diff --git a/changelog b/changelog --- a/changelog +++ b/changelog @@ -1,3 +1,25 @@ +pandoc-citeproc (0.8.1) + + * Improved performance in bibtex cross-reference resolution (#190). + * Take 'form' for date-part elements from date if not specified (#116). + Previously if the 'form' were unspecified in a date-part + element, it would go to the default 'long', even if the + date as a whole was 'numeric'. + * Transform only uppercase ASCII letters in titlecase transform. + This helps us pass one more citeproc test case. + * Cleaned up locator parsing code. + * Allow roman numeral locators (#173. + * Fixed missing dash between months in date ranges (#175). + * Fixed `strip-periods` (#185). + * Parse supplementary fields in CSL JSON "note" fields (#94). + * Support more biblatex markup in converting biblatex bibliographies: + `mkbibemph`, `mkbibitalic`, `mkbibbold`, `mkbibparens`, `mkbibbrackets`, + `autocap` (Nick Bart, #26). Treat reviews as articles. + * Add biblatex keys for additional languages (Nick Bart). + * Use HTTPS for DOI resolver (Andrew Dunning). + * Add biblatex keys for additional languages (Nick Bart): + ca-AD, da-DK, es-ES, fi-FI, it-IT, nl-NL, pl-PL, pt-PT, pt-BR, sv-SE + pandoc-citeproc (0.8.0.1) * Allow aeson 0.10.x (Felix Yan). diff --git a/man/man1/pandoc-citeproc.1 b/man/man1/pandoc-citeproc.1 --- a/man/man1/pandoc-citeproc.1 +++ b/man/man1/pandoc-citeproc.1 @@ -1,8 +1,8 @@ .\"t -.\" Automatically generated by Pandoc 1.15.1 +.\" Automatically generated by Pandoc 1.15.1.1 .\" .hy -.TH "pandoc\-citeproc" "1" "2015-10-13" "" "" +.TH "pandoc\-citeproc" "1" "2015-11-12" "pandoc-citeproc 0.8.1" "" .SH NAME .PP pandoc\-citeproc \- filter to resolve citations in a pandoc document. diff --git a/pandoc-citeproc.cabal b/pandoc-citeproc.cabal --- a/pandoc-citeproc.cabal +++ b/pandoc-citeproc.cabal @@ -1,5 +1,5 @@ name: pandoc-citeproc -version: 0.8.0.1 +version: 0.8.1 cabal-version: >= 1.12 synopsis: Supports using pandoc with citeproc @@ -96,6 +96,7 @@ bytestring, filepath, pandoc-types >= 1.12.3, tagsoup, aeson >= 0.7 && < 0.11, text, vector, xml-conduit >= 1.2 && < 1.4, + unordered-containers >= 0.2 && < 0.3, data-default, setenv >= 0.1 && < 0.2, split, yaml >= 0.8.8.7, pandoc >= 1.13 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 @@ -216,7 +216,7 @@ "doi" -> do d <- getStringVar "doi" let (prefixPart, linkPart) = T.breakOn (T.pack "http") (T.pack (prefix fm)) let u = if T.null linkPart - then "http://doi.org/" ++ d + then "https://doi.org/" ++ d else T.unpack linkPart ++ d if null d then return [] 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 @@ -99,7 +99,10 @@ diffDate (RefDate ya ma sa da _ _) (RefDate yb mb sb db _ _) = case () of _ | ya /= yb -> ["year","month","day"] - | ma /= mb -> ["month","day"] + | ma /= mb -> + if da == mempty && db == mempty + then ["month"] + else ["month","day"] | da /= db -> ["day"] | sa /= sb -> ["month"] | otherwise -> ["year","month","day"] 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 @@ -130,7 +130,8 @@ _ -> Formatted [] addFormatting :: Formatting -> Formatted -> Formatted -addFormatting f = addLink . addSuffix . pref . quote . font . text_case +addFormatting f = + addLink . addSuffix . pref . quote . font . text_case . strip_periods where addLink i = case hyperlink f of "" -> i url -> Formatted [Link (unFormatted i) (url, "")] @@ -143,6 +144,10 @@ , case lastInline (unFormatted i) of {(c:_) | isPunct c -> True; _ -> False} = i <> fromString (tail $ suffix f) | otherwise = i <> fromString (suffix f) + + strip_periods (Formatted ils) = Formatted (walk removePeriod ils) + removePeriod (Str xs) | stripPeriods f = Str (filter (/='.') xs) + removePeriod x = x quote (Formatted []) = Formatted [] quote (Formatted ils) = diff --git a/src/Text/CSL/Input/Bibtex.hs b/src/Text/CSL/Input/Bibtex.hs --- a/src/Text/CSL/Input/Bibtex.hs +++ b/src/Text/CSL/Input/Bibtex.hs @@ -64,7 +64,14 @@ where (command', contents') = break (=='{') xs command = trim command' contents = drop 1 $ reverse $ drop 1 $ reverse contents' - f "mkbibquote" ils = [Quoted DoubleQuote ils] + f "mkbibquote" ils = [Quoted DoubleQuote ils] + f "mkbibemph" ils = [Emph ils] + f "mkbibitalic" ils = [Emph ils] -- TODO: italic/=emph + f "mkbibbold" ils = [Strong ils] + f "mkbibparens" ils = [Str "("] ++ ils ++ [Str ")"] -- TODO: ... + f "mkbibbrackets" ils = [Str "["] ++ ils ++ [Str "]"] -- TODO: ... + -- ... both should be nestable & should work in year fields + f "autocap" ils = ils -- TODO: should work in year fields f "textnormal" ils = [Span ("",["nodecor"],[]) ils] f "bibstring" [Str s] = [Str $ resolveKey' lang s] f _ ils = [Span nullAttr ils] @@ -236,8 +243,8 @@ return (k',v) resolveCrossRef :: Bool -> [Item] -> Item -> Item -resolveCrossRef isBibtex entries entry = foldl go entry (fields entry) - where go entry' (key, val) = +resolveCrossRef isBibtex entries entry = foldr go entry (fields entry) + where go (key, val) entry' = if key == "crossref" || key == "xdata" then entry'{ fields = fields entry' ++ getXrefFields isBibtex entry entries val } @@ -333,7 +340,119 @@ where go (Str s) = Str $ resolveKey' lang s go x = x +-- biblatex localization keys, from files at +-- http://github.com/plk/biblatex/tree/master/tex/latex/biblatex/lbx +-- Some keys missing in these were added from csl locale files at +-- http://github.com/citation-style-language/locales -- labeled "csl" resolveKey' :: Lang -> String -> String +resolveKey' (Lang "ca" "AD") k = + case map toLower k of + "inpreparation" -> "en preparació" + "submitted" -> "enviat" + "forthcoming" -> "disponible en breu" + "inpress" -> "a impremta" + "prepublished" -> "pre-publicat" + "mathesis" -> "tesi de màster" + "phdthesis" -> "tesi doctoral" + "candthesis" -> "tesi de candidatura" + "techreport" -> "informe tècnic" + "resreport" -> "informe de recerca" + "software" -> "programari" + "datacd" -> "CD de dades" + "audiocd" -> "CD d’àudio" + "patent" -> "patent" + "patentde" -> "patent alemana" + "patenteu" -> "patent europea" + "patentfr" -> "patent francesa" + "patentuk" -> "patent britànica" + "patentus" -> "patent estatunidenca" + "patreq" -> "soŀlicitud de patent" + "patreqde" -> "soŀlicitud de patent alemana" + "patreqeu" -> "soŀlicitud de patent europea" + "patreqfr" -> "soŀlicitud de patent francesa" + "patrequk" -> "soŀlicitud de patent britànica" + "patrequs" -> "soŀlicitud de patent estatunidenca" + "countryde" -> "Alemanya" + "countryeu" -> "Unió Europea" + "countryep" -> "Unió Europea" + "countryfr" -> "França" + "countryuk" -> "Regne Unit" + "countryus" -> "Estats Units d’Amèrica" + "newseries" -> "sèrie nova" + "oldseries" -> "sèrie antiga" + _ -> k +resolveKey' (Lang "da" "DK") k = + case map toLower k of + -- "inpreparation" -> "" -- missing + -- "submitted" -> "" -- missing + "forthcoming" -> "kommende" -- csl + "inpress" -> "i tryk" -- csl + -- "prepublished" -> "" -- missing + "mathesis" -> "speciale" + "phdthesis" -> "ph.d.-afhandling" + "candthesis" -> "kandidatafhandling" + "techreport" -> "teknisk rapport" + "resreport" -> "forskningsrapport" + "software" -> "software" + "datacd" -> "data-cd" + "audiocd" -> "lyd-cd" + "patent" -> "patent" + "patentde" -> "tysk patent" + "patenteu" -> "europæisk patent" + "patentfr" -> "fransk patent" + "patentuk" -> "britisk patent" + "patentus" -> "amerikansk patent" + "patreq" -> "ansøgning om patent" + "patreqde" -> "ansøgning om tysk patent" + "patreqeu" -> "ansøgning om europæisk patent" + "patreqfr" -> "ansøgning om fransk patent" + "patrequk" -> "ansøgning om britisk patent" + "patrequs" -> "ansøgning om amerikansk patent" + "countryde" -> "Tyskland" + "countryeu" -> "Europæiske Union" + "countryep" -> "Europæiske Union" + "countryfr" -> "Frankrig" + "countryuk" -> "Storbritanien" + "countryus" -> "USA" + "newseries" -> "ny serie" + "oldseries" -> "gammel serie" + _ -> k +resolveKey' (Lang "de" "DE") k = + case map toLower k of + "inpreparation" -> "in Vorbereitung" + "submitted" -> "eingereicht" + "forthcoming" -> "im Erscheinen" + "inpress" -> "im Druck" + "prepublished" -> "Vorveröffentlichung" + "mathesis" -> "Magisterarbeit" + "phdthesis" -> "Dissertation" + -- "candthesis" -> "" -- missing + "techreport" -> "Technischer Bericht" + "resreport" -> "Forschungsbericht" + "software" -> "Computer-Software" + "datacd" -> "CD-ROM" + "audiocd" -> "Audio-CD" + "patent" -> "Patent" + "patentde" -> "deutsches Patent" + "patenteu" -> "europäisches Patent" + "patentfr" -> "französisches Patent" + "patentuk" -> "britisches Patent" + "patentus" -> "US-Patent" + "patreq" -> "Patentanmeldung" + "patreqde" -> "deutsche Patentanmeldung" + "patreqeu" -> "europäische