@flatfile/plugin-delimiter-extractor/dist/index.cjs.map

A plugin for parsing .delimiter files in Flatfile.

{"version":3,"sources":["../src/header.detection.ts","../src/parser.ts","../src/index.ts"],"names":["ROWS_TO_SEARCH_FOR_HEADER","indexToLetters","index","letters","result","headersToLetters","headers","_","Headerizer","options","ExplicitHeaders","SpecificRows","DataRowAndSubHeaderDetection","OriginalDetector","countNonEmptyCells","row","cell","likelyContainsData","dataStream","currentRow","skip","header","detector","stream","encoding","callback","resolve","reject","error","maxRow","rows","previousRow","fuzzyHeader","fuzzySkip","i","word","parseBuffer","buffer","skipEmptyLines","fileContents","Papa","transform","value","extractValues","data","headerizer","headerStream","Readable","isNullOrWhitespace","columnHeaders","prependNonUniqueHeaderColumns","mappedRow","mapKeys","key","mapValues","metadata","record","counts","cleanValue","NativeFileTypes","DelimiterExtractor","fileExt","Extractor","delimiterParser"],"mappings":";;;;;;;;;;;;AAEO,IAAMA,CAAAA,CAA4B,GAyC5BC,CAAkBC,CAAAA,CAAAA,EAA0B,CACvD,IAAMC,CAAU,CAAA,4BAAA,CACZC,CAAS,CAAA,EAAA,CAEb,KAAOF,CAAS,EAAA,CAAA,EACdE,CAASD,CAAAA,CAAAA,CAAQD,CAAQ,CAAA,EAAE,CAAIE,CAAAA,CAAAA,CAC/BF,CAAQ,CAAA,IAAA,CAAK,KAAMA,CAAAA,CAAAA,CAAQ,EAAE,CAAA,CAAI,CAGnC,CAAA,OAAOE,CACT,CAEaC,CAAAA,CAAAA,CAAoBC,CACxBA,EAAAA,CAAAA,CAAQ,GAAI,CAAA,CAACC,CAAGL,CAAAA,CAAAA,GAAUD,EAAeC,CAAK,CAAC,CAIlCM,CAAAA,CAAAA,CAAf,KAA0B,CAC/B,WAAc,EAAA,EAGd,OAAO,MAAA,CAAOC,CAAwC,CAAA,CACpD,OAAQA,CAAAA,CAAQ,SAAW,EACzB,IAAK,iBAAA,CACH,OAAO,IAAIC,CAAgBD,CAAAA,CAAO,CACpC,CAAA,IAAK,eACH,OAAO,IAAIE,CAAaF,CAAAA,CAAO,CACjC,CAAA,IAAK,8BACH,CAAA,OAAO,IAAIG,CAA6BH,CAAAA,CAAO,CACjD,CAAA,IAAK,YACH,CAAA,MAAM,IAAI,KAAA,CAAM,iBAAiB,CACnC,CAAA,QACE,OAAO,IAAII,CAAiBJ,CAAAA,CAAO,CACvC,CACF,CACF,CAAA,CAEaK,CAAsBC,CAAAA,CAAAA,EAC1BA,CAAI,CAAA,MAAA,CAAQC,CAAS,EAAA,CAAA,EAAGA,CAAI,CAAG,CAAA,CAAA,IAAA,EAAW,GAAA,EAAE,CAAE,CAAA,MAAA,CAG1CC,CAAsBF,CAAAA,CAAAA,EAC1BA,EAAI,IACRC,CAAAA,CAAAA,EACCA,CAAS,GAAA,IAAA,EACTA,CAAK,CAAA,IAAA,EAAW,GAAA,EAAA,EAChB,CAAC,KAAM,CAAA,MAAA,CAAOA,CAAK,CAAA,IAAA,EAAM,CAAC,CAC1BA,EAAAA,CAAAA,CAAK,IAAK,EAAA,CAAE,WAAY,EAAA,GAAM,MAC9BA,EAAAA,CAAAA,CAAK,IAAK,EAAA,CAAE,aAAkB,GAAA,OAClC,CAOIH,CAAAA,CAAAA,CAAN,cAA+BL,CAAW,CAGxC,WAAA,CAAoBC,EAAyB,CAC3C,KAAA,EADkB,CAAA,IAAA,CAAA,OAAA,CAAAA,CAElB,CAAA,IAAA,CAAK,YAAeA,CAAAA,CAAAA,CAAQ,cAAgBT,EAC9C,CALQ,YAOR,CAAA,MAAM,UAAWkB,CAAAA,CAAAA,CAAwD,CACvE,IAAIC,CAAa,CAAA,CAAA,CACbC,CAAO,CAAA,CAAA,CACPC,CAAmB,CAAA,EACnBlB,CAAAA,CAAAA,CAAoB,EAGlBmB,CAAAA,CAAAA,CAAW,IAAIC,kBAAAA,CAAO,QAAS,CAAA,CACnC,UAAY,CAAA,CAAA,CAAA,CACZ,MAAO,CAACR,CAAAA,CAAKS,CAAUC,CAAAA,CAAAA,GAAa,CAClCN,CAAAA,EAAAA,CACIA,CAAc,EAAA,IAAA,CAAK,cACrBD,CAAW,CAAA,OAAA,EAETJ,CAAAA,CAAAA,CAAmBC,CAAG,CAAA,CAAID,CAAmBO,CAAAA,CAAM,CACrDA,GAAAA,CAAAA,CAASN,CACTK,CAAAA,CAAAA,CAAOD,CACPhB,CAAAA,CAAAA,CAAUE,CAAiBgB,CAAAA,CAAM,GAEnCI,CAAS,GACX,CACF,CAAC,CAED,CAAA,OAAAP,CAAW,CAAA,IAAA,CAAKI,EAAU,CAAE,GAAA,CAAK,CAAK,CAAA,CAAC,CAEhC,CAAA,IAAI,OAAQ,CAAA,CAACI,EAASC,CAAW,GAAA,CACtCL,CAAS,CAAA,EAAA,CAAG,QAAU,CAAA,IAAM,CAC1BI,CAAAA,CAAQ,CAAE,MAAA,CAAAL,CAAQ,CAAA,IAAA,CAAAD,CAAM,CAAA,OAAA,CAAAjB,CAAQ,CAAC,EACnC,CAAC,CAAA,CACDe,CAAW,CAAA,EAAA,CAAG,OAAS,CAAA,IAAM,CAC3BQ,CAAAA,CAAQ,CAAE,MAAAL,CAAAA,CAAAA,CAAQ,IAAAD,CAAAA,CAAAA,CAAM,OAAAjB,CAAAA,CAAQ,CAAC,EACnC,CAAC,CACDe,CAAAA,CAAAA,CAAW,EAAG,CAAA,OAAA,CAAUU,CAAU,EAAA,CAChCD,CAAOC,CAAAA,CAAK,EACd,CAAC,EACH,CAAC,CACH,CACF,CAIMlB,CAAAA,CAAAA,CAAN,cAA8BF,CAAW,CAEvC,WAA6BC,CAAAA,CAAAA,CAAiC,CAC5D,KAAA,EAD2B,CAAA,IAAA,CAAA,OAAA,CAAAA,EAGvB,GAACA,CAAAA,CAAAA,CAAQ,OAAWA,EAAAA,CAAAA,CAAQ,OAAQ,CAAA,MAAA,GAAW,CACjD,CAAA,MAAM,IAAI,KAAM,CAAA,8CAA8C,CAElE,CAPA,OASA,CAAA,MAAM,UAAWS,CAAAA,CAAAA,CAAwD,CACvE,IAAMf,CAAUE,CAAAA,CAAAA,CAAiB,IAAK,CAAA,OAAA,CAAQ,OAAO,CAAA,CACrD,OAAO,CACL,MAAA,CAAQ,IAAK,CAAA,OAAA,CAAQ,OACrB,CAAA,IAAA,CAAM,IAAK,CAAA,OAAA,CAAQ,MAAQ,CAC3B,CAAA,OAAA,CAAAF,CACF,CACF,CACF,CAAA,CAKMQ,CAAN,CAAA,cAA2BH,CAAW,CACpC,WAAA,CAA6BC,CAA8B,CAAA,CACzD,KAAM,EAAA,CADqB,IAAAA,CAAAA,OAAAA,CAAAA,CAAAA,CAGvB,GAACA,CAAAA,CAAAA,CAAQ,UAAcA,EAAAA,CAAAA,CAAQ,UAAW,CAAA,MAAA,GAAW,CACvD,CAAA,MAAM,IAAI,KAAM,CAAA,+CAA+C,CAEnE,CAEA,MAAM,UAAA,CAAWS,CAAwD,CAAA,CACvE,IAAIC,CAAa,CAAA,CAAA,CACbU,CAAS,CAAA,IAAA,CAAK,GAAI,CAAA,GAAG,IAAK,CAAA,OAAA,CAAQ,UAAU,CAC5CR,CAAAA,CAAAA,CAAmB,EAAC,CACpBlB,CAAoB,CAAA,EAElBmB,CAAAA,CAAAA,CAAW,IAAIC,kBAAAA,CAAO,QAAS,CAAA,CACnC,UAAY,CAAA,CAAA,CAAA,CACZ,KAAO,CAAA,CAACR,EAAKS,CAAUC,CAAAA,CAAAA,GAAa,CAClC,GAAIN,CAAaU,CAAAA,CAAAA,CACfX,CAAW,CAAA,OAAA,WACF,IAAK,CAAA,OAAA,CAAQ,UAAW,CAAA,QAAA,CAASC,CAAU,CAAA,CACpD,GAAIE,CAAAA,CAAO,SAAW,CAEpBA,CAAAA,CAAAA,CAASN,CACTZ,CAAAA,CAAAA,CAAUE,CAAiBgB,CAAAA,CAAM,CAEjC,CAAA,KAAA,IAAA,IAAS,CAAI,CAAA,CAAA,CAAG,CAAIA,CAAAA,CAAAA,CAAO,MAAQ,CAAA,CAAA,EAAA,CAC7BA,CAAO,CAAA,CAAC,IAAM,EAChBA,CAAAA,CAAAA,CAAO,CAAC,CAAA,CAAIN,CAAI,CAAA,CAAC,CAAE,CAAA,IAAA,GAEnBM,CAAO,CAAA,CAAC,CAAI,CAAA,CAAA,EAAGA,CAAO,CAAA,CAAC,CAAE,CAAA,IAAA,EAAM,CAAIN,CAAAA,EAAAA,CAAAA,CAAI,CAAC,CAAA,CAAE,IAAK,EAAC,CAElDZ,CAAAA,CAAAA,CAAAA,CAAQ,CAAC,CAAA,CAAIF,CAAe,CAAA,CAAC,CAInCkB,CAAAA,CAAAA,EAAAA,CACAM,CAAS,GACX,CACF,CAAC,CAAA,CAEDP,CAAW,CAAA,IAAA,CAAKI,CAAU,CAAA,CAAE,GAAK,CAAA,CAAA,CAAK,CAAC,CAGvC,CAAA,IAAMF,CAAO,CAAA,IAAA,CAAK,OAAQ,CAAA,IAAA,EAAQS,CAAS,CAAA,CAAA,CAG3C,OAAO,IAAI,OAAA,CAAQ,CAACH,CAAAA,CAASC,CAAW,GAAA,CACtCL,CAAS,CAAA,EAAA,CAAG,QAAU,CAAA,IAAM,CAC1BI,CAAAA,CAAQ,CAAE,MAAA,CAAAL,CAAQ,CAAA,IAAA,CAAAD,EAAM,OAAAjB,CAAAA,CAAQ,CAAC,EACnC,CAAC,CAAA,CACDe,CAAW,CAAA,EAAA,CAAG,QAAS,IAAM,CAC3BQ,CAAQ,CAAA,CAAE,MAAAL,CAAAA,CAAAA,CAAQ,IAAAD,CAAAA,CAAAA,CAAM,QAAAjB,CAAQ,CAAC,EACnC,CAAC,CACDe,CAAAA,CAAAA,CAAW,EAAG,CAAA,OAAA,CAAUU,GAAU,CAChCD,CAAAA,CAAOC,CAAK,EACd,CAAC,EACH,CAAC,CACH,CACF,CASMhB,CAAAA,CAAAA,CAAN,cAA2CJ,CAAW,CAGpD,WAAA,CAAoBC,CAA8C,CAAA,CAChE,OADkB,CAAA,IAAA,CAAA,OAAA,CAAAA,CAElB,CAAA,IAAA,CAAK,YAAeA,CAAAA,CAAAA,CAAQ,YAAgBT,EAAAA,EAC9C,CALQ,YAOR,CAAA,MAAM,UAAWkB,CAAAA,CAAAA,CAAwD,CACvE,IAAIC,CAAa,CAAA,CAAA,CACbC,CAAO,CAAA,CAAA,CACPC,CAAmB,CAAA,EACjBS,CAAAA,CAAAA,CAAmB,EAAC,CACtB3B,EAAoB,EAAC,CAGnBmB,CAAW,CAAA,IAAIC,kBAAO,CAAA,QAAA,CAAS,CACnC,UAAA,CAAY,GACZ,KAAO,CAAA,CAACR,CAAKS,CAAAA,CAAAA,CAAUC,CAAa,GAAA,CAalC,GAZAN,CAAAA,EAAAA,CACIA,GAAc,IAAK,CAAA,YAAA,EACrBD,CAAW,CAAA,OAAA,EAEbY,CAAAA,CAAAA,CAAK,IAAKf,CAAAA,CAAG,CAETD,CAAAA,CAAAA,CAAmBC,CAAG,CAAA,CAAID,CAAmBO,CAAAA,CAAM,CACrDA,GAAAA,CAAAA,CAASN,EACTK,CAAOD,CAAAA,CAAAA,CACPhB,CAAUE,CAAAA,CAAAA,CAAiBgB,CAAM,CAAA,CAAA,CAG/BJ,CAAmBF,CAAAA,CAAG,EAAG,CAE3B,IAAMgB,CAAcD,CAAAA,CAAAA,CAAKA,CAAK,CAAA,MAAA,CAAS,CAAC,CAAA,CAEtCC,GACAjB,CAAmBO,CAAAA,CAAM,CAAMP,GAAAA,CAAAA,CAAmBiB,CAAW,CAAA,EAC7D,CAACd,CAAAA,CAAmBc,CAAW,CAAA,