EPUB 3 support improvements

README.md

@@ -1,10 +1,16 @@
 # EpubReader
 .NET library for reading EPUB files.
 
-Supports .NET Framework >= 4.5, .NET Core >= 1.0, and .NET Standard >= 1.3.
+Supports .NET Framework >= 4.6, .NET Core >= 1.0, and .NET Standard >= 1.3.
+
+Supports EPUB 2 (2.0, 2.0.1) and EPUB 3 (3.0, 3.0.1, 3.1).
 
 [Download](#download-latest-stable-release) | [WPF & .NET Core demo apps](#demo-apps)
 
+## Migration from 2.x
+
+[How to migrate from 2.x to 3.x](https:/vers-one/EpubReader/wiki/Migrating-from-2.x-to-3.x)
+
 ## Example
 ```csharp
 // Opens a book and reads all of its content into memory
@@ -32,19 +38,25 @@ if (coverImageContent != null)
  }
 }
 
-// CHAPTERS
+// TABLE OF CONTENTS
 
 // Enumerating chapters
-foreach (EpubChapter chapter in epubBook.Chapters)
+foreach (EpubNavigationItem chapter in epubBook.Navigation)
 {
  // Title of chapter
  string chapterTitle = chapter.Title;
 
- // HTML content of current chapter
- string chapterHtmlContent = chapter.HtmlContent;
-
  // Nested chapters
- List<EpubChapter> subChapters = chapter.SubChapters;
+ List<EpubNavigationItem> subChapters = chapter.NestedItems;
+}
+
+// READING ORDER
+
+// Enumerating the whole text content of the book in the order of reading
+foreach (EpubTextContentFile textContentFile in book.ReadingOrder)
+{
+ // HTML of current text content file
+ string htmlContent = textContentFile.Content;
 }
 
 
@@ -116,32 +128,41 @@ foreach (EpubMetadataContributor contributor in package.Metadata.Contributors)
  string contributorRole = contributor.Role;
 }
 
-// EPUB NCX data
-EpubNavigation navigation = epubBook.Schema.Navigation;
+// EPUB 2 NCX data
+Epub2Ncx epub2Ncx = epubBook.Schema.Epub2Ncx;
 
-// Enumerating NCX metadata
-foreach (EpubNavigationHeadMeta meta in navigation.Head)
+// Enumerating EPUB 2 NCX metadata
+foreach (Epub2NcxHeadMeta meta in epub2Ncx.Head)
 {
  string metadataItemName = meta.Name;
  string metadataItemContent = meta.Content;
 }
+
+// EPUB 3 navigation
+Epub3NavDocument epub3NavDocument = epubBook.Schema.Epub3NavDocument
+
+// Accessing structural semantics data of the head item
+StructuralSemanticsProperty? ssp = epub3NavDocument.Navs.First().Type;
 ```
 
 ## More examples
-[How to extract plain text from all chapters.](https:/vers-one/EpubReader/tree/master/Source/VersOne.Epub.NetCoreDemo/ExtractPlainText.cs)
+
+1. [How to extract the plain text of the whole book.](https:/vers-one/EpubReader/tree/master/Source/VersOne.Epub.NetCoreDemo/ExtractPlainText.cs)
+2. [How to extract the table of contents.](https:/vers-one/EpubReader/tree/master/Source/VersOne.Epub.NetCoreDemo/PrintNavigation.cs)
+3. [How to iterate over all EPUB files in a directory and collect some statistics.](https:/vers-one/EpubReader/tree/master/Source/VersOne.Epub.NetCoreDemo/TestDirectory.cs)
 
