Merge pull request #12 from BobLd/0.1.0-alpha001

version 0.1.0-alpha001

Tabula.Csv/Tabula.Csv.csproj

@@ -2,6 +2,14 @@
 
   <PropertyGroup>
     <TargetFrameworks>netcoreapp3.1;netstandard2.0;net45;net451;net452;net46;net461;net462;net47</TargetFrameworks>
+    <Description>Extract tables from PDF files (port of tabula-java using PdfPig). Csv and Tsv writers.</Description>
+    <PackageProjectUrl>https://github.com/BobLd/tabula-sharp</PackageProjectUrl>
+    <Version>0.1.0-alpha001</Version>
+  </PropertyGroup>
+
+  <PropertyGroup Condition="'$(Configuration)|$(TargetFramework)|$(Platform)'=='Release|netcoreapp3.1|AnyCPU'">
+    <DocumentationFile>D:\VS2017\source\repos\tabula-sharp\Tabula.Csv\Tabula.Csv.xml</DocumentationFile>
+    <WarningLevel>3</WarningLevel>
   </PropertyGroup>
 
   <ItemGroup>

Tabula.Json/Tabula.Json.csproj

@@ -2,6 +2,13 @@
 
   <PropertyGroup>
     <TargetFrameworks>netcoreapp3.1;netstandard2.0;net45;net451;net452;net46;net461;net462;net47</TargetFrameworks>
+    <Description>Extract tables from PDF files (port of tabula-java using PdfPig). Json writer.</Description>
+    <PackageProjectUrl>https://github.com/BobLd/tabula-sharp</PackageProjectUrl>
+    <Version>0.1.0-alpha001</Version>
+  </PropertyGroup>
+
+  <PropertyGroup Condition="'$(Configuration)|$(TargetFramework)|$(Platform)'=='Release|netcoreapp3.1|AnyCPU'">
+    <DocumentationFile>D:\VS2017\source\repos\tabula-sharp\Tabula.Json\Tabula.Json.xml</DocumentationFile>
   </PropertyGroup>
 
   <ItemGroup>

Tabula/Cell.cs

@@ -9,7 +9,7 @@ namespace Tabula
     * ** tabula/Cell.java **
     */
     /// <summary>
-    /// 
+    /// A cell in a table.
     /// </summary>
     public class Cell : RectangularTextContainer<TextChunk>
     {
@@ -19,7 +19,7 @@ public class Cell : RectangularTextContainer<TextChunk>
         public static Cell EMPTY => new Cell(new PdfRectangle());
 
         /// <summary>
-        /// 
+        /// Create a cell in a table.
         /// </summary>
         /// <param name="pdfRectangle"></param>
         public Cell(PdfRectangle pdfRectangle)
@@ -31,7 +31,7 @@ public Cell(PdfRectangle pdfRectangle)
         }
 
         /// <summary>
-        /// 
+        /// Create a cell in a table.
         /// </summary>
         /// <param name="chunk"></param>
         public Cell(TextChunk chunk)
@@ -41,7 +41,7 @@ public Cell(TextChunk chunk)
         }
 
         /// <summary>
-        /// 
+        /// Create a cell in a table.
         /// </summary>
         /// <param name="topLeft"></param>
         /// <param name="bottomRight"></param>
@@ -59,6 +59,10 @@ public Cell(PdfPoint topLeft, PdfPoint bottomRight)
             }
         }
 
+        /// <summary>
+        /// Gets the cell's text.
+        /// </summary>
+        /// <param name="useLineReturns"></param>
         public override string GetText(bool useLineReturns)
         {
             if (base.textElements.Count == 0)
@@ -81,6 +85,9 @@ public override string GetText(bool useLineReturns)
             return sb.ToString().Trim();
         }
 
+        /// <summary>
+        /// Gets the cell's text.
+        /// </summary>
         public override string GetText()
         {
             return GetText(true);
@@ -100,6 +107,7 @@ public void SetPlaceholder(bool placeholder)
             this.IsPlaceholder = placeholder;
         }
 
+        /// <inheritdoc/>
         public override string ToString()
         {
             return GetText();

