static PipelineText <TextLine> GetTextLines(string basename, string inputfolder, string outputfolder, out Execution.Pipeline pipeline) { string inputfile = $"{inputfolder}/{basename}.pdf"; string outputfile = $"{outputfolder}/{basename}-parser.pdf"; return(Examples.GetTextLines(inputfile, outputfile, out pipeline)); }
public static void ProcessStats(string basename) { //PdfWriteText.Test(); //return; Console.WriteLine(); Console.WriteLine("Program4 - Processing with hierachy"); Console.WriteLine(); // Extract(1); Examples.FollowText(basename); Examples.ShowHeaderFooter(basename); ExamplesWork.PrintAllSteps(basename, "bin", "bin"); PdfReaderException.ContinueOnException(); var conteudos = GetTextLinesWithPipelineBlockset(basename, out Execution.Pipeline pipeline) .Log <AnalyzeLines>($"bin/{basename}-lines.txt") .ConvertText <CreateStructures, TextStructure>() .Log <AnalyzeStructuresCentral>($"bin/{basename}-central.txt") //.PrintAnalytics($"bin/{basename}-print-analytics.txt") .ConvertText <CreateTextSegments, TextSegment>() .Log <AnalyzeSegmentTitles>($"bin/{basename}-tree.txt") .Log <AnalyzeSegmentStats>($"bin/{basename}-segments-stats.txt") .Log <AnalyzeSegments2>($"bin/{basename}-segments.csv") .ConvertText <CreateTreeSegments, TextSegment>() .ConvertText <TransformConteudo, Conteudo>() .ToList(); var validation = pipeline.Statistics.Calculate <ValidateFooter, StatsPageFooter>(); //Create XML var createArticle = new TransformArtigo(); var artigos = createArticle.Create(conteudos); createArticle.CreateXML(artigos, basename); var validator = new ProgramValidatorXML(); validator.ValidateArticle("bin"); }