replace pdfsharp with itextsharp to parse pdf

tvpro2005 · Sep 6, 2015 · 56742ce · 56742ce
1 parent 525fb17
commit 56742ce
Show file tree

Hide file tree

Showing 4 changed files with 30 additions and 22 deletions.
diff --git a/Toxy.Test/PDFParserTest.cs b/Toxy.Test/PDFParserTest.cs
@@ -41,14 +41,20 @@ public void TestParseToxyDocumentFromPDF()
             Assert.AreEqual("du 18-22 Mars 2003", results[3]);
         }
         [Test]
-        public void TestParsePlainTextFromPDF2()
+        public void TestParsePlainTextFromSample5()
         {
             string path = TestDataSample.GetPdfPath("Sample5.PDF");
             var parser = new PDFTextParser(new ParserContext(path));
             string result = parser.Parse();
             Assert.IsTrue(result.StartsWith("Philadelphia, Atlanta, Dallas, San Diego, and New Orleans."));
-
-
+        }
+        [Test]
+        public void TestReadBigPDFFile()
+        {
+            string path = TestDataSample.GetPdfPath("Word97-2007BinaryFileFormat(doc)Specification.pdf");
+            var parser = new PDFTextParser(new ParserContext(path));
+            string result = parser.Parse();
+            Assert.IsTrue(true);
         }
     }
 }
diff --git a/ToxyFramework/Parsers/PDFDocumentParser.cs b/ToxyFramework/Parsers/PDFDocumentParser.cs
@@ -1,14 +1,13 @@
-using PdfSharp.Pdf;
-using PdfSharp.Pdf.Content;
-using PdfSharp.Pdf.IO;
+using iTextSharp.text.pdf;
+using iTextSharp.text.pdf.parser;
 using System;
 using System.Collections.Generic;
 using System.IO;
 using System.Text;
 
 namespace Toxy.Parsers
 {
-    public class PDFDocumentParser: IDocumentParser
+    public class PDFDocumentParser : IDocumentParser
     {
         public PDFDocumentParser(ParserContext context)
         {
@@ -21,22 +20,23 @@ public ToxyDocument Parse()
                 throw new FileNotFoundException("File " + Context.Path + " is not found");
 
             ToxyDocument rdoc = new ToxyDocument();
-            using (Stream stream = File.OpenRead(Context.Path))
+            ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
 
-            using (PdfDocument doc = PdfReader.Open(stream, PdfDocumentOpenMode.ReadOnly))
+            using (PdfReader reader = new PdfReader(this.Context.Path))
             {
-                for (int i = 0; i < doc.PageCount; i++)
+
+                for (int i = 1; i <= reader.NumberOfPages; i++)
                 {
-                    var texts = doc.Pages[i].ExtractText();
-                    foreach (var text in texts)
+                    string thePage = PdfTextExtractor.GetTextFromPage(reader, i, its);
+                    string[] theLines = thePage.Split('\n');
+                    foreach (var theLine in theLines)
                     {
                         ToxyParagraph para = new ToxyParagraph();
-                        para.Text = text;
+                        para.Text = theLine;
                         rdoc.Paragraphs.Add(para);
                     }
                 }
             }
-
             return rdoc;
         }
         public ParserContext Context

diff --git a/ToxyFramework/Parsers/PDFTextParser.cs b/ToxyFramework/Parsers/PDFTextParser.cs
@@ -1,13 +1,13 @@
-using PdfSharp.Pdf;
-using PdfSharp.Pdf.IO;
+using iTextSharp.text.pdf;
+using iTextSharp.text.pdf.parser;
 using System;
 using System.Collections.Generic;
 using System.IO;
 using System.Text;
 
 namespace Toxy.Parsers
 {
-    public class PDFTextParser:ITextParser
+    public class PDFTextParser : ITextParser
     {
         public PDFTextParser(ParserContext context)
         {
@@ -18,19 +18,20 @@ public string Parse()
             if (!File.Exists(Context.Path))
                 throw new FileNotFoundException("File " + Context.Path + " is not found");
 
-            using (PdfDocument reader = PdfReader.Open(this.Context.Path, PdfDocumentOpenMode.ReadOnly))
+            using (PdfReader reader = new PdfReader(this.Context.Path))
             {
                 StringBuilder text = new StringBuilder();
 
-                for (int i = 0; i < reader.PageCount; i++)
+                for (int i = 1; i <= reader.NumberOfPages; i++)
                 {
-                    var lines = reader.Pages[i].ExtractWholeText();
-                        text.AppendLine(lines);
+                    ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
+                    string thePage = PdfTextExtractor.GetTextFromPage(reader, i, its);
+                    text.AppendLine(thePage);
                 }
                 return text.ToString();
             }
         }
 
         public ParserContext Context { get; set; }
     }
-}
+}
diff --git a/ToxyFramework/packages.config b/ToxyFramework/packages.config
@@ -2,6 +2,7 @@
 <packages>
   <package id="DocumentFormat.OpenXmlSDK" version="2.0" targetFramework="net40" />
   <package id="HtmlAgilityPack" version="1.4.9" targetFramework="net40" />
+  <package id="iTextSharp" version="5.5.6" targetFramework="net40" />
   <package id="LumenWorks.Framework.IO" version="3.8.0" targetFramework="net40" />
   <package id="NPOI" version="2.1.3.1" targetFramework="net40" />
   <package id="NUnit" version="2.6.4" targetFramework="net40" />