Merge pull request #14 from BobLd/nurminen-detect

Implement Simple Nurminen Detection Algorithm
BobLd · Sep 22, 2020 · 32c6f8a · 32c6f8a
2 parents f8c2fe9 + e9584ea
commit 32c6f8a
Show file tree

Hide file tree

Showing 12 changed files with 974 additions and 1,038 deletions.
diff --git a/Tabula.Csv/Tabula.Csv.csproj b/Tabula.Csv/Tabula.Csv.csproj
@@ -4,7 +4,8 @@
     <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>
+    <Version>0.1.0-alpha002</Version>
+    <Authors>BobLd</Authors>
   </PropertyGroup>
 
   <PropertyGroup Condition="'$(Configuration)|$(TargetFramework)|$(Platform)'=='Release|netcoreapp3.1|AnyCPU'">

diff --git a/Tabula.Json/Tabula.Json.csproj b/Tabula.Json/Tabula.Json.csproj
@@ -4,7 +4,9 @@
     <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>
+    <Version>0.1.0-alpha002</Version>
+    <Company>BobLd</Company>
+    <Authors>BobLd</Authors>
   </PropertyGroup>
 
   <PropertyGroup Condition="'$(Configuration)|$(TargetFramework)|$(Platform)'=='Release|netcoreapp3.1|AnyCPU'">

diff --git a/Tabula.Tests/TestsNurminenDetector.cs b/Tabula.Tests/TestsNurminenDetector.cs
@@ -0,0 +1,33 @@
+using System;
+using System.Collections.Generic;
+using System.Text;
+using Tabula.Detectors;
+using Tabula.Extractors;
+using UglyToad.PdfPig;
+using Xunit;
+
+namespace Tabula.Tests
+{
+    public class TestsNurminenDetector
+    {
+        [Fact(Skip = "TO DO")]
+        public void TestLinesToCells()
+        {
+            using (PdfDocument document = PdfDocument.Open(@"test3.pdf", new ParsingOptions() { ClipPaths = true }))
+            {
+                ObjectExtractor oe = new ObjectExtractor(document);
+                PageArea page = oe.Extract(1);
+
+                SimpleNurminenDetectionAlgorithm detector = new SimpleNurminenDetectionAlgorithm();
+                var regions = detector.Detect(page);
+
+                foreach (var a in regions)
+                {
+                    IExtractionAlgorithm ea = new BasicExtractionAlgorithm();
+                    var newArea = page.GetArea(a.BoundingBox);
+                    List<Table> tables = ea.Extract(newArea);
+                }
+            }
+        }
+    }
+}