directed by + dirigit per editat per editat per - illustrated by + il·lustrat per entrevistat per a - by + per traduït per editat i traduït per @@ -257,7 +257,7 @@ dir. ed. ed. - illus. + il·lust. trad. ed. i trad. per @@ -277,13 +277,13 @@ gen. - febr. + feb. març abr. maig juny jul. - ag. + ago. set. oct. nov. diff --git a/locales/locales-en-GB.xml b/locales/locales-en-GB.xml --- a/locales/locales-en-GB.xml +++ b/locales/locales-en-GB.xml @@ -260,11 +260,11 @@ by - dir. - ed. - ed. - illus. - trans. + dir. by + ed. by + ed. by + illus. by + trans. by ed. & trans. by diff --git a/locales/locales-en-US.xml b/locales/locales-en-US.xml --- a/locales/locales-en-US.xml +++ b/locales/locales-en-US.xml @@ -260,11 +260,11 @@ by - dir. - ed. - ed. - illus. - trans. + dir. by + ed. by + ed. by + illus. by + trans. by ed. & trans. by diff --git a/locales/locales-es-ES.xml b/locales/locales-es-ES.xml --- a/locales/locales-es-ES.xml +++ b/locales/locales-es-ES.xml @@ -22,7 +22,7 @@ anónimo anón. en - available at + disponible en de circa c. @@ -54,8 +54,8 @@ refs. recuperado - scale - version + escala + versión d. C. @@ -66,7 +66,7 @@ » “ ” - – + - .ª @@ -192,7 +192,7 @@ director - directors + directores editor @@ -203,8 +203,8 @@ editores - illustrator - illustrators + ilustrador + ilustradores traductor @@ -229,8 +229,8 @@ eds. - ill. - ills. + ilust. + ilusts. trad. @@ -242,13 +242,13 @@ - directed by + dirigido por editado por editado por - illustrated by + ilustrado por entrevistado por a - by + por traducido por editado y traducido por @@ -257,7 +257,7 @@ dir. ed. ed. - illus. + ilust. trad. ed. y trad. diff --git a/locales/locales-fr-CA.xml b/locales/locales-fr-CA.xml --- a/locales/locales-fr-CA.xml +++ b/locales/locales-fr-CA.xml @@ -159,8 +159,14 @@ chap. col. fig. - fᵒ - nᵒ + + fᵒ + fᵒˢ + + + nᵒ + nᵒˢ + l. n. op. diff --git a/locales/locales-fr-FR.xml b/locales/locales-fr-FR.xml --- a/locales/locales-fr-FR.xml +++ b/locales/locales-fr-FR.xml @@ -159,8 +159,14 @@ chap. col. fig. - fᵒ - nᵒ + + fᵒ + fᵒˢ + + + nᵒ + nᵒˢ + l. n. op. diff --git a/locales/locales-hr-HR.xml b/locales/locales-hr-HR.xml new file mode 100644 --- /dev/null +++ b/locales/locales-hr-HR.xml @@ -0,0 +1,304 @@ + + + + This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License + 2012-07-04T23:31:02+00:00 + + + + + + + + + + + + + + pristupljeno + i + i ostali + anonim + anon. + na + pristupačno na + od + circa + c. + citirano + + izdanje + izdanja + + izd. + i ostali + u pripremi + od + ibid. + u + u štampi + internet + intervju + pismo + bez datuma + bez datuma + na internetu + predstavljeno na + + reference + reference + + + ref. + ref. + + preuzeto + skala + verzija + + + AD + BC + + + „ + “ + ‚ + ‘ + – + + + th + st + nd + rd + th + th + th + + + prvi + drugi + treći + četvrti + peti + šesti + sedmi + osmi + deveti + deseti + + + + knjiga + knjige + + + poglavlje + poglavlja + + + kolona + kolone + + + crtež + crteži + + + folija + folije + + + broj + brojevi + + + linija + linije + + + beleška + beleške + + + opus + opera + + + stranica + stranice + + + paragraf + paragrafi + + + deo + delova + + + odeljak + odeljaka + + + sub verbo + sub verbis + + + strofa + strofe + + + tom + tomova + + + + knj + pog + kol + црт + fol + izd + l + n + op + + str. + str. + + par + deo + od + + s.v. + s.vv. + + + s + s + + + tom + tomova + + + + + + ¶¶ + + + § + §§ + + + + + director + directors + + + priređivač + priređivači + + + priređivač + priređivači + + + ilustrator + ilustratori + + + prevodilac + prevodioci + + + priređivač & prevodilac + priređivači & prevodioci + + + + + prir. + prir. + + + prir. + prir. + + + prir. + prir. + + + il. + il. + + + prev. + prev. + + + prir. & prev. + prir. & prev. + + + + directed by + priredio + priredio + ilustrovao + intervjuisao + prima + od + preveo + priredio & preveo by + + + by + dir. + prir. + prir. + ilus. + prev. + prir. & prev. by + + + januar + februar + mart + april + maj + jun + jul + avgust + septembar + oktobar + novembar + decembar + + + jan. + feb. + mart + apr. + maj + jun + jul + avg. + sep. + okt. + nov. + dec. + + + proleće + leto + jesen + zima + + diff --git a/locales/locales-it-IT.xml b/locales/locales-it-IT.xml --- a/locales/locales-it-IT.xml +++ b/locales/locales-it-IT.xml @@ -20,10 +20,10 @@ e e altri anonimo - anon + anon. a available at - by + di circa c. citato @@ -31,7 +31,7 @@ edizione edizioni - ed + ed. et al. futuro da @@ -41,8 +41,8 @@ internet intervista lettera - no date - S.d. + senza data + s.d. in linea presentato al @@ -58,36 +58,30 @@ version - AD - BC + d.C. + a.C. « » - ‘ - ’ + “ + ” – - th - st - nd - rd - th - th - th + ° - first - second - third - fourth - fifth - sixth - seventh - eighth - ninth - tenth + prima + seconda + terza + quarta + quinta + sesta + settima + ottava + nona + decima @@ -156,33 +150,33 @@ - lib - cap - col - fig - fgl - n° + lib. + cap. + col. + fig. + fgl. + n. l. n. - op + op. - pag - pagg + pag. + pagg. - cpv - pt - par + cpv. + pt. + par. s.v. s.vv. - v - vv + v. + vv. - vol - vol + vol. + vol. @@ -217,8 +211,8 @@ traduttori - editor & translator - editors & translators + curatore e traduttore + curatori e tradutori @@ -227,8 +221,8 @@ dirs. - cur - cur + a c. di + a c. di ed. @@ -239,12 +233,12 @@ ills. - trad - trad + trad. + trad. - ed. & tran. - eds. & trans. + a c. di e trad. da + a c. di e trad. da @@ -256,49 +250,49 @@ a by tradotto da - edited & translated by + a cura di e tradotto da - by + di dir. - cur. da + a c. di ed. illus. trad. da - ed. & trans. by + a c. di e trad. da - Gennaio - Febbraio - Marzo - Aprile - Maggio - Giugno - Luglio - Agosto - Settembre - Ottobre - Novembre - Dicembre + gennaio + febbraio + marzo + aprile + maggio + giugno + luglio + agosto + settembre + ottobre + novembre + dicembre - Gen - Feb - Mar - Apr - Mag - Giu - Lug - Ago - Set - Ott - Nov - Dic + gen. + feb. + mar. + apr. + mag. + giu. + lug. + ago. + set. + ott. + nov. + dic. - Spring - Summer - Autumn - Winter + primavera + estate + autunno + inverno diff --git a/locales/locales-lv-LV.xml b/locales/locales-lv-LV.xml new file mode 100644 --- /dev/null +++ b/locales/locales-lv-LV.xml @@ -0,0 +1,353 @@ + + + + + Andris Lupgins + + This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License + 2012-12-27T11:40:58+02:00 + + + + + + + + + + + + + + + + skatīts + m.ē. + un + un citi + anonīms + anon. + + pieejams + p.m.ē. + + apmēram + apm. + citēts + + redakcija + redakcijas + + red. + u.c. + gaidāms + no + turpat + no + presē + internets + intervija + vēstule + bez datuma + b.g. + tiešsaiste + iesniegts + + atsauce + atsauces + + + ats. + ats. + + iegūts + mērogs + versija + + + " + " + " + " + – + + + -ais + -ā + + + pirmais + otrais + trešais + ceturtais + piektais + sestais + septītais + astotais + devītais + desmitais + + pirmā + otrā + trešā + ceturtā + piektā + sestā + septītā + astotā + devītā + desmitā + + + + grāmata + grāmatas + + + nodaļa + nodaļas + + + sleja + slejas + + + ilustrācija + ilustrācijas + + + folio + folio + + + numurs + numuri + + + rinda + rindas + + + piezīme + piezīmes + + + opuss + opusi + + + lappuse + lappuses + + + rindkopa + rindkopas + + + daļa + daļas + + + apakšnodaļa + apakšnodaļas + + + skatīt + skatīt + + + pants + panti + + + sējums + sējumi + + + + grām. + nod. + sl. + il. + fo. + nr. + r. + piez. + op. + + lpp. + lpp. + + rindk. + d. + apakšnod. + + sk. + sk. + + + p. + p. + + + sēj. + sēj. + + + + + + ¶¶ + + + § + §§ + + + + + krājuma redaktors + krājuma redaktori + + + sastādītājs + sastādītāji + + + pamatmateriāla autors + pamatmateriāla autori + + + vadītājs + vadītāji + + + redaktors + redaktors + + + galvenais redaktors + galvenie redaktori + + + redaktors un tulkotājs + redaktors un tulkotājs + + + ilustrators + ilustratori + + + intervētājs + intervētāji + + + saņēmējs + saņēmēji + + + tulkotājs + tulkotāji + + + + + kr. red. + kr. red. + + + sast. + sast. + + + pamatmat. aut. + pamatmat. aut. + + + vad. + vad. + + + red. + red. + + + galv. red. + galv. red. + + + red. un tulk. + red. un tulk. + + + ilustr. + ilustr. + + + interv. + interv. + + + saņ. + saņ. + + + tulk. + tulk. + + + + sastādīja + vadīja + sagatavoja + sagatavoja + sagatavoja un tulkoja + ilustrēja + intervēja + saņēma + tulkoja + + + + sast. + sag. + sag. + ilustr. + tulk. + sag. un tulk. + + + janvārī + februārī + martā + aprīlī + maijā + jūnijā + jūlijā + augustā + septembrī + oktobrī + novembrī + decembrī + + + janv. + febr. + mar. + apr. + mai. + jūn. + jūl. + aug. + sept. + okt. + nov. + dec. + + + pavasaris + vasara + rudens + ziema + + diff --git a/locales/locales-nb-NO.xml b/locales/locales-nb-NO.xml --- a/locales/locales-nb-NO.xml +++ b/locales/locales-nb-NO.xml @@ -2,7 +2,7 @@ This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License - 2012-07-04T23:31:02+00:00 + 2013-03-01T12:20:00+01:00 @@ -22,7 +22,7 @@ anonym anon. på - available at + tilgjengelig på av circa ca. @@ -54,12 +54,12 @@ refr. hentet - scale - version + målestokk + versjon - f.Kr - e.Kr + fvt. + evt. « @@ -191,8 +191,8 @@ - director - directors + regissør + regissører redaktør @@ -203,8 +203,8 @@ redaktører - illustrator - illustrators + illustratør + illustratører oversetter @@ -217,8 +217,8 @@ - dir. - dirs. + regi + regi red. @@ -242,19 +242,19 @@ - directed by + regissert av redigert av redigert av - illustrated by + illustrert av intervjuet av - mottatt av - by + til + av oversatt av redigert & oversatt av av - dir. + regi red. red. illus. diff --git a/locales/locales-nl-NL.xml b/locales/locales-nl-NL.xml --- a/locales/locales-nl-NL.xml +++ b/locales/locales-nl-NL.xml @@ -57,7 +57,7 @@ ref. refs. - verkregen + geraadpleegd schaal versie diff --git a/locales/locales-nn-NO.xml b/locales/locales-nn-NO.xml --- a/locales/locales-nn-NO.xml +++ b/locales/locales-nn-NO.xml @@ -2,7 +2,7 @@ This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License - 2012-07-04T23:31:02+00:00 + 2013-03-01T12:20:00+01:00 @@ -22,7 +22,7 @@ anonym anon. på - available at + tilgjengeleg på av circa ca. @@ -54,12 +54,12 @@ refr. henta - scale - version + målestokk + versjon - f.Kr - e.Kr + fvt. + evt. « @@ -191,8 +191,8 @@ - director - directors + regissør + regissørar redaktør @@ -203,8 +203,8 @@ redaktørar - illustrator - illustrators + illustratør + illustratørar omsetjar @@ -217,8 +217,8 @@ - dir. - dirs. + regi + regi red. @@ -242,19 +242,19 @@ - directed by + regissert av redigert av redigert av - illustrated by + illustrert av intervjua av - motteke av - by + til + av omsett av redigert & omsett av av - dir. + regi red. red. illus. diff --git a/locales/locales-pt-PT.xml b/locales/locales-pt-PT.xml --- a/locales/locales-pt-PT.xml +++ b/locales/locales-pt-PT.xml @@ -22,8 +22,8 @@ anónimo anón em - available at - by + disponível em + por circa c. citado @@ -41,7 +41,7 @@ internet entrevista carta - no date + sem data sem data em linha apresentado na @@ -55,7 +55,7 @@ obtido scale - version + versão AD @@ -78,16 +78,16 @@ th - first - second - third - fourth - fifth - sixth - seventh - eighth - ninth - tenth + primeiro + segundo + terceiro + quarto + quinto + sexto + sétimo + oitavo + nono + décimo @@ -296,9 +296,9 @@ Dez - Spring - Summer - Autumn - Winter + Primavera + Verão + Outono + Inverno diff --git a/locales/locales-ro-RO.xml b/locales/locales-ro-RO.xml --- a/locales/locales-ro-RO.xml +++ b/locales/locales-ro-RO.xml @@ -1,6 +1,10 @@ + + Nicolae Turcan + nturcan@gmail.com + This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License 2012-07-04T23:31:02+00:00 @@ -16,13 +20,13 @@ - data accesării: + data accesării și și alții anonim anon. la - available at + valabil la de circa cca. @@ -54,8 +58,8 @@ ref. preluat în - scale - version + scală + versiunea d.Hr. @@ -66,7 +70,7 @@ ” « » - – + - -lea @@ -193,7 +197,7 @@ director - directors + directori editor @@ -204,8 +208,8 @@ editori - illustrator - illustrators + ilustrator + ilustratori traducător @@ -219,7 +223,7 @@ dir. - dirs. + dir. ed. @@ -230,8 +234,8 @@ ed. - ill. - ills. + ilustr. + ilustr. trad. @@ -243,13 +247,13 @@ - directed by + coordonat de ediție de ediție de - illustrated by + ilustrații de interviu de în - by + de traducere de ediție & traducere de @@ -258,7 +262,7 @@ dir. ed. ed. - illus. + ilustr. trad. ed. & trad. de diff --git a/locales/locales-sv-SE.xml b/locales/locales-sv-SE.xml --- a/locales/locales-sv-SE.xml +++ b/locales/locales-sv-SE.xml @@ -22,10 +22,10 @@ anonym anon vid - available at - by - circa - c. + tillgänglig vid + av + cirka + ca citerad upplaga @@ -41,13 +41,13 @@ internet intervju brev - no date + inget datum nd online presenterad vid - reference - references + referens + referenser ref. @@ -58,8 +58,8 @@ version - AD - BC + e. Kr. + f. Kr. ” @@ -69,25 +69,23 @@ – - th - st - nd - rd - th - th - th + e + a + a + e + e - first - second - third - fourth - fifth - sixth - seventh - eighth - ninth - tenth + första + andra + tredje + fjärde + femte + sjätte + sjunde + åttonde + nionde + tionde @@ -135,7 +133,7 @@ stycken - dek + del delar @@ -209,16 +207,16 @@ editors - illustrator - illustrators + illustratör + illustratörer översättare översättare - editor & translator - editors & translators + redaktör & översättare + redaktörer & översättare @@ -296,9 +294,9 @@ Dec - Spring - Summer - Autumn - Winter + Vår + Sommar + Höst + Vinter diff --git a/src/Text/CSL/Eval.hs b/src/Text/CSL/Eval.hs --- a/src/Text/CSL/Eval.hs +++ b/src/Text/CSL/Eval.hs @@ -24,9 +24,8 @@ import Control.Arrow import Control.Applicative ( (<$>) ) import Control.Monad.State -import Data.Char +import Data.Char ( toLower, isDigit, isLetter ) import Data.List -import qualified Data.Map as M import Data.Maybe import Text.CSL.Eval.Common @@ -36,7 +35,6 @@ import Text.CSL.Output.Plain import Text.CSL.Reference import Text.CSL.Style -import Text.Pandoc.Definition -- | Produce the output with a 'Layout', the 'EvalMode', a 'Bool' -- 'True' if the evaluation happens for disambiguation purposes, the @@ -52,7 +50,7 @@ then [] else [noOutputError] x | title r == citeId cit ++ " not found!" -> [noBibDataError $ cit] - | otherwise -> x + | otherwise -> suppTC x locale = case l of [x] -> x _ -> Locale [] [] [] [] [] @@ -60,9 +58,14 @@ cit = case em of EvalCite c -> c EvalSorting c -> c - EvalBiblio s -> emptyCite { citePosition = s } - initSt = EvalState (mkRefMap r) (Env cit (localeTermMap locale) m + EvalBiblio c -> c + initSt = EvalState (mkRefMap r) (Env cit (localeTerms locale) m (localeDate locale) o [] a) [] em b False [] [] False [] [] [] + suppTC = let getLang = take 2 . map toLower in + case (getLang $ localeLang locale, getLang $ language r) of + (_, "en") -> id + ("en", []) -> id + _ -> proc' rmTitleCase evalSorting :: EvalMode -> [Locale] -> [MacroMap] -> [Option] -> [Sort] -> [Abbrev] -> Reference -> [Sorting] @@ -98,7 +101,7 @@ | Choose i ei e <- el = evalIfThen i ei e | Macro s fm <- el = return . appendOutput fm =<< evalElements =<< getMacro s | Const s fm <- el = return $ rtfParser fm s - | Number s f fm <- el = formatNumber f fm =<< getStringVar s + | Number s f fm <- el = formatNumber f fm s =<< getStringVar s | Variable s f fm d <- el = return . addDelim d =<< concatMapM (getVariable f fm) s | Group fm d l <- el = when' ((/=) [] <$> tryGroup l) $ return . outputList fm d =<< evalElements l @@ -120,7 +123,16 @@ evalElement $ Names rs ns nfm (d' `betterThen` d) [] _ -> evalElement e - tryGroup l = get >>= \s -> evalElements (rmTermConst l) >>= \r -> put s >> return r + tryGroup l = if hasVar l + then get >>= \s -> evalElements (rmTermConst l) >>= \r -> put s >> return r + else return [ONull] + hasVar = not . null . query hasVarQ + hasVarQ e + | Variable {} <- e = [e] + | Date {} <- e = [e] + | Names {} <- e = [e] + | Number {} <- e = [e] + | otherwise = [] rmTermConst [] = [] rmTermConst (e:es) | Term {} <- e = rmTermConst es @@ -129,24 +141,24 @@ ifEmpty p t e = p >>= \r -> if r == [] then t else return (e r) - withNames e n f = modify (\s -> s { authSub = concat e + withNames e n f = modify (\s -> s { authSub = e ++ authSub s , env = (env s) {names = n : names (env s)}}) >> f >>= \r -> - modify (\s -> s { authSub = [] + modify (\s -> s { authSub = filter (not . flip elem e) (authSub s) , env = (env s) {names = tail $ names (env s)}}) >> return r getFirst [] = return [] - getFirst (x:xs) = whenElse ((/=) [] <$> evalElement x) - (consuming $ evalElement x) + getFirst (x:xs) = whenElse ((/=) [] <$> substituteWith x) + (consuming $ substituteWith x) (getFirst xs) - getMacro s = maybe [] id . lookup s <$> gets (macros . env) - getVariable f fm s = case (map toLower s) of + getVariable f fm s = if isTitleVar s || isTitleShortVar s + then consumeVariable s >> formatTitle s f fm else + case (map toLower s) of "year-suffix" -> getStringVar "ref-id" >>= \k -> return . return $ OYearSuf [] k [] fm "page" -> getStringVar "page" >>= formatRange fm - "title" -> formatTitle f fm "locator" -> getLocVar >>= formatRange fm . snd "url" -> getStringVar "url" >>= \k -> if null k then return [] else return [OUrl (k,k) fm] @@ -188,7 +200,9 @@ chkType t = let chk = (==) (formatVariable t) . show . fromMaybe NoType . fromValue in getVar False chk "ref-type" chkNumeric v = do val <- getStringVar v - return (v `elem` numericVars && or (map isDigit val)) + as <- gets (abbrevs . env) + let val' = if getAbbreviation as v val == [] then val else getAbbreviation as v val + return (isNumericString val') chkDate v = getDateVar v >>= return . not . null . filter ((/=) [] . circa) chkPosition s = if s == "near-note" then gets (nearNote . cite . env) @@ -214,42 +228,46 @@ | otherwise = [] where value = if stripPeriods fm then filter (/= '.') else id - getAbbr v = if f /= Short then v else - case lookup "default" as of - Nothing -> v - Just x -> case lookup s x of - Nothing -> v - Just x' -> case M.lookup v x' of - Nothing -> v - Just x'' -> x'' + getAbbr v = if f == Short + then let ab = getAbbreviation as s v in + if null ab then v else ab + else v nameOpts = ("name-as-sort-order","all") : o sortDate = [ DatePart "year" "numeric-leading-zeros" "" emptyFormatting , DatePart "month" "numeric-leading-zeros" "" emptyFormatting , DatePart "day" "numeric-leading-zeros" "" emptyFormatting] -formatTitle :: Form -> Formatting -> State EvalState [Output] -formatTitle f fm - | Short <- f = getIt "title-short" "title" - | otherwise = getIt "title" "title-short" +formatTitle :: String -> Form -> Formatting -> State EvalState [Output] +formatTitle s f fm + | Short <- f + , isTitleVar s = try (getIt $ s ++ "-short") $ getIt s + | isTitleShortVar s = try (getIt s) $ return . rtfParser fm =<< getTitleShort s + | otherwise = getIt s where - getIt x fb = do + try g h = g >>= \r -> if r == [] then h else return r + getIt x = do o <- gets (options . env) a <- gets (abbrevs . env) - r <- getVar [] (getFormattedValue o a f fm x) x - case r of - [] -> getVar [] (getFormattedValue o a f fm x) fb - _ -> return r + getVar [] (getFormattedValue o a f fm x) x -formatNumber :: NumericForm -> Formatting -> String -> State EvalState [Output] -formatNumber f fm s - | or (map isDigit s) = do tm <- gets (terms . env) - return . output fm . format tm . filter isDigit $ s - | otherwise = do return . output fm $ s +formatNumber :: NumericForm -> Formatting -> String -> String -> State EvalState [Output] +formatNumber f fm v n + = gets (abbrevs . env) >>= \as -> + if isNumericString (getAbbr as n) + then gets (terms . env) >>= + return . output fm . flip process (getAbbr as n) + else return . output fm . getAbbr as $ n where + getAbbr as = if getAbbreviation