Patentanmeldung" + "patreqfr" -> "französische Patentanmeldung" + "patrequk" -> "britische Patentanmeldung" + "patrequs" -> "US-Patentanmeldung" + "countryde" -> "Deutschland" + "countryeu" -> "Europäische Union" + "countryep" -> "Europäische Union" + "countryfr" -> "Frankreich" + "countryuk" -> "Großbritannien" + "countryus" -> "USA" + "newseries" -> "neue Folge" + "oldseries" -> "alte Folge" + _ -> k resolveKey' (Lang "en" "US") k = case map toLower k of "audiocd" -> "audio CD" @@ -382,42 +501,79 @@ "techreport" -> "technical report" "volume" -> "vol." _ -> k -resolveKey' (Lang "de" "DE") k = +resolveKey' (Lang "es" "ES") k = case map toLower k of - "inpreparation" -> "in Vorbereitung" - "submitted" -> "eingereicht" - "forthcoming" -> "im Erscheinen" - "inpress" -> "im Druck" - "prepublished" -> "Vorveröffentlichung" - "mathesis" -> "Magisterarbeit" - "phdthesis" -> "Dissertation" + -- "inpreparation" -> "" -- missing + -- "submitted" -> "" -- missing + "forthcoming" -> "previsto" -- csl + "inpress" -> "en imprenta" -- csl + -- "prepublished" -> "" -- missing + "mathesis" -> "Tesis de licenciatura" + "phdthesis" -> "Tesis doctoral" -- "candthesis" -> "" -- missing - "techreport" -> "Technischer Bericht" - "resreport" -> "Forschungsbericht" - "software" -> "Computer-Software" - "datacd" -> "CD-ROM" - "audiocd" -> "Audio-CD" - "patent" -> "Patent" - "patentde" -> "deutsches Patent" - "patenteu" -> "europäisches Patent" - "patentfr" -> "französisches Patent" - "patentuk" -> "britisches Patent" - "patentus" -> "US-Patent" - "patreq" -> "Patentanmeldung" - "patreqde" -> "deutsche Patentanmeldung" - "patreqeu" -> "europäische Patentanmeldung" - "patreqfr" -> "französische Patentanmeldung" - "patrequk" -> "britische Patentanmeldung" - "patrequs" -> "US-Patentanmeldung" - "countryde" -> "Deutschland" - "countryeu" -> "Europäische Union" - "countryep" -> "Europäische Union" - "countryfr" -> "Frankreich" - "countryuk" -> "Großbritannien" - "countryus" -> "USA" - "newseries" -> "neue Folge" - "oldseries" -> "alte Folge" + "techreport" -> "informe técnico" + -- "resreport" -> "" -- missing + -- "software" -> "" -- missing + -- "datacd" -> "" -- missing + -- "audiocd" -> "" -- missing + "patent" -> "patente" + "patentde" -> "patente alemana" + "patenteu" -> "patente europea" + "patentfr" -> "patente francesa" + "patentuk" -> "patente británica" + "patentus" -> "patente americana" + "patreq" -> "solicitud de patente" + "patreqde" -> "solicitud de patente alemana" + "patreqeu" -> "solicitud de patente europea" + "patreqfr" -> "solicitud de patente francesa" + "patrequk" -> "solicitud de patente británica" + "patrequs" -> "solicitud de patente americana" + "countryde" -> "Alemania" + "countryeu" -> "Unión Europea" + "countryep" -> "Unión Europea" + "countryfr" -> "Francia" + "countryuk" -> "Reino Unido" + "countryus" -> "Estados Unidos de América" + "newseries" -> "nueva época" + "oldseries" -> "antigua época" _ -> k +resolveKey' (Lang "fi" "FI") k = + case map toLower k of + -- "inpreparation" -> "" -- missing + -- "submitted" -> "" -- missing + "forthcoming" -> "tulossa" -- csl + "inpress" -> "painossa" -- csl + -- "prepublished" -> "" -- missing + "mathesis" -> "tutkielma" + "phdthesis" -> "tohtorinväitöskirja" + "candthesis" -> "kandidat" + "techreport" -> "tekninen raportti" + "resreport" -> "tutkimusraportti" + "software" -> "ohjelmisto" + "datacd" -> "data-CD" + "audiocd" -> "ääni-CD" + "patent" -> "patentti" + "patentde" -> "saksalainen patentti" + "patenteu" -> "Euroopan Unionin patentti" + "patentfr" -> "ranskalainen patentti" + "patentuk" -> "englantilainen patentti" + "patentus" -> "yhdysvaltalainen patentti" + "patreq" -> "patenttihakemus" + "patreqde" -> "saksalainen patenttihakemus" + "patreqeu" -> "Euroopan Unionin patenttihakemus" + "patreqfr" -> "ranskalainen patenttihakemus" + "patrequk" -> "englantilainen patenttihakemus" + "patrequs" -> "yhdysvaltalainen patenttihakemus" + "countryde" -> "Saksa" + "countryeu" -> "Euroopan Unioni" + "countryep" -> "Euroopan Unioni" + "countryfr" -> "Ranska" + "countryuk" -> "Iso-Britannia" + "countryus" -> "Yhdysvallat" + "newseries" -> "uusi sarja" + "oldseries" -> "vanha sarja" + _ -> k + resolveKey' (Lang "fr" "FR") k = case map toLower k of "inpreparation" -> "en préparation" @@ -454,6 +610,216 @@ "newseries" -> "nouvelle