ElementReader

1//
2// Copyright (c) 2001-2021 by PDFTron Systems Inc. All Rights Reserved.
3//
4
5using System;
6using pdftron;
7using pdftron.Common;
8using pdftron.Filters;
9using pdftron.SDF;
10using pdftron.PDF;
11
12using NUnit.Framework;
13
14namespace MiscellaneousSamples
15{
16	/// <summary>
17	/// Summary description for Class1.
18	/// </summary>
19	[TestFixture]
20	public class ElementReaderTest
21	{
22		
23		static void ProcessElements(ElementReader reader)
24		{
25			Element element;
26			while ((element = reader.Next()) != null) 	// Read page contents
27			{
28				switch (element.GetType())
29				{
30               
31					case Element.Type.e_path:				// Process path data...
32						{
33                            PathData data = element.GetPathData();
34                            double[] points = data.points;
35							break;
36						}
37					
38                    case Element.Type.e_text: 				// Process text strings...
39						{
40                            String str = element.GetTextString();
41                            Console.WriteLine(str);
42                            break;
43						}
44
45					case Element.Type.e_form:				// Process form XObjects
46						{
47							Console.WriteLine("Process Element.Type.e_form");
48							reader.FormBegin();
49							ProcessElements(reader);
50							reader.End();
51							break;
52						}
53				}
54			}
55		}
56
57		/// <summary>
58		/// The main entry point for the application.
59		/// </summary>
60		[Test]
61		public static void Sample()
62		{
63
64			// Relative path to the folder containing test files.
65			const string input_path =  "TestFiles/";
66
67			try
68			{
69				Console.WriteLine("-------------------------------------------------");
70				Console.WriteLine("Sample 1 - Extract text data from all pages in the document.");
71
72                // Open the test file
73                Console.WriteLine("Opening the input pdf...");
74                using (PDFDoc doc = new PDFDoc(Utils.GetAssetTempFile(input_path + "newsletter.pdf")))
75				using (ElementReader page_reader = new ElementReader())
76				{
77					doc.InitSecurityHandler();
78
79					PageIterator itr;
80					for (itr = doc.GetPageIterator(); itr.HasNext(); itr.Next())		//  Read every page
81					{
82						page_reader.Begin(itr.Current());
83						ProcessElements(page_reader);
84						page_reader.End();
85					}
86					Console.WriteLine("Done.");
87				}
88
89            }
90			catch (PDFNetException e)
91			{
92				Console.WriteLine(e.Message);
93				Assert.True(false);
94			}
95		}
96	}
97}