GAG/BV,CAASU,CAAAA,CAAAA,CACTX,CAAOD,CAAAA,CAAAA,CAAa,CACpBhB,CAAAA,CAAAA,CAAUE,EAAiBgB,CAAM,CAAA,EAErC,CAEAI,CAAAA,GACF,CACF,CAAC,CAAA,CAEDP,EAAW,IAAKI,CAAAA,CAAAA,CAAU,CAAE,GAAA,CAAK,CAAK,CAAA,CAAC,CAEvC,CAAA,MAAM,IAAI,OAAc,CAAA,CAACI,CAASC,CAAAA,CAAAA,GAAW,CAC3CL,CAAAA,CAAS,EAAG,CAAA,QAAA,CAAU,IAAM,CAC1BI,CAAQ,GACV,CAAC,CAAA,CACDR,CAAW,CAAA,EAAA,CAAG,QAAS,IAAM,CAC3BQ,CAAQ,GACV,CAAC,CAAA,CACDR,CAAW,CAAA,EAAA,CAAG,QAAUU,CAAU,EAAA,CAChCD,CAAOC,CAAAA,CAAK,EACd,CAAC,EACH,CAAC,EAED,IAAII,CAAAA,CACAC,CAGJ,CAAA,IAAA,IAASC,CAAId,CAAAA,CAAAA,CAAMc,CAAIJ,CAAAA,CAAAA,CAAK,MAAQI,CAAAA,CAAAA,EAAAA,CAAK,CACvC,IAAMnB,CAAMe,CAAAA,CAAAA,CAAKI,CAAC,CAAA,CACdpB,EAAmBO,CAAM,CAAA,GAAMP,CAAmBC,CAAAA,CAAG,CAClCM,EAAAA,CAAAA,CAAO,MAAO,CAAA,CAACL,EAAMd,CACxBa,GAAAA,CAAAA,CAAAA,CAAIb,CAAK,CAAA,EAAG,IAAK,EAAA,EAAK,EAEnC,EAAA,KAAA,CAAM,KAAK,CACX,CAAA,KAAA,CAAOiC,CAASnB,EAAAA,CAAAA,CAAK,WAAY,EAAA,CAAE,QAASmB,CAAAA,CAAAA,CAAK,WAAY,EAAC,CAAC,CACnE,CAEgB,CAAA,MAAA,CAASd,CAAO,CAAA,MAAA,CAAS,KACxCW,CAAcjB,CAAAA,CAAAA,CACdkB,CAAYC,CAAAA,CAAAA,CAAI,CAChB/B,CAAAA,CAAAA,CAAUE,CAAiB2B,CAAAA,CAAW,GAG5C,CAEA,OAAO,CAAE,MAAA,CAAQA,CAAeX,EAAAA,CAAAA,CAAQ,IAAMY,CAAAA,CAAAA,EAAab,EAAM,OAAAjB,CAAAA,CAAQ,CAC3E,CACF,CC3TA,CAAA,eAAsBiC,CACpBC,CAAAA,CAAAA,CACA5B,CAC0B,CAAA,CAC1B,GAAI,CACF,IAAM6B,CAAAA,CAAiB7B,CAAS,EAAA,sBAAA,CAC5B,GACCA,CAAS,EAAA,cAAA,EAAkB,CAC1B8B,CAAAA,CAAAA,CAAAA,CAAeF,CAAO,CAAA,QAAA,CAAS,MAAM,CAAA,CAqBvCP,EApBiDU,kBAAK,CAAA,KAAA,CACxDD,CACA,CAAA,CACE,SAAW9B,CAAAA,CAAAA,CAAQ,SACnB,CAAA,iBAAA,CAAmBA,EAAQ,eAAmB,EAAA,CAC5C,GACA,CAAA,GAAA,CACA,GACA,CAAA,GAAA,CACA,GACA,CAAA,GAAA,CACA,IACA,GACF,CAAA,CACA,aAAeA,CAAAA,CAAAA,EAAS,aAAiB,EAAA,CAAA,CAAA,CACzC,MAAQ,CAAA,CAAA,CAAA,CACR,eAAA6B,CACF,CACF,CAEmB,CAAA,IAAA,CACnB,GAAI,CAACR,CAAQ,EAAA,CAACA,EAAK,MACjB,CAAA,OAAA,OAAA,CAAQ,GAAI,CAAA,2BAA2B,CAChC,CAAA,EAET,CAAA,IAAMW,EAAYhC,CAAS,EAAA,SAAA,GAAeiC,CAAUA,EAAAA,CAAAA,CAAAA,CAE9CC,CAAiBC,CAAAA,CAAAA,EACrBA,CAAK,CAAA,GAAA,CAAK7B,CAAQ,EAAA,MAAA,CAAO,MAAOA,CAAAA,CAAG,CAAE,CAAA,MAAA,CAAQ2B,CAAUA,EAAAA,CAAAA,GAAU,IAAI,CAAC,CAAA,CAClEG,CAAarC,CAAAA,CAAAA,CAAW,MAC5BC,CAAAA,CAAAA,CAAQ,sBAA0B,EAAA,CAChC,UAAW,SACb,CACF,CACMqC,CAAAA,CAAAA,CAAeC,UAAS,CAAA,IAAA,CAAKJ,CAAcb,CAAAA,CAAI,CAAC,CAChD,CAAA,CAAE,MAAAT,CAAAA,CAAAA,CAAQ,IAAAD,CAAAA,CAAAA,CAAM,OAAAjB,CAAAA,CAAQ,CAAI,CAAA,MAAM0C,CAAW,CAAA,UAAA,CAAWC,CAAY,CAAA,CAK1E,GAHKrC,CAAAA,EAAS,wBAAwBqB,CAAK,CAAA,MAAA,CAAO,CAAGV,CAAAA,CAAI,CAGrDU,CAAAA,CAAAA,CAAK,MAAW,GAAA,CAAA,CAClB,OAGF,KACEA,CAAAA,CAAK,MAAS,CAAA,CAAA,EACd,MAAO,CAAA,MAAA,CAAOA,CAAKA,CAAAA,CAAAA,CAAK,OAAS,CAAC,CAAC,CAAE,CAAA,KAAA,CAAMkB,CAAkB,CAAA,EAE7DlB,CAAK,CAAA,GAAA,EAGP,CAAA,IAAMmB,CAAgBxC,CAAAA,CAAAA,EAAS,sBAAyBN,CAAAA,CAAAA,CAAUkB,CAE5Df,CAAAA,CAAAA,CAAU4C,EAA8BD,CAAa,CAAA,CAErDL,CAA8Bd,CAAAA,CAAAA,CACjC,MAAQf,CAAAA,CAAAA,EACFuB,CAME,CAAA,CALS,OAAO,MAAOvB,CAAAA,CAAG,CAAE,CAAA,KAAA,CACjCuB,CAAmB,GAAA,QAAA,CACfU,CACCN,CAAAA,CAAAA,EAAUA,IAAU,EAC3B,CAAA,CAL4B,CAO7B,CAAA,CAAA,CACA,GAAK3B,CAAAA,CAAAA,EAAQ,CACZ,IAAMoC,CAAYC,CAAAA,cAAAA,CAAQrC,CAAMsC,CAAAA,CAAAA,EAAQ/C,CAAQ+C,CAAAA,CAAG,CAAC,CAAA,CACpD,OAAOC,gBAAUH,CAAAA,CAAAA,CAAYT,CAAW,GAAA,CACtC,KAAOD,CAAAA,CAAAA,CAAUC,CAAK,CACxB,EAAE,CACJ,CAAC,CAECa,CAAAA,CAAAA,CAEJ,OAAI9C,CAAAA,EAAS,sBACX8C,GAAAA,CAAAA,CAAW,CACT,UAAY,CAAA,CAACnC,CAAI,CACnB,CAIK,CAAA,CAAA,CACL,CAFgB,QAEN,EAAG,CACX,OAAAd,CAAAA,CAAAA,CACA,IAAAsC,CAAAA,CAAAA,CACA,QAAAW,CAAAA,CACF,CACF,CACF,CAAA,MAAS3B,CAAO,CAAA,CACd,MAAQ,OAAA,CAAA,GAAA,CAAI,oBAAsBA,CAAAA,CAAK,EACjCA,CACR,CACF,CAEA,SAASsB,CAA8BM,CAAAA,CAAAA,CAA4B,CACjE,IAAMC,EAAiC,EAAC,CAClCrD,CAAmB,CAAA,EACzB,CAAA,IAAA,GAAW,CAACiD,CAAAA,CAAKX,CAAK,CAAA,GAAK,MAAO,CAAA,OAAA,CAAQc,CAAM,CAAA,CAAG,CACjD,IAAME,EAAahB,CAAO,EAAA,QAAA,EAAW,CAAA,OAAA,CAAQ,GAAK,CAAA,EAAE,CAChDgB,CAAAA,CAAAA,EAAcD,EAAOf,CAAK,CAAA,EAC5BtC,CAAOiD,CAAAA,CAAG,CAAI,CAAA,CAAA,EAAGK,CAAU,CAAA,CAAA,EAAID,EAAOf,CAAK,CAAC,CAC5Ce,CAAAA,CAAAA,CAAAA,CAAOf,CAAK,CAAA,EAAA,GAEZtC,CAAOiD,CAAAA,CAAG,CAAIK,CAAAA,CAAAA,CACdD,CAAOf,CAAAA,CAAK,CAAI,CAAA,CAAA,EAEpB,CAEA,OAAOtC,CACT,CAEA,IAAM4C,CAAsBN,CAAAA,CAAAA,EAC1BA,CAAU,GAAA,IAAA,EAAS,OAAOA,CAAAA,EAAU,UAAYA,CAAM,CAAA,IAAA,EAAW,GAAA,EAAA,CChIvDiB,IAAAA,CAAAA,CAAAA,CAAAA,CAAAA,GACVA,CAAA,CAAA,GAAA,CAAM,MACNA,CAAA,CAAA,GAAA,CAAM,KACNA,CAAAA,CAAAA,CAAA,GAAM,CAAA,KAAA,CAHIA,CAAA,CAAA,EAAA,CAAA,EAAA,EAAA,CAAA,CAoBCC,EAAqB,CAChCC,CAAAA,CACApD,CACG,GAAA,CACH,GAAI,MAAA,CAAO,MAAOkD,CAAAA,CAAe,EAAE,QAASE,CAAAA,CAA0B,CACpE,CAAA,MAAM,IAAI,KAAA,CACR,CAAGA,EAAAA,CAAO,sEACZ,CAGF,CAAA,OAAOC,uBAAUD,CAAAA,CAAAA,CAAS,WAAazB,CAAAA,CAAAA,CAAa3B,CAAO,CAC7D,EAEasD,CAAkB3B,CAAAA","file":"index.cjs","sourcesContent":["import stream from 'stream'\n\nexport const ROWS_TO_SEARCH_FOR_HEADER = 10\n\ninterface DefaultOptions {\n  algorithm: 'default'\n  rowsToSearch?: number\n}\n\ninterface ExplicitHeadersOptions {\n  algorithm: 'explicitHeaders'\n  headers: string[]\n  skip?: number\n}\n\ninterface SpecificRowsOptions {\n  algorithm: 'specificRows'\n  rowNumbers: number[]\n  skip?: number\n}\n\ninterface DataRowAndSubHeaderDetectionOptions {\n  algorithm: 'dataRowAndSubHeaderDetection'\n  rowsToSearch?: number\n}\n\ninterface NewfangledOptions {\n  algorithm: 'newfangled'\n}\n\nexport type GetHeadersOptions =\n  | DefaultOptions\n  | ExplicitHeadersOptions\n  | SpecificRowsOptions\n  | DataRowAndSubHeaderDetectionOptions\n  | NewfangledOptions\n\ninterface GetHeadersResult {\n  header: string[]\n  skip: number\n  letters: string[]\n}\n\nexport const indexToLetters = (index: number): string => {\n  const letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'\n  let result = ''\n\n  while (index >= 0) {\n    result = letters[index % 26] + result\n    index = Math.floor(index / 26) - 1\n  }\n\n  return result\n}\n\nexport const headersToLetters = (headers: string[]): string[] => {\n  return headers.map((_, index) => indexToLetters(index))\n}\n\n// Takes a datastream (representing a CSV) and returns the header row and the number of rows to skip\nexport abstract class Headerizer {\n  constructor() {}\n  abstract getHeaders(dataStream: stream.Readable): Promise<GetHeadersResult>\n\n  static create(options: GetHeadersOptions): Headerizer {\n    switch (options.algorithm) {\n      case 'explicitHeaders':\n        return new ExplicitHeaders(options)\n      case 'specificRows':\n        return new SpecificRows(options)\n      case 'dataRowAndSubHeaderDetection':\n        return new DataRowAndSubHeaderDetection(options)\n      case 'newfangled':\n        throw new Error('Not implemented')\n      default:\n        return new OriginalDetector(options)\n    }\n  }\n}\n\nexport const countNonEmptyCells = (row: string[]): number => {\n  return row.filter((cell) => `${cell}`.trim() !