série" "oldseries" -> "ancienne série" _ -> k +resolveKey' (Lang "it" "IT") k = + case map toLower k of + -- "inpreparation" -> "" -- missing + -- "submitted" -> "" -- missing + "forthcoming" -> "futuro" -- csl + "inpress" -> "in stampa" + -- "prepublished" -> "" -- missing + "mathesis" -> "tesi di laurea magistrale" + "phdthesis" -> "tesi di dottorato" + -- "candthesis" -> "" -- missing + "techreport" -> "rapporto tecnico" + "resreport" -> "rapporto di ricerca" + -- "software" -> "" -- missing + -- "datacd" -> "" -- missing + -- "audiocd" -> "" -- missing + "patent" -> "brevetto" + "patentde" -> "brevetto tedesco" + "patenteu" -> "brevetto europeo" + "patentfr" -> "brevetto francese" + "patentuk" -> "brevetto britannico" + "patentus" -> "brevetto americano" + "patreq" -> "brevetto richiesto" + "patreqde" -> "brevetto tedesco richiesto" + "patreqeu" -> "brevetto europeo richiesto" + "patreqfr" -> "brevetto francese richiesto" + "patrequk" -> "brevetto britannico richiesto" + "patrequs" -> "brevetto U.S.A. richiesto" + "countryde" -> "Germania" + "countryeu" -> "Unione Europea" + "countryep" -> "Unione Europea" + "countryfr" -> "Francia" + "countryuk" -> "Regno Unito" + "countryus" -> "Stati Uniti d’America" + "newseries" -> "nuova serie" + "oldseries" -> "vecchia serie" + _ -> k +resolveKey' (Lang "nl" "NL") k = + case map toLower k of + "inpreparation" -> "in voorbereiding" + "submitted" -> "ingediend" + "forthcoming" -> "onderweg" + "inpress" -> "in druk" + "prepublished" -> "voorpublicatie" + "mathesis" -> "masterscriptie" + "phdthesis" -> "proefschrift" + -- "candthesis" -> "" -- missing + "techreport" -> "technisch rapport" + "resreport" -> "onderzoeksrapport" + "software" -> "computersoftware" + "datacd" -> "cd-rom" + "audiocd" -> "audio-cd" + "patent" -> "patent" + "patentde" -> "Duits patent" + "patenteu" -> "Europees patent" + "patentfr" -> "Frans patent" + "patentuk" -> "Brits patent" + "patentus" -> "Amerikaans patent" + "patreq" -> "patentaanvraag" + "patreqde" -> "Duitse patentaanvraag" + "patreqeu" -> "Europese patentaanvraag" + "patreqfr" -> "Franse patentaanvraag" + "patrequk" -> "Britse patentaanvraag" + "patrequs" -> "Amerikaanse patentaanvraag" + "countryde" -> "Duitsland" + "countryeu" -> "Europese Unie" + "countryep" -> "Europese Unie" + "countryfr" -> "Frankrijk" + "countryuk" -> "Verenigd Koninkrijk" + "countryus" -> "Verenigde Staten van Amerika" + "newseries" -> "nieuwe reeks" + "oldseries" -> "oude reeks" + _ -> k +resolveKey' (Lang "pl" "PL") k = + case map toLower k of + "inpreparation" -> "przygotowanie" + "submitted" -> "prezentacja" + "forthcoming" -> "przygotowanie" + "inpress" -> "wydrukowane" + "prepublished" -> "przedwydanie" + "mathesis" -> "praca magisterska" + "phdthesis" -> "praca doktorska" + "techreport" -> "sprawozdanie techniczne" + "resreport" -> "sprawozdanie naukowe" + "software" -> "oprogramowanie" + "datacd" -> "CD-ROM" + "audiocd" -> "audio CD" + "patent" -> "patent" + "patentde" -> "patent Niemiec" + "patenteu" -> "patent Europy" + "patentfr" -> "patent Francji" + "patentuk" -> "patent Wielkiej Brytanji" + "patentus" -> "patent USA" + "patreq" -> "podanie na patent" + "patreqeu" -> "podanie na patent Europy" + "patrequs" -> "podanie na patent USA" + "countryde" -> "Niemcy" + "countryeu" -> "Unia Europejska" + "countryep" -> "Unia Europejska" + "countryfr" -> "Francja" + "countryuk" -> "Wielka Brytania" + "countryus" -> "Stany Zjednoczone Ameryki" + "newseries" -> "nowa serja" + "oldseries" -> "stara serja" + _ -> k +resolveKey' (Lang "pt" "PT") k = + case map toLower k of + -- "candthesis" -> "" -- missing + "techreport" -> "relatório técnico" + "resreport" -> "relatório de pesquisa" + "software" -> "software" + "datacd" -> "CD-ROM" + "patent" -> "patente" + "patentde" -> "patente alemã" + "patenteu" -> "patente européia" + "patentfr" -> "patente francesa" + "patentuk" -> "patente britânica" + "patentus" -> "patente americana" + "patreq" -> "pedido de patente" + "patreqde" -> "pedido de patente alemã" + "patreqeu" -> "pedido de patente européia" + "patreqfr" -> "pedido de patente francesa" + "patrequk" -> "pedido de patente britânica" + "patrequs" -> "pedido de patente americana" + "countryde" -> "Alemanha" + "countryeu" -> "União Europeia" + "countryep" -> "União Europeia" + "countryfr" -> "França" + "countryuk" -> "Reino