Tabula/Detectors/IDetectionAlgorithm.cs

@@ -3,12 +3,20 @@
 namespace Tabula.Detectors
 {
     // https://github.com/tabulapdf/tabula-java/blob/master/src/main/java/technology/
-    /**
+    /*
      * ** tabula/detectors/DetectionAlgorithm.java **
      * Created by matt on 2015-12-14.
      */
+
+    /// <summary>
+    /// Table detection algorithm.
+    /// </summary>
     public interface IDetectionAlgorithm
     {
+        /// <summary>
+        /// Detects the tables in the page.
+        /// </summary>
+        /// <param name="page">The page where to detect the tables.</param>
         List<TableRectangle> Detect(PageArea page);
     }
 }

Tabula/Detectors/NurminenDetectionAlgorithm.cs

@@ -8,14 +8,18 @@
 
 namespace Tabula.Detectors
 {
-    /**
+    /*
      * ** tabula/detectors/NurminenDetectionAlgorithm.java **
      * Created by matt on 2015-12-17.
      * <p>
      * Attempt at an implementation of the table finding algorithm described by
      * Anssi Nurminen's master's thesis:
      * http://dspace.cc.tut.fi/dpub/bitstream/handle/123456789/21520/Nurminen.pdf?sequence=3
      */
+
+    /// <summary>
+    /// Nurminen detection algorithm.
+    /// </summary>
     public class NurminenDetectionAlgorithm : IDetectionAlgorithm
     {
         private static int GRAYSCALE_INTENSITY_THRESHOLD = 25;

Tabula/Detectors/SpreadsheetDetectionAlgorithm.cs

@@ -16,6 +16,10 @@ namespace Tabula.Detectors
     /// </summary>
     public class SpreadsheetDetectionAlgorithm : IDetectionAlgorithm
     {
+        /// <summary>
+        /// Detects the tables in the page.
+        /// </summary>
+        /// <param name="page">The page where to detect the tables.</param>
         public List<TableRectangle> Detect(PageArea page)
         {
             List<Cell> cells = SpreadsheetExtractionAlgorithm.FindCells(page.HorizontalRulings, page.VerticalRulings);

Tabula/Extractors/BasicExtractionAlgorithm.cs

@@ -4,27 +4,33 @@
 namespace Tabula.Extractors
 {
     /// <summary>
-    /// stream
+    /// Stream extraction algorithm.
     /// </summary>
     public class BasicExtractionAlgorithm : IExtractionAlgorithm
     {
         private IReadOnlyList<Ruling> verticalRulings;
 
         /// <summary>
-        /// stream
+        /// Stream extraction algorithm.
         /// </summary>
         public BasicExtractionAlgorithm()
         {
         }
 
         /// <summary>
-        /// stream
+        /// Stream extraction algorithm.
         /// </summary>
+        /// <param name="verticalRulings">List of vertical rulings.</param>
         public BasicExtractionAlgorithm(IReadOnlyList<Ruling> verticalRulings)
         {
             this.verticalRulings = verticalRulings;
         }
 
+        /// <summary>
+        /// Extracts the tables in the page.
+        /// </summary>
+        /// <param name="page">The page where to extract the tables.</param>
+        /// <param name="verticalRulingPositions">List of vertical rulings, indicated by there x position.</param>
         public List<Table> Extract(PageArea page, IReadOnlyList<float> verticalRulingPositions)
         {
             List<Ruling> verticalRulings = new List<Ruling>(verticalRulingPositions.Count);
@@ -36,6 +42,10 @@ public List<Table> Extract(PageArea page, IReadOnlyList<float> verticalRulingPos
             return this.Extract(page);
         }
 
+        /// <summary>
+        /// Extracts the tables in the page.
+        /// </summary>
+        /// <param name="page">The page where to extract the tables.</param>
         public List<Table> Extract(PageArea page)
         {
             List<TextElement> textElements = page.GetText();
@@ -113,13 +123,14 @@ public List<Table> Extract(PageArea page)
             return new Table[] { table }.ToList();
         }
 
+        /// <inheritdoc/>
         public override string ToString()
         {
             return "stream";
         }
 
         /// <summary>
-        /// 
+        /// Gets columns positions.
         /// </summary>
         /// <param name="lines">Must be an array of lines sorted by their +top+ attribute.</param>
         /// <returns>a list of column boundaries (x axis).</returns>

Tabula/Extractors/IExtractionAlgorithm.cs

@@ -2,8 +2,15 @@
 
 namespace Tabula.Extractors
 {
+    /// <summary>
+    /// Table extraction algorithm.
+    /// </summary>
     public interface IExtractionAlgorithm
     {
+        /// <summary>
+        /// Extracts the tables in the page.
+        /// </summary>
+        /// <param name="page">The page where to extract the tables.</param>
         List<Table> Extract(PageArea page);
     }
 }