== '').length\n}\n\nexport const likelyContainsData = (row: string[]): boolean => {\n  return row.some(\n    (cell) =>\n      cell === null ||\n      cell.trim() === '' ||\n      !isNaN(Number(cell.trim())) ||\n      cell.trim().toLowerCase() === 'true' ||\n      cell.trim().toLowerCase() === 'false'\n  )\n}\n\n// This is the original / default implementation of detectHeader.\n// It looks at the first `rowsToSearch` rows and takes the row\n// with the most non-empty cells as the header, preferring the earliest\n// such row in the case of a tie.\nclass OriginalDetector extends Headerizer {\n  private rowsToSearch: number\n\n  constructor(private options: DefaultOptions) {\n    super()\n    this.rowsToSearch = options.rowsToSearch || ROWS_TO_SEARCH_FOR_HEADER\n  }\n\n  async getHeaders(dataStream: stream.Readable): Promise<GetHeadersResult> {\n    let currentRow = 0\n    let skip = 0\n    let header: string[] = []\n    let letters: string[] = []\n\n    // This is the original implementation of detectHeader\n    const detector = new stream.Writable({\n      objectMode: true,\n      write: (row, encoding, callback) => {\n        currentRow++\n        if (currentRow >= this.rowsToSearch) {\n          dataStream.destroy()\n        }\n        if (countNonEmptyCells(row) > countNonEmptyCells(header)) {\n          header = row\n          skip = currentRow\n          letters = headersToLetters(header)\n        }\n        callback()\n      },\n    })\n\n    dataStream.pipe(detector, { end: true })\n\n    return new Promise((resolve, reject) => {\n      detector.on('finish', () => {\n        resolve({ header, skip, letters })\n      })\n      dataStream.on('close', () => {\n        resolve({ header, skip, letters })\n      })\n      dataStream.on('error', (error) => {\n        reject(error)\n      })\n    })\n  }\n}\n\n// This implementation simply returns an explicit list of headers\n// it was provided with.\nclass ExplicitHeaders extends Headerizer {\n  headers: string[]\n  constructor(private readonly options: ExplicitHeadersOptions) {\n    super()\n\n    if (!options.headers || options.headers.length === 0) {\n      throw new Error('ExplicitHeaders requires at least one header')\n    }\n  }\n\n  async getHeaders(dataStream: stream.Readable): Promise<GetHeadersResult> {\n    const letters = headersToLetters(this.options.headers)\n    return {\n      header: this.options.headers,\n      skip: this.options.skip || 0,\n      letters,\n    }\n  }\n}\n\n// This implementation looks at specific rows and combines them into a single header.\n// For example, if you knew that the header was in the third row, you could pass it\n// { rowNumbers: [2] }\nclass SpecificRows extends Headerizer {\n  constructor(private readonly options: SpecificRowsOptions) {\n    super()\n\n    if (!options.rowNumbers || options.rowNumbers.length === 0) {\n      throw new Error('SpecificRows requires at least one row number')\n    }\n  }\n\n  async getHeaders(dataStream: stream.Readable): Promise<GetHeadersResult> {\n    let currentRow = 0\n    let maxRow = Math.max(...this.options.rowNumbers)\n    let header: string[] = []\n    let letters: string[] = []\n\n    const detector = new