Unido" + "countryus" -> "Estados Unidos da América" + "newseries" -> "nova série" + "oldseries" -> "série antiga" + -- "inpreparation" -> "" -- missing + "forthcoming" -> "a publicar" -- csl + "inpress" -> "na imprensa" + -- "prepublished" -> "" -- missing + "mathesis" -> "tese de mestrado" + "phdthesis" -> "tese de doutoramento" + "audiocd" -> "CD áudio" + _ -> k +resolveKey' (Lang "pt" "BR") k = + case map toLower k of + -- "candthesis" -> "" -- missing + "techreport" -> "relatório técnico" + "resreport" -> "relatório de pesquisa" + "software" -> "software" + "datacd" -> "CD-ROM" + "patent" -> "patente" + "patentde" -> "patente alemã" + "patenteu" -> "patente européia" + "patentfr" -> "patente francesa" + "patentuk" -> "patente britânica" + "patentus" -> "patente americana" + "patreq" -> "pedido de patente" + "patreqde" -> "pedido de patente alemã" + "patreqeu" -> "pedido de patente européia" + "patreqfr" -> "pedido de patente francesa" + "patrequk" -> "pedido de patente britânica" + "patrequs" -> "pedido de patente americana" + "countryde" -> "Alemanha" + "countryeu" -> "União Europeia" + "countryep" -> "União Europeia" + "countryfr" -> "França" + "countryuk" -> "Reino Unido" + "countryus" -> "Estados Unidos da América" + "newseries" -> "nova série" + "oldseries" -> "série antiga" + "inpreparation" -> "em preparação" + "forthcoming" -> "aceito para publicação" + "inpress" -> "no prelo" + "prepublished" -> "pré-publicado" + "mathesis" -> "dissertação de mestrado" + "phdthesis" -> "tese de doutorado" + "audiocd" -> "CD de áudio" + _ -> k +resolveKey' (Lang "sv" "SE") k = + case map toLower k of + -- "inpreparation" -> "" -- missing + -- "submitted" -> "" -- missing + "forthcoming" -> "kommande" -- csl + "inpress" -> "i tryck" -- csl + -- "prepublished" -> "" -- missing + "mathesis" -> "examensarbete" + "phdthesis" -> "doktorsavhandling" + "candthesis" -> "kandidatavhandling" + "techreport" -> "teknisk rapport" + "resreport" -> "forskningsrapport" + "software" -> "datorprogram" + "datacd" -> "data-cd" + "audiocd" -> "ljud-cd" + "patent" -> "patent" + "patentde" -> "tyskt patent" + "patenteu" -> "europeiskt patent" + "patentfr" -> "franskt patent" + "patentuk" -> "brittiskt patent" + "patentus" -> "amerikanskt patent" + "patreq" -> "patentansökan" + "patreqde" -> "ansökan om tyskt patent" + "patreqeu" -> "ansökan om europeiskt patent" + "patreqfr" -> "ansökan om franskt patent" + "patrequk" -> "ansökan om brittiskt patent" + "patrequs" -> "ansökan om amerikanskt patent" + "countryde" -> "Tyskland" + "countryeu" -> "Europeiska unionen" + "countryep" -> "Europeiska unionen" + "countryfr" -> "Frankrike" + "countryuk" -> "Storbritannien" + "countryus" -> "USA" + "newseries" -> "ny följd" + "oldseries" -> "gammal följd" + _ -> k resolveKey' _ k = resolveKey' (Lang "en" "US") k parseMonth :: String -> String @@ -949,7 +1315,7 @@ -- FIXME: add same for editora, editorb, editorc -- titles - let isArticle = et `elem` ["article", "periodical", "suppperiodical"] + let isArticle = et `elem` ["article", "periodical", "suppperiodical", "review"] let isPeriodical = et == "periodical" let isChapterlike = et `elem` ["inbook","incollection","inproceedings","inreference","bookinbook"] diff --git a/src/Text/CSL/Pandoc.hs b/src/Text/CSL/Pandoc.hs --- a/src/Text/CSL/Pandoc.hs +++ b/src/Text/CSL/Pandoc.hs @@ -5,7 +5,7 @@ import Text.Pandoc import Text.Pandoc.Walk import Text.Pandoc.Builder (setMeta, deleteMeta, Inlines, cite) -import Text.Pandoc.Shared (stringify, trim) +import Text.Pandoc.Shared (stringify) import Text.HTML.TagSoup.Entity (lookupEntity) import qualified Data.ByteString.Lazy as L import System.SetEnv (setEnv) @@ -29,7 +29,7 @@ import Control.Monad.State import System.FilePath import System.Directory (doesFileExist, getAppUserDataDirectory) -import Text.CSL.Util (findFile, splitStrWhen, tr') +import Text.CSL.Util (findFile, splitStrWhen, tr', parseRomanNumeral, trim) import System.IO.Error (isDoesNotExistError) -- | Process a 'Pandoc' document by adding citations formatted @@ -365,15 +365,25 @@ pLocator locMap = try $ do optional $ pMatch (== Str ",") optional pSpace - rawLoc <- many (notFollowedBy (pWordWithDigits True) >> anyToken) - la <- case trim (stringify rawLoc) of - "" -> lookAhead (optional pSpace >> pDigit) >> return "page" - s -> maybe mzero return $ parseLocator locMap s + la <- try (do ts <- many1 (notFollowedBy (pWordWithDigits True) >> anyToken) + case M.lookup (trim (stringify ts)) locMap of + Just l -> return l + Nothing -> mzero) + <|> (lookAhead pDigit >> return "page") g <- pWordWithDigits True gs <- many (pWordWithDigits False) let lo = concat (g:gs) return (la, lo) +pRoman :: Parsec [Inline] st String +pRoman = try $ do + t <- anyToken + case t of + Str xs -> case parseRomanNumeral xs of + Nothing -> mzero + Just _ -> return xs + _ -> mzero + -- we want to capture: 123, 123A, C22, XVII, 33-44, 22-33; 22-11 pWordWithDigits :: Bool -> Parsec [Inline] st String pWordWithDigits isfirst = try $ do @@ -381,9 +391,13 @@ then return "" else stringify `fmap` pLocatorPunct sp <- option "" (pSpace >> return " ") - r <- many1 (notFollowedBy pSpace >> notFollowedBy pLocatorPunct >> anyToken) - let s = stringify r - guard $ any isDigit s || all (`elem` ("IVXLCM" :: String)) s + s <- pRoman <|> + try (do ts <- many1 (notFollowedBy pSpace >> + notFollowedBy pLocatorPunct >> + anyToken) + let ts' = stringify ts + guard (any isDigit ts') + return ts') return $ punct ++ sp ++ s pDigit :: Parsec [Inline] st () @@ -401,9 +415,6 @@ isLocatorPunct _ = False type LocatorMap = M.Map String String - -parseLocator :: LocatorMap -> String -> Maybe String -parseLocator locMap s = M.lookup s locMap locatorMap :: Style -> LocatorMap locatorMap sty = 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 @@ -219,14 +219,17 @@ _ -> NoFormDate format = getFormatting cur delim = stringAttr "delimiter" cur - parts = cur $/ get "date-part" &| parseDatePart + parts = cur $/ get "date-part" &| (parseDatePart form) partsAttr = stringAttr "date-parts" cur -parseDatePart :: Cursor -> DatePart -parseDatePart cur = +parseDatePart :: DateForm -> Cursor -> DatePart +parseDatePart defaultForm cur = DatePart { dpName = stringAttr "name" cur , dpForm = case stringAttr "form" cur of - "" -> "long" + "" -> case defaultForm of + TextDate -> "long" + NumericDate -> "numeric" + _ -> "long" x -> x , dpRangeDelim = case stringAttr "range-delimiter" cur of "" -> "-" diff --git a/src/Text/CSL/Reference.hs b/src/Text/CSL/Reference.hs --- a/src/Text/CSL/Reference.hs +++ b/src/Text/CSL/Reference.hs @@ -46,11 +46,13 @@ import Data.Generics hiding (Generic) import GHC.Generics (Generic) import Data.Aeson hiding (Value) +import qualified Data.Aeson as Aeson import Data.Aeson.Types (Parser) import qualified Data.Yaml.Builder as Y import Data.Yaml.Builder (ToYaml(..)) import Control.Applicative ((<|>)) import qualified Data.Text as T +import Data.Text (Text) import qualified Data.Vector as V import Data.Char (toLower, isDigit) import Text.CSL.Style hiding (Number) @@ -59,6 +61,9 @@ (&=), mapping') import Text.Pandoc (Inline(Str)) import Data.String +import qualified Text.Parsec as P +import qualified Text.Parsec.String as P +import qualified Data.HashMap.Strict as H newtype Literal = Literal { unLiteral :: String } deriving ( Show, Read, Eq, Data, Typeable, Monoid, Generic ) @@ -366,7 +371,9 @@ } deriving ( Eq, Show, Read, Typeable, Data, Generic ) instance FromJSON Reference where - parseJSON (Object v) = addPageFirst <$> (Reference <$> + parseJSON (Object v') = do + v <- parseSuppFields v' + addPageFirst <$> (Reference <$> v .:? "id" .!= "" <*> v .:? "type" .!= NoType <*> v .:? "author" .!= [] <*> @@ -452,6 +459,31 @@ takeFirstNum (page ref) } else ref parseJSON _ = fail "Could not parse Reference" + +-- Syntax for adding supplementary fields in note variable +-- {:authority:Superior Court of California}{:section:A}{:original-date:1777} +-- see http://gsl-nagoya-u.net/http/pub/citeproc-doc.html#supplementary-fields +parseSuppFields :: Aeson.Object -> Parser Aeson.Object +parseSuppFields o = do + nt <- o .: "note" <|> return ("" :: String) + case P.parse noteFields "note" nt of + Left err -> fail (show err) + Right fs -> return $ foldr (\(k,v) x -> H.insert k v x) o fs + +noteFields :: P.Parser [(Text, Aeson.Value)] +noteFields = do + -- TODO - actually parse the fields + fs <- P.many noteField + rest <- P.getInput + return (("note", Aeson.String (T.pack rest)) : fs) + +noteField :: P.Parser (Text, Aeson.Value) +noteField = P.try $ do + P.char '{' + P.char ':' + k <- P.manyTill (P.letter <|> P.char '-') (P.char ':') + v <- P.manyTill P.anyChar (P.char '}') + return (T.pack k, Aeson.String (T.pack v)) instance ToJSON Reference where toJSON ref = object' [ diff --git a/src/Text/CSL/Util.hs b/src/Text/CSL/Util.hs --- a/src/Text/CSL/Util.hs +++ b/src/Text/CSL/Util.hs @@ -42,12 +42,14 @@ , findFile , (&=) , mapping' + , parseRomanNumeral ) where import Data.Aeson import Data.Aeson.Types (Parser) import Data.Text (Text) import qualified Data.Text as T -import Data.Char (toLower, toUpper, isLower, isUpper, isPunctuation) +import Data.Char (toLower, toUpper, isLower, isUpper, isPunctuation, + isLetter, isAscii) import qualified Data.Traversable import Text.Pandoc.Shared (safeRead, stringify) import Text.Pandoc.Walk (walk) @@ -60,6 +62,8 @@ import System.Directory (doesFileExist) import qualified Data.Yaml.Builder as Y import Data.Yaml.Builder (ToYaml(..), YamlBuilder) +import qualified Text.Parsec as P + #ifdef TRACE import qualified Debug.Trace import Text.Show.Pretty (ppShow) @@ -211,9 +215,9 @@ where tc (Str (x:xs)) = do st <- get return $ case st of - WordBoundary -> if isShortWord (x:xs) + WordBoundary -> if isShortWord (x:xs) || + not (isAscii x && isLetter x) then Str (x:xs) - -- or? map toLower (x:xs) else Str (toUpper x : xs) SentenceBoundary -> Str (toUpper x : xs) _ -> Str (x:xs) @@ -381,3 +385,43 @@ mapping' :: [[(Text, YamlBuilder)] -> [(Text, YamlBuilder)]] -> YamlBuilder mapping' = Y.mapping . foldr ($) [] + +-- TODO: romanNumeral is defined in Text.Pandoc.Parsing, but it's +-- not exported there. Eventually we should remove this code duplication +-- by exporting something from pandoc. + +parseRomanNumeral :: String -> Maybe Int +parseRomanNumeral s = case P.parse (pRomanNumeral <* P.eof) "" s of + Left _ -> Nothing + Right x -> Just x + +-- | Parses a roman numeral (uppercase or lowercase), returns number. +pRomanNumeral :: P.Stream s m Char => P.ParsecT s st m Int +pRomanNumeral = do + let lowercaseRomanDigits = ['i','v','x','l','c','d','m'] + let uppercaseRomanDigits = ['I','V','X','L','C','D','M'] + c <- P.lookAhead $ P.oneOf (lowercaseRomanDigits ++ uppercaseRomanDigits) + let romanDigits = if isUpper c + then uppercaseRomanDigits + else lowercaseRomanDigits + let [one, five, ten, fifty, hundred, fivehundred, thousand] = + map P.char romanDigits + thousands <- P.many thousand >>= (return . (1000 *) . length) + ninehundreds <- P.option 0 $ P.try $ hundred >> thousand >> return 900 + fivehundreds <- P.many fivehundred >>= (return . (500 *) . length) + fourhundreds <- P.option 0 $ P.try $ hundred >> fivehundred >> return 400 + hundreds <- P.many hundred >>= (return . (100 *) . length) + nineties <- P.option 0 $ P.try $ ten >> hundred >> return 90 + fifties <- P.many fifty >>= (return . (50 *) . length) + forties <- P.option 0 $ P.try $ ten >> fifty >> return 40 + tens <- P.many ten >>= (return . (10 *) . length) + nines <- P.option 0 $ P.try $ one >> ten >> return 9 + fives <- P.many five >>= (return . (5 *) . length) + fours <- P.option 0 $ P.try $ one >> five >> return 4 + ones <- P.many one >>= (return . length) + let total = thousands + ninehundreds + fivehundreds + fourhundreds + + hundreds + nineties + fifties + forties + tens + nines + + fives + fours + ones + if total == 0 + then fail "not a roman numeral" + else return total diff --git a/tests/biblio2yaml/kastenholz.biblatex b/tests/biblio2yaml/kastenholz.biblatex --- a/tests/biblio2yaml/kastenholz.biblatex +++ b/tests/biblio2yaml/kastenholz.biblatex @@ -11,7 +11,7 @@ Methodologyindependent Ionic Solvation Free Energies from Molecular Simulations: I. the Electrostatic Potential in Molecular Liquids.” *J. Chem. Phys.* 124. -doi:[10.1063/1.2172593](http://doi.org/10.1063/1.2172593 "10.1063/1.2172593"). +doi:[10.1063/1.2172593](https://doi.org/10.1063/1.2172593 "10.1063/1.2172593"). Formatted with pandoc and apa.csl, 2013-10-23: @@ -22,7 +22,7 @@ methodologyindependent ionic solvation free energies from molecular simulations: I. the electrostatic potential in molecular liquids. *J. Chem. Phys.