 ## Download latest stable release
 [Via NuGet package from nuget.org](https://www.nuget.org/packages/VersOne.Epub)
 
-DLL file from GitHub: [for .NET Framework](https:/vers-one/EpubReader/releases/download/v2.0.5/VersOne.Epub.Net45.zip) (26.9 KB) / [for .NET Core](https:/vers-one/EpubReader/releases/download/v2.0.5/VersOne.Epub.NetCore.zip) (27.0 KB) / [for .NET Standard](https:/vers-one/EpubReader/releases/download/v2.0.5/VersOne.Epub.NetStandard.zip) (27.0 KB)
+DLL file from GitHub: [for .NET Framework](https:/vers-one/EpubReader/releases/download/v3.0.0/VersOne.Epub.Net46.zip) (38.3 KB) / [for .NET Core](https:/vers-one/EpubReader/releases/download/v3.0.0/VersOne.Epub.NetCore.zip) (38.4 KB) / [for .NET Standard](https:/vers-one/EpubReader/releases/download/v3.0.0/VersOne.Epub.NetStandard.zip) (38.4 KB)
 
 ## Demo apps
-[Download WPF demo app ](https:/vers-one/EpubReader/releases/download/v2.0.5/WpfDemo.zip) (WpfDemo.zip, 409 KB)
+[Download WPF demo app](https:/vers-one/EpubReader/releases/download/v3.0.0/WpfDemo.zip) (WpfDemo.zip, 479 KB)
 
 This .NET Framework application demonstrates how to open EPUB books and extract their content using the library.
 
-HTML renderer used in this demo app may be a little bit slow for some books.
+HTML renderer used in this demo app may have difficulties while rendering HTML content for some of the books if the HTML structure is too complicated.
 
-[Download .NET Core console demo app](https:/vers-one/EpubReader/releases/download/v2.0.5/NetCoreDemo.zip) (NetCoreDemo.zip, 17.6 MB)
+[Download .NET Core console demo app](https:/vers-one/EpubReader/releases/download/v3.0.0/NetCoreDemo.zip) (NetCoreDemo.zip, 17.6 MB)
 
 This .NET Core console application demonstrates how to open EPUB books and retrieve their text content.

Source/EpubReader.sln

@@ -7,7 +7,7 @@ Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "VersOne.Epub", "VersOne.Epu
 EndProject
 Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "VersOne.Epub.WpfDemo", "VersOne.Epub.WpfDemo\VersOne.Epub.WpfDemo.csproj", "{2C48D6FB-EC93-4B79-8E52-79B579B3C324}"
 EndProject
-Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "VersOne.Epub.NetCoreDemo", "VersOne.Epub.NetCoreDemo\VersOne.Epub.NetCoreDemo.csproj", "{A6ED4735-3D37-4E44-BEE4-218C6BBAC1BD}"
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "VersOne.Epub.NetCoreDemo", "VersOne.Epub.NetCoreDemo\VersOne.Epub.NetCoreDemo.csproj", "{A6ED4735-3D37-4E44-BEE4-218C6BBAC1BD}"
 EndProject
 Global
  GlobalSection(SolutionConfigurationPlatforms) = preSolution

Source/VersOne.Epub.NetCoreDemo/ExtractPlainText.cs

@@ -9,30 +9,24 @@ internal static class ExtractPlainText
  public static void Run(string filePath)
  {
  EpubBook book = EpubReader.ReadBook(filePath);
- foreach (EpubChapter chapter in book.Chapters)
+ foreach (EpubTextContentFile textContentFile in book.ReadingOrder)
  {
- PrintChapter(chapter);
+ PrintTextContentFile(textContentFile);
  }
  }
 
- private static void PrintChapter(EpubChapter chapter)
+ private static void PrintTextContentFile(EpubTextContentFile textContentFile)
  {
  HtmlDocument htmlDocument = new HtmlDocument();
- htmlDocument.LoadHtml(chapter.HtmlContent);
+ htmlDocument.LoadHtml(textContentFile.Content);
  StringBuilder sb = new StringBuilder();
  foreach (HtmlNode node in htmlDocument.DocumentNode.SelectNodes("//text()"))
  {
  sb.AppendLine(node.InnerText.Trim());
  }
- string chapterTitle = chapter.Title;
- string chapterText = sb.ToString();
- Console.WriteLine("------------ ", chapterTitle, "------------ ");
- Console.WriteLine(chapterText);
+ string contentText = sb.ToString();
+ Console.WriteLine(contentText);
  Console.WriteLine();
- foreach (EpubChapter subChapter in chapter.SubChapters)
- {
- PrintChapter(subChapter);
- }
  }
  }
 }