Tabula/Extractors/SpreadsheetExtractionAlgorithm.cs

@@ -7,12 +7,12 @@ namespace Tabula.Extractors
 {
     //https://github.com/tabulapdf/tabula-java/blob/master/src/main/java/technology/tabula/extractors/SpreadsheetExtractionAlgorithm.java
     /// <summary>
-    /// lattice
+    /// Lattice extraction algorithm.
     /// </summary>
     public class SpreadsheetExtractionAlgorithm : IExtractionAlgorithm
     {
         /// <summary>
-        /// lattice
+        /// Lattice extraction algorithm.
         /// </summary>
         public SpreadsheetExtractionAlgorithm()
         {
@@ -81,13 +81,17 @@ public int Compare(PdfPoint arg0, PdfPoint arg1)
             }
         }
 
+        /// <summary>
+        /// Extracts the tables in the page.
+        /// </summary>
+        /// <param name="page">The page where to extract the tables.</param>
         public List<Table> Extract(PageArea page)
         {
             return Extract(page, page.GetRulings());
         }
 
         /// <summary>
-        /// Extract a list of Table from page using rulings as separators
+        /// Extracts the tables in the page using rulings as separators.
         /// </summary>
         /// <param name="page"></param>
         /// <param name="rulings"></param>
@@ -159,6 +163,10 @@ public List<Table> Extract(PageArea page, IReadOnlyList<Ruling> rulings)
             return spreadsheets;
         }
 
+        /// <summary>
+        /// 
+        /// </summary>
+        /// <param name="page"></param>
         public bool IsTabular(PageArea page)
         {
             // if there's no text at all on the page, it's not a table 
@@ -177,6 +185,7 @@ public bool IsTabular(PageArea page)
             {
                 return false;
             }
+
             Table table = tables[0];
             int rowsDefinedByLines = table.RowCount;
             int colsDefinedByLines = table.ColumnCount;
@@ -187,6 +196,7 @@ public bool IsTabular(PageArea page)
                 // TODO WHAT DO WE DO HERE?
                 System.Diagnostics.Debug.Write("SpreadsheetExtractionAlgorithm.isTabular(): no table found.");
             }
+
             table = tables[0];
             int rowsDefinedWithoutLines = table.RowCount;
             int colsDefinedWithoutLines = table.ColumnCount;
@@ -196,6 +206,11 @@ public bool IsTabular(PageArea page)
             return ratio > MAGIC_HEURISTIC_NUMBER && ratio < (1 / MAGIC_HEURISTIC_NUMBER);
         }
 
+        /// <summary>
+        /// Find cells from horizontal and vertical ruling lines.
+        /// </summary>
+        /// <param name="horizontalRulingLines"></param>
+        /// <param name="verticalRulingLines"></param>
         public static List<Cell> FindCells(IReadOnlyList<Ruling> horizontalRulingLines, IReadOnlyList<Ruling> verticalRulingLines)
         {
             List<Cell> cellsFound = new List<Cell>();
@@ -266,6 +281,11 @@ public static List<Cell> FindCells(IReadOnlyList<Ruling> horizontalRulingLines,
             return cellsFound;
         }
 
+        /// <summary>
+        /// Find spreadsheets areas from cells.
+        /// <para>Based on O'Rourke's `Uniqueness of orthogonal connect-the-dots`.</para>
+        /// </summary>
+        /// <param name="cells"></param>
         public static List<TableRectangle> FindSpreadsheetsFromCells(List<TableRectangle> cells)
         {
             // via: http://stackoverflow.com/questions/13746284/merging-multiple-adjacent-rectangles-into-one-polygon
@@ -390,6 +410,7 @@ public static List<TableRectangle> FindSpreadsheetsFromCells(List<TableRectangle
             return rectangles;
         }
 
+        /// <inheritdoc/>
         public override string ToString()
         {
             return "lattice";
@@ -419,12 +440,6 @@ public override bool Equals(object other)
                     return this.point.Equals(o.point);
                 }
                 return false;
-                /*
-                if (this == other)
-                    return true;
-                if (!(other is PolygonVertex)) return false;
-                return this.point.Equals(((PolygonVertex)other).point);
-                */
             }
 
             public override int GetHashCode()