*, *124*. -doi:[10.1063/1.2172593](http://doi.org/10.1063/1.2172593 "10.1063/1.2172593") +doi:[10.1063/1.2172593](https://doi.org/10.1063/1.2172593 "10.1063/1.2172593") NOTES: diff --git a/tests/biblio2yaml/sigfridsson.biblatex b/tests/biblio2yaml/sigfridsson.biblatex --- a/tests/biblio2yaml/sigfridsson.biblatex +++ b/tests/biblio2yaml/sigfridsson.biblatex @@ -9,7 +9,7 @@ Sigfridsson, Emma, and Ulf Ryde. 1998. “Comparison of Methods for Deriving Atomic Charges from the Electrostatic Potential and Moments.” *Journal of Computational Chemistry* 19 (4): 377–395. -doi:[10.1002/(SICI)1096-987X(199803)19:4\<377::AID-JCC1\>3.0.CO;2-P](http://doi.org/10.1002/(SICI)1096-987X(199803)19:4<377::AID-JCC1>3.0.CO;2-P "10.1002/(SICI)1096-987X(199803)19:4<377::AID-JCC1>3.0.CO;2-P"). +doi:[10.1002/(SICI)1096-987X(199803)19:4\<377::AID-JCC1\>3.0.CO;2-P](https://doi.org/10.1002/(SICI)1096-987X(199803)19:4<377::AID-JCC1>3.0.CO;2-P "10.1002/(SICI)1096-987X(199803)19:4<377::AID-JCC1>3.0.CO;2-P"). Formatted with pandoc and apa.csl, 2013-10-23: @@ -19,7 +19,7 @@ Sigfridsson, E., & Ryde, U. (1998). Comparison of methods for deriving atomic charges from the electrostatic potential and moments. *Journal of Computational Chemistry*, *19*(4), 377–395. -doi:[10.1002/(SICI)1096-987X(199803)19:4\<377::AID-JCC1\>3.0.CO;2-P](http://doi.org/10.1002/(SICI)1096-987X(199803)19:4<377::AID-JCC1>3.0.CO;2-P "10.1002/(SICI)1096-987X(199803)19:4<377::AID-JCC1>3.0.CO;2-P") +doi:[10.1002/(SICI)1096-987X(199803)19:4\<377::AID-JCC1\>3.0.CO;2-P](https://doi.org/10.1002/(SICI)1096-987X(199803)19:4<377::AID-JCC1>3.0.CO;2-P "10.1002/(SICI)1096-987X(199803)19:4<377::AID-JCC1>3.0.CO;2-P") NOTES: diff --git a/tests/issue175.expected.native b/tests/issue175.expected.native new file mode 100644 --- /dev/null +++ b/tests/issue175.expected.native @@ -0,0 +1,7 @@ +Pandoc (Meta {unMeta = fromList [("references",MetaList [MetaMap (fromList [("author",MetaList [MetaMap (fromList [("family",MetaInlines [Str "Doe"]),("given",MetaInlines [Str "Jane"])])]),("container-title",MetaInlines [Str "A",Space,Str "magazine"]),("id",MetaInlines [Str "item1"]),("issued",MetaList [MetaMap (fromList [("month",MetaString "1"),("year",MetaString "2011")]),MetaMap (fromList [("month",MetaString "2"),("year",MetaString "2011")])]),("page",MetaInlines [Str "33-44"]),("title",MetaInlines [Str "A",Space,Str "title"]),("type",MetaInlines [Str "article-magazine"])])])]}) +[Header 2 ("missing-en-dash-between-months",[],[]) [Str "Missing",Space,Str "en-dash",Space,Str "between",Space,Str "months"] +,Para [Str "Foo",Space,Cite [Citation {citationId = "item1", citationPrefix = [], citationSuffix = [], citationMode = NormalCitation, citationNoteNum = 0, citationHash = 1}] [Str "(",Str "Doe",Space,Str "2011",Str ")"],Str "."] +,Header 2 ("expected",[],[]) [Str "Expected"] +,BlockQuote + [Para [Str "Doe,",Space,Str "Jane.",Space,Str "2011.",Space,Str "\8220A",Space,Str "Title.\8221",Space,Emph [Str "A",Space,Str "Magazine"],Str ",",Space,Str "January\8211February."]] +,Div ("refs",["references"],[]) [Div ("ref-item1",[],[]) [Para [Str "Doe",Str ",",Space,Str "Jane",Str ".",Space,Str "2011",Str ".",Space,Str "\8220",Str "A",Space,Str "Title",Str ".",Str "\8221",Space,Emph [Str "A",Space,Str "Magazine"],Str ",",Space,Str "January",Str "\8211",Str "February",Str "."]]]] diff --git a/tests/issue175.in.native b/tests/issue175.in.native new file mode 100644 --- /dev/null +++ b/tests/issue175.in.native @@ -0,0 +1,6 @@ +Pandoc (Meta {unMeta = fromList [("references",MetaList [MetaMap (fromList [("author",MetaList [MetaMap (fromList [("family",MetaInlines [Str "Doe"]),("given",MetaInlines [Str "Jane"])])]),("container-title",MetaInlines [Str "A",Space,Str "magazine"]),("id",MetaInlines [Str "item1"]),("issued",MetaList [MetaMap (fromList [("month",MetaString "1"),("year",MetaString "2011")]),MetaMap (fromList [("month",MetaString "2"),("year",MetaString "2011")])]),("page",MetaInlines [Str "33-44"]),("title",MetaInlines [Str "A",Space,Str "title"]),("type",MetaInlines [Str "article-magazine"])])])]}) +[Header 2 ("missing-en-dash-between-months",[],[]) [Str "Missing",Space,Str "en-dash",Space,Str "between",Space,Str "months"] +,Para [Str "Foo",Space,Cite [Citation {citationId = "item1", citationPrefix = [], citationSuffix = [], citationMode = NormalCitation, citationNoteNum = 0, citationHash = 0}] [Str "[@item1]"],Str "."] +,Header 2 ("expected",[],[]) [Str "Expected"] +,BlockQuote + [Para [Str "Doe,",Space,Str "Jane.",Space,Str "2011.",Space,Str "\8220A",Space,Str "Title.\8221",Space,Emph [Str "A",Space,Str "Magazine"],Str ",",Space,Str "January\8211February."]]]