stream.Writable({\n      objectMode: true,\n      write: (row, encoding, callback) => {\n        if (currentRow > maxRow) {\n          dataStream.destroy()\n        } else if (this.options.rowNumbers.includes(currentRow)) {\n          if (header.length === 0) {\n            // This is the first header row we've seen, so just remember it\n            header = row\n            letters = headersToLetters(header)\n          } else {\n            for (let i = 0; i < header.length; i++) {\n              if (header[i] === '') {\n                header[i] = row[i].trim()\n              } else {\n                header[i] = `${header[i].trim()} ${row[i].trim()}`\n              }\n              letters[i] = indexToLetters(i)\n            }\n          }\n        }\n        currentRow++\n        callback()\n      },\n    })\n\n    dataStream.pipe(detector, { end: true })\n\n    // If we have an explicit skip, use it, otherwise skip past the last header row\n    const skip = this.options.skip ?? maxRow + 1\n\n    // TODO: this logic is duplicated, factor it out?\n    return new Promise((resolve, reject) => {\n      detector.on('finish', () => {\n        resolve({ header, skip, letters })\n      })\n      dataStream.on('close', () => {\n        resolve({ header, skip, letters })\n      })\n      dataStream.on('error', (error) => {\n        reject(error)\n      })\n    })\n  }\n}\n\n// This implementation attempts to detect the first data row and select the previous\n// row as the header. If the data row cannot be detected due to all of the sample\n// rows being full and not castable to a number or boolean type, it also will attempt\n// to detect a sub header row by checking following rows after a header is detected\n// for significant fuzzy matching. If over half of the fields in a possible sub header\n// row fuzzy match with the originally detected header row, the sub header row becomes\n// the new header.\nclass DataRowAndSubHeaderDetection extends Headerizer {\n  private rowsToSearch: number\n\n  constructor(private options: DataRowAndSubHeaderDetectionOptions) {\n    super()\n    this.rowsToSearch = options.rowsToSearch || ROWS_TO_SEARCH_FOR_HEADER\n  }\n\n  async getHeaders(dataStream: stream.Readable): Promise<GetHeadersResult> {\n    let currentRow = 0\n    let skip = 0\n    let header: string[] = []\n    const rows: string[][] = []\n    let letters: string[] = []\n\n    // This is the original implementation of detectHeader\n    const detector = new stream.Writable({\n      objectMode: true,\n      write: (row, encoding, callback) => {\n        currentRow++\n        if (currentRow >= this.rowsToSearch) {\n          dataStream.destroy()\n        }\n        rows.push(row)\n\n        if (countNonEmptyCells(row) > countNonEmptyCells(header)) {\n          header = row\n          skip = currentRow\n          letters = headersToLetters(header)\n        }\n        // check if row has numeric, boolean, or empty values\n        if (likelyContainsData(row)) {\n          // if so, check if the row before is as long as the current header and only contains strings\n          const previousRow = rows[rows.length - 2]\n          if (\n            previousRow &&\n            countNonEmptyCells(header) === countNonEmptyCells(previousRow) &&\n            !likelyContainsData(previousRow)\n          ) {\n            // if it is, make it the header\n            header = previousRow\n            skip = currentRow - 1\n            letters = headersToLetters(header)\n          }\n        }\n\n        callback()\n      },\n    })\n\n    dataStream.pipe(detector, { end: true })\n\n    await new Promise<void>((resolve, reject) => {\n      detector.on('finish', () => {\n        resolve()\n      })\n      dataStream.on('close', () => {\n        resolve()\n      })\n      dataStream.on('error', (error) => {\n        reject(error)\n      })\n    })\n\n    let fuzzyHeader: string[] | undefined\n    let fuzzySkip: number | undefined\n    // check if any rows after the header fuzzy match with the\n    // chosen header, indicating it's a sub header\n    for (let i = skip; i < rows.length; i++) {\n      const row = rows[i]\n      if (countNonEmptyCells(header) === countNonEmptyCells(row)) {\n        const fuzzyMatches = header.filter((cell, index) => {\n          const rowCell = row[index]?.trim() ?? ''\n          return rowCell\n            .split(/\\s+/)\n            .every((word) => cell.toLowerCase().includes(word.toLowerCase()))\n        })\n\n        if (fuzzyMatches.length / header.length > 0.5) {\n          fuzzyHeader = row\n          fuzzySkip = i + 1\n          letters = headersToLetters(fuzzyHeader)\n        }\n      }\n    }\n\n    return { header: fuzzyHeader ?? header, skip: fuzzySkip ?? skip, letters }\n  }\n}\n","import { Flatfile } from '@flatfile/api'\nimport { WorkbookCapture } from '@flatfile/util-extractor'\nimport Papa, { ParseResult } from 'papaparse'\nimport { mapKeys, mapValues } from 'remeda'\nimport { Readable } from 'stream'\nimport { DelimiterOptions } from '.'\nimport { Headerizer } from './header.detection'\n\ntype ParseBufferOptions = Omit<DelimiterOptions, 'chunkSize' | 'parallel'> & {\n  readonly headerSelectionEnabled?: boolean\n}\n\nexport async function parseBuffer(\n  buffer: Buffer,\n  options: ParseBufferOptions\n): Promise<WorkbookCapture> {\n  try {\n    const skipEmptyLines = options?.headerSelectionEnabled\n      ? false\n      : (options?.skipEmptyLines ?? false)\n    const fileContents = buffer.toString('utf8')\n    const results: ParseResult<Record<string, string>> = Papa.parse(\n      fileContents,\n      {\n        delimiter: options.delimiter,\n        delimitersToGuess: options.guessDelimiters || [\n          ',',\n          '|',\n          '\\t',\n          ';',\n          ':',\n          '~',\n          '^',\n          '#',\n        ],\n        dynamicTyping: options?.dynamicTyping || false,\n        header: false,\n        skipEmptyLines,\n      }\n    )\n\n    let rows = results.data\n    if (!rows || !rows.length) {\n      console.log('No data found in the file')\n      return {} as WorkbookCapture\n    }\n    const transform = options?.transform || ((value) => value)\n\n    const extractValues = (data: Record<string, any>[]) =>\n      data.map((row) => Object.values(row).filter((value) => value !