Source/VersOne.Epub.NetCoreDemo/PrintNavigation.cs

@@ -0,0 +1,30 @@
+using System;
+
+namespace VersOne.Epub.NetCoreDemo
+{
+ internal static class PrintNavigation
+ {
+ public static void Run(string filePath)
+ {
+ using (EpubBookRef bookRef = EpubReader.OpenBook(filePath))
+ {
+ Console.WriteLine("Navigation:");
+ foreach (EpubNavigationItemRef navigationItemRef in bookRef.GetNavigation())
+ {
+ PrintNavigationItem(navigationItemRef, 0);
+ }
+ }
+ Console.WriteLine();
+ }
+
+ private static void PrintNavigationItem(EpubNavigationItemRef navigationItemRef, int identLevel)
+ {
+ Console.Write(new string(' ', identLevel * 2));
+ Console.WriteLine(navigationItemRef.Title);
+ foreach (EpubNavigationItemRef nestedNavigationItemRef in navigationItemRef.NestedItems)
+ {
+ PrintNavigationItem(nestedNavigationItemRef, identLevel + 1);
+ }
+ }
+ }
+}

Source/VersOne.Epub.NetCoreDemo/Program.cs

@@ -11,49 +11,81 @@ static void Main(string[] args)
  while (input != 'Q')
  {
  Console.WriteLine("Select example:");
- Console.WriteLine("1. List all chapters");
- Console.WriteLine("2. Extract plain text from all chapters");
+ Console.WriteLine("1. Print book navigation tree (table of contents)");
+ Console.WriteLine("2. Extract plain text from the whole book");
+ Console.WriteLine("3. Test the library by reading all EPUB files from a directory");
  Console.WriteLine("Q. Exit");
  input = Char.ToUpper(Console.ReadKey(true).KeyChar);
+ Console.WriteLine();
  switch (input)
  {
  case '1':
- RunExample(ListChapters.Run);
+ RunFileExample(PrintNavigation.Run);
  break;
  case '2':
- RunExample(ExtractPlainText.Run);
+ RunFileExample(ExtractPlainText.Run);
+ break;
+ case '3':
+ RunDirectoryExample(TestDirectory.Run);
  break;
  case 'Q':
  break;
  default:
  Console.WriteLine("Input is not recognized. Please try again.");
+ Console.WriteLine();
  break;
  }
  }
  }
 
- static void RunExample(Action<string> example)
+ private static void RunFileExample(Action<string> example)
  {
  Console.Write("Enter the path to the EPUB file: ");
  string filePath = Console.ReadLine();
+ Console.WriteLine();
  if (File.Exists(filePath) && Path.GetExtension(filePath).ToLower() == ".epub")
  {
  try
  {
  example(filePath);
- Console.WriteLine();
  }
  catch (Exception ex)
  {
  Console.WriteLine("Exception was thrown:");
  Console.WriteLine(ex.ToString());
+ Console.WriteLine();
  }
  }
  else
  {
  Console.WriteLine("File doesn't exist.");
+ Console.WriteLine();
  }
  }
- }
 
+ private static void RunDirectoryExample(Action<string> example)
+ {
+ Console.Write("Enter the path to the directory with EPUB files: ");
+ string directoryPath = Console.ReadLine();
+ Console.WriteLine();
+ if (Directory.Exists(directoryPath))
+ {
+ try
+ {
+ example(directoryPath);
+ }
+ catch (Exception ex)
+ {
+ Console.WriteLine("Exception was thrown:");
+ Console.WriteLine(ex.ToString());
+ Console.WriteLine();
+ }
+ }
+ else
+ {
+ Console.WriteLine("Directory doesn't exist.");
+ Console.WriteLine();
+ }
+ }
+ }
 }