as v n == [] then id else getAbbreviation as v + checkRange' ts = if v == "page" then checkRange ts else id + process ts = checkRange' ts . printNumStr . map (renderNumber ts) . + breakNumericString . words + renderNumber ts x = if isTransNumber x then format ts x else x + format tm = case f of - Ordinal -> ordinal tm - LongOrdinal -> longOrdinal tm - Roman -> if readNum s < 6000 then roman else id + Ordinal -> ordinal tm v + LongOrdinal -> longOrdinal tm v + Roman -> if readNum n < 6000 then roman else id _ -> id roman = foldr (++) [] . reverse . map (uncurry (!!)) . zip romanList . @@ -260,23 +278,66 @@ ,[ "", "m", "mm", "mmm", "mmmm", "mmmmm"] ] + +checkRange :: [CslTerm] -> String -> String +checkRange _ [] = [] +checkRange ts (x:xs) = if x == '-' + then pageRange ts ++ checkRange ts xs + else x : checkRange ts xs + +printNumStr :: [String] -> String +printNumStr [] = [] +printNumStr (x:[]) = x +printNumStr (x:"-":y:xs) = x ++ "-" ++ y ++ printNumStr xs +printNumStr (x:",":y:xs) = x ++ ", " ++ y ++ printNumStr xs +printNumStr (x:xs) + | x == "-" = x ++ printNumStr xs + | otherwise = x ++ " " ++ printNumStr xs + +pageRange :: [CslTerm] -> String +pageRange = maybe "\x2013" termPlural . findTerm "page-range-delimiter" Long + +isNumericString :: String -> Bool +isNumericString [] = False +isNumericString s = null . filter (not . isNumber &&& not . isSpecialChar >>> uncurry (&&)) $ + words s + +isTransNumber, isSpecialChar,isNumber :: String -> Bool +isTransNumber = and . map isDigit +isSpecialChar = and . map (flip elem "&-,") +isNumber = filter (not . isLetter) >>> filter (not . flip elem "&-,") >>> + map isDigit >>> and &&& not . null >>> uncurry (&&) + +breakNumericString :: [String] -> [String] +breakNumericString [] = [] +breakNumericString (x:xs) + | isTransNumber x = x : breakNumericString xs + | otherwise = let (a,b) = break (flip elem "&-,") x + (c,d) = if null b then ("","") else (head' b, tail b) + in filter (/= []) $ a : c : breakNumericString (d : xs) + formatRange :: Formatting -> String -> State EvalState [Output] formatRange _ [] = return [] formatRange fm p = do ops <- gets (options . env) + ts <- gets (terms . env) let opt = getOptionVal "page-range-format" ops - splitRange = break (== '-') >>> trim *** trim . dropWhile (== '-') - pages = map splitRange . split (== ',') $ p - format a b = if b /= [] - then flip Output emptyFormatting [ OStr a emptyFormatting, OPan [Str "\x2013"] - , OStr b emptyFormatting] - else flip Output emptyFormatting [ OStr a emptyFormatting] - result = case opt of - "expanded" -> map (uncurry format . uncurry expandedRange) pages - "chicago" -> map (uncurry format . uncurry chicagoRange ) pages - "minimal" -> map (uncurry format . uncurry minimalRange ) pages - _ -> map (uncurry format ) pages - return [flip OLoc fm $ addDelim ", " result] + pages = tupleRange . breakNumericString . words $ p + + tupleRange [] = [] + tupleRange (x:"-":[] ) = return (x,[]) + tupleRange (x:"-":y:xs) = (x, y) : tupleRange xs + tupleRange (x: xs) = (x,[]) : tupleRange xs + + joinRange (a, []) = a + joinRange (a, b) = a ++ "-" ++ b + + process = case opt of + "expanded" -> checkRange ts . printNumStr . map (joinRange . uncurry expandedRange) + "chicago" -> checkRange ts . printNumStr . map (joinRange . uncurry chicagoRange ) + "minimal" -> checkRange ts . printNumStr . map (joinRange . uncurry minimalRange ) + _ -> checkRange ts . printNumStr . map (joinRange) + return [flip OLoc fm $ [OStr (process pages) emptyFormatting]] expandedRange :: String -> String -> (String, String) expandedRange sa [] = (sa,[]) diff --git a/src/Text/CSL/Eval/Common.hs b/src/Text/CSL/Eval/Common.hs --- a/src/Text/CSL/Eval/Common.hs +++ b/src/Text/CSL/Eval/Common.hs @@ -20,6 +20,7 @@ import Control.Monad.State import Data.Char ( toLower ) import Data.List ( elemIndex ) +import qualified Data.Map as M import Data.Maybe import Text.CSL.Reference @@ -33,7 +34,7 @@ , mode :: EvalMode , disamb :: Bool , consume :: Bool - , authSub :: String + , authSub :: [String] , consumed :: [String] , edtrans :: Bool , etal :: [[Output]] @@ -44,7 +45,7 @@ data Environment = Env { cite :: Cite - , terms :: [TermMap] + , terms :: [CslTerm] , macros :: [MacroMap] , dates :: [Element] , options :: [Option] @@ -55,20 +56,28 @@ data EvalMode = EvalSorting Cite | EvalCite Cite - | EvalBiblio String -- the reference position + | EvalBiblio Cite -- for the reference position deriving ( Show, Eq ) -getCite :: EvalMode -> Cite -getCite (EvalCite c) = c -getCite _ = emptyCite - isSorting :: EvalMode -> Bool isSorting m = case m of EvalSorting _ -> True; _ -> False +-- | With the variable name and the variable value search for an +-- abbreviation or return an empty string. +getAbbreviation :: [Abbrev] -> String -> String -> String +getAbbreviation as s v + = case lookup "default" as of + Nothing -> [] + Just x -> case lookup (if s `elem` numericVars then "number" else s) x of + Nothing -> [] + Just x' -> case M.lookup v x' of + Nothing -> [] + Just x'' -> x'' + -- | If the first parameter is 'True' the plural form will be retrieved. getTerm :: Bool -> Form -> String -> State EvalState String -getTerm b f s = maybe [] g . lookup (s,f') <$> gets (terms . env) -- FIXME: vedere i fallback - where g = if b then snd else fst +getTerm b f s = maybe [] g . findTerm s f' <$> gets (terms . env) -- FIXME: vedere i fallback + where g = if b then termPlural else termSingular f' = case f of NotSet -> Long; _ -> f getStringVar :: String -> State EvalState String @@ -121,10 +130,23 @@ isOptionSet :: String -> [Option] -> Bool isOptionSet s = maybe False (not . null) . lookup s +isTitleVar, isTitleShortVar :: String -> Bool +isTitleVar = flip elem ["title", "container-title", "collection-title"] +isTitleShortVar = flip elem ["title-short", "container-title-short"] + +getTitleShort :: String -> State EvalState String +getTitleShort s = do v <- getStringVar (take (length s - 6) s) + a <- gets (abbrevs . env) + return $ getAbbreviation a (take (length s - 6) s) v + isVarSet :: String -> State EvalState Bool -isVarSet s = if s /= "locator" - then getVar False isValueSet s - else getLocVar >>= return . (/=) "" . snd +isVarSet s + | isTitleShortVar s = do r <- getVar False isValueSet s + if r then return r + else return . not . null =<< getTitleShort s + | otherwise = if s /= "locator" + then getVar False isValueSet s + else getLocVar >>= return . (/=) "" . snd withRefMap :: (ReferenceMap -> a) -> State EvalState a withRefMap f = return . f =<< gets ref @@ -145,10 +167,11 @@ unsetConsume = modify $ \s -> s {consume = False } doConsume = do sl <- gets consumed modify $ \st -> st { ref = remove (ref st) sl } + doRemove s (k,v) = if isValueSet v then [(formatVariable s,Value Empty)] else [(k,v)] remove rm sl | (s:ss) <- sl = case elemIndex (formatVariable s) (map fst rm) of Just i -> let nrm = take i rm ++ - [(formatVariable s,Value Empty)] ++ + doRemove s (rm !! i) ++ drop (i + 1) rm in remove nrm ss Nothing -> remove rm ss diff --git a/src/Text/CSL/Eval/Date.hs b/src/Text/CSL/Eval/Date.hs --- a/src/Text/CSL/Eval/Date.hs +++ b/src/Text/CSL/Eval/Date.hs @@ -74,7 +74,7 @@ [x'] -> return x' _ -> return $ Date [] NoFormDate emptyFormatting [] [] [] -formatDate :: EvalMode -> String -> [TermMap] -> [DatePart] -> [RefDate] -> [Output] +formatDate :: EvalMode -> String -> [CslTerm] -> [DatePart] -> [RefDate] -> [Output] formatDate em k tm dp date | [d] <- date = concatMap (formatDatePart False d) dp | (a:b:_) <- date = return . ODate . concat $ (start a b ++ end a b ++ coda b) @@ -95,21 +95,21 @@ term f t = let f' = if f `elem` ["verb", "short", "verb-short", "symbol"] then read $ toRead f else Long - in maybe [] fst $ lookup (t, f') tm + in maybe [] termPlural $ findTerm t f' tm addZero n = if length n == 1 then '0' : n else n addZeros = reverse . take 5 . flip (++) (repeat '0') . reverse formatDatePart False (RefDate y m e d _ _) (DatePart n f _ fm) | "year" <- n, y /= [] = return $ OYear (formatYear f y) k fm | "month" <- n, m /= [] = output fm (formatMonth f fm m) - | "day" <- n, d /= [] = output fm (formatDay f d) + | "day" <- n, d /= [] = output fm (formatDay f m d) | "month" <- n, m == [] , e /= [] = output fm $ term f ("season-0" ++ e) formatDatePart True (RefDate y m e d _ _) (DatePart n f rd fm) | "year" <- n, y /= [] = OYear (formatYear f y) k (fm {suffix = []}) : formatDelim | "month" <- n, m /= [] = output (fm {suffix = []}) (formatMonth f fm m) ++ formatDelim - | "day" <- n, d /= [] = output (fm {suffix = []}) (formatDay f d) ++ formatDelim + | "day" <- n, d /= [] = output (fm {suffix = []}) (formatDay f m d) ++ formatDelim | "month" <- n, m == [] , e /= [] = output (fm {suffix = []}) (term f $ "season-0" ++ e) ++ formatDelim where @@ -132,34 +132,47 @@ where iy = readNum y formatMonth f fm m - | "short" <- f = getMonth $ period . fst - | "long" <- f = getMonth fst + | "short" <- f = getMonth $ period . termPlural + | "long" <- f = getMonth termPlural | "numeric" <- f = m | otherwise = addZero m where period = if stripPeriods fm then filter (/= '.') else id - getMonth g = maybe m g $ lookup ("month-" ++ addZero m, read $ toRead f) tm - formatDay f d + getMonth g = maybe m g $ findTerm ("month-" ++ addZero m) (read $ toRead f) tm + formatDay f m d | "numeric-leading-zeros" <- f = addZero d - | "ordinal" <- f = ordinal tm d + | "ordinal" <- f = ordinal tm ("month-" ++ addZero m) d | otherwise = d -ordinal :: [TermMap] -> String -> String -ordinal _ [] = [] -ordinal tm s - = case last s of - '1' -> s ++ term "1" - '2' -> s ++ term "2" - '3' -> s ++ term "3" - _ -> s ++ term "4" +ordinal :: [CslTerm] -> String -> String -> String +ordinal _ _ [] = [] +ordinal ts v s + | length s == 1 = let a = termPlural (getWith1 s) in + if a == [] then setOrd (term []) else