== null))\n    const headerizer = Headerizer.create(\n      options.headerDetectionOptions || {\n        algorithm: 'default',\n      }\n    )\n    const headerStream = Readable.from(extractValues(rows))\n    const { header, skip, letters } = await headerizer.getHeaders(headerStream)\n\n    if (!options?.headerSelectionEnabled) rows.splice(0, skip)\n\n    // return if there are no rows\n    if (rows.length === 0) {\n      return\n    }\n\n    while (\n      rows.length > 0 &&\n      Object.values(rows[rows.length - 1]).every(isNullOrWhitespace)\n    ) {\n      rows.pop()\n    }\n\n    const columnHeaders = options?.headerSelectionEnabled ? letters : header\n\n    const headers = prependNonUniqueHeaderColumns(columnHeaders)\n\n    const data: Flatfile.RecordData[] = rows\n      .filter((row) => {\n        if (!skipEmptyLines) return true\n        const isEmpty = Object.values(row).every(\n          skipEmptyLines === 'greedy'\n            ? isNullOrWhitespace\n            : (value) => value === ''\n        )\n        return !isEmpty\n      })\n      .map((row) => {\n        const mappedRow = mapKeys(row, (key) => headers[key])\n        return mapValues(mappedRow, (value) => ({\n          value: transform(value),\n        })) as Flatfile.RecordData\n      })\n\n    let metadata: { rowHeaders: number[] } | null\n\n    if (options?.headerSelectionEnabled) {\n      metadata = {\n        rowHeaders: [skip],\n      }\n    }\n\n    const sheetName = 'Sheet1'\n    return {\n      [sheetName]: {\n        headers,\n        data,\n        metadata,\n      },\n    } as WorkbookCapture\n  } catch (error) {\n    console.log('An error occurred:', error)\n    throw error\n  }\n}\n\nfunction prependNonUniqueHeaderColumns(record: string[]): string[] {\n  const counts: Record<string, number> = {}\n  const result: string[] = []\n  for (const [key, value] of Object.entries(record)) {\n    const cleanValue = value?.toString().replace('*', '')\n    if (cleanValue && counts[value]) {\n      result[key] = `${cleanValue}_${counts[value]}`\n      counts[value]++\n    } else {\n      result[key] = cleanValue\n      counts[value] = 1\n    }\n  }\n\n  return result\n}\n\nconst isNullOrWhitespace = (value: any) =>\n  value === null || (typeof value === 'string' && value.trim() === '')\n","import { Flatfile } from '@flatfile/api'\nimport { Extractor } from '@flatfile/util-extractor'\nimport { GetHeadersOptions } from './header.detection'\nimport { parseBuffer } from './parser'\n\nexport enum NativeFileTypes {\n  CSV = 'csv',\n  TSV = 'tsv',\n  PSV = 'psv',\n}\n\nexport type Delimiters = ',' | '|' | '\\t' | ';' | ':' | '~' | '^' | '#'\n\nexport interface DelimiterOptions {\n  readonly delimiter?: Delimiters\n  readonly guessDelimiters?: Delimiters[]\n  readonly dynamicTyping?: boolean\n  readonly skipEmptyLines?: boolean | 'greedy'\n  readonly transform?: (value: any) => Flatfile.CellValueUnion\n  readonly chunkSize?: number\n  readonly parallel?: number\n  readonly headerDetectionOptions?: GetHeadersOptions\n  readonly debug?: boolean\n}\n\nexport const DelimiterExtractor = (\n  fileExt: string,\n  options: DelimiterOptions\n) => {\n  if (Object.values(NativeFileTypes).includes(fileExt as NativeFileTypes)) {\n    throw new Error(\n      `${fileExt} is a native file type and not supported by the delimiter extractor.`\n    )\n  }\n\n  return Extractor(fileExt, 'delimiter', parseBuffer, options)\n}\n\nexport const delimiterParser = parseBuffer\n"]}