s ++ a + | length s == 2 = let a = termPlural (getWith2 s) + b = getWith1 [last s] in + if a /= [] + then s ++ a + else if termPlural b == [] || (termMatch b /= [] && termMatch b /= "last-digit") + then setOrd (term []) else setOrd b + | otherwise = let a = getWith2 last2 + b = getWith1 [last s] in + if termPlural a /= [] && termMatch a /= "whole-number" + then setOrd a + else if termPlural b == [] || (termMatch b /= [] && termMatch b /= "last-digit") + then setOrd (term []) else setOrd b where - term t = maybe [] fst $ lookup ("ordinal-0" ++ t, Long) tm + setOrd = (++) s . termPlural + getWith1 = term . (++) "-0" + getWith2 = term . (++) "-" + last2 = reverse . take 2 . reverse $ s + term t = getOrdinal v ("ordinal" ++ t) ts -longOrdinal :: [TermMap] -> String -> String -longOrdinal _ [] = [] -longOrdinal tm s +longOrdinal :: [CslTerm] -> String -> String -> String +longOrdinal _ _ [] = [] +longOrdinal ts v s | num > 10 || - num == 0 = ordinal tm s + num == 0 = ordinal ts v s | otherwise = case last s of '1' -> term "01" '2' -> term "02" @@ -173,8 +186,19 @@ _ -> term "10" where num = readNum s - term t = maybe [] fst $ lookup ("long-ordinal-" ++ t, Long) tm + term t = termPlural $ getOrdinal v ("long-ordinal-" ++ t) ts +getOrdinal :: String -> String -> [CslTerm] -> CslTerm +getOrdinal v s ts + = case findTerm' s Long gender ts of + Just x -> x + Nothing -> case findTerm' s Long Neuter ts of + Just x -> x + Nothing -> newTerm + where + gender = if v `elem` numericVars || "month" `isPrefixOf` v + then maybe Neuter termGender $ findTerm v Long ts + else Neuter parseRefDate :: RefDate -> [RefDate] parseRefDate r@(RefDate _ _ _ _ o c) diff --git a/src/Text/CSL/Eval/Names.hs b/src/Text/CSL/Eval/Names.hs --- a/src/Text/CSL/Eval/Names.hs +++ b/src/Text/CSL/Eval/Names.hs @@ -47,18 +47,14 @@ p <- gets (citePosition . cite . env) ops <- gets (options . env) aus <- gets authSub - r <- if s == "author" && ags /= [] && p == "subsequent" && - isOptionSet "subsequent-author-substitute" ops - then return $ output emptyFormatting $ - getOptionVal "subsequent-author-substitute" ops - else do res <- agents p s ags - st <- get - fb <- agents "subsequent" s ags - put st - if res /= [] - then let role = if aus == "author" then aus ++ "sub" else s - in return . return . OContrib k role res fb =<< gets etal - else return [] + r <- do res <- agents p s ags + st <- get + fb <- agents "subsequent" s ags + put st + if res /= [] + then let role = if aus == ["author"] then concat aus ++ "sub" else s + in return . return . OContrib k role res fb =<< gets etal + else return [] r' <- evalNames skipEdTrans xs nl d num <- gets contNum return $ if r /= [] && r' /= [] @@ -332,8 +328,12 @@ | "page" <- s = checkPlural | "volume" <- s = checkPlural | "ibid" <- s = format' s p - | otherwise = format s p + | otherwise = if isRole s then form (\fm' x -> [OLabel x fm']) id s p else format s p where + isRole = flip elem ["author", "collection-editor", "composer", "container-author" + ,"director", "editor", "editorial-director", "editortranslator" + ,"illustrator", "interviewer", "original-author", "recipient" + ,"reviewed-author", "translator"] checkPlural = when' (isVarSet s) $ do v <- getStringVar s format s ('-' `elem` v) diff --git a/src/Text/CSL/Eval/Output.hs b/src/Text/CSL/Eval/Output.hs --- a/src/Text/CSL/Eval/Output.hs +++ b/src/Text/CSL/Eval/Output.hs @@ -57,12 +57,12 @@ where check x xs | ONull <- x = xs - | otherwise = let text = renderPlainStrict $ formatOutputList [x] - in if d /= [] && text /= [] - then if head d == last text && head d `elem` ".,;:!?" + | otherwise = let text = renderPlainStrict . formatOutputList + in if d /= [] && text [x] /= [] && text xs /= [] + then if head d == last (text [x]) && head d `elem` ".,;:!?" then x : ODel (tail d) : xs else x : ODel d : xs - else x : ODel d : xs + else x : xs noOutputError :: Output noOutputError = OStr "[CSL STYLE ERROR: reference with no printed form.]" emptyFormatting @@ -144,4 +144,4 @@ ] parseQ a b = try $ do q <- string a >> manyTill anyChar (try $ string b >> notFollowedBy letter) - return [Output (rtfParser emptyFormatting q) (emptyFormatting {quotes = True})] + return [Output (rtfParser emptyFormatting q) (emptyFormatting {quotes = ParsedQuote})] diff --git a/src/Text/CSL/Input/MODS.hs b/src/Text/CSL/Input/MODS.hs --- a/src/Text/CSL/Input/MODS.hs +++ b/src/Text/CSL/Input/MODS.hs @@ -41,12 +41,12 @@ xpReference :: PU Reference xpReference - = xpWrap ( \ ( ref - , (ck,ty,ti,i,d) - ,((au,ed,tr),(re,it,pu',dr),(co,ce,dg,om)) - ,((di',pg,vl,is),(nu,sc,ch)) + = xpWrap ( \ ((ref,oref) + , (ck,(ty,gn),ti,i,d) + ,((au,ed,tr,sp),(re,it,pu',dr),(co,ce,dg,om)) + ,((di',pg,vl,is),(nu,sc,ch,vs)) , (di,ac,pu,pp,et) - , ((ac',uri),no) + , ((ac',uri),ln,st,no) ) -> ref { refId = ck `betterThen` take 10 (concat . words $ fst ti) , refType = if ty /= NoType then ty else @@ -63,11 +63,13 @@ , director = dr `betterThen` director ref , collectionEditor = ce `betterThen` collectionEditor ref , publisherPlace = pp `betterThen` publisherPlace ref + , numberOfVolumes = vs `betterThen` numberOfVolumes ref , containerAuthor = containerAuthor ref , url = uri , note = no , isbn = i , doi = d + , genre = genre ref `betterThen` gn , issued = issued ref `betterThen` di `betterThen` di' , accessed = accessed ref `betterThen` ac `betterThen` ac' , page = page ref `betterThen` pg @@ -77,25 +79,34 @@ , number = number ref `betterThen` nu , section = section ref `betterThen` sc , chapterNumber = chapterNumber ref `betterThen` ch + , language = language ref `betterThen` ln + , status = status ref `betterThen` st , publisher = fromAgent pu `betterThen` publisher ref `betterThen` fromAgent pu' `betterThen` fromAgent dg `betterThen` fromAgent om + `betterThen` fromAgent sp + , originalDate = issued oref + , originalTitle = title oref + , originalPublisher = publisher oref + , originalPublisherPlace = publisherPlace oref } - , \r -> ( r - , (refId r, refType r, (title r, titleShort r), isbn r, doi r) - ,((author r, editor r, translator r) - ,(recipient r, interviewer r, emptyAgents, director r) + , \r -> ( (emptyReference,emptyReference) + , (refId r,(refType r,genre r), (title r, titleShort r), isbn r, doi r) + ,((author r, editor r, translator r, director r) + ,(recipient r, interviewer r, emptyAgents, director r) ,(composer r, collectionEditor r, emptyAgents, emptyAgents)) ,((issued r, page r, volume r, issue r) - ,(number r, section r, chapterNumber r)) + ,(number r, section r, chapterNumber r, numberOfVolumes r)) , (issued r, accessed r, emptyAgents, publisherPlace r, edition r) - ,((accessed r, url r), note r) + ,((accessed r, url r), status r, language r, note r) )) $ - xp6Tuple (xpDefault emptyReference xpRelatedItem) - (xp5Tuple xpCiteKey xpRefType xpTitle xpIsbn xpDoi) - xpAgents xpPart xpOrigin (xpPair xpUrl xpNote) + xp6Tuple (xpPair (xpDefault emptyReference $ xpRelatedItem "host") + (xpDefault emptyReference $ xpRelatedItem "original")) + (xp5Tuple xpCiteKey xpRefType xpTitle xpIsbn xpDoi) + xpAgents xpPart xpOrigin + (xp4Tuple xpUrl xpLang xpStatus xpNote) xpCiteKey :: PU String xpCiteKey @@ -116,9 +127,9 @@ (xpDefault [] $ xpIElem "place" $ xpIElem "placeTerm" xpText0) (xpDefault [] $ xpIElem "edition" $ xpText0) -xpRefType :: PU RefType +xpRefType :: PU (RefType, String) xpRefType - = xpDefault NoType $ + = xpDefault (NoType,[]) $ xpWrap (readRefType, const []) xpGenre xpGenre :: PU [String] @@ -128,18 +139,23 @@ (xpPair (xpDefault [] $ xpAttr "authority" xpText) xpText) $ xpLift . snd -xpRelatedItem :: PU Reference -xpRelatedItem - = xpIElem "relatedItem" . xpAddFixedAttr "type" "host" $ - xpWrap ( \( (ty,ct) - ,((ca,ed,tr),(re,it,pu',dr),(co,ce,dg,om)) - ,((di,pg,vl,is),(nu,sc,ch)) +xpRelatedItem :: String -> PU Reference +xpRelatedItem t + = xpIElem "relatedItem" . xpAddFixedAttr "type" t $ + xpWrap ( \(((t3l,t3s),(t4l,_)) + ,((ty,gn),ct) + ,((ca,ed,tr,sp),(re,it,pu',dr),(co,ce,dg,om)) + ,((di,pg,vl,is),(nu,sc,ch,vs)) , (di',ac,pu,pp,et) + , (ln, st) ) -> emptyReference { refType = ty + , title = fst ct , containerAuthor = ca - , containerTitle = fst ct - , containerTitleShort = snd ct + , containerTitle = if t3l /= [] then t3l else fst ct + , containerTitleShort = if t3s /= [] then t3s else snd ct + , collectionTitle = t4l + , volumeTitle = if t3l /= [] then fst ct else [] , editor = ed , edition = et , translator = tr @@ -157,21 +173,35 @@ , number = nu , section = sc , chapterNumber = ch + , genre = gn + , numberOfVolumes = vs + , language = ln + , status = st , publisher = fromAgent $ pu `betterThen` pu' `betterThen` - dg `betterThen` om + dg `betterThen` om `betterThen` sp } - , \r -> ( (refType r, (containerTitle r, containerTitleShort r)) - ,((containerAuthor r, editor r, translator r) - ,(recipient r, interviewer r, emptyAgents, director r) + , \r -> (((volumeTitle r,[]),(collectionTitle r,[])) + ,((refType r,genre r), (containerTitle r, containerTitleShort r)) + ,((containerAuthor r, editor r, translator r, director r) + ,(recipient r, interviewer r, emptyAgents, director r) ,(composer r, collectionEditor r, emptyAgents, emptyAgents)) ,((issued r, page r, volume r, issue r) - ,(number r, section r, chapterNumber r)) + ,(number r, section r, chapterNumber r, numberOfVolumes r)) , (issued r, accessed r,emptyAgents, publisherPlace r, edition r) + , (language r, status r) )) $ - xp4Tuple (xpPair xpRefType xpTitle) + xp6Tuple xpNestedTitles + (xpPair xpRefType xpTitle) xpAgents xpPart xpOrigin + (xpPair xpLang xpStatus) +xpNestedTitles :: PU ((String, String), (String, String)) +xpNestedTitles + = xpDefault (([],[]),([],[])) . getRelated $ xpPair xpTitle (getRelated xpTitle) + where + getRelated = xpIElem "relatedItem" . xpAddFixedAttr "type" "host" + xpTitle :: PU (String,String) xpTitle = xpWrap (\((a,b),c) -> createTitle a b c , \s -> (s,[])) $ @@ -182,19 +212,22 @@ xpAddFixedAttr "type" "abbreviated" $ xpElem "title" xpText0) where createTitle [] [] [] = ([],[]) - createTitle s [] [] = (s ,[]) + createTitle s [] [] = breakLong s createTitle s [] ab = (s ,ab) createTitle s sub [] = (s ++ colon s ++ sub, s) createTitle s sub ab = (s ++ colon s ++ sub, ab) colon s = if last s == '!' || last s == '?' then " " else ": " + breakLong s = let (a,b) = break (== ':') s + in if b /= [] then (s,a) else (s, []) -xpAgents :: PU (([Agent],[Agent],[Agent]) +xpAgents :: PU (([Agent],[Agent],[Agent],[Agent]) ,([Agent],[Agent],[Agent],[Agent]) ,([Agent],[Agent],[Agent],[Agent])) xpAgents - = xpTriple (xpTriple (xpAgent "author" "aut") + = xpTriple (xp4Tuple (xpAgent "author" "aut") (xpAgent "editor" "edt") - (xpAgent "translator" "trl")) + (xpAgent "translator" "trl") + (xpAgent "sponsor" "spn")) (xp4Tuple (xpAgent "recipient" "rcp") (xpAgent "interviewer" "ivr") (xpAgent "publisher" "pbl") @@ -252,21 +285,22 @@ readg = foldr (\(k,v) xs -> if k == "given" then v:xs else xs) [] xpPart :: PU (([RefDate],String,String,String) - ,(String,String,String)) + ,(String,String,String,String)) xpPart = xpDefault none . xpIElem "part" . xpWrap (readIt none,const []) $ xpList xpDetail where - none = (([],"","",""),("","","")) + none = (([],"","",""),("","","","")) readIt r [] = r - readIt acc@((d,p,v,i),(n,s,c)) (x:xs) - | Date y <- x = readIt ((y,p,v,i),(n,s,c)) xs - | Page y <- x = readIt ((d,y,v,i),(n,s,c)) xs - | Volume y <- x = readIt ((d,p,y,i),(n,s,c)) xs - | Issue y <- x = readIt ((d,p,v,y),(n,s,c)) xs - | Number y <- x = readIt ((d,p,v,i),(y,s,c)) xs - | ChapterNr y <- x = readIt ((d,p,v,i),(n,s,y)) xs - | Section y <- x = readIt ((d,p,v,i),(n,y,c)) xs + readIt acc@((d,p,v,i),(n,s,c,vs)) (x:xs) + | Date y <- x = readIt ((y,p,v,i),(n,s,c,vs)) xs + | Page y <- x = readIt ((d,y,v,i),(n,s,c,vs)) xs + | Volume y <- x = readIt ((d,p,y,i),(n,s,c,vs)) xs + | Issue y <- x = readIt ((d,p,v,y),(n,s,c,vs)) xs + | Number y <- x = readIt ((d,p,v,i),(y,s,c,vs)) xs + | ChapterNr y <- x = readIt ((d,p,v,i),(n,s,y,vs)) xs + | Section y <- x = readIt ((d,p,v,i),(n,y,c,vs)) xs + | NrVols y <- x = readIt ((d,p,v,i),(n,s,c, y)) xs | otherwise = acc data Detail @@ -277,6 +311,7 @@ | Number String | ChapterNr String | Section String + | NrVols String deriving ( Eq, Show ) xpDetail :: PU Detail @@ -286,6 +321,7 @@ tag _ = 0 ps = [ xpWrap (Date, const []) $ xpDate , xpWrap (Page, show) $ xpPage + , xpWrap (NrVols, show) $ xpVolumes , xpWrap (Volume, show) $ xp "volume" , xpWrap (Issue, show) $ xp "issue" , xpWrap (Number, show) $ xp "number" @@ -305,6 +341,11 @@ (xpElem "end" xpText)) (\(s,e) -> xpLift (s ++ "-" ++ e)) +xpVolumes :: PU String +xpVolumes + = xpElemWithAttrValue "extent" "unit" "volumes" $ + xpElem "total" xpText + xpUrl :: PU ([RefDate],String) xpUrl = xpDefault ([],[]) . xpIElem "location" $ @@ -325,6 +366,21 @@ xpNote :: PU (String) xpNote = xpDefault [] $ xpIElem "note" xpText +xpLang :: PU String +xpLang + = xpDefault [] $ + xpChoice (xpIElem "recordInfo" $ xpIElem "languageOfCataloging" $ + xpIElem "language" $ xpIElem "languageTerm" xpText) + (xpIElem "recordInfo" $ xpIElem "languageOfCataloging" $ + xpIElem "languageTerm" xpText) + xpLift + +xpStatus :: PU String +xpStatus + = xpDefault [] $ + --xpElemWithAttrValue "note" "type" "publication status" xpText + xpIElem "note" $ xpAddFixedAttr "type" "publication status" xpText + readDate :: String -> [RefDate] readDate s = (parseDate $ takeWhile (/= '/') s) ++ (parseDate . tail' $ dropWhile (/= '/') s) @@ -345,12 +401,16 @@ fromAgent :: [Agent] -> String fromAgent = foldr (<+>) [] . map show -readRefType :: [String] -> RefType -readRefType [] = NoType -readRefType (t:_) = +readRefType :: [String] -> (RefType, String) +readRefType [] = (NoType,[]) +readRefType (t:ts) = case M.lookup t genreTypeMapping of - Just x -> x - Nothing -> ArticleJournal -- Reasonable default (?) + Just x -> (x, if ts /= [] then head ts else []) + Nothing -> if ts /= [] + then case M.lookup (head ts) genreTypeMapping of + Just x -> (x, t) + Nothing -> (ArticleJournal, t) + else (ArticleJournal, []) -- The string constants come from http://www.loc.gov/standards/valuelist/marcgt.html, which are used in the -- "" element (http://www.loc.gov/standards/mods/userguide/genre.html) @@ -360,9 +420,10 @@ , ( "book chapter", Chapter ) , ( "periodical", ArticleJournal ) , ( "newspaper", ArticleNewspaper ) + , ( "magazine", ArticleNewspaper ) , ( "magazine article", ArticleNewspaper ) , ( "encyclopedia", EntryEncyclopedia) - , ( "conference publication", PaperConference ) + , ( "conference publication", Book ) , ( "academic journal", ArticleJournal ) , ( "collection", Chapter ) , ( "legal case and case notes", LegalCase ) @@ -377,6 +438,7 @@ , ( "Ph.D. thesis", Thesis ) , ( "Masters thesis", Thesis ) , ( "report", Report ) + , ( "technical report", Report ) , ( "review", Review ) , ( "thesis", Thesis ) , ( "unpublished", NoType ) diff --git a/src/Text/CSL/Output/Pandoc.hs b/src/Text/CSL/Output/Pandoc.hs --- a/src/Text/CSL/Output/Pandoc.hs +++ b/src/Text/CSL/Output/Pandoc.hs @@ -25,7 +25,7 @@ , endWithPunct ) where -import Data.Char ( toUpper, toLower, isPunctuation ) +import Data.Char ( toUpper, toLower ) import Data.Maybe ( fromMaybe ) import Text.CSL.Style @@ -37,26 +37,48 @@ renderPandoc :: Style -> [FormattedOutput] -> [Inline] renderPandoc s = proc (convertQuoted s) . proc' (clean s $ isPunctuationInQuote s) . - concatMap (flipFlop . render s) + flipFlop . render s -- | Same as 'renderPandoc', but the output is wrapped in a pandoc -- paragraph block. renderPandoc' :: Style -> [FormattedOutput] -> Block renderPandoc' s = Para . proc (convertQuoted s) . proc' (clean s $ isPunctuationInQuote s) . - concatMap (flipFlop . render s) + flipFlop . render s -- | For the testsuite: we use 'Link' and 'Strikeout' to store -- "nocase" and "nodecor" rich text formatting classes. renderPandoc_ :: Style -> [FormattedOutput] -> [Inline] renderPandoc_ s = proc (convertQuoted s) . proc (clean' s $ isPunctuationInQuote s) . - concatMap (flipFlop . render s) + flipFlop . render s -render :: Style -> FormattedOutput -> [Inline] -render _ (FPan i) = i -render _ (FDel s) = toStr s -render sty fo +render :: Style -> [FormattedOutput] -> [Inline] +render _ [] = [] +render s (x:[]) = renderFo s x +render s (x:y:os) = let a = renderFo s x + b = renderFo s y + isPunct = and . map (flip elem ".!?") in + if isPunct (lastInline a) && isPunct (headInline b) + then a ++ render s (tailFO [y] ++ os) + else a ++ render s (y:os) + +tailFO :: [FormattedOutput] -> [FormattedOutput] +tailFO [] = [] +tailFO (f:fs) + | FDel s <- f = FDel (tail' s) : fs + | FPan is <- f = FPan (tailInline is) : fs + | FN s fm <- f = if prefix fm /= [] then FN s (tailFm fm) : fs else FN (tail' s) fm : fs + | FS s fm <- f = if prefix fm /= [] then FS s (tailFm fm) : fs else FS (tail' s) fm : fs + | FO fm fo <- f = if prefix fm /= [] then FO (tailFm fm) fo : fs else FO fm (tailFO fo) : fs + | otherwise = f : tailFO fs + where + tailFm fm = fm { prefix = tail $ prefix fm } + +renderFo :: Style -> FormattedOutput -> [Inline] +renderFo _ (FPan i) = i +renderFo _ (FDel s) = toStr s +renderFo sty fo | FS str fm <- fo = toPandoc fm $ toStr str | FN str fm <- fo = toPandoc fm $ toStr $ rmZeros str | FO fm xs <- fo = toPandoc fm $ rest xs @@ -74,9 +96,11 @@ toPandoc f i = addSuffix f $ toStr (prefix f) ++ (quote f . format f . proc cleanStrict $ i) format f = font_variant f . font f . text_case f - rest xs = procList xs $ concatMap (render sty) - quote f i = if i /= [] && quotes f - then [Quoted DoubleQuote . valign f $ i] + rest xs = procList xs $ render sty + quote f i = if i /= [] && quotes f /= NoQuote + then if quotes f == NativeQuote + then [escape "inquote" . valign f $ i] + else [Quoted DoubleQuote . valign f $ i] else valign f i setCase f i | Str s <- i = Str $ f s @@ -85,8 +109,8 @@ | Link s r <- i = Link (map (setCase f) s) r | otherwise = setCase f i - toCap s = if s /= [] then toUpper (head s) : map toLower (tail s) else [] - toTitleCap s = if isShortWord s then toUpper (head s) : tail s else s + toCap s = if s /= [] then toUpper (head s) : tail s else [] + toTitleCap s = if isShortWord s then toUpper (head s) : tail s else s isShortWord s = not $ s `elem` ["a","an","and","as","at","but","by","down","for","from" ,"in","into","nor","of","on","onto","or","over","so" ,"the","till","to","up","via","with","yet"] @@ -174,19 +198,20 @@ clean' :: Style -> Bool -> [Inline] -> [Inline] clean' _ _ [] = [] clean' s b (i:is) - | Quoted t inls <- i - , b = case headInline is of - [x] -> if isPunctuation x + | Link inls (y,z) <- i, y == "inquote" + , y == z = case headInline is of + [x] -> if x `elem` ".," && b then if lastInline inls `elem` [".",",",";",":","!","?"] - then Quoted t (reverseQuoted t inls ) : clean' s b (tailInline is) - else Quoted t (reverseQuoted t inls ++ [Str [x]]) : clean' s b (tailInline is) - else Quoted t (reverseQuoted t inls) : clean' s b is - _ -> Quoted t (reverseQuoted t inls) : clean' s b is - | Quoted t inls <- i = Quoted t (reverseQuoted t inls) : clean' s b is + then quote DoubleQuote inls : clean' s b (tailInline is) + else quote DoubleQuote (inls ++ [Str [x]]) : clean' s b (tailInline is) + else quote DoubleQuote inls : clean' s b is + _ -> quote DoubleQuote inls : clean' s b is + | Quoted t inls <- i = quote t inls : clean' s b is | otherwise = if lastInline [i] == headInline is && isPunct then i : clean' s b (tailInline is) else i : clean' s b is where + quote t x = Quoted t (reverseQuoted t x) isPunct = and . map (flip elem ".,;:!? ") $ headInline is reverseQuoted t = proc reverseQuoted' where @@ -238,7 +263,8 @@ convertQuoted s = convertQuoted' where locale = let l = styleLocale s in case l of [x] -> x; _ -> Locale [] [] [] [] [] - getQuote x y = entityToChar . fst . fromMaybe (x,[]) . lookup (y,Long) . localeTermMap $ locale + getQuote x y = entityToChar . termSingular . fromMaybe newTerm {termSingular = x} . + findTerm y Long . localeTerms $ locale doubleQuotesO = getQuote "\"" "open-quote" doubleQuotesC = getQuote "\"" "close-quote" singleQuotesO = getQuote "'" "open-inner-quote" diff --git a/src/Text/CSL/Output/Plain.hs b/src/Text/CSL/Output/Plain.hs --- a/src/Text/CSL/Output/Plain.hs +++ b/src/Text/CSL/Output/Plain.hs @@ -45,6 +45,7 @@ render b fo | (FS str fm ) <- fo = prefix fm <++> format fm (trim str ) <++> suffix fm | (FN str fm ) <- fo = prefix fm <++> format fm (trim str ) <++> suffix fm + | (FUrl t fm ) <- fo = prefix fm <++> format fm (trim $ fst t ) <++> suffix fm | (FO fm xs) <- fo = prefix fm <++> format fm (trim $ rest xs) <++> suffix fm | otherwise = [] where @@ -54,7 +55,7 @@ (<++>) = if b then (++) else (<>) concatM f = foldr (<++>) [] . map f - quote f s = if s /= [] && quotes f then "\"" ++ s ++ "\"" else s + quote f s = if s /= [] && quotes f /= NoQuote then "\"" ++ s ++ "\"" else s capital s = toUpper (head s) : (tail s) format f s = quote f . text_case f $ s @@ -91,11 +92,12 @@ where parseEntity = chr . readNum . takeWhile (/= ';') &&& entityToChar . tail' . dropWhile (/= ';') - readNum ('x': n) = readNum $ "0x" ++ n - readNum n = case readsPrec 1 n of - [(x,[])] -> x - _ -> error $ "Invalid character entity:" ++ n +readNum :: String -> Int +readNum ('x': n) = readNum $ "0x" ++ n +readNum n = case readsPrec 1 n of + [(x,[])] -> x + _ -> error $ "Invalid character entity:" ++ n head' :: [a] -> [a] head' = foldr (\x _ -> [x]) [] diff --git a/src/Text/CSL/Parser.hs b/src/Text/CSL/Parser.hs --- a/src/Text/CSL/Parser.hs +++ b/src/Text/CSL/Parser.hs @@ -151,9 +151,10 @@ instance XmlPickler Formatting where xpickle = xpWrap ( \(((p,s,ff),(fs,fv,fw)),(td,va,tc,d),(q,sp)) - -> Formatting p s ff fs fv fw td va tc d q sp False False - , \(Formatting p s ff fs fv fw td va tc d q sp _ _) - -> (((p,s,ff),(fs,fv,fw)),(td,va,tc,d),(q,sp))) $ + -> Formatting p s ff fs fv fw td va tc d + (if q then NativeQuote else NoQuote) sp False False + , \(Formatting p s ff fs fv fw td va tc d _ sp _ _) + -> (((p,s,ff),(fs,fv,fw)),(td,va,tc,d),(False,sp))) $ xpTriple (xpPair (xpTriple (xpAttrText' "prefix" ) (xpAttrText' "suffix" ) (xpAttrText' "font-family" )) @@ -192,6 +193,9 @@ instance XmlPickler Bool where xpickle = xpWrap readable xpText +instance XmlPickler Gender where + xpickle = xpWrap readable xpText + instance XmlPickler Form where xpickle = xpWrap readable (xpAttrWithDefault "long" "form" xpText) @@ -290,15 +294,21 @@ xpTerms (xpList xpLocaleDate)) -xpTerms :: PU [TermMap] +xpTerms :: PU [CslTerm] xpTerms = xpWrap (concat,return) $ xpList $ xpIElem "terms" $ xpList $ xpElem "term" $ - xpPair (xpPair (xpAttrText "name") xpickle) - (xpChoice (xpWrap (\s -> (s,s), fst) xpText0) - (xpPair (xpIElem "single" xpText0) - (xpIElem "multiple" xpText0)) - xpLift) + xpWrap (\((n,f,g,gf,m),(s,p)) -> CT n f g gf s p m, + undefined) $ + xpPair (xp5Tuple (xpAttrText "name") + xpickle + (xpAttrWithDefault Neuter "gender" xpickle) + (xpAttrWithDefault Neuter "gender-form" xpickle) + (xpAttrText' "match")) + (xpChoice (xpWrap (\s -> (s,s), fst) xpText0) + (xpPair (xpIElem "single" xpText0) + (xpIElem "multiple" xpText0)) + xpLift) xpMacros :: PU [MacroMap] xpMacros @@ -376,37 +386,41 @@ xpBibOpts :: PU [Option] xpBibOpts - = xpWrap ( \((a,b,c,d,e),(f,g)) -> + = xpWrap ( \((a,b,c,d,e,f),(g,h)) -> filter ((/=) [] . snd) $ [("hanging-indent",a) ,("second-field-align",b) ,("subsequent-author-substitute",c) - ,("line-spacing",d) - ,("entry-spacing",e)] ++ f ++ g - , const (([],[],[],[],[]),([],[]))) $ - xpPair (xp5Tuple (xpAttrText' "hanging-indent") + ,("subsequent-author-substitute-rule",d) + ,("line-spacing",e) + ,("entry-spacing",f)] ++ g ++ h + , const (([],[],[],[],[],[]),([],[]))) $ + xpPair (xp6Tuple (xpAttrText' "hanging-indent") (xpAttrText' "second-field-align") (xpAttrText' "subsequent-author-substitute") + (xpAttrText' "subsequent-author-substitute-rule") (xpAttrText' "line-spacing") (xpAttrText' "entry-spacing")) $ xpPair xpNameOpt xpNamesOpt xpCitOpts :: PU [Option] xpCitOpts - = xpWrap ( \((a,b,c),(d,e,f,g,h),(i,l)) -> + = xpWrap ( \((a,b,c),(d,e,f,g,h,i),(j,k)) -> filter ((/=) [] . snd) $ [("disambiguate-add-names",a) ,("disambiguate-add-givenname",b) ,("disambiguate-add-year-suffix",c) ,("givenname-disambiguation-rule",d) ,("collapse",e) - ,("year-suffix-delimiter",f) - ,("after-collapse-delimiter",g) - ,("near-note-distance",h)] ++ i ++ l - , const (([],[],[]),([],[],[],[],[]),([],[]))) $ + ,("cite-group-delimiter",f) + ,("year-suffix-delimiter",g) + ,("after-collapse-delimiter",h) + ,("near-note-distance",i)] ++ j ++ k + , const (([],[],[]),([],[],[],[],[],[]),([],[]))) $ xpTriple (xpTriple (xpAttrText' "disambiguate-add-names") (xpAttrText' "disambiguate-add-givenname") (xpAttrText' "disambiguate-add-year-suffix")) - (xp5Tuple (xpAttrText' "givenname-disambiguation-rule") + (xp6Tuple (xpAttrText' "givenname-disambiguation-rule") (xpAttrText' "collapse") + (xpAttrText' "cite-group-delimiter") (xpAttrText' "year-suffix-delimiter") (xpAttrText' "after-collapse-delimiter") (xpAttrText' "near-note-distance")) @@ -567,16 +581,23 @@ ,("en", "en-US") ,("es", "es-ES") ,("et", "et-EE") + ,("fa", "fa-IR") + ,("fi", "fi-FI") ,("fr", "fr-FR") ,("he", "he-IL") + ,("hr", "hr-HR") ,("hu", "hu-HU") ,("is", "is-IS") ,("it", "it-IT") ,("ja", "ja-JP") + ,("km", "km-KH") ,("ko", "ko-KR") + ,("lt", "lt-LT") + ,("lv", "lv-LV") ,("mn", "mn-MN") ,("nb", "nb-NO") ,("nl", "nl-NL") + ,("nn", "nn-NO") ,("pl", "pl-PL") ,("pt", "pt-PT") ,("ro", "ro-RO") diff --git a/src/Text/CSL/Pickle.hs b/src/Text/CSL/Pickle.hs --- a/src/Text/CSL/Pickle.hs +++ b/src/Text/CSL/Pickle.hs @@ -1,4 +1,4 @@ -{-# LANGUAGE PatternGuards #-} +{-# LANGUAGE PatternGuards, CPP #-} ----------------------------------------------------------------------------- -- | -- Module : Text.CSL.Pickle diff --git a/src/Text/CSL/Proc.hs b/src/Text/CSL/Proc.hs --- a/src/Text/CSL/Proc.hs +++ b/src/Text/CSL/Proc.hs @@ -83,12 +83,12 @@ -- 'Reference'. procRefs :: Style -> [Reference] -> [Reference] procRefs (Style {biblio = mb, csMacros = ms , styleLocale = l, styleAbbrevs = as, csOptions = opts}) rs - = maybe rs process mb + = maybe (setCNum rs) process mb where opts' b = mergeOptions (bibOptions b) opts - citNum x = x { citationNumber = maybe 0 ((+) 1 . fromIntegral) . elemIndex x $ rs } + setCNum = map (\(x,y) -> x { citationNumber = fromIntegral y }) . flip zip ([1..] :: [Int]) sort_ b = evalSorting (EvalSorting emptyCite {citePosition = "first"})l ms (opts' b) (bibSort b) as - process b = sortItems . map (citNum &&& sort_ b) $ rs + process b = setCNum . sortItems . map (id &&& sort_ b) $ rs sortItems :: Show a => [(a,[Sorting])] -> [a] sortItems [] = [] @@ -111,15 +111,87 @@ styleAbbrevs = as, csOptions = opts}) rs = maybe [] process mb where - render b = map (format b) . chkAut [] . filterRefs bos $ rs - process b = flip map (render b) $ uncurry formatBiblioLayout (layFormat &&& layDelim $ bibLayout b) - format b (p,r) = evalLayout (bibLayout b) (EvalBiblio p) False l ms - (mergeOptions (bibOptions b) opts) as r - chkAut _ [] = [] - chkAut a (x:xs) = if author x `elem` a - then ("subsequent",x) : chkAut a xs - else ("first" ,x) : chkAut (author x : a) xs + process b = flip map (render b) $ uncurry formatBiblioLayout (layFormat &&& layDelim $ bibLayout b) + render b = subsequentAuthorSubstitute b . map (evalBib b) . filterRefs bos $ rs + evalBib b r = evalLayout (bibLayout b) (EvalBiblio emptyCite {citePosition = "first"}) False l ms + (mergeOptions (bibOptions b) opts) as r +subsequentAuthorSubstitute :: Bibliography -> [[Output]] -> [[Output]] +subsequentAuthorSubstitute b = if null subAuthStr then id else chkCreator + where + subAuthStr = getOptionVal "subsequent-author-substitute" (bibOptions b) + subAuthRule = getOptionVal "subsequent-author-substitute-rule" (bibOptions b) + + queryContrib = proc' rmLabel . query contribsQ + getContrib = if null subAuthStr + then const [] + else case subAuthRule of + "partial-first" -> head' . query namesQ . queryContrib + "partial-each" -> query namesQ . queryContrib + _ -> queryContrib + + getPartialEach x xs = concat . head' . map fst . reverse . + sortBy (comparing $ length . snd) . filter ((<) 0 . length . snd) . + zip xs . map (takeWhile id . map (uncurry (==)) . zip x) $ xs + + chkCreator = if subAuthRule == "partial-each" then chPartialEach [] else chkCr [] + + chkCr _ [] = [] + chkCr a (x:xs) = let contribs = getContrib x in + if contribs `elem` a + then substituteAuth [] + x : chkCr a xs + else x : chkCr (contribs : a) xs + + chPartialEach _ [] = [] + chPartialEach a (x:xs) = let contribs = getContrib x + partial = getPartialEach contribs a in + if not $ null partial + then substituteAuth partial x : + if length partial < length contribs + then chPartialEach (contribs : a) xs + else chPartialEach a xs + else x : chPartialEach (contribs : a) xs + + substituteAuth a = if subAuthRule == "complete-each" + then proc chNamas else proc (updateContribs a) + + updateContribs a o@(OContrib i r y ds os) + = if r == "author" || r == "authorsub" then OContrib i r upCont ds os else o + where + upCont = case subAuthRule of + "partial-first" -> rmFirstName y + "partial-each" -> rmSelectedName a y + _ -> OStr subAuthStr emptyFormatting : proc rmNames y + updateContribs _ o = o + + contribsQ o + | OContrib _ r c _ _ <- o = if r == "author" || r == "authorsub" then c else [] + | otherwise = [] + namesQ o + | OName {} <- o = [o] + | otherwise = [] + rmSelectedName _ [] = [] + rmSelectedName a (o:os) + | OName {} <- o = (if o `elem` a then OStr subAuthStr emptyFormatting else o) : rmSelectedName a os + | otherwise = o : rmSelectedName a os + rmFirstName [] = [] + rmFirstName (o:os) + | OName {} <- o = OStr subAuthStr emptyFormatting : os + | otherwise = o : rmFirstName os + chNamas o + | OName s _ os f <- o = OName s [OStr subAuthStr emptyFormatting] os f + | otherwise = o + rmNames o + | OName {} <- o = ONull + | OStr {} <- o = ONull + | ODel {} <- o = ONull + | otherwise = o + rmLabel [] = [] + rmLabel (o:os) + | OLabel {} <- o = rmLabel os + | otherwise = o : rmLabel os + filterRefs :: BibOpts -> [Reference] -> [Reference] filterRefs bos refs | Select s q <- bos = filter (select s) . filter (quash q) $ refs @@ -211,7 +283,7 @@ -- pandoc terminology). localModifiers :: Style -> Bool -> Cite -> Output -> Output localModifiers s b c - | authorInText c = check . return . proc rmFormatting . contribOnly + | authorInText c = check . return . proc rmFormatting . contribOnly s | suppressAuthor c = check . rmContrib . return | otherwise = id where @@ -243,19 +315,6 @@ | Formatting {} <- f = emptyFormatting { prefix = prefix f , suffix = suffix f} | otherwise = f - contribOnly o - | isNumStyle [o] - , OCitNum {} <- o = Output [ OStr (query getRefTerm s) emptyFormatting - , OSpace, o] emptyFormatting - | OContrib _ "author" - _ _ _ <- o = o - | OContrib _ "authorsub" - _ _ _ <- o = o - | Output ot f <- o = Output (cleanOutput $ map contribOnly ot) f - | OStr x _ <- o - , "ibid" <- filter (/= '.') - (map toLower x) = o - | otherwise = ONull rmCitNum o | OCitNum {} <- o = ONull | otherwise = o @@ -284,7 +343,23 @@ , "ibid" <- filter (/= '.') (map toLower x) = rmContrib' os | otherwise = o : rmContrib' os - getRefTerm :: TermMap -> String + +contribOnly :: Style -> Output -> Output +contribOnly s o + | isNumStyle [o] + , OCitNum {} <- o = Output [ OStr (query getRefTerm s) emptyFormatting + , OSpace, o] emptyFormatting + | OContrib _ "author" + _ _ _ <- o = o + | OContrib _ "authorsub" + _ _ _ <- o = o + | Output ot f <- o = Output (cleanOutput $ map (contribOnly s) ot) f + | OStr x _ <- o + , "ibid" <- filter (/= '.') + (map toLower x) = o + | otherwise = ONull + where + getRefTerm :: CslTerm -> String getRefTerm t - | (("reference", Long), (x,_)) <- t = capitalize x - | otherwise = [] + | CT "reference" Long _ _ x _ _ <- t = capitalize x + | otherwise = [] diff --git a/src/Text/CSL/Proc/Collapse.hs b/src/Text/CSL/Proc/Collapse.hs --- a/src/Text/CSL/Proc/Collapse.hs +++ b/src/Text/CSL/Proc/Collapse.hs @@ -66,6 +66,31 @@ ] emptyFormatting else map (flip OCitNum f) x +groupCites :: [(Cite, Output)] -> [(Cite, Output)] +groupCites [] = [] +groupCites (x:xs) = let equal = filter ((==) (namesOf $ snd x) . namesOf . snd) xs + notequal = filter ((/=) (namesOf $ snd x) . namesOf . snd) xs + in x : equal ++ groupCites notequal + where + contribsQ o + | OContrib _ _ c _ _ <- o = [c] + | otherwise = [] + namesOf y = if null (query contribsQ y) then [] else proc rmNameHash . proc rmGivenNames $ head (query contribsQ y) + +getYearAndSuf :: Output -> Output +getYearAndSuf x + = case query getOYear x of + [] -> noOutputError + x' -> Output x' emptyFormatting + where + getOYear o + | OYear {} : _ <- o = [head o] + | OYearSuf {} : _ <- o = [head o] + | OPan {} : _ <- o = [head o] + | OLoc {} : _ <- o = [head o] + | ODel _ : OLoc {} : _ <- o = [head o] + | otherwise = [] + collapseYear :: Style -> String -> CitationGroup -> CitationGroup collapseYear s ranged (CG cs f d os) = CG cs f [] (process os) where @@ -76,16 +101,6 @@ format [] = [] format (x:xs) = x : map getYearAndSuf xs - getYearAndSuf x = case query getOYear x of - [] -> noOutputError - x' -> Output x' emptyFormatting - getOYear o - | OYear {} : _ <- o = [head o] - | OYearSuf {} : _ <- o = [head o] - | OPan {} : _ <- o = [head o] - | OLoc {} : _ <- o = [head o] - | ODel _ : OLoc {} : _ <- o = [head o] - | otherwise = [] isRanged = case ranged of "year-suffix-ranged" -> True @@ -95,11 +110,16 @@ else collapseYearSuf isRanged yearSufDel rmAffixes x = x {citePrefix = emptyAffix, citeSuffix = emptyAffix} + delim = let d' = getOptionVal "cite-group-delimiter" . citOptions . citation $ s + -- FIXME: see https://bitbucket.org/bdarcus/citeproc-test/issue/15 + -- in if null d' then if null d then ", " else d else d' + in if null d' then ", " else d' + collapsYS a = case a of [] -> (emptyCite, ONull) [x] -> rmAffixes . fst &&& uncurry addCiteAffixes $ x _ -> (,) (rmAffixes $ fst $ head a) . flip Output emptyFormatting . - addDelim d . collapseRange . + addDelim delim . collapseRange . uncurry zip . second format . unzip $ a doCollapse [] = [] @@ -110,10 +130,10 @@ else (a, Output (b : [ODel d ]) emptyFormatting) : doCollapse xs contribsQ o - | OContrib _ _ c _ _ <- o = [c] + | OContrib _ _ c _ _ <- o = [proc' rmNameHash . proc' rmGivenNames $ c] | otherwise = [] namesOf = query contribsQ - process = doCollapse . groupBy (\a b -> namesOf (snd a) == namesOf (snd b)) + process = doCollapse . groupBy (\a b -> namesOf (snd a) == namesOf (snd b)) . groupCites collapseYearSuf :: Bool -> String -> [(Cite,Output)] -> [Output] collapseYearSuf ranged ysd = process diff --git a/src/Text/CSL/Proc/Disamb.hs b/src/Text/CSL/Proc/Disamb.hs --- a/src/Text/CSL/Proc/Disamb.hs +++ b/src/Text/CSL/Proc/Disamb.hs @@ -68,8 +68,10 @@ needYSuff = filter_ snd $ zip duplics withNames newNames :: [CiteData] - newNames = when_ (hasNamesOpt || hasGNameOpt) $ disambAddNames givenNames $ needNames ++ - if hasYSuffOpt && givenNames == NoGiven then [] else needYSuff + newNames = if hasNamesOpt + then disambAddNames givenNames $ needNames ++ + if hasYSuffOpt && givenNames == NoGiven then [] else needYSuff + else map (\cd -> cd {disambed = collision cd} ) $ needNames ++ needYSuff newGName :: [NameData] newGName = when_ hasGNameOpt $ concatMap disambAddGivenNames nameDupls @@ -88,7 +90,8 @@ yearSuffs = when_ hasYSuffOpt . generateYearSuffix bibs . query getYearSuffixes $ withYearS - addNames = proc (updateContrib givenNames newNames newGName) + addGNames = if hasGNameOpt then newGName else [] + addNames = proc (updateContrib givenNames newNames addGNames) processed = if hasYSuffOpt then proc (updateYearSuffixes yearSuffs) . addNames $ withYearS @@ -128,16 +131,16 @@ addGName = map (\(c,n) -> c { nameDataSolved = if null n then nameCollision c else head n }) disSolved updateContrib :: GiveNameDisambiguation -> [CiteData] -> [NameData] -> Output -> Output +updateContrib ByCite [] _ o = o updateContrib g c n o | OContrib k r s d dd <- o = case filter (key &&& sameAs >>> uncurry (:) >>> elem k) c of - x:_ | clean (disambData x) == clean (d:dd) -> - OContrib k r (map processGNames $ disambed x) [] dd - _ | null c, AllNames <- g -> OContrib k r (map processGNames s) d dd - | otherwise -> o + x:_ -> OContrib k r (processGNames $ disambed x) [] dd + _ -> if null c + then OContrib k r (processGNames s) d dd + else o | otherwise = o where - clean = if g == NoGiven then proc rmNameHash . proc rmGivenNames else id - processGNames = if g /= NoGiven then updateOName n else id + processGNames = if g /= NoGiven then proc' (updateOName n) else id updateOName :: [NameData] -> Output -> Output updateOName n o @@ -201,7 +204,8 @@ then rmExtras xs else Output (rmExtras x) f : rmExtras xs | OContrib _ _ x _ _ : xs <- os = OContrib [] [] x [] [] : rmExtras xs - | OYear y _ f : xs <- os = OYear y [] f : rmExtras xs + | OYear y _ f : xs <- os = OYear y [] f : rmExtras xs + | OYearSuf s _ _ f : xs <- os = OYearSuf s [] [] f : rmExtras xs | ODel _ : xs <- os = rmExtras xs | OLoc _ _ : xs <- os = rmExtras xs | x : xs <- os = x : rmExtras xs @@ -225,7 +229,7 @@ else c {key = fst y ,citYear = snd y} contribsQ o - | OContrib k _ _ d dd <- o = [CD k [out] d (d:dd) [] [] []] + | OContrib k _ s d dd <- o = [CD k s d (d:dd) [] [] []] | otherwise = [] getYears :: Output -> [(String,String)] @@ -259,7 +263,7 @@ generateYearSuffix :: [Reference] -> [(String, [Output])] -> [(String,String)] generateYearSuffix refs - = concatMap (flip zip suffs) . + = flip zip suffs . concat . -- sort clashing cites using their position in the sorted bibliography getFst . map sort' . map (filter ((/=) 0 . snd)) . map (map getP) . -- group clashing cites @@ -280,7 +284,7 @@ setYS c o | OYearSuf _ k _ f <- o = OYearSuf [] k (getCollision k c) f | otherwise = o - collide = if b then disambed else disambYS + collide = if b then collision else disambYS getCollision k c = case find ((==) k . key) c of Just x -> if collide x == [] then [OStr (citYear x) emptyFormatting] diff --git a/src/Text/CSL/Reference.hs b/src/Text/CSL/Reference.hs --- a/src/Text/CSL/Reference.hs +++ b/src/Text/CSL/Reference.hs @@ -158,6 +158,7 @@ , titleShort :: String , reviewedTitle :: String , containerTitle :: String + , volumeTitle :: String , collectionTitle :: String , containerTitleShort :: String , collectionNumber :: String --Int @@ -203,6 +204,7 @@ , dimensions :: String , scale :: String , categories :: [String] + , language :: String , citationNumber :: CNum , firstReferenceNoteNumber :: Int @@ -240,6 +242,7 @@ , titleShort = [] , reviewedTitle = [] , containerTitle = [] + , volumeTitle = [] , collectionTitle = [] , containerTitleShort = [] , collectionNumber = [] @@ -285,6 +288,7 @@ , dimensions = [] , scale = [] , categories = [] + , language = [] , citationNumber = CNum 0 , firstReferenceNoteNumber = 0 @@ -325,7 +329,7 @@ processCites :: [Reference] -> [[Cite]] -> [[(Cite, Reference)]] processCites rs cs - = setCitationNumber $ procGr [[]] cs + = procGr [[]] cs where procRef r = case filter ((==) (refId r) . citeId) $ concat cs of x:_ -> r { firstReferenceNoteNumber = readNum $ citeNoteNumber x} @@ -358,17 +362,9 @@ last a == [] && citeId c == citeId (head . last $ init a) isLocSet = citeLocator c /= "" -setCitationNumber :: [[(Cite, Reference)]] -> [[(Cite, Reference)]] -setCitationNumber csrs = map (map setIt) csrs - where - selectFirst = map citeId . filter ((==) "first" . citePosition) . concatMap (map fst) - setIt (c,r) = case elemIndex (citeId c) (selectFirst csrs) of - Just i -> (c,r {citationNumber = CNum (i + 1)}) - Nothing -> (c,r) - setPageFirst :: Reference -> Reference -setPageFirst r = if ('-' `elem` page r) - then r { pageFirst = takeWhile (/= '-') $ page r} +setPageFirst r = if ('–' `elem` page r || '-' `elem` page r) + then r { pageFirst = takeWhile (not . flip elem "–-") $ page r} else r setNearNote :: Style -> [[Cite]] -> [[Cite]] diff --git a/src/Text/CSL/Style.hs b/src/Text/CSL/Style.hs --- a/src/Text/CSL/Style.hs +++ b/src/Text/CSL/Style.hs @@ -15,13 +15,20 @@ module Text.CSL.Style where -import Data.List ( nubBy, isPrefixOf ) +import Control.Arrow +import Data.List ( nubBy, isPrefixOf, isInfixOf ) import Data.Generics ( Typeable, Data, everywhere - , everywhere', everything, mkT, mkQ) + , everywhere', everything, mkT, mkQ ) +import Data.Maybe ( listToMaybe ) import qualified Data.Map as M import Text.JSON import Text.Pandoc.Definition ( Inline, Target ) +#ifdef UNICODE_COLLATION +import qualified Data.Text as T +import qualified Data.Text.ICU as T +#endif + -- | The representation of a parsed CSL style. data Style = Style @@ -42,7 +49,7 @@ { localeVersion :: String , localeLang :: String , localeOptions :: [Option] - , localeTermMap :: [TermMap] + , localeTerms :: [CslTerm] , localeDate :: [Element] } deriving ( Show, Read, Eq, Typeable, Data ) @@ -57,20 +64,58 @@ filter ((\x -> x /= [] && x `isPrefixOf` s) . localeLang) ls ++ filter ((==) [] . localeLang) ls doMerge x = return l { localeOptions = newOpt x - , localeTermMap = newTermMap x + , localeTerms = newTerms x , localeDate = newDate x } + cht = cslTerm &&& termForm &&& termGenderForm + checkedLoc = if hasOrdinals ls then rmOrdinals (localeTerms l) else localeTerms l + newTerms x = nubBy (\a b -> cht a == cht b) (concatMap localeTerms x ++ checkedLoc) newOpt x = nubBy (\a b -> fst a == fst b) (concatMap localeOptions x ++ localeOptions l) - newTermMap x = nubBy (\a b -> fst a == fst b) (concatMap localeTermMap x ++ localeTermMap l) newDate x = nubBy (\(Date _ a _ _ _ _) (Date _ b _ _ _ _) -> a == b) (concatMap localeDate x ++ localeDate l) +data CslTerm + = CT + { cslTerm :: String + , termForm :: Form + , termGender :: Gender + , termGenderForm :: Gender + , termSingular :: String + , termPlural :: String + , termMatch :: String + } deriving ( Show, Read, Eq, Typeable, Data ) + +newTerm :: CslTerm +newTerm = CT [] Long Neuter Neuter [] [] [] + +findTerm :: String -> Form -> [CslTerm] -> Maybe CslTerm +findTerm s f + = listToMaybe . filter (cslTerm &&& termForm >>> (==) (s, f)) + +findTerm' :: String -> Form -> Gender -> [CslTerm] -> Maybe CslTerm +findTerm' s f g + = listToMaybe . filter (cslTerm &&& termForm &&& termGenderForm >>> (==) (s,(f,g))) + +hasOrdinals :: Data a => a -> Bool +hasOrdinals = or . query hasOrd + where + hasOrd o + | CT {cslTerm = t} <- o + , "ordinal" `isInfixOf` t = [True] + | otherwise = [False] + +rmOrdinals :: Data a => a -> a +rmOrdinals = proc' doRemove + where + doRemove [] = [] + doRemove (o:os) + | CT {cslTerm = t} <- o + , "ordinal" `isInfixOf` t = doRemove os + | otherwise = o:doRemove os + type Abbrev = (String, [(String, M.Map String String)]) -type TermMap - = ((String,Form),(String,String)) - type MacroMap = (String,[Element]) @@ -180,10 +225,16 @@ compare' :: String -> String -> Ordering compare' x y = case (head x, head y) of - ('-','-') -> compare y x + ('-','-') -> comp y x ('-', _ ) -> LT (_ ,'-') -> GT - _ -> compare x y + _ -> comp x y + where +#ifdef UNICODE_COLLATION + comp a b = T.collate (T.collator T.Current) (T.pack a) (T.pack b) +#else + comp a b = compare a b +#endif data Form = Long @@ -195,6 +246,12 @@ | NotSet deriving ( Eq, Show, Read, Typeable, Data ) +data Gender + = Feminine + | Masculine + | Neuter + deriving ( Eq, Show, Read, Typeable, Data ) + data NumericForm = Numeric | Ordinal @@ -257,7 +314,7 @@ , verticalAlign :: String , textCase :: String , display :: String - , quotes :: Bool + , quotes :: Quote , stripPeriods :: Bool , noCase :: Bool , noDecor :: Bool @@ -265,9 +322,20 @@ instance Show Formatting where show _ = "emptyFormatting" +rmTitleCase :: Formatting -> Formatting +rmTitleCase f + | Formatting _ _ _ _ _ _ _ _ "title" _ _ _ _ _ <- f = f {textCase = []} + | otherwise = f + +data Quote + = NativeQuote + | ParsedQuote + | NoQuote + deriving ( Read, Eq, Ord, Typeable, Data ) + emptyFormatting :: Formatting emptyFormatting - = Formatting [] [] [] [] [] [] [] [] [] [] False False False False + = Formatting [] [] [] [] [] [] [] [] [] [] NoQuote False False False unsetAffixes :: Formatting -> Formatting unsetAffixes f = f {prefix = [], suffix = []} @@ -285,7 +353,7 @@ (bh `betterThen` ah) (bi `betterThen` ai) (bj `betterThen` aj) - (bk || ak) + (if bk == NoQuote then ak else bk) (bl || al) (bm || am) (bn || an) @@ -322,6 +390,7 @@ | OPan [Inline] | ODel String -- ^ A delimiter string. | OStr String Formatting -- ^ A simple 'String' + | OLabel String Formatting -- ^ A label used for roles | ONum Int Formatting -- ^ A number (used to count contributors) | OCitNum Int Formatting -- ^ The citation number | ODate [Output] -- ^ A (possibly) ranged date @@ -444,6 +513,8 @@ | ODel s <- o = FDel s | OStr [] _ <- o = FNull | OStr s f <- o = FS s f + | OLabel [] _ <- o = FNull + | OLabel s f <- o = FS s f | ODate os <- o = FO emptyFormatting (format os) | OYear s _ f <- o = FS s f | OYearSuf s _ _ f <- o = FS s f diff --git a/src/Text/CSL/Test.hs b/src/Text/CSL/Test.hs --- a/src/Text/CSL/Test.hs +++ b/src/Text/CSL/Test.hs @@ -24,7 +24,7 @@ import Control.Arrow import Control.Monad.State import Data.ByteString.Lazy.UTF8 ( fromString ) -import Data.Char (toLower) +import Data.Char (toLower, chr) import Data.List import Data.Maybe (isJust) import Data.Time @@ -242,13 +242,11 @@ (_, Just cs) -> cs _ -> [map (\r -> emptyCite { citeId = refId r }) $ testInput t] (BD cits bib) = citeproc opts style (testInput t) cites - fixCits = if isJust (testCitations t) - then flip (zipWith $ \c n -> ">>[" ++ show n ++ "] " ++ c) ([0..] :: [Int]) - else id - output = case testMode t of - "citation" -> unlines' . fixCits . map (pandocToHTML . renderPandoc_ style) $ cits + output = superscript $ + case testMode t of + "citation" -> unlines' . map (pandocToHTML . renderPandoc_ style) $ cits _ -> pandocBib . map (pandocToHTML . renderPandoc_ style) $ bib - return (output == testResult t, output) + return (output == getResult t, output) test :: FilePath -> IO Bool test = doTest readJsonFile 0 @@ -270,7 +268,7 @@ putStrLn' "++++++++++++++++++++++++++++++++++++++++++++++++++++++++" putStrLn' $ f ++ " failed!" putStrLn' "Expected:" - putStrLn' $ (testResult t) + putStrLn' $ getResult t putStrLn' "\nGot:" putStrLn' $ o when (v >= 3) $ putStrLn (show t) @@ -301,3 +299,44 @@ et <- getCurrentTime putStrLn $ (++) (formatTime defaultTimeLocale "%H:%M:%S" et) $ " <--------------END" putStrLn $ "Time: " ++ show (diffUTCTime et st) + +getResult :: Test -> String +getResult t + = if isJust (testCitations t) && testMode t == "citation" + then unlines' . map (\(a,b) -> drop (length (show b) + 5) a) . + flip zip ([0..] :: [Int]) . lines . testResult $ t + else testResult t + +superscript :: String -> String +superscript [] = [] +superscript (x:xs) + = let a = lookup x (map (first (chr . readNum)) sups) in + case a of + Nothing -> x : superscript xs + Just x' -> "" ++ [chr $ readNum x'] ++ "" ++ superscript xs + where + sups = [("0x00AA","0x0061"),("0x00B2","0x0032"),("0x00B3","0x0033"),("0x00B9","0x0031") + ,("0x00BA","0x006F"),("0x02B0","0x0068"),("0x02B1","0x0266"),("0x02B2","0x006A") + ,("0x02B3","0x0072"),("0x02B4","0x0279"),("0x02B5","0x027B"),("0x02B6","0x0281") + ,("0x02B7","0x0077"),("0x02B8","0x0079"),("0x02E0","0x0263"),("0x02E1","0x006C") + ,("0x02E2","0x0073"),("0x02E3","0x0078"),("0x02E4","0x0295"),("0x1D2C","0x0041") + ,("0x1D2D","0x00C6"),("0x1D2E","0x0042"),("0x1D30","0x0044"),("0x1D31","0x0045") + ,("0x1D32","0x018E"),("0x1D33","0x0047"),("0x1D34","0x0048"),("0x1D35","0x0049") + ,("0x1D36","0x004A"),("0x1D37","0x004B"),("0x1D38","0x004C"),("0x1D39","0x004D") + ,("0x1D3A","0x004E"),("0x1D3C","0x004F"),("0x1D3D","0x0222"),("0x1D3E","0x0050") + ,("0x1D3F","0x0052"),("0x1D40","0x0054"),("0x1D41","0x0055"),("0x1D42","0x0057") + ,("0x1D43","0x0061"),("0x1D44","0x0250"),("0x1D45","0x0251"),("0x1D46","0x1D02") + ,("0x1D47","0x0062"),("0x1D48","0x0064"),("0x1D49","0x0065"),("0x1D4A","0x0259") + ,("0x1D4B","0x025B"),("0x1D4C","0x025C"),("0x1D4D","0x0067"),("0x1D4F","0x006B") + ,("0x1D50","0x006D"),("0x1D51","0x014B"),("0x1D52","0x006F"),("0x1D53","0x0254") + ,("0x1D54","0x1D16"),("0x1D55","0x1D17"),("0x1D56","0x0070"),("0x1D57","0x0074") + ,("0x1D58","0x0075"),("0x1D59","0x1D1D"),("0x1D5A","0x026F"),("0x1D5B","0x0076") + ,("0x1D5C","0x1D25"),("0x1D5D","0x03B2"),("0x1D5E","0x03B3"),("0x1D5F","0x03B4") + ,("0x1D60","0x03C6"),("0x1D61","0x03C7"),("0x2070","0x0030"),("0x2071","0x0069") + ,("0x2074","0x0034"),("0x2075","0x0035"),("0x2076","0x0036"),("0x2077","0x0037") + ,("0x2078","0x0038"),("0x2079","0x0039"),("0x207A","0x002B"),("0x207B","0x2212") + ,("0x207C","0x003D"),("0x207D","0x0028"),("0x207E","0x0029"),("0x207F","0x006E") + ,("0x3194","0x4E09"),("0x3195","0x56DB"),("0x3196","0x4E0A"),("0x3197","0x4E2D") + ,("0x3198","0x4E0B"),("0x3199","0x7532"),("0x319A","0x4E59"),("0x319B","0x4E19") + ,("0x319C","0x4E01"),("0x319D","0x5929"),("0x319E","0x5730"),("0x319F","0x4EBA") + ,("0x02C0","0x0294"),("0x02C1","0x0295"),("0x06E5","0x0648"),("0x06E6","0x064A")]